diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/action_logprobs.pth.gz b/control_al_0.6_g_0.98_id_94_seed_9806094/action_logprobs.pth.gz new file mode 100644 index 0000000000000000000000000000000000000000..be12e0c339a6a20e4034f7ec624cc8febd064687 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/action_logprobs.pth.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4e95fb4410e9196ee8d51f32eda74701630b8ec7fbdabd9a5cfe88062477bd4 +size 224588009 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs.tar.gz b/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs.tar.gz new file mode 100644 index 0000000000000000000000000000000000000000..da66a85c514df247047940c4a1106412c90c8b19 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs.tar.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b80d2333f6ea65f2bd9f4f3719a642bcefd698f81f4615294d019720e8c07e84 +size 117062569 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/checkpoints.tar.gz b/control_al_0.6_g_0.98_id_94_seed_9806094/checkpoints.tar.gz new file mode 100644 index 0000000000000000000000000000000000000000..5c251ba64b4867eeb58917dc3130c9fff84d2a23 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/checkpoints.tar.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae8c2bc84e0cc5ce521d09f1adac4910f948f0da4f7ff900e75fdc703823630c +size 1538647742 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/config.cfg b/control_al_0.6_g_0.98_id_94_seed_9806094/config.cfg new file mode 100644 index 0000000000000000000000000000000000000000..ecea935aae50a6d1ff7b53df717f9a86ab718bdd --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/config.cfg @@ -0,0 +1,79 @@ +rl_action=train +model_type=impala +lr=5e-05 +discount_rate=0.98 +num_rollout_steps=64 +grad_acc_per_chunk=5 +num_rollout_chunks=1 +cheese_loc=any +env_layout=open +alpha=0.6 +env_size=13 +num_levels=9600 +compile=True +use_prev_action=False +weight_restrictions=None +weight_restrictions_invert=False +use_bf16=False +use_wandb=True +no_tqdm=True +seed=9806094 +mask_type=first_episode +ckpt_dir=jaxgmg2_antennaban2 +vis_average_state=False +trim_episodes=False +num_total_env_steps=9999974400 +eval_every=1 +eff_horizon=None +optim=adam +env_rule=ban:c[10,11], m[11,:]; c[11,10], m[:,11] +env_rule_mixture=None +hf_user=davidquarel +hf_collection=davidquarel/jaxgmg +use_hf=True +num_hf_uploads=1 +use_log=True +log_optimizer_state=True +resume=None +resume_id=None +resume_optim=False +checkpoint=control_al_0.6_g_0.98_id_94_seed_9806094 +wandb_project=jaxgmg2_antennaban +eval_schedule=0:1,250:2,500:5,2000:10 +render_sixel=False +sixel_idx=60 +live_monitor=False +run_id=94 +seed_formula= +deterministic=True +penalize_time=False +f_str_ckpt=control_al_0.6_g_0.98_id_94_seed_9806094 +duplication_factor=-1 +smoke=False +ntfy=david_jaxgmg +num_chains=6 +num_draws=3000 +num_steps_bw_draws=1 +on_policy=True +llc_nbeta=3000 +localization=10 +exact_solver_each_draw=False +llc_optimizer=sgld +iw_clip_eps=None +rmsprop_burnin_steps=20 +llc_data_file=llc_scan_open_reinforce.pkl +llc_checkpoint_index=None +llc_checkpoint_number=None +sink=None +repo_id=davidquarel/jaxgmg_ckpt_zip +use_shuffled_checkpoints=False +force_re_download=False +off_distribution_data=False +evaluate_every_position=False +num_prev_actions=1 +eff_acc_steps=5 +chunk_size=9600 +env_steps_per_microbatch=122880 +ckpt_path=jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094 +env_steps_per_loop=614400 +total_loops=16276 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/config.json b/control_al_0.6_g_0.98_id_94_seed_9806094/config.json new file mode 100644 index 0000000000000000000000000000000000000000..9a687c834d18f129eeb552752a847af9e4ceea6a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/config.json @@ -0,0 +1,81 @@ +{ + "alpha": 0.6, + "checkpoint": "control_al_0.6_g_0.98_id_94_seed_9806094", + "cheese_loc": "any", + "chunk_size": 9600, + "ckpt_dir": "jaxgmg2_antennaban2", + "ckpt_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094", + "compile": true, + "deterministic": true, + "discount_rate": 0.98, + "duplication_factor": -1, + "eff_acc_steps": 5, + "eff_horizon": null, + "env_layout": "open", + "env_rule": "ban:c[10,11], m[11,:]; c[11,10], m[:,11]", + "env_rule_mixture": null, + "env_size": 13, + "env_steps_per_loop": 614400, + "env_steps_per_microbatch": 122880, + "eval_every": 1, + "eval_schedule": "0:1,250:2,500:5,2000:10", + "evaluate_every_position": false, + "exact_solver_each_draw": false, + "f_str_ckpt": "control_al_0.6_g_0.98_id_94_seed_9806094", + "force_re_download": false, + "grad_acc_per_chunk": 5, + "hf_collection": "davidquarel/jaxgmg", + "hf_user": "davidquarel", + "iw_clip_eps": null, + "live_monitor": false, + "llc_checkpoint_index": null, + "llc_checkpoint_number": null, + "llc_data_file": "llc_scan_open_reinforce.pkl", + "llc_nbeta": 3000, + "llc_optimizer": "sgld", + "localization": 10, + "log_optimizer_state": true, + "lr": 5e-05, + "mask_type": "first_episode", + "model_type": "impala", + "no_tqdm": true, + "ntfy": "david_jaxgmg", + "num_chains": 6, + "num_draws": 3000, + "num_hf_uploads": 1, + "num_levels": 9600, + "num_prev_actions": 1, + "num_rollout_chunks": 1, + "num_rollout_steps": 64, + "num_steps_bw_draws": 1, + "num_total_env_steps": 9999974400, + "off_distribution_data": false, + "on_policy": true, + "optim": "adam", + "penalize_time": false, + "render_sixel": false, + "repo_id": "davidquarel/jaxgmg_ckpt_zip", + "resume": null, + "resume_id": null, + "resume_optim": false, + "rl_action": "train", + "rmsprop_burnin_steps": 20, + "run_id": 94, + "seed": 9806094, + "seed_formula": "", + "sink": null, + "sixel_idx": 60, + "smoke": false, + "total_loops": 16276, + "trim_episodes": false, + "use_bf16": false, + "use_hf": true, + "use_log": true, + "use_prev_action": false, + "use_shuffled_checkpoints": false, + "use_wandb": true, + "vis_average_state": false, + "wandb_project": "jaxgmg2_antennaban", + "weight_restrictions": null, + "weight_restrictions_invert": false +} \ No newline at end of file diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/eval.jsonl b/control_al_0.6_g_0.98_id_94_seed_9806094/eval.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..5621fd2e9ce0edd75bfb39c2fde1fca801c3c3e5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/eval.jsonl @@ -0,0 +1,2103 @@ +{"ts": "2026-03-20T17:23:27.541441Z", "loop": 0, "env_steps": 0, "exact_value_avg": 0.13593679666519165, "regret_dist": 0.7276439070701599, "regret_other_env": 0.7214499115943909, "regret_corner": 0.7369348406791687, "regret_row": 0.7426230311393738, "regret_any": 0.7213798761367798, "regret_bot": 0.7354499101638794, "value_dist": 0.13593679666519165, "value_other_env": 0.16076500713825226, "value_corner": 0.09869447350502014, "value_row": 0.1160036027431488, "value_any": 0.160870760679245, "value_bot": 0.123176708817482, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00000.png", "entropy": 1.385791301727295} +{"ts": "2026-03-20T17:23:28.491625Z", "loop": 1, "env_steps": 614400, "exact_value_avg": 0.13650046288967133, "regret_dist": 0.727080225944519, "regret_other_env": 0.7214719653129578, "regret_corner": 0.7354926466941833, "regret_row": 0.7417579889297485, "regret_any": 0.7214042544364929, "regret_bot": 0.7363818287849426, "value_dist": 0.13650046288967133, "value_other_env": 0.16074296832084656, "value_corner": 0.10013670474290848, "value_row": 0.11686858534812927, "value_any": 0.16084644198417664, "value_bot": 0.12224474549293518, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00001.png", "entropy": 1.3857605457305908} +{"ts": "2026-03-20T17:23:29.379967Z", "loop": 2, "env_steps": 1228800, "exact_value_avg": 0.13705024123191833, "regret_dist": 0.7265304327011108, "regret_other_env": 0.721494734287262, "regret_corner": 0.7340839505195618, "regret_row": 0.7409085631370544, "regret_any": 0.7214292287826538, "regret_bot": 0.7372918725013733, "value_dist": 0.13705024123191833, "value_other_env": 0.16072013974189758, "value_corner": 0.10154537111520767, "value_row": 0.11771806329488754, "value_any": 0.16082139313220978, "value_bot": 0.12133471667766571, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00002.png", "entropy": 1.3857282400131226} +{"ts": "2026-03-20T17:23:30.266832Z", "loop": 3, "env_steps": 1843200, "exact_value_avg": 0.13758498430252075, "regret_dist": 0.7259957194328308, "regret_other_env": 0.7215203046798706, "regret_corner": 0.732708752155304, "regret_row": 0.7401039600372314, "regret_any": 0.7214569449424744, "regret_bot": 0.7381580471992493, "value_dist": 0.13758498430252075, "value_other_env": 0.16069459915161133, "value_corner": 0.1029205471277237, "value_row": 0.11852269619703293, "value_any": 0.16079367697238922, "value_bot": 0.12046857178211212, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00003.png", "entropy": 1.3856922388076782} +{"ts": "2026-03-20T17:23:31.154638Z", "loop": 4, "env_steps": 2457600, "exact_value_avg": 0.13811786472797394, "regret_dist": 0.7254628539085388, "regret_other_env": 0.721546471118927, "regret_corner": 0.7313373684883118, "regret_row": 0.7392905950546265, "regret_any": 0.7214851975440979, "regret_bot": 0.7390241622924805, "value_dist": 0.13811786472797394, "value_other_env": 0.1606684774160385, "value_corner": 0.10429193824529648, "value_row": 0.11933601647615433, "value_any": 0.16076542437076569, "value_bot": 0.11960245668888092, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00004.png", "entropy": 1.3856544494628906} +{"ts": "2026-03-20T17:23:32.044040Z", "loop": 5, "env_steps": 3072000, "exact_value_avg": 0.13864238560199738, "regret_dist": 0.7249383926391602, "regret_other_env": 0.7215744853019714, "regret_corner": 0.7299841046333313, "regret_row": 0.7385078072547913, "regret_any": 0.7215152978897095, "regret_bot": 0.739855945110321, "value_dist": 0.13864238560199738, "value_other_env": 0.16064049303531647, "value_corner": 0.10564519464969635, "value_row": 0.12011880427598953, "value_any": 0.1607353389263153, "value_bot": 0.11877068877220154, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00005.png", "entropy": 1.3856141567230225} +{"ts": "2026-03-20T17:23:32.930876Z", "loop": 6, "env_steps": 3686400, "exact_value_avg": 0.13917109370231628, "regret_dist": 0.7244095802307129, "regret_other_env": 0.7216050624847412, "regret_corner": 0.7286163568496704, "regret_row": 0.737718939781189, "regret_any": 0.7215479612350464, "regret_bot": 0.7406910061836243, "value_dist": 0.13917109370231628, "value_other_env": 0.1606098711490631, "value_corner": 0.10701290518045425, "value_row": 0.12090770155191422, "value_any": 0.1607026755809784, "value_bot": 0.11793569475412369, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00006.png", "entropy": 1.3855717182159424} +{"ts": "2026-03-20T17:23:33.820307Z", "loop": 7, "env_steps": 4300800, "exact_value_avg": 0.1397026777267456, "regret_dist": 0.723878026008606, "regret_other_env": 0.7216380834579468, "regret_corner": 0.72723788022995, "regret_row": 0.7369237542152405, "regret_any": 0.7215830087661743, "regret_bot": 0.7415309548377991, "value_dist": 0.1397026777267456, "value_other_env": 0.16057683527469635, "value_corner": 0.10839145630598068, "value_row": 0.12170291692018509, "value_any": 0.16066764295101166, "value_bot": 0.11709564179182053, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00007.png", "entropy": 1.3855270147323608} +{"ts": "2026-03-20T17:23:34.708060Z", "loop": 8, "env_steps": 4915200, "exact_value_avg": 0.14024269580841064, "regret_dist": 0.7233380079269409, "regret_other_env": 0.7216734886169434, "regret_corner": 0.7258346676826477, "regret_row": 0.7361248135566711, "regret_any": 0.7216204404830933, "regret_bot": 0.7423681020736694, "value_dist": 0.14024269580841064, "value_other_env": 0.160541370511055, "value_corner": 0.10979466885328293, "value_row": 0.12250179797410965, "value_any": 0.16063013672828674, "value_bot": 0.11625858396291733, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00008.png", "entropy": 1.38547945022583} +{"ts": "2026-03-20T17:23:35.596193Z", "loop": 9, "env_steps": 5529600, "exact_value_avg": 0.14079327881336212, "regret_dist": 0.7227873802185059, "regret_other_env": 0.7217103838920593, "regret_corner": 0.724402904510498, "regret_row": 0.735308051109314, "regret_any": 0.7216593623161316, "regret_bot": 0.7432096600532532, "value_dist": 0.14079327881336212, "value_other_env": 0.1605045050382614, "value_corner": 0.11122642457485199, "value_row": 0.1233186423778534, "value_any": 0.16059128940105438, "value_bot": 0.11541704088449478, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00009.png", "entropy": 1.3854291439056396} +{"ts": "2026-03-20T17:23:36.483194Z", "loop": 10, "env_steps": 6144000, "exact_value_avg": 0.1413523554801941, "regret_dist": 0.7222282886505127, "regret_other_env": 0.7217505574226379, "regret_corner": 0.7229447960853577, "regret_row": 0.7344948649406433, "regret_any": 0.7217015027999878, "regret_bot": 0.7440403699874878, "value_dist": 0.1413523554801941, "value_other_env": 0.16046425700187683, "value_corner": 0.11268450319766998, "value_row": 0.12413178384304047, "value_any": 0.16054905951023102, "value_bot": 0.11458630859851837, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00010.png", "entropy": 1.3853750228881836} +{"ts": "2026-03-20T17:23:37.373608Z", "loop": 11, "env_steps": 6758400, "exact_value_avg": 0.1419256180524826, "regret_dist": 0.721655011177063, "regret_other_env": 0.7217952013015747, "regret_corner": 0.7214447259902954, "regret_row": 0.7336586713790894, "regret_any": 0.7217481136322021, "regret_bot": 0.7448925971984863, "value_dist": 0.1419256180524826, "value_other_env": 0.16041965782642365, "value_corner": 0.11418452858924866, "value_row": 0.12496796250343323, "value_any": 0.16050247848033905, "value_bot": 0.11373405903577805, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00011.png", "entropy": 1.385317087173462} +{"ts": "2026-03-20T17:23:38.262646Z", "loop": 12, "env_steps": 7372800, "exact_value_avg": 0.1425151228904724, "regret_dist": 0.7210655808448792, "regret_other_env": 0.7218432426452637, "regret_corner": 0.7198989987373352, "regret_row": 0.7328101396560669, "regret_any": 0.7217981219291687, "regret_bot": 0.745754599571228, "value_dist": 0.1425151228904724, "value_other_env": 0.16037167608737946, "value_corner": 0.11573028564453125, "value_row": 0.12581641972064972, "value_any": 0.1604524701833725, "value_bot": 0.11287201195955276, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00012.png", "entropy": 1.385254979133606} +{"ts": "2026-03-20T17:23:39.150505Z", "loop": 13, "env_steps": 7987200, "exact_value_avg": 0.14311110973358154, "regret_dist": 0.72046959400177, "regret_other_env": 0.7218926548957825, "regret_corner": 0.7183349132537842, "regret_row": 0.7319652438163757, "regret_any": 0.7218496203422546, "regret_bot": 0.7466073632240295, "value_dist": 0.14311110973358154, "value_other_env": 0.16032221913337708, "value_corner": 0.11729444563388824, "value_row": 0.12666139006614685, "value_any": 0.16040103137493134, "value_bot": 0.11201934516429901, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00013.png", "entropy": 1.3851898908615112} +{"ts": "2026-03-20T17:23:40.038714Z", "loop": 14, "env_steps": 8601600, "exact_value_avg": 0.14372518658638, "regret_dist": 0.7198554873466492, "regret_other_env": 0.7219445109367371, "regret_corner": 0.7167218923568726, "regret_row": 0.731100857257843, "regret_any": 0.721903383731842, "regret_bot": 0.7474714517593384, "value_dist": 0.14372518658638, "value_other_env": 0.16027039289474487, "value_corner": 0.1189073771238327, "value_row": 0.12752583622932434, "value_any": 0.16034720838069916, "value_bot": 0.11115521192550659, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00014.png", "entropy": 1.3851202726364136} +{"ts": "2026-03-20T17:23:40.925771Z", "loop": 15, "env_steps": 9216000, "exact_value_avg": 0.14436101913452148, "regret_dist": 0.7192196846008301, "regret_other_env": 0.7219995856285095, "regret_corner": 0.7150498032569885, "regret_row": 0.7302088737487793, "regret_any": 0.7219604849815369, "regret_bot": 0.7483553290367126, "value_dist": 0.14436101913452148, "value_other_env": 0.1602153331041336, "value_corner": 0.1205795481801033, "value_row": 0.12841777503490448, "value_any": 0.16029013693332672, "value_bot": 0.11027128994464874, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00015.png", "entropy": 1.3850458860397339} +{"ts": "2026-03-20T17:23:41.812185Z", "loop": 16, "env_steps": 9830400, "exact_value_avg": 0.1450110375881195, "regret_dist": 0.7185696363449097, "regret_other_env": 0.7220582962036133, "regret_corner": 0.7133365273475647, "regret_row": 0.7292913198471069, "regret_any": 0.722021222114563, "regret_bot": 0.7492578029632568, "value_dist": 0.1450110375881195, "value_other_env": 0.16015654802322388, "value_corner": 0.12229277938604355, "value_row": 0.12933531403541565, "value_any": 0.16022931039333344, "value_bot": 0.10936882346868515, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00016.png", "entropy": 1.3849676847457886} +{"ts": "2026-03-20T17:23:42.699158Z", "loop": 17, "env_steps": 10444800, "exact_value_avg": 0.14567767083644867, "regret_dist": 0.7179030179977417, "regret_other_env": 0.7221219539642334, "regret_corner": 0.7115745544433594, "regret_row": 0.7283481359481812, "regret_any": 0.7220869660377502, "regret_bot": 0.7501800060272217, "value_dist": 0.14567767083644867, "value_other_env": 0.16009287536144257, "value_corner": 0.12405483424663544, "value_row": 0.13027845323085785, "value_any": 0.16016359627246857, "value_bot": 0.10844655334949493, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00017.png", "entropy": 1.3848836421966553} +{"ts": "2026-03-20T17:23:43.587091Z", "loop": 18, "env_steps": 11059200, "exact_value_avg": 0.14636719226837158, "regret_dist": 0.71721351146698, "regret_other_env": 0.722189724445343, "regret_corner": 0.7097491025924683, "regret_row": 0.7273640036582947, "regret_any": 0.7221567630767822, "regret_bot": 0.7511318325996399, "value_dist": 0.14636719226837158, "value_other_env": 0.16002516448497772, "value_corner": 0.12588021159172058, "value_row": 0.13126260042190552, "value_any": 0.16009381413459778, "value_bot": 0.10749483853578568, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00018.png", "entropy": 1.3847938776016235} +{"ts": "2026-03-20T17:23:44.476386Z", "loop": 19, "env_steps": 11673600, "exact_value_avg": 0.14708387851715088, "regret_dist": 0.7164968252182007, "regret_other_env": 0.7222631573677063, "regret_corner": 0.7078472375869751, "regret_row": 0.7263484597206116, "regret_any": 0.7222322821617126, "regret_bot": 0.7521065473556519, "value_dist": 0.14708387851715088, "value_other_env": 0.15995177626609802, "value_corner": 0.12778203189373016, "value_row": 0.1322781890630722, "value_any": 0.16001828014850616, "value_bot": 0.10652007907629013, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00019.png", "entropy": 1.3846968412399292} +{"ts": "2026-03-20T17:23:45.364994Z", "loop": 20, "env_steps": 12288000, "exact_value_avg": 0.14783291518688202, "regret_dist": 0.7157477736473083, "regret_other_env": 0.7223420143127441, "regret_corner": 0.7058563828468323, "regret_row": 0.7252975702285767, "regret_any": 0.722313404083252, "regret_bot": 0.7531046271324158, "value_dist": 0.14783291518688202, "value_other_env": 0.1598728597164154, "value_corner": 0.12977297604084015, "value_row": 0.13332907855510712, "value_any": 0.15993717312812805, "value_bot": 0.10552199929952621, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00020.png", "entropy": 1.3845915794372559} +{"ts": "2026-03-20T17:23:46.252286Z", "loop": 21, "env_steps": 12902400, "exact_value_avg": 0.14860771596431732, "regret_dist": 0.7149729132652283, "regret_other_env": 0.7224258780479431, "regret_corner": 0.7037933468818665, "regret_row": 0.724219024181366, "regret_any": 0.7223995327949524, "regret_bot": 0.7541202306747437, "value_dist": 0.14860771596431732, "value_other_env": 0.15978892147541046, "value_corner": 0.13183589279651642, "value_row": 0.1344076246023178, "value_any": 0.15985101461410522, "value_bot": 0.10450640320777893, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00021.png", "entropy": 1.3844789266586304} +{"ts": "2026-03-20T17:23:47.140846Z", "loop": 22, "env_steps": 13516800, "exact_value_avg": 0.1494215428829193, "regret_dist": 0.7141591906547546, "regret_other_env": 0.7225180268287659, "regret_corner": 0.701620876789093, "regret_row": 0.7231001257896423, "regret_any": 0.7224939465522766, "regret_bot": 0.7551683783531189, "value_dist": 0.1494215428829193, "value_other_env": 0.15969692170619965, "value_corner": 0.13400845229625702, "value_row": 0.13552650809288025, "value_any": 0.15975672006607056, "value_bot": 0.10345828533172607, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00022.png", "entropy": 1.3843557834625244} +{"ts": "2026-03-20T17:23:48.029214Z", "loop": 23, "env_steps": 14131200, "exact_value_avg": 0.15026381611824036, "regret_dist": 0.7133169174194336, "regret_other_env": 0.7226162552833557, "regret_corner": 0.6993678212165833, "regret_row": 0.7219430208206177, "regret_any": 0.7225944399833679, "regret_bot": 0.7562420964241028, "value_dist": 0.15026381611824036, "value_other_env": 0.1595986783504486, "value_corner": 0.13626152276992798, "value_row": 0.13668358325958252, "value_any": 0.15965615212917328, "value_bot": 0.102384552359581, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00023.png", "entropy": 1.3842252492904663} +{"ts": "2026-03-20T17:23:48.914453Z", "loop": 24, "env_steps": 14745600, "exact_value_avg": 0.15114350616931915, "regret_dist": 0.7124371528625488, "regret_other_env": 0.7227234840393066, "regret_corner": 0.6970075368881226, "regret_row": 0.7207428812980652, "regret_any": 0.7227041721343994, "regret_bot": 0.7573485970497131, "value_dist": 0.15114350616931915, "value_other_env": 0.15949131548404694, "value_corner": 0.13862177729606628, "value_row": 0.13788378238677979, "value_any": 0.15954641997814178, "value_bot": 0.10127802193164825, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00024.png", "entropy": 1.3840843439102173} +{"ts": "2026-03-20T17:23:49.799727Z", "loop": 25, "env_steps": 15360000, "exact_value_avg": 0.15206195414066315, "regret_dist": 0.7115187644958496, "regret_other_env": 0.7228375673294067, "regret_corner": 0.6945404410362244, "regret_row": 0.7194904685020447, "regret_any": 0.7228206396102905, "regret_bot": 0.7584874033927917, "value_dist": 0.15206195414066315, "value_other_env": 0.159377321600914, "value_corner": 0.14108887314796448, "value_row": 0.1391361951828003, "value_any": 0.15942998230457306, "value_bot": 0.10013920068740845, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00025.png", "entropy": 1.3839335441589355} +{"ts": "2026-03-20T17:23:50.687775Z", "loop": 26, "env_steps": 15974400, "exact_value_avg": 0.15302574634552002, "regret_dist": 0.7105549573898315, "regret_other_env": 0.7229582667350769, "regret_corner": 0.6919499039649963, "regret_row": 0.7181882858276367, "regret_any": 0.7229438424110413, "regret_bot": 0.7596542835235596, "value_dist": 0.15302574634552002, "value_other_env": 0.15925657749176025, "value_corner": 0.14367946982383728, "value_row": 0.14043840765953064, "value_any": 0.15930671989917755, "value_bot": 0.09897234290838242, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00026.png", "entropy": 1.3837698698043823} +{"ts": "2026-03-20T17:23:51.575438Z", "loop": 27, "env_steps": 16588800, "exact_value_avg": 0.1540408432483673, "regret_dist": 0.7095398306846619, "regret_other_env": 0.7230867743492126, "regret_corner": 0.6892193555831909, "regret_row": 0.7168219089508057, "regret_any": 0.7230749726295471, "regret_bot": 0.7608634233474731, "value_dist": 0.1540408432483673, "value_other_env": 0.1591280847787857, "value_corner": 0.14640994369983673, "value_row": 0.1418047398328781, "value_any": 0.15917570888996124, "value_bot": 0.09776324033737183, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00027.png", "entropy": 1.3835935592651367} +{"ts": "2026-03-20T17:23:52.462217Z", "loop": 28, "env_steps": 17203200, "exact_value_avg": 0.155107781291008, "regret_dist": 0.7084729075431824, "regret_other_env": 0.7232266068458557, "regret_corner": 0.6863422989845276, "regret_row": 0.7154066562652588, "regret_any": 0.723217248916626, "regret_bot": 0.7621053457260132, "value_dist": 0.155107781291008, "value_other_env": 0.15898826718330383, "value_corner": 0.14928703010082245, "value_row": 0.1432199329137802, "value_any": 0.15903334319591522, "value_bot": 0.09652123600244522, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00028.png", "entropy": 1.3834022283554077} +{"ts": "2026-03-20T17:23:53.351059Z", "loop": 29, "env_steps": 17817600, "exact_value_avg": 0.15622995793819427, "regret_dist": 0.7073507308959961, "regret_other_env": 0.7233820557594299, "regret_corner": 0.683303713798523, "regret_row": 0.7139413952827454, "regret_any": 0.7233752608299255, "regret_bot": 0.7633907794952393, "value_dist": 0.15622995793819427, "value_other_env": 0.15883281826972961, "value_corner": 0.15232564508914948, "value_row": 0.1446852684020996, "value_any": 0.15887528657913208, "value_bot": 0.0952359214425087, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00029.png", "entropy": 1.3831945657730103} +{"ts": "2026-03-20T17:23:54.239984Z", "loop": 30, "env_steps": 18432000, "exact_value_avg": 0.15740232169628143, "regret_dist": 0.7061783671379089, "regret_other_env": 0.7235519886016846, "regret_corner": 0.6801179051399231, "regret_row": 0.7124408483505249, "regret_any": 0.7235478758811951, "regret_bot": 0.7647056579589844, "value_dist": 0.15740232169628143, "value_other_env": 0.15866291522979736, "value_corner": 0.15551142394542694, "value_row": 0.14618580043315887, "value_any": 0.15870271623134613, "value_bot": 0.09392095357179642, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00030.png", "entropy": 1.3829691410064697} +{"ts": "2026-03-20T17:23:55.127268Z", "loop": 31, "env_steps": 19046400, "exact_value_avg": 0.15860894322395325, "regret_dist": 0.7049717903137207, "regret_other_env": 0.7237293124198914, "regret_corner": 0.6768353581428528, "regret_row": 0.7109053134918213, "regret_any": 0.7237279415130615, "regret_bot": 0.7660244107246399, "value_dist": 0.15860894322395325, "value_other_env": 0.1584855616092682, "value_corner": 0.15879398584365845, "value_row": 0.14772139489650726, "value_any": 0.15852266550064087, "value_bot": 0.09260228276252747, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00031.png", "entropy": 1.3827272653579712} +{"ts": "2026-03-20T17:23:56.015399Z", "loop": 32, "env_steps": 19660800, "exact_value_avg": 0.15985608100891113, "regret_dist": 0.7037246227264404, "regret_other_env": 0.7239145040512085, "regret_corner": 0.673439621925354, "regret_row": 0.709320604801178, "regret_any": 0.7239158749580383, "regret_bot": 0.7673624753952026, "value_dist": 0.15985608100891113, "value_other_env": 0.15830032527446747, "value_corner": 0.16218967735767365, "value_row": 0.1493060439825058, "value_any": 0.15833474695682526, "value_bot": 0.09126409888267517, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00032.png", "entropy": 1.382468819618225} +{"ts": "2026-03-20T17:23:56.903045Z", "loop": 33, "env_steps": 20275200, "exact_value_avg": 0.16115280985832214, "regret_dist": 0.702427864074707, "regret_other_env": 0.7241137623786926, "regret_corner": 0.6698989868164062, "regret_row": 0.7076911330223083, "regret_any": 0.7241178154945374, "regret_bot": 0.7687287330627441, "value_dist": 0.16115280985832214, "value_other_env": 0.15810109674930573, "value_corner": 0.16573035717010498, "value_row": 0.15093547105789185, "value_any": 0.15813276171684265, "value_bot": 0.08989793062210083, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00033.png", "entropy": 1.38219153881073} +{"ts": "2026-03-20T17:23:57.790926Z", "loop": 34, "env_steps": 20889600, "exact_value_avg": 0.16251295804977417, "regret_dist": 0.7010676860809326, "regret_other_env": 0.7243334054946899, "regret_corner": 0.6661691665649414, "regret_row": 0.7060124278068542, "regret_any": 0.7243403196334839, "regret_bot": 0.7701308131217957, "value_dist": 0.16251295804977417, "value_other_env": 0.1578814536333084, "value_corner": 0.1694602072238922, "value_row": 0.15261422097682953, "value_any": 0.1579103022813797, "value_bot": 0.08849580585956573, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00034.png", "entropy": 1.3818895816802979} +{"ts": "2026-03-20T17:23:58.678966Z", "loop": 35, "env_steps": 21504000, "exact_value_avg": 0.16395393013954163, "regret_dist": 0.6996268033981323, "regret_other_env": 0.724576473236084, "regret_corner": 0.6622021198272705, "regret_row": 0.7042586207389832, "regret_any": 0.7245862483978271, "regret_bot": 0.7715920209884644, "value_dist": 0.16395393013954163, "value_other_env": 0.15763838589191437, "value_corner": 0.17342720925807953, "value_row": 0.15436804294586182, "value_any": 0.15766429901123047, "value_bot": 0.08703461289405823, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00035.png", "entropy": 1.3815586566925049} +{"ts": "2026-03-20T17:23:59.566457Z", "loop": 36, "env_steps": 22118400, "exact_value_avg": 0.16548076272010803, "regret_dist": 0.6980999708175659, "regret_other_env": 0.7248439192771912, "regret_corner": 0.6579838991165161, "regret_row": 0.7024336457252502, "regret_any": 0.7248567938804626, "regret_bot": 0.7731074690818787, "value_dist": 0.16548076272010803, "value_other_env": 0.1573709398508072, "value_corner": 0.1776454597711563, "value_row": 0.15619294345378876, "value_any": 0.15739385783672333, "value_bot": 0.08551914244890213, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00036.png", "entropy": 1.3811942338943481} +{"ts": "2026-03-20T17:24:00.453712Z", "loop": 37, "env_steps": 22732800, "exact_value_avg": 0.16710823774337769, "regret_dist": 0.6964724659919739, "regret_other_env": 0.7251358032226562, "regret_corner": 0.6534773707389832, "regret_row": 0.7005326151847839, "regret_any": 0.7251517176628113, "regret_bot": 0.7746695280075073, "value_dist": 0.16710823774337769, "value_other_env": 0.1570790857076645, "value_corner": 0.1821519434452057, "value_row": 0.15809403359889984, "value_any": 0.1570989340543747, "value_bot": 0.08395714312791824, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00037.png", "entropy": 1.3807933330535889} +{"ts": "2026-03-20T17:24:01.340554Z", "loop": 38, "env_steps": 23347200, "exact_value_avg": 0.1688411831855774, "regret_dist": 0.6947395205497742, "regret_other_env": 0.7254546284675598, "regret_corner": 0.6486667990684509, "regret_row": 0.6985343098640442, "regret_any": 0.7254736423492432, "regret_bot": 0.7762964963912964, "value_dist": 0.1688411831855774, "value_other_env": 0.15676024556159973, "value_corner": 0.1869625598192215, "value_row": 0.1600923240184784, "value_any": 0.15677696466445923, "value_bot": 0.08233010023832321, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00038.png", "entropy": 1.3803507089614868} +{"ts": "2026-03-20T17:24:02.227511Z", "loop": 39, "env_steps": 23961600, "exact_value_avg": 0.17068006098270416, "regret_dist": 0.6929006576538086, "regret_other_env": 0.7257946133613586, "regret_corner": 0.6435595750808716, "regret_row": 0.6964081525802612, "regret_any": 0.7258167862892151, "regret_bot": 0.7779887318611145, "value_dist": 0.17068006098270416, "value_other_env": 0.1564202457666397, "value_corner": 0.19206976890563965, "value_row": 0.16221846640110016, "value_any": 0.1564338058233261, "value_bot": 0.08063787966966629, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00039.png", "entropy": 1.3798656463623047} +{"ts": "2026-03-20T17:24:03.114839Z", "loop": 40, "env_steps": 24576000, "exact_value_avg": 0.1726694405078888, "regret_dist": 0.6909111738204956, "regret_other_env": 0.726166844367981, "regret_corner": 0.6380277276039124, "regret_row": 0.6941389441490173, "regret_any": 0.7261922955513, "regret_bot": 0.7797579169273376, "value_dist": 0.1726694405078888, "value_other_env": 0.1560480147600174, "value_corner": 0.1976015865802765, "value_row": 0.16448768973350525, "value_any": 0.15605834126472473, "value_bot": 0.07886870950460434, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00040.png", "entropy": 1.3793308734893799} +{"ts": "2026-03-20T17:24:04.004352Z", "loop": 41, "env_steps": 25190400, "exact_value_avg": 0.1748138666152954, "regret_dist": 0.6887668371200562, "regret_other_env": 0.7265864014625549, "regret_corner": 0.6320374011993408, "regret_row": 0.6917406320571899, "regret_any": 0.7266150712966919, "regret_bot": 0.7816141247749329, "value_dist": 0.1748138666152954, "value_other_env": 0.155628502368927, "value_corner": 0.20359191298484802, "value_row": 0.16688597202301025, "value_any": 0.1556355357170105, "value_bot": 0.07701243460178375, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00041.png", "entropy": 1.3787319660186768} +{"ts": "2026-03-20T17:24:04.894027Z", "loop": 42, "env_steps": 25804800, "exact_value_avg": 0.17711412906646729, "regret_dist": 0.6864665746688843, "regret_other_env": 0.7270525693893433, "regret_corner": 0.6255875825881958, "regret_row": 0.6892159581184387, "regret_any": 0.7270846962928772, "regret_bot": 0.783549427986145, "value_dist": 0.17711412906646729, "value_other_env": 0.15516236424446106, "value_corner": 0.21004177629947662, "value_row": 0.16941063106060028, "value_any": 0.15516597032546997, "value_bot": 0.07507721334695816, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00042.png", "entropy": 1.3780632019042969} +{"ts": "2026-03-20T17:24:05.785220Z", "loop": 43, "env_steps": 26419200, "exact_value_avg": 0.17958508431911469, "regret_dist": 0.6839956045150757, "regret_other_env": 0.7275669574737549, "regret_corner": 0.6186385154724121, "regret_row": 0.6865467429161072, "regret_any": 0.727602481842041, "regret_bot": 0.7855610251426697, "value_dist": 0.17958508431911469, "value_other_env": 0.15464793145656586, "value_corner": 0.21699079871177673, "value_row": 0.1720799058675766, "value_any": 0.154648095369339, "value_bot": 0.07306564599275589, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00043.png", "entropy": 1.3773162364959717} +{"ts": "2026-03-20T17:24:06.674225Z", "loop": 44, "env_steps": 27033600, "exact_value_avg": 0.18221575021743774, "regret_dist": 0.6813649535179138, "regret_other_env": 0.7281377911567688, "regret_corner": 0.6112055778503418, "regret_row": 0.6837811470031738, "regret_any": 0.7281768321990967, "regret_bot": 0.7876412868499756, "value_dist": 0.18221575021743774, "value_other_env": 0.15407708287239075, "value_corner": 0.22442373633384705, "value_row": 0.17484550178050995, "value_any": 0.15407373011112213, "value_bot": 0.07098538428544998, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00044.png", "entropy": 1.3764798641204834} +{"ts": "2026-03-20T17:24:07.561505Z", "loop": 45, "env_steps": 27648000, "exact_value_avg": 0.18500462174415588, "regret_dist": 0.6785760521888733, "regret_other_env": 0.7287659049034119, "regret_corner": 0.6032912731170654, "regret_row": 0.6809309124946594, "regret_any": 0.7288084626197815, "regret_bot": 0.7897784113883972, "value_dist": 0.18500462174415588, "value_other_env": 0.15344899892807007, "value_corner": 0.2323380559682846, "value_row": 0.17769573628902435, "value_any": 0.1534421294927597, "value_bot": 0.06884822249412537, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00045.png", "entropy": 1.3755465745925903} +{"ts": "2026-03-20T17:24:08.446744Z", "loop": 46, "env_steps": 28262400, "exact_value_avg": 0.18795126676559448, "regret_dist": 0.6756293773651123, "regret_other_env": 0.7294471263885498, "regret_corner": 0.5949026942253113, "regret_row": 0.6779929399490356, "regret_any": 0.729493260383606, "regret_bot": 0.7919366955757141, "value_dist": 0.18795126676559448, "value_other_env": 0.15276774764060974, "value_corner": 0.2407265454530716, "value_row": 0.18063373863697052, "value_any": 0.15275733172893524, "value_bot": 0.06668994575738907, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00046.png", "entropy": 1.3745088577270508} +{"ts": "2026-03-20T17:24:09.333217Z", "loop": 47, "env_steps": 28876800, "exact_value_avg": 0.19111470878124237, "regret_dist": 0.6724659204483032, "regret_other_env": 0.7301918864250183, "regret_corner": 0.585877001285553, "regret_row": 0.6749151945114136, "regret_any": 0.730241596698761, "regret_bot": 0.7941514849662781, "value_dist": 0.19111470878124237, "value_other_env": 0.15202294290065765, "value_corner": 0.24975234270095825, "value_row": 0.183711439371109, "value_any": 0.15200895071029663, "value_bot": 0.06447508931159973, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00047.png", "entropy": 1.3733450174331665} +{"ts": "2026-03-20T17:24:10.221535Z", "loop": 48, "env_steps": 29491200, "exact_value_avg": 0.1944715678691864, "regret_dist": 0.6691091060638428, "regret_other_env": 0.7310072183609009, "regret_corner": 0.5762619376182556, "regret_row": 0.6717127561569214, "regret_any": 0.7310604453086853, "regret_bot": 0.7964219450950623, "value_dist": 0.1944715678691864, "value_other_env": 0.15120768547058105, "value_corner": 0.25936734676361084, "value_row": 0.1869138777256012, "value_any": 0.1511901468038559, "value_bot": 0.06220470741391182, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00048.png", "entropy": 1.372044324874878} +{"ts": "2026-03-20T17:24:11.109663Z", "loop": 49, "env_steps": 30105600, "exact_value_avg": 0.1980377733707428, "regret_dist": 0.6655429005622864, "regret_other_env": 0.7319002747535706, "regret_corner": 0.5660068392753601, "regret_row": 0.6683558225631714, "regret_any": 0.7319570183753967, "regret_bot": 0.7987499833106995, "value_dist": 0.1980377733707428, "value_other_env": 0.15031464397907257, "value_corner": 0.26962247490882874, "value_row": 0.1902708262205124, "value_any": 0.15029357373714447, "value_bot": 0.05987665429711342, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00049.png", "entropy": 1.3705816268920898} +{"ts": "2026-03-20T17:24:11.996972Z", "loop": 50, "env_steps": 30720000, "exact_value_avg": 0.20179271697998047, "regret_dist": 0.6617880463600159, "regret_other_env": 0.7328696250915527, "regret_corner": 0.5551655888557434, "regret_row": 0.6648678779602051, "regret_any": 0.7329298257827759, "regret_bot": 0.801119327545166, "value_dist": 0.20179271697998047, "value_other_env": 0.1493452936410904, "value_corner": 0.2804638147354126, "value_row": 0.1937588006258011, "value_any": 0.1493208110332489, "value_bot": 0.05750732123851776, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00050.png", "entropy": 1.368960976600647} +{"ts": "2026-03-20T17:24:12.883477Z", "loop": 51, "env_steps": 31334400, "exact_value_avg": 0.20577868819236755, "regret_dist": 0.6578020453453064, "regret_other_env": 0.7339316606521606, "regret_corner": 0.5436075925827026, "regret_row": 0.6612405180931091, "regret_any": 0.7339951395988464, "regret_bot": 0.8035379648208618, "value_dist": 0.20577868819236755, "value_other_env": 0.14828328788280487, "value_corner": 0.292021781206131, "value_row": 0.19738614559173584, "value_any": 0.14825543761253357, "value_bot": 0.05508862063288689, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00051.png", "entropy": 1.367134690284729} +{"ts": "2026-03-20T17:24:13.771406Z", "loop": 52, "env_steps": 31948800, "exact_value_avg": 0.20999562740325928, "regret_dist": 0.6535850763320923, "regret_other_env": 0.7350981831550598, "regret_corner": 0.5313153266906738, "regret_row": 0.6575023531913757, "regret_any": 0.735164999961853, "regret_bot": 0.8059878945350647, "value_dist": 0.20999562740325928, "value_other_env": 0.14711670577526093, "value_corner": 0.304313987493515, "value_row": 0.20112431049346924, "value_any": 0.14708556234836578, "value_bot": 0.05263875797390938, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00052.png", "entropy": 1.3650619983673096} +{"ts": "2026-03-20T17:24:14.660329Z", "loop": 53, "env_steps": 32563200, "exact_value_avg": 0.21445706486701965, "regret_dist": 0.6491236686706543, "regret_other_env": 0.7363778352737427, "regret_corner": 0.5182422995567322, "regret_row": 0.6536726355552673, "regret_any": 0.7364479303359985, "regret_bot": 0.8084599375724792, "value_dist": 0.21445706486701965, "value_other_env": 0.14583702385425568, "value_corner": 0.31738707423210144, "value_row": 0.20495401322841644, "value_any": 0.14580269157886505, "value_bot": 0.05016670003533363, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00053.png", "entropy": 1.3627111911773682} +{"ts": "2026-03-20T17:24:15.549027Z", "loop": 54, "env_steps": 33177600, "exact_value_avg": 0.2191896140575409, "regret_dist": 0.6443910598754883, "regret_other_env": 0.7377768754959106, "regret_corner": 0.5043123364448547, "regret_row": 0.6497320532798767, "regret_any": 0.73785001039505, "regret_bot": 0.8109430074691772, "value_dist": 0.2191896140575409, "value_other_env": 0.1444380283355713, "value_corner": 0.3313170075416565, "value_row": 0.20889456570148468, "value_any": 0.14440062642097473, "value_bot": 0.04768366366624832, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00054.png", "entropy": 1.3600388765335083} +{"ts": "2026-03-20T17:24:16.436766Z", "loop": 55, "env_steps": 33792000, "exact_value_avg": 0.2241956740617752, "regret_dist": 0.6393849849700928, "regret_other_env": 0.7393150329589844, "regret_corner": 0.48948991298675537, "regret_row": 0.6456664204597473, "regret_any": 0.7393911480903625, "regret_bot": 0.8134512901306152, "value_dist": 0.2241956740617752, "value_other_env": 0.1428997963666916, "value_corner": 0.34613946080207825, "value_row": 0.21296022832393646, "value_any": 0.14285942912101746, "value_bot": 0.04517534747719765, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00055.png", "entropy": 1.356968879699707} +{"ts": "2026-03-20T17:24:17.325273Z", "loop": 56, "env_steps": 34406400, "exact_value_avg": 0.22949351370334625, "regret_dist": 0.6340872049331665, "regret_other_env": 0.7409974336624146, "regret_corner": 0.47372177243232727, "regret_row": 0.6414817571640015, "regret_any": 0.7410762906074524, "regret_bot": 0.8159720301628113, "value_dist": 0.22949351370334625, "value_other_env": 0.14121748507022858, "value_corner": 0.3619075417518616, "value_row": 0.21714486181735992, "value_any": 0.1411742866039276, "value_bot": 0.042654555290937424, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00056.png", "entropy": 1.3534328937530518} +{"ts": "2026-03-20T17:24:18.213310Z", "loop": 57, "env_steps": 35020800, "exact_value_avg": 0.23514869809150696, "regret_dist": 0.6284319758415222, "regret_other_env": 0.7428438067436218, "regret_corner": 0.4568141996860504, "regret_row": 0.6371718645095825, "regret_any": 0.7429254651069641, "regret_bot": 0.8185202479362488, "value_dist": 0.23514869809150696, "value_other_env": 0.13937106728553772, "value_corner": 0.3788151443004608, "value_row": 0.22145476937294006, "value_any": 0.1393251270055771, "value_bot": 0.04010631516575813, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00057.png", "entropy": 1.3493369817733765} +{"ts": "2026-03-20T17:24:19.102157Z", "loop": 58, "env_steps": 35635200, "exact_value_avg": 0.24107012152671814, "regret_dist": 0.6225104928016663, "regret_other_env": 0.7448511719703674, "regret_corner": 0.4389994740486145, "regret_row": 0.632801353931427, "regret_any": 0.7449353933334351, "regret_bot": 0.821056067943573, "value_dist": 0.24107012152671814, "value_other_env": 0.13736365735530853, "value_corner": 0.39662984013557434, "value_row": 0.2258252203464508, "value_any": 0.13731516897678375, "value_bot": 0.0375705286860466, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00058.png", "entropy": 1.3446100950241089} +{"ts": "2026-03-20T17:24:19.990368Z", "loop": 59, "env_steps": 36249600, "exact_value_avg": 0.2471655011177063, "regret_dist": 0.6164152026176453, "regret_other_env": 0.7470039129257202, "regret_corner": 0.4205320477485657, "regret_row": 0.6284921169281006, "regret_any": 0.7470904588699341, "regret_bot": 0.8235244154930115, "value_dist": 0.2471655011177063, "value_other_env": 0.13521096110343933, "value_corner": 0.41509726643562317, "value_row": 0.2301345318555832, "value_any": 0.1351601630449295, "value_bot": 0.03510214015841484, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00059.png", "entropy": 1.33919095993042} +{"ts": "2026-03-20T17:24:20.881651Z", "loop": 60, "env_steps": 36864000, "exact_value_avg": 0.25339382886886597, "regret_dist": 0.6101868152618408, "regret_other_env": 0.7492839694023132, "regret_corner": 0.4015411138534546, "regret_row": 0.6243112087249756, "regret_any": 0.7493726015090942, "regret_bot": 0.8259051442146301, "value_dist": 0.25339382886886597, "value_other_env": 0.1329309195280075, "value_corner": 0.43408820033073425, "value_row": 0.2343153953552246, "value_any": 0.13287805020809174, "value_bot": 0.0327213890850544, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00060.png", "entropy": 1.3330259323120117} +{"ts": "2026-03-20T17:24:21.770498Z", "loop": 61, "env_steps": 37478400, "exact_value_avg": 0.2596614956855774, "regret_dist": 0.6039192080497742, "regret_other_env": 0.7516801357269287, "regret_corner": 0.3822776973247528, "regret_row": 0.6202957630157471, "regret_any": 0.7517704367637634, "regret_bot": 0.8281707763671875, "value_dist": 0.2596614956855774, "value_other_env": 0.13053475320339203, "value_corner": 0.45335161685943604, "value_row": 0.23833085596561432, "value_any": 0.13048015534877777, "value_bot": 0.030455851927399635, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00061.png", "entropy": 1.3260289430618286} +{"ts": "2026-03-20T17:24:22.657882Z", "loop": 62, "env_steps": 38092800, "exact_value_avg": 0.2660406529903412, "regret_dist": 0.597540020942688, "regret_other_env": 0.7542184591293335, "regret_corner": 0.36252233386039734, "regret_row": 0.6164613962173462, "regret_any": 0.7543101906776428, "regret_bot": 0.8303498029708862, "value_dist": 0.2660406529903412, "value_other_env": 0.12799641489982605, "value_corner": 0.4731069803237915, "value_row": 0.24216525256633759, "value_any": 0.1279403418302536, "value_bot": 0.028276842087507248, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00062.png", "entropy": 1.3179709911346436} +{"ts": "2026-03-20T17:24:23.546969Z", "loop": 63, "env_steps": 38707200, "exact_value_avg": 0.2724168598651886, "regret_dist": 0.5911638140678406, "regret_other_env": 0.7568790316581726, "regret_corner": 0.34259092807769775, "regret_row": 0.612939715385437, "regret_any": 0.7569720149040222, "regret_bot": 0.832416296005249, "value_dist": 0.2724168598651886, "value_other_env": 0.12533581256866455, "value_corner": 0.4930383861064911, "value_row": 0.24568688869476318, "value_any": 0.1252785623073578, "value_bot": 0.02621026709675789, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00063.png", "entropy": 1.3087527751922607} +{"ts": "2026-03-20T17:24:24.437782Z", "loop": 64, "env_steps": 39321600, "exact_value_avg": 0.2787972688674927, "regret_dist": 0.5847834348678589, "regret_other_env": 0.7596573233604431, "regret_corner": 0.3224724531173706, "regret_row": 0.6096926927566528, "regret_any": 0.7597511410713196, "regret_bot": 0.8343725800514221, "value_dist": 0.2787972688674927, "value_other_env": 0.12255758047103882, "value_corner": 0.5131568312644958, "value_row": 0.24893400073051453, "value_any": 0.12249942123889923, "value_bot": 0.024254081770777702, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00064.png", "entropy": 1.298186182975769} +{"ts": "2026-03-20T17:24:25.326637Z", "loop": 65, "env_steps": 39936000, "exact_value_avg": 0.285138338804245, "regret_dist": 0.5784423351287842, "regret_other_env": 0.7625405192375183, "regret_corner": 0.302295058965683, "regret_row": 0.6067507266998291, "regret_any": 0.7626349925994873, "regret_bot": 0.8362244963645935, "value_dist": 0.285138338804245, "value_other_env": 0.11967439204454422, "value_corner": 0.5333342552185059, "value_row": 0.2518759071826935, "value_any": 0.1196155995130539, "value_bot": 0.02240215800702572, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00065.png", "entropy": 1.2860945463180542} +{"ts": "2026-03-20T17:24:26.215677Z", "loop": 66, "env_steps": 40550400, "exact_value_avg": 0.29137200117111206, "regret_dist": 0.5722086429595947, "regret_other_env": 0.7655085921287537, "regret_corner": 0.2822587490081787, "regret_row": 0.6040788292884827, "regret_any": 0.7656034827232361, "regret_bot": 0.8379741311073303, "value_dist": 0.29137200117111206, "value_other_env": 0.11670626699924469, "value_corner": 0.5533705949783325, "value_row": 0.2545478045940399, "value_any": 0.11664711683988571, "value_bot": 0.020652495324611664, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00066.png", "entropy": 1.2722874879837036} +{"ts": "2026-03-20T17:24:27.106157Z", "loop": 67, "env_steps": 41164800, "exact_value_avg": 0.2974091172218323, "regret_dist": 0.5661715865135193, "regret_other_env": 0.7685348391532898, "regret_corner": 0.26262661814689636, "regret_row": 0.6017369031906128, "regret_any": 0.768629789352417, "regret_bot": 0.8396188020706177, "value_dist": 0.2974091172218323, "value_other_env": 0.11368007212877274, "value_corner": 0.5730026960372925, "value_row": 0.2568897008895874, "value_any": 0.113620825111866, "value_bot": 0.01900787651538849, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00067.png", "entropy": 1.2566157579421997} +{"ts": "2026-03-20T17:24:27.995598Z", "loop": 68, "env_steps": 41779200, "exact_value_avg": 0.3031659722328186, "regret_dist": 0.5604146718978882, "regret_other_env": 0.7715646624565125, "regret_corner": 0.2436896711587906, "regret_row": 0.5997874140739441, "regret_any": 0.7716595530509949, "regret_bot": 0.8411300778388977, "value_dist": 0.3031659722328186, "value_other_env": 0.11065015941858292, "value_corner": 0.5919396281242371, "value_row": 0.2588392198085785, "value_any": 0.11059103906154633, "value_bot": 0.01749652624130249, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00068.png", "entropy": 1.2390810251235962} +{"ts": "2026-03-20T17:24:28.887152Z", "loop": 69, "env_steps": 42393600, "exact_value_avg": 0.30856388807296753, "regret_dist": 0.5550167560577393, "regret_other_env": 0.7745521664619446, "regret_corner": 0.22571362555027008, "regret_row": 0.5984662175178528, "regret_any": 0.7746466398239136, "regret_bot": 0.8424757122993469, "value_dist": 0.30856388807296753, "value_other_env": 0.10766272246837616, "value_corner": 0.6099156737327576, "value_row": 0.26016050577163696, "value_any": 0.10760395973920822, "value_bot": 0.016150884330272675, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00069.png", "entropy": 1.2197483777999878} +{"ts": "2026-03-20T17:24:29.776267Z", "loop": 70, "env_steps": 43008000, "exact_value_avg": 0.3135528266429901, "regret_dist": 0.5500278472900391, "regret_other_env": 0.7774560451507568, "regret_corner": 0.2088855504989624, "regret_row": 0.5975937843322754, "regret_any": 0.7775499820709229, "regret_bot": 0.8436779379844666, "value_dist": 0.3135528266429901, "value_other_env": 0.10475887358188629, "value_corner": 0.626743733882904, "value_row": 0.2610327899456024, "value_any": 0.10470065474510193, "value_bot": 0.014948672614991665, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00070.png", "entropy": 1.1987661123275757} +{"ts": "2026-03-20T17:24:30.666075Z", "loop": 71, "env_steps": 43622400, "exact_value_avg": 0.31813183426856995, "regret_dist": 0.545448899269104, "regret_other_env": 0.7802507281303406, "regret_corner": 0.1932460218667984, "regret_row": 0.5971112847328186, "regret_any": 0.7803439497947693, "regret_bot": 0.8447497487068176, "value_dist": 0.31813183426856995, "value_other_env": 0.10196416079998016, "value_corner": 0.642383337020874, "value_row": 0.2615153193473816, "value_any": 0.10190659761428833, "value_bot": 0.013876882381737232, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00071.png", "entropy": 1.1762020587921143} +{"ts": "2026-03-20T17:24:31.553760Z", "loop": 72, "env_steps": 44236800, "exact_value_avg": 0.3223031759262085, "regret_dist": 0.5412774682044983, "regret_other_env": 0.7829189896583557, "regret_corner": 0.17881518602371216, "regret_row": 0.5967959761619568, "regret_any": 0.7830116152763367, "regret_bot": 0.8457234501838684, "value_dist": 0.3223031759262085, "value_other_env": 0.09929586946964264, "value_corner": 0.6568140983581543, "value_row": 0.2618306279182434, "value_any": 0.09923908114433289, "value_bot": 0.012903161346912384, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00072.png", "entropy": 1.1521917581558228} +{"ts": "2026-03-20T17:24:32.442027Z", "loop": 73, "env_steps": 44851200, "exact_value_avg": 0.32604551315307617, "regret_dist": 0.5375351309776306, "regret_other_env": 0.7854297161102295, "regret_corner": 0.1656932830810547, "regret_row": 0.5967059135437012, "regret_any": 0.785521388053894, "regret_bot": 0.8465871810913086, "value_dist": 0.32604551315307617, "value_other_env": 0.09678517282009125, "value_corner": 0.6699360013008118, "value_row": 0.2619207501411438, "value_any": 0.09672924131155014, "value_bot": 0.012039445340633392, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00073.png", "entropy": 1.127102017402649} +{"ts": "2026-03-20T17:24:33.331696Z", "loop": 74, "env_steps": 45465600, "exact_value_avg": 0.32941824197769165, "regret_dist": 0.5341624617576599, "regret_other_env": 0.787804126739502, "regret_corner": 0.15369988977909088, "regret_row": 0.5968351364135742, "regret_any": 0.7878949046134949, "regret_bot": 0.8473541140556335, "value_dist": 0.32941824197769165, "value_other_env": 0.09441078454256058, "value_corner": 0.6819294095039368, "value_row": 0.26179155707359314, "value_any": 0.0943557471036911, "value_bot": 0.011272483505308628, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00074.png", "entropy": 1.1009080410003662} +{"ts": "2026-03-20T17:24:34.221090Z", "loop": 75, "env_steps": 46080000, "exact_value_avg": 0.3323953151702881, "regret_dist": 0.5311853885650635, "regret_other_env": 0.7899878621101379, "regret_corner": 0.142981618642807, "regret_row": 0.5971564650535583, "regret_any": 0.7900776863098145, "regret_bot": 0.8480216860771179, "value_dist": 0.3323953151702881, "value_other_env": 0.0922270342707634, "value_corner": 0.6926476955413818, "value_row": 0.26147016882896423, "value_any": 0.09217292070388794, "value_bot": 0.010604922659695148, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00075.png", "entropy": 1.0743818283081055} +{"ts": "2026-03-20T17:24:35.108258Z", "loop": 76, "env_steps": 46694400, "exact_value_avg": 0.33496931195259094, "regret_dist": 0.5286113619804382, "regret_other_env": 0.7919632196426392, "regret_corner": 0.13358360528945923, "regret_row": 0.5976752638816833, "regret_any": 0.7920522093772888, "regret_bot": 0.8485931158065796, "value_dist": 0.33496931195259094, "value_other_env": 0.09025165438652039, "value_corner": 0.702045738697052, "value_row": 0.26095131039619446, "value_any": 0.09019842743873596, "value_bot": 0.010033565573394299, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00076.png", "entropy": 1.0481313467025757} +{"ts": "2026-03-20T17:24:35.994433Z", "loop": 77, "env_steps": 47308800, "exact_value_avg": 0.3372077941894531, "regret_dist": 0.5263728499412537, "regret_other_env": 0.7937448024749756, "regret_corner": 0.12531492114067078, "regret_row": 0.5987450480461121, "regret_any": 0.7938328981399536, "regret_bot": 0.8490503430366516, "value_dist": 0.3372077941894531, "value_other_env": 0.08847004175186157, "value_corner": 0.7103143930435181, "value_row": 0.25988155603408813, "value_any": 0.0884176716208458, "value_bot": 0.009576329030096531, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00077.png", "entropy": 1.0224592685699463} +{"ts": "2026-03-20T17:24:36.881987Z", "loop": 78, "env_steps": 47923200, "exact_value_avg": 0.3391914665699005, "regret_dist": 0.5243892669677734, "regret_other_env": 0.7953893542289734, "regret_corner": 0.11788906157016754, "regret_row": 0.5998967289924622, "regret_any": 0.7954766154289246, "regret_bot": 0.8494539856910706, "value_dist": 0.3391914665699005, "value_other_env": 0.08682557195425034, "value_corner": 0.7177402973175049, "value_row": 0.2587299048900604, "value_any": 0.08677403628826141, "value_bot": 0.00917260441929102, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00078.png", "entropy": 0.9968768954277039} +{"ts": "2026-03-20T17:24:37.771472Z", "loop": 79, "env_steps": 48537600, "exact_value_avg": 0.34089216589927673, "regret_dist": 0.5226885080337524, "regret_other_env": 0.7968543767929077, "regret_corner": 0.11143974959850311, "regret_row": 0.6011911630630493, "regret_any": 0.796940803527832, "regret_bot": 0.8497896790504456, "value_dist": 0.34089216589927673, "value_other_env": 0.08536054193973541, "value_corner": 0.7241895794868469, "value_row": 0.2574354410171509, "value_any": 0.08530979603528976, "value_bot": 0.008836984634399414, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00079.png", "entropy": 0.9724310040473938} +{"ts": "2026-03-20T17:24:38.661651Z", "loop": 80, "env_steps": 49152000, "exact_value_avg": 0.3423362076282501, "regret_dist": 0.521244466304779, "regret_other_env": 0.798143208026886, "regret_corner": 0.10589630901813507, "regret_row": 0.6025131344795227, "regret_any": 0.7982289791107178, "regret_bot": 0.8500693440437317, "value_dist": 0.3423362076282501, "value_other_env": 0.08407165110111237, "value_corner": 0.7297329902648926, "value_row": 0.2561134397983551, "value_any": 0.08402162790298462, "value_bot": 0.008557251654565334, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00080.png", "entropy": 0.9494876861572266} +{"ts": "2026-03-20T17:24:39.557474Z", "loop": 81, "env_steps": 49766400, "exact_value_avg": 0.3436060845851898, "regret_dist": 0.5199745297431946, "regret_other_env": 0.7993127107620239, "regret_corner": 0.10096725821495056, "regret_row": 0.6041041612625122, "regret_any": 0.7993978261947632, "regret_bot": 0.8502933382987976, "value_dist": 0.3436060845851898, "value_other_env": 0.08290212601423264, "value_corner": 0.7346620559692383, "value_row": 0.25452256202697754, "value_any": 0.0828527882695198, "value_bot": 0.008333340287208557, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00081.png", "entropy": 0.9274040460586548} +{"ts": "2026-03-20T17:24:40.446667Z", "loop": 82, "env_steps": 50380800, "exact_value_avg": 0.3446832299232483, "regret_dist": 0.5188973546028137, "regret_other_env": 0.8003439903259277, "regret_corner": 0.09672744572162628, "regret_row": 0.6053017377853394, "regret_any": 0.8004285097122192, "regret_bot": 0.8505079746246338, "value_dist": 0.3446832299232483, "value_other_env": 0.08187080174684525, "value_corner": 0.7389018535614014, "value_row": 0.25332486629486084, "value_any": 0.08182208240032196, "value_bot": 0.008118703961372375, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00082.png", "entropy": 0.9068289995193481} +{"ts": "2026-03-20T17:24:41.336051Z", "loop": 83, "env_steps": 50995200, "exact_value_avg": 0.34560900926589966, "regret_dist": 0.5179716348648071, "regret_other_env": 0.8012627363204956, "regret_corner": 0.0930350050330162, "regret_row": 0.606510579586029, "regret_any": 0.8013466596603394, "regret_bot": 0.8506907820701599, "value_dist": 0.34560900926589966, "value_other_env": 0.08095213025808334, "value_corner": 0.742594301700592, "value_row": 0.25211605429649353, "value_any": 0.08090399950742722, "value_bot": 0.007935833185911179, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00083.png", "entropy": 0.887611448764801} +{"ts": "2026-03-20T17:24:42.225749Z", "loop": 84, "env_steps": 51609600, "exact_value_avg": 0.34636417031288147, "regret_dist": 0.5172165036201477, "regret_other_env": 0.8020322322845459, "regret_corner": 0.0899929404258728, "regret_row": 0.607940673828125, "regret_any": 0.8021156191825867, "regret_bot": 0.8508145809173584, "value_dist": 0.34636417031288147, "value_other_env": 0.08018264919519424, "value_corner": 0.7456364035606384, "value_row": 0.25068601965904236, "value_any": 0.08013501018285751, "value_bot": 0.007812043186277151, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00084.png", "entropy": 0.8708462715148926} +{"ts": "2026-03-20T17:24:43.114654Z", "loop": 85, "env_steps": 52224000, "exact_value_avg": 0.3469858169555664, "regret_dist": 0.5165948271751404, "regret_other_env": 0.8026947379112244, "regret_corner": 0.08744494616985321, "regret_row": 0.6094692349433899, "regret_any": 0.8027776479721069, "regret_bot": 0.8509013652801514, "value_dist": 0.3469858169555664, "value_other_env": 0.0795200988650322, "value_corner": 0.7481843829154968, "value_row": 0.24915747344493866, "value_any": 0.07947291433811188, "value_bot": 0.0077252378687262535, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00085.png", "entropy": 0.8559593558311462} +{"ts": "2026-03-20T17:24:44.002877Z", "loop": 86, "env_steps": 52838400, "exact_value_avg": 0.34749501943588257, "regret_dist": 0.5160857439041138, "regret_other_env": 0.8032631874084473, "regret_corner": 0.08531943708658218, "regret_row": 0.6113530993461609, "regret_any": 0.8033456802368164, "regret_bot": 0.8509387969970703, "value_dist": 0.34749501943588257, "value_other_env": 0.07895169407129288, "value_corner": 0.750309944152832, "value_row": 0.2472735196352005, "value_any": 0.0789048969745636, "value_bot": 0.007687824312597513, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00086.png", "entropy": 0.8428489565849304} +{"ts": "2026-03-20T17:24:44.891654Z", "loop": 87, "env_steps": 53452800, "exact_value_avg": 0.34790804982185364, "regret_dist": 0.5156726837158203, "regret_other_env": 0.8037684559822083, "regret_corner": 0.08352897316217422, "regret_row": 0.6137487292289734, "regret_any": 0.803850531578064, "regret_bot": 0.8509228825569153, "value_dist": 0.34790804982185364, "value_other_env": 0.07844649255275726, "value_corner": 0.7521003484725952, "value_row": 0.2448778748512268, "value_any": 0.07840006798505783, "value_bot": 0.00770381698384881, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00087.png", "entropy": 0.8310025334358215} +{"ts": "2026-03-20T17:24:45.779412Z", "loop": 88, "env_steps": 54067200, "exact_value_avg": 0.34828007221221924, "regret_dist": 0.5153006315231323, "regret_other_env": 0.8042656779289246, "regret_corner": 0.0818530023097992, "regret_row": 0.6162320375442505, "regret_any": 0.8043474555015564, "regret_bot": 0.8509030938148499, "value_dist": 0.34828007221221924, "value_other_env": 0.07794918864965439, "value_corner": 0.7537763118743896, "value_row": 0.24239462614059448, "value_any": 0.07790310680866241, "value_bot": 0.007723498623818159, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00088.png", "entropy": 0.819098711013794} +{"ts": "2026-03-20T17:24:46.668026Z", "loop": 89, "env_steps": 54681600, "exact_value_avg": 0.34862685203552246, "regret_dist": 0.5149537920951843, "regret_other_env": 0.8047440648078918, "regret_corner": 0.08026831597089767, "regret_row": 0.617999255657196, "regret_any": 0.8048255443572998, "regret_bot": 0.8509331345558167, "value_dist": 0.34862685203552246, "value_other_env": 0.07747074961662292, "value_corner": 0.755361020565033, "value_row": 0.24062734842300415, "value_any": 0.0774250477552414, "value_bot": 0.007693457417190075, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00089.png", "entropy": 0.8074173331260681} +{"ts": "2026-03-20T17:24:47.557573Z", "loop": 90, "env_steps": 55296000, "exact_value_avg": 0.3489423990249634, "regret_dist": 0.5146382451057434, "regret_other_env": 0.8051722049713135, "regret_corner": 0.0788373053073883, "regret_row": 0.6189275979995728, "regret_any": 0.8052533268928528, "regret_bot": 0.8510103821754456, "value_dist": 0.3489423990249634, "value_other_env": 0.0770426094532013, "value_corner": 0.7567920684814453, "value_row": 0.23969906568527222, "value_any": 0.07699722796678543, "value_bot": 0.007616295944899321, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00090.png", "entropy": 0.7968684434890747} +{"ts": "2026-03-20T17:24:48.446437Z", "loop": 91, "env_steps": 55910400, "exact_value_avg": 0.3492220938205719, "regret_dist": 0.514358639717102, "regret_other_env": 0.8055640459060669, "regret_corner": 0.07755047082901001, "regret_row": 0.6196272969245911, "regret_any": 0.8056448698043823, "regret_bot": 0.8510953783988953, "value_dist": 0.3492220938205719, "value_other_env": 0.07665086537599564, "value_corner": 0.7580788731575012, "value_row": 0.23899933695793152, "value_any": 0.07660579681396484, "value_bot": 0.007531296461820602, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00091.png", "entropy": 0.7871950268745422} +{"ts": "2026-03-20T17:24:49.333406Z", "loop": 92, "env_steps": 56524800, "exact_value_avg": 0.34947970509529114, "regret_dist": 0.5141009092330933, "regret_other_env": 0.805903434753418, "regret_corner": 0.0763971284031868, "regret_row": 0.619394063949585, "regret_any": 0.8059839606285095, "regret_bot": 0.8512276411056519, "value_dist": 0.34947970509529114, "value_other_env": 0.0763113871216774, "value_corner": 0.7592321634292603, "value_row": 0.23923254013061523, "value_any": 0.0762665718793869, "value_bot": 0.007399039342999458, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00092.png", "entropy": 0.778719425201416} +{"ts": "2026-03-20T17:24:50.223507Z", "loop": 93, "env_steps": 57139200, "exact_value_avg": 0.34969767928123474, "regret_dist": 0.5138829946517944, "regret_other_env": 0.806196391582489, "regret_corner": 0.0754128023982048, "regret_row": 0.6183037757873535, "regret_any": 0.8062767386436462, "regret_bot": 0.8514013886451721, "value_dist": 0.34969767928123474, "value_other_env": 0.07601848244667053, "value_corner": 0.760216474533081, "value_row": 0.24032284319400787, "value_any": 0.07597390562295914, "value_bot": 0.0072252401150763035, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00093.png", "entropy": 0.7712888121604919} +{"ts": "2026-03-20T17:24:51.111910Z", "loop": 94, "env_steps": 57753600, "exact_value_avg": 0.3498639464378357, "regret_dist": 0.5137166976928711, "regret_other_env": 0.8064622282981873, "regret_corner": 0.07459835708141327, "regret_row": 0.6180588006973267, "regret_any": 0.8065423369407654, "regret_bot": 0.851505696773529, "value_dist": 0.3498639464378357, "value_other_env": 0.07575264573097229, "value_corner": 0.761030912399292, "value_row": 0.24056778848171234, "value_any": 0.0757082998752594, "value_bot": 0.007120977621525526, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00094.png", "entropy": 0.7645776867866516} +{"ts": "2026-03-20T17:24:51.998784Z", "loop": 95, "env_steps": 58368000, "exact_value_avg": 0.3500007092952728, "regret_dist": 0.5135800242424011, "regret_other_env": 0.8067108988761902, "regret_corner": 0.07388361543416977, "regret_row": 0.6178951263427734, "regret_any": 0.8067907094955444, "regret_bot": 0.8515965342521667, "value_dist": 0.3500007092952728, "value_other_env": 0.07550403475761414, "value_corner": 0.7617456912994385, "value_row": 0.24073155224323273, "value_any": 0.07545989006757736, "value_bot": 0.007030066568404436, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00095.png", "entropy": 0.7583106160163879} +{"ts": "2026-03-20T17:24:52.886845Z", "loop": 96, "env_steps": 58982400, "exact_value_avg": 0.35010263323783875, "regret_dist": 0.5134780406951904, "regret_other_env": 0.806922197341919, "regret_corner": 0.07331184297800064, "regret_row": 0.6168163418769836, "regret_any": 0.8070018291473389, "regret_bot": 0.8517327904701233, "value_dist": 0.35010263323783875, "value_other_env": 0.07529274374246597, "value_corner": 0.7623174786567688, "value_row": 0.24181027710437775, "value_any": 0.07524878531694412, "value_bot": 0.0068938541226089, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00096.png", "entropy": 0.7528337836265564} +{"ts": "2026-03-20T17:24:53.774066Z", "loop": 97, "env_steps": 59596800, "exact_value_avg": 0.35017767548561096, "regret_dist": 0.5134029984474182, "regret_other_env": 0.8070980906486511, "regret_corner": 0.07286032289266586, "regret_row": 0.6166825294494629, "regret_any": 0.8071776032447815, "regret_bot": 0.8517981767654419, "value_dist": 0.35017767548561096, "value_other_env": 0.07511676847934723, "value_corner": 0.7627690434455872, "value_row": 0.24194404482841492, "value_any": 0.07507298141717911, "value_bot": 0.006828383542597294, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00097.png", "entropy": 0.7483818531036377} +{"ts": "2026-03-20T17:24:54.662868Z", "loop": 98, "env_steps": 60211200, "exact_value_avg": 0.3502295911312103, "regret_dist": 0.5133510828018188, "regret_other_env": 0.8072497248649597, "regret_corner": 0.07250310480594635, "regret_row": 0.6162412166595459, "regret_any": 0.8073291182518005, "regret_bot": 0.8518739342689514, "value_dist": 0.3502295911312103, "value_other_env": 0.07496517151594162, "value_corner": 0.7631261944770813, "value_row": 0.24238541722297668, "value_any": 0.07492151111364365, "value_bot": 0.006752741523087025, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00098.png", "entropy": 0.7444962859153748} +{"ts": "2026-03-20T17:24:55.551815Z", "loop": 99, "env_steps": 60825600, "exact_value_avg": 0.3502988815307617, "regret_dist": 0.5132818222045898, "regret_other_env": 0.8073873519897461, "regret_corner": 0.0721234381198883, "regret_row": 0.616912841796875, "regret_any": 0.8074665665626526, "regret_bot": 0.8518763184547424, "value_dist": 0.3502988815307617, "value_other_env": 0.07482754439115524, "value_corner": 0.7635058760643005, "value_row": 0.241713747382164, "value_any": 0.07478401064872742, "value_bot": 0.0067502763122320175, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00099.png", "entropy": 0.7410885691642761} +{"ts": "2026-03-20T17:24:56.443710Z", "loop": 100, "env_steps": 61440000, "exact_value_avg": 0.3503570556640625, "regret_dist": 0.5132235884666443, "regret_other_env": 0.8074987530708313, "regret_corner": 0.07181081920862198, "regret_row": 0.6175568103790283, "regret_any": 0.8075779676437378, "regret_bot": 0.8518717288970947, "value_dist": 0.3503570556640625, "value_other_env": 0.07471610605716705, "value_corner": 0.7638184428215027, "value_row": 0.24106985330581665, "value_any": 0.07467268407344818, "value_bot": 0.006754845846444368, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00100.png", "entropy": 0.7383096814155579} +{"ts": "2026-03-20T17:24:57.332163Z", "loop": 101, "env_steps": 62054400, "exact_value_avg": 0.35042068362236023, "regret_dist": 0.5131600499153137, "regret_other_env": 0.8076085448265076, "regret_corner": 0.07148721069097519, "regret_row": 0.6190352439880371, "regret_any": 0.8076875805854797, "regret_bot": 0.8518152832984924, "value_dist": 0.35042068362236023, "value_other_env": 0.07460633665323257, "value_corner": 0.7641421556472778, "value_row": 0.23959137499332428, "value_any": 0.07456301897764206, "value_bot": 0.006811282131820917, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00101.png", "entropy": 0.7357510924339294} +{"ts": "2026-03-20T17:24:58.223249Z", "loop": 102, "env_steps": 62668800, "exact_value_avg": 0.35045963525772095, "regret_dist": 0.5131210684776306, "regret_other_env": 0.8076995015144348, "regret_corner": 0.07125335186719894, "regret_row": 0.6193711757659912, "regret_any": 0.8077783584594727, "regret_bot": 0.8518223166465759, "value_dist": 0.35045963525772095, "value_other_env": 0.07451540976762772, "value_corner": 0.7643759846687317, "value_row": 0.23925548791885376, "value_any": 0.07447217404842377, "value_bot": 0.006804356351494789, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00102.png", "entropy": 0.7334715127944946} +{"ts": "2026-03-20T17:24:59.112046Z", "loop": 103, "env_steps": 63283200, "exact_value_avg": 0.3504936099052429, "regret_dist": 0.5130870342254639, "regret_other_env": 0.8077778816223145, "regret_corner": 0.0710507407784462, "regret_row": 0.6201671957969666, "regret_any": 0.8078567981719971, "regret_bot": 0.8517975211143494, "value_dist": 0.3504936099052429, "value_other_env": 0.07443695515394211, "value_corner": 0.7645785808563232, "value_row": 0.23845939338207245, "value_any": 0.07439381629228592, "value_bot": 0.006829060148447752, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00103.png", "entropy": 0.7316026091575623} +{"ts": "2026-03-20T17:25:00.000765Z", "loop": 104, "env_steps": 63897600, "exact_value_avg": 0.3505088686943054, "regret_dist": 0.5130718350410461, "regret_other_env": 0.8078381419181824, "regret_corner": 0.07092230021953583, "regret_row": 0.6199347972869873, "regret_any": 0.8079169392585754, "regret_bot": 0.8518293499946594, "value_dist": 0.3505088686943054, "value_other_env": 0.07437674701213837, "value_corner": 0.7647070288658142, "value_row": 0.23869183659553528, "value_any": 0.07433365285396576, "value_bot": 0.006797241047024727, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00104.png", "entropy": 0.7300848364830017} +{"ts": "2026-03-20T17:25:00.890101Z", "loop": 105, "env_steps": 64512000, "exact_value_avg": 0.35053980350494385, "regret_dist": 0.5130408406257629, "regret_other_env": 0.8079068064689636, "regret_corner": 0.07074189186096191, "regret_row": 0.6206362247467041, "regret_any": 0.8079856038093567, "regret_bot": 0.8518059849739075, "value_dist": 0.35053980350494385, "value_other_env": 0.07430808991193771, "value_corner": 0.7648873925209045, "value_row": 0.2379903793334961, "value_any": 0.07426505535840988, "value_bot": 0.006820711772888899, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00105.png", "entropy": 0.7284305691719055} +{"ts": "2026-03-20T17:25:01.780822Z", "loop": 106, "env_steps": 65126400, "exact_value_avg": 0.3505631387233734, "regret_dist": 0.5130175948143005, "regret_other_env": 0.8079743981361389, "regret_corner": 0.07058236002922058, "regret_row": 0.6205005049705505, "regret_any": 0.8080530166625977, "regret_bot": 0.8518360257148743, "value_dist": 0.3505631387233734, "value_other_env": 0.074240542948246, "value_corner": 0.765047013759613, "value_row": 0.23812606930732727, "value_any": 0.07419758290052414, "value_bot": 0.006790583487600088, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00106.png", "entropy": 0.7267091274261475} +{"ts": "2026-03-20T17:25:02.670368Z", "loop": 107, "env_steps": 65740800, "exact_value_avg": 0.35059425234794617, "regret_dist": 0.5129864811897278, "regret_other_env": 0.8080452680587769, "regret_corner": 0.07039821147918701, "regret_row": 0.6215957999229431, "regret_any": 0.8081239461898804, "regret_bot": 0.8517909049987793, "value_dist": 0.35059425234794617, "value_other_env": 0.07416961342096329, "value_corner": 0.7652311325073242, "value_row": 0.23703089356422424, "value_any": 0.0741267204284668, "value_bot": 0.0068357279524207115, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00107.png", "entropy": 0.7250341176986694} +{"ts": "2026-03-20T17:25:03.557197Z", "loop": 108, "env_steps": 66355200, "exact_value_avg": 0.3506133556365967, "regret_dist": 0.5129672884941101, "regret_other_env": 0.8081122636795044, "regret_corner": 0.07024986296892166, "regret_row": 0.6211517453193665, "regret_any": 0.8081908226013184, "regret_bot": 0.8518410325050354, "value_dist": 0.3506133556365967, "value_other_env": 0.07410255819559097, "value_corner": 0.7653794884681702, "value_row": 0.23747488856315613, "value_any": 0.07405973225831985, "value_bot": 0.006785642355680466, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00108.png", "entropy": 0.7233397364616394} +{"ts": "2026-03-20T17:25:04.446159Z", "loop": 109, "env_steps": 66969600, "exact_value_avg": 0.35062628984451294, "regret_dist": 0.5129544138908386, "regret_other_env": 0.808173418045044, "regret_corner": 0.0701257660984993, "regret_row": 0.620775580406189, "regret_any": 0.8082519769668579, "regret_bot": 0.8518853783607483, "value_dist": 0.35062628984451294, "value_other_env": 0.074041448533535, "value_corner": 0.7655035853385925, "value_row": 0.23785099387168884, "value_any": 0.07399867475032806, "value_bot": 0.0067412336356937885, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00109.png", "entropy": 0.7217896580696106} +{"ts": "2026-03-20T17:25:05.334549Z", "loop": 110, "env_steps": 67584000, "exact_value_avg": 0.35064446926116943, "regret_dist": 0.5129362344741821, "regret_other_env": 0.8082320094108582, "regret_corner": 0.06999249756336212, "regret_row": 0.6210635900497437, "regret_any": 0.8083105087280273, "regret_bot": 0.8518884778022766, "value_dist": 0.35064446926116943, "value_other_env": 0.07398287951946259, "value_corner": 0.7656368613243103, "value_row": 0.23756301403045654, "value_any": 0.07394018024206161, "value_bot": 0.0067381104454398155, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00110.png", "entropy": 0.7203824520111084} +{"ts": "2026-03-20T17:25:06.222977Z", "loop": 111, "env_steps": 68198400, "exact_value_avg": 0.3506581783294678, "regret_dist": 0.5129225254058838, "regret_other_env": 0.8082788586616516, "regret_corner": 0.06988796591758728, "regret_row": 0.6208755970001221, "regret_any": 0.8083572387695312, "regret_bot": 0.8519163131713867, "value_dist": 0.3506581783294678, "value_other_env": 0.07393603026866913, "value_corner": 0.7657414078712463, "value_row": 0.2377510666847229, "value_any": 0.07389336824417114, "value_bot": 0.0067102923057973385, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00111.png", "entropy": 0.7192096710205078} +{"ts": "2026-03-20T17:25:07.110739Z", "loop": 112, "env_steps": 68812800, "exact_value_avg": 0.3506525456905365, "regret_dist": 0.5129281282424927, "regret_other_env": 0.8083135485649109, "regret_corner": 0.0698499083518982, "regret_row": 0.6201104521751404, "regret_any": 0.8083919286727905, "regret_bot": 0.8519741892814636, "value_dist": 0.3506525456905365, "value_other_env": 0.07390127331018448, "value_corner": 0.765779435634613, "value_row": 0.23851613700389862, "value_any": 0.07385866343975067, "value_bot": 0.006652498617768288, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00112.png", "entropy": 0.7182648777961731} +{"ts": "2026-03-20T17:25:07.999137Z", "loop": 113, "env_steps": 69427200, "exact_value_avg": 0.3506487309932709, "regret_dist": 0.5129319429397583, "regret_other_env": 0.8083382248878479, "regret_corner": 0.06982244551181793, "regret_row": 0.619979202747345, "regret_any": 0.808416485786438, "regret_bot": 0.8519909977912903, "value_dist": 0.3506487309932709, "value_other_env": 0.07387664169073105, "value_corner": 0.7658068537712097, "value_row": 0.2386474460363388, "value_any": 0.07383404672145844, "value_bot": 0.006635654717683792, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00113.png", "entropy": 0.7176464796066284} +{"ts": "2026-03-20T17:25:08.887752Z", "loop": 114, "env_steps": 70041600, "exact_value_avg": 0.3506685197353363, "regret_dist": 0.5129121541976929, "regret_other_env": 0.8083642721176147, "regret_corner": 0.06973397731781006, "regret_row": 0.62054842710495, "regret_any": 0.8084425926208496, "regret_bot": 0.8519653081893921, "value_dist": 0.3506685197353363, "value_other_env": 0.073850616812706, "value_corner": 0.7658953666687012, "value_row": 0.23807820677757263, "value_any": 0.07380805164575577, "value_bot": 0.006661226507276297, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00114.png", "entropy": 0.7170883417129517} +{"ts": "2026-03-20T17:25:09.776321Z", "loop": 115, "env_steps": 70656000, "exact_value_avg": 0.3506677746772766, "regret_dist": 0.5129128694534302, "regret_other_env": 0.8083877563476562, "regret_corner": 0.06970053911209106, "regret_row": 0.6202402710914612, "regret_any": 0.8084660768508911, "regret_bot": 0.8519917726516724, "value_dist": 0.3506677746772766, "value_other_env": 0.07382708042860031, "value_corner": 0.7659288048744202, "value_row": 0.2383863478899002, "value_any": 0.07378453761339188, "value_bot": 0.006634839344769716, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00115.png", "entropy": 0.7164692282676697} +{"ts": "2026-03-20T17:25:10.665199Z", "loop": 116, "env_steps": 71270400, "exact_value_avg": 0.35065990686416626, "regret_dist": 0.5129207968711853, "regret_other_env": 0.808407187461853, "regret_corner": 0.06969112157821655, "regret_row": 0.6197521090507507, "regret_any": 0.8084854483604431, "regret_bot": 0.8520277142524719, "value_dist": 0.35065990686416626, "value_other_env": 0.07380767911672592, "value_corner": 0.7659382224082947, "value_row": 0.23887448012828827, "value_any": 0.07376515865325928, "value_bot": 0.006598973646759987, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00116.png", "entropy": 0.7159342765808105} +{"ts": "2026-03-20T17:25:11.553950Z", "loop": 117, "env_steps": 71884800, "exact_value_avg": 0.35064512491226196, "regret_dist": 0.5129355192184448, "regret_other_env": 0.8084306120872498, "regret_corner": 0.06969287246465683, "regret_row": 0.619060218334198, "regret_any": 0.8085088729858398, "regret_bot": 0.8520761132240295, "value_dist": 0.35064512491226196, "value_other_env": 0.073784239590168, "value_corner": 0.7659364342689514, "value_row": 0.2395664006471634, "value_any": 0.07374173402786255, "value_bot": 0.006550489459186792, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00117.png", "entropy": 0.7152354121208191} +{"ts": "2026-03-20T17:25:12.441026Z", "loop": 118, "env_steps": 72499200, "exact_value_avg": 0.35060393810272217, "regret_dist": 0.5129767656326294, "regret_other_env": 0.8084489107131958, "regret_corner": 0.06976845115423203, "regret_row": 0.6177933812141418, "regret_any": 0.8085270524024963, "regret_bot": 0.8521564602851868, "value_dist": 0.35060393810272217, "value_other_env": 0.07376596331596375, "value_corner": 0.765860915184021, "value_row": 0.24083325266838074, "value_any": 0.07372348010540009, "value_bot": 0.006470161490142345, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00118.png", "entropy": 0.7145660519599915} +{"ts": "2026-03-20T17:25:13.329354Z", "loop": 119, "env_steps": 73113600, "exact_value_avg": 0.35051169991493225, "regret_dist": 0.5130689740180969, "regret_other_env": 0.8084642887115479, "regret_corner": 0.06997592747211456, "regret_row": 0.6157212257385254, "regret_any": 0.8085425496101379, "regret_bot": 0.8522801995277405, "value_dist": 0.35051169991493225, "value_other_env": 0.0737505555152893, "value_corner": 0.7656533718109131, "value_row": 0.242905393242836, "value_any": 0.07370809465646744, "value_bot": 0.006346445064991713, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00119.png", "entropy": 0.7137067317962646} +{"ts": "2026-03-20T17:25:14.217920Z", "loop": 120, "env_steps": 73728000, "exact_value_avg": 0.3503219485282898, "regret_dist": 0.513258695602417, "regret_other_env": 0.8084815740585327, "regret_corner": 0.07042437046766281, "regret_row": 0.6127223372459412, "regret_any": 0.808559775352478, "regret_bot": 0.8524535894393921, "value_dist": 0.3503219485282898, "value_other_env": 0.07373329997062683, "value_corner": 0.765204906463623, "value_row": 0.24590428173542023, "value_any": 0.07369083911180496, "value_bot": 0.006172994151711464, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00120.png", "entropy": 0.7125994563102722} +{"ts": "2026-03-20T17:25:15.112442Z", "loop": 121, "env_steps": 74342400, "exact_value_avg": 0.3502686321735382, "regret_dist": 0.513312041759491, "regret_other_env": 0.8084996342658997, "regret_corner": 0.07053060829639435, "regret_row": 0.6119723320007324, "regret_any": 0.808577835559845, "regret_bot": 0.8525000214576721, "value_dist": 0.3502686321735382, "value_other_env": 0.0737152025103569, "value_corner": 0.7650987505912781, "value_row": 0.24665430188179016, "value_any": 0.07367276400327682, "value_bot": 0.006126658525317907, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00121.png", "entropy": 0.7119238972663879} +{"ts": "2026-03-20T17:25:15.999857Z", "loop": 122, "env_steps": 74956800, "exact_value_avg": 0.35032233595848083, "regret_dist": 0.5132583975791931, "regret_other_env": 0.8085060715675354, "regret_corner": 0.07038675993680954, "regret_row": 0.6126887798309326, "regret_any": 0.8085842132568359, "regret_bot": 0.8524627685546875, "value_dist": 0.35032233595848083, "value_other_env": 0.07370883226394653, "value_corner": 0.7652425765991211, "value_row": 0.24593786895275116, "value_any": 0.07366639375686646, "value_bot": 0.0061639221385121346, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00122.png", "entropy": 0.7119367122650146} +{"ts": "2026-03-20T17:25:16.888793Z", "loop": 123, "env_steps": 75571200, "exact_value_avg": 0.35037147998809814, "regret_dist": 0.5132092237472534, "regret_other_env": 0.8085039258003235, "regret_corner": 0.07026704400777817, "regret_row": 0.6133325099945068, "regret_any": 0.8085821270942688, "regret_bot": 0.8524250984191895, "value_dist": 0.35037147998809814, "value_other_env": 0.07371091842651367, "value_corner": 0.7653622627258301, "value_row": 0.24529418349266052, "value_any": 0.0736684799194336, "value_bot": 0.006201482377946377, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00123.png", "entropy": 0.7121403813362122} +{"ts": "2026-03-20T17:25:17.778257Z", "loop": 124, "env_steps": 76185600, "exact_value_avg": 0.35050275921821594, "regret_dist": 0.513077974319458, "regret_other_env": 0.8084931969642639, "regret_corner": 0.0699550062417984, "regret_row": 0.6154540777206421, "regret_any": 0.8085713982582092, "regret_bot": 0.8523032069206238, "value_dist": 0.35050275921821594, "value_other_env": 0.07372168451547623, "value_corner": 0.765674352645874, "value_row": 0.2431725412607193, "value_any": 0.07367923855781555, "value_bot": 0.0063234297558665276, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00124.png", "entropy": 0.7128788828849792} +{"ts": "2026-03-20T17:25:18.667693Z", "loop": 125, "env_steps": 76800000, "exact_value_avg": 0.3505963087081909, "regret_dist": 0.5129843354225159, "regret_other_env": 0.8084933757781982, "regret_corner": 0.0697207972407341, "regret_row": 0.6173022985458374, "regret_any": 0.8085715770721436, "regret_bot": 0.8521970510482788, "value_dist": 0.3505963087081909, "value_other_env": 0.07372146099805832, "value_corner": 0.7659085392951965, "value_row": 0.24132433533668518, "value_any": 0.07367902249097824, "value_bot": 0.006429604254662991, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00125.png", "entropy": 0.7132514119148254} +{"ts": "2026-03-20T17:25:19.556831Z", "loop": 126, "env_steps": 77414400, "exact_value_avg": 0.3506499230861664, "regret_dist": 0.5129307508468628, "regret_other_env": 0.8084939122200012, "regret_corner": 0.0695858970284462, "regret_row": 0.6186537742614746, "regret_any": 0.8085720539093018, "regret_bot": 0.8521177172660828, "value_dist": 0.3506499230861664, "value_other_env": 0.07372096925973892, "value_corner": 0.7660433650016785, "value_row": 0.2399728149175644, "value_any": 0.07367853075265884, "value_bot": 0.006508879829198122, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00126.png", "entropy": 0.7134765982627869} +{"ts": "2026-03-20T17:25:20.445278Z", "loop": 127, "env_steps": 78028800, "exact_value_avg": 0.35071754455566406, "regret_dist": 0.5128630995750427, "regret_other_env": 0.80849689245224, "regret_corner": 0.06941241025924683, "regret_row": 0.6211878657341003, "regret_any": 0.8085750937461853, "regret_bot": 0.8519675135612488, "value_dist": 0.35071754455566406, "value_other_env": 0.07371792197227478, "value_corner": 0.7662169337272644, "value_row": 0.23743876814842224, "value_any": 0.0736754909157753, "value_bot": 0.006659152917563915, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00127.png", "entropy": 0.7137744426727295} +{"ts": "2026-03-20T17:25:21.333965Z", "loop": 128, "env_steps": 78643200, "exact_value_avg": 0.3507458567619324, "regret_dist": 0.5128347873687744, "regret_other_env": 0.8085100054740906, "regret_corner": 0.06932199001312256, "regret_row": 0.6238836646080017, "regret_any": 0.8085881471633911, "regret_bot": 0.8518062233924866, "value_dist": 0.3507458567619324, "value_other_env": 0.07370483875274658, "value_corner": 0.7663073539733887, "value_row": 0.23474295437335968, "value_any": 0.07366243004798889, "value_bot": 0.006820296868681908, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00128.png", "entropy": 0.7137570381164551} +{"ts": "2026-03-20T17:25:22.223932Z", "loop": 129, "env_steps": 79257600, "exact_value_avg": 0.3507106304168701, "regret_dist": 0.5128700733184814, "regret_other_env": 0.8085326552391052, "regret_corner": 0.06937617063522339, "regret_row": 0.6273050308227539, "regret_any": 0.808610737323761, "regret_bot": 0.8515952229499817, "value_dist": 0.3507106304168701, "value_other_env": 0.0736822560429573, "value_corner": 0.7662531733512878, "value_row": 0.23132158815860748, "value_any": 0.0736398845911026, "value_bot": 0.007031443994492292, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00129.png", "entropy": 0.7134870290756226} +{"ts": "2026-03-20T17:25:23.112939Z", "loop": 130, "env_steps": 79872000, "exact_value_avg": 0.3506872355937958, "regret_dist": 0.5128934979438782, "regret_other_env": 0.8085442781448364, "regret_corner": 0.06941722333431244, "regret_row": 0.628200113773346, "regret_any": 0.8086223602294922, "regret_bot": 0.8515405654907227, "value_dist": 0.3506872355937958, "value_other_env": 0.0736706405878067, "value_corner": 0.7662121057510376, "value_row": 0.23042646050453186, "value_any": 0.0736282616853714, "value_bot": 0.007086120545864105, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00130.png", "entropy": 0.7132422924041748} +{"ts": "2026-03-20T17:25:24.002277Z", "loop": 131, "env_steps": 80486400, "exact_value_avg": 0.35069164633750916, "regret_dist": 0.5128890872001648, "regret_other_env": 0.8085461258888245, "regret_corner": 0.06940343230962753, "regret_row": 0.6280978918075562, "regret_any": 0.8086242079734802, "regret_bot": 0.8515478372573853, "value_dist": 0.35069164633750916, "value_other_env": 0.07366879284381866, "value_corner": 0.7662258744239807, "value_row": 0.23052874207496643, "value_any": 0.07362640649080276, "value_bot": 0.0070787109434604645, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00131.png", "entropy": 0.7131829261779785} +{"ts": "2026-03-20T17:25:24.891733Z", "loop": 132, "env_steps": 81100800, "exact_value_avg": 0.35071271657943726, "regret_dist": 0.5128679275512695, "regret_other_env": 0.8085503578186035, "regret_corner": 0.06934420019388199, "regret_row": 0.6275286674499512, "regret_any": 0.808628499507904, "regret_bot": 0.8515858054161072, "value_dist": 0.35071271657943726, "value_other_env": 0.07366445660591125, "value_corner": 0.7662851214408875, "value_row": 0.231098011136055, "value_any": 0.07362210750579834, "value_bot": 0.007040849886834621, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00132.png", "entropy": 0.7130469679832458} +{"ts": "2026-03-20T17:25:25.780594Z", "loop": 133, "env_steps": 81715200, "exact_value_avg": 0.3506726026535034, "regret_dist": 0.5129081010818481, "regret_other_env": 0.8085651993751526, "regret_corner": 0.06942248344421387, "regret_row": 0.6289905309677124, "regret_any": 0.8086432814598083, "regret_bot": 0.8514958620071411, "value_dist": 0.3506726026535034, "value_other_env": 0.07364973425865173, "value_corner": 0.7662068605422974, "value_row": 0.22963611781597137, "value_any": 0.07360740005970001, "value_bot": 0.0071307020261883736, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00133.png", "entropy": 0.7127362489700317} +{"ts": "2026-03-20T17:25:26.667898Z", "loop": 134, "env_steps": 82329600, "exact_value_avg": 0.35066550970077515, "regret_dist": 0.5129151344299316, "regret_other_env": 0.8085731267929077, "regret_corner": 0.06942816078662872, "regret_row": 0.6293163299560547, "regret_any": 0.8086512088775635, "regret_bot": 0.851477861404419, "value_dist": 0.35066550970077515, "value_other_env": 0.07364170998334885, "value_corner": 0.7662011981010437, "value_row": 0.2293102741241455, "value_any": 0.07359939068555832, "value_bot": 0.007148816715925932, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00134.png", "entropy": 0.7125478982925415} +{"ts": "2026-03-20T17:25:27.555482Z", "loop": 135, "env_steps": 82944000, "exact_value_avg": 0.35063454508781433, "regret_dist": 0.5129461288452148, "regret_other_env": 0.808584451675415, "regret_corner": 0.06948863714933395, "regret_row": 0.6302587985992432, "regret_any": 0.8086625337600708, "regret_bot": 0.8514198660850525, "value_dist": 0.35063454508781433, "value_other_env": 0.07363047450780869, "value_corner": 0.7661406397819519, "value_row": 0.22836783528327942, "value_any": 0.07358815521001816, "value_bot": 0.007206847425550222, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00135.png", "entropy": 0.7123141288757324} +{"ts": "2026-03-20T17:25:28.443511Z", "loop": 136, "env_steps": 83558400, "exact_value_avg": 0.35061711072921753, "regret_dist": 0.5129635334014893, "regret_other_env": 0.8085938692092896, "regret_corner": 0.06951801478862762, "regret_row": 0.6307755708694458, "regret_any": 0.8086719512939453, "regret_bot": 0.8513891696929932, "value_dist": 0.35061711072921753, "value_other_env": 0.07362094521522522, "value_corner": 0.7661113142967224, "value_row": 0.22785112261772156, "value_any": 0.07357864081859589, "value_bot": 0.007237396668642759, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00136.png", "entropy": 0.7120910286903381} +{"ts": "2026-03-20T17:25:29.332785Z", "loop": 137, "env_steps": 84172800, "exact_value_avg": 0.3506103456020355, "regret_dist": 0.5129703283309937, "regret_other_env": 0.8085969686508179, "regret_corner": 0.06953035295009613, "regret_row": 0.6309174299240112, "regret_any": 0.8086750507354736, "regret_bot": 0.8513814806938171, "value_dist": 0.3506103456020355, "value_other_env": 0.07361789792776108, "value_corner": 0.7660989761352539, "value_row": 0.22770926356315613, "value_any": 0.07357559353113174, "value_bot": 0.007245121523737907, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00137.png", "entropy": 0.7120514512062073} +{"ts": "2026-03-20T17:25:30.220689Z", "loop": 138, "env_steps": 84787200, "exact_value_avg": 0.35062238574028015, "regret_dist": 0.512958288192749, "regret_other_env": 0.808600664138794, "regret_corner": 0.06949465721845627, "regret_row": 0.630682110786438, "regret_any": 0.8086786270141602, "regret_bot": 0.851398766040802, "value_dist": 0.35062238574028015, "value_other_env": 0.07361418753862381, "value_corner": 0.7661346793174744, "value_row": 0.227944478392601, "value_any": 0.07357188314199448, "value_bot": 0.007227846886962652, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00138.png", "entropy": 0.7119821310043335} +{"ts": "2026-03-20T17:25:31.108421Z", "loop": 139, "env_steps": 85401600, "exact_value_avg": 0.35064437985420227, "regret_dist": 0.5129362940788269, "regret_other_env": 0.8086033463478088, "regret_corner": 0.06943567842245102, "regret_row": 0.6303115487098694, "regret_any": 0.8086814284324646, "regret_bot": 0.8514236807823181, "value_dist": 0.35064437985420227, "value_other_env": 0.07361148297786713, "value_corner": 0.766193687915802, "value_row": 0.22831504046916962, "value_any": 0.07356919348239899, "value_bot": 0.007202981039881706, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00139.png", "entropy": 0.7118986248970032} +{"ts": "2026-03-20T17:25:31.997253Z", "loop": 140, "env_steps": 86016000, "exact_value_avg": 0.3506390452384949, "regret_dist": 0.5129416584968567, "regret_other_env": 0.8086071610450745, "regret_corner": 0.06944338232278824, "regret_row": 0.6304091215133667, "regret_any": 0.8086852431297302, "regret_bot": 0.8514191508293152, "value_dist": 0.3506390452384949, "value_other_env": 0.07360770553350449, "value_corner": 0.766185998916626, "value_row": 0.2282174974679947, "value_any": 0.07356542348861694, "value_bot": 0.007207478862255812, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00140.png", "entropy": 0.7118152379989624} +{"ts": "2026-03-20T17:25:32.886041Z", "loop": 141, "env_steps": 86630400, "exact_value_avg": 0.35061362385749817, "regret_dist": 0.512967050075531, "regret_other_env": 0.8086123466491699, "regret_corner": 0.06949905306100845, "regret_row": 0.6310362815856934, "regret_any": 0.8086903691291809, "regret_bot": 0.8513787388801575, "value_dist": 0.35061362385749817, "value_other_env": 0.07360247522592545, "value_corner": 0.766130268573761, "value_row": 0.2275903820991516, "value_any": 0.0735602006316185, "value_bot": 0.0072479164227843285, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00141.png", "entropy": 0.7117008566856384} +{"ts": "2026-03-20T17:25:33.775512Z", "loop": 142, "env_steps": 87244800, "exact_value_avg": 0.3506110906600952, "regret_dist": 0.5129696130752563, "regret_other_env": 0.8086163997650146, "regret_corner": 0.06949940323829651, "regret_row": 0.6311488747596741, "regret_any": 0.8086944222450256, "regret_bot": 0.8513725399971008, "value_dist": 0.3506110906600952, "value_other_env": 0.07359851151704788, "value_corner": 0.7661299109458923, "value_row": 0.2274777591228485, "value_any": 0.07355624437332153, "value_bot": 0.007254108786582947, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00142.png", "entropy": 0.7115700840950012} +{"ts": "2026-03-20T17:25:34.664800Z", "loop": 143, "env_steps": 87859200, "exact_value_avg": 0.3506338894367218, "regret_dist": 0.5129467844963074, "regret_other_env": 0.8086175322532654, "regret_corner": 0.06944065541028976, "regret_row": 0.6306837201118469, "regret_any": 0.8086955547332764, "regret_bot": 0.8514053821563721, "value_dist": 0.3506338894367218, "value_other_env": 0.07359734922647476, "value_corner": 0.7661887407302856, "value_row": 0.22794294357299805, "value_any": 0.07355508208274841, "value_bot": 0.007221278268843889, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00143.png", "entropy": 0.7115659117698669} +{"ts": "2026-03-20T17:25:35.553403Z", "loop": 144, "env_steps": 88473600, "exact_value_avg": 0.3506466746330261, "regret_dist": 0.5129339694976807, "regret_other_env": 0.8086175918579102, "regret_corner": 0.06940856575965881, "regret_row": 0.6304061412811279, "regret_any": 0.8086956143379211, "regret_bot": 0.8514247536659241, "value_dist": 0.3506466746330261, "value_other_env": 0.07359729707241058, "value_corner": 0.76622074842453, "value_row": 0.22822052240371704, "value_any": 0.07355502247810364, "value_bot": 0.007201882544904947, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00144.png", "entropy": 0.7115947008132935} +{"ts": "2026-03-20T17:25:36.442567Z", "loop": 145, "env_steps": 89088000, "exact_value_avg": 0.3506879508495331, "regret_dist": 0.5128926634788513, "regret_other_env": 0.8086040019989014, "regret_corner": 0.06932570785284042, "regret_row": 0.6291850209236145, "regret_any": 0.8086820244789124, "regret_bot": 0.8515018224716187, "value_dist": 0.3506879508495331, "value_other_env": 0.07361085712909698, "value_corner": 0.7663035988807678, "value_row": 0.22944161295890808, "value_any": 0.07356856763362885, "value_bot": 0.007124793715775013, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00145.png", "entropy": 0.7119390964508057} +{"ts": "2026-03-20T17:25:37.332842Z", "loop": 146, "env_steps": 89702400, "exact_value_avg": 0.35072198510169983, "regret_dist": 0.5128586888313293, "regret_other_env": 0.8085920214653015, "regret_corner": 0.06925872713327408, "regret_row": 0.6279407739639282, "regret_any": 0.8086700439453125, "regret_bot": 0.8515796065330505, "value_dist": 0.35072198510169983, "value_other_env": 0.07362289726734161, "value_corner": 0.7663705945014954, "value_row": 0.23068583011627197, "value_any": 0.07358059287071228, "value_bot": 0.00704709067940712, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00146.png", "entropy": 0.7121788263320923} +{"ts": "2026-03-20T17:25:38.223130Z", "loop": 147, "env_steps": 90316800, "exact_value_avg": 0.35075390338897705, "regret_dist": 0.5128267407417297, "regret_other_env": 0.8085818290710449, "regret_corner": 0.06919410079717636, "regret_row": 0.6260512471199036, "regret_any": 0.8086599111557007, "regret_bot": 0.8516975045204163, "value_dist": 0.35075390338897705, "value_other_env": 0.07363306730985641, "value_corner": 0.7664352059364319, "value_row": 0.2325754016637802, "value_any": 0.07359074056148529, "value_bot": 0.006929181516170502, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00147.png", "entropy": 0.7123414278030396} +{"ts": "2026-03-20T17:25:39.112774Z", "loop": 148, "env_steps": 90931200, "exact_value_avg": 0.3507597744464874, "regret_dist": 0.5128209590911865, "regret_other_env": 0.8085682988166809, "regret_corner": 0.06919986754655838, "regret_row": 0.623660683631897, "regret_any": 0.8086463212966919, "regret_bot": 0.851841926574707, "value_dist": 0.3507597744464874, "value_other_env": 0.07364663481712341, "value_corner": 0.7664294242858887, "value_row": 0.2349659502506256, "value_any": 0.0736042782664299, "value_bot": 0.0067847236059606075, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00148.png", "entropy": 0.7124730944633484} +{"ts": "2026-03-20T17:25:40.003403Z", "loop": 149, "env_steps": 91545600, "exact_value_avg": 0.3507528007030487, "regret_dist": 0.5128278732299805, "regret_other_env": 0.8085607290267944, "regret_corner": 0.06922858208417892, "regret_row": 0.6225557327270508, "regret_any": 0.8086388111114502, "regret_bot": 0.8519077897071838, "value_dist": 0.3507528007030487, "value_other_env": 0.07365413755178452, "value_corner": 0.7664007544517517, "value_row": 0.23607084155082703, "value_any": 0.07361176609992981, "value_bot": 0.006718876771628857, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00149.png", "entropy": 0.7125046253204346} +{"ts": "2026-03-20T17:25:40.894008Z", "loop": 150, "env_steps": 92160000, "exact_value_avg": 0.3507152199745178, "regret_dist": 0.5128654837608337, "regret_other_env": 0.8085576295852661, "regret_corner": 0.06932719796895981, "regret_row": 0.620482861995697, "regret_any": 0.8086357712745667, "regret_bot": 0.8520313501358032, "value_dist": 0.3507152199745178, "value_other_env": 0.07365722954273224, "value_corner": 0.7663021683692932, "value_row": 0.23814377188682556, "value_any": 0.07361484318971634, "value_bot": 0.006595264654606581, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00150.png", "entropy": 0.712295413017273} +{"ts": "2026-03-20T17:25:41.783539Z", "loop": 151, "env_steps": 92774400, "exact_value_avg": 0.35068774223327637, "regret_dist": 0.5128929018974304, "regret_other_env": 0.8085538148880005, "regret_corner": 0.06940155476331711, "regret_row": 0.6195056438446045, "regret_any": 0.8086318969726562, "regret_bot": 0.8520875573158264, "value_dist": 0.35068774223327637, "value_other_env": 0.07366108149290085, "value_corner": 0.7662277817726135, "value_row": 0.2391209900379181, "value_any": 0.07361868768930435, "value_bot": 0.006539028137922287, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00151.png", "entropy": 0.7122126221656799} +{"ts": "2026-03-20T17:25:42.672500Z", "loop": 152, "env_steps": 93388800, "exact_value_avg": 0.35068443417549133, "regret_dist": 0.5128962397575378, "regret_other_env": 0.8085533380508423, "regret_corner": 0.06941057741641998, "regret_row": 0.6193263530731201, "regret_any": 0.808631420135498, "regret_bot": 0.8520971536636353, "value_dist": 0.35068443417549133, "value_other_env": 0.07366155833005905, "value_corner": 0.7662187218666077, "value_row": 0.23930029571056366, "value_any": 0.07361917942762375, "value_bot": 0.0065294052474200726, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00152.png", "entropy": 0.712147057056427} +{"ts": "2026-03-20T17:25:43.561691Z", "loop": 153, "env_steps": 94003200, "exact_value_avg": 0.3506918251514435, "regret_dist": 0.5128888487815857, "regret_other_env": 0.8085541129112244, "regret_corner": 0.06939084082841873, "regret_row": 0.61942458152771, "regret_any": 0.8086322546005249, "regret_bot": 0.8520910739898682, "value_dist": 0.3506918251514435, "value_other_env": 0.0736607164144516, "value_corner": 0.7662385106086731, "value_row": 0.239202082157135, "value_any": 0.0736183300614357, "value_bot": 0.0065355501137673855, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00153.png", "entropy": 0.7120727896690369} +{"ts": "2026-03-20T17:25:44.451088Z", "loop": 154, "env_steps": 94617600, "exact_value_avg": 0.3507155478000641, "regret_dist": 0.5128651261329651, "regret_other_env": 0.8085587024688721, "regret_corner": 0.06932475417852402, "regret_row": 0.6202751994132996, "regret_any": 0.8086368441581726, "regret_bot": 0.8520416617393494, "value_dist": 0.3507155478000641, "value_other_env": 0.07365617156028748, "value_corner": 0.7663045525550842, "value_row": 0.23835143446922302, "value_any": 0.07361380010843277, "value_bot": 0.0065849339589476585, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00154.png", "entropy": 0.7120530009269714} +{"ts": "2026-03-20T17:25:45.342280Z", "loop": 155, "env_steps": 95232000, "exact_value_avg": 0.350740909576416, "regret_dist": 0.5128397345542908, "regret_other_env": 0.8085634708404541, "regret_corner": 0.06925415992736816, "regret_row": 0.6214444041252136, "regret_any": 0.8086416721343994, "regret_bot": 0.8519718050956726, "value_dist": 0.350740909576416, "value_other_env": 0.07365137338638306, "value_corner": 0.7663751840591431, "value_row": 0.23718217015266418, "value_any": 0.07360900938510895, "value_bot": 0.006654825992882252, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00155.png", "entropy": 0.7120823860168457} +{"ts": "2026-03-20T17:25:46.232518Z", "loop": 156, "env_steps": 95846400, "exact_value_avg": 0.3507649600505829, "regret_dist": 0.5128157734870911, "regret_other_env": 0.808567225933075, "regret_corner": 0.06918850541114807, "regret_row": 0.6234564185142517, "regret_any": 0.8086453080177307, "regret_bot": 0.8518503308296204, "value_dist": 0.3507649600505829, "value_other_env": 0.07364771515130997, "value_corner": 0.7664408087730408, "value_row": 0.2351701855659485, "value_any": 0.07360535115003586, "value_bot": 0.006776254624128342, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00156.png", "entropy": 0.7122129201889038} +{"ts": "2026-03-20T17:25:47.122390Z", "loop": 157, "env_steps": 96460800, "exact_value_avg": 0.3507646322250366, "regret_dist": 0.5128160119056702, "regret_other_env": 0.8085639476776123, "regret_corner": 0.06919411569833755, "regret_row": 0.623099684715271, "regret_any": 0.8086420893669128, "regret_bot": 0.8518707752227783, "value_dist": 0.3507646322250366, "value_other_env": 0.07365090399980545, "value_corner": 0.7664351463317871, "value_row": 0.2355269342660904, "value_any": 0.07360853254795074, "value_bot": 0.006755818612873554, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00157.png", "entropy": 0.7122575044631958} +{"ts": "2026-03-20T17:25:48.011230Z", "loop": 158, "env_steps": 97075200, "exact_value_avg": 0.35077375173568726, "regret_dist": 0.5128070116043091, "regret_other_env": 0.8085708618164062, "regret_corner": 0.06916113197803497, "regret_row": 0.6240046620368958, "regret_any": 0.808648943901062, "regret_bot": 0.8518160581588745, "value_dist": 0.35077375173568726, "value_other_env": 0.07364404946565628, "value_corner": 0.7664682269096375, "value_row": 0.23462192714214325, "value_any": 0.07360169291496277, "value_bot": 0.006810549180954695, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00158.png", "entropy": 0.7121633887290955} +{"ts": "2026-03-20T17:25:48.899893Z", "loop": 159, "env_steps": 97689600, "exact_value_avg": 0.35075926780700684, "regret_dist": 0.5128213763237, "regret_other_env": 0.8085813522338867, "regret_corner": 0.0691814050078392, "regret_row": 0.6264113187789917, "regret_any": 0.8086594343185425, "regret_bot": 0.8516698479652405, "value_dist": 0.35075926780700684, "value_other_env": 0.07363352179527283, "value_corner": 0.7664478421211243, "value_row": 0.23221531510353088, "value_any": 0.0735911950469017, "value_bot": 0.006956733297556639, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00159.png", "entropy": 0.7121543288230896} +{"ts": "2026-03-20T17:25:49.788937Z", "loop": 160, "env_steps": 98304000, "exact_value_avg": 0.35071077942848206, "regret_dist": 0.5128698945045471, "regret_other_env": 0.8085960149765015, "regret_corner": 0.0692806988954544, "regret_row": 0.6286457180976868, "regret_any": 0.8086740970611572, "regret_bot": 0.8515329957008362, "value_dist": 0.35071077942848206, "value_other_env": 0.0736188292503357, "value_corner": 0.766348659992218, "value_row": 0.229980930685997, "value_any": 0.07357653975486755, "value_bot": 0.0070936670526862144, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00160.png", "entropy": 0.7119771242141724} +{"ts": "2026-03-20T17:25:50.677566Z", "loop": 161, "env_steps": 98918400, "exact_value_avg": 0.3506636619567871, "regret_dist": 0.5129169821739197, "regret_other_env": 0.8086099624633789, "regret_corner": 0.06937753409147263, "regret_row": 0.63017338514328, "regret_any": 0.8086879849433899, "regret_bot": 0.8514389395713806, "value_dist": 0.3506636619567871, "value_other_env": 0.07360485941171646, "value_corner": 0.766251802444458, "value_row": 0.22845318913459778, "value_any": 0.07356258481740952, "value_bot": 0.007187707349658012, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00161.png", "entropy": 0.711707592010498} +{"ts": "2026-03-20T17:25:51.567481Z", "loop": 162, "env_steps": 99532800, "exact_value_avg": 0.35060063004493713, "regret_dist": 0.512980043888092, "regret_other_env": 0.8086233139038086, "regret_corner": 0.06951513141393661, "regret_row": 0.631659209728241, "regret_any": 0.8087012767791748, "regret_bot": 0.8513455390930176, "value_dist": 0.35060063004493713, "value_other_env": 0.07359156012535095, "value_corner": 0.7661142349243164, "value_row": 0.22696740925312042, "value_any": 0.0735493004322052, "value_bot": 0.007281036581844091, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00162.png", "entropy": 0.711376428604126} +{"ts": "2026-03-20T17:25:52.457179Z", "loop": 163, "env_steps": 100147200, "exact_value_avg": 0.35053572058677673, "regret_dist": 0.5130450129508972, "regret_other_env": 0.8086433410644531, "regret_corner": 0.06964744627475739, "regret_row": 0.6329731345176697, "regret_any": 0.8087213039398193, "regret_bot": 0.8512645363807678, "value_dist": 0.35053572058677673, "value_other_env": 0.0735715851187706, "value_corner": 0.7659818530082703, "value_row": 0.2256535291671753, "value_any": 0.07352935522794724, "value_bot": 0.007362101227045059, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00163.png", "entropy": 0.7109102606773376} +{"ts": "2026-03-20T17:25:53.345064Z", "loop": 164, "env_steps": 100761600, "exact_value_avg": 0.3504769206047058, "regret_dist": 0.5131037831306458, "regret_other_env": 0.808663547039032, "regret_corner": 0.06976409256458282, "regret_row": 0.634047269821167, "regret_any": 0.8087414503097534, "regret_bot": 0.8511987328529358, "value_dist": 0.3504769206047058, "value_other_env": 0.07355132699012756, "value_corner": 0.7658652663230896, "value_row": 0.2245793640613556, "value_any": 0.07350913435220718, "value_bot": 0.007427937816828489, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00164.png", "entropy": 0.7104046940803528} +{"ts": "2026-03-20T17:25:54.231144Z", "loop": 165, "env_steps": 101376000, "exact_value_avg": 0.35048651695251465, "regret_dist": 0.5130941867828369, "regret_other_env": 0.80866539478302, "regret_corner": 0.06973733752965927, "regret_row": 0.6339352130889893, "regret_any": 0.8087433576583862, "regret_bot": 0.8512076139450073, "value_dist": 0.35048651695251465, "value_other_env": 0.07354950904846191, "value_corner": 0.7658920288085938, "value_row": 0.22469143569469452, "value_any": 0.07350730895996094, "value_bot": 0.007418941706418991, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00165.png", "entropy": 0.7103777527809143} +{"ts": "2026-03-20T17:25:55.120625Z", "loop": 166, "env_steps": 101990400, "exact_value_avg": 0.35054296255111694, "regret_dist": 0.5130377411842346, "regret_other_env": 0.808660626411438, "regret_corner": 0.06960335373878479, "regret_row": 0.6330256462097168, "regret_any": 0.8087385296821594, "regret_bot": 0.8512687683105469, "value_dist": 0.35054296255111694, "value_other_env": 0.07355425506830215, "value_corner": 0.766025960445404, "value_row": 0.2256009876728058, "value_any": 0.07351204007863998, "value_bot": 0.007357864640653133, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00166.png", "entropy": 0.7105042338371277} +{"ts": "2026-03-20T17:25:56.008795Z", "loop": 167, "env_steps": 102604800, "exact_value_avg": 0.35058972239494324, "regret_dist": 0.5129909515380859, "regret_other_env": 0.8086569905281067, "regret_corner": 0.06949188560247421, "regret_row": 0.6322064995765686, "regret_any": 0.8087350130081177, "regret_bot": 0.8513222336769104, "value_dist": 0.35058972239494324, "value_other_env": 0.07355787605047226, "value_corner": 0.766137421131134, "value_row": 0.22642019391059875, "value_any": 0.0735156387090683, "value_bot": 0.007304417435079813, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00167.png", "entropy": 0.7105657458305359} +{"ts": "2026-03-20T17:25:56.899739Z", "loop": 168, "env_steps": 103219200, "exact_value_avg": 0.3506620526313782, "regret_dist": 0.5129185914993286, "regret_other_env": 0.8086446523666382, "regret_corner": 0.06932951509952545, "regret_row": 0.6305628418922424, "regret_any": 0.8087226152420044, "regret_bot": 0.8514276146888733, "value_dist": 0.3506620526313782, "value_other_env": 0.07357022166252136, "value_corner": 0.7662997841835022, "value_row": 0.22806382179260254, "value_any": 0.07352796941995621, "value_bot": 0.007198992185294628, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00168.png", "entropy": 0.7108842730522156} +{"ts": "2026-03-20T17:25:57.789301Z", "loop": 169, "env_steps": 103833600, "exact_value_avg": 0.35071900486946106, "regret_dist": 0.5128616690635681, "regret_other_env": 0.8086344003677368, "regret_corner": 0.0692024901509285, "regret_row": 0.6289694309234619, "regret_any": 0.8087124228477478, "regret_bot": 0.8515286445617676, "value_dist": 0.35071900486946106, "value_other_env": 0.07358044385910034, "value_corner": 0.7664268612861633, "value_row": 0.22965718805789948, "value_any": 0.07353817671537399, "value_bot": 0.007098059635609388, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00169.png", "entropy": 0.7111018896102905} +{"ts": "2026-03-20T17:25:58.679457Z", "loop": 170, "env_steps": 104448000, "exact_value_avg": 0.35073813796043396, "regret_dist": 0.5128425359725952, "regret_other_env": 0.808629035949707, "regret_corner": 0.06916274130344391, "regret_row": 0.6281969547271729, "regret_any": 0.808707058429718, "regret_bot": 0.8515763282775879, "value_dist": 0.35073813796043396, "value_other_env": 0.0735858753323555, "value_corner": 0.7664665579795837, "value_row": 0.23042966425418854, "value_any": 0.07354360073804855, "value_bot": 0.0070502981543540955, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00170.png", "entropy": 0.7111771702766418} +{"ts": "2026-03-20T17:25:59.567467Z", "loop": 171, "env_steps": 105062400, "exact_value_avg": 0.3507608473300934, "regret_dist": 0.5128198266029358, "regret_other_env": 0.8086263537406921, "regret_corner": 0.06910998374223709, "regret_row": 0.6273165941238403, "regret_any": 0.8087043762207031, "regret_bot": 0.8516319990158081, "value_dist": 0.3507608473300934, "value_other_env": 0.0735885426402092, "value_corner": 0.76651930809021, "value_row": 0.23131005465984344, "value_any": 0.07354627549648285, "value_bot": 0.006994674913585186, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00171.png", "entropy": 0.7111947536468506} +{"ts": "2026-03-20T17:26:00.457472Z", "loop": 172, "env_steps": 105676800, "exact_value_avg": 0.3507852256298065, "regret_dist": 0.5127953886985779, "regret_other_env": 0.8086140751838684, "regret_corner": 0.06906738877296448, "regret_row": 0.6247755289077759, "regret_any": 0.8086920976638794, "regret_bot": 0.8517862558364868, "value_dist": 0.3507852256298065, "value_other_env": 0.07360076904296875, "value_corner": 0.7665619254112244, "value_row": 0.2338511049747467, "value_any": 0.07355846464633942, "value_bot": 0.006840390618890524, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00172.png", "entropy": 0.7112478613853455} +{"ts": "2026-03-20T17:26:01.347989Z", "loop": 173, "env_steps": 106291200, "exact_value_avg": 0.3507569134235382, "regret_dist": 0.5128238201141357, "regret_other_env": 0.8086127638816833, "regret_corner": 0.06914040446281433, "regret_row": 0.6213770508766174, "regret_any": 0.8086907863616943, "regret_bot": 0.851991593837738, "value_dist": 0.3507569134235382, "value_other_env": 0.07360218465328217, "value_corner": 0.7664889693260193, "value_row": 0.23724962770938873, "value_any": 0.07355987280607224, "value_bot": 0.006635051686316729, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00173.png", "entropy": 0.7108901739120483} +{"ts": "2026-03-20T17:26:02.237702Z", "loop": 174, "env_steps": 106905600, "exact_value_avg": 0.35067620873451233, "regret_dist": 0.5129044651985168, "regret_other_env": 0.8086081743240356, "regret_corner": 0.06934892386198044, "regret_row": 0.6184902191162109, "regret_any": 0.8086861968040466, "regret_bot": 0.8521588444709778, "value_dist": 0.35067620873451233, "value_other_env": 0.07360672950744629, "value_corner": 0.7662804126739502, "value_row": 0.24013641476631165, "value_any": 0.07356441020965576, "value_bot": 0.006467762868851423, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00174.png", "entropy": 0.7104968428611755} +{"ts": "2026-03-20T17:26:03.126438Z", "loop": 175, "env_steps": 107520000, "exact_value_avg": 0.3504747450351715, "regret_dist": 0.5131059885025024, "regret_other_env": 0.8086108565330505, "regret_corner": 0.06984870135784149, "regret_row": 0.6145468950271606, "regret_any": 0.8086888790130615, "regret_bot": 0.8523828387260437, "value_dist": 0.3504747450351715, "value_other_env": 0.07360408455133438, "value_corner": 0.7657806873321533, "value_row": 0.24407976865768433, "value_any": 0.07356176525354385, "value_bot": 0.006243784911930561, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00175.png", "entropy": 0.7095462083816528} +{"ts": "2026-03-20T17:26:04.016052Z", "loop": 176, "env_steps": 108134400, "exact_value_avg": 0.350155234336853, "regret_dist": 0.513425350189209, "regret_other_env": 0.8086317181587219, "regret_corner": 0.07061585038900375, "regret_row": 0.6104181408882141, "regret_any": 0.8087098002433777, "regret_bot": 0.8526126742362976, "value_dist": 0.350155234336853, "value_other_env": 0.07358308881521225, "value_corner": 0.7650134563446045, "value_row": 0.24820852279663086, "value_any": 0.07354077696800232, "value_bot": 0.006014016456902027, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00176.png", "entropy": 0.7079169750213623} +{"ts": "2026-03-20T17:26:04.906896Z", "loop": 177, "env_steps": 108748800, "exact_value_avg": 0.3496429920196533, "regret_dist": 0.5139376521110535, "regret_other_env": 0.8086695671081543, "regret_corner": 0.07183977961540222, "regret_row": 0.6056650280952454, "regret_any": 0.8087476491928101, "regret_bot": 0.8528741598129272, "value_dist": 0.3496429920196533, "value_other_env": 0.07354524731636047, "value_corner": 0.7637895345687866, "value_row": 0.2529616355895996, "value_any": 0.07350298017263412, "value_bot": 0.005752511788159609, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00177.png", "entropy": 0.7053126096725464} +{"ts": "2026-03-20T17:26:05.797574Z", "loop": 178, "env_steps": 109363200, "exact_value_avg": 0.3493109941482544, "regret_dist": 0.5142697095870972, "regret_other_env": 0.8086972832679749, "regret_corner": 0.07262826710939407, "regret_row": 0.6031509637832642, "regret_any": 0.8087752461433411, "regret_bot": 0.853009819984436, "value_dist": 0.3493109941482544, "value_other_env": 0.07351761311292648, "value_corner": 0.763001024723053, "value_row": 0.2554756700992584, "value_any": 0.07347538322210312, "value_bot": 0.005616751499474049, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00178.png", "entropy": 0.7035959362983704} +{"ts": "2026-03-20T17:26:06.688038Z", "loop": 179, "env_steps": 109977600, "exact_value_avg": 0.3491072654724121, "regret_dist": 0.5144733786582947, "regret_other_env": 0.8087120056152344, "regret_corner": 0.07311537116765976, "regret_row": 0.6017824411392212, "regret_any": 0.8087900280952454, "regret_bot": 0.8530800938606262, "value_dist": 0.3491072654724121, "value_other_env": 0.07350283116102219, "value_corner": 0.7625139355659485, "value_row": 0.2568441927433014, "value_any": 0.07346061617136002, "value_bot": 0.005546503700315952, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00179.png", "entropy": 0.7026301026344299} +{"ts": "2026-03-20T17:26:07.579518Z", "loop": 180, "env_steps": 110592000, "exact_value_avg": 0.34905940294265747, "regret_dist": 0.5145213007926941, "regret_other_env": 0.8087186217308044, "regret_corner": 0.0732252299785614, "regret_row": 0.6014841794967651, "regret_any": 0.8087964653968811, "regret_bot": 0.8530953526496887, "value_dist": 0.34905940294265747, "value_other_env": 0.0734962597489357, "value_corner": 0.7624040842056274, "value_row": 0.25714239478111267, "value_any": 0.07345404475927353, "value_bot": 0.005531244445592165, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00180.png", "entropy": 0.7023378610610962} +{"ts": "2026-03-20T17:26:08.471497Z", "loop": 181, "env_steps": 111206400, "exact_value_avg": 0.3490033745765686, "regret_dist": 0.514577329158783, "regret_other_env": 0.8087208271026611, "regret_corner": 0.07336203753948212, "regret_row": 0.6011156439781189, "regret_any": 0.8087987303733826, "regret_bot": 0.8531134128570557, "value_dist": 0.3490033745765686, "value_other_env": 0.07349404692649841, "value_corner": 0.7622672915458679, "value_row": 0.2575110197067261, "value_any": 0.07345183193683624, "value_bot": 0.0055132173001766205, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00181.png", "entropy": 0.7020719051361084} +{"ts": "2026-03-20T17:26:09.361626Z", "loop": 182, "env_steps": 111820800, "exact_value_avg": 0.34932830929756165, "regret_dist": 0.5142523646354675, "regret_other_env": 0.8086994290351868, "regret_corner": 0.07258175313472748, "regret_row": 0.6032882928848267, "regret_any": 0.808777391910553, "regret_bot": 0.8529990911483765, "value_dist": 0.34932830929756165, "value_other_env": 0.07351545989513397, "value_corner": 0.7630475759506226, "value_row": 0.25533831119537354, "value_any": 0.07347323000431061, "value_bot": 0.005627567879855633, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00182.png", "entropy": 0.7034780979156494} +{"ts": "2026-03-20T17:26:10.251699Z", "loop": 183, "env_steps": 112435200, "exact_value_avg": 0.3498864769935608, "regret_dist": 0.5136942267417908, "regret_other_env": 0.8086637258529663, "regret_corner": 0.0712399110198021, "regret_row": 0.6077600717544556, "regret_any": 0.8087417483329773, "regret_bot": 0.852759063243866, "value_dist": 0.3498864769935608, "value_other_env": 0.07355116307735443, "value_corner": 0.7643894553184509, "value_row": 0.25086668133735657, "value_any": 0.07350888103246689, "value_bot": 0.00586761673912406, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00183.png", "entropy": 0.706096351146698} +{"ts": "2026-03-20T17:26:11.142932Z", "loop": 184, "env_steps": 113049600, "exact_value_avg": 0.35034993290901184, "regret_dist": 0.5132307410240173, "regret_other_env": 0.808638334274292, "regret_corner": 0.07011930644512177, "regret_row": 0.6128175854682922, "regret_any": 0.8087164163589478, "regret_bot": 0.8524819612503052, "value_dist": 0.35034993290901184, "value_other_env": 0.07357655465602875, "value_corner": 0.7655099630355835, "value_row": 0.24580904841423035, "value_any": 0.07353425025939941, "value_bot": 0.006144676823168993, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00184.png", "entropy": 0.7083331346511841} +{"ts": "2026-03-20T17:26:12.031624Z", "loop": 185, "env_steps": 113664000, "exact_value_avg": 0.3506561815738678, "regret_dist": 0.5129244327545166, "regret_other_env": 0.8086296319961548, "regret_corner": 0.06936667859554291, "regret_row": 0.6180418133735657, "regret_any": 0.8087077140808105, "regret_bot": 0.8521866798400879, "value_dist": 0.3506561815738678, "value_other_env": 0.07358522713184357, "value_corner": 0.7662626504898071, "value_row": 0.2405848354101181, "value_any": 0.07354290783405304, "value_bot": 0.006439970340579748, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00185.png", "entropy": 0.7097805738449097} +{"ts": "2026-03-20T17:26:12.920490Z", "loop": 186, "env_steps": 114278400, "exact_value_avg": 0.3507870137691498, "regret_dist": 0.5127936601638794, "regret_other_env": 0.8086379170417786, "regret_corner": 0.06902722269296646, "regret_row": 0.6232324838638306, "regret_any": 0.8087159395217896, "regret_bot": 0.8518831729888916, "value_dist": 0.3507870137691498, "value_other_env": 0.07357697188854218, "value_corner": 0.766602098941803, "value_row": 0.23539412021636963, "value_any": 0.07353468984365463, "value_bot": 0.006743442267179489, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00186.png", "entropy": 0.7104546427726746} +{"ts": "2026-03-20T17:26:13.810909Z", "loop": 187, "env_steps": 114892800, "exact_value_avg": 0.3507803976535797, "regret_dist": 0.5128002762794495, "regret_other_env": 0.8086487054824829, "regret_corner": 0.06902763247489929, "regret_row": 0.6265506148338318, "regret_any": 0.8087266683578491, "regret_bot": 0.8516834378242493, "value_dist": 0.3507803976535797, "value_other_env": 0.07356617599725723, "value_corner": 0.7666016817092896, "value_row": 0.2320760041475296, "value_any": 0.07352390885353088, "value_bot": 0.006943163461983204, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00187.png", "entropy": 0.7105229496955872} +{"ts": "2026-03-20T17:26:14.702100Z", "loop": 188, "env_steps": 115507200, "exact_value_avg": 0.35071060061454773, "regret_dist": 0.5128700733184814, "regret_other_env": 0.8086613416671753, "regret_corner": 0.06918316334486008, "regret_row": 0.6294739246368408, "regret_any": 0.8087393045425415, "regret_bot": 0.8515023589134216, "value_dist": 0.35071060061454773, "value_other_env": 0.07355351746082306, "value_corner": 0.7664461731910706, "value_row": 0.22915269434452057, "value_any": 0.0735112652182579, "value_bot": 0.007124301046133041, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00188.png", "entropy": 0.7103744745254517} +{"ts": "2026-03-20T17:26:15.591585Z", "loop": 189, "env_steps": 116121600, "exact_value_avg": 0.3505653142929077, "regret_dist": 0.5130154490470886, "regret_other_env": 0.8086800575256348, "regret_corner": 0.06951840221881866, "regret_row": 0.6328321695327759, "regret_any": 0.8087579607963562, "regret_bot": 0.8512861728668213, "value_dist": 0.3505653142929077, "value_other_env": 0.07353487610816956, "value_corner": 0.766110897064209, "value_row": 0.2257944941520691, "value_any": 0.07349266856908798, "value_bot": 0.00734053086489439, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00189.png", "entropy": 0.7099252939224243} +{"ts": "2026-03-20T17:26:16.480276Z", "loop": 190, "env_steps": 116736000, "exact_value_avg": 0.35038450360298157, "regret_dist": 0.5131962299346924, "regret_other_env": 0.8087059855461121, "regret_corner": 0.06993144750595093, "regret_row": 0.6357194185256958, "regret_any": 0.8087838292121887, "regret_bot": 0.8510974049568176, "value_dist": 0.35038450360298157, "value_other_env": 0.07350891083478928, "value_corner": 0.7656978964805603, "value_row": 0.222907155752182, "value_any": 0.07346674054861069, "value_bot": 0.0075292265973985195, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00190.png", "entropy": 0.7091098427772522} +{"ts": "2026-03-20T17:26:17.368374Z", "loop": 191, "env_steps": 117350400, "exact_value_avg": 0.35027387738227844, "regret_dist": 0.5133067965507507, "regret_other_env": 0.8087265491485596, "regret_corner": 0.07017706334590912, "regret_row": 0.637102484703064, "regret_any": 0.808804452419281, "regret_bot": 0.8510075211524963, "value_dist": 0.35027387738227844, "value_other_env": 0.07348828762769699, "value_corner": 0.7654522061347961, "value_row": 0.22152408957481384, "value_any": 0.07344614714384079, "value_bot": 0.007619145326316357, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00191.png", "entropy": 0.7084630131721497} +{"ts": "2026-03-20T17:26:18.257565Z", "loop": 192, "env_steps": 117964800, "exact_value_avg": 0.35029053688049316, "regret_dist": 0.5132901668548584, "regret_other_env": 0.8087378740310669, "regret_corner": 0.07011852413415909, "regret_row": 0.6370180249214172, "regret_any": 0.8088157176971436, "regret_bot": 0.8510183095932007, "value_dist": 0.35029053688049316, "value_other_env": 0.07347699999809265, "value_corner": 0.7655108571052551, "value_row": 0.22160860896110535, "value_any": 0.07343485951423645, "value_bot": 0.007608226966112852, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00192.png", "entropy": 0.7081843614578247} +{"ts": "2026-03-20T17:26:19.146814Z", "loop": 193, "env_steps": 118579200, "exact_value_avg": 0.35034334659576416, "regret_dist": 0.5132372975349426, "regret_other_env": 0.8087460994720459, "regret_corner": 0.06997408717870712, "regret_row": 0.6365068554878235, "regret_any": 0.8088239431381226, "regret_bot": 0.8510593771934509, "value_dist": 0.35034334659576416, "value_other_env": 0.07346879690885544, "value_corner": 0.7656551599502563, "value_row": 0.2221197783946991, "value_any": 0.07342668622732162, "value_bot": 0.0075672464445233345, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00193.png", "entropy": 0.7080752849578857} +{"ts": "2026-03-20T17:26:20.037850Z", "loop": 194, "env_steps": 119193600, "exact_value_avg": 0.3504643142223358, "regret_dist": 0.5131163597106934, "regret_other_env": 0.8087482452392578, "regret_corner": 0.06966855376958847, "regret_row": 0.6349602937698364, "regret_any": 0.8088261485099792, "regret_bot": 0.8511688709259033, "value_dist": 0.3504643142223358, "value_other_env": 0.07346662878990173, "value_corner": 0.7659608125686646, "value_row": 0.22366636991500854, "value_any": 0.07342450320720673, "value_bot": 0.007457714062184095, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00194.png", "entropy": 0.7082074284553528} +{"ts": "2026-03-20T17:26:20.927443Z", "loop": 195, "env_steps": 119808000, "exact_value_avg": 0.3506508767604828, "regret_dist": 0.5129297971725464, "regret_other_env": 0.8087329268455505, "regret_corner": 0.06922504305839539, "regret_row": 0.6316423416137695, "regret_any": 0.8088107705116272, "regret_bot": 0.8513903021812439, "value_dist": 0.3506508767604828, "value_other_env": 0.07348193973302841, "value_corner": 0.7664042711257935, "value_row": 0.22698427736759186, "value_any": 0.07343978434801102, "value_bot": 0.007236317731440067, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00195.png", "entropy": 0.70870441198349} +{"ts": "2026-03-20T17:26:21.817898Z", "loop": 196, "env_steps": 120422400, "exact_value_avg": 0.3507964611053467, "regret_dist": 0.5127841830253601, "regret_other_env": 0.808718204498291, "regret_corner": 0.06888307631015778, "regret_row": 0.6268199682235718, "regret_any": 0.808796226978302, "regret_bot": 0.8516982197761536, "value_dist": 0.3507964611053467, "value_other_env": 0.07349660247564316, "value_corner": 0.7667462229728699, "value_row": 0.2318067103624344, "value_any": 0.07345440983772278, "value_bot": 0.006928391754627228, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00196.png", "entropy": 0.7088882327079773} +{"ts": "2026-03-20T17:26:22.708630Z", "loop": 197, "env_steps": 121036800, "exact_value_avg": 0.35079067945480347, "regret_dist": 0.5127900242805481, "regret_other_env": 0.8087195158004761, "regret_corner": 0.06889574229717255, "regret_row": 0.6221991777420044, "regret_any": 0.8087974190711975, "regret_bot": 0.8519810438156128, "value_dist": 0.35079067945480347, "value_other_env": 0.07349538058042526, "value_corner": 0.7667335867881775, "value_row": 0.23642748594284058, "value_any": 0.07345318049192429, "value_bot": 0.006645546294748783, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00197.png", "entropy": 0.7084020972251892} +{"ts": "2026-03-20T17:26:23.600020Z", "loop": 198, "env_steps": 121651200, "exact_value_avg": 0.3506695032119751, "regret_dist": 0.5129111409187317, "regret_other_env": 0.8087273240089417, "regret_corner": 0.06918686628341675, "regret_row": 0.6180636882781982, "regret_any": 0.8088052868843079, "regret_bot": 0.8522250056266785, "value_dist": 0.3506695032119751, "value_other_env": 0.0734875425696373, "value_corner": 0.7664424180984497, "value_row": 0.24056294560432434, "value_any": 0.07344533503055573, "value_bot": 0.006401646416634321, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00198.png", "entropy": 0.7074443101882935} +{"ts": "2026-03-20T17:26:24.489460Z", "loop": 199, "env_steps": 122265600, "exact_value_avg": 0.35049113631248474, "regret_dist": 0.5130895376205444, "regret_other_env": 0.8087435364723206, "regret_corner": 0.06960853189229965, "regret_row": 0.6147425770759583, "regret_any": 0.808821439743042, "regret_bot": 0.8524149060249329, "value_dist": 0.35049113631248474, "value_other_env": 0.07347137480974197, "value_corner": 0.7660207748413086, "value_row": 0.2438841015100479, "value_any": 0.0734291821718216, "value_bot": 0.0062116533517837524, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00199.png", "entropy": 0.7061967849731445} +{"ts": "2026-03-20T17:26:25.377973Z", "loop": 200, "env_steps": 122880000, "exact_value_avg": 0.35030892491340637, "regret_dist": 0.5132717490196228, "regret_other_env": 0.808761715888977, "regret_corner": 0.07003676146268845, "regret_row": 0.6122218370437622, "regret_any": 0.8088396787643433, "regret_bot": 0.8525567650794983, "value_dist": 0.35030892491340637, "value_other_env": 0.0734531357884407, "value_corner": 0.7655925750732422, "value_row": 0.24640484154224396, "value_any": 0.07341095060110092, "value_bot": 0.0060698795132339, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00200.png", "entropy": 0.7049885392189026} +{"ts": "2026-03-20T17:26:26.265908Z", "loop": 201, "env_steps": 123494400, "exact_value_avg": 0.35009539127349854, "regret_dist": 0.513485312461853, "regret_other_env": 0.8087878227233887, "regret_corner": 0.0705314576625824, "regret_row": 0.6098970770835876, "regret_any": 0.8088657259941101, "regret_bot": 0.8526860475540161, "value_dist": 0.35009539127349854, "value_other_env": 0.07342706620693207, "value_corner": 0.7650978565216064, "value_row": 0.24872958660125732, "value_any": 0.07338492572307587, "value_bot": 0.005940531846135855, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00201.png", "entropy": 0.7035598754882812} +{"ts": "2026-03-20T17:26:27.154834Z", "loop": 202, "env_steps": 124108800, "exact_value_avg": 0.35000085830688477, "regret_dist": 0.513579785823822, "regret_other_env": 0.8088047504425049, "regret_corner": 0.07074230909347534, "regret_row": 0.6089600324630737, "regret_any": 0.8088825941085815, "regret_bot": 0.8527396321296692, "value_dist": 0.35000085830688477, "value_other_env": 0.07341008633375168, "value_corner": 0.7648870348930359, "value_row": 0.24966657161712646, "value_any": 0.07336796820163727, "value_bot": 0.005887026432901621, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00202.png", "entropy": 0.7027497887611389} +{"ts": "2026-03-20T17:26:28.045999Z", "loop": 203, "env_steps": 124723200, "exact_value_avg": 0.3498472571372986, "regret_dist": 0.513733446598053, "regret_other_env": 0.8088258504867554, "regret_corner": 0.0710948035120964, "regret_row": 0.6075944304466248, "regret_any": 0.8089036345481873, "regret_bot": 0.8528151512145996, "value_dist": 0.3498472571372986, "value_other_env": 0.07338906824588776, "value_corner": 0.7645345330238342, "value_row": 0.2510322332382202, "value_any": 0.07334695756435394, "value_bot": 0.005811486858874559, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00203.png", "entropy": 0.7017350792884827} +{"ts": "2026-03-20T17:26:28.935388Z", "loop": 204, "env_steps": 125337600, "exact_value_avg": 0.3498256504535675, "regret_dist": 0.5137550234794617, "regret_other_env": 0.8088358044624329, "regret_corner": 0.07113382965326309, "regret_row": 0.6073856353759766, "regret_any": 0.8089136481285095, "regret_bot": 0.8528280258178711, "value_dist": 0.3498256504535675, "value_other_env": 0.07337908446788788, "value_corner": 0.7644954919815063, "value_row": 0.251240998506546, "value_any": 0.07333699613809586, "value_bot": 0.005798582918941975, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00204.png", "entropy": 0.7013782262802124} +{"ts": "2026-03-20T17:26:29.824995Z", "loop": 205, "env_steps": 125952000, "exact_value_avg": 0.34993046522140503, "regret_dist": 0.5136501789093018, "regret_other_env": 0.8088420033454895, "regret_corner": 0.07086240500211716, "regret_row": 0.6083366870880127, "regret_any": 0.8089198470115662, "regret_bot": 0.8527799248695374, "value_dist": 0.34993046522140503, "value_other_env": 0.07337282598018646, "value_corner": 0.7647669315338135, "value_row": 0.2502899467945099, "value_any": 0.07333073019981384, "value_bot": 0.005846701562404633, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00205.png", "entropy": 0.7015469670295715} +{"ts": "2026-03-20T17:26:30.715725Z", "loop": 206, "env_steps": 126566400, "exact_value_avg": 0.35005977749824524, "regret_dist": 0.5135208964347839, "regret_other_env": 0.8088512420654297, "regret_corner": 0.07052534818649292, "regret_row": 0.6096224188804626, "regret_any": 0.8089289665222168, "regret_bot": 0.8527145385742188, "value_dist": 0.35005977749824524, "value_other_env": 0.07336366176605225, "value_corner": 0.7651039361953735, "value_row": 0.24900420010089874, "value_any": 0.07332158833742142, "value_bot": 0.005911997519433498, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00206.png", "entropy": 0.7017554044723511} +{"ts": "2026-03-20T17:26:31.605967Z", "loop": 207, "env_steps": 127180800, "exact_value_avg": 0.35032734274864197, "regret_dist": 0.5132533311843872, "regret_other_env": 0.8088545799255371, "regret_corner": 0.06985148042440414, "regret_row": 0.6125882267951965, "regret_any": 0.808932363986969, "regret_bot": 0.852557897567749, "value_dist": 0.35032734274864197, "value_other_env": 0.07336033135652542, "value_corner": 0.7657778263092041, "value_row": 0.24603842198848724, "value_any": 0.073318250477314, "value_bot": 0.006068775895982981, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00207.png", "entropy": 0.7026017904281616} +{"ts": "2026-03-20T17:26:32.495535Z", "loop": 208, "env_steps": 127795200, "exact_value_avg": 0.35058337450027466, "regret_dist": 0.5129973292350769, "regret_other_env": 0.8088607788085938, "regret_corner": 0.06920216977596283, "regret_row": 0.6163027286529541, "regret_any": 0.8089384436607361, "regret_bot": 0.85235595703125, "value_dist": 0.35058337450027466, "value_other_env": 0.07335416972637177, "value_corner": 0.7664271593093872, "value_row": 0.2423238903284073, "value_any": 0.07331210374832153, "value_bot": 0.006270688958466053, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00208.png", "entropy": 0.7034640908241272} +{"ts": "2026-03-20T17:26:33.385672Z", "loop": 209, "env_steps": 128409600, "exact_value_avg": 0.3507445156574249, "regret_dist": 0.5128361582756042, "regret_other_env": 0.8088694214820862, "regret_corner": 0.06878628581762314, "regret_row": 0.6197317838668823, "regret_any": 0.8089471459388733, "regret_bot": 0.8521656394004822, "value_dist": 0.3507445156574249, "value_other_env": 0.07334546744823456, "value_corner": 0.7668430805206299, "value_row": 0.23889483511447906, "value_any": 0.07330341637134552, "value_bot": 0.006460935343056917, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00209.png", "entropy": 0.7040189504623413} +{"ts": "2026-03-20T17:26:34.274144Z", "loop": 210, "env_steps": 129024000, "exact_value_avg": 0.3508378863334656, "regret_dist": 0.5127427577972412, "regret_other_env": 0.808883786201477, "regret_corner": 0.06853117048740387, "regret_row": 0.6235513091087341, "regret_any": 0.8089616298675537, "regret_bot": 0.851947546005249, "value_dist": 0.3508378863334656, "value_other_env": 0.07333105802536011, "value_corner": 0.7670981287956238, "value_row": 0.23507528007030487, "value_any": 0.07328901439905167, "value_bot": 0.006679109763354063, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00210.png", "entropy": 0.7042955160140991} +{"ts": "2026-03-20T17:26:35.161741Z", "loop": 211, "env_steps": 129638400, "exact_value_avg": 0.3508542776107788, "regret_dist": 0.5127264261245728, "regret_other_env": 0.8088976740837097, "regret_corner": 0.06846946477890015, "regret_row": 0.6258242130279541, "regret_any": 0.8089754581451416, "regret_bot": 0.8518152236938477, "value_dist": 0.3508542776107788, "value_other_env": 0.07331717014312744, "value_corner": 0.7671598792076111, "value_row": 0.2328024059534073, "value_any": 0.07327516376972198, "value_bot": 0.006811422761529684, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00211.png", "entropy": 0.7042414546012878} +{"ts": "2026-03-20T17:26:36.052623Z", "loop": 212, "env_steps": 130252800, "exact_value_avg": 0.3508431315422058, "regret_dist": 0.5127375721931458, "regret_other_env": 0.8089101314544678, "regret_corner": 0.06847863644361496, "regret_row": 0.6276431679725647, "regret_any": 0.8089878559112549, "regret_bot": 0.85170978307724, "value_dist": 0.3508431315422058, "value_other_env": 0.07330474257469177, "value_corner": 0.7671506404876709, "value_row": 0.23098346590995789, "value_any": 0.0732627734541893, "value_bot": 0.006916836369782686, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00212.png", "entropy": 0.704102635383606} +{"ts": "2026-03-20T17:26:36.944530Z", "loop": 213, "env_steps": 130867200, "exact_value_avg": 0.3508201241493225, "regret_dist": 0.512760579586029, "regret_other_env": 0.8089253902435303, "regret_corner": 0.06851325929164886, "regret_row": 0.6290968060493469, "regret_any": 0.8090031743049622, "regret_bot": 0.851624608039856, "value_dist": 0.3508201241493225, "value_other_env": 0.07328946888446808, "value_corner": 0.7671160697937012, "value_row": 0.22952981293201447, "value_any": 0.0732475146651268, "value_bot": 0.007002025377005339, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00213.png", "entropy": 0.703831672668457} +{"ts": "2026-03-20T17:26:37.836126Z", "loop": 214, "env_steps": 131481600, "exact_value_avg": 0.35079628229141235, "regret_dist": 0.5127844214439392, "regret_other_env": 0.8089399933815002, "regret_corner": 0.0685509741306305, "regret_row": 0.630222737789154, "regret_any": 0.8090177178382874, "regret_bot": 0.8515574932098389, "value_dist": 0.35079628229141235, "value_other_env": 0.0732748880982399, "value_corner": 0.7670783996582031, "value_row": 0.22840385138988495, "value_any": 0.07323294132947922, "value_bot": 0.007069179322570562, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00214.png", "entropy": 0.7034896016120911} +{"ts": "2026-03-20T17:26:38.726676Z", "loop": 215, "env_steps": 132096000, "exact_value_avg": 0.35078102350234985, "regret_dist": 0.5127996206283569, "regret_other_env": 0.808946967124939, "regret_corner": 0.0685785785317421, "regret_row": 0.6307536363601685, "regret_any": 0.8090246319770813, "regret_bot": 0.8515262007713318, "value_dist": 0.35078102350234985, "value_other_env": 0.07326788455247879, "value_corner": 0.7670507431030273, "value_row": 0.22787299752235413, "value_any": 0.07322593778371811, "value_bot": 0.007100345566868782, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00215.png", "entropy": 0.7032784819602966} +{"ts": "2026-03-20T17:26:39.617535Z", "loop": 216, "env_steps": 132710400, "exact_value_avg": 0.35080572962760925, "regret_dist": 0.5127748847007751, "regret_other_env": 0.8089497089385986, "regret_corner": 0.0685126930475235, "regret_row": 0.6301069855690002, "regret_any": 0.8090274333953857, "regret_bot": 0.8515691161155701, "value_dist": 0.35080572962760925, "value_other_env": 0.07326514273881912, "value_corner": 0.7671166062355042, "value_row": 0.22851963341236115, "value_any": 0.07322320342063904, "value_bot": 0.007057611830532551, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00216.png", "entropy": 0.7031620144844055} +{"ts": "2026-03-20T17:26:40.506731Z", "loop": 217, "env_steps": 133324800, "exact_value_avg": 0.3508143723011017, "regret_dist": 0.5127663016319275, "regret_other_env": 0.8089558482170105, "regret_corner": 0.06848195940256119, "regret_row": 0.6298982501029968, "regret_any": 0.8090335130691528, "regret_bot": 0.8515833616256714, "value_dist": 0.3508143723011017, "value_other_env": 0.07325902581214905, "value_corner": 0.7671473622322083, "value_row": 0.22872841358184814, "value_any": 0.07321710139513016, "value_bot": 0.007043234072625637, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00217.png", "entropy": 0.702968180179596} +{"ts": "2026-03-20T17:26:41.396629Z", "loop": 218, "env_steps": 133939200, "exact_value_avg": 0.3508407175540924, "regret_dist": 0.5127400159835815, "regret_other_env": 0.808955729007721, "regret_corner": 0.06841638684272766, "regret_row": 0.6285264492034912, "regret_any": 0.8090333938598633, "regret_bot": 0.8516708612442017, "value_dist": 0.3508407175540924, "value_other_env": 0.07325918972492218, "value_corner": 0.767212986946106, "value_row": 0.23010016977787018, "value_any": 0.07321725785732269, "value_bot": 0.006955751217901707, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00218.png", "entropy": 0.7028855085372925} +{"ts": "2026-03-20T17:26:42.284777Z", "loop": 219, "env_steps": 134553600, "exact_value_avg": 0.3508411645889282, "regret_dist": 0.5127394795417786, "regret_other_env": 0.8089622855186462, "regret_corner": 0.06840526312589645, "regret_row": 0.6288126707077026, "regret_any": 0.8090399503707886, "regret_bot": 0.851655125617981, "value_dist": 0.3508411645889282, "value_other_env": 0.07325257360935211, "value_corner": 0.7672240138053894, "value_row": 0.22981400787830353, "value_any": 0.07321064919233322, "value_bot": 0.0069715166464447975, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00219.png", "entropy": 0.7027277946472168} +{"ts": "2026-03-20T17:26:43.175200Z", "loop": 220, "env_steps": 135168000, "exact_value_avg": 0.3508166968822479, "regret_dist": 0.5127639770507812, "regret_other_env": 0.8089709281921387, "regret_corner": 0.06845347583293915, "regret_row": 0.6299579739570618, "regret_any": 0.809048593044281, "regret_bot": 0.8515859842300415, "value_dist": 0.3508166968822479, "value_other_env": 0.07324393838644028, "value_corner": 0.7671758532524109, "value_row": 0.228668674826622, "value_any": 0.07320203632116318, "value_bot": 0.007040686905384064, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00220.png", "entropy": 0.7026317715644836} +{"ts": "2026-03-20T17:26:44.064294Z", "loop": 221, "env_steps": 135782400, "exact_value_avg": 0.3508286774158478, "regret_dist": 0.5127519369125366, "regret_other_env": 0.8089682459831238, "regret_corner": 0.0684274435043335, "regret_row": 0.6295250654220581, "regret_any": 0.8090459704399109, "regret_bot": 0.8516131639480591, "value_dist": 0.3508286774158478, "value_other_env": 0.0732465535402298, "value_corner": 0.767201840877533, "value_row": 0.22910158336162567, "value_any": 0.0732046440243721, "value_bot": 0.0070135029964149, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00221.png", "entropy": 0.7027229070663452} +{"ts": "2026-03-20T17:26:44.953750Z", "loop": 222, "env_steps": 136396800, "exact_value_avg": 0.3508543074131012, "regret_dist": 0.5127264261245728, "regret_other_env": 0.808962345123291, "regret_corner": 0.06837254017591476, "regret_row": 0.6281561255455017, "regret_any": 0.8090399503707886, "regret_bot": 0.8516978621482849, "value_dist": 0.3508543074131012, "value_other_env": 0.0732526034116745, "value_corner": 0.7672568559646606, "value_row": 0.23047049343585968, "value_any": 0.07321067899465561, "value_bot": 0.006928796414285898, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00222.png", "entropy": 0.7028332948684692} +{"ts": "2026-03-20T17:26:45.841303Z", "loop": 223, "env_steps": 137011200, "exact_value_avg": 0.35085293650627136, "regret_dist": 0.5127277374267578, "regret_other_env": 0.8089651465415955, "regret_corner": 0.06837152689695358, "regret_row": 0.6280773282051086, "regret_any": 0.8090428709983826, "regret_bot": 0.8517037034034729, "value_dist": 0.35085293650627136, "value_other_env": 0.0732496976852417, "value_corner": 0.767257809638977, "value_row": 0.23054929077625275, "value_any": 0.073207788169384, "value_bot": 0.006922908127307892, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00223.png", "entropy": 0.7028169631958008} +{"ts": "2026-03-20T17:26:46.730773Z", "loop": 224, "env_steps": 137625600, "exact_value_avg": 0.350839227437973, "regret_dist": 0.5127415060997009, "regret_other_env": 0.8089671730995178, "regret_corner": 0.06840291619300842, "regret_row": 0.6289320588111877, "regret_any": 0.8090447783470154, "regret_bot": 0.8516504168510437, "value_dist": 0.350839227437973, "value_other_env": 0.0732477605342865, "value_corner": 0.7672264575958252, "value_row": 0.22969461977481842, "value_any": 0.07320583611726761, "value_bot": 0.006976218428462744, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00224.png", "entropy": 0.7028246521949768} +{"ts": "2026-03-20T17:26:47.619181Z", "loop": 225, "env_steps": 138240000, "exact_value_avg": 0.3508329391479492, "regret_dist": 0.5127477645874023, "regret_other_env": 0.8089675903320312, "regret_corner": 0.0684179812669754, "regret_row": 0.6292889714241028, "regret_any": 0.8090451955795288, "regret_bot": 0.8516269326210022, "value_dist": 0.3508329391479492, "value_other_env": 0.07324729114770889, "value_corner": 0.767211377620697, "value_row": 0.229337677359581, "value_any": 0.0732053816318512, "value_bot": 0.006999696139246225, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00225.png", "entropy": 0.7028303146362305} +{"ts": "2026-03-20T17:26:48.508051Z", "loop": 226, "env_steps": 138854400, "exact_value_avg": 0.3508415222167969, "regret_dist": 0.5127391219139099, "regret_other_env": 0.8089634776115417, "regret_corner": 0.06840258091688156, "regret_row": 0.6285371780395508, "regret_any": 0.8090410828590393, "regret_bot": 0.8516717553138733, "value_dist": 0.3508415222167969, "value_other_env": 0.07325137406587601, "value_corner": 0.7672267556190491, "value_row": 0.23008939623832703, "value_any": 0.07320947200059891, "value_bot": 0.006954771000891924, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00226.png", "entropy": 0.7028958797454834} +{"ts": "2026-03-20T17:26:49.395618Z", "loop": 227, "env_steps": 139468800, "exact_value_avg": 0.35087138414382935, "regret_dist": 0.5127092599868774, "regret_other_env": 0.8089523315429688, "regret_corner": 0.0683446153998375, "regret_row": 0.6262262463569641, "regret_any": 0.8090299963951111, "regret_bot": 0.851811408996582, "value_dist": 0.35087138414382935, "value_other_env": 0.07326249778270721, "value_corner": 0.7672846913337708, "value_row": 0.23240041732788086, "value_any": 0.07322055846452713, "value_bot": 0.006815232336521149, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00227.png", "entropy": 0.7029500007629395} +{"ts": "2026-03-20T17:26:50.285552Z", "loop": 228, "env_steps": 140083200, "exact_value_avg": 0.35086145997047424, "regret_dist": 0.5127192139625549, "regret_other_env": 0.8089491724967957, "regret_corner": 0.06837420165538788, "regret_row": 0.6241652965545654, "regret_any": 0.8090268969535828, "regret_bot": 0.8519349694252014, "value_dist": 0.35086145997047424, "value_other_env": 0.0732656940817833, "value_corner": 0.7672551274299622, "value_row": 0.23446139693260193, "value_any": 0.07322374731302261, "value_bot": 0.006691635586321354, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00228.png", "entropy": 0.7028247117996216} +{"ts": "2026-03-20T17:26:51.174495Z", "loop": 229, "env_steps": 140697600, "exact_value_avg": 0.3508220314979553, "regret_dist": 0.5127586722373962, "regret_other_env": 0.8089447021484375, "regret_corner": 0.06847959756851196, "regret_row": 0.621891975402832, "regret_any": 0.8090223073959351, "regret_bot": 0.8520684838294983, "value_dist": 0.3508220314979553, "value_other_env": 0.07327017933130264, "value_corner": 0.7671497464179993, "value_row": 0.23673464357852936, "value_any": 0.07322822511196136, "value_bot": 0.0065580192022025585, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00229.png", "entropy": 0.7025784850120544} +{"ts": "2026-03-20T17:26:52.063540Z", "loop": 230, "env_steps": 141312000, "exact_value_avg": 0.3507290482521057, "regret_dist": 0.5128515958786011, "regret_other_env": 0.8089445233345032, "regret_corner": 0.06871221214532852, "regret_row": 0.619085967540741, "regret_any": 0.8090221881866455, "regret_bot": 0.852230429649353, "value_dist": 0.3507290482521057, "value_other_env": 0.07327032834291458, "value_corner": 0.7669170498847961, "value_row": 0.23954065144062042, "value_any": 0.07322835177183151, "value_bot": 0.006396201904863119, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00230.png", "entropy": 0.7020270228385925} +{"ts": "2026-03-20T17:26:52.952806Z", "loop": 231, "env_steps": 141926400, "exact_value_avg": 0.35062357783317566, "regret_dist": 0.5129570960998535, "regret_other_env": 0.8089516162872314, "regret_corner": 0.06896530836820602, "regret_row": 0.6169152855873108, "regret_any": 0.8090293407440186, "regret_bot": 0.8523546457290649, "value_dist": 0.35062357783317566, "value_other_env": 0.07326323539018631, "value_corner": 0.7666640281677246, "value_row": 0.24171137809753418, "value_any": 0.07322127372026443, "value_bot": 0.006271935533732176, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00231.png", "entropy": 0.7013576626777649} +{"ts": "2026-03-20T17:26:53.841802Z", "loop": 232, "env_steps": 142540800, "exact_value_avg": 0.35063648223876953, "regret_dist": 0.5129441618919373, "regret_other_env": 0.8089548945426941, "regret_corner": 0.06892804056406021, "regret_row": 0.6171637773513794, "regret_any": 0.8090326189994812, "regret_bot": 0.8523401021957397, "value_dist": 0.35063648223876953, "value_other_env": 0.07325993478298187, "value_corner": 0.7667012810707092, "value_row": 0.24146288633346558, "value_any": 0.07321797311306, "value_bot": 0.006286532152444124, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00232.png", "entropy": 0.7012420892715454} +{"ts": "2026-03-20T17:26:54.734627Z", "loop": 233, "env_steps": 143155200, "exact_value_avg": 0.35069647431373596, "regret_dist": 0.5128841996192932, "regret_other_env": 0.8089592456817627, "regret_corner": 0.06877155601978302, "regret_row": 0.6183318495750427, "regret_any": 0.809036910533905, "regret_bot": 0.8522745370864868, "value_dist": 0.35069647431373596, "value_other_env": 0.07325561344623566, "value_corner": 0.7668577432632446, "value_row": 0.24029475450515747, "value_any": 0.07321366667747498, "value_bot": 0.006352038588374853, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00233.png", "entropy": 0.7014057636260986} +{"ts": "2026-03-20T17:26:55.624170Z", "loop": 234, "env_steps": 143769600, "exact_value_avg": 0.35072141885757446, "regret_dist": 0.5128592252731323, "regret_other_env": 0.8089614510536194, "regret_corner": 0.06870590150356293, "regret_row": 0.6188765168190002, "regret_any": 0.8090391755104065, "regret_bot": 0.8522446155548096, "value_dist": 0.35072141885757446, "value_other_env": 0.07325341552495956, "value_corner": 0.7669234275817871, "value_row": 0.23975010216236115, "value_any": 0.07321145385503769, "value_bot": 0.006382006220519543, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00234.png", "entropy": 0.7014277577400208} +{"ts": "2026-03-20T17:26:56.514724Z", "loop": 235, "env_steps": 144384000, "exact_value_avg": 0.3508045971393585, "regret_dist": 0.5127760767936707, "regret_other_env": 0.8089661598205566, "regret_corner": 0.06849093735218048, "regret_row": 0.6210700273513794, "regret_any": 0.8090438842773438, "regret_bot": 0.8521197438240051, "value_dist": 0.3508045971393585, "value_other_env": 0.07324870675802231, "value_corner": 0.7671384215354919, "value_row": 0.23755668103694916, "value_any": 0.07320675998926163, "value_bot": 0.006506845820695162, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00235.png", "entropy": 0.7016642689704895} +{"ts": "2026-03-20T17:26:57.404695Z", "loop": 236, "env_steps": 144998400, "exact_value_avg": 0.3508334755897522, "regret_dist": 0.5127471685409546, "regret_other_env": 0.8089706897735596, "regret_corner": 0.06841189414262772, "regret_row": 0.6218332648277283, "regret_any": 0.8090482950210571, "regret_bot": 0.8520764708518982, "value_dist": 0.3508334755897522, "value_other_env": 0.07324418425559998, "value_corner": 0.7672173976898193, "value_row": 0.2367933690547943, "value_any": 0.0732022374868393, "value_bot": 0.006550123915076256, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00236.png", "entropy": 0.7016173601150513} +{"ts": "2026-03-20T17:26:58.294672Z", "loop": 237, "env_steps": 145612800, "exact_value_avg": 0.3508574664592743, "regret_dist": 0.5127232670783997, "regret_other_env": 0.808977484703064, "regret_corner": 0.06834180653095245, "regret_row": 0.6228229999542236, "regret_any": 0.8090551495552063, "regret_bot": 0.8520200252532959, "value_dist": 0.3508574664592743, "value_other_env": 0.07323740422725677, "value_corner": 0.7672874927520752, "value_row": 0.23580358922481537, "value_any": 0.07319547235965729, "value_bot": 0.006606524344533682, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00237.png", "entropy": 0.7015357613563538} +{"ts": "2026-03-20T17:26:59.185050Z", "loop": 238, "env_steps": 146227200, "exact_value_avg": 0.3508486747741699, "regret_dist": 0.5127320289611816, "regret_other_env": 0.8089825510978699, "regret_corner": 0.0683562308549881, "regret_row": 0.6225056648254395, "regret_any": 0.8090601563453674, "regret_bot": 0.8520409464836121, "value_dist": 0.3508486747741699, "value_other_env": 0.07323237508535385, "value_corner": 0.7672731280326843, "value_row": 0.23612092435359955, "value_any": 0.07319045066833496, "value_bot": 0.0065856752917170525, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00238.png", "entropy": 0.7013149261474609} +{"ts": "2026-03-20T17:27:00.074556Z", "loop": 239, "env_steps": 146841600, "exact_value_avg": 0.3508678674697876, "regret_dist": 0.512712836265564, "regret_other_env": 0.8089893460273743, "regret_corner": 0.06829800456762314, "regret_row": 0.6235440373420715, "regret_any": 0.8090670108795166, "regret_bot": 0.8519821166992188, "value_dist": 0.3508678674697876, "value_other_env": 0.07322553545236588, "value_corner": 0.7673313617706299, "value_row": 0.23508265614509583, "value_any": 0.07318361848592758, "value_bot": 0.006644447334110737, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00239.png", "entropy": 0.7013016939163208} +{"ts": "2026-03-20T17:27:00.965873Z", "loop": 240, "env_steps": 147456000, "exact_value_avg": 0.35088440775871277, "regret_dist": 0.5126962661743164, "regret_other_env": 0.8089951276779175, "regret_corner": 0.06824788451194763, "regret_row": 0.6246142387390137, "regret_any": 0.8090727925300598, "regret_bot": 0.8519209027290344, "value_dist": 0.35088440775871277, "value_other_env": 0.07321973890066147, "value_corner": 0.7673814296722412, "value_row": 0.23401233553886414, "value_any": 0.07317782938480377, "value_bot": 0.006705683656036854, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00240.png", "entropy": 0.7013536095619202} +{"ts": "2026-03-20T17:27:01.856361Z", "loop": 241, "env_steps": 148070400, "exact_value_avg": 0.35088714957237244, "regret_dist": 0.5126935243606567, "regret_other_env": 0.8090014457702637, "regret_corner": 0.06823156028985977, "regret_row": 0.6263578534126282, "regret_any": 0.809079110622406, "regret_bot": 0.8518180847167969, "value_dist": 0.35088714957237244, "value_other_env": 0.07321339100599289, "value_corner": 0.7673978209495544, "value_row": 0.23226884007453918, "value_any": 0.07317148894071579, "value_bot": 0.006808582693338394, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00241.png", "entropy": 0.7014824748039246} +{"ts": "2026-03-20T17:27:02.745316Z", "loop": 242, "env_steps": 148684800, "exact_value_avg": 0.3508895933628082, "regret_dist": 0.5126911401748657, "regret_other_env": 0.8090019226074219, "regret_corner": 0.06822489202022552, "regret_row": 0.6265246868133545, "regret_any": 0.8090795278549194, "regret_bot": 0.8518093228340149, "value_dist": 0.3508895933628082, "value_other_env": 0.07321298867464066, "value_corner": 0.7674044966697693, "value_row": 0.2321019470691681, "value_any": 0.07317109405994415, "value_bot": 0.006817286368459463, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00242.png", "entropy": 0.7015484571456909} +{"ts": "2026-03-20T17:27:03.633295Z", "loop": 243, "env_steps": 149299200, "exact_value_avg": 0.35088416934013367, "regret_dist": 0.5126964449882507, "regret_other_env": 0.8089961409568787, "regret_corner": 0.06824693828821182, "regret_row": 0.6252437233924866, "regret_any": 0.809073805809021, "regret_bot": 0.8518883585929871, "value_dist": 0.35088416934013367, "value_other_env": 0.07321875542402267, "value_corner": 0.7673823237419128, "value_row": 0.23338285088539124, "value_any": 0.07317685335874557, "value_bot": 0.0067382934503257275, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00243.png", "entropy": 0.701617956161499} +{"ts": "2026-03-20T17:27:04.524792Z", "loop": 244, "env_steps": 149913600, "exact_value_avg": 0.35088807344436646, "regret_dist": 0.5126925706863403, "regret_other_env": 0.8089982867240906, "regret_corner": 0.06823396682739258, "regret_row": 0.6258392333984375, "regret_any": 0.8090760111808777, "regret_bot": 0.8518534898757935, "value_dist": 0.35088807344436646, "value_other_env": 0.0732165202498436, "value_corner": 0.7673953771591187, "value_row": 0.2327873557806015, "value_any": 0.07317463308572769, "value_bot": 0.00677311047911644, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00244.png", "entropy": 0.7016867995262146} +{"ts": "2026-03-20T17:27:05.417172Z", "loop": 245, "env_steps": 150528000, "exact_value_avg": 0.35088518261909485, "regret_dist": 0.5126955509185791, "regret_other_env": 0.8090046048164368, "regret_corner": 0.06823182106018066, "regret_row": 0.6267821788787842, "regret_any": 0.8090822100639343, "regret_bot": 0.8517969846725464, "value_dist": 0.35088518261909485, "value_other_env": 0.07321029156446457, "value_corner": 0.7673974633216858, "value_row": 0.2318444401025772, "value_any": 0.07316841185092926, "value_bot": 0.00682956213131547, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00245.png", "entropy": 0.701650083065033} +{"ts": "2026-03-20T17:27:06.307450Z", "loop": 246, "env_steps": 151142400, "exact_value_avg": 0.35088077187538147, "regret_dist": 0.5126999020576477, "regret_other_env": 0.8090077042579651, "regret_corner": 0.06823816150426865, "regret_row": 0.6274780631065369, "regret_any": 0.8090853095054626, "regret_bot": 0.8517542481422424, "value_dist": 0.35088077187538147, "value_other_env": 0.07320716232061386, "value_corner": 0.7673911452293396, "value_row": 0.23114857077598572, "value_any": 0.07316528260707855, "value_bot": 0.006872321479022503, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00246.png", "entropy": 0.7016019225120544} +{"ts": "2026-03-20T17:27:07.196268Z", "loop": 247, "env_steps": 151756800, "exact_value_avg": 0.35086458921432495, "regret_dist": 0.5127160549163818, "regret_other_env": 0.80901700258255, "regret_corner": 0.06826458126306534, "regret_row": 0.6288549304008484, "regret_any": 0.8090945482254028, "regret_bot": 0.8516700267791748, "value_dist": 0.35086458921432495, "value_other_env": 0.07319783419370651, "value_corner": 0.7673647403717041, "value_row": 0.22977164387702942, "value_any": 0.07315598428249359, "value_bot": 0.006956648081541061, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00247.png", "entropy": 0.7014630436897278} +{"ts": "2026-03-20T17:27:08.084407Z", "loop": 248, "env_steps": 152371200, "exact_value_avg": 0.35086342692375183, "regret_dist": 0.5127172470092773, "regret_other_env": 0.8090230822563171, "regret_corner": 0.06825846433639526, "regret_row": 0.6292104125022888, "regret_any": 0.8091006278991699, "regret_bot": 0.8516477346420288, "value_dist": 0.35086342692375183, "value_other_env": 0.07319178432226181, "value_corner": 0.767370879650116, "value_row": 0.22941620647907257, "value_any": 0.07314993441104889, "value_bot": 0.006978865712881088, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00248.png", "entropy": 0.7012979388237} +{"ts": "2026-03-20T17:27:08.972232Z", "loop": 249, "env_steps": 152985600, "exact_value_avg": 0.35083577036857605, "regret_dist": 0.5127449035644531, "regret_other_env": 0.809033989906311, "regret_corner": 0.06831126660108566, "regret_row": 0.6302723288536072, "regret_any": 0.8091115951538086, "regret_bot": 0.8515831828117371, "value_dist": 0.35083577036857605, "value_other_env": 0.0731809064745903, "value_corner": 0.767318069934845, "value_row": 0.2283543348312378, "value_any": 0.07313907146453857, "value_bot": 0.007043447345495224, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00249.png", "entropy": 0.701036810874939} +{"ts": "2026-03-20T17:27:09.861880Z", "loop": 250, "env_steps": 153600000, "exact_value_avg": 0.35079050064086914, "regret_dist": 0.5127901434898376, "regret_other_env": 0.8090501427650452, "regret_corner": 0.06840009987354279, "regret_row": 0.6318889856338501, "regret_any": 0.8091277480125427, "regret_bot": 0.8514824509620667, "value_dist": 0.35079050064086914, "value_other_env": 0.0731646716594696, "value_corner": 0.7672292590141296, "value_row": 0.2267376184463501, "value_any": 0.07312285900115967, "value_bot": 0.007144146133214235, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00250.png", "entropy": 0.7006316781044006} +{"ts": "2026-03-20T17:27:11.604853Z", "loop": 252, "env_steps": 154828800, "exact_value_avg": 0.35071074962615967, "regret_dist": 0.5128698945045471, "regret_other_env": 0.8090725541114807, "regret_corner": 0.06856586784124374, "regret_row": 0.6339009404182434, "regret_any": 0.8091500997543335, "regret_bot": 0.8513546586036682, "value_dist": 0.35071074962615967, "value_other_env": 0.07314231246709824, "value_corner": 0.7670634388923645, "value_row": 0.22472567856311798, "value_any": 0.07310052961111069, "value_bot": 0.007271918933838606, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00252.png", "entropy": 0.6999633312225342} +{"ts": "2026-03-20T17:27:13.345073Z", "loop": 254, "env_steps": 156057600, "exact_value_avg": 0.35074666142463684, "regret_dist": 0.5128339529037476, "regret_other_env": 0.8090770840644836, "regret_corner": 0.06846927106380463, "regret_row": 0.6333324313163757, "regret_any": 0.8091546893119812, "regret_bot": 0.8513991832733154, "value_dist": 0.35074666142463684, "value_other_env": 0.07313773781061172, "value_corner": 0.7671600580215454, "value_row": 0.22529423236846924, "value_any": 0.07309595495462418, "value_bot": 0.007227449677884579, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00254.png", "entropy": 0.6998682022094727} +{"ts": "2026-03-20T17:27:15.087049Z", "loop": 256, "env_steps": 157286400, "exact_value_avg": 0.35076451301574707, "regret_dist": 0.5128161907196045, "regret_other_env": 0.8090837001800537, "regret_corner": 0.0684148296713829, "regret_row": 0.6328800320625305, "regret_any": 0.8091611266136169, "regret_bot": 0.8514363169670105, "value_dist": 0.35076451301574707, "value_other_env": 0.07313119620084763, "value_corner": 0.7672144770622253, "value_row": 0.22574658691883087, "value_any": 0.07308943569660187, "value_bot": 0.00719023821875453, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00256.png", "entropy": 0.6998161673545837} +{"ts": "2026-03-20T17:27:16.828094Z", "loop": 258, "env_steps": 158515200, "exact_value_avg": 0.35078194737434387, "regret_dist": 0.5127987265586853, "regret_other_env": 0.8090909123420715, "regret_corner": 0.06836044788360596, "regret_row": 0.6325486898422241, "regret_any": 0.8091683983802795, "regret_bot": 0.8514643311500549, "value_dist": 0.35078194737434387, "value_other_env": 0.07312395423650742, "value_corner": 0.7672688961029053, "value_row": 0.22607792913913727, "value_any": 0.07308218628168106, "value_bot": 0.007162261288613081, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00258.png", "entropy": 0.6997028589248657} +{"ts": "2026-03-20T17:27:18.571609Z", "loop": 260, "env_steps": 159744000, "exact_value_avg": 0.3509061336517334, "regret_dist": 0.5126745700836182, "regret_other_env": 0.80906742811203, "regret_corner": 0.06808529049158096, "regret_row": 0.626771092414856, "regret_any": 0.8091449737548828, "regret_bot": 0.8518238067626953, "value_dist": 0.3509061336517334, "value_other_env": 0.07314752042293549, "value_corner": 0.7675440311431885, "value_row": 0.23185546696186066, "value_any": 0.07310570776462555, "value_bot": 0.006802835967391729, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00260.png", "entropy": 0.6999834179878235} +{"ts": "2026-03-20T17:27:20.316410Z", "loop": 262, "env_steps": 160972800, "exact_value_avg": 0.35089021921157837, "regret_dist": 0.5126904845237732, "regret_other_env": 0.8090659379959106, "regret_corner": 0.06812731921672821, "regret_row": 0.6239246129989624, "regret_any": 0.8091434240341187, "regret_bot": 0.851993978023529, "value_dist": 0.35089021921157837, "value_other_env": 0.07314898073673248, "value_corner": 0.7675020098686218, "value_row": 0.23470202088356018, "value_any": 0.07310714572668076, "value_bot": 0.006632626987993717, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00262.png", "entropy": 0.6995990872383118} +{"ts": "2026-03-20T17:27:22.060209Z", "loop": 264, "env_steps": 162201600, "exact_value_avg": 0.3507871925830841, "regret_dist": 0.5127934217453003, "regret_other_env": 0.8090687394142151, "regret_corner": 0.06838042289018631, "regret_row": 0.6200953125953674, "regret_any": 0.8091463446617126, "regret_bot": 0.8522146344184875, "value_dist": 0.3507871925830841, "value_other_env": 0.07314607501029968, "value_corner": 0.7672488689422607, "value_row": 0.23853135108947754, "value_any": 0.07310424000024796, "value_bot": 0.006412032060325146, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00264.png", "entropy": 0.6987810134887695} +{"ts": "2026-03-20T17:27:23.803144Z", "loop": 266, "env_steps": 163430400, "exact_value_avg": 0.350588858127594, "regret_dist": 0.5129918456077576, "regret_other_env": 0.8090715408325195, "regret_corner": 0.06887233257293701, "regret_row": 0.616223156452179, "regret_any": 0.8091490268707275, "regret_bot": 0.8524269461631775, "value_dist": 0.350588858127594, "value_other_env": 0.073143370449543, "value_corner": 0.7667570114135742, "value_row": 0.24240347743034363, "value_any": 0.07310152053833008, "value_bot": 0.006199715193361044, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00266.png", "entropy": 0.6976625323295593} +{"ts": "2026-03-20T17:27:25.545549Z", "loop": 268, "env_steps": 164659200, "exact_value_avg": 0.3506981134414673, "regret_dist": 0.5128825902938843, "regret_other_env": 0.809076189994812, "regret_corner": 0.06859210133552551, "regret_row": 0.6181281805038452, "regret_any": 0.8091537356376648, "regret_bot": 0.8523181080818176, "value_dist": 0.3506981134414673, "value_other_env": 0.07313874363899231, "value_corner": 0.7670372128486633, "value_row": 0.24049848318099976, "value_any": 0.07309690117835999, "value_bot": 0.006308541167527437, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00268.png", "entropy": 0.6978934407234192} +{"ts": "2026-03-20T17:27:27.287993Z", "loop": 270, "env_steps": 165888000, "exact_value_avg": 0.3507925570011139, "regret_dist": 0.5127881169319153, "regret_other_env": 0.8090841174125671, "regret_corner": 0.06834409385919571, "regret_row": 0.6202229857444763, "regret_any": 0.8091616630554199, "regret_bot": 0.8522012233734131, "value_dist": 0.3507925570011139, "value_other_env": 0.07313072681427002, "value_corner": 0.7672852873802185, "value_row": 0.23840363323688507, "value_any": 0.07308891415596008, "value_bot": 0.006425376050174236, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00270.png", "entropy": 0.6981697082519531} +{"ts": "2026-03-20T17:27:29.030490Z", "loop": 272, "env_steps": 167116800, "exact_value_avg": 0.3509095013141632, "regret_dist": 0.512671172618866, "regret_other_env": 0.8091011047363281, "regret_corner": 0.06802621483802795, "regret_row": 0.6245294809341431, "regret_any": 0.8091786503791809, "regret_bot": 0.8519559502601624, "value_dist": 0.3509095013141632, "value_other_env": 0.07311375439167023, "value_corner": 0.7676031589508057, "value_row": 0.23409713804721832, "value_any": 0.07307197898626328, "value_bot": 0.006670644041150808, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00272.png", "entropy": 0.6985675692558289} +{"ts": "2026-03-20T17:27:30.772937Z", "loop": 274, "env_steps": 168345600, "exact_value_avg": 0.35090768337249756, "regret_dist": 0.5126729607582092, "regret_other_env": 0.8091250061988831, "regret_corner": 0.06799488514661789, "regret_row": 0.6287518739700317, "regret_any": 0.8092024326324463, "regret_bot": 0.8517072796821594, "value_dist": 0.35090768337249756, "value_other_env": 0.07308986783027649, "value_corner": 0.7676344513893127, "value_row": 0.22987473011016846, "value_any": 0.07304812222719193, "value_bot": 0.006919346749782562, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00274.png", "entropy": 0.6984784007072449} +{"ts": "2026-03-20T17:27:32.515567Z", "loop": 276, "env_steps": 169574400, "exact_value_avg": 0.35085728764533997, "regret_dist": 0.5127233862876892, "regret_other_env": 0.809138298034668, "regret_corner": 0.06810096651315689, "regret_row": 0.6312879323959351, "regret_any": 0.809215784072876, "regret_bot": 0.8515517711639404, "value_dist": 0.35085728764533997, "value_other_env": 0.07307657599449158, "value_corner": 0.7675283551216125, "value_row": 0.22733870148658752, "value_any": 0.0730348527431488, "value_bot": 0.007074899971485138, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00276.png", "entropy": 0.6982934474945068} +{"ts": "2026-03-20T17:27:34.255231Z", "loop": 278, "env_steps": 170803200, "exact_value_avg": 0.35085105895996094, "regret_dist": 0.5127296447753906, "regret_other_env": 0.8091349601745605, "regret_corner": 0.06812164187431335, "regret_row": 0.631430983543396, "regret_any": 0.8092123866081238, "regret_bot": 0.8515432476997375, "value_dist": 0.35085105895996094, "value_other_env": 0.0730799064040184, "value_corner": 0.7675077319145203, "value_row": 0.2271956354379654, "value_any": 0.07303818315267563, "value_bot": 0.007083377335220575, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00278.png", "entropy": 0.6983845233917236} +{"ts": "2026-03-20T17:27:35.997284Z", "loop": 280, "env_steps": 172032000, "exact_value_avg": 0.35092291235923767, "regret_dist": 0.5126578211784363, "regret_other_env": 0.809105396270752, "regret_corner": 0.06798633933067322, "regret_row": 0.6262816786766052, "regret_any": 0.80918288230896, "regret_bot": 0.8518585562705994, "value_dist": 0.35092291235923767, "value_other_env": 0.07310948520898819, "value_corner": 0.7676430344581604, "value_row": 0.23234497010707855, "value_any": 0.07306769490242004, "value_bot": 0.006768081337213516, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00280.png", "entropy": 0.6987633109092712} +{"ts": "2026-03-20T17:27:37.736818Z", "loop": 282, "env_steps": 173260800, "exact_value_avg": 0.35080060362815857, "regret_dist": 0.5127801299095154, "regret_other_env": 0.8090912699699402, "regret_corner": 0.0683133453130722, "regret_row": 0.6201739311218262, "regret_any": 0.8091686964035034, "regret_bot": 0.8522127866744995, "value_dist": 0.35080060362815857, "value_other_env": 0.07312368601560593, "value_corner": 0.7673159837722778, "value_row": 0.23845267295837402, "value_any": 0.0730818659067154, "value_bot": 0.006413792725652456, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00282.png", "entropy": 0.6981720924377441} +{"ts": "2026-03-20T17:27:39.478908Z", "loop": 284, "env_steps": 174489600, "exact_value_avg": 0.3506755828857422, "regret_dist": 0.5129051208496094, "regret_other_env": 0.809091329574585, "regret_corner": 0.06862571090459824, "regret_row": 0.617588996887207, "regret_any": 0.8091688752174377, "regret_bot": 0.852356493473053, "value_dist": 0.3506755828857422, "value_other_env": 0.07312354445457458, "value_corner": 0.7670036554336548, "value_row": 0.24103757739067078, "value_any": 0.07308173179626465, "value_bot": 0.00627013947814703, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00284.png", "entropy": 0.6975497603416443} +{"ts": "2026-03-20T17:27:41.222902Z", "loop": 286, "env_steps": 175718400, "exact_value_avg": 0.35081732273101807, "regret_dist": 0.5127633810043335, "regret_other_env": 0.8090930581092834, "regret_corner": 0.0682687982916832, "regret_row": 0.6206983923912048, "regret_any": 0.8091705441474915, "regret_bot": 0.8521772623062134, "value_dist": 0.35081732273101807, "value_other_env": 0.0731218159198761, "value_corner": 0.767360508441925, "value_row": 0.23792828619480133, "value_any": 0.07308000326156616, "value_bot": 0.006449380423873663, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00286.png", "entropy": 0.6981161832809448} +{"ts": "2026-03-20T17:27:42.965268Z", "loop": 288, "env_steps": 176947200, "exact_value_avg": 0.35093018412590027, "regret_dist": 0.5126505494117737, "regret_other_env": 0.8091093301773071, "regret_corner": 0.06796228140592575, "regret_row": 0.626957893371582, "regret_any": 0.8091866970062256, "regret_bot": 0.8518080711364746, "value_dist": 0.35093018412590027, "value_other_env": 0.07310560345649719, "value_corner": 0.7676670551300049, "value_row": 0.23166872560977936, "value_any": 0.07306384295225143, "value_bot": 0.0068185776472091675, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00288.png", "entropy": 0.6985825300216675} +{"ts": "2026-03-20T17:27:44.710584Z", "loop": 290, "env_steps": 178176000, "exact_value_avg": 0.35082876682281494, "regret_dist": 0.5127519369125366, "regret_other_env": 0.8091409802436829, "regret_corner": 0.06816837936639786, "regret_row": 0.6323139667510986, "regret_any": 0.8092183470726013, "regret_bot": 0.8514786958694458, "value_dist": 0.35082876682281494, "value_other_env": 0.07307396084070206, "value_corner": 0.7674609422683716, "value_row": 0.22631266713142395, "value_any": 0.07303225249052048, "value_bot": 0.007147975265979767, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00290.png", "entropy": 0.6981517672538757} +{"ts": "2026-03-20T17:27:46.453673Z", "loop": 292, "env_steps": 179404800, "exact_value_avg": 0.35048869252204895, "regret_dist": 0.513092041015625, "regret_other_env": 0.8091901540756226, "regret_corner": 0.06894482672214508, "regret_row": 0.6384133100509644, "regret_any": 0.8092674016952515, "regret_bot": 0.8510825037956238, "value_dist": 0.35048869252204895, "value_other_env": 0.07302477210760117, "value_corner": 0.7666845321655273, "value_row": 0.22021335363388062, "value_any": 0.07298313826322556, "value_bot": 0.007544125895947218, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00292.png", "entropy": 0.6966651678085327} +{"ts": "2026-03-20T17:27:48.195527Z", "loop": 294, "env_steps": 180633600, "exact_value_avg": 0.3502967059612274, "regret_dist": 0.5132839679718018, "regret_other_env": 0.8092125654220581, "regret_corner": 0.06939104944467545, "regret_row": 0.6406845450401306, "regret_any": 0.8092898726463318, "regret_bot": 0.8509302735328674, "value_dist": 0.3502967059612274, "value_other_env": 0.07300234586000443, "value_corner": 0.766238272190094, "value_row": 0.21794210374355316, "value_any": 0.0729607492685318, "value_bot": 0.007696296088397503, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00294.png", "entropy": 0.6958974599838257} +{"ts": "2026-03-20T17:27:49.937337Z", "loop": 296, "env_steps": 181862400, "exact_value_avg": 0.3507055938243866, "regret_dist": 0.5128750801086426, "regret_other_env": 0.8091650605201721, "regret_corner": 0.06844000518321991, "regret_row": 0.63515305519104, "regret_any": 0.8092424869537354, "regret_bot": 0.8513109087944031, "value_dist": 0.3507055938243866, "value_other_env": 0.07304977625608444, "value_corner": 0.7671893239021301, "value_row": 0.22347357869148254, "value_any": 0.07300812005996704, "value_bot": 0.007315686903893948, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00296.png", "entropy": 0.6977084279060364} +{"ts": "2026-03-20T17:27:51.679955Z", "loop": 298, "env_steps": 183091200, "exact_value_avg": 0.35092735290527344, "regret_dist": 0.5126532912254333, "regret_other_env": 0.8091177940368652, "regret_corner": 0.06795652955770493, "regret_row": 0.6274722814559937, "regret_any": 0.809195339679718, "regret_bot": 0.8517934083938599, "value_dist": 0.35092735290527344, "value_other_env": 0.07309701293706894, "value_corner": 0.7676728367805481, "value_row": 0.2311544120311737, "value_any": 0.07305523753166199, "value_bot": 0.0068332357332110405, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00298.png", "entropy": 0.6987138390541077} +{"ts": "2026-03-20T17:27:53.421052Z", "loop": 300, "env_steps": 184320000, "exact_value_avg": 0.3508453965187073, "regret_dist": 0.5127352476119995, "regret_other_env": 0.80909264087677, "regret_corner": 0.06819915771484375, "regret_row": 0.6213634014129639, "regret_any": 0.8091701865196228, "regret_bot": 0.8521513938903809, "value_dist": 0.3508453965187073, "value_other_env": 0.07312225550413132, "value_corner": 0.7674301266670227, "value_row": 0.23726320266723633, "value_any": 0.07308045029640198, "value_bot": 0.0064752185717225075, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00300.png", "entropy": 0.6984698176383972} +{"ts": "2026-03-20T17:27:55.160712Z", "loop": 302, "env_steps": 185548800, "exact_value_avg": 0.3506309986114502, "regret_dist": 0.5129497051239014, "regret_other_env": 0.8090877532958984, "regret_corner": 0.06874261051416397, "regret_row": 0.6166377663612366, "regret_any": 0.8091652393341064, "regret_bot": 0.8524163961410522, "value_dist": 0.3506309986114502, "value_other_env": 0.07312716543674469, "value_corner": 0.7668867707252502, "value_row": 0.241988867521286, "value_any": 0.07308533787727356, "value_bot": 0.006210200022906065, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00302.png", "entropy": 0.697507917881012} +{"ts": "2026-03-20T17:27:56.902660Z", "loop": 304, "env_steps": 186777600, "exact_value_avg": 0.35048145055770874, "regret_dist": 0.5130992531776428, "regret_other_env": 0.8090817928314209, "regret_corner": 0.06912535429000854, "regret_row": 0.614454984664917, "regret_any": 0.8091592788696289, "regret_bot": 0.8525334596633911, "value_dist": 0.35048145055770874, "value_other_env": 0.07313308864831924, "value_corner": 0.7665039300918579, "value_row": 0.24417169392108917, "value_any": 0.07309126853942871, "value_bot": 0.006093162111938, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00304.png", "entropy": 0.6970009803771973} +{"ts": "2026-03-20T17:27:58.644506Z", "loop": 306, "env_steps": 188006400, "exact_value_avg": 0.35061395168304443, "regret_dist": 0.5129666924476624, "regret_other_env": 0.8090699911117554, "regret_corner": 0.06881164014339447, "regret_row": 0.6163585782051086, "regret_any": 0.8091475963592529, "regret_bot": 0.8524245619773865, "value_dist": 0.35061395168304443, "value_other_env": 0.07314485311508179, "value_corner": 0.7668176293373108, "value_row": 0.24226808547973633, "value_any": 0.07310301065444946, "value_bot": 0.006202049553394318, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00306.png", "entropy": 0.6977563500404358} +{"ts": "2026-03-20T17:28:00.386759Z", "loop": 308, "env_steps": 189235200, "exact_value_avg": 0.35088393092155457, "regret_dist": 0.5126968026161194, "regret_other_env": 0.8090622425079346, "regret_corner": 0.06814856827259064, "regret_row": 0.6226776838302612, "regret_any": 0.8091397881507874, "regret_bot": 0.8520640730857849, "value_dist": 0.35088393092155457, "value_other_env": 0.07315266877412796, "value_corner": 0.7674807906150818, "value_row": 0.23594896495342255, "value_any": 0.07311081886291504, "value_bot": 0.006562582217156887, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00308.png", "entropy": 0.6993242502212524} +{"ts": "2026-03-20T17:28:02.131092Z", "loop": 310, "env_steps": 190464000, "exact_value_avg": 0.3508613407611847, "regret_dist": 0.5127193927764893, "regret_other_env": 0.8090852499008179, "regret_corner": 0.06817051768302917, "regret_row": 0.6307359933853149, "regret_any": 0.8091627955436707, "regret_bot": 0.8515793085098267, "value_dist": 0.3508613407611847, "value_other_env": 0.07312964648008347, "value_corner": 0.7674588561058044, "value_row": 0.22789065539836884, "value_any": 0.07308785617351532, "value_bot": 0.007047319784760475, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00310.png", "entropy": 0.6996762752532959} +{"ts": "2026-03-20T17:28:03.875077Z", "loop": 312, "env_steps": 191692800, "exact_value_avg": 0.3504602313041687, "regret_dist": 0.5131204128265381, "regret_other_env": 0.8091475367546082, "regret_corner": 0.06907966732978821, "regret_row": 0.6384652256965637, "regret_any": 0.8092249631881714, "regret_bot": 0.8510863780975342, "value_dist": 0.3504602313041687, "value_other_env": 0.07306730002164841, "value_corner": 0.7665496468544006, "value_row": 0.22016143798828125, "value_any": 0.07302562147378922, "value_bot": 0.007540206890553236, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00312.png", "entropy": 0.6982093453407288} +{"ts": "2026-03-20T17:28:05.619978Z", "loop": 314, "env_steps": 192921600, "exact_value_avg": 0.34993821382522583, "regret_dist": 0.513642430305481, "regret_other_env": 0.809210479259491, "regret_corner": 0.07029039412736893, "regret_row": 0.6439330577850342, "regret_any": 0.8092877268791199, "regret_bot": 0.8507155776023865, "value_dist": 0.34993821382522583, "value_other_env": 0.07300437241792679, "value_corner": 0.7653389573097229, "value_row": 0.2146936058998108, "value_any": 0.07296280562877655, "value_bot": 0.00791105069220066, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00314.png", "entropy": 0.6961556673049927} +{"ts": "2026-03-20T17:28:07.362826Z", "loop": 316, "env_steps": 194150400, "exact_value_avg": 0.35035279393196106, "regret_dist": 0.5132278800010681, "regret_other_env": 0.8091511130332947, "regret_corner": 0.0693429484963417, "regret_row": 0.6397700905799866, "regret_any": 0.8092284798622131, "regret_bot": 0.8509939312934875, "value_dist": 0.35035279393196106, "value_other_env": 0.07306373864412308, "value_corner": 0.7662863731384277, "value_row": 0.218856543302536, "value_any": 0.07302207499742508, "value_bot": 0.007632732857018709, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00316.png", "entropy": 0.6981426477432251} +{"ts": "2026-03-20T17:28:09.105859Z", "loop": 318, "env_steps": 195379200, "exact_value_avg": 0.3507503867149353, "regret_dist": 0.5128302574157715, "regret_other_env": 0.8090838193893433, "regret_corner": 0.0684499517083168, "regret_row": 0.6337029337882996, "regret_any": 0.809161365032196, "regret_bot": 0.851381242275238, "value_dist": 0.3507503867149353, "value_other_env": 0.0731310322880745, "value_corner": 0.7671794295310974, "value_row": 0.22492367029190063, "value_any": 0.07308927178382874, "value_bot": 0.007245452143251896, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00318.png", "entropy": 0.6999347805976868} +{"ts": "2026-03-20T17:28:10.849570Z", "loop": 320, "env_steps": 196608000, "exact_value_avg": 0.35092201828956604, "regret_dist": 0.5126587152481079, "regret_other_env": 0.8090385794639587, "regret_corner": 0.0680888220667839, "regret_row": 0.6277456283569336, "regret_any": 0.8091161847114563, "regret_bot": 0.8517413139343262, "value_dist": 0.35092201828956604, "value_other_env": 0.073176309466362, "value_corner": 0.7675405144691467, "value_row": 0.2308809906244278, "value_any": 0.07313445955514908, "value_bot": 0.006885269191116095, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00320.png", "entropy": 0.7005419135093689} +{"ts": "2026-03-20T17:28:12.592578Z", "loop": 322, "env_steps": 197836800, "exact_value_avg": 0.35082411766052246, "regret_dist": 0.5127565860748291, "regret_other_env": 0.809014618396759, "regret_corner": 0.06836953014135361, "regret_row": 0.6205387711524963, "regret_any": 0.8090921640396118, "regret_bot": 0.8521609902381897, "value_dist": 0.35082411766052246, "value_other_env": 0.07320030778646469, "value_corner": 0.7672598361968994, "value_row": 0.23808784782886505, "value_any": 0.07315842807292938, "value_bot": 0.006465619895607233, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00322.png", "entropy": 0.7000380754470825} +{"ts": "2026-03-20T17:28:14.336388Z", "loop": 324, "env_steps": 199065600, "exact_value_avg": 0.35058438777923584, "regret_dist": 0.512996256351471, "regret_other_env": 0.8090099096298218, "regret_corner": 0.06897582113742828, "regret_row": 0.6158048510551453, "regret_any": 0.8090875744819641, "regret_bot": 0.8524225354194641, "value_dist": 0.35058438777923584, "value_other_env": 0.07320497184991837, "value_corner": 0.7666534781455994, "value_row": 0.2428217977285385, "value_any": 0.07316306978464127, "value_bot": 0.00620417483150959, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00324.png", "entropy": 0.699104905128479} +{"ts": "2026-03-20T17:28:16.078297Z", "loop": 326, "env_steps": 200294400, "exact_value_avg": 0.35015007853507996, "regret_dist": 0.513430655002594, "regret_other_env": 0.8090190291404724, "regret_corner": 0.07004804909229279, "regret_row": 0.6104445457458496, "regret_any": 0.8090965747833252, "regret_bot": 0.8527126312255859, "value_dist": 0.35015007853507996, "value_other_env": 0.0731959119439125, "value_corner": 0.7655813097953796, "value_row": 0.24818213284015656, "value_any": 0.073154017329216, "value_bot": 0.005914007779210806, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00326.png", "entropy": 0.6971918940544128} +{"ts": "2026-03-20T17:28:17.822500Z", "loop": 328, "env_steps": 201523200, "exact_value_avg": 0.34953969717025757, "regret_dist": 0.514041006565094, "regret_other_env": 0.8090420961380005, "regret_corner": 0.07153931260108948, "regret_row": 0.60524982213974, "regret_any": 0.8091196417808533, "regret_bot": 0.85298752784729, "value_dist": 0.34953969717025757, "value_other_env": 0.07317280769348145, "value_corner": 0.7640900015830994, "value_row": 0.2533768117427826, "value_any": 0.07313095033168793, "value_bot": 0.005639052949845791, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00328.png", "entropy": 0.6945846676826477} +{"ts": "2026-03-20T17:28:19.565900Z", "loop": 330, "env_steps": 202752000, "exact_value_avg": 0.34987902641296387, "regret_dist": 0.5137016773223877, "regret_other_env": 0.8090100288391113, "regret_corner": 0.07073904573917389, "regret_row": 0.6078984141349792, "regret_any": 0.8090876340866089, "regret_bot": 0.8528470993041992, "value_dist": 0.34987902641296387, "value_other_env": 0.07320483773946762, "value_corner": 0.7648903131484985, "value_row": 0.25072821974754333, "value_any": 0.07316292822360992, "value_bot": 0.005779562518000603, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00330.png", "entropy": 0.696483314037323} +{"ts": "2026-03-20T17:28:21.310255Z", "loop": 332, "env_steps": 203980800, "exact_value_avg": 0.3505614399909973, "regret_dist": 0.5130192637443542, "regret_other_env": 0.8089742064476013, "regret_corner": 0.06908673793077469, "regret_row": 0.6153400540351868, "regret_any": 0.8090518712997437, "regret_bot": 0.8524437546730042, "value_dist": 0.3505614399909973, "value_other_env": 0.07324063777923584, "value_corner": 0.7665426135063171, "value_row": 0.243286594748497, "value_any": 0.07319869101047516, "value_bot": 0.006182840093970299, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00332.png", "entropy": 0.6998814940452576} +{"ts": "2026-03-20T17:28:23.054711Z", "loop": 334, "env_steps": 205209600, "exact_value_avg": 0.3509066700935364, "regret_dist": 0.5126739740371704, "regret_other_env": 0.8089672923088074, "regret_corner": 0.06823404133319855, "regret_row": 0.6240962147712708, "regret_any": 0.8090449571609497, "regret_bot": 0.8519415259361267, "value_dist": 0.3509066700935364, "value_other_env": 0.0732475221157074, "value_corner": 0.7673953175544739, "value_row": 0.23453041911125183, "value_any": 0.07320559769868851, "value_bot": 0.006685089319944382, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00334.png", "entropy": 0.7020155787467957} +{"ts": "2026-03-20T17:28:24.798733Z", "loop": 336, "env_steps": 206438400, "exact_value_avg": 0.3507499694824219, "regret_dist": 0.5128306746482849, "regret_other_env": 0.8090048432350159, "regret_corner": 0.06856947392225266, "regret_row": 0.6333840489387512, "regret_any": 0.8090824484825134, "regret_bot": 0.8513702750205994, "value_dist": 0.3507499694824219, "value_other_env": 0.07321003824472427, "value_corner": 0.767059862613678, "value_row": 0.22524261474609375, "value_any": 0.07316818088293076, "value_bot": 0.007256305310875177, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00336.png", "entropy": 0.7018705606460571} +{"ts": "2026-03-20T17:28:26.542672Z", "loop": 338, "env_steps": 207667200, "exact_value_avg": 0.3503086566925049, "regret_dist": 0.5132719874382019, "regret_other_env": 0.8090598583221436, "regret_corner": 0.06959011405706406, "regret_row": 0.6398389339447021, "regret_any": 0.8091373443603516, "regret_bot": 0.850946307182312, "value_dist": 0.3503086566925049, "value_other_env": 0.0731549859046936, "value_corner": 0.7660391926765442, "value_row": 0.21878769993782043, "value_any": 0.07311322540044785, "value_bot": 0.007680344861000776, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00338.png", "entropy": 0.7002511620521545} +{"ts": "2026-03-20T17:28:28.283140Z", "loop": 340, "env_steps": 208896000, "exact_value_avg": 0.35012513399124146, "regret_dist": 0.5134556293487549, "regret_other_env": 0.8090618252754211, "regret_corner": 0.07004625350236893, "regret_row": 0.6416441202163696, "regret_any": 0.8091392517089844, "regret_bot": 0.8508152365684509, "value_dist": 0.35012513399124146, "value_other_env": 0.07315311580896378, "value_corner": 0.7655830979347229, "value_row": 0.21698249876499176, "value_any": 0.07311137020587921, "value_bot": 0.007811304647475481, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00340.png", "entropy": 0.6999374628067017} +{"ts": "2026-03-20T17:28:30.025602Z", "loop": 342, "env_steps": 210124800, "exact_value_avg": 0.3502200245857239, "regret_dist": 0.5133606195449829, "regret_other_env": 0.8090286254882812, "regret_corner": 0.06985865533351898, "regret_row": 0.6405547857284546, "regret_any": 0.8091060519218445, "regret_bot": 0.8508766889572144, "value_dist": 0.3502200245857239, "value_other_env": 0.07318632304668427, "value_corner": 0.7657706141471863, "value_row": 0.2180718034505844, "value_any": 0.07314453274011612, "value_bot": 0.007750025484710932, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00342.png", "entropy": 0.7007439732551575} +{"ts": "2026-03-20T17:28:31.767044Z", "loop": 344, "env_steps": 211353600, "exact_value_avg": 0.3505084216594696, "regret_dist": 0.5130723118782043, "regret_other_env": 0.8089659810066223, "regret_corner": 0.06923170387744904, "regret_row": 0.63702392578125, "regret_any": 0.8090435266494751, "regret_bot": 0.8511036038398743, "value_dist": 0.3505084216594696, "value_other_env": 0.07324893772602081, "value_corner": 0.7663976550102234, "value_row": 0.22160272300243378, "value_any": 0.07320705056190491, "value_bot": 0.007522988598793745, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00344.png", "entropy": 0.7025043964385986} +{"ts": "2026-03-20T17:28:33.508074Z", "loop": 346, "env_steps": 212582400, "exact_value_avg": 0.35074251890182495, "regret_dist": 0.5128381848335266, "regret_other_env": 0.8088994026184082, "regret_corner": 0.06874626874923706, "regret_row": 0.6327541470527649, "regret_any": 0.8089771270751953, "regret_bot": 0.8513733744621277, "value_dist": 0.35074251890182495, "value_other_env": 0.07331543415784836, "value_corner": 0.7668830752372742, "value_row": 0.2258724719285965, "value_any": 0.07327346503734589, "value_bot": 0.007253228221088648, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00346.png", "entropy": 0.7044450640678406} +{"ts": "2026-03-20T17:28:35.249693Z", "loop": 348, "env_steps": 213811200, "exact_value_avg": 0.35082823038101196, "regret_dist": 0.5127524733543396, "regret_other_env": 0.8088597655296326, "regret_corner": 0.06859146803617477, "regret_row": 0.6302338242530823, "regret_any": 0.8089374303817749, "regret_bot": 0.8515249490737915, "value_dist": 0.35082823038101196, "value_other_env": 0.07335516065359116, "value_corner": 0.7670378684997559, "value_row": 0.22839276492595673, "value_any": 0.0733131468296051, "value_bot": 0.00710174348205328, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00348.png", "entropy": 0.7053704857826233} +{"ts": "2026-03-20T17:28:36.992402Z", "loop": 350, "env_steps": 215040000, "exact_value_avg": 0.35089239478111267, "regret_dist": 0.5126882195472717, "regret_other_env": 0.8088304400444031, "regret_corner": 0.0684749186038971, "regret_row": 0.6264652609825134, "regret_any": 0.8089082837104797, "regret_bot": 0.851754367351532, "value_dist": 0.35089239478111267, "value_other_env": 0.07338441163301468, "value_corner": 0.7671543955802917, "value_row": 0.23216140270233154, "value_any": 0.07334234565496445, "value_bot": 0.006872250698506832, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00350.png", "entropy": 0.7058345079421997} +{"ts": "2026-03-20T17:28:38.735464Z", "loop": 352, "env_steps": 216268800, "exact_value_avg": 0.3508346378803253, "regret_dist": 0.5127459764480591, "regret_other_env": 0.8088001012802124, "regret_corner": 0.06866477429866791, "regret_row": 0.6211254000663757, "regret_any": 0.8088780045509338, "regret_bot": 0.8520671129226685, "value_dist": 0.3508346378803253, "value_other_env": 0.07341470569372177, "value_corner": 0.7669645547866821, "value_row": 0.23750123381614685, "value_any": 0.07337260246276855, "value_bot": 0.00655945623293519, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00352.png", "entropy": 0.7058380246162415} +{"ts": "2026-03-20T17:28:40.478540Z", "loop": 354, "env_steps": 217497600, "exact_value_avg": 0.3507630228996277, "regret_dist": 0.5128176808357239, "regret_other_env": 0.808785080909729, "regret_corner": 0.06886647641658783, "regret_row": 0.6190522909164429, "regret_any": 0.8088629245758057, "regret_bot": 0.8521826267242432, "value_dist": 0.3507630228996277, "value_other_env": 0.07342977076768875, "value_corner": 0.7667628526687622, "value_row": 0.2395744025707245, "value_any": 0.07338763028383255, "value_bot": 0.0064439307898283005, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00354.png", "entropy": 0.7057799100875854} +{"ts": "2026-03-20T17:28:42.221290Z", "loop": 356, "env_steps": 218726400, "exact_value_avg": 0.35079100728034973, "regret_dist": 0.5127897262573242, "regret_other_env": 0.808767557144165, "regret_corner": 0.06882289052009583, "regret_row": 0.6196858882904053, "regret_any": 0.8088454604148865, "regret_bot": 0.8521365523338318, "value_dist": 0.35079100728034973, "value_other_env": 0.07344735413789749, "value_corner": 0.766806423664093, "value_row": 0.2389407455921173, "value_any": 0.0734051913022995, "value_bot": 0.006489998660981655, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00356.png", "entropy": 0.7062085270881653} +{"ts": "2026-03-20T17:28:43.965175Z", "loop": 358, "env_steps": 219955200, "exact_value_avg": 0.35075581073760986, "regret_dist": 0.5128248929977417, "regret_other_env": 0.8087629675865173, "regret_corner": 0.06891777366399765, "regret_row": 0.6188193559646606, "regret_any": 0.808840811252594, "regret_bot": 0.8521833419799805, "value_dist": 0.35075581073760986, "value_other_env": 0.07345196604728699, "value_corner": 0.7667115330696106, "value_row": 0.23980730772018433, "value_any": 0.0734097957611084, "value_bot": 0.006443191319704056, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00358.png", "entropy": 0.7061368823051453} +{"ts": "2026-03-20T17:28:45.709409Z", "loop": 360, "env_steps": 221184000, "exact_value_avg": 0.35076814889907837, "regret_dist": 0.5128125548362732, "regret_other_env": 0.8087640404701233, "regret_corner": 0.06888531148433685, "regret_row": 0.6189758777618408, "regret_any": 0.8088418841362, "regret_bot": 0.8521744608879089, "value_dist": 0.35076814889907837, "value_other_env": 0.07345087826251984, "value_corner": 0.7667440176010132, "value_row": 0.23965071141719818, "value_any": 0.07340871542692184, "value_bot": 0.0064521655440330505, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00360.png", "entropy": 0.7061600089073181} +{"ts": "2026-03-20T17:28:47.452782Z", "loop": 362, "env_steps": 222412800, "exact_value_avg": 0.3508315980434418, "regret_dist": 0.5127491354942322, "regret_other_env": 0.808768630027771, "regret_corner": 0.0687197744846344, "regret_row": 0.6208613514900208, "regret_any": 0.8088465332984924, "regret_bot": 0.8520645499229431, "value_dist": 0.3508315980434418, "value_other_env": 0.07344622164964676, "value_corner": 0.7669095993041992, "value_row": 0.23776531219482422, "value_any": 0.07340407371520996, "value_bot": 0.006562157068401575, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00362.png", "entropy": 0.7063496708869934} +{"ts": "2026-03-20T17:28:49.194936Z", "loop": 364, "env_steps": 223641600, "exact_value_avg": 0.35086631774902344, "regret_dist": 0.5127143263816833, "regret_other_env": 0.8087834119796753, "regret_corner": 0.06861075013875961, "regret_row": 0.6220076680183411, "regret_any": 0.8088611960411072, "regret_bot": 0.8520017266273499, "value_dist": 0.35086631774902344, "value_other_env": 0.07343148440122604, "value_corner": 0.7670185565948486, "value_row": 0.23661896586418152, "value_any": 0.07338934391736984, "value_bot": 0.0066248285584151745, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00364.png", "entropy": 0.7061136364936829} +{"ts": "2026-03-20T17:28:50.937500Z", "loop": 366, "env_steps": 224870400, "exact_value_avg": 0.3509058356285095, "regret_dist": 0.5126748085021973, "regret_other_env": 0.8088164329528809, "regret_corner": 0.06846235692501068, "regret_row": 0.6256263852119446, "regret_any": 0.8088942766189575, "regret_bot": 0.8517922759056091, "value_dist": 0.3509058356285095, "value_other_env": 0.07339842617511749, "value_corner": 0.7671669125556946, "value_row": 0.23300021886825562, "value_any": 0.07335633784532547, "value_bot": 0.006834325380623341, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00366.png", "entropy": 0.70570969581604} +{"ts": "2026-03-20T17:28:52.680113Z", "loop": 368, "env_steps": 226099200, "exact_value_avg": 0.35080087184906006, "regret_dist": 0.5127798318862915, "regret_other_env": 0.808857262134552, "regret_corner": 0.06866373121738434, "regret_row": 0.6313529014587402, "regret_any": 0.8089349865913391, "regret_bot": 0.8514450192451477, "value_dist": 0.35080087184906006, "value_other_env": 0.07335764169692993, "value_corner": 0.7669656276702881, "value_row": 0.22727371752262115, "value_any": 0.07331562042236328, "value_bot": 0.00718165235593915, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00368.png", "entropy": 0.7051018476486206} +{"ts": "2026-03-20T17:28:54.429161Z", "loop": 370, "env_steps": 227328000, "exact_value_avg": 0.35059356689453125, "regret_dist": 0.5129871368408203, "regret_other_env": 0.8088945150375366, "regret_corner": 0.06912604719400406, "regret_row": 0.6354941129684448, "regret_any": 0.808972179889679, "regret_bot": 0.8511813879013062, "value_dist": 0.35059356689453125, "value_other_env": 0.07332037389278412, "value_corner": 0.7665033340454102, "value_row": 0.22313250601291656, "value_any": 0.07327840477228165, "value_bot": 0.007445246912539005, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00370.png", "entropy": 0.7041640281677246} +{"ts": "2026-03-20T17:28:56.171263Z", "loop": 372, "env_steps": 228556800, "exact_value_avg": 0.35036563873291016, "regret_dist": 0.5132150053977966, "regret_other_env": 0.808937132358551, "regret_corner": 0.06963185220956802, "regret_row": 0.6386623978614807, "regret_any": 0.8090147972106934, "regret_bot": 0.8509793281555176, "value_dist": 0.35036563873291016, "value_other_env": 0.07327777147293091, "value_corner": 0.7659974694252014, "value_row": 0.21996425092220306, "value_any": 0.07323586940765381, "value_bot": 0.007647286634892225, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00372.png", "entropy": 0.702954113483429} +{"ts": "2026-03-20T17:28:57.913956Z", "loop": 374, "env_steps": 229785600, "exact_value_avg": 0.35046061873435974, "regret_dist": 0.5131200551986694, "regret_other_env": 0.8089397549629211, "regret_corner": 0.0693904310464859, "regret_row": 0.637453556060791, "regret_any": 0.8090174198150635, "regret_bot": 0.8510743975639343, "value_dist": 0.35046061873435974, "value_other_env": 0.0732751190662384, "value_corner": 0.7662388682365417, "value_row": 0.22117304801940918, "value_any": 0.0732332319021225, "value_bot": 0.007552298251539469, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00374.png", "entropy": 0.7032280564308167} +{"ts": "2026-03-20T17:28:59.658744Z", "loop": 376, "env_steps": 231014400, "exact_value_avg": 0.35065650939941406, "regret_dist": 0.5129241943359375, "regret_other_env": 0.808914840221405, "regret_corner": 0.06893820315599442, "regret_row": 0.6345176100730896, "regret_any": 0.8089924454689026, "regret_bot": 0.8512711524963379, "value_dist": 0.35065650939941406, "value_other_env": 0.07330003380775452, "value_corner": 0.7666911482810974, "value_row": 0.2241089940071106, "value_any": 0.07325808703899384, "value_bot": 0.007355405017733574, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00376.png", "entropy": 0.7040808200836182} +{"ts": "2026-03-20T17:29:01.401430Z", "loop": 378, "env_steps": 232243200, "exact_value_avg": 0.3508679270744324, "regret_dist": 0.5127127766609192, "regret_other_env": 0.8088604807853699, "regret_corner": 0.06849116086959839, "regret_row": 0.6291449666023254, "regret_any": 0.8089382648468018, "regret_bot": 0.8516054749488831, "value_dist": 0.3508679270744324, "value_other_env": 0.07335436344146729, "value_corner": 0.7671381831169128, "value_row": 0.22948171198368073, "value_any": 0.07331232726573944, "value_bot": 0.007021172437816858, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00378.png", "entropy": 0.7052448987960815} +{"ts": "2026-03-20T17:29:03.146137Z", "loop": 380, "env_steps": 233472000, "exact_value_avg": 0.35090208053588867, "regret_dist": 0.5126786231994629, "regret_other_env": 0.808828592300415, "regret_corner": 0.06845357269048691, "regret_row": 0.623862624168396, "regret_any": 0.8089064359664917, "regret_bot": 0.8519201874732971, "value_dist": 0.35090208053588867, "value_other_env": 0.07338625937700272, "value_corner": 0.7671757340431213, "value_row": 0.23476403951644897, "value_any": 0.0733441710472107, "value_bot": 0.00670642452314496, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00380.png", "entropy": 0.7053987383842468} +{"ts": "2026-03-20T17:29:04.888057Z", "loop": 382, "env_steps": 234700800, "exact_value_avg": 0.3507581651210785, "regret_dist": 0.5128225088119507, "regret_other_env": 0.8088216185569763, "regret_corner": 0.06882380694150925, "regret_row": 0.6184962391853333, "regret_any": 0.8088994026184082, "regret_bot": 0.8522285223007202, "value_dist": 0.3507581651210785, "value_other_env": 0.07339327037334442, "value_corner": 0.7668054699897766, "value_row": 0.24013039469718933, "value_any": 0.07335115969181061, "value_bot": 0.006398098077625036, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00382.png", "entropy": 0.7044795751571655} +{"ts": "2026-03-20T17:29:06.634248Z", "loop": 384, "env_steps": 235929600, "exact_value_avg": 0.3505306839942932, "regret_dist": 0.5130500197410583, "regret_other_env": 0.8088234066963196, "regret_corner": 0.06938991695642471, "regret_row": 0.614450991153717, "regret_any": 0.8089011311531067, "regret_bot": 0.852451741695404, "value_dist": 0.3505306839942932, "value_other_env": 0.07339151948690414, "value_corner": 0.7662394046783447, "value_row": 0.24417568743228912, "value_any": 0.07334941625595093, "value_bot": 0.006174910813570023, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00384.png", "entropy": 0.7033079862594604} +{"ts": "2026-03-20T17:29:08.378260Z", "loop": 386, "env_steps": 237158400, "exact_value_avg": 0.3504917621612549, "regret_dist": 0.5130889415740967, "regret_other_env": 0.8088259696960449, "regret_corner": 0.06948337703943253, "regret_row": 0.613877534866333, "regret_any": 0.8089038133621216, "regret_bot": 0.8524817228317261, "value_dist": 0.3504917621612549, "value_other_env": 0.07338889688253403, "value_corner": 0.7661460041999817, "value_row": 0.24474911391735077, "value_any": 0.07334679365158081, "value_bot": 0.006144907791167498, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00386.png", "entropy": 0.7030833959579468} +{"ts": "2026-03-20T17:29:10.118790Z", "loop": 388, "env_steps": 238387200, "exact_value_avg": 0.35064542293548584, "regret_dist": 0.5129352807998657, "regret_other_env": 0.8088204264640808, "regret_corner": 0.0691075325012207, "regret_row": 0.6161379814147949, "regret_any": 0.8088982701301575, "regret_bot": 0.852350115776062, "value_dist": 0.35064542293548584, "value_other_env": 0.07339448481798172, "value_corner": 0.7665218114852905, "value_row": 0.24248874187469482, "value_any": 0.0733523815870285, "value_bot": 0.006276538595557213, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00388.png", "entropy": 0.7037992477416992} +{"ts": "2026-03-20T17:29:11.861054Z", "loop": 390, "env_steps": 239616000, "exact_value_avg": 0.3508392870426178, "regret_dist": 0.5127413868904114, "regret_other_env": 0.808822751045227, "regret_corner": 0.06861937046051025, "regret_row": 0.620354950428009, "regret_any": 0.8089004755020142, "regret_bot": 0.8521081805229187, "value_dist": 0.3508392870426178, "value_other_env": 0.07339217513799667, "value_corner": 0.7670099139213562, "value_row": 0.23827165365219116, "value_any": 0.07335008680820465, "value_bot": 0.0065184300765395164, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00390.png", "entropy": 0.7047200798988342} +{"ts": "2026-03-20T17:29:13.604859Z", "loop": 392, "env_steps": 240844800, "exact_value_avg": 0.3508773446083069, "regret_dist": 0.5127033591270447, "regret_other_env": 0.8088288307189941, "regret_corner": 0.06851503252983093, "regret_row": 0.6217500567436218, "regret_any": 0.8089066743850708, "regret_bot": 0.8520267009735107, "value_dist": 0.3508773446083069, "value_other_env": 0.073386050760746, "value_corner": 0.7671142816543579, "value_row": 0.23687660694122314, "value_any": 0.07334395498037338, "value_bot": 0.006599933374673128, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00392.png", "entropy": 0.7048344016075134} +{"ts": "2026-03-20T17:29:15.345834Z", "loop": 394, "env_steps": 242073600, "exact_value_avg": 0.3509180247783661, "regret_dist": 0.5126626491546631, "regret_other_env": 0.8088245391845703, "regret_corner": 0.06841979920864105, "regret_row": 0.6253750920295715, "regret_any": 0.8089022636413574, "regret_bot": 0.851805567741394, "value_dist": 0.3509180247783661, "value_other_env": 0.07339037209749222, "value_corner": 0.767209529876709, "value_row": 0.23325152695178986, "value_any": 0.0733482837677002, "value_bot": 0.006821093149483204, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00394.png", "entropy": 0.7054940462112427} +{"ts": "2026-03-20T17:29:17.092216Z", "loop": 396, "env_steps": 243302400, "exact_value_avg": 0.3509197533130646, "regret_dist": 0.5126609206199646, "regret_other_env": 0.8088261485099792, "regret_corner": 0.06841301918029785, "regret_row": 0.6262547373771667, "regret_any": 0.8089039921760559, "regret_bot": 0.8517563343048096, "value_dist": 0.3509197533130646, "value_other_env": 0.0733887329697609, "value_corner": 0.7672162652015686, "value_row": 0.23237191140651703, "value_any": 0.07334665954113007, "value_bot": 0.00687035545706749, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00396.png", "entropy": 0.7055716514587402} +{"ts": "2026-03-20T17:29:18.832306Z", "loop": 398, "env_steps": 244531200, "exact_value_avg": 0.3509211540222168, "regret_dist": 0.51265949010849, "regret_other_env": 0.8088224530220032, "regret_corner": 0.06841506063938141, "regret_row": 0.6244292259216309, "regret_any": 0.8089002370834351, "regret_bot": 0.8518699407577515, "value_dist": 0.3509211540222168, "value_other_env": 0.07339246571063995, "value_corner": 0.7672142386436462, "value_row": 0.23419736325740814, "value_any": 0.07335036993026733, "value_bot": 0.006756632588803768, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00398.png", "entropy": 0.7054348587989807} +{"ts": "2026-03-20T17:29:20.573884Z", "loop": 400, "env_steps": 245760000, "exact_value_avg": 0.3508724272251129, "regret_dist": 0.5127082467079163, "regret_other_env": 0.808827817440033, "regret_corner": 0.06852887570858002, "regret_row": 0.6214103698730469, "regret_any": 0.8089056611061096, "regret_bot": 0.8520559072494507, "value_dist": 0.3508724272251129, "value_other_env": 0.07338705658912659, "value_corner": 0.76710045337677, "value_row": 0.23721621930599213, "value_any": 0.07334497570991516, "value_bot": 0.006570673547685146, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00400.png", "entropy": 0.7048683762550354} +{"ts": "2026-03-20T17:29:22.315912Z", "loop": 402, "env_steps": 246988800, "exact_value_avg": 0.3505437672138214, "regret_dist": 0.5130369067192078, "regret_other_env": 0.8088366389274597, "regret_corner": 0.06933721154928207, "regret_row": 0.6145204305648804, "regret_any": 0.8089145421981812, "regret_bot": 0.8524539470672607, "value_dist": 0.3505437672138214, "value_other_env": 0.07337818294763565, "value_corner": 0.7662920951843262, "value_row": 0.2441062182188034, "value_any": 0.07333609461784363, "value_bot": 0.006172674708068371, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00402.png", "entropy": 0.7032368183135986} +{"ts": "2026-03-20T17:29:24.057799Z", "loop": 404, "env_steps": 248217600, "exact_value_avg": 0.3503723740577698, "regret_dist": 0.513208270072937, "regret_other_env": 0.8088381886482239, "regret_corner": 0.06976332515478134, "regret_row": 0.6122684478759766, "regret_any": 0.8089160919189453, "regret_bot": 0.8525778651237488, "value_dist": 0.3503723740577698, "value_other_env": 0.07337664812803268, "value_corner": 0.7658659815788269, "value_row": 0.24635814130306244, "value_any": 0.07333455979824066, "value_bot": 0.0060487473383545876, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00404.png", "entropy": 0.7026172876358032} +{"ts": "2026-03-20T17:29:25.799389Z", "loop": 406, "env_steps": 249446400, "exact_value_avg": 0.35064995288848877, "regret_dist": 0.512930691242218, "regret_other_env": 0.8088274598121643, "regret_corner": 0.0690855011343956, "regret_row": 0.6161088347434998, "regret_any": 0.8089053630828857, "regret_bot": 0.8523626923561096, "value_dist": 0.35064995288848877, "value_other_env": 0.07338733226060867, "value_corner": 0.7665438652038574, "value_row": 0.24251782894134521, "value_any": 0.07334524393081665, "value_bot": 0.006263958755880594, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00406.png", "entropy": 0.7039694786071777} +{"ts": "2026-03-20T17:29:27.542382Z", "loop": 408, "env_steps": 250675200, "exact_value_avg": 0.35090890526771545, "regret_dist": 0.5126717686653137, "regret_other_env": 0.8088371753692627, "regret_corner": 0.06842359155416489, "regret_row": 0.6226695775985718, "regret_any": 0.8089150190353394, "regret_bot": 0.851982593536377, "value_dist": 0.35090890526771545, "value_other_env": 0.07337767630815506, "value_corner": 0.7672057151794434, "value_row": 0.2359570562839508, "value_any": 0.07333559542894363, "value_bot": 0.006644025444984436, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00408.png", "entropy": 0.7049127817153931} +{"ts": "2026-03-20T17:29:29.283962Z", "loop": 410, "env_steps": 251904000, "exact_value_avg": 0.3508942723274231, "regret_dist": 0.5126864314079285, "regret_other_env": 0.8088551163673401, "regret_corner": 0.06843342632055283, "regret_row": 0.6291329264640808, "regret_any": 0.8089328408241272, "regret_bot": 0.8515827059745789, "value_dist": 0.3508942723274231, "value_other_env": 0.07335982471704483, "value_corner": 0.7671959400177002, "value_row": 0.22949372231960297, "value_any": 0.07331778854131699, "value_bot": 0.0070438929833471775, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00410.png", "entropy": 0.7049785852432251} +{"ts": "2026-03-20T17:29:31.024957Z", "loop": 412, "env_steps": 253132800, "exact_value_avg": 0.3506786823272705, "regret_dist": 0.5129019618034363, "regret_other_env": 0.80888432264328, "regret_corner": 0.06892844289541245, "regret_row": 0.634452223777771, "regret_any": 0.8089620471000671, "regret_bot": 0.8512317538261414, "value_dist": 0.3506786823272705, "value_other_env": 0.07333051413297653, "value_corner": 0.7667009234428406, "value_row": 0.22417442500591278, "value_any": 0.07328851521015167, "value_bot": 0.0073948148638010025, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00412.png", "entropy": 0.7040905356407166} +{"ts": "2026-03-20T17:29:32.765854Z", "loop": 414, "env_steps": 254361600, "exact_value_avg": 0.35055872797966003, "regret_dist": 0.5130219459533691, "regret_other_env": 0.8088957667350769, "regret_corner": 0.06921122968196869, "regret_row": 0.6361927390098572, "regret_any": 0.8089733719825745, "regret_bot": 0.8511160612106323, "value_dist": 0.35055872797966003, "value_other_env": 0.07331910729408264, "value_corner": 0.7664180994033813, "value_row": 0.22243383526802063, "value_any": 0.07327715307474136, "value_bot": 0.007510549854487181, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00414.png", "entropy": 0.7037405371665955} +{"ts": "2026-03-20T17:29:34.507897Z", "loop": 416, "env_steps": 255590400, "exact_value_avg": 0.35067299008369446, "regret_dist": 0.5129076838493347, "regret_other_env": 0.8088933825492859, "regret_corner": 0.06892911344766617, "regret_row": 0.6346620321273804, "regret_any": 0.808971107006073, "regret_bot": 0.8512308597564697, "value_dist": 0.35067299008369446, "value_other_env": 0.07332149893045425, "value_corner": 0.7667002081871033, "value_row": 0.2239646166563034, "value_any": 0.07327953726053238, "value_bot": 0.007395718712359667, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00416.png", "entropy": 0.704097330570221} +{"ts": "2026-03-20T17:29:36.248192Z", "loop": 418, "env_steps": 256819200, "exact_value_avg": 0.3508095145225525, "regret_dist": 0.5127711892127991, "regret_other_env": 0.8088821768760681, "regret_corner": 0.06860465556383133, "regret_row": 0.6318333148956299, "regret_any": 0.8089598417282104, "regret_bot": 0.851425051689148, "value_dist": 0.3508095145225525, "value_other_env": 0.07333271950483322, "value_corner": 0.7670246362686157, "value_row": 0.2267933338880539, "value_any": 0.07329072058200836, "value_bot": 0.00720160361379385, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00418.png", "entropy": 0.7046177387237549} +{"ts": "2026-03-20T17:29:37.990216Z", "loop": 420, "env_steps": 258048000, "exact_value_avg": 0.3508757948875427, "regret_dist": 0.5127048492431641, "regret_other_env": 0.8088670969009399, "regret_corner": 0.06846150010824203, "regret_row": 0.6299124956130981, "regret_any": 0.8089448809623718, "regret_bot": 0.8515478372573853, "value_dist": 0.3508757948875427, "value_other_env": 0.0733477845788002, "value_corner": 0.7671678066253662, "value_row": 0.22871412336826324, "value_any": 0.07330577820539474, "value_bot": 0.00707878777757287, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00420.png", "entropy": 0.7049561738967896} +{"ts": "2026-03-20T17:29:39.731881Z", "loop": 422, "env_steps": 259276800, "exact_value_avg": 0.3509003520011902, "regret_dist": 0.5126802921295166, "regret_other_env": 0.8088696599006653, "regret_corner": 0.06839622557163239, "regret_row": 0.6291798949241638, "regret_any": 0.8089473843574524, "regret_bot": 0.8515942096710205, "value_dist": 0.3509003520011902, "value_other_env": 0.07334516197443008, "value_corner": 0.76723313331604, "value_row": 0.22944676876068115, "value_any": 0.07330314069986343, "value_bot": 0.0070323944091796875, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00422.png", "entropy": 0.7047920227050781} +{"ts": "2026-03-20T17:29:41.476061Z", "loop": 424, "env_steps": 260505600, "exact_value_avg": 0.350891649723053, "regret_dist": 0.5126890540122986, "regret_other_env": 0.808869481086731, "regret_corner": 0.06841844320297241, "regret_row": 0.6295881867408752, "regret_any": 0.8089472651481628, "regret_bot": 0.8515635132789612, "value_dist": 0.350891649723053, "value_other_env": 0.07334543019533157, "value_corner": 0.7672109007835388, "value_row": 0.22903849184513092, "value_any": 0.07330340147018433, "value_bot": 0.007063122000545263, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00424.png", "entropy": 0.7046160101890564} +{"ts": "2026-03-20T17:29:43.217876Z", "loop": 426, "env_steps": 261734400, "exact_value_avg": 0.35090962052345276, "regret_dist": 0.5126710534095764, "regret_other_env": 0.8088706731796265, "regret_corner": 0.06837163120508194, "regret_row": 0.6290072798728943, "regret_any": 0.8089485168457031, "regret_bot": 0.8515974283218384, "value_dist": 0.35090962052345276, "value_other_env": 0.07334419339895248, "value_corner": 0.7672576904296875, "value_row": 0.22961930930614471, "value_any": 0.07330216467380524, "value_bot": 0.007029222324490547, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00426.png", "entropy": 0.7044315338134766} +{"ts": "2026-03-20T17:29:44.959052Z", "loop": 428, "env_steps": 262963200, "exact_value_avg": 0.35093316435813904, "regret_dist": 0.5126475095748901, "regret_other_env": 0.8088541626930237, "regret_corner": 0.06833748519420624, "regret_row": 0.6273719072341919, "regret_any": 0.8089319467544556, "regret_bot": 0.8516945242881775, "value_dist": 0.35093316435813904, "value_other_env": 0.07336074858903885, "value_corner": 0.767291784286499, "value_row": 0.2312547117471695, "value_any": 0.07331869751214981, "value_bot": 0.006932158023118973, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00428.png", "entropy": 0.7047144174575806} +{"ts": "2026-03-20T17:29:46.701428Z", "loop": 430, "env_steps": 264192000, "exact_value_avg": 0.3509419560432434, "regret_dist": 0.5126386880874634, "regret_other_env": 0.8088380098342896, "regret_corner": 0.06833968311548233, "regret_row": 0.6257436871528625, "regret_any": 0.8089157938957214, "regret_bot": 0.8517909646034241, "value_dist": 0.3509419560432434, "value_other_env": 0.0733768567442894, "value_corner": 0.7672896385192871, "value_row": 0.23288296163082123, "value_any": 0.07333478331565857, "value_bot": 0.0068356432020664215, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00430.png", "entropy": 0.7050977945327759} +{"ts": "2026-03-20T17:29:48.445704Z", "loop": 432, "env_steps": 265420800, "exact_value_avg": 0.3509237766265869, "regret_dist": 0.5126568675041199, "regret_other_env": 0.8088402152061462, "regret_corner": 0.06838186830282211, "regret_row": 0.627674400806427, "regret_any": 0.8089179396629333, "regret_bot": 0.8516708612442017, "value_dist": 0.3509237766265869, "value_other_env": 0.0733746811747551, "value_corner": 0.7672474384307861, "value_row": 0.2309522181749344, "value_any": 0.07333263009786606, "value_bot": 0.006955756340175867, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00432.png", "entropy": 0.7053148746490479} +{"ts": "2026-03-20T17:29:50.190076Z", "loop": 434, "env_steps": 266649600, "exact_value_avg": 0.3508698344230652, "regret_dist": 0.5127108693122864, "regret_other_env": 0.8088392019271851, "regret_corner": 0.0685182735323906, "regret_row": 0.6299834251403809, "regret_any": 0.8089169859886169, "regret_bot": 0.8515204191207886, "value_dist": 0.3508698344230652, "value_other_env": 0.0733756572008133, "value_corner": 0.76711106300354, "value_row": 0.2286432385444641, "value_any": 0.07333359867334366, "value_bot": 0.007106195669621229, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00434.png", "entropy": 0.7054468989372253} +{"ts": "2026-03-20T17:29:51.935161Z", "loop": 436, "env_steps": 267878400, "exact_value_avg": 0.3508572578430176, "regret_dist": 0.5127233862876892, "regret_other_env": 0.8088269829750061, "regret_corner": 0.0685679167509079, "regret_row": 0.6303758025169373, "regret_any": 0.8089048266410828, "regret_bot": 0.8514837026596069, "value_dist": 0.3508572578430176, "value_other_env": 0.07338783144950867, "value_corner": 0.7670614123344421, "value_row": 0.2282508760690689, "value_any": 0.07334578037261963, "value_bot": 0.007143040653318167, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00436.png", "entropy": 0.7056015133857727} +{"ts": "2026-03-20T17:29:53.679818Z", "loop": 438, "env_steps": 269107200, "exact_value_avg": 0.3509001135826111, "regret_dist": 0.5126805305480957, "regret_other_env": 0.8088056445121765, "regret_corner": 0.0684928297996521, "regret_row": 0.6289498805999756, "regret_any": 0.808883547782898, "regret_bot": 0.8515704274177551, "value_dist": 0.3509001135826111, "value_other_env": 0.07340916991233826, "value_corner": 0.7671365141868591, "value_row": 0.2296767234802246, "value_any": 0.07336707413196564, "value_bot": 0.007056192494928837, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00438.png", "entropy": 0.705963134765625} +{"ts": "2026-03-20T17:29:55.422401Z", "loop": 440, "env_steps": 270336000, "exact_value_avg": 0.35089993476867676, "regret_dist": 0.5126807689666748, "regret_other_env": 0.8088138699531555, "regret_corner": 0.06848104298114777, "regret_row": 0.6291518211364746, "regret_any": 0.8088917136192322, "regret_bot": 0.851564347743988, "value_dist": 0.35089993476867676, "value_other_env": 0.07340103387832642, "value_corner": 0.7671482563018799, "value_row": 0.22947479784488678, "value_any": 0.0733589455485344, "value_bot": 0.007062291726469994, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00440.png", "entropy": 0.7057575583457947} +{"ts": "2026-03-20T17:29:57.165512Z", "loop": 442, "env_steps": 271564800, "exact_value_avg": 0.3508604168891907, "regret_dist": 0.5127202868461609, "regret_other_env": 0.8088246583938599, "regret_corner": 0.06856364011764526, "regret_row": 0.6305205821990967, "regret_any": 0.8089024424552917, "regret_bot": 0.8514837622642517, "value_dist": 0.3508604168891907, "value_other_env": 0.07339026778936386, "value_corner": 0.7670656442642212, "value_row": 0.2281060367822647, "value_any": 0.07334819436073303, "value_bot": 0.007142883259803057, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00442.png", "entropy": 0.7055718302726746} +{"ts": "2026-03-20T17:29:58.909835Z", "loop": 444, "env_steps": 272793600, "exact_value_avg": 0.3507808446884155, "regret_dist": 0.512799859046936, "regret_other_env": 0.8088507056236267, "regret_corner": 0.06872350722551346, "regret_row": 0.6326304078102112, "regret_any": 0.8089284300804138, "regret_bot": 0.8513584733009338, "value_dist": 0.3507808446884155, "value_other_env": 0.07336417585611343, "value_corner": 0.7669058442115784, "value_row": 0.22599618136882782, "value_any": 0.07332213968038559, "value_bot": 0.007268224842846394, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00444.png", "entropy": 0.7050684094429016} +{"ts": "2026-03-20T17:30:00.653667Z", "loop": 446, "env_steps": 274022400, "exact_value_avg": 0.3507034182548523, "regret_dist": 0.5128772258758545, "regret_other_env": 0.8088725805282593, "regret_corner": 0.06888410449028015, "regret_row": 0.6342153549194336, "regret_any": 0.8089503049850464, "regret_bot": 0.8512639403343201, "value_dist": 0.3507034182548523, "value_other_env": 0.07334227114915848, "value_corner": 0.7667451500892639, "value_row": 0.2244112342596054, "value_any": 0.07330027967691422, "value_bot": 0.007362669799476862, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00446.png", "entropy": 0.7046860456466675} +{"ts": "2026-03-20T17:30:02.398818Z", "loop": 448, "env_steps": 275251200, "exact_value_avg": 0.35075482726097107, "regret_dist": 0.5128258466720581, "regret_other_env": 0.8088777661323547, "regret_corner": 0.0687478557229042, "regret_row": 0.6332787275314331, "regret_any": 0.8089555501937866, "regret_bot": 0.8513293266296387, "value_dist": 0.35075482726097107, "value_other_env": 0.07333706319332123, "value_corner": 0.7668814659118652, "value_row": 0.22534792125225067, "value_any": 0.07329507172107697, "value_bot": 0.007297280244529247, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00448.png", "entropy": 0.7046469449996948} +{"ts": "2026-03-20T17:30:04.147493Z", "loop": 450, "env_steps": 276480000, "exact_value_avg": 0.3508993089199066, "regret_dist": 0.5126813650131226, "regret_other_env": 0.8088600635528564, "regret_corner": 0.06841327995061874, "regret_row": 0.6298424601554871, "regret_any": 0.8089377880096436, "regret_bot": 0.8515456318855286, "value_dist": 0.3508993089199066, "value_other_env": 0.07335484027862549, "value_corner": 0.7672160267829895, "value_row": 0.22878417372703552, "value_any": 0.07331282645463943, "value_bot": 0.007080927491188049, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00450.png", "entropy": 0.7049122452735901} +{"ts": "2026-03-20T17:30:05.889389Z", "loop": 452, "env_steps": 277708800, "exact_value_avg": 0.3509611487388611, "regret_dist": 0.5126195549964905, "regret_other_env": 0.8088459968566895, "regret_corner": 0.06827982515096664, "regret_row": 0.626252293586731, "regret_any": 0.8089237213134766, "regret_bot": 0.8517600297927856, "value_dist": 0.3509611487388611, "value_other_env": 0.07336888462305069, "value_corner": 0.7673495411872864, "value_row": 0.23237431049346924, "value_any": 0.07332683354616165, "value_bot": 0.006866664160043001, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00452.png", "entropy": 0.7047591805458069} +{"ts": "2026-03-20T17:30:07.631661Z", "loop": 454, "env_steps": 278937600, "exact_value_avg": 0.35093820095062256, "regret_dist": 0.512642502784729, "regret_other_env": 0.8088322877883911, "regret_corner": 0.06835778802633286, "regret_row": 0.6225602030754089, "regret_any": 0.8089100122451782, "regret_bot": 0.8519759178161621, "value_dist": 0.35093820095062256, "value_other_env": 0.07338263839483261, "value_corner": 0.7672715187072754, "value_row": 0.23606644570827484, "value_any": 0.07334055006504059, "value_bot": 0.006650702096521854, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00454.png", "entropy": 0.7044427394866943} +{"ts": "2026-03-20T17:30:09.375420Z", "loop": 456, "env_steps": 280166400, "exact_value_avg": 0.35091152787208557, "regret_dist": 0.5126692056655884, "regret_other_env": 0.8088180422782898, "regret_corner": 0.0684458464384079, "regret_row": 0.6214568614959717, "regret_any": 0.8088958859443665, "regret_bot": 0.8520315289497375, "value_dist": 0.35091152787208557, "value_other_env": 0.07339686900377274, "value_corner": 0.7671834826469421, "value_row": 0.2371697574853897, "value_any": 0.07335475832223892, "value_bot": 0.0065950797870755196, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00456.png", "entropy": 0.7044642567634583} +{"ts": "2026-03-20T17:30:11.118995Z", "loop": 458, "env_steps": 281395200, "exact_value_avg": 0.3509508967399597, "regret_dist": 0.5126297473907471, "regret_other_env": 0.8088051676750183, "regret_corner": 0.06836660951375961, "regret_row": 0.6235113739967346, "regret_any": 0.8088830709457397, "regret_bot": 0.8519039750099182, "value_dist": 0.3509508967399597, "value_other_env": 0.07340969145298004, "value_corner": 0.7672626972198486, "value_row": 0.23511530458927155, "value_any": 0.07336758822202682, "value_bot": 0.0067226337268948555, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00458.png", "entropy": 0.7051394581794739} +{"ts": "2026-03-20T17:30:12.861697Z", "loop": 460, "env_steps": 282624000, "exact_value_avg": 0.3509616553783417, "regret_dist": 0.5126190185546875, "regret_other_env": 0.8087953925132751, "regret_corner": 0.06835445016622543, "regret_row": 0.6253128051757812, "regret_any": 0.8088732957839966, "regret_bot": 0.851794421672821, "value_dist": 0.3509616553783417, "value_other_env": 0.0734194740653038, "value_corner": 0.7672749161720276, "value_row": 0.23331385850906372, "value_any": 0.07337736338376999, "value_bot": 0.006832252722233534, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00460.png", "entropy": 0.7057323455810547} +{"ts": "2026-03-20T17:30:14.605134Z", "loop": 462, "env_steps": 283852800, "exact_value_avg": 0.35094717144966125, "regret_dist": 0.5126335024833679, "regret_other_env": 0.8087875247001648, "regret_corner": 0.06840245425701141, "regret_row": 0.6237500309944153, "regret_any": 0.8088653683662415, "regret_bot": 0.8518972396850586, "value_dist": 0.35094717144966125, "value_other_env": 0.07342735677957535, "value_corner": 0.7672268748283386, "value_row": 0.2348765730857849, "value_any": 0.07338524609804153, "value_bot": 0.006729398854076862, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00462.png", "entropy": 0.7061207294464111} +{"ts": "2026-03-20T17:30:16.347781Z", "loop": 464, "env_steps": 285081600, "exact_value_avg": 0.35093235969543457, "regret_dist": 0.512648344039917, "regret_other_env": 0.8087838292121887, "regret_corner": 0.06844506412744522, "regret_row": 0.6231274008750916, "regret_any": 0.8088616728782654, "regret_bot": 0.8519383072853088, "value_dist": 0.35093235969543457, "value_other_env": 0.07343107461929321, "value_corner": 0.7671842575073242, "value_row": 0.23549924790859222, "value_any": 0.0733889639377594, "value_bot": 0.006688363384455442, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00464.png", "entropy": 0.7063210010528564} +{"ts": "2026-03-20T17:30:18.091037Z", "loop": 466, "env_steps": 286310400, "exact_value_avg": 0.35090240836143494, "regret_dist": 0.5126782655715942, "regret_other_env": 0.8087724447250366, "regret_corner": 0.06853689253330231, "regret_row": 0.621578574180603, "regret_any": 0.8088503479957581, "regret_bot": 0.8520286679267883, "value_dist": 0.35090240836143494, "value_other_env": 0.07344242185354233, "value_corner": 0.7670924067497253, "value_row": 0.23704805970191956, "value_any": 0.07340027391910553, "value_bot": 0.0065979924984276295, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00466.png", "entropy": 0.7064018845558167} +{"ts": "2026-03-20T17:30:19.835555Z", "loop": 468, "env_steps": 287539200, "exact_value_avg": 0.35091733932495117, "regret_dist": 0.5126633048057556, "regret_other_env": 0.8087652325630188, "regret_corner": 0.06851038336753845, "regret_row": 0.6222395896911621, "regret_any": 0.8088431358337402, "regret_bot": 0.8519865870475769, "value_dist": 0.35091733932495117, "value_other_env": 0.07344961911439896, "value_corner": 0.7671189308166504, "value_row": 0.23638702929019928, "value_any": 0.07340747117996216, "value_bot": 0.006640129256993532, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00468.png", "entropy": 0.7067272663116455} +{"ts": "2026-03-20T17:30:21.579969Z", "loop": 470, "env_steps": 288768000, "exact_value_avg": 0.35092541575431824, "regret_dist": 0.5126552581787109, "regret_other_env": 0.8087482452392578, "regret_corner": 0.06851574033498764, "regret_row": 0.6226208806037903, "regret_any": 0.808826208114624, "regret_bot": 0.8519554138183594, "value_dist": 0.35092541575431824, "value_other_env": 0.07346659153699875, "value_corner": 0.7671136260032654, "value_row": 0.2360057681798935, "value_any": 0.07342442125082016, "value_bot": 0.006671215873211622, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00470.png", "entropy": 0.7071168422698975} +{"ts": "2026-03-20T17:30:23.324252Z", "loop": 472, "env_steps": 289996800, "exact_value_avg": 0.3509121537208557, "regret_dist": 0.5126684904098511, "regret_other_env": 0.8087315559387207, "regret_corner": 0.06857390701770782, "regret_row": 0.6219111680984497, "regret_any": 0.8088095188140869, "regret_bot": 0.8519889712333679, "value_dist": 0.3509121537208557, "value_other_env": 0.07348326593637466, "value_corner": 0.7670554518699646, "value_row": 0.23671548068523407, "value_any": 0.07344107329845428, "value_bot": 0.00663759745657444, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00472.png", "entropy": 0.7073209285736084} +{"ts": "2026-03-20T17:30:25.065755Z", "loop": 474, "env_steps": 291225600, "exact_value_avg": 0.35092151165008545, "regret_dist": 0.5126591324806213, "regret_other_env": 0.808713436126709, "regret_corner": 0.06857764720916748, "regret_row": 0.6225889325141907, "regret_any": 0.8087913990020752, "regret_bot": 0.8519362807273865, "value_dist": 0.35092151165008545, "value_other_env": 0.07350143790245056, "value_corner": 0.767051637172699, "value_row": 0.2360377311706543, "value_any": 0.07345922291278839, "value_bot": 0.006690393667668104, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00474.png", "entropy": 0.7077777981758118} +{"ts": "2026-03-20T17:30:26.807808Z", "loop": 476, "env_steps": 292454400, "exact_value_avg": 0.35087278485298157, "regret_dist": 0.5127079486846924, "regret_other_env": 0.8086904883384705, "regret_corner": 0.06873404234647751, "regret_row": 0.6203781366348267, "regret_any": 0.8087684512138367, "regret_bot": 0.8520540595054626, "value_dist": 0.35087278485298157, "value_other_env": 0.07352440059185028, "value_corner": 0.7668952941894531, "value_row": 0.23824848234653473, "value_any": 0.07348217070102692, "value_bot": 0.006572517100721598, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00476.png", "entropy": 0.7079208493232727} +{"ts": "2026-03-20T17:30:28.549766Z", "loop": 478, "env_steps": 293683200, "exact_value_avg": 0.35073649883270264, "regret_dist": 0.5128442049026489, "regret_other_env": 0.8086872100830078, "regret_corner": 0.06907954812049866, "regret_row": 0.6169673204421997, "regret_any": 0.808765172958374, "regret_bot": 0.8522480726242065, "value_dist": 0.35073649883270264, "value_other_env": 0.07352764904499054, "value_corner": 0.7665497660636902, "value_row": 0.24165931344032288, "value_any": 0.07348540425300598, "value_bot": 0.006378458347171545, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00478.png", "entropy": 0.707213282585144} +{"ts": "2026-03-20T17:30:30.295464Z", "loop": 480, "env_steps": 294912000, "exact_value_avg": 0.35070812702178955, "regret_dist": 0.512872576713562, "regret_other_env": 0.8086972236633301, "regret_corner": 0.0691356435418129, "regret_row": 0.6163303256034851, "regret_any": 0.8087751269340515, "regret_bot": 0.8522944450378418, "value_dist": 0.35070812702178955, "value_other_env": 0.07351770251989365, "value_corner": 0.7664937376976013, "value_row": 0.24229633808135986, "value_any": 0.07347548007965088, "value_bot": 0.00633218651637435, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00480.png", "entropy": 0.706924319267273} +{"ts": "2026-03-20T17:30:32.038534Z", "loop": 482, "env_steps": 296140800, "exact_value_avg": 0.35090404748916626, "regret_dist": 0.5126765966415405, "regret_other_env": 0.8087068796157837, "regret_corner": 0.068631112575531, "regret_row": 0.6213183403015137, "regret_any": 0.8087848424911499, "regret_bot": 0.8520153164863586, "value_dist": 0.35090404748916626, "value_other_env": 0.07350794970989227, "value_corner": 0.7669982314109802, "value_row": 0.23730823397636414, "value_any": 0.0734657347202301, "value_bot": 0.006611296907067299, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00482.png", "entropy": 0.7077589631080627} +{"ts": "2026-03-20T17:30:33.780506Z", "loop": 484, "env_steps": 297369600, "exact_value_avg": 0.35094791650772095, "regret_dist": 0.5126327872276306, "regret_other_env": 0.808729350566864, "regret_corner": 0.06848783791065216, "regret_row": 0.6258217096328735, "regret_any": 0.8088072538375854, "regret_bot": 0.8517538905143738, "value_dist": 0.35094791650772095, "value_other_env": 0.07348554581403732, "value_corner": 0.7671415209770203, "value_row": 0.23280498385429382, "value_any": 0.07344335317611694, "value_bot": 0.006872669793665409, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00484.png", "entropy": 0.7078861594200134} +{"ts": "2026-03-20T17:30:35.523136Z", "loop": 486, "env_steps": 298598400, "exact_value_avg": 0.3509191870689392, "regret_dist": 0.5126614570617676, "regret_other_env": 0.8087683916091919, "regret_corner": 0.06850102543830872, "regret_row": 0.6284845471382141, "regret_any": 0.8088462352752686, "regret_bot": 0.8516031503677368, "value_dist": 0.3509191870689392, "value_other_env": 0.07344645261764526, "value_corner": 0.7671282887458801, "value_row": 0.23014211654663086, "value_any": 0.07340431958436966, "value_bot": 0.007023470941931009, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00486.png", "entropy": 0.7071491479873657} +{"ts": "2026-03-20T17:30:37.266212Z", "loop": 488, "env_steps": 299827200, "exact_value_avg": 0.35095202922821045, "regret_dist": 0.5126286745071411, "regret_other_env": 0.8088023066520691, "regret_corner": 0.06836812198162079, "regret_row": 0.6271885633468628, "regret_any": 0.808880090713501, "regret_bot": 0.8516963720321655, "value_dist": 0.35095202922821045, "value_other_env": 0.07341256737709045, "value_corner": 0.7672612071037292, "value_row": 0.23143808543682098, "value_any": 0.07337046414613724, "value_bot": 0.006930169183760881, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00488.png", "entropy": 0.7061787247657776} +{"ts": "2026-03-20T17:30:39.008868Z", "loop": 490, "env_steps": 301056000, "exact_value_avg": 0.35097137093544006, "regret_dist": 0.5126092433929443, "regret_other_env": 0.8088403940200806, "regret_corner": 0.06826242059469223, "regret_row": 0.6265493631362915, "regret_any": 0.8089182376861572, "regret_bot": 0.8517481684684753, "value_dist": 0.35097137093544006, "value_other_env": 0.0733744204044342, "value_corner": 0.7673668265342712, "value_row": 0.23207730054855347, "value_any": 0.07333236187696457, "value_bot": 0.006878511514514685, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00490.png", "entropy": 0.7051227688789368} +{"ts": "2026-03-20T17:30:40.752712Z", "loop": 492, "env_steps": 302284800, "exact_value_avg": 0.35098040103912354, "regret_dist": 0.5126002430915833, "regret_other_env": 0.8088554739952087, "regret_corner": 0.06821734458208084, "regret_row": 0.6262782216072083, "regret_any": 0.8089333176612854, "regret_bot": 0.8517666459083557, "value_dist": 0.35098040103912354, "value_other_env": 0.07335934042930603, "value_corner": 0.7674119472503662, "value_row": 0.2323484569787979, "value_any": 0.07331729680299759, "value_bot": 0.006859986577183008, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00492.png", "entropy": 0.7046308517456055} +{"ts": "2026-03-20T17:30:42.496618Z", "loop": 494, "env_steps": 303513600, "exact_value_avg": 0.3509896993637085, "regret_dist": 0.5125910043716431, "regret_other_env": 0.8088688254356384, "regret_corner": 0.06817416101694107, "regret_row": 0.6260247230529785, "regret_any": 0.8089466691017151, "regret_bot": 0.851780891418457, "value_dist": 0.3509896993637085, "value_other_env": 0.07334598898887634, "value_corner": 0.7674552202224731, "value_row": 0.23260194063186646, "value_any": 0.0733039602637291, "value_bot": 0.0068457480520009995, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00494.png", "entropy": 0.7041726112365723} +{"ts": "2026-03-20T17:30:44.239623Z", "loop": 496, "env_steps": 304742400, "exact_value_avg": 0.3509950637817383, "regret_dist": 0.5125856399536133, "regret_other_env": 0.8088904023170471, "regret_corner": 0.06812842935323715, "regret_row": 0.6265562772750854, "regret_any": 0.8089681267738342, "regret_bot": 0.8517463207244873, "value_dist": 0.3509950637817383, "value_other_env": 0.07332450151443481, "value_corner": 0.7675008773803711, "value_row": 0.23207038640975952, "value_any": 0.07328249514102936, "value_bot": 0.006880368571728468, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00496.png", "entropy": 0.7035298943519592} +{"ts": "2026-03-20T17:30:45.982539Z", "loop": 498, "env_steps": 305971200, "exact_value_avg": 0.35097551345825195, "regret_dist": 0.5126051902770996, "regret_other_env": 0.8089056611061096, "regret_corner": 0.06815433502197266, "regret_row": 0.6282594799995422, "regret_any": 0.808983325958252, "regret_bot": 0.8516339659690857, "value_dist": 0.35097551345825195, "value_other_env": 0.07330920547246933, "value_corner": 0.7674749493598938, "value_row": 0.23036715388298035, "value_any": 0.07326722890138626, "value_bot": 0.006992695387452841, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00498.png", "entropy": 0.7030978798866272} +{"ts": "2026-03-20T17:30:47.726267Z", "loop": 500, "env_steps": 307200000, "exact_value_avg": 0.35099875926971436, "regret_dist": 0.5125819444656372, "regret_other_env": 0.8089004755020142, "regret_corner": 0.06810405850410461, "regret_row": 0.6272234916687012, "regret_any": 0.8089781999588013, "regret_bot": 0.8516958355903625, "value_dist": 0.35099875926971436, "value_other_env": 0.07331441342830658, "value_corner": 0.7675252556800842, "value_row": 0.231403186917305, "value_any": 0.07327240705490112, "value_bot": 0.006930809933692217, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00500.png", "entropy": 0.7029892802238464} +{"ts": "2026-03-20T17:30:52.027301Z", "loop": 505, "env_steps": 310272000, "exact_value_avg": 0.3509630560874939, "regret_dist": 0.5126175880432129, "regret_other_env": 0.8089115619659424, "regret_corner": 0.06817665696144104, "regret_row": 0.6215922832489014, "regret_any": 0.8089892268180847, "regret_bot": 0.8520570397377014, "value_dist": 0.3509630560874939, "value_other_env": 0.07330334931612015, "value_corner": 0.7674526572227478, "value_row": 0.23703435063362122, "value_any": 0.07326134294271469, "value_bot": 0.006569594144821167, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00505.png", "entropy": 0.7021163105964661} +{"ts": "2026-03-20T17:30:56.330561Z", "loop": 510, "env_steps": 313344000, "exact_value_avg": 0.3509792983531952, "regret_dist": 0.5126013159751892, "regret_other_env": 0.8089326620101929, "regret_corner": 0.0681043192744255, "regret_row": 0.6222303509712219, "regret_any": 0.8090104460716248, "regret_bot": 0.8520392775535583, "value_dist": 0.3509792983531952, "value_other_env": 0.07328213006258011, "value_corner": 0.7675250172615051, "value_row": 0.23639626801013947, "value_any": 0.07324016094207764, "value_bot": 0.006587387528270483, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00510.png", "entropy": 0.7021538615226746} +{"ts": "2026-03-20T17:31:00.631211Z", "loop": 515, "env_steps": 316416000, "exact_value_avg": 0.35096800327301025, "regret_dist": 0.5126126408576965, "regret_other_env": 0.8089458346366882, "regret_corner": 0.06811288744211197, "regret_row": 0.6301518082618713, "regret_any": 0.8090235590934753, "regret_bot": 0.851550817489624, "value_dist": 0.35096800327301025, "value_other_env": 0.07326903194189072, "value_corner": 0.7675164341926575, "value_row": 0.22847484052181244, "value_any": 0.07322709262371063, "value_bot": 0.007075839675962925, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00515.png", "entropy": 0.7025936245918274} +{"ts": "2026-03-20T17:31:04.927613Z", "loop": 520, "env_steps": 319488000, "exact_value_avg": 0.3510114252567291, "regret_dist": 0.5125692486763, "regret_other_env": 0.808928370475769, "regret_corner": 0.06803043931722641, "regret_row": 0.6282715797424316, "regret_any": 0.8090060353279114, "regret_bot": 0.8516471982002258, "value_dist": 0.3510114252567291, "value_other_env": 0.07328645884990692, "value_corner": 0.7675988674163818, "value_row": 0.23035502433776855, "value_any": 0.07324447482824326, "value_bot": 0.00697941891849041, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00520.png", "entropy": 0.7025693655014038} +{"ts": "2026-03-20T17:31:09.228463Z", "loop": 525, "env_steps": 322560000, "exact_value_avg": 0.35102128982543945, "regret_dist": 0.5125594139099121, "regret_other_env": 0.8089072108268738, "regret_corner": 0.06803770363330841, "regret_row": 0.6248096823692322, "regret_any": 0.8089849352836609, "regret_bot": 0.8518311381340027, "value_dist": 0.35102128982543945, "value_other_env": 0.07330767810344696, "value_corner": 0.767591655254364, "value_row": 0.2338169366121292, "value_any": 0.07326566427946091, "value_bot": 0.006795520428568125, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00525.png", "entropy": 0.7022780776023865} +{"ts": "2026-03-20T17:31:13.530091Z", "loop": 530, "env_steps": 325632000, "exact_value_avg": 0.3509955108165741, "regret_dist": 0.5125851631164551, "regret_other_env": 0.8089227080345154, "regret_corner": 0.06807883083820343, "regret_row": 0.6226016879081726, "regret_any": 0.8090004324913025, "regret_bot": 0.8519738912582397, "value_dist": 0.3509955108165741, "value_other_env": 0.07329221814870834, "value_corner": 0.7675504684448242, "value_row": 0.23602500557899475, "value_any": 0.07325022667646408, "value_bot": 0.0066526816226542, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00530.png", "entropy": 0.7018219828605652} +{"ts": "2026-03-20T17:31:17.830933Z", "loop": 535, "env_steps": 328704000, "exact_value_avg": 0.35082411766052246, "regret_dist": 0.5127565264701843, "regret_other_env": 0.8089874982833862, "regret_corner": 0.06841001659631729, "regret_row": 0.6341977715492249, "regret_any": 0.8090651631355286, "regret_bot": 0.8512710928916931, "value_dist": 0.35082411766052246, "value_other_env": 0.07322730869054794, "value_corner": 0.7672193050384521, "value_row": 0.22442887723445892, "value_any": 0.07318542897701263, "value_bot": 0.007355531677603722, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00535.png", "entropy": 0.7009530663490295} +{"ts": "2026-03-20T17:31:22.132190Z", "loop": 540, "env_steps": 331776000, "exact_value_avg": 0.3507351279258728, "regret_dist": 0.512845516204834, "regret_other_env": 0.8090122938156128, "regret_corner": 0.06859539449214935, "regret_row": 0.63592928647995, "regret_any": 0.8090898394584656, "regret_bot": 0.8511679768562317, "value_dist": 0.3507351279258728, "value_other_env": 0.07320257276296616, "value_corner": 0.7670339345932007, "value_row": 0.22269730269908905, "value_any": 0.07316074520349503, "value_bot": 0.007458712439984083, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00540.png", "entropy": 0.700486421585083} +{"ts": "2026-03-20T17:31:26.433711Z", "loop": 545, "env_steps": 334848000, "exact_value_avg": 0.3509950041770935, "regret_dist": 0.5125856995582581, "regret_other_env": 0.8089854717254639, "regret_corner": 0.06798600405454636, "regret_row": 0.6299667358398438, "regret_any": 0.8090630173683167, "regret_bot": 0.8515526652336121, "value_dist": 0.3509950041770935, "value_other_env": 0.07322943955659866, "value_corner": 0.7676433324813843, "value_row": 0.22865988314151764, "value_any": 0.07318755984306335, "value_bot": 0.007073938846588135, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00545.png", "entropy": 0.70121169090271} +{"ts": "2026-03-20T17:31:30.734314Z", "loop": 550, "env_steps": 337920000, "exact_value_avg": 0.3508501350879669, "regret_dist": 0.5127305388450623, "regret_other_env": 0.8089936971664429, "regret_corner": 0.06833571940660477, "regret_row": 0.6339126825332642, "regret_any": 0.8090713024139404, "regret_bot": 0.8512976169586182, "value_dist": 0.3508501350879669, "value_other_env": 0.07322118431329727, "value_corner": 0.7672935724258423, "value_row": 0.22471396625041962, "value_any": 0.07317934185266495, "value_bot": 0.0073289754800498486, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00550.png", "entropy": 0.7011672854423523} +{"ts": "2026-03-20T17:31:35.037387Z", "loop": 555, "env_steps": 340992000, "exact_value_avg": 0.3509564995765686, "regret_dist": 0.5126241445541382, "regret_other_env": 0.8089799284934998, "regret_corner": 0.06809043884277344, "regret_row": 0.6315423846244812, "regret_any": 0.8090575933456421, "regret_bot": 0.8514505624771118, "value_dist": 0.3509564995765686, "value_other_env": 0.0732349380850792, "value_corner": 0.767538845539093, "value_row": 0.22708424925804138, "value_any": 0.07319304347038269, "value_bot": 0.007176029030233622, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00555.png", "entropy": 0.7014541029930115} +{"ts": "2026-03-20T17:31:39.335057Z", "loop": 560, "env_steps": 344064000, "exact_value_avg": 0.3510682284832001, "regret_dist": 0.5125124454498291, "regret_other_env": 0.8089386820793152, "regret_corner": 0.06787305325269699, "regret_row": 0.6259109973907471, "regret_any": 0.8090164065361023, "regret_bot": 0.8517887592315674, "value_dist": 0.3510682284832001, "value_other_env": 0.07327616214752197, "value_corner": 0.7677562832832336, "value_row": 0.23271562159061432, "value_any": 0.07323421537876129, "value_bot": 0.006837846711277962, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00560.png", "entropy": 0.7017568945884705} +{"ts": "2026-03-20T17:31:43.635034Z", "loop": 565, "env_steps": 347136000, "exact_value_avg": 0.3510454297065735, "regret_dist": 0.5125352144241333, "regret_other_env": 0.8088868856430054, "regret_corner": 0.06800761818885803, "regret_row": 0.62310791015625, "regret_any": 0.8089646100997925, "regret_bot": 0.8519289493560791, "value_dist": 0.3510454297065735, "value_other_env": 0.07332797348499298, "value_corner": 0.767621636390686, "value_row": 0.2355187088251114, "value_any": 0.07328595966100693, "value_bot": 0.006697640288621187, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00565.png", "entropy": 0.7021692991256714} +{"ts": "2026-03-20T17:31:47.933729Z", "loop": 570, "env_steps": 350208000, "exact_value_avg": 0.35090047121047974, "regret_dist": 0.512680172920227, "regret_other_env": 0.8088455200195312, "regret_corner": 0.06843212246894836, "regret_row": 0.6185628175735474, "regret_any": 0.8089234232902527, "regret_bot": 0.8521907925605774, "value_dist": 0.35090047121047974, "value_other_env": 0.07336930930614471, "value_corner": 0.7671971917152405, "value_row": 0.24006378650665283, "value_any": 0.07332723587751389, "value_bot": 0.006435863673686981, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00570.png", "entropy": 0.702957034111023} +{"ts": "2026-03-20T17:31:52.233514Z", "loop": 575, "env_steps": 353280000, "exact_value_avg": 0.35106685757637024, "regret_dist": 0.5125138163566589, "regret_other_env": 0.80887770652771, "regret_corner": 0.06796794384717941, "regret_row": 0.627446174621582, "regret_any": 0.8089554905891418, "regret_bot": 0.8516725301742554, "value_dist": 0.35106685757637024, "value_other_env": 0.0733371451497078, "value_corner": 0.7676613926887512, "value_row": 0.23118048906326294, "value_any": 0.07329512387514114, "value_bot": 0.00695418007671833, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00575.png", "entropy": 0.7034075856208801} +{"ts": "2026-03-20T17:31:56.535563Z", "loop": 580, "env_steps": 356352000, "exact_value_avg": 0.35050857067108154, "regret_dist": 0.51307213306427, "regret_other_env": 0.8089880347251892, "regret_corner": 0.06919816881418228, "regret_row": 0.6393019556999207, "regret_any": 0.8090656399726868, "regret_bot": 0.8509116172790527, "value_dist": 0.35050857067108154, "value_other_env": 0.07322686165571213, "value_corner": 0.7664311528205872, "value_row": 0.21932464838027954, "value_any": 0.0731850191950798, "value_bot": 0.007714920211583376, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00580.png", "entropy": 0.7004340887069702} +{"ts": "2026-03-20T17:32:00.836417Z", "loop": 585, "env_steps": 359424000, "exact_value_avg": 0.35106560587882996, "regret_dist": 0.5125150680541992, "regret_other_env": 0.8088851571083069, "regret_corner": 0.06795993447303772, "regret_row": 0.62799072265625, "regret_any": 0.808962881565094, "regret_bot": 0.851642370223999, "value_dist": 0.35106560587882996, "value_other_env": 0.07332973927259445, "value_corner": 0.7676693797111511, "value_row": 0.2306358963251114, "value_any": 0.0732877254486084, "value_bot": 0.006984269712120295, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00585.png", "entropy": 0.7034178376197815} +{"ts": "2026-03-20T17:32:05.138611Z", "loop": 590, "env_steps": 362496000, "exact_value_avg": 0.35106146335601807, "regret_dist": 0.512519121170044, "regret_other_env": 0.8088197708129883, "regret_corner": 0.06806814670562744, "regret_row": 0.6226862072944641, "regret_any": 0.8088976144790649, "regret_bot": 0.8519425392150879, "value_dist": 0.35106146335601807, "value_other_env": 0.07339504361152649, "value_corner": 0.767561137676239, "value_row": 0.23594045639038086, "value_any": 0.07335294783115387, "value_bot": 0.00668405182659626, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00590.png", "entropy": 0.7040683627128601} +{"ts": "2026-03-20T17:32:09.442476Z", "loop": 595, "env_steps": 365568000, "exact_value_avg": 0.3510238230228424, "regret_dist": 0.5125568509101868, "regret_other_env": 0.8087683320045471, "regret_corner": 0.06823951005935669, "regret_row": 0.6211092472076416, "regret_any": 0.8088462352752686, "regret_bot": 0.8520204424858093, "value_dist": 0.3510238230228424, "value_other_env": 0.07344648241996765, "value_corner": 0.7673898339271545, "value_row": 0.2375173568725586, "value_any": 0.07340432703495026, "value_bot": 0.006606152281165123, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00595.png", "entropy": 0.7051673531532288} +{"ts": "2026-03-20T17:32:13.743079Z", "loop": 600, "env_steps": 368640000, "exact_value_avg": 0.35105907917022705, "regret_dist": 0.5125216245651245, "regret_other_env": 0.8087671995162964, "regret_corner": 0.06815319508314133, "regret_row": 0.62823086977005, "regret_any": 0.808845043182373, "regret_bot": 0.8515858054161072, "value_dist": 0.35105907917022705, "value_other_env": 0.07344769686460495, "value_corner": 0.7674761414527893, "value_row": 0.23039577901363373, "value_any": 0.07340555638074875, "value_bot": 0.0070408666506409645, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00600.png", "entropy": 0.7060074806213379} +{"ts": "2026-03-20T17:32:18.043511Z", "loop": 605, "env_steps": 371712000, "exact_value_avg": 0.3505065441131592, "regret_dist": 0.5130741596221924, "regret_other_env": 0.808857798576355, "regret_corner": 0.06939861923456192, "regret_row": 0.6389601826667786, "regret_any": 0.8089354634284973, "regret_bot": 0.8508942127227783, "value_dist": 0.3505065441131592, "value_other_env": 0.07335708290338516, "value_corner": 0.7662307024002075, "value_row": 0.2196664661169052, "value_any": 0.0733151063323021, "value_bot": 0.007732403464615345, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00605.png", "entropy": 0.7037631273269653} +{"ts": "2026-03-20T17:32:22.347401Z", "loop": 610, "env_steps": 374784000, "exact_value_avg": 0.3505641222000122, "regret_dist": 0.5130165815353394, "regret_other_env": 0.8088067770004272, "regret_corner": 0.06933119148015976, "regret_row": 0.6379827260971069, "regret_any": 0.8088846206665039, "regret_bot": 0.8509544134140015, "value_dist": 0.3505641222000122, "value_other_env": 0.07340812683105469, "value_corner": 0.7662980556488037, "value_row": 0.22064398229122162, "value_any": 0.07336607575416565, "value_bot": 0.007672196254134178, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00610.png", "entropy": 0.7053638696670532} +{"ts": "2026-03-20T17:32:26.648618Z", "loop": 615, "env_steps": 377856000, "exact_value_avg": 0.3510704040527344, "regret_dist": 0.5125102996826172, "regret_other_env": 0.808653712272644, "regret_corner": 0.06829522550106049, "regret_row": 0.6267594695091248, "regret_any": 0.8087316751480103, "regret_bot": 0.8516425490379333, "value_dist": 0.3510704040527344, "value_other_env": 0.07356121391057968, "value_corner": 0.7673341631889343, "value_row": 0.23186719417572021, "value_any": 0.07351894676685333, "value_bot": 0.006984073203057051, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00615.png", "entropy": 0.7086710333824158} +{"ts": "2026-03-20T17:32:30.956272Z", "loop": 620, "env_steps": 380928000, "exact_value_avg": 0.3506704568862915, "regret_dist": 0.5129102468490601, "regret_other_env": 0.8086304664611816, "regret_corner": 0.0693298876285553, "regret_row": 0.6136288642883301, "regret_any": 0.8087084889411926, "regret_bot": 0.8523999452590942, "value_dist": 0.3506704568862915, "value_other_env": 0.07358443737030029, "value_corner": 0.7662994861602783, "value_row": 0.2449978142976761, "value_any": 0.07354212552309036, "value_bot": 0.006226726341992617, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00620.png", "entropy": 0.7066222429275513} +{"ts": "2026-03-20T17:32:35.260380Z", "loop": 625, "env_steps": 384000000, "exact_value_avg": 0.35106948018074036, "regret_dist": 0.5125111937522888, "regret_other_env": 0.8086134791374207, "regret_corner": 0.0683576762676239, "regret_row": 0.6221847534179688, "regret_any": 0.8086915612220764, "regret_bot": 0.8519019484519958, "value_dist": 0.35106948018074036, "value_other_env": 0.0736013650894165, "value_corner": 0.7672716379165649, "value_row": 0.23644191026687622, "value_any": 0.07355905324220657, "value_bot": 0.006724626291543245, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00625.png", "entropy": 0.708681046962738} +{"ts": "2026-03-20T17:32:39.562859Z", "loop": 630, "env_steps": 387072000, "exact_value_avg": 0.350989431142807, "regret_dist": 0.5125912427902222, "regret_other_env": 0.8087145686149597, "regret_corner": 0.06840628385543823, "regret_row": 0.6313754916191101, "regret_any": 0.8087924718856812, "regret_bot": 0.8513529300689697, "value_dist": 0.350989431142807, "value_other_env": 0.07350031286478043, "value_corner": 0.767223060131073, "value_row": 0.2272510826587677, "value_any": 0.07345813512802124, "value_bot": 0.00727366516366601, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00630.png", "entropy": 0.706847608089447} +{"ts": "2026-03-20T17:32:43.867202Z", "loop": 635, "env_steps": 390144000, "exact_value_avg": 0.35094448924064636, "regret_dist": 0.512636125087738, "regret_other_env": 0.8088218569755554, "regret_corner": 0.06835751235485077, "regret_row": 0.6333538889884949, "regret_any": 0.8088997006416321, "regret_bot": 0.8512637615203857, "value_dist": 0.35094448924064636, "value_other_env": 0.07339297235012054, "value_corner": 0.7672717571258545, "value_row": 0.22527271509170532, "value_any": 0.07335090637207031, "value_bot": 0.007362884934991598, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00635.png", "entropy": 0.7044184803962708} +{"ts": "2026-03-20T17:32:48.171683Z", "loop": 640, "env_steps": 393216000, "exact_value_avg": 0.35109952092170715, "regret_dist": 0.512481153011322, "regret_other_env": 0.8087992072105408, "regret_corner": 0.06800412386655807, "regret_row": 0.6296950578689575, "regret_any": 0.8088769316673279, "regret_bot": 0.8514912724494934, "value_dist": 0.35109952092170715, "value_other_env": 0.07341571897268295, "value_corner": 0.7676252126693726, "value_row": 0.22893157601356506, "value_any": 0.07337362319231033, "value_bot": 0.007135420106351376, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00640.png", "entropy": 0.704505205154419} +{"ts": "2026-03-20T17:32:52.477683Z", "loop": 645, "env_steps": 396288000, "exact_value_avg": 0.3511171042919159, "regret_dist": 0.5124635696411133, "regret_other_env": 0.8087422847747803, "regret_corner": 0.068045474588871, "regret_row": 0.622265100479126, "regret_any": 0.8088201880455017, "regret_bot": 0.851945698261261, "value_dist": 0.3511171042919159, "value_other_env": 0.07347261905670166, "value_corner": 0.7675838470458984, "value_row": 0.2363615483045578, "value_any": 0.07343044131994247, "value_bot": 0.006680914666503668, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00645.png", "entropy": 0.7057690024375916} +{"ts": "2026-03-20T17:32:56.781518Z", "loop": 650, "env_steps": 399360000, "exact_value_avg": 0.3510698676109314, "regret_dist": 0.5125108361244202, "regret_other_env": 0.8086848855018616, "regret_corner": 0.0682496428489685, "regret_row": 0.6200940608978271, "regret_any": 0.8087628483772278, "regret_bot": 0.8520494699478149, "value_dist": 0.3510698676109314, "value_other_env": 0.07352999597787857, "value_corner": 0.7673797011375427, "value_row": 0.2385326474905014, "value_any": 0.07348774373531342, "value_bot": 0.006577104330062866, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00650.png", "entropy": 0.7065365314483643} +{"ts": "2026-03-20T17:33:01.086113Z", "loop": 655, "env_steps": 402432000, "exact_value_avg": 0.35113394260406494, "regret_dist": 0.5124467611312866, "regret_other_env": 0.8087594509124756, "regret_corner": 0.06797771155834198, "regret_row": 0.6289862990379333, "regret_any": 0.8088372945785522, "regret_bot": 0.8515147566795349, "value_dist": 0.35113394260406494, "value_other_env": 0.07345545291900635, "value_corner": 0.7676516175270081, "value_row": 0.22964037954807281, "value_any": 0.07341329753398895, "value_bot": 0.007111825048923492, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00655.png", "entropy": 0.7051361203193665} +{"ts": "2026-03-20T17:33:05.385237Z", "loop": 660, "env_steps": 405504000, "exact_value_avg": 0.3511960506439209, "regret_dist": 0.5123846530914307, "regret_other_env": 0.8087702393531799, "regret_corner": 0.0678061991930008, "regret_row": 0.6249765753746033, "regret_any": 0.8088481426239014, "regret_bot": 0.8517770171165466, "value_dist": 0.3511960506439209, "value_other_env": 0.07344463467597961, "value_corner": 0.7678231596946716, "value_row": 0.23365001380443573, "value_any": 0.07340247184038162, "value_bot": 0.006849630270153284, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00660.png", "entropy": 0.7046740651130676} +{"ts": "2026-03-20T17:33:09.686163Z", "loop": 665, "env_steps": 408576000, "exact_value_avg": 0.3512042462825775, "regret_dist": 0.5123764872550964, "regret_other_env": 0.8088034987449646, "regret_corner": 0.06773586571216583, "regret_row": 0.6235851049423218, "regret_any": 0.8088812828063965, "regret_bot": 0.8518746495246887, "value_dist": 0.3512042462825775, "value_other_env": 0.07341144233942032, "value_corner": 0.7678934335708618, "value_row": 0.23504145443439484, "value_any": 0.07336931675672531, "value_bot": 0.006752020679414272, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00665.png", "entropy": 0.7037277817726135} +{"ts": "2026-03-20T17:33:13.991557Z", "loop": 670, "env_steps": 411648000, "exact_value_avg": 0.3506945073604584, "regret_dist": 0.5128862261772156, "regret_other_env": 0.8089430928230286, "regret_corner": 0.06880083680152893, "regret_row": 0.6387412548065186, "regret_any": 0.8090206980705261, "regret_bot": 0.8509408235549927, "value_dist": 0.3506945073604584, "value_other_env": 0.07327178865671158, "value_corner": 0.7668285369873047, "value_row": 0.21988533437252045, "value_any": 0.07322989404201508, "value_bot": 0.0076857744716107845, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00670.png", "entropy": 0.7011062502861023} +{"ts": "2026-03-20T17:33:18.292773Z", "loop": 675, "env_steps": 414720000, "exact_value_avg": 0.35064855217933655, "regret_dist": 0.5129321217536926, "regret_other_env": 0.8089467287063599, "regret_corner": 0.06891020387411118, "regret_row": 0.6395067572593689, "regret_any": 0.8090243339538574, "regret_bot": 0.8508815765380859, "value_dist": 0.35064855217933655, "value_other_env": 0.07326815277338028, "value_corner": 0.7667191028594971, "value_row": 0.2191198617219925, "value_any": 0.07322625815868378, "value_bot": 0.0077450331300497055, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00675.png", "entropy": 0.7008835077285767} +{"ts": "2026-03-20T17:33:22.590835Z", "loop": 680, "env_steps": 417792000, "exact_value_avg": 0.350690633058548, "regret_dist": 0.5128900408744812, "regret_other_env": 0.8088199496269226, "regret_corner": 0.06899519264698029, "regret_row": 0.6123365163803101, "regret_any": 0.8088977932929993, "regret_bot": 0.8525136709213257, "value_dist": 0.350690633058548, "value_other_env": 0.07339491695165634, "value_corner": 0.7666341662406921, "value_row": 0.24629007279872894, "value_any": 0.07335279136896133, "value_bot": 0.006112929433584213, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00680.png", "entropy": 0.700779914855957} +{"ts": "2026-03-20T17:33:26.891859Z", "loop": 685, "env_steps": 420864000, "exact_value_avg": 0.3504520058631897, "regret_dist": 0.5131286978721619, "regret_other_env": 0.8088535666465759, "regret_corner": 0.069541335105896, "regret_row": 0.6095635890960693, "regret_any": 0.8089314103126526, "regret_bot": 0.8526643514633179, "value_dist": 0.3504520058631897, "value_other_env": 0.0733613446354866, "value_corner": 0.7660880088806152, "value_row": 0.24906305968761444, "value_any": 0.07331925630569458, "value_bot": 0.005962258670479059, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00685.png", "entropy": 0.6985810399055481} +{"ts": "2026-03-20T17:33:31.194062Z", "loop": 690, "env_steps": 423936000, "exact_value_avg": 0.3509427607059479, "regret_dist": 0.5126379132270813, "regret_other_env": 0.8088842630386353, "regret_corner": 0.0682683140039444, "regret_row": 0.6153121590614319, "regret_any": 0.8089620471000671, "regret_bot": 0.8523684144020081, "value_dist": 0.3509427607059479, "value_other_env": 0.0733305811882019, "value_corner": 0.7673609852790833, "value_row": 0.2433144897222519, "value_any": 0.07328851521015167, "value_bot": 0.006258165463805199, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00690.png", "entropy": 0.6995329856872559} +{"ts": "2026-03-20T17:33:35.496186Z", "loop": 695, "env_steps": 427008000, "exact_value_avg": 0.35130301117897034, "regret_dist": 0.5122776627540588, "regret_other_env": 0.8089268803596497, "regret_corner": 0.06730376183986664, "regret_row": 0.6259202361106873, "regret_any": 0.8090046048164368, "regret_bot": 0.8517765402793884, "value_dist": 0.35130301117897034, "value_other_env": 0.0732879713177681, "value_corner": 0.7683255672454834, "value_row": 0.23270635306835175, "value_any": 0.07324598729610443, "value_bot": 0.006850025616586208, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00695.png", "entropy": 0.7008305788040161} +{"ts": "2026-03-20T17:33:39.801196Z", "loop": 700, "env_steps": 430080000, "exact_value_avg": 0.3508358299732208, "regret_dist": 0.5127448439598083, "regret_other_env": 0.8090162873268127, "regret_corner": 0.06833763420581818, "regret_row": 0.6383539438247681, "regret_any": 0.8090938925743103, "regret_bot": 0.850983202457428, "value_dist": 0.3508358299732208, "value_other_env": 0.07319855690002441, "value_corner": 0.7672916650772095, "value_row": 0.2202727347612381, "value_any": 0.07315670698881149, "value_bot": 0.007643418852239847, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00700.png", "entropy": 0.6985288858413696} +{"ts": "2026-03-20T17:33:44.108403Z", "loop": 705, "env_steps": 433152000, "exact_value_avg": 0.35129278898239136, "regret_dist": 0.5122878551483154, "regret_other_env": 0.8089170455932617, "regret_corner": 0.0673440471291542, "regret_row": 0.6285364031791687, "regret_any": 0.8089947700500488, "regret_bot": 0.8516179323196411, "value_dist": 0.35129278898239136, "value_other_env": 0.07329779118299484, "value_corner": 0.7682852745056152, "value_row": 0.23009026050567627, "value_any": 0.07325579971075058, "value_bot": 0.007008620072156191, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00705.png", "entropy": 0.7013123035430908} +{"ts": "2026-03-20T17:33:48.413467Z", "loop": 710, "env_steps": 436224000, "exact_value_avg": 0.3513069748878479, "regret_dist": 0.5122737288475037, "regret_other_env": 0.8087790608406067, "regret_corner": 0.06751564890146255, "regret_row": 0.6257153153419495, "regret_any": 0.8088569641113281, "regret_bot": 0.8517453670501709, "value_dist": 0.3513069748878479, "value_other_env": 0.07343579083681107, "value_corner": 0.7681137323379517, "value_row": 0.23291133344173431, "value_any": 0.07339362800121307, "value_bot": 0.006881180685013533, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00710.png", "entropy": 0.7043401598930359} +{"ts": "2026-03-20T17:33:52.721899Z", "loop": 715, "env_steps": 439296000, "exact_value_avg": 0.3513062000274658, "regret_dist": 0.5122745037078857, "regret_other_env": 0.8086910843849182, "regret_corner": 0.06764962524175644, "regret_row": 0.6257460713386536, "regret_any": 0.8087690472602844, "regret_bot": 0.8517013788223267, "value_dist": 0.3513062000274658, "value_other_env": 0.07352380454540253, "value_corner": 0.7679797410964966, "value_row": 0.2328805774450302, "value_any": 0.07348153740167618, "value_bot": 0.006925279274582863, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00715.png", "entropy": 0.7060496807098389} +{"ts": "2026-03-20T17:33:57.028616Z", "loop": 720, "env_steps": 442368000, "exact_value_avg": 0.3510838747024536, "regret_dist": 0.5124967098236084, "regret_other_env": 0.8086177110671997, "regret_corner": 0.06831523776054382, "regret_row": 0.616439163684845, "regret_any": 0.8086958527565002, "regret_bot": 0.8522218465805054, "value_dist": 0.3510838747024536, "value_other_env": 0.07359708845615387, "value_corner": 0.767314076423645, "value_row": 0.2421874850988388, "value_any": 0.07355474680662155, "value_bot": 0.006404847837984562, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00720.png", "entropy": 0.7058136463165283} +{"ts": "2026-03-20T17:34:01.333471Z", "loop": 725, "env_steps": 445440000, "exact_value_avg": 0.35091790556907654, "regret_dist": 0.5126628279685974, "regret_other_env": 0.8086076974868774, "regret_corner": 0.068745456635952, "regret_row": 0.6134961247444153, "regret_any": 0.8086857795715332, "regret_bot": 0.8523814678192139, "value_dist": 0.35091790556907654, "value_other_env": 0.0736071988940239, "value_corner": 0.766883909702301, "value_row": 0.2451305389404297, "value_any": 0.07356482744216919, "value_bot": 0.0062452154234051704, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00725.png", "entropy": 0.7050507664680481} +{"ts": "2026-03-20T17:34:05.636454Z", "loop": 730, "env_steps": 448512000, "exact_value_avg": 0.35130730271339417, "regret_dist": 0.512273371219635, "regret_other_env": 0.8086187839508057, "regret_corner": 0.06775516271591187, "regret_row": 0.6216747164726257, "regret_any": 0.8086968064308167, "regret_bot": 0.8519416451454163, "value_dist": 0.35130730271339417, "value_other_env": 0.07359610497951508, "value_corner": 0.7678741216659546, "value_row": 0.23695194721221924, "value_any": 0.07355375587940216, "value_bot": 0.006684980820864439, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00730.png", "entropy": 0.7073747515678406} +{"ts": "2026-03-20T17:34:09.938650Z", "loop": 735, "env_steps": 451584000, "exact_value_avg": 0.351348876953125, "regret_dist": 0.5122317671775818, "regret_other_env": 0.8086233735084534, "regret_corner": 0.06764440983533859, "regret_row": 0.6270655393600464, "regret_any": 0.8087013959884644, "regret_bot": 0.8515980839729309, "value_dist": 0.351348876953125, "value_other_env": 0.07359150797128677, "value_corner": 0.767984926700592, "value_row": 0.231561079621315, "value_any": 0.07354918122291565, "value_bot": 0.0070286099798977375, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00735.png", "entropy": 0.7072853446006775} +{"ts": "2026-03-20T17:34:14.243219Z", "loop": 740, "env_steps": 454656000, "exact_value_avg": 0.351399689912796, "regret_dist": 0.5121810436248779, "regret_other_env": 0.8086664080619812, "regret_corner": 0.06745287775993347, "regret_row": 0.6249216198921204, "regret_any": 0.8087444305419922, "regret_bot": 0.8517359495162964, "value_dist": 0.351399689912796, "value_other_env": 0.07354848831892014, "value_corner": 0.7681764364242554, "value_row": 0.23370501399040222, "value_any": 0.07350621372461319, "value_bot": 0.006890610791742802, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00740.png", "entropy": 0.7057397961616516} +{"ts": "2026-03-20T17:34:18.547758Z", "loop": 745, "env_steps": 457728000, "exact_value_avg": 0.35123199224472046, "regret_dist": 0.5123487114906311, "regret_other_env": 0.8086647391319275, "regret_corner": 0.06787465512752533, "regret_row": 0.6173677444458008, "regret_any": 0.8087427616119385, "regret_bot": 0.852187991142273, "value_dist": 0.35123199224472046, "value_other_env": 0.07355017215013504, "value_corner": 0.7677546739578247, "value_row": 0.24125881493091583, "value_any": 0.07350785285234451, "value_bot": 0.006438619457185268, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00745.png", "entropy": 0.7044640779495239} +{"ts": "2026-03-20T17:34:22.854574Z", "loop": 750, "env_steps": 460800000, "exact_value_avg": 0.3506302833557129, "regret_dist": 0.5129504203796387, "regret_other_env": 0.808620035648346, "regret_corner": 0.06944592297077179, "regret_row": 0.6087613105773926, "regret_any": 0.8086981773376465, "regret_bot": 0.8526389002799988, "value_dist": 0.3506302833557129, "value_other_env": 0.07359487563371658, "value_corner": 0.7661833763122559, "value_row": 0.2498653680086136, "value_any": 0.07355250418186188, "value_bot": 0.005987685639411211, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00750.png", "entropy": 0.7022090554237366} +{"ts": "2026-03-20T17:34:27.157345Z", "loop": 755, "env_steps": 463872000, "exact_value_avg": 0.3510386645793915, "regret_dist": 0.5125420093536377, "regret_other_env": 0.8085428476333618, "regret_corner": 0.06854075193405151, "regret_row": 0.6131777167320251, "regret_any": 0.8086209893226624, "regret_bot": 0.8523849844932556, "value_dist": 0.3510386645793915, "value_other_env": 0.07367204129695892, "value_corner": 0.7670885920524597, "value_row": 0.24544894695281982, "value_any": 0.07362958043813705, "value_bot": 0.006241637282073498, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00755.png", "entropy": 0.7053191065788269} +{"ts": "2026-03-20T17:34:31.460671Z", "loop": 760, "env_steps": 466944000, "exact_value_avg": 0.3513320982456207, "regret_dist": 0.5122485756874084, "regret_other_env": 0.8085565567016602, "regret_corner": 0.0677865520119667, "regret_row": 0.6306589841842651, "regret_any": 0.8086346983909607, "regret_bot": 0.8513638377189636, "value_dist": 0.3513320982456207, "value_other_env": 0.07365832477807999, "value_corner": 0.7678427696228027, "value_row": 0.22796764969825745, "value_any": 0.07361593097448349, "value_bot": 0.007262824103236198, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00760.png", "entropy": 0.7089203596115112} +{"ts": "2026-03-20T17:34:35.761784Z", "loop": 765, "env_steps": 470016000, "exact_value_avg": 0.3507080674171448, "regret_dist": 0.5128725171089172, "regret_other_env": 0.8085768818855286, "regret_corner": 0.06931598484516144, "regret_row": 0.6396142244338989, "regret_any": 0.8086550235748291, "regret_bot": 0.8507611751556396, "value_dist": 0.3507080674171448, "value_other_env": 0.07363790273666382, "value_corner": 0.7663133144378662, "value_row": 0.21901246905326843, "value_any": 0.0735955685377121, "value_bot": 0.007865461520850658, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00765.png", "entropy": 0.7084993720054626} +{"ts": "2026-03-20T17:34:40.064169Z", "loop": 770, "env_steps": 473088000, "exact_value_avg": 0.35147812962532043, "regret_dist": 0.5121025443077087, "regret_other_env": 0.8084166049957275, "regret_corner": 0.06763140857219696, "regret_row": 0.6241809725761414, "regret_any": 0.8084949254989624, "regret_bot": 0.851723849773407, "value_dist": 0.35147812962532043, "value_other_env": 0.07379826158285141, "value_corner": 0.7679979205131531, "value_row": 0.23444564640522003, "value_any": 0.07375568896532059, "value_bot": 0.006902820896357298, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00770.png", "entropy": 0.7111859917640686} +{"ts": "2026-03-20T17:34:44.369659Z", "loop": 775, "env_steps": 476160000, "exact_value_avg": 0.35084080696105957, "regret_dist": 0.512739896774292, "regret_other_env": 0.8083310723304749, "regret_corner": 0.06935310363769531, "regret_row": 0.6098300814628601, "regret_any": 0.8084093332290649, "regret_bot": 0.8524969816207886, "value_dist": 0.35084080696105957, "value_other_env": 0.07388387620449066, "value_corner": 0.7662761807441711, "value_row": 0.24879653751850128, "value_any": 0.07384119927883148, "value_bot": 0.006129637360572815, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00775.png", "entropy": 0.709023654460907} +{"ts": "2026-03-20T17:34:48.673122Z", "loop": 780, "env_steps": 479232000, "exact_value_avg": 0.35149580240249634, "regret_dist": 0.5120849013328552, "regret_other_env": 0.8083508610725403, "regret_corner": 0.06768586486577988, "regret_row": 0.62156742811203, "regret_any": 0.8084292411804199, "regret_bot": 0.85182785987854, "value_dist": 0.35149580240249634, "value_other_env": 0.07386399805545807, "value_corner": 0.7679435014724731, "value_row": 0.23705920577049255, "value_any": 0.07382135093212128, "value_bot": 0.0067986962385475636, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00780.png", "entropy": 0.7114477157592773} +{"ts": "2026-03-20T17:34:52.974365Z", "loop": 785, "env_steps": 482304000, "exact_value_avg": 0.35098519921302795, "regret_dist": 0.5125954747200012, "regret_other_env": 0.8085446357727051, "regret_corner": 0.06867174059152603, "regret_row": 0.638144850730896, "regret_any": 0.8086227178573608, "regret_bot": 0.8508255481719971, "value_dist": 0.35098519921302795, "value_other_env": 0.07367026060819626, "value_corner": 0.7669576406478882, "value_row": 0.2204817235469818, "value_any": 0.07362788170576096, "value_bot": 0.007801127154380083, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00785.png", "entropy": 0.7081314325332642} +{"ts": "2026-03-20T17:34:57.274983Z", "loop": 790, "env_steps": 485376000, "exact_value_avg": 0.35115787386894226, "regret_dist": 0.5124228000640869, "regret_other_env": 0.8085634112358093, "regret_corner": 0.06821183115243912, "regret_row": 0.6366151571273804, "regret_any": 0.8086415529251099, "regret_bot": 0.8509624600410461, "value_dist": 0.35115787386894226, "value_other_env": 0.07365141808986664, "value_corner": 0.7674175500869751, "value_row": 0.22201140224933624, "value_any": 0.07360904663801193, "value_bot": 0.007664110977202654, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00790.png", "entropy": 0.7079166173934937} +{"ts": "2026-03-20T17:35:01.580034Z", "loop": 795, "env_steps": 488448000, "exact_value_avg": 0.35161522030830383, "regret_dist": 0.5119655132293701, "regret_other_env": 0.8084442615509033, "regret_corner": 0.06724730134010315, "regret_row": 0.6225929856300354, "regret_any": 0.8085224628448486, "regret_bot": 0.851835310459137, "value_dist": 0.35161522030830383, "value_other_env": 0.07377062737941742, "value_corner": 0.7683820724487305, "value_row": 0.2360336184501648, "value_any": 0.07372806966304779, "value_bot": 0.006791379768401384, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00795.png", "entropy": 0.7093883156776428} +{"ts": "2026-03-20T17:35:05.881729Z", "loop": 800, "env_steps": 491520000, "exact_value_avg": 0.35091161727905273, "regret_dist": 0.5126690864562988, "regret_other_env": 0.8084556460380554, "regret_corner": 0.06898912042379379, "regret_row": 0.6087958812713623, "regret_any": 0.8085339665412903, "regret_bot": 0.8525741696357727, "value_dist": 0.35091161727905273, "value_other_env": 0.07375921308994293, "value_corner": 0.7666402459144592, "value_row": 0.24983073770999908, "value_any": 0.07371663302183151, "value_bot": 0.006052437704056501, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00800.png", "entropy": 0.7041574120521545} +{"ts": "2026-03-20T17:35:10.185546Z", "loop": 805, "env_steps": 494592000, "exact_value_avg": 0.3510344922542572, "regret_dist": 0.5125462412834167, "regret_other_env": 0.8085048198699951, "regret_corner": 0.06860825419425964, "regret_row": 0.6096324324607849, "regret_any": 0.80858314037323, "regret_bot": 0.8525476455688477, "value_dist": 0.3510344922542572, "value_other_env": 0.07371006160974503, "value_corner": 0.767021119594574, "value_row": 0.24899420142173767, "value_any": 0.073667511343956, "value_bot": 0.00607895664870739, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00805.png", "entropy": 0.7032861113548279} +{"ts": "2026-03-20T17:35:14.486063Z", "loop": 810, "env_steps": 497664000, "exact_value_avg": 0.3512233793735504, "regret_dist": 0.5123572945594788, "regret_other_env": 0.8086600303649902, "regret_corner": 0.06790317595005035, "regret_row": 0.6378984451293945, "regret_any": 0.8087380528450012, "regret_bot": 0.850899875164032, "value_dist": 0.3512233793735504, "value_other_env": 0.07355482876300812, "value_corner": 0.7677261829376221, "value_row": 0.22072824835777283, "value_any": 0.07351255416870117, "value_bot": 0.007726762909442186, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00810.png", "entropy": 0.7047332525253296} +{"ts": "2026-03-20T17:35:18.790058Z", "loop": 815, "env_steps": 500736000, "exact_value_avg": 0.3506312966346741, "regret_dist": 0.5129494667053223, "regret_other_env": 0.8086958527565002, "regret_corner": 0.06932977586984634, "regret_row": 0.6439082026481628, "regret_any": 0.8087736964225769, "regret_bot": 0.8504798412322998, "value_dist": 0.3506312966346741, "value_other_env": 0.07351908087730408, "value_corner": 0.7662995457649231, "value_row": 0.21471841633319855, "value_any": 0.0734768807888031, "value_bot": 0.008146798238158226, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00815.png", "entropy": 0.7032870054244995} +{"ts": "2026-03-20T17:35:23.093185Z", "loop": 820, "env_steps": 503808000, "exact_value_avg": 0.3514707684516907, "regret_dist": 0.5121099352836609, "regret_other_env": 0.8083280920982361, "regret_corner": 0.06778259575366974, "regret_row": 0.6146735548973083, "regret_any": 0.8084065318107605, "regret_bot": 0.8522480726242065, "value_dist": 0.3514707684516907, "value_other_env": 0.07388681173324585, "value_corner": 0.7678467035293579, "value_row": 0.24395312368869781, "value_any": 0.07384409010410309, "value_bot": 0.006378563120961189, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00820.png", "entropy": 0.7095180153846741} +{"ts": "2026-03-20T17:35:27.400516Z", "loop": 825, "env_steps": 506880000, "exact_value_avg": 0.3507167100906372, "regret_dist": 0.5128639340400696, "regret_other_env": 0.8082656860351562, "regret_corner": 0.06976132839918137, "regret_row": 0.605735182762146, "regret_any": 0.8083441853523254, "regret_bot": 0.8526914119720459, "value_dist": 0.3507167100906372, "value_other_env": 0.0739491656422615, "value_corner": 0.7658680081367493, "value_row": 0.252891480922699, "value_any": 0.07390637695789337, "value_bot": 0.005935207009315491, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00825.png", "entropy": 0.7072640061378479} +{"ts": "2026-03-20T17:35:31.709300Z", "loop": 830, "env_steps": 509952000, "exact_value_avg": 0.35147809982299805, "regret_dist": 0.5121025443077087, "regret_other_env": 0.8082572221755981, "regret_corner": 0.06787051260471344, "regret_row": 0.6136223673820496, "regret_any": 0.8083357810974121, "regret_bot": 0.8522611260414124, "value_dist": 0.35147809982299805, "value_other_env": 0.07395761460065842, "value_corner": 0.7677587866783142, "value_row": 0.24500423669815063, "value_any": 0.07391480356454849, "value_bot": 0.006365481298416853, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00830.png", "entropy": 0.709583044052124} +{"ts": "2026-03-20T17:35:36.012698Z", "loop": 835, "env_steps": 513024000, "exact_value_avg": 0.351855605840683, "regret_dist": 0.5117250084877014, "regret_other_env": 0.8083054423332214, "regret_corner": 0.06685435026884079, "regret_row": 0.6224902272224426, "regret_any": 0.8083839416503906, "regret_bot": 0.8517488241195679, "value_dist": 0.351855605840683, "value_other_env": 0.07390935719013214, "value_corner": 0.7687749862670898, "value_row": 0.23613643646240234, "value_any": 0.0738665983080864, "value_bot": 0.0068778395652771, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00835.png", "entropy": 0.7100418210029602} +{"ts": "2026-03-20T17:35:40.317107Z", "loop": 840, "env_steps": 516096000, "exact_value_avg": 0.3518686890602112, "regret_dist": 0.5117120742797852, "regret_other_env": 0.8083900809288025, "regret_corner": 0.06669491529464722, "regret_row": 0.6287875771522522, "regret_any": 0.8084684014320374, "regret_bot": 0.8514072299003601, "value_dist": 0.3518686890602112, "value_other_env": 0.07382485270500183, "value_corner": 0.768934428691864, "value_row": 0.22983896732330322, "value_any": 0.07378220558166504, "value_bot": 0.007219448685646057, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00840.png", "entropy": 0.709303617477417} +{"ts": "2026-03-20T17:35:44.619996Z", "loop": 845, "env_steps": 519168000, "exact_value_avg": 0.35196059942245483, "regret_dist": 0.5116201639175415, "regret_other_env": 0.8083621263504028, "regret_corner": 0.06650711596012115, "regret_row": 0.6240439414978027, "regret_any": 0.8084404468536377, "regret_bot": 0.8517204523086548, "value_dist": 0.35196059942245483, "value_other_env": 0.07385280728340149, "value_corner": 0.7691222429275513, "value_row": 0.23458269238471985, "value_any": 0.07381010800600052, "value_bot": 0.006906143389642239, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00845.png", "entropy": 0.7096537351608276} +{"ts": "2026-03-20T17:35:48.925555Z", "loop": 850, "env_steps": 522240000, "exact_value_avg": 0.35188859701156616, "regret_dist": 0.5116921067237854, "regret_other_env": 0.8083041310310364, "regret_corner": 0.06677403301000595, "regret_row": 0.6178910732269287, "regret_any": 0.8083825707435608, "regret_bot": 0.8520593643188477, "value_dist": 0.35188859701156616, "value_other_env": 0.07391077280044556, "value_corner": 0.7688552737236023, "value_row": 0.24073554575443268, "value_any": 0.07386797666549683, "value_bot": 0.0065672742202878, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00850.png", "entropy": 0.7090317606925964} +{"ts": "2026-03-20T17:35:53.231739Z", "loop": 855, "env_steps": 525312000, "exact_value_avg": 0.3520936369895935, "regret_dist": 0.5114870667457581, "regret_other_env": 0.8083551526069641, "regret_corner": 0.066184863448143, "regret_row": 0.6232886910438538, "regret_any": 0.8084335923194885, "regret_bot": 0.8517134189605713, "value_dist": 0.3520936369895935, "value_other_env": 0.07385974377393723, "value_corner": 0.769444465637207, "value_row": 0.23533795773983002, "value_any": 0.07381699979305267, "value_bot": 0.006913227494806051, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00855.png", "entropy": 0.70755535364151} +{"ts": "2026-03-20T17:35:57.541399Z", "loop": 860, "env_steps": 528384000, "exact_value_avg": 0.35212674736976624, "regret_dist": 0.5114539265632629, "regret_other_env": 0.8084430694580078, "regret_corner": 0.06597017496824265, "regret_row": 0.6196708679199219, "regret_any": 0.8085213899612427, "regret_bot": 0.8519527316093445, "value_dist": 0.35212674736976624, "value_other_env": 0.07377178966999054, "value_corner": 0.769659161567688, "value_row": 0.2389557659626007, "value_any": 0.07372912764549255, "value_bot": 0.006673905998468399, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00860.png", "entropy": 0.7042787671089172} +{"ts": "2026-03-20T17:36:01.844921Z", "loop": 865, "env_steps": 531456000, "exact_value_avg": 0.35173094272613525, "regret_dist": 0.5118497014045715, "regret_other_env": 0.808452308177948, "regret_corner": 0.06694584339857101, "regret_row": 0.6110589504241943, "regret_any": 0.8085307478904724, "regret_bot": 0.8524187207221985, "value_dist": 0.35173094272613525, "value_other_env": 0.07376255840063095, "value_corner": 0.7686835527420044, "value_row": 0.24756766855716705, "value_any": 0.07371985912322998, "value_bot": 0.006207919679582119, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00865.png", "entropy": 0.7008253931999207} +{"ts": "2026-03-20T17:36:06.149186Z", "loop": 870, "env_steps": 534528000, "exact_value_avg": 0.35234785079956055, "regret_dist": 0.5112327933311462, "regret_other_env": 0.8084596991539001, "regret_corner": 0.065392404794693, "regret_row": 0.6211323142051697, "regret_any": 0.8085380792617798, "regret_bot": 0.85186368227005, "value_dist": 0.35234785079956055, "value_other_env": 0.07375514507293701, "value_corner": 0.7702369093894958, "value_row": 0.2374943047761917, "value_any": 0.07371246069669724, "value_bot": 0.006762930657714605, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00870.png", "entropy": 0.7029543519020081} +{"ts": "2026-03-20T17:36:10.455780Z", "loop": 875, "env_steps": 537600000, "exact_value_avg": 0.352430522441864, "regret_dist": 0.5111501812934875, "regret_other_env": 0.8085198402404785, "regret_corner": 0.06509558111429214, "regret_row": 0.629513144493103, "regret_any": 0.8085982203483582, "regret_bot": 0.8513641953468323, "value_dist": 0.352430522441864, "value_other_env": 0.07369500398635864, "value_corner": 0.7705337405204773, "value_row": 0.22911350429058075, "value_any": 0.07365242391824722, "value_bot": 0.007262497674673796, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00875.png", "entropy": 0.702340841293335} +{"ts": "2026-03-20T17:36:14.759130Z", "loop": 880, "env_steps": 540672000, "exact_value_avg": 0.3522800803184509, "regret_dist": 0.5113006234169006, "regret_other_env": 0.8084694147109985, "regret_corner": 0.06554733961820602, "regret_row": 0.6150338053703308, "regret_any": 0.8085477948188782, "regret_bot": 0.8522007465362549, "value_dist": 0.3522800803184509, "value_other_env": 0.0737454742193222, "value_corner": 0.7700819969177246, "value_row": 0.24359282851219177, "value_any": 0.07370277494192123, "value_bot": 0.00642579747363925, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00880.png", "entropy": 0.7002285718917847} +{"ts": "2026-03-20T17:36:19.064861Z", "loop": 885, "env_steps": 543744000, "exact_value_avg": 0.35229578614234924, "regret_dist": 0.5112848877906799, "regret_other_env": 0.8085208535194397, "regret_corner": 0.06543097645044327, "regret_row": 0.6140666604042053, "regret_any": 0.8085991740226746, "regret_bot": 0.8522906303405762, "value_dist": 0.35229578614234924, "value_other_env": 0.07369408011436462, "value_corner": 0.7701983451843262, "value_row": 0.24455992877483368, "value_any": 0.07365142554044724, "value_bot": 0.0063359676860272884, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00885.png", "entropy": 0.6989583969116211} +{"ts": "2026-03-20T17:36:23.365966Z", "loop": 890, "env_steps": 546816000, "exact_value_avg": 0.35218891501426697, "regret_dist": 0.511391818523407, "regret_other_env": 0.8087128400802612, "regret_corner": 0.06541015952825546, "regret_row": 0.6398030519485474, "regret_any": 0.8087908625602722, "regret_bot": 0.8508095145225525, "value_dist": 0.35218891501426697, "value_other_env": 0.0735020712018013, "value_corner": 0.7702191472053528, "value_row": 0.2188236266374588, "value_any": 0.07345972210168839, "value_bot": 0.007817041128873825, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00890.png", "entropy": 0.6985598206520081} +{"ts": "2026-03-20T17:36:27.667502Z", "loop": 895, "env_steps": 549888000, "exact_value_avg": 0.3523792028427124, "regret_dist": 0.5112015008926392, "regret_other_env": 0.8086422681808472, "regret_corner": 0.06504032015800476, "regret_row": 0.638859748840332, "regret_any": 0.8087203502655029, "regret_bot": 0.8508278131484985, "value_dist": 0.3523792028427124, "value_other_env": 0.07357266545295715, "value_corner": 0.7705889940261841, "value_row": 0.21976682543754578, "value_any": 0.07353019714355469, "value_bot": 0.007798829581588507, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00895.png", "entropy": 0.6986585259437561} +{"ts": "2026-03-20T17:36:31.967664Z", "loop": 900, "env_steps": 552960000, "exact_value_avg": 0.3525477945804596, "regret_dist": 0.5110328793525696, "regret_other_env": 0.8084046244621277, "regret_corner": 0.06497528403997421, "regret_row": 0.6124635338783264, "regret_any": 0.8084831833839417, "regret_bot": 0.8522915840148926, "value_dist": 0.3525477945804596, "value_other_env": 0.07381025701761246, "value_corner": 0.7706540822982788, "value_row": 0.24616310000419617, "value_any": 0.07376740872859955, "value_bot": 0.006335160229355097, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00900.png", "entropy": 0.6979434490203857} +{"ts": "2026-03-20T17:36:36.270271Z", "loop": 905, "env_steps": 556032000, "exact_value_avg": 0.3531046509742737, "regret_dist": 0.5104760527610779, "regret_other_env": 0.8083733916282654, "regret_corner": 0.06362995505332947, "regret_row": 0.6231368780136108, "regret_any": 0.8084520101547241, "regret_bot": 0.8516636490821838, "value_dist": 0.3531046509742737, "value_other_env": 0.07384148985147476, "value_corner": 0.7719993591308594, "value_row": 0.23548969626426697, "value_any": 0.07379860430955887, "value_bot": 0.006963040214031935, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00905.png", "entropy": 0.7002862095832825} +{"ts": "2026-03-20T17:36:40.568580Z", "loop": 910, "env_steps": 559104000, "exact_value_avg": 0.35171887278556824, "regret_dist": 0.5118618011474609, "regret_other_env": 0.8086715936660767, "regret_corner": 0.06664709001779556, "regret_row": 0.6485872864723206, "regret_any": 0.8087496757507324, "regret_bot": 0.8500373363494873, "value_dist": 0.35171887278556824, "value_other_env": 0.07354329526424408, "value_corner": 0.7689822316169739, "value_row": 0.21003925800323486, "value_any": 0.07350084185600281, "value_bot": 0.008589304983615875, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00910.png", "entropy": 0.6925570368766785} +{"ts": "2026-03-20T17:36:44.871856Z", "loop": 915, "env_steps": 562176000, "exact_value_avg": 0.35336002707481384, "regret_dist": 0.5102206468582153, "regret_other_env": 0.8084986805915833, "regret_corner": 0.06280352175235748, "regret_row": 0.6288231015205383, "regret_any": 0.8085771799087524, "regret_bot": 0.8514668345451355, "value_dist": 0.35336002707481384, "value_other_env": 0.07371620833873749, "value_corner": 0.7728257775306702, "value_row": 0.22980354726314545, "value_any": 0.07367347180843353, "value_bot": 0.007159791421145201, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00915.png", "entropy": 0.6996963024139404} +{"ts": "2026-03-20T17:36:49.180355Z", "loop": 920, "env_steps": 565248000, "exact_value_avg": 0.353093683719635, "regret_dist": 0.5104870200157166, "regret_other_env": 0.8083969354629517, "regret_corner": 0.0636221393942833, "regret_row": 0.6144933104515076, "regret_any": 0.8084754943847656, "regret_bot": 0.8522684574127197, "value_dist": 0.353093683719635, "value_other_env": 0.07381796091794968, "value_corner": 0.7720072269439697, "value_row": 0.2441333532333374, "value_any": 0.07377511262893677, "value_bot": 0.006358184851706028, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00920.png", "entropy": 0.6986058950424194} +{"ts": "2026-03-20T17:36:53.487307Z", "loop": 925, "env_steps": 568320000, "exact_value_avg": 0.3535294830799103, "regret_dist": 0.5100512504577637, "regret_other_env": 0.8084424138069153, "regret_corner": 0.06246441975235939, "regret_row": 0.6334024667739868, "regret_any": 0.8085208535194397, "regret_bot": 0.8511978983879089, "value_dist": 0.3535294830799103, "value_other_env": 0.07377251982688904, "value_corner": 0.7731649279594421, "value_row": 0.22522413730621338, "value_any": 0.07372971624135971, "value_bot": 0.007428734563291073, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00925.png", "entropy": 0.699670135974884} +{"ts": "2026-03-20T17:36:57.792645Z", "loop": 930, "env_steps": 571392000, "exact_value_avg": 0.3530493676662445, "regret_dist": 0.5105313658714294, "regret_other_env": 0.8085117936134338, "regret_corner": 0.06356062740087509, "regret_row": 0.6438320875167847, "regret_any": 0.8085902333259583, "regret_bot": 0.8504900932312012, "value_dist": 0.3530493676662445, "value_other_env": 0.07370311766862869, "value_corner": 0.7720686793327332, "value_row": 0.21479454636573792, "value_any": 0.07366041839122772, "value_bot": 0.008136570453643799, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00930.png", "entropy": 0.6956920623779297} +{"ts": "2026-03-20T17:37:02.102305Z", "loop": 935, "env_steps": 574464000, "exact_value_avg": 0.3540859818458557, "regret_dist": 0.5094947218894958, "regret_other_env": 0.8081938624382019, "regret_corner": 0.06144599989056587, "regret_row": 0.6214585304260254, "regret_any": 0.8082727789878845, "regret_bot": 0.8517448306083679, "value_dist": 0.3540859818458557, "value_other_env": 0.07402104884386063, "value_corner": 0.7741833329200745, "value_row": 0.23716813325881958, "value_any": 0.07397785782814026, "value_bot": 0.006881764158606529, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00935.png", "entropy": 0.6991662979125977} +{"ts": "2026-03-20T17:37:06.408677Z", "loop": 940, "env_steps": 577536000, "exact_value_avg": 0.3544328808784485, "regret_dist": 0.5091478228569031, "regret_other_env": 0.8081406354904175, "regret_corner": 0.0606585368514061, "regret_row": 0.6236567497253418, "regret_any": 0.8082196712493896, "regret_bot": 0.8515818119049072, "value_dist": 0.3544328808784485, "value_other_env": 0.07407428324222565, "value_corner": 0.7749707698822021, "value_row": 0.23496989905834198, "value_any": 0.07403095811605453, "value_bot": 0.007044808007776737, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00940.png", "entropy": 0.6980056166648865} +{"ts": "2026-03-20T17:37:10.714123Z", "loop": 945, "env_steps": 580608000, "exact_value_avg": 0.3547280728816986, "regret_dist": 0.5088525414466858, "regret_other_env": 0.8081041574478149, "regret_corner": 0.05997508764266968, "regret_row": 0.6201342940330505, "regret_any": 0.8081833720207214, "regret_bot": 0.8518078923225403, "value_dist": 0.3547280728816986, "value_other_env": 0.07411064207553864, "value_corner": 0.7756542563438416, "value_row": 0.23849236965179443, "value_any": 0.07406722754240036, "value_bot": 0.006818717811256647, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00945.png", "entropy": 0.6966665387153625} +{"ts": "2026-03-20T17:37:15.016847Z", "loop": 950, "env_steps": 583680000, "exact_value_avg": 0.3546864688396454, "regret_dist": 0.5088942646980286, "regret_other_env": 0.8080393671989441, "regret_corner": 0.060176488012075424, "regret_row": 0.6126409769058228, "regret_any": 0.8081187009811401, "regret_bot": 0.8521985411643982, "value_dist": 0.3546864688396454, "value_other_env": 0.07417549192905426, "value_corner": 0.7754529118537903, "value_row": 0.24598565697669983, "value_any": 0.07413196563720703, "value_bot": 0.006428147666156292, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00950.png", "entropy": 0.6943378448486328} +{"ts": "2026-03-20T17:37:19.319584Z", "loop": 955, "env_steps": 586752000, "exact_value_avg": 0.35508933663368225, "regret_dist": 0.5084913969039917, "regret_other_env": 0.8080235123634338, "regret_corner": 0.059193145483732224, "regret_row": 0.6405513286590576, "regret_any": 0.8081026673316956, "regret_bot": 0.8506173491477966, "value_dist": 0.35508933663368225, "value_other_env": 0.07419142127037048, "value_corner": 0.7764361500740051, "value_row": 0.21807532012462616, "value_any": 0.07414786517620087, "value_bot": 0.008009279146790504, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00955.png", "entropy": 0.6945922374725342} +{"ts": "2026-03-20T17:37:23.623196Z", "loop": 960, "env_steps": 589824000, "exact_value_avg": 0.3560057580471039, "regret_dist": 0.5075749158859253, "regret_other_env": 0.8077245950698853, "regret_corner": 0.05735034495592117, "regret_row": 0.6285865306854248, "regret_any": 0.8078043460845947, "regret_bot": 0.8512139320373535, "value_dist": 0.3560057580471039, "value_other_env": 0.0744902715086937, "value_corner": 0.7782790064811707, "value_row": 0.23004010319709778, "value_any": 0.07444626092910767, "value_bot": 0.0074126687832176685, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00960.png", "entropy": 0.6969979405403137} +{"ts": "2026-03-20T17:37:27.927500Z", "loop": 965, "env_steps": 592896000, "exact_value_avg": 0.3563292622566223, "regret_dist": 0.5072514414787292, "regret_other_env": 0.8075183033943176, "regret_corner": 0.0568510964512825, "regret_row": 0.6181832551956177, "regret_any": 0.8075982928276062, "regret_bot": 0.851685643196106, "value_dist": 0.3563292622566223, "value_other_env": 0.0746966004371643, "value_corner": 0.7787782549858093, "value_row": 0.24044331908226013, "value_any": 0.07465224713087082, "value_bot": 0.006941033061593771, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00965.png", "entropy": 0.6954443454742432} +{"ts": "2026-03-20T17:37:32.231490Z", "loop": 970, "env_steps": 595968000, "exact_value_avg": 0.35708141326904297, "regret_dist": 0.5064992308616638, "regret_other_env": 0.8073790073394775, "regret_corner": 0.05517955869436264, "regret_row": 0.6234632134437561, "regret_any": 0.80745929479599, "regret_bot": 0.8513767719268799, "value_dist": 0.35708141326904297, "value_other_env": 0.0748358890414238, "value_corner": 0.7804496884346008, "value_row": 0.23516345024108887, "value_any": 0.07479128986597061, "value_bot": 0.007249830290675163, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00970.png", "entropy": 0.694373369216919} +{"ts": "2026-03-20T17:37:36.534845Z", "loop": 975, "env_steps": 599040000, "exact_value_avg": 0.3577811121940613, "regret_dist": 0.5057995319366455, "regret_other_env": 0.8072086572647095, "regret_corner": 0.05368586257100105, "regret_row": 0.6295852065086365, "regret_any": 0.8072893023490906, "regret_bot": 0.8509773015975952, "value_dist": 0.3577811121940613, "value_other_env": 0.07500623911619186, "value_corner": 0.7819434404373169, "value_row": 0.2290414422750473, "value_any": 0.074961356818676, "value_bot": 0.00764929736033082, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00975.png", "entropy": 0.6923123002052307} +{"ts": "2026-03-20T17:37:40.838464Z", "loop": 980, "env_steps": 602112000, "exact_value_avg": 0.35844874382019043, "regret_dist": 0.5051319599151611, "regret_other_env": 0.8069929480552673, "regret_corner": 0.052340373396873474, "regret_row": 0.6356542706489563, "regret_any": 0.8070740103721619, "regret_bot": 0.8505532741546631, "value_dist": 0.35844874382019043, "value_other_env": 0.07522188127040863, "value_corner": 0.7832890152931213, "value_row": 0.22297237813472748, "value_any": 0.0751766487956047, "value_bot": 0.008073391392827034, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00980.png", "entropy": 0.6890896558761597} +{"ts": "2026-03-20T17:37:45.140140Z", "loop": 985, "env_steps": 605184000, "exact_value_avg": 0.3593123257160187, "regret_dist": 0.5042682886123657, "regret_other_env": 0.8067765235900879, "regret_corner": 0.05050598084926605, "regret_row": 0.6187002658843994, "regret_any": 0.8068578839302063, "regret_bot": 0.8513728976249695, "value_dist": 0.3593123257160187, "value_other_env": 0.07543830573558807, "value_corner": 0.785123348236084, "value_row": 0.2399263232946396, "value_any": 0.0753927156329155, "value_bot": 0.007253766059875488, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00985.png", "entropy": 0.6874050498008728} +{"ts": "2026-03-20T17:37:49.443346Z", "loop": 990, "env_steps": 608256000, "exact_value_avg": 0.36039066314697266, "regret_dist": 0.5031899809837341, "regret_other_env": 0.8064327239990234, "regret_corner": 0.04832573980093002, "regret_row": 0.6266375780105591, "regret_any": 0.8065146803855896, "regret_bot": 0.850908637046814, "value_dist": 0.36039066314697266, "value_other_env": 0.07578203827142715, "value_corner": 0.7873035669326782, "value_row": 0.2319890260696411, "value_any": 0.075735904276371, "value_bot": 0.007718037813901901, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00990.png", "entropy": 0.6860176920890808} +{"ts": "2026-03-20T17:37:53.744462Z", "loop": 995, "env_steps": 611328000, "exact_value_avg": 0.3581216633319855, "regret_dist": 0.5054590106010437, "regret_other_env": 0.806201159954071, "regret_corner": 0.05434567853808403, "regret_row": 0.6673142313957214, "regret_any": 0.8062835335731506, "regret_bot": 0.848198413848877, "value_dist": 0.3581216633319855, "value_other_env": 0.07601365447044373, "value_corner": 0.7812836766242981, "value_row": 0.19131243228912354, "value_any": 0.07596705108880997, "value_bot": 0.01042823027819395, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_00995.png", "entropy": 0.6623193621635437} +{"ts": "2026-03-20T17:37:58.045674Z", "loop": 1000, "env_steps": 614400000, "exact_value_avg": 0.3585822880268097, "regret_dist": 0.5049983859062195, "regret_other_env": 0.8062845468521118, "regret_corner": 0.05306908115744591, "regret_row": 0.5850308537483215, "regret_any": 0.8063668012619019, "regret_bot": 0.8526093363761902, "value_dist": 0.3585822880268097, "value_other_env": 0.07593027502298355, "value_corner": 0.7825602889060974, "value_row": 0.2735958397388458, "value_any": 0.07588387280702591, "value_bot": 0.0060173524543643, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01000.png", "entropy": 0.6642181277275085} +{"ts": "2026-03-20T17:38:02.346791Z", "loop": 1005, "env_steps": 617472000, "exact_value_avg": 0.36336439847946167, "regret_dist": 0.5002162456512451, "regret_other_env": 0.8048028349876404, "regret_corner": 0.043336354196071625, "regret_row": 0.6434884667396545, "regret_any": 0.8048872947692871, "regret_bot": 0.8494660258293152, "value_dist": 0.36336439847946167, "value_other_env": 0.07741204649209976, "value_corner": 0.7922929525375366, "value_row": 0.21513815224170685, "value_any": 0.07736328989267349, "value_bot": 0.009160589426755905, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01005.png", "entropy": 0.6747375726699829} +{"ts": "2026-03-20T17:38:06.649023Z", "loop": 1010, "env_steps": 620544000, "exact_value_avg": 0.36432456970214844, "regret_dist": 0.49925607442855835, "regret_other_env": 0.8046943545341492, "regret_corner": 0.04109858348965645, "regret_row": 0.6118353605270386, "regret_any": 0.8047789931297302, "regret_bot": 0.8510290384292603, "value_dist": 0.36432456970214844, "value_other_env": 0.0775204747915268, "value_corner": 0.7945306897163391, "value_row": 0.246791273355484, "value_any": 0.07747156172990799, "value_bot": 0.007597618270665407, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01010.png", "entropy": 0.6723586916923523} +{"ts": "2026-03-20T17:38:10.953820Z", "loop": 1015, "env_steps": 623616000, "exact_value_avg": 0.36604270339012146, "regret_dist": 0.4975379705429077, "regret_other_env": 0.8038327097892761, "regret_corner": 0.03809575363993645, "regret_row": 0.6112242937088013, "regret_any": 0.8039187788963318, "regret_bot": 0.8507310748100281, "value_dist": 0.36604270339012146, "value_other_env": 0.07838208973407745, "value_corner": 0.7975335717201233, "value_row": 0.2474023401737213, "value_any": 0.0783318355679512, "value_bot": 0.007895560935139656, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01015.png", "entropy": 0.6671916246414185} +{"ts": "2026-03-20T17:38:15.255932Z", "loop": 1020, "env_steps": 626688000, "exact_value_avg": 0.3680858016014099, "regret_dist": 0.49549487233161926, "regret_other_env": 0.8019381165504456, "regret_corner": 0.03582999110221863, "regret_row": 0.6472092866897583, "regret_any": 0.8020270466804504, "regret_bot": 0.8481432199478149, "value_dist": 0.3680858016014099, "value_other_env": 0.08027669787406921, "value_corner": 0.799799382686615, "value_row": 0.2114173173904419, "value_any": 0.08022350817918777, "value_bot": 0.010483394376933575, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01020.png", "entropy": 0.6546297073364258} +{"ts": "2026-03-20T17:38:19.560070Z", "loop": 1025, "env_steps": 629760000, "exact_value_avg": 0.36875608563423157, "regret_dist": 0.4948245882987976, "regret_other_env": 0.8023260831832886, "regret_corner": 0.03357228264212608, "regret_row": 0.5972265601158142, "regret_any": 0.8024144172668457, "regret_bot": 0.8504801392555237, "value_dist": 0.36875608563423157, "value_other_env": 0.07988880574703217, "value_corner": 0.8020570278167725, "value_row": 0.2614000737667084, "value_any": 0.07983620464801788, "value_bot": 0.008146560750901699, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01025.png", "entropy": 0.6474694609642029} +{"ts": "2026-03-20T17:38:23.864128Z", "loop": 1030, "env_steps": 632832000, "exact_value_avg": 0.3695084750652313, "regret_dist": 0.49407219886779785, "regret_other_env": 0.7985320091247559, "regret_corner": 0.03738247603178024, "regret_row": 0.6773988604545593, "regret_any": 0.7986261248588562, "regret_bot": 0.8445968627929688, "value_dist": 0.3695084750652313, "value_other_env": 0.08368293195962906, "value_corner": 0.7982468008995056, "value_row": 0.18122781813144684, "value_any": 0.08362448960542679, "value_bot": 0.014029750600457191, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01030.png", "entropy": 0.6009596586227417} +{"ts": "2026-03-20T17:38:28.169911Z", "loop": 1035, "env_steps": 635904000, "exact_value_avg": 0.37471258640289307, "regret_dist": 0.4888680875301361, "regret_other_env": 0.7989913821220398, "regret_corner": 0.023683050647377968, "regret_row": 0.6123696565628052, "regret_any": 0.7990849614143372, "regret_bot": 0.8484581708908081, "value_dist": 0.37471258640289307, "value_other_env": 0.08322343975305557, "value_corner": 0.8119462728500366, "value_row": 0.2462569922208786, "value_any": 0.08316563069820404, "value_bot": 0.010168390348553658, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01035.png", "entropy": 0.6159132719039917} +{"ts": "2026-03-20T17:38:32.470783Z", "loop": 1040, "env_steps": 638976000, "exact_value_avg": 0.3754265308380127, "regret_dist": 0.4881541430950165, "regret_other_env": 0.7983936667442322, "regret_corner": 0.022794844582676888, "regret_row": 0.5890536904335022, "regret_any": 0.7984880805015564, "regret_bot": 0.8488412499427795, "value_dist": 0.3754265308380127, "value_other_env": 0.08382126688957214, "value_corner": 0.8128344416618347, "value_row": 0.269572913646698, "value_any": 0.08376254886388779, "value_bot": 0.009785348549485207, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01040.png", "entropy": 0.5944167971611023} +{"ts": "2026-03-20T17:38:36.770969Z", "loop": 1045, "env_steps": 642048000, "exact_value_avg": 0.380864679813385, "regret_dist": 0.4827159643173218, "regret_other_env": 0.7929092645645142, "regret_corner": 0.01742597483098507, "regret_row": 0.633117139339447, "regret_any": 0.7930120825767517, "regret_bot": 0.8444949984550476, "value_dist": 0.380864679813385, "value_other_env": 0.0893055871129036, "value_corner": 0.818203330039978, "value_row": 0.22550949454307556, "value_any": 0.0892384797334671, "value_bot": 0.014131695963442326, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01045.png", "entropy": 0.5612431764602661} +{"ts": "2026-03-20T17:38:41.072610Z", "loop": 1050, "env_steps": 645120000, "exact_value_avg": 0.3827604651451111, "regret_dist": 0.48082026839256287, "regret_other_env": 0.7878802418708801, "regret_corner": 0.020230228081345558, "regret_row": 0.664573073387146, "regret_any": 0.7879905700683594, "regret_bot": 0.8400429487228394, "value_dist": 0.3827604651451111, "value_other_env": 0.09433465451002121, "value_corner": 0.8153991103172302, "value_row": 0.1940535306930542, "value_any": 0.09426000714302063, "value_bot": 0.01858380064368248, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01050.png", "entropy": 0.5060555934906006} +{"ts": "2026-03-20T17:38:45.373878Z", "loop": 1055, "env_steps": 648192000, "exact_value_avg": 0.38597679138183594, "regret_dist": 0.47760388255119324, "regret_other_env": 0.7878401875495911, "regret_corner": 0.012249314226210117, "regret_row": 0.6147112846374512, "regret_any": 0.7879506349563599, "regret_bot": 0.8422988057136536, "value_dist": 0.38597679138183594, "value_other_env": 0.09437467157840729, "value_corner": 0.8233799934387207, "value_row": 0.24391528964042664, "value_any": 0.09429997205734253, "value_bot": 0.016327742487192154, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01055.png", "entropy": 0.5106515884399414} +{"ts": "2026-03-20T17:38:49.676411Z", "loop": 1060, "env_steps": 651264000, "exact_value_avg": 0.3787960112094879, "regret_dist": 0.48478469252586365, "regret_other_env": 0.7946385145187378, "regret_corner": 0.020003948360681534, "regret_row": 0.5285951495170593, "regret_any": 0.7947386503219604, "regret_bot": 0.8476086854934692, "value_dist": 0.3787960112094879, "value_other_env": 0.08757638931274414, "value_corner": 0.8156254291534424, "value_row": 0.33003151416778564, "value_any": 0.08751197159290314, "value_bot": 0.011017885990440845, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01060.png", "entropy": 0.48511382937431335} +{"ts": "2026-03-20T17:38:53.979546Z", "loop": 1065, "env_steps": 654336000, "exact_value_avg": 0.3884495198726654, "regret_dist": 0.47513115406036377, "regret_other_env": 0.7750862240791321, "regret_corner": 0.02519853226840496, "regret_row": 0.6771301627159119, "regret_any": 0.7752158045768738, "regret_bot": 0.8319555521011353, "value_dist": 0.3884495198726654, "value_other_env": 0.10712862014770508, "value_corner": 0.8104308247566223, "value_row": 0.18149647116661072, "value_any": 0.10703478753566742, "value_bot": 0.026671012863516808, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01065.png", "entropy": 0.3998306691646576} +{"ts": "2026-03-20T17:38:58.283637Z", "loop": 1070, "env_steps": 657408000, "exact_value_avg": 0.39274725317955017, "regret_dist": 0.4708334505558014, "regret_other_env": 0.7798197269439697, "regret_corner": 0.00735399778932333, "regret_row": 0.5789810419082642, "regret_any": 0.7799421548843384, "regret_bot": 0.8392149806022644, "value_dist": 0.39274725317955017, "value_other_env": 0.10239522904157639, "value_corner": 0.8282753229141235, "value_row": 0.27964556217193604, "value_any": 0.10230845957994461, "value_bot": 0.019411668181419373, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01070.png", "entropy": 0.4378332495689392} +{"ts": "2026-03-20T17:39:02.587012Z", "loop": 1075, "env_steps": 660480000, "exact_value_avg": 0.3971859812736511, "regret_dist": 0.46639469265937805, "regret_other_env": 0.7725988626480103, "regret_corner": 0.0070883906446397305, "regret_row": 0.6024423837661743, "regret_any": 0.7727322578430176, "regret_bot": 0.8353504538536072, "value_dist": 0.3971859812736511, "value_other_env": 0.1096159815788269, "value_corner": 0.8285409808158875, "value_row": 0.25618425011634827, "value_any": 0.10951832681894302, "value_bot": 0.0232761949300766, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01075.png", "entropy": 0.40829354524612427} +{"ts": "2026-03-20T17:39:06.889552Z", "loop": 1080, "env_steps": 663552000, "exact_value_avg": 0.4002668559551239, "regret_dist": 0.46331384778022766, "regret_other_env": 0.7675630450248718, "regret_corner": 0.006939981132745743, "regret_row": 0.6040725111961365, "regret_any": 0.7677039504051208, "regret_bot": 0.8331224322319031, "value_dist": 0.4002668559551239, "value_other_env": 0.11465185880661011, "value_corner": 0.8286893367767334, "value_row": 0.2545540928840637, "value_any": 0.11454661190509796, "value_bot": 0.025504227727651596, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01080.png", "entropy": 0.3871000409126282} +{"ts": "2026-03-20T17:39:11.192218Z", "loop": 1085, "env_steps": 666624000, "exact_value_avg": 0.40355241298675537, "regret_dist": 0.4600282907485962, "regret_other_env": 0.7618104815483093, "regret_corner": 0.007355012930929661, "regret_row": 0.6030295491218567, "regret_any": 0.7619600892066956, "regret_bot": 0.83088618516922, "value_dist": 0.40355241298675537, "value_other_env": 0.120404452085495, "value_corner": 0.8282743096351624, "value_row": 0.2555971145629883, "value_any": 0.12029052525758743, "value_bot": 0.027740485966205597, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01085.png", "entropy": 0.3689684569835663} +{"ts": "2026-03-20T17:39:15.496526Z", "loop": 1090, "env_steps": 669696000, "exact_value_avg": 0.4055716395378113, "regret_dist": 0.4580090045928955, "regret_other_env": 0.7595052719116211, "regret_corner": 0.005764603614807129, "regret_row": 0.5656634569168091, "regret_any": 0.7596583962440491, "regret_bot": 0.8316042423248291, "value_dist": 0.4055716395378113, "value_other_env": 0.12270959466695786, "value_corner": 0.8298647403717041, "value_row": 0.2929632067680359, "value_any": 0.12259219586849213, "value_bot": 0.027022425085306168, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01090.png", "entropy": 0.37869036197662354} +{"ts": "2026-03-20T17:39:19.798648Z", "loop": 1095, "env_steps": 672768000, "exact_value_avg": 0.40811967849731445, "regret_dist": 0.45546093583106995, "regret_other_env": 0.747187077999115, "regret_corner": 0.017871735617518425, "regret_row": 0.6223422288894653, "regret_any": 0.7473588585853577, "regret_bot": 0.8264241218566895, "value_dist": 0.40811967849731445, "value_other_env": 0.1350277215242386, "value_corner": 0.8177576065063477, "value_row": 0.23628437519073486, "value_any": 0.13489171862602234, "value_bot": 0.032202523201704025, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01095.png", "entropy": 0.35333728790283203} +{"ts": "2026-03-20T17:39:24.103441Z", "loop": 1100, "env_steps": 675840000, "exact_value_avg": 0.40583139657974243, "regret_dist": 0.45774930715560913, "regret_other_env": 0.7593655586242676, "regret_corner": 0.005324823781847954, "regret_row": 0.5099406838417053, "regret_any": 0.7595189809799194, "regret_bot": 0.8350178599357605, "value_dist": 0.40583139657974243, "value_other_env": 0.12284930795431137, "value_corner": 0.8303045034408569, "value_row": 0.34868597984313965, "value_any": 0.12273170053958893, "value_bot": 0.02360873483121395, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01100.png", "entropy": 0.4018818736076355} +{"ts": "2026-03-20T17:39:28.412509Z", "loop": 1105, "env_steps": 678912000, "exact_value_avg": 0.4135197103023529, "regret_dist": 0.4500609040260315, "regret_other_env": 0.74014812707901, "regret_corner": 0.014930029399693012, "regret_row": 0.6208705902099609, "regret_any": 0.7403305768966675, "regret_bot": 0.8262932896614075, "value_dist": 0.4135197103023529, "value_other_env": 0.14206668734550476, "value_corner": 0.8206992745399475, "value_row": 0.23775605857372284, "value_any": 0.14192001521587372, "value_bot": 0.032333359122276306, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01105.png", "entropy": 0.34459906816482544} +{"ts": "2026-03-20T17:39:32.715162Z", "loop": 1110, "env_steps": 681984000, "exact_value_avg": 0.41989752650260925, "regret_dist": 0.4436831772327423, "regret_other_env": 0.736013650894165, "regret_corner": 0.005187409929931164, "regret_row": 0.5524788498878479, "regret_any": 0.7362023591995239, "regret_bot": 0.8290345668792725, "value_dist": 0.41989752650260925, "value_other_env": 0.1462012380361557, "value_corner": 0.830441951751709, "value_row": 0.30614781379699707, "value_any": 0.14604826271533966, "value_bot": 0.029591986909508705, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01110.png", "entropy": 0.3664880692958832} +{"ts": "2026-03-20T17:39:37.020378Z", "loop": 1115, "env_steps": 685056000, "exact_value_avg": 0.4242222011089325, "regret_dist": 0.4393584728240967, "regret_other_env": 0.7254912257194519, "regret_corner": 0.010159295052289963, "regret_row": 0.5771861672401428, "regret_any": 0.7256958484649658, "regret_bot": 0.8261246085166931, "value_dist": 0.4242222011089325, "value_other_env": 0.15672363340854645, "value_corner": 0.8254700303077698, "value_row": 0.28144049644470215, "value_any": 0.15655475854873657, "value_bot": 0.032502029091119766, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01115.png", "entropy": 0.35222938656806946} +{"ts": "2026-03-20T17:39:41.322529Z", "loop": 1120, "env_steps": 688128000, "exact_value_avg": 0.4249619245529175, "regret_dist": 0.4386187195777893, "regret_other_env": 0.7285692095756531, "regret_corner": 0.0036929703783243895, "regret_row": 0.5002720952033997, "regret_any": 0.728769063949585, "regret_bot": 0.8293749094009399, "value_dist": 0.4249619245529175, "value_other_env": 0.15364564955234528, "value_corner": 0.8319363594055176, "value_row": 0.35835450887680054, "value_any": 0.15348146855831146, "value_bot": 0.029251761734485626, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01120.png", "entropy": 0.3688468635082245} +{"ts": "2026-03-20T17:39:45.628021Z", "loop": 1125, "env_steps": 691200000, "exact_value_avg": 0.4338439106941223, "regret_dist": 0.42973679304122925, "regret_other_env": 0.7100431323051453, "regret_corner": 0.009277211502194405, "regret_row": 0.5521953701972961, "regret_any": 0.7102710008621216, "regret_bot": 0.8242180943489075, "value_dist": 0.4338439106941223, "value_other_env": 0.17217174172401428, "value_corner": 0.8263521194458008, "value_row": 0.30643123388290405, "value_any": 0.17197951674461365, "value_bot": 0.03440853953361511, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01125.png", "entropy": 0.33259207010269165} +{"ts": "2026-03-20T17:39:49.933067Z", "loop": 1130, "env_steps": 694272000, "exact_value_avg": 0.4380883574485779, "regret_dist": 0.4254923164844513, "regret_other_env": 0.7024217247962952, "regret_corner": 0.010098160244524479, "regret_row": 0.5460609197616577, "regret_any": 0.7026611566543579, "regret_bot": 0.8233156800270081, "value_dist": 0.4380883574485779, "value_other_env": 0.17979314923286438, "value_corner": 0.8255311846733093, "value_row": 0.31256571412086487, "value_any": 0.17958945035934448, "value_bot": 0.03531095013022423, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01130.png", "entropy": 0.32158729434013367} +{"ts": "2026-03-20T17:39:54.237261Z", "loop": 1135, "env_steps": 697344000, "exact_value_avg": 0.44063055515289307, "regret_dist": 0.4229501187801361, "regret_other_env": 0.7032308578491211, "regret_corner": 0.0025289373006671667, "regret_row": 0.4837121069431305, "regret_any": 0.7034690380096436, "regret_bot": 0.8261697888374329, "value_dist": 0.44063055515289307, "value_other_env": 0.17898400127887726, "value_corner": 0.8331003785133362, "value_row": 0.3749145269393921, "value_any": 0.17878152430057526, "value_bot": 0.0324569009244442, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01135.png", "entropy": 0.331586629152298} +{"ts": "2026-03-20T17:39:58.544192Z", "loop": 1140, "env_steps": 700416000, "exact_value_avg": 0.4473501741886139, "regret_dist": 0.41623055934906006, "regret_other_env": 0.6872207522392273, "regret_corner": 0.009745190851390362, "regret_row": 0.522951602935791, "regret_any": 0.6874831318855286, "regret_bot": 0.8227075338363647, "value_dist": 0.4473501741886139, "value_other_env": 0.19499416649341583, "value_corner": 0.8258841633796692, "value_row": 0.33567509055137634, "value_any": 0.19476743042469025, "value_bot": 0.03591908514499664, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01140.png", "entropy": 0.3124448359012604} +{"ts": "2026-03-20T17:40:02.853712Z", "loop": 1145, "env_steps": 703488000, "exact_value_avg": 0.4527384340763092, "regret_dist": 0.41084223985671997, "regret_other_env": 0.6819333434104919, "regret_corner": 0.004205578472465277, "regret_row": 0.4920513927936554, "regret_any": 0.6822038292884827, "regret_bot": 0.8237395882606506, "value_dist": 0.4527384340763092, "value_other_env": 0.2002815157175064, "value_corner": 0.8314237594604492, "value_row": 0.3665752112865448, "value_any": 0.20004677772521973, "value_bot": 0.034887056797742844, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01145.png", "entropy": 0.3134934604167938} +{"ts": "2026-03-20T17:40:07.163648Z", "loop": 1150, "env_steps": 706560000, "exact_value_avg": 0.455801784992218, "regret_dist": 0.40777888894081116, "regret_other_env": 0.678147554397583, "regret_corner": 0.0022258691024035215, "regret_row": 0.4792966842651367, "regret_any": 0.6784237027168274, "regret_bot": 0.824083149433136, "value_dist": 0.455801784992218, "value_other_env": 0.20406731963157654, "value_corner": 0.833403468132019, "value_row": 0.37932994961738586, "value_any": 0.20382685959339142, "value_bot": 0.03454355150461197, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01150.png", "entropy": 0.29825034737586975} +{"ts": "2026-03-20T17:40:11.468747Z", "loop": 1155, "env_steps": 709632000, "exact_value_avg": 0.45953965187072754, "regret_dist": 0.40404102206230164, "regret_other_env": 0.6712879538536072, "regret_corner": 0.0031705659348517656, "regret_row": 0.4866068363189697, "regret_any": 0.6715745329856873, "regret_bot": 0.8224862217903137, "value_dist": 0.45953965187072754, "value_other_env": 0.21092689037322998, "value_corner": 0.8324587941169739, "value_row": 0.37201979756355286, "value_any": 0.21067604422569275, "value_bot": 0.03614033758640289, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01155.png", "entropy": 0.27909407019615173} +{"ts": "2026-03-20T17:40:15.778026Z", "loop": 1160, "env_steps": 712704000, "exact_value_avg": 0.458331823348999, "regret_dist": 0.40524888038635254, "regret_other_env": 0.674820065498352, "regret_corner": 0.0008920828695409, "regret_row": 0.4471931457519531, "regret_any": 0.6751013398170471, "regret_bot": 0.8254200220108032, "value_dist": 0.458331823348999, "value_other_env": 0.2073947787284851, "value_corner": 0.8347373008728027, "value_row": 0.41143348813056946, "value_any": 0.20714935660362244, "value_bot": 0.03320658206939697, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01160.png", "entropy": 0.28738850355148315} +{"ts": "2026-03-20T17:40:20.084242Z", "loop": 1165, "env_steps": 715776000, "exact_value_avg": 0.46429377794265747, "regret_dist": 0.3992868661880493, "regret_other_env": 0.6646819114685059, "regret_corner": 0.001194281387142837, "regret_row": 0.47626063227653503, "regret_any": 0.664978563785553, "regret_bot": 0.8225212097167969, "value_dist": 0.46429377794265747, "value_other_env": 0.2175329327583313, "value_corner": 0.8344350457191467, "value_row": 0.38236600160598755, "value_any": 0.217272087931633, "value_bot": 0.03610541671514511, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01165.png", "entropy": 0.25414589047431946} +{"ts": "2026-03-20T17:40:24.391568Z", "loop": 1170, "env_steps": 718848000, "exact_value_avg": 0.4598495662212372, "regret_dist": 0.403731107711792, "regret_other_env": 0.6717234253883362, "regret_corner": 0.0017426054691895843, "regret_row": 0.5174492597579956, "regret_any": 0.672009289264679, "regret_bot": 0.8214527368545532, "value_dist": 0.4598495662212372, "value_other_env": 0.21049144864082336, "value_corner": 0.8338866829872131, "value_row": 0.3411773443222046, "value_any": 0.21024127304553986, "value_bot": 0.037173982709646225, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01170.png", "entropy": 0.2154918611049652} +{"ts": "2026-03-20T17:40:28.700230Z", "loop": 1175, "env_steps": 721920000, "exact_value_avg": 0.4644293189048767, "regret_dist": 0.39915135502815247, "regret_other_env": 0.6650390028953552, "regret_corner": 0.00031982464133761823, "regret_row": 0.4503116011619568, "regret_any": 0.6653349995613098, "regret_bot": 0.8260431885719299, "value_dist": 0.4644293189048767, "value_other_env": 0.2171759009361267, "value_corner": 0.8353094458580017, "value_row": 0.4083150625228882, "value_any": 0.21691559255123138, "value_bot": 0.03258338198065758, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01175.png", "entropy": 0.22925375401973724} +{"ts": "2026-03-20T17:40:33.005339Z", "loop": 1180, "env_steps": 724992000, "exact_value_avg": 0.46989843249320984, "regret_dist": 0.39368224143981934, "regret_other_env": 0.6559963822364807, "regret_corner": 0.0002109696506522596, "regret_row": 0.44056957960128784, "regret_any": 0.6563059687614441, "regret_bot": 0.823779821395874, "value_dist": 0.46989843249320984, "value_other_env": 0.22621849179267883, "value_corner": 0.8354183435440063, "value_row": 0.41805705428123474, "value_any": 0.22594456374645233, "value_bot": 0.03484680876135826, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01180.png", "entropy": 0.22587189078330994} +{"ts": "2026-03-20T17:40:37.307895Z", "loop": 1185, "env_steps": 728064000, "exact_value_avg": 0.472230464220047, "regret_dist": 0.39135023951530457, "regret_other_env": 0.6521105766296387, "regret_corner": 0.00020962805137969553, "regret_row": 0.43603813648223877, "regret_any": 0.65242600440979, "regret_bot": 0.8228790760040283, "value_dist": 0.472230464220047, "value_other_env": 0.23010432720184326, "value_corner": 0.8354196548461914, "value_row": 0.4225884974002838, "value_any": 0.22982454299926758, "value_bot": 0.035747479647397995, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01185.png", "entropy": 0.22786284983158112} +{"ts": "2026-03-20T17:40:41.612104Z", "loop": 1190, "env_steps": 731136000, "exact_value_avg": 0.4749985933303833, "regret_dist": 0.38858211040496826, "regret_other_env": 0.6473088264465332, "regret_corner": 0.0004919723141938448, "regret_row": 0.43899956345558167, "regret_any": 0.6476315855979919, "regret_bot": 0.8211395740509033, "value_dist": 0.4749985933303833, "value_other_env": 0.23490603268146515, "value_corner": 0.8351373672485352, "value_row": 0.41962704062461853, "value_any": 0.23461897671222687, "value_bot": 0.03748698905110359, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01190.png", "entropy": 0.22447742521762848} +{"ts": "2026-03-20T17:40:45.920588Z", "loop": 1195, "env_steps": 734208000, "exact_value_avg": 0.47051891684532166, "regret_dist": 0.3930617868900299, "regret_other_env": 0.6524908542633057, "regret_corner": 0.003918131813406944, "regret_row": 0.4658227860927582, "regret_any": 0.652805745601654, "regret_bot": 0.8198557496070862, "value_dist": 0.47051891684532166, "value_other_env": 0.22972404956817627, "value_corner": 0.8317111730575562, "value_row": 0.3928038477897644, "value_any": 0.22944483160972595, "value_bot": 0.03877091035246849, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01195.png", "entropy": 0.19660480320453644} +{"ts": "2026-03-20T17:40:50.227088Z", "loop": 1200, "env_steps": 737280000, "exact_value_avg": 0.477312833070755, "regret_dist": 0.38626784086227417, "regret_other_env": 0.6436120867729187, "regret_corner": 0.00025144865503534675, "regret_row": 0.43644097447395325, "regret_any": 0.6439405083656311, "regret_bot": 0.821232795715332, "value_dist": 0.477312833070755, "value_other_env": 0.23860278725624084, "value_corner": 0.8353778719902039, "value_row": 0.42218562960624695, "value_any": 0.23831012845039368, "value_bot": 0.037393759936094284, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01200.png", "entropy": 0.20767146348953247} +{"ts": "2026-03-20T17:40:54.529553Z", "loop": 1205, "env_steps": 740352000, "exact_value_avg": 0.4753311276435852, "regret_dist": 0.38824957609176636, "regret_other_env": 0.6470186710357666, "regret_corner": 9.585222142050043e-05, "regret_row": 0.4314790666103363, "regret_any": 0.6473418474197388, "regret_bot": 0.8259194493293762, "value_dist": 0.4753311276435852, "value_other_env": 0.23519624769687653, "value_corner": 0.8355334401130676, "value_row": 0.4271475374698639, "value_any": 0.23490877449512482, "value_bot": 0.032707177102565765, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01205.png", "entropy": 0.20245839655399323} +{"ts": "2026-03-20T17:40:58.831611Z", "loop": 1210, "env_steps": 743424000, "exact_value_avg": 0.4664882719516754, "regret_dist": 0.39709237217903137, "regret_other_env": 0.6604400873184204, "regret_corner": 0.002070714719593525, "regret_row": 0.4948175847530365, "regret_any": 0.660742998123169, "regret_bot": 0.8197076916694641, "value_dist": 0.4664882719516754, "value_other_env": 0.22177472710609436, "value_corner": 0.8335585594177246, "value_row": 0.3638090193271637, "value_any": 0.22150754928588867, "value_bot": 0.03891892731189728, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01210.png", "entropy": 0.1526651680469513} +{"ts": "2026-03-20T17:41:03.136173Z", "loop": 1215, "env_steps": 746496000, "exact_value_avg": 0.47406455874443054, "regret_dist": 0.389516144990921, "regret_other_env": 0.6489567160606384, "regret_corner": 0.000355271011358127, "regret_row": 0.4542672336101532, "regret_any": 0.6492770314216614, "regret_bot": 0.8200836777687073, "value_dist": 0.47406455874443054, "value_other_env": 0.2332582026720047, "value_corner": 0.8352740406990051, "value_row": 0.404359370470047, "value_any": 0.2329736202955246, "value_bot": 0.03854293003678322, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01215.png", "entropy": 0.16001924872398376} +{"ts": "2026-03-20T17:41:07.439830Z", "loop": 1220, "env_steps": 749568000, "exact_value_avg": 0.47024595737457275, "regret_dist": 0.3933347165584564, "regret_other_env": 0.6554321050643921, "regret_corner": 0.0001885836391011253, "regret_row": 0.4262666404247284, "regret_any": 0.6557425856590271, "regret_bot": 0.8338293433189392, "value_dist": 0.47024595737457275, "value_other_env": 0.22678272426128387, "value_corner": 0.8354407548904419, "value_row": 0.4323599934577942, "value_any": 0.2265080064535141, "value_bot": 0.024797288700938225, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01220.png", "entropy": 0.17395837604999542} +{"ts": "2026-03-20T17:41:11.743004Z", "loop": 1225, "env_steps": 752640000, "exact_value_avg": 0.4802982807159424, "regret_dist": 0.3832824230194092, "regret_other_env": 0.6387779712677002, "regret_corner": 3.9042039134074e-05, "regret_row": 0.4323806166648865, "regret_any": 0.63911372423172, "regret_bot": 0.8220391869544983, "value_dist": 0.4802982807159424, "value_other_env": 0.24343690276145935, "value_corner": 0.8355903029441833, "value_row": 0.4262460172176361, "value_any": 0.2431369125843048, "value_bot": 0.036587461829185486, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01225.png", "entropy": 0.1682131439447403} +{"ts": "2026-03-20T17:41:16.048248Z", "loop": 1230, "env_steps": 755712000, "exact_value_avg": 0.4771502614021301, "regret_dist": 0.38643044233322144, "regret_other_env": 0.6427419185638428, "regret_corner": 0.0019631560426205397, "regret_row": 0.4418371021747589, "regret_any": 0.6430715918540955, "regret_bot": 0.8196331262588501, "value_dist": 0.4771502614021301, "value_other_env": 0.23947298526763916, "value_corner": 0.8336661458015442, "value_row": 0.41678956151008606, "value_any": 0.23917901515960693, "value_bot": 0.0389934740960598, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01230.png", "entropy": 0.1565064936876297} +{"ts": "2026-03-20T17:41:20.353474Z", "loop": 1235, "env_steps": 758784000, "exact_value_avg": 0.48054713010787964, "regret_dist": 0.38303354382514954, "regret_other_env": 0.6379430294036865, "regret_corner": 0.0006693060277029872, "regret_row": 0.43375515937805176, "regret_any": 0.6382799744606018, "regret_bot": 0.8199101090431213, "value_dist": 0.48054713010787964, "value_other_env": 0.2442718744277954, "value_corner": 0.8349600434303284, "value_row": 0.4248714745044708, "value_any": 0.24397064745426178, "value_bot": 0.03871653974056244, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01235.png", "entropy": 0.16630150377750397} +{"ts": "2026-03-20T17:41:24.658405Z", "loop": 1240, "env_steps": 761856000, "exact_value_avg": 0.481023371219635, "regret_dist": 0.38255736231803894, "regret_other_env": 0.637153148651123, "regret_corner": 0.0006636068574152887, "regret_row": 0.4292801320552826, "regret_any": 0.6374913454055786, "regret_bot": 0.8199994564056396, "value_dist": 0.481023371219635, "value_other_env": 0.2450617253780365, "value_corner": 0.8349657654762268, "value_row": 0.4293465316295624, "value_any": 0.24475929141044617, "value_bot": 0.038627173751592636, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01240.png", "entropy": 0.17038245499134064} +{"ts": "2026-03-20T17:41:28.966056Z", "loop": 1245, "env_steps": 764928000, "exact_value_avg": 0.48113882541656494, "regret_dist": 0.3824418783187866, "regret_other_env": 0.6368702054023743, "regret_corner": 0.0007993693579919636, "regret_row": 0.4228583872318268, "regret_any": 0.6372088193893433, "regret_bot": 0.8201124668121338, "value_dist": 0.48113882541656494, "value_other_env": 0.24534465372562408, "value_corner": 0.8348299860954285, "value_row": 0.4357682466506958, "value_any": 0.2450418323278427, "value_bot": 0.03851418197154999, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01245.png", "entropy": 0.17442075908184052} +{"ts": "2026-03-20T17:41:33.275827Z", "loop": 1250, "env_steps": 768000000, "exact_value_avg": 0.4818500280380249, "regret_dist": 0.3817306458950043, "regret_other_env": 0.635988712310791, "regret_corner": 0.00034349365159869194, "regret_row": 0.42134979367256165, "regret_any": 0.6363286375999451, "regret_bot": 0.8203598260879517, "value_dist": 0.4818500280380249, "value_other_env": 0.24622610211372375, "value_corner": 0.8352858424186707, "value_row": 0.43727684020996094, "value_any": 0.24592195451259613, "value_bot": 0.038266751915216446, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01250.png", "entropy": 0.16812102496623993} +{"ts": "2026-03-20T17:41:37.585524Z", "loop": 1255, "env_steps": 771072000, "exact_value_avg": 0.4823548197746277, "regret_dist": 0.3812258839607239, "regret_other_env": 0.6353117823600769, "regret_corner": 9.69901739154011e-05, "regret_row": 0.41721051931381226, "regret_any": 0.6356526017189026, "regret_bot": 0.8213295340538025, "value_dist": 0.4823548197746277, "value_other_env": 0.24690312147140503, "value_corner": 0.8355323672294617, "value_row": 0.4414161741733551, "value_any": 0.24659794569015503, "value_bot": 0.03729710727930069, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01255.png", "entropy": 0.16527551412582397} +{"ts": "2026-03-20T17:41:41.895114Z", "loop": 1260, "env_steps": 774144000, "exact_value_avg": 0.47788113355636597, "regret_dist": 0.3856995105743408, "regret_other_env": 0.6428017616271973, "regret_corner": 4.6124561777105555e-05, "regret_row": 0.41281330585479736, "regret_any": 0.6431311368942261, "regret_bot": 0.8292173147201538, "value_dist": 0.47788113355636597, "value_other_env": 0.23941311240196228, "value_corner": 0.8355831503868103, "value_row": 0.4458133578300476, "value_any": 0.23911945521831512, "value_bot": 0.029409274458885193, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01260.png", "entropy": 0.16214415431022644} +{"ts": "2026-03-20T17:41:46.201665Z", "loop": 1265, "env_steps": 777216000, "exact_value_avg": 0.48240548372268677, "regret_dist": 0.3811752200126648, "regret_other_env": 0.6352702975273132, "regret_corner": 3.257145726820454e-05, "regret_row": 0.42637544870376587, "regret_any": 0.635611355304718, "regret_bot": 0.8218758702278137, "value_dist": 0.48240548372268677, "value_other_env": 0.2469445914030075, "value_corner": 0.8355967402458191, "value_row": 0.4322511851787567, "value_any": 0.24663929641246796, "value_bot": 0.03675072267651558, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01265.png", "entropy": 0.14679387211799622} +{"ts": "2026-03-20T17:41:50.509570Z", "loop": 1270, "env_steps": 780288000, "exact_value_avg": 0.47012072801589966, "regret_dist": 0.3934599459171295, "regret_other_env": 0.6513955593109131, "regret_corner": 0.006556525826454163, "regret_row": 0.4617256224155426, "regret_any": 0.6517121195793152, "regret_bot": 0.8194898962974548, "value_dist": 0.47012072801589966, "value_other_env": 0.23081934452056885, "value_corner": 0.8290728330612183, "value_row": 0.3969009816646576, "value_any": 0.2305385023355484, "value_bot": 0.03913678973913193, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01270.png", "entropy": 0.12111802399158478} +{"ts": "2026-03-20T17:41:54.818001Z", "loop": 1275, "env_steps": 783360000, "exact_value_avg": 0.4780975878238678, "regret_dist": 0.38548311591148376, "regret_other_env": 0.6411603689193726, "regret_corner": 0.001967179821804166, "regret_row": 0.43968963623046875, "regret_any": 0.641492486000061, "regret_bot": 0.8195973634719849, "value_dist": 0.4780975878238678, "value_other_env": 0.24105453491210938, "value_corner": 0.8336621522903442, "value_row": 0.41893696784973145, "value_any": 0.24075816571712494, "value_bot": 0.03902924805879593, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01275.png", "entropy": 0.13378708064556122} +{"ts": "2026-03-20T17:41:59.127219Z", "loop": 1280, "env_steps": 786432000, "exact_value_avg": 0.48221448063850403, "regret_dist": 0.38136622309684753, "regret_other_env": 0.6355851292610168, "regret_corner": 3.7842495657969266e-05, "regret_row": 0.41255536675453186, "regret_any": 0.6359255313873291, "regret_bot": 0.8314768075942993, "value_dist": 0.48221448063850403, "value_other_env": 0.24662980437278748, "value_corner": 0.8355914950370789, "value_row": 0.4460712671279907, "value_any": 0.24632510542869568, "value_bot": 0.027149831876158714, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01280.png", "entropy": 0.15251801908016205} +{"ts": "2026-03-20T17:42:03.433219Z", "loop": 1285, "env_steps": 789504000, "exact_value_avg": 0.4827389121055603, "regret_dist": 0.38084176182746887, "regret_other_env": 0.6347112059593201, "regret_corner": 3.753602868528105e-05, "regret_row": 0.41243135929107666, "regret_any": 0.6350529789924622, "regret_bot": 0.8309577703475952, "value_dist": 0.4827389121055603, "value_other_env": 0.24750366806983948, "value_corner": 0.8355917930603027, "value_row": 0.44619524478912354, "value_any": 0.24719764292240143, "value_bot": 0.027668900787830353, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01285.png", "entropy": 0.15137037634849548} +{"ts": "2026-03-20T17:42:07.740735Z", "loop": 1290, "env_steps": 792576000, "exact_value_avg": 0.48261046409606934, "regret_dist": 0.3809702694416046, "regret_other_env": 0.6348912715911865, "regret_corner": 8.870065357768908e-05, "regret_row": 0.42443475127220154, "regret_any": 0.6352328062057495, "regret_bot": 0.8204106092453003, "value_dist": 0.48261046409606934, "value_other_env": 0.24732361733913422, "value_corner": 0.8355406522750854, "value_row": 0.43419188261032104, "value_any": 0.2470177561044693, "value_bot": 0.03821602836251259, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01290.png", "entropy": 0.13742707669734955} +{"ts": "2026-03-20T17:42:12.048360Z", "loop": 1295, "env_steps": 795648000, "exact_value_avg": 0.4683479964733124, "regret_dist": 0.3952326774597168, "regret_other_env": 0.6542323231697083, "regret_corner": 0.006733154412358999, "regret_row": 0.47114747762680054, "regret_any": 0.6545446515083313, "regret_bot": 0.8194923996925354, "value_dist": 0.4683479964733124, "value_other_env": 0.2279825359582901, "value_corner": 0.828896164894104, "value_row": 0.3874792158603668, "value_any": 0.2277059704065323, "value_bot": 0.039134226739406586, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01295.png", "entropy": 0.10891988128423691} +{"ts": "2026-03-20T17:42:16.357032Z", "loop": 1300, "env_steps": 798720000, "exact_value_avg": 0.4829293489456177, "regret_dist": 0.3806513845920563, "regret_other_env": 0.634370744228363, "regret_corner": 7.227013702504337e-05, "regret_row": 0.42257946729660034, "regret_any": 0.6347131729125977, "regret_bot": 0.8201574683189392, "value_dist": 0.4829293489456177, "value_other_env": 0.2478441298007965, "value_corner": 0.8355571031570435, "value_row": 0.43604716658592224, "value_any": 0.24753746390342712, "value_bot": 0.03846907243132591, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01300.png", "entropy": 0.1290857493877411} +{"ts": "2026-03-20T17:42:20.664602Z", "loop": 1305, "env_steps": 801792000, "exact_value_avg": 0.48441246151924133, "regret_dist": 0.37916824221611023, "regret_other_env": 0.6319336295127869, "regret_corner": 2.0123025024076924e-05, "regret_row": 0.4123792052268982, "regret_any": 0.632279634475708, "regret_bot": 0.8272616267204285, "value_dist": 0.48441246151924133, "value_other_env": 0.25028127431869507, "value_corner": 0.8356091976165771, "value_row": 0.4462474286556244, "value_any": 0.24997098743915558, "value_bot": 0.03136499226093292, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01305.png", "entropy": 0.13158132135868073} +{"ts": "2026-03-20T17:42:24.974655Z", "loop": 1310, "env_steps": 804864000, "exact_value_avg": 0.4833510220050812, "regret_dist": 0.3802296221256256, "regret_other_env": 0.6336768269538879, "regret_corner": 5.881687320652418e-05, "regret_row": 0.42007362842559814, "regret_any": 0.6340203285217285, "regret_bot": 0.8202345967292786, "value_dist": 0.4833510220050812, "value_other_env": 0.24853800237178802, "value_corner": 0.8355705142021179, "value_row": 0.4385530352592468, "value_any": 0.24823029339313507, "value_bot": 0.0383920781314373, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01310.png", "entropy": 0.12315718084573746} +{"ts": "2026-03-20T17:42:29.283435Z", "loop": 1315, "env_steps": 807936000, "exact_value_avg": 0.48430532217025757, "regret_dist": 0.3792753219604492, "regret_other_env": 0.6321032047271729, "regret_corner": 3.3434233046136796e-05, "regret_row": 0.4150465726852417, "regret_any": 0.6324490308761597, "regret_bot": 0.8214824199676514, "value_dist": 0.48430532217025757, "value_other_env": 0.2501116394996643, "value_corner": 0.8355958461761475, "value_row": 0.4435800611972809, "value_any": 0.24980154633522034, "value_bot": 0.037144262343645096, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01315.png", "entropy": 0.12476753443479538} +{"ts": "2026-03-20T17:42:33.589248Z", "loop": 1320, "env_steps": 811008000, "exact_value_avg": 0.48476165533065796, "regret_dist": 0.3788190484046936, "regret_other_env": 0.6313475966453552, "regret_corner": 2.6133160645258613e-05, "regret_row": 0.41211017966270447, "regret_any": 0.631694495677948, "regret_bot": 0.8294324278831482, "value_dist": 0.48476165533065796, "value_other_env": 0.2508672773838043, "value_corner": 0.8356032371520996, "value_row": 0.4465164542198181, "value_any": 0.2505561113357544, "value_bot": 0.029194246977567673, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01320.png", "entropy": 0.13147704303264618} +{"ts": "2026-03-20T17:42:37.893863Z", "loop": 1325, "env_steps": 814080000, "exact_value_avg": 0.48054981231689453, "regret_dist": 0.3830309212207794, "regret_other_env": 0.6383404731750488, "regret_corner": 6.6543128923513e-05, "regret_row": 0.4094827175140381, "regret_any": 0.6386762261390686, "regret_bot": 0.8367624878883362, "value_dist": 0.48054981231689453, "value_other_env": 0.24387440085411072, "value_corner": 0.8355628252029419, "value_row": 0.4491438865661621, "value_any": 0.2435743808746338, "value_bot": 0.021864132955670357, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01325.png", "entropy": 0.13976846635341644} +{"ts": "2026-03-20T17:42:42.199702Z", "loop": 1330, "env_steps": 817152000, "exact_value_avg": 0.4804922938346863, "regret_dist": 0.3830883800983429, "regret_other_env": 0.6384317874908447, "regret_corner": 7.32585831428878e-05, "regret_row": 0.40851208567619324, "regret_any": 0.638767421245575, "regret_bot": 0.8368039131164551, "value_dist": 0.4804922938346863, "value_other_env": 0.24378305673599243, "value_corner": 0.8355560898780823, "value_row": 0.45011457800865173, "value_any": 0.24348317086696625, "value_bot": 0.021822746843099594, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01330.png", "entropy": 0.13751810789108276} +{"ts": "2026-03-20T17:42:46.512312Z", "loop": 1335, "env_steps": 820224000, "exact_value_avg": 0.48481449484825134, "regret_dist": 0.3787662088871002, "regret_other_env": 0.631256639957428, "regret_corner": 3.052652027690783e-05, "regret_row": 0.41192445158958435, "regret_any": 0.6316036581993103, "regret_bot": 0.8297411799430847, "value_dist": 0.48481449484825134, "value_other_env": 0.25095823407173157, "value_corner": 0.8355988264083862, "value_row": 0.44670218229293823, "value_any": 0.2506469488143921, "value_bot": 0.028885377570986748, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01335.png", "entropy": 0.1296742856502533} +{"ts": "2026-03-20T17:42:50.824266Z", "loop": 1340, "env_steps": 823296000, "exact_value_avg": 0.4846741259098053, "regret_dist": 0.37890657782554626, "regret_other_env": 0.6314916610717773, "regret_corner": 2.892414886446204e-05, "regret_row": 0.41413646936416626, "regret_any": 0.6318383812904358, "regret_bot": 0.8218551874160767, "value_dist": 0.4846741259098053, "value_other_env": 0.2507232427597046, "value_corner": 0.8356003761291504, "value_row": 0.4444901645183563, "value_any": 0.2504122257232666, "value_bot": 0.03677142411470413, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01340.png", "entropy": 0.12271571904420853} +{"ts": "2026-03-20T17:42:55.127063Z", "loop": 1345, "env_steps": 826368000, "exact_value_avg": 0.4829769730567932, "regret_dist": 0.38060373067855835, "regret_other_env": 0.634305477142334, "regret_corner": 5.102455907035619e-05, "regret_row": 0.4201372563838959, "regret_any": 0.6346479654312134, "regret_bot": 0.8200095295906067, "value_dist": 0.4829769730567932, "value_other_env": 0.24790941178798676, "value_corner": 0.8355782628059387, "value_row": 0.4384894073009491, "value_any": 0.2476026564836502, "value_bot": 0.03861715644598007, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01345.png", "entropy": 0.11846012622117996} +{"ts": "2026-03-20T17:42:59.433507Z", "loop": 1350, "env_steps": 829440000, "exact_value_avg": 0.4825820326805115, "regret_dist": 0.3809986412525177, "regret_other_env": 0.6349459886550903, "regret_corner": 7.758935680612922e-05, "regret_row": 0.4197191596031189, "regret_any": 0.6352875828742981, "regret_bot": 0.8198453783988953, "value_dist": 0.4825820326805115, "value_other_env": 0.24726887047290802, "value_corner": 0.8355517387390137, "value_row": 0.4389074444770813, "value_any": 0.24696308374404907, "value_bot": 0.038781244307756424, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01350.png", "entropy": 0.12067443132400513} +{"ts": "2026-03-20T17:43:03.737305Z", "loop": 1355, "env_steps": 832512000, "exact_value_avg": 0.4849584102630615, "regret_dist": 0.37862229347229004, "regret_other_env": 0.6309977769851685, "regret_corner": 5.898426388739608e-05, "regret_row": 0.4134799838066101, "regret_any": 0.631345272064209, "regret_bot": 0.8201150298118591, "value_dist": 0.4849584102630615, "value_other_env": 0.2512170970439911, "value_corner": 0.8355703353881836, "value_row": 0.4451466202735901, "value_any": 0.2509053349494934, "value_bot": 0.03851158916950226, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01355.png", "entropy": 0.13135533034801483} +{"ts": "2026-03-20T17:43:08.040658Z", "loop": 1360, "env_steps": 835584000, "exact_value_avg": 0.48571667075157166, "regret_dist": 0.3778640031814575, "regret_other_env": 0.629740297794342, "regret_corner": 4.952351446263492e-05, "regret_row": 0.4026922881603241, "regret_any": 0.6300892233848572, "regret_bot": 0.8230196833610535, "value_dist": 0.48571667075157166, "value_other_env": 0.2524745464324951, "value_corner": 0.8355798721313477, "value_row": 0.4559343159198761, "value_any": 0.25216132402420044, "value_bot": 0.03560705482959747, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01360.png", "entropy": 0.14708416163921356} +{"ts": "2026-03-20T17:43:12.345924Z", "loop": 1365, "env_steps": 838656000, "exact_value_avg": 0.4836007356643677, "regret_dist": 0.3799799382686615, "regret_other_env": 0.6332492232322693, "regret_corner": 7.602424011565745e-05, "regret_row": 0.40078771114349365, "regret_any": 0.6335922479629517, "regret_bot": 0.8290553092956543, "value_dist": 0.4836007356643677, "value_other_env": 0.24896563589572906, "value_corner": 0.8355532884597778, "value_row": 0.45783892273902893, "value_any": 0.24865837395191193, "value_bot": 0.029571371152997017, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01365.png", "entropy": 0.14789599180221558} +{"ts": "2026-03-20T17:43:16.652999Z", "loop": 1370, "env_steps": 841728000, "exact_value_avg": 0.48613041639328003, "regret_dist": 0.37745025753974915, "regret_other_env": 0.6290543675422668, "regret_corner": 4.4006112148053944e-05, "regret_row": 0.40850356221199036, "regret_any": 0.6294047236442566, "regret_bot": 0.8236991167068481, "value_dist": 0.48613041639328003, "value_other_env": 0.2531604766845703, "value_corner": 0.8355852961540222, "value_row": 0.4501230716705322, "value_any": 0.2528458535671234, "value_bot": 0.034927528351545334, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01370.png", "entropy": 0.1366448849439621} +{"ts": "2026-03-20T17:43:20.956586Z", "loop": 1375, "env_steps": 844800000, "exact_value_avg": 0.4855187237262726, "regret_dist": 0.378061980009079, "regret_other_env": 0.6300740242004395, "regret_corner": 4.389087553136051e-05, "regret_row": 0.4127415418624878, "regret_any": 0.6304228901863098, "regret_bot": 0.8203044533729553, "value_dist": 0.4855187237262726, "value_other_env": 0.2521408498287201, "value_corner": 0.8355854749679565, "value_row": 0.4458850920200348, "value_any": 0.2518276870250702, "value_bot": 0.03832218050956726, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01375.png", "entropy": 0.12637752294540405} +{"ts": "2026-03-20T17:43:25.259473Z", "loop": 1380, "env_steps": 847872000, "exact_value_avg": 0.48508891463279724, "regret_dist": 0.3784918189048767, "regret_other_env": 0.6307784914970398, "regret_corner": 6.177475734148175e-05, "regret_row": 0.4136502742767334, "regret_any": 0.631126344203949, "regret_bot": 0.8198901414871216, "value_dist": 0.48508891463279724, "value_other_env": 0.25143641233444214, "value_corner": 0.8355675935745239, "value_row": 0.4449763298034668, "value_any": 0.2511242926120758, "value_bot": 0.03873652592301369, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01380.png", "entropy": 0.1248796358704567} +{"ts": "2026-03-20T17:43:29.568640Z", "loop": 1385, "env_steps": 850944000, "exact_value_avg": 0.4851442277431488, "regret_dist": 0.37843647599220276, "regret_other_env": 0.630673348903656, "regret_corner": 8.111397619359195e-05, "regret_row": 0.413980096578598, "regret_any": 0.6310212016105652, "regret_bot": 0.8197624087333679, "value_dist": 0.4851442277431488, "value_other_env": 0.2515415847301483, "value_corner": 0.8355481624603271, "value_row": 0.44464656710624695, "value_any": 0.25122934579849243, "value_bot": 0.038864221423864365, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01385.png", "entropy": 0.1255190372467041} +{"ts": "2026-03-20T17:43:33.876032Z", "loop": 1390, "env_steps": 854016000, "exact_value_avg": 0.48614978790283203, "regret_dist": 0.37743085622787476, "regret_other_env": 0.6290245652198792, "regret_corner": 4.026194801554084e-05, "regret_row": 0.40183258056640625, "regret_any": 0.6293749213218689, "regret_bot": 0.8241985440254211, "value_dist": 0.48614978790283203, "value_other_env": 0.2531902492046356, "value_corner": 0.8355890512466431, "value_row": 0.4567940831184387, "value_any": 0.2528756856918335, "value_bot": 0.034428056329488754, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01390.png", "entropy": 0.13235116004943848} +{"ts": "2026-03-20T17:43:38.182654Z", "loop": 1395, "env_steps": 857088000, "exact_value_avg": 0.4848076403141022, "regret_dist": 0.3787730932235718, "regret_other_env": 0.6312413215637207, "regret_corner": 7.071942673064768e-05, "regret_row": 0.40049558877944946, "regret_any": 0.6315880417823792, "regret_bot": 0.8305374383926392, "value_dist": 0.4848076403141022, "value_other_env": 0.250973641872406, "value_corner": 0.8355585932731628, "value_row": 0.4581310749053955, "value_any": 0.25066253542900085, "value_bot": 0.028089236468076706, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01395.png", "entropy": 0.13113592565059662} +{"ts": "2026-03-20T17:43:42.487550Z", "loop": 1400, "env_steps": 860160000, "exact_value_avg": 0.48124954104423523, "regret_dist": 0.38233113288879395, "regret_other_env": 0.637068510055542, "regret_corner": 0.0002249861863674596, "regret_row": 0.40121912956237793, "regret_any": 0.637406587600708, "regret_bot": 0.8363500833511353, "value_dist": 0.48124954104423523, "value_other_env": 0.24514633417129517, "value_corner": 0.8354043364524841, "value_row": 0.45740753412246704, "value_any": 0.244843989610672, "value_bot": 0.02227647230029106, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01400.png", "entropy": 0.12786516547203064} +{"ts": "2026-03-20T17:43:46.789951Z", "loop": 1405, "env_steps": 863232000, "exact_value_avg": 0.4859430193901062, "regret_dist": 0.377637654542923, "regret_other_env": 0.6293666958808899, "regret_corner": 4.400114266900346e-05, "regret_row": 0.4097976088523865, "regret_any": 0.6297166347503662, "regret_bot": 0.8270153403282166, "value_dist": 0.4859430193901062, "value_other_env": 0.25284814834594727, "value_corner": 0.8355852961540222, "value_row": 0.4488290250301361, "value_any": 0.2525339126586914, "value_bot": 0.031611327081918716, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01405.png", "entropy": 0.12076824903488159} +{"ts": "2026-03-20T17:43:51.092995Z", "loop": 1410, "env_steps": 866304000, "exact_value_avg": 0.4858953356742859, "regret_dist": 0.37768539786338806, "regret_other_env": 0.6294521689414978, "regret_corner": 3.5133463825332e-05, "regret_row": 0.4122234880924225, "regret_any": 0.6298019886016846, "regret_bot": 0.8231711387634277, "value_dist": 0.4858953356742859, "value_other_env": 0.25276270508766174, "value_corner": 0.8355942368507385, "value_row": 0.4464031755924225, "value_any": 0.25244858860969543, "value_bot": 0.035455528646707535, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01410.png", "entropy": 0.11674196273088455} +{"ts": "2026-03-20T17:43:55.401472Z", "loop": 1415, "env_steps": 869376000, "exact_value_avg": 0.48484307527542114, "regret_dist": 0.37873759865760803, "regret_other_env": 0.6312100291252136, "regret_corner": 2.889782263082452e-05, "regret_row": 0.4147150218486786, "regret_any": 0.6315572261810303, "regret_bot": 0.8203361630439758, "value_dist": 0.48484307527542114, "value_other_env": 0.25100481510162354, "value_corner": 0.8356004357337952, "value_row": 0.4439116418361664, "value_any": 0.2506933808326721, "value_bot": 0.03829052299261093, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01415.png", "entropy": 0.11341703683137894} +{"ts": "2026-03-20T17:43:59.706745Z", "loop": 1420, "env_steps": 872448000, "exact_value_avg": 0.48576539754867554, "regret_dist": 0.37781527638435364, "regret_other_env": 0.6296730637550354, "regret_corner": 2.8498472602223046e-05, "regret_row": 0.41287726163864136, "regret_any": 0.6300225853919983, "regret_bot": 0.8209607601165771, "value_dist": 0.48576539754867554, "value_other_env": 0.25254181027412415, "value_corner": 0.8356007933616638, "value_row": 0.44574934244155884, "value_any": 0.2522280216217041, "value_bot": 0.03766591101884842, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01420.png", "entropy": 0.11370303481817245} +{"ts": "2026-03-20T17:44:04.015775Z", "loop": 1425, "env_steps": 875520000, "exact_value_avg": 0.48599913716316223, "regret_dist": 0.37758156657218933, "regret_other_env": 0.6292741298675537, "regret_corner": 4.2665007640607655e-05, "regret_row": 0.411484032869339, "regret_any": 0.6296242475509644, "regret_bot": 0.8257614970207214, "value_dist": 0.48599913716316223, "value_other_env": 0.25294074416160583, "value_corner": 0.835586667060852, "value_row": 0.4471426010131836, "value_any": 0.25262632966041565, "value_bot": 0.03286511451005936, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01425.png", "entropy": 0.11497531086206436} +{"ts": "2026-03-20T17:44:08.325205Z", "loop": 1430, "env_steps": 878592000, "exact_value_avg": 0.484085351228714, "regret_dist": 0.37949538230895996, "regret_other_env": 0.6324091553688049, "regret_corner": 0.00012462686572689563, "regret_row": 0.40297114849090576, "regret_any": 0.632754385471344, "regret_bot": 0.8343966007232666, "value_dist": 0.484085351228714, "value_other_env": 0.2498057335615158, "value_corner": 0.8355047106742859, "value_row": 0.45565545558929443, "value_any": 0.24949616193771362, "value_bot": 0.02423008158802986, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01430.png", "entropy": 0.11693457514047623} +{"ts": "2026-03-20T17:44:12.634678Z", "loop": 1435, "env_steps": 881664000, "exact_value_avg": 0.48475325107574463, "regret_dist": 0.37882739305496216, "regret_other_env": 0.631305456161499, "regret_corner": 0.00011026512220269069, "regret_row": 0.4006364643573761, "regret_any": 0.6316524147987366, "regret_bot": 0.8331515192985535, "value_dist": 0.48475325107574463, "value_other_env": 0.25090938806533813, "value_corner": 0.8355190753936768, "value_row": 0.4579901695251465, "value_any": 0.2505981922149658, "value_bot": 0.025475095957517624, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01435.png", "entropy": 0.11632569879293442} +{"ts": "2026-03-20T17:44:16.940567Z", "loop": 1440, "env_steps": 884736000, "exact_value_avg": 0.48674076795578003, "regret_dist": 0.37683987617492676, "regret_other_env": 0.6280500292778015, "regret_corner": 2.458492963341996e-05, "regret_row": 0.41042959690093994, "regret_any": 0.628402054309845, "regret_bot": 0.8207231760025024, "value_dist": 0.48674076795578003, "value_other_env": 0.25416475534439087, "value_corner": 0.8356047868728638, "value_row": 0.44819703698158264, "value_any": 0.2538485527038574, "value_bot": 0.037903450429439545, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01440.png", "entropy": 0.11364790797233582} +{"ts": "2026-03-20T17:44:21.244392Z", "loop": 1445, "env_steps": 887808000, "exact_value_avg": 0.485647052526474, "regret_dist": 0.3779336214065552, "regret_other_env": 0.629871666431427, "regret_corner": 2.6520094252191484e-05, "regret_row": 0.4131779074668884, "regret_any": 0.630220890045166, "regret_bot": 0.8195717334747314, "value_dist": 0.485647052526474, "value_other_env": 0.25234320759773254, "value_corner": 0.8356028199195862, "value_row": 0.44544875621795654, "value_any": 0.25202974677085876, "value_bot": 0.039054855704307556, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01445.png", "entropy": 0.10942946374416351} +{"ts": "2026-03-20T17:44:25.550382Z", "loop": 1450, "env_steps": 890880000, "exact_value_avg": 0.48152798414230347, "regret_dist": 0.3820526897907257, "regret_other_env": 0.6364494562149048, "regret_corner": 0.00045744184171780944, "regret_row": 0.4213069975376129, "regret_any": 0.6367887258529663, "regret_bot": 0.8194434642791748, "value_dist": 0.48152798414230347, "value_other_env": 0.24576537311077118, "value_corner": 0.8351718187332153, "value_row": 0.4373196065425873, "value_any": 0.24546188116073608, "value_bot": 0.03918316587805748, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01450.png", "entropy": 0.10355749726295471} +{"ts": "2026-03-20T17:44:29.860502Z", "loop": 1455, "env_steps": 893952000, "exact_value_avg": 0.48398953676223755, "regret_dist": 0.379591166973114, "regret_other_env": 0.6325006484985352, "regret_corner": 0.00022686869488097727, "regret_row": 0.41621971130371094, "regret_any": 0.6328458786010742, "regret_bot": 0.8194654583930969, "value_dist": 0.48398953676223755, "value_other_env": 0.2497142106294632, "value_corner": 0.8354024887084961, "value_row": 0.44240692257881165, "value_any": 0.24940474331378937, "value_bot": 0.03916122019290924, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01455.png", "entropy": 0.10981027781963348} +{"ts": "2026-03-20T17:44:34.163867Z", "loop": 1460, "env_steps": 897024000, "exact_value_avg": 0.4873815178871155, "regret_dist": 0.3761991560459137, "regret_other_env": 0.6269799470901489, "regret_corner": 2.7930242140428163e-05, "regret_row": 0.39965102076530457, "regret_any": 0.627333402633667, "regret_bot": 0.8197121024131775, "value_dist": 0.4873815178871155, "value_other_env": 0.2552349269390106, "value_corner": 0.8356013894081116, "value_row": 0.45897558331489563, "value_any": 0.2549172341823578, "value_bot": 0.0389145091176033, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01460.png", "entropy": 0.1250060796737671} +{"ts": "2026-03-20T17:44:38.465902Z", "loop": 1465, "env_steps": 900096000, "exact_value_avg": 0.4863452911376953, "regret_dist": 0.37723538279533386, "regret_other_env": 0.6287006735801697, "regret_corner": 3.737509541679174e-05, "regret_row": 0.3995492458343506, "regret_any": 0.629050612449646, "regret_bot": 0.8217055797576904, "value_dist": 0.4863452911376953, "value_other_env": 0.25351420044898987, "value_corner": 0.8355919122695923, "value_row": 0.459077388048172, "value_any": 0.253199964761734, "value_bot": 0.036921050399541855, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01465.png", "entropy": 0.12770627439022064} +{"ts": "2026-03-20T17:44:42.770834Z", "loop": 1470, "env_steps": 903168000, "exact_value_avg": 0.4823087453842163, "regret_dist": 0.38127195835113525, "regret_other_env": 0.6352797150611877, "regret_corner": 0.00026027412968687713, "regret_row": 0.40276265144348145, "regret_any": 0.6356179118156433, "regret_bot": 0.8349316716194153, "value_dist": 0.4823087453842163, "value_other_env": 0.2469351589679718, "value_corner": 0.8353690505027771, "value_row": 0.45586398243904114, "value_any": 0.2466326206922531, "value_bot": 0.023694979026913643, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01470.png", "entropy": 0.12758544087409973} +{"ts": "2026-03-20T17:44:47.076480Z", "loop": 1475, "env_steps": 906240000, "exact_value_avg": 0.48158442974090576, "regret_dist": 0.3819962441921234, "regret_other_env": 0.6361420154571533, "regret_corner": 0.0007775336853228509, "regret_row": 0.39952021837234497, "regret_any": 0.6364813446998596, "regret_bot": 0.8372883796691895, "value_dist": 0.48158442974090576, "value_other_env": 0.24607284367084503, "value_corner": 0.8348518013954163, "value_row": 0.4591063857078552, "value_any": 0.24576924741268158, "value_bot": 0.02133823372423649, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01475.png", "entropy": 0.12264694273471832} +{"ts": "2026-03-20T17:44:51.382018Z", "loop": 1480, "env_steps": 909312000, "exact_value_avg": 0.4856243133544922, "regret_dist": 0.3779563307762146, "regret_other_env": 0.6297908425331116, "regret_corner": 0.00020455521007534117, "regret_row": 0.40753185749053955, "regret_any": 0.6301401853561401, "regret_bot": 0.8323162198066711, "value_dist": 0.4856243133544922, "value_other_env": 0.252424031496048, "value_corner": 0.8354247212409973, "value_row": 0.45109474658966064, "value_any": 0.25211045145988464, "value_bot": 0.026310425251722336, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01480.png", "entropy": 0.1135023832321167} +{"ts": "2026-03-20T17:44:55.687566Z", "loop": 1485, "env_steps": 912384000, "exact_value_avg": 0.4856942892074585, "regret_dist": 0.37788641452789307, "regret_other_env": 0.6297886967658997, "regret_corner": 3.296236536698416e-05, "regret_row": 0.41321030259132385, "regret_any": 0.6301379799842834, "regret_bot": 0.8201701641082764, "value_dist": 0.4856942892074585, "value_other_env": 0.2524262070655823, "value_corner": 0.8355963826179504, "value_row": 0.44541633129119873, "value_any": 0.25211259722709656, "value_bot": 0.03845645487308502, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01485.png", "entropy": 0.10567624121904373} +{"ts": "2026-03-20T17:44:59.992108Z", "loop": 1490, "env_steps": 915456000, "exact_value_avg": 0.4835779666900635, "regret_dist": 0.3800027072429657, "regret_other_env": 0.6333158612251282, "regret_corner": 3.292362089268863e-05, "regret_row": 0.4171368181705475, "regret_any": 0.6336598992347717, "regret_bot": 0.819476306438446, "value_dist": 0.4835779666900635, "value_other_env": 0.2488989681005478, "value_corner": 0.8355963826179504, "value_row": 0.4414898455142975, "value_any": 0.24859073758125305, "value_bot": 0.039150387048721313, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01490.png", "entropy": 0.10025281459093094} +{"ts": "2026-03-20T17:45:04.300656Z", "loop": 1495, "env_steps": 918528000, "exact_value_avg": 0.4826962351799011, "regret_dist": 0.38088443875312805, "regret_other_env": 0.6347633004188538, "regret_corner": 6.605884118471295e-05, "regret_row": 0.41891273856163025, "regret_any": 0.6351050734519958, "regret_bot": 0.8194307088851929, "value_dist": 0.4826962351799011, "value_other_env": 0.2474515289068222, "value_corner": 0.8355632424354553, "value_row": 0.43971389532089233, "value_any": 0.24714547395706177, "value_bot": 0.03919589892029762, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01495.png", "entropy": 0.0980600118637085} +{"ts": "2026-03-20T17:45:08.607319Z", "loop": 1500, "env_steps": 921600000, "exact_value_avg": 0.48259758949279785, "regret_dist": 0.3809831142425537, "regret_other_env": 0.6348055005073547, "regret_corner": 0.00024949759244918823, "regret_row": 0.41770026087760925, "regret_any": 0.635147213935852, "regret_bot": 0.8194143176078796, "value_dist": 0.48259758949279785, "value_other_env": 0.247409388422966, "value_corner": 0.8353798389434814, "value_row": 0.44092631340026855, "value_any": 0.24710340797901154, "value_bot": 0.039212312549352646, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01500.png", "entropy": 0.0985734611749649} +{"ts": "2026-03-20T17:45:12.914440Z", "loop": 1505, "env_steps": 924672000, "exact_value_avg": 0.48490244150161743, "regret_dist": 0.37867823243141174, "regret_other_env": 0.6309816837310791, "regret_corner": 0.000223021226702258, "regret_row": 0.41269049048423767, "regret_any": 0.6313291192054749, "regret_bot": 0.8194206357002258, "value_dist": 0.48490244150161743, "value_other_env": 0.25123319029808044, "value_corner": 0.8354063034057617, "value_row": 0.4459361433982849, "value_any": 0.2509213984012604, "value_bot": 0.03920596092939377, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01505.png", "entropy": 0.10640587657690048} +{"ts": "2026-03-20T17:45:17.218935Z", "loop": 1510, "env_steps": 927744000, "exact_value_avg": 0.4869168996810913, "regret_dist": 0.37666380405426025, "regret_other_env": 0.6277157068252563, "regret_corner": 8.59201027196832e-05, "regret_row": 0.40226271748542786, "regret_any": 0.6280680298805237, "regret_bot": 0.819446325302124, "value_dist": 0.4869168996810913, "value_other_env": 0.2544991970062256, "value_corner": 0.8355433940887451, "value_row": 0.4563639163970947, "value_any": 0.25418251752853394, "value_bot": 0.03918036073446274, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01510.png", "entropy": 0.11627676337957382} +{"ts": "2026-03-20T17:45:21.523398Z", "loop": 1515, "env_steps": 930816000, "exact_value_avg": 0.4870277941226959, "regret_dist": 0.376552939414978, "regret_other_env": 0.627554178237915, "regret_corner": 5.105485615786165e-05, "regret_row": 0.40080565214157104, "regret_any": 0.6279066801071167, "regret_bot": 0.8194648027420044, "value_dist": 0.4870277941226959, "value_other_env": 0.2546607255935669, "value_corner": 0.8355783224105835, "value_row": 0.45782098174095154, "value_any": 0.2543438971042633, "value_bot": 0.0391618050634861, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01515.png", "entropy": 0.11771908402442932} +{"ts": "2026-03-20T17:45:25.833212Z", "loop": 1520, "env_steps": 933888000, "exact_value_avg": 0.4867006838321686, "regret_dist": 0.376880019903183, "regret_other_env": 0.628113329410553, "regret_corner": 2.9998025638633408e-05, "regret_row": 0.4000270366668701, "regret_any": 0.6284646391868591, "regret_bot": 0.8195077180862427, "value_dist": 0.4867006838321686, "value_other_env": 0.25410160422325134, "value_corner": 0.8355993032455444, "value_row": 0.45859959721565247, "value_any": 0.2537859082221985, "value_bot": 0.03911885991692543, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01520.png", "entropy": 0.11710501462221146} +{"ts": "2026-03-20T17:45:30.136599Z", "loop": 1525, "env_steps": 936960000, "exact_value_avg": 0.4866946041584015, "regret_dist": 0.3768860995769501, "regret_other_env": 0.6281335353851318, "regret_corner": 1.4935931176296435e-05, "regret_row": 0.399148553609848, "regret_any": 0.6284845471382141, "regret_bot": 0.819627046585083, "value_dist": 0.4866946041584015, "value_other_env": 0.2540813684463501, "value_corner": 0.8356144428253174, "value_row": 0.4594780504703522, "value_any": 0.2537660300731659, "value_bot": 0.03899961709976196, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01525.png", "entropy": 0.11197708547115326} +{"ts": "2026-03-20T17:45:34.444731Z", "loop": 1530, "env_steps": 940032000, "exact_value_avg": 0.4862818717956543, "regret_dist": 0.37729883193969727, "regret_other_env": 0.6288191080093384, "regret_corner": 1.840740515035577e-05, "regret_row": 0.4000849723815918, "regret_any": 0.6291686296463013, "regret_bot": 0.820823609828949, "value_dist": 0.4862818717956543, "value_other_env": 0.25339579582214355, "value_corner": 0.8356109261512756, "value_row": 0.4585416316986084, "value_any": 0.2530819773674011, "value_bot": 0.03780302032828331, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01530.png", "entropy": 0.10556227713823318} +{"ts": "2026-03-20T17:45:38.754856Z", "loop": 1535, "env_steps": 943104000, "exact_value_avg": 0.4877614378929138, "regret_dist": 0.37581920623779297, "regret_other_env": 0.6263508200645447, "regret_corner": 2.1736324924859218e-05, "regret_row": 0.39847642183303833, "regret_any": 0.6267052292823792, "regret_bot": 0.8214460611343384, "value_dist": 0.4877614378929138, "value_other_env": 0.2558640241622925, "value_corner": 0.8356075882911682, "value_row": 0.46015021204948425, "value_any": 0.2555452883243561, "value_bot": 0.037180572748184204, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01535.png", "entropy": 0.10168968886137009} +{"ts": "2026-03-20T17:45:43.062537Z", "loop": 1540, "env_steps": 946176000, "exact_value_avg": 0.48724499344825745, "regret_dist": 0.3763357102870941, "regret_other_env": 0.6271913051605225, "regret_corner": 5.2272778702899814e-05, "regret_row": 0.3989115357398987, "regret_any": 0.6275444626808167, "regret_bot": 0.8292944431304932, "value_dist": 0.48724499344825745, "value_other_env": 0.2550235688686371, "value_corner": 0.8355770707130432, "value_row": 0.4597151279449463, "value_any": 0.25470608472824097, "value_bot": 0.029332252219319344, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01540.png", "entropy": 0.09761272370815277} +{"ts": "2026-03-20T17:45:47.369131Z", "loop": 1545, "env_steps": 949248000, "exact_value_avg": 0.4872966408729553, "regret_dist": 0.37628409266471863, "regret_other_env": 0.6271165609359741, "regret_corner": 3.52789975295309e-05, "regret_row": 0.4032054841518402, "regret_any": 0.6274699568748474, "regret_bot": 0.8252927660942078, "value_dist": 0.4872966408729553, "value_other_env": 0.25509828329086304, "value_corner": 0.835594117641449, "value_row": 0.4554211497306824, "value_any": 0.254780650138855, "value_bot": 0.03333396092057228, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01545.png", "entropy": 0.09549123793840408} +{"ts": "2026-03-20T17:45:51.673111Z", "loop": 1550, "env_steps": 952320000, "exact_value_avg": 0.48735910654067993, "regret_dist": 0.37622153759002686, "regret_other_env": 0.6270222067832947, "regret_corner": 2.0523866623989306e-05, "regret_row": 0.40612441301345825, "regret_any": 0.6273757219314575, "regret_bot": 0.8209478855133057, "value_dist": 0.48735910654067993, "value_other_env": 0.25519266724586487, "value_corner": 0.8356087803840637, "value_row": 0.45250219106674194, "value_any": 0.2548748850822449, "value_bot": 0.03767869248986244, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01550.png", "entropy": 0.09519213438034058} +{"ts": "2026-03-20T17:45:55.976841Z", "loop": 1555, "env_steps": 955392000, "exact_value_avg": 0.4871150255203247, "regret_dist": 0.37646567821502686, "regret_other_env": 0.6274330615997314, "regret_corner": 1.4537573406414595e-05, "regret_row": 0.40911248326301575, "regret_any": 0.627785861492157, "regret_bot": 0.819611668586731, "value_dist": 0.4871150255203247, "value_other_env": 0.2547818422317505, "value_corner": 0.835614800453186, "value_row": 0.44951412081718445, "value_any": 0.254464715719223, "value_bot": 0.03901490569114685, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01555.png", "entropy": 0.09537303447723389} +{"ts": "2026-03-20T17:46:00.278832Z", "loop": 1560, "env_steps": 958464000, "exact_value_avg": 0.48761656880378723, "regret_dist": 0.37596404552459717, "regret_other_env": 0.6265981793403625, "regret_corner": 1.283635720028542e-05, "regret_row": 0.4033355712890625, "regret_any": 0.6269524097442627, "regret_bot": 0.819491446018219, "value_dist": 0.48761656880378723, "value_other_env": 0.25561660528182983, "value_corner": 0.8356164693832397, "value_row": 0.45529109239578247, "value_any": 0.2552981972694397, "value_bot": 0.03913510963320732, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01560.png", "entropy": 0.09727341681718826} +{"ts": "2026-03-20T17:46:04.582023Z", "loop": 1565, "env_steps": 961536000, "exact_value_avg": 0.4869493842124939, "regret_dist": 0.3766312897205353, "regret_other_env": 0.627670168876648, "regret_corner": 7.293174712685868e-05, "regret_row": 0.40748676657676697, "regret_any": 0.6280226707458496, "regret_bot": 0.8194020986557007, "value_dist": 0.4869493842124939, "value_other_env": 0.254544734954834, "value_corner": 0.8355563879013062, "value_row": 0.451139897108078, "value_any": 0.25422796607017517, "value_bot": 0.0392245277762413, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01565.png", "entropy": 0.09983212500810623} +{"ts": "2026-03-20T17:46:08.885801Z", "loop": 1570, "env_steps": 964608000, "exact_value_avg": 0.48680579662323, "regret_dist": 0.3767748773097992, "regret_other_env": 0.6276978254318237, "regret_corner": 0.0003903876058757305, "regret_row": 0.4030172526836395, "regret_any": 0.6280503869056702, "regret_bot": 0.8193965554237366, "value_dist": 0.48680579662323, "value_other_env": 0.2545170187950134, "value_corner": 0.8352389335632324, "value_row": 0.45560938119888306, "value_any": 0.254200279712677, "value_bot": 0.03923003375530243, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01570.png", "entropy": 0.10505583137273788} +{"ts": "2026-03-20T17:46:13.190810Z", "loop": 1575, "env_steps": 967680000, "exact_value_avg": 0.4858400225639343, "regret_dist": 0.37774068117141724, "regret_other_env": 0.6287879347801208, "regret_corner": 0.001169756636954844, "regret_row": 0.40277570486068726, "regret_any": 0.629138708114624, "regret_bot": 0.8193985223770142, "value_dist": 0.4858400225639343, "value_other_env": 0.2534269392490387, "value_corner": 0.8344595432281494, "value_row": 0.4558509588241577, "value_any": 0.253111869096756, "value_bot": 0.03922811895608902, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01575.png", "entropy": 0.1070893332362175} +{"ts": "2026-03-20T17:46:17.497229Z", "loop": 1580, "env_steps": 970752000, "exact_value_avg": 0.4869094491004944, "regret_dist": 0.3766712546348572, "regret_other_env": 0.6275469064712524, "regret_corner": 0.00035773369017988443, "regret_row": 0.40193572640419006, "regret_any": 0.6278995871543884, "regret_bot": 0.8194146752357483, "value_dist": 0.4869094491004944, "value_other_env": 0.2546679973602295, "value_corner": 0.8352715969085693, "value_row": 0.45669087767601013, "value_any": 0.25435104966163635, "value_bot": 0.039211854338645935, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01580.png", "entropy": 0.10817833989858627} +{"ts": "2026-03-20T17:46:21.800482Z", "loop": 1585, "env_steps": 973824000, "exact_value_avg": 0.48743754625320435, "regret_dist": 0.37614309787750244, "regret_other_env": 0.6268496513366699, "regret_corner": 8.324385271407664e-05, "regret_row": 0.401136577129364, "regret_any": 0.6272034049034119, "regret_bot": 0.8194421529769897, "value_dist": 0.48743754625320435, "value_other_env": 0.25536519289016724, "value_corner": 0.83554607629776, "value_row": 0.45749005675315857, "value_any": 0.2550472021102905, "value_bot": 0.039184436202049255, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01585.png", "entropy": 0.10814515501260757} +{"ts": "2026-03-20T17:46:26.107866Z", "loop": 1590, "env_steps": 976896000, "exact_value_avg": 0.4876447319984436, "regret_dist": 0.37593594193458557, "regret_other_env": 0.6265417337417603, "regret_corner": 2.721647615544498e-05, "regret_row": 0.39864495396614075, "regret_any": 0.6268958449363708, "regret_bot": 0.8195854425430298, "value_dist": 0.4876447319984436, "value_other_env": 0.2556731402873993, "value_corner": 0.8356021046638489, "value_row": 0.4599817395210266, "value_any": 0.2553548216819763, "value_bot": 0.03904115408658981, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01590.png", "entropy": 0.10896766930818558} +{"ts": "2026-03-20T17:46:30.415512Z", "loop": 1595, "env_steps": 979968000, "exact_value_avg": 0.4863768517971039, "regret_dist": 0.3772038519382477, "regret_other_env": 0.6286572217941284, "regret_corner": 2.3780266928952187e-05, "regret_row": 0.39971187710762024, "regret_any": 0.6290053129196167, "regret_bot": 0.8261733055114746, "value_dist": 0.4863768517971039, "value_other_env": 0.2535577118396759, "value_corner": 0.8356055617332458, "value_row": 0.45891475677490234, "value_any": 0.2532452344894409, "value_bot": 0.03245331719517708, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01595.png", "entropy": 0.10245528072118759} +{"ts": "2026-03-20T17:46:34.720569Z", "loop": 1600, "env_steps": 983040000, "exact_value_avg": 0.4857962727546692, "regret_dist": 0.37778440117836, "regret_other_env": 0.6296173930168152, "regret_corner": 3.488362199277617e-05, "regret_row": 0.4002339541912079, "regret_any": 0.629964292049408, "regret_bot": 0.8342099785804749, "value_dist": 0.4857962727546692, "value_other_env": 0.252597451210022, "value_corner": 0.8355944752693176, "value_row": 0.4583926796913147, "value_any": 0.25228628516197205, "value_bot": 0.024416619911789894, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01600.png", "entropy": 0.09857909381389618} +{"ts": "2026-03-20T17:46:39.025668Z", "loop": 1605, "env_steps": 986112000, "exact_value_avg": 0.48666784167289734, "regret_dist": 0.37691283226013184, "regret_other_env": 0.6281592845916748, "regret_corner": 4.316717604524456e-05, "regret_row": 0.39847317337989807, "regret_any": 0.6285104155540466, "regret_bot": 0.8346447944641113, "value_dist": 0.48666784167289734, "value_other_env": 0.25405558943748474, "value_corner": 0.8355861902236938, "value_row": 0.4601534605026245, "value_any": 0.2537401616573334, "value_bot": 0.023981763049960136, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01605.png", "entropy": 0.09680218249559402} +{"ts": "2026-03-20T17:46:43.331149Z", "loop": 1610, "env_steps": 989184000, "exact_value_avg": 0.4861677587032318, "regret_dist": 0.377412885427475, "regret_other_env": 0.6289612054824829, "regret_corner": 9.038746793521568e-05, "regret_row": 0.3983073830604553, "regret_any": 0.6293116211891174, "regret_bot": 0.8368750810623169, "value_dist": 0.4861677587032318, "value_other_env": 0.25325360894203186, "value_corner": 0.835538923740387, "value_row": 0.46031928062438965, "value_any": 0.25293898582458496, "value_bot": 0.021751495078206062, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01610.png", "entropy": 0.09778433293104172} +{"ts": "2026-03-20T17:46:47.634559Z", "loop": 1615, "env_steps": 992256000, "exact_value_avg": 0.4861995577812195, "regret_dist": 0.3773811161518097, "regret_other_env": 0.6289016008377075, "regret_corner": 0.00010038813343271613, "regret_row": 0.3983813524246216, "regret_any": 0.6292522549629211, "regret_bot": 0.8368064165115356, "value_dist": 0.4861995577812195, "value_other_env": 0.25331324338912964, "value_corner": 0.8355289697647095, "value_row": 0.460245281457901, "value_any": 0.2529984414577484, "value_bot": 0.021820276975631714, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01615.png", "entropy": 0.09701061248779297} +{"ts": "2026-03-20T17:46:51.937903Z", "loop": 1620, "env_steps": 995328000, "exact_value_avg": 0.48448318243026733, "regret_dist": 0.37909752130508423, "regret_other_env": 0.6316066384315491, "regret_corner": 0.00033377212821505964, "regret_row": 0.3988642692565918, "regret_any": 0.6319531798362732, "regret_bot": 0.8381173610687256, "value_dist": 0.48448318243026733, "value_other_env": 0.2506082057952881, "value_corner": 0.8352956175804138, "value_row": 0.4597623348236084, "value_any": 0.2502973973751068, "value_bot": 0.020509321242570877, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01620.png", "entropy": 0.09889223426580429} +{"ts": "2026-03-20T17:46:56.241159Z", "loop": 1625, "env_steps": 998400000, "exact_value_avg": 0.48654094338417053, "regret_dist": 0.37703973054885864, "regret_other_env": 0.6283341646194458, "regret_corner": 9.802530985325575e-05, "regret_row": 0.40116557478904724, "regret_any": 0.6286856532096863, "regret_bot": 0.8352958559989929, "value_dist": 0.48654094338417053, "value_other_env": 0.25388070940971375, "value_corner": 0.8355312943458557, "value_row": 0.45746105909347534, "value_any": 0.2535649240016937, "value_bot": 0.023330753669142723, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01625.png", "entropy": 0.09557796269655228} +{"ts": "2026-03-20T17:47:00.546935Z", "loop": 1630, "env_steps": 1001472000, "exact_value_avg": 0.4869561791419983, "regret_dist": 0.37662452459335327, "regret_other_env": 0.6276693940162659, "regret_corner": 5.718171814805828e-05, "regret_row": 0.40283045172691345, "regret_any": 0.6280218362808228, "regret_bot": 0.8305978178977966, "value_dist": 0.4869561791419983, "value_other_env": 0.25454550981521606, "value_corner": 0.8355721831321716, "value_row": 0.4557962119579315, "value_any": 0.25422874093055725, "value_bot": 0.02802879363298416, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01630.png", "entropy": 0.09460566192865372} +{"ts": "2026-03-20T17:47:04.851639Z", "loop": 1635, "env_steps": 1004544000, "exact_value_avg": 0.48742586374282837, "regret_dist": 0.3761548101902008, "regret_other_env": 0.6269000172615051, "regret_corner": 3.6985678889323026e-05, "regret_row": 0.40289318561553955, "regret_any": 0.6272537708282471, "regret_bot": 0.823218047618866, "value_dist": 0.48742586374282837, "value_other_env": 0.25531482696533203, "value_corner": 0.8355923295021057, "value_row": 0.45573341846466064, "value_any": 0.2549968659877777, "value_bot": 0.035408638417720795, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01635.png", "entropy": 0.09501529484987259} +{"ts": "2026-03-20T17:47:09.155889Z", "loop": 1640, "env_steps": 1007616000, "exact_value_avg": 0.48712077736854553, "regret_dist": 0.37645992636680603, "regret_other_env": 0.6274101734161377, "regret_corner": 3.449519499554299e-05, "regret_row": 0.40627458691596985, "regret_any": 0.627763032913208, "regret_bot": 0.8196043968200684, "value_dist": 0.48712077736854553, "value_other_env": 0.25480473041534424, "value_corner": 0.8355948328971863, "value_row": 0.45235204696655273, "value_any": 0.254487544298172, "value_bot": 0.03902227804064751, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01640.png", "entropy": 0.09511139243841171} +{"ts": "2026-03-20T17:47:13.460015Z", "loop": 1645, "env_steps": 1010688000, "exact_value_avg": 0.4875657558441162, "regret_dist": 0.3760148882865906, "regret_other_env": 0.6266652941703796, "regret_corner": 3.924171323888004e-05, "regret_row": 0.40103578567504883, "regret_any": 0.6270193457603455, "regret_bot": 0.819475531578064, "value_dist": 0.4875657558441162, "value_other_env": 0.2555495500564575, "value_corner": 0.8355900645256042, "value_row": 0.45759081840515137, "value_any": 0.25523123145103455, "value_bot": 0.03915109112858772, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01645.png", "entropy": 0.09952046722173691} +{"ts": "2026-03-20T17:47:17.765940Z", "loop": 1650, "env_steps": 1013760000, "exact_value_avg": 0.48779600858688354, "regret_dist": 0.3757847249507904, "regret_other_env": 0.6262840032577515, "regret_corner": 3.576030576368794e-05, "regret_row": 0.3989555537700653, "regret_any": 0.6266385316848755, "regret_bot": 0.8195062279701233, "value_dist": 0.48779600858688354, "value_other_env": 0.25593093037605286, "value_corner": 0.835593581199646, "value_row": 0.45967110991477966, "value_any": 0.2556121051311493, "value_bot": 0.039120372384786606, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01650.png", "entropy": 0.10654334723949432} +{"ts": "2026-03-20T17:47:22.067795Z", "loop": 1655, "env_steps": 1016832000, "exact_value_avg": 0.48769232630729675, "regret_dist": 0.3758883774280548, "regret_other_env": 0.6264528036117554, "regret_corner": 4.171232649241574e-05, "regret_row": 0.3997148275375366, "regret_any": 0.6268069744110107, "regret_bot": 0.8194699883460999, "value_dist": 0.48769232630729675, "value_other_env": 0.25576213002204895, "value_corner": 0.8355876207351685, "value_row": 0.45891180634498596, "value_any": 0.25544363260269165, "value_bot": 0.03915661945939064, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01655.png", "entropy": 0.10860532522201538} +{"ts": "2026-03-20T17:47:26.370560Z", "loop": 1660, "env_steps": 1019904000, "exact_value_avg": 0.48685285449028015, "regret_dist": 0.376727819442749, "regret_other_env": 0.6277323365211487, "regret_corner": 0.00022100757632870227, "regret_row": 0.4017121195793152, "regret_any": 0.6280847191810608, "regret_bot": 0.8194212913513184, "value_dist": 0.48685285449028015, "value_other_env": 0.2544825077056885, "value_corner": 0.8354083299636841, "value_row": 0.456914484500885, "value_any": 0.2541658580303192, "value_bot": 0.03920537605881691, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01660.png", "entropy": 0.10751650482416153} +{"ts": "2026-03-20T17:47:30.675560Z", "loop": 1665, "env_steps": 1022976000, "exact_value_avg": 0.48473143577575684, "regret_dist": 0.3788492679595947, "regret_other_env": 0.6306888461112976, "regret_corner": 0.0010898655746132135, "regret_row": 0.4025030732154846, "regret_any": 0.6310365796089172, "regret_bot": 0.8194204568862915, "value_dist": 0.48473143577575684, "value_other_env": 0.2515260577201843, "value_corner": 0.8345394730567932, "value_row": 0.45612356066703796, "value_any": 0.25121399760246277, "value_bot": 0.039206162095069885, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01665.png", "entropy": 0.11245772987604141} +{"ts": "2026-03-20T17:47:34.981710Z", "loop": 1670, "env_steps": 1026048000, "exact_value_avg": 0.4867270886898041, "regret_dist": 0.3768536150455475, "regret_other_env": 0.6280162930488586, "regret_corner": 0.00010949622082989663, "regret_row": 0.40133461356163025, "regret_any": 0.6283665895462036, "regret_bot": 0.8195482492446899, "value_dist": 0.4867270886898041, "value_other_env": 0.2541985511779785, "value_corner": 0.8355198502540588, "value_row": 0.45729202032089233, "value_any": 0.2538839876651764, "value_bot": 0.03907844424247742, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01670.png", "entropy": 0.1196230873465538} +{"ts": "2026-03-20T17:47:39.288076Z", "loop": 1675, "env_steps": 1029120000, "exact_value_avg": 0.48651522397994995, "regret_dist": 0.377065509557724, "regret_other_env": 0.6284189820289612, "regret_corner": 3.52179013134446e-05, "regret_row": 0.3998371660709381, "regret_any": 0.6287650465965271, "regret_bot": 0.8198075294494629, "value_dist": 0.48651522397994995, "value_other_env": 0.25379592180252075, "value_corner": 0.835594117641449, "value_row": 0.4587894678115845, "value_any": 0.2534855306148529, "value_bot": 0.03881910443305969, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01675.png", "entropy": 0.11772331595420837} +{"ts": "2026-03-20T17:47:43.593578Z", "loop": 1680, "env_steps": 1032192000, "exact_value_avg": 0.48703935742378235, "regret_dist": 0.3765413165092468, "regret_other_env": 0.6275488138198853, "regret_corner": 2.9993057978572324e-05, "regret_row": 0.39925628900527954, "regret_any": 0.6278990507125854, "regret_bot": 0.8196150064468384, "value_dist": 0.48703935742378235, "value_other_env": 0.2546660602092743, "value_corner": 0.8355993032455444, "value_row": 0.45937031507492065, "value_any": 0.25435155630111694, "value_bot": 0.03901155665516853, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01680.png", "entropy": 0.1119508370757103} +{"ts": "2026-03-20T17:47:47.899186Z", "loop": 1685, "env_steps": 1035264000, "exact_value_avg": 0.4868927001953125, "regret_dist": 0.37668800354003906, "regret_other_env": 0.6276711225509644, "regret_corner": 0.0002133369562216103, "regret_row": 0.40161368250846863, "regret_any": 0.628023624420166, "regret_bot": 0.8194020390510559, "value_dist": 0.4868927001953125, "value_other_env": 0.2545437812805176, "value_corner": 0.8354160189628601, "value_row": 0.45701301097869873, "value_any": 0.25422704219818115, "value_bot": 0.039224639534950256, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01685.png", "entropy": 0.10469785332679749} +{"ts": "2026-03-20T17:47:52.203525Z", "loop": 1690, "env_steps": 1038336000, "exact_value_avg": 0.482781320810318, "regret_dist": 0.38079941272735596, "regret_other_env": 0.6336314678192139, "regret_corner": 0.0015513008693233132, "regret_row": 0.4091530442237854, "regret_any": 0.6339749097824097, "regret_bot": 0.819381594657898, "value_dist": 0.482781320810318, "value_other_env": 0.24858345091342926, "value_corner": 0.8340780735015869, "value_row": 0.44947364926338196, "value_any": 0.24827569723129272, "value_bot": 0.03924497216939926, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01690.png", "entropy": 0.08875588327646255} +{"ts": "2026-03-20T17:47:56.511865Z", "loop": 1695, "env_steps": 1041408000, "exact_value_avg": 0.4867379069328308, "regret_dist": 0.3768427073955536, "regret_other_env": 0.6279768943786621, "regret_corner": 0.00014141351857688278, "regret_row": 0.4046984016895294, "regret_any": 0.6283289194107056, "regret_bot": 0.8193903565406799, "value_dist": 0.4867379069328308, "value_other_env": 0.25423794984817505, "value_corner": 0.8354878425598145, "value_row": 0.45392823219299316, "value_any": 0.25392165780067444, "value_bot": 0.03923618793487549, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01695.png", "entropy": 0.09164522588253021} +{"ts": "2026-03-20T17:48:00.815218Z", "loop": 1700, "env_steps": 1044480000, "exact_value_avg": 0.48765039443969727, "regret_dist": 0.3759302794933319, "regret_other_env": 0.6265258193016052, "regret_corner": 3.69374974980019e-05, "regret_row": 0.4003269374370575, "regret_any": 0.6268800497055054, "regret_bot": 0.8194118142127991, "value_dist": 0.48765039443969727, "value_other_env": 0.2556890845298767, "value_corner": 0.8355923891067505, "value_row": 0.4582996666431427, "value_any": 0.255370557308197, "value_bot": 0.03921481594443321, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01700.png", "entropy": 0.09711805731058121} +{"ts": "2026-03-20T17:48:05.121506Z", "loop": 1705, "env_steps": 1047552000, "exact_value_avg": 0.48807698488235474, "regret_dist": 0.37550365924835205, "regret_other_env": 0.6258218884468079, "regret_corner": 2.6266774511896074e-05, "regret_row": 0.39821359515190125, "regret_any": 0.6261771321296692, "regret_bot": 0.8195311427116394, "value_dist": 0.48807698488235474, "value_other_env": 0.2563929259777069, "value_corner": 0.8356031179428101, "value_row": 0.46041303873062134, "value_any": 0.2560734748840332, "value_bot": 0.03909549117088318, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01705.png", "entropy": 0.09814618527889252} +{"ts": "2026-03-20T17:48:09.427268Z", "loop": 1710, "env_steps": 1050624000, "exact_value_avg": 0.48809951543807983, "regret_dist": 0.37548112869262695, "regret_other_env": 0.6257820129394531, "regret_corner": 2.97556343866745e-05, "regret_row": 0.39819881319999695, "regret_any": 0.6261372566223145, "regret_bot": 0.8195591568946838, "value_dist": 0.48809951543807983, "value_other_env": 0.2564328610897064, "value_corner": 0.8355995416641235, "value_row": 0.460427850484848, "value_any": 0.25611335039138794, "value_bot": 0.039067480713129044, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01710.png", "entropy": 0.09901750087738037} +{"ts": "2026-03-20T17:48:13.733453Z", "loop": 1715, "env_steps": 1053696000, "exact_value_avg": 0.4880674481391907, "regret_dist": 0.3755132555961609, "regret_other_env": 0.6258317232131958, "regret_corner": 3.554324575816281e-05, "regret_row": 0.3982337713241577, "regret_any": 0.6261868476867676, "regret_bot": 0.8195316195487976, "value_dist": 0.4880674481391907, "value_other_env": 0.25638318061828613, "value_corner": 0.8355937600135803, "value_row": 0.4603928029537201, "value_any": 0.2560637891292572, "value_bot": 0.039094991981983185, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01715.png", "entropy": 0.10191487520933151} +{"ts": "2026-03-20T17:48:18.038235Z", "loop": 1720, "env_steps": 1056768000, "exact_value_avg": 0.4880620837211609, "regret_dist": 0.3755186200141907, "regret_other_env": 0.6258410215377808, "regret_corner": 3.49144174833782e-05, "regret_row": 0.3982486426830292, "regret_any": 0.6261957883834839, "regret_bot": 0.8195637464523315, "value_dist": 0.4880620837211609, "value_other_env": 0.2563738524913788, "value_corner": 0.8355944156646729, "value_row": 0.460377961397171, "value_any": 0.2560548186302185, "value_bot": 0.039062898606061935, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01720.png", "entropy": 0.10244819521903992} +{"ts": "2026-03-20T17:48:22.342613Z", "loop": 1725, "env_steps": 1059840000, "exact_value_avg": 0.4867154359817505, "regret_dist": 0.37686529755592346, "regret_other_env": 0.6280879974365234, "regret_corner": 3.119558095932007e-05, "regret_row": 0.40078669786453247, "regret_any": 0.6284322738647461, "regret_bot": 0.8210875988006592, "value_dist": 0.4867154359817505, "value_other_env": 0.2541269063949585, "value_corner": 0.8355981707572937, "value_row": 0.4578399658203125, "value_any": 0.2538183927536011, "value_bot": 0.03753901273012161, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01725.png", "entropy": 0.09953194856643677} +{"ts": "2026-03-20T17:48:26.650022Z", "loop": 1730, "env_steps": 1062912000, "exact_value_avg": 0.48509660363197327, "regret_dist": 0.3784841001033783, "regret_other_env": 0.6307704448699951, "regret_corner": 5.4556134273298085e-05, "regret_row": 0.40378063917160034, "regret_any": 0.6311080455780029, "regret_bot": 0.8310681581497192, "value_dist": 0.48509660363197327, "value_other_env": 0.2514444589614868, "value_corner": 0.835574746131897, "value_row": 0.45484599471092224, "value_any": 0.25114256143569946, "value_bot": 0.027558447793126106, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01730.png", "entropy": 0.09459114819765091} +{"ts": "2026-03-20T17:48:30.953871Z", "loop": 1735, "env_steps": 1065984000, "exact_value_avg": 0.4877750873565674, "regret_dist": 0.3758056163787842, "regret_other_env": 0.626312255859375, "regret_corner": 4.5585136831505224e-05, "regret_row": 0.39820611476898193, "regret_any": 0.6266667246818542, "regret_bot": 0.8259613513946533, "value_dist": 0.4877750873565674, "value_other_env": 0.25590261816978455, "value_corner": 0.8355837464332581, "value_row": 0.46042054891586304, "value_any": 0.25558391213417053, "value_bot": 0.03266522288322449, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01735.png", "entropy": 0.09000878036022186} +{"ts": "2026-03-20T17:48:35.257432Z", "loop": 1740, "env_steps": 1069056000, "exact_value_avg": 0.4878893196582794, "regret_dist": 0.37569135427474976, "regret_other_env": 0.6261276006698608, "regret_corner": 3.696034400491044e-05, "regret_row": 0.3987628221511841, "regret_any": 0.6264824271202087, "regret_bot": 0.8223285675048828, "value_dist": 0.4878893196582794, "value_other_env": 0.2560872733592987, "value_corner": 0.8355923891067505, "value_row": 0.4598638117313385, "value_any": 0.25576817989349365, "value_bot": 0.036298058927059174, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01740.png", "entropy": 0.08804373443126678} +{"ts": "2026-03-20T17:48:39.562911Z", "loop": 1745, "env_steps": 1072128000, "exact_value_avg": 0.4876646399497986, "regret_dist": 0.375916063785553, "regret_other_env": 0.6264983415603638, "regret_corner": 4.262328366166912e-05, "regret_row": 0.3995644748210907, "regret_any": 0.6268525719642639, "regret_bot": 0.8243376612663269, "value_dist": 0.4876646399497986, "value_other_env": 0.25571656227111816, "value_corner": 0.8355867266654968, "value_row": 0.4590621292591095, "value_any": 0.2553979754447937, "value_bot": 0.034288983792066574, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01745.png", "entropy": 0.08529534190893173} +{"ts": "2026-03-20T17:48:43.864125Z", "loop": 1750, "env_steps": 1075200000, "exact_value_avg": 0.487527072429657, "regret_dist": 0.3760536015033722, "regret_other_env": 0.6267221570014954, "regret_corner": 5.0772232498275116e-05, "regret_row": 0.3990980088710785, "regret_any": 0.6270760893821716, "regret_bot": 0.8268267512321472, "value_dist": 0.487527072429657, "value_other_env": 0.2554927468299866, "value_corner": 0.8355785608291626, "value_row": 0.4595286250114441, "value_any": 0.25517451763153076, "value_bot": 0.03179987519979477, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01750.png", "entropy": 0.08383240550756454} +{"ts": "2026-03-20T17:48:48.170028Z", "loop": 1755, "env_steps": 1078272000, "exact_value_avg": 0.4864521324634552, "regret_dist": 0.377128541469574, "regret_other_env": 0.6284798383712769, "regret_corner": 0.00010156433563679457, "regret_row": 0.39834243059158325, "regret_any": 0.6288310885429382, "regret_bot": 0.8339406251907349, "value_dist": 0.4864521324634552, "value_other_env": 0.2537350356578827, "value_corner": 0.835527777671814, "value_row": 0.4602842330932617, "value_any": 0.2534194886684418, "value_bot": 0.024686003103852272, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01755.png", "entropy": 0.08419954776763916} +{"ts": "2026-03-20T17:48:52.476189Z", "loop": 1760, "env_steps": 1081344000, "exact_value_avg": 0.48690134286880493, "regret_dist": 0.37667933106422424, "regret_other_env": 0.6277501583099365, "regret_corner": 7.303506572498009e-05, "regret_row": 0.3982897996902466, "regret_any": 0.6281025409698486, "regret_bot": 0.8322004675865173, "value_dist": 0.48690134286880493, "value_other_env": 0.25446468591690063, "value_corner": 0.8355562686920166, "value_row": 0.4603368043899536, "value_any": 0.25414803624153137, "value_bot": 0.026426170021295547, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01760.png", "entropy": 0.08187145739793777} +{"ts": "2026-03-20T17:48:56.781435Z", "loop": 1765, "env_steps": 1084416000, "exact_value_avg": 0.48288649320602417, "regret_dist": 0.3806942403316498, "regret_other_env": 0.6343162059783936, "regret_corner": 0.0002612158714327961, "regret_row": 0.3995177745819092, "regret_any": 0.6346585750579834, "regret_bot": 0.8364338874816895, "value_dist": 0.48288649320602417, "value_other_env": 0.247898668050766, "value_corner": 0.8353681564331055, "value_row": 0.4591088891029358, "value_any": 0.2475920170545578, "value_bot": 0.02219276688992977, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01765.png", "entropy": 0.08167193830013275} +{"ts": "2026-03-20T17:49:01.086832Z", "loop": 1770, "env_steps": 1087488000, "exact_value_avg": 0.48471543192863464, "regret_dist": 0.37886518239974976, "regret_other_env": 0.6313394904136658, "regret_corner": 0.00015373231144621968, "regret_row": 0.399547815322876, "regret_any": 0.631686270236969, "regret_bot": 0.8352753520011902, "value_dist": 0.48471543192863464, "value_other_env": 0.2508753538131714, "value_corner": 0.8354755640029907, "value_row": 0.4590788185596466, "value_any": 0.2505642771720886, "value_bot": 0.02335127256810665, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01770.png", "entropy": 0.07897411286830902} +{"ts": "2026-03-20T17:49:05.392911Z", "loop": 1775, "env_steps": 1090560000, "exact_value_avg": 0.4880076050758362, "regret_dist": 0.3755730092525482, "regret_other_env": 0.6259301900863647, "regret_corner": 3.719181040651165e-05, "regret_row": 0.39821484684944153, "regret_any": 0.6262854337692261, "regret_bot": 0.8216175436973572, "value_dist": 0.4880076050758362, "value_other_env": 0.25628459453582764, "value_corner": 0.8355921506881714, "value_row": 0.46041178703308105, "value_any": 0.2559652030467987, "value_bot": 0.03700917586684227, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01775.png", "entropy": 0.08051157742738724} +{"ts": "2026-03-20T17:49:09.698740Z", "loop": 1780, "env_steps": 1093632000, "exact_value_avg": 0.48806437849998474, "regret_dist": 0.37551629543304443, "regret_other_env": 0.6258507370948792, "regret_corner": 1.4609596291847993e-05, "regret_row": 0.39907410740852356, "regret_any": 0.6262059807777405, "regret_bot": 0.8194157481193542, "value_dist": 0.48806437849998474, "value_other_env": 0.2563641369342804, "value_corner": 0.8356146812438965, "value_row": 0.4595525562763214, "value_any": 0.2560445964336395, "value_bot": 0.039210885763168335, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01780.png", "entropy": 0.08202493190765381} +{"ts": "2026-03-20T17:49:14.007697Z", "loop": 1785, "env_steps": 1096704000, "exact_value_avg": 0.4859069287776947, "regret_dist": 0.3776737153530121, "regret_other_env": 0.6294359564781189, "regret_corner": 3.0357639843714423e-05, "regret_row": 0.413232684135437, "regret_any": 0.6297858357429504, "regret_bot": 0.819372832775116, "value_dist": 0.4859069287776947, "value_other_env": 0.25277891755104065, "value_corner": 0.8355989456176758, "value_row": 0.44539394974708557, "value_any": 0.25246480107307434, "value_bot": 0.039253849536180496, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01785.png", "entropy": 0.08064264059066772} +{"ts": "2026-03-20T17:49:18.311578Z", "loop": 1790, "env_steps": 1099776000, "exact_value_avg": 0.48176735639572144, "regret_dist": 0.38181331753730774, "regret_other_env": 0.6359784603118896, "regret_corner": 0.0005655850400216877, "regret_row": 0.41904571652412415, "regret_any": 0.6363183259963989, "regret_bot": 0.819365382194519, "value_dist": 0.48176735639572144, "value_other_env": 0.24623644351959229, "value_corner": 0.8350636959075928, "value_row": 0.43958085775375366, "value_any": 0.24593223631381989, "value_bot": 0.039261192083358765, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01790.png", "entropy": 0.07491238415241241} +{"ts": "2026-03-20T17:49:22.614869Z", "loop": 1795, "env_steps": 1102848000, "exact_value_avg": 0.48466062545776367, "regret_dist": 0.3789200782775879, "regret_other_env": 0.6314015984535217, "regret_corner": 0.00019771607185248286, "regret_row": 0.41503679752349854, "regret_any": 0.6317484974861145, "regret_bot": 0.8193683624267578, "value_dist": 0.48466062545776367, "value_other_env": 0.2508132755756378, "value_corner": 0.8354315757751465, "value_row": 0.44358986616134644, "value_any": 0.2505021095275879, "value_bot": 0.0392582081258297, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01795.png", "entropy": 0.07916885614395142} +{"ts": "2026-03-20T17:49:26.921162Z", "loop": 1800, "env_steps": 1105920000, "exact_value_avg": 0.4876609444618225, "regret_dist": 0.37591975927352905, "regret_other_env": 0.6265125274658203, "regret_corner": 3.0533970857504755e-05, "regret_row": 0.3997291326522827, "regret_any": 0.6268668174743652, "regret_bot": 0.8193780779838562, "value_dist": 0.4876609444618225, "value_other_env": 0.25570234656333923, "value_corner": 0.8355988264083862, "value_row": 0.45889753103256226, "value_any": 0.25538381934165955, "value_bot": 0.03924849256873131, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01800.png", "entropy": 0.08852531015872955} +{"ts": "2026-03-20T17:49:31.229089Z", "loop": 1805, "env_steps": 1108992000, "exact_value_avg": 0.4881054759025574, "regret_dist": 0.3754751980304718, "regret_other_env": 0.6257784962654114, "regret_corner": 2.0202498490107246e-05, "regret_row": 0.3981931507587433, "regret_any": 0.6261338591575623, "regret_bot": 0.8193997144699097, "value_dist": 0.4881054759025574, "value_other_env": 0.25643640756607056, "value_corner": 0.8356090784072876, "value_row": 0.4604334235191345, "value_any": 0.2561168074607849, "value_bot": 0.03922692686319351, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01805.png", "entropy": 0.09025215357542038} +{"ts": "2026-03-20T17:49:35.538010Z", "loop": 1810, "env_steps": 1112064000, "exact_value_avg": 0.48797136545181274, "regret_dist": 0.37560930848121643, "regret_other_env": 0.6260004043579102, "regret_corner": 2.267311174364295e-05, "regret_row": 0.3983153700828552, "regret_any": 0.6263550519943237, "regret_bot": 0.8194752931594849, "value_dist": 0.48797136545181274, "value_other_env": 0.2562144696712494, "value_corner": 0.8356066346168518, "value_row": 0.46031123399734497, "value_any": 0.2558955252170563, "value_bot": 0.039151355624198914, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01810.png", "entropy": 0.08749216049909592} +{"ts": "2026-03-20T17:49:39.845610Z", "loop": 1815, "env_steps": 1115136000, "exact_value_avg": 0.4875340461730957, "regret_dist": 0.37604665756225586, "regret_other_env": 0.6267220377922058, "regret_corner": 3.3509237255202606e-05, "regret_row": 0.39908769726753235, "regret_any": 0.6270750164985657, "regret_bot": 0.819826602935791, "value_dist": 0.4875340461730957, "value_other_env": 0.25549283623695374, "value_corner": 0.8355957865715027, "value_row": 0.45953890681266785, "value_any": 0.2551756203174591, "value_bot": 0.0387999601662159, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01815.png", "entropy": 0.08503591269254684} +{"ts": "2026-03-20T17:49:44.158727Z", "loop": 1820, "env_steps": 1118208000, "exact_value_avg": 0.4862768054008484, "regret_dist": 0.37730392813682556, "regret_other_env": 0.6287978887557983, "regret_corner": 6.297876825556159e-05, "regret_row": 0.4020446240901947, "regret_any": 0.6291459798812866, "regret_bot": 0.8233857750892639, "value_dist": 0.4862768054008484, "value_other_env": 0.2534170150756836, "value_corner": 0.8355664014816284, "value_row": 0.45658203959465027, "value_any": 0.25310462713241577, "value_bot": 0.035240791738033295, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01820.png", "entropy": 0.08232245594263077} +{"ts": "2026-03-20T17:49:48.469298Z", "loop": 1825, "env_steps": 1121280000, "exact_value_avg": 0.48490890860557556, "regret_dist": 0.3786717355251312, "regret_other_env": 0.6310341358184814, "regret_corner": 0.0001280759897781536, "regret_row": 0.40315771102905273, "regret_any": 0.6313798427581787, "regret_bot": 0.8328024744987488, "value_dist": 0.48490890860557556, "value_other_env": 0.2511806786060333, "value_corner": 0.8355012536048889, "value_row": 0.4554688632488251, "value_any": 0.25087082386016846, "value_bot": 0.02582419663667679, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01825.png", "entropy": 0.07910983264446259} +{"ts": "2026-03-20T17:49:52.782402Z", "loop": 1830, "env_steps": 1124352000, "exact_value_avg": 0.4866447150707245, "regret_dist": 0.3769359886646271, "regret_other_env": 0.6281371712684631, "regret_corner": 0.00013418446178548038, "regret_row": 0.3987116813659668, "regret_any": 0.6284888982772827, "regret_bot": 0.832251787185669, "value_dist": 0.4866447150707245, "value_other_env": 0.2540777027606964, "value_corner": 0.8354951739311218, "value_row": 0.4599149525165558, "value_any": 0.25376176834106445, "value_bot": 0.026374828070402145, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01830.png", "entropy": 0.07669182121753693} +{"ts": "2026-03-20T17:49:57.087648Z", "loop": 1835, "env_steps": 1127424000, "exact_value_avg": 0.487739622592926, "regret_dist": 0.37584105134010315, "regret_other_env": 0.6263531446456909, "regret_corner": 7.289201312232763e-05, "regret_row": 0.3985130786895752, "regret_any": 0.6267076730728149, "regret_bot": 0.8246604204177856, "value_dist": 0.487739622592926, "value_other_env": 0.25586172938346863, "value_corner": 0.8355564475059509, "value_row": 0.4601135551929474, "value_any": 0.25554293394088745, "value_bot": 0.03396626561880112, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01835.png", "entropy": 0.0754498839378357} +{"ts": "2026-03-20T17:50:01.393625Z", "loop": 1840, "env_steps": 1130496000, "exact_value_avg": 0.4862942099571228, "regret_dist": 0.377286434173584, "regret_other_env": 0.6287866234779358, "regret_corner": 3.610700514400378e-05, "regret_row": 0.41307663917541504, "regret_any": 0.6291375160217285, "regret_bot": 0.8195127248764038, "value_dist": 0.4862942099571228, "value_other_env": 0.2534281611442566, "value_corner": 0.8355932235717773, "value_row": 0.44554996490478516, "value_any": 0.2531130611896515, "value_bot": 0.039113886654376984, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01840.png", "entropy": 0.07524992525577545} +{"ts": "2026-03-20T17:50:05.697918Z", "loop": 1845, "env_steps": 1133568000, "exact_value_avg": 0.4850635528564453, "regret_dist": 0.3785170912742615, "regret_other_env": 0.6308424472808838, "regret_corner": 2.9005112082813866e-05, "regret_row": 0.4160749316215515, "regret_any": 0.6311901807785034, "regret_bot": 0.819401204586029, "value_dist": 0.4850635528564453, "value_other_env": 0.25137242674827576, "value_corner": 0.8356002569198608, "value_row": 0.4425516724586487, "value_any": 0.251060426235199, "value_bot": 0.03922545164823532, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01845.png", "entropy": 0.07434329390525818} +{"ts": "2026-03-20T17:50:10.001611Z", "loop": 1850, "env_steps": 1136640000, "exact_value_avg": 0.48548874258995056, "regret_dist": 0.3780919015407562, "regret_other_env": 0.6301339864730835, "regret_corner": 2.8735401429003105e-05, "regret_row": 0.41513246297836304, "regret_any": 0.6304827332496643, "regret_bot": 0.8193869590759277, "value_dist": 0.48548874258995056, "value_other_env": 0.25208085775375366, "value_corner": 0.8356005549430847, "value_row": 0.44349420070648193, "value_any": 0.2517678141593933, "value_bot": 0.03923967853188515, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01850.png", "entropy": 0.07438457012176514} +{"ts": "2026-03-20T17:50:14.311118Z", "loop": 1855, "env_steps": 1139712000, "exact_value_avg": 0.4861468970775604, "regret_dist": 0.3774338364601135, "regret_other_env": 0.6290350556373596, "regret_corner": 3.19446153298486e-05, "regret_row": 0.41308629512786865, "regret_any": 0.6293854713439941, "regret_bot": 0.8193778991699219, "value_dist": 0.4861468970775604, "value_other_env": 0.2531798481941223, "value_corner": 0.8355973958969116, "value_row": 0.44554033875465393, "value_any": 0.25286513566970825, "value_bot": 0.03924865648150444, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01855.png", "entropy": 0.07573553174734116} +{"ts": "2026-03-20T17:50:18.621012Z", "loop": 1860, "env_steps": 1142784000, "exact_value_avg": 0.4862135350704193, "regret_dist": 0.37736713886260986, "regret_other_env": 0.6289173364639282, "regret_corner": 4.181564145255834e-05, "regret_row": 0.41168656945228577, "regret_any": 0.6292679905891418, "regret_bot": 0.8193718194961548, "value_dist": 0.4862135350704193, "value_other_env": 0.2532975375652313, "value_corner": 0.8355875015258789, "value_row": 0.4469400942325592, "value_any": 0.25298261642456055, "value_bot": 0.039254795759916306, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01860.png", "entropy": 0.07776021957397461} +{"ts": "2026-03-20T17:50:22.926215Z", "loop": 1865, "env_steps": 1145856000, "exact_value_avg": 0.4873444437980652, "regret_dist": 0.376236230134964, "regret_other_env": 0.6270297169685364, "regret_corner": 4.598001760314219e-05, "regret_row": 0.4016982913017273, "regret_any": 0.6273831725120544, "regret_bot": 0.8193740248680115, "value_dist": 0.4873444437980652, "value_other_env": 0.25518518686294556, "value_corner": 0.8355833292007446, "value_row": 0.4569283425807953, "value_any": 0.25486743450164795, "value_bot": 0.03925260901451111, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01865.png", "entropy": 0.08209121227264404} +{"ts": "2026-03-20T17:50:27.231812Z", "loop": 1870, "env_steps": 1148928000, "exact_value_avg": 0.48755306005477905, "regret_dist": 0.3760276734828949, "regret_other_env": 0.6266773343086243, "regret_corner": 5.310575579642318e-05, "regret_row": 0.3997168242931366, "regret_any": 0.6270313262939453, "regret_bot": 0.8193767070770264, "value_dist": 0.48755306005477905, "value_other_env": 0.2555375397205353, "value_corner": 0.8355762362480164, "value_row": 0.458909809589386, "value_any": 0.2552192807197571, "value_bot": 0.0392499677836895, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01870.png", "entropy": 0.08837844431400299} +{"ts": "2026-03-20T17:50:31.538140Z", "loop": 1875, "env_steps": 1152000000, "exact_value_avg": 0.48782455921173096, "regret_dist": 0.3757561147212982, "regret_other_env": 0.6262310147285461, "regret_corner": 4.371007526060566e-05, "regret_row": 0.39880675077438354, "regret_any": 0.6265856027603149, "regret_bot": 0.8193874955177307, "value_dist": 0.48782455921173096, "value_other_env": 0.2559838593006134, "value_corner": 0.8355855941772461, "value_row": 0.45981988310813904, "value_any": 0.25566497445106506, "value_bot": 0.0392390601336956, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01875.png", "entropy": 0.09284641593694687} +{"ts": "2026-03-20T17:50:35.844788Z", "loop": 1880, "env_steps": 1155072000, "exact_value_avg": 0.4878148138523102, "regret_dist": 0.3757658302783966, "regret_other_env": 0.6262522339820862, "regret_corner": 3.622621443355456e-05, "regret_row": 0.39839059114456177, "regret_any": 0.6266065239906311, "regret_bot": 0.8194072246551514, "value_dist": 0.4878148138523102, "value_other_env": 0.255962610244751, "value_corner": 0.8355931043624878, "value_row": 0.4602360427379608, "value_any": 0.2556440830230713, "value_bot": 0.03921940177679062, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01880.png", "entropy": 0.09278957545757294} +{"ts": "2026-03-20T17:50:40.151002Z", "loop": 1885, "env_steps": 1158144000, "exact_value_avg": 0.4874378442764282, "regret_dist": 0.37614285945892334, "regret_other_env": 0.6268853545188904, "regret_corner": 2.9028953576926142e-05, "regret_row": 0.39880648255348206, "regret_any": 0.6272372007369995, "regret_bot": 0.8194583654403687, "value_dist": 0.4874378442764282, "value_other_env": 0.2553294897079468, "value_corner": 0.8356003165245056, "value_row": 0.4598201811313629, "value_any": 0.2550134062767029, "value_bot": 0.039168231189250946, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01885.png", "entropy": 0.09248805791139603} +{"ts": "2026-03-20T17:50:44.453632Z", "loop": 1890, "env_steps": 1161216000, "exact_value_avg": 0.487998366355896, "regret_dist": 0.37558233737945557, "regret_other_env": 0.6259506940841675, "regret_corner": 2.970745299535338e-05, "regret_row": 0.39826899766921997, "regret_any": 0.6263052821159363, "regret_bot": 0.8194221258163452, "value_dist": 0.487998366355896, "value_other_env": 0.25626417994499207, "value_corner": 0.8355996012687683, "value_row": 0.4603576064109802, "value_any": 0.2559453248977661, "value_bot": 0.03920445963740349, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01890.png", "entropy": 0.09014556556940079} +{"ts": "2026-03-20T17:50:48.759607Z", "loop": 1895, "env_steps": 1164288000, "exact_value_avg": 0.4878993630409241, "regret_dist": 0.3756813108921051, "regret_other_env": 0.6261106133460999, "regret_corner": 3.7360689020715654e-05, "regret_row": 0.3985331952571869, "regret_any": 0.6264653205871582, "regret_bot": 0.8193925023078918, "value_dist": 0.4878993630409241, "value_other_env": 0.2561042904853821, "value_corner": 0.8355919122695923, "value_row": 0.4600934386253357, "value_any": 0.2557852566242218, "value_bot": 0.039234112948179245, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01895.png", "entropy": 0.0920637845993042} +{"ts": "2026-03-20T17:50:53.065398Z", "loop": 1900, "env_steps": 1167360000, "exact_value_avg": 0.4876479208469391, "regret_dist": 0.3759327232837677, "regret_other_env": 0.6265270709991455, "regret_corner": 4.1163963032886386e-05, "regret_row": 0.3991962671279907, "regret_any": 0.6268810629844666, "regret_bot": 0.8193957209587097, "value_dist": 0.4876479208469391, "value_other_env": 0.25568777322769165, "value_corner": 0.8355880975723267, "value_row": 0.45943036675453186, "value_any": 0.25536954402923584, "value_bot": 0.03923087194561958, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01900.png", "entropy": 0.09415468573570251} +{"ts": "2026-03-20T17:50:57.368703Z", "loop": 1905, "env_steps": 1170432000, "exact_value_avg": 0.48759758472442627, "regret_dist": 0.3759830892086029, "regret_other_env": 0.6266131401062012, "regret_corner": 3.801485217991285e-05, "regret_row": 0.3988228440284729, "regret_any": 0.6269665956497192, "regret_bot": 0.8194130659103394, "value_dist": 0.48759758472442627, "value_other_env": 0.25560176372528076, "value_corner": 0.8355913162231445, "value_row": 0.4598037898540497, "value_any": 0.25528404116630554, "value_bot": 0.03921360522508621, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01905.png", "entropy": 0.09458725899457932} +{"ts": "2026-03-20T17:51:01.678510Z", "loop": 1910, "env_steps": 1173504000, "exact_value_avg": 0.48731523752212524, "regret_dist": 0.3762654662132263, "regret_other_env": 0.6270893216133118, "regret_corner": 2.9628974516526796e-05, "regret_row": 0.39895349740982056, "regret_any": 0.6274400353431702, "regret_bot": 0.819482684135437, "value_dist": 0.48731523752212524, "value_other_env": 0.25512561202049255, "value_corner": 0.8355996608734131, "value_row": 0.459673136472702, "value_any": 0.25481054186820984, "value_bot": 0.03914397209882736, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01910.png", "entropy": 0.09321363270282745} +{"ts": "2026-03-20T17:51:05.982734Z", "loop": 1915, "env_steps": 1176576000, "exact_value_avg": 0.48762190341949463, "regret_dist": 0.37595877051353455, "regret_other_env": 0.6265715956687927, "regret_corner": 3.947665391024202e-05, "regret_row": 0.3986951410770416, "regret_any": 0.626923680305481, "regret_bot": 0.8195084929466248, "value_dist": 0.48762190341949463, "value_other_env": 0.25564324855804443, "value_corner": 0.8355898261070251, "value_row": 0.45993152260780334, "value_any": 0.25532686710357666, "value_bot": 0.039118122309446335, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01915.png", "entropy": 0.08892224729061127} +{"ts": "2026-03-20T17:51:10.290598Z", "loop": 1920, "env_steps": 1179648000, "exact_value_avg": 0.48808878660202026, "regret_dist": 0.3754919171333313, "regret_other_env": 0.6257808804512024, "regret_corner": 5.8426958275958896e-05, "regret_row": 0.39825883507728577, "regret_any": 0.6261355876922607, "regret_bot": 0.819636344909668, "value_dist": 0.48808878660202026, "value_other_env": 0.25643399357795715, "value_corner": 0.8355708718299866, "value_row": 0.46036776900291443, "value_any": 0.25611501932144165, "value_bot": 0.03899029269814491, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01920.png", "entropy": 0.08516598492860794} +{"ts": "2026-03-20T17:51:14.598385Z", "loop": 1925, "env_steps": 1182720000, "exact_value_avg": 0.4881979823112488, "regret_dist": 0.3753826916217804, "regret_other_env": 0.6255854964256287, "regret_corner": 7.848242967156693e-05, "regret_row": 0.3981305658817291, "regret_any": 0.6259410977363586, "regret_bot": 0.8197083473205566, "value_dist": 0.4881979823112488, "value_other_env": 0.2566293478012085, "value_corner": 0.835550844669342, "value_row": 0.46049609780311584, "value_any": 0.25630947947502136, "value_bot": 0.03891829028725624, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01925.png", "entropy": 0.08657611906528473} +{"ts": "2026-03-20T17:51:18.905719Z", "loop": 1930, "env_steps": 1185792000, "exact_value_avg": 0.4880802631378174, "regret_dist": 0.3755004405975342, "regret_other_env": 0.6257768869400024, "regret_corner": 8.577803964726627e-05, "regret_row": 0.39843249320983887, "regret_any": 0.6261323094367981, "regret_bot": 0.8195334672927856, "value_dist": 0.4880802631378174, "value_other_env": 0.2564379870891571, "value_corner": 0.8355436325073242, "value_row": 0.4601941406726837, "value_any": 0.2561183273792267, "value_bot": 0.03909314423799515, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01930.png", "entropy": 0.08636155724525452} +{"ts": "2026-03-20T17:51:23.212604Z", "loop": 1935, "env_steps": 1188864000, "exact_value_avg": 0.48794886469841003, "regret_dist": 0.37563180923461914, "regret_other_env": 0.6259979009628296, "regret_corner": 8.264383359346539e-05, "regret_row": 0.39910411834716797, "regret_any": 0.6263529658317566, "regret_bot": 0.8194699883460999, "value_dist": 0.48794886469841003, "value_other_env": 0.25621697306632996, "value_corner": 0.8355466723442078, "value_row": 0.4595224857330322, "value_any": 0.2558976411819458, "value_bot": 0.039156604558229446, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01935.png", "entropy": 0.08667659759521484} +{"ts": "2026-03-20T17:51:27.522566Z", "loop": 1940, "env_steps": 1191936000, "exact_value_avg": 0.4880450367927551, "regret_dist": 0.37553563714027405, "regret_other_env": 0.6257832646369934, "regret_corner": 0.00016416559810750186, "regret_row": 0.3982037901878357, "regret_any": 0.6261385083198547, "regret_bot": 0.8202390670776367, "value_dist": 0.4880450367927551, "value_other_env": 0.2564316689968109, "value_corner": 0.835465133190155, "value_row": 0.4604228436946869, "value_any": 0.25611206889152527, "value_bot": 0.038387540727853775, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01940.png", "entropy": 0.08977706730365753} +{"ts": "2026-03-20T17:51:31.832125Z", "loop": 1945, "env_steps": 1195008000, "exact_value_avg": 0.48806580901145935, "regret_dist": 0.3755148947238922, "regret_other_env": 0.6257667541503906, "regret_corner": 0.0001370867103105411, "regret_row": 0.3982832729816437, "regret_any": 0.6261221170425415, "regret_bot": 0.8197927474975586, "value_dist": 0.48806580901145935, "value_other_env": 0.2564481794834137, "value_corner": 0.8354922533035278, "value_row": 0.4603433609008789, "value_any": 0.2561285197734833, "value_bot": 0.03883391246199608, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01945.png", "entropy": 0.08925467729568481} +{"ts": "2026-03-20T17:51:36.136099Z", "loop": 1950, "env_steps": 1198080000, "exact_value_avg": 0.4880177974700928, "regret_dist": 0.3755628764629364, "regret_other_env": 0.6258397102355957, "regret_corner": 0.0001476138859288767, "regret_row": 0.3984265625476837, "regret_any": 0.626194953918457, "regret_bot": 0.8199412822723389, "value_dist": 0.4880177974700928, "value_other_env": 0.25637513399124146, "value_corner": 0.8354817628860474, "value_row": 0.4602000117301941, "value_any": 0.2560555934906006, "value_bot": 0.038685351610183716, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01950.png", "entropy": 0.08816541731357574} +{"ts": "2026-03-20T17:51:40.441397Z", "loop": 1955, "env_steps": 1201152000, "exact_value_avg": 0.4880020022392273, "regret_dist": 0.3755786716938019, "regret_other_env": 0.6258571743965149, "regret_corner": 0.00016082824731711298, "regret_row": 0.39836347103118896, "regret_any": 0.626212477684021, "regret_bot": 0.8203293085098267, "value_dist": 0.4880020022392273, "value_other_env": 0.2563576400279999, "value_corner": 0.8354685306549072, "value_row": 0.46026313304901123, "value_any": 0.2560381293296814, "value_bot": 0.038297317922115326, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01955.png", "entropy": 0.08716918528079987} +{"ts": "2026-03-20T17:51:44.743117Z", "loop": 1960, "env_steps": 1204224000, "exact_value_avg": 0.48797357082366943, "regret_dist": 0.37560713291168213, "regret_other_env": 0.6258869767189026, "regret_corner": 0.00018734237528406084, "regret_row": 0.3982310891151428, "regret_any": 0.6262421011924744, "regret_bot": 0.8211561441421509, "value_dist": 0.48797357082366943, "value_other_env": 0.25632795691490173, "value_corner": 0.8354420065879822, "value_row": 0.46039557456970215, "value_any": 0.25600847601890564, "value_bot": 0.03747045248746872, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01960.png", "entropy": 0.08683952689170837} +{"ts": "2026-03-20T17:51:49.045995Z", "loop": 1965, "env_steps": 1207296000, "exact_value_avg": 0.48808103799819946, "regret_dist": 0.3754997253417969, "regret_other_env": 0.6257399916648865, "regret_corner": 0.00013928115367889404, "regret_row": 0.39815348386764526, "regret_any": 0.6260953545570374, "regret_bot": 0.8203831911087036, "value_dist": 0.48808103799819946, "value_other_env": 0.25647494196891785, "value_corner": 0.8354901075363159, "value_row": 0.4604731500148773, "value_any": 0.25615525245666504, "value_bot": 0.03824346512556076, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01965.png", "entropy": 0.08645137399435043} +{"ts": "2026-03-20T17:51:53.351434Z", "loop": 1970, "env_steps": 1210368000, "exact_value_avg": 0.48815596103668213, "regret_dist": 0.3754247725009918, "regret_other_env": 0.6256297826766968, "regret_corner": 0.00011716435983544216, "regret_row": 0.3981090188026428, "regret_any": 0.625985324382782, "regret_bot": 0.8200176358222961, "value_dist": 0.48815596103668213, "value_other_env": 0.25658509135246277, "value_corner": 0.8355122208595276, "value_row": 0.46051764488220215, "value_any": 0.2562652826309204, "value_bot": 0.038608990609645844, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01970.png", "entropy": 0.08793141692876816} +{"ts": "2026-03-20T17:51:57.655826Z", "loop": 1975, "env_steps": 1213440000, "exact_value_avg": 0.48803454637527466, "regret_dist": 0.3755461275577545, "regret_other_env": 0.6257869005203247, "regret_corner": 0.00018495322728995234, "regret_row": 0.3981499671936035, "regret_any": 0.6261419653892517, "regret_bot": 0.8223389983177185, "value_dist": 0.48803454637527466, "value_other_env": 0.25642794370651245, "value_corner": 0.8354443907737732, "value_row": 0.46047666668891907, "value_any": 0.2561086118221283, "value_bot": 0.03628767654299736, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01975.png", "entropy": 0.08693966269493103} +{"ts": "2026-03-20T17:52:01.961682Z", "loop": 1980, "env_steps": 1216512000, "exact_value_avg": 0.48791614174842834, "regret_dist": 0.37566447257995605, "regret_other_env": 0.6259773373603821, "regret_corner": 0.0001951525773620233, "regret_row": 0.39820998907089233, "regret_any": 0.6263316869735718, "regret_bot": 0.8240544199943542, "value_dist": 0.48791614174842834, "value_other_env": 0.2562374770641327, "value_corner": 0.8354341387748718, "value_row": 0.46041664481163025, "value_any": 0.2559189200401306, "value_bot": 0.034572187811136246, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01980.png", "entropy": 0.08495897054672241} +{"ts": "2026-03-20T17:52:06.268653Z", "loop": 1985, "env_steps": 1219584000, "exact_value_avg": 0.48597943782806396, "regret_dist": 0.3776012659072876, "regret_other_env": 0.6290858387947083, "regret_corner": 0.0003743559354916215, "regret_row": 0.40007850527763367, "regret_any": 0.6294320821762085, "regret_bot": 0.8344589471817017, "value_dist": 0.48597943782806396, "value_other_env": 0.2531290352344513, "value_corner": 0.835254967212677, "value_row": 0.4585481584072113, "value_any": 0.2528184652328491, "value_bot": 0.024167632684111595, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01985.png", "entropy": 0.08178871124982834} +{"ts": "2026-03-20T17:52:10.576374Z", "loop": 1990, "env_steps": 1222656000, "exact_value_avg": 0.484693706035614, "regret_dist": 0.37888699769973755, "regret_other_env": 0.6311727166175842, "regret_corner": 0.00045838457299396396, "regret_row": 0.4023776650428772, "regret_any": 0.6315146088600159, "regret_bot": 0.8358215093612671, "value_dist": 0.484693706035614, "value_other_env": 0.2510421574115753, "value_corner": 0.8351709246635437, "value_row": 0.4562489688396454, "value_any": 0.2507360279560089, "value_bot": 0.02280508168041706, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01990.png", "entropy": 0.07968062907457352} +{"ts": "2026-03-20T17:52:14.885892Z", "loop": 1995, "env_steps": 1225728000, "exact_value_avg": 0.4864041805267334, "regret_dist": 0.3771764636039734, "regret_other_env": 0.6284900903701782, "regret_corner": 0.00020601900178007782, "regret_row": 0.40061071515083313, "regret_any": 0.6288374066352844, "regret_bot": 0.8321619629859924, "value_dist": 0.4864041805267334, "value_other_env": 0.25372472405433655, "value_corner": 0.8354233503341675, "value_row": 0.45801594853401184, "value_any": 0.25341320037841797, "value_bot": 0.026464642956852913, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_01995.png", "entropy": 0.07616113126277924} +{"ts": "2026-03-20T17:52:19.195531Z", "loop": 2000, "env_steps": 1228800000, "exact_value_avg": 0.4875684380531311, "regret_dist": 0.37601223587989807, "regret_other_env": 0.6265889406204224, "regret_corner": 0.00014712513075210154, "regret_row": 0.3986327648162842, "regret_any": 0.6269417405128479, "regret_bot": 0.8269838094711304, "value_dist": 0.4875684380531311, "value_other_env": 0.2556259334087372, "value_corner": 0.8354821801185608, "value_row": 0.4599938988685608, "value_any": 0.2553088665008545, "value_bot": 0.031642839312553406, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02000.png", "entropy": 0.07517588138580322} +{"ts": "2026-03-20T17:52:27.770837Z", "loop": 2010, "env_steps": 1234944000, "exact_value_avg": 0.4882431626319885, "regret_dist": 0.3753375709056854, "regret_other_env": 0.6254969835281372, "regret_corner": 9.838939149631187e-05, "regret_row": 0.39813175797462463, "regret_any": 0.6258527040481567, "regret_bot": 0.8198835849761963, "value_dist": 0.4882431626319885, "value_other_env": 0.2567179203033447, "value_corner": 0.8355309367179871, "value_row": 0.46049487590789795, "value_any": 0.25639793276786804, "value_bot": 0.03874312341213226, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02010.png", "entropy": 0.07771211117506027} +{"ts": "2026-03-20T17:52:36.336333Z", "loop": 2020, "env_steps": 1241088000, "exact_value_avg": 0.4880785346031189, "regret_dist": 0.37550216913223267, "regret_other_env": 0.6257635951042175, "regret_corner": 0.00010997057688655332, "regret_row": 0.39819666743278503, "regret_any": 0.6261187195777893, "regret_bot": 0.8228310346603394, "value_dist": 0.4880785346031189, "value_other_env": 0.2564513087272644, "value_corner": 0.8355193138122559, "value_row": 0.46042993664741516, "value_any": 0.2561319172382355, "value_bot": 0.035795558243989944, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02020.png", "entropy": 0.07298972457647324} +{"ts": "2026-03-20T17:52:44.902875Z", "loop": 2030, "env_steps": 1247232000, "exact_value_avg": 0.48820948600769043, "regret_dist": 0.37537121772766113, "regret_other_env": 0.6255913972854614, "regret_corner": 4.090269794687629e-05, "regret_row": 0.3981581926345825, "regret_any": 0.6259470582008362, "regret_bot": 0.8194058537483215, "value_dist": 0.48820948600769043, "value_other_env": 0.2566234767436981, "value_corner": 0.8355884552001953, "value_row": 0.46046844124794006, "value_any": 0.2563035488128662, "value_bot": 0.03922082856297493, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02030.png", "entropy": 0.07656696438789368} +{"ts": "2026-03-20T17:52:53.478260Z", "loop": 2040, "env_steps": 1253376000, "exact_value_avg": 0.48807066679000854, "regret_dist": 0.37550997734069824, "regret_other_env": 0.625819742679596, "regret_corner": 4.5293076254893094e-05, "regret_row": 0.3990626335144043, "regret_any": 0.6261751055717468, "regret_bot": 0.8194178342819214, "value_dist": 0.48807066679000854, "value_other_env": 0.2563951015472412, "value_corner": 0.8355840444564819, "value_row": 0.4595640003681183, "value_any": 0.25607550144195557, "value_bot": 0.039208706468343735, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02040.png", "entropy": 0.07283591479063034} +{"ts": "2026-03-20T17:53:02.049354Z", "loop": 2050, "env_steps": 1259520000, "exact_value_avg": 0.48789894580841064, "regret_dist": 0.3756817579269409, "regret_other_env": 0.6260983347892761, "regret_corner": 5.681117545464076e-05, "regret_row": 0.4005338251590729, "regret_any": 0.6264532208442688, "regret_bot": 0.8195044994354248, "value_dist": 0.48789894580841064, "value_other_env": 0.25611650943756104, "value_corner": 0.8355725407600403, "value_row": 0.4580928385257721, "value_any": 0.2557973265647888, "value_bot": 0.03912210464477539, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02050.png", "entropy": 0.07145316153764725} +{"ts": "2026-03-20T17:53:10.619676Z", "loop": 2060, "env_steps": 1265664000, "exact_value_avg": 0.487664133310318, "regret_dist": 0.37591660022735596, "regret_other_env": 0.6264902353286743, "regret_corner": 5.610386870102957e-05, "regret_row": 0.40253525972366333, "regret_any": 0.6268444657325745, "regret_bot": 0.8194146752357483, "value_dist": 0.487664133310318, "value_other_env": 0.2557246685028076, "value_corner": 0.8355732560157776, "value_row": 0.45609137415885925, "value_any": 0.25540608167648315, "value_bot": 0.039211906492710114, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02060.png", "entropy": 0.0700974091887474} +{"ts": "2026-03-20T17:53:19.188858Z", "loop": 2070, "env_steps": 1271808000, "exact_value_avg": 0.48815178871154785, "regret_dist": 0.3754289150238037, "regret_other_env": 0.6256645321846008, "regret_corner": 7.550468581030145e-05, "regret_row": 0.3981649875640869, "regret_any": 0.6260200142860413, "regret_bot": 0.8198117017745972, "value_dist": 0.48815178871154785, "value_other_env": 0.2565503716468811, "value_corner": 0.8355538249015808, "value_row": 0.4604615867137909, "value_any": 0.25623056292533875, "value_bot": 0.038814958184957504, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02070.png", "entropy": 0.0757010355591774} +{"ts": "2026-03-20T17:53:27.756916Z", "loop": 2080, "env_steps": 1277952000, "exact_value_avg": 0.48824363946914673, "regret_dist": 0.37533700466156006, "regret_other_env": 0.625523567199707, "regret_corner": 5.714893632102758e-05, "regret_row": 0.3980983793735504, "regret_any": 0.6258793473243713, "regret_bot": 0.8195114135742188, "value_dist": 0.48824363946914673, "value_other_env": 0.2566912770271301, "value_corner": 0.8355721831321716, "value_row": 0.46052828431129456, "value_any": 0.25637125968933105, "value_bot": 0.03911518678069115, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02080.png", "entropy": 0.07810060679912567} +{"ts": "2026-03-20T17:53:36.328479Z", "loop": 2090, "env_steps": 1284096000, "exact_value_avg": 0.4882154166698456, "regret_dist": 0.3753652572631836, "regret_other_env": 0.6255748867988586, "regret_corner": 5.071809209766798e-05, "regret_row": 0.3981055021286011, "regret_any": 0.6259306073188782, "regret_bot": 0.8193895220756531, "value_dist": 0.4882154166698456, "value_other_env": 0.2566399574279785, "value_corner": 0.8355785608291626, "value_row": 0.4605211615562439, "value_any": 0.2563200294971466, "value_bot": 0.03923708572983742, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02090.png", "entropy": 0.07657851278781891} +{"ts": "2026-03-20T17:53:44.902362Z", "loop": 2100, "env_steps": 1290240000, "exact_value_avg": 0.4881669878959656, "regret_dist": 0.3754136562347412, "regret_other_env": 0.6256158947944641, "regret_corner": 0.00011027108121197671, "regret_row": 0.398118257522583, "regret_any": 0.6259714961051941, "regret_bot": 0.8213032484054565, "value_dist": 0.4881669878959656, "value_other_env": 0.25659894943237305, "value_corner": 0.8355190753936768, "value_row": 0.4605083763599396, "value_any": 0.2562791407108307, "value_bot": 0.03732333332300186, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02100.png", "entropy": 0.07596825808286667} +{"ts": "2026-03-20T17:53:53.477887Z", "loop": 2110, "env_steps": 1296384000, "exact_value_avg": 0.4842466711997986, "regret_dist": 0.3793340027332306, "regret_other_env": 0.6318003535270691, "regret_corner": 0.0006344105349853635, "regret_row": 0.39930978417396545, "regret_any": 0.632146418094635, "regret_bot": 0.8367518186569214, "value_dist": 0.4842466711997986, "value_other_env": 0.25041449069976807, "value_corner": 0.834994912147522, "value_row": 0.45931684970855713, "value_any": 0.25010421872138977, "value_bot": 0.021874742582440376, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02110.png", "entropy": 0.06966659426689148} +{"ts": "2026-03-20T17:54:02.051163Z", "loop": 2120, "env_steps": 1302528000, "exact_value_avg": 0.48793527483940125, "regret_dist": 0.37564539909362793, "regret_other_env": 0.6260147094726562, "regret_corner": 9.139577741734684e-05, "regret_row": 0.398149698972702, "regret_any": 0.6263695359230042, "regret_bot": 0.8262110352516174, "value_dist": 0.48793527483940125, "value_other_env": 0.2562001645565033, "value_corner": 0.8355379104614258, "value_row": 0.46047693490982056, "value_any": 0.25588101148605347, "value_bot": 0.032415568828582764, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02120.png", "entropy": 0.0651438981294632} +{"ts": "2026-03-20T17:54:10.628020Z", "loop": 2130, "env_steps": 1308672000, "exact_value_avg": 0.488189160823822, "regret_dist": 0.37539151310920715, "regret_other_env": 0.6256055235862732, "regret_corner": 7.049491250654683e-05, "regret_row": 0.39813175797462463, "regret_any": 0.6259612441062927, "regret_bot": 0.8207242488861084, "value_dist": 0.488189160823822, "value_other_env": 0.25660932064056396, "value_corner": 0.8355588912963867, "value_row": 0.46049487590789795, "value_any": 0.25628942251205444, "value_bot": 0.03790237382054329, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02130.png", "entropy": 0.06661465764045715} +{"ts": "2026-03-20T17:54:19.202557Z", "loop": 2140, "env_steps": 1314816000, "exact_value_avg": 0.4860239028930664, "regret_dist": 0.3775567412376404, "regret_other_env": 0.6291075348854065, "regret_corner": 0.0002305050875293091, "regret_row": 0.3985985815525055, "regret_any": 0.6294578313827515, "regret_bot": 0.835338294506073, "value_dist": 0.4860239028930664, "value_other_env": 0.25310730934143066, "value_corner": 0.83539879322052, "value_row": 0.4600280523300171, "value_any": 0.25279271602630615, "value_bot": 0.023288344964385033, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02140.png", "entropy": 0.06221393495798111} +{"ts": "2026-03-20T17:54:27.778716Z", "loop": 2150, "env_steps": 1320960000, "exact_value_avg": 0.4879930019378662, "regret_dist": 0.37558773159980774, "regret_other_env": 0.6259346604347229, "regret_corner": 6.72673195367679e-05, "regret_row": 0.3981499671936035, "regret_any": 0.6262897253036499, "regret_bot": 0.8244363069534302, "value_dist": 0.4879930019378662, "value_other_env": 0.2562802731990814, "value_corner": 0.8355620503425598, "value_row": 0.46047666668891907, "value_any": 0.2559608519077301, "value_bot": 0.03419031202793121, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02150.png", "entropy": 0.06347347050905228} +{"ts": "2026-03-20T17:54:36.351643Z", "loop": 2160, "env_steps": 1327104000, "exact_value_avg": 0.48739659786224365, "regret_dist": 0.3761840760707855, "regret_other_env": 0.6268953680992126, "regret_corner": 0.0001170977993751876, "regret_row": 0.3983703553676605, "regret_any": 0.6272489428520203, "regret_bot": 0.8308406472206116, "value_dist": 0.48739659786224365, "value_other_env": 0.2553195059299469, "value_corner": 0.8355122208595276, "value_row": 0.4602562487125397, "value_any": 0.25500163435935974, "value_bot": 0.027785953134298325, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02160.png", "entropy": 0.06064954772591591} +{"ts": "2026-03-20T17:54:44.932922Z", "loop": 2170, "env_steps": 1333248000, "exact_value_avg": 0.48634201288223267, "regret_dist": 0.3772386312484741, "regret_other_env": 0.6285274028778076, "regret_corner": 0.0003053695254493505, "regret_row": 0.3992883861064911, "regret_any": 0.6288784742355347, "regret_bot": 0.8343908786773682, "value_dist": 0.48634201288223267, "value_other_env": 0.25368741154670715, "value_corner": 0.8353239297866821, "value_row": 0.4593382775783539, "value_any": 0.25337210297584534, "value_bot": 0.024235814809799194, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02170.png", "entropy": 0.0615600049495697} +{"ts": "2026-03-20T17:54:53.510400Z", "loop": 2180, "env_steps": 1339392000, "exact_value_avg": 0.4882426857948303, "regret_dist": 0.37533798813819885, "regret_other_env": 0.6255025267601013, "regret_corner": 9.110024257097393e-05, "regret_row": 0.39813676476478577, "regret_any": 0.6258583664894104, "regret_bot": 0.8195828199386597, "value_dist": 0.4882426857948303, "value_other_env": 0.25671231746673584, "value_corner": 0.8355382084846497, "value_row": 0.4604898989200592, "value_any": 0.2563922703266144, "value_bot": 0.03904386982321739, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02180.png", "entropy": 0.06945013254880905} +{"ts": "2026-03-20T17:55:02.085248Z", "loop": 2190, "env_steps": 1345536000, "exact_value_avg": 0.48817187547683716, "regret_dist": 0.3754088282585144, "regret_other_env": 0.625646710395813, "regret_corner": 5.191862874198705e-05, "regret_row": 0.3982774019241333, "regret_any": 0.6260022521018982, "regret_bot": 0.819366455078125, "value_dist": 0.48817187547683716, "value_other_env": 0.25656816363334656, "value_corner": 0.8355774283409119, "value_row": 0.4603492319583893, "value_any": 0.2562483251094818, "value_bot": 0.03926011919975281, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02190.png", "entropy": 0.07097843289375305} +{"ts": "2026-03-20T17:55:10.660992Z", "loop": 2200, "env_steps": 1351680000, "exact_value_avg": 0.48758643865585327, "regret_dist": 0.3759942352771759, "regret_other_env": 0.6266210675239563, "regret_corner": 5.3926807595416903e-05, "regret_row": 0.40031248331069946, "regret_any": 0.6269751787185669, "regret_bot": 0.8193520307540894, "value_dist": 0.48758643865585327, "value_other_env": 0.25559380650520325, "value_corner": 0.8355754017829895, "value_row": 0.4583141803741455, "value_any": 0.2552754282951355, "value_bot": 0.03927469998598099, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02200.png", "entropy": 0.07113942503929138} +{"ts": "2026-03-20T17:55:19.235538Z", "loop": 2210, "env_steps": 1357824000, "exact_value_avg": 0.48656851053237915, "regret_dist": 0.3770121932029724, "regret_other_env": 0.6282985210418701, "regret_corner": 8.26184987090528e-05, "regret_row": 0.40290966629981995, "regret_any": 0.6286500096321106, "regret_bot": 0.8193420171737671, "value_dist": 0.48656851053237915, "value_other_env": 0.2539163827896118, "value_corner": 0.8355466723442078, "value_row": 0.45571693778038025, "value_any": 0.253600537776947, "value_bot": 0.03928465396165848, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02210.png", "entropy": 0.07062985002994537} +{"ts": "2026-03-20T17:55:27.807287Z", "loop": 2220, "env_steps": 1363968000, "exact_value_avg": 0.48626837134361267, "regret_dist": 0.3773123025894165, "regret_other_env": 0.6287935972213745, "regret_corner": 9.030054206959903e-05, "regret_row": 0.40144726634025574, "regret_any": 0.6291444301605225, "regret_bot": 0.8193379640579224, "value_dist": 0.48626837134361267, "value_other_env": 0.25342124700546265, "value_corner": 0.8355390429496765, "value_row": 0.45717933773994446, "value_any": 0.25310614705085754, "value_bot": 0.039288751780986786, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02220.png", "entropy": 0.07266394793987274} +{"ts": "2026-03-20T17:55:36.378966Z", "loop": 2230, "env_steps": 1370112000, "exact_value_avg": 0.48807257413864136, "regret_dist": 0.3755081295967102, "regret_other_env": 0.6258008480072021, "regret_corner": 6.899038999108598e-05, "regret_row": 0.39823874831199646, "regret_any": 0.6261560320854187, "regret_bot": 0.8193500638008118, "value_dist": 0.48807257413864136, "value_other_env": 0.2564140856266022, "value_corner": 0.8355603218078613, "value_row": 0.4603878855705261, "value_any": 0.2560946047306061, "value_bot": 0.03927657753229141, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02230.png", "entropy": 0.08404060453176498} +{"ts": "2026-03-20T17:55:44.954923Z", "loop": 2240, "env_steps": 1376256000, "exact_value_avg": 0.488381564617157, "regret_dist": 0.3751991391181946, "regret_other_env": 0.6252682209014893, "regret_corner": 9.54285278567113e-05, "regret_row": 0.3980748951435089, "regret_any": 0.6256241798400879, "regret_bot": 0.8193684816360474, "value_dist": 0.488381564617157, "value_other_env": 0.2569466531276703, "value_corner": 0.8355339765548706, "value_row": 0.46055176854133606, "value_any": 0.2566264569759369, "value_bot": 0.0392582006752491, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02240.png", "entropy": 0.08351147919893265} +{"ts": "2026-03-20T17:55:53.525090Z", "loop": 2250, "env_steps": 1382400000, "exact_value_avg": 0.4881693422794342, "regret_dist": 0.37541133165359497, "regret_other_env": 0.6256037354469299, "regret_corner": 0.00012271454033907503, "regret_row": 0.39807572960853577, "regret_any": 0.6259593963623047, "regret_bot": 0.8193488717079163, "value_dist": 0.4881693422794342, "value_other_env": 0.2566111385822296, "value_corner": 0.8355066180229187, "value_row": 0.46055087447166443, "value_any": 0.2562912702560425, "value_bot": 0.03927776217460632, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02250.png", "entropy": 0.08001727610826492} +{"ts": "2026-03-20T17:56:02.109517Z", "loop": 2260, "env_steps": 1388544000, "exact_value_avg": 0.4880019724369049, "regret_dist": 0.37557870149612427, "regret_other_env": 0.6258625984191895, "regret_corner": 0.00015280644583981484, "regret_row": 0.3982100486755371, "regret_any": 0.626217782497406, "regret_bot": 0.8193522691726685, "value_dist": 0.4880019724369049, "value_other_env": 0.2563523054122925, "value_corner": 0.8354764580726624, "value_row": 0.46041661500930786, "value_any": 0.256032794713974, "value_bot": 0.039274346083402634, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02260.png", "entropy": 0.0796378031373024} +{"ts": "2026-03-20T17:56:10.684955Z", "loop": 2270, "env_steps": 1394688000, "exact_value_avg": 0.48780491948127747, "regret_dist": 0.3757758140563965, "regret_other_env": 0.6261747479438782, "regret_corner": 0.00017739436589181423, "regret_row": 0.39874741435050964, "regret_any": 0.6265295147895813, "regret_bot": 0.8193623423576355, "value_dist": 0.48780491948127747, "value_other_env": 0.25604018568992615, "value_corner": 0.8354519605636597, "value_row": 0.45987915992736816, "value_any": 0.25572115182876587, "value_bot": 0.039264336228370667, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02270.png", "entropy": 0.07863253355026245} +{"ts": "2026-03-20T17:56:19.260289Z", "loop": 2280, "env_steps": 1400832000, "exact_value_avg": 0.48766234517097473, "regret_dist": 0.37591835856437683, "regret_other_env": 0.6264216899871826, "regret_corner": 0.00016328941273968667, "regret_row": 0.39878660440444946, "regret_any": 0.6267759799957275, "regret_bot": 0.81935054063797, "value_dist": 0.48766234517097473, "value_other_env": 0.2557932138442993, "value_corner": 0.8354660272598267, "value_row": 0.4598400592803955, "value_any": 0.2554745674133301, "value_bot": 0.039276123046875, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02280.png", "entropy": 0.07824715971946716} +{"ts": "2026-03-20T17:56:27.834160Z", "loop": 2290, "env_steps": 1406976000, "exact_value_avg": 0.48761439323425293, "regret_dist": 0.37596628069877625, "regret_other_env": 0.626505970954895, "regret_corner": 0.0001566514401929453, "regret_row": 0.3987445533275604, "regret_any": 0.6268602609634399, "regret_bot": 0.8193468451499939, "value_dist": 0.48761439323425293, "value_other_env": 0.25570887327194214, "value_corner": 0.8354726433753967, "value_row": 0.45988208055496216, "value_any": 0.25539034605026245, "value_bot": 0.03927984461188316, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02290.png", "entropy": 0.07743841409683228} +{"ts": "2026-03-20T17:56:36.408700Z", "loop": 2300, "env_steps": 1413120000, "exact_value_avg": 0.4876551032066345, "regret_dist": 0.37592557072639465, "regret_other_env": 0.6264510154724121, "regret_corner": 0.00013742198643740267, "regret_row": 0.398398220539093, "regret_any": 0.6268053650856018, "regret_bot": 0.8193427324295044, "value_dist": 0.4876551032066345, "value_other_env": 0.2557638883590698, "value_corner": 0.8354918956756592, "value_row": 0.4602283537387848, "value_any": 0.2554452419281006, "value_bot": 0.039283815771341324, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02300.png", "entropy": 0.07723458111286163} +{"ts": "2026-03-20T17:56:44.987860Z", "loop": 2310, "env_steps": 1419264000, "exact_value_avg": 0.4869042634963989, "regret_dist": 0.37667641043663025, "regret_other_env": 0.6277003884315491, "regret_corner": 0.000140383854159154, "regret_row": 0.39908191561698914, "regret_any": 0.6280527710914612, "regret_bot": 0.8193411827087402, "value_dist": 0.4869042634963989, "value_other_env": 0.2545144557952881, "value_corner": 0.8354889154434204, "value_row": 0.45954471826553345, "value_any": 0.25419774651527405, "value_bot": 0.03928545117378235, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02310.png", "entropy": 0.07327202707529068} +{"ts": "2026-03-20T17:56:53.569714Z", "loop": 2320, "env_steps": 1425408000, "exact_value_avg": 0.48788154125213623, "regret_dist": 0.37569916248321533, "regret_other_env": 0.6261027455329895, "regret_corner": 9.373724606120959e-05, "regret_row": 0.39821046590805054, "regret_any": 0.6264576315879822, "regret_bot": 0.8193426728248596, "value_dist": 0.48788154125213623, "value_other_env": 0.25611215829849243, "value_corner": 0.8355355858802795, "value_row": 0.46041619777679443, "value_any": 0.255793035030365, "value_bot": 0.03928398713469505, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02320.png", "entropy": 0.07613352686166763} +{"ts": "2026-03-20T17:57:02.143918Z", "loop": 2330, "env_steps": 1431552000, "exact_value_avg": 0.48484373092651367, "regret_dist": 0.3787369132041931, "regret_other_env": 0.6311549544334412, "regret_corner": 0.00010979970829794183, "regret_row": 0.40230268239974976, "regret_any": 0.6315021514892578, "regret_bot": 0.819328248500824, "value_dist": 0.48484373092651367, "value_other_env": 0.251059889793396, "value_corner": 0.8355194926261902, "value_row": 0.45632392168045044, "value_any": 0.2507484257221222, "value_bot": 0.03929842263460159, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02330.png", "entropy": 0.06811148673295975} +{"ts": "2026-03-20T17:57:10.720757Z", "loop": 2340, "env_steps": 1437696000, "exact_value_avg": 0.4842734932899475, "regret_dist": 0.3793071508407593, "regret_other_env": 0.632119357585907, "regret_corner": 8.882532711140811e-05, "regret_row": 0.4025612771511078, "regret_any": 0.6324650645256042, "regret_bot": 0.8193041086196899, "value_dist": 0.4842734932899475, "value_other_env": 0.2500954866409302, "value_corner": 0.8355404734611511, "value_row": 0.45606529712677, "value_any": 0.24978552758693695, "value_bot": 0.03932250663638115, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02340.png", "entropy": 0.0734415352344513} +{"ts": "2026-03-20T17:57:19.292423Z", "loop": 2350, "env_steps": 1443840000, "exact_value_avg": 0.48749640583992004, "regret_dist": 0.3760842978954315, "regret_other_env": 0.6267111897468567, "regret_corner": 0.00014394920435734093, "regret_row": 0.4002752900123596, "regret_any": 0.6270509362220764, "regret_bot": 0.8195939064025879, "value_dist": 0.48749640583992004, "value_other_env": 0.25550374388694763, "value_corner": 0.8354853987693787, "value_row": 0.45835134387016296, "value_any": 0.2551996409893036, "value_bot": 0.039032794535160065, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02350.png", "entropy": 0.09290093183517456} +{"ts": "2026-03-20T17:57:27.866417Z", "loop": 2360, "env_steps": 1449984000, "exact_value_avg": 0.4879612624645233, "regret_dist": 0.37561944127082825, "regret_other_env": 0.6259663105010986, "regret_corner": 9.912103996612132e-05, "regret_row": 0.39788076281547546, "regret_any": 0.626292884349823, "regret_bot": 0.8198915123939514, "value_dist": 0.4879612624645233, "value_other_env": 0.2562485933303833, "value_corner": 0.8355302214622498, "value_row": 0.4607458710670471, "value_any": 0.2559577524662018, "value_bot": 0.03873506933450699, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02360.png", "entropy": 0.0803079605102539} +{"ts": "2026-03-20T17:57:36.435301Z", "loop": 2370, "env_steps": 1456128000, "exact_value_avg": 0.48811590671539307, "regret_dist": 0.3754647672176361, "regret_other_env": 0.6256029605865479, "regret_corner": 0.0002574036770965904, "regret_row": 0.39812520146369934, "regret_any": 0.6259517669677734, "regret_bot": 0.8243380188941956, "value_dist": 0.48811590671539307, "value_other_env": 0.2566118538379669, "value_corner": 0.8353719711303711, "value_row": 0.46050146222114563, "value_any": 0.25629886984825134, "value_bot": 0.034288570284843445, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02370.png", "entropy": 0.06625393033027649} +{"ts": "2026-03-20T17:57:45.010450Z", "loop": 2380, "env_steps": 1462272000, "exact_value_avg": 0.488018274307251, "regret_dist": 0.3755623996257782, "regret_other_env": 0.6257460713386536, "regret_corner": 0.00028681359253823757, "regret_row": 0.3981695771217346, "regret_any": 0.6261011362075806, "regret_bot": 0.8250082731246948, "value_dist": 0.488018274307251, "value_other_env": 0.2564687728881836, "value_corner": 0.835342526435852, "value_row": 0.46045705676078796, "value_any": 0.25614938139915466, "value_bot": 0.03361837938427925, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02380.png", "entropy": 0.06824345886707306} +{"ts": "2026-03-20T17:57:53.583943Z", "loop": 2390, "env_steps": 1468416000, "exact_value_avg": 0.48334723711013794, "regret_dist": 0.3802334666252136, "regret_other_env": 0.6321869492530823, "regret_corner": 0.002303188666701317, "regret_row": 0.4077588617801666, "regret_any": 0.6325316429138184, "regret_bot": 0.8370737433433533, "value_dist": 0.48334723711013794, "value_other_env": 0.25002795457839966, "value_corner": 0.8333261013031006, "value_row": 0.45086780190467834, "value_any": 0.24971897900104523, "value_bot": 0.021552911028265953, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02390.png", "entropy": 0.06497640907764435} +{"ts": "2026-03-20T17:58:02.156138Z", "loop": 2400, "env_steps": 1474560000, "exact_value_avg": 0.48765692114830017, "regret_dist": 0.3759237825870514, "regret_other_env": 0.6263622045516968, "regret_corner": 0.00026615362730808556, "regret_row": 0.39830297231674194, "regret_any": 0.626716136932373, "regret_bot": 0.8303742408752441, "value_dist": 0.48765692114830017, "value_other_env": 0.25585272908210754, "value_corner": 0.8353631496429443, "value_row": 0.46032363176345825, "value_any": 0.25553447008132935, "value_bot": 0.02825245074927807, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02400.png", "entropy": 0.06671937555074692} +{"ts": "2026-03-20T17:58:10.731493Z", "loop": 2410, "env_steps": 1480704000, "exact_value_avg": 0.48810258507728577, "regret_dist": 0.3754781186580658, "regret_other_env": 0.6256324648857117, "regret_corner": 0.00024650743580423295, "regret_row": 0.3981955647468567, "regret_any": 0.6259874701499939, "regret_bot": 0.8247043490409851, "value_dist": 0.48810258507728577, "value_other_env": 0.2565823793411255, "value_corner": 0.8353828191757202, "value_row": 0.4604310691356659, "value_any": 0.2562631666660309, "value_bot": 0.033922288566827774, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02410.png", "entropy": 0.0686444342136383} +{"ts": "2026-03-20T17:58:19.308044Z", "loop": 2420, "env_steps": 1486848000, "exact_value_avg": 0.4880496859550476, "regret_dist": 0.37553098797798157, "regret_other_env": 0.625762403011322, "regret_corner": 0.00018381228437647223, "regret_row": 0.3987213969230652, "regret_any": 0.6261069774627686, "regret_bot": 0.8250776529312134, "value_dist": 0.4880496859550476, "value_other_env": 0.25645244121551514, "value_corner": 0.8354455232620239, "value_row": 0.459905207157135, "value_any": 0.25614362955093384, "value_bot": 0.03354897350072861, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02420.png", "entropy": 0.06451162695884705} +{"ts": "2026-03-20T17:58:27.883253Z", "loop": 2430, "env_steps": 1492992000, "exact_value_avg": 0.48821350932121277, "regret_dist": 0.3753671944141388, "regret_other_env": 0.6254754066467285, "regret_corner": 0.00020483187108766288, "regret_row": 0.398315966129303, "regret_any": 0.6258277893066406, "regret_bot": 0.8236636519432068, "value_dist": 0.48821350932121277, "value_other_env": 0.25673943758010864, "value_corner": 0.835424542427063, "value_row": 0.4603106677532196, "value_any": 0.25642284750938416, "value_bot": 0.03496300056576729, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02430.png", "entropy": 0.06530891358852386} +{"ts": "2026-03-20T17:58:36.455149Z", "loop": 2440, "env_steps": 1499136000, "exact_value_avg": 0.48786455392837524, "regret_dist": 0.3757161498069763, "regret_other_env": 0.6260300278663635, "regret_corner": 0.0002452756161801517, "regret_row": 0.3989528715610504, "regret_any": 0.6263790726661682, "regret_bot": 0.827586829662323, "value_dist": 0.48786455392837524, "value_other_env": 0.2561849057674408, "value_corner": 0.8353840112686157, "value_row": 0.45967379212379456, "value_any": 0.25587165355682373, "value_bot": 0.031039759516716003, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02440.png", "entropy": 0.06233132258057594} +{"ts": "2026-03-20T17:58:45.033743Z", "loop": 2450, "env_steps": 1505280000, "exact_value_avg": 0.48822587728500366, "regret_dist": 0.3753548264503479, "regret_other_env": 0.6254889965057373, "regret_corner": 0.00015356342191807926, "regret_row": 0.39842551946640015, "regret_any": 0.6258416771888733, "regret_bot": 0.8235647082328796, "value_dist": 0.48822587728500366, "value_other_env": 0.25672590732574463, "value_corner": 0.8354758024215698, "value_row": 0.4602011442184448, "value_any": 0.2564089000225067, "value_bot": 0.035061877220869064, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02450.png", "entropy": 0.06249883398413658} +{"ts": "2026-03-20T17:58:53.616057Z", "loop": 2460, "env_steps": 1511424000, "exact_value_avg": 0.4883989691734314, "regret_dist": 0.37518173456192017, "regret_other_env": 0.6251752376556396, "regret_corner": 0.00019140045333188027, "regret_row": 0.3981982469558716, "regret_any": 0.6255309581756592, "regret_bot": 0.8197792768478394, "value_dist": 0.4883989691734314, "value_other_env": 0.2570396363735199, "value_corner": 0.8354379534721375, "value_row": 0.4604283571243286, "value_any": 0.2567196190357208, "value_bot": 0.03884730488061905, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02460.png", "entropy": 0.06609392911195755} +{"ts": "2026-03-20T17:59:02.195673Z", "loop": 2470, "env_steps": 1517568000, "exact_value_avg": 0.4867962896823883, "regret_dist": 0.3767843544483185, "regret_other_env": 0.6278749704360962, "regret_corner": 0.0001484071253798902, "regret_row": 0.4058687388896942, "regret_any": 0.6281953454017639, "regret_bot": 0.8260120749473572, "value_dist": 0.4867962896823883, "value_other_env": 0.25433987379074097, "value_corner": 0.8354809284210205, "value_row": 0.4527578353881836, "value_any": 0.2540552020072937, "value_bot": 0.03261450305581093, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02470.png", "entropy": 0.05867303907871246} +{"ts": "2026-03-20T17:59:10.769792Z", "loop": 2480, "env_steps": 1523712000, "exact_value_avg": 0.4873548448085785, "regret_dist": 0.3762257993221283, "regret_other_env": 0.6268163919448853, "regret_corner": 0.00033991190139204264, "regret_row": 0.4008200764656067, "regret_any": 0.6271647214889526, "regret_bot": 0.8285903334617615, "value_dist": 0.4873548448085785, "value_other_env": 0.2553984522819519, "value_corner": 0.8352894186973572, "value_row": 0.4578065574169159, "value_any": 0.25508591532707214, "value_bot": 0.030036361888051033, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02480.png", "entropy": 0.05573069304227829} +{"ts": "2026-03-20T17:59:19.339576Z", "loop": 2490, "env_steps": 1529856000, "exact_value_avg": 0.4832976460456848, "regret_dist": 0.3802829384803772, "regret_other_env": 0.6321274638175964, "regret_corner": 0.0025161649100482464, "regret_row": 0.40925928950309753, "regret_any": 0.6324729919433594, "regret_bot": 0.8354423642158508, "value_dist": 0.4832976460456848, "value_other_env": 0.25008735060691833, "value_corner": 0.8331131339073181, "value_row": 0.44936731457710266, "value_any": 0.24977752566337585, "value_bot": 0.02318420261144638, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02490.png", "entropy": 0.059398192912340164} +{"ts": "2026-03-20T17:59:27.911141Z", "loop": 2500, "env_steps": 1536000000, "exact_value_avg": 0.486572265625, "regret_dist": 0.37700843811035156, "regret_other_env": 0.6278578042984009, "regret_corner": 0.0007343347533605993, "regret_row": 0.40200942754745483, "regret_any": 0.6282098293304443, "regret_bot": 0.8313767313957214, "value_dist": 0.486572265625, "value_other_env": 0.25435709953308105, "value_corner": 0.8348950147628784, "value_row": 0.45661720633506775, "value_any": 0.25404077768325806, "value_bot": 0.027249908074736595, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02500.png", "entropy": 0.056349512189626694} +{"ts": "2026-03-20T17:59:36.481686Z", "loop": 2510, "env_steps": 1542144000, "exact_value_avg": 0.4883045554161072, "regret_dist": 0.3752761781215668, "regret_other_env": 0.6253563165664673, "regret_corner": 0.00015592774434480816, "regret_row": 0.3982674777507782, "regret_any": 0.6257121562957764, "regret_bot": 0.8213968873023987, "value_dist": 0.4883045554161072, "value_other_env": 0.25685858726501465, "value_corner": 0.8354734182357788, "value_row": 0.460359126329422, "value_any": 0.2565384805202484, "value_bot": 0.037229813635349274, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02510.png", "entropy": 0.05564805865287781} +{"ts": "2026-03-20T17:59:45.055312Z", "loop": 2520, "env_steps": 1548288000, "exact_value_avg": 0.48835325241088867, "regret_dist": 0.37522751092910767, "regret_other_env": 0.6252567172050476, "regret_corner": 0.00018363397975917906, "regret_row": 0.39816200733184814, "regret_any": 0.625612735748291, "regret_bot": 0.8192853331565857, "value_dist": 0.48835325241088867, "value_other_env": 0.2569582164287567, "value_corner": 0.8354457020759583, "value_row": 0.4604646563529968, "value_any": 0.256637841463089, "value_bot": 0.039341289550065994, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02520.png", "entropy": 0.06378573179244995} +{"ts": "2026-03-20T17:59:53.629278Z", "loop": 2530, "env_steps": 1554432000, "exact_value_avg": 0.4877421259880066, "regret_dist": 0.3758385479450226, "regret_other_env": 0.6263195276260376, "regret_corner": 0.0001170183313661255, "regret_row": 0.3998867869377136, "regret_any": 0.6266740560531616, "regret_bot": 0.8191855549812317, "value_dist": 0.4877421259880066, "value_other_env": 0.25589534640312195, "value_corner": 0.8355122804641724, "value_row": 0.45873984694480896, "value_any": 0.25557658076286316, "value_bot": 0.03944109007716179, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02530.png", "entropy": 0.07204856723546982} +{"ts": "2026-03-20T18:00:02.213822Z", "loop": 2540, "env_steps": 1560576000, "exact_value_avg": 0.48649895191192627, "regret_dist": 0.3770817518234253, "regret_other_env": 0.6283692121505737, "regret_corner": 0.00015049676585476846, "regret_row": 0.40134644508361816, "regret_any": 0.6287200450897217, "regret_bot": 0.8192167282104492, "value_dist": 0.48649895191192627, "value_other_env": 0.2538456916809082, "value_corner": 0.8354788422584534, "value_row": 0.4572801887989044, "value_any": 0.2535305619239807, "value_bot": 0.03940992429852486, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02540.png", "entropy": 0.0778023973107338} +{"ts": "2026-03-20T18:00:10.802568Z", "loop": 2550, "env_steps": 1566720000, "exact_value_avg": 0.48518192768096924, "regret_dist": 0.37839871644973755, "regret_other_env": 0.6305716037750244, "regret_corner": 0.00013933033915236592, "regret_row": 0.40166139602661133, "regret_any": 0.6309168338775635, "regret_bot": 0.8192132711410522, "value_dist": 0.48518192768096924, "value_other_env": 0.25164327025413513, "value_corner": 0.8354899287223816, "value_row": 0.45696526765823364, "value_any": 0.2513337731361389, "value_bot": 0.039413344115018845, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02550.png", "entropy": 0.08048856258392334} +{"ts": "2026-03-20T18:00:19.379273Z", "loop": 2560, "env_steps": 1572864000, "exact_value_avg": 0.48756080865859985, "regret_dist": 0.3760198652744293, "regret_other_env": 0.6265958547592163, "regret_corner": 0.00015585274377372116, "regret_row": 0.4015868902206421, "regret_any": 0.6269403696060181, "regret_bot": 0.8193172216415405, "value_dist": 0.48756080865859985, "value_other_env": 0.25561901926994324, "value_corner": 0.8354734778404236, "value_row": 0.4570397436618805, "value_any": 0.25531020760536194, "value_bot": 0.03930928558111191, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02560.png", "entropy": 0.07867482304573059} +{"ts": "2026-03-20T18:00:27.958821Z", "loop": 2570, "env_steps": 1579008000, "exact_value_avg": 0.48707789182662964, "regret_dist": 0.3765028417110443, "regret_other_env": 0.6273759007453918, "regret_corner": 0.00019315979443490505, "regret_row": 0.4018988311290741, "regret_any": 0.6276894807815552, "regret_bot": 0.8201330900192261, "value_dist": 0.48707789182662964, "value_other_env": 0.2548389732837677, "value_corner": 0.8354361653327942, "value_row": 0.4567278027534485, "value_any": 0.2545611262321472, "value_bot": 0.03849353268742561, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02570.png", "entropy": 0.08012793213129044} +{"ts": "2026-03-20T18:00:36.536126Z", "loop": 2580, "env_steps": 1585152000, "exact_value_avg": 0.48712432384490967, "regret_dist": 0.3764563798904419, "regret_other_env": 0.6272835731506348, "regret_corner": 0.00021552096586674452, "regret_row": 0.4018297493457794, "regret_any": 0.6276057362556458, "regret_bot": 0.8199661374092102, "value_dist": 0.48712432384490967, "value_other_env": 0.2549312710762024, "value_corner": 0.8354138135910034, "value_row": 0.4567968547344208, "value_any": 0.25464490056037903, "value_bot": 0.0386604443192482, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02580.png", "entropy": 0.08017249405384064} +{"ts": "2026-03-20T18:00:45.115520Z", "loop": 2590, "env_steps": 1591296000, "exact_value_avg": 0.4875330328941345, "regret_dist": 0.37604764103889465, "regret_other_env": 0.6266693472862244, "regret_corner": 0.00011507273302413523, "regret_row": 0.4013529419898987, "regret_any": 0.6270232200622559, "regret_bot": 0.8191942572593689, "value_dist": 0.4875330328941345, "value_other_env": 0.2555455267429352, "value_corner": 0.83551424741745, "value_row": 0.4572736620903015, "value_any": 0.25522735714912415, "value_bot": 0.03943242132663727, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02590.png", "entropy": 0.07415194809436798} +{"ts": "2026-03-20T18:00:53.688603Z", "loop": 2600, "env_steps": 1597440000, "exact_value_avg": 0.4863467812538147, "regret_dist": 0.3772338628768921, "regret_other_env": 0.6286605596542358, "regret_corner": 9.382615826325491e-05, "regret_row": 0.4020687937736511, "regret_any": 0.6290115714073181, "regret_bot": 0.8191812634468079, "value_dist": 0.4863467812538147, "value_other_env": 0.2535543143749237, "value_corner": 0.83553546667099, "value_row": 0.45655784010887146, "value_any": 0.2532390356063843, "value_bot": 0.03944529965519905, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02600.png", "entropy": 0.06560541689395905} +{"ts": "2026-03-20T18:01:02.266507Z", "loop": 2610, "env_steps": 1603584000, "exact_value_avg": 0.4870845675468445, "regret_dist": 0.3764960765838623, "regret_other_env": 0.6274338960647583, "regret_corner": 8.931706543080509e-05, "regret_row": 0.4015321433544159, "regret_any": 0.6277866959571838, "regret_bot": 0.8191973567008972, "value_dist": 0.4870845675468445, "value_other_env": 0.25478091835975647, "value_corner": 0.8355399966239929, "value_row": 0.4570944905281067, "value_any": 0.2544638514518738, "value_bot": 0.03942926600575447, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02610.png", "entropy": 0.06698745489120483} +{"ts": "2026-03-20T18:01:10.840192Z", "loop": 2620, "env_steps": 1609728000, "exact_value_avg": 0.4876999258995056, "regret_dist": 0.37588074803352356, "regret_other_env": 0.6263781189918518, "regret_corner": 0.00013463100185617805, "regret_row": 0.4011664092540741, "regret_any": 0.6267325282096863, "regret_bot": 0.8192492723464966, "value_dist": 0.4876999258995056, "value_other_env": 0.25583675503730774, "value_corner": 0.8354946374893188, "value_row": 0.4574602246284485, "value_any": 0.2555180788040161, "value_bot": 0.039377354085445404, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02620.png", "entropy": 0.06824613362550735} +{"ts": "2026-03-20T18:01:19.414870Z", "loop": 2630, "env_steps": 1615872000, "exact_value_avg": 0.48764508962631226, "regret_dist": 0.3759355843067169, "regret_other_env": 0.6264979243278503, "regret_corner": 9.200275235343724e-05, "regret_row": 0.40137603878974915, "regret_any": 0.6268519759178162, "regret_bot": 0.8192318081855774, "value_dist": 0.48764508962631226, "value_other_env": 0.2557169198989868, "value_corner": 0.835537314414978, "value_row": 0.45725053548812866, "value_any": 0.25539860129356384, "value_bot": 0.039394840598106384, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02630.png", "entropy": 0.07319305837154388} +{"ts": "2026-03-20T18:01:27.988389Z", "loop": 2640, "env_steps": 1622016000, "exact_value_avg": 0.4858960211277008, "regret_dist": 0.37768468260765076, "regret_other_env": 0.6294288039207458, "regret_corner": 6.84345795889385e-05, "regret_row": 0.40217921137809753, "regret_any": 0.6297783255577087, "regret_bot": 0.8191907405853271, "value_dist": 0.4858960211277008, "value_other_env": 0.2527860701084137, "value_corner": 0.8355609178543091, "value_row": 0.45644742250442505, "value_any": 0.25247228145599365, "value_bot": 0.03943585231900215, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02640.png", "entropy": 0.07493092119693756} +{"ts": "2026-03-20T18:01:36.567199Z", "loop": 2650, "env_steps": 1628160000, "exact_value_avg": 0.4878939986228943, "regret_dist": 0.37568673491477966, "regret_other_env": 0.6260268092155457, "regret_corner": 0.00017654598923400044, "regret_row": 0.40067076683044434, "regret_any": 0.6263662576675415, "regret_bot": 0.8194122910499573, "value_dist": 0.4878939986228943, "value_other_env": 0.25618812441825867, "value_corner": 0.8354527950286865, "value_row": 0.45795586705207825, "value_any": 0.2558842599391937, "value_bot": 0.03921432048082352, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02650.png", "entropy": 0.07670942693948746} +{"ts": "2026-03-20T18:01:45.148717Z", "loop": 2660, "env_steps": 1634304000, "exact_value_avg": 0.4861011505126953, "regret_dist": 0.3774794936180115, "regret_other_env": 0.6290119290351868, "regret_corner": 0.00018083553004544228, "regret_row": 0.4057566225528717, "regret_any": 0.6292972564697266, "regret_bot": 0.82196044921875, "value_dist": 0.4861011505126953, "value_other_env": 0.2532029151916504, "value_corner": 0.8354485034942627, "value_row": 0.4528700113296509, "value_any": 0.2529533803462982, "value_bot": 0.03666616231203079, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02660.png", "entropy": 0.07737727463245392} +{"ts": "2026-03-20T18:01:53.724508Z", "loop": 2670, "env_steps": 1640448000, "exact_value_avg": 0.48833853006362915, "regret_dist": 0.3752421438694, "regret_other_env": 0.6252826452255249, "regret_corner": 0.00018133671255782247, "regret_row": 0.3982447683811188, "regret_any": 0.6256066560745239, "regret_bot": 0.8194823265075684, "value_dist": 0.48833853006362915, "value_other_env": 0.25693219900131226, "value_corner": 0.8354479670524597, "value_row": 0.4603818356990814, "value_any": 0.2566439211368561, "value_bot": 0.03914429247379303, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02670.png", "entropy": 0.06917092949151993} +{"ts": "2026-03-20T18:02:02.300022Z", "loop": 2680, "env_steps": 1646592000, "exact_value_avg": 0.4885391294956207, "regret_dist": 0.37504157423973083, "regret_other_env": 0.6249123811721802, "regret_corner": 0.0002353285817662254, "regret_row": 0.3980793356895447, "regret_any": 0.6252650022506714, "regret_bot": 0.819261908531189, "value_dist": 0.4885391294956207, "value_other_env": 0.25730252265930176, "value_corner": 0.835394024848938, "value_row": 0.4605473279953003, "value_any": 0.256985604763031, "value_bot": 0.03936465457081795, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02680.png", "entropy": 0.07003190368413925} +{"ts": "2026-03-20T18:02:10.875169Z", "loop": 2690, "env_steps": 1652736000, "exact_value_avg": 0.4885439872741699, "regret_dist": 0.37503671646118164, "regret_other_env": 0.6248496770858765, "regret_corner": 0.0003172144351992756, "regret_row": 0.3981276750564575, "regret_any": 0.6252032518386841, "regret_bot": 0.8193135261535645, "value_dist": 0.4885439872741699, "value_other_env": 0.2573651969432831, "value_corner": 0.8353121280670166, "value_row": 0.4604988992214203, "value_any": 0.25704729557037354, "value_bot": 0.03931306675076485, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02690.png", "entropy": 0.0709276795387268} +{"ts": "2026-03-20T18:02:19.451353Z", "loop": 2700, "env_steps": 1658880000, "exact_value_avg": 0.48839595913887024, "regret_dist": 0.3751847445964813, "regret_other_env": 0.6249277591705322, "regret_corner": 0.0005701626650989056, "regret_row": 0.398000031709671, "regret_any": 0.6252666711807251, "regret_bot": 0.8204392790794373, "value_dist": 0.48839595913887024, "value_other_env": 0.2572871148586273, "value_corner": 0.8350591659545898, "value_row": 0.4606265723705292, "value_any": 0.2569839060306549, "value_bot": 0.03818736970424652, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02700.png", "entropy": 0.07208546251058578} +{"ts": "2026-03-20T18:02:28.028872Z", "loop": 2710, "env_steps": 1665024000, "exact_value_avg": 0.4876999855041504, "regret_dist": 0.3758806586265564, "regret_other_env": 0.6258939504623413, "regret_corner": 0.0008606811752542853, "regret_row": 0.39821645617485046, "regret_any": 0.6262058615684509, "regret_bot": 0.8281885981559753, "value_dist": 0.4876999855041504, "value_other_env": 0.25632089376449585, "value_corner": 0.8347686529159546, "value_row": 0.4604101777076721, "value_any": 0.2560447156429291, "value_bot": 0.0304380115121603, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02710.png", "entropy": 0.06981285661458969} +{"ts": "2026-03-20T18:02:36.610575Z", "loop": 2720, "env_steps": 1671168000, "exact_value_avg": 0.4845578968524933, "regret_dist": 0.37902283668518066, "regret_other_env": 0.6311783790588379, "regret_corner": 0.0007894382579252124, "regret_row": 0.40555816888809204, "regret_any": 0.6314606666564941, "regret_bot": 0.8372556567192078, "value_dist": 0.4845578968524933, "value_other_env": 0.25103652477264404, "value_corner": 0.834839940071106, "value_row": 0.45306849479675293, "value_any": 0.25078991055488586, "value_bot": 0.02137097343802452, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02720.png", "entropy": 0.06880634278059006} +{"ts": "2026-03-20T18:02:45.187500Z", "loop": 2730, "env_steps": 1677312000, "exact_value_avg": 0.48654183745384216, "regret_dist": 0.3770388662815094, "regret_other_env": 0.6279943585395813, "regret_corner": 0.0006055807461962104, "regret_row": 0.4008021056652069, "regret_any": 0.6282995939254761, "regret_bot": 0.8357080221176147, "value_dist": 0.48654183745384216, "value_other_env": 0.25422051548957825, "value_corner": 0.835023820400238, "value_row": 0.4578244984149933, "value_any": 0.25395095348358154, "value_bot": 0.0229185838252306, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02730.png", "entropy": 0.060487423092126846} +{"ts": "2026-03-20T18:02:53.765742Z", "loop": 2740, "env_steps": 1683456000, "exact_value_avg": 0.48789921402931213, "regret_dist": 0.37568148970603943, "regret_other_env": 0.625910222530365, "regret_corner": 0.00033836514921858907, "regret_row": 0.3982745409011841, "regret_any": 0.6262612342834473, "regret_bot": 0.8286358118057251, "value_dist": 0.48789921402931213, "value_other_env": 0.25630468130111694, "value_corner": 0.8352909684181213, "value_row": 0.4603520929813385, "value_any": 0.2559894323348999, "value_bot": 0.029990749433636665, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02740.png", "entropy": 0.055180132389068604} +{"ts": "2026-03-20T18:03:02.342411Z", "loop": 2750, "env_steps": 1689600000, "exact_value_avg": 0.48828768730163574, "regret_dist": 0.37529298663139343, "regret_other_env": 0.6252257823944092, "regret_corner": 0.0003937562578357756, "regret_row": 0.3982270658016205, "regret_any": 0.6255801916122437, "regret_bot": 0.8224482536315918, "value_dist": 0.48828768730163574, "value_other_env": 0.256989061832428, "value_corner": 0.835235595703125, "value_row": 0.4603995382785797, "value_any": 0.2566704750061035, "value_bot": 0.03617837652564049, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02750.png", "entropy": 0.05560851842164993} +{"ts": "2026-03-20T18:03:10.914140Z", "loop": 2760, "env_steps": 1695744000, "exact_value_avg": 0.48805156350135803, "regret_dist": 0.37552914023399353, "regret_other_env": 0.6257467269897461, "regret_corner": 0.00020273776317480952, "regret_row": 0.3987818658351898, "regret_any": 0.6260952353477478, "regret_bot": 0.8249526023864746, "value_dist": 0.48805156350135803, "value_other_env": 0.2564682066440582, "value_corner": 0.8354265689849854, "value_row": 0.45984476804733276, "value_any": 0.256155401468277, "value_bot": 0.033673979341983795, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02760.png", "entropy": 0.04852912947535515} +{"ts": "2026-03-20T18:03:19.483523Z", "loop": 2770, "env_steps": 1701888000, "exact_value_avg": 0.4863930642604828, "regret_dist": 0.3771875500679016, "regret_other_env": 0.6284709572792053, "regret_corner": 0.0002624402695801109, "regret_row": 0.40566498041152954, "regret_any": 0.6288049817085266, "regret_bot": 0.8336495757102966, "value_dist": 0.4863930642604828, "value_other_env": 0.25374385714530945, "value_corner": 0.8353668451309204, "value_row": 0.45296162366867065, "value_any": 0.2534456253051758, "value_bot": 0.024977032095193863, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02770.png", "entropy": 0.04670167341828346} +{"ts": "2026-03-20T18:03:28.053602Z", "loop": 2780, "env_steps": 1708032000, "exact_value_avg": 0.48836421966552734, "regret_dist": 0.3752165138721466, "regret_other_env": 0.6251707673072815, "regret_corner": 0.00028504084912128747, "regret_row": 0.39819130301475525, "regret_any": 0.6255269646644592, "regret_bot": 0.819782555103302, "value_dist": 0.48836421966552734, "value_other_env": 0.25704410672187805, "value_corner": 0.8353443145751953, "value_row": 0.46043530106544495, "value_any": 0.25672364234924316, "value_bot": 0.03884407877922058, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02780.png", "entropy": 0.05063619837164879} +{"ts": "2026-03-20T18:03:36.625739Z", "loop": 2790, "env_steps": 1714176000, "exact_value_avg": 0.48828065395355225, "regret_dist": 0.3753000497817993, "regret_other_env": 0.6253837943077087, "regret_corner": 0.00017439425573684275, "regret_row": 0.39835646748542786, "regret_any": 0.6257396936416626, "regret_bot": 0.8192523121833801, "value_dist": 0.48828065395355225, "value_other_env": 0.2568311095237732, "value_corner": 0.8354549407958984, "value_row": 0.4602701663970947, "value_any": 0.2565108835697174, "value_bot": 0.039374396204948425, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02790.png", "entropy": 0.056593723595142365} +{"ts": "2026-03-20T18:03:45.198577Z", "loop": 2800, "env_steps": 1720320000, "exact_value_avg": 0.4864240288734436, "regret_dist": 0.37715664505958557, "regret_other_env": 0.6284509301185608, "regret_corner": 0.0002151787339244038, "regret_row": 0.4134589731693268, "regret_any": 0.6288022994995117, "regret_bot": 0.8192387819290161, "value_dist": 0.4864240288734436, "value_other_env": 0.25376394391059875, "value_corner": 0.8354141712188721, "value_row": 0.4451676309108734, "value_any": 0.25344833731651306, "value_bot": 0.03938780725002289, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02800.png", "entropy": 0.054852381348609924} +{"ts": "2026-03-20T18:03:53.773247Z", "loop": 2810, "env_steps": 1726464000, "exact_value_avg": 0.48311129212379456, "regret_dist": 0.38046935200691223, "regret_other_env": 0.6339434385299683, "regret_corner": 0.0002581735607236624, "regret_row": 0.4222840964794159, "regret_any": 0.6342865228652954, "regret_bot": 0.8192735910415649, "value_dist": 0.48311129212379456, "value_other_env": 0.2482713758945465, "value_corner": 0.8353711366653442, "value_row": 0.4363425374031067, "value_any": 0.24796408414840698, "value_bot": 0.03935309872031212, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02810.png", "entropy": 0.05264449864625931} +{"ts": "2026-03-20T18:04:02.343824Z", "loop": 2820, "env_steps": 1732608000, "exact_value_avg": 0.48633331060409546, "regret_dist": 0.3772473931312561, "regret_other_env": 0.628562867641449, "regret_corner": 0.0002741262433119118, "regret_row": 0.41386517882347107, "regret_any": 0.6289139986038208, "regret_bot": 0.8192585706710815, "value_dist": 0.48633331060409546, "value_other_env": 0.25365206599235535, "value_corner": 0.8353551626205444, "value_row": 0.4447614252567291, "value_any": 0.2533366084098816, "value_bot": 0.03936806321144104, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02820.png", "entropy": 0.05648833513259888} +{"ts": "2026-03-20T18:04:10.914458Z", "loop": 2830, "env_steps": 1738752000, "exact_value_avg": 0.48608484864234924, "regret_dist": 0.37749582529067993, "regret_other_env": 0.6290849447250366, "regret_corner": 0.00011215161066502333, "regret_row": 0.40606141090393066, "regret_any": 0.6294352412223816, "regret_bot": 0.8191303610801697, "value_dist": 0.48608484864234924, "value_other_env": 0.2531299293041229, "value_corner": 0.835517168045044, "value_row": 0.4525652229785919, "value_any": 0.2528153359889984, "value_bot": 0.0394962914288044, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02830.png", "entropy": 0.05516868084669113} +{"ts": "2026-03-20T18:04:19.491530Z", "loop": 2840, "env_steps": 1744896000, "exact_value_avg": 0.48787182569503784, "regret_dist": 0.3757089078426361, "regret_other_env": 0.6260225176811218, "regret_corner": 0.00023838183551561087, "regret_row": 0.40037262439727783, "regret_any": 0.6263774037361145, "regret_bot": 0.8192049860954285, "value_dist": 0.48787182569503784, "value_other_env": 0.2561923563480377, "value_corner": 0.8353909850120544, "value_row": 0.45825400948524475, "value_any": 0.2558732032775879, "value_bot": 0.039421726018190384, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02840.png", "entropy": 0.06856545060873032} +{"ts": "2026-03-20T18:04:28.063301Z", "loop": 2850, "env_steps": 1751040000, "exact_value_avg": 0.4885452687740326, "regret_dist": 0.3750354051589966, "regret_other_env": 0.6248743534088135, "regret_corner": 0.0002769634302239865, "regret_row": 0.3979818522930145, "regret_any": 0.6252220869064331, "regret_bot": 0.819242537021637, "value_dist": 0.4885452687740326, "value_other_env": 0.25734052062034607, "value_corner": 0.83535236120224, "value_row": 0.46064478158950806, "value_any": 0.2570284605026245, "value_bot": 0.03938419371843338, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02850.png", "entropy": 0.06352197378873825} +{"ts": "2026-03-20T18:04:36.638211Z", "loop": 2860, "env_steps": 1757184000, "exact_value_avg": 0.4885938763618469, "regret_dist": 0.37498679757118225, "regret_other_env": 0.6248297095298767, "regret_corner": 0.00022236954828258604, "regret_row": 0.39780664443969727, "regret_any": 0.625164270401001, "regret_bot": 0.819275975227356, "value_dist": 0.4885938763618469, "value_other_env": 0.25738516449928284, "value_corner": 0.8354068994522095, "value_row": 0.46081995964050293, "value_any": 0.25708630681037903, "value_bot": 0.039350636303424835, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02860.png", "entropy": 0.059404414147138596} +{"ts": "2026-03-20T18:04:45.215819Z", "loop": 2870, "env_steps": 1763328000, "exact_value_avg": 0.48860496282577515, "regret_dist": 0.3749757409095764, "regret_other_env": 0.6247994303703308, "regret_corner": 0.0002401997771812603, "regret_row": 0.39810827374458313, "regret_any": 0.6251538395881653, "regret_bot": 0.819214940071106, "value_dist": 0.48860496282577515, "value_other_env": 0.2574155032634735, "value_corner": 0.8353891372680664, "value_row": 0.46051838994026184, "value_any": 0.2570967376232147, "value_bot": 0.039411772042512894, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02870.png", "entropy": 0.061539944261312485} +{"ts": "2026-03-20T18:04:53.792978Z", "loop": 2880, "env_steps": 1769472000, "exact_value_avg": 0.48860296607017517, "regret_dist": 0.3749777376651764, "regret_other_env": 0.6247648000717163, "regret_corner": 0.000297152524581179, "regret_row": 0.39813101291656494, "regret_any": 0.6251206994056702, "regret_bot": 0.8191936612129211, "value_dist": 0.48860296607017517, "value_other_env": 0.257450133562088, "value_corner": 0.8353321552276611, "value_row": 0.46049559116363525, "value_any": 0.25712987780570984, "value_bot": 0.03943299502134323, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02880.png", "entropy": 0.0643027201294899} +{"ts": "2026-03-20T18:05:02.364290Z", "loop": 2890, "env_steps": 1775616000, "exact_value_avg": 0.4885944724082947, "regret_dist": 0.3749862015247345, "regret_other_env": 0.6247325539588928, "regret_corner": 0.00036662668571807444, "regret_row": 0.3981555104255676, "regret_any": 0.6250890493392944, "regret_bot": 0.8191556930541992, "value_dist": 0.4885944724082947, "value_other_env": 0.2574823498725891, "value_corner": 0.835262656211853, "value_row": 0.46047112345695496, "value_any": 0.2571614980697632, "value_bot": 0.039470918476581573, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02890.png", "entropy": 0.06626429408788681} +{"ts": "2026-03-20T18:05:10.936220Z", "loop": 2900, "env_steps": 1781760000, "exact_value_avg": 0.488502562046051, "regret_dist": 0.3750781714916229, "regret_other_env": 0.6248112320899963, "regret_corner": 0.00047851703129708767, "regret_row": 0.3980499505996704, "regret_any": 0.6251677870750427, "regret_bot": 0.8190239071846008, "value_dist": 0.488502562046051, "value_other_env": 0.2574036717414856, "value_corner": 0.8351508378982544, "value_row": 0.4605766832828522, "value_any": 0.25708281993865967, "value_bot": 0.03960276395082474, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02900.png", "entropy": 0.07137157768011093} +{"ts": "2026-03-20T18:05:19.509228Z", "loop": 2910, "env_steps": 1787904000, "exact_value_avg": 0.48838597536087036, "regret_dist": 0.3751947283744812, "regret_other_env": 0.625018835067749, "regret_corner": 0.00045851670438423753, "regret_row": 0.39799535274505615, "regret_any": 0.6253752708435059, "regret_bot": 0.8191113471984863, "value_dist": 0.48838597536087036, "value_other_env": 0.2571960389614105, "value_corner": 0.8351708054542542, "value_row": 0.46063128113746643, "value_any": 0.2568753659725189, "value_bot": 0.039515264332294464, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02910.png", "entropy": 0.06580761820077896} +{"ts": "2026-03-20T18:05:28.083934Z", "loop": 2920, "env_steps": 1794048000, "exact_value_avg": 0.48797643184661865, "regret_dist": 0.3756042420864105, "regret_other_env": 0.6256166696548462, "regret_corner": 0.0005855635390616953, "regret_row": 0.399034708738327, "regret_any": 0.6259721517562866, "regret_bot": 0.8191465139389038, "value_dist": 0.48797643184661865, "value_other_env": 0.25659820437431335, "value_corner": 0.8350437879562378, "value_row": 0.45959192514419556, "value_any": 0.2562783658504486, "value_bot": 0.03948015719652176, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02920.png", "entropy": 0.0627649575471878} +{"ts": "2026-03-20T18:05:36.658076Z", "loop": 2930, "env_steps": 1800192000, "exact_value_avg": 0.4876975417137146, "regret_dist": 0.3758831322193146, "regret_other_env": 0.6260066032409668, "regret_corner": 0.000697899900842458, "regret_row": 0.40027233958244324, "regret_any": 0.6263615489006042, "regret_bot": 0.8190475702285767, "value_dist": 0.4876975417137146, "value_other_env": 0.25620830059051514, "value_corner": 0.8349314332008362, "value_row": 0.45835432410240173, "value_any": 0.25588905811309814, "value_bot": 0.03957910090684891, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02930.png", "entropy": 0.06522490084171295} +{"ts": "2026-03-20T18:05:45.233367Z", "loop": 2940, "env_steps": 1806336000, "exact_value_avg": 0.4883681535720825, "regret_dist": 0.37521252036094666, "regret_other_env": 0.624750018119812, "regret_corner": 0.0009062116732820868, "regret_row": 0.3981168568134308, "regret_any": 0.6251068115234375, "regret_bot": 0.81890869140625, "value_dist": 0.4883681535720825, "value_other_env": 0.25746485590934753, "value_corner": 0.8347231149673462, "value_row": 0.4605097770690918, "value_any": 0.2571438252925873, "value_bot": 0.03971802443265915, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02940.png", "entropy": 0.07169191539287567} +{"ts": "2026-03-20T18:05:53.810599Z", "loop": 2950, "env_steps": 1812480000, "exact_value_avg": 0.48825573921203613, "regret_dist": 0.37532490491867065, "regret_other_env": 0.6245337128639221, "regret_corner": 0.0015116111608222127, "regret_row": 0.3983330726623535, "regret_any": 0.6248907446861267, "regret_bot": 0.8186854124069214, "value_dist": 0.48825573921203613, "value_other_env": 0.25768107175827026, "value_corner": 0.8341176509857178, "value_row": 0.4602935314178467, "value_any": 0.2573598325252533, "value_bot": 0.039941128343343735, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02950.png", "entropy": 0.07895548641681671} +{"ts": "2026-03-20T18:06:02.382513Z", "loop": 2960, "env_steps": 1818624000, "exact_value_avg": 0.48871076107025146, "regret_dist": 0.37486985325813293, "regret_other_env": 0.623953640460968, "regret_corner": 0.0012442008592188358, "regret_row": 0.39793047308921814, "regret_any": 0.6243112683296204, "regret_bot": 0.8185750842094421, "value_dist": 0.48871076107025146, "value_other_env": 0.25826123356819153, "value_corner": 0.834385097026825, "value_row": 0.46069613099098206, "value_any": 0.25793930888175964, "value_bot": 0.04005153849720955, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02960.png", "entropy": 0.08175498247146606} +{"ts": "2026-03-20T18:06:10.952490Z", "loop": 2970, "env_steps": 1824768000, "exact_value_avg": 0.48869186639785767, "regret_dist": 0.3748888373374939, "regret_other_env": 0.623819887638092, "regret_corner": 0.0014921691035851836, "regret_row": 0.3979121744632721, "regret_any": 0.6241773962974548, "regret_bot": 0.8185165524482727, "value_dist": 0.48869186639785767, "value_other_env": 0.2583950161933899, "value_corner": 0.8341371417045593, "value_row": 0.4607144892215729, "value_any": 0.25807318091392517, "value_bot": 0.04011005535721779, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02970.png", "entropy": 0.08533115684986115} +{"ts": "2026-03-20T18:06:19.521652Z", "loop": 2980, "env_steps": 1830912000, "exact_value_avg": 0.48852506279945374, "regret_dist": 0.3750556707382202, "regret_other_env": 0.6239376068115234, "regret_corner": 0.00173268374055624, "regret_row": 0.3994885981082916, "regret_any": 0.6242946982383728, "regret_bot": 0.8180911540985107, "value_dist": 0.48852506279945374, "value_other_env": 0.2582772970199585, "value_corner": 0.8338966965675354, "value_row": 0.45913806557655334, "value_any": 0.2579558789730072, "value_bot": 0.04053552448749542, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02980.png", "entropy": 0.09209757298231125} +{"ts": "2026-03-20T18:06:28.094604Z", "loop": 2990, "env_steps": 1837056000, "exact_value_avg": 0.4891164302825928, "regret_dist": 0.3744643032550812, "regret_other_env": 0.6227395534515381, "regret_corner": 0.0020513655617833138, "regret_row": 0.40168389678001404, "regret_any": 0.6230970621109009, "regret_bot": 0.8153834342956543, "value_dist": 0.4891164302825928, "value_other_env": 0.25947532057762146, "value_corner": 0.8335779905319214, "value_row": 0.45694273710250854, "value_any": 0.2591535747051239, "value_bot": 0.04324312508106232, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_02990.png", "entropy": 0.1167159229516983} +{"ts": "2026-03-20T18:06:36.670806Z", "loop": 3000, "env_steps": 1843200000, "exact_value_avg": 0.49097537994384766, "regret_dist": 0.37260526418685913, "regret_other_env": 0.6167793273925781, "regret_corner": 0.006344163324683905, "regret_row": 0.40202608704566956, "regret_any": 0.6171419024467468, "regret_bot": 0.811279833316803, "value_dist": 0.49097537994384766, "value_other_env": 0.2654355764389038, "value_corner": 0.8292850852012634, "value_row": 0.4566005766391754, "value_any": 0.26510870456695557, "value_bot": 0.047346796840429306, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03000.png", "entropy": 0.17781947553157806} +{"ts": "2026-03-20T18:06:45.243077Z", "loop": 3010, "env_steps": 1849344000, "exact_value_avg": 0.4965963661670685, "regret_dist": 0.3669842779636383, "regret_other_env": 0.5945444703102112, "regret_corner": 0.025643931701779366, "regret_row": 0.41072526574134827, "regret_any": 0.594910204410553, "regret_bot": 0.78187096118927, "value_dist": 0.4965963661670685, "value_other_env": 0.2876703441143036, "value_corner": 0.8099853992462158, "value_row": 0.4479013979434967, "value_any": 0.287340372800827, "value_bot": 0.07675568759441376, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03010.png", "entropy": 0.3779566287994385} +{"ts": "2026-03-20T18:06:53.820836Z", "loop": 3020, "env_steps": 1855488000, "exact_value_avg": 0.4999784231185913, "regret_dist": 0.3636021912097931, "regret_other_env": 0.5657928586006165, "regret_corner": 0.06031619757413864, "regret_row": 0.42832639813423157, "regret_any": 0.5661207437515259, "regret_bot": 0.7275581955909729, "value_dist": 0.4999784231185913, "value_other_env": 0.3164219558238983, "value_corner": 0.7753130793571472, "value_row": 0.430300235748291, "value_any": 0.3161298334598541, "value_bot": 0.13106848299503326, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03020.png", "entropy": 0.5344660878181458} +{"ts": "2026-03-20T18:07:02.394703Z", "loop": 3030, "env_steps": 1861632000, "exact_value_avg": 0.5038982033729553, "regret_dist": 0.35968247056007385, "regret_other_env": 0.5634254217147827, "regret_corner": 0.05406804382801056, "regret_row": 0.4245944619178772, "regret_any": 0.5637233853340149, "regret_bot": 0.7296583652496338, "value_dist": 0.5038982033729553, "value_other_env": 0.31878945231437683, "value_corner": 0.7815612554550171, "value_row": 0.4340321719646454, "value_any": 0.3185271918773651, "value_bot": 0.1289682239294052, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03030.png", "entropy": 0.5085973143577576} +{"ts": "2026-03-20T18:07:10.983906Z", "loop": 3040, "env_steps": 1867776000, "exact_value_avg": 0.506295382976532, "regret_dist": 0.3572852611541748, "regret_other_env": 0.5535265803337097, "regret_corner": 0.06292329728603363, "regret_row": 0.43292975425720215, "regret_any": 0.5537140369415283, "regret_bot": 0.7010146379470825, "value_dist": 0.506295382976532, "value_other_env": 0.32868829369544983, "value_corner": 0.7727060317993164, "value_row": 0.42569684982299805, "value_any": 0.32853659987449646, "value_bot": 0.15761201083660126, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03040.png", "entropy": 0.5135068893432617} +{"ts": "2026-03-20T18:07:19.561143Z", "loop": 3050, "env_steps": 1873920000, "exact_value_avg": 0.5080168843269348, "regret_dist": 0.355563759803772, "regret_other_env": 0.5491316318511963, "regret_corner": 0.0652119517326355, "regret_row": 0.43932026624679565, "regret_any": 0.5492291450500488, "regret_bot": 0.6827247738838196, "value_dist": 0.5080168843269348, "value_other_env": 0.33308324217796326, "value_corner": 0.7704173922538757, "value_row": 0.41930633783340454, "value_any": 0.3330214023590088, "value_bot": 0.17590183019638062, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03050.png", "entropy": 0.4893617331981659} +{"ts": "2026-03-20T18:07:28.141095Z", "loop": 3060, "env_steps": 1880064000, "exact_value_avg": 0.5091215372085571, "regret_dist": 0.3544592261314392, "regret_other_env": 0.5544846057891846, "regret_corner": 0.05442115664482117, "regret_row": 0.43723392486572266, "regret_any": 0.5546666979789734, "regret_bot": 0.6987900733947754, "value_dist": 0.5091215372085571, "value_other_env": 0.32773035764694214, "value_corner": 0.7812081575393677, "value_row": 0.4213927090167999, "value_any": 0.3275839388370514, "value_bot": 0.1598365306854248, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03060.png", "entropy": 0.4334161877632141} +{"ts": "2026-03-20T18:07:36.729406Z", "loop": 3070, "env_steps": 1886208000, "exact_value_avg": 0.5142573714256287, "regret_dist": 0.3493233323097229, "regret_other_env": 0.5492795705795288, "regret_corner": 0.04938891902565956, "regret_row": 0.4362136125564575, "regret_any": 0.549361526966095, "regret_bot": 0.6699614524841309, "value_dist": 0.5142573714256287, "value_other_env": 0.33293530344963074, "value_corner": 0.7862403988838196, "value_row": 0.42241302132606506, "value_any": 0.3328891098499298, "value_bot": 0.1886652261018753, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03070.png", "entropy": 0.4747077524662018} +{"ts": "2026-03-20T18:07:45.308781Z", "loop": 3080, "env_steps": 1892352000, "exact_value_avg": 0.5143522620201111, "regret_dist": 0.3492283821105957, "regret_other_env": 0.5398434400558472, "regret_corner": 0.06330583244562149, "regret_row": 0.44444698095321655, "regret_any": 0.5398840308189392, "regret_bot": 0.6573393940925598, "value_dist": 0.5143522620201111, "value_other_env": 0.3423714339733124, "value_corner": 0.7723234295845032, "value_row": 0.41417965292930603, "value_any": 0.3423665761947632, "value_bot": 0.20128720998764038, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03080.png", "entropy": 0.4877026081085205} +{"ts": "2026-03-20T18:07:53.883062Z", "loop": 3090, "env_steps": 1898496000, "exact_value_avg": 0.5198786854743958, "regret_dist": 0.3437019884586334, "regret_other_env": 0.5405476093292236, "regret_corner": 0.048433560878038406, "regret_row": 0.4510948657989502, "regret_any": 0.5406224727630615, "regret_bot": 0.65763920545578, "value_dist": 0.5198786854743958, "value_other_env": 0.3416672646999359, "value_corner": 0.7871957421302795, "value_row": 0.40753182768821716, "value_any": 0.3416281044483185, "value_bot": 0.20098747313022614, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03090.png", "entropy": 0.5008220672607422} +{"ts": "2026-03-20T18:08:02.455562Z", "loop": 3100, "env_steps": 1904640000, "exact_value_avg": 0.5258365869522095, "regret_dist": 0.3377440869808197, "regret_other_env": 0.5262935161590576, "regret_corner": 0.054919954389333725, "regret_row": 0.45519429445266724, "regret_any": 0.5262760519981384, "regret_bot": 0.6150901317596436, "value_dist": 0.5258365869522095, "value_other_env": 0.35592132806777954, "value_corner": 0.7807093858718872, "value_row": 0.40343233942985535, "value_any": 0.35597455501556396, "value_bot": 0.24353653192520142, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03100.png", "entropy": 0.4750809371471405} +{"ts": "2026-03-20T18:08:11.027345Z", "loop": 3110, "env_steps": 1910784000, "exact_value_avg": 0.5300179719924927, "regret_dist": 0.3335627317428589, "regret_other_env": 0.5251709222793579, "regret_corner": 0.04615042358636856, "regret_row": 0.43154987692832947, "regret_any": 0.5252158641815186, "regret_bot": 0.6321433782577515, "value_dist": 0.5300179719924927, "value_other_env": 0.357043981552124, "value_corner": 0.7894788384437561, "value_row": 0.4270767569541931, "value_any": 0.3570347726345062, "value_bot": 0.22648321092128754, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03110.png", "entropy": 0.5059211850166321} +{"ts": "2026-03-20T18:08:19.607797Z", "loop": 3120, "env_steps": 1916928000, "exact_value_avg": 0.5600695610046387, "regret_dist": 0.3035111725330353, "regret_other_env": 0.4750899076461792, "regret_corner": 0.04614298418164253, "regret_row": 0.42059195041656494, "regret_any": 0.47509047389030457, "regret_bot": 0.5074378252029419, "value_dist": 0.5600695610046387, "value_other_env": 0.40712499618530273, "value_corner": 0.7894863486289978, "value_row": 0.43803468346595764, "value_any": 0.4071601331233978, "value_bot": 0.3511888384819031, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03120.png", "entropy": 0.6107602119445801} +{"ts": "2026-03-20T18:08:28.186515Z", "loop": 3130, "env_steps": 1923072000, "exact_value_avg": 0.5891718864440918, "regret_dist": 0.2744087278842926, "regret_other_env": 0.43704432249069214, "regret_corner": 0.03045530430972576, "regret_row": 0.37244704365730286, "regret_any": 0.43713414669036865, "regret_bot": 0.4954981207847595, "value_dist": 0.5891718864440918, "value_other_env": 0.44517049193382263, "value_corner": 0.8051740527153015, "value_row": 0.4861795902252197, "value_any": 0.44511646032333374, "value_bot": 0.36312851309776306, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03130.png", "entropy": 0.6753659248352051} +{"ts": "2026-03-20T18:08:36.762579Z", "loop": 3140, "env_steps": 1929216000, "exact_value_avg": 0.6136319637298584, "regret_dist": 0.24994875490665436, "regret_other_env": 0.39137473702430725, "regret_corner": 0.037809763103723526, "regret_row": 0.3565414547920227, "regret_any": 0.3915278911590576, "regret_bot": 0.4404344856739044, "value_dist": 0.6136319637298584, "value_other_env": 0.49084019660949707, "value_corner": 0.7978195548057556, "value_row": 0.5020851492881775, "value_any": 0.4907227158546448, "value_bot": 0.4181921184062958, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03140.png", "entropy": 0.6733273863792419} +{"ts": "2026-03-20T18:08:45.348039Z", "loop": 3150, "env_steps": 1935360000, "exact_value_avg": 0.6258853673934937, "regret_dist": 0.23769527673721313, "regret_other_env": 0.3691573143005371, "regret_corner": 0.04050222411751747, "regret_row": 0.37195247411727905, "regret_any": 0.3693666458129883, "regret_bot": 0.4197043478488922, "value_dist": 0.6258853673934937, "value_other_env": 0.5130575895309448, "value_corner": 0.7951270341873169, "value_row": 0.48667415976524353, "value_any": 0.5128839612007141, "value_bot": 0.43892228603363037, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03150.png", "entropy": 0.6903534531593323} +{"ts": "2026-03-20T18:08:53.921650Z", "loop": 3160, "env_steps": 1941504000, "exact_value_avg": 0.6502333879470825, "regret_dist": 0.21334728598594666, "regret_other_env": 0.3340012729167938, "regret_corner": 0.03236629441380501, "regret_row": 0.3307848274707794, "regret_any": 0.3341521918773651, "regret_bot": 0.3911975622177124, "value_dist": 0.6502333879470825, "value_other_env": 0.5482136011123657, "value_corner": 0.8032630085945129, "value_row": 0.5278418064117432, "value_any": 0.5480983853340149, "value_bot": 0.4674290418624878, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03160.png", "entropy": 0.6913318634033203} +{"ts": "2026-03-20T18:09:02.500192Z", "loop": 3170, "env_steps": 1947648000, "exact_value_avg": 0.669203519821167, "regret_dist": 0.19437719881534576, "regret_other_env": 0.3020627796649933, "regret_corner": 0.03284883126616478, "regret_row": 0.33661362528800964, "regret_any": 0.30212441086769104, "regret_bot": 0.3439391255378723, "value_dist": 0.669203519821167, "value_other_env": 0.5801520943641663, "value_corner": 0.8027805089950562, "value_row": 0.5220130681991577, "value_any": 0.580126166343689, "value_bot": 0.5146874785423279, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03170.png", "entropy": 0.7004109621047974} +{"ts": "2026-03-20T18:09:11.076705Z", "loop": 3180, "env_steps": 1953792000, "exact_value_avg": 0.696966290473938, "regret_dist": 0.16661450266838074, "regret_other_env": 0.25670233368873596, "regret_corner": 0.03148270770907402, "regret_row": 0.3221743106842041, "regret_any": 0.2566433846950531, "regret_bot": 0.2701281011104584, "value_dist": 0.696966290473938, "value_other_env": 0.6255125999450684, "value_corner": 0.8041466474533081, "value_row": 0.5364523530006409, "value_any": 0.6256071925163269, "value_bot": 0.5884985327720642, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03180.png", "entropy": 0.6680440306663513} +{"ts": "2026-03-20T18:09:19.647879Z", "loop": 3190, "env_steps": 1959936000, "exact_value_avg": 0.7179132699966431, "regret_dist": 0.1456674188375473, "regret_other_env": 0.22176523506641388, "regret_corner": 0.031520694494247437, "regret_row": 0.3135695159435272, "regret_any": 0.22175897657871246, "regret_bot": 0.21786604821681976, "value_dist": 0.7179132699966431, "value_other_env": 0.6604496836662292, "value_corner": 0.8041086196899414, "value_row": 0.5450571179389954, "value_any": 0.6604915857315063, "value_bot": 0.640760600566864, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03190.png", "entropy": 0.6459403038024902} +{"ts": "2026-03-20T18:09:28.223939Z", "loop": 3200, "env_steps": 1966080000, "exact_value_avg": 0.7317428588867188, "regret_dist": 0.1318378746509552, "regret_other_env": 0.2030101716518402, "regret_corner": 0.025079410523176193, "regret_row": 0.26974549889564514, "regret_any": 0.20295384526252747, "regret_bot": 0.20920923352241516, "value_dist": 0.7317428588867188, "value_other_env": 0.6792047619819641, "value_corner": 0.8105499148368835, "value_row": 0.5888811349868774, "value_any": 0.6792967915534973, "value_bot": 0.6494174003601074, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03200.png", "entropy": 0.6489772796630859} +{"ts": "2026-03-20T18:09:36.806743Z", "loop": 3210, "env_steps": 1972224000, "exact_value_avg": 0.7432080507278442, "regret_dist": 0.12037254869937897, "regret_other_env": 0.18534249067306519, "regret_corner": 0.02291763760149479, "regret_row": 0.2610234320163727, "regret_any": 0.185268372297287, "regret_bot": 0.15327134728431702, "value_dist": 0.7432080507278442, "value_other_env": 0.696872353553772, "value_corner": 0.8127116560935974, "value_row": 0.5976031422615051, "value_any": 0.696982204914093, "value_bot": 0.7053552865982056, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03210.png", "entropy": 0.6035515666007996} +{"ts": "2026-03-20T18:09:45.389183Z", "loop": 3220, "env_steps": 1978368000, "exact_value_avg": 0.7588953971862793, "regret_dist": 0.10468529164791107, "regret_other_env": 0.163694828748703, "regret_corner": 0.016170984134078026, "regret_row": 0.24691937863826752, "regret_any": 0.16365830600261688, "regret_bot": 0.14054594933986664, "value_dist": 0.7588953971862793, "value_other_env": 0.7185200452804565, "value_corner": 0.8194583058357239, "value_row": 0.6117072105407715, "value_any": 0.7185922861099243, "value_bot": 0.7180806994438171, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03220.png", "entropy": 0.583213210105896} +{"ts": "2026-03-20T18:09:53.967048Z", "loop": 3230, "env_steps": 1984512000, "exact_value_avg": 0.7657010555267334, "regret_dist": 0.09787961840629578, "regret_other_env": 0.1512245535850525, "regret_corner": 0.017862217500805855, "regret_row": 0.22268426418304443, "regret_any": 0.15122276544570923, "regret_bot": 0.12584258615970612, "value_dist": 0.7657010555267334, "value_other_env": 0.7309902906417847, "value_corner": 0.8177671432495117, "value_row": 0.6359423995018005, "value_any": 0.7310277819633484, "value_bot": 0.7327839732170105, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03230.png", "entropy": 0.5757265090942383} +{"ts": "2026-03-20T18:10:02.546175Z", "loop": 3240, "env_steps": 1990656000, "exact_value_avg": 0.7643884420394897, "regret_dist": 0.09919213503599167, "regret_other_env": 0.15032653510570526, "regret_corner": 0.022490525618195534, "regret_row": 0.22710047662258148, "regret_any": 0.15023711323738098, "regret_bot": 0.1278112381696701, "value_dist": 0.7643884420394897, "value_other_env": 0.7318882942199707, "value_corner": 0.8131387233734131, "value_row": 0.6315261125564575, "value_any": 0.7320135235786438, "value_bot": 0.7308154106140137, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03240.png", "entropy": 0.5454933643341064} +{"ts": "2026-03-20T18:10:11.131030Z", "loop": 3250, "env_steps": 1996800000, "exact_value_avg": 0.7742586135864258, "regret_dist": 0.08932209014892578, "regret_other_env": 0.14163672924041748, "regret_corner": 0.010850124061107635, "regret_row": 0.19013270735740662, "regret_any": 0.14162996411323547, "regret_bot": 0.13800553977489471, "value_dist": 0.7742586135864258, "value_other_env": 0.7405781745910645, "value_corner": 0.824779212474823, "value_row": 0.668493926525116, "value_any": 0.7406206727027893, "value_bot": 0.7206211090087891, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03250.png", "entropy": 0.5085402727127075} +{"ts": "2026-03-20T18:10:19.702347Z", "loop": 3260, "env_steps": 2002944000, "exact_value_avg": 0.7789325714111328, "regret_dist": 0.08464816957712173, "regret_other_env": 0.13107115030288696, "regret_corner": 0.01501367799937725, "regret_row": 0.20564548671245575, "regret_any": 0.13103488087654114, "regret_bot": 0.11739563941955566, "value_dist": 0.7789325714111328, "value_other_env": 0.751143753528595, "value_corner": 0.8206156492233276, "value_row": 0.6529811024665833, "value_any": 0.7512157559394836, "value_bot": 0.7412309646606445, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03260.png", "entropy": 0.518991231918335} +{"ts": "2026-03-20T18:10:28.274303Z", "loop": 3270, "env_steps": 2009088000, "exact_value_avg": 0.7847242951393127, "regret_dist": 0.07885639369487762, "regret_other_env": 0.12381144613027573, "regret_corner": 0.011423804797232151, "regret_row": 0.19616307318210602, "regret_any": 0.12385079264640808, "regret_bot": 0.0831536129117012, "value_dist": 0.7847242951393127, "value_other_env": 0.7584034204483032, "value_corner": 0.8242055773735046, "value_row": 0.6624635457992554, "value_any": 0.7583997845649719, "value_bot": 0.7754729986190796, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03270.png", "entropy": 0.4897244870662689} +{"ts": "2026-03-20T18:10:36.846807Z", "loop": 3280, "env_steps": 2015232000, "exact_value_avg": 0.7929871082305908, "regret_dist": 0.07059357315301895, "regret_other_env": 0.1108536496758461, "regret_corner": 0.010203463025391102, "regret_row": 0.13885565102100372, "regret_any": 0.11090954393148422, "regret_bot": 0.09714548289775848, "value_dist": 0.7929871082305908, "value_other_env": 0.771361231803894, "value_corner": 0.8254258632659912, "value_row": 0.7197710275650024, "value_any": 0.77134108543396, "value_bot": 0.7614811658859253, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03280.png", "entropy": 0.5087944865226746} +{"ts": "2026-03-20T18:10:45.422965Z", "loop": 3290, "env_steps": 2021376000, "exact_value_avg": 0.7968162298202515, "regret_dist": 0.06676443666219711, "regret_other_env": 0.10404615849256516, "regret_corner": 0.010841847397387028, "regret_row": 0.203491672873497, "regret_any": 0.10404279828071594, "regret_bot": 0.06233057379722595, "value_dist": 0.7968162298202515, "value_other_env": 0.7781687378883362, "value_corner": 0.824787437915802, "value_row": 0.6551349759101868, "value_any": 0.7782077789306641, "value_bot": 0.7962960600852966, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03290.png", "entropy": 0.49131473898887634} +{"ts": "2026-03-20T18:10:54.006085Z", "loop": 3300, "env_steps": 2027520000, "exact_value_avg": 0.8018426299095154, "regret_dist": 0.061738040298223495, "regret_other_env": 0.09765902161598206, "regret_corner": 0.007856559939682484, "regret_row": 0.14885634183883667, "regret_any": 0.0977218970656395, "regret_bot": 0.06531133502721786, "value_dist": 0.8018426299095154, "value_other_env": 0.7845558524131775, "value_corner": 0.8277727365493774, "value_row": 0.7097702622413635, "value_any": 0.7845286130905151, "value_bot": 0.7933153510093689, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03300.png", "entropy": 0.45521700382232666} +{"ts": "2026-03-20T18:11:02.585066Z", "loop": 3310, "env_steps": 2033664000, "exact_value_avg": 0.8072550296783447, "regret_dist": 0.056325674057006836, "regret_other_env": 0.08859765529632568, "regret_corner": 0.007917693816125393, "regret_row": 0.15932725369930267, "regret_any": 0.08869017660617828, "regret_bot": 0.07354697585105896, "value_dist": 0.8072550296783447, "value_other_env": 0.7936172485351562, "value_corner": 0.8277116417884827, "value_row": 0.6992993950843811, "value_any": 0.7935605049133301, "value_bot": 0.7850796580314636, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03310.png", "entropy": 0.46945276856422424} +{"ts": "2026-03-20T18:11:11.167813Z", "loop": 3320, "env_steps": 2039808000, "exact_value_avg": 0.8083690404891968, "regret_dist": 0.055211666971445084, "regret_other_env": 0.08605159819126129, "regret_corner": 0.008951757103204727, "regret_row": 0.14893656969070435, "regret_any": 0.08604834228754044, "regret_bot": 0.057042449712753296, "value_dist": 0.8083690404891968, "value_other_env": 0.7961632609367371, "value_corner": 0.8266776204109192, "value_row": 0.7096900343894958, "value_any": 0.7962022423744202, "value_bot": 0.8015841841697693, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03320.png", "entropy": 0.45675739645957947} +{"ts": "2026-03-20T18:11:19.744050Z", "loop": 3330, "env_steps": 2045952000, "exact_value_avg": 0.8076468110084534, "regret_dist": 0.055933915078639984, "regret_other_env": 0.08712951093912125, "regret_corner": 0.009140513837337494, "regret_row": 0.14726901054382324, "regret_any": 0.08715386688709259, "regret_bot": 0.05671276897192001, "value_dist": 0.8076468110084534, "value_other_env": 0.7950854301452637, "value_corner": 0.8264887928962708, "value_row": 0.711357593536377, "value_any": 0.7950966954231262, "value_bot": 0.8019139170646667, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03330.png", "entropy": 0.43391093611717224} +{"ts": "2026-03-20T18:11:28.324689Z", "loop": 3340, "env_steps": 2052096000, "exact_value_avg": 0.8145650029182434, "regret_dist": 0.049015697091817856, "regret_other_env": 0.07464820891618729, "regret_corner": 0.010566921904683113, "regret_row": 0.1347649097442627, "regret_any": 0.07468606531620026, "regret_bot": 0.04469507187604904, "value_dist": 0.8145650029182434, "value_other_env": 0.8075666427612305, "value_corner": 0.8250624537467957, "value_row": 0.7238617539405823, "value_any": 0.8075645565986633, "value_bot": 0.8139315247535706, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03340.png", "entropy": 0.4478348195552826} +{"ts": "2026-03-20T18:11:36.898777Z", "loop": 3350, "env_steps": 2058240000, "exact_value_avg": 0.8196989297866821, "regret_dist": 0.04388173669576645, "regret_other_env": 0.06890257447957993, "regret_corner": 0.0063504730351269245, "regret_row": 0.13936592638492584, "regret_any": 0.06898217648267746, "regret_bot": 0.04740632697939873, "value_dist": 0.8196989297866821, "value_other_env": 0.813312292098999, "value_corner": 0.8292788863182068, "value_row": 0.7192606925964355, "value_any": 0.8132684230804443, "value_bot": 0.8112202882766724, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03350.png", "entropy": 0.42566224932670593} +{"ts": "2026-03-20T18:11:45.478023Z", "loop": 3360, "env_steps": 2064384000, "exact_value_avg": 0.8213365077972412, "regret_dist": 0.04224422574043274, "regret_other_env": 0.0667772963643074, "regret_corner": 0.005444612354040146, "regret_row": 0.13693305850028992, "regret_any": 0.06680190563201904, "regret_bot": 0.053646814078092575, "value_dist": 0.8213365077972412, "value_other_env": 0.8154376149177551, "value_corner": 0.8301846981048584, "value_row": 0.7216935157775879, "value_any": 0.8154487013816833, "value_bot": 0.8049798011779785, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03360.png", "entropy": 0.42281579971313477} +{"ts": "2026-03-20T18:11:54.051955Z", "loop": 3370, "env_steps": 2070528000, "exact_value_avg": 0.8222929239273071, "regret_dist": 0.04128770902752876, "regret_other_env": 0.06577624380588531, "regret_corner": 0.004554901737719774, "regret_row": 0.09358938038349152, "regret_any": 0.06584873050451279, "regret_bot": 0.07026615738868713, "value_dist": 0.8222929239273071, "value_other_env": 0.816438615322113, "value_corner": 0.8310744166374207, "value_row": 0.7650372385978699, "value_any": 0.8164018392562866, "value_bot": 0.7883604764938354, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03370.png", "entropy": 0.40212351083755493} +{"ts": "2026-03-20T18:12:02.632760Z", "loop": 3380, "env_steps": 2076672000, "exact_value_avg": 0.8241164088249207, "regret_dist": 0.03946429491043091, "regret_other_env": 0.06258045136928558, "regret_corner": 0.004790057428181171, "regret_row": 0.11296140402555466, "regret_any": 0.0625782236456871, "regret_bot": 0.04308019205927849, "value_dist": 0.8241164088249207, "value_other_env": 0.8196344375610352, "value_corner": 0.8308393359184265, "value_row": 0.7456652522087097, "value_any": 0.8196724057197571, "value_bot": 0.815546452999115, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03380.png", "entropy": 0.38102683424949646} +{"ts": "2026-03-20T18:12:11.217953Z", "loop": 3390, "env_steps": 2082816000, "exact_value_avg": 0.8273727297782898, "regret_dist": 0.036207977682352066, "regret_other_env": 0.056307170540094376, "regret_corner": 0.0060591804794967175, "regret_row": 0.10702867805957794, "regret_any": 0.05631353333592415, "regret_bot": 0.03793105483055115, "value_dist": 0.8273727297782898, "value_other_env": 0.8259077072143555, "value_corner": 0.8295701742172241, "value_row": 0.7515980005264282, "value_any": 0.8259370923042297, "value_bot": 0.8206955194473267, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03390.png", "entropy": 0.38848477602005005} +{"ts": "2026-03-20T18:12:19.795811Z", "loop": 3400, "env_steps": 2088960000, "exact_value_avg": 0.8245540261268616, "regret_dist": 0.03902669623494148, "regret_other_env": 0.06288033723831177, "regret_corner": 0.0032462275121361017, "regret_row": 0.08095041662454605, "regret_any": 0.06293661147356033, "regret_bot": 0.0525662936270237, "value_dist": 0.8245540261268616, "value_other_env": 0.8193345665931702, "value_corner": 0.8323831558227539, "value_row": 0.7776762843132019, "value_any": 0.8193140625953674, "value_bot": 0.8060603737831116, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03400.png", "entropy": 0.37020012736320496} +{"ts": "2026-03-20T18:12:28.377404Z", "loop": 3410, "env_steps": 2095104000, "exact_value_avg": 0.8245158195495605, "regret_dist": 0.03906489536166191, "regret_other_env": 0.06300204247236252, "regret_corner": 0.003159163985401392, "regret_row": 0.10175769031047821, "regret_any": 0.06320194900035858, "regret_bot": 0.07108814269304276, "value_dist": 0.8245158195495605, "value_other_env": 0.8192128539085388, "value_corner": 0.832470178604126, "value_row": 0.7568688988685608, "value_any": 0.8190486431121826, "value_bot": 0.787538468837738, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03410.png", "entropy": 0.3796950578689575} +{"ts": "2026-03-20T18:12:36.958439Z", "loop": 3420, "env_steps": 2101248000, "exact_value_avg": 0.8325892686843872, "regret_dist": 0.03099149279296398, "regret_other_env": 0.04949233680963516, "regret_corner": 0.003240225836634636, "regret_row": 0.09945850819349289, "regret_any": 0.049519941210746765, "regret_bot": 0.04464449733495712, "value_dist": 0.8325892686843872, "value_other_env": 0.8327226042747498, "value_corner": 0.8323891162872314, "value_row": 0.7591680884361267, "value_any": 0.8327306509017944, "value_bot": 0.8139821290969849, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03420.png", "entropy": 0.36950379610061646} +{"ts": "2026-03-20T18:12:45.543040Z", "loop": 3430, "env_steps": 2107392000, "exact_value_avg": 0.82635098695755, "regret_dist": 0.0372297540307045, "regret_other_env": 0.05872068554162979, "regret_corner": 0.004993351176381111, "regret_row": 0.10305074602365494, "regret_any": 0.058715030550956726, "regret_bot": 0.0440497100353241, "value_dist": 0.82635098695755, "value_other_env": 0.8234942555427551, "value_corner": 0.8306360244750977, "value_row": 0.7555758357048035, "value_any": 0.8235355615615845, "value_bot": 0.8145769238471985, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03430.png", "entropy": 0.3567768335342407} +{"ts": "2026-03-20T18:12:54.126833Z", "loop": 3440, "env_steps": 2113536000, "exact_value_avg": 0.8371857404708862, "regret_dist": 0.02639492228627205, "regret_other_env": 0.04186130687594414, "regret_corner": 0.003195343539118767, "regret_row": 0.07464674860239029, "regret_any": 0.0418962724506855, "regret_bot": 0.030403176322579384, "value_dist": 0.8371857404708862, "value_other_env": 0.8403534889221191, "value_corner": 0.8324339985847473, "value_row": 0.7839798927307129, "value_any": 0.8403542637825012, "value_bot": 0.828223466873169, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03440.png", "entropy": 0.35934287309646606} +{"ts": "2026-03-20T18:13:02.706457Z", "loop": 3450, "env_steps": 2119680000, "exact_value_avg": 0.8357675075531006, "regret_dist": 0.027813266962766647, "regret_other_env": 0.04469342902302742, "regret_corner": 0.002493019914254546, "regret_row": 0.10683716088533401, "regret_any": 0.044774409383535385, "regret_bot": 0.03564425930380821, "value_dist": 0.8357675075531006, "value_other_env": 0.837521493434906, "value_corner": 0.8331363201141357, "value_row": 0.7517894506454468, "value_any": 0.8374761343002319, "value_bot": 0.8229823112487793, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03450.png", "entropy": 0.35229775309562683} +{"ts": "2026-03-20T18:13:11.292227Z", "loop": 3460, "env_steps": 2125824000, "exact_value_avg": 0.8388363122940063, "regret_dist": 0.024744374677538872, "regret_other_env": 0.03911878541111946, "regret_corner": 0.0031827581115067005, "regret_row": 0.07137618213891983, "regret_any": 0.03918558731675148, "regret_bot": 0.02955552563071251, "value_dist": 0.8388363122940063, "value_other_env": 0.8430960774421692, "value_corner": 0.8324465751647949, "value_row": 0.7872504591941833, "value_any": 0.8430649638175964, "value_bot": 0.829071044921875, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03460.png", "entropy": 0.3463561236858368} +{"ts": "2026-03-20T18:13:19.869796Z", "loop": 3470, "env_steps": 2131968000, "exact_value_avg": 0.8346718549728394, "regret_dist": 0.02890879102051258, "regret_other_env": 0.04387788474559784, "regret_corner": 0.006455145310610533, "regret_row": 0.09328412264585495, "regret_any": 0.04390711337327957, "regret_bot": 0.021133549511432648, "value_dist": 0.8346718549728394, "value_other_env": 0.8383370041847229, "value_corner": 0.8291741609573364, "value_row": 0.7653425335884094, "value_any": 0.8383435010910034, "value_bot": 0.8374931216239929, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03470.png", "entropy": 0.3476901054382324} +{"ts": "2026-03-20T18:13:28.446554Z", "loop": 3480, "env_steps": 2138112000, "exact_value_avg": 0.8379524350166321, "regret_dist": 0.025628212839365005, "regret_other_env": 0.03919472172856331, "regret_corner": 0.005278449039906263, "regret_row": 0.08909432590007782, "regret_any": 0.039239898324012756, "regret_bot": 0.019290698692202568, "value_dist": 0.8379524350166321, "value_other_env": 0.8430200815200806, "value_corner": 0.830350935459137, "value_row": 0.769532322883606, "value_any": 0.8430107235908508, "value_bot": 0.8393359184265137, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03480.png", "entropy": 0.34210121631622314} +{"ts": "2026-03-20T18:13:37.026769Z", "loop": 3490, "env_steps": 2144256000, "exact_value_avg": 0.8356762528419495, "regret_dist": 0.02790442667901516, "regret_other_env": 0.043249599635601044, "regret_corner": 0.004886662121862173, "regret_row": 0.11784372478723526, "regret_any": 0.04332463815808296, "regret_bot": 0.021870329976081848, "value_dist": 0.8356762528419495, "value_other_env": 0.8389652371406555, "value_corner": 0.8307427167892456, "value_row": 0.7407829165458679, "value_any": 0.8389260172843933, "value_bot": 0.8367562890052795, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03490.png", "entropy": 0.3508788049221039} +{"ts": "2026-03-20T18:13:45.604667Z", "loop": 3500, "env_steps": 2150400000, "exact_value_avg": 0.8330589532852173, "regret_dist": 0.03052169643342495, "regret_other_env": 0.04707307368516922, "regret_corner": 0.005694625899195671, "regret_row": 0.10935860127210617, "regret_any": 0.04704217612743378, "regret_bot": 0.034384582191705704, "value_dist": 0.8330589532852173, "value_other_env": 0.8351418375968933, "value_corner": 0.8299346566200256, "value_row": 0.7492679953575134, "value_any": 0.8352084755897522, "value_bot": 0.8242420554161072, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03500.png", "entropy": 0.3383086323738098} +{"ts": "2026-03-20T18:13:54.182030Z", "loop": 3510, "env_steps": 2156544000, "exact_value_avg": 0.8406501412391663, "regret_dist": 0.022930508479475975, "regret_other_env": 0.03688240796327591, "regret_corner": 0.002002654131501913, "regret_row": 0.046290937811136246, "regret_any": 0.03696855530142784, "regret_bot": 0.03493240848183632, "value_dist": 0.8406501412391663, "value_other_env": 0.8453324437141418, "value_corner": 0.8336266875267029, "value_row": 0.812335729598999, "value_any": 0.8452820777893066, "value_bot": 0.8236942887306213, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03510.png", "entropy": 0.3377566635608673} +{"ts": "2026-03-20T18:14:02.756582Z", "loop": 3520, "env_steps": 2162688000, "exact_value_avg": 0.8419393301010132, "regret_dist": 0.021641336381435394, "regret_other_env": 0.03463128209114075, "regret_corner": 0.002156415255740285, "regret_row": 0.05156523734331131, "regret_any": 0.03468656912446022, "regret_bot": 0.03369567543268204, "value_dist": 0.8419393301010132, "value_other_env": 0.8475835919380188, "value_corner": 0.8334729075431824, "value_row": 0.8070613741874695, "value_any": 0.8475639820098877, "value_bot": 0.8249309659004211, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03520.png", "entropy": 0.3272027373313904} +{"ts": "2026-03-20T18:14:11.336428Z", "loop": 3530, "env_steps": 2168832000, "exact_value_avg": 0.8435705900192261, "regret_dist": 0.020010054111480713, "regret_other_env": 0.03213519603013992, "regret_corner": 0.0018223380902782083, "regret_row": 0.07041717320680618, "regret_any": 0.03213935345411301, "regret_bot": 0.020920122042298317, "value_dist": 0.8435705900192261, "value_other_env": 0.8500796556472778, "value_corner": 0.8338069915771484, "value_row": 0.7882094383239746, "value_any": 0.8501112461090088, "value_bot": 0.8377065658569336, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03530.png", "entropy": 0.31555482745170593} +{"ts": "2026-03-20T18:14:19.911825Z", "loop": 3540, "env_steps": 2174976000, "exact_value_avg": 0.8419119119644165, "regret_dist": 0.02166878618299961, "regret_other_env": 0.03546789661049843, "regret_corner": 0.0009701153030619025, "regret_row": 0.04859539121389389, "regret_any": 0.035469770431518555, "regret_bot": 0.032613251358270645, "value_dist": 0.8419119119644165, "value_other_env": 0.8467469811439514, "value_corner": 0.834659218788147, "value_row": 0.8100312948226929, "value_any": 0.8467808961868286, "value_bot": 0.826013445854187, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03540.png", "entropy": 0.3075660169124603} +{"ts": "2026-03-20T18:14:28.486626Z", "loop": 3550, "env_steps": 2181120000, "exact_value_avg": 0.842006266117096, "regret_dist": 0.021574389189481735, "regret_other_env": 0.033065542578697205, "regret_corner": 0.004337657243013382, "regret_row": 0.04668116569519043, "regret_any": 0.03316275402903557, "regret_bot": 0.03684842959046364, "value_dist": 0.842006266117096, "value_other_env": 0.8491492867469788, "value_corner": 0.831291675567627, "value_row": 0.8119454979896545, "value_any": 0.8490878343582153, "value_bot": 0.8217781782150269, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03550.png", "entropy": 0.3274538516998291} +{"ts": "2026-03-20T18:14:37.069399Z", "loop": 3560, "env_steps": 2187264000, "exact_value_avg": 0.8430577516555786, "regret_dist": 0.02052290551364422, "regret_other_env": 0.03273872658610344, "regret_corner": 0.0021991741377860308, "regret_row": 0.05108458548784256, "regret_any": 0.03275851160287857, "regret_bot": 0.018340278416872025, "value_dist": 0.8430577516555786, "value_other_env": 0.849476158618927, "value_corner": 0.8334301710128784, "value_row": 0.807542085647583, "value_any": 0.8494921326637268, "value_bot": 0.8402863144874573, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03560.png", "entropy": 0.3082229495048523} +{"ts": "2026-03-20T18:14:45.643180Z", "loop": 3570, "env_steps": 2193408000, "exact_value_avg": 0.8458333611488342, "regret_dist": 0.017747322097420692, "regret_other_env": 0.028371192514896393, "regret_corner": 0.0018115174025297165, "regret_row": 0.06230359897017479, "regret_any": 0.028443442657589912, "regret_bot": 0.019270287826657295, "value_dist": 0.8458333611488342, "value_other_env": 0.853843629360199, "value_corner": 0.8338178396224976, "value_row": 0.7963230609893799, "value_any": 0.8538071513175964, "value_bot": 0.8393563628196716, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03570.png", "entropy": 0.30766013264656067} +{"ts": "2026-03-20T18:14:54.218915Z", "loop": 3580, "env_steps": 2199552000, "exact_value_avg": 0.847855806350708, "regret_dist": 0.015724914148449898, "regret_other_env": 0.024890748783946037, "regret_corner": 0.0019761607982218266, "regret_row": 0.04582960903644562, "regret_any": 0.024915063753724098, "regret_bot": 0.01519324816763401, "value_dist": 0.847855806350708, "value_other_env": 0.8573241233825684, "value_corner": 0.8336531519889832, "value_row": 0.8127970099449158, "value_any": 0.8573355674743652, "value_bot": 0.8434333205223083, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03580.png", "entropy": 0.3108326494693756} +{"ts": "2026-03-20T18:15:02.795223Z", "loop": 3590, "env_steps": 2205696000, "exact_value_avg": 0.8464950323104858, "regret_dist": 0.017085669562220573, "regret_other_env": 0.026768676936626434, "regret_corner": 0.00256115454249084, "regret_row": 0.03985991328954697, "regret_any": 0.0267711840569973, "regret_bot": 0.018375331535935402, "value_dist": 0.8464950323104858, "value_other_env": 0.8554462194442749, "value_corner": 0.8330681920051575, "value_row": 0.818766713142395, "value_any": 0.8554794192314148, "value_bot": 0.8402512669563293, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03590.png", "entropy": 0.3053050637245178} +{"ts": "2026-03-20T18:15:11.365683Z", "loop": 3600, "env_steps": 2211840000, "exact_value_avg": 0.8486111164093018, "regret_dist": 0.014969583600759506, "regret_other_env": 0.024087516590952873, "regret_corner": 0.0012926827184855938, "regret_row": 0.0290647204965353, "regret_any": 0.024107173085212708, "regret_bot": 0.022850772365927696, "value_dist": 0.8486111164093018, "value_other_env": 0.8581273555755615, "value_corner": 0.8343366384506226, "value_row": 0.8295618891716003, "value_any": 0.8581434488296509, "value_bot": 0.8357758522033691, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03600.png", "entropy": 0.29048842191696167} +{"ts": "2026-03-20T18:15:19.948434Z", "loop": 3610, "env_steps": 2217984000, "exact_value_avg": 0.8491820693016052, "regret_dist": 0.014398603700101376, "regret_other_env": 0.022747209295630455, "regret_corner": 0.001875692163594067, "regret_row": 0.03202344477176666, "regret_any": 0.0227805282920599, "regret_bot": 0.0204258244484663, "value_dist": 0.8491820693016052, "value_other_env": 0.8594676852226257, "value_corner": 0.8337536454200745, "value_row": 0.8266031742095947, "value_any": 0.8594700694084167, "value_bot": 0.8382008671760559, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03610.png", "entropy": 0.2881737947463989} +{"ts": "2026-03-20T18:15:28.526843Z", "loop": 3620, "env_steps": 2224128000, "exact_value_avg": 0.8486701250076294, "regret_dist": 0.014910592697560787, "regret_other_env": 0.023846089839935303, "regret_corner": 0.001507344888523221, "regret_row": 0.03402115777134895, "regret_any": 0.02386045642197132, "regret_bot": 0.017717253416776657, "value_dist": 0.8486701250076294, "value_other_env": 0.8583688139915466, "value_corner": 0.8341220021247864, "value_row": 0.8246054649353027, "value_any": 0.8583901524543762, "value_bot": 0.8409094214439392, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03620.png", "entropy": 0.2724311947822571} +{"ts": "2026-03-20T18:15:37.102871Z", "loop": 3630, "env_steps": 2230272000, "exact_value_avg": 0.8488099575042725, "regret_dist": 0.0147707499563694, "regret_other_env": 0.024249250069260597, "regret_corner": 0.0005529994959942997, "regret_row": 0.03130872920155525, "regret_any": 0.024284377694129944, "regret_bot": 0.02210422232747078, "value_dist": 0.8488099575042725, "value_other_env": 0.8579655885696411, "value_corner": 0.8350763916969299, "value_row": 0.8273178339004517, "value_any": 0.8579661846160889, "value_bot": 0.8365224003791809, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03630.png", "entropy": 0.26712000370025635} +{"ts": "2026-03-20T18:15:45.681843Z", "loop": 3640, "env_steps": 2236416000, "exact_value_avg": 0.8510186672210693, "regret_dist": 0.012562040239572525, "regret_other_env": 0.020299438387155533, "regret_corner": 0.0009559428435750306, "regret_row": 0.02895922213792801, "regret_any": 0.020333683118224144, "regret_bot": 0.015755383297801018, "value_dist": 0.8510186672210693, "value_other_env": 0.8619154691696167, "value_corner": 0.8346734046936035, "value_row": 0.8296673893928528, "value_any": 0.8619168996810913, "value_bot": 0.8428712487220764, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03640.png", "entropy": 0.2725902795791626} +{"ts": "2026-03-20T18:15:54.261965Z", "loop": 3650, "env_steps": 2242560000, "exact_value_avg": 0.8488085269927979, "regret_dist": 0.014772135764360428, "regret_other_env": 0.023259172216057777, "regret_corner": 0.0020415803883224726, "regret_row": 0.03054770827293396, "regret_any": 0.023287035524845123, "regret_bot": 0.02599131502211094, "value_dist": 0.8488085269927979, "value_other_env": 0.8589556813240051, "value_corner": 0.8335877060890198, "value_row": 0.8280789256095886, "value_any": 0.8589635491371155, "value_bot": 0.8326354026794434, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03650.png", "entropy": 0.2759287357330322} +{"ts": "2026-03-20T18:16:02.839471Z", "loop": 3660, "env_steps": 2248704000, "exact_value_avg": 0.8509831428527832, "regret_dist": 0.012597563676536083, "regret_other_env": 0.020554352551698685, "regret_corner": 0.0006623810040764511, "regret_row": 0.024684812873601913, "regret_any": 0.020591942593455315, "regret_bot": 0.018946964293718338, "value_dist": 0.8509831428527832, "value_other_env": 0.8616604804992676, "value_corner": 0.8349669575691223, "value_row": 0.8339418172836304, "value_any": 0.8616586327552795, "value_bot": 0.8396796584129333, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03660.png", "entropy": 0.2658070921897888} +{"ts": "2026-03-20T18:16:11.421718Z", "loop": 3670, "env_steps": 2254848000, "exact_value_avg": 0.8519129753112793, "regret_dist": 0.011667675338685513, "regret_other_env": 0.018769821152091026, "regret_corner": 0.0010144537081941962, "regret_row": 0.03146926313638687, "regret_any": 0.01879563182592392, "regret_bot": 0.008750341832637787, "value_dist": 0.8519129753112793, "value_other_env": 0.8634450435638428, "value_corner": 0.8346148729324341, "value_row": 0.8271573185920715, "value_any": 0.8634549379348755, "value_bot": 0.8498762249946594, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03670.png", "entropy": 0.26421526074409485} +{"ts": "2026-03-20T18:16:20.001764Z", "loop": 3680, "env_steps": 2260992000, "exact_value_avg": 0.8517826199531555, "regret_dist": 0.011798067949712276, "regret_other_env": 0.019265243783593178, "regret_corner": 0.0005973041406832635, "regret_row": 0.027008937671780586, "regret_any": 0.019317984580993652, "regret_bot": 0.0166571494191885, "value_dist": 0.8517826199531555, "value_other_env": 0.8629496097564697, "value_corner": 0.8350319862365723, "value_row": 0.8316176533699036, "value_any": 0.8629326224327087, "value_bot": 0.8419694304466248, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03680.png", "entropy": 0.2615574896335602} +{"ts": "2026-03-20T18:16:28.575865Z", "loop": 3690, "env_steps": 2267136000, "exact_value_avg": 0.8515876531600952, "regret_dist": 0.011992995627224445, "regret_other_env": 0.01940944977104664, "regret_corner": 0.0008683150517754257, "regret_row": 0.025797778740525246, "regret_any": 0.01945382170379162, "regret_bot": 0.019876576960086823, "value_dist": 0.8515876531600952, "value_other_env": 0.8628054261207581, "value_corner": 0.8347610235214233, "value_row": 0.832828938961029, "value_any": 0.8627967834472656, "value_bot": 0.8387500643730164, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03690.png", "entropy": 0.255433052778244} +{"ts": "2026-03-20T18:16:37.151510Z", "loop": 3700, "env_steps": 2273280000, "exact_value_avg": 0.8535110950469971, "regret_dist": 0.010069583542644978, "regret_other_env": 0.016019053757190704, "regret_corner": 0.0011453772895038128, "regret_row": 0.020417330786585808, "regret_any": 0.01604112610220909, "regret_bot": 0.014533646404743195, "value_dist": 0.8535110950469971, "value_other_env": 0.8661958575248718, "value_corner": 0.8344840407371521, "value_row": 0.8382092714309692, "value_any": 0.8662095069885254, "value_bot": 0.8440929651260376, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03700.png", "entropy": 0.25768229365348816} +{"ts": "2026-03-20T18:16:45.726725Z", "loop": 3710, "env_steps": 2279424000, "exact_value_avg": 0.852216362953186, "regret_dist": 0.011364289559423923, "regret_other_env": 0.018616842105984688, "regret_corner": 0.00048545998288318515, "regret_row": 0.023132268339395523, "regret_any": 0.01864941604435444, "regret_bot": 0.021711736917495728, "value_dist": 0.852216362953186, "value_other_env": 0.8635980486869812, "value_corner": 0.8351438045501709, "value_row": 0.8354943990707397, "value_any": 0.8636011481285095, "value_bot": 0.8369149565696716, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03710.png", "entropy": 0.24864105880260468} +{"ts": "2026-03-20T18:16:54.304542Z", "loop": 3720, "env_steps": 2285568000, "exact_value_avg": 0.8529711961746216, "regret_dist": 0.010609538294374943, "regret_other_env": 0.016134414821863174, "regret_corner": 0.0023222235031425953, "regret_row": 0.027096157893538475, "regret_any": 0.0161577258259058, "regret_bot": 0.010722547769546509, "value_dist": 0.8529711961746216, "value_other_env": 0.8660804629325867, "value_corner": 0.833307147026062, "value_row": 0.8315305709838867, "value_any": 0.8660928606987, "value_bot": 0.8479040861129761, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03720.png", "entropy": 0.26203110814094543} +{"ts": "2026-03-20T18:17:02.880514Z", "loop": 3730, "env_steps": 2291712000, "exact_value_avg": 0.8535753488540649, "regret_dist": 0.010005306452512741, "regret_other_env": 0.01621135324239731, "regret_corner": 0.0006962354527786374, "regret_row": 0.01904069446027279, "regret_any": 0.016248997300863266, "regret_bot": 0.010811851359903812, "value_dist": 0.8535753488540649, "value_other_env": 0.8660034537315369, "value_corner": 0.8349331617355347, "value_row": 0.8395859003067017, "value_any": 0.8660016059875488, "value_bot": 0.8478147387504578, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03730.png", "entropy": 0.2521117329597473} +{"ts": "2026-03-20T18:17:11.457903Z", "loop": 3740, "env_steps": 2297856000, "exact_value_avg": 0.8525732755661011, "regret_dist": 0.011007453314960003, "regret_other_env": 0.017966261133551598, "regret_corner": 0.0005692397826351225, "regret_row": 0.034867677837610245, "regret_any": 0.017979703843593597, "regret_bot": 0.012121140956878662, "value_dist": 0.8525732755661011, "value_other_env": 0.8642486333847046, "value_corner": 0.8350601196289062, "value_row": 0.8237589001655579, "value_any": 0.8642708659172058, "value_bot": 0.8465054035186768, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03740.png", "entropy": 0.24117638170719147} +{"ts": "2026-03-20T18:17:20.030367Z", "loop": 3750, "env_steps": 2304000000, "exact_value_avg": 0.8481576442718506, "regret_dist": 0.015423067845404148, "regret_other_env": 0.025077270343899727, "regret_corner": 0.0009417623514309525, "regret_row": 0.049618590623140335, "regret_any": 0.02522967755794525, "regret_bot": 0.02536592446267605, "value_dist": 0.8481576442718506, "value_other_env": 0.8571376204490662, "value_corner": 0.8346875905990601, "value_row": 0.809008002281189, "value_any": 0.857020914554596, "value_bot": 0.8332605957984924, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03750.png", "entropy": 0.25972163677215576} +{"ts": "2026-03-20T18:17:28.606610Z", "loop": 3760, "env_steps": 2310144000, "exact_value_avg": 0.8493471145629883, "regret_dist": 0.014233613386750221, "regret_other_env": 0.022406931966543198, "regret_corner": 0.001973632490262389, "regret_row": 0.026718268170952797, "regret_any": 0.022407859563827515, "regret_bot": 0.014800753444433212, "value_dist": 0.8493471145629883, "value_other_env": 0.8598079681396484, "value_corner": 0.8336557149887085, "value_row": 0.8319084048271179, "value_any": 0.8598427176475525, "value_bot": 0.8438258767127991, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03760.png", "entropy": 0.25202929973602295} +{"ts": "2026-03-20T18:17:37.184632Z", "loop": 3770, "env_steps": 2316288000, "exact_value_avg": 0.8501853942871094, "regret_dist": 0.013395257294178009, "regret_other_env": 0.022142913192510605, "regret_corner": 0.0002737721079029143, "regret_row": 0.024204565212130547, "regret_any": 0.022249795496463776, "regret_bot": 0.02991093136370182, "value_dist": 0.8501853942871094, "value_other_env": 0.8600719571113586, "value_corner": 0.8353554606437683, "value_row": 0.8344220519065857, "value_any": 0.8600007891654968, "value_bot": 0.8287157416343689, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03770.png", "entropy": 0.24276642501354218} +{"ts": "2026-03-20T18:17:45.763776Z", "loop": 3780, "env_steps": 2322432000, "exact_value_avg": 0.8519442081451416, "regret_dist": 0.011636516079306602, "regret_other_env": 0.01794230379164219, "regret_corner": 0.002177831716835499, "regret_row": 0.027253897860646248, "regret_any": 0.017948057502508163, "regret_bot": 0.014957030303776264, "value_dist": 0.8519442081451416, "value_other_env": 0.8642725944519043, "value_corner": 0.833451509475708, "value_row": 0.8313727974891663, "value_any": 0.8643025755882263, "value_bot": 0.843669593334198, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03780.png", "entropy": 0.23879288136959076} +{"ts": "2026-03-20T18:17:54.341718Z", "loop": 3790, "env_steps": 2328576000, "exact_value_avg": 0.8545845746994019, "regret_dist": 0.00899612344801426, "regret_other_env": 0.01378943957388401, "regret_corner": 0.0018061479786410928, "regret_row": 0.023190222680568695, "regret_any": 0.01382342167198658, "regret_bot": 0.00841954629868269, "value_dist": 0.8545845746994019, "value_other_env": 0.8684254288673401, "value_corner": 0.8338232040405273, "value_row": 0.8354364037513733, "value_any": 0.8684272170066833, "value_bot": 0.8502071499824524, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03790.png", "entropy": 0.24415996670722961} +{"ts": "2026-03-20T18:18:02.919983Z", "loop": 3800, "env_steps": 2334720000, "exact_value_avg": 0.8551011681556702, "regret_dist": 0.008479529060423374, "regret_other_env": 0.013304993510246277, "regret_corner": 0.0012413313379511237, "regret_row": 0.0254482701420784, "regret_any": 0.013377214781939983, "regret_bot": 0.008343581110239029, "value_dist": 0.8551011681556702, "value_other_env": 0.8689098954200745, "value_corner": 0.8343879580497742, "value_row": 0.8331783413887024, "value_any": 0.8688733577728271, "value_bot": 0.8502830266952515, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03800.png", "entropy": 0.24164386093616486} +{"ts": "2026-03-20T18:18:11.495570Z", "loop": 3810, "env_steps": 2340864000, "exact_value_avg": 0.8561999797821045, "regret_dist": 0.0073806787841022015, "regret_other_env": 0.011994769796729088, "regret_corner": 0.00045954188681207597, "regret_row": 0.016694767400622368, "regret_any": 0.01204537320882082, "regret_bot": 0.008054602891206741, "value_dist": 0.8561999797821045, "value_other_env": 0.8702201247215271, "value_corner": 0.835169792175293, "value_row": 0.8419318795204163, "value_any": 0.8702051639556885, "value_bot": 0.8505720496177673, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03810.png", "entropy": 0.22815430164337158} +{"ts": "2026-03-20T18:18:20.070895Z", "loop": 3820, "env_steps": 2347008000, "exact_value_avg": 0.8522771596908569, "regret_dist": 0.011303535662591457, "regret_other_env": 0.01819618232548237, "regret_corner": 0.0009645646205171943, "regret_row": 0.026104290038347244, "regret_any": 0.018202081322669983, "regret_bot": 0.021336311474442482, "value_dist": 0.8522771596908569, "value_other_env": 0.8640187382698059, "value_corner": 0.8346647620201111, "value_row": 0.8325223922729492, "value_any": 0.8640485405921936, "value_bot": 0.837290346622467, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03820.png", "entropy": 0.23151618242263794} +{"ts": "2026-03-20T18:18:28.645749Z", "loop": 3830, "env_steps": 2353152000, "exact_value_avg": 0.8527652025222778, "regret_dist": 0.010815467685461044, "regret_other_env": 0.017729518935084343, "regret_corner": 0.00044439040357246995, "regret_row": 0.02779010310769081, "regret_any": 0.017834439873695374, "regret_bot": 0.02304213121533394, "value_dist": 0.8527652025222778, "value_other_env": 0.8644853234291077, "value_corner": 0.8351849913597107, "value_row": 0.8308365345001221, "value_any": 0.8644161820411682, "value_bot": 0.8355845808982849, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03830.png", "entropy": 0.23600056767463684} +{"ts": "2026-03-20T18:18:37.222568Z", "loop": 3840, "env_steps": 2359296000, "exact_value_avg": 0.8533108234405518, "regret_dist": 0.010269916616380215, "regret_other_env": 0.015229589305818081, "regret_corner": 0.0028304047882556915, "regret_row": 0.02316710166633129, "regret_any": 0.015228250063955784, "regret_bot": 0.01279230322688818, "value_dist": 0.8533108234405518, "value_other_env": 0.8669852614402771, "value_corner": 0.832798957824707, "value_row": 0.8354595303535461, "value_any": 0.8670223355293274, "value_bot": 0.8458343148231506, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03840.png", "entropy": 0.2397376000881195} +{"ts": "2026-03-20T18:18:45.798630Z", "loop": 3850, "env_steps": 2365440000, "exact_value_avg": 0.8555876016616821, "regret_dist": 0.007993057370185852, "regret_other_env": 0.012913652695715427, "regret_corner": 0.0006121640908531845, "regret_row": 0.03058885969221592, "regret_any": 0.012969393283128738, "regret_bot": 0.006516983266919851, "value_dist": 0.8555876016616821, "value_other_env": 0.8693011999130249, "value_corner": 0.835017204284668, "value_row": 0.8280377388000488, "value_any": 0.8692812323570251, "value_bot": 0.8521095514297485, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03850.png", "entropy": 0.23426932096481323} +{"ts": "2026-03-20T18:18:54.373251Z", "loop": 3860, "env_steps": 2371584000, "exact_value_avg": 0.8558083176612854, "regret_dist": 0.007772418670356274, "regret_other_env": 0.012718932703137398, "regret_corner": 0.00035264642792753875, "regret_row": 0.022227391600608826, "regret_any": 0.012755568139255047, "regret_bot": 0.010267381556332111, "value_dist": 0.8558083176612854, "value_other_env": 0.8694959878921509, "value_corner": 0.8352766633033752, "value_row": 0.8363991975784302, "value_any": 0.8694950342178345, "value_bot": 0.848359227180481, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03860.png", "entropy": 0.22772322595119476} +{"ts": "2026-03-20T18:19:02.951025Z", "loop": 3870, "env_steps": 2377728000, "exact_value_avg": 0.8533966541290283, "regret_dist": 0.010184070095419884, "regret_other_env": 0.015773748978972435, "regret_corner": 0.0017995497910305858, "regret_row": 0.025568392127752304, "regret_any": 0.015792757272720337, "regret_bot": 0.01580989547073841, "value_dist": 0.8533966541290283, "value_other_env": 0.8664410710334778, "value_corner": 0.8338298201560974, "value_row": 0.8330582976341248, "value_any": 0.8664578795433044, "value_bot": 0.8428167700767517, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03870.png", "entropy": 0.2213057279586792} +{"ts": "2026-03-20T18:19:11.523054Z", "loop": 3880, "env_steps": 2383872000, "exact_value_avg": 0.8527539968490601, "regret_dist": 0.010826684534549713, "regret_other_env": 0.01667388714849949, "regret_corner": 0.0020558806136250496, "regret_row": 0.049827128648757935, "regret_any": 0.01675528660416603, "regret_bot": 0.004972389899194241, "value_dist": 0.8527539968490601, "value_other_env": 0.8655409812927246, "value_corner": 0.8335734605789185, "value_row": 0.8087995648384094, "value_any": 0.8654952645301819, "value_bot": 0.8536542057991028, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03880.png", "entropy": 0.2267857789993286} +{"ts": "2026-03-20T18:19:20.095253Z", "loop": 3890, "env_steps": 2390016000, "exact_value_avg": 0.8558328747749329, "regret_dist": 0.007747779134660959, "regret_other_env": 0.012554826214909554, "regret_corner": 0.0005372082232497633, "regret_row": 0.018588194623589516, "regret_any": 0.012613781727850437, "regret_bot": 0.012823776341974735, "value_dist": 0.8558328747749329, "value_other_env": 0.8696600794792175, "value_corner": 0.8350920677185059, "value_row": 0.8400384783744812, "value_any": 0.8696368932723999, "value_bot": 0.8458027839660645, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03890.png", "entropy": 0.21995767951011658} +{"ts": "2026-03-20T18:19:28.673643Z", "loop": 3900, "env_steps": 2396160000, "exact_value_avg": 0.856794536113739, "regret_dist": 0.006786183454096317, "regret_other_env": 0.011103116907179356, "regret_corner": 0.0003107821103185415, "regret_row": 0.01706014573574066, "regret_any": 0.011132010258734226, "regret_bot": 0.008301171474158764, "value_dist": 0.856794536113739, "value_other_env": 0.8711118102073669, "value_corner": 0.8353185653686523, "value_row": 0.8415665030479431, "value_any": 0.8711185455322266, "value_bot": 0.8503254652023315, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03900.png", "entropy": 0.21247348189353943} +{"ts": "2026-03-20T18:19:37.250575Z", "loop": 3910, "env_steps": 2402304000, "exact_value_avg": 0.8500632047653198, "regret_dist": 0.013517476618289948, "regret_other_env": 0.022349635139107704, "regret_corner": 0.00026923767291009426, "regret_row": 0.019043074920773506, "regret_any": 0.02252310886979103, "regret_bot": 0.03440576791763306, "value_dist": 0.8500632047653198, "value_other_env": 0.8598652482032776, "value_corner": 0.8353601098060608, "value_row": 0.8395835161209106, "value_any": 0.8597274422645569, "value_bot": 0.8242208361625671, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03910.png", "entropy": 0.2217552214860916} +{"ts": "2026-03-20T18:19:45.824972Z", "loop": 3920, "env_steps": 2408448000, "exact_value_avg": 0.8503034710884094, "regret_dist": 0.013277238234877586, "regret_other_env": 0.021353792399168015, "regret_corner": 0.0011624048929661512, "regret_row": 0.02113044261932373, "regret_any": 0.021355370059609413, "regret_bot": 0.030783727765083313, "value_dist": 0.8503034710884094, "value_other_env": 0.8608611226081848, "value_corner": 0.8344669342041016, "value_row": 0.8374961614608765, "value_any": 0.8608952164649963, "value_bot": 0.8278428912162781, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03920.png", "entropy": 0.22540980577468872} +{"ts": "2026-03-20T18:19:54.404492Z", "loop": 3930, "env_steps": 2414592000, "exact_value_avg": 0.8480570316314697, "regret_dist": 0.015523656271398067, "regret_other_env": 0.025715980678796768, "regret_corner": 0.0002351691509829834, "regret_row": 0.016263889148831367, "regret_any": 0.025875283405184746, "regret_bot": 0.054472487419843674, "value_dist": 0.8480570316314697, "value_other_env": 0.8564988970756531, "value_corner": 0.8353941440582275, "value_row": 0.8423627018928528, "value_any": 0.8563753366470337, "value_bot": 0.8041541576385498, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03930.png", "entropy": 0.2191731035709381} +{"ts": "2026-03-20T18:20:02.985076Z", "loop": 3940, "env_steps": 2420736000, "exact_value_avg": 0.8571188449859619, "regret_dist": 0.006461809854954481, "regret_other_env": 0.010308920405805111, "regret_corner": 0.0006911442033015192, "regret_row": 0.014315336011350155, "regret_any": 0.010334855876863003, "regret_bot": 0.00844796933233738, "value_dist": 0.8571188449859619, "value_other_env": 0.8719059228897095, "value_corner": 0.8349382281303406, "value_row": 0.8443112969398499, "value_any": 0.8719156980514526, "value_bot": 0.8501786589622498, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03940.png", "entropy": 0.21253684163093567} +{"ts": "2026-03-20T18:20:11.569959Z", "loop": 3950, "env_steps": 2426880000, "exact_value_avg": 0.8536667823791504, "regret_dist": 0.00991387851536274, "regret_other_env": 0.015760093927383423, "regret_corner": 0.0011445528361946344, "regret_row": 0.04992365837097168, "regret_any": 0.015874048694968224, "regret_bot": 0.003868205938488245, "value_dist": 0.8536667823791504, "value_other_env": 0.8664547801017761, "value_corner": 0.8344847559928894, "value_row": 0.8087029457092285, "value_any": 0.8663765788078308, "value_bot": 0.8547585010528564, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03950.png", "entropy": 0.22068914771080017} +{"ts": "2026-03-20T18:20:20.150293Z", "loop": 3960, "env_steps": 2433024000, "exact_value_avg": 0.8562948703765869, "regret_dist": 0.00728584174066782, "regret_other_env": 0.011960024014115334, "regret_corner": 0.0002745678066276014, "regret_row": 0.014221744611859322, "regret_any": 0.011982879601418972, "regret_bot": 0.01317641232162714, "value_dist": 0.8562948703765869, "value_other_env": 0.8702548742294312, "value_corner": 0.8353548049926758, "value_row": 0.8444048762321472, "value_any": 0.8702677488327026, "value_bot": 0.8454501628875732, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03960.png", "entropy": 0.2059558480978012} +{"ts": "2026-03-20T18:20:28.725985Z", "loop": 3970, "env_steps": 2439168000, "exact_value_avg": 0.856673538684845, "regret_dist": 0.006907148286700249, "regret_other_env": 0.011279412545263767, "regret_corner": 0.0003487507638055831, "regret_row": 0.01246547233313322, "regret_any": 0.011304778978228569, "regret_bot": 0.013350402936339378, "value_dist": 0.856673538684845, "value_other_env": 0.8709354400634766, "value_corner": 0.8352805376052856, "value_row": 0.8461612462997437, "value_any": 0.8709458112716675, "value_bot": 0.8452762365341187, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03970.png", "entropy": 0.20698808133602142} +{"ts": "2026-03-20T18:20:37.312799Z", "loop": 3980, "env_steps": 2445312000, "exact_value_avg": 0.8546918630599976, "regret_dist": 0.0088888481259346, "regret_other_env": 0.01350646186619997, "regret_corner": 0.001962427981197834, "regret_row": 0.021845584735274315, "regret_any": 0.013502797111868858, "regret_bot": 0.01723805069923401, "value_dist": 0.8546918630599976, "value_other_env": 0.8687084317207336, "value_corner": 0.8336669206619263, "value_row": 0.8367810249328613, "value_any": 0.8687478303909302, "value_bot": 0.8413885831832886, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03980.png", "entropy": 0.21529991924762726} +{"ts": "2026-03-20T18:20:45.897769Z", "loop": 3990, "env_steps": 2451456000, "exact_value_avg": 0.8559401631355286, "regret_dist": 0.007640533614903688, "regret_other_env": 0.012572724372148514, "regret_corner": 0.0002422461984679103, "regret_row": 0.011315125972032547, "regret_any": 0.012599947862327099, "regret_bot": 0.013802147470414639, "value_dist": 0.8559401631355286, "value_other_env": 0.8696421980857849, "value_corner": 0.835387110710144, "value_row": 0.8473114967346191, "value_any": 0.8696506023406982, "value_bot": 0.844824492931366, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_03990.png", "entropy": 0.20251953601837158} +{"ts": "2026-03-20T18:20:54.478230Z", "loop": 4000, "env_steps": 2457600000, "exact_value_avg": 0.8522787094116211, "regret_dist": 0.011301921680569649, "regret_other_env": 0.018546834588050842, "regret_corner": 0.00043455115519464016, "regret_row": 0.013281678780913353, "regret_any": 0.01864677481353283, "regret_bot": 0.02608609013259411, "value_dist": 0.8522787094116211, "value_other_env": 0.8636680245399475, "value_corner": 0.8351948261260986, "value_row": 0.8453449606895447, "value_any": 0.8636038303375244, "value_bot": 0.8325405716896057, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04000.png", "entropy": 0.2197272628545761} +{"ts": "2026-03-20T18:21:03.054104Z", "loop": 4010, "env_steps": 2463744000, "exact_value_avg": 0.8539649248123169, "regret_dist": 0.009615748189389706, "regret_other_env": 0.015146477147936821, "regret_corner": 0.0013196544023230672, "regret_row": 0.028644757345318794, "regret_any": 0.015209393575787544, "regret_bot": 0.005778779741376638, "value_dist": 0.8539649248123169, "value_other_env": 0.8670684099197388, "value_corner": 0.8343096971511841, "value_row": 0.8299819231033325, "value_any": 0.8670412302017212, "value_bot": 0.8528479337692261, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04010.png", "entropy": 0.21698717772960663} +{"ts": "2026-03-20T18:21:11.633156Z", "loop": 4020, "env_steps": 2469888000, "exact_value_avg": 0.8572595119476318, "regret_dist": 0.006321164313703775, "regret_other_env": 0.010461471974849701, "regret_corner": 0.00011070172331528738, "regret_row": 0.012500917539000511, "regret_any": 0.01049140002578497, "regret_bot": 0.009100395254790783, "value_dist": 0.8572595119476318, "value_other_env": 0.8717533946037292, "value_corner": 0.8355185985565186, "value_row": 0.8461257219314575, "value_any": 0.8717592358589172, "value_bot": 0.8495262265205383, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04020.png", "entropy": 0.19695250689983368} +{"ts": "2026-03-20T18:21:20.210296Z", "loop": 4030, "env_steps": 2476032000, "exact_value_avg": 0.8559910655021667, "regret_dist": 0.0075896321795880795, "regret_other_env": 0.012503418140113354, "regret_corner": 0.00021895220561418682, "regret_row": 0.012506990693509579, "regret_any": 0.012534656561911106, "regret_bot": 0.018620910122990608, "value_dist": 0.8559910655021667, "value_other_env": 0.8697114586830139, "value_corner": 0.8354103565216064, "value_row": 0.8461196422576904, "value_any": 0.8697159886360168, "value_bot": 0.8400057554244995, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04030.png", "entropy": 0.19832034409046173} +{"ts": "2026-03-20T18:21:28.788809Z", "loop": 4040, "env_steps": 2482176000, "exact_value_avg": 0.8581653833389282, "regret_dist": 0.005415340419858694, "regret_other_env": 0.008926820941269398, "regret_corner": 0.00014811854634899646, "regret_row": 0.01073880959302187, "regret_any": 0.008967588655650616, "regret_bot": 0.00798568595200777, "value_dist": 0.8581653833389282, "value_other_env": 0.873288094997406, "value_corner": 0.8354812264442444, "value_row": 0.8478878140449524, "value_any": 0.8732829689979553, "value_bot": 0.8506409525871277, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04040.png", "entropy": 0.19628164172172546} +{"ts": "2026-03-20T18:21:37.368835Z", "loop": 4050, "env_steps": 2488320000, "exact_value_avg": 0.8572129011154175, "regret_dist": 0.006367759313434362, "regret_other_env": 0.01047863531857729, "regret_corner": 0.00020144484005868435, "regret_row": 0.01614689826965332, "regret_any": 0.010486728511750698, "regret_bot": 0.005999155342578888, "value_dist": 0.8572129011154175, "value_other_env": 0.8717362284660339, "value_corner": 0.8354278802871704, "value_row": 0.8424797058105469, "value_any": 0.8717639446258545, "value_bot": 0.8526275157928467, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04050.png", "entropy": 0.194577157497406} +{"ts": "2026-03-20T18:21:45.948788Z", "loop": 4060, "env_steps": 2494464000, "exact_value_avg": 0.8580803871154785, "regret_dist": 0.005500332918018103, "regret_other_env": 0.009026997722685337, "regret_corner": 0.00021033536177128553, "regret_row": 0.010857406072318554, "regret_any": 0.009093035943806171, "regret_bot": 0.005388599820435047, "value_dist": 0.8580803871154785, "value_other_env": 0.8731878995895386, "value_corner": 0.8354189991950989, "value_row": 0.8477692604064941, "value_any": 0.8731575608253479, "value_bot": 0.853238046169281, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04060.png", "entropy": 0.19756418466567993} +{"ts": "2026-03-20T18:21:54.525447Z", "loop": 4070, "env_steps": 2500608000, "exact_value_avg": 0.858620822429657, "regret_dist": 0.004959840793162584, "regret_other_env": 0.008128377608954906, "regret_corner": 0.00020703524933196604, "regret_row": 0.009785640984773636, "regret_any": 0.008146741427481174, "regret_bot": 0.006036472041159868, "value_dist": 0.858620822429657, "value_other_env": 0.8740864992141724, "value_corner": 0.8354222774505615, "value_row": 0.8488410711288452, "value_any": 0.874103844165802, "value_bot": 0.8525902032852173, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04070.png", "entropy": 0.19608549773693085} +{"ts": "2026-03-20T18:22:03.105215Z", "loop": 4080, "env_steps": 2506752000, "exact_value_avg": 0.8578996658325195, "regret_dist": 0.005681028589606285, "regret_other_env": 0.0092095285654068, "regret_corner": 0.0003882780729327351, "regret_row": 0.021151069551706314, "regret_any": 0.009243743494153023, "regret_bot": 0.00646634679287672, "value_dist": 0.8578996658325195, "value_other_env": 0.8730053901672363, "value_corner": 0.8352410793304443, "value_row": 0.8374755382537842, "value_any": 0.8730068206787109, "value_bot": 0.8521602749824524, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04080.png", "entropy": 0.20040714740753174} +{"ts": "2026-03-20T18:22:11.683147Z", "loop": 4090, "env_steps": 2512896000, "exact_value_avg": 0.8563348054885864, "regret_dist": 0.007245856337249279, "regret_other_env": 0.010987014509737492, "regret_corner": 0.001634118496440351, "regret_row": 0.017524829134345055, "regret_any": 0.011009182780981064, "regret_bot": 0.01479555107653141, "value_dist": 0.8563348054885864, "value_other_env": 0.8712278604507446, "value_corner": 0.8339951634407043, "value_row": 0.8411017656326294, "value_any": 0.8712413907051086, "value_bot": 0.8438310623168945, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04090.png", "entropy": 0.20798729360103607} +{"ts": "2026-03-20T18:22:20.266074Z", "loop": 4100, "env_steps": 2519040000, "exact_value_avg": 0.8499534130096436, "regret_dist": 0.013627282343804836, "regret_other_env": 0.02262766659259796, "regret_corner": 0.00012670407886616886, "regret_row": 0.040755461901426315, "regret_any": 0.022656511515378952, "regret_bot": 0.02649196982383728, "value_dist": 0.8499534130096436, "value_other_env": 0.8595871925354004, "value_corner": 0.8355026841163635, "value_row": 0.8178711533546448, "value_any": 0.8595941066741943, "value_bot": 0.8321347236633301, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04100.png", "entropy": 0.17616045475006104} +{"ts": "2026-03-20T18:22:28.842947Z", "loop": 4110, "env_steps": 2525184000, "exact_value_avg": 0.8544082641601562, "regret_dist": 0.009172439575195312, "regret_other_env": 0.014736057259142399, "regret_corner": 0.0008270115358754992, "regret_row": 0.034922946244478226, "regret_any": 0.014903387986123562, "regret_bot": 0.004816044121980667, "value_dist": 0.8544082641601562, "value_other_env": 0.8674788475036621, "value_corner": 0.8348022699356079, "value_row": 0.8237037062644958, "value_any": 0.8673471808433533, "value_bot": 0.8538106083869934, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04110.png", "entropy": 0.19379110634326935} +{"ts": "2026-03-20T18:22:37.422492Z", "loop": 4120, "env_steps": 2531328000, "exact_value_avg": 0.8551158905029297, "regret_dist": 0.008464737795293331, "regret_other_env": 0.014012973755598068, "regret_corner": 0.00014238407311495394, "regret_row": 0.021453889086842537, "regret_any": 0.01405870821326971, "regret_bot": 0.0184782724827528, "value_dist": 0.8551158905029297, "value_other_env": 0.8682019114494324, "value_corner": 0.835486888885498, "value_row": 0.83717280626297, "value_any": 0.8681918978691101, "value_bot": 0.8401483297348022, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04120.png", "entropy": 0.19062544405460358} +{"ts": "2026-03-20T18:22:46.001139Z", "loop": 4130, "env_steps": 2537472000, "exact_value_avg": 0.8587520122528076, "regret_dist": 0.004828667268157005, "regret_other_env": 0.007828792557120323, "regret_corner": 0.00032847822876647115, "regret_row": 0.008124742656946182, "regret_any": 0.007843711413443089, "regret_bot": 0.007519328035414219, "value_dist": 0.8587520122528076, "value_other_env": 0.8743860721588135, "value_corner": 0.8353008031845093, "value_row": 0.8505019545555115, "value_any": 0.8744068741798401, "value_bot": 0.8511072993278503, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04130.png", "entropy": 0.19392624497413635} +{"ts": "2026-03-20T18:22:54.578732Z", "loop": 4140, "env_steps": 2543616000, "exact_value_avg": 0.8572258949279785, "regret_dist": 0.006354824639856815, "regret_other_env": 0.010272271931171417, "regret_corner": 0.0004786536446772516, "regret_row": 0.012846775352954865, "regret_any": 0.010313141159713268, "regret_bot": 0.004825511947274208, "value_dist": 0.8572258949279785, "value_other_env": 0.8719425797462463, "value_corner": 0.8351507186889648, "value_row": 0.8457798361778259, "value_any": 0.8719374537467957, "value_bot": 0.8538011908531189, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04140.png", "entropy": 0.1923321932554245} +{"ts": "2026-03-20T18:23:03.156445Z", "loop": 4150, "env_steps": 2549760000, "exact_value_avg": 0.8591448068618774, "regret_dist": 0.004435883369296789, "regret_other_env": 0.007191873155534267, "regret_corner": 0.0003018985444214195, "regret_row": 0.006853747647255659, "regret_any": 0.0072092330083251, "regret_bot": 0.006020302884280682, "value_dist": 0.8591448068618774, "value_other_env": 0.8750230073928833, "value_corner": 0.8353274464607239, "value_row": 0.8517729640007019, "value_any": 0.8750413656234741, "value_bot": 0.8526063561439514, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04150.png", "entropy": 0.1958913803100586} +{"ts": "2026-03-20T18:23:11.739774Z", "loop": 4160, "env_steps": 2555904000, "exact_value_avg": 0.8584802150726318, "regret_dist": 0.005100437439978123, "regret_other_env": 0.008100627921521664, "regret_corner": 0.000600151252001524, "regret_row": 0.007534256670624018, "regret_any": 0.008114827796816826, "regret_bot": 0.006542949937283993, "value_dist": 0.8584802150726318, "value_other_env": 0.8741142749786377, "value_corner": 0.835029125213623, "value_row": 0.8510923981666565, "value_any": 0.8741357326507568, "value_bot": 0.852083683013916, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04160.png", "entropy": 0.2033625841140747} +{"ts": "2026-03-20T18:23:20.315135Z", "loop": 4170, "env_steps": 2562048000, "exact_value_avg": 0.8573631048202515, "regret_dist": 0.006217528134584427, "regret_other_env": 0.010009351186454296, "regret_corner": 0.0005297939060255885, "regret_row": 0.010191063396632671, "regret_any": 0.01001596637070179, "regret_bot": 0.010021312162280083, "value_dist": 0.8573631048202515, "value_other_env": 0.8722054958343506, "value_corner": 0.8350995779037476, "value_row": 0.848435640335083, "value_any": 0.8722346425056458, "value_bot": 0.8486053347587585, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04170.png", "entropy": 0.204301118850708} +{"ts": "2026-03-20T18:23:28.890092Z", "loop": 4180, "env_steps": 2568192000, "exact_value_avg": 0.8585741519927979, "regret_dist": 0.005006518680602312, "regret_other_env": 0.008171715773642063, "regret_corner": 0.0002587229246273637, "regret_row": 0.006971522234380245, "regret_any": 0.008186997845768929, "regret_bot": 0.008836159482598305, "value_dist": 0.8585741519927979, "value_other_env": 0.8740431666374207, "value_corner": 0.8353706002235413, "value_row": 0.851655125617981, "value_any": 0.8740636110305786, "value_bot": 0.8497903943061829, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04180.png", "entropy": 0.19631829857826233} +{"ts": "2026-03-20T18:23:37.470706Z", "loop": 4190, "env_steps": 2574336000, "exact_value_avg": 0.8549516201019287, "regret_dist": 0.008629005402326584, "regret_other_env": 0.012907181866466999, "regret_corner": 0.002211740706115961, "regret_row": 0.011317756026983261, "regret_any": 0.012905093841254711, "regret_bot": 0.021327432245016098, "value_dist": 0.8549516201019287, "value_other_env": 0.8693076372146606, "value_corner": 0.833417534828186, "value_row": 0.847308874130249, "value_any": 0.8693455457687378, "value_bot": 0.8372992277145386, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04190.png", "entropy": 0.2037121057510376} +{"ts": "2026-03-20T18:23:46.052880Z", "loop": 4200, "env_steps": 2580480000, "exact_value_avg": 0.8553760051727295, "regret_dist": 0.008204720914363861, "regret_other_env": 0.011347604915499687, "regret_corner": 0.003490395611152053, "regret_row": 0.013438021764159203, "regret_any": 0.011363617144525051, "regret_bot": 0.015289564616978168, "value_dist": 0.8553760051727295, "value_other_env": 0.8708673119544983, "value_corner": 0.8321389555931091, "value_row": 0.8451886177062988, "value_any": 0.870887041091919, "value_bot": 0.8433370590209961, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04200.png", "entropy": 0.19582635164260864} +{"ts": "2026-03-20T18:23:54.642004Z", "loop": 4210, "env_steps": 2586624000, "exact_value_avg": 0.8542541265487671, "regret_dist": 0.009326576255261898, "regret_other_env": 0.01502566784620285, "regret_corner": 0.0007779385196045041, "regret_row": 0.05019862949848175, "regret_any": 0.01508474163711071, "regret_bot": 0.010840521194040775, "value_dist": 0.8542541265487671, "value_other_env": 0.8671892285346985, "value_corner": 0.8348513841629028, "value_row": 0.8084279894828796, "value_any": 0.8671658635139465, "value_bot": 0.8477860689163208, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04210.png", "entropy": 0.19769306480884552} +{"ts": "2026-03-20T18:24:03.225375Z", "loop": 4220, "env_steps": 2592768000, "exact_value_avg": 0.8586022853851318, "regret_dist": 0.00497842114418745, "regret_other_env": 0.00821396429091692, "regret_corner": 0.00012510617671068758, "regret_row": 0.006263953633606434, "regret_any": 0.00824127346277237, "regret_bot": 0.009244191460311413, "value_dist": 0.8586022853851318, "value_other_env": 0.8740009069442749, "value_corner": 0.8355041742324829, "value_row": 0.8523626923561096, "value_any": 0.874009370803833, "value_bot": 0.8493824005126953, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04220.png", "entropy": 0.18192559480667114} +{"ts": "2026-03-20T18:24:11.809332Z", "loop": 4230, "env_steps": 2598912000, "exact_value_avg": 0.8585186004638672, "regret_dist": 0.005062040872871876, "regret_other_env": 0.00827990286052227, "regret_corner": 0.00023524713469669223, "regret_row": 0.013063185848295689, "regret_any": 0.00829798448830843, "regret_bot": 0.005339485593140125, "value_dist": 0.8585186004638672, "value_other_env": 0.8739349246025085, "value_corner": 0.8353940844535828, "value_row": 0.8455634713172913, "value_any": 0.8739525675773621, "value_bot": 0.8532871603965759, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04230.png", "entropy": 0.17378126084804535} +{"ts": "2026-03-20T18:24:20.396966Z", "loop": 4240, "env_steps": 2605056000, "exact_value_avg": 0.8573451042175293, "regret_dist": 0.006235537119209766, "regret_other_env": 0.010188206098973751, "regret_corner": 0.0003065333003178239, "regret_row": 0.008542697876691818, "regret_any": 0.010249737650156021, "regret_bot": 0.00909728929400444, "value_dist": 0.8573451042175293, "value_other_env": 0.8720266819000244, "value_corner": 0.8353227972984314, "value_row": 0.8500839471817017, "value_any": 0.8720008134841919, "value_bot": 0.8495293259620667, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04240.png", "entropy": 0.17870184779167175} +{"ts": "2026-03-20T18:24:28.982997Z", "loop": 4250, "env_steps": 2611200000, "exact_value_avg": 0.8576771020889282, "regret_dist": 0.0059035890735685825, "regret_other_env": 0.009514284320175648, "regret_corner": 0.0004875461454503238, "regret_row": 0.016884295269846916, "regret_any": 0.009592096321284771, "regret_bot": 0.0029166669119149446, "value_dist": 0.8576771020889282, "value_other_env": 0.872700572013855, "value_corner": 0.8351417183876038, "value_row": 0.8417422771453857, "value_any": 0.8726584911346436, "value_bot": 0.855709969997406, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04250.png", "entropy": 0.18036586046218872} +{"ts": "2026-03-20T18:24:37.574850Z", "loop": 4260, "env_steps": 2617344000, "exact_value_avg": 0.8581738471984863, "regret_dist": 0.005406857468187809, "regret_other_env": 0.008533214218914509, "regret_corner": 0.0007173215853981674, "regret_row": 0.009724127128720284, "regret_any": 0.008542592637240887, "regret_bot": 0.00680244155228138, "value_dist": 0.8581738471984863, "value_other_env": 0.8736816644668579, "value_corner": 0.8349119424819946, "value_row": 0.8489025235176086, "value_any": 0.8737079501152039, "value_bot": 0.851824164390564, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04260.png", "entropy": 0.1812351495027542} +{"ts": "2026-03-20T18:24:46.155437Z", "loop": 4270, "env_steps": 2623488000, "exact_value_avg": 0.8587241172790527, "regret_dist": 0.00485654454678297, "regret_other_env": 0.007890678010880947, "regret_corner": 0.0003053436812479049, "regret_row": 0.006264321506023407, "regret_any": 0.007893974892795086, "regret_bot": 0.008341802284121513, "value_dist": 0.8587241172790527, "value_other_env": 0.8743242025375366, "value_corner": 0.8353239893913269, "value_row": 0.852362334728241, "value_any": 0.8743566274642944, "value_bot": 0.8502848148345947, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04270.png", "entropy": 0.17611563205718994} +{"ts": "2026-03-20T18:24:54.735593Z", "loop": 4280, "env_steps": 2629632000, "exact_value_avg": 0.8588602542877197, "regret_dist": 0.004720434546470642, "regret_other_env": 0.007820666767656803, "regret_corner": 7.008562533883378e-05, "regret_row": 0.005197008606046438, "regret_any": 0.007838317193090916, "regret_bot": 0.006248085759580135, "value_dist": 0.8588602542877197, "value_other_env": 0.8743941783905029, "value_corner": 0.8355592489242554, "value_row": 0.8534296154975891, "value_any": 0.8744122982025146, "value_bot": 0.8523786067962646, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04280.png", "entropy": 0.1700083166360855} +{"ts": "2026-03-20T18:25:03.317485Z", "loop": 4290, "env_steps": 2635776000, "exact_value_avg": 0.8599214553833008, "regret_dist": 0.0036592097021639347, "regret_other_env": 0.005973853636533022, "regret_corner": 0.00018724352412391454, "regret_row": 0.007843169383704662, "regret_any": 0.0060010855086147785, "regret_bot": 0.0048276339657604694, "value_dist": 0.8599214553833008, "value_other_env": 0.8762410283088684, "value_corner": 0.8354420065879822, "value_row": 0.8507834672927856, "value_any": 0.8762494921684265, "value_bot": 0.853799045085907, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04290.png", "entropy": 0.1769287884235382} +{"ts": "2026-03-20T18:25:11.901192Z", "loop": 4300, "env_steps": 2641920000, "exact_value_avg": 0.8598729372024536, "regret_dist": 0.0037077313754707575, "regret_other_env": 0.005954790394753218, "regret_corner": 0.00033714226447045803, "regret_row": 0.007090074010193348, "regret_any": 0.006003092043101788, "regret_bot": 0.002868170849978924, "value_dist": 0.8598729372024536, "value_other_env": 0.8762600421905518, "value_corner": 0.8352922201156616, "value_row": 0.8515365719795227, "value_any": 0.8762475252151489, "value_bot": 0.8557583689689636, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04300.png", "entropy": 0.17476114630699158} +{"ts": "2026-03-20T18:25:20.489518Z", "loop": 4310, "env_steps": 2648064000, "exact_value_avg": 0.8599001169204712, "regret_dist": 0.0036806077696383, "regret_other_env": 0.006068796385079622, "regret_corner": 9.832432260736823e-05, "regret_row": 0.0049294959753751755, "regret_any": 0.006098195444792509, "regret_bot": 0.00612943060696125, "value_dist": 0.8599001169204712, "value_other_env": 0.8761460781097412, "value_corner": 0.8355309367179871, "value_row": 0.8536971211433411, "value_any": 0.8761524558067322, "value_bot": 0.8524972200393677, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04310.png", "entropy": 0.1723325550556183} +{"ts": "2026-03-20T18:25:29.064457Z", "loop": 4320, "env_steps": 2654208000, "exact_value_avg": 0.8592849373817444, "regret_dist": 0.004295762628316879, "regret_other_env": 0.00659857178106904, "regret_corner": 0.0008415486081503332, "regret_row": 0.015387722291052341, "regret_any": 0.006632565055042505, "regret_bot": 0.0027808176819235086, "value_dist": 0.8592849373817444, "value_other_env": 0.8756163120269775, "value_corner": 0.8347877860069275, "value_row": 0.8432389497756958, "value_any": 0.875618040561676, "value_bot": 0.8558458685874939, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04320.png", "entropy": 0.17603282630443573} +{"ts": "2026-03-20T18:25:37.649233Z", "loop": 4330, "env_steps": 2660352000, "exact_value_avg": 0.8572702407836914, "regret_dist": 0.006310394499450922, "regret_other_env": 0.01048710010945797, "regret_corner": 4.5335793402045965e-05, "regret_row": 0.01152093056589365, "regret_any": 0.010524795390665531, "regret_bot": 0.01425519771873951, "value_dist": 0.8572702407836914, "value_other_env": 0.8717277646064758, "value_corner": 0.8355839848518372, "value_row": 0.8471056818962097, "value_any": 0.8717257976531982, "value_bot": 0.8443714380264282, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04330.png", "entropy": 0.16820836067199707} +{"ts": "2026-03-20T18:25:46.229430Z", "loop": 4340, "env_steps": 2666496000, "exact_value_avg": 0.858366847038269, "regret_dist": 0.005213856231421232, "regret_other_env": 0.008294332772493362, "regret_corner": 0.0005931402556598186, "regret_row": 0.007988442666828632, "regret_any": 0.00841206032782793, "regret_bot": 0.0025408233050256968, "value_dist": 0.858366847038269, "value_other_env": 0.8739205002784729, "value_corner": 0.8350362181663513, "value_row": 0.8506382703781128, "value_any": 0.873838484287262, "value_bot": 0.8560857176780701, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04340.png", "entropy": 0.16658802330493927} +{"ts": "2026-03-20T18:25:54.809901Z", "loop": 4350, "env_steps": 2672640000, "exact_value_avg": 0.8600684404373169, "regret_dist": 0.003512241644784808, "regret_other_env": 0.005663026124238968, "regret_corner": 0.0002860645472537726, "regret_row": 0.006116504315286875, "regret_any": 0.005692455917596817, "regret_bot": 0.004150037188082933, "value_dist": 0.8600684404373169, "value_other_env": 0.8765518069267273, "value_corner": 0.8353432416915894, "value_row": 0.8525101542472839, "value_any": 0.8765581846237183, "value_bot": 0.8544766306877136, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04350.png", "entropy": 0.1722506284713745} +{"ts": "2026-03-20T18:26:03.397075Z", "loop": 4360, "env_steps": 2678784000, "exact_value_avg": 0.8546276092529297, "regret_dist": 0.008953085169196129, "regret_other_env": 0.014881971292197704, "regret_corner": 5.975614476483315e-05, "regret_row": 0.03690427914261818, "regret_any": 0.014896013773977757, "regret_bot": 0.008340527303516865, "value_dist": 0.8546276092529297, "value_other_env": 0.867332935333252, "value_corner": 0.8355695605278015, "value_row": 0.8217223882675171, "value_any": 0.8673545718193054, "value_bot": 0.8502861261367798, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04360.png", "entropy": 0.15475639700889587} +{"ts": "2026-03-20T18:26:11.973625Z", "loop": 4370, "env_steps": 2684928000, "exact_value_avg": 0.8581581711769104, "regret_dist": 0.005422535352408886, "regret_other_env": 0.008860364556312561, "regret_corner": 0.0002657910226844251, "regret_row": 0.021215742453932762, "regret_any": 0.008990325033664703, "regret_bot": 0.0035978052765130997, "value_dist": 0.8581581711769104, "value_other_env": 0.8733545541763306, "value_corner": 0.8353635668754578, "value_row": 0.8374109268188477, "value_any": 0.8732602596282959, "value_bot": 0.8550288081169128, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04370.png", "entropy": 0.16847877204418182} +{"ts": "2026-03-20T18:26:20.553969Z", "loop": 4380, "env_steps": 2691072000, "exact_value_avg": 0.8588956594467163, "regret_dist": 0.004685087129473686, "regret_other_env": 0.007394080050289631, "regret_corner": 0.0006215969915501773, "regret_row": 0.008133003488183022, "regret_any": 0.0074474262073636055, "regret_bot": 0.004276054911315441, "value_dist": 0.8588956594467163, "value_other_env": 0.8748208284378052, "value_corner": 0.8350077867507935, "value_row": 0.8504936099052429, "value_any": 0.8748031258583069, "value_bot": 0.8543505668640137, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04380.png", "entropy": 0.1728900671005249} +{"ts": "2026-03-20T18:26:29.136716Z", "loop": 4390, "env_steps": 2697216000, "exact_value_avg": 0.8596118688583374, "regret_dist": 0.00396878132596612, "regret_other_env": 0.00632532499730587, "regret_corner": 0.00043396506225690246, "regret_row": 0.006334469188004732, "regret_any": 0.006370218470692635, "regret_bot": 0.003637229558080435, "value_dist": 0.8596118688583374, "value_other_env": 0.8758895397186279, "value_corner": 0.8351953029632568, "value_row": 0.8522921204566956, "value_any": 0.8758804202079773, "value_bot": 0.8549892902374268, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04390.png", "entropy": 0.16992656886577606} +{"ts": "2026-03-20T18:26:37.719542Z", "loop": 4400, "env_steps": 2703360000, "exact_value_avg": 0.85816890001297, "regret_dist": 0.005411813501268625, "regret_other_env": 0.00887851882725954, "regret_corner": 0.0002117549447575584, "regret_row": 0.011151745915412903, "regret_any": 0.008902501314878464, "regret_bot": 0.00929558090865612, "value_dist": 0.85816890001297, "value_other_env": 0.8733363747596741, "value_corner": 0.835417628288269, "value_row": 0.8474748730659485, "value_any": 0.87334805727005, "value_bot": 0.8493310809135437, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04400.png", "entropy": 0.16819632053375244} +{"ts": "2026-03-20T18:26:46.303015Z", "loop": 4410, "env_steps": 2709504000, "exact_value_avg": 0.8583583831787109, "regret_dist": 0.005222289822995663, "regret_other_env": 0.00730513222515583, "regret_corner": 0.00209802552126348, "regret_row": 0.011986641213297844, "regret_any": 0.0073228501714766026, "regret_bot": 0.008441747166216373, "value_dist": 0.8583583831787109, "value_other_env": 0.8749097585678101, "value_corner": 0.833531379699707, "value_row": 0.8466399908065796, "value_any": 0.874927818775177, "value_bot": 0.8501849174499512, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04410.png", "entropy": 0.17612046003341675} +{"ts": "2026-03-20T18:26:54.886340Z", "loop": 4420, "env_steps": 2715648000, "exact_value_avg": 0.8603760600090027, "regret_dist": 0.003204712411388755, "regret_other_env": 0.005295365583151579, "regret_corner": 6.873210804769769e-05, "regret_row": 0.0037021730095148087, "regret_any": 0.005317777395248413, "regret_bot": 0.004478285554796457, "value_dist": 0.8603760600090027, "value_other_env": 0.8769195675849915, "value_corner": 0.83556067943573, "value_row": 0.8549244999885559, "value_any": 0.8769328594207764, "value_bot": 0.8541483283042908, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04420.png", "entropy": 0.16503942012786865} +{"ts": "2026-03-20T18:27:03.466425Z", "loop": 4430, "env_steps": 2721792000, "exact_value_avg": 0.8596334457397461, "regret_dist": 0.003947271499782801, "regret_other_env": 0.006485920399427414, "regret_corner": 0.0001392975536873564, "regret_row": 0.004818366840481758, "regret_any": 0.006496518384665251, "regret_bot": 0.006091981660574675, "value_dist": 0.8596334457397461, "value_other_env": 0.875728964805603, "value_corner": 0.8354901075363159, "value_row": 0.8538082838058472, "value_any": 0.8757541179656982, "value_bot": 0.8525345921516418, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04430.png", "entropy": 0.1665295511484146} +{"ts": "2026-03-20T18:27:12.052350Z", "loop": 4440, "env_steps": 2727936000, "exact_value_avg": 0.8583393096923828, "regret_dist": 0.005241368897259235, "regret_other_env": 0.008311511017382145, "regret_corner": 0.0006361549603752792, "regret_row": 0.006237071938812733, "regret_any": 0.00831583607941866, "regret_bot": 0.01210129726678133, "value_dist": 0.8583393096923828, "value_other_env": 0.8739033937454224, "value_corner": 0.8349931240081787, "value_row": 0.8523895740509033, "value_any": 0.8739347457885742, "value_bot": 0.8465254306793213, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04440.png", "entropy": 0.17217500507831573} +{"ts": "2026-03-20T18:27:20.643908Z", "loop": 4450, "env_steps": 2734080000, "exact_value_avg": 0.8564984798431396, "regret_dist": 0.007082275580614805, "regret_other_env": 0.011210321448743343, "regret_corner": 0.0008902053232304752, "regret_row": 0.050441451370716095, "regret_any": 0.01121659018099308, "regret_bot": 0.00718540558591485, "value_dist": 0.8564984798431396, "value_other_env": 0.871004581451416, "value_corner": 0.834739089012146, "value_row": 0.8081851601600647, "value_any": 0.8710339665412903, "value_bot": 0.8514412641525269, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04450.png", "entropy": 0.1682104766368866} +{"ts": "2026-03-20T18:27:29.224231Z", "loop": 4460, "env_steps": 2740224000, "exact_value_avg": 0.8598589301109314, "regret_dist": 0.0037217549979686737, "regret_other_env": 0.006134713999927044, "regret_corner": 0.0001023163422360085, "regret_row": 0.005384370684623718, "regret_any": 0.006151146721094847, "regret_bot": 0.007373887579888105, "value_dist": 0.8598589301109314, "value_other_env": 0.8760801553726196, "value_corner": 0.8355270028114319, "value_row": 0.8532422184944153, "value_any": 0.8760994672775269, "value_bot": 0.8512527942657471, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04460.png", "entropy": 0.15988248586654663} +{"ts": "2026-03-20T18:27:37.806111Z", "loop": 4470, "env_steps": 2746368000, "exact_value_avg": 0.859503984451294, "regret_dist": 0.004076696000993252, "regret_other_env": 0.006753296125680208, "regret_corner": 6.179511547088623e-05, "regret_row": 0.004016328603029251, "regret_any": 0.0067762341350317, "regret_bot": 0.007724498864263296, "value_dist": 0.859503984451294, "value_other_env": 0.8754615187644958, "value_corner": 0.8355675339698792, "value_row": 0.8546103239059448, "value_any": 0.8754743337631226, "value_bot": 0.8509021997451782, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04470.png", "entropy": 0.15815453231334686} +{"ts": "2026-03-20T18:27:46.387989Z", "loop": 4480, "env_steps": 2752512000, "exact_value_avg": 0.8592267036437988, "regret_dist": 0.004354051314294338, "regret_other_env": 0.007213905919343233, "regret_corner": 6.426970503525808e-05, "regret_row": 0.004137497395277023, "regret_any": 0.0072395377792418, "regret_bot": 0.011701644398272038, "value_dist": 0.8592267036437988, "value_other_env": 0.8750010132789612, "value_corner": 0.8355650901794434, "value_row": 0.8544890880584717, "value_any": 0.8750110864639282, "value_bot": 0.8469250202178955, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04480.png", "entropy": 0.1600669026374817} +{"ts": "2026-03-20T18:27:54.964673Z", "loop": 4490, "env_steps": 2758656000, "exact_value_avg": 0.859980046749115, "regret_dist": 0.003600663272663951, "regret_other_env": 0.005612993612885475, "regret_corner": 0.0005821675295010209, "regret_row": 0.004916824400424957, "regret_any": 0.0056375740095973015, "regret_bot": 0.007790556643158197, "value_dist": 0.859980046749115, "value_other_env": 0.8766019344329834, "value_corner": 0.83504718542099, "value_row": 0.8537098169326782, "value_any": 0.8766129612922668, "value_bot": 0.8508360385894775, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04490.png", "entropy": 0.1669224202632904} +{"ts": "2026-03-20T18:28:03.542320Z", "loop": 4500, "env_steps": 2764800000, "exact_value_avg": 0.8607814311981201, "regret_dist": 0.002799247857183218, "regret_other_env": 0.004538652952760458, "regret_corner": 0.00019013982091564685, "regret_row": 0.00728754373267293, "regret_any": 0.004622557666152716, "regret_bot": 0.0021346197463572025, "value_dist": 0.8607814311981201, "value_other_env": 0.877676248550415, "value_corner": 0.8354392051696777, "value_row": 0.8513391613960266, "value_any": 0.8776280879974365, "value_bot": 0.8564921021461487, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04500.png", "entropy": 0.15830367803573608} +{"ts": "2026-03-20T18:28:12.130341Z", "loop": 4510, "env_steps": 2770944000, "exact_value_avg": 0.8598196506500244, "regret_dist": 0.003761074272915721, "regret_other_env": 0.006238052621483803, "regret_corner": 4.560649540508166e-05, "regret_row": 0.012834146618843079, "regret_any": 0.006260374095290899, "regret_bot": 0.0035635321401059628, "value_dist": 0.8598196506500244, "value_other_env": 0.8759768009185791, "value_corner": 0.8355837464332581, "value_row": 0.8457924127578735, "value_any": 0.8759901523590088, "value_bot": 0.8550631403923035, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04510.png", "entropy": 0.15556232631206512} +{"ts": "2026-03-20T18:28:20.707495Z", "loop": 4520, "env_steps": 2777088000, "exact_value_avg": 0.860522985458374, "regret_dist": 0.003057696158066392, "regret_other_env": 0.005026983562856913, "regret_corner": 0.00010376473801443353, "regret_row": 0.006746850907802582, "regret_any": 0.005076489876955748, "regret_bot": 0.0023703682236373425, "value_dist": 0.860522985458374, "value_other_env": 0.8771879076957703, "value_corner": 0.8355255722999573, "value_row": 0.8518798351287842, "value_any": 0.8771740794181824, "value_bot": 0.8562562465667725, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04520.png", "entropy": 0.15765449404716492} +{"ts": "2026-03-20T18:28:29.287868Z", "loop": 4530, "env_steps": 2783232000, "exact_value_avg": 0.8605936765670776, "regret_dist": 0.0029870308935642242, "regret_other_env": 0.004930077586323023, "regret_corner": 7.246037421282381e-05, "regret_row": 0.005132429301738739, "regret_any": 0.004987600725144148, "regret_bot": 0.0032247514463961124, "value_dist": 0.8605936765670776, "value_other_env": 0.8772847652435303, "value_corner": 0.8355568647384644, "value_row": 0.8534941673278809, "value_any": 0.8772629499435425, "value_bot": 0.855401873588562, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04530.png", "entropy": 0.15783675014972687} +{"ts": "2026-03-20T18:28:37.873878Z", "loop": 4540, "env_steps": 2789376000, "exact_value_avg": 0.8596292734146118, "regret_dist": 0.003951421007514, "regret_other_env": 0.006489899475127459, "regret_corner": 0.00014370333519764245, "regret_row": 0.0049631609581410885, "regret_any": 0.006578995380550623, "regret_bot": 0.005758142098784447, "value_dist": 0.8596292734146118, "value_other_env": 0.8757249712944031, "value_corner": 0.8354856371879578, "value_row": 0.853663444519043, "value_any": 0.8756716251373291, "value_bot": 0.8528684377670288, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04540.png", "entropy": 0.1555119901895523} +{"ts": "2026-03-20T18:28:46.462482Z", "loop": 4550, "env_steps": 2795520000, "exact_value_avg": 0.8590341806411743, "regret_dist": 0.004546512383967638, "regret_other_env": 0.0074529037810862064, "regret_corner": 0.00018692464800551534, "regret_row": 0.0057248324155807495, "regret_any": 0.007512995973229408, "regret_bot": 0.00909088458865881, "value_dist": 0.8590341806411743, "value_other_env": 0.8747619390487671, "value_corner": 0.8354424238204956, "value_row": 0.852901816368103, "value_any": 0.8747376203536987, "value_bot": 0.8495357632637024, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04550.png", "entropy": 0.15797072649002075} +{"ts": "2026-03-20T18:28:55.044947Z", "loop": 4560, "env_steps": 2801664000, "exact_value_avg": 0.8607730865478516, "regret_dist": 0.002807616489008069, "regret_other_env": 0.004375851713120937, "regret_corner": 0.0004552637692540884, "regret_row": 0.005275626666843891, "regret_any": 0.0043972996063530445, "regret_bot": 0.005028194282203913, "value_dist": 0.8607730865478516, "value_other_env": 0.8778390288352966, "value_corner": 0.8351740837097168, "value_row": 0.8533509969711304, "value_any": 0.8778533339500427, "value_bot": 0.8535984754562378, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04560.png", "entropy": 0.16496475040912628} +{"ts": "2026-03-20T18:29:03.629793Z", "loop": 4570, "env_steps": 2807808000, "exact_value_avg": 0.8602120876312256, "regret_dist": 0.003368605626747012, "regret_other_env": 0.005452629178762436, "regret_corner": 0.0002425700513413176, "regret_row": 0.006092017982155085, "regret_any": 0.0054909540340304375, "regret_bot": 0.00882602296769619, "value_dist": 0.8602120876312256, "value_other_env": 0.8767622113227844, "value_corner": 0.8353867530822754, "value_row": 0.8525345921516418, "value_any": 0.8767596483230591, "value_bot": 0.8498005867004395, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04570.png", "entropy": 0.16724935173988342} +{"ts": "2026-03-20T18:29:12.212257Z", "loop": 4580, "env_steps": 2813952000, "exact_value_avg": 0.8578863143920898, "regret_dist": 0.0056944130919873714, "regret_other_env": 0.009439623914659023, "regret_corner": 7.659693801542744e-05, "regret_row": 0.008374610915780067, "regret_any": 0.009534232318401337, "regret_bot": 0.012240721844136715, "value_dist": 0.8578863143920898, "value_other_env": 0.8727752566337585, "value_corner": 0.8355527520179749, "value_row": 0.8502519726753235, "value_any": 0.8727164268493652, "value_bot": 0.8463859558105469, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04580.png", "entropy": 0.15974445641040802} +{"ts": "2026-03-20T18:29:20.800496Z", "loop": 4590, "env_steps": 2820096000, "exact_value_avg": 0.8597375154495239, "regret_dist": 0.0038431789726018906, "regret_other_env": 0.006381932180374861, "regret_corner": 3.504852793412283e-05, "regret_row": 0.009650371968746185, "regret_any": 0.006400969810783863, "regret_bot": 0.006608632858842611, "value_dist": 0.8597375154495239, "value_other_env": 0.8758330345153809, "value_corner": 0.8355942964553833, "value_row": 0.8489762544631958, "value_any": 0.8758496642112732, "value_bot": 0.8520179986953735, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04590.png", "entropy": 0.15577463805675507} +{"ts": "2026-03-20T18:29:29.385195Z", "loop": 4600, "env_steps": 2826240000, "exact_value_avg": 0.8592578768730164, "regret_dist": 0.004322801250964403, "regret_other_env": 0.007004984654486179, "regret_corner": 0.0002995257673319429, "regret_row": 0.007401269394904375, "regret_any": 0.007123718969523907, "regret_bot": 0.00400345167145133, "value_dist": 0.8592578768730164, "value_other_env": 0.8752098679542542, "value_corner": 0.8353298902511597, "value_row": 0.8512253165245056, "value_any": 0.8751268982887268, "value_bot": 0.8546231985092163, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04600.png", "entropy": 0.15226267278194427} +{"ts": "2026-03-20T18:29:37.968496Z", "loop": 4610, "env_steps": 2832384000, "exact_value_avg": 0.8598273992538452, "regret_dist": 0.003753281431272626, "regret_other_env": 0.006237698718905449, "regret_corner": 2.665519787115045e-05, "regret_row": 0.007665503770112991, "regret_any": 0.006271369755268097, "regret_bot": 0.00874093733727932, "value_dist": 0.8598273992538452, "value_other_env": 0.8759771585464478, "value_corner": 0.8356027007102966, "value_row": 0.8509610891342163, "value_any": 0.8759792447090149, "value_bot": 0.8498856425285339, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04610.png", "entropy": 0.1558099240064621} +{"ts": "2026-03-20T18:29:46.553909Z", "loop": 4620, "env_steps": 2838528000, "exact_value_avg": 0.8592269420623779, "regret_dist": 0.004353711381554604, "regret_other_env": 0.007197499740868807, "regret_corner": 8.802861702861264e-05, "regret_row": 0.004607882350683212, "regret_any": 0.007379155606031418, "regret_bot": 0.00523152993991971, "value_dist": 0.8592269420623779, "value_other_env": 0.8750173449516296, "value_corner": 0.835541307926178, "value_row": 0.8540187478065491, "value_any": 0.8748714327812195, "value_bot": 0.8533951044082642, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04620.png", "entropy": 0.15006105601787567} +{"ts": "2026-03-20T18:29:55.136071Z", "loop": 4630, "env_steps": 2844672000, "exact_value_avg": 0.8572272062301636, "regret_dist": 0.006353516131639481, "regret_other_env": 0.010583928786218166, "regret_corner": 7.896622264524922e-06, "regret_row": 0.020779641345143318, "regret_any": 0.010618322528898716, "regret_bot": 0.015038182027637959, "value_dist": 0.8572272062301636, "value_other_env": 0.8716309666633606, "value_corner": 0.8356214165687561, "value_row": 0.8378469347953796, "value_any": 0.8716322183609009, "value_bot": 0.8435885310173035, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04630.png", "entropy": 0.1513359546661377} +{"ts": "2026-03-20T18:30:03.714244Z", "loop": 4640, "env_steps": 2850816000, "exact_value_avg": 0.8592351675033569, "regret_dist": 0.004345542751252651, "regret_other_env": 0.006968168541789055, "regret_corner": 0.0004116043564863503, "regret_row": 0.012308352626860142, "regret_any": 0.007036222144961357, "regret_bot": 0.005739079788327217, "value_dist": 0.8592351675033569, "value_other_env": 0.8752466440200806, "value_corner": 0.8352177143096924, "value_row": 0.846318244934082, "value_any": 0.8752143979072571, "value_bot": 0.8528875112533569, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04640.png", "entropy": 0.15977199375629425} +{"ts": "2026-03-20T18:30:12.298018Z", "loop": 4650, "env_steps": 2856960000, "exact_value_avg": 0.8599572777748108, "regret_dist": 0.003623431548476219, "regret_other_env": 0.005837122444063425, "regret_corner": 0.0003028949140571058, "regret_row": 0.0069737606681883335, "regret_any": 0.005874575115740299, "regret_bot": 0.009253636933863163, "value_dist": 0.8599572777748108, "value_other_env": 0.8763777613639832, "value_corner": 0.8353264331817627, "value_row": 0.8516529202461243, "value_any": 0.8763760328292847, "value_bot": 0.8493729829788208, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04650.png", "entropy": 0.16172689199447632} +{"ts": "2026-03-20T18:30:20.886641Z", "loop": 4660, "env_steps": 2863104000, "exact_value_avg": 0.8604422807693481, "regret_dist": 0.003138457890599966, "regret_other_env": 0.004967209417372942, "regret_corner": 0.0003953303094021976, "regret_row": 0.003018117044121027, "regret_any": 0.004993718583136797, "regret_bot": 0.0023762467317283154, "value_dist": 0.8604422807693481, "value_other_env": 0.87724769115448, "value_corner": 0.8352339863777161, "value_row": 0.8556085228919983, "value_any": 0.8772568702697754, "value_bot": 0.8562503457069397, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04660.png", "entropy": 0.15578307211399078} +{"ts": "2026-03-20T18:30:29.467119Z", "loop": 4670, "env_steps": 2869248000, "exact_value_avg": 0.8615436553955078, "regret_dist": 0.002037063241004944, "regret_other_env": 0.0033174133859574795, "regret_corner": 0.00011653751425910741, "regret_row": 0.003058479633182287, "regret_any": 0.0033381199464201927, "regret_bot": 0.0026186322793364525, "value_dist": 0.8615436553955078, "value_other_env": 0.878897488117218, "value_corner": 0.8355127573013306, "value_row": 0.8555681109428406, "value_any": 0.8789124488830566, "value_bot": 0.8560079336166382, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04670.png", "entropy": 0.1559217870235443} +{"ts": "2026-03-20T18:30:38.048068Z", "loop": 4680, "env_steps": 2875392000, "exact_value_avg": 0.859939455986023, "regret_dist": 0.00364122586324811, "regret_other_env": 0.00538918050006032, "regret_corner": 0.001019293675199151, "regret_row": 0.021258052438497543, "regret_any": 0.0054017482325434685, "regret_bot": 0.002331694820895791, "value_dist": 0.859939455986023, "value_other_env": 0.876825749874115, "value_corner": 0.8346100449562073, "value_row": 0.8373685479164124, "value_any": 0.8768489360809326, "value_bot": 0.8562949299812317, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04680.png", "entropy": 0.16420727968215942} +{"ts": "2026-03-20T18:30:46.631802Z", "loop": 4690, "env_steps": 2881536000, "exact_value_avg": 0.8604981899261475, "regret_dist": 0.003082453506067395, "regret_other_env": 0.004979086574167013, "regret_corner": 0.0002375036565354094, "regret_row": 0.004270315635949373, "regret_any": 0.004984005354344845, "regret_bot": 0.0076674530282616615, "value_dist": 0.8604981899261475, "value_other_env": 0.8772357702255249, "value_corner": 0.8353917598724365, "value_row": 0.8543562889099121, "value_any": 0.8772666454315186, "value_bot": 0.8509591221809387, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04690.png", "entropy": 0.15856504440307617} +{"ts": "2026-03-20T18:30:55.218367Z", "loop": 4700, "env_steps": 2887680000, "exact_value_avg": 0.8611871600151062, "regret_dist": 0.0023935141507536173, "regret_other_env": 0.0038921083323657513, "regret_corner": 0.00014562260184902698, "regret_row": 0.003945300821214914, "regret_any": 0.0039025298319756985, "regret_bot": 0.005251271650195122, "value_dist": 0.8611871600151062, "value_other_env": 0.8783227801322937, "value_corner": 0.8354836702346802, "value_row": 0.8546813726425171, "value_any": 0.8783480525016785, "value_bot": 0.8533753752708435, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04700.png", "entropy": 0.15778830647468567} +{"ts": "2026-03-20T18:31:03.802698Z", "loop": 4710, "env_steps": 2893824000, "exact_value_avg": 0.8591206073760986, "regret_dist": 0.004460064694285393, "regret_other_env": 0.0060796188190579414, "regret_corner": 0.002030733274295926, "regret_row": 0.01393066719174385, "regret_any": 0.006092162802815437, "regret_bot": 0.006237829104065895, "value_dist": 0.8591206073760986, "value_other_env": 0.8761352300643921, "value_corner": 0.8335986137390137, "value_row": 0.844696044921875, "value_any": 0.8761584162712097, "value_bot": 0.852388858795166, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04710.png", "entropy": 0.16966651380062103} +{"ts": "2026-03-20T18:31:12.391057Z", "loop": 4720, "env_steps": 2899968000, "exact_value_avg": 0.8588147163391113, "regret_dist": 0.00476592592895031, "regret_other_env": 0.007672409527003765, "regret_corner": 0.00040619971696287394, "regret_row": 0.0053652748465538025, "regret_any": 0.00772495660930872, "regret_bot": 0.012486151419579983, "value_dist": 0.8588147163391113, "value_other_env": 0.8745424747467041, "value_corner": 0.8352231383323669, "value_row": 0.8532612919807434, "value_any": 0.8745256066322327, "value_bot": 0.8461405038833618, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04720.png", "entropy": 0.17800140380859375} +{"ts": "2026-03-20T18:31:20.974313Z", "loop": 4730, "env_steps": 2906112000, "exact_value_avg": 0.8613594770431519, "regret_dist": 0.0022211840841919184, "regret_other_env": 0.0034538297913968563, "regret_corner": 0.00037221514503471553, "regret_row": 0.0030936275143176317, "regret_any": 0.0034749405458569527, "regret_bot": 0.0031098586041480303, "value_dist": 0.8613594770431519, "value_other_env": 0.8787609934806824, "value_corner": 0.8352570533752441, "value_row": 0.8555330038070679, "value_any": 0.8787756562232971, "value_bot": 0.855516791343689, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04730.png", "entropy": 0.16943666338920593} +{"ts": "2026-03-20T18:31:29.554950Z", "loop": 4740, "env_steps": 2912256000, "exact_value_avg": 0.857734203338623, "regret_dist": 0.005846476182341576, "regret_other_env": 0.009359749034047127, "regret_corner": 0.0005765666719526052, "regret_row": 0.0173004399985075, "regret_any": 0.009355206973850727, "regret_bot": 0.017410768195986748, "value_dist": 0.857734203338623, "value_other_env": 0.8728551268577576, "value_corner": 0.8350527286529541, "value_row": 0.841326117515564, "value_any": 0.872895359992981, "value_bot": 0.8412159085273743, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04740.png", "entropy": 0.1680639535188675} +{"ts": "2026-03-20T18:31:38.137759Z", "loop": 4750, "env_steps": 2918400000, "exact_value_avg": 0.8616714477539062, "regret_dist": 0.0019092480652034283, "regret_other_env": 0.0029375378508120775, "regret_corner": 0.00036681347410194576, "regret_row": 0.0029425444081425667, "regret_any": 0.002962517086416483, "regret_bot": 0.0019491072744131088, "value_dist": 0.8616714477539062, "value_other_env": 0.8792773485183716, "value_corner": 0.8352625370025635, "value_row": 0.8556841015815735, "value_any": 0.8792880177497864, "value_bot": 0.8566775918006897, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04750.png", "entropy": 0.16319748759269714} +{"ts": "2026-03-20T18:31:46.739429Z", "loop": 4760, "env_steps": 2924544000, "exact_value_avg": 0.8601793646812439, "regret_dist": 0.003401351161301136, "regret_other_env": 0.005605658981949091, "regret_corner": 9.488911018706858e-05, "regret_row": 0.005414726212620735, "regret_any": 0.005634305998682976, "regret_bot": 0.009117653593420982, "value_dist": 0.8601793646812439, "value_other_env": 0.876609206199646, "value_corner": 0.8355344533920288, "value_row": 0.8532118797302246, "value_any": 0.8766162395477295, "value_bot": 0.8495090007781982, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04760.png", "entropy": 0.16302625834941864} +{"ts": "2026-03-20T18:31:55.316693Z", "loop": 4770, "env_steps": 2930688000, "exact_value_avg": 0.8603658676147461, "regret_dist": 0.0032149124890565872, "regret_other_env": 0.004870987962931395, "regret_corner": 0.000730798696167767, "regret_row": 0.006203108467161655, "regret_any": 0.00486798444762826, "regret_bot": 0.0052457707934081554, "value_dist": 0.8603658676147461, "value_other_env": 0.8773439526557922, "value_corner": 0.8348985314369202, "value_row": 0.8524235486984253, "value_any": 0.8773826360702515, "value_bot": 0.8533808588981628, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04770.png", "entropy": 0.16737781465053558} +{"ts": "2026-03-20T18:32:03.897566Z", "loop": 4780, "env_steps": 2936832000, "exact_value_avg": 0.8606789112091064, "regret_dist": 0.002901734784245491, "regret_other_env": 0.004490296822041273, "regret_corner": 0.0005188917275518179, "regret_row": 0.005444053094834089, "regret_any": 0.004488837439566851, "regret_bot": 0.005008648615330458, "value_dist": 0.8606789112091064, "value_other_env": 0.8777245879173279, "value_corner": 0.8351103663444519, "value_row": 0.8531826138496399, "value_any": 0.877761721611023, "value_bot": 0.8536179661750793, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04780.png", "entropy": 0.16378861665725708} +{"ts": "2026-03-20T18:32:12.477106Z", "loop": 4790, "env_steps": 2942976000, "exact_value_avg": 0.8612339496612549, "regret_dist": 0.0023467042483389378, "regret_other_env": 0.0038767890073359013, "regret_corner": 5.157639679964632e-05, "regret_row": 0.003953773062676191, "regret_any": 0.0038960580714046955, "regret_bot": 0.004465165548026562, "value_dist": 0.8612339496612549, "value_other_env": 0.878338098526001, "value_corner": 0.8355777263641357, "value_row": 0.8546728491783142, "value_any": 0.8783544898033142, "value_bot": 0.8541614413261414, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04790.png", "entropy": 0.15371063351631165} +{"ts": "2026-03-20T18:32:21.053648Z", "loop": 4800, "env_steps": 2949120000, "exact_value_avg": 0.8583879470825195, "regret_dist": 0.005192701704800129, "regret_other_env": 0.008549581281840801, "regret_corner": 0.0001573820918565616, "regret_row": 0.008626003749668598, "regret_any": 0.008616795763373375, "regret_bot": 0.012540113180875778, "value_dist": 0.8583879470825195, "value_other_env": 0.8736652731895447, "value_corner": 0.8354719877243042, "value_row": 0.8500006198883057, "value_any": 0.8736338019371033, "value_bot": 0.8460865020751953, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04800.png", "entropy": 0.15828989446163177} +{"ts": "2026-03-20T18:32:29.650346Z", "loop": 4810, "env_steps": 2955264000, "exact_value_avg": 0.8598023653030396, "regret_dist": 0.003778348211199045, "regret_other_env": 0.006280440837144852, "regret_corner": 2.5209288651240058e-05, "regret_row": 0.0033979907166212797, "regret_any": 0.0063051884062588215, "regret_bot": 0.009572860784828663, "value_dist": 0.8598023653030396, "value_other_env": 0.8759344816207886, "value_corner": 0.8356041312217712, "value_row": 0.8552286624908447, "value_any": 0.8759453892707825, "value_bot": 0.8490537405014038, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04810.png", "entropy": 0.1511400043964386} +{"ts": "2026-03-20T18:32:38.230521Z", "loop": 4820, "env_steps": 2961408000, "exact_value_avg": 0.8618564009666443, "regret_dist": 0.0017242622561752796, "regret_other_env": 0.0028069030959159136, "regret_corner": 0.00010030071280198172, "regret_row": 0.0029736494179815054, "regret_any": 0.0028189655859023333, "regret_bot": 0.0024425566662102938, "value_dist": 0.8618564009666443, "value_other_env": 0.8794079422950745, "value_corner": 0.8355289697647095, "value_row": 0.855652928352356, "value_any": 0.8794316053390503, "value_bot": 0.8561841249465942, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04820.png", "entropy": 0.153203085064888} +{"ts": "2026-03-20T18:32:46.817366Z", "loop": 4830, "env_steps": 2967552000, "exact_value_avg": 0.8608267307281494, "regret_dist": 0.002753977198153734, "regret_other_env": 0.0039854515343904495, "regret_corner": 0.0009067655191756785, "regret_row": 0.00910534430295229, "regret_any": 0.004004687536507845, "regret_bot": 0.0021893871016800404, "value_dist": 0.8608267307281494, "value_other_env": 0.8782294392585754, "value_corner": 0.8347225785255432, "value_row": 0.8495213389396667, "value_any": 0.8782459497451782, "value_bot": 0.8564372658729553, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04830.png", "entropy": 0.1593737006187439} +{"ts": "2026-03-20T18:32:55.401484Z", "loop": 4840, "env_steps": 2973696000, "exact_value_avg": 0.8600749373435974, "regret_dist": 0.0035057293716818094, "regret_other_env": 0.005682690534740686, "regret_corner": 0.0002402871905360371, "regret_row": 0.011430308222770691, "regret_any": 0.005765336100012064, "regret_bot": 0.0016212386544793844, "value_dist": 0.8600749373435974, "value_other_env": 0.8765321969985962, "value_corner": 0.8353890180587769, "value_row": 0.8471964001655579, "value_any": 0.8764852285385132, "value_bot": 0.8570053577423096, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04840.png", "entropy": 0.15195271372795105} +{"ts": "2026-03-20T18:33:03.977219Z", "loop": 4850, "env_steps": 2979840000, "exact_value_avg": 0.8613312244415283, "regret_dist": 0.0022495018783956766, "regret_other_env": 0.003499309765174985, "regret_corner": 0.00037478955346159637, "regret_row": 0.004011498298496008, "regret_any": 0.0035039789509028196, "regret_bot": 0.0032415299210697412, "value_dist": 0.8613312244415283, "value_other_env": 0.8787155747413635, "value_corner": 0.8352546095848083, "value_row": 0.8546151518821716, "value_any": 0.8787466287612915, "value_bot": 0.8553851246833801, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04850.png", "entropy": 0.1583993136882782} +{"ts": "2026-03-20T18:33:12.566112Z", "loop": 4860, "env_steps": 2985984000, "exact_value_avg": 0.8609545230865479, "regret_dist": 0.002626220928505063, "regret_other_env": 0.004155197646468878, "regret_corner": 0.00033275585155934095, "regret_row": 0.004006273113191128, "regret_any": 0.004157087299972773, "regret_bot": 0.005980228073894978, "value_dist": 0.8609545230865479, "value_other_env": 0.8780596852302551, "value_corner": 0.8352965712547302, "value_row": 0.8546203374862671, "value_any": 0.8780934810638428, "value_bot": 0.8526464104652405, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04860.png", "entropy": 0.15503360331058502} +{"ts": "2026-03-20T18:33:21.152258Z", "loop": 4870, "env_steps": 2992128000, "exact_value_avg": 0.8589907288551331, "regret_dist": 0.0045899758115410805, "regret_other_env": 0.007629400584846735, "regret_corner": 3.0837953090667725e-05, "regret_row": 0.025091229006648064, "regret_any": 0.007646241690963507, "regret_bot": 0.004972507711499929, "value_dist": 0.8589907288551331, "value_other_env": 0.8745854496955872, "value_corner": 0.8355985283851624, "value_row": 0.833535373210907, "value_any": 0.874604344367981, "value_bot": 0.853654146194458, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04870.png", "entropy": 0.15022777020931244} +{"ts": "2026-03-20T18:33:29.739330Z", "loop": 4880, "env_steps": 2998272000, "exact_value_avg": 0.8611620664596558, "regret_dist": 0.002418571151793003, "regret_other_env": 0.003417196450755, "regret_corner": 0.0009206325048580766, "regret_row": 0.0029719576705247164, "regret_any": 0.00343726621940732, "regret_bot": 0.0032142777927219868, "value_dist": 0.8611620664596558, "value_other_env": 0.8787976503372192, "value_corner": 0.8347086906433105, "value_row": 0.8556547164916992, "value_any": 0.8788133263587952, "value_bot": 0.8554123044013977, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04880.png", "entropy": 0.15815865993499756} +{"ts": "2026-03-20T18:33:38.331973Z", "loop": 4890, "env_steps": 3004416000, "exact_value_avg": 0.8619352579116821, "regret_dist": 0.001645460957661271, "regret_other_env": 0.0025862453039735556, "regret_corner": 0.00023428451095242053, "regret_row": 0.0031193236354738474, "regret_any": 0.002619160106405616, "regret_bot": 0.002078372286632657, "value_dist": 0.8619352579116821, "value_other_env": 0.8796286582946777, "value_corner": 0.835395097732544, "value_row": 0.8555073142051697, "value_any": 0.8796314597129822, "value_bot": 0.8565483093261719, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04890.png", "entropy": 0.15446028113365173} +{"ts": "2026-03-20T18:33:46.916014Z", "loop": 4900, "env_steps": 3010560000, "exact_value_avg": 0.8613806962966919, "regret_dist": 0.0021999317687004805, "regret_other_env": 0.003600085387006402, "regret_corner": 9.970118844648823e-05, "regret_row": 0.005812669172883034, "regret_any": 0.0036316774785518646, "regret_bot": 0.002615902805700898, "value_dist": 0.8613806962966919, "value_other_env": 0.8786147832870483, "value_corner": 0.835529625415802, "value_row": 0.8528139591217041, "value_any": 0.8786189556121826, "value_bot": 0.8560107350349426, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04900.png", "entropy": 0.1553770899772644} +{"ts": "2026-03-20T18:33:55.499470Z", "loop": 4910, "env_steps": 3016704000, "exact_value_avg": 0.8599036931991577, "regret_dist": 0.0036769320722669363, "regret_other_env": 0.006018185522407293, "regret_corner": 0.00016505122766830027, "regret_row": 0.012112974189221859, "regret_any": 0.00605674646794796, "regret_bot": 0.012782379984855652, "value_dist": 0.8599036931991577, "value_other_env": 0.8761966824531555, "value_corner": 0.8354642391204834, "value_row": 0.8465136885643005, "value_any": 0.8761938214302063, "value_bot": 0.8458442091941833, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04910.png", "entropy": 0.1549919992685318} +{"ts": "2026-03-20T18:34:04.079182Z", "loop": 4920, "env_steps": 3022848000, "exact_value_avg": 0.8609826564788818, "regret_dist": 0.002598026068881154, "regret_other_env": 0.004296527244150639, "regret_corner": 5.0274036766495556e-05, "regret_row": 0.007108919322490692, "regret_any": 0.004308098927140236, "regret_bot": 0.0029891980811953545, "value_dist": 0.8609826564788818, "value_other_env": 0.8779183626174927, "value_corner": 0.8355790972709656, "value_row": 0.8515177369117737, "value_any": 0.8779425024986267, "value_bot": 0.8556374311447144, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04920.png", "entropy": 0.1497926563024521} +{"ts": "2026-03-20T18:34:12.660647Z", "loop": 4930, "env_steps": 3028992000, "exact_value_avg": 0.8599990606307983, "regret_dist": 0.003581627272069454, "regret_other_env": 0.0059529864229261875, "regret_corner": 2.4587910957052372e-05, "regret_row": 0.007939842529594898, "regret_any": 0.005977245979011059, "regret_bot": 0.006693610921502113, "value_dist": 0.8599990606307983, "value_other_env": 0.8762618899345398, "value_corner": 0.8356047868728638, "value_row": 0.8506867289543152, "value_any": 0.8762733936309814, "value_bot": 0.8519330024719238, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04930.png", "entropy": 0.14786078035831451} +{"ts": "2026-03-20T18:34:21.248397Z", "loop": 4940, "env_steps": 3035136000, "exact_value_avg": 0.8610237836837769, "regret_dist": 0.002556955674663186, "regret_other_env": 0.004222629126161337, "regret_corner": 5.844533734489232e-05, "regret_row": 0.0020666872151196003, "regret_any": 0.004269610159099102, "regret_bot": 0.005545474123209715, "value_dist": 0.8610237836837769, "value_other_env": 0.8779923319816589, "value_corner": 0.8355708718299866, "value_row": 0.8565599322319031, "value_any": 0.8779809474945068, "value_bot": 0.8530811667442322, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04940.png", "entropy": 0.14809727668762207} +{"ts": "2026-03-20T18:34:29.829751Z", "loop": 4950, "env_steps": 3041280000, "exact_value_avg": 0.8587068319320679, "regret_dist": 0.004873879719525576, "regret_other_env": 0.007970786653459072, "regret_corner": 0.00022851825633551925, "regret_row": 0.007108848541975021, "regret_any": 0.00808628648519516, "regret_bot": 0.007828458212316036, "value_dist": 0.8587068319320679, "value_other_env": 0.8742440938949585, "value_corner": 0.8354008197784424, "value_row": 0.8515177965164185, "value_any": 0.8741642832756042, "value_bot": 0.8507981300354004, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04950.png", "entropy": 0.14792507886886597} +{"ts": "2026-03-20T18:34:38.416413Z", "loop": 4960, "env_steps": 3047424000, "exact_value_avg": 0.8599823713302612, "regret_dist": 0.0035982737317681313, "regret_other_env": 0.005682212300598621, "regret_corner": 0.00047236535465344787, "regret_row": 0.006787407677620649, "regret_any": 0.0057350872084498405, "regret_bot": 0.00750328553840518, "value_dist": 0.8599823713302612, "value_other_env": 0.8765326738357544, "value_corner": 0.8351569175720215, "value_row": 0.8518392443656921, "value_any": 0.8765155076980591, "value_bot": 0.8511233925819397, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04960.png", "entropy": 0.15687395632266998} +{"ts": "2026-03-20T18:34:46.999001Z", "loop": 4970, "env_steps": 3053568000, "exact_value_avg": 0.8615467548370361, "regret_dist": 0.0020339747425168753, "regret_other_env": 0.003142708446830511, "regret_corner": 0.00037087404052726924, "regret_row": 0.0037977073807269335, "regret_any": 0.0032081773970276117, "regret_bot": 0.0023063283879309893, "value_dist": 0.8615467548370361, "value_other_env": 0.8790721893310547, "value_corner": 0.835258424282074, "value_row": 0.854828953742981, "value_any": 0.879042387008667, "value_bot": 0.8563202619552612, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04970.png", "entropy": 0.1517818123102188} +{"ts": "2026-03-20T18:34:55.583829Z", "loop": 4980, "env_steps": 3059712000, "exact_value_avg": 0.8614844083786011, "regret_dist": 0.0020962567068636417, "regret_other_env": 0.0034526782110333443, "regret_corner": 6.162425415823236e-05, "regret_row": 0.003458321327343583, "regret_any": 0.003515677759423852, "regret_bot": 0.0022199025843292475, "value_dist": 0.8614844083786011, "value_other_env": 0.8787622451782227, "value_corner": 0.8355676531791687, "value_row": 0.855168342590332, "value_any": 0.8787348866462708, "value_bot": 0.8564067482948303, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04980.png", "entropy": 0.14771422743797302} +{"ts": "2026-03-20T18:35:04.169300Z", "loop": 4990, "env_steps": 3065856000, "exact_value_avg": 0.8604530692100525, "regret_dist": 0.0031276410445570946, "regret_other_env": 0.005158800166100264, "regret_corner": 8.090238407021388e-05, "regret_row": 0.0037175207398831844, "regret_any": 0.005205478984862566, "regret_bot": 0.005120483227074146, "value_dist": 0.8604530692100525, "value_other_env": 0.8770560622215271, "value_corner": 0.835548460483551, "value_row": 0.8549090623855591, "value_any": 0.8770451545715332, "value_bot": 0.8535061478614807, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_04990.png", "entropy": 0.1526464819908142} +{"ts": "2026-03-20T18:35:12.756568Z", "loop": 5000, "env_steps": 3072000000, "exact_value_avg": 0.8592935800552368, "regret_dist": 0.004287195857614279, "regret_other_env": 0.0070048109628260136, "regret_corner": 0.00021077196288388222, "regret_row": 0.005313854198902845, "regret_any": 0.007051241584122181, "regret_bot": 0.00698584970086813, "value_dist": 0.8592935800552368, "value_other_env": 0.8752101063728333, "value_corner": 0.8354186415672302, "value_row": 0.8533127903938293, "value_any": 0.8751993775367737, "value_bot": 0.8516408205032349, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05000.png", "entropy": 0.15957902371883392} +{"ts": "2026-03-20T18:35:21.345071Z", "loop": 5010, "env_steps": 3078144000, "exact_value_avg": 0.85752272605896, "regret_dist": 0.006057970225811005, "regret_other_env": 0.009655820205807686, "regret_corner": 0.0006611953722313046, "regret_row": 0.021534623578190804, "regret_any": 0.009674293920397758, "regret_bot": 0.01802089251577854, "value_dist": 0.85752272605896, "value_other_env": 0.8725590705871582, "value_corner": 0.834968090057373, "value_row": 0.8370919823646545, "value_any": 0.8725762963294983, "value_bot": 0.8406057357788086, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05010.png", "entropy": 0.16004350781440735} +{"ts": "2026-03-20T18:35:29.925974Z", "loop": 5020, "env_steps": 3084288000, "exact_value_avg": 0.859248697757721, "regret_dist": 0.004331971984356642, "regret_other_env": 0.005632034968584776, "regret_corner": 0.002381877740845084, "regret_row": 0.011530491523444653, "regret_any": 0.005626663099974394, "regret_bot": 0.009505178779363632, "value_dist": 0.859248697757721, "value_other_env": 0.8765828609466553, "value_corner": 0.8332474231719971, "value_row": 0.8470960855484009, "value_any": 0.8766239285469055, "value_bot": 0.8491214513778687, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05020.png", "entropy": 0.16867384314537048} +{"ts": "2026-03-20T18:35:38.507038Z", "loop": 5030, "env_steps": 3090432000, "exact_value_avg": 0.8614947199821472, "regret_dist": 0.002085944404825568, "regret_other_env": 0.0034689379390329123, "regret_corner": 1.1454026207502466e-05, "regret_row": 0.0038876959588378668, "regret_any": 0.0034962266217917204, "regret_bot": 0.002818464767187834, "value_dist": 0.8614947199821472, "value_other_env": 0.8787459135055542, "value_corner": 0.8356178998947144, "value_row": 0.8547388911247253, "value_any": 0.8787543773651123, "value_bot": 0.8558081388473511, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05030.png", "entropy": 0.14499811828136444} +{"ts": "2026-03-20T18:35:47.092003Z", "loop": 5040, "env_steps": 3096576000, "exact_value_avg": 0.8613419532775879, "regret_dist": 0.002238800283521414, "regret_other_env": 0.0037209009751677513, "regret_corner": 1.564920057717245e-05, "regret_row": 0.004547967109829187, "regret_any": 0.0037445751950144768, "regret_bot": 0.0026464934926480055, "value_dist": 0.8613419532775879, "value_other_env": 0.8784940242767334, "value_corner": 0.8356136679649353, "value_row": 0.8540785908699036, "value_any": 0.8785059452056885, "value_bot": 0.8559800982475281, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05040.png", "entropy": 0.14313514530658722} +{"ts": "2026-03-20T18:35:55.675255Z", "loop": 5050, "env_steps": 3102720000, "exact_value_avg": 0.8603736162185669, "regret_dist": 0.0032070777378976345, "regret_other_env": 0.005301344208419323, "regret_corner": 6.567737000295892e-05, "regret_row": 0.0077788811177015305, "regret_any": 0.005301794037222862, "regret_bot": 0.013976318761706352, "value_dist": 0.8603736162185669, "value_other_env": 0.8769134879112244, "value_corner": 0.8355636596679688, "value_row": 0.8508477210998535, "value_any": 0.8769488334655762, "value_bot": 0.8446503281593323, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05050.png", "entropy": 0.15190690755844116} +{"ts": "2026-03-20T18:36:04.259123Z", "loop": 5060, "env_steps": 3108864000, "exact_value_avg": 0.8611282110214233, "regret_dist": 0.002452491084113717, "regret_other_env": 0.003914037719368935, "regret_corner": 0.0002601708110887557, "regret_row": 0.0025752861984074116, "regret_any": 0.003928735386580229, "regret_bot": 0.003327918704599142, "value_dist": 0.8611282110214233, "value_other_env": 0.8783008456230164, "value_corner": 0.8353691697120667, "value_row": 0.8560513257980347, "value_any": 0.8783218264579773, "value_bot": 0.8552987575531006, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05060.png", "entropy": 0.1528186798095703} +{"ts": "2026-03-20T18:36:12.848842Z", "loop": 5070, "env_steps": 3115008000, "exact_value_avg": 0.8611754179000854, "regret_dist": 0.002405276522040367, "regret_other_env": 0.003942801617085934, "regret_corner": 9.89884210866876e-05, "regret_row": 0.0023441121447831392, "regret_any": 0.00397139647975564, "regret_bot": 0.005967679899185896, "value_dist": 0.8611754179000854, "value_other_env": 0.8782720565795898, "value_corner": 0.8355304002761841, "value_row": 0.8562825322151184, "value_any": 0.8782792091369629, "value_bot": 0.8526588678359985, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05070.png", "entropy": 0.1537577211856842} +{"ts": "2026-03-20T18:36:21.427176Z", "loop": 5080, "env_steps": 3121152000, "exact_value_avg": 0.8591703176498413, "regret_dist": 0.0044103660620749, "regret_other_env": 0.00732551421970129, "regret_corner": 3.7643316318280995e-05, "regret_row": 0.01687309890985489, "regret_any": 0.007350997533649206, "regret_bot": 0.01094869151711464, "value_dist": 0.8591703176498413, "value_other_env": 0.8748893737792969, "value_corner": 0.8355916738510132, "value_row": 0.8417535424232483, "value_any": 0.8748995661735535, "value_bot": 0.8476778864860535, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05080.png", "entropy": 0.1528472751379013} +{"ts": "2026-03-20T18:36:30.001062Z", "loop": 5090, "env_steps": 3127296000, "exact_value_avg": 0.8562393188476562, "regret_dist": 0.007341325748711824, "regret_other_env": 0.01052330806851387, "regret_corner": 0.0025683508720248938, "regret_row": 0.01802760176360607, "regret_any": 0.010510257445275784, "regret_bot": 0.030204355716705322, "value_dist": 0.8562393188476562, "value_other_env": 0.8716915249824524, "value_corner": 0.8330609798431396, "value_row": 0.8405990600585938, "value_any": 0.8717403411865234, "value_bot": 0.8284223079681396, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05090.png", "entropy": 0.16979597508907318} +{"ts": "2026-03-20T18:36:38.577427Z", "loop": 5100, "env_steps": 3133440000, "exact_value_avg": 0.8596234321594238, "regret_dist": 0.003957265056669712, "regret_other_env": 0.0065650176256895065, "regret_corner": 4.5636297727469355e-05, "regret_row": 0.013832559809088707, "regret_any": 0.006583647336810827, "regret_bot": 0.008550393395125866, "value_dist": 0.8596234321594238, "value_other_env": 0.8756498694419861, "value_corner": 0.8355837464332581, "value_row": 0.8447940349578857, "value_any": 0.8756669163703918, "value_bot": 0.8500761985778809, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05100.png", "entropy": 0.1510951817035675} +{"ts": "2026-03-20T18:36:47.163857Z", "loop": 5110, "env_steps": 3139584000, "exact_value_avg": 0.8578161597251892, "regret_dist": 0.005764493253082037, "regret_other_env": 0.00948304682970047, "regret_corner": 0.00018666288815438747, "regret_row": 0.020182650536298752, "regret_any": 0.00958262663334608, "regret_bot": 0.009060755372047424, "value_dist": 0.8578161597251892, "value_other_env": 0.8727318048477173, "value_corner": 0.8354426622390747, "value_row": 0.8384439945220947, "value_any": 0.8726679682731628, "value_bot": 0.849565863609314, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05110.png", "entropy": 0.15664580464363098} +{"ts": "2026-03-20T18:36:55.752928Z", "loop": 5120, "env_steps": 3145728000, "exact_value_avg": 0.8616888523101807, "regret_dist": 0.001891855150461197, "regret_other_env": 0.003134225495159626, "regret_corner": 2.8299293262534775e-05, "regret_row": 0.004845116753131151, "regret_any": 0.0031509767286479473, "regret_bot": 0.0035343547351658344, "value_dist": 0.8616888523101807, "value_other_env": 0.8790807127952576, "value_corner": 0.8356010317802429, "value_row": 0.8537814617156982, "value_any": 0.8790996670722961, "value_bot": 0.8550923466682434, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05120.png", "entropy": 0.1527891904115677} +{"ts": "2026-03-20T18:37:04.336404Z", "loop": 5130, "env_steps": 3151872000, "exact_value_avg": 0.8611584901809692, "regret_dist": 0.0024222631473094225, "regret_other_env": 0.004016794729977846, "regret_corner": 3.0465425879810937e-05, "regret_row": 0.0059037418104708195, "regret_any": 0.004039220046252012, "regret_bot": 0.00558119872584939, "value_dist": 0.8611584901809692, "value_other_env": 0.8781980872154236, "value_corner": 0.835598886013031, "value_row": 0.8527228832244873, "value_any": 0.8782113790512085, "value_bot": 0.8530454635620117, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05130.png", "entropy": 0.1546270102262497} +{"ts": "2026-03-20T18:37:12.917545Z", "loop": 5140, "env_steps": 3158016000, "exact_value_avg": 0.8611738681793213, "regret_dist": 0.002406761283054948, "regret_other_env": 0.003970344550907612, "regret_corner": 6.138633034424856e-05, "regret_row": 0.002840795088559389, "regret_any": 0.003996951039880514, "regret_bot": 0.00802993681281805, "value_dist": 0.8611738681793213, "value_other_env": 0.8782445192337036, "value_corner": 0.8355678915977478, "value_row": 0.8557858467102051, "value_any": 0.8782536387443542, "value_bot": 0.8505967259407043, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05140.png", "entropy": 0.15692821145057678} +{"ts": "2026-03-20T18:37:21.497300Z", "loop": 5150, "env_steps": 3164160000, "exact_value_avg": 0.8620903491973877, "regret_dist": 0.0014903424307703972, "regret_other_env": 0.002376511227339506, "regret_corner": 0.00016108901763800532, "regret_row": 0.0019359642174094915, "regret_any": 0.0024000450503081083, "regret_bot": 0.0035435755271464586, "value_dist": 0.8620903491973877, "value_other_env": 0.8798383474349976, "value_corner": 0.8354682326316833, "value_row": 0.8566907048225403, "value_any": 0.8798505663871765, "value_bot": 0.8550831079483032, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05150.png", "entropy": 0.1570802628993988} +{"ts": "2026-03-20T18:37:30.078564Z", "loop": 5160, "env_steps": 3170304000, "exact_value_avg": 0.8567764759063721, "regret_dist": 0.006804260425269604, "regret_other_env": 0.009586851112544537, "regret_corner": 0.00263037346303463, "regret_row": 0.012115693651139736, "regret_any": 0.009577244520187378, "regret_bot": 0.013912723399698734, "value_dist": 0.8567764759063721, "value_other_env": 0.8726280331611633, "value_corner": 0.8329989314079285, "value_row": 0.8465110063552856, "value_any": 0.8726733922958374, "value_bot": 0.8447139859199524, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05160.png", "entropy": 0.16954362392425537} +{"ts": "2026-03-20T18:37:38.661076Z", "loop": 5170, "env_steps": 3176448000, "exact_value_avg": 0.8619506359100342, "regret_dist": 0.001630099955946207, "regret_other_env": 0.0027008350007236004, "regret_corner": 2.3997328753466718e-05, "regret_row": 0.004536137450486422, "regret_any": 0.0027141915634274483, "regret_bot": 0.002285715891048312, "value_dist": 0.8619506359100342, "value_other_env": 0.8795140981674194, "value_corner": 0.8356053233146667, "value_row": 0.8540904521942139, "value_any": 0.8795363903045654, "value_bot": 0.8563409447669983, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05170.png", "entropy": 0.1526271402835846} +{"ts": "2026-03-20T18:37:47.241384Z", "loop": 5180, "env_steps": 3182592000, "exact_value_avg": 0.8605142831802368, "regret_dist": 0.003066436154767871, "regret_other_env": 0.005091833882033825, "regret_corner": 2.8339029086055234e-05, "regret_row": 0.0022683043498545885, "regret_any": 0.005129250232130289, "regret_bot": 0.009302097372710705, "value_dist": 0.8605142831802368, "value_other_env": 0.8771229982376099, "value_corner": 0.8356010317802429, "value_row": 0.8563583493232727, "value_any": 0.8771213889122009, "value_bot": 0.8493245244026184, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05180.png", "entropy": 0.15248440206050873} +{"ts": "2026-03-20T18:37:55.815925Z", "loop": 5190, "env_steps": 3188736000, "exact_value_avg": 0.8612884283065796, "regret_dist": 0.0022921781055629253, "regret_other_env": 0.003808105131611228, "regret_corner": 1.8287202692590654e-05, "regret_row": 0.002997772069647908, "regret_any": 0.003830853383988142, "regret_bot": 0.0052964650094509125, "value_dist": 0.8612884283065796, "value_other_env": 0.8784067630767822, "value_corner": 0.8356109857559204, "value_row": 0.8556289076805115, "value_any": 0.8784197568893433, "value_bot": 0.8533301949501038, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05190.png", "entropy": 0.14886292815208435} +{"ts": "2026-03-20T18:38:04.393954Z", "loop": 5200, "env_steps": 3194880000, "exact_value_avg": 0.8617672920227051, "regret_dist": 0.0018134238198399544, "regret_other_env": 0.002942025661468506, "regret_corner": 0.00012052109377691522, "regret_row": 0.00952888559550047, "regret_any": 0.002969360677525401, "regret_bot": 0.002011004136875272, "value_dist": 0.8617672920227051, "value_other_env": 0.8792728781700134, "value_corner": 0.8355087637901306, "value_row": 0.8490977883338928, "value_any": 0.879281222820282, "value_bot": 0.8566156029701233, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05200.png", "entropy": 0.1492057889699936} +{"ts": "2026-03-20T18:38:12.987848Z", "loop": 5210, "env_steps": 3201024000, "exact_value_avg": 0.860835075378418, "regret_dist": 0.0027456101961433887, "regret_other_env": 0.004517674446105957, "regret_corner": 8.751353016123176e-05, "regret_row": 0.0019648426678031683, "regret_any": 0.004559711087495089, "regret_bot": 0.01379087008535862, "value_dist": 0.860835075378418, "value_other_env": 0.877697229385376, "value_corner": 0.835541844367981, "value_row": 0.8566617965698242, "value_any": 0.8776909112930298, "value_bot": 0.8448357582092285, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05210.png", "entropy": 0.15575408935546875} +{"ts": "2026-03-20T18:38:21.572203Z", "loop": 5220, "env_steps": 3207168000, "exact_value_avg": 0.8617124557495117, "regret_dist": 0.0018682758091017604, "regret_other_env": 0.002898606937378645, "regret_corner": 0.0003227790293749422, "regret_row": 0.00312633253633976, "regret_any": 0.00293047190643847, "regret_bot": 0.0017719506286084652, "value_dist": 0.8617124557495117, "value_other_env": 0.8793163299560547, "value_corner": 0.8353065848350525, "value_row": 0.8555002808570862, "value_any": 0.8793202042579651, "value_bot": 0.8568546772003174, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05220.png", "entropy": 0.15274231135845184} +{"ts": "2026-03-20T18:38:30.157640Z", "loop": 5230, "env_steps": 3213312000, "exact_value_avg": 0.8601802587509155, "regret_dist": 0.0034004838671535254, "regret_other_env": 0.00564922159537673, "regret_corner": 2.7376911020837724e-05, "regret_row": 0.01720239780843258, "regret_any": 0.0056709591299295425, "regret_bot": 0.006820763926953077, "value_dist": 0.8601802587509155, "value_other_env": 0.87656569480896, "value_corner": 0.8356019854545593, "value_row": 0.8414242267608643, "value_any": 0.8765796422958374, "value_bot": 0.8518058657646179, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05230.png", "entropy": 0.14687570929527283} +{"ts": "2026-03-20T18:38:38.738197Z", "loop": 5240, "env_steps": 3219456000, "exact_value_avg": 0.860131025314331, "regret_dist": 0.003449707292020321, "regret_other_env": 0.005369928665459156, "regret_corner": 0.0005693748826161027, "regret_row": 0.011545835062861443, "regret_any": 0.005433659069240093, "regret_bot": 0.0020044867414981127, "value_dist": 0.860131025314331, "value_other_env": 0.8768449425697327, "value_corner": 0.8350600004196167, "value_row": 0.8470808267593384, "value_any": 0.876816987991333, "value_bot": 0.8566220998764038, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05240.png", "entropy": 0.15546509623527527} +{"ts": "2026-03-20T18:38:47.318231Z", "loop": 5250, "env_steps": 3225600000, "exact_value_avg": 0.8613477349281311, "regret_dist": 0.00223292363807559, "regret_other_env": 0.003650682047009468, "regret_corner": 0.0001062860173988156, "regret_row": 0.003924539312720299, "regret_any": 0.003654185449704528, "regret_bot": 0.006924198940396309, "value_dist": 0.8613477349281311, "value_other_env": 0.878564178943634, "value_corner": 0.8355230093002319, "value_row": 0.8547020554542542, "value_any": 0.8785964250564575, "value_bot": 0.8517025113105774, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05250.png", "entropy": 0.15327143669128418} +{"ts": "2026-03-20T18:38:55.901299Z", "loop": 5260, "env_steps": 3231744000, "exact_value_avg": 0.8599086403846741, "regret_dist": 0.003672068240121007, "regret_other_env": 0.006069294176995754, "regret_corner": 7.622888369951397e-05, "regret_row": 0.003336974885314703, "regret_any": 0.006093678064644337, "regret_bot": 0.01704305224120617, "value_dist": 0.8599086403846741, "value_other_env": 0.876145601272583, "value_corner": 0.8355531096458435, "value_row": 0.8552896976470947, "value_any": 0.8761569857597351, "value_bot": 0.8415836095809937, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05260.png", "entropy": 0.15199199318885803} +{"ts": "2026-03-20T18:39:04.483600Z", "loop": 5270, "env_steps": 3237888000, "exact_value_avg": 0.8595609664916992, "regret_dist": 0.0040197125636041164, "regret_other_env": 0.006488151848316193, "regret_corner": 0.00031705302535556257, "regret_row": 0.017166970297694206, "regret_any": 0.0065524997189641, "regret_bot": 0.0015951159875839949, "value_dist": 0.8595609664916992, "value_other_env": 0.8757266998291016, "value_corner": 0.8353123068809509, "value_row": 0.8414596915245056, "value_any": 0.8756981492042542, "value_bot": 0.857031524181366, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05270.png", "entropy": 0.14607039093971252} +{"ts": "2026-03-20T18:39:13.061297Z", "loop": 5280, "env_steps": 3244032000, "exact_value_avg": 0.861126184463501, "regret_dist": 0.0024545739870518446, "regret_other_env": 0.004029376897960901, "regret_corner": 9.236932237399742e-05, "regret_row": 0.0032353876158595085, "regret_any": 0.00406586704775691, "regret_bot": 0.00404201028868556, "value_dist": 0.861126184463501, "value_other_env": 0.8781855702400208, "value_corner": 0.8355370163917542, "value_row": 0.8553912043571472, "value_any": 0.8781847357749939, "value_bot": 0.8545846343040466, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05280.png", "entropy": 0.14521001279354095} +{"ts": "2026-03-20T18:39:21.646504Z", "loop": 5290, "env_steps": 3250176000, "exact_value_avg": 0.8621368408203125, "regret_dist": 0.0014439040096476674, "regret_other_env": 0.0023446446284651756, "regret_corner": 9.279301593778655e-05, "regret_row": 0.001606450998224318, "regret_any": 0.002365345833823085, "regret_bot": 0.0038310966920107603, "value_dist": 0.8621368408203125, "value_other_env": 0.8798702955245972, "value_corner": 0.835536539554596, "value_row": 0.8570201396942139, "value_any": 0.8798852562904358, "value_bot": 0.854795515537262, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05290.png", "entropy": 0.14642082154750824} +{"ts": "2026-03-20T18:39:30.228607Z", "loop": 5300, "env_steps": 3256320000, "exact_value_avg": 0.8604946732521057, "regret_dist": 0.0030860155820846558, "regret_other_env": 0.0048176622949540615, "regret_corner": 0.0004885450471192598, "regret_row": 0.0027404932770878077, "regret_any": 0.004819988273084164, "regret_bot": 0.011381668038666248, "value_dist": 0.8604946732521057, "value_other_env": 0.8773972392082214, "value_corner": 0.8351407647132874, "value_row": 0.8558861613273621, "value_any": 0.8774306178092957, "value_bot": 0.8472449779510498, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05300.png", "entropy": 0.14968028664588928} +{"ts": "2026-03-20T18:39:38.807897Z", "loop": 5310, "env_steps": 3262464000, "exact_value_avg": 0.8619804382324219, "regret_dist": 0.0016002972843125463, "regret_other_env": 0.0025408887304365635, "regret_corner": 0.00018941015878226608, "regret_row": 0.002094924682751298, "regret_any": 0.00256208423525095, "regret_bot": 0.0018111865501850843, "value_dist": 0.8619804382324219, "value_other_env": 0.8796740174293518, "value_corner": 0.835439920425415, "value_row": 0.8565317392349243, "value_any": 0.8796885013580322, "value_bot": 0.8568154573440552, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05310.png", "entropy": 0.14477986097335815} +{"ts": "2026-03-20T18:39:47.387597Z", "loop": 5320, "env_steps": 3268608000, "exact_value_avg": 0.8542013168334961, "regret_dist": 0.009379337541759014, "regret_other_env": 0.0156206414103508, "regret_corner": 1.7381707948516123e-05, "regret_row": 0.028049973770976067, "regret_any": 0.015677444636821747, "regret_bot": 0.031707052141427994, "value_dist": 0.8542013168334961, "value_other_env": 0.8665942549705505, "value_corner": 0.835611879825592, "value_row": 0.8305766582489014, "value_any": 0.8665732145309448, "value_bot": 0.8269196152687073, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05320.png", "entropy": 0.14567893743515015} +{"ts": "2026-03-20T18:39:55.969401Z", "loop": 5330, "env_steps": 3274752000, "exact_value_avg": 0.8575769662857056, "regret_dist": 0.006003732793033123, "regret_other_env": 0.009707564488053322, "regret_corner": 0.0004479850467760116, "regret_row": 0.004057115875184536, "regret_any": 0.009760393761098385, "regret_bot": 0.004148127511143684, "value_dist": 0.8575769662857056, "value_other_env": 0.8725073337554932, "value_corner": 0.8351813554763794, "value_row": 0.8545694947242737, "value_any": 0.8724902272224426, "value_bot": 0.8544785380363464, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05330.png", "entropy": 0.15280187129974365} +{"ts": "2026-03-20T18:40:04.552906Z", "loop": 5340, "env_steps": 3280896000, "exact_value_avg": 0.8603436350822449, "regret_dist": 0.003237081691622734, "regret_other_env": 0.005324322730302811, "regret_corner": 0.00010621995170367882, "regret_row": 0.00973205454647541, "regret_any": 0.00532910693436861, "regret_bot": 0.0053932759910821915, "value_dist": 0.8603436350822449, "value_other_env": 0.8768905997276306, "value_corner": 0.8355231285095215, "value_row": 0.8488945960998535, "value_any": 0.876921534538269, "value_bot": 0.8532333374023438, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05340.png", "entropy": 0.15684868395328522} +{"ts": "2026-03-20T18:40:13.140288Z", "loop": 5350, "env_steps": 3287040000, "exact_value_avg": 0.8611428737640381, "regret_dist": 0.002437824849039316, "regret_other_env": 0.0035825232043862343, "regret_corner": 0.0007207771413959563, "regret_row": 0.003746872767806053, "regret_any": 0.0035841267090290785, "regret_bot": 0.004002258647233248, "value_dist": 0.8611428737640381, "value_other_env": 0.8786323666572571, "value_corner": 0.8349086046218872, "value_row": 0.8548797965049744, "value_any": 0.8786664605140686, "value_bot": 0.8546243906021118, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05350.png", "entropy": 0.16488565504550934} +{"ts": "2026-03-20T18:40:21.727118Z", "loop": 5360, "env_steps": 3293184000, "exact_value_avg": 0.8617141842842102, "regret_dist": 0.0018665038514882326, "regret_other_env": 0.0029769784305244684, "regret_corner": 0.00020079166279174387, "regret_row": 0.0031415624544024467, "regret_any": 0.003003107849508524, "regret_bot": 0.001351960119791329, "value_dist": 0.8617141842842102, "value_other_env": 0.8792378902435303, "value_corner": 0.8354285359382629, "value_row": 0.8554850816726685, "value_any": 0.8792474865913391, "value_bot": 0.8572746515274048, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05360.png", "entropy": 0.15503215789794922} +{"ts": "2026-03-20T18:40:30.318952Z", "loop": 5370, "env_steps": 3299328000, "exact_value_avg": 0.8596268892288208, "regret_dist": 0.003953846637159586, "regret_other_env": 0.006407285574823618, "regret_corner": 0.0002736881433520466, "regret_row": 0.014276083558797836, "regret_any": 0.006495388224720955, "regret_bot": 0.0032451802399009466, "value_dist": 0.8596268892288208, "value_other_env": 0.8758076429367065, "value_corner": 0.8353556990623474, "value_row": 0.8443505167961121, "value_any": 0.8757551908493042, "value_bot": 0.855381429195404, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05370.png", "entropy": 0.1567472666501999} +{"ts": "2026-03-20T18:40:38.895524Z", "loop": 5380, "env_steps": 3305472000, "exact_value_avg": 0.8620941638946533, "regret_dist": 0.0014865288976579905, "regret_other_env": 0.0024185716174542904, "regret_corner": 8.846472337609157e-05, "regret_row": 0.002594637917354703, "regret_any": 0.002446163911372423, "regret_bot": 0.0018150227842852473, "value_dist": 0.8620941638946533, "value_other_env": 0.8797963261604309, "value_corner": 0.8355408310890198, "value_row": 0.8560320138931274, "value_any": 0.8798044323921204, "value_bot": 0.8568115830421448, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05380.png", "entropy": 0.14997512102127075} +{"ts": "2026-03-20T18:40:47.471974Z", "loop": 5390, "env_steps": 3311616000, "exact_value_avg": 0.86238032579422, "regret_dist": 0.0012003593146800995, "regret_other_env": 0.0019524755189195275, "regret_corner": 7.218470273073763e-05, "regret_row": 0.0013665866572409868, "regret_any": 0.0019754457753151655, "regret_bot": 0.002198448870331049, "value_dist": 0.86238032579422, "value_other_env": 0.8802624344825745, "value_corner": 0.8355571031570435, "value_row": 0.85725998878479, "value_any": 0.8802751302719116, "value_bot": 0.8564282655715942, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05390.png", "entropy": 0.14668408036231995} +{"ts": "2026-03-20T18:40:56.052851Z", "loop": 5400, "env_steps": 3317760000, "exact_value_avg": 0.8619427680969238, "regret_dist": 0.001637913752347231, "regret_other_env": 0.0026872139424085617, "regret_corner": 6.396323442459106e-05, "regret_row": 0.004105198662728071, "regret_any": 0.0027081503067165613, "regret_bot": 0.0033187265507876873, "value_dist": 0.8619427680969238, "value_other_env": 0.8795276880264282, "value_corner": 0.8355653285980225, "value_row": 0.8545213937759399, "value_any": 0.8795424699783325, "value_bot": 0.8553078770637512, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05400.png", "entropy": 0.15104839205741882} +{"ts": "2026-03-20T18:41:04.635325Z", "loop": 5410, "env_steps": 3323904000, "exact_value_avg": 0.8617031574249268, "regret_dist": 0.0018775201169773936, "regret_other_env": 0.0029009212739765644, "regret_corner": 0.00034241826506331563, "regret_row": 0.0024577733129262924, "regret_any": 0.0029256248380988836, "regret_bot": 0.0019908419344574213, "value_dist": 0.8617031574249268, "value_other_env": 0.8793139457702637, "value_corner": 0.8352868556976318, "value_row": 0.8561688661575317, "value_any": 0.8793250322341919, "value_bot": 0.8566358089447021, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05410.png", "entropy": 0.1524468958377838} +{"ts": "2026-03-20T18:41:13.223719Z", "loop": 5420, "env_steps": 3330048000, "exact_value_avg": 0.8567387461662292, "regret_dist": 0.006841940339654684, "regret_other_env": 0.011174969375133514, "regret_corner": 0.0003423964080866426, "regret_row": 0.005620767828077078, "regret_any": 0.011248516850173473, "regret_bot": 0.015724433586001396, "value_dist": 0.8567387461662292, "value_other_env": 0.8710399270057678, "value_corner": 0.8352869749069214, "value_row": 0.8530058860778809, "value_any": 0.8710020184516907, "value_bot": 0.8429022431373596, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05420.png", "entropy": 0.15239383280277252} +{"ts": "2026-03-20T18:41:21.808642Z", "loop": 5430, "env_steps": 3336192000, "exact_value_avg": 0.8599497079849243, "regret_dist": 0.00363095011562109, "regret_other_env": 0.005846888292580843, "regret_corner": 0.00030704241362400353, "regret_row": 0.003700320841744542, "regret_any": 0.005893847439438105, "regret_bot": 0.006653119344264269, "value_dist": 0.8599497079849243, "value_other_env": 0.87636798620224, "value_corner": 0.8353222608566284, "value_row": 0.8549262285232544, "value_any": 0.8763567209243774, "value_bot": 0.8519735336303711, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05430.png", "entropy": 0.15145517885684967} +{"ts": "2026-03-20T18:41:30.386392Z", "loop": 5440, "env_steps": 3342336000, "exact_value_avg": 0.8621481657028198, "regret_dist": 0.0014324872754514217, "regret_other_env": 0.002306085079908371, "regret_corner": 0.00012209068518131971, "regret_row": 0.003178143873810768, "regret_any": 0.002327388385310769, "regret_bot": 0.002197584602981806, "value_dist": 0.8621481657028198, "value_other_env": 0.8799088001251221, "value_corner": 0.8355072736740112, "value_row": 0.8554485440254211, "value_any": 0.8799232244491577, "value_bot": 0.8564291000366211, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05440.png", "entropy": 0.15303003787994385} +{"ts": "2026-03-20T18:41:38.966692Z", "loop": 5450, "env_steps": 3348480000, "exact_value_avg": 0.8616122007369995, "regret_dist": 0.001968464581295848, "regret_other_env": 0.0031857748981565237, "regret_corner": 0.0001424988149665296, "regret_row": 0.0032896059565246105, "regret_any": 0.0032070414163172245, "regret_bot": 0.001756321988068521, "value_dist": 0.8616122007369995, "value_other_env": 0.8790290951728821, "value_corner": 0.8354868292808533, "value_row": 0.8553370237350464, "value_any": 0.8790436387062073, "value_bot": 0.8568702936172485, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05450.png", "entropy": 0.15057896077632904} +{"ts": "2026-03-20T18:41:47.547174Z", "loop": 5460, "env_steps": 3354624000, "exact_value_avg": 0.8595873117446899, "regret_dist": 0.003993379883468151, "regret_other_env": 0.0062790559604763985, "regret_corner": 0.0005648647784255445, "regret_row": 0.0055505274794995785, "regret_any": 0.006314399186521769, "regret_bot": 0.0025407893117517233, "value_dist": 0.8595873117446899, "value_other_env": 0.8759358525276184, "value_corner": 0.8350644707679749, "value_row": 0.853076159954071, "value_any": 0.8759361505508423, "value_bot": 0.8560858368873596, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05460.png", "entropy": 0.15876828134059906} +{"ts": "2026-03-20T18:41:56.132011Z", "loop": 5470, "env_steps": 3360768000, "exact_value_avg": 0.860938310623169, "regret_dist": 0.002642399398609996, "regret_other_env": 0.004219480324536562, "regret_corner": 0.00027677815523929894, "regret_row": 0.006274789571762085, "regret_any": 0.004241501912474632, "regret_bot": 0.006346040405333042, "value_dist": 0.860938310623169, "value_other_env": 0.8779954314231873, "value_corner": 0.8353525400161743, "value_row": 0.8523518443107605, "value_any": 0.8780090808868408, "value_bot": 0.8522805571556091, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05470.png", "entropy": 0.1594349443912506} +{"ts": "2026-03-20T18:42:04.712135Z", "loop": 5480, "env_steps": 3366912000, "exact_value_avg": 0.8619540929794312, "regret_dist": 0.0016265354352071881, "regret_other_env": 0.0025887037627398968, "regret_corner": 0.00018328279838897288, "regret_row": 0.0032523074187338352, "regret_any": 0.002609135350212455, "regret_bot": 0.002958989702165127, "value_dist": 0.8619540929794312, "value_other_env": 0.8796261548995972, "value_corner": 0.8354460000991821, "value_row": 0.855374276638031, "value_any": 0.8796414732933044, "value_bot": 0.8556676506996155, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05480.png", "entropy": 0.1542767435312271} +{"ts": "2026-03-20T18:42:13.295067Z", "loop": 5490, "env_steps": 3373056000, "exact_value_avg": 0.859950065612793, "regret_dist": 0.0036306295078247786, "regret_other_env": 0.005432646255940199, "regret_corner": 0.0009276042692363262, "regret_row": 0.0034968352410942316, "regret_any": 0.0054367780685424805, "regret_bot": 0.0031712364871054888, "value_dist": 0.859950065612793, "value_other_env": 0.8767822980880737, "value_corner": 0.8347017168998718, "value_row": 0.8551297783851624, "value_any": 0.8768138289451599, "value_bot": 0.8554553985595703, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05490.png", "entropy": 0.15622444450855255} +{"ts": "2026-03-20T18:42:21.879750Z", "loop": 5500, "env_steps": 3379200000, "exact_value_avg": 0.8617553114891052, "regret_dist": 0.001825380721129477, "regret_other_env": 0.002889331430196762, "regret_corner": 0.00022945455566514283, "regret_row": 0.004466878715902567, "regret_any": 0.0029043464455753565, "regret_bot": 0.0032897437922656536, "value_dist": 0.8617553114891052, "value_other_env": 0.8793255686759949, "value_corner": 0.8353999257087708, "value_row": 0.8541597723960876, "value_any": 0.8793462514877319, "value_bot": 0.8553368449211121, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05500.png", "entropy": 0.15266671776771545} +{"ts": "2026-03-20T18:42:30.458556Z", "loop": 5510, "env_steps": 3385344000, "exact_value_avg": 0.861440896987915, "regret_dist": 0.0021397899836301804, "regret_other_env": 0.0034054401330649853, "regret_corner": 0.00024131438112817705, "regret_row": 0.0028903840575367212, "regret_any": 0.003432854311540723, "regret_bot": 0.0021576464641839266, "value_dist": 0.861440896987915, "value_other_env": 0.8788094520568848, "value_corner": 0.8353879451751709, "value_row": 0.8557361960411072, "value_any": 0.8788177967071533, "value_bot": 0.8564689755439758, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05510.png", "entropy": 0.14923973381519318} +{"ts": "2026-03-20T18:42:39.037736Z", "loop": 5520, "env_steps": 3391488000, "exact_value_avg": 0.8607219457626343, "regret_dist": 0.0028587656561285257, "regret_other_env": 0.004598656203597784, "regret_corner": 0.00024892986402846873, "regret_row": 0.0049294070340693, "regret_any": 0.00463611725717783, "regret_bot": 0.0020382024813443422, "value_dist": 0.8607219457626343, "value_other_env": 0.8776161670684814, "value_corner": 0.8353804349899292, "value_row": 0.8536972403526306, "value_any": 0.8776144981384277, "value_bot": 0.8565884232521057, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05520.png", "entropy": 0.1481604129076004} +{"ts": "2026-03-20T18:42:47.620725Z", "loop": 5530, "env_steps": 3397632000, "exact_value_avg": 0.859959602355957, "regret_dist": 0.003621070645749569, "regret_other_env": 0.006024499889463186, "regret_corner": 1.5926361811580136e-05, "regret_row": 0.010023827664554119, "regret_any": 0.006054969038814306, "regret_bot": 0.012414663098752499, "value_dist": 0.859959602355957, "value_other_env": 0.8761903643608093, "value_corner": 0.8356133699417114, "value_row": 0.848602831363678, "value_any": 0.8761956095695496, "value_bot": 0.8462120294570923, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05530.png", "entropy": 0.14436468482017517} +{"ts": "2026-03-20T18:42:56.197038Z", "loop": 5540, "env_steps": 3403776000, "exact_value_avg": 0.8624460697174072, "regret_dist": 0.001134598278440535, "regret_other_env": 0.0018463984597474337, "regret_corner": 6.689777364954352e-05, "regret_row": 0.0017617461271584034, "regret_any": 0.0018695959588512778, "regret_bot": 0.0018489878857508302, "value_dist": 0.8624460697174072, "value_other_env": 0.8803684711456299, "value_corner": 0.8355624079704285, "value_row": 0.856864869594574, "value_any": 0.8803809881210327, "value_bot": 0.8567776679992676, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05540.png", "entropy": 0.14652514457702637} +{"ts": "2026-03-20T18:43:04.777441Z", "loop": 5550, "env_steps": 3409920000, "exact_value_avg": 0.8616605997085571, "regret_dist": 0.0019201295217499137, "regret_other_env": 0.003085555974394083, "regret_corner": 0.00017198971181642264, "regret_row": 0.0026510083116590977, "regret_any": 0.0031216617207974195, "regret_bot": 0.0014200849691405892, "value_dist": 0.8616605997085571, "value_other_env": 0.8791293501853943, "value_corner": 0.8354573249816895, "value_row": 0.8559755682945251, "value_any": 0.8791288733482361, "value_bot": 0.8572065830230713, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05550.png", "entropy": 0.1486758589744568} +{"ts": "2026-03-20T18:43:13.365383Z", "loop": 5560, "env_steps": 3416064000, "exact_value_avg": 0.8617159724235535, "regret_dist": 0.00186470418702811, "regret_other_env": 0.0029689210932701826, "regret_corner": 0.00020837884221691638, "regret_row": 0.0023860514629632235, "regret_any": 0.0029971636831760406, "regret_bot": 0.0013736276887357235, "value_dist": 0.8617159724235535, "value_other_env": 0.8792459964752197, "value_corner": 0.8354209065437317, "value_row": 0.8562405109405518, "value_any": 0.8792534470558167, "value_bot": 0.8572529554367065, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05560.png", "entropy": 0.15012653172016144} +{"ts": "2026-03-20T18:43:21.945440Z", "loop": 5570, "env_steps": 3422208000, "exact_value_avg": 0.8615947961807251, "regret_dist": 0.0019858814775943756, "regret_other_env": 0.0032916830386966467, "regret_corner": 2.7178726668353193e-05, "regret_row": 0.0072561949491500854, "regret_any": 0.003311834065243602, "regret_bot": 0.003917837515473366, "value_dist": 0.8615947961807251, "value_other_env": 0.878923237323761, "value_corner": 0.8356021642684937, "value_row": 0.8513703942298889, "value_any": 0.8789387941360474, "value_bot": 0.8547088503837585, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05570.png", "entropy": 0.14687488973140717} +{"ts": "2026-03-20T18:43:30.526261Z", "loop": 5580, "env_steps": 3428352000, "exact_value_avg": 0.8486915230751038, "regret_dist": 0.014889146201312542, "regret_other_env": 0.02389112487435341, "regret_corner": 0.0013861756306141615, "regret_row": 0.0493561252951622, "regret_any": 0.024074893444776535, "regret_bot": 0.0013396426802501082, "value_dist": 0.8486915230751038, "value_other_env": 0.8583237528800964, "value_corner": 0.83424311876297, "value_row": 0.8092705011367798, "value_any": 0.8581756949424744, "value_bot": 0.8572869896888733, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05580.png", "entropy": 0.1566198468208313} +{"ts": "2026-03-20T18:43:39.112874Z", "loop": 5590, "env_steps": 3434496000, "exact_value_avg": 0.8559087514877319, "regret_dist": 0.007671944331377745, "regret_other_env": 0.012726892717182636, "regret_corner": 8.952121424954385e-05, "regret_row": 0.045411381870508194, "regret_any": 0.012750368565320969, "regret_bot": 0.009174930863082409, "value_dist": 0.8559087514877319, "value_other_env": 0.869488000869751, "value_corner": 0.8355398178100586, "value_row": 0.8132153153419495, "value_any": 0.8695002198219299, "value_bot": 0.8494517803192139, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05590.png", "entropy": 0.1456034928560257} +{"ts": "2026-03-20T18:43:47.692266Z", "loop": 5600, "env_steps": 3440640000, "exact_value_avg": 0.8603365421295166, "regret_dist": 0.0032441921066492796, "regret_other_env": 0.005087372846901417, "regret_corner": 0.00047942055971361697, "regret_row": 0.005512426607310772, "regret_any": 0.005117448046803474, "regret_bot": 0.011999018490314484, "value_dist": 0.8603365421295166, "value_other_env": 0.8771275281906128, "value_corner": 0.8351499438285828, "value_row": 0.8531142473220825, "value_any": 0.8771331310272217, "value_bot": 0.8466275930404663, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05600.png", "entropy": 0.16242913901805878} +{"ts": "2026-03-20T18:43:56.270522Z", "loop": 5610, "env_steps": 3446784000, "exact_value_avg": 0.8593358397483826, "regret_dist": 0.004244896117597818, "regret_other_env": 0.006086707580834627, "regret_corner": 0.0014821788063272834, "regret_row": 0.008753239177167416, "regret_any": 0.006139479111880064, "regret_bot": 0.005587616469711065, "value_dist": 0.8593358397483826, "value_other_env": 0.8761281967163086, "value_corner": 0.8341471552848816, "value_row": 0.8498734831809998, "value_any": 0.8761110901832581, "value_bot": 0.8530389666557312, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05610.png", "entropy": 0.17111629247665405} +{"ts": "2026-03-20T18:44:04.864896Z", "loop": 5620, "env_steps": 3452928000, "exact_value_avg": 0.8616468906402588, "regret_dist": 0.0019337573321536183, "regret_other_env": 0.003044423181563616, "regret_corner": 0.00026775847072713077, "regret_row": 0.002244414296001196, "regret_any": 0.003078288631513715, "regret_bot": 0.006249392870813608, "value_dist": 0.8616468906402588, "value_other_env": 0.8791704177856445, "value_corner": 0.8353615403175354, "value_row": 0.8563821911811829, "value_any": 0.8791723251342773, "value_bot": 0.85237717628479, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05620.png", "entropy": 0.15852898359298706} +{"ts": "2026-03-20T18:44:13.445954Z", "loop": 5630, "env_steps": 3459072000, "exact_value_avg": 0.8609542846679688, "regret_dist": 0.0026264020707458258, "regret_other_env": 0.004215605091303587, "regret_corner": 0.00024259737983811647, "regret_row": 0.0026095309294760227, "regret_any": 0.004267069045454264, "regret_bot": 0.010125811211764812, "value_dist": 0.8609542846679688, "value_other_env": 0.8779992461204529, "value_corner": 0.8353866934776306, "value_row": 0.8560171127319336, "value_any": 0.8779835104942322, "value_bot": 0.8485008478164673, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05630.png", "entropy": 0.16123424470424652} +{"ts": "2026-03-20T18:44:22.027691Z", "loop": 5640, "env_steps": 3465216000, "exact_value_avg": 0.8618757724761963, "regret_dist": 0.001704927533864975, "regret_other_env": 0.0026826648972928524, "regret_corner": 0.00023832124134059995, "regret_row": 0.001954231411218643, "regret_any": 0.0027179131284356117, "regret_bot": 0.0028343189042061567, "value_dist": 0.8618757724761963, "value_other_env": 0.8795322179794312, "value_corner": 0.8353910446166992, "value_row": 0.8566724061965942, "value_any": 0.8795326948165894, "value_bot": 0.8557922840118408, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05640.png", "entropy": 0.14712803065776825} +{"ts": "2026-03-20T18:44:30.610145Z", "loop": 5650, "env_steps": 3471360000, "exact_value_avg": 0.8623300790786743, "regret_dist": 0.0012505293125286698, "regret_other_env": 0.0020704041235148907, "regret_corner": 2.0717085135402158e-05, "regret_row": 0.0011589389760047197, "regret_any": 0.002105347579345107, "regret_bot": 0.002223424846306443, "value_dist": 0.8623300790786743, "value_other_env": 0.8801444172859192, "value_corner": 0.8356086015701294, "value_row": 0.8574677109718323, "value_any": 0.880145251750946, "value_bot": 0.8564032316207886, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05650.png", "entropy": 0.135716512799263} +{"ts": "2026-03-20T18:44:39.196308Z", "loop": 5660, "env_steps": 3477504000, "exact_value_avg": 0.862288773059845, "regret_dist": 0.001291970256716013, "regret_other_env": 0.002138512907549739, "regret_corner": 2.2156040358822793e-05, "regret_row": 0.0015507428906857967, "regret_any": 0.0021781260147690773, "regret_bot": 0.0021069785580039024, "value_dist": 0.862288773059845, "value_other_env": 0.8800764083862305, "value_corner": 0.8356071710586548, "value_row": 0.8570758104324341, "value_any": 0.8800724148750305, "value_bot": 0.8565196394920349, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05660.png", "entropy": 0.13464657962322235} +{"ts": "2026-03-20T18:44:47.775808Z", "loop": 5670, "env_steps": 3483648000, "exact_value_avg": 0.862519383430481, "regret_dist": 0.0010613540653139353, "regret_other_env": 0.001742498017847538, "regret_corner": 3.963808558182791e-05, "regret_row": 0.0009786568116396666, "regret_any": 0.0017666015774011612, "regret_bot": 0.0032660942524671555, "value_dist": 0.862519383430481, "value_other_env": 0.8804724216461182, "value_corner": 0.8355897068977356, "value_row": 0.8576480746269226, "value_any": 0.8804839849472046, "value_bot": 0.8553605079650879, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05670.png", "entropy": 0.1387203186750412} +{"ts": "2026-03-20T18:44:56.364115Z", "loop": 5680, "env_steps": 3489792000, "exact_value_avg": 0.8620989322662354, "regret_dist": 0.0014817510964348912, "regret_other_env": 0.0021133292466402054, "regret_corner": 0.0005343839875422418, "regret_row": 0.001464096480049193, "regret_any": 0.0021313398610800505, "regret_bot": 0.0032374453730881214, "value_dist": 0.8620989322662354, "value_other_env": 0.8801015615463257, "value_corner": 0.8350949287414551, "value_row": 0.8571625351905823, "value_any": 0.8801193237304688, "value_bot": 0.8553891777992249, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05680.png", "entropy": 0.14992091059684753} +{"ts": "2026-03-20T18:45:04.960155Z", "loop": 5690, "env_steps": 3495936000, "exact_value_avg": 0.8608112931251526, "regret_dist": 0.002769401064142585, "regret_other_env": 0.003943599760532379, "regret_corner": 0.0010081023210659623, "regret_row": 0.0027308152057230473, "regret_any": 0.003940384369343519, "regret_bot": 0.007355944253504276, "value_dist": 0.8608112931251526, "value_other_env": 0.8782712817192078, "value_corner": 0.8346211910247803, "value_row": 0.8558957576751709, "value_any": 0.8783102631568909, "value_bot": 0.8512706160545349, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05690.png", "entropy": 0.1504313200712204} +{"ts": "2026-03-20T18:45:13.548623Z", "loop": 5700, "env_steps": 3502080000, "exact_value_avg": 0.862589955329895, "regret_dist": 0.0009907418861985207, "regret_other_env": 0.0016213151393458247, "regret_corner": 4.4881802750751376e-05, "regret_row": 0.00112262018956244, "regret_any": 0.0016393921105191112, "regret_bot": 0.0024201448541134596, "value_dist": 0.862589955329895, "value_other_env": 0.8805935978889465, "value_corner": 0.8355844020843506, "value_row": 0.8575039505958557, "value_any": 0.8806112408638, "value_bot": 0.8562065362930298, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05700.png", "entropy": 0.1362261325120926} +{"ts": "2026-03-20T18:45:22.135750Z", "loop": 5710, "env_steps": 3508224000, "exact_value_avg": 0.8594002723693848, "regret_dist": 0.004180485848337412, "regret_other_env": 0.006804352626204491, "regret_corner": 0.0002446855360176414, "regret_row": 0.015611667186021805, "regret_any": 0.0068715764209628105, "regret_bot": 0.0022929618135094643, "value_dist": 0.8594002723693848, "value_other_env": 0.8754105567932129, "value_corner": 0.8353846669197083, "value_row": 0.8430149555206299, "value_any": 0.8753790855407715, "value_bot": 0.8563336730003357, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05710.png", "entropy": 0.13483501970767975} +{"ts": "2026-03-20T18:45:30.715632Z", "loop": 5720, "env_steps": 3514368000, "exact_value_avg": 0.8614101409912109, "regret_dist": 0.0021704910323023796, "regret_other_env": 0.003612515050917864, "regret_corner": 7.454554634023225e-06, "regret_row": 0.003415766404941678, "regret_any": 0.003639488248154521, "regret_bot": 0.004735408816486597, "value_dist": 0.8614101409912109, "value_other_env": 0.8786023259162903, "value_corner": 0.8356218934059143, "value_row": 0.8552109003067017, "value_any": 0.878611147403717, "value_bot": 0.8538912534713745, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05720.png", "entropy": 0.13769733905792236} +{"ts": "2026-03-20T18:45:39.297051Z", "loop": 5730, "env_steps": 3520512000, "exact_value_avg": 0.8613402843475342, "regret_dist": 0.0022403416223824024, "regret_other_env": 0.003730920609086752, "regret_corner": 4.472832188184839e-06, "regret_row": 0.006848888471722603, "regret_any": 0.003753552446141839, "regret_bot": 0.003932759165763855, "value_dist": 0.8613402843475342, "value_other_env": 0.8784839510917664, "value_corner": 0.8356248736381531, "value_row": 0.8517777323722839, "value_any": 0.8784970641136169, "value_bot": 0.8546938300132751, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05730.png", "entropy": 0.13865764439105988} +{"ts": "2026-03-20T18:45:47.885226Z", "loop": 5740, "env_steps": 3526656000, "exact_value_avg": 0.8610104322433472, "regret_dist": 0.0025702016428112984, "regret_other_env": 0.004267681855708361, "regret_corner": 2.3980936020961963e-05, "regret_row": 0.005791643634438515, "regret_any": 0.004266570787876844, "regret_bot": 0.005383856128901243, "value_dist": 0.8610104322433472, "value_other_env": 0.877947211265564, "value_corner": 0.8356053233146667, "value_row": 0.852834939956665, "value_any": 0.8779840469360352, "value_bot": 0.853242814540863, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05740.png", "entropy": 0.14564643800258636} +{"ts": "2026-03-20T18:45:56.464391Z", "loop": 5750, "env_steps": 3532800000, "exact_value_avg": 0.861960768699646, "regret_dist": 0.0016199704259634018, "regret_other_env": 0.0026871529407799244, "regret_corner": 1.919667010952253e-05, "regret_row": 0.0049964492209255695, "regret_any": 0.002695281757041812, "regret_bot": 0.002136401366442442, "value_dist": 0.861960768699646, "value_other_env": 0.879527747631073, "value_corner": 0.8356100916862488, "value_row": 0.8536301851272583, "value_any": 0.8795552849769592, "value_bot": 0.8564902544021606, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05750.png", "entropy": 0.14308996498584747} +{"ts": "2026-03-20T18:46:05.044211Z", "loop": 5760, "env_steps": 3538944000, "exact_value_avg": 0.8617151975631714, "regret_dist": 0.0018654927844181657, "regret_other_env": 0.0025142126251012087, "regret_corner": 0.0008924127323552966, "regret_row": 0.0032879612408578396, "regret_any": 0.0025370700750499964, "regret_bot": 0.0020549953915178776, "value_dist": 0.8617151975631714, "value_other_env": 0.8797006607055664, "value_corner": 0.8347369432449341, "value_row": 0.8553386926651001, "value_any": 0.8797134757041931, "value_bot": 0.856571614742279, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05760.png", "entropy": 0.15083415806293488} +{"ts": "2026-03-20T18:46:13.632808Z", "loop": 5770, "env_steps": 3545088000, "exact_value_avg": 0.8623315095901489, "regret_dist": 0.001249197288416326, "regret_other_env": 0.0019315831596031785, "regret_corner": 0.0002256184961879626, "regret_row": 0.001685900380834937, "regret_any": 0.0019528076518326998, "regret_bot": 0.0020309751853346825, "value_dist": 0.8623315095901489, "value_other_env": 0.8802832961082458, "value_corner": 0.8354036808013916, "value_row": 0.8569408059120178, "value_any": 0.880297839641571, "value_bot": 0.8565956354141235, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05770.png", "entropy": 0.14455102384090424} +{"ts": "2026-03-20T18:46:22.220797Z", "loop": 5780, "env_steps": 3551232000, "exact_value_avg": 0.8615412712097168, "regret_dist": 0.002039457904174924, "regret_other_env": 0.0032927552238106728, "regret_corner": 0.00015951147361192852, "regret_row": 0.0021309873554855585, "regret_any": 0.003300040028989315, "regret_bot": 0.005588873289525509, "value_dist": 0.8615412712097168, "value_other_env": 0.878922164440155, "value_corner": 0.8354698419570923, "value_row": 0.8564956188201904, "value_any": 0.8789505362510681, "value_bot": 0.8530377745628357, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05780.png", "entropy": 0.14891201257705688} +{"ts": "2026-03-20T18:46:30.807336Z", "loop": 5790, "env_steps": 3557376000, "exact_value_avg": 0.8601471781730652, "regret_dist": 0.003433533012866974, "regret_other_env": 0.00545646483078599, "regret_corner": 0.00039913508226163685, "regret_row": 0.0044060866348445415, "regret_any": 0.005458564963191748, "regret_bot": 0.008731966838240623, "value_dist": 0.8601471781730652, "value_other_env": 0.8767584562301636, "value_corner": 0.8352301716804504, "value_row": 0.8542205691337585, "value_any": 0.8767920136451721, "value_bot": 0.849894642829895, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05790.png", "entropy": 0.15625914931297302} +{"ts": "2026-03-20T18:46:39.390855Z", "loop": 5800, "env_steps": 3563520000, "exact_value_avg": 0.8625641465187073, "regret_dist": 0.0010165367275476456, "regret_other_env": 0.001578030874952674, "regret_corner": 0.00017429541912861168, "regret_row": 0.0022851054091006517, "regret_any": 0.001594895264133811, "regret_bot": 0.0016512416768819094, "value_dist": 0.8625641465187073, "value_other_env": 0.8806368112564087, "value_corner": 0.835455060005188, "value_row": 0.856341540813446, "value_any": 0.8806557655334473, "value_bot": 0.8569753766059875, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05800.png", "entropy": 0.14482370018959045} +{"ts": "2026-03-20T18:46:47.969709Z", "loop": 5810, "env_steps": 3569664000, "exact_value_avg": 0.8625919818878174, "regret_dist": 0.0009887154446914792, "regret_other_env": 0.0016340557485818863, "regret_corner": 2.0704668713733554e-05, "regret_row": 0.0010918689658865333, "regret_any": 0.0016589182196184993, "regret_bot": 0.0021806529257446527, "value_dist": 0.8625919818878174, "value_other_env": 0.8805808424949646, "value_corner": 0.8356086015701294, "value_row": 0.8575347661972046, "value_any": 0.8805917501449585, "value_bot": 0.8564460277557373, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05810.png", "entropy": 0.14036114513874054} +{"ts": "2026-03-20T18:46:56.557186Z", "loop": 5820, "env_steps": 3575808000, "exact_value_avg": 0.8574080467224121, "regret_dist": 0.006172605324536562, "regret_other_env": 0.010283859446644783, "regret_corner": 5.723039521399187e-06, "regret_row": 0.0070923385210335255, "regret_any": 0.010349228046834469, "regret_bot": 0.031741704791784286, "value_dist": 0.8574080467224121, "value_other_env": 0.8719310164451599, "value_corner": 0.8356236219406128, "value_row": 0.851534366607666, "value_any": 0.8719013929367065, "value_bot": 0.826884925365448, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05820.png", "entropy": 0.14140568673610687} +{"ts": "2026-03-20T18:47:05.136272Z", "loop": 5830, "env_steps": 3581952000, "exact_value_avg": 0.8625514507293701, "regret_dist": 0.001029269304126501, "regret_other_env": 0.0016828913940116763, "regret_corner": 4.883607471128926e-05, "regret_row": 0.0009785505244508386, "regret_any": 0.001704520545899868, "regret_bot": 0.0012478932039812207, "value_dist": 0.8625514507293701, "value_other_env": 0.8805320262908936, "value_corner": 0.8355804681777954, "value_row": 0.8576480746269226, "value_any": 0.8805460333824158, "value_bot": 0.8573787808418274, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05830.png", "entropy": 0.13922244310379028} +{"ts": "2026-03-20T18:47:13.728970Z", "loop": 5840, "env_steps": 3588096000, "exact_value_avg": 0.861549973487854, "regret_dist": 0.002030751435086131, "regret_other_env": 0.0032621051650494337, "regret_corner": 0.0001837208983488381, "regret_row": 0.0013281811261549592, "regret_any": 0.0032935733906924725, "regret_bot": 0.0018973230617120862, "value_dist": 0.861549973487854, "value_other_env": 0.8789528012275696, "value_corner": 0.8354455828666687, "value_row": 0.8572984933853149, "value_any": 0.8789570331573486, "value_bot": 0.85672926902771, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05840.png", "entropy": 0.13979268074035645} +{"ts": "2026-03-20T18:47:22.327253Z", "loop": 5850, "env_steps": 3594240000, "exact_value_avg": 0.8609740734100342, "regret_dist": 0.0026065753772854805, "regret_other_env": 0.004333375953137875, "regret_corner": 1.6374389815609902e-05, "regret_row": 0.004819633439183235, "regret_any": 0.00438022380694747, "regret_bot": 0.006160912103950977, "value_dist": 0.8609740734100342, "value_other_env": 0.8778814673423767, "value_corner": 0.835612952709198, "value_row": 0.8538070917129517, "value_any": 0.8778703808784485, "value_bot": 0.8524656891822815, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05850.png", "entropy": 0.13912683725357056} +{"ts": "2026-03-20T18:47:30.936117Z", "loop": 5860, "env_steps": 3600384000, "exact_value_avg": 0.861674427986145, "regret_dist": 0.0019062322098761797, "regret_other_env": 0.00314801256172359, "regret_corner": 4.356155841378495e-05, "regret_row": 0.002167224884033203, "regret_any": 0.0031836119014769793, "regret_bot": 0.003153233788907528, "value_dist": 0.861674427986145, "value_other_env": 0.8790668249130249, "value_corner": 0.8355857729911804, "value_row": 0.8564593195915222, "value_any": 0.8790670037269592, "value_bot": 0.8554733395576477, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05860.png", "entropy": 0.1345236599445343} +{"ts": "2026-03-20T18:47:39.535333Z", "loop": 5870, "env_steps": 3606528000, "exact_value_avg": 0.8627055883407593, "regret_dist": 0.0008750498527660966, "regret_other_env": 0.0014499388635158539, "regret_corner": 1.2716154742520303e-05, "regret_row": 0.0007473414298146963, "regret_any": 0.0014724066713824868, "regret_bot": 0.0017680255696177483, "value_dist": 0.8627055883407593, "value_other_env": 0.880764901638031, "value_corner": 0.8356165885925293, "value_row": 0.8578792214393616, "value_any": 0.8807781338691711, "value_bot": 0.8568586707115173, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05870.png", "entropy": 0.13413740694522858} +{"ts": "2026-03-20T18:47:48.135716Z", "loop": 5880, "env_steps": 3612672000, "exact_value_avg": 0.862214207649231, "regret_dist": 0.001366536831483245, "regret_other_env": 0.00225503440015018, "regret_corner": 3.379037298145704e-05, "regret_row": 0.0010556683409959078, "regret_any": 0.002289437223225832, "regret_bot": 0.004339165054261684, "value_dist": 0.862214207649231, "value_other_env": 0.8799598813056946, "value_corner": 0.8355955481529236, "value_row": 0.8575709462165833, "value_any": 0.8799611330032349, "value_bot": 0.8542875051498413, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05880.png", "entropy": 0.13689330220222473} +{"ts": "2026-03-20T18:47:56.728159Z", "loop": 5890, "env_steps": 3618816000, "exact_value_avg": 0.8625156283378601, "regret_dist": 0.001065114513039589, "regret_other_env": 0.0017117325915023685, "regret_corner": 9.518713341094553e-05, "regret_row": 0.0020688658114522696, "regret_any": 0.00173770054243505, "regret_bot": 0.0025988954585045576, "value_dist": 0.8625156283378601, "value_other_env": 0.8805031776428223, "value_corner": 0.8355341553688049, "value_row": 0.8565577268600464, "value_any": 0.8805128931999207, "value_bot": 0.8560277223587036, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05890.png", "entropy": 0.13702166080474854} +{"ts": "2026-03-20T18:48:05.321047Z", "loop": 5900, "env_steps": 3624960000, "exact_value_avg": 0.8624104261398315, "regret_dist": 0.0011702580377459526, "regret_other_env": 0.0018716370686888695, "regret_corner": 0.00011818955681519583, "regret_row": 0.0013358055148273706, "regret_any": 0.001882445067167282, "regret_bot": 0.0028839188162237406, "value_dist": 0.8624104261398315, "value_other_env": 0.8803432583808899, "value_corner": 0.8355111479759216, "value_row": 0.8572909235954285, "value_any": 0.880368173122406, "value_bot": 0.8557427525520325, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05900.png", "entropy": 0.13926909863948822} +{"ts": "2026-03-20T18:48:13.919518Z", "loop": 5910, "env_steps": 3631104000, "exact_value_avg": 0.8609848022460938, "regret_dist": 0.0025958335027098656, "regret_other_env": 0.004292427562177181, "regret_corner": 5.0942104280693457e-05, "regret_row": 0.0023418122436851263, "regret_any": 0.004300241358578205, "regret_bot": 0.009981035254895687, "value_dist": 0.8609848022460938, "value_other_env": 0.8779224157333374, "value_corner": 0.8355783820152283, "value_row": 0.8562848567962646, "value_any": 0.8779503703117371, "value_bot": 0.8486455678939819, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05910.png", "entropy": 0.14385145902633667} +{"ts": "2026-03-20T18:48:22.516479Z", "loop": 5920, "env_steps": 3637248000, "exact_value_avg": 0.8608576059341431, "regret_dist": 0.002723107812926173, "regret_other_env": 0.004462938290089369, "regret_corner": 0.00011336158058838919, "regret_row": 0.001732325297780335, "regret_any": 0.004469619132578373, "regret_bot": 0.006065468303859234, "value_dist": 0.8608576059341431, "value_other_env": 0.8777520060539246, "value_corner": 0.8355159759521484, "value_row": 0.8568942546844482, "value_any": 0.8777809739112854, "value_bot": 0.8525611162185669, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05920.png", "entropy": 0.14111094176769257} +{"ts": "2026-03-20T18:48:31.119058Z", "loop": 5930, "env_steps": 3643392000, "exact_value_avg": 0.86142498254776, "regret_dist": 0.002155706286430359, "regret_other_env": 0.003401774913072586, "regret_corner": 0.00028660299722105265, "regret_row": 0.001490903552621603, "regret_any": 0.0034044035710394382, "regret_bot": 0.005470083095133305, "value_dist": 0.86142498254776, "value_other_env": 0.8788131475448608, "value_corner": 0.8353427052497864, "value_row": 0.8571357131004333, "value_any": 0.8788461685180664, "value_bot": 0.8531566262245178, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05930.png", "entropy": 0.1456066071987152} +{"ts": "2026-03-20T18:48:39.716188Z", "loop": 5940, "env_steps": 3649536000, "exact_value_avg": 0.8618735074996948, "regret_dist": 0.001707190414890647, "regret_other_env": 0.0025085965171456337, "regret_corner": 0.0005050808540545404, "regret_row": 0.0025417786091566086, "regret_any": 0.0025262744165956974, "regret_bot": 0.003233028342947364, "value_dist": 0.8618735074996948, "value_other_env": 0.8797063231468201, "value_corner": 0.8351242542266846, "value_row": 0.8560848236083984, "value_any": 0.8797243237495422, "value_bot": 0.855393648147583, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05940.png", "entropy": 0.15089239180088043} +{"ts": "2026-03-20T18:48:48.315515Z", "loop": 5950, "env_steps": 3655680000, "exact_value_avg": 0.8612265586853027, "regret_dist": 0.0023540975525975227, "regret_other_env": 0.0038593027275055647, "regret_corner": 9.62893245741725e-05, "regret_row": 0.002657695673406124, "regret_any": 0.003892763750627637, "regret_bot": 0.010103893466293812, "value_dist": 0.8612265586853027, "value_other_env": 0.8783555626869202, "value_corner": 0.835533082485199, "value_row": 0.8559690117835999, "value_any": 0.8783578872680664, "value_bot": 0.8485227227210999, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05950.png", "entropy": 0.14645294845104218} +{"ts": "2026-03-20T18:48:56.922035Z", "loop": 5960, "env_steps": 3661824000, "exact_value_avg": 0.8619544506072998, "regret_dist": 0.0016261739656329155, "regret_other_env": 0.0024648301769047976, "regret_corner": 0.0003681893285829574, "regret_row": 0.0013292086077854037, "regret_any": 0.0024916273541748524, "regret_bot": 0.002957516349852085, "value_dist": 0.8619544506072998, "value_other_env": 0.8797500133514404, "value_corner": 0.8352610468864441, "value_row": 0.8572974801063538, "value_any": 0.8797589540481567, "value_bot": 0.8556691408157349, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05960.png", "entropy": 0.14760638773441315} +{"ts": "2026-03-20T18:49:05.517272Z", "loop": 5970, "env_steps": 3667968000, "exact_value_avg": 0.8620464205741882, "regret_dist": 0.0015342436963692307, "regret_other_env": 0.0021647466346621513, "regret_corner": 0.0005884891143068671, "regret_row": 0.0014051030157133937, "regret_any": 0.0021843493450433016, "regret_bot": 0.002437264658510685, "value_dist": 0.8620464205741882, "value_other_env": 0.8800501227378845, "value_corner": 0.835040807723999, "value_row": 0.8572215437889099, "value_any": 0.8800662755966187, "value_bot": 0.8561894297599792, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05970.png", "entropy": 0.14687739312648773} +{"ts": "2026-03-20T18:49:14.112556Z", "loop": 5980, "env_steps": 3674112000, "exact_value_avg": 0.859011709690094, "regret_dist": 0.004568994045257568, "regret_other_env": 0.00722569739446044, "regret_corner": 0.0005839377990923822, "regret_row": 0.011220423504710197, "regret_any": 0.0072690644301474094, "regret_bot": 0.0034115847665816545, "value_dist": 0.859011709690094, "value_other_env": 0.8749892115592957, "value_corner": 0.8350453972816467, "value_row": 0.8474061489105225, "value_any": 0.8749815225601196, "value_bot": 0.8552150726318359, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05980.png", "entropy": 0.15114137530326843} +{"ts": "2026-03-20T18:49:22.709480Z", "loop": 5990, "env_steps": 3680256000, "exact_value_avg": 0.8599863052368164, "regret_dist": 0.0035943351686000824, "regret_other_env": 0.005953451618552208, "regret_corner": 5.565981336985715e-05, "regret_row": 0.0038968974258750677, "regret_any": 0.006003758870065212, "regret_bot": 0.005821445491164923, "value_dist": 0.8599863052368164, "value_other_env": 0.8762614130973816, "value_corner": 0.8355736136436462, "value_row": 0.8547297120094299, "value_any": 0.8762468099594116, "value_bot": 0.8528051972389221, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_05990.png", "entropy": 0.14422117173671722} +{"ts": "2026-03-20T18:49:31.298961Z", "loop": 6000, "env_steps": 3686400000, "exact_value_avg": 0.8621665239334106, "regret_dist": 0.0014141907449811697, "regret_other_env": 0.0022235300857573748, "regret_corner": 0.00020018171926494688, "regret_row": 0.0022702612914144993, "regret_any": 0.002245820127427578, "regret_bot": 0.002639198675751686, "value_dist": 0.8621665239334106, "value_other_env": 0.8799912929534912, "value_corner": 0.8354291915893555, "value_row": 0.8563563227653503, "value_any": 0.8800047636032104, "value_bot": 0.8559874296188354, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06000.png", "entropy": 0.1406034380197525} +{"ts": "2026-03-20T18:49:39.902339Z", "loop": 6010, "env_steps": 3692544000, "exact_value_avg": 0.8601058721542358, "regret_dist": 0.0034748127218335867, "regret_other_env": 0.005704743787646294, "regret_corner": 0.00012991628318559378, "regret_row": 0.005772956181317568, "regret_any": 0.005707523785531521, "regret_bot": 0.020807450637221336, "value_dist": 0.8601058721542358, "value_other_env": 0.8765101432800293, "value_corner": 0.8354994058609009, "value_row": 0.8528536558151245, "value_any": 0.8765431046485901, "value_bot": 0.8378192186355591, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06010.png", "entropy": 0.1425817906856537} +{"ts": "2026-03-20T18:49:48.505615Z", "loop": 6020, "env_steps": 3698688000, "exact_value_avg": 0.8623297214508057, "regret_dist": 0.0012509297812357545, "regret_other_env": 0.00207755365408957, "regret_corner": 1.0994077456416562e-05, "regret_row": 0.0018984162015840411, "regret_any": 0.0021006895694881678, "regret_bot": 0.003988577984273434, "value_dist": 0.8623297214508057, "value_other_env": 0.8801372647285461, "value_corner": 0.8356183767318726, "value_row": 0.8567282557487488, "value_any": 0.8801499009132385, "value_bot": 0.8546380996704102, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06020.png", "entropy": 0.1357780396938324} +{"ts": "2026-03-20T18:49:57.094226Z", "loop": 6030, "env_steps": 3704832000, "exact_value_avg": 0.8599375486373901, "regret_dist": 0.0036431539338082075, "regret_other_env": 0.0060506537556648254, "regret_corner": 3.1903884519124404e-05, "regret_row": 0.002331101568415761, "regret_any": 0.006129004992544651, "regret_bot": 0.009848314337432384, "value_dist": 0.8599375486373901, "value_other_env": 0.8761642575263977, "value_corner": 0.8355973958969116, "value_row": 0.8562955856323242, "value_any": 0.8761215806007385, "value_bot": 0.8487783670425415, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06030.png", "entropy": 0.14077988266944885} +{"ts": "2026-03-20T18:50:05.698554Z", "loop": 6040, "env_steps": 3710976000, "exact_value_avg": 0.8592455387115479, "regret_dist": 0.004335147328674793, "regret_other_env": 0.007222657557576895, "regret_corner": 3.880759322782978e-06, "regret_row": 0.007689476478844881, "regret_any": 0.007273996248841286, "regret_bot": 0.027453690767288208, "value_dist": 0.8592455387115479, "value_other_env": 0.8749921917915344, "value_corner": 0.835625410079956, "value_row": 0.8509371280670166, "value_any": 0.874976634979248, "value_bot": 0.8311729431152344, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06040.png", "entropy": 0.13639895617961884} +{"ts": "2026-03-20T18:50:14.290589Z", "loop": 6050, "env_steps": 3717120000, "exact_value_avg": 0.8622342348098755, "regret_dist": 0.0013464940711855888, "regret_other_env": 0.0022378936409950256, "regret_corner": 9.39468554861378e-06, "regret_row": 0.002808579709380865, "regret_any": 0.002260376699268818, "regret_bot": 0.003323404584079981, "value_dist": 0.8622342348098755, "value_other_env": 0.8799769878387451, "value_corner": 0.8356199264526367, "value_row": 0.8558180928230286, "value_any": 0.8799901604652405, "value_bot": 0.8553032875061035, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06050.png", "entropy": 0.1355591118335724} +{"ts": "2026-03-20T18:50:22.887136Z", "loop": 6060, "env_steps": 3723264000, "exact_value_avg": 0.8616366386413574, "regret_dist": 0.001944087096489966, "regret_other_env": 0.0032029221765697002, "regret_corner": 5.5834156228229403e-05, "regret_row": 0.0015438622795045376, "regret_any": 0.003377472748979926, "regret_bot": 0.0013288715854287148, "value_dist": 0.8616366386413574, "value_other_env": 0.8790119886398315, "value_corner": 0.8355734944343567, "value_row": 0.8570828437805176, "value_any": 0.8788730502128601, "value_bot": 0.8572977185249329, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06060.png", "entropy": 0.13430899381637573} +{"ts": "2026-03-20T18:50:31.489912Z", "loop": 6070, "env_steps": 3729408000, "exact_value_avg": 0.8624148964881897, "regret_dist": 0.0011657745344564319, "regret_other_env": 0.0019215570064261556, "regret_corner": 3.210057911928743e-05, "regret_row": 0.0008995091775432229, "regret_any": 0.001995427766814828, "regret_bot": 0.0016294133383780718, "value_dist": 0.8624148964881897, "value_other_env": 0.8802933096885681, "value_corner": 0.8355972170829773, "value_row": 0.8577271103858948, "value_any": 0.8802551627159119, "value_bot": 0.8569971919059753, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06070.png", "entropy": 0.13257870078086853} +{"ts": "2026-03-20T18:50:40.083565Z", "loop": 6080, "env_steps": 3735552000, "exact_value_avg": 0.8625430464744568, "regret_dist": 0.0010376694845035672, "regret_other_env": 0.0017100973054766655, "regret_corner": 2.9027463824604638e-05, "regret_row": 0.0009390462073497474, "regret_any": 0.0017383394297212362, "regret_bot": 0.0026109374593943357, "value_dist": 0.8625430464744568, "value_other_env": 0.8805047869682312, "value_corner": 0.8356003165245056, "value_row": 0.8576876521110535, "value_any": 0.8805122375488281, "value_bot": 0.8560156226158142, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06080.png", "entropy": 0.13568778336048126} +{"ts": "2026-03-20T18:50:48.681159Z", "loop": 6090, "env_steps": 3741696000, "exact_value_avg": 0.8620877265930176, "regret_dist": 0.001492989482358098, "regret_other_env": 0.0024775888305157423, "regret_corner": 1.609027458471246e-05, "regret_row": 0.0012742449762299657, "regret_any": 0.0024912317749112844, "regret_bot": 0.004894354846328497, "value_dist": 0.8620877265930176, "value_other_env": 0.8797373175621033, "value_corner": 0.8356133103370667, "value_row": 0.8573523759841919, "value_any": 0.8797593712806702, "value_bot": 0.8537323474884033, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06090.png", "entropy": 0.136819988489151} +{"ts": "2026-03-20T18:50:57.287307Z", "loop": 6100, "env_steps": 3747840000, "exact_value_avg": 0.861013650894165, "regret_dist": 0.0025670435279607773, "regret_other_env": 0.004251975100487471, "regret_corner": 3.96460309275426e-05, "regret_row": 0.019779758527874947, "regret_any": 0.004350255709141493, "regret_bot": 0.0014628155622631311, "value_dist": 0.861013650894165, "value_other_env": 0.8779628872871399, "value_corner": 0.8355896472930908, "value_row": 0.8388468027114868, "value_any": 0.8779004216194153, "value_bot": 0.8571637272834778, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06100.png", "entropy": 0.1349262297153473} +{"ts": "2026-03-20T18:51:05.880107Z", "loop": 6110, "env_steps": 3753984000, "exact_value_avg": 0.8609083890914917, "regret_dist": 0.0026723279152065516, "regret_other_env": 0.004448617342859507, "regret_corner": 7.893641850387212e-06, "regret_row": 0.0031821068841964006, "regret_any": 0.004483857192099094, "regret_bot": 0.008136920630931854, "value_dist": 0.8609083890914917, "value_other_env": 0.8777662515640259, "value_corner": 0.8356214165687561, "value_row": 0.8554444909095764, "value_any": 0.8777667284011841, "value_bot": 0.8504897356033325, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06110.png", "entropy": 0.13584363460540771} +{"ts": "2026-03-20T18:51:14.475891Z", "loop": 6120, "env_steps": 3760128000, "exact_value_avg": 0.8621714115142822, "regret_dist": 0.0014092504279688, "regret_other_env": 0.0023397270124405622, "regret_corner": 1.3535222024074756e-05, "regret_row": 0.0023519431706517935, "regret_any": 0.0023628748022019863, "regret_bot": 0.0026678252033889294, "value_dist": 0.8621714115142822, "value_other_env": 0.879875123500824, "value_corner": 0.8356157541275024, "value_row": 0.8562746644020081, "value_any": 0.8798877000808716, "value_bot": 0.855958878993988, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06120.png", "entropy": 0.13763049244880676} +{"ts": "2026-03-20T18:51:23.069926Z", "loop": 6130, "env_steps": 3766272000, "exact_value_avg": 0.8623844385147095, "regret_dist": 0.0011961903655901551, "regret_other_env": 0.0019485525554046035, "regret_corner": 6.764680438209325e-05, "regret_row": 0.0009876778349280357, "regret_any": 0.0019498112378641963, "regret_bot": 0.0022250094916671515, "value_dist": 0.8623844385147095, "value_other_env": 0.8802662491798401, "value_corner": 0.8355616927146912, "value_row": 0.8576390147209167, "value_any": 0.880300760269165, "value_bot": 0.8564016222953796, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06130.png", "entropy": 0.13611231744289398} +{"ts": "2026-03-20T18:51:31.662752Z", "loop": 6140, "env_steps": 3772416000, "exact_value_avg": 0.8620911836624146, "regret_dist": 0.0014894771156832576, "regret_other_env": 0.002260475652292371, "regret_corner": 0.00033297936897724867, "regret_row": 0.0013793163234367967, "regret_any": 0.0022596842609345913, "regret_bot": 0.002646022941917181, "value_dist": 0.8620911836624146, "value_other_env": 0.8799543976783752, "value_corner": 0.8352963328361511, "value_row": 0.8572472333908081, "value_any": 0.8799908757209778, "value_bot": 0.8559806942939758, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06140.png", "entropy": 0.14229881763458252} +{"ts": "2026-03-20T18:51:40.262386Z", "loop": 6150, "env_steps": 3778560000, "exact_value_avg": 0.858826220035553, "regret_dist": 0.004754469729959965, "regret_other_env": 0.007016435265541077, "regret_corner": 0.0013615216594189405, "regret_row": 0.0049652899615466595, "regret_any": 0.007013807073235512, "regret_bot": 0.014305448159575462, "value_dist": 0.858826220035553, "value_other_env": 0.8751984238624573, "value_corner": 0.8342678546905518, "value_row": 0.8536613583564758, "value_any": 0.8752367496490479, "value_bot": 0.8443211317062378, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06150.png", "entropy": 0.15457262098789215} +{"ts": "2026-03-20T18:51:48.855956Z", "loop": 6160, "env_steps": 3784704000, "exact_value_avg": 0.8558968901634216, "regret_dist": 0.007683805655688047, "regret_other_env": 0.012448805384337902, "regret_corner": 0.0005363057134672999, "regret_row": 0.012375449761748314, "regret_any": 0.012489426881074905, "regret_bot": 0.017358358949422836, "value_dist": 0.8558968901634216, "value_other_env": 0.8697660565376282, "value_corner": 0.835093080997467, "value_row": 0.8462511301040649, "value_any": 0.8697611689567566, "value_bot": 0.8412682414054871, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06160.png", "entropy": 0.14447608590126038} +{"ts": "2026-03-20T18:51:57.449275Z", "loop": 6170, "env_steps": 3790848000, "exact_value_avg": 0.8611922264099121, "regret_dist": 0.0023884137626737356, "regret_other_env": 0.0035969335585832596, "regret_corner": 0.0005756333703175187, "regret_row": 0.0023262035101652145, "regret_any": 0.0036196582950651646, "regret_bot": 0.0102840606123209, "value_dist": 0.8611922264099121, "value_other_env": 0.8786179423332214, "value_corner": 0.8350536823272705, "value_row": 0.8563004732131958, "value_any": 0.8786309361457825, "value_bot": 0.8483425974845886, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06170.png", "entropy": 0.15443497896194458} +{"ts": "2026-03-20T18:52:06.041086Z", "loop": 6180, "env_steps": 3796992000, "exact_value_avg": 0.8613667488098145, "regret_dist": 0.002213904168456793, "regret_other_env": 0.0033405525609850883, "regret_corner": 0.000523931288626045, "regret_row": 0.003322085365653038, "regret_any": 0.0033722734078764915, "regret_bot": 0.005556092597544193, "value_dist": 0.8613667488098145, "value_other_env": 0.8788743019104004, "value_corner": 0.8351053595542908, "value_row": 0.855304479598999, "value_any": 0.8788782954216003, "value_bot": 0.8530706167221069, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06180.png", "entropy": 0.15262021124362946} +{"ts": "2026-03-20T18:52:14.635949Z", "loop": 6190, "env_steps": 3803136000, "exact_value_avg": 0.8625140190124512, "regret_dist": 0.0010667274473235011, "regret_other_env": 0.0017351533751934767, "regret_corner": 6.408840999938548e-05, "regret_row": 0.001020784373395145, "regret_any": 0.0017616887344047427, "regret_bot": 0.0018890504725277424, "value_dist": 0.8625140190124512, "value_other_env": 0.8804797530174255, "value_corner": 0.8355652093887329, "value_row": 0.8576058745384216, "value_any": 0.880488932132721, "value_bot": 0.8567376136779785, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06190.png", "entropy": 0.13789865374565125} +{"ts": "2026-03-20T18:52:23.233058Z", "loop": 6200, "env_steps": 3809280000, "exact_value_avg": 0.8611154556274414, "regret_dist": 0.0024652599822729826, "regret_other_env": 0.004070384427905083, "regret_corner": 5.7573121011955664e-05, "regret_row": 0.004541407339274883, "regret_any": 0.0041582961566746235, "regret_bot": 0.001763726701028645, "value_dist": 0.8611154556274414, "value_other_env": 0.8781445622444153, "value_corner": 0.8355717062950134, "value_row": 0.8540852665901184, "value_any": 0.878092348575592, "value_bot": 0.8568629026412964, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06200.png", "entropy": 0.1367868334054947} +{"ts": "2026-03-20T18:52:31.828737Z", "loop": 6210, "env_steps": 3815424000, "exact_value_avg": 0.8615584969520569, "regret_dist": 0.0020221599843353033, "regret_other_env": 0.0033555368427187204, "regret_corner": 2.209444937761873e-05, "regret_row": 0.002635431243106723, "regret_any": 0.003358122892677784, "regret_bot": 0.005390272010117769, "value_dist": 0.8615584969520569, "value_other_env": 0.8788593411445618, "value_corner": 0.8356071710586548, "value_row": 0.8559912443161011, "value_any": 0.8788924217224121, "value_bot": 0.8532363176345825, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06210.png", "entropy": 0.13668940961360931} +{"ts": "2026-03-20T18:52:40.427076Z", "loop": 6220, "env_steps": 3821568000, "exact_value_avg": 0.8614102005958557, "regret_dist": 0.002170477993786335, "regret_other_env": 0.003605369245633483, "regret_corner": 1.8141170585295185e-05, "regret_row": 0.0033171852119266987, "regret_any": 0.003605108242481947, "regret_bot": 0.005982698407024145, "value_dist": 0.8614102005958557, "value_other_env": 0.8786094784736633, "value_corner": 0.8356112241744995, "value_row": 0.8553094863891602, "value_any": 0.8786455392837524, "value_bot": 0.8526439070701599, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06220.png", "entropy": 0.13606330752372742} +{"ts": "2026-03-20T18:52:49.022094Z", "loop": 6230, "env_steps": 3827712000, "exact_value_avg": 0.8586918115615845, "regret_dist": 0.004888871684670448, "regret_other_env": 0.008142050355672836, "regret_corner": 9.10411290533375e-06, "regret_row": 0.005265702959150076, "regret_any": 0.008197339251637459, "regret_bot": 0.016074642539024353, "value_dist": 0.8586918115615845, "value_other_env": 0.8740728497505188, "value_corner": 0.8356202244758606, "value_row": 0.8533609509468079, "value_any": 0.8740532398223877, "value_bot": 0.8425520062446594, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06230.png", "entropy": 0.13541768491268158} +{"ts": "2026-03-20T18:52:57.616652Z", "loop": 6240, "env_steps": 3833856000, "exact_value_avg": 0.8624178171157837, "regret_dist": 0.0011628266656771302, "regret_other_env": 0.0019153532339259982, "regret_corner": 3.403673690627329e-05, "regret_row": 0.001214123098179698, "regret_any": 0.0019457393791526556, "regret_bot": 0.0028825202025473118, "value_dist": 0.8624178171157837, "value_other_env": 0.8802995085716248, "value_corner": 0.8355952501296997, "value_row": 0.8574125170707703, "value_any": 0.8803048729896545, "value_bot": 0.8557441234588623, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06240.png", "entropy": 0.12830373644828796} +{"ts": "2026-03-20T18:53:06.211059Z", "loop": 6250, "env_steps": 3840000000, "exact_value_avg": 0.8544783592224121, "regret_dist": 0.009102300740778446, "regret_other_env": 0.015114967711269855, "regret_corner": 8.329997945111245e-05, "regret_row": 0.006000494584441185, "regret_any": 0.015147839672863483, "regret_bot": 0.030874406918883324, "value_dist": 0.8544783592224121, "value_other_env": 0.867099940776825, "value_corner": 0.8355460166931152, "value_row": 0.8526261448860168, "value_any": 0.8671028017997742, "value_bot": 0.8277521729469299, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06250.png", "entropy": 0.14220663905143738} +{"ts": "2026-03-20T18:53:14.801974Z", "loop": 6260, "env_steps": 3846144000, "exact_value_avg": 0.8508893251419067, "regret_dist": 0.012691349722445011, "regret_other_env": 0.014924445189535618, "regret_corner": 0.009341704659163952, "regret_row": 0.018583210185170174, "regret_any": 0.014905614778399467, "regret_bot": 0.019888872280716896, "value_dist": 0.8508893251419067, "value_other_env": 0.8672904372215271, "value_corner": 0.8262876272201538, "value_row": 0.8400434851646423, "value_any": 0.8673450350761414, "value_bot": 0.8387377858161926, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06260.png", "entropy": 0.15236860513687134} +{"ts": "2026-03-20T18:53:23.398503Z", "loop": 6270, "env_steps": 3852288000, "exact_value_avg": 0.8614962100982666, "regret_dist": 0.00208448339253664, "regret_other_env": 0.0033502376172691584, "regret_corner": 0.0001858517643995583, "regret_row": 0.0010550579754635692, "regret_any": 0.003368364879861474, "regret_bot": 0.008526438847184181, "value_dist": 0.8614962100982666, "value_other_env": 0.8788647055625916, "value_corner": 0.8354434967041016, "value_row": 0.857571542263031, "value_any": 0.8788822889328003, "value_bot": 0.8501001000404358, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06270.png", "entropy": 0.13773946464061737} +{"ts": "2026-03-20T18:53:31.992918Z", "loop": 6280, "env_steps": 3858432000, "exact_value_avg": 0.8611264824867249, "regret_dist": 0.002454218454658985, "regret_other_env": 0.004027640912681818, "regret_corner": 9.408444748260081e-05, "regret_row": 0.011926595121622086, "regret_any": 0.0041860598139464855, "regret_bot": 0.002486961893737316, "value_dist": 0.8611264824867249, "value_other_env": 0.8781872391700745, "value_corner": 0.8355352282524109, "value_row": 0.8467000126838684, "value_any": 0.8780645132064819, "value_bot": 0.8561397194862366, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06280.png", "entropy": 0.12545186281204224} +{"ts": "2026-03-20T18:53:40.585677Z", "loop": 6290, "env_steps": 3864576000, "exact_value_avg": 0.8615542650222778, "regret_dist": 0.002026390051469207, "regret_other_env": 0.003374038729816675, "regret_corner": 4.9168866098625585e-06, "regret_row": 0.004034506622701883, "regret_any": 0.003407938638702035, "regret_bot": 0.0027064040768891573, "value_dist": 0.8615542650222778, "value_other_env": 0.8788408637046814, "value_corner": 0.8356243968009949, "value_row": 0.8545921444892883, "value_any": 0.8788426518440247, "value_bot": 0.8559201955795288, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06290.png", "entropy": 0.12547019124031067} +{"ts": "2026-03-20T18:53:49.176802Z", "loop": 6300, "env_steps": 3870720000, "exact_value_avg": 0.8601206541061401, "regret_dist": 0.0034600156359374523, "regret_other_env": 0.005760121159255505, "regret_corner": 9.857119039224926e-06, "regret_row": 0.010481804609298706, "regret_any": 0.005812100134789944, "regret_bot": 0.0055799661204218864, "value_dist": 0.8601206541061401, "value_other_env": 0.8764547109603882, "value_corner": 0.8356194496154785, "value_row": 0.8481448888778687, "value_any": 0.8764384984970093, "value_bot": 0.8530466556549072, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06300.png", "entropy": 0.13095204532146454} +{"ts": "2026-03-20T18:53:57.777850Z", "loop": 6310, "env_steps": 3876864000, "exact_value_avg": 0.8615912199020386, "regret_dist": 0.001989486627280712, "regret_other_env": 0.0032911058515310287, "regret_corner": 3.705720155267045e-05, "regret_row": 0.01219461765140295, "regret_any": 0.0033052104990929365, "regret_bot": 0.0016587990103289485, "value_dist": 0.8615912199020386, "value_other_env": 0.878923773765564, "value_corner": 0.8355923295021057, "value_row": 0.8464320302009583, "value_any": 0.8789454102516174, "value_bot": 0.8569678068161011, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06310.png", "entropy": 0.13428841531276703} +{"ts": "2026-03-20T18:54:06.373523Z", "loop": 6320, "env_steps": 3883008000, "exact_value_avg": 0.8590855598449707, "regret_dist": 0.004495156463235617, "regret_other_env": 0.0073179216124117374, "regret_corner": 0.00026100725517608225, "regret_row": 0.00470039201900363, "regret_any": 0.00736529566347599, "regret_bot": 0.007248284295201302, "value_dist": 0.8590855598449707, "value_other_env": 0.8748969435691833, "value_corner": 0.8353683948516846, "value_row": 0.8539261817932129, "value_any": 0.8748853206634521, "value_bot": 0.8513782620429993, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06320.png", "entropy": 0.14271321892738342} +{"ts": "2026-03-20T18:54:14.964237Z", "loop": 6330, "env_steps": 3889152000, "exact_value_avg": 0.8616985082626343, "regret_dist": 0.0018822082784026861, "regret_other_env": 0.002897352911531925, "regret_corner": 0.00035949103767052293, "regret_row": 0.0032859675120562315, "regret_any": 0.002913047093898058, "regret_bot": 0.002563090529292822, "value_dist": 0.8616985082626343, "value_other_env": 0.8793175220489502, "value_corner": 0.8352698683738708, "value_row": 0.8553406596183777, "value_any": 0.8793375492095947, "value_bot": 0.8560635447502136, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06330.png", "entropy": 0.14131122827529907} +{"ts": "2026-03-20T18:54:23.559637Z", "loop": 6340, "env_steps": 3895296000, "exact_value_avg": 0.8612964749336243, "regret_dist": 0.0022842336911708117, "regret_other_env": 0.003628301667049527, "regret_corner": 0.00026813099975697696, "regret_row": 0.006533598527312279, "regret_any": 0.0036492703948169947, "regret_bot": 0.006310604512691498, "value_dist": 0.8612964749336243, "value_other_env": 0.8785866498947144, "value_corner": 0.8353611826896667, "value_row": 0.8520931005477905, "value_any": 0.8786013126373291, "value_bot": 0.8523160815238953, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06340.png", "entropy": 0.14077989757061005} +{"ts": "2026-03-20T18:54:32.154932Z", "loop": 6350, "env_steps": 3901440000, "exact_value_avg": 0.8615838885307312, "regret_dist": 0.001996844308450818, "regret_other_env": 0.0030216111335903406, "regret_corner": 0.0004596938961185515, "regret_row": 0.002992398804053664, "regret_any": 0.0030612910632044077, "regret_bot": 0.003353115636855364, "value_dist": 0.8615838885307312, "value_other_env": 0.8791933059692383, "value_corner": 0.8351696729660034, "value_row": 0.8556342720985413, "value_any": 0.8791893124580383, "value_bot": 0.8552734851837158, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06350.png", "entropy": 0.14234931766986847} +{"ts": "2026-03-20T18:54:40.749638Z", "loop": 6360, "env_steps": 3907584000, "exact_value_avg": 0.8618278503417969, "regret_dist": 0.0017528727184981108, "regret_other_env": 0.002477213041856885, "regret_corner": 0.0006663620588369668, "regret_row": 0.002455375622957945, "regret_any": 0.0025086391251534224, "regret_bot": 0.002282298868522048, "value_dist": 0.8618278503417969, "value_other_env": 0.8797376751899719, "value_corner": 0.8349630236625671, "value_row": 0.8561712503433228, "value_any": 0.8797419667243958, "value_bot": 0.8563442826271057, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06360.png", "entropy": 0.14154911041259766} +{"ts": "2026-03-20T18:54:49.346499Z", "loop": 6370, "env_steps": 3913728000, "exact_value_avg": 0.862790048122406, "regret_dist": 0.0007906815153546631, "regret_other_env": 0.001290916814468801, "regret_corner": 4.032850483781658e-05, "regret_row": 0.0008046722505241632, "regret_any": 0.0013176451902836561, "regret_bot": 0.0016221987316384912, "value_dist": 0.862790048122406, "value_other_env": 0.8809239864349365, "value_corner": 0.8355889916419983, "value_row": 0.8578218817710876, "value_any": 0.8809329867362976, "value_bot": 0.8570044040679932, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06370.png", "entropy": 0.12763544917106628} +{"ts": "2026-03-20T18:54:57.946555Z", "loop": 6380, "env_steps": 3919872000, "exact_value_avg": 0.8625644445419312, "regret_dist": 0.0010161844547837973, "regret_other_env": 0.001689769676886499, "regret_corner": 5.806486115034204e-06, "regret_row": 0.002042100764811039, "regret_any": 0.0017132344655692577, "regret_bot": 0.0015915757976472378, "value_dist": 0.8625644445419312, "value_other_env": 0.8805251121520996, "value_corner": 0.8356235027313232, "value_row": 0.8565845489501953, "value_any": 0.8805373907089233, "value_bot": 0.8570351004600525, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06380.png", "entropy": 0.1225983053445816} +{"ts": "2026-03-20T18:55:06.541464Z", "loop": 6390, "env_steps": 3926016000, "exact_value_avg": 0.8606140613555908, "regret_dist": 0.0029666293412446976, "regret_other_env": 0.004943098407238722, "regret_corner": 1.9257267922512256e-06, "regret_row": 0.01068772841244936, "regret_any": 0.004940600600093603, "regret_bot": 0.0030680091585963964, "value_dist": 0.8606140613555908, "value_other_env": 0.8772717714309692, "value_corner": 0.8356274366378784, "value_row": 0.8479389548301697, "value_any": 0.877310037612915, "value_bot": 0.8555586338043213, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06390.png", "entropy": 0.12243110686540604} +{"ts": "2026-03-20T18:55:15.137113Z", "loop": 6400, "env_steps": 3932160000, "exact_value_avg": 0.8614048361778259, "regret_dist": 0.002175845205783844, "regret_other_env": 0.0035724786575883627, "regret_corner": 8.089493348961696e-05, "regret_row": 0.008292347192764282, "regret_any": 0.0036156552378088236, "regret_bot": 0.001204189844429493, "value_dist": 0.8614048361778259, "value_other_env": 0.8786423802375793, "value_corner": 0.835548460483551, "value_row": 0.8503343462944031, "value_any": 0.8786349892616272, "value_bot": 0.857422411441803, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06400.png", "entropy": 0.12424132227897644} +{"ts": "2026-03-20T18:55:23.732486Z", "loop": 6410, "env_steps": 3938304000, "exact_value_avg": 0.8623230457305908, "regret_dist": 0.0012575885048136115, "regret_other_env": 0.002092085313051939, "regret_corner": 5.843242433911655e-06, "regret_row": 0.0006862048176117241, "regret_any": 0.00211584335193038, "regret_bot": 0.0035764831118285656, "value_dist": 0.8623230457305908, "value_other_env": 0.8801227807998657, "value_corner": 0.8356234431266785, "value_row": 0.8579404354095459, "value_any": 0.8801347613334656, "value_bot": 0.8550501465797424, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06410.png", "entropy": 0.12275125086307526} +{"ts": "2026-03-20T18:55:32.325380Z", "loop": 6420, "env_steps": 3944448000, "exact_value_avg": 0.8601568937301636, "regret_dist": 0.003423811635002494, "regret_other_env": 0.005696319043636322, "regret_corner": 1.5050173715280835e-05, "regret_row": 0.006754998583346605, "regret_any": 0.0057744053192436695, "regret_bot": 0.011645563878118992, "value_dist": 0.8601568937301636, "value_other_env": 0.8765185475349426, "value_corner": 0.8356143236160278, "value_row": 0.8518716096878052, "value_any": 0.8764761686325073, "value_bot": 0.8469811081886292, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06420.png", "entropy": 0.12746044993400574} +{"ts": "2026-03-20T18:55:40.921444Z", "loop": 6430, "env_steps": 3950592000, "exact_value_avg": 0.8615187406539917, "regret_dist": 0.002061894629150629, "regret_other_env": 0.0034056082367897034, "regret_corner": 4.632423588191159e-05, "regret_row": 0.002336739096790552, "regret_any": 0.003464329522103071, "regret_bot": 0.005750535521656275, "value_dist": 0.8615187406539917, "value_other_env": 0.8788092732429504, "value_corner": 0.835582971572876, "value_row": 0.8562899231910706, "value_any": 0.8787863254547119, "value_bot": 0.8528761267662048, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06430.png", "entropy": 0.12469033896923065} +{"ts": "2026-03-20T18:55:49.523721Z", "loop": 6440, "env_steps": 3956736000, "exact_value_avg": 0.8616594076156616, "regret_dist": 0.001921299728564918, "regret_other_env": 0.0031966199167072773, "regret_corner": 8.319319022120908e-06, "regret_row": 0.0035760498140007257, "regret_any": 0.003217302728444338, "regret_bot": 0.003828646382316947, "value_dist": 0.8616594076156616, "value_other_env": 0.8790183067321777, "value_corner": 0.8356209993362427, "value_row": 0.8550505638122559, "value_any": 0.8790333271026611, "value_bot": 0.8547979593276978, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06440.png", "entropy": 0.12843787670135498} +{"ts": "2026-03-20T18:55:58.121516Z", "loop": 6450, "env_steps": 3962880000, "exact_value_avg": 0.8608500957489014, "regret_dist": 0.0027305246330797672, "regret_other_env": 0.00453196233138442, "regret_corner": 2.836833482433576e-05, "regret_row": 0.0028478277381509542, "regret_any": 0.00453567411750555, "regret_bot": 0.00519407307729125, "value_dist": 0.8608500957489014, "value_other_env": 0.8776828646659851, "value_corner": 0.8356009721755981, "value_row": 0.8557788133621216, "value_any": 0.8777148723602295, "value_bot": 0.8534325361251831, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06450.png", "entropy": 0.1319032460451126} +{"ts": "2026-03-20T18:56:06.717003Z", "loop": 6460, "env_steps": 3969024000, "exact_value_avg": 0.8552956581115723, "regret_dist": 0.00828498974442482, "regret_other_env": 0.012074412778019905, "regret_corner": 0.0026008556596934795, "regret_row": 0.021425046026706696, "regret_any": 0.012056824751198292, "regret_bot": 0.017291588708758354, "value_dist": 0.8552956581115723, "value_other_env": 0.8701404929161072, "value_corner": 0.8330284357070923, "value_row": 0.8372016549110413, "value_any": 0.8701937794685364, "value_bot": 0.8413349986076355, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06460.png", "entropy": 0.14755825698375702} +{"ts": "2026-03-20T18:56:15.316530Z", "loop": 6470, "env_steps": 3975168000, "exact_value_avg": 0.8561534881591797, "regret_dist": 0.007427152246236801, "regret_other_env": 0.012356939725577831, "regret_corner": 3.2470128644490615e-05, "regret_row": 0.015352888964116573, "regret_any": 0.012390529736876488, "regret_bot": 0.01196164172142744, "value_dist": 0.8561534881591797, "value_other_env": 0.869857907295227, "value_corner": 0.8355967998504639, "value_row": 0.8432736992835999, "value_any": 0.869860053062439, "value_bot": 0.8466649651527405, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06470.png", "entropy": 0.12004151195287704} +{"ts": "2026-03-20T18:56:23.909065Z", "loop": 6480, "env_steps": 3981312000, "exact_value_avg": 0.8603354096412659, "regret_dist": 0.0032452635932713747, "regret_other_env": 0.00511320261284709, "regret_corner": 0.00044335477286949754, "regret_row": 0.002574821701273322, "regret_any": 0.005132457707077265, "regret_bot": 0.008874226361513138, "value_dist": 0.8603354096412659, "value_other_env": 0.877101719379425, "value_corner": 0.8351859450340271, "value_row": 0.8560518622398376, "value_any": 0.8771180510520935, "value_bot": 0.8497524261474609, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06480.png", "entropy": 0.14199699461460114} +{"ts": "2026-03-20T18:56:32.500374Z", "loop": 6490, "env_steps": 3987456000, "exact_value_avg": 0.8612470626831055, "regret_dist": 0.0023335341829806566, "regret_other_env": 0.0034969174303114414, "regret_corner": 0.0005884593119844794, "regret_row": 0.015444997698068619, "regret_any": 0.0035126549191772938, "regret_bot": 0.0017883467953652143, "value_dist": 0.8612470626831055, "value_other_env": 0.8787178993225098, "value_corner": 0.835040807723999, "value_row": 0.8431816101074219, "value_any": 0.8787379264831543, "value_bot": 0.8568382859230042, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06490.png", "entropy": 0.13511662185192108} +{"ts": "2026-03-20T18:56:41.095391Z", "loop": 6500, "env_steps": 3993600000, "exact_value_avg": 0.8612229824066162, "regret_dist": 0.00235771294683218, "regret_other_env": 0.0038885651156306267, "regret_corner": 6.143451173556969e-05, "regret_row": 0.0008818671340122819, "regret_any": 0.0038862675428390503, "regret_bot": 0.009463145397603512, "value_dist": 0.8612229824066162, "value_other_env": 0.8783262968063354, "value_corner": 0.8355678915977478, "value_row": 0.8577447533607483, "value_any": 0.8783643245697021, "value_bot": 0.8491635322570801, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06500.png", "entropy": 0.13128824532032013} +{"ts": "2026-03-20T18:56:49.692366Z", "loop": 6510, "env_steps": 3999744000, "exact_value_avg": 0.8581864833831787, "regret_dist": 0.005394178442656994, "regret_other_env": 0.008988945744931698, "regret_corner": 2.0265579223632812e-06, "regret_row": 0.006827888078987598, "regret_any": 0.008988689631223679, "regret_bot": 0.011193061247467995, "value_dist": 0.8581864833831787, "value_other_env": 0.8732259273529053, "value_corner": 0.8356272578239441, "value_row": 0.8517987728118896, "value_any": 0.8732619285583496, "value_bot": 0.8474335670471191, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06510.png", "entropy": 0.12495534867048264} +{"ts": "2026-03-20T18:56:58.287678Z", "loop": 6520, "env_steps": 4005888000, "exact_value_avg": 0.8619968891143799, "regret_dist": 0.0015837587416172028, "regret_other_env": 0.002565028378739953, "regret_corner": 0.00011185408220626414, "regret_row": 0.005308355670422316, "regret_any": 0.002585676498711109, "regret_bot": 0.0013300954597070813, "value_dist": 0.8619968891143799, "value_other_env": 0.8796498775482178, "value_corner": 0.835517406463623, "value_row": 0.8533182740211487, "value_any": 0.879664957523346, "value_bot": 0.8572964668273926, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06520.png", "entropy": 0.123788021504879} +{"ts": "2026-03-20T18:57:06.886418Z", "loop": 6530, "env_steps": 4012032000, "exact_value_avg": 0.8609362840652466, "regret_dist": 0.0026443847455084324, "regret_other_env": 0.004122913349419832, "regret_corner": 0.00042659195605665445, "regret_row": 0.01354370079934597, "regret_any": 0.004150483291596174, "regret_bot": 0.0008604381582699716, "value_dist": 0.8609362840652466, "value_other_env": 0.8780919909477234, "value_corner": 0.835202693939209, "value_row": 0.8450829386711121, "value_any": 0.8781001567840576, "value_bot": 0.8577662110328674, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06530.png", "entropy": 0.12811294198036194} +{"ts": "2026-03-20T18:57:15.488470Z", "loop": 6540, "env_steps": 4018176000, "exact_value_avg": 0.8614243268966675, "regret_dist": 0.002156337257474661, "regret_other_env": 0.0034331022761762142, "regret_corner": 0.00024118922010529786, "regret_row": 0.007907715626060963, "regret_any": 0.003522315062582493, "regret_bot": 0.0016459194011986256, "value_dist": 0.8614243268966675, "value_other_env": 0.8787817358970642, "value_corner": 0.8353881239891052, "value_row": 0.8507189154624939, "value_any": 0.8787283301353455, "value_bot": 0.8569807410240173, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06540.png", "entropy": 0.1235322430729866} +{"ts": "2026-03-20T18:57:24.093010Z", "loop": 6550, "env_steps": 4024320000, "exact_value_avg": 0.862328052520752, "regret_dist": 0.0012526406208053231, "regret_other_env": 0.0020424381364136934, "regret_corner": 6.794433284085244e-05, "regret_row": 0.0012909527868032455, "regret_any": 0.002076713601127267, "regret_bot": 0.004463200457394123, "value_dist": 0.862328052520752, "value_other_env": 0.8801724314689636, "value_corner": 0.8355613946914673, "value_row": 0.8573356866836548, "value_any": 0.880173921585083, "value_bot": 0.854163408279419, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06550.png", "entropy": 0.13059674203395844} +{"ts": "2026-03-20T18:57:32.687215Z", "loop": 6560, "env_steps": 4030464000, "exact_value_avg": 0.8615354895591736, "regret_dist": 0.0020452591124922037, "regret_other_env": 0.002810136880725622, "regret_corner": 0.0008979420526884496, "regret_row": 0.002358371391892433, "regret_any": 0.0028518838807940483, "regret_bot": 0.006790350191295147, "value_dist": 0.8615354895591736, "value_other_env": 0.8794047832489014, "value_corner": 0.8347314596176147, "value_row": 0.8562682867050171, "value_any": 0.8793987035751343, "value_bot": 0.8518362045288086, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06560.png", "entropy": 0.14133165776729584} +{"ts": "2026-03-20T18:57:41.286877Z", "loop": 6570, "env_steps": 4036608000, "exact_value_avg": 0.8560109734535217, "regret_dist": 0.007569757290184498, "regret_other_env": 0.008092992939054966, "regret_corner": 0.006784903351217508, "regret_row": 0.017035340890288353, "regret_any": 0.008112811483442783, "regret_bot": 0.017955156043171883, "value_dist": 0.8560109734535217, "value_other_env": 0.874121904373169, "value_corner": 0.828844428062439, "value_row": 0.8415913581848145, "value_any": 0.874137818813324, "value_bot": 0.8406714797019958, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06570.png", "entropy": 0.15060457587242126} +{"ts": "2026-03-20T18:57:49.886355Z", "loop": 6580, "env_steps": 4042752000, "exact_value_avg": 0.8624346256256104, "regret_dist": 0.001146102324128151, "regret_other_env": 0.00187072460539639, "regret_corner": 5.9168542065890506e-05, "regret_row": 0.008978699333965778, "regret_any": 0.0018818104872480035, "regret_bot": 0.0008703352650627494, "value_dist": 0.8624346256256104, "value_other_env": 0.8803441524505615, "value_corner": 0.835570216178894, "value_row": 0.8496479392051697, "value_any": 0.8803688287734985, "value_bot": 0.8577562570571899, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06580.png", "entropy": 0.11758198589086533} +{"ts": "2026-03-20T18:57:58.482552Z", "loop": 6590, "env_steps": 4048896000, "exact_value_avg": 0.8622264862060547, "regret_dist": 0.0013541835360229015, "regret_other_env": 0.0022204711567610502, "regret_corner": 5.4751835705246776e-05, "regret_row": 0.005910211242735386, "regret_any": 0.002234503161162138, "regret_bot": 0.0008764557424001396, "value_dist": 0.8622264862060547, "value_other_env": 0.8799943923950195, "value_corner": 0.8355745673179626, "value_row": 0.8527163863182068, "value_any": 0.8800161480903625, "value_bot": 0.8577502369880676, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06590.png", "entropy": 0.11488597095012665} +{"ts": "2026-03-20T18:58:07.075710Z", "loop": 6600, "env_steps": 4055040000, "exact_value_avg": 0.8619959354400635, "regret_dist": 0.001584700308740139, "regret_other_env": 0.0025756037794053555, "regret_corner": 9.83451827778481e-05, "regret_row": 0.003718191757798195, "regret_any": 0.0025720633566379547, "regret_bot": 0.0036855945363640785, "value_dist": 0.8619959354400635, "value_other_env": 0.879639208316803, "value_corner": 0.8355309963226318, "value_row": 0.8549084067344666, "value_any": 0.8796785473823547, "value_bot": 0.8549410700798035, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06600.png", "entropy": 0.12161929905414581} +{"ts": "2026-03-20T18:58:15.674059Z", "loop": 6610, "env_steps": 4061184000, "exact_value_avg": 0.8624436855316162, "regret_dist": 0.0011370280990377069, "regret_other_env": 0.001803815015591681, "regret_corner": 0.00013684779696632177, "regret_row": 0.0019048155518248677, "regret_any": 0.001801648992113769, "regret_bot": 0.0020423235837370157, "value_dist": 0.8624436855316162, "value_other_env": 0.8804110288619995, "value_corner": 0.8354924917221069, "value_row": 0.856721818447113, "value_any": 0.8804489374160767, "value_bot": 0.856584370136261, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06610.png", "entropy": 0.12102435529232025} +{"ts": "2026-03-20T18:58:24.266431Z", "loop": 6620, "env_steps": 4067328000, "exact_value_avg": 0.8626080751419067, "regret_dist": 0.0009726693970151246, "regret_other_env": 0.0015552487457171082, "regret_corner": 9.880017023533583e-05, "regret_row": 0.0043378244154155254, "regret_any": 0.0015791176119819283, "regret_bot": 0.001405334915034473, "value_dist": 0.8626080751419067, "value_other_env": 0.8806596398353577, "value_corner": 0.8355305194854736, "value_row": 0.8542888164520264, "value_any": 0.880671501159668, "value_bot": 0.8572213649749756, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06620.png", "entropy": 0.1157408356666565} +{"ts": "2026-03-20T18:58:32.867800Z", "loop": 6630, "env_steps": 4073472000, "exact_value_avg": 0.8610138297080994, "regret_dist": 0.002566874958574772, "regret_other_env": 0.004269064869731665, "regret_corner": 1.3589859918283764e-05, "regret_row": 0.002543398179113865, "regret_any": 0.004314103629440069, "regret_bot": 0.009970310144126415, "value_dist": 0.8610138297080994, "value_other_env": 0.8779458403587341, "value_corner": 0.8356156945228577, "value_row": 0.8560832142829895, "value_any": 0.8779364824295044, "value_bot": 0.8486562967300415, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06630.png", "entropy": 0.1199183240532875} +{"ts": "2026-03-20T18:58:41.467212Z", "loop": 6640, "env_steps": 4079616000, "exact_value_avg": 0.8609545230865479, "regret_dist": 0.0026261191815137863, "regret_other_env": 0.004342410713434219, "regret_corner": 5.168120333109982e-05, "regret_row": 0.003554383758455515, "regret_any": 0.004401066806167364, "regret_bot": 0.006698095239698887, "value_dist": 0.8609545230865479, "value_other_env": 0.8778724074363708, "value_corner": 0.8355776071548462, "value_row": 0.8550722599029541, "value_any": 0.8778495788574219, "value_bot": 0.8519285917282104, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06640.png", "entropy": 0.11536647379398346} +{"ts": "2026-03-20T18:58:50.065685Z", "loop": 6650, "env_steps": 4085760000, "exact_value_avg": 0.8626600503921509, "regret_dist": 0.0009206765098497272, "regret_other_env": 0.0014728140085935593, "regret_corner": 9.247015259461477e-05, "regret_row": 0.0013710827333852649, "regret_any": 0.0015066374326124787, "regret_bot": 0.0014879289083182812, "value_dist": 0.8626600503921509, "value_other_env": 0.8807420134544373, "value_corner": 0.8355368971824646, "value_row": 0.8572555780410767, "value_any": 0.8807439804077148, "value_bot": 0.8571386933326721, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06650.png", "entropy": 0.11395496129989624} +{"ts": "2026-03-20T18:58:58.662919Z", "loop": 6660, "env_steps": 4091904000, "exact_value_avg": 0.8627294301986694, "regret_dist": 0.0008512299973517656, "regret_other_env": 0.0013557890197262168, "regret_corner": 9.439141285838559e-05, "regret_row": 0.0016470522386953235, "regret_any": 0.0013841086765751243, "regret_bot": 0.0026206912007182837, "value_dist": 0.8627294301986694, "value_other_env": 0.8808590769767761, "value_corner": 0.8355349898338318, "value_row": 0.8569796085357666, "value_any": 0.880866527557373, "value_bot": 0.8560059070587158, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06660.png", "entropy": 0.12397990375757217} +{"ts": "2026-03-20T18:59:07.263071Z", "loop": 6670, "env_steps": 4098048000, "exact_value_avg": 0.8543499708175659, "regret_dist": 0.009230665862560272, "regret_other_env": 0.015381244011223316, "regret_corner": 4.798670943273464e-06, "regret_row": 0.010653235018253326, "regret_any": 0.015412094071507454, "regret_bot": 0.04645980894565582, "value_dist": 0.8543499708175659, "value_other_env": 0.8668335676193237, "value_corner": 0.8356244564056396, "value_row": 0.8479734063148499, "value_any": 0.8668384552001953, "value_bot": 0.8121668696403503, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06670.png", "entropy": 0.1196451187133789} +{"ts": "2026-03-20T18:59:15.863177Z", "loop": 6680, "env_steps": 4104192000, "exact_value_avg": 0.8620561361312866, "regret_dist": 0.0015245582908391953, "regret_other_env": 0.002537989057600498, "regret_corner": 4.411737336340593e-06, "regret_row": 0.0006520875031128526, "regret_any": 0.0026042598765343428, "regret_bot": 0.003281329059973359, "value_dist": 0.8620561361312866, "value_other_env": 0.879676878452301, "value_corner": 0.8356248736381531, "value_row": 0.8579744696617126, "value_any": 0.8796463012695312, "value_bot": 0.8553452491760254, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06680.png", "entropy": 0.11512668430805206} +{"ts": "2026-03-20T18:59:24.461349Z", "loop": 6690, "env_steps": 4110336000, "exact_value_avg": 0.8622720241546631, "regret_dist": 0.0013086559483781457, "regret_other_env": 0.002178746508434415, "regret_corner": 3.5201512673666002e-06, "regret_row": 0.0005670604878105223, "regret_any": 0.0022342000156641006, "regret_bot": 0.002240381669253111, "value_dist": 0.8622720241546631, "value_other_env": 0.8800361156463623, "value_corner": 0.8356258273124695, "value_row": 0.8580595850944519, "value_any": 0.8800163865089417, "value_bot": 0.8563861846923828, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06690.png", "entropy": 0.11547673493623734} +{"ts": "2026-03-20T18:59:33.057141Z", "loop": 6700, "env_steps": 4116480000, "exact_value_avg": 0.862239420413971, "regret_dist": 0.0013412418775260448, "regret_other_env": 0.0022339457646012306, "regret_corner": 2.1860005290363915e-06, "regret_row": 0.0016248056199401617, "regret_any": 0.0022582057863473892, "regret_bot": 0.0025758589617908, "value_dist": 0.862239420413971, "value_other_env": 0.8799808621406555, "value_corner": 0.8356271386146545, "value_row": 0.8570018410682678, "value_any": 0.8799924254417419, "value_bot": 0.8560507893562317, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06700.png", "entropy": 0.11923481523990631} +{"ts": "2026-03-20T18:59:41.648537Z", "loop": 6710, "env_steps": 4122624000, "exact_value_avg": 0.8621240854263306, "regret_dist": 0.001456553814932704, "regret_other_env": 0.002425081329420209, "regret_corner": 3.7625434288202086e-06, "regret_row": 0.0011905431747436523, "regret_any": 0.002456335350871086, "regret_bot": 0.0031374164391309023, "value_dist": 0.8621240854263306, "value_other_env": 0.8797897696495056, "value_corner": 0.8356255888938904, "value_row": 0.8574360609054565, "value_any": 0.8797943592071533, "value_bot": 0.8554891347885132, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06710.png", "entropy": 0.11883679032325745} +{"ts": "2026-03-20T18:59:50.241561Z", "loop": 6720, "env_steps": 4128768000, "exact_value_avg": 0.8620048761367798, "regret_dist": 0.0015758269000798464, "regret_other_env": 0.0026234074030071497, "regret_corner": 4.455944235814968e-06, "regret_row": 0.001368036144413054, "regret_any": 0.0026516751386225224, "regret_bot": 0.0033258909825235605, "value_dist": 0.8620048761367798, "value_other_env": 0.8795914649963379, "value_corner": 0.8356248736381531, "value_row": 0.8572585582733154, "value_any": 0.8795989751815796, "value_bot": 0.855300784111023, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06720.png", "entropy": 0.116921067237854} +{"ts": "2026-03-20T18:59:58.841503Z", "loop": 6730, "env_steps": 4134912000, "exact_value_avg": 0.8623955249786377, "regret_dist": 0.0011851724702864885, "regret_other_env": 0.001973116071894765, "regret_corner": 3.2568973438174e-06, "regret_row": 0.0007393971318379045, "regret_any": 0.001995627535507083, "regret_bot": 0.002822328358888626, "value_dist": 0.8623955249786377, "value_other_env": 0.8802417516708374, "value_corner": 0.8356260657310486, "value_row": 0.8578872084617615, "value_any": 0.8802549242973328, "value_bot": 0.8558043241500854, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06730.png", "entropy": 0.11603502929210663} +{"ts": "2026-03-20T19:00:07.436980Z", "loop": 6740, "env_steps": 4141056000, "exact_value_avg": 0.8627815842628479, "regret_dist": 0.0007991258171387017, "regret_other_env": 0.0013218775857239962, "regret_corner": 1.4998019651102368e-05, "regret_row": 0.002041470492258668, "regret_any": 0.0013468012912198901, "regret_bot": 0.0012206105748191476, "value_dist": 0.8627815842628479, "value_other_env": 0.8808930516242981, "value_corner": 0.8356143236160278, "value_row": 0.8565852046012878, "value_any": 0.8809037804603577, "value_bot": 0.8574060201644897, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06740.png", "entropy": 0.11719785630702972} +{"ts": "2026-03-20T19:00:16.035035Z", "loop": 6750, "env_steps": 4147200000, "exact_value_avg": 0.8627859950065613, "regret_dist": 0.0007947072735987604, "regret_other_env": 0.0013063764199614525, "regret_corner": 2.7203561330679804e-05, "regret_row": 0.0017945014405995607, "regret_any": 0.0013277274556457996, "regret_bot": 0.0012575476430356503, "value_dist": 0.8627859950065613, "value_other_env": 0.8809085488319397, "value_corner": 0.8356021046638489, "value_row": 0.8568322062492371, "value_any": 0.8809228539466858, "value_bot": 0.8573691248893738, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06750.png", "entropy": 0.11998745054006577} +{"ts": "2026-03-20T19:00:24.636580Z", "loop": 6760, "env_steps": 4153344000, "exact_value_avg": 0.8620844483375549, "regret_dist": 0.0014962356071919203, "regret_other_env": 0.0024411051999777555, "regret_corner": 7.893095607869327e-05, "regret_row": 0.005281412973999977, "regret_any": 0.002444204641506076, "regret_bot": 0.0014539591502398252, "value_dist": 0.8620844483375549, "value_other_env": 0.879773736000061, "value_corner": 0.8355504274368286, "value_row": 0.8533452749252319, "value_any": 0.879806399345398, "value_bot": 0.8571727275848389, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06760.png", "entropy": 0.12538668513298035} +{"ts": "2026-03-20T19:00:33.234589Z", "loop": 6770, "env_steps": 4159488000, "exact_value_avg": 0.8622491359710693, "regret_dist": 0.0013315618271008134, "regret_other_env": 0.0020377214532345533, "regret_corner": 0.0002723222132772207, "regret_row": 0.001408036332577467, "regret_any": 0.002038385020568967, "regret_bot": 0.0027943828608840704, "value_dist": 0.8622491359710693, "value_other_env": 0.8801771402359009, "value_corner": 0.8353569507598877, "value_row": 0.8572185635566711, "value_any": 0.8802122473716736, "value_bot": 0.8558322787284851, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06770.png", "entropy": 0.13120855391025543} +{"ts": "2026-03-20T19:00:41.836925Z", "loop": 6780, "env_steps": 4165632000, "exact_value_avg": 0.8619377017021179, "regret_dist": 0.001642965362407267, "regret_other_env": 0.002724620047956705, "regret_corner": 2.048313763225451e-05, "regret_row": 0.0009995602304115891, "regret_any": 0.0027480069547891617, "regret_bot": 0.004982615355402231, "value_dist": 0.8619377017021179, "value_other_env": 0.8794902563095093, "value_corner": 0.8356088399887085, "value_row": 0.8576271533966064, "value_any": 0.8795025944709778, "value_bot": 0.8536439538002014, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06780.png", "entropy": 0.1272900253534317} +{"ts": "2026-03-20T19:00:50.432097Z", "loop": 6790, "env_steps": 4171776000, "exact_value_avg": 0.8619541525840759, "regret_dist": 0.0016265774611383677, "regret_other_env": 0.0027002755086869, "regret_corner": 1.6030173355829902e-05, "regret_row": 0.0016236521769315004, "regret_any": 0.0027235127054154873, "regret_bot": 0.0044433255679905415, "value_dist": 0.8619541525840759, "value_other_env": 0.8795146346092224, "value_corner": 0.8356133103370667, "value_row": 0.8570030331611633, "value_any": 0.8795270323753357, "value_bot": 0.8541832566261292, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06790.png", "entropy": 0.12643587589263916} +{"ts": "2026-03-20T19:00:59.023559Z", "loop": 6800, "env_steps": 4177920000, "exact_value_avg": 0.8583963513374329, "regret_dist": 0.005184374283999205, "regret_other_env": 0.008622362278401852, "regret_corner": 2.7391315597924404e-05, "regret_row": 0.011128763668239117, "regret_any": 0.008659480139613152, "regret_bot": 0.010308921337127686, "value_dist": 0.8583963513374329, "value_other_env": 0.8735925555229187, "value_corner": 0.8356019854545593, "value_row": 0.8474978804588318, "value_any": 0.8735911250114441, "value_bot": 0.8483177423477173, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06800.png", "entropy": 0.12663201987743378} +{"ts": "2026-03-20T19:01:07.618068Z", "loop": 6810, "env_steps": 4184064000, "exact_value_avg": 0.8564962148666382, "regret_dist": 0.007084470242261887, "regret_other_env": 0.010398373007774353, "regret_corner": 0.0021136156283318996, "regret_row": 0.009097115136682987, "regret_any": 0.010384739376604557, "regret_bot": 0.01356616709381342, "value_dist": 0.8564962148666382, "value_other_env": 0.8718165159225464, "value_corner": 0.8335157036781311, "value_row": 0.8495294451713562, "value_any": 0.8718658685684204, "value_bot": 0.8450604677200317, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06810.png", "entropy": 0.14026404917240143} +{"ts": "2026-03-20T19:01:16.207707Z", "loop": 6820, "env_steps": 4190208000, "exact_value_avg": 0.8536319136619568, "regret_dist": 0.009948812425136566, "regret_other_env": 0.01654071733355522, "regret_corner": 6.095568824093789e-05, "regret_row": 0.009634528309106827, "regret_any": 0.01655137911438942, "regret_bot": 0.02137657068669796, "value_dist": 0.8536319136619568, "value_other_env": 0.8656741380691528, "value_corner": 0.8355684280395508, "value_row": 0.8489921689033508, "value_any": 0.865699291229248, "value_bot": 0.8372501134872437, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06820.png", "entropy": 0.12903450429439545} +{"ts": "2026-03-20T19:01:24.799384Z", "loop": 6830, "env_steps": 4196352000, "exact_value_avg": 0.8627920150756836, "regret_dist": 0.000788709323387593, "regret_other_env": 0.001288782455958426, "regret_corner": 3.859947173623368e-05, "regret_row": 0.002904281485825777, "regret_any": 0.0013086030958220363, "regret_bot": 0.001878803945146501, "value_dist": 0.8627920150756836, "value_other_env": 0.8809261322021484, "value_corner": 0.8355907201766968, "value_row": 0.8557223081588745, "value_any": 0.8809419870376587, "value_bot": 0.8567478656768799, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06830.png", "entropy": 0.12209518998861313} +{"ts": "2026-03-20T19:01:33.391561Z", "loop": 6840, "env_steps": 4202496000, "exact_value_avg": 0.8628284335136414, "regret_dist": 0.0007522840169258416, "regret_other_env": 0.0012445709435269237, "regret_corner": 1.3853610653313808e-05, "regret_row": 0.0012350284960120916, "regret_any": 0.001268439693376422, "regret_bot": 0.0011659881565719843, "value_dist": 0.8628284335136414, "value_other_env": 0.880970299243927, "value_corner": 0.8356155157089233, "value_row": 0.8573915958404541, "value_any": 0.8809822201728821, "value_bot": 0.8574606776237488, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06840.png", "entropy": 0.11998969316482544} +{"ts": "2026-03-20T19:01:41.988591Z", "loop": 6850, "env_steps": 4208640000, "exact_value_avg": 0.8626314401626587, "regret_dist": 0.0009492130484431982, "regret_other_env": 0.0015624227235093713, "regret_corner": 2.9398503102129325e-05, "regret_row": 0.0018966422649100423, "regret_any": 0.001590240397490561, "regret_bot": 0.0010829608654603362, "value_dist": 0.8626314401626587, "value_other_env": 0.8806524276733398, "value_corner": 0.835599958896637, "value_row": 0.856730043888092, "value_any": 0.880660355091095, "value_bot": 0.8575436472892761, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06850.png", "entropy": 0.12225894629955292} +{"ts": "2026-03-20T19:01:50.585924Z", "loop": 6860, "env_steps": 4214784000, "exact_value_avg": 0.8629286885261536, "regret_dist": 0.0006519993185065687, "regret_other_env": 0.0010801848256960511, "regret_corner": 9.721021342556924e-06, "regret_row": 0.000699599040672183, "regret_any": 0.001102015026845038, "regret_bot": 0.0017049384769052267, "value_dist": 0.8629286885261536, "value_other_env": 0.8811346888542175, "value_corner": 0.8356195688247681, "value_row": 0.8579270243644714, "value_any": 0.881148636341095, "value_bot": 0.8569217324256897, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06860.png", "entropy": 0.12025342136621475} +{"ts": "2026-03-20T19:01:59.182193Z", "loop": 6870, "env_steps": 4220928000, "exact_value_avg": 0.8619212508201599, "regret_dist": 0.001659441040828824, "regret_other_env": 0.002762638032436371, "regret_corner": 4.645188710128423e-06, "regret_row": 0.0014950674958527088, "regret_any": 0.0027852801140397787, "regret_bot": 0.007009468507021666, "value_dist": 0.8619212508201599, "value_other_env": 0.8794522285461426, "value_corner": 0.8356247544288635, "value_row": 0.8571315407752991, "value_any": 0.8794653415679932, "value_bot": 0.8516172170639038, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06870.png", "entropy": 0.12061277776956558} +{"ts": "2026-03-20T19:02:07.774725Z", "loop": 6880, "env_steps": 4227072000, "exact_value_avg": 0.8627038598060608, "regret_dist": 0.0008768411935307086, "regret_other_env": 0.0014564723242074251, "regret_corner": 7.394453405140666e-06, "regret_row": 0.0008831430459395051, "regret_any": 0.0014794704038649797, "regret_bot": 0.0021475006360560656, "value_dist": 0.8627038598060608, "value_other_env": 0.8807584643363953, "value_corner": 0.8356219530105591, "value_row": 0.857743501663208, "value_any": 0.8807711601257324, "value_bot": 0.8564791083335876, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06880.png", "entropy": 0.11895397305488586} +{"ts": "2026-03-20T19:02:16.380539Z", "loop": 6890, "env_steps": 4233216000, "exact_value_avg": 0.8626733422279358, "regret_dist": 0.00090739008737728, "regret_other_env": 0.0015046552289277315, "regret_corner": 1.1492273188196123e-05, "regret_row": 0.0011808499693870544, "regret_any": 0.0015289493603631854, "regret_bot": 0.0020928054582327604, "value_dist": 0.8626733422279358, "value_other_env": 0.880710244178772, "value_corner": 0.8356178998947144, "value_row": 0.8574457764625549, "value_any": 0.8807216882705688, "value_bot": 0.8565337657928467, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06890.png", "entropy": 0.12035758048295975} +{"ts": "2026-03-20T19:02:24.980734Z", "loop": 6900, "env_steps": 4239360000, "exact_value_avg": 0.8625698685646057, "regret_dist": 0.0010107419220730662, "regret_other_env": 0.001668549026362598, "regret_corner": 2.4031103748711757e-05, "regret_row": 0.0015751291066408157, "regret_any": 0.0016940591158345342, "regret_bot": 0.001960651483386755, "value_dist": 0.8625698685646057, "value_other_env": 0.8805462718009949, "value_corner": 0.835605263710022, "value_row": 0.8570515513420105, "value_any": 0.8805565237998962, "value_bot": 0.8566659092903137, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06900.png", "entropy": 0.12168356031179428} +{"ts": "2026-03-20T19:02:33.575013Z", "loop": 6910, "env_steps": 4245504000, "exact_value_avg": 0.8629105091094971, "regret_dist": 0.0006701719830743968, "regret_other_env": 0.001102743553929031, "regret_corner": 2.1314621335477568e-05, "regret_row": 0.0008220342569984496, "regret_any": 0.0011265557259321213, "regret_bot": 0.0015438315458595753, "value_dist": 0.8629105091094971, "value_other_env": 0.8811120986938477, "value_corner": 0.8356080055236816, "value_row": 0.8578045964241028, "value_any": 0.8811240196228027, "value_bot": 0.8570828437805176, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06910.png", "entropy": 0.12016025185585022} +{"ts": "2026-03-20T19:02:42.168871Z", "loop": 6920, "env_steps": 4251648000, "exact_value_avg": 0.8628233671188354, "regret_dist": 0.0007573440088890493, "regret_other_env": 0.0012506759958341718, "regret_corner": 1.734594661684241e-05, "regret_row": 0.0006923675537109375, "regret_any": 0.0012734484625980258, "regret_bot": 0.002179963979870081, "value_dist": 0.8628233671188354, "value_other_env": 0.8809642195701599, "value_corner": 0.8356119990348816, "value_row": 0.8579342365264893, "value_any": 0.8809770941734314, "value_bot": 0.8564466834068298, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06920.png", "entropy": 0.12161466479301453} +{"ts": "2026-03-20T19:02:50.763845Z", "loop": 6930, "env_steps": 4257792000, "exact_value_avg": 0.8611688613891602, "regret_dist": 0.0024118113797158003, "regret_other_env": 0.004013090394437313, "regret_corner": 9.892384696286172e-06, "regret_row": 0.0047251381911337376, "regret_any": 0.004036338999867439, "regret_bot": 0.007750262506306171, "value_dist": 0.8611688613891602, "value_other_env": 0.8782017827033997, "value_corner": 0.8356193900108337, "value_row": 0.8539015054702759, "value_any": 0.8782142996788025, "value_bot": 0.8508763909339905, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06930.png", "entropy": 0.11824575811624527} +{"ts": "2026-03-20T19:02:59.362492Z", "loop": 6940, "env_steps": 4263936000, "exact_value_avg": 0.8616301417350769, "regret_dist": 0.0019505827222019434, "regret_other_env": 0.00322930165566504, "regret_corner": 3.2503903639735654e-05, "regret_row": 0.004912577569484711, "regret_any": 0.0032607365865260363, "regret_bot": 0.002421109238639474, "value_dist": 0.8616301417350769, "value_other_env": 0.878985583782196, "value_corner": 0.8355969190597534, "value_row": 0.8537140488624573, "value_any": 0.8789899349212646, "value_bot": 0.8562055826187134, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06940.png", "entropy": 0.12200701236724854} +{"ts": "2026-03-20T19:03:07.957531Z", "loop": 6950, "env_steps": 4270080000, "exact_value_avg": 0.8617879152297974, "regret_dist": 0.0017928022425621748, "regret_other_env": 0.0029083394911140203, "regret_corner": 0.00011949639156227931, "regret_row": 0.0030071744695305824, "regret_any": 0.0029365483205765486, "regret_bot": 0.0017021152889356017, "value_dist": 0.8617879152297974, "value_other_env": 0.8793065547943115, "value_corner": 0.8355097770690918, "value_row": 0.855619490146637, "value_any": 0.8793140649795532, "value_bot": 0.8569244742393494, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06950.png", "entropy": 0.12742796540260315} +{"ts": "2026-03-20T19:03:16.558833Z", "loop": 6960, "env_steps": 4276224000, "exact_value_avg": 0.8616397380828857, "regret_dist": 0.0019409290980547667, "regret_other_env": 0.003231969429180026, "regret_corner": 4.368524059827905e-06, "regret_row": 0.004050905350595713, "regret_any": 0.003254773560911417, "regret_bot": 0.004826451651751995, "value_dist": 0.8616397380828857, "value_other_env": 0.8789829015731812, "value_corner": 0.8356249928474426, "value_row": 0.8545757532119751, "value_any": 0.8789958953857422, "value_bot": 0.8538002371788025, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06960.png", "entropy": 0.11882111430168152} +{"ts": "2026-03-20T19:03:25.154020Z", "loop": 6970, "env_steps": 4282368000, "exact_value_avg": 0.8609439134597778, "regret_dist": 0.0026367383543401957, "regret_other_env": 0.004393698647618294, "regret_corner": 1.2973945331395953e-06, "regret_row": 0.008086943067610264, "regret_any": 0.0044160811230540276, "regret_bot": 0.003954239655286074, "value_dist": 0.8609439134597778, "value_other_env": 0.877821147441864, "value_corner": 0.8356280326843262, "value_row": 0.8505396842956543, "value_any": 0.8778344988822937, "value_bot": 0.854672372341156, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06970.png", "entropy": 0.11447685956954956} +{"ts": "2026-03-20T19:03:33.754200Z", "loop": 6980, "env_steps": 4288512000, "exact_value_avg": 0.8629838228225708, "regret_dist": 0.0005968853947706521, "regret_other_env": 0.000984309008345008, "regret_corner": 1.5750030797789805e-05, "regret_row": 0.00039677604218013585, "regret_any": 0.0009940292220562696, "regret_bot": 0.0013296843972057104, "value_dist": 0.8629838228225708, "value_other_env": 0.8812305927276611, "value_corner": 0.8356135487556458, "value_row": 0.8582298159599304, "value_any": 0.8812565803527832, "value_bot": 0.857296884059906, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06980.png", "entropy": 0.11572834104299545} +{"ts": "2026-03-20T19:03:42.354185Z", "loop": 6990, "env_steps": 4294656000, "exact_value_avg": 0.8626163005828857, "regret_dist": 0.0009643075172789395, "regret_other_env": 0.0015994947170838714, "regret_corner": 1.1526545677043032e-05, "regret_row": 0.0005210221279412508, "regret_any": 0.0015992678236216307, "regret_bot": 0.002367296488955617, "value_dist": 0.8626163005828857, "value_other_env": 0.8806153535842896, "value_corner": 0.83561772108078, "value_row": 0.8581055998802185, "value_any": 0.8806512951850891, "value_bot": 0.8562594056129456, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_06990.png", "entropy": 0.11676067858934402} +{"ts": "2026-03-20T19:03:50.952206Z", "loop": 7000, "env_steps": 4300800000, "exact_value_avg": 0.862107515335083, "regret_dist": 0.001473197597078979, "regret_other_env": 0.0024530566297471523, "regret_corner": 3.408889142519911e-06, "regret_row": 0.002138974145054817, "regret_any": 0.0024767748545855284, "regret_bot": 0.0026959157548844814, "value_dist": 0.862107515335083, "value_other_env": 0.879761815071106, "value_corner": 0.8356258869171143, "value_row": 0.8564877510070801, "value_any": 0.8797737956047058, "value_bot": 0.855930745601654, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07000.png", "entropy": 0.11546436697244644} +{"ts": "2026-03-20T19:03:59.546552Z", "loop": 7010, "env_steps": 4306944000, "exact_value_avg": 0.862351655960083, "regret_dist": 0.001229127636179328, "regret_other_env": 0.00203655450604856, "regret_corner": 1.798719313228503e-05, "regret_row": 0.0010112379677593708, "regret_any": 0.0020597127731889486, "regret_bot": 0.0033012796193361282, "value_dist": 0.862351655960083, "value_other_env": 0.8801783323287964, "value_corner": 0.8356114029884338, "value_row": 0.8576154112815857, "value_any": 0.8801908493041992, "value_bot": 0.8553254008293152, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07010.png", "entropy": 0.11123065650463104} +{"ts": "2026-03-20T19:04:08.136173Z", "loop": 7020, "env_steps": 4313088000, "exact_value_avg": 0.8622390031814575, "regret_dist": 0.0013416860019788146, "regret_other_env": 0.0021541849710047245, "regret_corner": 0.00012293756299186498, "regret_row": 0.0033450706396251917, "regret_any": 0.0021793025080114603, "regret_bot": 0.0019249337492510676, "value_dist": 0.8622390031814575, "value_other_env": 0.8800606727600098, "value_corner": 0.8355063796043396, "value_row": 0.8552815318107605, "value_any": 0.8800712823867798, "value_bot": 0.8567017316818237, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07020.png", "entropy": 0.11647207289934158} +{"ts": "2026-03-20T19:04:16.730943Z", "loop": 7030, "env_steps": 4319232000, "exact_value_avg": 0.8603832721710205, "regret_dist": 0.00319743063300848, "regret_other_env": 0.005025565158575773, "regret_corner": 0.00045522901928052306, "regret_row": 0.018580839037895203, "regret_any": 0.005048679653555155, "regret_bot": 0.0020875870250165462, "value_dist": 0.8603832721710205, "value_other_env": 0.8771892786026001, "value_corner": 0.8351740837097168, "value_row": 0.8400458097457886, "value_any": 0.8772019147872925, "value_bot": 0.8565390706062317, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07030.png", "entropy": 0.1346321702003479} +{"ts": "2026-03-20T19:04:25.326240Z", "loop": 7040, "env_steps": 4325376000, "exact_value_avg": 0.8616570830345154, "regret_dist": 0.0019236297812312841, "regret_other_env": 0.0031223467085510492, "regret_corner": 0.00012555421562865376, "regret_row": 0.0022012866102159023, "regret_any": 0.0031477520242333412, "regret_bot": 0.007283022161573172, "value_dist": 0.8616570830345154, "value_other_env": 0.8790925741195679, "value_corner": 0.8355037569999695, "value_row": 0.8564252853393555, "value_any": 0.8791028261184692, "value_bot": 0.8513436913490295, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07040.png", "entropy": 0.12998288869857788} +{"ts": "2026-03-20T19:04:33.926753Z", "loop": 7050, "env_steps": 4331520000, "exact_value_avg": 0.8618135452270508, "regret_dist": 0.0017670794622972608, "regret_other_env": 0.0028063557110726833, "regret_corner": 0.00020816476899199188, "regret_row": 0.002617689548060298, "regret_any": 0.002832049271091819, "regret_bot": 0.0042239027097821236, "value_dist": 0.8618135452270508, "value_other_env": 0.8794084787368774, "value_corner": 0.8354211449623108, "value_row": 0.8560089468955994, "value_any": 0.8794184923171997, "value_bot": 0.8544027209281921, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07050.png", "entropy": 0.13473273813724518} +{"ts": "2026-03-20T19:04:42.519855Z", "loop": 7060, "env_steps": 4337664000, "exact_value_avg": 0.8584554195404053, "regret_dist": 0.005125252064317465, "regret_other_env": 0.008532668463885784, "regret_corner": 1.4127294889476616e-05, "regret_row": 0.005852639675140381, "regret_any": 0.008565906435251236, "regret_bot": 0.024932028725743294, "value_dist": 0.8584554195404053, "value_other_env": 0.8736822009086609, "value_corner": 0.8356152176856995, "value_row": 0.852773904800415, "value_any": 0.8736847043037415, "value_bot": 0.8336946368217468, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07060.png", "entropy": 0.11778739839792252} +{"ts": "2026-03-20T19:04:51.113233Z", "loop": 7070, "env_steps": 4343808000, "exact_value_avg": 0.8622816801071167, "regret_dist": 0.0012990370159968734, "regret_other_env": 0.0021513118408620358, "regret_corner": 2.0624698663596064e-05, "regret_row": 0.0023382953368127346, "regret_any": 0.002185053890570998, "regret_bot": 0.0018029181519523263, "value_dist": 0.8622816801071167, "value_other_env": 0.880063533782959, "value_corner": 0.835608720779419, "value_row": 0.8562884330749512, "value_any": 0.8800655603408813, "value_bot": 0.8568236827850342, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07070.png", "entropy": 0.1179620623588562} +{"ts": "2026-03-20T19:04:59.713915Z", "loop": 7080, "env_steps": 4349952000, "exact_value_avg": 0.8615957498550415, "regret_dist": 0.001984938746318221, "regret_other_env": 0.003286173567175865, "regret_corner": 3.308654049760662e-05, "regret_row": 0.004371856804937124, "regret_any": 0.003386356867849827, "regret_bot": 0.0016967863775789738, "value_dist": 0.8615957498550415, "value_other_env": 0.8789287209510803, "value_corner": 0.8355962634086609, "value_row": 0.8542547821998596, "value_any": 0.8788642287254333, "value_bot": 0.8569298386573792, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07080.png", "entropy": 0.11752930283546448} +{"ts": "2026-03-20T19:05:08.311155Z", "loop": 7090, "env_steps": 4356096000, "exact_value_avg": 0.8626912832260132, "regret_dist": 0.0008893622434698045, "regret_other_env": 0.001477627083659172, "regret_corner": 6.964803105802275e-06, "regret_row": 0.0017237119609490037, "regret_any": 0.0014992309734225273, "regret_bot": 0.0014965087175369263, "value_dist": 0.8626912832260132, "value_other_env": 0.8807372450828552, "value_corner": 0.8356223106384277, "value_row": 0.8569029569625854, "value_any": 0.8807513117790222, "value_bot": 0.8571301698684692, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07090.png", "entropy": 0.11682001501321793} +{"ts": "2026-03-20T19:05:16.908808Z", "loop": 7100, "env_steps": 4362240000, "exact_value_avg": 0.862824559211731, "regret_dist": 0.000756132765673101, "regret_other_env": 0.0012471857480704784, "regret_corner": 1.9553304809960537e-05, "regret_row": 0.0006905397749505937, "regret_any": 0.0012715901248157024, "regret_bot": 0.002003688598051667, "value_dist": 0.862824559211731, "value_other_env": 0.8809676766395569, "value_corner": 0.8356097936630249, "value_row": 0.8579360246658325, "value_any": 0.8809790015220642, "value_bot": 0.8566229343414307, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07100.png", "entropy": 0.11939980089664459} +{"ts": "2026-03-20T19:05:25.510689Z", "loop": 7110, "env_steps": 4368384000, "exact_value_avg": 0.862922191619873, "regret_dist": 0.0006584566435776651, "regret_other_env": 0.0010782727040350437, "regret_corner": 2.8732420105370693e-05, "regret_row": 0.0006497091962955892, "regret_any": 0.001103468588553369, "regret_bot": 0.0016127907438203692, "value_dist": 0.862922191619873, "value_other_env": 0.8811365962028503, "value_corner": 0.8356005549430847, "value_row": 0.8579769134521484, "value_any": 0.8811471462249756, "value_bot": 0.8570138216018677, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07110.png", "entropy": 0.11983564496040344} +{"ts": "2026-03-20T19:05:34.119237Z", "loop": 7120, "env_steps": 4374528000, "exact_value_avg": 0.8628503084182739, "regret_dist": 0.0007303814054466784, "regret_other_env": 0.0012120004976168275, "regret_corner": 7.952749911055434e-06, "regret_row": 0.0014765593223273754, "regret_any": 0.0012340245302766562, "regret_bot": 0.00124592543579638, "value_dist": 0.8628503084182739, "value_other_env": 0.8810029029846191, "value_corner": 0.8356213569641113, "value_row": 0.8571500778198242, "value_any": 0.8810164928436279, "value_bot": 0.8573806881904602, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07120.png", "entropy": 0.11794526129961014} +{"ts": "2026-03-20T19:05:42.717212Z", "loop": 7130, "env_steps": 4380672000, "exact_value_avg": 0.8626616597175598, "regret_dist": 0.0009190279524773359, "regret_other_env": 0.0015267706476151943, "regret_corner": 7.413824732793728e-06, "regret_row": 0.0026904973201453686, "regret_any": 0.0015445922035723925, "regret_bot": 0.0010696034878492355, "value_dist": 0.8626616597175598, "value_other_env": 0.8806881308555603, "value_corner": 0.8356219530105591, "value_row": 0.8559361100196838, "value_any": 0.8807060122489929, "value_bot": 0.8575570583343506, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07130.png", "entropy": 0.11946383863687515} +{"ts": "2026-03-20T19:05:51.311811Z", "loop": 7140, "env_steps": 4386816000, "exact_value_avg": 0.862723708152771, "regret_dist": 0.0008569954079575837, "regret_other_env": 0.0014087083982303739, "regret_corner": 2.9425820684991777e-05, "regret_row": 0.0007311941590160131, "regret_any": 0.0014372281730175018, "regret_bot": 0.001014544046483934, "value_dist": 0.862723708152771, "value_other_env": 0.8808061480522156, "value_corner": 0.835599958896637, "value_row": 0.8578954339027405, "value_any": 0.8808134198188782, "value_bot": 0.8576121926307678, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07140.png", "entropy": 0.11958862096071243} +{"ts": "2026-03-20T19:05:59.909473Z", "loop": 7150, "env_steps": 4392960000, "exact_value_avg": 0.8612008094787598, "regret_dist": 0.0023798777256160975, "regret_other_env": 0.0038951870519667864, "regret_corner": 0.0001069133504643105, "regret_row": 0.0016716561513021588, "regret_any": 0.003963051363825798, "regret_bot": 0.0014901302056387067, "value_dist": 0.8612008094787598, "value_other_env": 0.8783196806907654, "value_corner": 0.8355223536491394, "value_row": 0.8569549918174744, "value_any": 0.8782874941825867, "value_bot": 0.8571364879608154, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07150.png", "entropy": 0.12502549588680267} +{"ts": "2026-03-20T19:06:08.508642Z", "loop": 7160, "env_steps": 4399104000, "exact_value_avg": 0.8623406887054443, "regret_dist": 0.001239969627931714, "regret_other_env": 0.002060307189822197, "regret_corner": 9.4632314358023e-06, "regret_row": 0.0028406463097780943, "regret_any": 0.002084800973534584, "regret_bot": 0.002902181353420019, "value_dist": 0.8623406887054443, "value_other_env": 0.880154550075531, "value_corner": 0.8356198668479919, "value_row": 0.8557859063148499, "value_any": 0.8801658749580383, "value_bot": 0.8557243943214417, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07160.png", "entropy": 0.11442539095878601} +{"ts": "2026-03-20T19:06:17.103560Z", "loop": 7170, "env_steps": 4405248000, "exact_value_avg": 0.8604110479354858, "regret_dist": 0.0031697156373411417, "regret_other_env": 0.005274079740047455, "regret_corner": 1.3169150406611152e-05, "regret_row": 0.005829955916851759, "regret_any": 0.005314239766448736, "regret_bot": 0.01126077026128769, "value_dist": 0.8604110479354858, "value_other_env": 0.8769408464431763, "value_corner": 0.8356161713600159, "value_row": 0.8527966737747192, "value_any": 0.8769363164901733, "value_bot": 0.8473658561706543, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07170.png", "entropy": 0.11391747742891312} +{"ts": "2026-03-20T19:06:25.702633Z", "loop": 7180, "env_steps": 4411392000, "exact_value_avg": 0.8615741729736328, "regret_dist": 0.0020065216813236475, "regret_other_env": 0.0033377159852534533, "regret_corner": 9.729961675475352e-06, "regret_row": 0.004557569976896048, "regret_any": 0.0033811433240771294, "regret_bot": 0.00747168343514204, "value_dist": 0.8615741729736328, "value_other_env": 0.8788771629333496, "value_corner": 0.8356195688247681, "value_row": 0.8540690541267395, "value_any": 0.8788694143295288, "value_bot": 0.8511550426483154, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07180.png", "entropy": 0.11357215791940689} +{"ts": "2026-03-20T19:06:34.298054Z", "loop": 7190, "env_steps": 4417536000, "exact_value_avg": 0.8546829223632812, "regret_dist": 0.008897799998521805, "regret_other_env": 0.014335926622152328, "regret_corner": 0.0007406076183542609, "regret_row": 0.013001835905015469, "regret_any": 0.014496740885078907, "regret_bot": 0.021526897326111794, "value_dist": 0.8546829223632812, "value_other_env": 0.8678789734840393, "value_corner": 0.834888756275177, "value_row": 0.8456247448921204, "value_any": 0.867753803730011, "value_bot": 0.8370997309684753, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07190.png", "entropy": 0.12931810319423676} +{"ts": "2026-03-20T19:06:42.891899Z", "loop": 7200, "env_steps": 4423680000, "exact_value_avg": 0.8623602390289307, "regret_dist": 0.001220368780195713, "regret_other_env": 0.0020071601029485464, "regret_corner": 4.018147956230678e-05, "regret_row": 0.0009610836859792471, "regret_any": 0.0020332173444330692, "regret_bot": 0.005910739302635193, "value_dist": 0.8623602390289307, "value_other_env": 0.8802077174186707, "value_corner": 0.8355891108512878, "value_row": 0.8576655387878418, "value_any": 0.8802173733711243, "value_bot": 0.8527158498764038, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07200.png", "entropy": 0.12305467575788498} +{"ts": "2026-03-20T19:06:51.488108Z", "loop": 7210, "env_steps": 4429824000, "exact_value_avg": 0.8626441955566406, "regret_dist": 0.0009365080040879548, "regret_other_env": 0.0015334341442212462, "regret_corner": 4.111876478418708e-05, "regret_row": 0.0008693950367160141, "regret_any": 0.0015566140646114945, "regret_bot": 0.00440676836296916, "value_dist": 0.8626441955566406, "value_other_env": 0.8806813955307007, "value_corner": 0.8355882167816162, "value_row": 0.8577571511268616, "value_any": 0.8806939721107483, "value_bot": 0.854219913482666, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07210.png", "entropy": 0.12359388917684555} +{"ts": "2026-03-20T19:07:00.094332Z", "loop": 7220, "env_steps": 4435968000, "exact_value_avg": 0.8607491254806519, "regret_dist": 0.002831648802384734, "regret_other_env": 0.004714051261544228, "regret_corner": 8.044640708249062e-06, "regret_row": 0.011706897988915443, "regret_any": 0.00473070191219449, "regret_bot": 0.0025572706945240498, "value_dist": 0.8607491254806519, "value_other_env": 0.8775008916854858, "value_corner": 0.8356212973594666, "value_row": 0.8469197154045105, "value_any": 0.8775198459625244, "value_bot": 0.8560693860054016, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07220.png", "entropy": 0.11755263805389404} +{"ts": "2026-03-20T19:07:08.692483Z", "loop": 7230, "env_steps": 4442112000, "exact_value_avg": 0.8572087287902832, "regret_dist": 0.006371898576617241, "regret_other_env": 0.010562804527580738, "regret_corner": 8.553863153792918e-05, "regret_row": 0.005071008577942848, "regret_any": 0.010547786951065063, "regret_bot": 0.0071228849701583385, "value_dist": 0.8572087287902832, "value_other_env": 0.8716520667076111, "value_corner": 0.8355438113212585, "value_row": 0.8535556197166443, "value_any": 0.8717028498649597, "value_bot": 0.8515037298202515, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07230.png", "entropy": 0.1267491579055786} +{"ts": "2026-03-20T19:07:17.285645Z", "loop": 7240, "env_steps": 4448256000, "exact_value_avg": 0.8623144626617432, "regret_dist": 0.0012662045191973448, "regret_other_env": 0.0018108466174453497, "regret_corner": 0.0004492412263061851, "regret_row": 0.0011837502242997289, "regret_any": 0.0018109894590452313, "regret_bot": 0.0007700020214542747, "value_dist": 0.8623144626617432, "value_other_env": 0.880403995513916, "value_corner": 0.8351800441741943, "value_row": 0.8574428558349609, "value_any": 0.8804396390914917, "value_bot": 0.8578565716743469, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07240.png", "entropy": 0.1261620968580246} +{"ts": "2026-03-20T19:07:25.883086Z", "loop": 7250, "env_steps": 4454400000, "exact_value_avg": 0.8626832962036133, "regret_dist": 0.0008974011288955808, "regret_other_env": 0.0012289817677810788, "regret_corner": 0.00040003014146350324, "regret_row": 0.001220006262883544, "regret_any": 0.0012518158182501793, "regret_bot": 0.0013194336788728833, "value_dist": 0.8626832962036133, "value_other_env": 0.8809859156608582, "value_corner": 0.8352292776107788, "value_row": 0.8574066162109375, "value_any": 0.8809987902641296, "value_bot": 0.8573071956634521, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07250.png", "entropy": 0.12495167553424835} +{"ts": "2026-03-20T19:07:34.477858Z", "loop": 7260, "env_steps": 4460544000, "exact_value_avg": 0.8624749183654785, "regret_dist": 0.0011057308875024319, "regret_other_env": 0.0017447620630264282, "regret_corner": 0.0001471837458666414, "regret_row": 0.0016510012792423368, "regret_any": 0.0017712225671857595, "regret_bot": 0.0018308140570297837, "value_dist": 0.8624749183654785, "value_other_env": 0.8804701566696167, "value_corner": 0.835482120513916, "value_row": 0.8569756150245667, "value_any": 0.8804793953895569, "value_bot": 0.8567957878112793, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07260.png", "entropy": 0.12077125161886215} +{"ts": "2026-03-20T19:07:43.075115Z", "loop": 7270, "env_steps": 4466688000, "exact_value_avg": 0.8625185489654541, "regret_dist": 0.001062088878825307, "regret_other_env": 0.0017459336668252945, "regret_corner": 3.632158404798247e-05, "regret_row": 0.0012847483158111572, "regret_any": 0.0017736164154484868, "regret_bot": 0.0035101675894111395, "value_dist": 0.8625185489654541, "value_other_env": 0.8804689645767212, "value_corner": 0.8355929851531982, "value_row": 0.8573418259620667, "value_any": 0.8804770112037659, "value_bot": 0.8551164865493774, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07270.png", "entropy": 0.1162719577550888} +{"ts": "2026-03-20T19:07:51.666576Z", "loop": 7280, "env_steps": 4472832000, "exact_value_avg": 0.862278938293457, "regret_dist": 0.0013017556630074978, "regret_other_env": 0.002164625097066164, "regret_corner": 7.451574219885515e-06, "regret_row": 0.002288012532517314, "regret_any": 0.0021911112125962973, "regret_bot": 0.004695620387792587, "value_dist": 0.862278938293457, "value_other_env": 0.8800502419471741, "value_corner": 0.8356218934059143, "value_row": 0.8563386797904968, "value_any": 0.8800594806671143, "value_bot": 0.8539310097694397, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07280.png", "entropy": 0.11170922219753265} +{"ts": "2026-03-20T19:08:00.259603Z", "loop": 7290, "env_steps": 4478976000, "exact_value_avg": 0.8606477975845337, "regret_dist": 0.0029329415410757065, "regret_other_env": 0.004884885624051094, "regret_corner": 5.025168320571538e-06, "regret_row": 0.004968305118381977, "regret_any": 0.0049287076108157635, "regret_bot": 0.007156123407185078, "value_dist": 0.8606477975845337, "value_other_env": 0.8773300647735596, "value_corner": 0.8356243371963501, "value_row": 0.8536583781242371, "value_any": 0.8773218989372253, "value_bot": 0.8514705300331116, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07290.png", "entropy": 0.10915270447731018} +{"ts": "2026-03-20T19:08:08.852101Z", "loop": 7300, "env_steps": 4485120000, "exact_value_avg": 0.8615476489067078, "regret_dist": 0.0020330059342086315, "regret_other_env": 0.0033759523648768663, "regret_corner": 1.8586219084681943e-05, "regret_row": 0.01610649563372135, "regret_any": 0.0034104781225323677, "regret_bot": 0.0015897565754130483, "value_dist": 0.8615476489067078, "value_other_env": 0.8788388967514038, "value_corner": 0.8356107473373413, "value_row": 0.8425202369689941, "value_any": 0.8788400888442993, "value_bot": 0.8570368885993958, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07300.png", "entropy": 0.10757821798324585} +{"ts": "2026-03-20T19:08:17.446953Z", "loop": 7310, "env_steps": 4491264000, "exact_value_avg": 0.8625056743621826, "regret_dist": 0.0010750570800155401, "regret_other_env": 0.001791090238839388, "regret_corner": 1.0073185876535717e-06, "regret_row": 0.004340853542089462, "regret_any": 0.0018113696714863181, "regret_bot": 0.0012723346007987857, "value_dist": 0.8625056743621826, "value_other_env": 0.8804238438606262, "value_corner": 0.8356282711029053, "value_row": 0.8542857766151428, "value_any": 0.880439281463623, "value_bot": 0.8573542237281799, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07310.png", "entropy": 0.11072614789009094} +{"ts": "2026-03-20T19:08:26.043695Z", "loop": 7320, "env_steps": 4497408000, "exact_value_avg": 0.8626357316970825, "regret_dist": 0.0009448736673220992, "regret_other_env": 0.0015731966122984886, "regret_corner": 2.389152996329358e-06, "regret_row": 0.002045038156211376, "regret_any": 0.0015951674431562424, "regret_bot": 0.0013992668827995658, "value_dist": 0.8626357316970825, "value_other_env": 0.8806416392326355, "value_corner": 0.8356269001960754, "value_row": 0.8565815687179565, "value_any": 0.8806554675102234, "value_bot": 0.8572272658348083, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07320.png", "entropy": 0.10837660729885101} +{"ts": "2026-03-20T19:08:34.635646Z", "loop": 7330, "env_steps": 4503552000, "exact_value_avg": 0.8628048896789551, "regret_dist": 0.0007758420542813838, "regret_other_env": 0.0012856055982410908, "regret_corner": 1.119673288485501e-05, "regret_row": 0.0011326264357194304, "regret_any": 0.0013098446652293205, "regret_bot": 0.0008407319546677172, "value_dist": 0.8628048896789551, "value_other_env": 0.8809292912483215, "value_corner": 0.8356181383132935, "value_row": 0.8574939966201782, "value_any": 0.8809407949447632, "value_bot": 0.8577858209609985, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07330.png", "entropy": 0.11143234372138977} +{"ts": "2026-03-20T19:08:43.239314Z", "loop": 7340, "env_steps": 4509696000, "exact_value_avg": 0.8630678653717041, "regret_dist": 0.0005128552438691258, "regret_other_env": 0.0008503724238835275, "regret_corner": 6.579359705938259e-06, "regret_row": 0.0005445990827865899, "regret_any": 0.0008624249021522701, "regret_bot": 0.00102534971665591, "value_dist": 0.8630678653717041, "value_other_env": 0.8813645839691162, "value_corner": 0.8356227278709412, "value_row": 0.8580819368362427, "value_any": 0.8813881874084473, "value_bot": 0.8576012253761292, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07340.png", "entropy": 0.11062028259038925} +{"ts": "2026-03-20T19:08:51.835777Z", "loop": 7350, "env_steps": 4515840000, "exact_value_avg": 0.8622483611106873, "regret_dist": 0.0013323582243174314, "regret_other_env": 0.0022181435488164425, "regret_corner": 3.680090230773203e-06, "regret_row": 0.0019690210465341806, "regret_any": 0.0022398196160793304, "regret_bot": 0.0034427279606461525, "value_dist": 0.8622483611106873, "value_other_env": 0.8799967765808105, "value_corner": 0.8356256484985352, "value_row": 0.8566576242446899, "value_any": 0.8800107836723328, "value_bot": 0.8551838994026184, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07350.png", "entropy": 0.11271485686302185} +{"ts": "2026-03-20T19:09:00.430383Z", "loop": 7360, "env_steps": 4521984000, "exact_value_avg": 0.8618031740188599, "regret_dist": 0.0017774990992620587, "regret_other_env": 0.0029620311688631773, "regret_corner": 7.008513307482644e-07, "regret_row": 0.005005292594432831, "regret_any": 0.0029836008325219154, "regret_bot": 0.005326073616743088, "value_dist": 0.8618031740188599, "value_other_env": 0.8792528510093689, "value_corner": 0.8356286287307739, "value_row": 0.8536213636398315, "value_any": 0.8792669773101807, "value_bot": 0.8533005714416504, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07360.png", "entropy": 0.10784610360860825} +{"ts": "2026-03-20T19:09:09.027647Z", "loop": 7370, "env_steps": 4528128000, "exact_value_avg": 0.8623813390731812, "regret_dist": 0.0011993980733677745, "regret_other_env": 0.0019969483837485313, "regret_corner": 3.072619620070327e-06, "regret_row": 0.002371100941672921, "regret_any": 0.002019126433879137, "regret_bot": 0.0029545873403549194, "value_dist": 0.8623813390731812, "value_other_env": 0.880217969417572, "value_corner": 0.8356262445449829, "value_row": 0.8562555313110352, "value_any": 0.880231499671936, "value_bot": 0.8556720018386841, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07370.png", "entropy": 0.10561937093734741} +{"ts": "2026-03-20T19:09:17.622930Z", "loop": 7380, "env_steps": 4534272000, "exact_value_avg": 0.8627765774726868, "regret_dist": 0.0008041007095016539, "regret_other_env": 0.0013340602163225412, "regret_corner": 9.1612346295733e-06, "regret_row": 0.000870770076289773, "regret_any": 0.0013585026608780026, "regret_bot": 0.002401522593572736, "value_dist": 0.8627765774726868, "value_other_env": 0.8808807730674744, "value_corner": 0.8356201648712158, "value_row": 0.8577558994293213, "value_any": 0.8808920979499817, "value_bot": 0.8562251925468445, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07380.png", "entropy": 0.10154255479574203} +{"ts": "2026-03-20T19:09:26.217382Z", "loop": 7390, "env_steps": 4540416000, "exact_value_avg": 0.862902045249939, "regret_dist": 0.0006785803707316518, "regret_other_env": 0.0011050256434828043, "regret_corner": 3.891239612130448e-05, "regret_row": 0.0003395975800231099, "regret_any": 0.0011282794876024127, "regret_bot": 0.002268944401293993, "value_dist": 0.862902045249939, "value_other_env": 0.8811098337173462, "value_corner": 0.8355904221534729, "value_row": 0.85828697681427, "value_any": 0.8811222910881042, "value_bot": 0.8563576936721802, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07390.png", "entropy": 0.10823611915111542} +{"ts": "2026-03-20T19:09:34.812371Z", "loop": 7400, "env_steps": 4546560000, "exact_value_avg": 0.861566424369812, "regret_dist": 0.002014322206377983, "regret_other_env": 0.003110351040959358, "regret_corner": 0.0003702784888446331, "regret_row": 0.0038537688087671995, "regret_any": 0.0031303996220231056, "regret_bot": 0.002319799503311515, "value_dist": 0.861566424369812, "value_other_env": 0.8791045546531677, "value_corner": 0.8352590203285217, "value_row": 0.8547729253768921, "value_any": 0.8791202306747437, "value_bot": 0.8563067317008972, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07400.png", "entropy": 0.11774415522813797} +{"ts": "2026-03-20T19:09:43.408035Z", "loop": 7410, "env_steps": 4552704000, "exact_value_avg": 0.8615183234214783, "regret_dist": 0.002062385668978095, "regret_other_env": 0.0032635510433465242, "regret_corner": 0.0002606377238407731, "regret_row": 0.014161736704409122, "regret_any": 0.0032935538329184055, "regret_bot": 0.00244598975405097, "value_dist": 0.8615183234214783, "value_other_env": 0.878951370716095, "value_corner": 0.8353686332702637, "value_row": 0.844464898109436, "value_any": 0.8789569735527039, "value_bot": 0.8561806082725525, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07410.png", "entropy": 0.11723396182060242} +{"ts": "2026-03-20T19:09:52.003512Z", "loop": 7420, "env_steps": 4558848000, "exact_value_avg": 0.8625366687774658, "regret_dist": 0.0010439315810799599, "regret_other_env": 0.001650376827456057, "regret_corner": 0.00013426344958133996, "regret_row": 0.004054255783557892, "regret_any": 0.0016745113534852862, "regret_bot": 0.002862414810806513, "value_dist": 0.8625366687774658, "value_other_env": 0.8805644512176514, "value_corner": 0.8354950547218323, "value_row": 0.8545723557472229, "value_any": 0.8805761337280273, "value_bot": 0.8557642102241516, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07420.png", "entropy": 0.11340288072824478} +{"ts": "2026-03-20T19:10:00.599578Z", "loop": 7430, "env_steps": 4564992000, "exact_value_avg": 0.8623965382575989, "regret_dist": 0.001184138935059309, "regret_other_env": 0.0017871522577479482, "regret_corner": 0.000279618805507198, "regret_row": 0.0015939058503136039, "regret_any": 0.0018100792076438665, "regret_bot": 0.005240604281425476, "value_dist": 0.8623965382575989, "value_other_env": 0.8804277181625366, "value_corner": 0.8353496789932251, "value_row": 0.8570327162742615, "value_any": 0.8804405331611633, "value_bot": 0.8533860445022583, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07430.png", "entropy": 0.11685506999492645} +{"ts": "2026-03-20T19:10:09.204034Z", "loop": 7440, "env_steps": 4571136000, "exact_value_avg": 0.8622758388519287, "regret_dist": 0.0013048878172412515, "regret_other_env": 0.0021313652396202087, "regret_corner": 6.517172005260363e-05, "regret_row": 0.0004733173409476876, "regret_any": 0.002156183822080493, "regret_bot": 0.007801311556249857, "value_dist": 0.8622758388519287, "value_other_env": 0.8800835609436035, "value_corner": 0.835564136505127, "value_row": 0.858153223991394, "value_any": 0.8800944089889526, "value_bot": 0.8508252501487732, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07440.png", "entropy": 0.11143629252910614} +{"ts": "2026-03-20T19:10:17.805023Z", "loop": 7450, "env_steps": 4577280000, "exact_value_avg": 0.8626205921173096, "regret_dist": 0.0009601243655197322, "regret_other_env": 0.0015186913078650832, "regret_corner": 0.000122273966553621, "regret_row": 0.0015256657497957349, "regret_any": 0.0015416127862408757, "regret_bot": 0.004836398176848888, "value_dist": 0.8626205921173096, "value_other_env": 0.8806962370872498, "value_corner": 0.8355070352554321, "value_row": 0.8571009635925293, "value_any": 0.8807089924812317, "value_bot": 0.853790283203125, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07450.png", "entropy": 0.111300989985466} +{"ts": "2026-03-20T19:10:26.406688Z", "loop": 7460, "env_steps": 4583424000, "exact_value_avg": 0.8630197048187256, "regret_dist": 0.0005609743529930711, "regret_other_env": 0.0009077238501049578, "regret_corner": 4.085004547960125e-05, "regret_row": 0.0010166856227442622, "regret_any": 0.0009329332388006151, "regret_bot": 0.0016685865120962262, "value_dist": 0.8630197048187256, "value_other_env": 0.8813071846961975, "value_corner": 0.8355885148048401, "value_row": 0.8576099276542664, "value_any": 0.8813176155090332, "value_bot": 0.8569580912590027, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07460.png", "entropy": 0.1079849824309349} +{"ts": "2026-03-20T19:10:35.012012Z", "loop": 7470, "env_steps": 4589568000, "exact_value_avg": 0.8626850843429565, "regret_dist": 0.0008956589736044407, "regret_other_env": 0.0014447745634242892, "regret_corner": 7.198552339104936e-05, "regret_row": 0.0017572239739820361, "regret_any": 0.0014571287902072072, "regret_bot": 0.0008753633592277765, "value_dist": 0.8626850843429565, "value_other_env": 0.8807701468467712, "value_corner": 0.8355573415756226, "value_row": 0.8568693995475769, "value_any": 0.8807935118675232, "value_bot": 0.8577512502670288, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07470.png", "entropy": 0.11103428900241852} +{"ts": "2026-03-20T19:10:43.609556Z", "loop": 7480, "env_steps": 4595712000, "exact_value_avg": 0.8625895977020264, "regret_dist": 0.000991066568531096, "regret_other_env": 0.001551146968267858, "regret_corner": 0.00015094579430297017, "regret_row": 0.0008809143328107893, "regret_any": 0.0015514395199716091, "regret_bot": 0.0010710293427109718, "value_dist": 0.8625895977020264, "value_other_env": 0.8806637525558472, "value_corner": 0.8354783654212952, "value_row": 0.8577457070350647, "value_any": 0.8806991577148438, "value_bot": 0.8575555682182312, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07480.png", "entropy": 0.11234966665506363} +{"ts": "2026-03-20T19:10:52.205065Z", "loop": 7490, "env_steps": 4601856000, "exact_value_avg": 0.8616558313369751, "regret_dist": 0.0019248828757554293, "regret_other_env": 0.002972954185679555, "regret_corner": 0.0003527755616232753, "regret_row": 0.0031163643579930067, "regret_any": 0.00301905139349401, "regret_bot": 0.001237013260833919, "value_dist": 0.8616558313369751, "value_other_env": 0.879241943359375, "value_corner": 0.8352766036987305, "value_row": 0.8555102348327637, "value_any": 0.8792315125465393, "value_bot": 0.8573896884918213, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07490.png", "entropy": 0.12273269146680832} +{"ts": "2026-03-20T19:11:00.804572Z", "loop": 7500, "env_steps": 4608000000, "exact_value_avg": 0.8620513677597046, "regret_dist": 0.0015293469186872244, "regret_other_env": 0.0023350634146481752, "regret_corner": 0.0003207718546036631, "regret_row": 0.004122007172554731, "regret_any": 0.0023567562457174063, "regret_bot": 0.001515218522399664, "value_dist": 0.8620513677597046, "value_other_env": 0.8798798322677612, "value_corner": 0.8353085517883301, "value_row": 0.8545046448707581, "value_any": 0.8798938989639282, "value_bot": 0.857111394405365, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07500.png", "entropy": 0.12133920937776566} +{"ts": "2026-03-20T19:11:09.402704Z", "loop": 7510, "env_steps": 4614144000, "exact_value_avg": 0.8605642318725586, "regret_dist": 0.003016514703631401, "regret_other_env": 0.004562201909720898, "regret_corner": 0.0006979838362894952, "regret_row": 0.006178331095725298, "regret_any": 0.004589541349560022, "regret_bot": 0.0030715244356542826, "value_dist": 0.8605642318725586, "value_other_env": 0.8776527047157288, "value_corner": 0.8349313735961914, "value_row": 0.8524483442306519, "value_any": 0.8776610493659973, "value_bot": 0.8555551171302795, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07510.png", "entropy": 0.12467798590660095} +{"ts": "2026-03-20T19:11:17.997805Z", "loop": 7520, "env_steps": 4620288000, "exact_value_avg": 0.8619858622550964, "regret_dist": 0.001594752655364573, "regret_other_env": 0.0025928234681487083, "regret_corner": 9.764631977304816e-05, "regret_row": 0.0063163056038320065, "regret_any": 0.0026147926691919565, "regret_bot": 0.0023425351828336716, "value_dist": 0.8619858622550964, "value_other_env": 0.8796219825744629, "value_corner": 0.8355316519737244, "value_row": 0.8523103594779968, "value_any": 0.8796358108520508, "value_bot": 0.8562840819358826, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07520.png", "entropy": 0.12217661738395691} +{"ts": "2026-03-20T19:11:26.590941Z", "loop": 7530, "env_steps": 4626432000, "exact_value_avg": 0.8618149757385254, "regret_dist": 0.0017657080898061395, "regret_other_env": 0.002917206846177578, "regret_corner": 3.845990067929961e-05, "regret_row": 0.007872555404901505, "regret_any": 0.002936106873676181, "regret_bot": 0.004419433418661356, "value_dist": 0.8618149757385254, "value_other_env": 0.87929767370224, "value_corner": 0.8355908393859863, "value_row": 0.8507540225982666, "value_any": 0.8793144822120667, "value_bot": 0.8542071580886841, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07530.png", "entropy": 0.11825920641422272} +{"ts": "2026-03-20T19:11:35.185894Z", "loop": 7540, "env_steps": 4632576000, "exact_value_avg": 0.8623262047767639, "regret_dist": 0.001254475791938603, "regret_other_env": 0.001955146435648203, "regret_corner": 0.0002034698991337791, "regret_row": 0.0016025649383664131, "regret_any": 0.0019526185933500528, "regret_bot": 0.0016327282646670938, "value_dist": 0.8623262047767639, "value_other_env": 0.8802596926689148, "value_corner": 0.835425853729248, "value_row": 0.857024073600769, "value_any": 0.8802979588508606, "value_bot": 0.8569939732551575, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07540.png", "entropy": 0.11728504300117493} +{"ts": "2026-03-20T19:11:43.785864Z", "loop": 7550, "env_steps": 4638720000, "exact_value_avg": 0.8612457513809204, "regret_dist": 0.0023349158000200987, "regret_other_env": 0.0037882078904658556, "regret_corner": 0.0001549775479361415, "regret_row": 0.00407072389498353, "regret_any": 0.0038202786818146706, "regret_bot": 0.0007408506935462356, "value_dist": 0.8612457513809204, "value_other_env": 0.8784266710281372, "value_corner": 0.8354743123054504, "value_row": 0.8545559048652649, "value_any": 0.8784303069114685, "value_bot": 0.8578857183456421, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07550.png", "entropy": 0.1207946315407753} +{"ts": "2026-03-20T19:11:52.391603Z", "loop": 7560, "env_steps": 4644864000, "exact_value_avg": 0.8627325296401978, "regret_dist": 0.0008481726399622858, "regret_other_env": 0.001258708885870874, "regret_corner": 0.00023236822744365782, "regret_row": 0.0011971984058618546, "regret_any": 0.0012745794374495745, "regret_bot": 0.0016775826225057244, "value_dist": 0.8627325296401978, "value_other_env": 0.88095623254776, "value_corner": 0.835396945476532, "value_row": 0.8574294447898865, "value_any": 0.8809760212898254, "value_bot": 0.8569490909576416, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07560.png", "entropy": 0.11917568743228912} +{"ts": "2026-03-20T19:12:00.994439Z", "loop": 7570, "env_steps": 4651008000, "exact_value_avg": 0.8612956404685974, "regret_dist": 0.002284994348883629, "regret_other_env": 0.0034850065130740404, "regret_corner": 0.0004849756951443851, "regret_row": 0.003964407369494438, "regret_any": 0.003483276581391692, "regret_bot": 0.004453923553228378, "value_dist": 0.8612956404685974, "value_other_env": 0.8787298202514648, "value_corner": 0.8351443409919739, "value_row": 0.8546622395515442, "value_any": 0.8787673115730286, "value_bot": 0.8541727662086487, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07570.png", "entropy": 0.12500952184200287} +{"ts": "2026-03-20T19:12:09.593609Z", "loop": 7580, "env_steps": 4657152000, "exact_value_avg": 0.8624918460845947, "regret_dist": 0.0010889054974541068, "regret_other_env": 0.0017847833223640919, "regret_corner": 4.508843267103657e-05, "regret_row": 0.0023362531792372465, "regret_any": 0.001783704967238009, "regret_bot": 0.0016051495913416147, "value_dist": 0.8624918460845947, "value_other_env": 0.8804301619529724, "value_corner": 0.8355841636657715, "value_row": 0.8562902808189392, "value_any": 0.880466878414154, "value_bot": 0.8570215106010437, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07580.png", "entropy": 0.12092698365449905} +{"ts": "2026-03-20T19:12:18.187513Z", "loop": 7590, "env_steps": 4663296000, "exact_value_avg": 0.8628820180892944, "regret_dist": 0.0006986832013353705, "regret_other_env": 0.001155333942733705, "regret_corner": 1.3707081961911172e-05, "regret_row": 0.0016884218202903867, "regret_any": 0.001175510580651462, "regret_bot": 0.0014200140722095966, "value_dist": 0.8628820180892944, "value_other_env": 0.8810595273971558, "value_corner": 0.8356155753135681, "value_row": 0.8569381833076477, "value_any": 0.8810750842094421, "value_bot": 0.8572065830230713, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07590.png", "entropy": 0.11389296501874924} +{"ts": "2026-03-20T19:12:26.784249Z", "loop": 7600, "env_steps": 4669440000, "exact_value_avg": 0.8624569177627563, "regret_dist": 0.0011237554717808962, "regret_other_env": 0.0018661486683413386, "regret_corner": 1.0165572348341811e-05, "regret_row": 0.0011857005301862955, "regret_any": 0.0018900204449892044, "regret_bot": 0.007321598008275032, "value_dist": 0.8624569177627563, "value_other_env": 0.8803486824035645, "value_corner": 0.8356191515922546, "value_row": 0.8574408888816833, "value_any": 0.8803606033325195, "value_bot": 0.8513050079345703, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07600.png", "entropy": 0.11519800871610641} +{"ts": "2026-03-20T19:12:35.385029Z", "loop": 7610, "env_steps": 4675584000, "exact_value_avg": 0.8620395064353943, "regret_dist": 0.0015412033535540104, "regret_other_env": 0.0017563170986250043, "regret_corner": 0.0012185325613245368, "regret_row": 0.0013804193586111069, "regret_any": 0.0017781918868422508, "regret_bot": 0.0026715146377682686, "value_dist": 0.8620395064353943, "value_other_env": 0.8804585933685303, "value_corner": 0.8344107866287231, "value_row": 0.8572461605072021, "value_any": 0.8804724216461182, "value_bot": 0.855955183506012, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07610.png", "entropy": 0.12507189810276031} +{"ts": "2026-03-20T19:12:43.976877Z", "loop": 7620, "env_steps": 4681728000, "exact_value_avg": 0.8626858592033386, "regret_dist": 0.0008947960450313985, "regret_other_env": 0.001380699803121388, "regret_corner": 0.00016594033513683826, "regret_row": 0.0010162765393033624, "regret_any": 0.0014041706454008818, "regret_bot": 0.0028381850570440292, "value_dist": 0.8626858592033386, "value_other_env": 0.88083416223526, "value_corner": 0.8354634046554565, "value_row": 0.8576104044914246, "value_any": 0.8808464407920837, "value_bot": 0.8557884097099304, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07620.png", "entropy": 0.11899008601903915} +{"ts": "2026-03-20T19:12:52.571653Z", "loop": 7630, "env_steps": 4687872000, "exact_value_avg": 0.8628309965133667, "regret_dist": 0.0007496345788240433, "regret_other_env": 0.00122805533464998, "regret_corner": 3.200322680640966e-05, "regret_row": 0.0007350472151301801, "regret_any": 0.0012524951016530395, "regret_bot": 0.0031183508690446615, "value_dist": 0.8628309965133667, "value_other_env": 0.8809868097305298, "value_corner": 0.8355972766876221, "value_row": 0.8578915596008301, "value_any": 0.8809980750083923, "value_bot": 0.8555083274841309, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07630.png", "entropy": 0.11336951702833176} +{"ts": "2026-03-20T19:13:01.168985Z", "loop": 7640, "env_steps": 4694016000, "exact_value_avg": 0.8623418807983398, "regret_dist": 0.0012388667091727257, "regret_other_env": 0.0020431936718523502, "regret_corner": 3.237625060137361e-05, "regret_row": 0.0017621867591515183, "regret_any": 0.0020723268389701843, "regret_bot": 0.002191632753238082, "value_dist": 0.8623418807983398, "value_other_env": 0.8801717162132263, "value_corner": 0.8355969786643982, "value_row": 0.8568643927574158, "value_any": 0.8801782131195068, "value_bot": 0.8564350008964539, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07640.png", "entropy": 0.11100731790065765} +{"ts": "2026-03-20T19:13:09.773047Z", "loop": 7650, "env_steps": 4700160000, "exact_value_avg": 0.8600292205810547, "regret_dist": 0.003551381640136242, "regret_other_env": 0.005329854786396027, "regret_corner": 0.0008836716879159212, "regret_row": 0.006997305434197187, "regret_any": 0.005354609806090593, "regret_bot": 0.0019130803411826491, "value_dist": 0.8600292205810547, "value_other_env": 0.876884937286377, "value_corner": 0.8347456455230713, "value_row": 0.8516293168067932, "value_any": 0.8768959641456604, "value_bot": 0.8567135334014893, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07650.png", "entropy": 0.12746760249137878} +{"ts": "2026-03-20T19:13:18.368305Z", "loop": 7660, "env_steps": 4706304000, "exact_value_avg": 0.8628231287002563, "regret_dist": 0.0007575824856758118, "regret_other_env": 0.0011453308397904038, "regret_corner": 0.00017595986719243228, "regret_row": 0.0007829186506569386, "regret_any": 0.0011681810719892383, "regret_bot": 0.0022532150615006685, "value_dist": 0.8628231287002563, "value_other_env": 0.8810696005821228, "value_corner": 0.8354533314704895, "value_row": 0.8578437566757202, "value_any": 0.8810824155807495, "value_bot": 0.8563734292984009, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07660.png", "entropy": 0.11836946755647659} +{"ts": "2026-03-20T19:13:26.965569Z", "loop": 7670, "env_steps": 4712448000, "exact_value_avg": 0.8629562854766846, "regret_dist": 0.0006243825191631913, "regret_other_env": 0.00103753840085119, "regret_corner": 4.648665708373301e-06, "regret_row": 0.0019168331054970622, "regret_any": 0.0010538630886003375, "regret_bot": 0.0014072648482397199, "value_dist": 0.8629562854766846, "value_other_env": 0.8811773061752319, "value_corner": 0.8356246948242188, "value_row": 0.8567097783088684, "value_any": 0.8811967372894287, "value_bot": 0.857219398021698, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07670.png", "entropy": 0.11044211685657501} +{"ts": "2026-03-20T19:13:35.566701Z", "loop": 7680, "env_steps": 4718592000, "exact_value_avg": 0.8626658916473389, "regret_dist": 0.0009148305980488658, "regret_other_env": 0.0015188812976703048, "regret_corner": 8.7544331108802e-06, "regret_row": 0.00355749879963696, "regret_any": 0.001518934965133667, "regret_bot": 0.0005373682361096144, "value_dist": 0.8626658916473389, "value_other_env": 0.8806959986686707, "value_corner": 0.8356205821037292, "value_row": 0.8550692200660706, "value_any": 0.8807317018508911, "value_bot": 0.8580891489982605, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07680.png", "entropy": 0.10488613694906235} +{"ts": "2026-03-20T19:13:44.173698Z", "loop": 7690, "env_steps": 4724736000, "exact_value_avg": 0.8606314659118652, "regret_dist": 0.0029492073226720095, "regret_other_env": 0.004875393118709326, "regret_corner": 5.9928501286776736e-05, "regret_row": 0.008843135088682175, "regret_any": 0.004868725780397654, "regret_bot": 0.009329996071755886, "value_dist": 0.8606314659118652, "value_other_env": 0.8773394823074341, "value_corner": 0.835569441318512, "value_row": 0.8497835993766785, "value_any": 0.8773818612098694, "value_bot": 0.8492965698242188, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07690.png", "entropy": 0.11232364922761917} +{"ts": "2026-03-20T19:13:52.771475Z", "loop": 7700, "env_steps": 4730880000, "exact_value_avg": 0.8628115653991699, "regret_dist": 0.000769126636441797, "regret_other_env": 0.001279126270674169, "regret_corner": 4.127125066588633e-06, "regret_row": 0.0030551922973245382, "regret_any": 0.0012816792586818337, "regret_bot": 0.000756260531488806, "value_dist": 0.8628115653991699, "value_other_env": 0.8809357285499573, "value_corner": 0.8356252312660217, "value_row": 0.855571448802948, "value_any": 0.8809689283370972, "value_bot": 0.85787034034729, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07700.png", "entropy": 0.10652011632919312} +{"ts": "2026-03-20T19:14:01.371053Z", "loop": 7710, "env_steps": 4737024000, "exact_value_avg": 0.8628883361816406, "regret_dist": 0.0006923230248503387, "regret_other_env": 0.0011504751164466143, "regret_corner": 5.094707375974394e-06, "regret_row": 0.0017413838068023324, "regret_any": 0.0011750933481380343, "regret_bot": 0.0013601362006738782, "value_dist": 0.8628883361816406, "value_other_env": 0.8810644149780273, "value_corner": 0.8356242179870605, "value_row": 0.8568853139877319, "value_any": 0.8810755014419556, "value_bot": 0.8572664856910706, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07710.png", "entropy": 0.1042003482580185} +{"ts": "2026-03-20T19:14:09.971813Z", "loop": 7720, "env_steps": 4743168000, "exact_value_avg": 0.8630232810974121, "regret_dist": 0.0005573455127887428, "regret_other_env": 0.0009106191573664546, "regret_corner": 2.743502591329161e-05, "regret_row": 0.0008148955530487001, "regret_any": 0.0009291143505834043, "regret_bot": 0.0014370245626196265, "value_dist": 0.8630232810974121, "value_other_env": 0.8813042044639587, "value_corner": 0.8356019258499146, "value_row": 0.8578117489814758, "value_any": 0.8813214302062988, "value_bot": 0.8571896553039551, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07720.png", "entropy": 0.1112150177359581} +{"ts": "2026-03-20T19:14:18.571113Z", "loop": 7730, "env_steps": 4749312000, "exact_value_avg": 0.8613642454147339, "regret_dist": 0.0022164604160934687, "regret_other_env": 0.003197506768628955, "regret_corner": 0.0007448907126672566, "regret_row": 0.003297131508588791, "regret_any": 0.003199789673089981, "regret_bot": 0.004226423799991608, "value_dist": 0.8613642454147339, "value_other_env": 0.8790174126625061, "value_corner": 0.8348844051361084, "value_row": 0.8553294539451599, "value_any": 0.8790507912635803, "value_bot": 0.8544002175331116, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07730.png", "entropy": 0.12267552316188812} +{"ts": "2026-03-20T19:14:27.170008Z", "loop": 7740, "env_steps": 4755456000, "exact_value_avg": 0.8539639115333557, "regret_dist": 0.009616776369512081, "regret_other_env": 0.01503370888531208, "regret_corner": 0.0014913767809048295, "regret_row": 0.026432326063513756, "regret_any": 0.015051793307065964, "regret_bot": 0.02251243032515049, "value_dist": 0.8539639115333557, "value_other_env": 0.8671811819076538, "value_corner": 0.8341379165649414, "value_row": 0.8321943283081055, "value_any": 0.8671988248825073, "value_bot": 0.8361141085624695, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07740.png", "entropy": 0.11615940928459167} +{"ts": "2026-03-20T19:14:35.772671Z", "loop": 7750, "env_steps": 4761600000, "exact_value_avg": 0.8622927665710449, "regret_dist": 0.0012879178393632174, "regret_other_env": 0.001839393749833107, "regret_corner": 0.0004607036826200783, "regret_row": 0.0018442340660840273, "regret_any": 0.0018444779561832547, "regret_bot": 0.0023162246216088533, "value_dist": 0.8622927665710449, "value_other_env": 0.8803754448890686, "value_corner": 0.8351686000823975, "value_row": 0.8567824363708496, "value_any": 0.8804061412811279, "value_bot": 0.8563104271888733, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07750.png", "entropy": 0.12453281134366989} +{"ts": "2026-03-20T19:14:44.368821Z", "loop": 7760, "env_steps": 4767744000, "exact_value_avg": 0.8611149787902832, "regret_dist": 0.0024657314643263817, "regret_other_env": 0.0040893713012337685, "regret_corner": 3.0271710784290917e-05, "regret_row": 0.004673642106354237, "regret_any": 0.004110123962163925, "regret_bot": 0.006618996616452932, "value_dist": 0.8611149787902832, "value_other_env": 0.8781254887580872, "value_corner": 0.8355990648269653, "value_row": 0.8539530038833618, "value_any": 0.8781405091285706, "value_bot": 0.8520076870918274, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07760.png", "entropy": 0.1220356747508049} +{"ts": "2026-03-20T19:14:52.961153Z", "loop": 7770, "env_steps": 4773888000, "exact_value_avg": 0.8612083196640015, "regret_dist": 0.002372405957430601, "regret_other_env": 0.003930762875825167, "regret_corner": 3.4870707168010995e-05, "regret_row": 0.0043053715489804745, "regret_any": 0.0039508407935500145, "regret_bot": 0.006669067312031984, "value_dist": 0.8612083196640015, "value_other_env": 0.8782840967178345, "value_corner": 0.8355944752693176, "value_row": 0.8543212413787842, "value_any": 0.8782997727394104, "value_bot": 0.8519575595855713, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07770.png", "entropy": 0.12083358317613602} +{"ts": "2026-03-20T19:15:01.563903Z", "loop": 7780, "env_steps": 4780032000, "exact_value_avg": 0.8629106283187866, "regret_dist": 0.0006700619705952704, "regret_other_env": 0.0010918647749349475, "regret_corner": 3.7357709516072646e-05, "regret_row": 0.0002888352901209146, "regret_any": 0.001116066938266158, "regret_bot": 0.0015686110127717257, "value_dist": 0.8629106283187866, "value_other_env": 0.8811230063438416, "value_corner": 0.8355919122695923, "value_row": 0.8583377599716187, "value_any": 0.881134569644928, "value_bot": 0.857058048248291, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07780.png", "entropy": 0.11101202666759491} +{"ts": "2026-03-20T19:15:10.166329Z", "loop": 7790, "env_steps": 4786176000, "exact_value_avg": 0.8621741533279419, "regret_dist": 0.0014065542491152883, "regret_other_env": 0.0023349279072135687, "regret_corner": 1.3993681022839155e-05, "regret_row": 0.0005440233508124948, "regret_any": 0.0023649001959711313, "regret_bot": 0.0009509415249340236, "value_dist": 0.8621741533279419, "value_other_env": 0.8798799514770508, "value_corner": 0.835615336894989, "value_row": 0.8580827116966248, "value_any": 0.8798856735229492, "value_bot": 0.8576756715774536, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07790.png", "entropy": 0.10945186018943787} +{"ts": "2026-03-20T19:15:18.759808Z", "loop": 7800, "env_steps": 4792320000, "exact_value_avg": 0.8610832691192627, "regret_dist": 0.0024975098203867674, "regret_other_env": 0.004162076395004988, "regret_corner": 6.596247885681805e-07, "regret_row": 0.004240911453962326, "regret_any": 0.004163833335042, "regret_bot": 0.007749099284410477, "value_dist": 0.8610832691192627, "value_other_env": 0.878052830696106, "value_corner": 0.8356286883354187, "value_row": 0.8543857336044312, "value_any": 0.8780867457389832, "value_bot": 0.8508774638175964, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07800.png", "entropy": 0.10827665030956268} +{"ts": "2026-03-20T19:15:27.349200Z", "loop": 7810, "env_steps": 4798464000, "exact_value_avg": 0.8617793321609497, "regret_dist": 0.0018013104563578963, "regret_other_env": 0.002993570873513818, "regret_corner": 1.2919804248667788e-05, "regret_row": 0.0006737515795975924, "regret_any": 0.003013047156855464, "regret_bot": 0.00737393693998456, "value_dist": 0.8617793321609497, "value_other_env": 0.8792213201522827, "value_corner": 0.8356163501739502, "value_row": 0.8579528331756592, "value_any": 0.8792375922203064, "value_bot": 0.8512526750564575, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07810.png", "entropy": 0.11206157505512238} +{"ts": "2026-03-20T19:15:35.945053Z", "loop": 7820, "env_steps": 4804608000, "exact_value_avg": 0.859310507774353, "regret_dist": 0.0042701843194663525, "regret_other_env": 0.006040935404598713, "regret_corner": 0.0016140571096912026, "regret_row": 0.004001896362751722, "regret_any": 0.006039520259946585, "regret_bot": 0.004515241831541061, "value_dist": 0.859310507774353, "value_other_env": 0.8761739134788513, "value_corner": 0.8340153098106384, "value_row": 0.8546247482299805, "value_any": 0.8762110471725464, "value_bot": 0.8541113138198853, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07820.png", "entropy": 0.11704468727111816} +{"ts": "2026-03-20T19:15:44.541858Z", "loop": 7830, "env_steps": 4810752000, "exact_value_avg": 0.8598387837409973, "regret_dist": 0.003741975873708725, "regret_other_env": 0.0055497013963758945, "regret_corner": 0.0010303875897079706, "regret_row": 0.006318307481706142, "regret_any": 0.00554168876260519, "regret_bot": 0.007396084256470203, "value_dist": 0.8598387837409973, "value_other_env": 0.8766652345657349, "value_corner": 0.834598958492279, "value_row": 0.8523083329200745, "value_any": 0.8767088651657104, "value_bot": 0.8512305021286011, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07830.png", "entropy": 0.11644924432039261} +{"ts": "2026-03-20T19:15:53.139528Z", "loop": 7840, "env_steps": 4816896000, "exact_value_avg": 0.860660195350647, "regret_dist": 0.002920476021245122, "regret_other_env": 0.004863787908107042, "regret_corner": 5.508462891157251e-06, "regret_row": 0.002883019158616662, "regret_any": 0.004859547130763531, "regret_bot": 0.009151624515652657, "value_dist": 0.860660195350647, "value_other_env": 0.8773511648178101, "value_corner": 0.8356238007545471, "value_row": 0.8557436466217041, "value_any": 0.8773910403251648, "value_bot": 0.8494749665260315, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07840.png", "entropy": 0.11919756978750229} +{"ts": "2026-03-20T19:16:01.741019Z", "loop": 7850, "env_steps": 4823040000, "exact_value_avg": 0.8601810932159424, "regret_dist": 0.003399698995053768, "regret_other_env": 0.00566472951322794, "regret_corner": 2.1532177925109863e-06, "regret_row": 0.0038498591165989637, "regret_any": 0.005660900380462408, "regret_bot": 0.009792376309633255, "value_dist": 0.8601810932159424, "value_other_env": 0.8765501976013184, "value_corner": 0.8356271982192993, "value_row": 0.8547767996788025, "value_any": 0.8765897154808044, "value_bot": 0.8488342761993408, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07850.png", "entropy": 0.11823286861181259} +{"ts": "2026-03-20T19:16:10.333267Z", "loop": 7860, "env_steps": 4829184000, "exact_value_avg": 0.8608278036117554, "regret_dist": 0.002752867294475436, "regret_other_env": 0.004531473387032747, "regret_corner": 8.495798101648688e-05, "regret_row": 0.01959204114973545, "regret_any": 0.004534102976322174, "regret_bot": 0.003990947734564543, "value_dist": 0.8608278036117554, "value_other_env": 0.8776834011077881, "value_corner": 0.8355443477630615, "value_row": 0.8390345573425293, "value_any": 0.8777165412902832, "value_bot": 0.8546356558799744, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07860.png", "entropy": 0.11357148736715317} +{"ts": "2026-03-20T19:16:18.936032Z", "loop": 7870, "env_steps": 4835328000, "exact_value_avg": 0.8523402214050293, "regret_dist": 0.011240498162806034, "regret_other_env": 0.018710142001509666, "regret_corner": 3.60300145985093e-05, "regret_row": 0.017526062205433846, "regret_any": 0.018772481009364128, "regret_bot": 0.044089727103710175, "value_dist": 0.8523402214050293, "value_other_env": 0.8635047674179077, "value_corner": 0.8355933427810669, "value_row": 0.8411005139350891, "value_any": 0.8634781241416931, "value_bot": 0.8145368695259094, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07870.png", "entropy": 0.11509045213460922} +{"ts": "2026-03-20T19:16:27.531476Z", "loop": 7880, "env_steps": 4841472000, "exact_value_avg": 0.8599829077720642, "regret_dist": 0.0035977535881102085, "regret_other_env": 0.004560412373393774, "regret_corner": 0.0021537647116929293, "regret_row": 0.006420922931283712, "regret_any": 0.004554194398224354, "regret_bot": 0.004559425637125969, "value_dist": 0.8599829077720642, "value_other_env": 0.8776544332504272, "value_corner": 0.8334755897521973, "value_row": 0.852205753326416, "value_any": 0.8776963949203491, "value_bot": 0.8540672063827515, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07880.png", "entropy": 0.1393473595380783} +{"ts": "2026-03-20T19:16:36.127994Z", "loop": 7890, "env_steps": 4847616000, "exact_value_avg": 0.8623201847076416, "regret_dist": 0.001260519027709961, "regret_other_env": 0.002067854627966881, "regret_corner": 4.951556911692023e-05, "regret_row": 0.002429374260827899, "regret_any": 0.0020910613238811493, "regret_bot": 0.000980284297838807, "value_dist": 0.8623201847076416, "value_other_env": 0.8801469802856445, "value_corner": 0.8355798125267029, "value_row": 0.8561972379684448, "value_any": 0.8801595568656921, "value_bot": 0.8576464056968689, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07890.png", "entropy": 0.1200946494936943} +{"ts": "2026-03-20T19:16:44.722979Z", "loop": 7900, "env_steps": 4853760000, "exact_value_avg": 0.8604234457015991, "regret_dist": 0.0031572466250509024, "regret_other_env": 0.005251571536064148, "regret_corner": 1.5758972949697636e-05, "regret_row": 0.0011563858715817332, "regret_any": 0.005610504187643528, "regret_bot": 0.0008640236919745803, "value_dist": 0.8604234457015991, "value_other_env": 0.8769633173942566, "value_corner": 0.8356135487556458, "value_row": 0.8574702143669128, "value_any": 0.8766400814056396, "value_bot": 0.8577626347541809, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07900.png", "entropy": 0.12027569860219955} +{"ts": "2026-03-20T19:16:53.324683Z", "loop": 7910, "env_steps": 4859904000, "exact_value_avg": 0.862159013748169, "regret_dist": 0.0014216756680980325, "regret_other_env": 0.0023637861013412476, "regret_corner": 8.510053703503218e-06, "regret_row": 0.0013418233720585704, "regret_any": 0.002419635420665145, "regret_bot": 0.0008329330012202263, "value_dist": 0.862159013748169, "value_other_env": 0.8798511624336243, "value_corner": 0.8356208205223083, "value_row": 0.8572847843170166, "value_any": 0.8798308968544006, "value_bot": 0.8577936887741089, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07910.png", "entropy": 0.11421281844377518} +{"ts": "2026-03-20T19:17:01.917438Z", "loop": 7920, "env_steps": 4866048000, "exact_value_avg": 0.8589951992034912, "regret_dist": 0.0045855059288442135, "regret_other_env": 0.007641179021447897, "regret_corner": 1.9957622043875745e-06, "regret_row": 0.0031990502029657364, "regret_any": 0.007730900309979916, "regret_bot": 0.02199491485953331, "value_dist": 0.8589951992034912, "value_other_env": 0.8745737075805664, "value_corner": 0.8356273174285889, "value_row": 0.8554275631904602, "value_any": 0.8745197057723999, "value_bot": 0.8366317749023438, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07920.png", "entropy": 0.11214344203472137} +{"ts": "2026-03-20T19:17:10.508689Z", "loop": 7930, "env_steps": 4872192000, "exact_value_avg": 0.8617294430732727, "regret_dist": 0.0018512568203732371, "regret_other_env": 0.0030848754104226828, "regret_corner": 8.290012942779867e-07, "regret_row": 0.014131519943475723, "regret_any": 0.0031022753100842237, "regret_bot": 0.0019792707171291113, "value_dist": 0.8617294430732727, "value_other_env": 0.8791300058364868, "value_corner": 0.8356285095214844, "value_row": 0.8444951772689819, "value_any": 0.8791483640670776, "value_bot": 0.8566473722457886, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07930.png", "entropy": 0.1122271791100502} +{"ts": "2026-03-20T19:17:19.099288Z", "loop": 7940, "env_steps": 4878336000, "exact_value_avg": 0.8623114228248596, "regret_dist": 0.0012692251475527883, "regret_other_env": 0.0021138761658221483, "regret_corner": 2.2485853605758166e-06, "regret_row": 0.006480042822659016, "regret_any": 0.0021336989011615515, "regret_bot": 0.002038142876699567, "value_dist": 0.8623114228248596, "value_other_env": 0.8801009654998779, "value_corner": 0.835627019405365, "value_row": 0.852146565914154, "value_any": 0.880116879940033, "value_bot": 0.8565884232521057, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07940.png", "entropy": 0.11628954112529755} +{"ts": "2026-03-20T19:17:27.695564Z", "loop": 7950, "env_steps": 4884480000, "exact_value_avg": 0.8610541820526123, "regret_dist": 0.0025264841970056295, "regret_other_env": 0.004177260212600231, "regret_corner": 5.0319733418291435e-05, "regret_row": 0.0018445736495777965, "regret_any": 0.004200110211968422, "regret_bot": 0.014118753373622894, "value_dist": 0.8610541820526123, "value_other_env": 0.8780375719070435, "value_corner": 0.835578978061676, "value_row": 0.856782078742981, "value_any": 0.8780505061149597, "value_bot": 0.8445079326629639, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07950.png", "entropy": 0.12311241775751114} +{"ts": "2026-03-20T19:17:36.289264Z", "loop": 7960, "env_steps": 4890624000, "exact_value_avg": 0.859451174736023, "regret_dist": 0.004129475448280573, "regret_other_env": 0.005030564032495022, "regret_corner": 0.002777842339128256, "regret_row": 0.0017162091098725796, "regret_any": 0.00505346292629838, "regret_bot": 0.01189940981566906, "value_dist": 0.859451174736023, "value_other_env": 0.877184271812439, "value_corner": 0.8328514695167542, "value_row": 0.8569104671478271, "value_any": 0.8771971464157104, "value_bot": 0.846727192401886, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07960.png", "entropy": 0.13454747200012207} +{"ts": "2026-03-20T19:17:44.895093Z", "loop": 7970, "env_steps": 4896768000, "exact_value_avg": 0.8620222806930542, "regret_dist": 0.0015585047658532858, "regret_other_env": 0.002567073330283165, "regret_corner": 4.5651697291759774e-05, "regret_row": 0.0006415772368200123, "regret_any": 0.002588852308690548, "regret_bot": 0.010362515226006508, "value_dist": 0.8620222806930542, "value_other_env": 0.8796478509902954, "value_corner": 0.8355836868286133, "value_row": 0.8579850196838379, "value_any": 0.8796616792678833, "value_bot": 0.8482641577720642, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07970.png", "entropy": 0.11829816550016403} +{"ts": "2026-03-20T19:17:53.500279Z", "loop": 7980, "env_steps": 4902912000, "exact_value_avg": 0.86101233959198, "regret_dist": 0.002568416064605117, "regret_other_env": 0.004276487044990063, "regret_corner": 6.309152013272978e-06, "regret_row": 0.007695221807807684, "regret_any": 0.004296678584069014, "regret_bot": 0.009121160954236984, "value_dist": 0.86101233959198, "value_other_env": 0.877938449382782, "value_corner": 0.835623025894165, "value_row": 0.8509314060211182, "value_any": 0.8779539465904236, "value_bot": 0.8495054841041565, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07980.png", "entropy": 0.11548171192407608} +{"ts": "2026-03-20T19:18:02.094373Z", "loop": 7990, "env_steps": 4909056000, "exact_value_avg": 0.8628643155097961, "regret_dist": 0.0007164121489040554, "regret_other_env": 0.0011331400601193309, "regret_corner": 9.132028208114207e-05, "regret_row": 0.0004329735820647329, "regret_any": 0.0011512241326272488, "regret_bot": 0.0016749260248616338, "value_dist": 0.8628643155097961, "value_other_env": 0.881081759929657, "value_corner": 0.8355380296707153, "value_row": 0.8581936359405518, "value_any": 0.8810994029045105, "value_bot": 0.8569517135620117, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_07990.png", "entropy": 0.11376499384641647} +{"ts": "2026-03-20T19:18:10.690144Z", "loop": 8000, "env_steps": 4915200000, "exact_value_avg": 0.8607956171035767, "regret_dist": 0.002785034477710724, "regret_other_env": 0.004239353816956282, "regret_corner": 0.0006035551778040826, "regret_row": 0.0015072672395035625, "regret_any": 0.004237726796418428, "regret_bot": 0.0009718685760162771, "value_dist": 0.8607956171035767, "value_other_env": 0.8779755234718323, "value_corner": 0.8350258469581604, "value_row": 0.8571194410324097, "value_any": 0.8780128359794617, "value_bot": 0.8576548099517822, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08000.png", "entropy": 0.1152023896574974} +{"ts": "2026-03-20T19:18:19.284874Z", "loop": 8010, "env_steps": 4921344000, "exact_value_avg": 0.862147331237793, "regret_dist": 0.0014333720318973064, "regret_other_env": 0.0023828293196856976, "regret_corner": 9.186069291899912e-06, "regret_row": 0.0019016783917322755, "regret_any": 0.0023804467637091875, "regret_bot": 0.002303941873833537, "value_dist": 0.862147331237793, "value_other_env": 0.8798320293426514, "value_corner": 0.8356201648712158, "value_row": 0.8567249178886414, "value_any": 0.8798701763153076, "value_bot": 0.8563226461410522, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08010.png", "entropy": 0.11413133889436722} +{"ts": "2026-03-20T19:18:27.878237Z", "loop": 8020, "env_steps": 4927488000, "exact_value_avg": 0.8612876534461975, "regret_dist": 0.0022929836995899677, "regret_other_env": 0.0038137631490826607, "regret_corner": 1.181463449029252e-05, "regret_row": 0.004509874153882265, "regret_any": 0.0038087391294538975, "regret_bot": 0.006162744946777821, "value_dist": 0.8612876534461975, "value_other_env": 0.8784011006355286, "value_corner": 0.8356174826622009, "value_row": 0.8541167974472046, "value_any": 0.8784418702125549, "value_bot": 0.852463960647583, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08020.png", "entropy": 0.11723648011684418} +{"ts": "2026-03-20T19:18:36.473260Z", "loop": 8030, "env_steps": 4933632000, "exact_value_avg": 0.856763482093811, "regret_dist": 0.006817210931330919, "regret_other_env": 0.01132529228925705, "regret_corner": 5.5088105000322685e-05, "regret_row": 0.028313737362623215, "regret_any": 0.011328074149787426, "regret_bot": 0.01207713969051838, "value_dist": 0.856763482093811, "value_other_env": 0.8708896636962891, "value_corner": 0.835574209690094, "value_row": 0.8303129076957703, "value_any": 0.8709225654602051, "value_bot": 0.8465494513511658, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08030.png", "entropy": 0.12111220508813858} +{"ts": "2026-03-20T19:18:45.064974Z", "loop": 8040, "env_steps": 4939776000, "exact_value_avg": 0.8603556156158447, "regret_dist": 0.003225100925192237, "regret_other_env": 0.0036941340658813715, "regret_corner": 0.002521551214158535, "regret_row": 0.00534087885171175, "regret_any": 0.003713292069733143, "regret_bot": 0.005948404781520367, "value_dist": 0.8603556156158447, "value_other_env": 0.8785207271575928, "value_corner": 0.8331078290939331, "value_row": 0.8532856702804565, "value_any": 0.8785372972488403, "value_bot": 0.8526782393455505, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08040.png", "entropy": 0.1369173377752304} +{"ts": "2026-03-20T19:18:53.657861Z", "loop": 8050, "env_steps": 4945920000, "exact_value_avg": 0.8558332920074463, "regret_dist": 0.007747367024421692, "regret_other_env": 0.012533703818917274, "regret_corner": 0.0005678609595634043, "regret_row": 0.05252974480390549, "regret_any": 0.012559493072330952, "regret_bot": 0.0011301197810098529, "value_dist": 0.8558332920074463, "value_other_env": 0.869681179523468, "value_corner": 0.8350614309310913, "value_row": 0.8060968518257141, "value_any": 0.8696910738945007, "value_bot": 0.8574965596199036, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08050.png", "entropy": 0.12403701990842819} +{"ts": "2026-03-20T19:19:02.249528Z", "loop": 8060, "env_steps": 4952064000, "exact_value_avg": 0.8622715473175049, "regret_dist": 0.0013091121800243855, "regret_other_env": 0.002179417759180069, "regret_corner": 3.6537649066303857e-06, "regret_row": 0.003209381364285946, "regret_any": 0.002204686403274536, "regret_bot": 0.003923088777810335, "value_dist": 0.8622715473175049, "value_other_env": 0.8800354599952698, "value_corner": 0.8356257081031799, "value_row": 0.8554173111915588, "value_any": 0.8800459504127502, "value_bot": 0.8547035455703735, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08060.png", "entropy": 0.11608386039733887} +{"ts": "2026-03-20T19:19:10.827916Z", "loop": 8070, "env_steps": 4958208000, "exact_value_avg": 0.8615109920501709, "regret_dist": 0.0020697324071079493, "regret_other_env": 0.0034474253188818693, "regret_corner": 3.19282230520912e-06, "regret_row": 0.003390110796317458, "regret_any": 0.0034795620013028383, "regret_bot": 0.004229671321809292, "value_dist": 0.8615109920501709, "value_other_env": 0.8787674903869629, "value_corner": 0.8356261253356934, "value_row": 0.8552365303039551, "value_any": 0.8787710070610046, "value_bot": 0.8543969988822937, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08070.png", "entropy": 0.11371621489524841} +{"ts": "2026-03-20T19:19:19.408330Z", "loop": 8080, "env_steps": 4964352000, "exact_value_avg": 0.8626083135604858, "regret_dist": 0.0009723613620735705, "regret_other_env": 0.0016185501590371132, "regret_corner": 3.078083409491228e-06, "regret_row": 0.004622340202331543, "regret_any": 0.0016413194825872779, "regret_bot": 0.0027034138329327106, "value_dist": 0.8626083135604858, "value_other_env": 0.8805963397026062, "value_corner": 0.8356262445449829, "value_row": 0.8540042638778687, "value_any": 0.8806093335151672, "value_bot": 0.8559232354164124, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08080.png", "entropy": 0.11593987792730331} +{"ts": "2026-03-20T19:19:27.988010Z", "loop": 8090, "env_steps": 4970496000, "exact_value_avg": 0.8602623343467712, "regret_dist": 0.003318400587886572, "regret_other_env": 0.0055269780568778515, "regret_corner": 5.533795047085732e-06, "regret_row": 0.022608771920204163, "regret_any": 0.005545626860111952, "regret_bot": 0.007822711020708084, "value_dist": 0.8602623343467712, "value_other_env": 0.8766878843307495, "value_corner": 0.8356238603591919, "value_row": 0.836017906665802, "value_any": 0.8767049908638, "value_bot": 0.8508039712905884, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08090.png", "entropy": 0.120213083922863} +{"ts": "2026-03-20T19:19:36.565632Z", "loop": 8100, "env_steps": 4976640000, "exact_value_avg": 0.8607820272445679, "regret_dist": 0.0027986266650259495, "regret_other_env": 0.004551387391984463, "regret_corner": 0.00016948582197073847, "regret_row": 0.003018895396962762, "regret_any": 0.004575864877551794, "regret_bot": 0.017761649563908577, "value_dist": 0.8607820272445679, "value_other_env": 0.8776634931564331, "value_corner": 0.83545982837677, "value_row": 0.8556076884269714, "value_any": 0.8776747584342957, "value_bot": 0.8408649563789368, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08100.png", "entropy": 0.13291457295417786} +{"ts": "2026-03-20T19:19:45.148143Z", "loop": 8110, "env_steps": 4982784000, "exact_value_avg": 0.8623071908950806, "regret_dist": 0.0012734468327835202, "regret_other_env": 0.0017145125893875957, "regret_corner": 0.0006118481396697462, "regret_row": 0.0012499615550041199, "regret_any": 0.0017376963514834642, "regret_bot": 0.0036232315469533205, "value_dist": 0.8623071908950806, "value_other_env": 0.8805003762245178, "value_corner": 0.8350175023078918, "value_row": 0.8573766946792603, "value_any": 0.8805128931999207, "value_bot": 0.8550033569335938, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08110.png", "entropy": 0.12931980192661285} +{"ts": "2026-03-20T19:19:53.733228Z", "loop": 8120, "env_steps": 4988928000, "exact_value_avg": 0.8608509302139282, "regret_dist": 0.002729747211560607, "regret_other_env": 0.0031480772886425257, "regret_corner": 0.0021022518631070852, "regret_row": 0.0032011140137910843, "regret_any": 0.0031716153025627136, "regret_bot": 0.006284982897341251, "value_dist": 0.8608509302139282, "value_other_env": 0.8790668249130249, "value_corner": 0.8335270285606384, "value_row": 0.8554255366325378, "value_any": 0.8790789842605591, "value_bot": 0.8523415923118591, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08120.png", "entropy": 0.13701516389846802} +{"ts": "2026-03-20T19:20:02.316052Z", "loop": 8130, "env_steps": 4995072000, "exact_value_avg": 0.8610316514968872, "regret_dist": 0.002549096941947937, "regret_other_env": 0.0033883899450302124, "regret_corner": 0.0012901569716632366, "regret_row": 0.003597444389015436, "regret_any": 0.0034207343123853207, "regret_bot": 0.008106101304292679, "value_dist": 0.8610316514968872, "value_other_env": 0.8788264989852905, "value_corner": 0.8343392014503479, "value_row": 0.855029284954071, "value_any": 0.8788298964500427, "value_bot": 0.8505205512046814, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08130.png", "entropy": 0.13832980394363403} +{"ts": "2026-03-20T19:20:10.892072Z", "loop": 8140, "env_steps": 5001216000, "exact_value_avg": 0.8622642755508423, "regret_dist": 0.0013163411058485508, "regret_other_env": 0.002164171077311039, "regret_corner": 4.459619594854303e-05, "regret_row": 0.0024736998602747917, "regret_any": 0.0021908350754529238, "regret_bot": 0.004999500699341297, "value_dist": 0.8622642755508423, "value_other_env": 0.8800506591796875, "value_corner": 0.8355847001075745, "value_row": 0.8561529517173767, "value_any": 0.8800597190856934, "value_bot": 0.8536271452903748, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08140.png", "entropy": 0.11445529758930206} +{"ts": "2026-03-20T19:20:19.471174Z", "loop": 8150, "env_steps": 5007360000, "exact_value_avg": 0.858809769153595, "regret_dist": 0.004770967643707991, "regret_other_env": 0.007946712896227837, "regret_corner": 7.349252882704604e-06, "regret_row": 0.003240809543058276, "regret_any": 0.008090301416814327, "regret_bot": 0.025085344910621643, "value_dist": 0.858809769153595, "value_other_env": 0.8742682337760925, "value_corner": 0.8356219530105591, "value_row": 0.8553858399391174, "value_any": 0.8741602897644043, "value_bot": 0.8335412740707397, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08150.png", "entropy": 0.10786324739456177} +{"ts": "2026-03-20T19:20:28.050435Z", "loop": 8160, "env_steps": 5013504000, "exact_value_avg": 0.8624316453933716, "regret_dist": 0.0011490461183711886, "regret_other_env": 0.0019134122412651777, "regret_corner": 2.4969381229311693e-06, "regret_row": 0.003436771221458912, "regret_any": 0.0019368079956620932, "regret_bot": 0.0028058409225195646, "value_dist": 0.8624316453933716, "value_other_env": 0.8803014755249023, "value_corner": 0.8356268405914307, "value_row": 0.8551898002624512, "value_any": 0.8803138136863708, "value_bot": 0.8558207750320435, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08160.png", "entropy": 0.1096327155828476} +{"ts": "2026-03-20T19:20:36.635583Z", "loop": 8170, "env_steps": 5019648000, "exact_value_avg": 0.862162709236145, "regret_dist": 0.0014179619029164314, "regret_other_env": 0.0023575806990265846, "regret_corner": 8.533398613508325e-06, "regret_row": 0.0037941844202578068, "regret_any": 0.002379252575337887, "regret_bot": 0.004784037824720144, "value_dist": 0.862162709236145, "value_other_env": 0.8798573017120361, "value_corner": 0.8356208205223083, "value_row": 0.8548324704170227, "value_any": 0.8798713684082031, "value_bot": 0.8538426160812378, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08170.png", "entropy": 0.11756375432014465} +{"ts": "2026-03-20T19:20:45.214958Z", "loop": 8180, "env_steps": 5025792000, "exact_value_avg": 0.861269474029541, "regret_dist": 0.002311214804649353, "regret_other_env": 0.0038375449366867542, "regret_corner": 2.17194374272367e-05, "regret_row": 0.0027363356202840805, "regret_any": 0.0038603050634264946, "regret_bot": 0.013525908812880516, "value_dist": 0.861269474029541, "value_other_env": 0.8783773183822632, "value_corner": 0.8356075882911682, "value_row": 0.8558903336524963, "value_any": 0.8783903121948242, "value_bot": 0.8451007008552551, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08180.png", "entropy": 0.11815953999757767} +{"ts": "2026-03-20T19:20:53.797949Z", "loop": 8190, "env_steps": 5031936000, "exact_value_avg": 0.8616192936897278, "regret_dist": 0.0019614025950431824, "regret_other_env": 0.003214640775695443, "regret_corner": 8.1545120337978e-05, "regret_row": 0.0012726313434541225, "regret_any": 0.0032446756958961487, "regret_bot": 0.012761806137859821, "value_dist": 0.8616192936897278, "value_other_env": 0.8790002465248108, "value_corner": 0.8355477452278137, "value_row": 0.8573539853096008, "value_any": 0.8790059685707092, "value_bot": 0.8458648324012756, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08190.png", "entropy": 0.12180177122354507} +{"ts": "2026-03-20T19:21:02.380940Z", "loop": 8200, "env_steps": 5038080000, "exact_value_avg": 0.8595757484436035, "regret_dist": 0.004004940390586853, "regret_other_env": 0.003889767685905099, "regret_corner": 0.004177698865532875, "regret_row": 0.006337609142065048, "regret_any": 0.003910158295184374, "regret_bot": 0.006836815271526575, "value_dist": 0.8595757484436035, "value_other_env": 0.8783251643180847, "value_corner": 0.8314515948295593, "value_row": 0.8522889614105225, "value_any": 0.878340482711792, "value_bot": 0.8517897725105286, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08200.png", "entropy": 0.1376807987689972} +{"ts": "2026-03-20T19:21:10.965328Z", "loop": 8210, "env_steps": 5044224000, "exact_value_avg": 0.8622151613235474, "regret_dist": 0.001365551957860589, "regret_other_env": 0.002035442739725113, "regret_corner": 0.000360715901479125, "regret_row": 0.0008899226668290794, "regret_any": 0.002049720147624612, "regret_bot": 0.003408431075513363, "value_dist": 0.8622151613235474, "value_other_env": 0.8801794648170471, "value_corner": 0.8352685570716858, "value_row": 0.8577366471290588, "value_any": 0.8802008032798767, "value_bot": 0.8552181720733643, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08210.png", "entropy": 0.11997267603874207} +{"ts": "2026-03-20T19:21:19.554566Z", "loop": 8220, "env_steps": 5050368000, "exact_value_avg": 0.8610623478889465, "regret_dist": 0.002518310211598873, "regret_other_env": 0.004155823029577732, "regret_corner": 6.204048986546695e-05, "regret_row": 0.0040120468474924564, "regret_any": 0.004156010691076517, "regret_bot": 0.00793667882680893, "value_dist": 0.8610623478889465, "value_other_env": 0.8780590295791626, "value_corner": 0.8355672359466553, "value_row": 0.8546146154403687, "value_any": 0.8780946135520935, "value_bot": 0.8506899476051331, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08220.png", "entropy": 0.12484782189130783} +{"ts": "2026-03-20T19:21:28.143458Z", "loop": 8230, "env_steps": 5056512000, "exact_value_avg": 0.8607957363128662, "regret_dist": 0.0027849639300256968, "regret_other_env": 0.004549339879304171, "regret_corner": 0.0001383995113428682, "regret_row": 0.006410249508917332, "regret_any": 0.004544953349977732, "regret_bot": 0.005891434382647276, "value_dist": 0.8607957363128662, "value_other_env": 0.8776655197143555, "value_corner": 0.835490882396698, "value_row": 0.852216362953186, "value_any": 0.8777056932449341, "value_bot": 0.8527352809906006, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08230.png", "entropy": 0.12780767679214478} +{"ts": "2026-03-20T19:21:36.723865Z", "loop": 8240, "env_steps": 5062656000, "exact_value_avg": 0.8626370429992676, "regret_dist": 0.0009436187683604658, "regret_other_env": 0.001536710187792778, "regret_corner": 5.3981446399120614e-05, "regret_row": 0.001133020967245102, "regret_any": 0.001536066411063075, "regret_bot": 0.0021785853896290064, "value_dist": 0.8626370429992676, "value_other_env": 0.8806781768798828, "value_corner": 0.8355753421783447, "value_row": 0.8574936389923096, "value_any": 0.8807145357131958, "value_bot": 0.8564480543136597, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08240.png", "entropy": 0.11964970827102661} +{"ts": "2026-03-20T19:21:45.300605Z", "loop": 8250, "env_steps": 5068800000, "exact_value_avg": 0.8590649366378784, "regret_dist": 0.004515713546425104, "regret_other_env": 0.00689980061724782, "regret_corner": 0.0009395823581144214, "regret_row": 0.008948944509029388, "regret_any": 0.007046862039715052, "regret_bot": 0.0013031187700107694, "value_dist": 0.8590649366378784, "value_other_env": 0.8753150701522827, "value_corner": 0.834689736366272, "value_row": 0.8496776819229126, "value_any": 0.8752036690711975, "value_bot": 0.8573234677314758, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08250.png", "entropy": 0.11564407497644424} +{"ts": "2026-03-20T19:21:53.882304Z", "loop": 8260, "env_steps": 5074944000, "exact_value_avg": 0.8627053499221802, "regret_dist": 0.0008753532310947776, "regret_other_env": 0.0014565371675416827, "regret_corner": 3.5772723094851244e-06, "regret_row": 0.0007988126599229872, "regret_any": 0.0014867677818983793, "regret_bot": 0.0025698912795633078, "value_dist": 0.8627053499221802, "value_other_env": 0.8807583451271057, "value_corner": 0.8356257677078247, "value_row": 0.8578278422355652, "value_any": 0.880763828754425, "value_bot": 0.856056809425354, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08260.png", "entropy": 0.10423813760280609} +{"ts": "2026-03-20T19:22:02.464470Z", "loop": 8270, "env_steps": 5081088000, "exact_value_avg": 0.8621715307235718, "regret_dist": 0.0014091599732637405, "regret_other_env": 0.0023480665404349566, "regret_corner": 8.001924243217218e-07, "regret_row": 0.008844812400639057, "regret_any": 0.0023695840500295162, "regret_bot": 0.002207864308729768, "value_dist": 0.8621715307235718, "value_other_env": 0.8798667788505554, "value_corner": 0.8356285691261292, "value_row": 0.8497818112373352, "value_any": 0.8798810243606567, "value_bot": 0.8564187288284302, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08270.png", "entropy": 0.10654562711715698} +{"ts": "2026-03-20T19:22:11.044349Z", "loop": 8280, "env_steps": 5087232000, "exact_value_avg": 0.8629738092422485, "regret_dist": 0.0006068928050808609, "regret_other_env": 0.0010103101376444101, "regret_corner": 1.7667811107457965e-06, "regret_row": 0.001051202998496592, "regret_any": 0.001034457003697753, "regret_bot": 0.0016521585639566183, "value_dist": 0.8629738092422485, "value_other_env": 0.8812046051025391, "value_corner": 0.835627555847168, "value_row": 0.8575753569602966, "value_any": 0.8812161087989807, "value_bot": 0.8569744229316711, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08280.png", "entropy": 0.10489621758460999} +{"ts": "2026-03-20T19:22:19.623893Z", "loop": 8290, "env_steps": 5093376000, "exact_value_avg": 0.8562062978744507, "regret_dist": 0.00737431924790144, "regret_other_env": 0.01226807851344347, "regret_corner": 3.367960744071752e-05, "regret_row": 0.008682399056851864, "regret_any": 0.012487165629863739, "regret_bot": 0.028629451990127563, "value_dist": 0.8562062978744507, "value_other_env": 0.8699467778205872, "value_corner": 0.8355956673622131, "value_row": 0.8499442934989929, "value_any": 0.8697634339332581, "value_bot": 0.829997181892395, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08290.png", "entropy": 0.10684013366699219} +{"ts": "2026-03-20T19:22:28.200121Z", "loop": 8300, "env_steps": 5099520000, "exact_value_avg": 0.8628491163253784, "regret_dist": 0.0007316078408621252, "regret_other_env": 0.0012157810851931572, "regret_corner": 5.3480271162698045e-06, "regret_row": 0.0007508923299610615, "regret_any": 0.001240233425050974, "regret_bot": 0.0019470363622531295, "value_dist": 0.8628491163253784, "value_other_env": 0.8809990882873535, "value_corner": 0.8356239795684814, "value_row": 0.8578757047653198, "value_any": 0.8810103535652161, "value_bot": 0.8566796183586121, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08300.png", "entropy": 0.10370573401451111} +{"ts": "2026-03-20T19:22:36.781795Z", "loop": 8310, "env_steps": 5105664000, "exact_value_avg": 0.862384557723999, "regret_dist": 0.0011961522977799177, "regret_other_env": 0.0019927036482840776, "regret_corner": 1.32520995066443e-06, "regret_row": 0.0018007386242970824, "regret_any": 0.0020162854343652725, "regret_bot": 0.0041090138256549835, "value_dist": 0.862384557723999, "value_other_env": 0.8802221417427063, "value_corner": 0.8356280326843262, "value_row": 0.8568259477615356, "value_any": 0.8802343010902405, "value_bot": 0.8545176982879639, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08310.png", "entropy": 0.10751357674598694} +{"ts": "2026-03-20T19:22:45.360072Z", "loop": 8320, "env_steps": 5111808000, "exact_value_avg": 0.863023042678833, "regret_dist": 0.0005576072726398706, "regret_other_env": 0.0009275078773498535, "regret_corner": 2.7562182367546484e-06, "regret_row": 0.0005435853381641209, "regret_any": 0.0009273627074435353, "regret_bot": 0.0011017735814675689, "value_dist": 0.863023042678833, "value_other_env": 0.8812873363494873, "value_corner": 0.8356266021728516, "value_row": 0.8580830693244934, "value_any": 0.8813232183456421, "value_bot": 0.8575247526168823, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08320.png", "entropy": 0.10341521352529526} +{"ts": "2026-03-20T19:22:53.943148Z", "loop": 8330, "env_steps": 5117952000, "exact_value_avg": 0.8627197742462158, "regret_dist": 0.0008608184871263802, "regret_other_env": 0.001426182920113206, "regret_corner": 1.2771785804943647e-05, "regret_row": 0.007592772599309683, "regret_any": 0.0014249682426452637, "regret_bot": 0.00039391277823597193, "value_dist": 0.8627197742462158, "value_other_env": 0.8807886242866516, "value_corner": 0.8356165289878845, "value_row": 0.8510338664054871, "value_any": 0.8808256387710571, "value_bot": 0.8582326769828796, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08330.png", "entropy": 0.0968182384967804} +{"ts": "2026-03-20T19:23:02.521954Z", "loop": 8340, "env_steps": 5124096000, "exact_value_avg": 0.8624758720397949, "regret_dist": 0.0011048426385968924, "regret_other_env": 0.0018409928306937218, "regret_corner": 6.174047939566663e-07, "regret_row": 0.001530249835923314, "regret_any": 0.001838882453739643, "regret_bot": 0.0016826775390654802, "value_dist": 0.8624758720397949, "value_other_env": 0.8803738355636597, "value_corner": 0.8356287479400635, "value_row": 0.8570964336395264, "value_any": 0.8804117441177368, "value_bot": 0.8569439053535461, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08340.png", "entropy": 0.09604251384735107} +{"ts": "2026-03-20T19:23:11.096507Z", "loop": 8350, "env_steps": 5130240000, "exact_value_avg": 0.8623334169387817, "regret_dist": 0.0012472791131585836, "regret_other_env": 0.0020786006934940815, "regret_corner": 2.965331304949359e-07, "regret_row": 0.0037796590477228165, "regret_any": 0.002099554752930999, "regret_bot": 0.0025483102072030306, "value_dist": 0.8623334169387817, "value_other_env": 0.8801363706588745, "value_corner": 0.8356290459632874, "value_row": 0.8548468947410583, "value_any": 0.8801510334014893, "value_bot": 0.8560783267021179, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08350.png", "entropy": 0.1026586964726448} +{"ts": "2026-03-20T19:23:19.678897Z", "loop": 8360, "env_steps": 5136384000, "exact_value_avg": 0.8631752729415894, "regret_dist": 0.00040538187022320926, "regret_other_env": 0.0006720806704834104, "regret_corner": 5.333622539183125e-06, "regret_row": 0.00036610016832128167, "regret_any": 0.0006964319036342204, "regret_bot": 0.0017354257870465517, "value_dist": 0.8631752729415894, "value_other_env": 0.8815428018569946, "value_corner": 0.8356239795684814, "value_row": 0.858260452747345, "value_any": 0.8815541863441467, "value_bot": 0.8568912148475647, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08360.png", "entropy": 0.1029931828379631} +{"ts": "2026-03-20T19:23:28.263643Z", "loop": 8370, "env_steps": 5142528000, "exact_value_avg": 0.8621358275413513, "regret_dist": 0.0014448348665609956, "regret_other_env": 0.002370764035731554, "regret_corner": 5.594094909611158e-05, "regret_row": 0.0015998610761016607, "regret_any": 0.002398822456598282, "regret_bot": 0.003912333399057388, "value_dist": 0.8621358275413513, "value_other_env": 0.8798441290855408, "value_corner": 0.8355733752250671, "value_row": 0.8570267558097839, "value_any": 0.879851758480072, "value_bot": 0.8547142744064331, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08370.png", "entropy": 0.10621882975101471} +{"ts": "2026-03-20T19:23:36.840529Z", "loop": 8380, "env_steps": 5148672000, "exact_value_avg": 0.8626372814178467, "regret_dist": 0.0009433606173843145, "regret_other_env": 0.0014718917664140463, "regret_corner": 0.00015056382108014077, "regret_row": 0.0016259821131825447, "regret_any": 0.0014960846165195107, "regret_bot": 0.0018820101395249367, "value_dist": 0.8626372814178467, "value_other_env": 0.8807429671287537, "value_corner": 0.8354787826538086, "value_row": 0.8570005893707275, "value_any": 0.8807544708251953, "value_bot": 0.856744647026062, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08380.png", "entropy": 0.11059319227933884} +{"ts": "2026-03-20T19:23:45.421267Z", "loop": 8390, "env_steps": 5154816000, "exact_value_avg": 0.8629330992698669, "regret_dist": 0.0006475689588114619, "regret_other_env": 0.0008794549503363669, "regret_corner": 0.00029973985510878265, "regret_row": 0.0007962658419273794, "regret_any": 0.000903059437405318, "regret_bot": 0.001886945334263146, "value_dist": 0.8629330992698669, "value_other_env": 0.881335437297821, "value_corner": 0.8353295922279358, "value_row": 0.8578304052352905, "value_any": 0.8813475370407104, "value_bot": 0.8567397594451904, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08390.png", "entropy": 0.11355865001678467} +{"ts": "2026-03-20T19:23:54.012942Z", "loop": 8400, "env_steps": 5160960000, "exact_value_avg": 0.863166093826294, "regret_dist": 0.00041461430373601615, "regret_other_env": 0.0006771154003217816, "regret_corner": 2.086262065859046e-05, "regret_row": 0.00028225037385709584, "regret_any": 0.0007010099943727255, "regret_bot": 0.0015587243251502514, "value_dist": 0.863166093826294, "value_other_env": 0.8815377950668335, "value_corner": 0.8356084823608398, "value_row": 0.8583443760871887, "value_any": 0.881549596786499, "value_bot": 0.8570679426193237, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08400.png", "entropy": 0.10537879914045334} +{"ts": "2026-03-20T19:24:02.597474Z", "loop": 8410, "env_steps": 5167104000, "exact_value_avg": 0.8624937534332275, "regret_dist": 0.0010869069956243038, "regret_other_env": 0.001776506076566875, "regret_corner": 5.250821777735837e-05, "regret_row": 0.003849688218906522, "regret_any": 0.0018021311843767762, "regret_bot": 0.001458645798265934, "value_dist": 0.8624937534332275, "value_other_env": 0.8804383873939514, "value_corner": 0.8355767726898193, "value_row": 0.8547769784927368, "value_any": 0.8804484605789185, "value_bot": 0.8571678996086121, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08410.png", "entropy": 0.10949345678091049} +{"ts": "2026-03-20T19:24:11.176805Z", "loop": 8420, "env_steps": 5173248000, "exact_value_avg": 0.8623291254043579, "regret_dist": 0.0012515031266957521, "regret_other_env": 0.0020340338815003633, "regret_corner": 7.770707452436909e-05, "regret_row": 0.0037536295130848885, "regret_any": 0.002035812009125948, "regret_bot": 0.0007789367809891701, "value_dist": 0.8623291254043579, "value_other_env": 0.8801807761192322, "value_corner": 0.8355516195297241, "value_row": 0.85487300157547, "value_any": 0.8802148103713989, "value_bot": 0.8578478097915649, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08420.png", "entropy": 0.1133439689874649} +{"ts": "2026-03-20T19:24:19.766692Z", "loop": 8430, "env_steps": 5179392000, "exact_value_avg": 0.863107442855835, "regret_dist": 0.0004732687375508249, "regret_other_env": 0.0007616309449076653, "regret_corner": 4.0725371945882216e-05, "regret_row": 0.0007365464116446674, "regret_any": 0.0007606339640915394, "regret_bot": 0.0005051982589066029, "value_dist": 0.863107442855835, "value_other_env": 0.8814532160758972, "value_corner": 0.8355886340141296, "value_row": 0.8578900694847107, "value_any": 0.8814899921417236, "value_bot": 0.8581214547157288, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08430.png", "entropy": 0.11090392619371414} +{"ts": "2026-03-20T19:24:28.352085Z", "loop": 8440, "env_steps": 5185536000, "exact_value_avg": 0.8631203174591064, "regret_dist": 0.00046037050196900964, "regret_other_env": 0.000762672396376729, "regret_corner": 6.917616246937541e-06, "regret_row": 0.0010768960928544402, "regret_any": 0.0007779095321893692, "regret_bot": 0.0010988349094986916, "value_dist": 0.8631203174591064, "value_other_env": 0.881452202796936, "value_corner": 0.8356223702430725, "value_row": 0.8575496673583984, "value_any": 0.881472647190094, "value_bot": 0.8575278520584106, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08440.png", "entropy": 0.10687631368637085} +{"ts": "2026-03-20T19:24:36.937013Z", "loop": 8450, "env_steps": 5191680000, "exact_value_avg": 0.8630355596542358, "regret_dist": 0.0005451393080875278, "regret_other_env": 0.0009067501523531973, "regret_corner": 2.722938916122075e-06, "regret_row": 0.0016456193989142776, "regret_any": 0.0009212479926645756, "regret_bot": 0.0011746118543669581, "value_dist": 0.8630355596542358, "value_other_env": 0.8813081383705139, "value_corner": 0.8356266617774963, "value_row": 0.8569809794425964, "value_any": 0.8813294172286987, "value_bot": 0.8574519753456116, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08450.png", "entropy": 0.10502440482378006} +{"ts": "2026-03-20T19:24:45.521405Z", "loop": 8460, "env_steps": 5197824000, "exact_value_avg": 0.8627790212631226, "regret_dist": 0.0008017178042791784, "regret_other_env": 0.0013352277455851436, "regret_corner": 1.4528633300869842e-06, "regret_row": 0.003197153564542532, "regret_any": 0.0013335531111806631, "regret_bot": 0.0009286808199249208, "value_dist": 0.8627790212631226, "value_other_env": 0.8808797001838684, "value_corner": 0.8356278538703918, "value_row": 0.8554295301437378, "value_any": 0.8809171319007874, "value_bot": 0.8576979041099548, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08460.png", "entropy": 0.10593913495540619} +{"ts": "2026-03-20T19:24:54.103113Z", "loop": 8470, "env_steps": 5203968000, "exact_value_avg": 0.8623574376106262, "regret_dist": 0.0012232454027980566, "regret_other_env": 0.0020376527681946754, "regret_corner": 1.6341607533831848e-06, "regret_row": 0.0020184956956654787, "regret_any": 0.0020349195692688227, "regret_bot": 0.0024796018842607737, "value_dist": 0.8623574376106262, "value_other_env": 0.8801771402359009, "value_corner": 0.8356277346611023, "value_row": 0.8566080331802368, "value_any": 0.8802157044410706, "value_bot": 0.8561469316482544, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08470.png", "entropy": 0.10499617457389832} +{"ts": "2026-03-20T19:25:02.689083Z", "loop": 8480, "env_steps": 5210112000, "exact_value_avg": 0.8622136116027832, "regret_dist": 0.0013670477783307433, "regret_other_env": 0.0022754946257919073, "regret_corner": 4.377464847493684e-06, "regret_row": 0.000568161893170327, "regret_any": 0.002281606663018465, "regret_bot": 0.0009222751250490546, "value_dist": 0.8622136116027832, "value_other_env": 0.8799393773078918, "value_corner": 0.8356249332427979, "value_row": 0.8580584526062012, "value_any": 0.8799690008163452, "value_bot": 0.8577042818069458, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08480.png", "entropy": 0.10470303893089294} +{"ts": "2026-03-20T19:25:11.271300Z", "loop": 8490, "env_steps": 5216256000, "exact_value_avg": 0.8630504608154297, "regret_dist": 0.0005302989156916738, "regret_other_env": 0.0008821867522783577, "regret_corner": 2.467135800543474e-06, "regret_row": 0.000818928936496377, "regret_any": 0.0008833210449665785, "regret_bot": 0.0005946624442003667, "value_dist": 0.8630504608154297, "value_other_env": 0.8813326954841614, "value_corner": 0.8356269001960754, "value_row": 0.8578077554702759, "value_any": 0.8813673257827759, "value_bot": 0.8580319881439209, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08490.png", "entropy": 0.10442756116390228} +{"ts": "2026-03-20T19:25:19.856990Z", "loop": 8500, "env_steps": 5222400000, "exact_value_avg": 0.8632404208183289, "regret_dist": 0.00034022104227915406, "regret_other_env": 0.0005625723279081285, "regret_corner": 6.6940988290298264e-06, "regret_row": 0.00042591625242494047, "regret_any": 0.0005835836636833847, "regret_bot": 0.001163985813036561, "value_dist": 0.8632404208183289, "value_other_env": 0.881652295589447, "value_corner": 0.8356225490570068, "value_row": 0.8582006692886353, "value_any": 0.8816670179367065, "value_bot": 0.8574626445770264, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08500.png", "entropy": 0.10581572353839874} +{"ts": "2026-03-20T19:25:28.450417Z", "loop": 8510, "env_steps": 5228544000, "exact_value_avg": 0.863184928894043, "regret_dist": 0.00039577484130859375, "regret_other_env": 0.0006501657771877944, "regret_corner": 1.418838928657351e-05, "regret_row": 0.00021619714971166104, "regret_any": 0.0006740918615832925, "regret_bot": 0.0016813346883282065, "value_dist": 0.863184928894043, "value_other_env": 0.881564736366272, "value_corner": 0.8356151580810547, "value_row": 0.8584104180335999, "value_any": 0.8815764784812927, "value_bot": 0.8569453358650208, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08510.png", "entropy": 0.10686083137989044} +{"ts": "2026-03-20T19:25:37.034280Z", "loop": 8520, "env_steps": 5234688000, "exact_value_avg": 0.8632256388664246, "regret_dist": 0.0003550084074959159, "regret_other_env": 0.0005817051860503852, "regret_corner": 1.496325057814829e-05, "regret_row": 0.00019951854483224452, "regret_any": 0.0006058235303498805, "regret_bot": 0.0014598150737583637, "value_dist": 0.8632256388664246, "value_other_env": 0.8816331624984741, "value_corner": 0.8356143236160278, "value_row": 0.858427107334137, "value_any": 0.8816448450088501, "value_bot": 0.8571667671203613, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08520.png", "entropy": 0.10692782700061798} +{"ts": "2026-03-20T19:25:45.617975Z", "loop": 8530, "env_steps": 5240832000, "exact_value_avg": 0.8623515963554382, "regret_dist": 0.0012291220482438803, "regret_other_env": 0.0020239977166056633, "regret_corner": 3.6808352888328955e-05, "regret_row": 0.0007810192182660103, "regret_any": 0.0020573169458657503, "regret_bot": 0.0032340174075216055, "value_dist": 0.8623515963554382, "value_other_env": 0.880190908908844, "value_corner": 0.8355925679206848, "value_row": 0.8578456044197083, "value_any": 0.880193293094635, "value_bot": 0.8553926944732666, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08530.png", "entropy": 0.11115899682044983} +{"ts": "2026-03-20T19:25:54.199998Z", "loop": 8540, "env_steps": 5246976000, "exact_value_avg": 0.8632632493972778, "regret_dist": 0.0003174160956405103, "regret_other_env": 0.00051107257604599, "regret_corner": 2.69313659373438e-05, "regret_row": 0.00022372404055204242, "regret_any": 0.0005303606740199029, "regret_bot": 0.0009504897752776742, "value_dist": 0.8632632493972778, "value_other_env": 0.881703794002533, "value_corner": 0.835602343082428, "value_row": 0.8584029674530029, "value_any": 0.881720244884491, "value_bot": 0.8576761484146118, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08540.png", "entropy": 0.10826659947633743} +{"ts": "2026-03-20T19:26:02.787211Z", "loop": 8550, "env_steps": 5253120000, "exact_value_avg": 0.8626377582550049, "regret_dist": 0.0009428742341697216, "regret_other_env": 0.001532057300209999, "regret_corner": 5.909949686611071e-05, "regret_row": 0.001420128159224987, "regret_any": 0.0015513147227466106, "regret_bot": 0.0008589893113821745, "value_dist": 0.8626377582550049, "value_other_env": 0.8806827664375305, "value_corner": 0.8355702757835388, "value_row": 0.8572065830230713, "value_any": 0.8806992769241333, "value_bot": 0.857767641544342, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08550.png", "entropy": 0.111185222864151} +{"ts": "2026-03-20T19:26:11.371898Z", "loop": 8560, "env_steps": 5259264000, "exact_value_avg": 0.8621504306793213, "regret_dist": 0.0014303565258160233, "regret_other_env": 0.002375244628638029, "regret_corner": 1.3024112377024721e-05, "regret_row": 0.0005797132034786046, "regret_any": 0.002396782860159874, "regret_bot": 0.005002176389098167, "value_dist": 0.8621504306793213, "value_other_env": 0.8798397183418274, "value_corner": 0.8356163501739502, "value_row": 0.8580468893051147, "value_any": 0.8798537850379944, "value_bot": 0.8536244630813599, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08560.png", "entropy": 0.10823556035757065} +{"ts": "2026-03-20T19:26:19.955305Z", "loop": 8570, "env_steps": 5265408000, "exact_value_avg": 0.8627034425735474, "regret_dist": 0.0008772521978244185, "regret_other_env": 0.001459782593883574, "regret_corner": 3.4565728128654882e-06, "regret_row": 0.0013618620578199625, "regret_any": 0.0014888257719576359, "regret_bot": 0.0026947285514324903, "value_dist": 0.8627034425735474, "value_other_env": 0.8807550668716431, "value_corner": 0.8356258869171143, "value_row": 0.8572648167610168, "value_any": 0.8807618021965027, "value_bot": 0.8559319376945496, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08570.png", "entropy": 0.10476884990930557} +{"ts": "2026-03-20T19:26:28.542766Z", "loop": 8580, "env_steps": 5271552000, "exact_value_avg": 0.8603489995002747, "regret_dist": 0.0032317491713911295, "regret_other_env": 0.005385180003941059, "regret_corner": 1.6023716398194665e-06, "regret_row": 0.026023348793387413, "regret_any": 0.005405801348388195, "regret_bot": 0.003920497838407755, "value_dist": 0.8603489995002747, "value_other_env": 0.8768297433853149, "value_corner": 0.8356277346611023, "value_row": 0.8326032757759094, "value_any": 0.8768447637557983, "value_bot": 0.8547061681747437, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08580.png", "entropy": 0.10848851501941681} +{"ts": "2026-03-20T19:26:37.120021Z", "loop": 8590, "env_steps": 5277696000, "exact_value_avg": 0.8631891012191772, "regret_dist": 0.00039153758552856743, "regret_other_env": 0.0006418589618988335, "regret_corner": 1.605550460226368e-05, "regret_row": 0.0003152843564748764, "regret_any": 0.000665899773593992, "regret_bot": 0.0015491663943976164, "value_dist": 0.8631891012191772, "value_other_env": 0.881572961807251, "value_corner": 0.8356133103370667, "value_row": 0.8583114147186279, "value_any": 0.8815847039222717, "value_bot": 0.8570774793624878, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08590.png", "entropy": 0.10905632376670837} +{"ts": "2026-03-20T19:26:45.706890Z", "loop": 8600, "env_steps": 5283840000, "exact_value_avg": 0.863229513168335, "regret_dist": 0.00035119298263452947, "regret_other_env": 0.0005580577999353409, "regret_corner": 4.089574213139713e-05, "regret_row": 0.0002676428121048957, "regret_any": 0.0005810895236209035, "regret_bot": 0.0012952742399647832, "value_dist": 0.863229513168335, "value_other_env": 0.88165682554245, "value_corner": 0.8355884552001953, "value_row": 0.8583590388298035, "value_any": 0.8816695213317871, "value_bot": 0.857331395149231, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08600.png", "entropy": 0.10958218574523926} +{"ts": "2026-03-20T19:26:54.289447Z", "loop": 8610, "env_steps": 5289984000, "exact_value_avg": 0.8632127642631531, "regret_dist": 0.000367897329851985, "regret_other_env": 0.000571410811971873, "regret_corner": 6.262709939619526e-05, "regret_row": 0.00047788090887479484, "regret_any": 0.0005778360064141452, "regret_bot": 0.0007777087157592177, "value_dist": 0.8632127642631531, "value_other_env": 0.8816434144973755, "value_corner": 0.8355666399002075, "value_row": 0.8581486940383911, "value_any": 0.881672739982605, "value_bot": 0.8578488826751709, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08610.png", "entropy": 0.11288521438837051} +{"ts": "2026-03-20T19:27:02.875698Z", "loop": 8620, "env_steps": 5296128000, "exact_value_avg": 0.8628890514373779, "regret_dist": 0.0006916652782820165, "regret_other_env": 0.0010360023006796837, "regret_corner": 0.00017515968647785485, "regret_row": 0.000873614801093936, "regret_any": 0.0010349598014727235, "regret_bot": 0.0013287340989336371, "value_dist": 0.8628890514373779, "value_other_env": 0.8811789155006409, "value_corner": 0.8354541659355164, "value_row": 0.8577530384063721, "value_any": 0.8812155723571777, "value_bot": 0.857297956943512, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08620.png", "entropy": 0.12240304052829742} +{"ts": "2026-03-20T19:27:11.463553Z", "loop": 8630, "env_steps": 5302272000, "exact_value_avg": 0.8624460697174072, "regret_dist": 0.0011346661485731602, "regret_other_env": 0.0017087487503886223, "regret_corner": 0.0002735421294346452, "regret_row": 0.0012447121553122997, "regret_any": 0.001706596347503364, "regret_bot": 0.0022368261124938726, "value_dist": 0.8624460697174072, "value_other_env": 0.880506157875061, "value_corner": 0.835355818271637, "value_row": 0.8573818802833557, "value_any": 0.8805440664291382, "value_bot": 0.8563898205757141, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08630.png", "entropy": 0.12446083873510361} +{"ts": "2026-03-20T19:27:20.052013Z", "loop": 8640, "env_steps": 5308416000, "exact_value_avg": 0.8623168468475342, "regret_dist": 0.0012638687621802092, "regret_other_env": 0.0019634305499494076, "regret_corner": 0.0002145260659744963, "regret_row": 0.0015352437039837241, "regret_any": 0.001960897585377097, "regret_bot": 0.0024073102977126837, "value_dist": 0.8623168468475342, "value_other_env": 0.8802514672279358, "value_corner": 0.8354148268699646, "value_row": 0.8570913076400757, "value_any": 0.8802897334098816, "value_bot": 0.8562192916870117, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08640.png", "entropy": 0.12000773102045059} +{"ts": "2026-03-20T19:27:28.634191Z", "loop": 8650, "env_steps": 5314560000, "exact_value_avg": 0.8631458282470703, "regret_dist": 0.000434789399150759, "regret_other_env": 0.000673413451295346, "regret_corner": 7.685324089834467e-05, "regret_row": 0.0006610172567889094, "regret_any": 0.0006729962769895792, "regret_bot": 0.0006890689255669713, "value_dist": 0.8631458282470703, "value_other_env": 0.8815414309501648, "value_corner": 0.835552453994751, "value_row": 0.8579655885696411, "value_any": 0.8815775513648987, "value_bot": 0.8579375743865967, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08650.png", "entropy": 0.11579354852437973} +{"ts": "2026-03-20T19:27:37.218026Z", "loop": 8660, "env_steps": 5320704000, "exact_value_avg": 0.8633478283882141, "regret_dist": 0.00023290872923098505, "regret_other_env": 0.0003630687715485692, "regret_corner": 3.7668647564714774e-05, "regret_row": 0.00035270070657134056, "regret_any": 0.0003659288340713829, "regret_bot": 0.0004251064092386514, "value_dist": 0.8633478283882141, "value_other_env": 0.881851851940155, "value_corner": 0.8355916738510132, "value_row": 0.8582739233970642, "value_any": 0.8818846344947815, "value_bot": 0.8582016229629517, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08660.png", "entropy": 0.10989533364772797} +{"ts": "2026-03-20T19:27:45.803180Z", "loop": 8670, "env_steps": 5326848000, "exact_value_avg": 0.8633289337158203, "regret_dist": 0.00025169129366986454, "regret_other_env": 0.0004155376518610865, "regret_corner": 5.921721822232939e-06, "regret_row": 0.00026688576326705515, "regret_any": 0.0004354782577138394, "regret_bot": 0.001042824937030673, "value_dist": 0.8633289337158203, "value_other_env": 0.8817992806434631, "value_corner": 0.8356233835220337, "value_row": 0.8583597540855408, "value_any": 0.8818151354789734, "value_bot": 0.85758376121521, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08670.png", "entropy": 0.10665164142847061} +{"ts": "2026-03-20T19:27:54.386459Z", "loop": 8680, "env_steps": 5332992000, "exact_value_avg": 0.8630294799804688, "regret_dist": 0.0005512361531145871, "regret_other_env": 0.0009155566222034395, "regret_corner": 4.755457666760776e-06, "regret_row": 0.0005094690714031458, "regret_any": 0.0009422803996130824, "regret_bot": 0.0024740751832723618, "value_dist": 0.8630294799804688, "value_other_env": 0.8812993764877319, "value_corner": 0.835624635219574, "value_row": 0.8581171631813049, "value_any": 0.8813082575798035, "value_bot": 0.8561524748802185, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08680.png", "entropy": 0.10835452377796173} +{"ts": "2026-03-20T19:28:02.971284Z", "loop": 8690, "env_steps": 5339136000, "exact_value_avg": 0.8621005415916443, "regret_dist": 0.001480144215747714, "regret_other_env": 0.002462470903992653, "regret_corner": 6.653865511907497e-06, "regret_row": 0.0011956007219851017, "regret_any": 0.002492411294952035, "regret_bot": 0.0071046059019863605, "value_dist": 0.8621005415916443, "value_other_env": 0.8797523975372314, "value_corner": 0.8356226682662964, "value_row": 0.8574311137199402, "value_any": 0.8797581791877747, "value_bot": 0.8515219688415527, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08690.png", "entropy": 0.11201115697622299} +{"ts": "2026-03-20T19:28:11.545454Z", "loop": 8700, "env_steps": 5345280000, "exact_value_avg": 0.8623702526092529, "regret_dist": 0.0012103895423933864, "regret_other_env": 0.0020107508171349764, "regret_corner": 9.847681212704629e-06, "regret_row": 0.0011273418786004186, "regret_any": 0.0020342397037893534, "regret_bot": 0.005768537521362305, "value_dist": 0.8623702526092529, "value_other_env": 0.8802040815353394, "value_corner": 0.8356195092201233, "value_row": 0.8574992418289185, "value_any": 0.8802163600921631, "value_bot": 0.8528580665588379, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08700.png", "entropy": 0.1135486289858818} +{"ts": "2026-03-20T19:28:20.123961Z", "loop": 8710, "env_steps": 5351424000, "exact_value_avg": 0.8630838394165039, "regret_dist": 0.0004968214780092239, "regret_other_env": 0.0008142306469380856, "regret_corner": 2.0707648218376562e-05, "regret_row": 0.00029674696270376444, "regret_any": 0.0008384000393562019, "regret_bot": 0.002016602084040642, "value_dist": 0.8630838394165039, "value_other_env": 0.8814006447792053, "value_corner": 0.8356086015701294, "value_row": 0.8583298921585083, "value_any": 0.8814122080802917, "value_bot": 0.8566100597381592, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08710.png", "entropy": 0.11155760288238525} +{"ts": "2026-03-20T19:28:28.713140Z", "loop": 8720, "env_steps": 5357568000, "exact_value_avg": 0.86257004737854, "regret_dist": 0.0010105854598805308, "regret_other_env": 0.0016651496989652514, "regret_corner": 2.873887751775328e-05, "regret_row": 0.0006292406469583511, "regret_any": 0.0016925670206546783, "regret_bot": 0.0037367024924606085, "value_dist": 0.86257004737854, "value_other_env": 0.8805497288703918, "value_corner": 0.8356005549430847, "value_row": 0.8579974174499512, "value_any": 0.8805580139160156, "value_bot": 0.854889988899231, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08720.png", "entropy": 0.10823171585798264} +{"ts": "2026-03-20T19:28:37.289657Z", "loop": 8730, "env_steps": 5363712000, "exact_value_avg": 0.8626377582550049, "regret_dist": 0.000942908285651356, "regret_other_env": 0.0015592103591188788, "regret_corner": 1.8455089957569726e-05, "regret_row": 0.0005035822396166623, "regret_any": 0.001585882157087326, "regret_bot": 0.003430368145927787, "value_dist": 0.8626377582550049, "value_other_env": 0.8806556463241577, "value_corner": 0.8356108665466309, "value_row": 0.8581230044364929, "value_any": 0.8806647658348083, "value_bot": 0.8551962971687317, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08730.png", "entropy": 0.10755869746208191} +{"ts": "2026-03-20T19:28:45.878505Z", "loop": 8740, "env_steps": 5369856000, "exact_value_avg": 0.8632211685180664, "regret_dist": 0.0003595342568587512, "regret_other_env": 0.0005885969148948789, "regret_corner": 1.5940269804559648e-05, "regret_row": 0.0002856555802281946, "regret_any": 0.000604989065323025, "regret_bot": 0.0009825036395341158, "value_dist": 0.8632211685180664, "value_other_env": 0.881626307964325, "value_corner": 0.8356134295463562, "value_row": 0.8583409786224365, "value_any": 0.8816456198692322, "value_bot": 0.8576441407203674, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08740.png", "entropy": 0.108985535800457} +{"ts": "2026-03-20T19:28:54.460412Z", "loop": 8750, "env_steps": 5376000000, "exact_value_avg": 0.8631359338760376, "regret_dist": 0.00044481095392256975, "regret_other_env": 0.0007355735288001597, "regret_corner": 8.667012480145786e-06, "regret_row": 0.0009252423187717795, "regret_any": 0.0007352586835622787, "regret_bot": 0.00029074697522446513, "value_dist": 0.8631359338760376, "value_other_env": 0.8814793229103088, "value_corner": 0.835620641708374, "value_row": 0.8577014207839966, "value_any": 0.8815152645111084, "value_bot": 0.8583359122276306, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08750.png", "entropy": 0.10794642567634583} +{"ts": "2026-03-20T19:29:03.043780Z", "loop": 8760, "env_steps": 5382144000, "exact_value_avg": 0.8628120422363281, "regret_dist": 0.0007686598692089319, "regret_other_env": 0.0012743220431730151, "regret_corner": 1.016656642605085e-05, "regret_row": 0.0030563182663172483, "regret_any": 0.0012913139071315527, "regret_bot": 0.00040455724229104817, "value_dist": 0.8628120422363281, "value_other_env": 0.8809406161308289, "value_corner": 0.8356191515922546, "value_row": 0.8555702567100525, "value_any": 0.8809592723846436, "value_bot": 0.8582221269607544, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08760.png", "entropy": 0.10462871193885803} +{"ts": "2026-03-20T19:29:11.622841Z", "loop": 8770, "env_steps": 5388288000, "exact_value_avg": 0.861854076385498, "regret_dist": 0.0017266840441152453, "regret_other_env": 0.0028684446588158607, "regret_corner": 1.4042854672879912e-05, "regret_row": 0.001821200712583959, "regret_any": 0.0029146878514438868, "regret_bot": 0.00864352099597454, "value_dist": 0.861854076385498, "value_other_env": 0.879346489906311, "value_corner": 0.835615336894989, "value_row": 0.8568053841590881, "value_any": 0.8793359398841858, "value_bot": 0.8499831557273865, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08770.png", "entropy": 0.10502414405345917} +{"ts": "2026-03-20T19:29:20.212914Z", "loop": 8780, "env_steps": 5394432000, "exact_value_avg": 0.8628515005111694, "regret_dist": 0.000729172897990793, "regret_other_env": 0.0012123995693400502, "regret_corner": 4.332761363912141e-06, "regret_row": 0.0006910703959874809, "regret_any": 0.0012337062507867813, "regret_bot": 0.0033625629730522633, "value_dist": 0.8628515005111694, "value_other_env": 0.8810024857521057, "value_corner": 0.8356249928474426, "value_row": 0.8579354882240295, "value_any": 0.8810168504714966, "value_bot": 0.8552640676498413, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08780.png", "entropy": 0.10412055253982544} +{"ts": "2026-03-20T19:29:28.806860Z", "loop": 8790, "env_steps": 5400576000, "exact_value_avg": 0.8620003461837769, "regret_dist": 0.001580335316248238, "regret_other_env": 0.002631303621456027, "regret_corner": 3.882746113959001e-06, "regret_row": 0.002050800248980522, "regret_any": 0.002655282150954008, "regret_bot": 0.007021662313491106, "value_dist": 0.8620003461837769, "value_other_env": 0.8795835971832275, "value_corner": 0.835625410079956, "value_row": 0.8565758466720581, "value_any": 0.8795953392982483, "value_bot": 0.8516049981117249, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08790.png", "entropy": 0.10734140872955322} +{"ts": "2026-03-20T19:29:37.396647Z", "loop": 8800, "env_steps": 5406720000, "exact_value_avg": 0.8619176149368286, "regret_dist": 0.0016630978789180517, "regret_other_env": 0.002765599638223648, "regret_corner": 9.345015314465854e-06, "regret_row": 0.0006136923329904675, "regret_any": 0.0028000331949442625, "regret_bot": 0.012812248431146145, "value_dist": 0.8619176149368286, "value_other_env": 0.8794493079185486, "value_corner": 0.8356199860572815, "value_row": 0.8580129742622375, "value_any": 0.8794505000114441, "value_bot": 0.8458143472671509, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08800.png", "entropy": 0.10014355927705765} +{"ts": "2026-03-20T19:29:45.982517Z", "loop": 8810, "env_steps": 5412864000, "exact_value_avg": 0.8597185611724854, "regret_dist": 0.0038620829582214355, "regret_other_env": 0.0064143408089876175, "regret_corner": 3.3695996535243466e-05, "regret_row": 0.0014500743709504604, "regret_any": 0.0064713964238762856, "regret_bot": 0.02743581309914589, "value_dist": 0.8597185611724854, "value_other_env": 0.8758005499839783, "value_corner": 0.8355956673622131, "value_row": 0.8571764826774597, "value_any": 0.8757791519165039, "value_bot": 0.8311907649040222, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08810.png", "entropy": 0.10102131962776184} +{"ts": "2026-03-20T19:29:54.562469Z", "loop": 8820, "env_steps": 5419008000, "exact_value_avg": 0.8627042174339294, "regret_dist": 0.0008764667436480522, "regret_other_env": 0.0014477114891633391, "regret_corner": 1.9599498045863584e-05, "regret_row": 0.0005770025891251862, "regret_any": 0.0014738048193976283, "regret_bot": 0.0023899772204458714, "value_dist": 0.8627042174339294, "value_other_env": 0.8807671666145325, "value_corner": 0.8356097340583801, "value_row": 0.8580496907234192, "value_any": 0.8807768225669861, "value_bot": 0.8562366366386414, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08820.png", "entropy": 0.09678131341934204} +{"ts": "2026-03-20T19:30:03.145252Z", "loop": 8830, "env_steps": 5425152000, "exact_value_avg": 0.8628695607185364, "regret_dist": 0.000711164204403758, "regret_other_env": 0.0011532347416505218, "regret_corner": 4.805823482456617e-05, "regret_row": 0.0006008957279846072, "regret_any": 0.0011789854615926743, "regret_bot": 0.002546935807913542, "value_dist": 0.8628695607185364, "value_other_env": 0.8810617327690125, "value_corner": 0.8355812430381775, "value_row": 0.8580257296562195, "value_any": 0.8810716867446899, "value_bot": 0.856079638004303, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08830.png", "entropy": 0.09840366989374161} +{"ts": "2026-03-20T19:30:11.729350Z", "loop": 8840, "env_steps": 5431296000, "exact_value_avg": 0.8625422120094299, "regret_dist": 0.0010384556371718645, "regret_other_env": 0.0016842270269989967, "regret_corner": 6.979853060329333e-05, "regret_row": 0.0010746823390945792, "regret_any": 0.0017162150470539927, "regret_bot": 0.0037051034159958363, "value_dist": 0.8625422120094299, "value_other_env": 0.8805306553840637, "value_corner": 0.8355594873428345, "value_row": 0.8575519919395447, "value_any": 0.8805344104766846, "value_bot": 0.8549215197563171, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08840.png", "entropy": 0.09757735580205917} +{"ts": "2026-03-20T19:30:20.309733Z", "loop": 8850, "env_steps": 5437440000, "exact_value_avg": 0.8629767298698425, "regret_dist": 0.0006039483705535531, "regret_other_env": 0.000980192911811173, "regret_corner": 3.9581460441695526e-05, "regret_row": 0.0006211490835994482, "regret_any": 0.0010044202208518982, "regret_bot": 0.00264882599003613, "value_dist": 0.8629767298698425, "value_other_env": 0.8812347054481506, "value_corner": 0.8355897665023804, "value_row": 0.8580054640769958, "value_any": 0.8812461495399475, "value_bot": 0.8559778332710266, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08850.png", "entropy": 0.10044779628515244} +{"ts": "2026-03-20T19:30:28.893859Z", "loop": 8860, "env_steps": 5443584000, "exact_value_avg": 0.8623571395874023, "regret_dist": 0.0012235331814736128, "regret_other_env": 0.002036244608461857, "regret_corner": 4.465878191695083e-06, "regret_row": 0.00010057647159555927, "regret_any": 0.002069880021736026, "regret_bot": 0.006338443141430616, "value_dist": 0.8623571395874023, "value_other_env": 0.8801786303520203, "value_corner": 0.8356248736381531, "value_row": 0.8585260510444641, "value_any": 0.8801807165145874, "value_bot": 0.8522882461547852, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08860.png", "entropy": 0.10607758909463882} +{"ts": "2026-03-20T19:30:37.474623Z", "loop": 8870, "env_steps": 5449728000, "exact_value_avg": 0.8628286123275757, "regret_dist": 0.0007520414656028152, "regret_other_env": 0.0012442172737792134, "regret_corner": 1.3777614185528364e-05, "regret_row": 0.00012804684229195118, "regret_any": 0.0012712824391201138, "regret_bot": 0.004168931394815445, "value_dist": 0.8628286123275757, "value_other_env": 0.8809706568717957, "value_corner": 0.8356155157089233, "value_row": 0.8584986329078674, "value_any": 0.8809792995452881, "value_bot": 0.8544577360153198, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08870.png", "entropy": 0.10656656324863434} +{"ts": "2026-03-20T19:30:46.065527Z", "loop": 8880, "env_steps": 5455872000, "exact_value_avg": 0.8631876111030579, "regret_dist": 0.00039309755084104836, "regret_other_env": 0.0006202945369295776, "regret_corner": 5.2302086260169744e-05, "regret_row": 0.0015892694937065244, "regret_any": 0.0006436584517359734, "regret_bot": 0.00143013137858361, "value_dist": 0.8631876111030579, "value_other_env": 0.8815945982933044, "value_corner": 0.8355770707130432, "value_row": 0.8570373058319092, "value_any": 0.881606936454773, "value_bot": 0.8571965098381042, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08880.png", "entropy": 0.10618478059768677} +{"ts": "2026-03-20T19:30:54.648202Z", "loop": 8890, "env_steps": 5462016000, "exact_value_avg": 0.8632054328918457, "regret_dist": 0.000375192379578948, "regret_other_env": 0.0006177613977342844, "regret_corner": 1.133879050030373e-05, "regret_row": 0.00041503520333208144, "regret_any": 0.0006416692631319165, "regret_bot": 0.001397867570631206, "value_dist": 0.8632054328918457, "value_other_env": 0.881597101688385, "value_corner": 0.8356180191040039, "value_row": 0.8582115769386292, "value_any": 0.8816089630126953, "value_bot": 0.8572287559509277, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08890.png", "entropy": 0.10001425445079803} +{"ts": "2026-03-20T19:31:03.228811Z", "loop": 8900, "env_steps": 5468160000, "exact_value_avg": 0.8628719449043274, "regret_dist": 0.0007087461417540908, "regret_other_env": 0.0011609058128669858, "regret_corner": 3.05066514556529e-05, "regret_row": 0.0010813248809427023, "regret_any": 0.0011792817385867238, "regret_bot": 0.0011212393874302506, "value_dist": 0.8628719449043274, "value_other_env": 0.8810539841651917, "value_corner": 0.8355988264083862, "value_row": 0.8575453162193298, "value_any": 0.8810713291168213, "value_bot": 0.8575054407119751, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08900.png", "entropy": 0.10110363364219666} +{"ts": "2026-03-20T19:31:11.810306Z", "loop": 8910, "env_steps": 5474304000, "exact_value_avg": 0.8618125319480896, "regret_dist": 0.0017681935569271445, "regret_other_env": 0.002880920423194766, "regret_corner": 9.910315566230565e-05, "regret_row": 0.0063791172578930855, "regret_any": 0.002902478678151965, "regret_bot": 0.0012617801548913121, "value_dist": 0.8618125319480896, "value_other_env": 0.8793339729309082, "value_corner": 0.8355302810668945, "value_row": 0.8522475361824036, "value_any": 0.8793481588363647, "value_bot": 0.8573648929595947, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08910.png", "entropy": 0.10398013144731522} +{"ts": "2026-03-20T19:31:20.393910Z", "loop": 8920, "env_steps": 5480448000, "exact_value_avg": 0.8630686402320862, "regret_dist": 0.0005120310815982521, "regret_other_env": 0.0008441844838671386, "regret_corner": 1.3800959095533472e-05, "regret_row": 0.00042699105688370764, "regret_any": 0.0008688551606610417, "regret_bot": 0.0017152094515040517, "value_dist": 0.8630686402320862, "value_other_env": 0.8813706636428833, "value_corner": 0.8356155157089233, "value_row": 0.8581995964050293, "value_any": 0.8813816905021667, "value_bot": 0.8569114804267883, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08920.png", "entropy": 0.09687816351652145} +{"ts": "2026-03-20T19:31:28.973659Z", "loop": 8930, "env_steps": 5486592000, "exact_value_avg": 0.8628566265106201, "regret_dist": 0.000724065350368619, "regret_other_env": 0.001189845148473978, "regret_corner": 2.5395553166163154e-05, "regret_row": 0.0005870939348824322, "regret_any": 0.0012152501149103045, "regret_bot": 0.001970248529687524, "value_dist": 0.8628566265106201, "value_other_env": 0.8810250759124756, "value_corner": 0.8356039524078369, "value_row": 0.8580394983291626, "value_any": 0.881035327911377, "value_bot": 0.8566564917564392, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08930.png", "entropy": 0.0948723629117012} +{"ts": "2026-03-20T19:31:37.563639Z", "loop": 8940, "env_steps": 5492736000, "exact_value_avg": 0.8630741834640503, "regret_dist": 0.0005065588047727942, "regret_other_env": 0.0008346344693563879, "regret_corner": 1.4445186025113799e-05, "regret_row": 0.0004281874862499535, "regret_any": 0.0008595130639150739, "regret_bot": 0.0018033601809293032, "value_dist": 0.8630741834640503, "value_other_env": 0.8813803195953369, "value_corner": 0.8356148600578308, "value_row": 0.8581984043121338, "value_any": 0.8813911080360413, "value_bot": 0.8568233251571655, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08940.png", "entropy": 0.09592889249324799} +{"ts": "2026-03-20T19:31:46.148331Z", "loop": 8950, "env_steps": 5498880000, "exact_value_avg": 0.8626705408096313, "regret_dist": 0.0009101021569222212, "regret_other_env": 0.0014682816108688712, "regret_corner": 7.283290324267e-05, "regret_row": 0.0027353321202099323, "regret_any": 0.0014916496584191918, "regret_bot": 0.0014901685062795877, "value_dist": 0.8626705408096313, "value_other_env": 0.880746603012085, "value_corner": 0.8355564475059509, "value_row": 0.855891227722168, "value_any": 0.8807590007781982, "value_bot": 0.8571364879608154, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08950.png", "entropy": 0.09602959454059601} +{"ts": "2026-03-20T19:31:54.733812Z", "loop": 8960, "env_steps": 5505024000, "exact_value_avg": 0.8619207143783569, "regret_dist": 0.0016600069357082248, "regret_other_env": 0.0027378550730645657, "regret_corner": 4.3234729673713446e-05, "regret_row": 0.007328695151954889, "regret_any": 0.002761462237685919, "regret_bot": 0.0020079866517335176, "value_dist": 0.8619207143783569, "value_other_env": 0.8794770240783691, "value_corner": 0.8355860710144043, "value_row": 0.8512979745864868, "value_any": 0.8794891238212585, "value_bot": 0.8566187024116516, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08960.png", "entropy": 0.09522054344415665} +{"ts": "2026-03-20T19:32:03.313939Z", "loop": 8970, "env_steps": 5511168000, "exact_value_avg": 0.8630509376525879, "regret_dist": 0.0005296925664879382, "regret_other_env": 0.0008784571546129882, "regret_corner": 6.545583801198518e-06, "regret_row": 0.00035118209780193865, "regret_any": 0.0009022058802656829, "regret_bot": 0.0016570072621107101, "value_dist": 0.8630509376525879, "value_other_env": 0.8813363909721375, "value_corner": 0.8356227874755859, "value_row": 0.8582754135131836, "value_any": 0.8813484311103821, "value_bot": 0.8569696545600891, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08970.png", "entropy": 0.09498044103384018} +{"ts": "2026-03-20T19:32:11.895604Z", "loop": 8980, "env_steps": 5517312000, "exact_value_avg": 0.8623698949813843, "regret_dist": 0.0012107567163184285, "regret_other_env": 0.0020112774800509214, "regret_corner": 9.97533425106667e-06, "regret_row": 0.0007444193470291793, "regret_any": 0.002036730293184519, "regret_bot": 0.003733255434781313, "value_dist": 0.8623698949813843, "value_other_env": 0.8802035450935364, "value_corner": 0.835619330406189, "value_row": 0.8578822016716003, "value_any": 0.8802138566970825, "value_bot": 0.8548934459686279, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08980.png", "entropy": 0.09640451520681381} +{"ts": "2026-03-20T19:32:20.480212Z", "loop": 8990, "env_steps": 5523456000, "exact_value_avg": 0.861729621887207, "regret_dist": 0.0018511289963498712, "regret_other_env": 0.0030519459396600723, "regret_corner": 4.9903494073078036e-05, "regret_row": 0.011496005579829216, "regret_any": 0.0030738397035747766, "regret_bot": 0.0018418943509459496, "value_dist": 0.861729621887207, "value_other_env": 0.8791629672050476, "value_corner": 0.8355793952941895, "value_row": 0.8471306562423706, "value_any": 0.8791767954826355, "value_bot": 0.8567847609519958, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_08990.png", "entropy": 0.09662573784589767} +{"ts": "2026-03-20T19:32:29.058241Z", "loop": 9000, "env_steps": 5529600000, "exact_value_avg": 0.8628125786781311, "regret_dist": 0.0007680689450353384, "regret_other_env": 0.0012763832928612828, "regret_corner": 5.597373274213169e-06, "regret_row": 0.0003639045753516257, "regret_any": 0.0012995421420782804, "regret_bot": 0.0027376317884773016, "value_dist": 0.8628125786781311, "value_other_env": 0.8809384703636169, "value_corner": 0.8356237411499023, "value_row": 0.8582627177238464, "value_any": 0.8809509873390198, "value_bot": 0.8558890223503113, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09000.png", "entropy": 0.09782296419143677} +{"ts": "2026-03-20T19:32:37.644992Z", "loop": 9010, "env_steps": 5535744000, "exact_value_avg": 0.8625626564025879, "regret_dist": 0.0010179381351917982, "regret_other_env": 0.001695376937277615, "regret_corner": 1.7796954807636212e-06, "regret_row": 8.459596574539319e-05, "regret_any": 0.0017268788069486618, "regret_bot": 0.0042273132130503654, "value_dist": 0.8625626564025879, "value_other_env": 0.880519449710846, "value_corner": 0.835627555847168, "value_row": 0.8585420250892639, "value_any": 0.8805238008499146, "value_bot": 0.8543993234634399, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09010.png", "entropy": 0.09715781360864639} +{"ts": "2026-03-20T19:32:46.227252Z", "loop": 9020, "env_steps": 5541888000, "exact_value_avg": 0.862991452217102, "regret_dist": 0.0005892078625038266, "regret_other_env": 0.0009731902391649783, "regret_corner": 1.3234218386060093e-05, "regret_row": 0.00018301398085895926, "regret_any": 0.0009891132358461618, "regret_bot": 0.003581761848181486, "value_dist": 0.862991452217102, "value_other_env": 0.8812416195869446, "value_corner": 0.8356161117553711, "value_row": 0.8584436178207397, "value_any": 0.8812614679336548, "value_bot": 0.8550447821617126, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09020.png", "entropy": 0.09777296334505081} +{"ts": "2026-03-20T19:32:54.820959Z", "loop": 9030, "env_steps": 5548032000, "exact_value_avg": 0.8620361089706421, "regret_dist": 0.0015445619355887175, "regret_other_env": 0.002541555091738701, "regret_corner": 4.9072008550865576e-05, "regret_row": 0.0003834322851616889, "regret_any": 0.0025742091238498688, "regret_bot": 0.008264034055173397, "value_dist": 0.8620361089706421, "value_other_env": 0.8796733021736145, "value_corner": 0.8355802297592163, "value_row": 0.8582432270050049, "value_any": 0.879676342010498, "value_bot": 0.8503626585006714, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09030.png", "entropy": 0.09962793439626694} +{"ts": "2026-03-20T19:33:03.404236Z", "loop": 9040, "env_steps": 5554176000, "exact_value_avg": 0.8624041080474854, "regret_dist": 0.0011765811359509826, "regret_other_env": 0.0017621727893128991, "regret_corner": 0.00029819359770044684, "regret_row": 0.0040145511738955975, "regret_any": 0.0017863605171442032, "regret_bot": 0.003670244012027979, "value_dist": 0.8624041080474854, "value_other_env": 0.8804526329040527, "value_corner": 0.8353311419487, "value_row": 0.8546121120452881, "value_any": 0.8804641962051392, "value_bot": 0.8549563884735107, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09040.png", "entropy": 0.1024855300784111} +{"ts": "2026-03-20T19:33:11.985466Z", "loop": 9050, "env_steps": 5560320000, "exact_value_avg": 0.8631836175918579, "regret_dist": 0.0003970950492657721, "regret_other_env": 0.0006304680719040334, "regret_corner": 4.7035518946358934e-05, "regret_row": 0.0010601527756080031, "regret_any": 0.0006512565305456519, "regret_bot": 0.0008818633505143225, "value_dist": 0.8631836175918579, "value_other_env": 0.8815844058990479, "value_corner": 0.8355822563171387, "value_row": 0.8575664758682251, "value_any": 0.8815993666648865, "value_bot": 0.8577447533607483, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09050.png", "entropy": 0.10018248856067657} +{"ts": "2026-03-20T19:33:20.566334Z", "loop": 9060, "env_steps": 5566464000, "exact_value_avg": 0.8621737360954285, "regret_dist": 0.0014069083845242858, "regret_other_env": 0.002344027627259493, "regret_corner": 1.2293459121792694e-06, "regret_row": 0.001490709139034152, "regret_any": 0.002364661078900099, "regret_bot": 0.004176066257059574, "value_dist": 0.8621737360954285, "value_other_env": 0.8798708319664001, "value_corner": 0.8356280326843262, "value_row": 0.8571358919143677, "value_any": 0.8798859119415283, "value_bot": 0.854450523853302, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09060.png", "entropy": 0.10300977528095245} +{"ts": "2026-03-20T19:33:29.145045Z", "loop": 9070, "env_steps": 5572608000, "exact_value_avg": 0.8591486215591431, "regret_dist": 0.0044320691376924515, "regret_other_env": 0.007385052274912596, "regret_corner": 2.593795670691179e-06, "regret_row": 0.01882839761674404, "regret_any": 0.0074034142307937145, "regret_bot": 0.007007249630987644, "value_dist": 0.8591486215591431, "value_other_env": 0.8748298287391663, "value_corner": 0.8356267809867859, "value_row": 0.8397982120513916, "value_any": 0.8748472332954407, "value_bot": 0.8516194224357605, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09070.png", "entropy": 0.10159443318843842} +{"ts": "2026-03-20T19:33:37.729104Z", "loop": 9080, "env_steps": 5578752000, "exact_value_avg": 0.8602945804595947, "regret_dist": 0.0032860995270311832, "regret_other_env": 0.00547462422400713, "regret_corner": 3.312031594759901e-06, "regret_row": 0.012695538811385632, "regret_any": 0.005489750765264034, "regret_bot": 0.004557215142995119, "value_dist": 0.8602945804595947, "value_other_env": 0.8767402768135071, "value_corner": 0.8356260061264038, "value_row": 0.8459311723709106, "value_any": 0.8767607808113098, "value_bot": 0.8540694713592529, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09080.png", "entropy": 0.10336937755346298} +{"ts": "2026-03-20T19:33:46.318867Z", "loop": 9090, "env_steps": 5584896000, "exact_value_avg": 0.8624125719070435, "regret_dist": 0.0011681286850944161, "regret_other_env": 0.0019436279544606805, "regret_corner": 4.879633706877939e-06, "regret_row": 0.0011043098056688905, "regret_any": 0.0019694569054991007, "regret_bot": 0.003611326916143298, "value_dist": 0.8624125719070435, "value_other_env": 0.8802712559700012, "value_corner": 0.8356244564056396, "value_row": 0.8575222492218018, "value_any": 0.8802811503410339, "value_bot": 0.8550152778625488, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09090.png", "entropy": 0.10605237632989883} +{"ts": "2026-03-20T19:33:54.904468Z", "loop": 9100, "env_steps": 5591040000, "exact_value_avg": 0.8627647161483765, "regret_dist": 0.0008159191347658634, "regret_other_env": 0.001348007470369339, "regret_corner": 1.7786524040275253e-05, "regret_row": 0.00018661590002011508, "regret_any": 0.0013692753855139017, "regret_bot": 0.003410575445741415, "value_dist": 0.8627647161483765, "value_other_env": 0.8808668255805969, "value_corner": 0.8356115221977234, "value_row": 0.8584400415420532, "value_any": 0.8808813095092773, "value_bot": 0.8552160859107971, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09100.png", "entropy": 0.10892687737941742} +{"ts": "2026-03-20T19:34:03.492844Z", "loop": 9110, "env_steps": 5597184000, "exact_value_avg": 0.8624213337898254, "regret_dist": 0.0011593988165259361, "regret_other_env": 0.001836625044234097, "regret_corner": 0.00014355928578879684, "regret_row": 0.0010437159799039364, "regret_any": 0.001846090191975236, "regret_bot": 0.003816902404651046, "value_dist": 0.8624213337898254, "value_other_env": 0.8803783059120178, "value_corner": 0.8354857563972473, "value_row": 0.8575829267501831, "value_any": 0.8804044723510742, "value_bot": 0.8548097014427185, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09110.png", "entropy": 0.11648593097925186} +{"ts": "2026-03-20T19:34:12.073369Z", "loop": 9120, "env_steps": 5603328000, "exact_value_avg": 0.8624367713928223, "regret_dist": 0.0011438875226303935, "regret_other_env": 0.00189661153126508, "regret_corner": 1.4801324141444638e-05, "regret_row": 0.0002877030347008258, "regret_any": 0.001913060201331973, "regret_bot": 0.005343632772564888, "value_dist": 0.8624367713928223, "value_other_env": 0.880318284034729, "value_corner": 0.8356145620346069, "value_row": 0.8583389520645142, "value_any": 0.8803375363349915, "value_bot": 0.8532829880714417, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09120.png", "entropy": 0.10705643892288208} +{"ts": "2026-03-20T19:34:20.654796Z", "loop": 9130, "env_steps": 5609472000, "exact_value_avg": 0.8625885844230652, "regret_dist": 0.0009920955635607243, "regret_other_env": 0.0016478468896821141, "regret_corner": 8.468330634059384e-06, "regret_row": 0.0002290838456247002, "regret_any": 0.0016777107957750559, "regret_bot": 0.005332281347364187, "value_dist": 0.8625885844230652, "value_other_env": 0.8805670142173767, "value_corner": 0.8356208801269531, "value_row": 0.8583974838256836, "value_any": 0.8805729150772095, "value_bot": 0.8532943725585938, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09130.png", "entropy": 0.10391346365213394} +{"ts": "2026-03-20T19:34:29.239640Z", "loop": 9140, "env_steps": 5615616000, "exact_value_avg": 0.862943172454834, "regret_dist": 0.0006376034580171108, "regret_other_env": 0.001012321445159614, "regret_corner": 7.552654278697446e-05, "regret_row": 0.0005759591585956514, "regret_any": 0.0010343354661017656, "regret_bot": 0.0011831315932795405, "value_dist": 0.862943172454834, "value_other_env": 0.8812026381492615, "value_corner": 0.835553765296936, "value_row": 0.8580507040023804, "value_any": 0.881216287612915, "value_bot": 0.8574435114860535, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09140.png", "entropy": 0.10126470774412155} +{"ts": "2026-03-20T19:34:37.822301Z", "loop": 9150, "env_steps": 5621760000, "exact_value_avg": 0.8626445531845093, "regret_dist": 0.0009361159172840416, "regret_other_env": 0.0014641776215285063, "regret_corner": 0.00014402320084627718, "regret_row": 0.0010165575658902526, "regret_any": 0.0014855542685836554, "regret_bot": 0.0016613320913165808, "value_dist": 0.8626445531845093, "value_other_env": 0.8807507157325745, "value_corner": 0.8354852199554443, "value_row": 0.8576101064682007, "value_any": 0.8807650208473206, "value_bot": 0.8569653034210205, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09150.png", "entropy": 0.101816326379776} +{"ts": "2026-03-20T19:34:46.403938Z", "loop": 9160, "env_steps": 5627904000, "exact_value_avg": 0.8608438968658447, "regret_dist": 0.0027367223519831896, "regret_other_env": 0.004547734744846821, "regret_corner": 2.0203491658321582e-05, "regret_row": 0.002313310047611594, "regret_any": 0.004556105937808752, "regret_bot": 0.010022908449172974, "value_dist": 0.8608438968658447, "value_other_env": 0.8776671290397644, "value_corner": 0.8356090784072876, "value_row": 0.8563134074211121, "value_any": 0.8776944279670715, "value_bot": 0.8486037254333496, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09160.png", "entropy": 0.10616714507341385} +{"ts": "2026-03-20T19:34:54.984545Z", "loop": 9170, "env_steps": 5634048000, "exact_value_avg": 0.8622627258300781, "regret_dist": 0.0013179212110117078, "regret_other_env": 0.002128985244780779, "regret_corner": 0.00010132492025149986, "regret_row": 0.0023785007651895285, "regret_any": 0.0021441883873194456, "regret_bot": 0.0029539482202380896, "value_dist": 0.8622627258300781, "value_other_env": 0.8800858855247498, "value_corner": 0.8355279564857483, "value_row": 0.856248140335083, "value_any": 0.8801063895225525, "value_bot": 0.8556727170944214, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09170.png", "entropy": 0.10841260105371475} +{"ts": "2026-03-20T19:35:03.575979Z", "loop": 9180, "env_steps": 5640192000, "exact_value_avg": 0.8624985218048096, "regret_dist": 0.0010821755276992917, "regret_other_env": 0.0016891262494027615, "regret_corner": 0.0001717492996249348, "regret_row": 0.002128424821421504, "regret_any": 0.001708957483060658, "regret_bot": 0.0026324097998440266, "value_dist": 0.8624985218048096, "value_other_env": 0.8805257678031921, "value_corner": 0.8354575634002686, "value_row": 0.8564981818199158, "value_any": 0.8805416226387024, "value_bot": 0.8559941649436951, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09180.png", "entropy": 0.11302167177200317} +{"ts": "2026-03-20T19:35:12.158636Z", "loop": 9190, "env_steps": 5646336000, "exact_value_avg": 0.8608154654502869, "regret_dist": 0.002765282057225704, "regret_other_env": 0.003048404585570097, "regret_corner": 0.0023405980318784714, "regret_row": 0.006088289897888899, "regret_any": 0.003068051766604185, "regret_bot": 0.00389339798130095, "value_dist": 0.8608154654502869, "value_other_env": 0.8791665434837341, "value_corner": 0.8332887291908264, "value_row": 0.8525382876396179, "value_any": 0.8791825771331787, "value_bot": 0.8547332286834717, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09190.png", "entropy": 0.12128894031047821} +{"ts": "2026-03-20T19:35:20.741641Z", "loop": 9200, "env_steps": 5652480000, "exact_value_avg": 0.8621125221252441, "regret_dist": 0.0014682257315143943, "regret_other_env": 0.002259174594655633, "regret_corner": 0.0002818023203872144, "regret_row": 0.002567121759057045, "regret_any": 0.0022835605777800083, "regret_bot": 0.006520003080368042, "value_dist": 0.8621125221252441, "value_other_env": 0.8799557089805603, "value_corner": 0.8353475332260132, "value_row": 0.8560594916343689, "value_any": 0.8799670338630676, "value_bot": 0.8521066308021545, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09200.png", "entropy": 0.11304394155740738} +{"ts": "2026-03-20T19:35:29.322899Z", "loop": 9210, "env_steps": 5658624000, "exact_value_avg": 0.8608900308609009, "regret_dist": 0.002690621418878436, "regret_other_env": 0.0037299878895282745, "regret_corner": 0.001131571363657713, "regret_row": 0.007850145921111107, "regret_any": 0.003751937299966812, "regret_bot": 0.008285416290163994, "value_dist": 0.8608900308609009, "value_other_env": 0.878484845161438, "value_corner": 0.8344977498054504, "value_row": 0.8507764339447021, "value_any": 0.8784987330436707, "value_bot": 0.8503412008285522, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09210.png", "entropy": 0.12248606234788895} +{"ts": "2026-03-20T19:35:37.902412Z", "loop": 9220, "env_steps": 5664768000, "exact_value_avg": 0.8623100519180298, "regret_dist": 0.0012706094421446323, "regret_other_env": 0.0016612986801192164, "regret_corner": 0.0006845752941444516, "regret_row": 0.004722404759377241, "regret_any": 0.0016834614798426628, "regret_bot": 0.002293333411216736, "value_dist": 0.8623100519180298, "value_other_env": 0.8805535435676575, "value_corner": 0.8349447846412659, "value_row": 0.8539041876792908, "value_any": 0.8805671334266663, "value_bot": 0.856333315372467, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09220.png", "entropy": 0.11554357409477234} +{"ts": "2026-03-20T19:35:46.481032Z", "loop": 9230, "env_steps": 5670912000, "exact_value_avg": 0.858168363571167, "regret_dist": 0.005412308499217033, "regret_other_env": 0.00722224498167634, "regret_corner": 0.0026974028442054987, "regret_row": 0.015442226082086563, "regret_any": 0.007256666664034128, "regret_bot": 0.0015601720660924911, "value_dist": 0.858168363571167, "value_other_env": 0.8749926686286926, "value_corner": 0.8329319357872009, "value_row": 0.8431843519210815, "value_any": 0.8749939799308777, "value_bot": 0.8570664525032043, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09230.png", "entropy": 0.1213039979338646} +{"ts": "2026-03-20T19:35:55.058612Z", "loop": 9240, "env_steps": 5677056000, "exact_value_avg": 0.8632320165634155, "regret_dist": 0.0003486328641884029, "regret_other_env": 0.000564095564186573, "regret_corner": 2.5438766897423193e-05, "regret_row": 0.0005550450296141207, "regret_any": 0.0005859709344804287, "regret_bot": 0.0010761149460449815, "value_dist": 0.8632320165634155, "value_other_env": 0.8816507458686829, "value_corner": 0.8356038928031921, "value_row": 0.8580715656280518, "value_any": 0.8816645741462708, "value_bot": 0.8575505018234253, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09240.png", "entropy": 0.09951895475387573} +{"ts": "2026-03-20T19:36:03.649235Z", "loop": 9250, "env_steps": 5683200000, "exact_value_avg": 0.8619335889816284, "regret_dist": 0.0016470125410705805, "regret_other_env": 0.0027443976141512394, "regret_corner": 9.347995728603564e-07, "regret_row": 0.012913583777844906, "regret_any": 0.0027623334899544716, "regret_bot": 0.0017485400894656777, "value_dist": 0.8619335889816284, "value_other_env": 0.8794704079627991, "value_corner": 0.8356284499168396, "value_row": 0.8457130789756775, "value_any": 0.8794882893562317, "value_bot": 0.8568781018257141, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09250.png", "entropy": 0.09658961743116379} +{"ts": "2026-03-20T19:36:12.239950Z", "loop": 9260, "env_steps": 5689344000, "exact_value_avg": 0.8628945350646973, "regret_dist": 0.0006861362489871681, "regret_other_env": 0.00114158121868968, "regret_corner": 2.9688080758205615e-06, "regret_row": 0.0005763487424701452, "regret_any": 0.0011592413065955043, "regret_bot": 0.0005309692351147532, "value_dist": 0.8628945350646973, "value_other_env": 0.8810732960700989, "value_corner": 0.8356263041496277, "value_row": 0.8580503463745117, "value_any": 0.8810913562774658, "value_bot": 0.858095645904541, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09260.png", "entropy": 0.0893004834651947} +{"ts": "2026-03-20T19:36:20.826614Z", "loop": 9270, "env_steps": 5695488000, "exact_value_avg": 0.8616740107536316, "regret_dist": 0.0019066801760345697, "regret_other_env": 0.0031626070849597454, "regret_corner": 2.2789836293668486e-05, "regret_row": 0.0014798443298786879, "regret_any": 0.0031962739303708076, "regret_bot": 0.0020236524287611246, "value_dist": 0.8616740107536316, "value_other_env": 0.8790522217750549, "value_corner": 0.835606575012207, "value_row": 0.8571467995643616, "value_any": 0.8790543079376221, "value_bot": 0.8566030263900757, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09270.png", "entropy": 0.09444767236709595} +{"ts": "2026-03-20T19:36:29.404871Z", "loop": 9280, "env_steps": 5701632000, "exact_value_avg": 0.8625261783599854, "regret_dist": 0.0010544703109189868, "regret_other_env": 0.0017430614680051804, "regret_corner": 2.1583338821073994e-05, "regret_row": 0.0012973902048543096, "regret_any": 0.0017614959506317973, "regret_bot": 0.0013271040515974164, "value_dist": 0.8625261783599854, "value_other_env": 0.8804717659950256, "value_corner": 0.8356077075004578, "value_row": 0.8573291897773743, "value_any": 0.8804891109466553, "value_bot": 0.8572995066642761, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09280.png", "entropy": 0.09168648719787598} +{"ts": "2026-03-20T19:36:37.985956Z", "loop": 9290, "env_steps": 5707776000, "exact_value_avg": 0.8581885099411011, "regret_dist": 0.005392163060605526, "regret_other_env": 0.008859473280608654, "regret_corner": 0.00019119730859529227, "regret_row": 0.01043839380145073, "regret_any": 0.00888277031481266, "regret_bot": 0.00975067913532257, "value_dist": 0.8581885099411011, "value_other_env": 0.8733553886413574, "value_corner": 0.8354381322860718, "value_row": 0.8481882214546204, "value_any": 0.8733678460121155, "value_bot": 0.8488759994506836, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09290.png", "entropy": 0.10294919461011887} +{"ts": "2026-03-20T19:36:46.570065Z", "loop": 9300, "env_steps": 5713920000, "exact_value_avg": 0.8623824715614319, "regret_dist": 0.0011982055148109794, "regret_other_env": 0.0019895867444574833, "regret_corner": 1.1133651241834741e-05, "regret_row": 0.0018898462876677513, "regret_any": 0.0020093645434826612, "regret_bot": 0.0016219220124185085, "value_dist": 0.8623824715614319, "value_other_env": 0.8802252411842346, "value_corner": 0.8356181979179382, "value_row": 0.8567367792129517, "value_any": 0.8802412748336792, "value_bot": 0.857004702091217, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09300.png", "entropy": 0.09110496193170547} +{"ts": "2026-03-20T19:36:55.149043Z", "loop": 9310, "env_steps": 5720064000, "exact_value_avg": 0.8627012968063354, "regret_dist": 0.0008794133900664747, "regret_other_env": 0.0014622401213273406, "regret_corner": 5.173186764295679e-06, "regret_row": 0.002198822796344757, "regret_any": 0.0014664423651993275, "regret_bot": 0.003041982650756836, "value_dist": 0.8627012968063354, "value_other_env": 0.880752682685852, "value_corner": 0.835624098777771, "value_row": 0.8564279079437256, "value_any": 0.8807841539382935, "value_bot": 0.8555846810340881, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09310.png", "entropy": 0.09697052091360092} +{"ts": "2026-03-20T19:37:03.731364Z", "loop": 9320, "env_steps": 5726208000, "exact_value_avg": 0.8629981279373169, "regret_dist": 0.0005825561820529401, "regret_other_env": 0.0009565138607285917, "regret_corner": 2.1619598555844277e-05, "regret_row": 0.0006580343469977379, "regret_any": 0.000955474388319999, "regret_bot": 0.002037914702668786, "value_dist": 0.8629981279373169, "value_other_env": 0.8812583088874817, "value_corner": 0.8356077075004578, "value_row": 0.8579685688018799, "value_any": 0.8812951445579529, "value_bot": 0.8565887808799744, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09320.png", "entropy": 0.09435958415269852} +{"ts": "2026-03-20T19:37:12.318946Z", "loop": 9330, "env_steps": 5732352000, "exact_value_avg": 0.8586199879646301, "regret_dist": 0.004960667807608843, "regret_other_env": 0.008231677114963531, "regret_corner": 5.4153304517967626e-05, "regret_row": 0.00826004333794117, "regret_any": 0.00824896339327097, "regret_bot": 0.0134621886536479, "value_dist": 0.8586199879646301, "value_other_env": 0.8739832043647766, "value_corner": 0.8355751633644104, "value_row": 0.8503665328025818, "value_any": 0.874001681804657, "value_bot": 0.84516441822052, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09330.png", "entropy": 0.09895791113376617} +{"ts": "2026-03-20T19:37:20.900359Z", "loop": 9340, "env_steps": 5738496000, "exact_value_avg": 0.8618208169937134, "regret_dist": 0.0017598849954083562, "regret_other_env": 0.0029297182336449623, "regret_corner": 5.1349402383493725e-06, "regret_row": 0.001471473602578044, "regret_any": 0.0029496101196855307, "regret_bot": 0.0035644173622131348, "value_dist": 0.8618208169937134, "value_other_env": 0.8792851567268372, "value_corner": 0.8356242179870605, "value_row": 0.8571551442146301, "value_any": 0.8793010115623474, "value_bot": 0.8550621867179871, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09340.png", "entropy": 0.08907909691333771} +{"ts": "2026-03-20T19:37:29.491287Z", "loop": 9350, "env_steps": 5744640000, "exact_value_avg": 0.8624933958053589, "regret_dist": 0.0010873068822547793, "regret_other_env": 0.001805298263207078, "regret_corner": 1.0319551620341372e-05, "regret_row": 0.0010727493790909648, "regret_any": 0.0018271373119205236, "regret_bot": 0.0017321857158094645, "value_dist": 0.8624933958053589, "value_other_env": 0.8804095983505249, "value_corner": 0.8356190323829651, "value_row": 0.8575538992881775, "value_any": 0.8804234266281128, "value_bot": 0.8568945527076721, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09350.png", "entropy": 0.0900484174489975} +{"ts": "2026-03-20T19:37:38.068096Z", "loop": 9360, "env_steps": 5750784000, "exact_value_avg": 0.8627454042434692, "regret_dist": 0.0008353068260475993, "regret_other_env": 0.0013721853028982878, "regret_corner": 2.998908530571498e-05, "regret_row": 0.0020792230498045683, "regret_any": 0.0013938399497419596, "regret_bot": 0.0010800781892612576, "value_dist": 0.8627454042434692, "value_other_env": 0.8808427453041077, "value_corner": 0.8355993628501892, "value_row": 0.8565473556518555, "value_any": 0.8808568120002747, "value_bot": 0.8575466275215149, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09360.png", "entropy": 0.09007084369659424} +{"ts": "2026-03-20T19:37:46.649283Z", "loop": 9370, "env_steps": 5756928000, "exact_value_avg": 0.8623201251029968, "regret_dist": 0.0012605235679075122, "regret_other_env": 0.0020929984748363495, "regret_corner": 1.1811157492047641e-05, "regret_row": 0.0013377513969317079, "regret_any": 0.0021153658162802458, "regret_bot": 0.0017481195973232388, "value_dist": 0.8623201251029968, "value_other_env": 0.8801218867301941, "value_corner": 0.8356174826622009, "value_row": 0.8572888374328613, "value_any": 0.880135178565979, "value_bot": 0.8568785190582275, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09370.png", "entropy": 0.08888770639896393} +{"ts": "2026-03-20T19:37:55.224164Z", "loop": 9380, "env_steps": 5763072000, "exact_value_avg": 0.8615967035293579, "regret_dist": 0.0019839671440422535, "regret_other_env": 0.003304576501250267, "regret_corner": 3.052751480936422e-06, "regret_row": 0.0025332183577120304, "regret_any": 0.0033268232364207506, "regret_bot": 0.0033246043603867292, "value_dist": 0.8615967035293579, "value_other_env": 0.8789103031158447, "value_corner": 0.8356262445449829, "value_row": 0.8560934066772461, "value_any": 0.878923773765564, "value_bot": 0.8553019762039185, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09380.png", "entropy": 0.0893077701330185} +{"ts": "2026-03-20T19:38:03.808310Z", "loop": 9390, "env_steps": 5769216000, "exact_value_avg": 0.8631589412689209, "regret_dist": 0.0004217141540721059, "regret_other_env": 0.0007021505734883249, "regret_corner": 1.0594726518320385e-06, "regret_row": 0.0009275966440327466, "regret_any": 0.0007260908605530858, "regret_bot": 0.0025204115081578493, "value_dist": 0.8631589412689209, "value_other_env": 0.8815127611160278, "value_corner": 0.8356282711029053, "value_row": 0.8576989769935608, "value_any": 0.8815245032310486, "value_bot": 0.8561062812805176, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09390.png", "entropy": 0.09341377019882202} +{"ts": "2026-03-20T19:38:12.395667Z", "loop": 9400, "env_steps": 5775360000, "exact_value_avg": 0.8631163835525513, "regret_dist": 0.000464198412373662, "regret_other_env": 0.0007711778162047267, "regret_corner": 3.7292641081876354e-06, "regret_row": 0.001783474232070148, "regret_any": 0.0007782539469189942, "regret_bot": 0.0012389619369059801, "value_dist": 0.8631163835525513, "value_other_env": 0.8814436197280884, "value_corner": 0.8356255888938904, "value_row": 0.856843113899231, "value_any": 0.8814724087715149, "value_bot": 0.8573876023292542, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09400.png", "entropy": 0.09884562343358994} +{"ts": "2026-03-20T19:38:20.978101Z", "loop": 9410, "env_steps": 5781504000, "exact_value_avg": 0.8626282811164856, "regret_dist": 0.0009524207562208176, "regret_other_env": 0.0015710295410826802, "regret_corner": 2.4507444322807714e-05, "regret_row": 0.0033417176455259323, "regret_any": 0.001570077845826745, "regret_bot": 0.0021952339448034763, "value_dist": 0.8626282811164856, "value_other_env": 0.8806438446044922, "value_corner": 0.8356047868728638, "value_row": 0.8552848696708679, "value_any": 0.880680501461029, "value_bot": 0.8564314246177673, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09410.png", "entropy": 0.10551638901233673} +{"ts": "2026-03-20T19:38:29.559794Z", "loop": 9420, "env_steps": 5787648000, "exact_value_avg": 0.862686276435852, "regret_dist": 0.0008944541332311928, "regret_other_env": 0.0013487073592841625, "regret_corner": 0.0002130741922883317, "regret_row": 0.000748616992495954, "regret_any": 0.001351711223833263, "regret_bot": 0.0007148906588554382, "value_dist": 0.862686276435852, "value_other_env": 0.8808661699295044, "value_corner": 0.8354162573814392, "value_row": 0.8578780293464661, "value_any": 0.8808988928794861, "value_bot": 0.8579117059707642, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09420.png", "entropy": 0.10747968405485153} +{"ts": "2026-03-20T19:38:38.147450Z", "loop": 9430, "env_steps": 5793792000, "exact_value_avg": 0.8617936968803406, "regret_dist": 0.0017869711155071855, "regret_other_env": 0.0029728536028414965, "regret_corner": 8.147459084284492e-06, "regret_row": 0.012388613075017929, "regret_any": 0.002994834678247571, "regret_bot": 0.0026040817610919476, "value_dist": 0.8617936968803406, "value_other_env": 0.8792420029640198, "value_corner": 0.835621178150177, "value_row": 0.8462380170822144, "value_any": 0.8792557716369629, "value_bot": 0.8560225963592529, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09430.png", "entropy": 0.10034017264842987} +{"ts": "2026-03-20T19:38:46.728363Z", "loop": 9440, "env_steps": 5799936000, "exact_value_avg": 0.8634042739868164, "regret_dist": 0.00017635320546105504, "regret_other_env": 0.0002880088868550956, "regret_corner": 8.869667908584233e-06, "regret_row": 0.00020674028201028705, "regret_any": 0.0003111013793386519, "regret_bot": 0.0012035015970468521, "value_dist": 0.8634042739868164, "value_other_env": 0.8819268345832825, "value_corner": 0.8356204032897949, "value_row": 0.8584198355674744, "value_any": 0.8819394707679749, "value_bot": 0.8574231266975403, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09440.png", "entropy": 0.0910104289650917} +{"ts": "2026-03-20T19:38:55.310883Z", "loop": 9450, "env_steps": 5806080000, "exact_value_avg": 0.8634270429611206, "regret_dist": 0.00015358705422841012, "regret_other_env": 0.00024687545374035835, "regret_corner": 1.3654431313625537e-05, "regret_row": 7.171007746364921e-05, "regret_any": 0.00026829750277101994, "regret_bot": 0.0008310053963214159, "value_dist": 0.8634270429611206, "value_other_env": 0.8819679617881775, "value_corner": 0.8356156349182129, "value_row": 0.8585548996925354, "value_any": 0.8819823265075684, "value_bot": 0.8577956557273865, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09450.png", "entropy": 0.08870607614517212} +{"ts": "2026-03-20T19:39:03.898458Z", "loop": 9460, "env_steps": 5812224000, "exact_value_avg": 0.8629963994026184, "regret_dist": 0.0005843251710757613, "regret_other_env": 0.0009164027287624776, "regret_corner": 8.620868902653456e-05, "regret_row": 0.0004523186944425106, "regret_any": 0.0009253043681383133, "regret_bot": 0.000491358689032495, "value_dist": 0.8629963994026184, "value_other_env": 0.8812985420227051, "value_corner": 0.8355430960655212, "value_row": 0.8581743240356445, "value_any": 0.8813253045082092, "value_bot": 0.8581352233886719, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09460.png", "entropy": 0.09204139560461044} +{"ts": "2026-03-20T19:39:12.483992Z", "loop": 9470, "env_steps": 5818368000, "exact_value_avg": 0.8631373643875122, "regret_dist": 0.00044330311357043684, "regret_other_env": 0.0007382073090411723, "regret_corner": 9.467204904467508e-07, "regret_row": 0.000388616812415421, "regret_any": 0.0007494373712688684, "regret_bot": 0.0014530811458826065, "value_dist": 0.8631373643875122, "value_other_env": 0.881476640701294, "value_corner": 0.8356284499168396, "value_row": 0.8582380414009094, "value_any": 0.8815011382102966, "value_bot": 0.8571735620498657, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09470.png", "entropy": 0.0955362468957901} +{"ts": "2026-03-20T19:39:21.070042Z", "loop": 9480, "env_steps": 5824512000, "exact_value_avg": 0.862236738204956, "regret_dist": 0.0013439289759844542, "regret_other_env": 0.0022398019209504128, "regret_corner": 1.1920928955078125e-07, "regret_row": 0.0032927230931818485, "regret_any": 0.0022609014995396137, "regret_bot": 0.0035747215151786804, "value_dist": 0.862236738204956, "value_other_env": 0.8799750804901123, "value_corner": 0.8356291651725769, "value_row": 0.8553338646888733, "value_any": 0.879989743232727, "value_bot": 0.8550518155097961, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09480.png", "entropy": 0.09195984154939651} +{"ts": "2026-03-20T19:39:29.653531Z", "loop": 9490, "env_steps": 5830656000, "exact_value_avg": 0.8625681400299072, "regret_dist": 0.001012542168609798, "regret_other_env": 0.0016874001594260335, "regret_corner": 2.548098620991368e-07, "regret_row": 0.0011015033815056086, "regret_any": 0.0017097676172852516, "regret_bot": 0.003008222207427025, "value_dist": 0.8625681400299072, "value_other_env": 0.8805274963378906, "value_corner": 0.8356290459632874, "value_row": 0.8575251698493958, "value_any": 0.8805407881736755, "value_bot": 0.855618417263031, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09490.png", "entropy": 0.08954495936632156} +{"ts": "2026-03-20T19:39:38.238495Z", "loop": 9500, "env_steps": 5836800000, "exact_value_avg": 0.8622467517852783, "regret_dist": 0.0013339314609766006, "regret_other_env": 0.002219215966761112, "regret_corner": 6.0046713770134374e-06, "regret_row": 0.0004687457112595439, "regret_any": 0.0022432890255004168, "regret_bot": 0.005392296239733696, "value_dist": 0.8622467517852783, "value_other_env": 0.8799957036972046, "value_corner": 0.8356233239173889, "value_row": 0.8581578731536865, "value_any": 0.880007266998291, "value_bot": 0.8532342910766602, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09500.png", "entropy": 0.08769688010215759} +{"ts": "2026-03-20T19:39:46.820458Z", "loop": 9510, "env_steps": 5842944000, "exact_value_avg": 0.8632123470306396, "regret_dist": 0.0003683442191686481, "regret_other_env": 0.0006121817859821022, "regret_corner": 2.5878350697894348e-06, "regret_row": 0.0001714248937787488, "regret_any": 0.0006330936448648572, "regret_bot": 0.0012264827964827418, "value_dist": 0.8632123470306396, "value_other_env": 0.8816027641296387, "value_corner": 0.8356267809867859, "value_row": 0.8584551811218262, "value_any": 0.881617546081543, "value_bot": 0.8574001789093018, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09510.png", "entropy": 0.08679021149873734} +{"ts": "2026-03-20T19:39:55.409069Z", "loop": 9520, "env_steps": 5849088000, "exact_value_avg": 0.8631753921508789, "regret_dist": 0.0004052674921695143, "regret_other_env": 0.0006746311555616558, "regret_corner": 1.2218953315823455e-06, "regret_row": 0.0004764259501826018, "regret_any": 0.0006823627045378089, "regret_bot": 0.0005990053759887815, "value_dist": 0.8631753921508789, "value_other_env": 0.8815402388572693, "value_corner": 0.835628092288971, "value_row": 0.8581501841545105, "value_any": 0.881568193435669, "value_bot": 0.8580276966094971, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09520.png", "entropy": 0.08799300342798233} +{"ts": "2026-03-20T19:40:03.990796Z", "loop": 9530, "env_steps": 5855232000, "exact_value_avg": 0.8619179725646973, "regret_dist": 0.0016627280274406075, "regret_other_env": 0.0027592366095632315, "regret_corner": 1.7964841390494257e-05, "regret_row": 0.00041005632374435663, "regret_any": 0.002785132732242346, "regret_bot": 0.005314328242093325, "value_dist": 0.8619179725646973, "value_other_env": 0.8794556260108948, "value_corner": 0.8356114029884338, "value_row": 0.8582165837287903, "value_any": 0.8794654607772827, "value_bot": 0.8533123135566711, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09530.png", "entropy": 0.09115397930145264} +{"ts": "2026-03-20T19:40:12.572502Z", "loop": 9540, "env_steps": 5861376000, "exact_value_avg": 0.8617523312568665, "regret_dist": 0.0018283671233803034, "regret_other_env": 0.0030405509751290083, "regret_corner": 1.0091066542372573e-05, "regret_row": 0.0006066730129532516, "regret_any": 0.0030640456825494766, "regret_bot": 0.004374153912067413, "value_dist": 0.8617523312568665, "value_other_env": 0.8791743516921997, "value_corner": 0.8356192708015442, "value_row": 0.858020007610321, "value_any": 0.8791866302490234, "value_bot": 0.8542524576187134, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09540.png", "entropy": 0.08937615901231766} +{"ts": "2026-03-20T19:40:21.155976Z", "loop": 9550, "env_steps": 5867520000, "exact_value_avg": 0.8620203137397766, "regret_dist": 0.0015603307401761413, "regret_other_env": 0.002600008388981223, "regret_corner": 8.141001330841391e-07, "regret_row": 0.0004957733326591551, "regret_any": 0.002623066771775484, "regret_bot": 0.00715524610131979, "value_dist": 0.8620203137397766, "value_other_env": 0.8796148300170898, "value_corner": 0.8356285095214844, "value_row": 0.8581308722496033, "value_any": 0.879627525806427, "value_bot": 0.8514713644981384, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09550.png", "entropy": 0.09238991141319275} +{"ts": "2026-03-20T19:40:29.740493Z", "loop": 9560, "env_steps": 5873664000, "exact_value_avg": 0.8596611618995667, "regret_dist": 0.0039194743148982525, "regret_other_env": 0.006532101891934872, "regret_corner": 5.319714659890451e-07, "regret_row": 0.010805990546941757, "regret_any": 0.006571237463504076, "regret_bot": 0.010160669684410095, "value_dist": 0.8596611618995667, "value_other_env": 0.8756827116012573, "value_corner": 0.8356288075447083, "value_row": 0.8478206396102905, "value_any": 0.8756793141365051, "value_bot": 0.8484659790992737, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09560.png", "entropy": 0.09970224648714066} +{"ts": "2026-03-20T19:40:38.321288Z", "loop": 9570, "env_steps": 5879808000, "exact_value_avg": 0.8626534938812256, "regret_dist": 0.000927237153518945, "regret_other_env": 0.001505073276348412, "regret_corner": 6.048282375559211e-05, "regret_row": 0.0011795655591413379, "regret_any": 0.0015030496288090944, "regret_bot": 0.0040185293182730675, "value_dist": 0.8626534938812256, "value_other_env": 0.8807098269462585, "value_corner": 0.8355688452720642, "value_row": 0.85744708776474, "value_any": 0.8807475566864014, "value_bot": 0.8546081185340881, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09570.png", "entropy": 0.11458801478147507} +{"ts": "2026-03-20T19:40:46.900329Z", "loop": 9580, "env_steps": 5885952000, "exact_value_avg": 0.8613955974578857, "regret_dist": 0.002185097197070718, "regret_other_env": 0.002659037709236145, "regret_corner": 0.0014741863124072552, "regret_row": 0.0040840343572199345, "regret_any": 0.0026552213821560144, "regret_bot": 0.002050717594102025, "value_dist": 0.8613955974578857, "value_other_env": 0.8795558214187622, "value_corner": 0.8341552019119263, "value_row": 0.8545425534248352, "value_any": 0.8795953989028931, "value_bot": 0.8565758466720581, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09580.png", "entropy": 0.13270995020866394} +{"ts": "2026-03-20T19:40:55.480473Z", "loop": 9590, "env_steps": 5892096000, "exact_value_avg": 0.8609535694122314, "regret_dist": 0.0026270770467817783, "regret_other_env": 0.0034667972940951586, "regret_corner": 0.0013674965593963861, "regret_row": 0.005850478075444698, "regret_any": 0.003464888781309128, "regret_bot": 0.0033357387874275446, "value_dist": 0.8609535694122314, "value_other_env": 0.8787480592727661, "value_corner": 0.8342618346214294, "value_row": 0.8527761697769165, "value_any": 0.8787857294082642, "value_bot": 0.8552908897399902, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09590.png", "entropy": 0.14101049304008484} +{"ts": "2026-03-20T19:41:04.061514Z", "loop": 9600, "env_steps": 5898240000, "exact_value_avg": 0.8565940856933594, "regret_dist": 0.006986659485846758, "regret_other_env": 0.011634395457804203, "regret_corner": 1.5055140465847217e-05, "regret_row": 0.02354724332690239, "regret_any": 0.011624998413026333, "regret_bot": 0.008455573581159115, "value_dist": 0.8565940856933594, "value_other_env": 0.8705804944038391, "value_corner": 0.8356143236160278, "value_row": 0.8350794911384583, "value_any": 0.8706256151199341, "value_bot": 0.8501710295677185, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09600.png", "entropy": 0.11013150215148926} +{"ts": "2026-03-20T19:41:12.639808Z", "loop": 9610, "env_steps": 5904384000, "exact_value_avg": 0.8633278012275696, "regret_dist": 0.00025293033104389906, "regret_other_env": 0.000413336354540661, "regret_corner": 1.232127397088334e-05, "regret_row": 0.0001172768315882422, "regret_any": 0.0004262753063812852, "regret_bot": 0.00018735992489382625, "value_dist": 0.8633278012275696, "value_other_env": 0.8818016052246094, "value_corner": 0.8356170058250427, "value_row": 0.858509361743927, "value_any": 0.8818243145942688, "value_bot": 0.8584392666816711, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09610.png", "entropy": 0.09295937418937683} +{"ts": "2026-03-20T19:41:21.220583Z", "loop": 9620, "env_steps": 5910528000, "exact_value_avg": 0.8626993894577026, "regret_dist": 0.0008812693995423615, "regret_other_env": 0.0014481948455795646, "regret_corner": 3.088116864091717e-05, "regret_row": 0.000509169592987746, "regret_any": 0.0016037153545767069, "regret_bot": 0.00015064938634168357, "value_dist": 0.8626993894577026, "value_other_env": 0.8807666897773743, "value_corner": 0.8355984091758728, "value_row": 0.8581174612045288, "value_any": 0.8806468844413757, "value_bot": 0.858475923538208, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09620.png", "entropy": 0.09395567327737808} +{"ts": "2026-03-20T19:41:29.798597Z", "loop": 9630, "env_steps": 5916672000, "exact_value_avg": 0.862926721572876, "regret_dist": 0.0006539209862239659, "regret_other_env": 0.0010700139682739973, "regret_corner": 2.978146221721545e-05, "regret_row": 0.0005189530784264207, "regret_any": 0.001148426323197782, "regret_bot": 0.0001390788092976436, "value_dist": 0.862926721572876, "value_other_env": 0.8811448216438293, "value_corner": 0.8355995416641235, "value_row": 0.8581076860427856, "value_any": 0.8811022043228149, "value_bot": 0.8584875464439392, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09630.png", "entropy": 0.0939594954252243} +{"ts": "2026-03-20T19:41:38.377917Z", "loop": 9640, "env_steps": 5922816000, "exact_value_avg": 0.8632152080535889, "regret_dist": 0.00036548220668919384, "regret_other_env": 0.000597217702306807, "regret_corner": 1.7878910512081347e-05, "regret_row": 0.0002242406626464799, "regret_any": 0.0006474422989413142, "regret_bot": 0.0007023660582490265, "value_dist": 0.8632152080535889, "value_other_env": 0.8816176652908325, "value_corner": 0.8356114625930786, "value_row": 0.8584023714065552, "value_any": 0.8816031217575073, "value_bot": 0.8579242825508118, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09640.png", "entropy": 0.08909190446138382} +{"ts": "2026-03-20T19:41:46.964983Z", "loop": 9650, "env_steps": 5928960000, "exact_value_avg": 0.8633078336715698, "regret_dist": 0.00027288973797112703, "regret_other_env": 0.00045122142182663083, "regret_corner": 5.3922340157441795e-06, "regret_row": 0.00026447075651958585, "regret_any": 0.0004868044634349644, "regret_bot": 0.0006444212631322443, "value_dist": 0.8633078336715698, "value_other_env": 0.8817636370658875, "value_corner": 0.8356239795684814, "value_row": 0.8583621382713318, "value_any": 0.8817638158798218, "value_bot": 0.8579822778701782, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09650.png", "entropy": 0.08506281673908234} +{"ts": "2026-03-20T19:41:55.550258Z", "loop": 9660, "env_steps": 5935104000, "exact_value_avg": 0.8591530323028564, "regret_dist": 0.0044276099652051926, "regret_other_env": 0.007379333488643169, "regret_corner": 2.4338564941217555e-08, "regret_row": 0.013073853217065334, "regret_any": 0.007374907378107309, "regret_bot": 0.00456165662035346, "value_dist": 0.8591530323028564, "value_other_env": 0.8748355507850647, "value_corner": 0.8356293439865112, "value_row": 0.8455527424812317, "value_any": 0.8748756647109985, "value_bot": 0.8540650010108948, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09660.png", "entropy": 0.09491055458784103} +{"ts": "2026-03-20T19:42:04.135900Z", "loop": 9670, "env_steps": 5941248000, "exact_value_avg": 0.863350510597229, "regret_dist": 0.0002301494823768735, "regret_other_env": 0.00038230823702178895, "regret_corner": 1.9113224425382214e-06, "regret_row": 0.00010365671914769337, "regret_any": 0.00038351016701199114, "regret_bot": 0.0004592652840074152, "value_dist": 0.863350510597229, "value_other_env": 0.8818325400352478, "value_corner": 0.8356274366378784, "value_row": 0.8585230708122253, "value_any": 0.8818671703338623, "value_bot": 0.8581674098968506, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09670.png", "entropy": 0.09056522697210312} +{"ts": "2026-03-20T19:42:12.722427Z", "loop": 9680, "env_steps": 5947392000, "exact_value_avg": 0.8571360111236572, "regret_dist": 0.006444703321903944, "regret_other_env": 0.010627523064613342, "regret_corner": 0.000170472267200239, "regret_row": 0.014958512969315052, "regret_any": 0.011143420822918415, "regret_bot": 0.00011510058538988233, "value_dist": 0.8571360111236572, "value_other_env": 0.871587336063385, "value_corner": 0.8354588150978088, "value_row": 0.8436680436134338, "value_any": 0.8711072206497192, "value_bot": 0.8585116267204285, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09680.png", "entropy": 0.09154503047466278} +{"ts": "2026-03-20T19:42:21.307597Z", "loop": 9690, "env_steps": 5953536000, "exact_value_avg": 0.8634530901908875, "regret_dist": 0.00012759647506754845, "regret_other_env": 0.000210805403185077, "regret_corner": 2.7830403723783093e-06, "regret_row": 6.966301589272916e-05, "regret_any": 0.00021360686514526606, "regret_bot": 0.00024190291878767312, "value_dist": 0.8634530901908875, "value_other_env": 0.8820040822029114, "value_corner": 0.8356265425682068, "value_row": 0.8585569262504578, "value_any": 0.8820369839668274, "value_bot": 0.8583847284317017, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09690.png", "entropy": 0.090665303170681} +{"ts": "2026-03-20T19:42:29.893626Z", "loop": 9700, "env_steps": 5959680000, "exact_value_avg": 0.8630620241165161, "regret_dist": 0.0005186601192690432, "regret_other_env": 0.000863485096488148, "regret_corner": 1.4225643099052832e-06, "regret_row": 0.0012301020324230194, "regret_any": 0.0008714410942047834, "regret_bot": 0.001095903804525733, "value_dist": 0.8630620241165161, "value_other_env": 0.8813514113426208, "value_corner": 0.8356279134750366, "value_row": 0.8573964834213257, "value_any": 0.8813791871070862, "value_bot": 0.8575307726860046, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09700.png", "entropy": 0.0996234342455864} +{"ts": "2026-03-20T19:42:38.470481Z", "loop": 9710, "env_steps": 5965824000, "exact_value_avg": 0.8625146150588989, "regret_dist": 0.0010660701664164662, "regret_other_env": 0.0017755937296897173, "regret_corner": 1.7846624587036786e-06, "regret_row": 0.0033756711054593325, "regret_any": 0.0017958695534616709, "regret_bot": 0.002369345398619771, "value_dist": 0.8625146150588989, "value_other_env": 0.8804393410682678, "value_corner": 0.835627555847168, "value_row": 0.8552510142326355, "value_any": 0.8804547190666199, "value_bot": 0.8562572598457336, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09710.png", "entropy": 0.1011757180094719} +{"ts": "2026-03-20T19:42:47.050086Z", "loop": 9720, "env_steps": 5971968000, "exact_value_avg": 0.8632380366325378, "regret_dist": 0.0003426560142543167, "regret_other_env": 0.0005644749035127461, "regret_corner": 9.927651262842119e-06, "regret_row": 0.00010566927812760696, "regret_any": 0.0005882735713385046, "regret_bot": 0.0017239487497135997, "value_dist": 0.8632380366325378, "value_other_env": 0.881650447845459, "value_corner": 0.8356193900108337, "value_row": 0.8585209250450134, "value_any": 0.8816623091697693, "value_bot": 0.8569026589393616, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09720.png", "entropy": 0.09458263963460922} +{"ts": "2026-03-20T19:42:55.640185Z", "loop": 9730, "env_steps": 5978112000, "exact_value_avg": 0.8613604307174683, "regret_dist": 0.0022202967666089535, "regret_other_env": 0.003672728780657053, "regret_corner": 4.1648749174783006e-05, "regret_row": 0.0016251270426437259, "regret_any": 0.0037032715044915676, "regret_bot": 0.0039581661112606525, "value_dist": 0.8613604307174683, "value_other_env": 0.8785421848297119, "value_corner": 0.8355876803398132, "value_row": 0.857001543045044, "value_any": 0.8785474300384521, "value_bot": 0.8546684384346008, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09730.png", "entropy": 0.09150254726409912} +{"ts": "2026-03-20T19:43:04.220019Z", "loop": 9740, "env_steps": 5984256000, "exact_value_avg": 0.8616710901260376, "regret_dist": 0.0019096375908702612, "regret_other_env": 0.0030706492252647877, "regret_corner": 0.00016811987734399736, "regret_row": 0.0010470100678503513, "regret_any": 0.0031049486715346575, "regret_bot": 0.0018721000524237752, "value_dist": 0.8616710901260376, "value_other_env": 0.8791443109512329, "value_corner": 0.8354611992835999, "value_row": 0.8575795888900757, "value_any": 0.879145622253418, "value_bot": 0.8567545413970947, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09740.png", "entropy": 0.09649215638637543} +{"ts": "2026-03-20T19:43:12.803283Z", "loop": 9750, "env_steps": 5990400000, "exact_value_avg": 0.8634097576141357, "regret_dist": 0.0001709006610326469, "regret_other_env": 0.00025338734849356115, "regret_corner": 4.71706225653179e-05, "regret_row": 0.0001499902573414147, "regret_any": 0.0002538996050134301, "regret_bot": 0.0002020722022280097, "value_dist": 0.8634097576141357, "value_other_env": 0.881961464881897, "value_corner": 0.8355821371078491, "value_row": 0.8584766387939453, "value_any": 0.8819966912269592, "value_bot": 0.8584246039390564, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09750.png", "entropy": 0.1035628616809845} +{"ts": "2026-03-20T19:43:21.384274Z", "loop": 9760, "env_steps": 5996544000, "exact_value_avg": 0.8619967699050903, "regret_dist": 0.0015838874969631433, "regret_other_env": 0.0024721568915992975, "regret_corner": 0.00025148343411274254, "regret_row": 0.0034188551362603903, "regret_any": 0.002485041506588459, "regret_bot": 0.0006184555822983384, "value_dist": 0.8619967699050903, "value_other_env": 0.8797426819801331, "value_corner": 0.8353778123855591, "value_row": 0.8552077412605286, "value_any": 0.8797655701637268, "value_bot": 0.8580081462860107, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09760.png", "entropy": 0.11664501577615738} +{"ts": "2026-03-20T19:43:29.966644Z", "loop": 9770, "env_steps": 6002688000, "exact_value_avg": 0.8629759550094604, "regret_dist": 0.000604763743467629, "regret_other_env": 0.000899441190995276, "regret_corner": 0.00016274751396849751, "regret_row": 0.000879519444424659, "regret_any": 0.0008981465944088995, "regret_bot": 0.0009884285973384976, "value_dist": 0.8629759550094604, "value_other_env": 0.8813154697418213, "value_corner": 0.8354665637016296, "value_row": 0.8577471971511841, "value_any": 0.8813524842262268, "value_bot": 0.8576382398605347, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09770.png", "entropy": 0.11792155355215073} +{"ts": "2026-03-20T19:43:38.549772Z", "loop": 9780, "env_steps": 6008832000, "exact_value_avg": 0.8622152805328369, "regret_dist": 0.001365370349958539, "regret_other_env": 0.0018195770680904388, "regret_corner": 0.0006840602145530283, "regret_row": 0.001550352550111711, "regret_any": 0.001816897070966661, "regret_bot": 0.0022701947018504143, "value_dist": 0.8622152805328369, "value_other_env": 0.8803952932357788, "value_corner": 0.8349452018737793, "value_row": 0.8570762872695923, "value_any": 0.8804337382316589, "value_bot": 0.8563564419746399, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09780.png", "entropy": 0.12862443923950195} +{"ts": "2026-03-20T19:43:47.131752Z", "loop": 9790, "env_steps": 6014976000, "exact_value_avg": 0.8607295751571655, "regret_dist": 0.0028510887641459703, "regret_other_env": 0.0040742177516222, "regret_corner": 0.0010163948172703385, "regret_row": 0.003576848655939102, "regret_any": 0.004068275913596153, "regret_bot": 0.004538416862487793, "value_dist": 0.8607295751571655, "value_other_env": 0.8781406283378601, "value_corner": 0.8346129655838013, "value_row": 0.8550497889518738, "value_any": 0.8781823515892029, "value_bot": 0.8540882468223572, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09790.png", "entropy": 0.1350104957818985} +{"ts": "2026-03-20T19:43:55.712746Z", "loop": 9800, "env_steps": 6021120000, "exact_value_avg": 0.8629707098007202, "regret_dist": 0.000610023271292448, "regret_other_env": 0.0009669282590039074, "regret_corner": 7.466574606951326e-05, "regret_row": 0.000519996858201921, "regret_any": 0.0009655245812609792, "regret_bot": 0.0013635053765028715, "value_dist": 0.8629707098007202, "value_other_env": 0.8812479376792908, "value_corner": 0.8355546593666077, "value_row": 0.8581066727638245, "value_any": 0.8812850713729858, "value_bot": 0.8572631478309631, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09800.png", "entropy": 0.10985246300697327} +{"ts": "2026-03-20T19:44:04.293885Z", "loop": 9810, "env_steps": 6027264000, "exact_value_avg": 0.861821174621582, "regret_dist": 0.0017595372628420591, "regret_other_env": 0.0028555537573993206, "regret_corner": 0.00011551231727935374, "regret_row": 0.003840142162516713, "regret_any": 0.0029245319310575724, "regret_bot": 0.00025715361698530614, "value_dist": 0.861821174621582, "value_other_env": 0.8793593049049377, "value_corner": 0.8355138301849365, "value_row": 0.8547865152359009, "value_any": 0.8793261051177979, "value_bot": 0.8583694696426392, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09810.png", "entropy": 0.1070479303598404} +{"ts": "2026-03-20T19:44:12.882865Z", "loop": 9820, "env_steps": 6033408000, "exact_value_avg": 0.8630297183990479, "regret_dist": 0.0005510188639163971, "regret_other_env": 0.0008052474004216492, "regret_corner": 0.0001696760591585189, "regret_row": 0.0005771151045337319, "regret_any": 0.0008043046691454947, "regret_bot": 0.0012650263961404562, "value_dist": 0.8630297183990479, "value_other_env": 0.8814097046852112, "value_corner": 0.8354596495628357, "value_row": 0.8580495715141296, "value_any": 0.8814463019371033, "value_bot": 0.8573615550994873, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09820.png", "entropy": 0.11211356520652771} +{"ts": "2026-03-20T19:44:21.467584Z", "loop": 9830, "env_steps": 6039552000, "exact_value_avg": 0.8632957935333252, "regret_dist": 0.00028482344350777566, "regret_other_env": 0.000471718842163682, "regret_corner": 4.4802827687817626e-06, "regret_row": 0.00016384215268772095, "regret_any": 0.0004720987635664642, "regret_bot": 0.0011223293840885162, "value_dist": 0.8632957935333252, "value_other_env": 0.8817431330680847, "value_corner": 0.8356248736381531, "value_row": 0.8584628701210022, "value_any": 0.8817784786224365, "value_bot": 0.8575043082237244, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09830.png", "entropy": 0.09773390740156174} +{"ts": "2026-03-20T19:44:30.055727Z", "loop": 9840, "env_steps": 6045696000, "exact_value_avg": 0.863314688205719, "regret_dist": 0.00026598290423862636, "regret_other_env": 0.00043847388587892056, "regret_corner": 7.246434961416526e-06, "regret_row": 0.0014747466193512082, "regret_any": 0.00043850656948052347, "regret_bot": 0.0005628688377328217, "value_dist": 0.863314688205719, "value_other_env": 0.8817763924598694, "value_corner": 0.8356220722198486, "value_row": 0.8571518063545227, "value_any": 0.8818120956420898, "value_bot": 0.858063817024231, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09840.png", "entropy": 0.09613564610481262} +{"ts": "2026-03-20T19:44:38.642761Z", "loop": 9850, "env_steps": 6051840000, "exact_value_avg": 0.8626794815063477, "regret_dist": 0.0009011747315526009, "regret_other_env": 0.0014975735684856772, "regret_corner": 6.576379291800549e-06, "regret_row": 0.007628103252500296, "regret_any": 0.0015129754319787025, "regret_bot": 0.0010704181622713804, "value_dist": 0.8626794815063477, "value_other_env": 0.8807173371315002, "value_corner": 0.8356227278709412, "value_row": 0.8509985208511353, "value_any": 0.8807376623153687, "value_bot": 0.8575562238693237, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09850.png", "entropy": 0.09507226198911667} +{"ts": "2026-03-20T19:44:47.224747Z", "loop": 9860, "env_steps": 6057984000, "exact_value_avg": 0.8627705574035645, "regret_dist": 0.0008100611157715321, "regret_other_env": 0.0013447694946080446, "regret_corner": 7.998447472346015e-06, "regret_row": 0.0038084397092461586, "regret_any": 0.001362204784527421, "regret_bot": 0.00118452578317374, "value_dist": 0.8627705574035645, "value_other_env": 0.8808701038360596, "value_corner": 0.8356212973594666, "value_row": 0.8548182249069214, "value_any": 0.8808884024620056, "value_bot": 0.8574422001838684, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09860.png", "entropy": 0.09650270640850067} +{"ts": "2026-03-20T19:44:55.800147Z", "loop": 9870, "env_steps": 6064128000, "exact_value_avg": 0.8632981777191162, "regret_dist": 0.00028253308846615255, "regret_other_env": 0.0004650061600841582, "regret_corner": 8.823474672681186e-06, "regret_row": 0.00014097920211497694, "regret_any": 0.0004770245577674359, "regret_bot": 0.0014113461365923285, "value_dist": 0.8632981777191162, "value_other_env": 0.8817498683929443, "value_corner": 0.8356205224990845, "value_row": 0.8584856390953064, "value_any": 0.8817735314369202, "value_bot": 0.8572152256965637, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09870.png", "entropy": 0.09846760332584381} +{"ts": "2026-03-20T19:45:04.384604Z", "loop": 9880, "env_steps": 6070272000, "exact_value_avg": 0.8633788824081421, "regret_dist": 0.00020184801542200148, "regret_other_env": 0.0003347831661812961, "regret_corner": 2.4452806428598706e-06, "regret_row": 0.00014331065176520497, "regret_any": 0.00033443071879446507, "regret_bot": 0.0006933026015758514, "value_dist": 0.8633788824081421, "value_other_env": 0.8818801045417786, "value_corner": 0.8356269001960754, "value_row": 0.8584833145141602, "value_any": 0.8819161653518677, "value_bot": 0.8579333424568176, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09880.png", "entropy": 0.09766834229230881} +{"ts": "2026-03-20T19:45:12.968783Z", "loop": 9890, "env_steps": 6076416000, "exact_value_avg": 0.8631715774536133, "regret_dist": 0.00040904872003011405, "regret_other_env": 0.0006800458068028092, "regret_corner": 2.553065769461682e-06, "regret_row": 0.0003512385883368552, "regret_any": 0.0006793487700633705, "regret_bot": 0.001598239061422646, "value_dist": 0.8631715774536133, "value_other_env": 0.8815348148345947, "value_corner": 0.8356267809867859, "value_row": 0.8582754135131836, "value_any": 0.8815712332725525, "value_bot": 0.8570284247398376, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09890.png", "entropy": 0.10203296691179276} +{"ts": "2026-03-20T19:45:21.552457Z", "loop": 9900, "env_steps": 6082560000, "exact_value_avg": 0.8625611066818237, "regret_dist": 0.0010195383802056313, "regret_other_env": 0.0016985074616968632, "regret_corner": 1.0848045803868445e-06, "regret_row": 0.00235744914971292, "regret_any": 0.001699831453152001, "regret_bot": 0.003138108178973198, "value_dist": 0.8625611066818237, "value_other_env": 0.8805163502693176, "value_corner": 0.8356282114982605, "value_row": 0.8562691807746887, "value_any": 0.8805506825447083, "value_bot": 0.8554885387420654, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09900.png", "entropy": 0.09986046701669693} +{"ts": "2026-03-20T19:45:30.135178Z", "loop": 9910, "env_steps": 6088704000, "exact_value_avg": 0.8613201379776001, "regret_dist": 0.0022606514394283295, "regret_other_env": 0.0037659055087715387, "regret_corner": 2.7701260023604846e-06, "regret_row": 0.0024210168048739433, "regret_any": 0.0037792008370161057, "regret_bot": 0.008184701204299927, "value_dist": 0.8613201379776001, "value_other_env": 0.878449022769928, "value_corner": 0.8356266021728516, "value_row": 0.8562055826187134, "value_any": 0.8784713745117188, "value_bot": 0.8504419326782227, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09910.png", "entropy": 0.10083048045635223} +{"ts": "2026-03-20T19:45:38.719170Z", "loop": 9920, "env_steps": 6094848000, "exact_value_avg": 0.8632078170776367, "regret_dist": 0.000372882786905393, "regret_other_env": 0.0006188218831084669, "regret_corner": 3.97413987229811e-06, "regret_row": 0.000127998529933393, "regret_any": 0.0006183049408718944, "regret_bot": 0.0019671765621751547, "value_dist": 0.8632078170776367, "value_other_env": 0.881596028804779, "value_corner": 0.8356253504753113, "value_row": 0.8584986329078674, "value_any": 0.8816322684288025, "value_bot": 0.856659471988678, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09920.png", "entropy": 0.09623172134160995} +{"ts": "2026-03-20T19:45:47.314227Z", "loop": 9930, "env_steps": 6100992000, "exact_value_avg": 0.8633867502212524, "regret_dist": 0.00019393432012293488, "regret_other_env": 0.00030878992401994765, "regret_corner": 2.165089244954288e-05, "regret_row": 6.646125257248059e-05, "regret_any": 0.00030891166534274817, "regret_bot": 0.0007268913905136287, "value_dist": 0.8633867502212524, "value_other_env": 0.8819060921669006, "value_corner": 0.835607647895813, "value_row": 0.8585601449012756, "value_any": 0.8819416761398315, "value_bot": 0.8578997850418091, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09930.png", "entropy": 0.0911126434803009} +{"ts": "2026-03-20T19:45:55.905545Z", "loop": 9940, "env_steps": 6107136000, "exact_value_avg": 0.8633511662483215, "regret_dist": 0.00022953690495342016, "regret_other_env": 0.0003795150259975344, "regret_corner": 4.5696897359448485e-06, "regret_row": 5.9411966503830627e-05, "regret_any": 0.0004027343529742211, "regret_bot": 0.0012629585107788444, "value_dist": 0.8633511662483215, "value_other_env": 0.881835401058197, "value_corner": 0.8356247544288635, "value_row": 0.8585672974586487, "value_any": 0.8818479180335999, "value_bot": 0.8573637008666992, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09940.png", "entropy": 0.0846240222454071} +{"ts": "2026-03-20T19:46:04.491537Z", "loop": 9950, "env_steps": 6113280000, "exact_value_avg": 0.8629185557365417, "regret_dist": 0.0006621634238399565, "regret_other_env": 0.001102503971196711, "regret_corner": 1.6525389128219103e-06, "regret_row": 0.00011630139488261193, "regret_any": 0.0011255198623985052, "regret_bot": 0.0022971094585955143, "value_dist": 0.8629185557365417, "value_other_env": 0.8811123371124268, "value_corner": 0.8356277346611023, "value_row": 0.8585103154182434, "value_any": 0.8811250925064087, "value_bot": 0.8563295006752014, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09950.png", "entropy": 0.08658959716558456} +{"ts": "2026-03-20T19:46:13.080682Z", "loop": 9960, "env_steps": 6119424000, "exact_value_avg": 0.8613994121551514, "regret_dist": 0.0021812180057168007, "regret_other_env": 0.0036345876287668943, "regret_corner": 1.1637807801889721e-06, "regret_row": 0.000325290224282071, "regret_any": 0.0036544527392834425, "regret_bot": 0.006098180543631315, "value_dist": 0.8613994121551514, "value_other_env": 0.8785802721977234, "value_corner": 0.8356281518936157, "value_row": 0.8583012819290161, "value_any": 0.8785961866378784, "value_bot": 0.8525285124778748, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09960.png", "entropy": 0.08644574135541916} +{"ts": "2026-03-20T19:46:21.673451Z", "loop": 9970, "env_steps": 6125568000, "exact_value_avg": 0.8611106872558594, "regret_dist": 0.0024700486101210117, "regret_other_env": 0.004103812389075756, "regret_corner": 1.9402803445700556e-05, "regret_row": 0.0022575268521904945, "regret_any": 0.004130704794079065, "regret_bot": 0.004383407533168793, "value_dist": 0.8611106872558594, "value_other_env": 0.8781110644340515, "value_corner": 0.8356099128723145, "value_row": 0.8563691973686218, "value_any": 0.878119945526123, "value_bot": 0.8542432188987732, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09970.png", "entropy": 0.0862584188580513} +{"ts": "2026-03-20T19:46:30.253871Z", "loop": 9980, "env_steps": 6131712000, "exact_value_avg": 0.8619934320449829, "regret_dist": 0.0015872552758082747, "regret_other_env": 0.0025814080145210028, "regret_corner": 9.602606587577611e-05, "regret_row": 0.006367946043610573, "regret_any": 0.002605957444757223, "regret_bot": 0.0016044307267293334, "value_dist": 0.8619934320449829, "value_other_env": 0.8796334266662598, "value_corner": 0.8355333209037781, "value_row": 0.8522586226463318, "value_any": 0.8796446323394775, "value_bot": 0.8570221662521362, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09980.png", "entropy": 0.08866303414106369} +{"ts": "2026-03-20T19:46:38.834708Z", "loop": 9990, "env_steps": 6137856000, "exact_value_avg": 0.8626919388771057, "regret_dist": 0.0008887166623026133, "regret_other_env": 0.0014755012234672904, "regret_corner": 8.539856025890913e-06, "regret_row": 0.0006146934465505183, "regret_any": 0.0014983222354203463, "regret_bot": 0.0042135147377848625, "value_dist": 0.8626919388771057, "value_other_env": 0.8807393312454224, "value_corner": 0.8356207609176636, "value_row": 0.8580119609832764, "value_any": 0.8807523250579834, "value_bot": 0.8544130921363831, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_09990.png", "entropy": 0.09328537434339523} +{"ts": "2026-03-20T19:46:47.419305Z", "loop": 10000, "env_steps": 6144000000, "exact_value_avg": 0.8629458546638489, "regret_dist": 0.0006348696770146489, "regret_other_env": 0.001041723182424903, "regret_corner": 2.4589400709373876e-05, "regret_row": 0.00017338372708763927, "regret_any": 0.0010619621025398374, "regret_bot": 0.00403281394392252, "value_dist": 0.8629458546638489, "value_other_env": 0.8811731934547424, "value_corner": 0.8356047868728638, "value_row": 0.8584532737731934, "value_any": 0.881188690662384, "value_bot": 0.854593813419342, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10000.png", "entropy": 0.09826561063528061} +{"ts": "2026-03-20T19:46:55.997987Z", "loop": 10010, "env_steps": 6150144000, "exact_value_avg": 0.8631359338760376, "regret_dist": 0.0004447404353413731, "regret_other_env": 0.0007128125289455056, "regret_corner": 4.263222581357695e-05, "regret_row": 0.00024107635545078665, "regret_any": 0.0007119453512132168, "regret_bot": 0.0012790001928806305, "value_dist": 0.8631359338760376, "value_other_env": 0.881502091884613, "value_corner": 0.8355867266654968, "value_row": 0.8583855628967285, "value_any": 0.8815386891365051, "value_bot": 0.8573476672172546, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10010.png", "entropy": 0.10241526365280151} +{"ts": "2026-03-20T19:47:04.583775Z", "loop": 10020, "env_steps": 6156288000, "exact_value_avg": 0.8632605075836182, "regret_dist": 0.00032022499362938106, "regret_other_env": 0.0005273362039588392, "regret_corner": 9.558101737638935e-06, "regret_row": 0.00017239247972611338, "regret_any": 0.0005265700165182352, "regret_bot": 0.0006702078389935195, "value_dist": 0.8632605075836182, "value_other_env": 0.8816875219345093, "value_corner": 0.8356198072433472, "value_row": 0.8584542870521545, "value_any": 0.8817240595817566, "value_bot": 0.8579564690589905, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10020.png", "entropy": 0.09615527838468552} +{"ts": "2026-03-20T19:47:13.165344Z", "loop": 10030, "env_steps": 6162432000, "exact_value_avg": 0.8627166152000427, "regret_dist": 0.0008641103631816804, "regret_other_env": 0.0014389136340469122, "regret_corner": 1.9053619553233148e-06, "regret_row": 0.0006284384871833026, "regret_any": 0.0014367818366736174, "regret_bot": 0.0036159860901534557, "value_dist": 0.8627166152000427, "value_other_env": 0.8807759881019592, "value_corner": 0.8356274366378784, "value_row": 0.8579981923103333, "value_any": 0.8808137774467468, "value_bot": 0.8550105690956116, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10030.png", "entropy": 0.09462343156337738} +{"ts": "2026-03-20T19:47:21.751501Z", "loop": 10040, "env_steps": 6168576000, "exact_value_avg": 0.863178014755249, "regret_dist": 0.0004027355753351003, "regret_other_env": 0.0006710457964800298, "regret_corner": 2.7020774950869964e-07, "regret_row": 0.00040751846972852945, "regret_any": 0.0006702083628624678, "regret_bot": 0.0004360124294180423, "value_dist": 0.863178014755249, "value_other_env": 0.8815438747406006, "value_corner": 0.8356290459632874, "value_row": 0.8582192063331604, "value_any": 0.8815804123878479, "value_bot": 0.8581905364990234, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10040.png", "entropy": 0.08713506907224655} +{"ts": "2026-03-20T19:47:30.329794Z", "loop": 10050, "env_steps": 6174720000, "exact_value_avg": 0.8604691028594971, "regret_dist": 0.003111559199169278, "regret_other_env": 0.005181734915822744, "regret_corner": 6.295244020293467e-06, "regret_row": 0.0016990939620882273, "regret_any": 0.00568810198456049, "regret_bot": 0.0003711114695761353, "value_dist": 0.8604691028594971, "value_other_env": 0.8770331144332886, "value_corner": 0.835623025894165, "value_row": 0.8569275736808777, "value_any": 0.8765625357627869, "value_bot": 0.8582555055618286, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10050.png", "entropy": 0.08325370401144028} +{"ts": "2026-03-20T19:47:38.908123Z", "loop": 10060, "env_steps": 6180864000, "exact_value_avg": 0.8631702661514282, "regret_dist": 0.0004103656974621117, "regret_other_env": 0.0006794751388952136, "regret_corner": 6.70154940962675e-06, "regret_row": 0.0002644885971676558, "regret_any": 0.0006956882425583899, "regret_bot": 9.54496135818772e-05, "value_dist": 0.8631702661514282, "value_other_env": 0.8815353512763977, "value_corner": 0.8356225490570068, "value_row": 0.8583621382713318, "value_any": 0.881554901599884, "value_bot": 0.8585312366485596, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10060.png", "entropy": 0.08411670476198196} +{"ts": "2026-03-20T19:47:47.489466Z", "loop": 10070, "env_steps": 6187008000, "exact_value_avg": 0.862934947013855, "regret_dist": 0.0006457027047872543, "regret_other_env": 0.0010713547235354781, "regret_corner": 7.224579803732922e-06, "regret_row": 0.0009659837232902646, "regret_any": 0.0010981386294588447, "regret_bot": 0.000575327081605792, "value_dist": 0.862934947013855, "value_other_env": 0.8811435103416443, "value_corner": 0.8356220722198486, "value_row": 0.8576606512069702, "value_any": 0.8811524510383606, "value_bot": 0.8580513596534729, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10070.png", "entropy": 0.08287958800792694} +{"ts": "2026-03-20T19:47:56.072577Z", "loop": 10080, "env_steps": 6193152000, "exact_value_avg": 0.862564206123352, "regret_dist": 0.0010164844570681453, "regret_other_env": 0.0016917074099183083, "regret_corner": 3.6497913242783397e-06, "regret_row": 0.0015055702533572912, "regret_any": 0.0017134214285761118, "regret_bot": 0.0020531932823359966, "value_dist": 0.862564206123352, "value_other_env": 0.8805232048034668, "value_corner": 0.8356257081031799, "value_row": 0.8571211099624634, "value_any": 0.8805372714996338, "value_bot": 0.8565734624862671, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10080.png", "entropy": 0.0818612277507782} +{"ts": "2026-03-20T19:48:04.654920Z", "loop": 10090, "env_steps": 6199296000, "exact_value_avg": 0.861770749092102, "regret_dist": 0.001809937646612525, "regret_other_env": 0.003014163812622428, "regret_corner": 3.598133844207041e-06, "regret_row": 0.0021065862383693457, "regret_any": 0.003036537440493703, "regret_bot": 0.004563326947391033, "value_dist": 0.861770749092102, "value_other_env": 0.8792007565498352, "value_corner": 0.8356257677078247, "value_row": 0.8565199971199036, "value_any": 0.8792140483856201, "value_bot": 0.8540633320808411, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10090.png", "entropy": 0.08306542038917542} +{"ts": "2026-03-20T19:48:13.233560Z", "loop": 10100, "env_steps": 6205440000, "exact_value_avg": 0.8623547554016113, "regret_dist": 0.0012259014183655381, "regret_other_env": 0.002039283746853471, "regret_corner": 5.8278442338632885e-06, "regret_row": 0.0017550538759678602, "regret_any": 0.0020603681914508343, "regret_bot": 0.0026309932582080364, "value_dist": 0.8623547554016113, "value_other_env": 0.8801755905151367, "value_corner": 0.8356234431266785, "value_row": 0.8568716049194336, "value_any": 0.8801902532577515, "value_bot": 0.8559956550598145, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10100.png", "entropy": 0.08334904909133911} +{"ts": "2026-03-20T19:48:21.816926Z", "loop": 10110, "env_steps": 6211584000, "exact_value_avg": 0.8625220060348511, "regret_dist": 0.0010586370481178164, "regret_other_env": 0.0017602297011762857, "regret_corner": 6.248057161428733e-06, "regret_row": 0.0008476332877762616, "regret_any": 0.001783397514373064, "regret_bot": 0.002739137504249811, "value_dist": 0.8625220060348511, "value_other_env": 0.8804545998573303, "value_corner": 0.8356230854988098, "value_row": 0.8577789664268494, "value_any": 0.8804671764373779, "value_bot": 0.8558874726295471, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10110.png", "entropy": 0.08304562419652939} +{"ts": "2026-03-20T19:48:30.403612Z", "loop": 10120, "env_steps": 6217728000, "exact_value_avg": 0.8634293079376221, "regret_dist": 0.00015135729336179793, "regret_other_env": 0.00024830506299622357, "regret_corner": 5.9356293604651e-06, "regret_row": 0.0001311474188696593, "regret_any": 0.00026398501358926296, "regret_bot": 0.0006758866948075593, "value_dist": 0.8634293079376221, "value_other_env": 0.8819665908813477, "value_corner": 0.8356233239173889, "value_row": 0.8584955334663391, "value_any": 0.8819865584373474, "value_bot": 0.857950747013092, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10120.png", "entropy": 0.08416727930307388} +{"ts": "2026-03-20T19:48:38.990076Z", "loop": 10130, "env_steps": 6223872000, "exact_value_avg": 0.8632428646087646, "regret_dist": 0.00033788805012591183, "regret_other_env": 0.0005406754789873958, "regret_corner": 3.370692502357997e-05, "regret_row": 0.0002904070133809, "regret_any": 0.0005460406537167728, "regret_bot": 0.0003695983614306897, "value_dist": 0.8632428646087646, "value_other_env": 0.8816742300987244, "value_corner": 0.8355956077575684, "value_row": 0.8583361506462097, "value_any": 0.881704568862915, "value_bot": 0.858256995677948, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10130.png", "entropy": 0.08731421828269958} +{"ts": "2026-03-20T19:48:47.572678Z", "loop": 10140, "env_steps": 6230016000, "exact_value_avg": 0.8626438975334167, "regret_dist": 0.0009368144674226642, "regret_other_env": 0.001533394563011825, "regret_corner": 4.1944287659134716e-05, "regret_row": 0.0021671089343726635, "regret_any": 0.0015349442837759852, "regret_bot": 0.0005682585760951042, "value_dist": 0.8626438975334167, "value_other_env": 0.8806815147399902, "value_corner": 0.8355873823165894, "value_row": 0.8564594984054565, "value_any": 0.8807156682014465, "value_bot": 0.8580583930015564, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10140.png", "entropy": 0.09424562752246857} +{"ts": "2026-03-20T19:48:56.150977Z", "loop": 10150, "env_steps": 6236160000, "exact_value_avg": 0.8628600835800171, "regret_dist": 0.000720590993296355, "regret_other_env": 0.0011992402141913772, "regret_corner": 2.617140808069962e-06, "regret_row": 0.0007304665050469339, "regret_any": 0.0011975894449278712, "regret_bot": 0.0021060523577034473, "value_dist": 0.8628600835800171, "value_other_env": 0.8810156583786011, "value_corner": 0.8356267809867859, "value_row": 0.8578961491584778, "value_any": 0.8810530304908752, "value_bot": 0.8565205335617065, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10150.png", "entropy": 0.0972818061709404} +{"ts": "2026-03-20T19:49:04.728029Z", "loop": 10160, "env_steps": 6242304000, "exact_value_avg": 0.8618619441986084, "regret_dist": 0.0017187456833198667, "regret_other_env": 0.0028624290134757757, "regret_corner": 3.220637836420792e-06, "regret_row": 0.0013193900231271982, "regret_any": 0.002858724445104599, "regret_bot": 0.007878206670284271, "value_dist": 0.8618619441986084, "value_other_env": 0.8793524503707886, "value_corner": 0.8356261253356934, "value_row": 0.8573071956634521, "value_any": 0.8793918490409851, "value_bot": 0.8507484793663025, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10160.png", "entropy": 0.0954667255282402} +{"ts": "2026-03-20T19:49:13.310419Z", "loop": 10170, "env_steps": 6248448000, "exact_value_avg": 0.8633646368980408, "regret_dist": 0.0002160603180527687, "regret_other_env": 0.0003583474608603865, "regret_corner": 2.6295583666069433e-06, "regret_row": 0.0003841238794848323, "regret_any": 0.0003578952746465802, "regret_bot": 0.0003459956496953964, "value_dist": 0.8633646368980408, "value_other_env": 0.8818565011024475, "value_corner": 0.8356267213821411, "value_row": 0.8582425117492676, "value_any": 0.881892740726471, "value_bot": 0.8582806587219238, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10170.png", "entropy": 0.09075085818767548} +{"ts": "2026-03-20T19:49:21.893270Z", "loop": 10180, "env_steps": 6254592000, "exact_value_avg": 0.8633824586868286, "regret_dist": 0.0001982895191758871, "regret_other_env": 0.000326815847074613, "regret_corner": 5.50001868759864e-06, "regret_row": 0.0006250434671528637, "regret_any": 0.0003275215858593583, "regret_bot": 0.00024389877216890454, "value_dist": 0.8633824586868286, "value_other_env": 0.8818880915641785, "value_corner": 0.8356238603591919, "value_row": 0.8580015897750854, "value_any": 0.8819231390953064, "value_bot": 0.8583827018737793, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10180.png", "entropy": 0.0885995626449585} +{"ts": "2026-03-20T19:49:30.481820Z", "loop": 10190, "env_steps": 6260736000, "exact_value_avg": 0.8632732629776001, "regret_dist": 0.00030745600815862417, "regret_other_env": 0.0005065433797426522, "regret_corner": 8.82496442500269e-06, "regret_row": 0.0012732511386275291, "regret_any": 0.0005199301522225142, "regret_bot": 0.0006490522646345198, "value_dist": 0.8632732629776001, "value_other_env": 0.8817083239555359, "value_corner": 0.8356205224990845, "value_row": 0.8573533892631531, "value_any": 0.8817307353019714, "value_bot": 0.857977569103241, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10190.png", "entropy": 0.08914186805486679} +{"ts": "2026-03-20T19:49:39.074856Z", "loop": 10200, "env_steps": 6266880000, "exact_value_avg": 0.8633437752723694, "regret_dist": 0.0002369429130339995, "regret_other_env": 0.0003925484779756516, "regret_corner": 3.5345556170796044e-06, "regret_row": 0.0004726007755380124, "regret_any": 0.00041431954014115036, "regret_bot": 0.001074251369573176, "value_dist": 0.8633437752723694, "value_other_env": 0.8818223476409912, "value_corner": 0.8356258273124695, "value_row": 0.8581540584564209, "value_any": 0.8818362951278687, "value_bot": 0.8575523495674133, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10200.png", "entropy": 0.08973361551761627} +{"ts": "2026-03-20T19:49:47.662241Z", "loop": 10210, "env_steps": 6273024000, "exact_value_avg": 0.8633357286453247, "regret_dist": 0.00024496877449564636, "regret_other_env": 0.0004073067393619567, "regret_corner": 1.4618040040659253e-06, "regret_row": 0.00019620213424786925, "regret_any": 0.0004072651790920645, "regret_bot": 0.0007006560917943716, "value_dist": 0.8633357286453247, "value_other_env": 0.8818076252937317, "value_corner": 0.8356277942657471, "value_row": 0.8584303855895996, "value_any": 0.8818433880805969, "value_bot": 0.8579259514808655, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10210.png", "entropy": 0.09079072624444962} +{"ts": "2026-03-20T19:49:56.246077Z", "loop": 10220, "env_steps": 6279168000, "exact_value_avg": 0.860770583152771, "regret_dist": 0.0028102046344429255, "regret_other_env": 0.004683376289904118, "regret_corner": 4.470348642371391e-07, "regret_row": 0.002894788281992078, "regret_any": 0.004677133169025183, "regret_bot": 0.016343124210834503, "value_dist": 0.860770583152771, "value_other_env": 0.8775315880775452, "value_corner": 0.835628867149353, "value_row": 0.8557319045066833, "value_any": 0.877573549747467, "value_bot": 0.8422834873199463, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10220.png", "entropy": 0.09427588433027267} +{"ts": "2026-03-20T19:50:04.830717Z", "loop": 10230, "env_steps": 6285312000, "exact_value_avg": 0.8630129098892212, "regret_dist": 0.0005678018205799162, "regret_other_env": 0.000945896259509027, "regret_corner": 6.601214863621863e-07, "regret_row": 0.000557086372282356, "regret_any": 0.0009448782075196505, "regret_bot": 0.0015140743926167488, "value_dist": 0.8630129098892212, "value_other_env": 0.8812689781188965, "value_corner": 0.8356286883354187, "value_row": 0.8580695390701294, "value_any": 0.8813056945800781, "value_bot": 0.8571125864982605, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10230.png", "entropy": 0.09085675328969955} +{"ts": "2026-03-20T19:50:13.413793Z", "loop": 10240, "env_steps": 6291456000, "exact_value_avg": 0.8627232313156128, "regret_dist": 0.0008574798121117055, "regret_other_env": 0.0014188478235155344, "regret_corner": 1.5427669495693408e-05, "regret_row": 0.007775390055030584, "regret_any": 0.0014167778426781297, "regret_bot": 0.0015781987458467484, "value_dist": 0.8627232313156128, "value_other_env": 0.8807960748672485, "value_corner": 0.8356139063835144, "value_row": 0.8508512377738953, "value_any": 0.8808338642120361, "value_bot": 0.8570484519004822, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10240.png", "entropy": 0.09572954475879669} +{"ts": "2026-03-20T19:50:21.992502Z", "loop": 10250, "env_steps": 6297600000, "exact_value_avg": 0.8623760938644409, "regret_dist": 0.0012046124320477247, "regret_other_env": 0.002000311156734824, "regret_corner": 1.1064113095926587e-05, "regret_row": 0.00041591416811570525, "regret_any": 0.00199758424423635, "regret_bot": 0.004098075907677412, "value_dist": 0.8623760938644409, "value_other_env": 0.8802146315574646, "value_corner": 0.835618257522583, "value_row": 0.8582106828689575, "value_any": 0.8802530169487, "value_bot": 0.8545286059379578, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10250.png", "entropy": 0.09706884622573853} +{"ts": "2026-03-20T19:50:30.569547Z", "loop": 10260, "env_steps": 6303744000, "exact_value_avg": 0.8628940582275391, "regret_dist": 0.0006866130279377103, "regret_other_env": 0.001131627126596868, "regret_corner": 1.9091865397058427e-05, "regret_row": 0.00041048851562663913, "regret_any": 0.0011300157057121396, "regret_bot": 0.002417182782664895, "value_dist": 0.8628940582275391, "value_other_env": 0.8810832500457764, "value_corner": 0.8356101512908936, "value_row": 0.8582161664962769, "value_any": 0.8811205625534058, "value_bot": 0.8562094569206238, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10260.png", "entropy": 0.09872037172317505} +{"ts": "2026-03-20T19:50:39.154863Z", "loop": 10270, "env_steps": 6309888000, "exact_value_avg": 0.8632099628448486, "regret_dist": 0.0003706089046318084, "regret_other_env": 0.0006153158028610051, "regret_corner": 3.5484633826854406e-06, "regret_row": 0.00030229208641685545, "regret_any": 0.0006147196399979293, "regret_bot": 0.0010107913985848427, "value_dist": 0.8632099628448486, "value_other_env": 0.881599485874176, "value_corner": 0.8356257677078247, "value_row": 0.858324408531189, "value_any": 0.8816359043121338, "value_bot": 0.8576158881187439, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10270.png", "entropy": 0.09405749291181564} +{"ts": "2026-03-20T19:50:47.738402Z", "loop": 10280, "env_steps": 6316032000, "exact_value_avg": 0.8629834651947021, "regret_dist": 0.0005971895880065858, "regret_other_env": 0.0009942821925505996, "regret_corner": 1.5507142734350055e-06, "regret_row": 0.0005377313937060535, "regret_any": 0.000992846442386508, "regret_bot": 0.0013692547800019383, "value_dist": 0.8629834651947021, "value_other_env": 0.8812205195426941, "value_corner": 0.8356277942657471, "value_row": 0.8580889105796814, "value_any": 0.8812577128410339, "value_bot": 0.8572573065757751, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10280.png", "entropy": 0.09146641194820404} +{"ts": "2026-03-20T19:50:56.319530Z", "loop": 10290, "env_steps": 6322176000, "exact_value_avg": 0.8606926202774048, "regret_dist": 0.0028880969621241093, "regret_other_env": 0.004813457373529673, "regret_corner": 5.612771047935894e-08, "regret_row": 0.0034154211170971394, "regret_any": 0.0048065693117678165, "regret_bot": 0.007708228658884764, "value_dist": 0.8606926202774048, "value_other_env": 0.8774014711380005, "value_corner": 0.8356292247772217, "value_row": 0.8552111983299255, "value_any": 0.8774439692497253, "value_bot": 0.8509183526039124, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10290.png", "entropy": 0.09433183073997498} +{"ts": "2026-03-20T19:51:04.906320Z", "loop": 10300, "env_steps": 6328320000, "exact_value_avg": 0.8614903092384338, "regret_dist": 0.002090355148538947, "regret_other_env": 0.0034839126747101545, "regret_corner": 1.887480571838296e-08, "regret_row": 0.01330939307808876, "regret_any": 0.003482735250145197, "regret_bot": 0.0024945333134382963, "value_dist": 0.8614903092384338, "value_other_env": 0.8787309527397156, "value_corner": 0.8356292247772217, "value_row": 0.8453173041343689, "value_any": 0.8787678480148315, "value_bot": 0.8561321496963501, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10300.png", "entropy": 0.09078296273946762} +{"ts": "2026-03-20T19:51:13.498359Z", "loop": 10310, "env_steps": 6334464000, "exact_value_avg": 0.8634237051010132, "regret_dist": 0.00015694285684730858, "regret_other_env": 0.0002608415961731225, "regret_corner": 1.094738649953797e-06, "regret_row": 0.00016410915122833103, "regret_any": 0.0002618801954668015, "regret_bot": 0.00032970760366879404, "value_dist": 0.8634237051010132, "value_other_env": 0.8819540143013, "value_corner": 0.8356282114982605, "value_row": 0.8584625124931335, "value_any": 0.8819887042045593, "value_bot": 0.8582969903945923, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10310.png", "entropy": 0.08767195791006088} +{"ts": "2026-03-20T19:51:22.093506Z", "loop": 10320, "env_steps": 6340608000, "exact_value_avg": 0.8633972406387329, "regret_dist": 0.00018350573373027146, "regret_other_env": 0.0003035216068383306, "regret_corner": 3.481904741420294e-06, "regret_row": 0.0001523665414424613, "regret_any": 0.00030362658435478806, "regret_bot": 0.0002825113188009709, "value_dist": 0.8633972406387329, "value_other_env": 0.8819113969802856, "value_corner": 0.8356258869171143, "value_row": 0.8584742546081543, "value_any": 0.8819469809532166, "value_bot": 0.8583441376686096, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10320.png", "entropy": 0.0880904495716095} +{"ts": "2026-03-20T19:51:30.684404Z", "loop": 10330, "env_steps": 6346752000, "exact_value_avg": 0.86305171251297, "regret_dist": 0.0005289784166961908, "regret_other_env": 0.0008552403305657208, "regret_corner": 3.958543311455287e-05, "regret_row": 0.000812581623904407, "regret_any": 0.0008664383785799146, "regret_bot": 0.0005614019464701414, "value_dist": 0.86305171251297, "value_other_env": 0.8813596367835999, "value_corner": 0.8355897665023804, "value_row": 0.8578140735626221, "value_any": 0.8813841342926025, "value_bot": 0.8580651879310608, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10330.png", "entropy": 0.08777309954166412} +{"ts": "2026-03-20T19:51:39.273701Z", "loop": 10340, "env_steps": 6352896000, "exact_value_avg": 0.8634212017059326, "regret_dist": 0.0001595003268448636, "regret_other_env": 0.00026005422114394605, "regret_corner": 8.669496310176328e-06, "regret_row": 0.0003325834695715457, "regret_any": 0.0002764739911071956, "regret_bot": 0.0007182229892350733, "value_dist": 0.8634212017059326, "value_other_env": 0.8819547891616821, "value_corner": 0.835620641708374, "value_row": 0.8582940101623535, "value_any": 0.8819741010665894, "value_bot": 0.8579084873199463, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10340.png", "entropy": 0.08656647056341171} +{"ts": "2026-03-20T19:51:47.858342Z", "loop": 10350, "env_steps": 6359040000, "exact_value_avg": 0.8629748821258545, "regret_dist": 0.0006057763821445405, "regret_other_env": 0.001009528641588986, "regret_corner": 1.4801820213961037e-07, "regret_row": 0.00047646029270254076, "regret_any": 0.00100853166077286, "regret_bot": 0.0014700526371598244, "value_dist": 0.8629748821258545, "value_other_env": 0.8812053203582764, "value_corner": 0.8356291651725769, "value_row": 0.8581501841545105, "value_any": 0.8812420964241028, "value_bot": 0.8571566343307495, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10350.png", "entropy": 0.08711660653352737} +{"ts": "2026-03-20T19:51:56.442430Z", "loop": 10360, "env_steps": 6365184000, "exact_value_avg": 0.8631772994995117, "regret_dist": 0.0004033893928863108, "regret_other_env": 0.0006720090168528259, "regret_corner": 4.599492058332544e-07, "regret_row": 0.00016016805602703243, "regret_any": 0.0006710594170726836, "regret_bot": 0.0011709292884916067, "value_dist": 0.8631772994995117, "value_other_env": 0.8815429210662842, "value_corner": 0.835628867149353, "value_row": 0.8584664463996887, "value_any": 0.881579577922821, "value_bot": 0.8574556708335876, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10360.png", "entropy": 0.0830543264746666} +{"ts": "2026-03-20T19:52:05.023691Z", "loop": 10370, "env_steps": 6371328000, "exact_value_avg": 0.8632301092147827, "regret_dist": 0.00035062417737208307, "regret_other_env": 0.0005839994410052896, "regret_corner": 5.612770905827347e-07, "regret_row": 0.00017681541794445366, "regret_any": 0.0005847546271979809, "regret_bot": 0.0010517158079892397, "value_dist": 0.8632301092147827, "value_other_env": 0.8816308975219727, "value_corner": 0.8356287479400635, "value_row": 0.8584498167037964, "value_any": 0.881665825843811, "value_bot": 0.8575748801231384, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10370.png", "entropy": 0.08289316296577454} +{"ts": "2026-03-20T19:52:13.604353Z", "loop": 10380, "env_steps": 6377472000, "exact_value_avg": 0.8626484870910645, "regret_dist": 0.000932206166908145, "regret_other_env": 0.0015534519916400313, "regret_corner": 3.372629748810141e-07, "regret_row": 0.0003275319468230009, "regret_any": 0.0015529317315667868, "regret_bot": 0.0020271800458431244, "value_dist": 0.8626484870910645, "value_other_env": 0.8806614279747009, "value_corner": 0.8356289863586426, "value_row": 0.8582990765571594, "value_any": 0.8806977272033691, "value_bot": 0.8565994501113892, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10380.png", "entropy": 0.0809178501367569} +{"ts": "2026-03-20T19:52:22.189717Z", "loop": 10390, "env_steps": 6383616000, "exact_value_avg": 0.8629082441329956, "regret_dist": 0.0006724235136061907, "regret_other_env": 0.0011193780228495598, "regret_corner": 1.9917886220355285e-06, "regret_row": 0.00031429334194399416, "regret_any": 0.0011347394902259111, "regret_bot": 0.001547474879771471, "value_dist": 0.8629082441329956, "value_other_env": 0.8810955286026001, "value_corner": 0.8356272578239441, "value_row": 0.8583124279975891, "value_any": 0.8811159133911133, "value_bot": 0.8570791482925415, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10390.png", "entropy": 0.08336248993873596} +{"ts": "2026-03-20T19:52:30.771917Z", "loop": 10400, "env_steps": 6389760000, "exact_value_avg": 0.8633719682693481, "regret_dist": 0.00020874587062280625, "regret_other_env": 0.00034370136563666165, "regret_corner": 6.312629011517856e-06, "regret_row": 0.0003004525206051767, "regret_any": 0.0003668821882456541, "regret_bot": 0.0011403214884921908, "value_dist": 0.8633719682693481, "value_other_env": 0.8818711638450623, "value_corner": 0.835623025894165, "value_row": 0.8583260774612427, "value_any": 0.8818837404251099, "value_bot": 0.8574863076210022, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10400.png", "entropy": 0.08672191202640533} +{"ts": "2026-03-20T19:52:39.359269Z", "loop": 10410, "env_steps": 6395904000, "exact_value_avg": 0.8624599575996399, "regret_dist": 0.0011207208735868335, "regret_other_env": 0.0018473243108019233, "regret_corner": 3.081560134887695e-05, "regret_row": 0.006576227955520153, "regret_any": 0.0018605547957122326, "regret_bot": 0.000667835003696382, "value_dist": 0.8624599575996399, "value_other_env": 0.8803675174713135, "value_corner": 0.8355985283851624, "value_row": 0.8520503640174866, "value_any": 0.8803901076316833, "value_bot": 0.8579587936401367, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10410.png", "entropy": 0.09307695180177689} +{"ts": "2026-03-20T19:52:47.940980Z", "loop": 10420, "env_steps": 6402048000, "exact_value_avg": 0.863371729850769, "regret_dist": 0.0002090393245453015, "regret_other_env": 0.0003428191994316876, "regret_corner": 8.369485840376001e-06, "regret_row": 0.0002092006034217775, "regret_any": 0.00034285688889212906, "regret_bot": 0.0005386538687162101, "value_dist": 0.863371729850769, "value_other_env": 0.8818721175193787, "value_corner": 0.8356209397315979, "value_row": 0.8584174513816833, "value_any": 0.8819078207015991, "value_bot": 0.858087956905365, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10420.png", "entropy": 0.09486144781112671} +{"ts": "2026-03-20T19:52:56.521359Z", "loop": 10430, "env_steps": 6408192000, "exact_value_avg": 0.863217830657959, "regret_dist": 0.0003628304984886199, "regret_other_env": 0.0006022968445904553, "regret_corner": 3.6309163533587707e-06, "regret_row": 0.0005520849954336882, "regret_any": 0.000602566113229841, "regret_bot": 0.0011778807966038585, "value_dist": 0.863217830657959, "value_other_env": 0.8816125988960266, "value_corner": 0.8356257677078247, "value_row": 0.8580745458602905, "value_any": 0.881648063659668, "value_bot": 0.8574487566947937, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10430.png", "entropy": 0.09805683046579361} +{"ts": "2026-03-20T19:53:05.101011Z", "loop": 10440, "env_steps": 6414336000, "exact_value_avg": 0.8620837926864624, "regret_dist": 0.0014968989416956902, "regret_other_env": 0.0024930923245847225, "regret_corner": 2.6086968318850268e-06, "regret_row": 0.008556000888347626, "regret_any": 0.0024905670434236526, "regret_bot": 0.0025272436905652285, "value_dist": 0.8620837926864624, "value_other_env": 0.8797218203544617, "value_corner": 0.8356267213821411, "value_row": 0.8500706553459167, "value_any": 0.8797600269317627, "value_bot": 0.8560994267463684, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10440.png", "entropy": 0.09855227917432785} +{"ts": "2026-03-20T19:53:13.690386Z", "loop": 10450, "env_steps": 6420480000, "exact_value_avg": 0.8633226156234741, "regret_dist": 0.0002580785658210516, "regret_other_env": 0.00041463933303020895, "regret_corner": 2.3237369532580487e-05, "regret_row": 0.00030543465982191265, "regret_any": 0.000414452952099964, "regret_bot": 0.000684003287460655, "value_dist": 0.8633226156234741, "value_other_env": 0.8818002343177795, "value_corner": 0.8356060981750488, "value_row": 0.8583210706710815, "value_any": 0.8818361163139343, "value_bot": 0.8579425811767578, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10450.png", "entropy": 0.1021435484290123} +{"ts": "2026-03-20T19:53:22.271650Z", "loop": 10460, "env_steps": 6426624000, "exact_value_avg": 0.8631631731987, "regret_dist": 0.00041752500692382455, "regret_other_env": 0.0006480495212599635, "regret_corner": 7.173816993599758e-05, "regret_row": 0.0005342347430996597, "regret_any": 0.0006473000394180417, "regret_bot": 0.0008491450571455061, "value_dist": 0.8631631731987, "value_other_env": 0.8815668821334839, "value_corner": 0.8355575799942017, "value_row": 0.8580924272537231, "value_any": 0.8816032409667969, "value_bot": 0.8577775359153748, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10460.png", "entropy": 0.10848743468523026} +{"ts": "2026-03-20T19:53:30.849873Z", "loop": 10470, "env_steps": 6432768000, "exact_value_avg": 0.8625388145446777, "regret_dist": 0.0010418647434562445, "regret_other_env": 0.0014302412746474147, "regret_corner": 0.00045930000487715006, "regret_row": 0.0013406958896666765, "regret_any": 0.0014293525600805879, "regret_bot": 0.00084037019405514, "value_dist": 0.8625388145446777, "value_other_env": 0.8807846903800964, "value_corner": 0.8351700305938721, "value_row": 0.8572859168052673, "value_any": 0.8808212876319885, "value_bot": 0.857786238193512, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10470.png", "entropy": 0.1238957867026329} +{"ts": "2026-03-20T19:53:39.436260Z", "loop": 10480, "env_steps": 6438912000, "exact_value_avg": 0.8625578880310059, "regret_dist": 0.0010228455066680908, "regret_other_env": 0.0013521567452698946, "regret_corner": 0.0005288784741424024, "regret_row": 0.001412164536304772, "regret_any": 0.0013608778826892376, "regret_bot": 0.000843584886752069, "value_dist": 0.8625578880310059, "value_other_env": 0.8808627128601074, "value_corner": 0.8351004719734192, "value_row": 0.8572143912315369, "value_any": 0.8808897137641907, "value_bot": 0.8577830791473389, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10480.png", "entropy": 0.12255518138408661} +{"ts": "2026-03-20T19:53:48.022163Z", "loop": 10490, "env_steps": 6445056000, "exact_value_avg": 0.8631446361541748, "regret_dist": 0.00043603297672234476, "regret_other_env": 0.0006494007539004087, "regret_corner": 0.00011598120909184217, "regret_row": 0.0004190090694464743, "regret_any": 0.0006717947544530034, "regret_bot": 0.0027283395174890757, "value_dist": 0.8631446361541748, "value_other_env": 0.881565511226654, "value_corner": 0.8355133533477783, "value_row": 0.858207643032074, "value_any": 0.881578803062439, "value_bot": 0.8558982610702515, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10490.png", "entropy": 0.1089739203453064} +{"ts": "2026-03-20T19:53:56.610342Z", "loop": 10500, "env_steps": 6451200000, "exact_value_avg": 0.862899899482727, "regret_dist": 0.0006807802128605545, "regret_other_env": 0.0011254340643063188, "regret_corner": 1.3799469343211967e-05, "regret_row": 0.0006333452765829861, "regret_any": 0.0011489171301946044, "regret_bot": 0.007307030726224184, "value_dist": 0.862899899482727, "value_other_env": 0.881089448928833, "value_corner": 0.8356155157089233, "value_row": 0.8579933643341064, "value_any": 0.881101667881012, "value_bot": 0.8513196110725403, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10500.png", "entropy": 0.09920304268598557} +{"ts": "2026-03-20T19:54:05.195908Z", "loop": 10510, "env_steps": 6457344000, "exact_value_avg": 0.8632078766822815, "regret_dist": 0.00037278796662576497, "regret_other_env": 0.0006154180155135691, "regret_corner": 8.842846000334248e-06, "regret_row": 0.001146493712440133, "regret_any": 0.0006380222039297223, "regret_bot": 0.0019308916525915265, "value_dist": 0.8632078766822815, "value_other_env": 0.881599485874176, "value_corner": 0.8356204628944397, "value_row": 0.8574801087379456, "value_any": 0.8816125988960266, "value_bot": 0.8566957116127014, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10510.png", "entropy": 0.09595344215631485} +{"ts": "2026-03-20T19:54:13.776532Z", "loop": 10520, "env_steps": 6463488000, "exact_value_avg": 0.8629213571548462, "regret_dist": 0.0006594029837287962, "regret_other_env": 0.001021475181914866, "regret_corner": 0.00011629462824203074, "regret_row": 0.0025071019772440195, "regret_any": 0.0010407865047454834, "regret_bot": 0.0009784973226487637, "value_dist": 0.8629213571548462, "value_other_env": 0.8811933994293213, "value_corner": 0.8355130553245544, "value_row": 0.8561195731163025, "value_any": 0.8812097907066345, "value_bot": 0.8576480746269226, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10520.png", "entropy": 0.09465522319078445} +{"ts": "2026-03-20T19:54:22.354582Z", "loop": 10530, "env_steps": 6469632000, "exact_value_avg": 0.863060712814331, "regret_dist": 0.0005200519226491451, "regret_other_env": 0.0007920264615677297, "regret_corner": 0.00011209001968381926, "regret_row": 0.0019952303264290094, "regret_any": 0.0008044683490879834, "regret_bot": 0.0007772500393912196, "value_dist": 0.863060712814331, "value_other_env": 0.8814228773117065, "value_corner": 0.8355172872543335, "value_row": 0.856631338596344, "value_any": 0.881446123123169, "value_bot": 0.8578493595123291, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10530.png", "entropy": 0.09405114501714706} +{"ts": "2026-03-20T19:54:30.933039Z", "loop": 10540, "env_steps": 6475776000, "exact_value_avg": 0.8632329702377319, "regret_dist": 0.0003477234859019518, "regret_other_env": 0.0005551929352805018, "regret_corner": 3.651927181635983e-05, "regret_row": 0.0009022369049489498, "regret_any": 0.0005545950843952596, "regret_bot": 0.00026142384740523994, "value_dist": 0.8632329702377319, "value_other_env": 0.881659746170044, "value_corner": 0.8355928063392639, "value_row": 0.8577244281768799, "value_any": 0.8816959261894226, "value_bot": 0.8583652377128601, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10540.png", "entropy": 0.09787912666797638} +{"ts": "2026-03-20T19:54:39.517247Z", "loop": 10550, "env_steps": 6481920000, "exact_value_avg": 0.8581572771072388, "regret_dist": 0.005423429422080517, "regret_other_env": 0.008847635239362717, "regret_corner": 0.0002871195611078292, "regret_row": 0.01405043713748455, "regret_any": 0.008839737623929977, "regret_bot": 0.000507537683006376, "value_dist": 0.8581572771072388, "value_other_env": 0.8733673095703125, "value_corner": 0.8353421688079834, "value_row": 0.8445761799812317, "value_any": 0.8734108805656433, "value_bot": 0.858119010925293, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10550.png", "entropy": 0.10806027054786682} +{"ts": "2026-03-20T19:54:48.093913Z", "loop": 10560, "env_steps": 6488064000, "exact_value_avg": 0.8633855581283569, "regret_dist": 0.0001952258899109438, "regret_other_env": 0.00031788149499334395, "regret_corner": 1.124243044614559e-05, "regret_row": 0.0001209072070196271, "regret_any": 0.00031744735315442085, "regret_bot": 0.00045293563744053245, "value_dist": 0.8633855581283569, "value_other_env": 0.8818970322608948, "value_corner": 0.8356181383132935, "value_row": 0.8585056662559509, "value_any": 0.8819331526756287, "value_bot": 0.858173668384552, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10560.png", "entropy": 0.09734414517879486} +{"ts": "2026-03-20T19:54:56.679788Z", "loop": 10570, "env_steps": 6494208000, "exact_value_avg": 0.8629430532455444, "regret_dist": 0.0006376099772751331, "regret_other_env": 0.0010607109870761633, "regret_corner": 2.9583773084596032e-06, "regret_row": 0.0005183491739444435, "regret_any": 0.0010592243634164333, "regret_bot": 0.0016343988245353103, "value_dist": 0.8629430532455444, "value_other_env": 0.8811541199684143, "value_corner": 0.8356263637542725, "value_row": 0.8581082820892334, "value_any": 0.8811913728713989, "value_bot": 0.8569921851158142, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10570.png", "entropy": 0.09642796963453293} +{"ts": "2026-03-20T19:55:05.264602Z", "loop": 10580, "env_steps": 6500352000, "exact_value_avg": 0.8630326390266418, "regret_dist": 0.0005479864194057882, "regret_other_env": 0.0009094217675738037, "regret_corner": 5.833308023284189e-06, "regret_row": 0.00043435918632894754, "regret_any": 0.0009081970783881843, "regret_bot": 0.0012914100661873817, "value_dist": 0.8630326390266418, "value_other_env": 0.8813053965568542, "value_corner": 0.8356234431266785, "value_row": 0.8581922650337219, "value_any": 0.8813424706459045, "value_bot": 0.8573352694511414, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10580.png", "entropy": 0.09612037241458893} +{"ts": "2026-03-20T19:55:13.844349Z", "loop": 10590, "env_steps": 6506496000, "exact_value_avg": 0.8633897304534912, "regret_dist": 0.00019096871255896986, "regret_other_env": 0.00030759075889363885, "regret_corner": 1.6035637599998154e-05, "regret_row": 0.0002810267615132034, "regret_any": 0.0003086603246629238, "regret_bot": 0.0004747269267681986, "value_dist": 0.8633897304534912, "value_other_env": 0.8819073438644409, "value_corner": 0.8356133103370667, "value_row": 0.858345627784729, "value_any": 0.8819419741630554, "value_bot": 0.8581518530845642, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10590.png", "entropy": 0.09761592000722885} +{"ts": "2026-03-20T19:55:22.425151Z", "loop": 10600, "env_steps": 6512640000, "exact_value_avg": 0.8630096912384033, "regret_dist": 0.0005710759432986379, "regret_other_env": 0.000946111511439085, "regret_corner": 8.522471034666523e-06, "regret_row": 0.0006215936737135053, "regret_any": 0.0009685209370218217, "regret_bot": 0.004280790686607361, "value_dist": 0.8630096912384033, "value_other_env": 0.8812687993049622, "value_corner": 0.8356208205223083, "value_row": 0.8580049872398376, "value_any": 0.8812820315361023, "value_bot": 0.8543458580970764, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10600.png", "entropy": 0.09681254625320435} +{"ts": "2026-03-20T19:55:31.012324Z", "loop": 10610, "env_steps": 6518784000, "exact_value_avg": 0.8615538477897644, "regret_dist": 0.0020268799271434546, "regret_other_env": 0.003376561915501952, "regret_corner": 2.356867071284796e-06, "regret_row": 0.012706611305475235, "regret_any": 0.0033985243644565344, "regret_bot": 0.007680970709770918, "value_dist": 0.8615538477897644, "value_other_env": 0.8788383603096008, "value_corner": 0.835627019405365, "value_row": 0.8459200263023376, "value_any": 0.8788520693778992, "value_bot": 0.8509456515312195, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10610.png", "entropy": 0.09712237864732742} +{"ts": "2026-03-20T19:55:39.590792Z", "loop": 10620, "env_steps": 6524928000, "exact_value_avg": 0.8608882427215576, "regret_dist": 0.0026925222482532263, "regret_other_env": 0.004486291203647852, "regret_corner": 1.8686057501327014e-06, "regret_row": 0.020156605169177055, "regret_any": 0.004501720424741507, "regret_bot": 0.006129959132522345, "value_dist": 0.8608882427215576, "value_other_env": 0.8777286410331726, "value_corner": 0.8356274962425232, "value_row": 0.8384699821472168, "value_any": 0.8777488470077515, "value_bot": 0.8524966835975647, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10620.png", "entropy": 0.09492409229278564} +{"ts": "2026-03-20T19:55:48.168738Z", "loop": 10630, "env_steps": 6531072000, "exact_value_avg": 0.8631861209869385, "regret_dist": 0.0003945597563870251, "regret_other_env": 0.0006540381582453847, "regret_corner": 5.342066742741736e-06, "regret_row": 0.0004593996563926339, "regret_any": 0.0006735878414474428, "regret_bot": 0.002009408315643668, "value_dist": 0.8631861209869385, "value_other_env": 0.8815608620643616, "value_corner": 0.8356239795684814, "value_row": 0.8581672310829163, "value_any": 0.8815770149230957, "value_bot": 0.856617271900177, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10630.png", "entropy": 0.09313719719648361} +{"ts": "2026-03-20T19:55:56.752998Z", "loop": 10640, "env_steps": 6537216000, "exact_value_avg": 0.861540675163269, "regret_dist": 0.0020400334615260363, "regret_other_env": 0.0033977653365582228, "regret_corner": 3.4352144666627282e-06, "regret_row": 0.0018387221498414874, "regret_any": 0.0034221757669001818, "regret_bot": 0.023968348279595375, "value_dist": 0.861540675163269, "value_other_env": 0.8788171410560608, "value_corner": 0.8356258869171143, "value_row": 0.856787919998169, "value_any": 0.8788284063339233, "value_bot": 0.8346583247184753, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10640.png", "entropy": 0.09752366691827774} +{"ts": "2026-03-20T19:56:05.337287Z", "loop": 10650, "env_steps": 6543360000, "exact_value_avg": 0.8629528284072876, "regret_dist": 0.0006278363871388137, "regret_other_env": 0.0010450200643390417, "regret_corner": 2.060830638583866e-06, "regret_row": 0.003050081664696336, "regret_any": 0.0010467233369126916, "regret_bot": 0.001197136822156608, "value_dist": 0.8629528284072876, "value_other_env": 0.8811699151992798, "value_corner": 0.8356272578239441, "value_row": 0.8555765748023987, "value_any": 0.8812038898468018, "value_bot": 0.8574295043945312, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10650.png", "entropy": 0.09646464139223099} +{"ts": "2026-03-20T19:56:13.923704Z", "loop": 10660, "env_steps": 6549504000, "exact_value_avg": 0.863248348236084, "regret_dist": 0.0003323203418403864, "regret_other_env": 0.0005509975599125028, "regret_corner": 4.30444879384595e-06, "regret_row": 0.00048043133574537933, "regret_any": 0.0005502073909156024, "regret_bot": 0.00038030074210837483, "value_dist": 0.863248348236084, "value_other_env": 0.8816639184951782, "value_corner": 0.8356249928474426, "value_row": 0.8581461310386658, "value_any": 0.8817004561424255, "value_bot": 0.858246386051178, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10660.png", "entropy": 0.09888207167387009} +{"ts": "2026-03-20T19:56:22.507243Z", "loop": 10670, "env_steps": 6555648000, "exact_value_avg": 0.8632042407989502, "regret_dist": 0.000376418320229277, "regret_other_env": 0.0006247465498745441, "regret_corner": 3.925959390471689e-06, "regret_row": 0.00040434158290736377, "regret_any": 0.0006238764035515487, "regret_bot": 0.00047178330714814365, "value_dist": 0.8632042407989502, "value_other_env": 0.8815901279449463, "value_corner": 0.8356253504753113, "value_row": 0.8582223057746887, "value_any": 0.8816267251968384, "value_bot": 0.858154833316803, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10670.png", "entropy": 0.09873329848051071} +{"ts": "2026-03-20T19:56:31.093427Z", "loop": 10680, "env_steps": 6561792000, "exact_value_avg": 0.8633170127868652, "regret_dist": 0.00026371239800937474, "regret_other_env": 0.00043634665780700743, "regret_corner": 4.760921456181677e-06, "regret_row": 0.00032753567211329937, "regret_any": 0.0004357751167844981, "regret_bot": 0.00022317752882372588, "value_dist": 0.8633170127868652, "value_other_env": 0.8817785382270813, "value_corner": 0.8356245756149292, "value_row": 0.8582990765571594, "value_any": 0.8818148374557495, "value_bot": 0.8584035038948059, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10680.png", "entropy": 0.09366729110479355} +{"ts": "2026-03-20T19:56:39.676050Z", "loop": 10690, "env_steps": 6567936000, "exact_value_avg": 0.8631587028503418, "regret_dist": 0.0004219851107336581, "regret_other_env": 0.0006861228030174971, "regret_corner": 2.577851410023868e-05, "regret_row": 0.0010750355431810021, "regret_any": 0.0007047942490316927, "regret_bot": 0.000572723220102489, "value_dist": 0.8631587028503418, "value_other_env": 0.8815287947654724, "value_corner": 0.8356034755706787, "value_row": 0.8575515747070312, "value_any": 0.8815458416938782, "value_bot": 0.8580539226531982, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10690.png", "entropy": 0.091385118663311} +{"ts": "2026-03-20T19:56:48.262191Z", "loop": 10700, "env_steps": 6574080000, "exact_value_avg": 0.8626953363418579, "regret_dist": 0.0008853740291669965, "regret_other_env": 0.0014225728809833527, "regret_corner": 7.957567868288606e-05, "regret_row": 0.0021225546952337027, "regret_any": 0.0014604468597099185, "regret_bot": 0.0013623369159176946, "value_dist": 0.8626953363418579, "value_other_env": 0.8807922601699829, "value_corner": 0.8355497121810913, "value_row": 0.8565040826797485, "value_any": 0.880790114402771, "value_bot": 0.8572642803192139, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10700.png", "entropy": 0.08911155164241791} +{"ts": "2026-03-20T19:56:56.847163Z", "loop": 10710, "env_steps": 6580224000, "exact_value_avg": 0.8609451055526733, "regret_dist": 0.002635541372001171, "regret_other_env": 0.004026240669190884, "regret_corner": 0.0005494917859323323, "regret_row": 0.004056783393025398, "regret_any": 0.004054132848978043, "regret_bot": 0.0030941551085561514, "value_dist": 0.8609451055526733, "value_other_env": 0.8781886100769043, "value_corner": 0.8350798487663269, "value_row": 0.8545698523521423, "value_any": 0.8781964778900146, "value_bot": 0.8555325269699097, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10710.png", "entropy": 0.08691510558128357} +{"ts": "2026-03-20T19:57:05.429176Z", "loop": 10720, "env_steps": 6586368000, "exact_value_avg": 0.8604348301887512, "regret_dist": 0.003145847236737609, "regret_other_env": 0.005239326972514391, "regret_corner": 5.627672180708032e-06, "regret_row": 0.017316123470664024, "regret_any": 0.005277208983898163, "regret_bot": 0.004705831408500671, "value_dist": 0.8604348301887512, "value_other_env": 0.8769755363464355, "value_corner": 0.8356237411499023, "value_row": 0.8413105010986328, "value_any": 0.8769733309745789, "value_bot": 0.8539208173751831, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10720.png", "entropy": 0.08986587822437286} +{"ts": "2026-03-20T19:57:14.014198Z", "loop": 10730, "env_steps": 6592512000, "exact_value_avg": 0.862152099609375, "regret_dist": 0.0014285885263234377, "regret_other_env": 0.0023758145980536938, "regret_corner": 7.749101314402651e-06, "regret_row": 0.0013204064453020692, "regret_any": 0.002408168977126479, "regret_bot": 0.0031300897244364023, "value_dist": 0.862152099609375, "value_other_env": 0.8798390626907349, "value_corner": 0.8356215357780457, "value_row": 0.8573062419891357, "value_any": 0.8798424005508423, "value_bot": 0.8554965853691101, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10730.png", "entropy": 0.08733147382736206} +{"ts": "2026-03-20T19:57:22.600241Z", "loop": 10740, "env_steps": 6598656000, "exact_value_avg": 0.8632434010505676, "regret_dist": 0.0003372645587660372, "regret_other_env": 0.0005579994758591056, "regret_corner": 6.162127192510525e-06, "regret_row": 0.0002961011487059295, "regret_any": 0.0005873036570847034, "regret_bot": 0.0012437747791409492, "value_dist": 0.8632434010505676, "value_other_env": 0.8816568851470947, "value_corner": 0.8356231451034546, "value_row": 0.8583305478096008, "value_any": 0.8816632628440857, "value_bot": 0.8573828339576721, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10740.png", "entropy": 0.08903991430997849} +{"ts": "2026-03-20T19:57:31.189531Z", "loop": 10750, "env_steps": 6604800000, "exact_value_avg": 0.8631646037101746, "regret_dist": 0.0004161187680438161, "regret_other_env": 0.0006902145687490702, "regret_corner": 4.975001502316445e-06, "regret_row": 0.00017447512072976679, "regret_any": 0.0007366508943960071, "regret_bot": 0.0008800110663287342, "value_dist": 0.8631646037101746, "value_other_env": 0.8815247416496277, "value_corner": 0.8356243371963501, "value_row": 0.8584522604942322, "value_any": 0.8815139532089233, "value_bot": 0.8577466011047363, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10750.png", "entropy": 0.09116975963115692} +{"ts": "2026-03-20T19:57:39.776009Z", "loop": 10760, "env_steps": 6610944000, "exact_value_avg": 0.8629822731018066, "regret_dist": 0.0005984176532365382, "regret_other_env": 0.0009970588143914938, "regret_corner": 4.559755666377896e-07, "regret_row": 0.0006970732938498259, "regret_any": 0.0010120099177584052, "regret_bot": 0.0011050661560148, "value_dist": 0.8629822731018066, "value_other_env": 0.8812178373336792, "value_corner": 0.835628867149353, "value_row": 0.857929527759552, "value_any": 0.881238579750061, "value_bot": 0.8575215339660645, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10760.png", "entropy": 0.08778471499681473} +{"ts": "2026-03-20T19:57:48.359983Z", "loop": 10770, "env_steps": 6617088000, "exact_value_avg": 0.8614858388900757, "regret_dist": 0.0020948555320501328, "regret_other_env": 0.0034911262337118387, "regret_corner": 4.4951838162887725e-07, "regret_row": 0.013309186324477196, "regret_any": 0.003511037677526474, "regret_bot": 0.0020526463631540537, "value_dist": 0.8614858388900757, "value_other_env": 0.8787237405776978, "value_corner": 0.835628867149353, "value_row": 0.8453174829483032, "value_any": 0.878739595413208, "value_bot": 0.8565739989280701, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10770.png", "entropy": 0.09019652754068375} +{"ts": "2026-03-20T19:57:56.937122Z", "loop": 10780, "env_steps": 6623232000, "exact_value_avg": 0.8627867698669434, "regret_dist": 0.0007939295028336346, "regret_other_env": 0.0013216037768870592, "regret_corner": 2.4179619231290417e-06, "regret_row": 0.0012330388417467475, "regret_any": 0.0013443253701552749, "regret_bot": 0.002193005522713065, "value_dist": 0.8627867698669434, "value_other_env": 0.8808932900428772, "value_corner": 0.8356269001960754, "value_row": 0.8573936223983765, "value_any": 0.8809062838554382, "value_bot": 0.856433629989624, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10780.png", "entropy": 0.09114417433738708} +{"ts": "2026-03-20T19:58:05.520384Z", "loop": 10790, "env_steps": 6629376000, "exact_value_avg": 0.8627711534500122, "regret_dist": 0.0008095384109765291, "regret_other_env": 0.0013468610122799873, "regret_corner": 3.5544237562135095e-06, "regret_row": 0.0007004852523095906, "regret_any": 0.0013711065985262394, "regret_bot": 0.0021647915709763765, "value_dist": 0.8627711534500122, "value_other_env": 0.8808680176734924, "value_corner": 0.8356257677078247, "value_row": 0.8579261302947998, "value_any": 0.8808795213699341, "value_bot": 0.8564618229866028, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10790.png", "entropy": 0.08968845754861832} +{"ts": "2026-03-20T19:58:14.102075Z", "loop": 10800, "env_steps": 6635520000, "exact_value_avg": 0.8628541231155396, "regret_dist": 0.0007265081512741745, "regret_other_env": 0.0012079563457518816, "regret_corner": 4.3357413233025e-06, "regret_row": 0.0004864333022851497, "regret_any": 0.0012331914622336626, "regret_bot": 0.0018294642213732004, "value_dist": 0.8628541231155396, "value_other_env": 0.8810068964958191, "value_corner": 0.8356249928474426, "value_row": 0.858140230178833, "value_any": 0.8810174465179443, "value_bot": 0.8567971587181091, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10800.png", "entropy": 0.090074822306633} +{"ts": "2026-03-20T19:58:22.686081Z", "loop": 10810, "env_steps": 6641664000, "exact_value_avg": 0.8630099892616272, "regret_dist": 0.0005706933443434536, "regret_other_env": 0.0009485054761171341, "regret_corner": 3.975133495259797e-06, "regret_row": 0.0003041512973140925, "regret_any": 0.0009727142751216888, "regret_bot": 0.0017147244652733207, "value_dist": 0.8630099892616272, "value_other_env": 0.8812663555145264, "value_corner": 0.8356253504753113, "value_row": 0.8583225011825562, "value_any": 0.881277859210968, "value_bot": 0.8569118976593018, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10810.png", "entropy": 0.09048616886138916} +{"ts": "2026-03-20T19:58:31.273100Z", "loop": 10820, "env_steps": 6647808000, "exact_value_avg": 0.8611394166946411, "regret_dist": 0.0024413091596215963, "regret_other_env": 0.004068207461386919, "regret_corner": 9.616217084840173e-07, "regret_row": 0.004143193364143372, "regret_any": 0.0040892926044762135, "regret_bot": 0.01240527257323265, "value_dist": 0.8611394166946411, "value_other_env": 0.8781467080116272, "value_corner": 0.8356284499168396, "value_row": 0.8544834852218628, "value_any": 0.8781613707542419, "value_bot": 0.8462213277816772, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10820.png", "entropy": 0.09478645026683807} +{"ts": "2026-03-20T19:58:39.853407Z", "loop": 10830, "env_steps": 6653952000, "exact_value_avg": 0.8627899885177612, "regret_dist": 0.0007906676037237048, "regret_other_env": 0.001315596397034824, "regret_corner": 3.2742818802944385e-06, "regret_row": 0.0005552525399252772, "regret_any": 0.0013395727146416903, "regret_bot": 0.0022353536915034056, "value_dist": 0.8627899885177612, "value_other_env": 0.8808992505073547, "value_corner": 0.8356260657310486, "value_row": 0.8580713868141174, "value_any": 0.8809110522270203, "value_bot": 0.8563912510871887, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10830.png", "entropy": 0.09037885069847107} +{"ts": "2026-03-20T19:58:48.432154Z", "loop": 10840, "env_steps": 6660096000, "exact_value_avg": 0.8612093925476074, "regret_dist": 0.002371283480897546, "regret_other_env": 0.003927885089069605, "regret_corner": 3.638118869275786e-05, "regret_row": 0.00359622435644269, "regret_any": 0.003962757997214794, "regret_bot": 0.004869568627327681, "value_dist": 0.8612093925476074, "value_other_env": 0.8782870173454285, "value_corner": 0.8355929255485535, "value_row": 0.855030357837677, "value_any": 0.8782877922058105, "value_bot": 0.8537570834159851, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10840.png", "entropy": 0.09157156944274902} +{"ts": "2026-03-20T19:58:57.007354Z", "loop": 10850, "env_steps": 6666240000, "exact_value_avg": 0.8613597750663757, "regret_dist": 0.0022208953741937876, "regret_other_env": 0.0036908236797899008, "regret_corner": 1.600235736987088e-05, "regret_row": 0.0031231623142957687, "regret_any": 0.003721545683220029, "regret_bot": 0.004062302876263857, "value_dist": 0.8613597750663757, "value_other_env": 0.8785240650177002, "value_corner": 0.8356133103370667, "value_row": 0.855503499507904, "value_any": 0.8785290122032166, "value_bot": 0.8545643091201782, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10850.png", "entropy": 0.09105101972818375} +{"ts": "2026-03-20T19:59:05.583778Z", "loop": 10860, "env_steps": 6672384000, "exact_value_avg": 0.8628584146499634, "regret_dist": 0.0007223448483273387, "regret_other_env": 0.001198121695779264, "regret_corner": 8.679429811309092e-06, "regret_row": 0.0006529046804644167, "regret_any": 0.001222454709932208, "regret_bot": 0.001605576602742076, "value_dist": 0.8628584146499634, "value_other_env": 0.8810167908668518, "value_corner": 0.835620641708374, "value_row": 0.8579737544059753, "value_any": 0.8810281753540039, "value_bot": 0.8570210337638855, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10860.png", "entropy": 0.09025005996227264} +{"ts": "2026-03-20T19:59:14.168289Z", "loop": 10870, "env_steps": 6678528000, "exact_value_avg": 0.8632742166519165, "regret_dist": 0.0003064436314161867, "regret_other_env": 0.0005044603603892028, "regret_corner": 9.418527952220757e-06, "regret_row": 0.00015587716188747436, "regret_any": 0.0005283767241053283, "regret_bot": 0.0015394911170005798, "value_dist": 0.8632742166519165, "value_other_env": 0.8817103505134583, "value_corner": 0.8356199264526367, "value_row": 0.8584707379341125, "value_any": 0.8817221522331238, "value_bot": 0.8570871949195862, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10870.png", "entropy": 0.09162499010562897} +{"ts": "2026-03-20T19:59:22.748396Z", "loop": 10880, "env_steps": 6684672000, "exact_value_avg": 0.8632851839065552, "regret_dist": 0.00029549183091148734, "regret_other_env": 0.00048679052270017564, "regret_corner": 8.543829608242959e-06, "regret_row": 0.00010658737301127985, "regret_any": 0.0005107304896228015, "regret_bot": 0.0016842512413859367, "value_dist": 0.8632851839065552, "value_other_env": 0.8817281126976013, "value_corner": 0.8356208205223083, "value_row": 0.8585200309753418, "value_any": 0.8817398548126221, "value_bot": 0.8569424152374268, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10880.png", "entropy": 0.09115451574325562} +{"ts": "2026-03-20T19:59:31.336491Z", "loop": 10890, "env_steps": 6690816000, "exact_value_avg": 0.862686038017273, "regret_dist": 0.0008946519228629768, "regret_other_env": 0.0014771082205697894, "regret_corner": 2.096742537105456e-05, "regret_row": 0.004115962889045477, "regret_any": 0.001551091205328703, "regret_bot": 0.0012587594101205468, "value_dist": 0.862686038017273, "value_other_env": 0.8807377815246582, "value_corner": 0.8356083631515503, "value_row": 0.8545106649398804, "value_any": 0.8806994557380676, "value_bot": 0.8573678135871887, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10890.png", "entropy": 0.08829070627689362} +{"ts": "2026-03-20T19:59:39.917646Z", "loop": 10900, "env_steps": 6696960000, "exact_value_avg": 0.8631166219711304, "regret_dist": 0.0004640785919036716, "regret_other_env": 0.0007653279462829232, "regret_corner": 1.22045485113631e-05, "regret_row": 0.0003293815825600177, "regret_any": 0.0008016955689527094, "regret_bot": 0.0012660257052630186, "value_dist": 0.8631166219711304, "value_other_env": 0.8814495801925659, "value_corner": 0.8356171250343323, "value_row": 0.8582972288131714, "value_any": 0.8814489841461182, "value_bot": 0.8573606014251709, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10900.png", "entropy": 0.08576734364032745} +{"ts": "2026-03-20T19:59:48.505271Z", "loop": 10910, "env_steps": 6703104000, "exact_value_avg": 0.8617891073226929, "regret_dist": 0.0017915813950821757, "regret_other_env": 0.0029389513656497, "regret_corner": 7.052620640024543e-05, "regret_row": 0.002156808041036129, "regret_any": 0.0029796375893056393, "regret_bot": 0.002266502007842064, "value_dist": 0.8617891073226929, "value_other_env": 0.879275918006897, "value_corner": 0.8355588316917419, "value_row": 0.8564698100090027, "value_any": 0.8792709708213806, "value_bot": 0.8563601970672607, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10910.png", "entropy": 0.08658963441848755} +{"ts": "2026-03-20T19:59:57.087532Z", "loop": 10920, "env_steps": 6709248000, "exact_value_avg": 0.860357403755188, "regret_dist": 0.0032233400270342827, "regret_other_env": 0.00531580438837409, "regret_corner": 8.464307029498741e-05, "regret_row": 0.014040111564099789, "regret_any": 0.005347422789782286, "regret_bot": 0.0021502419840544462, "value_dist": 0.860357403755188, "value_other_env": 0.8768991231918335, "value_corner": 0.8355447053909302, "value_row": 0.8445865511894226, "value_any": 0.8769031763076782, "value_bot": 0.856476366519928, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10920.png", "entropy": 0.09001725912094116} +{"ts": "2026-03-20T20:00:05.668985Z", "loop": 10930, "env_steps": 6715392000, "exact_value_avg": 0.8626925945281982, "regret_dist": 0.0008880869136191905, "regret_other_env": 0.0014728846726939082, "regret_corner": 1.0890265912166797e-05, "regret_row": 0.0008537023095414042, "regret_any": 0.0014974239747971296, "regret_bot": 0.00187139050103724, "value_dist": 0.8626925945281982, "value_other_env": 0.8807419538497925, "value_corner": 0.8356184959411621, "value_row": 0.8577728867530823, "value_any": 0.8807531595230103, "value_bot": 0.856755256652832, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10930.png", "entropy": 0.08517416566610336} +{"ts": "2026-03-20T20:00:14.249969Z", "loop": 10940, "env_steps": 6721536000, "exact_value_avg": 0.8631893396377563, "regret_dist": 0.0003913475957233459, "regret_other_env": 0.0006482481840066612, "regret_corner": 5.996724212309346e-06, "regret_row": 0.00039157160790637136, "regret_any": 0.0006719888770021498, "regret_bot": 0.0012913566315546632, "value_dist": 0.8631893396377563, "value_other_env": 0.8815666437149048, "value_corner": 0.8356233239173889, "value_row": 0.8582351207733154, "value_any": 0.8815786242485046, "value_bot": 0.8573352694511414, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10940.png", "entropy": 0.08579226583242416} +{"ts": "2026-03-20T20:00:22.836061Z", "loop": 10950, "env_steps": 6727680000, "exact_value_avg": 0.8631048202514648, "regret_dist": 0.00047587003791704774, "regret_other_env": 0.0007873674621805549, "regret_corner": 8.623798748885747e-06, "regret_row": 0.0005720413755625486, "regret_any": 0.0007992801256477833, "regret_bot": 0.0005157088744454086, "value_dist": 0.8631048202514648, "value_other_env": 0.881427526473999, "value_corner": 0.835620641708374, "value_row": 0.8580545783042908, "value_any": 0.8814512491226196, "value_bot": 0.8581109642982483, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10950.png", "entropy": 0.08974415808916092} +{"ts": "2026-03-20T20:00:31.418118Z", "loop": 10960, "env_steps": 6733824000, "exact_value_avg": 0.8629547953605652, "regret_dist": 0.000625906977802515, "regret_other_env": 0.0010392384137958288, "regret_corner": 5.909800620429451e-06, "regret_row": 0.0006838827393949032, "regret_any": 0.0010385268833488226, "regret_bot": 0.0002906912995968014, "value_dist": 0.8629547953605652, "value_other_env": 0.881175696849823, "value_corner": 0.8356234431266785, "value_row": 0.8579427599906921, "value_any": 0.8812121152877808, "value_bot": 0.8583359122276306, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10960.png", "entropy": 0.091841921210289} +{"ts": "2026-03-20T20:00:39.999094Z", "loop": 10970, "env_steps": 6739968000, "exact_value_avg": 0.8629171848297119, "regret_dist": 0.0006634874735027552, "regret_other_env": 0.0010989840375259519, "regret_corner": 1.0242561984341592e-05, "regret_row": 0.0008361071813851595, "regret_any": 0.0010981244267895818, "regret_bot": 0.00032682291930541396, "value_dist": 0.8629171848297119, "value_other_env": 0.8811158537864685, "value_corner": 0.8356190919876099, "value_row": 0.8577905297279358, "value_any": 0.8811525106430054, "value_bot": 0.8582998514175415, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10970.png", "entropy": 0.09372838586568832} +{"ts": "2026-03-20T20:00:48.579785Z", "loop": 10980, "env_steps": 6746112000, "exact_value_avg": 0.8610804080963135, "regret_dist": 0.002500273287296295, "regret_other_env": 0.004118237644433975, "regret_corner": 7.332662789849564e-05, "regret_row": 0.008282036520540714, "regret_any": 0.00413593091070652, "regret_bot": 0.00046456698328256607, "value_dist": 0.8610804080963135, "value_other_env": 0.8780966401100159, "value_corner": 0.8355560302734375, "value_row": 0.8503445386886597, "value_any": 0.8781147003173828, "value_bot": 0.8581620454788208, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10980.png", "entropy": 0.09899277985095978} +{"ts": "2026-03-20T20:00:57.159228Z", "loop": 10990, "env_steps": 6752256000, "exact_value_avg": 0.863442063331604, "regret_dist": 0.0001385994255542755, "regret_other_env": 0.00022975959291215986, "regret_corner": 1.8591682646729168e-06, "regret_row": 7.07889994373545e-05, "regret_any": 0.00023827965196687728, "regret_bot": 0.000494826992508024, "value_dist": 0.863442063331604, "value_other_env": 0.8819851279258728, "value_corner": 0.8356274962425232, "value_row": 0.858555793762207, "value_any": 0.8820123076438904, "value_bot": 0.8581318259239197, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_10990.png", "entropy": 0.08665245026350021} +{"ts": "2026-03-20T20:01:05.741101Z", "loop": 11000, "env_steps": 6758400000, "exact_value_avg": 0.8634045124053955, "regret_dist": 0.00017620933067519218, "regret_other_env": 0.00029282885952852666, "regret_corner": 1.2800097692888812e-06, "regret_row": 8.247087680501863e-05, "regret_any": 0.00029482218087650836, "regret_bot": 0.0003869974461849779, "value_dist": 0.8634045124053955, "value_other_env": 0.8819220662117004, "value_corner": 0.8356280326843262, "value_row": 0.8585441708564758, "value_any": 0.8819558024406433, "value_bot": 0.8582396507263184, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11000.png", "entropy": 0.08568816632032394} +{"ts": "2026-03-20T20:01:14.321437Z", "loop": 11010, "env_steps": 6764544000, "exact_value_avg": 0.8632573485374451, "regret_dist": 0.00032330528483726084, "regret_other_env": 0.0005382854724302888, "regret_corner": 8.349617814928934e-07, "regret_row": 0.00013179995585232973, "regret_any": 0.0005377574125304818, "regret_bot": 0.0005406746058724821, "value_dist": 0.8632573485374451, "value_other_env": 0.8816765546798706, "value_corner": 0.8356285095214844, "value_row": 0.858494758605957, "value_any": 0.881712794303894, "value_bot": 0.8580860495567322, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11010.png", "entropy": 0.08524548262357712} +{"ts": "2026-03-20T20:01:22.912437Z", "loop": 11020, "env_steps": 6770688000, "exact_value_avg": 0.8607879281044006, "regret_dist": 0.002792775398120284, "regret_other_env": 0.004653797019273043, "regret_corner": 1.242756866304262e-06, "regret_row": 0.003143525682389736, "regret_any": 0.004646888468414545, "regret_bot": 0.006012910511344671, "value_dist": 0.8607879281044006, "value_other_env": 0.877561092376709, "value_corner": 0.8356280326843262, "value_row": 0.8554831743240356, "value_any": 0.8776037096977234, "value_bot": 0.8526137471199036, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11020.png", "entropy": 0.08779969811439514} +{"ts": "2026-03-20T20:01:31.496747Z", "loop": 11030, "env_steps": 6776832000, "exact_value_avg": 0.8630519509315491, "regret_dist": 0.0005287756212055683, "regret_other_env": 0.0008790379506535828, "regret_corner": 3.38206700689625e-06, "regret_row": 0.0008495149668306112, "regret_any": 0.0008777901530265808, "regret_bot": 0.0010865665972232819, "value_dist": 0.8630519509315491, "value_other_env": 0.8813358545303345, "value_corner": 0.835625946521759, "value_row": 0.8577771186828613, "value_any": 0.88137286901474, "value_bot": 0.8575400114059448, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11030.png", "entropy": 0.08483564108610153} +{"ts": "2026-03-20T20:01:40.077956Z", "loop": 11040, "env_steps": 6782976000, "exact_value_avg": 0.8628355264663696, "regret_dist": 0.0007452034624293447, "regret_other_env": 0.0012301115784794092, "regret_corner": 1.784116102498956e-05, "regret_row": 0.005648273043334484, "regret_any": 0.0012298106448724866, "regret_bot": 0.00032852773438207805, "value_dist": 0.8628355264663696, "value_other_env": 0.8809847831726074, "value_corner": 0.8356115221977234, "value_row": 0.8529782891273499, "value_any": 0.8810208439826965, "value_bot": 0.8582980632781982, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11040.png", "entropy": 0.08337154984474182} +{"ts": "2026-03-20T20:01:48.663085Z", "loop": 11050, "env_steps": 6789120000, "exact_value_avg": 0.863445520401001, "regret_dist": 0.00013526486873161048, "regret_other_env": 0.00022372615057975054, "regret_corner": 2.572933908595587e-06, "regret_row": 2.456573747622315e-05, "regret_any": 0.000246560201048851, "regret_bot": 0.000999439274892211, "value_dist": 0.863445520401001, "value_other_env": 0.8819912075996399, "value_corner": 0.8356267809867859, "value_row": 0.8586020469665527, "value_any": 0.8820040822029114, "value_bot": 0.8576272130012512, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11050.png", "entropy": 0.07906372845172882} +{"ts": "2026-03-20T20:01:57.243559Z", "loop": 11060, "env_steps": 6795264000, "exact_value_avg": 0.8617863655090332, "regret_dist": 0.0017943474231287837, "regret_other_env": 0.0029906074050813913, "regret_corner": -4.2716663983810577e-08, "regret_row": 0.006083193700760603, "regret_any": 0.003013483714312315, "regret_bot": 0.0059037357568740845, "value_dist": 0.8617863655090332, "value_other_env": 0.8792243003845215, "value_corner": 0.835629403591156, "value_row": 0.8525434732437134, "value_any": 0.8792371153831482, "value_bot": 0.8527228832244873, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11060.png", "entropy": 0.08487619459629059} +{"ts": "2026-03-20T20:02:05.824683Z", "loop": 11070, "env_steps": 6801408000, "exact_value_avg": 0.8632893562316895, "regret_dist": 0.0002913002099376172, "regret_other_env": 0.00048532450455240905, "regret_corner": 2.637505644997873e-07, "regret_row": 0.0006993332644924521, "regret_any": 0.0005029327585361898, "regret_bot": 0.001043672556988895, "value_dist": 0.8632893562316895, "value_other_env": 0.8817295432090759, "value_corner": 0.8356290459632874, "value_row": 0.8579273223876953, "value_any": 0.8817477226257324, "value_bot": 0.8575829267501831, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11070.png", "entropy": 0.0848953127861023} +{"ts": "2026-03-20T20:02:14.407762Z", "loop": 11080, "env_steps": 6807552000, "exact_value_avg": 0.8633935451507568, "regret_dist": 0.0001870642154244706, "regret_other_env": 0.0003111213445663452, "regret_corner": 9.78509660853888e-07, "regret_row": 8.985580643638968e-05, "regret_any": 0.000315484736347571, "regret_bot": 0.0006127621163614094, "value_dist": 0.8633935451507568, "value_other_env": 0.8819037675857544, "value_corner": 0.8356282711029053, "value_row": 0.8585367798805237, "value_any": 0.8819351196289062, "value_bot": 0.8580138683319092, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11080.png", "entropy": 0.08746320009231567} +{"ts": "2026-03-20T20:02:22.999051Z", "loop": 11090, "env_steps": 6813696000, "exact_value_avg": 0.8629246354103088, "regret_dist": 0.0006560856709256768, "regret_other_env": 0.0010897362371906638, "regret_corner": 5.6097906053764746e-06, "regret_row": 0.001635835156776011, "regret_any": 0.001088161370716989, "regret_bot": 0.0020658504217863083, "value_dist": 0.8629246354103088, "value_other_env": 0.8811251521110535, "value_corner": 0.8356237411499023, "value_row": 0.8569908142089844, "value_any": 0.8811624646186829, "value_bot": 0.8565607666969299, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11090.png", "entropy": 0.09502691775560379} +{"ts": "2026-03-20T20:02:31.588705Z", "loop": 11100, "env_steps": 6819840000, "exact_value_avg": 0.8629869222640991, "regret_dist": 0.0005937537061981857, "regret_other_env": 0.0009866284672170877, "regret_corner": 4.4415396587282885e-06, "regret_row": 0.0007398271118290722, "regret_any": 0.0009854596573859453, "regret_bot": 0.0022844804916530848, "value_dist": 0.8629869222640991, "value_other_env": 0.8812282681465149, "value_corner": 0.8356248736381531, "value_row": 0.8578868508338928, "value_any": 0.8812651038169861, "value_bot": 0.8563421964645386, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11100.png", "entropy": 0.0939389020204544} +{"ts": "2026-03-20T20:02:40.174606Z", "loop": 11110, "env_steps": 6825984000, "exact_value_avg": 0.8625418543815613, "regret_dist": 0.0010388060472905636, "regret_other_env": 0.0017153351800516248, "regret_corner": 2.4012229914660566e-05, "regret_row": 0.0018799951067194343, "regret_any": 0.001726621063426137, "regret_bot": 0.0014460122911259532, "value_dist": 0.8625418543815613, "value_other_env": 0.880499541759491, "value_corner": 0.835605263710022, "value_row": 0.8567465543746948, "value_any": 0.8805239200592041, "value_bot": 0.857180655002594, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11110.png", "entropy": 0.09544665366411209} +{"ts": "2026-03-20T20:02:48.756264Z", "loop": 11120, "env_steps": 6832128000, "exact_value_avg": 0.8629765510559082, "regret_dist": 0.0006040958687663078, "regret_other_env": 0.0009750555036589503, "regret_corner": 4.765639823745005e-05, "regret_row": 0.0015254247700795531, "regret_any": 0.000975702132564038, "regret_bot": 0.000556289276573807, "value_dist": 0.8629765510559082, "value_other_env": 0.8812398314476013, "value_corner": 0.8355816602706909, "value_row": 0.8571012020111084, "value_any": 0.881274938583374, "value_bot": 0.8580703735351562, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11120.png", "entropy": 0.09256294369697571} +{"ts": "2026-03-20T20:02:57.333232Z", "loop": 11130, "env_steps": 6838272000, "exact_value_avg": 0.861678421497345, "regret_dist": 0.001902223564684391, "regret_other_env": 0.0029892895836383104, "regret_corner": 0.0002716243325266987, "regret_row": 0.012532208114862442, "regret_any": 0.002991635352373123, "regret_bot": 0.0007912201108410954, "value_dist": 0.861678421497345, "value_other_env": 0.879225492477417, "value_corner": 0.8353577256202698, "value_row": 0.8460944890975952, "value_any": 0.8792589902877808, "value_bot": 0.8578354120254517, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11130.png", "entropy": 0.09364835917949677} +{"ts": "2026-03-20T20:03:05.912218Z", "loop": 11140, "env_steps": 6844416000, "exact_value_avg": 0.8632355332374573, "regret_dist": 0.0003451357188168913, "regret_other_env": 0.0005566149484366179, "regret_corner": 2.791683073155582e-05, "regret_row": 0.0007288057822734118, "regret_any": 0.0005558478878811002, "regret_bot": 0.00051596958655864, "value_dist": 0.8632355332374573, "value_other_env": 0.8816582560539246, "value_corner": 0.8356013894081116, "value_row": 0.8578978180885315, "value_any": 0.8816947340965271, "value_bot": 0.8581106066703796, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11140.png", "entropy": 0.09180701524019241} +{"ts": "2026-03-20T20:03:14.493699Z", "loop": 11150, "env_steps": 6850560000, "exact_value_avg": 0.8610321283340454, "regret_dist": 0.0025485316291451454, "regret_other_env": 0.004246667493134737, "regret_corner": 1.3276935533212963e-06, "regret_row": 0.019840897992253304, "regret_any": 0.004240555223077536, "regret_bot": 0.0033694931771606207, "value_dist": 0.8610321283340454, "value_other_env": 0.8779681921005249, "value_corner": 0.8356279730796814, "value_row": 0.8387857675552368, "value_any": 0.8780100345611572, "value_bot": 0.8552571535110474, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11150.png", "entropy": 0.09534358978271484} +{"ts": "2026-03-20T20:03:23.071591Z", "loop": 11160, "env_steps": 6856704000, "exact_value_avg": 0.8622475862503052, "regret_dist": 0.0013330315705388784, "regret_other_env": 0.0022205242421478033, "regret_corner": 1.7926097370946081e-06, "regret_row": 0.004593237303197384, "regret_any": 0.0022173654288053513, "regret_bot": 0.005289074499160051, "value_dist": 0.8622475862503052, "value_other_env": 0.8799943327903748, "value_corner": 0.835627555847168, "value_row": 0.854033350944519, "value_any": 0.8800332546234131, "value_bot": 0.8533375859260559, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11160.png", "entropy": 0.0978892520070076} +{"ts": "2026-03-20T20:03:31.649381Z", "loop": 11170, "env_steps": 6862848000, "exact_value_avg": 0.8623077869415283, "regret_dist": 0.0012728782603517175, "regret_other_env": 0.0021133674308657646, "regret_corner": 1.2144447282480542e-05, "regret_row": 0.001989024691283703, "regret_any": 0.002110607922077179, "regret_bot": 0.007163842208683491, "value_dist": 0.8623077869415283, "value_other_env": 0.8801015019416809, "value_corner": 0.835617184638977, "value_row": 0.8566375374794006, "value_any": 0.8801400065422058, "value_bot": 0.8514627814292908, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11170.png", "entropy": 0.1022467389702797} +{"ts": "2026-03-20T20:03:40.225784Z", "loop": 11180, "env_steps": 6868992000, "exact_value_avg": 0.8623632192611694, "regret_dist": 0.001217491109855473, "regret_other_env": 0.0020168882329016924, "regret_corner": 1.8395485312794335e-05, "regret_row": 0.007252824958413839, "regret_any": 0.002013926859945059, "regret_bot": 0.0013296834658831358, "value_dist": 0.8623632192611694, "value_other_env": 0.8801980018615723, "value_corner": 0.8356109261512756, "value_row": 0.8513737916946411, "value_any": 0.8802366256713867, "value_bot": 0.8572970032691956, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11180.png", "entropy": 0.10670708864927292} +{"ts": "2026-03-20T20:03:48.803197Z", "loop": 11190, "env_steps": 6875136000, "exact_value_avg": 0.8627057671546936, "regret_dist": 0.0008749051485210657, "regret_other_env": 0.0014167755143716931, "regret_corner": 6.209959974512458e-05, "regret_row": 0.0022747984621673822, "regret_any": 0.001414784463122487, "regret_bot": 0.001483779400587082, "value_dist": 0.8627057671546936, "value_other_env": 0.8807980418205261, "value_corner": 0.8355672359466553, "value_row": 0.8563517928123474, "value_any": 0.8808358907699585, "value_bot": 0.8571428656578064, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11190.png", "entropy": 0.11033475399017334} +{"ts": "2026-03-20T20:03:57.383534Z", "loop": 11200, "env_steps": 6881280000, "exact_value_avg": 0.8629181385040283, "regret_dist": 0.0006624953239224851, "regret_other_env": 0.0010622385889291763, "regret_corner": 6.288041913649067e-05, "regret_row": 0.0009542307816445827, "regret_any": 0.0010607292642816901, "regret_bot": 0.00147888099309057, "value_dist": 0.8629181385040283, "value_other_env": 0.8811526298522949, "value_corner": 0.8355664610862732, "value_row": 0.857672393321991, "value_any": 0.8811898827552795, "value_bot": 0.857147753238678, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11200.png", "entropy": 0.10817397385835648} +{"ts": "2026-03-20T20:04:05.965275Z", "loop": 11210, "env_steps": 6887424000, "exact_value_avg": 0.8631364107131958, "regret_dist": 0.00044432125287130475, "regret_other_env": 0.0006887631025165319, "regret_corner": 7.76583983679302e-05, "regret_row": 0.0004908112459816039, "regret_any": 0.000688048719894141, "regret_bot": 0.001183992368169129, "value_dist": 0.8631364107131958, "value_other_env": 0.8815261721611023, "value_corner": 0.8355516791343689, "value_row": 0.8581357598304749, "value_any": 0.8815625309944153, "value_bot": 0.8574425578117371, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11210.png", "entropy": 0.10474270582199097} +{"ts": "2026-03-20T20:04:14.545911Z", "loop": 11220, "env_steps": 6893568000, "exact_value_avg": 0.8632246255874634, "regret_dist": 0.0003560449986252934, "regret_other_env": 0.0005844828556291759, "regret_corner": 1.3388197658059653e-05, "regret_row": 0.0002682529448065907, "regret_any": 0.0005879207164980471, "regret_bot": 0.0022796231787651777, "value_dist": 0.8632246255874634, "value_other_env": 0.8816303610801697, "value_corner": 0.8356159925460815, "value_row": 0.8583583831787109, "value_any": 0.8816627264022827, "value_bot": 0.8563469648361206, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11220.png", "entropy": 0.09641280770301819} +{"ts": "2026-03-20T20:04:23.127236Z", "loop": 11230, "env_steps": 6899712000, "exact_value_avg": 0.8629987239837646, "regret_dist": 0.0005820168880745769, "regret_other_env": 0.0009537222795188427, "regret_corner": 2.4458768166368827e-05, "regret_row": 0.0010870591504499316, "regret_any": 0.0009752801852300763, "regret_bot": 0.0014602860901504755, "value_dist": 0.8629987239837646, "value_other_env": 0.8812611699104309, "value_corner": 0.8356049060821533, "value_row": 0.8575395941734314, "value_any": 0.8812752962112427, "value_bot": 0.8571663498878479, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11230.png", "entropy": 0.08881513774394989} +{"ts": "2026-03-20T20:04:31.708660Z", "loop": 11240, "env_steps": 6905856000, "exact_value_avg": 0.8592348098754883, "regret_dist": 0.004345869179815054, "regret_other_env": 0.007118667010217905, "regret_corner": 0.00018667231779545546, "regret_row": 0.005691194906830788, "regret_any": 0.007142225746065378, "regret_bot": 0.007093653082847595, "value_dist": 0.8592348098754883, "value_other_env": 0.8750962018966675, "value_corner": 0.8354426622390747, "value_row": 0.8529353737831116, "value_any": 0.8751083016395569, "value_bot": 0.851533055305481, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11240.png", "entropy": 0.09016527235507965} +{"ts": "2026-03-20T20:04:40.294184Z", "loop": 11250, "env_steps": 6912000000, "exact_value_avg": 0.8626255989074707, "regret_dist": 0.0009550288086757064, "regret_other_env": 0.00158097711391747, "regret_corner": 1.6106168914120644e-05, "regret_row": 0.0006326136062853038, "regret_any": 0.0016055346932262182, "regret_bot": 0.0016286327736452222, "value_dist": 0.8626255989074707, "value_other_env": 0.8806338906288147, "value_corner": 0.8356131911277771, "value_row": 0.8579940795898438, "value_any": 0.8806450366973877, "value_bot": 0.8569980263710022, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11250.png", "entropy": 0.08861524611711502} +{"ts": "2026-03-20T20:04:48.873517Z", "loop": 11260, "env_steps": 6918144000, "exact_value_avg": 0.8628088235855103, "regret_dist": 0.0007718444103375077, "regret_other_env": 0.0012521320022642612, "regret_corner": 5.1412982429610565e-05, "regret_row": 0.0005357632180675864, "regret_any": 0.0012743998086079955, "regret_bot": 0.0010846941731870174, "value_dist": 0.8628088235855103, "value_other_env": 0.8809626698493958, "value_corner": 0.8355779051780701, "value_row": 0.8580908179283142, "value_any": 0.880976140499115, "value_bot": 0.8575418591499329, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11260.png", "entropy": 0.09203889220952988} +{"ts": "2026-03-20T20:04:57.453484Z", "loop": 11270, "env_steps": 6924288000, "exact_value_avg": 0.8630738258361816, "regret_dist": 0.0005068943719379604, "regret_other_env": 0.0008073061471804976, "regret_corner": 5.627671998809092e-05, "regret_row": 0.00055422552395612, "regret_any": 0.000821509282104671, "regret_bot": 0.0008065940346568823, "value_dist": 0.8630738258361816, "value_other_env": 0.881407618522644, "value_corner": 0.8355729579925537, "value_row": 0.8580723404884338, "value_any": 0.8814290761947632, "value_bot": 0.8578200340270996, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11270.png", "entropy": 0.09676060080528259} +{"ts": "2026-03-20T20:05:06.044440Z", "loop": 11280, "env_steps": 6930432000, "exact_value_avg": 0.8634016513824463, "regret_dist": 0.0001791067043086514, "regret_other_env": 0.00029111423646099865, "regret_corner": 1.1095405170635786e-05, "regret_row": 0.00016103056259453297, "regret_any": 0.00029105268185958266, "regret_bot": 0.0006723768310621381, "value_dist": 0.8634016513824463, "value_other_env": 0.8819237947463989, "value_corner": 0.835618257522583, "value_row": 0.8584655523300171, "value_any": 0.8819595575332642, "value_bot": 0.8579543232917786, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11280.png", "entropy": 0.08983197808265686} +{"ts": "2026-03-20T20:05:14.626185Z", "loop": 11290, "env_steps": 6936576000, "exact_value_avg": 0.8633850812911987, "regret_dist": 0.00019567992421798408, "regret_other_env": 0.0003237188793718815, "regret_corner": 3.621478981585824e-06, "regret_row": 0.00014516561350319535, "regret_any": 0.00032330164685845375, "regret_bot": 0.0006969092064537108, "value_dist": 0.8633850812911987, "value_other_env": 0.8818911910057068, "value_corner": 0.8356257081031799, "value_row": 0.8584814667701721, "value_any": 0.8819273114204407, "value_bot": 0.8579297065734863, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11290.png", "entropy": 0.08725365996360779} +{"ts": "2026-03-20T20:05:23.205411Z", "loop": 11300, "env_steps": 6942720000, "exact_value_avg": 0.8631614446640015, "regret_dist": 0.00041924536344595253, "regret_other_env": 0.000698089599609375, "regret_corner": 9.790063586478936e-07, "regret_row": 0.00108480139169842, "regret_any": 0.0006971202092245221, "regret_bot": 0.0009550359682179987, "value_dist": 0.8631614446640015, "value_other_env": 0.8815168142318726, "value_corner": 0.8356282711029053, "value_row": 0.8575418591499329, "value_any": 0.8815534710884094, "value_bot": 0.8576715588569641, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11300.png", "entropy": 0.08970939368009567} +{"ts": "2026-03-20T20:05:31.785085Z", "loop": 11310, "env_steps": 6948864000, "exact_value_avg": 0.8607039451599121, "regret_dist": 0.002876739948987961, "regret_other_env": 0.004783929325640202, "regret_corner": 1.5956164133967832e-05, "regret_row": 0.006262291222810745, "regret_any": 0.00477822357788682, "regret_bot": 0.026507845148444176, "value_dist": 0.8607039451599121, "value_other_env": 0.8774309754371643, "value_corner": 0.8356133103370667, "value_row": 0.8523642420768738, "value_any": 0.8774724006652832, "value_bot": 0.8321188688278198, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11310.png", "entropy": 0.09305156022310257} +{"ts": "2026-03-20T20:05:40.368304Z", "loop": 11320, "env_steps": 6955008000, "exact_value_avg": 0.8630247116088867, "regret_dist": 0.0005560250720009208, "regret_other_env": 0.0009213181911036372, "regret_corner": 8.08537060947856e-06, "regret_row": 0.002074810676276684, "regret_any": 0.0009200960048474371, "regret_bot": 0.0017263377085328102, "value_dist": 0.8630247116088867, "value_other_env": 0.881293535232544, "value_corner": 0.8356212377548218, "value_row": 0.8565518260002136, "value_any": 0.8813304901123047, "value_bot": 0.8569002747535706, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11320.png", "entropy": 0.09035451710224152} +{"ts": "2026-03-20T20:05:48.947460Z", "loop": 11330, "env_steps": 6961152000, "exact_value_avg": 0.8633261919021606, "regret_dist": 0.00025451459805481136, "regret_other_env": 0.0004222336574457586, "regret_corner": 2.9360255666688317e-06, "regret_row": 0.00048635454731993377, "regret_any": 0.0004216715460643172, "regret_bot": 0.0005642923642881215, "value_dist": 0.8633261919021606, "value_other_env": 0.8817926645278931, "value_corner": 0.8356263637542725, "value_row": 0.858140230178833, "value_any": 0.8818289041519165, "value_bot": 0.8580623269081116, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11330.png", "entropy": 0.09064283221960068} +{"ts": "2026-03-20T20:05:57.530142Z", "loop": 11340, "env_steps": 6967296000, "exact_value_avg": 0.8608866930007935, "regret_dist": 0.002693988149985671, "regret_other_env": 0.0044850073754787445, "regret_corner": 7.459024800482439e-06, "regret_row": 0.00736567098647356, "regret_any": 0.004479021765291691, "regret_bot": 0.010598978959023952, "value_dist": 0.8608866930007935, "value_other_env": 0.8777298927307129, "value_corner": 0.8356218934059143, "value_row": 0.8512610197067261, "value_any": 0.8777716159820557, "value_bot": 0.8480275869369507, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11340.png", "entropy": 0.10059483349323273} +{"ts": "2026-03-20T20:06:06.112524Z", "loop": 11350, "env_steps": 6973440000, "exact_value_avg": 0.8627331256866455, "regret_dist": 0.000847552961204201, "regret_other_env": 0.0014089758042246103, "regret_corner": 5.418559339886997e-06, "regret_row": 0.0027474157977849245, "regret_any": 0.0014070901088416576, "regret_bot": 0.001909696264192462, "value_dist": 0.8627331256866455, "value_other_env": 0.8808059096336365, "value_corner": 0.8356239199638367, "value_row": 0.8558792471885681, "value_any": 0.8808435201644897, "value_bot": 0.8567169904708862, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11350.png", "entropy": 0.09704764187335968} +{"ts": "2026-03-20T20:06:14.693181Z", "loop": 11360, "env_steps": 6979584000, "exact_value_avg": 0.8621115684509277, "regret_dist": 0.0014690692769363523, "regret_other_env": 0.0024363903794437647, "regret_corner": 1.8087526768795215e-05, "regret_row": 0.003711163531988859, "regret_any": 0.002432939363643527, "regret_bot": 0.0031412928365170956, "value_dist": 0.8621115684509277, "value_other_env": 0.8797784447669983, "value_corner": 0.8356112837791443, "value_row": 0.8549154996871948, "value_any": 0.8798176646232605, "value_bot": 0.8554853796958923, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11360.png", "entropy": 0.09617231786251068} +{"ts": "2026-03-20T20:06:23.270522Z", "loop": 11370, "env_steps": 6985728000, "exact_value_avg": 0.8630858659744263, "regret_dist": 0.0004948138375766575, "regret_other_env": 0.000813629012554884, "regret_corner": 1.659095323702786e-05, "regret_row": 0.0005162268062122166, "regret_any": 0.0008124859305098653, "regret_bot": 0.00042490442865528166, "value_dist": 0.8630858659744263, "value_other_env": 0.8814012408256531, "value_corner": 0.8356127142906189, "value_row": 0.8581104278564453, "value_any": 0.8814380764961243, "value_bot": 0.8582016825675964, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11370.png", "entropy": 0.0915503054857254} +{"ts": "2026-03-20T20:06:31.864340Z", "loop": 11380, "env_steps": 6991872000, "exact_value_avg": 0.8631126880645752, "regret_dist": 0.00046802195720374584, "regret_other_env": 0.0007688103360123932, "regret_corner": 1.683930713625159e-05, "regret_row": 0.0003664291580207646, "regret_any": 0.0007678189431317151, "regret_bot": 0.0006480748415924609, "value_dist": 0.8631126880645752, "value_other_env": 0.8814460635185242, "value_corner": 0.8356125354766846, "value_row": 0.8582601547241211, "value_any": 0.8814827799797058, "value_bot": 0.8579785823822021, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11380.png", "entropy": 0.0896531492471695} +{"ts": "2026-03-20T20:06:40.447375Z", "loop": 11390, "env_steps": 6998016000, "exact_value_avg": 0.8626281023025513, "regret_dist": 0.0009525212226435542, "regret_other_env": 0.0014846023404970765, "regret_corner": 0.00015439938579220325, "regret_row": 0.0005593202658928931, "regret_any": 0.0014835764886811376, "regret_bot": 0.002509424928575754, "value_dist": 0.8626281023025513, "value_other_env": 0.8807302117347717, "value_corner": 0.835474967956543, "value_row": 0.8580673336982727, "value_any": 0.8807669878005981, "value_bot": 0.8561171889305115, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11390.png", "entropy": 0.08602306246757507} +{"ts": "2026-03-20T20:06:49.030655Z", "loop": 11400, "env_steps": 7004160000, "exact_value_avg": 0.8617756366729736, "regret_dist": 0.001805078354664147, "regret_other_env": 0.0029261382296681404, "regret_corner": 0.00012348841119091958, "regret_row": 0.0010163247352465987, "regret_any": 0.0029484264086931944, "regret_bot": 0.007697835564613342, "value_dist": 0.8617756366729736, "value_other_env": 0.8792887330055237, "value_corner": 0.8355058431625366, "value_row": 0.8576103448867798, "value_any": 0.8793021440505981, "value_bot": 0.8509288430213928, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11400.png", "entropy": 0.08576729148626328} +{"ts": "2026-03-20T20:06:57.617689Z", "loop": 11410, "env_steps": 7010304000, "exact_value_avg": 0.8625900745391846, "regret_dist": 0.0009905888000503182, "regret_other_env": 0.0016451117116957903, "regret_corner": 8.804103345028125e-06, "regret_row": 0.0003117647429462522, "regret_any": 0.0016683166613802314, "regret_bot": 0.005926622077822685, "value_dist": 0.8625900745391846, "value_other_env": 0.8805698156356812, "value_corner": 0.8356205224990845, "value_row": 0.8583148121833801, "value_any": 0.880582332611084, "value_bot": 0.8527000546455383, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11410.png", "entropy": 0.08489921689033508} +{"ts": "2026-03-20T20:07:06.198856Z", "loop": 11420, "env_steps": 7016448000, "exact_value_avg": 0.8628865480422974, "regret_dist": 0.0006941693718545139, "regret_other_env": 0.0011513305362313986, "regret_corner": 8.427600732829887e-06, "regret_row": 0.00024795171339064837, "regret_any": 0.0011751772835850716, "regret_bot": 0.002128225052729249, "value_dist": 0.8628865480422974, "value_other_env": 0.8810635805130005, "value_corner": 0.8356209397315979, "value_row": 0.8583787083625793, "value_any": 0.8810754418373108, "value_bot": 0.8564983606338501, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11420.png", "entropy": 0.0854184702038765} +{"ts": "2026-03-20T20:07:14.781201Z", "loop": 11430, "env_steps": 7022592000, "exact_value_avg": 0.8628464937210083, "regret_dist": 0.000734209839720279, "regret_other_env": 0.0012058784486725926, "regret_corner": 2.6706855351221748e-05, "regret_row": 0.0007165849674493074, "regret_any": 0.0012291684979572892, "regret_bot": 0.0014352435246109962, "value_dist": 0.8628464937210083, "value_other_env": 0.881009042263031, "value_corner": 0.8356026411056519, "value_row": 0.85791015625, "value_any": 0.8810214400291443, "value_bot": 0.8571913838386536, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11430.png", "entropy": 0.09027665108442307} +{"ts": "2026-03-20T20:07:23.361397Z", "loop": 11440, "env_steps": 7028736000, "exact_value_avg": 0.8603502511978149, "regret_dist": 0.0032304469496011734, "regret_other_env": 0.004087214823812246, "regret_corner": 0.0019452950218692422, "regret_row": 0.014044397510588169, "regret_any": 0.004103437531739473, "regret_bot": 0.006561933550983667, "value_dist": 0.8603502511978149, "value_other_env": 0.8781276941299438, "value_corner": 0.8336840867996216, "value_row": 0.8445822596549988, "value_any": 0.8781471848487854, "value_bot": 0.8520647287368774, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11440.png", "entropy": 0.11854908615350723} +{"ts": "2026-03-20T20:07:31.938657Z", "loop": 11450, "env_steps": 7034880000, "exact_value_avg": 0.8626953363418579, "regret_dist": 0.0008853903855197132, "regret_other_env": 0.0012849080376327038, "regret_corner": 0.0002861137327272445, "regret_row": 0.0029653720557689667, "regret_any": 0.0013041485799476504, "regret_bot": 0.002178621245548129, "value_dist": 0.8626953363418579, "value_other_env": 0.8809299468994141, "value_corner": 0.8353432416915894, "value_row": 0.8556612730026245, "value_any": 0.8809464573860168, "value_bot": 0.8564479947090149, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11450.png", "entropy": 0.10875009745359421} +{"ts": "2026-03-20T20:07:40.517557Z", "loop": 11460, "env_steps": 7041024000, "exact_value_avg": 0.8620145320892334, "regret_dist": 0.001566156162880361, "regret_other_env": 0.0025681941770017147, "regret_corner": 6.30989670753479e-05, "regret_row": 0.01369414571672678, "regret_any": 0.0025704249273985624, "regret_bot": 0.0006765918806195259, "value_dist": 0.8620145320892334, "value_other_env": 0.8796467185020447, "value_corner": 0.8355662226676941, "value_row": 0.844932496547699, "value_any": 0.8796801567077637, "value_bot": 0.8579500913619995, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11460.png", "entropy": 0.10039745271205902} +{"ts": "2026-03-20T20:07:49.095835Z", "loop": 11470, "env_steps": 7047168000, "exact_value_avg": 0.8612202405929565, "regret_dist": 0.002360474318265915, "regret_other_env": 0.0038733233232051134, "regret_corner": 9.120007598539814e-05, "regret_row": 0.012724203057587147, "regret_any": 0.003873942419886589, "regret_bot": 0.0008377092890441418, "value_dist": 0.8612202405929565, "value_other_env": 0.878341555595398, "value_corner": 0.8355381488800049, "value_row": 0.8459023833274841, "value_any": 0.8783767223358154, "value_bot": 0.8577889800071716, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11470.png", "entropy": 0.10543455928564072} +{"ts": "2026-03-20T20:07:57.678505Z", "loop": 11480, "env_steps": 7053312000, "exact_value_avg": 0.8629574775695801, "regret_dist": 0.0006232043961063027, "regret_other_env": 0.0009940499439835548, "regret_corner": 6.693601608276367e-05, "regret_row": 0.0009264143882319331, "regret_any": 0.0010009974939748645, "regret_bot": 0.0017090077744796872, "value_dist": 0.8629574775695801, "value_other_env": 0.881220817565918, "value_corner": 0.8355624079704285, "value_row": 0.8577002286911011, "value_any": 0.8812496066093445, "value_bot": 0.856917679309845, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11480.png", "entropy": 0.10435861349105835} +{"ts": "2026-03-20T20:08:06.264427Z", "loop": 11490, "env_steps": 7059456000, "exact_value_avg": 0.8616892695426941, "regret_dist": 0.0018913927488029003, "regret_other_env": 0.0030082385055720806, "regret_corner": 0.00021612396812997758, "regret_row": 0.001962200738489628, "regret_any": 0.0030162844341248274, "regret_bot": 0.0123660983517766, "value_dist": 0.8616892695426941, "value_other_env": 0.879206657409668, "value_corner": 0.8354131579399109, "value_row": 0.8566644787788391, "value_any": 0.8792343735694885, "value_bot": 0.8462605476379395, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11490.png", "entropy": 0.11220890283584595} +{"ts": "2026-03-20T20:08:14.841625Z", "loop": 11500, "env_steps": 7065600000, "exact_value_avg": 0.86261385679245, "regret_dist": 0.0009668111451901495, "regret_other_env": 0.0016028720419853926, "regret_corner": 1.271963174076518e-05, "regret_row": 0.0017631460214033723, "regret_any": 0.0016233709175139666, "regret_bot": 0.00546948192641139, "value_dist": 0.86261385679245, "value_other_env": 0.8806120157241821, "value_corner": 0.8356165885925293, "value_row": 0.8568634390830994, "value_any": 0.8806272149085999, "value_bot": 0.8531571626663208, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11500.png", "entropy": 0.10464474558830261} +{"ts": "2026-03-20T20:08:23.427916Z", "loop": 11510, "env_steps": 7071744000, "exact_value_avg": 0.8629841804504395, "regret_dist": 0.0005965214804746211, "regret_other_env": 0.0009930302621796727, "regret_corner": 1.7583371345608612e-06, "regret_row": 0.0011594407260417938, "regret_any": 0.0010164771229028702, "regret_bot": 0.00254723709076643, "value_dist": 0.8629841804504395, "value_other_env": 0.8812218904495239, "value_corner": 0.835627555847168, "value_row": 0.8574671745300293, "value_any": 0.8812341690063477, "value_bot": 0.8560794591903687, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11510.png", "entropy": 0.09401368349790573} +{"ts": "2026-03-20T20:08:32.006374Z", "loop": 11520, "env_steps": 7077888000, "exact_value_avg": 0.8627743721008301, "regret_dist": 0.0008063004934228957, "regret_other_env": 0.0013424946228042245, "regret_corner": 2.0091733858862426e-06, "regret_row": 0.00287521630525589, "regret_any": 0.0013671094784513116, "regret_bot": 0.002357667777687311, "value_dist": 0.8627743721008301, "value_other_env": 0.880872368812561, "value_corner": 0.8356272578239441, "value_row": 0.8557514548301697, "value_any": 0.8808834552764893, "value_bot": 0.8562690019607544, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11520.png", "entropy": 0.09431234747171402} +{"ts": "2026-03-20T20:08:40.588402Z", "loop": 11530, "env_steps": 7084032000, "exact_value_avg": 0.8612783551216125, "regret_dist": 0.0023023365065455437, "regret_other_env": 0.003828402142971754, "regret_corner": 1.323769538430497e-05, "regret_row": 0.008515645749866962, "regret_any": 0.0038515476044267416, "regret_bot": 0.011554908007383347, "value_dist": 0.8612783551216125, "value_other_env": 0.8783864974975586, "value_corner": 0.8356161117553711, "value_row": 0.8501109480857849, "value_any": 0.8783990144729614, "value_bot": 0.8470717668533325, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11530.png", "entropy": 0.10339841991662979} +{"ts": "2026-03-20T20:08:49.164354Z", "loop": 11540, "env_steps": 7090176000, "exact_value_avg": 0.8622881174087524, "regret_dist": 0.0012925600167363882, "regret_other_env": 0.0021349762100726366, "regret_corner": 2.893557211791631e-05, "regret_row": 0.002913334174081683, "regret_any": 0.002159294905140996, "regret_bot": 0.005007152911275625, "value_dist": 0.8622881174087524, "value_other_env": 0.8800799250602722, "value_corner": 0.8356003761291504, "value_row": 0.8557133078575134, "value_any": 0.8800913095474243, "value_bot": 0.8536194562911987, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11540.png", "entropy": 0.10603493452072144} +{"ts": "2026-03-20T20:08:57.744392Z", "loop": 11550, "env_steps": 7096320000, "exact_value_avg": 0.8627599477767944, "regret_dist": 0.0008207387290894985, "regret_other_env": 0.0013606555294245481, "regret_corner": 1.0863444003916811e-05, "regret_row": 0.0025047773960977793, "regret_any": 0.0013808549847453833, "regret_bot": 0.0026072547771036625, "value_dist": 0.8627599477767944, "value_other_env": 0.8808542490005493, "value_corner": 0.8356184363365173, "value_row": 0.8561217784881592, "value_any": 0.8808697462081909, "value_bot": 0.8560193181037903, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11550.png", "entropy": 0.10329615324735641} +{"ts": "2026-03-20T20:09:06.330578Z", "loop": 11560, "env_steps": 7102464000, "exact_value_avg": 0.8627384901046753, "regret_dist": 0.0008421176462434232, "regret_other_env": 0.0013806633651256561, "regret_corner": 3.429899879847653e-05, "regret_row": 0.0008848108118399978, "regret_any": 0.0014010516460984945, "regret_bot": 0.001479883911088109, "value_dist": 0.8627384901046753, "value_other_env": 0.88083416223526, "value_corner": 0.8355950713157654, "value_row": 0.8577418327331543, "value_any": 0.8808495998382568, "value_bot": 0.8571467399597168, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11560.png", "entropy": 0.10009873658418655} +{"ts": "2026-03-20T20:09:14.916364Z", "loop": 11570, "env_steps": 7108608000, "exact_value_avg": 0.8621305227279663, "regret_dist": 0.001450179610401392, "regret_other_env": 0.0024039822164922953, "regret_corner": 1.947581949934829e-05, "regret_row": 0.0009433999075554311, "regret_any": 0.002427724888548255, "regret_bot": 0.0017523861024528742, "value_dist": 0.8621305227279663, "value_other_env": 0.8798108696937561, "value_corner": 0.8356098532676697, "value_row": 0.8576831817626953, "value_any": 0.879822850227356, "value_bot": 0.8568742871284485, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11570.png", "entropy": 0.09498719871044159} +{"ts": "2026-03-20T20:09:23.498850Z", "loop": 11580, "env_steps": 7114752000, "exact_value_avg": 0.8618634939193726, "regret_dist": 0.001717168022878468, "regret_other_env": 0.0028585202526301146, "regret_corner": 5.139410859555937e-06, "regret_row": 0.001241210731677711, "regret_any": 0.002883056178689003, "regret_bot": 0.001967331627383828, "value_dist": 0.8618634939193726, "value_other_env": 0.879356324672699, "value_corner": 0.8356241583824158, "value_row": 0.8573853969573975, "value_any": 0.8793675303459167, "value_bot": 0.8566592931747437, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11580.png", "entropy": 0.0883246511220932} +{"ts": "2026-03-20T20:09:32.083387Z", "loop": 11590, "env_steps": 7120896000, "exact_value_avg": 0.8627091646194458, "regret_dist": 0.0008715496514923871, "regret_other_env": 0.001451597549021244, "regret_corner": 1.4776985608477844e-06, "regret_row": 0.0015341555699706078, "regret_any": 0.0014839041978120804, "regret_bot": 0.0022468003444373608, "value_dist": 0.8627091646194458, "value_other_env": 0.8807632923126221, "value_corner": 0.8356278538703918, "value_row": 0.8570924401283264, "value_any": 0.880766749382019, "value_bot": 0.8563798069953918, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11590.png", "entropy": 0.08873866498470306} +{"ts": "2026-03-20T20:09:40.670231Z", "loop": 11600, "env_steps": 7127040000, "exact_value_avg": 0.8624385595321655, "regret_dist": 0.0011421192903071642, "regret_other_env": 0.0019031274132430553, "regret_corner": 6.069739697522891e-07, "regret_row": 0.002507986733689904, "regret_any": 0.0019424880156293511, "regret_bot": 0.0029574288055300713, "value_dist": 0.8624385595321655, "value_other_env": 0.8803117275238037, "value_corner": 0.8356286883354187, "value_row": 0.8561186790466309, "value_any": 0.8803080916404724, "value_bot": 0.8556692004203796, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11600.png", "entropy": 0.08526747673749924} +{"ts": "2026-03-20T20:09:49.258036Z", "loop": 11610, "env_steps": 7133184000, "exact_value_avg": 0.858801007270813, "regret_dist": 0.004779621493071318, "regret_other_env": 0.007965531200170517, "regret_corner": 7.56979034122196e-07, "regret_row": 0.016725489869713783, "regret_any": 0.00798689853399992, "regret_bot": 0.03475352004170418, "value_dist": 0.858801007270813, "value_other_env": 0.8742493391036987, "value_corner": 0.8356285691261292, "value_row": 0.8419010639190674, "value_any": 0.8742637038230896, "value_bot": 0.8238731622695923, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11610.png", "entropy": 0.08601666241884232} +{"ts": "2026-03-20T20:09:57.839040Z", "loop": 11620, "env_steps": 7139328000, "exact_value_avg": 0.8632471561431885, "regret_dist": 0.0003335121728014201, "regret_other_env": 0.0005529001937247813, "regret_corner": 4.430115495779319e-06, "regret_row": 0.0002368183631915599, "regret_any": 0.0005552400834858418, "regret_bot": 0.0008340781787410378, "value_dist": 0.8632471561431885, "value_other_env": 0.8816619515419006, "value_corner": 0.8356248736381531, "value_row": 0.8583897948265076, "value_any": 0.8816953897476196, "value_bot": 0.8577926158905029, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11620.png", "entropy": 0.09502555429935455} +{"ts": "2026-03-20T20:10:06.427649Z", "loop": 11630, "env_steps": 7145472000, "exact_value_avg": 0.8621301651000977, "regret_dist": 0.0014505538856610656, "regret_other_env": 0.0023491056635975838, "regret_corner": 0.0001027261241688393, "regret_row": 0.0031986141111701727, "regret_any": 0.002345637883991003, "regret_bot": 0.0028802526649087667, "value_dist": 0.8621301651000977, "value_other_env": 0.879865825176239, "value_corner": 0.8355265855789185, "value_row": 0.8554280400276184, "value_any": 0.8799049854278564, "value_bot": 0.855746328830719, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11630.png", "entropy": 0.09865989536046982} +{"ts": "2026-03-20T20:10:15.028708Z", "loop": 11640, "env_steps": 7151616000, "exact_value_avg": 0.8623129725456238, "regret_dist": 0.0012677571503445506, "regret_other_env": 0.001980699598789215, "regret_corner": 0.00019834340491797775, "regret_row": 0.0036165304481983185, "regret_any": 0.001977846957743168, "regret_bot": 0.0024512331001460552, "value_dist": 0.8623129725456238, "value_other_env": 0.8802342414855957, "value_corner": 0.8354310393333435, "value_row": 0.8550101518630981, "value_any": 0.8802728056907654, "value_bot": 0.856175422668457, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11640.png", "entropy": 0.1011912003159523} +{"ts": "2026-03-20T20:10:23.611521Z", "loop": 11650, "env_steps": 7157760000, "exact_value_avg": 0.8628197908401489, "regret_dist": 0.0007608062005601823, "regret_other_env": 0.0012596679152920842, "regret_corner": 1.2513499314081855e-05, "regret_row": 0.0011881786631420255, "regret_any": 0.0012593576684594154, "regret_bot": 0.001890278304927051, "value_dist": 0.8628197908401489, "value_other_env": 0.880955159664154, "value_corner": 0.8356167674064636, "value_row": 0.8574385046958923, "value_any": 0.8809912204742432, "value_bot": 0.856736421585083, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11650.png", "entropy": 0.09864276647567749} +{"ts": "2026-03-20T20:10:32.193278Z", "loop": 11660, "env_steps": 7163904000, "exact_value_avg": 0.8628374338150024, "regret_dist": 0.000743325799703598, "regret_other_env": 0.001237229211255908, "regret_corner": 2.4706125714146765e-06, "regret_row": 0.001208805595524609, "regret_any": 0.001243694918230176, "regret_bot": 0.0015771376201882958, "value_dist": 0.8628374338150024, "value_other_env": 0.8809776306152344, "value_corner": 0.8356269001960754, "value_row": 0.8574178814888, "value_any": 0.8810068964958191, "value_bot": 0.8570494651794434, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11660.png", "entropy": 0.09054466336965561} +{"ts": "2026-03-20T20:10:40.772127Z", "loop": 11670, "env_steps": 7170048000, "exact_value_avg": 0.8625431060791016, "regret_dist": 0.001037530368193984, "regret_other_env": 0.0017289253883063793, "regret_corner": 4.375974640424829e-07, "regret_row": 0.0014198838034644723, "regret_any": 0.0017557155806571245, "regret_bot": 0.0026836225297302008, "value_dist": 0.8625431060791016, "value_other_env": 0.8804859519004822, "value_corner": 0.835628867149353, "value_row": 0.8572067618370056, "value_any": 0.8804948925971985, "value_bot": 0.8559430241584778, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11670.png", "entropy": 0.08663856983184814} +{"ts": "2026-03-20T20:10:49.356443Z", "loop": 11680, "env_steps": 7176192000, "exact_value_avg": 0.8621931672096252, "regret_dist": 0.0013875359436497092, "regret_other_env": 0.0023123198188841343, "regret_corner": 3.601114144657913e-07, "regret_row": 0.0017892185132950544, "regret_any": 0.002334888093173504, "regret_bot": 0.0030282794032245874, "value_dist": 0.8621931672096252, "value_other_env": 0.8799026012420654, "value_corner": 0.8356289267539978, "value_row": 0.8568373918533325, "value_any": 0.879915714263916, "value_bot": 0.8555983901023865, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11680.png", "entropy": 0.08574703335762024} +{"ts": "2026-03-20T20:10:57.934686Z", "loop": 11690, "env_steps": 7182336000, "exact_value_avg": 0.8629621267318726, "regret_dist": 0.0006185745005495846, "regret_other_env": 0.0010309141362085938, "regret_corner": 6.506840577458206e-08, "regret_row": 0.0007303169113583863, "regret_any": 0.0010316718835383654, "regret_bot": 0.0011863294057548046, "value_dist": 0.8629621267318726, "value_other_env": 0.8811839818954468, "value_corner": 0.8356292247772217, "value_row": 0.8578962683677673, "value_any": 0.8812189698219299, "value_bot": 0.8574403524398804, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11690.png", "entropy": 0.08488074690103531} +{"ts": "2026-03-20T20:11:06.519102Z", "loop": 11700, "env_steps": 7188480000, "exact_value_avg": 0.8576279878616333, "regret_dist": 0.005952737759798765, "regret_other_env": 0.00992107018828392, "regret_corner": 2.3891530531727767e-07, "regret_row": 0.018069416284561157, "regret_any": 0.009917620569467545, "regret_bot": 0.0062291063368320465, "value_dist": 0.8576279878616333, "value_other_env": 0.8722938299179077, "value_corner": 0.8356290459632874, "value_row": 0.8405572772026062, "value_any": 0.8723329901695251, "value_bot": 0.8523975610733032, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11700.png", "entropy": 0.08373280614614487} +{"ts": "2026-03-20T20:11:15.099712Z", "loop": 11710, "env_steps": 7194624000, "exact_value_avg": 0.8626407384872437, "regret_dist": 0.0009400304988957942, "regret_other_env": 0.0015657150652259588, "regret_corner": 1.503527187196596e-06, "regret_row": 0.0005582025623880327, "regret_any": 0.001563657191582024, "regret_bot": 0.0023354634176939726, "value_dist": 0.8626407384872437, "value_other_env": 0.880649209022522, "value_corner": 0.8356277942657471, "value_row": 0.8580684661865234, "value_any": 0.8806869387626648, "value_bot": 0.8562912344932556, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11710.png", "entropy": 0.09307301044464111} +{"ts": "2026-03-20T20:11:23.676774Z", "loop": 11720, "env_steps": 7200768000, "exact_value_avg": 0.8632556200027466, "regret_dist": 0.00032506967545486987, "regret_other_env": 0.0005393860046751797, "regret_corner": 3.5951536574430065e-06, "regret_row": 0.000512661412358284, "regret_any": 0.0005386016564443707, "regret_bot": 0.0007607795996591449, "value_dist": 0.8632556200027466, "value_other_env": 0.8816754817962646, "value_corner": 0.8356257677078247, "value_row": 0.8581139445304871, "value_any": 0.8817119598388672, "value_bot": 0.8578658103942871, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11720.png", "entropy": 0.0876750722527504} +{"ts": "2026-03-20T20:11:32.256908Z", "loop": 11730, "env_steps": 7206912000, "exact_value_avg": 0.8617302179336548, "regret_dist": 0.0018504193285480142, "regret_other_env": 0.003058420028537512, "regret_corner": 3.841817670036107e-05, "regret_row": 0.0057454705238342285, "regret_any": 0.0030776674393564463, "regret_bot": 0.0011282145278528333, "value_dist": 0.8617302179336548, "value_other_env": 0.8791564106941223, "value_corner": 0.8355908989906311, "value_row": 0.8528811931610107, "value_any": 0.8791729807853699, "value_bot": 0.8574984073638916, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11730.png", "entropy": 0.0896778404712677} +{"ts": "2026-03-20T20:11:40.836564Z", "loop": 11740, "env_steps": 7213056000, "exact_value_avg": 0.8630200624465942, "regret_dist": 0.0005606953636743128, "regret_other_env": 0.0009327078005298972, "regret_corner": 2.6767454528453527e-06, "regret_row": 0.0007665687007829547, "regret_any": 0.0009356844238936901, "regret_bot": 0.0005471857148222625, "value_dist": 0.8630200624465942, "value_other_env": 0.8812822699546814, "value_corner": 0.8356266617774963, "value_row": 0.8578600287437439, "value_any": 0.8813149929046631, "value_bot": 0.8580794334411621, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11740.png", "entropy": 0.0808258205652237} +{"ts": "2026-03-20T20:11:49.417038Z", "loop": 11750, "env_steps": 7219200000, "exact_value_avg": 0.8631817102432251, "regret_dist": 0.0003990127006545663, "regret_other_env": 0.0006566297961398959, "regret_corner": 1.2587011951836757e-05, "regret_row": 0.0006493152468465269, "regret_any": 0.0006586181698367, "regret_bot": 0.0013389686355367303, "value_dist": 0.8631817102432251, "value_other_env": 0.8815582990646362, "value_corner": 0.8356167078018188, "value_row": 0.8579772710800171, "value_any": 0.8815919756889343, "value_bot": 0.8572876453399658, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11750.png", "entropy": 0.09387918561697006} +{"ts": "2026-03-20T20:11:58.002800Z", "loop": 11760, "env_steps": 7225344000, "exact_value_avg": 0.8616992235183716, "regret_dist": 0.0018815221264958382, "regret_other_env": 0.0029839894268661737, "regret_corner": 0.00022782088490203023, "regret_row": 0.0023002701345831156, "regret_any": 0.0029819472692906857, "regret_bot": 0.00908226054161787, "value_dist": 0.8616992235183716, "value_other_env": 0.8792309165000916, "value_corner": 0.8354014754295349, "value_row": 0.8563263416290283, "value_any": 0.8792686462402344, "value_bot": 0.8495444059371948, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11760.png", "entropy": 0.10302148014307022} +{"ts": "2026-03-20T20:12:06.581605Z", "loop": 11770, "env_steps": 7231488000, "exact_value_avg": 0.8598845601081848, "regret_dist": 0.0036961473524570465, "regret_other_env": 0.005211491137742996, "regret_corner": 0.0014231315581128001, "regret_row": 0.009019829332828522, "regret_any": 0.005206773057579994, "regret_bot": 0.005707996431738138, "value_dist": 0.8598845601081848, "value_other_env": 0.8770034313201904, "value_corner": 0.8342061638832092, "value_row": 0.8496067523956299, "value_any": 0.8770438432693481, "value_bot": 0.8529185652732849, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11770.png", "entropy": 0.10412075370550156} +{"ts": "2026-03-20T20:12:15.167702Z", "loop": 11780, "env_steps": 7237632000, "exact_value_avg": 0.8597097992897034, "regret_dist": 0.0038708809297531843, "regret_other_env": 0.006191139575093985, "regret_corner": 0.0003904924087692052, "regret_row": 0.006862518843263388, "regret_any": 0.006190289277583361, "regret_bot": 0.005455717444419861, "value_dist": 0.8597097992897034, "value_other_env": 0.8760237097740173, "value_corner": 0.8352388143539429, "value_row": 0.8517640829086304, "value_any": 0.8760603070259094, "value_bot": 0.8531709313392639, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11780.png", "entropy": 0.10001230984926224} +{"ts": "2026-03-20T20:12:23.743537Z", "loop": 11790, "env_steps": 7243776000, "exact_value_avg": 0.862886905670166, "regret_dist": 0.0006937397411093116, "regret_other_env": 0.0011493610218167305, "regret_corner": 1.0307630873285234e-05, "regret_row": 0.0004406308871693909, "regret_any": 0.0011500592809170485, "regret_bot": 0.004157331306487322, "value_dist": 0.862886905670166, "value_other_env": 0.8810654878616333, "value_corner": 0.8356190323829651, "value_row": 0.8581860065460205, "value_any": 0.8811005353927612, "value_bot": 0.8544692993164062, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11790.png", "entropy": 0.09487201273441315} +{"ts": "2026-03-20T20:12:32.326527Z", "loop": 11800, "env_steps": 7249920000, "exact_value_avg": 0.8623902797698975, "regret_dist": 0.001190374605357647, "regret_other_env": 0.001863694516941905, "regret_corner": 0.00018039446149487048, "regret_row": 0.001431985991075635, "regret_any": 0.0018710377626121044, "regret_bot": 0.006308823358267546, "value_dist": 0.8623902797698975, "value_other_env": 0.880351185798645, "value_corner": 0.8354488611221313, "value_row": 0.8571946024894714, "value_any": 0.8803796172142029, "value_bot": 0.8523178100585938, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11800.png", "entropy": 0.10178092867136002} +{"ts": "2026-03-20T20:12:40.911500Z", "loop": 11810, "env_steps": 7256064000, "exact_value_avg": 0.8633512258529663, "regret_dist": 0.00022942510258872062, "regret_other_env": 0.00038202546420507133, "regret_corner": 5.245208853921213e-07, "regret_row": 0.0003400745044928044, "regret_any": 0.0003842325822915882, "regret_bot": 0.0006485412013716996, "value_dist": 0.8633512258529663, "value_other_env": 0.8818328380584717, "value_corner": 0.8356288075447083, "value_row": 0.8582864999771118, "value_any": 0.8818663954734802, "value_bot": 0.8579781651496887, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11810.png", "entropy": 0.08289430290460587} +{"ts": "2026-03-20T20:12:49.502359Z", "loop": 11820, "env_steps": 7262208000, "exact_value_avg": 0.8632022738456726, "regret_dist": 0.0003783986030612141, "regret_other_env": 0.000630613008979708, "regret_corner": 7.698933757183113e-08, "regret_row": 0.0007809416856616735, "regret_any": 0.0006317657534964383, "regret_bot": 0.0006033306708559394, "value_dist": 0.8632022738456726, "value_other_env": 0.8815842866897583, "value_corner": 0.8356292247772217, "value_row": 0.857845664024353, "value_any": 0.881618857383728, "value_bot": 0.8580233454704285, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11820.png", "entropy": 0.07370445132255554} +{"ts": "2026-03-20T20:12:58.087913Z", "loop": 11830, "env_steps": 7268352000, "exact_value_avg": 0.8569847345352173, "regret_dist": 0.006595988292247057, "regret_other_env": 0.010992472991347313, "regret_corner": 1.260638327948982e-06, "regret_row": 0.0024168225936591625, "regret_any": 0.011110929772257805, "regret_bot": 0.0272805355489254, "value_dist": 0.8569847345352173, "value_other_env": 0.8712223768234253, "value_corner": 0.835628092288971, "value_row": 0.8562098145484924, "value_any": 0.871139645576477, "value_bot": 0.8313461542129517, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11830.png", "entropy": 0.07930826395750046} +{"ts": "2026-03-20T20:13:06.669922Z", "loop": 11840, "env_steps": 7274496000, "exact_value_avg": 0.8620413541793823, "regret_dist": 0.0015393405919894576, "regret_other_env": 0.002565478440374136, "regret_corner": 1.3361375295062317e-07, "regret_row": 0.0015353423077613115, "regret_any": 0.0025628400035202503, "regret_bot": 0.001313120243139565, "value_dist": 0.8620413541793823, "value_other_env": 0.8796494603157043, "value_corner": 0.8356291055679321, "value_row": 0.8570913076400757, "value_any": 0.8796877264976501, "value_bot": 0.8573134541511536, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11840.png", "entropy": 0.07441338151693344} +{"ts": "2026-03-20T20:13:15.248102Z", "loop": 11850, "env_steps": 7280640000, "exact_value_avg": 0.8624078631401062, "regret_dist": 0.0011728592216968536, "regret_other_env": 0.0019547082483768463, "regret_corner": 8.543332796762115e-08, "regret_row": 0.002072960138320923, "regret_any": 0.0019521674839779735, "regret_bot": 0.0006837560795247555, "value_dist": 0.8624078631401062, "value_other_env": 0.8802602291107178, "value_corner": 0.8356292247772217, "value_row": 0.8565536737442017, "value_any": 0.8802984356880188, "value_bot": 0.8579428791999817, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11850.png", "entropy": 0.0760357677936554} +{"ts": "2026-03-20T20:13:23.826803Z", "loop": 11860, "env_steps": 7286784000, "exact_value_avg": 0.8633124828338623, "regret_dist": 0.00026819028425961733, "regret_other_env": 0.000446893012849614, "regret_corner": 1.3609728455321601e-07, "regret_row": 0.0006510643288493156, "regret_any": 0.00044623774010688066, "regret_bot": 0.0002741027856245637, "value_dist": 0.8633124828338623, "value_other_env": 0.881767988204956, "value_corner": 0.8356291651725769, "value_row": 0.8579756021499634, "value_any": 0.881804347038269, "value_bot": 0.858352541923523, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11860.png", "entropy": 0.07708819210529327} +{"ts": "2026-03-20T20:13:32.411237Z", "loop": 11870, "env_steps": 7292928000, "exact_value_avg": 0.8631179332733154, "regret_dist": 0.0004627332091331482, "regret_other_env": 0.0007710309000685811, "regret_corner": 2.865990040845645e-07, "regret_row": 0.0003297425573691726, "regret_any": 0.0007708112243562937, "regret_bot": 0.0015812418423593044, "value_dist": 0.8631179332733154, "value_other_env": 0.8814438581466675, "value_corner": 0.8356289863586426, "value_row": 0.8582968711853027, "value_any": 0.881479799747467, "value_bot": 0.8570453524589539, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11870.png", "entropy": 0.08572179824113846} +{"ts": "2026-03-20T20:13:40.991553Z", "loop": 11880, "env_steps": 7299072000, "exact_value_avg": 0.8619973063468933, "regret_dist": 0.0015834217192605138, "regret_other_env": 0.0026387625839561224, "regret_corner": 4.102786590465257e-07, "regret_row": 0.0006957047153264284, "regret_any": 0.0026544304564595222, "regret_bot": 0.0037256493233144283, "value_dist": 0.8619973063468933, "value_other_env": 0.8795762062072754, "value_corner": 0.8356289267539978, "value_row": 0.8579309582710266, "value_any": 0.8795961737632751, "value_bot": 0.8549008965492249, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11880.png", "entropy": 0.08235463500022888} +{"ts": "2026-03-20T20:13:49.575363Z", "loop": 11890, "env_steps": 7305216000, "exact_value_avg": 0.8620072603225708, "regret_dist": 0.0015734502812847495, "regret_other_env": 0.0026219398714601994, "regret_corner": 7.157524919421121e-07, "regret_row": 0.0005315991584211588, "regret_any": 0.0026386950630694628, "regret_bot": 0.004336995538324118, "value_dist": 0.8620072603225708, "value_other_env": 0.8795929551124573, "value_corner": 0.8356286287307739, "value_row": 0.858095109462738, "value_any": 0.8796119093894958, "value_bot": 0.8542896509170532, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11890.png", "entropy": 0.08406294882297516} +{"ts": "2026-03-20T20:13:58.157585Z", "loop": 11900, "env_steps": 7311360000, "exact_value_avg": 0.8632889986038208, "regret_dist": 0.00029168379842303693, "regret_other_env": 0.00048400810919702053, "regret_corner": 3.197292699042009e-06, "regret_row": 0.0010294875828549266, "regret_any": 0.0004833143320865929, "regret_bot": 0.0003655478358268738, "value_dist": 0.8632889986038208, "value_other_env": 0.881730854511261, "value_corner": 0.8356261253356934, "value_row": 0.8575971722602844, "value_any": 0.8817672729492188, "value_bot": 0.8582611083984375, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11900.png", "entropy": 0.08236081153154373} +{"ts": "2026-03-20T20:14:06.743702Z", "loop": 11910, "env_steps": 7317504000, "exact_value_avg": 0.8627489805221558, "regret_dist": 0.0008317201863974333, "regret_other_env": 0.001379644381813705, "regret_corner": 9.833773219725117e-06, "regret_row": 0.008599166758358479, "regret_any": 0.0013775884872302413, "regret_bot": 0.0004088899295311421, "value_dist": 0.8627489805221558, "value_other_env": 0.880835235118866, "value_corner": 0.8356195092201233, "value_row": 0.8500274419784546, "value_any": 0.8808729648590088, "value_bot": 0.858217716217041, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11910.png", "entropy": 0.0843648836016655} +{"ts": "2026-03-20T20:14:15.327326Z", "loop": 11920, "env_steps": 7323648000, "exact_value_avg": 0.8632340431213379, "regret_dist": 0.0003466284542810172, "regret_other_env": 0.0005692840204574168, "regret_corner": 1.2645125934795942e-05, "regret_row": 0.001190317329019308, "regret_any": 0.0005684758070856333, "regret_bot": 0.000915359880309552, "value_dist": 0.8632340431213379, "value_other_env": 0.8816455602645874, "value_corner": 0.8356166481971741, "value_row": 0.8574362993240356, "value_any": 0.8816821575164795, "value_bot": 0.8577113151550293, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11920.png", "entropy": 0.0889739841222763} +{"ts": "2026-03-20T20:14:23.906488Z", "loop": 11930, "env_steps": 7329792000, "exact_value_avg": 0.8631113171577454, "regret_dist": 0.00046940689207985997, "regret_other_env": 0.0007607513689436018, "regret_corner": 3.2390158594353124e-05, "regret_row": 0.0009603531798347831, "regret_any": 0.0007597216172143817, "regret_bot": 0.001714711426757276, "value_dist": 0.8631113171577454, "value_other_env": 0.8814541697502136, "value_corner": 0.8355969190597534, "value_row": 0.8576663732528687, "value_any": 0.8814908862113953, "value_bot": 0.8569118976593018, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11930.png", "entropy": 0.09475027024745941} +{"ts": "2026-03-20T20:14:32.491670Z", "loop": 11940, "env_steps": 7335936000, "exact_value_avg": 0.8629271984100342, "regret_dist": 0.0006534166168421507, "regret_other_env": 0.0009670586441643536, "regret_corner": 0.00018295348854735494, "regret_row": 0.001818134100176394, "regret_any": 0.0009657008922658861, "regret_bot": 0.0016724708257243037, "value_dist": 0.8629271984100342, "value_other_env": 0.8812477588653564, "value_corner": 0.8354463577270508, "value_row": 0.8568084239959717, "value_any": 0.8812848925590515, "value_bot": 0.8569540977478027, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11940.png", "entropy": 0.098914735019207} +{"ts": "2026-03-20T20:14:41.074906Z", "loop": 11950, "env_steps": 7342080000, "exact_value_avg": 0.8594518899917603, "regret_dist": 0.004128873813897371, "regret_other_env": 0.003047828795388341, "regret_corner": 0.005750441458076239, "regret_row": 0.012211296707391739, "regret_any": 0.0030432825442403555, "regret_bot": 0.0027830570470541716, "value_dist": 0.8594518899917603, "value_other_env": 0.8791670799255371, "value_corner": 0.8298789262771606, "value_row": 0.8464153409004211, "value_any": 0.8792073130607605, "value_bot": 0.8558436036109924, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11950.png", "entropy": 0.1054486632347107} +{"ts": "2026-03-20T20:14:49.653896Z", "loop": 11960, "env_steps": 7348224000, "exact_value_avg": 0.8631227016448975, "regret_dist": 0.00045795453479513526, "regret_other_env": 0.000730653468053788, "regret_corner": 4.890610944130458e-05, "regret_row": 0.0007029606495052576, "regret_any": 0.0007297482225112617, "regret_bot": 0.002312807599082589, "value_dist": 0.8631227016448975, "value_other_env": 0.8814842104911804, "value_corner": 0.8355804681777954, "value_row": 0.8579236268997192, "value_any": 0.8815208673477173, "value_bot": 0.8563137650489807, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11960.png", "entropy": 0.09881694614887238} +{"ts": "2026-03-20T20:14:58.241622Z", "loop": 11970, "env_steps": 7354368000, "exact_value_avg": 0.8632040619850159, "regret_dist": 0.0003766616864595562, "regret_other_env": 0.000612006988376379, "regret_corner": 2.3643673557671718e-05, "regret_row": 0.0010217524832114577, "regret_any": 0.0006111111142672598, "regret_bot": 0.001159259001724422, "value_dist": 0.8632040619850159, "value_other_env": 0.881602942943573, "value_corner": 0.8356056809425354, "value_row": 0.85760498046875, "value_any": 0.8816394209861755, "value_bot": 0.8574673533439636, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11970.png", "entropy": 0.0937994122505188} +{"ts": "2026-03-20T20:15:06.827564Z", "loop": 11980, "env_steps": 7360512000, "exact_value_avg": 0.8631029725074768, "regret_dist": 0.000477711291750893, "regret_other_env": 0.0007931237923912704, "regret_corner": 4.592538061842788e-06, "regret_row": 0.0011772633297368884, "regret_any": 0.0007919514318928123, "regret_bot": 0.00042068681796081364, "value_dist": 0.8631029725074768, "value_other_env": 0.8814217448234558, "value_corner": 0.8356247544288635, "value_row": 0.8574494123458862, "value_any": 0.8814586400985718, "value_bot": 0.8582059741020203, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11980.png", "entropy": 0.08556783199310303} +{"ts": "2026-03-20T20:15:15.419698Z", "loop": 11990, "env_steps": 7366656000, "exact_value_avg": 0.8630364537239075, "regret_dist": 0.0005442133406177163, "regret_other_env": 0.0009061039891093969, "regret_corner": 1.3773640148428967e-06, "regret_row": 0.0011841217055916786, "regret_any": 0.0009047695202752948, "regret_bot": 0.00033250232809223235, "value_dist": 0.8630364537239075, "value_other_env": 0.8813087940216064, "value_corner": 0.8356279134750366, "value_row": 0.8574425578117371, "value_any": 0.8813458681106567, "value_bot": 0.8582940697669983, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_11990.png", "entropy": 0.08194548636674881} +{"ts": "2026-03-20T20:15:24.003855Z", "loop": 12000, "env_steps": 7372800000, "exact_value_avg": 0.8625537157058716, "regret_dist": 0.001026924466714263, "regret_other_env": 0.0017107685562223196, "regret_corner": 1.1583169907680713e-06, "regret_row": 0.0015195072628557682, "regret_any": 0.0017083032289519906, "regret_bot": 0.00030540209263563156, "value_dist": 0.8625537157058716, "value_other_env": 0.8805041313171387, "value_corner": 0.8356281518936157, "value_row": 0.8571071624755859, "value_any": 0.8805423378944397, "value_bot": 0.8583213090896606, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12000.png", "entropy": 0.08101736009120941} +{"ts": "2026-03-20T20:15:32.595088Z", "loop": 12010, "env_steps": 7378944000, "exact_value_avg": 0.8633567094802856, "regret_dist": 0.00022401358000934124, "regret_other_env": 0.00037289567990228534, "regret_corner": 6.904205065438873e-07, "regret_row": 0.0006915072444826365, "regret_any": 0.0003723532136064023, "regret_bot": 0.00037178536877036095, "value_dist": 0.8633567094802856, "value_other_env": 0.8818420171737671, "value_corner": 0.8356286287307739, "value_row": 0.8579350709915161, "value_any": 0.8818782567977905, "value_bot": 0.8582549095153809, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12010.png", "entropy": 0.08182087540626526} +{"ts": "2026-03-20T20:15:41.175179Z", "loop": 12020, "env_steps": 7385088000, "exact_value_avg": 0.8617149591445923, "regret_dist": 0.0018656885949894786, "regret_other_env": 0.0031093403231352568, "regret_corner": 2.106030905224543e-07, "regret_row": 0.001685396651737392, "regret_any": 0.0031142046209424734, "regret_bot": 0.014262295328080654, "value_dist": 0.8617149591445923, "value_other_env": 0.8791055083274841, "value_corner": 0.8356291055679321, "value_row": 0.8569412231445312, "value_any": 0.8791364431381226, "value_bot": 0.8443642854690552, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12020.png", "entropy": 0.09420323371887207} +{"ts": "2026-03-20T20:15:49.759337Z", "loop": 12030, "env_steps": 7391232000, "exact_value_avg": 0.860647439956665, "regret_dist": 0.002933243755251169, "regret_other_env": 0.004888078197836876, "regret_corner": 9.919207286657183e-07, "regret_row": 0.0005406576092354953, "regret_any": 0.00488888006657362, "regret_bot": 0.023699695244431496, "value_dist": 0.860647439956665, "value_other_env": 0.8773268461227417, "value_corner": 0.8356282711029053, "value_row": 0.8580859303474426, "value_any": 0.8773618340492249, "value_bot": 0.8349269032478333, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12030.png", "entropy": 0.10051662474870682} +{"ts": "2026-03-20T20:15:58.343160Z", "loop": 12040, "env_steps": 7397376000, "exact_value_avg": 0.8618574142456055, "regret_dist": 0.0017233188264071941, "regret_other_env": 0.002871171338483691, "regret_corner": 1.5397866945932037e-06, "regret_row": 0.0003613774897530675, "regret_any": 0.0028690339531749487, "regret_bot": 0.015617309138178825, "value_dist": 0.8618574142456055, "value_other_env": 0.8793436884880066, "value_corner": 0.8356277942657471, "value_row": 0.858265221118927, "value_any": 0.879381537437439, "value_bot": 0.8430092930793762, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12040.png", "entropy": 0.10064339637756348} +{"ts": "2026-03-20T20:16:06.931745Z", "loop": 12050, "env_steps": 7403520000, "exact_value_avg": 0.8632797002792358, "regret_dist": 0.00030099094146862626, "regret_other_env": 0.000496892083901912, "regret_corner": 7.139146873669233e-06, "regret_row": 0.0003976039297413081, "regret_any": 0.0004961885861121118, "regret_bot": 0.0017659482546150684, "value_dist": 0.8632797002792358, "value_other_env": 0.8817180395126343, "value_corner": 0.8356221914291382, "value_row": 0.8582289814949036, "value_any": 0.881754457950592, "value_bot": 0.8568606972694397, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12050.png", "entropy": 0.09019453823566437} +{"ts": "2026-03-20T20:16:15.512688Z", "loop": 12060, "env_steps": 7409664000, "exact_value_avg": 0.8634016513824463, "regret_dist": 0.0001790538663044572, "regret_other_env": 0.0002955637173727155, "regret_corner": 4.289051048544934e-06, "regret_row": 0.0004646038287319243, "regret_any": 0.00029513408662751317, "regret_bot": 0.0007960603106766939, "value_dist": 0.8634016513824463, "value_other_env": 0.8819193243980408, "value_corner": 0.8356249928474426, "value_row": 0.8581620454788208, "value_any": 0.8819554448127747, "value_bot": 0.8578305840492249, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12060.png", "entropy": 0.08431979268789291} +{"ts": "2026-03-20T20:16:24.092263Z", "loop": 12070, "env_steps": 7415808000, "exact_value_avg": 0.8631318807601929, "regret_dist": 0.00044883269583806396, "regret_other_env": 0.000741032708901912, "regret_corner": 1.0532638043514453e-05, "regret_row": 0.0011264898348599672, "regret_any": 0.000740308896638453, "regret_bot": 0.00046864463365636766, "value_dist": 0.8631318807601929, "value_other_env": 0.8814738392829895, "value_corner": 0.8356187343597412, "value_row": 0.8575001955032349, "value_any": 0.881510317325592, "value_bot": 0.8581579923629761, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12070.png", "entropy": 0.08212630450725555} +{"ts": "2026-03-20T20:16:32.675218Z", "loop": 12080, "env_steps": 7421952000, "exact_value_avg": 0.8625173568725586, "regret_dist": 0.0010633994825184345, "regret_other_env": 0.001762168831191957, "regret_corner": 1.5245378563122358e-05, "regret_row": 0.002232929226011038, "regret_any": 0.0017606493784114718, "regret_bot": 0.00034705724101513624, "value_dist": 0.8625173568725586, "value_other_env": 0.8804528117179871, "value_corner": 0.8356140851974487, "value_row": 0.8563936948776245, "value_any": 0.8804900050163269, "value_bot": 0.8582795858383179, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12080.png", "entropy": 0.08274758607149124} +{"ts": "2026-03-20T20:16:41.260600Z", "loop": 12090, "env_steps": 7428096000, "exact_value_avg": 0.8633886575698853, "regret_dist": 0.00019197781512048095, "regret_other_env": 0.00031669833697378635, "regret_corner": 4.897018698102329e-06, "regret_row": 0.00046025667688809335, "regret_any": 0.0003163004294037819, "regret_bot": 0.0005535556701943278, "value_dist": 0.8633886575698853, "value_other_env": 0.8818981647491455, "value_corner": 0.8356243968009949, "value_row": 0.8581663966178894, "value_any": 0.8819342851638794, "value_bot": 0.8580730557441711, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12090.png", "entropy": 0.08499569445848465} +{"ts": "2026-03-20T20:16:49.849761Z", "loop": 12100, "env_steps": 7434240000, "exact_value_avg": 0.8630974292755127, "regret_dist": 0.00048321971553377807, "regret_other_env": 0.0008028339361771941, "regret_corner": 3.798306124735973e-06, "regret_row": 0.0009419915731996298, "regret_any": 0.0008016661740839481, "regret_bot": 0.0019130720756947994, "value_dist": 0.8630974292755127, "value_other_env": 0.8814120292663574, "value_corner": 0.8356255292892456, "value_row": 0.8576846718788147, "value_any": 0.8814489245414734, "value_bot": 0.8567135334014893, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12100.png", "entropy": 0.08875838667154312} +{"ts": "2026-03-20T20:16:58.439602Z", "loop": 12110, "env_steps": 7440384000, "exact_value_avg": 0.8615018129348755, "regret_dist": 0.002078915713354945, "regret_other_env": 0.003323930548503995, "regret_corner": 0.00021139334421604872, "regret_row": 0.008085159584879875, "regret_any": 0.003318960079923272, "regret_bot": 0.00861109234392643, "value_dist": 0.8615018129348755, "value_other_env": 0.8788909316062927, "value_corner": 0.8354179859161377, "value_row": 0.8505415320396423, "value_any": 0.8789317011833191, "value_bot": 0.8500155210494995, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12110.png", "entropy": 0.09782464057207108} +{"ts": "2026-03-20T20:17:07.024275Z", "loop": 12120, "env_steps": 7446528000, "exact_value_avg": 0.8568985462188721, "regret_dist": 0.006682112347334623, "regret_other_env": 0.011081463657319546, "regret_corner": 8.308440737891942e-05, "regret_row": 0.019278153777122498, "regret_any": 0.01106560043990612, "regret_bot": 0.0424608550965786, "value_dist": 0.8568985462188721, "value_other_env": 0.8711335062980652, "value_corner": 0.8355461955070496, "value_row": 0.8393484950065613, "value_any": 0.8711850047111511, "value_bot": 0.8161658048629761, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12120.png", "entropy": 0.11162607371807098} +{"ts": "2026-03-20T20:17:15.603710Z", "loop": 12130, "env_steps": 7452672000, "exact_value_avg": 0.8600484132766724, "regret_dist": 0.003532291855663061, "regret_other_env": 0.005873268470168114, "regret_corner": 2.0826857507927343e-05, "regret_row": 0.008973205462098122, "regret_any": 0.005869271699339151, "regret_bot": 0.012874651700258255, "value_dist": 0.8600484132766724, "value_other_env": 0.8763416409492493, "value_corner": 0.8356084823608398, "value_row": 0.8496534824371338, "value_any": 0.8763813376426697, "value_bot": 0.8457520008087158, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12130.png", "entropy": 0.10870242118835449} +{"ts": "2026-03-20T20:17:24.187484Z", "loop": 12140, "env_steps": 7458816000, "exact_value_avg": 0.8614976406097412, "regret_dist": 0.0020830552093684673, "regret_other_env": 0.003446961287409067, "regret_corner": 3.7195783079368994e-05, "regret_row": 0.00444399006664753, "regret_any": 0.003442019922658801, "regret_bot": 0.0052100359462201595, "value_dist": 0.8614976406097412, "value_other_env": 0.8787679076194763, "value_corner": 0.8355920314788818, "value_row": 0.8541827201843262, "value_any": 0.8788086175918579, "value_bot": 0.8534166216850281, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12140.png", "entropy": 0.10534382611513138} +{"ts": "2026-03-20T20:17:32.767298Z", "loop": 12150, "env_steps": 7464960000, "exact_value_avg": 0.8617730140686035, "regret_dist": 0.0018076928099617362, "regret_other_env": 0.0026225026231259108, "regret_corner": 0.0005854780902154744, "regret_row": 0.003845729399472475, "regret_any": 0.002618652069941163, "regret_bot": 0.0050849514082074165, "value_dist": 0.8617730140686035, "value_other_env": 0.8795923590660095, "value_corner": 0.8350438475608826, "value_row": 0.8547808527946472, "value_any": 0.8796319961547852, "value_bot": 0.8535416722297668, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12150.png", "entropy": 0.11305660754442215} +{"ts": "2026-03-20T20:17:41.344275Z", "loop": 12160, "env_steps": 7471104000, "exact_value_avg": 0.8610929250717163, "regret_dist": 0.002487742342054844, "regret_other_env": 0.0027205634396523237, "regret_corner": 0.0021385103464126587, "regret_row": 0.006504418328404427, "regret_any": 0.0027164656203240156, "regret_bot": 0.0038552379701286554, "value_dist": 0.8610929250717163, "value_other_env": 0.879494309425354, "value_corner": 0.833490788936615, "value_row": 0.8521221280097961, "value_any": 0.8795341849327087, "value_bot": 0.8547714352607727, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12160.png", "entropy": 0.11803052574396133} +{"ts": "2026-03-20T20:17:49.927242Z", "loop": 12170, "env_steps": 7477248000, "exact_value_avg": 0.8623566627502441, "regret_dist": 0.0012239995412528515, "regret_other_env": 0.001622770563699305, "regret_corner": 0.0006258428329601884, "regret_row": 0.0026555154472589493, "regret_any": 0.0016204274725168943, "regret_bot": 0.0023856700863689184, "value_dist": 0.8623566627502441, "value_other_env": 0.8805921077728271, "value_corner": 0.8350034952163696, "value_row": 0.8559711575508118, "value_any": 0.8806301951408386, "value_bot": 0.8562409281730652, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12170.png", "entropy": 0.10771935433149338} +{"ts": "2026-03-20T20:17:58.509348Z", "loop": 12180, "env_steps": 7483392000, "exact_value_avg": 0.8626517057418823, "regret_dist": 0.0009289902518503368, "regret_other_env": 0.0013190682511776686, "regret_corner": 0.00034387310734018683, "regret_row": 0.002143752295523882, "regret_any": 0.0013170989695936441, "regret_bot": 0.0027140972670167685, "value_dist": 0.8626517057418823, "value_other_env": 0.8808957934379578, "value_corner": 0.835285484790802, "value_row": 0.8564828038215637, "value_any": 0.8809335231781006, "value_bot": 0.8559126257896423, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12180.png", "entropy": 0.10903201252222061} +{"ts": "2026-03-20T20:18:07.095463Z", "loop": 12190, "env_steps": 7489536000, "exact_value_avg": 0.8564494848251343, "regret_dist": 0.007131163962185383, "regret_other_env": 0.004948197863996029, "regret_corner": 0.01040561217814684, "regret_row": 0.013013085350394249, "regret_any": 0.004941186867654324, "regret_bot": 0.00807003490626812, "value_dist": 0.8564494848251343, "value_other_env": 0.8772666454315186, "value_corner": 0.8252236843109131, "value_row": 0.8456135988235474, "value_any": 0.8773094415664673, "value_bot": 0.8505566120147705, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12190.png", "entropy": 0.1250496208667755} +{"ts": "2026-03-20T20:18:15.682753Z", "loop": 12200, "env_steps": 7495680000, "exact_value_avg": 0.8590401411056519, "regret_dist": 0.004540476948022842, "regret_other_env": 0.00746218441054225, "regret_corner": 0.00015791456098668277, "regret_row": 0.024902349337935448, "regret_any": 0.007455961778759956, "regret_bot": 0.006102589424699545, "value_dist": 0.8590401411056519, "value_other_env": 0.8747527003288269, "value_corner": 0.8354713916778564, "value_row": 0.833724319934845, "value_any": 0.874794602394104, "value_bot": 0.8525240421295166, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12200.png", "entropy": 0.10508500784635544} +{"ts": "2026-03-20T20:18:24.265844Z", "loop": 12210, "env_steps": 7501824000, "exact_value_avg": 0.8601328134536743, "regret_dist": 0.0034478772431612015, "regret_other_env": 0.005741173401474953, "regret_corner": 7.932385415188037e-06, "regret_row": 0.022144362330436707, "regret_any": 0.005735497456043959, "regret_bot": 0.003771475050598383, "value_dist": 0.8601328134536743, "value_other_env": 0.8764736652374268, "value_corner": 0.8356214165687561, "value_row": 0.8364822864532471, "value_any": 0.8765150904655457, "value_bot": 0.8548551201820374, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12210.png", "entropy": 0.09598550945520401} +{"ts": "2026-03-20T20:18:32.846521Z", "loop": 12220, "env_steps": 7507968000, "exact_value_avg": 0.8633279800415039, "regret_dist": 0.00025267968885600567, "regret_other_env": 0.0004206075973343104, "regret_corner": 7.877747520979028e-07, "regret_row": 0.000956979114562273, "regret_any": 0.00042002307600341737, "regret_bot": 0.0003662349481601268, "value_dist": 0.8633279800415039, "value_other_env": 0.881794273853302, "value_corner": 0.8356285691261292, "value_row": 0.8576697111129761, "value_any": 0.8818305730819702, "value_bot": 0.8582603335380554, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12220.png", "entropy": 0.08757427334785461} +{"ts": "2026-03-20T20:18:41.431506Z", "loop": 12230, "env_steps": 7514112000, "exact_value_avg": 0.8627973198890686, "regret_dist": 0.0007833775016479194, "regret_other_env": 0.0013048165710642934, "regret_corner": 1.2189150311314734e-06, "regret_row": 0.0026852875016629696, "regret_any": 0.0013035425217822194, "regret_bot": 0.0005897680530324578, "value_dist": 0.8627973198890686, "value_other_env": 0.8809100985527039, "value_corner": 0.8356280326843262, "value_row": 0.8559412956237793, "value_any": 0.8809470534324646, "value_bot": 0.8580368161201477, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12230.png", "entropy": 0.08112231642007828} +{"ts": "2026-03-20T20:18:50.012347Z", "loop": 12240, "env_steps": 7520256000, "exact_value_avg": 0.8614293932914734, "regret_dist": 0.0021512662060558796, "regret_other_env": 0.0035851907450705767, "regret_corner": 3.7898621485510375e-07, "regret_row": 0.012124222703278065, "regret_any": 0.0035926327109336853, "regret_bot": 0.0015001881401985884, "value_dist": 0.8614293932914734, "value_other_env": 0.8786296844482422, "value_corner": 0.8356289267539978, "value_row": 0.8465023636817932, "value_any": 0.8786579966545105, "value_bot": 0.8571264743804932, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12240.png", "entropy": 0.08367009460926056} +{"ts": "2026-03-20T20:18:58.591847Z", "loop": 12250, "env_steps": 7526400000, "exact_value_avg": 0.8624727725982666, "regret_dist": 0.001107875956222415, "regret_other_env": 0.00184630136936903, "regret_corner": 2.3792188130755676e-07, "regret_row": 0.007261240389198065, "regret_any": 0.001856692717410624, "regret_bot": 0.001067492994479835, "value_dist": 0.8624727725982666, "value_other_env": 0.8803685903549194, "value_corner": 0.8356290459632874, "value_row": 0.8513653874397278, "value_any": 0.880393922328949, "value_bot": 0.8575592041015625, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12250.png", "entropy": 0.08516884595155716} +{"ts": "2026-03-20T20:19:07.171613Z", "loop": 12260, "env_steps": 7532544000, "exact_value_avg": 0.86314857006073, "regret_dist": 0.0004321039014030248, "regret_other_env": 0.0007199893589131534, "regret_corner": 2.7567151050789107e-07, "regret_row": 0.0017627585912123322, "regret_any": 0.0007227517198771238, "regret_bot": 0.0007810576935298741, "value_dist": 0.86314857006073, "value_other_env": 0.8814948201179504, "value_corner": 0.8356290459632874, "value_row": 0.8568638563156128, "value_any": 0.8815277814865112, "value_bot": 0.8578456044197083, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12260.png", "entropy": 0.08604059368371964} +{"ts": "2026-03-20T20:19:15.753220Z", "loop": 12270, "env_steps": 7538688000, "exact_value_avg": 0.8631839752197266, "regret_dist": 0.0003966382937505841, "regret_other_env": 0.0006609548581764102, "regret_corner": 1.6341607533831848e-07, "regret_row": 0.0016347834607586265, "regret_any": 0.0006618008483201265, "regret_bot": 0.00044864468509331346, "value_dist": 0.8631839752197266, "value_other_env": 0.8815538883209229, "value_corner": 0.8356291651725769, "value_row": 0.8569918274879456, "value_any": 0.8815888166427612, "value_bot": 0.8581779599189758, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12270.png", "entropy": 0.08309818804264069} +{"ts": "2026-03-20T20:19:24.338545Z", "loop": 12280, "env_steps": 7544832000, "exact_value_avg": 0.8628197908401489, "regret_dist": 0.0007608757587149739, "regret_other_env": 0.0012680805521085858, "regret_corner": 6.85453471760411e-08, "regret_row": 0.0029435257893055677, "regret_any": 0.0012664503883570433, "regret_bot": 0.0009979127207770944, "value_dist": 0.8628197908401489, "value_other_env": 0.8809468150138855, "value_corner": 0.8356292247772217, "value_row": 0.8556830883026123, "value_any": 0.8809841871261597, "value_bot": 0.8576287031173706, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12280.png", "entropy": 0.0831817090511322} +{"ts": "2026-03-20T20:19:32.919855Z", "loop": 12290, "env_steps": 7550976000, "exact_value_avg": 0.8618500232696533, "regret_dist": 0.0017306336667388678, "regret_other_env": 0.0028842638712376356, "regret_corner": 1.882513487316828e-07, "regret_row": 0.004315220285207033, "regret_any": 0.002882084809243679, "regret_bot": 0.0023528635501861572, "value_dist": 0.8618500232696533, "value_other_env": 0.879330575466156, "value_corner": 0.8356291055679321, "value_row": 0.854311466217041, "value_any": 0.8793684840202332, "value_bot": 0.8562738299369812, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12290.png", "entropy": 0.08215776830911636} +{"ts": "2026-03-20T20:19:41.500571Z", "loop": 12300, "env_steps": 7557120000, "exact_value_avg": 0.8634600639343262, "regret_dist": 0.0001206405577249825, "regret_other_env": 0.00020048610167577863, "regret_corner": 8.722146844775125e-07, "regret_row": 0.00019356982375029474, "regret_any": 0.00020047124417033046, "regret_bot": 0.0005439794040285051, "value_dist": 0.8634600639343262, "value_other_env": 0.8820144534111023, "value_corner": 0.8356284499168396, "value_row": 0.8584330081939697, "value_any": 0.882050096988678, "value_bot": 0.8580827116966248, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12300.png", "entropy": 0.08625835180282593} +{"ts": "2026-03-20T20:19:50.079978Z", "loop": 12310, "env_steps": 7563264000, "exact_value_avg": 0.8632014989852905, "regret_dist": 0.0003791126364376396, "regret_other_env": 0.0006284936680458486, "regret_corner": 5.041063104727073e-06, "regret_row": 0.0005380812799558043, "regret_any": 0.0006295185885392129, "regret_bot": 0.00033141986932605505, "value_dist": 0.8632014989852905, "value_other_env": 0.8815863728523254, "value_corner": 0.8356242775917053, "value_row": 0.8580886125564575, "value_any": 0.8816210627555847, "value_bot": 0.858295202255249, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12310.png", "entropy": 0.07742224633693695} +{"ts": "2026-03-20T20:19:58.667730Z", "loop": 12320, "env_steps": 7569408000, "exact_value_avg": 0.8621892929077148, "regret_dist": 0.001391363563016057, "regret_other_env": 0.0023175394162535667, "regret_corner": 2.09957374863734e-06, "regret_row": 0.0022615815978497267, "regret_any": 0.00233915401622653, "regret_bot": 0.00354962982237339, "value_dist": 0.8621892929077148, "value_other_env": 0.8798973560333252, "value_corner": 0.8356271982192993, "value_row": 0.8563650250434875, "value_any": 0.879911482334137, "value_bot": 0.8550769686698914, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12320.png", "entropy": 0.07685089856386185} +{"ts": "2026-03-20T20:20:07.248976Z", "loop": 12330, "env_steps": 7575552000, "exact_value_avg": 0.8576877117156982, "regret_dist": 0.0058929831720888615, "regret_other_env": 0.00982050970196724, "regret_corner": 1.692772002570564e-06, "regret_row": 0.015854746103286743, "regret_any": 0.010008960962295532, "regret_bot": 0.03565950691699982, "value_dist": 0.8576877117156982, "value_other_env": 0.8723943829536438, "value_corner": 0.8356276750564575, "value_row": 0.8427719473838806, "value_any": 0.8722416162490845, "value_bot": 0.8229671120643616, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12330.png", "entropy": 0.07776516675949097} +{"ts": "2026-03-20T20:20:15.823589Z", "loop": 12340, "env_steps": 7581696000, "exact_value_avg": 0.8604704141616821, "regret_dist": 0.00311027723364532, "regret_other_env": 0.005181876011192799, "regret_corner": 2.8789045245503075e-06, "regret_row": 0.008770965971052647, "regret_any": 0.005213533062487841, "regret_bot": 0.004826580639928579, "value_dist": 0.8604704141616821, "value_other_env": 0.877032995223999, "value_corner": 0.835626482963562, "value_row": 0.8498556017875671, "value_any": 0.8770371079444885, "value_bot": 0.8538000583648682, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12340.png", "entropy": 0.07893388718366623} +{"ts": "2026-03-20T20:20:24.410755Z", "loop": 12350, "env_steps": 7587840000, "exact_value_avg": 0.8632800579071045, "regret_dist": 0.0003006459737662226, "regret_other_env": 0.000497015193104744, "regret_corner": 6.0920915530005004e-06, "regret_row": 0.0007208341849036515, "regret_any": 0.0005191311938688159, "regret_bot": 0.001074302475899458, "value_dist": 0.8632800579071045, "value_other_env": 0.8817179203033447, "value_corner": 0.8356232047080994, "value_row": 0.8579058051109314, "value_any": 0.8817315101623535, "value_bot": 0.8575523495674133, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12350.png", "entropy": 0.0829787328839302} +{"ts": "2026-03-20T20:20:32.995776Z", "loop": 12360, "env_steps": 7593984000, "exact_value_avg": 0.863381028175354, "regret_dist": 0.00019964971579611301, "regret_other_env": 0.00033147266367450356, "regret_corner": 1.9152960248902673e-06, "regret_row": 8.472330227959901e-05, "regret_any": 0.00033986131893470883, "regret_bot": 0.0013936784816905856, "value_dist": 0.863381028175354, "value_other_env": 0.8818833231925964, "value_corner": 0.8356274366378784, "value_row": 0.8585419058799744, "value_any": 0.8819107413291931, "value_bot": 0.8572329878807068, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12360.png", "entropy": 0.08993078023195267} +{"ts": "2026-03-20T20:20:41.582966Z", "loop": 12370, "env_steps": 7600128000, "exact_value_avg": 0.8633654117584229, "regret_dist": 0.0002153142268070951, "regret_other_env": 0.0003572573186829686, "regret_corner": 2.399583763690316e-06, "regret_row": 0.00036048507899977267, "regret_any": 0.0003794104850385338, "regret_bot": 0.00142135180067271, "value_dist": 0.8633654117584229, "value_other_env": 0.8818576335906982, "value_corner": 0.8356269001960754, "value_row": 0.8582661747932434, "value_any": 0.881871223449707, "value_bot": 0.8572052717208862, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12370.png", "entropy": 0.0878380686044693} +{"ts": "2026-03-20T20:20:50.173022Z", "loop": 12380, "env_steps": 7606272000, "exact_value_avg": 0.8630098104476929, "regret_dist": 0.0005709049291908741, "regret_other_env": 0.0009413011721335351, "regret_corner": 1.53104465425713e-05, "regret_row": 0.0011959313414990902, "regret_any": 0.0009583038627170026, "regret_bot": 0.0008160305442288518, "value_dist": 0.8630098104476929, "value_other_env": 0.8812735676765442, "value_corner": 0.8356139659881592, "value_row": 0.8574306964874268, "value_any": 0.8812923431396484, "value_bot": 0.8578106164932251, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12380.png", "entropy": 0.08339816331863403} +{"ts": "2026-03-20T20:20:58.766036Z", "loop": 12390, "env_steps": 7612416000, "exact_value_avg": 0.8614232540130615, "regret_dist": 0.002157478826120496, "regret_other_env": 0.003549519693478942, "regret_corner": 6.94170594215393e-05, "regret_row": 0.012451880611479282, "regret_any": 0.0035616587847471237, "regret_bot": 0.0008059445535764098, "value_dist": 0.8614232540130615, "value_other_env": 0.8786653876304626, "value_corner": 0.8355599641799927, "value_row": 0.8461747169494629, "value_any": 0.8786889314651489, "value_bot": 0.8578206300735474, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12390.png", "entropy": 0.08668173849582672} +{"ts": "2026-03-20T20:21:07.366450Z", "loop": 12400, "env_steps": 7618560000, "exact_value_avg": 0.8616859912872314, "regret_dist": 0.0018947446951642632, "regret_other_env": 0.0031141822692006826, "regret_corner": 6.558796303579584e-05, "regret_row": 0.00731281004846096, "regret_any": 0.003133665770292282, "regret_bot": 0.0013002410996705294, "value_dist": 0.8616859912872314, "value_other_env": 0.8791006803512573, "value_corner": 0.8355637788772583, "value_row": 0.8513138294219971, "value_any": 0.879116952419281, "value_bot": 0.8573263883590698, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12400.png", "entropy": 0.08948507159948349} +{"ts": "2026-03-20T20:21:15.961696Z", "loop": 12410, "env_steps": 7624704000, "exact_value_avg": 0.8622314929962158, "regret_dist": 0.0013491910649463534, "regret_other_env": 0.002244437113404274, "regret_corner": 6.322066383290803e-06, "regret_row": 0.003079039743170142, "regret_any": 0.0022683797869831324, "regret_bot": 0.0035165417939424515, "value_dist": 0.8622314929962158, "value_other_env": 0.8799704313278198, "value_corner": 0.835623025894165, "value_row": 0.8555476069450378, "value_any": 0.8799822330474854, "value_bot": 0.8551101088523865, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12410.png", "entropy": 0.09373693913221359} +{"ts": "2026-03-20T20:21:24.563570Z", "loop": 12420, "env_steps": 7630848000, "exact_value_avg": 0.8626004457473755, "regret_dist": 0.0009802350541576743, "regret_other_env": 0.0016230037435889244, "regret_corner": 1.60818308359012e-05, "regret_row": 0.0006027343915775418, "regret_any": 0.0016472400166094303, "regret_bot": 0.005316379480063915, "value_dist": 0.8626004457473755, "value_other_env": 0.880591869354248, "value_corner": 0.8356133103370667, "value_row": 0.8580239415168762, "value_any": 0.8806033730506897, "value_bot": 0.8533102869987488, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12420.png", "entropy": 0.10026471316814423} +{"ts": "2026-03-20T20:21:33.145024Z", "loop": 12430, "env_steps": 7636992000, "exact_value_avg": 0.8628790378570557, "regret_dist": 0.0007016987074166536, "regret_other_env": 0.0011115793604403734, "regret_corner": 8.68777497089468e-05, "regret_row": 0.0005289844120852649, "regret_any": 0.001120600732974708, "regret_bot": 0.003201408078894019, "value_dist": 0.8628790378570557, "value_other_env": 0.8811033368110657, "value_corner": 0.8355424404144287, "value_row": 0.8580976724624634, "value_any": 0.881130039691925, "value_bot": 0.8554251790046692, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12430.png", "entropy": 0.1043296828866005} +{"ts": "2026-03-20T20:21:41.727746Z", "loop": 12440, "env_steps": 7643136000, "exact_value_avg": 0.8630388975143433, "regret_dist": 0.0005418192013166845, "regret_other_env": 0.0008672940311953425, "regret_corner": 5.360693103284575e-05, "regret_row": 0.0005603088065981865, "regret_any": 0.000873437209520489, "regret_bot": 0.0023597769904881716, "value_dist": 0.8630388975143433, "value_other_env": 0.8813475966453552, "value_corner": 0.8355756998062134, "value_row": 0.8580663204193115, "value_any": 0.8813772201538086, "value_bot": 0.8562669157981873, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12440.png", "entropy": 0.10127159208059311} +{"ts": "2026-03-20T20:21:50.309179Z", "loop": 12450, "env_steps": 7649280000, "exact_value_avg": 0.862636923789978, "regret_dist": 0.0009437153930775821, "regret_other_env": 0.0014768858673051, "regret_corner": 0.00014395962352864444, "regret_row": 0.0004239599220454693, "regret_any": 0.0014797255862504244, "regret_bot": 0.003829335328191519, "value_dist": 0.862636923789978, "value_other_env": 0.8807379603385925, "value_corner": 0.8354853987693787, "value_row": 0.8582026362419128, "value_any": 0.8807708024978638, "value_bot": 0.85479736328125, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12450.png", "entropy": 0.1066974401473999} +{"ts": "2026-03-20T20:21:58.890519Z", "loop": 12460, "env_steps": 7655424000, "exact_value_avg": 0.8613828420639038, "regret_dist": 0.0021978244185447693, "regret_other_env": 0.0029283431358635426, "regret_corner": 0.0011020462261512876, "regret_row": 0.0007559862569905818, "regret_any": 0.0029345841612666845, "regret_bot": 0.005746366456151009, "value_dist": 0.8613828420639038, "value_other_env": 0.879286527633667, "value_corner": 0.8345272541046143, "value_row": 0.8578706383705139, "value_any": 0.8793160319328308, "value_bot": 0.8528802990913391, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12460.png", "entropy": 0.11962305754423141} +{"ts": "2026-03-20T20:22:07.466980Z", "loop": 12470, "env_steps": 7661568000, "exact_value_avg": 0.8624959588050842, "regret_dist": 0.00108470325358212, "regret_other_env": 0.0014206412015482783, "regret_corner": 0.0005807961570098996, "regret_row": 0.001449792878702283, "regret_any": 0.0014217204879969358, "regret_bot": 0.0017820862121880054, "value_dist": 0.8624959588050842, "value_other_env": 0.8807942271232605, "value_corner": 0.8350485563278198, "value_row": 0.8571768999099731, "value_any": 0.880828857421875, "value_bot": 0.8568444848060608, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12470.png", "entropy": 0.10894792526960373} +{"ts": "2026-03-20T20:22:16.040262Z", "loop": 12480, "env_steps": 7667712000, "exact_value_avg": 0.8622406721115112, "regret_dist": 0.0013400078751146793, "regret_other_env": 0.002178625902161002, "regret_corner": 8.208056533476338e-05, "regret_row": 0.0071611562743783, "regret_any": 0.002177440794184804, "regret_bot": 0.0007502052467316389, "value_dist": 0.8622406721115112, "value_other_env": 0.8800362348556519, "value_corner": 0.8355473279953003, "value_row": 0.8514654636383057, "value_any": 0.8800731897354126, "value_bot": 0.8578764796257019, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12480.png", "entropy": 0.09379251301288605} +{"ts": "2026-03-20T20:22:24.619994Z", "loop": 12490, "env_steps": 7673856000, "exact_value_avg": 0.8630651235580444, "regret_dist": 0.0005155755206942558, "regret_other_env": 0.000857542094308883, "regret_corner": 2.6255847842548974e-06, "regret_row": 0.0006699863588437438, "regret_any": 0.0008626481285318732, "regret_bot": 0.0005142938462086022, "value_dist": 0.8630651235580444, "value_other_env": 0.8813573718070984, "value_corner": 0.8356267213821411, "value_row": 0.8579566478729248, "value_any": 0.8813878893852234, "value_bot": 0.8581123948097229, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12490.png", "entropy": 0.08232846111059189} +{"ts": "2026-03-20T20:22:33.201689Z", "loop": 12500, "env_steps": 7680000000, "exact_value_avg": 0.8623875379562378, "regret_dist": 0.001193147269077599, "regret_other_env": 0.0019882689230144024, "regret_corner": 4.6491624061673065e-07, "regret_row": 0.0012943507172167301, "regret_any": 0.002006063237786293, "regret_bot": 0.0011604505125433207, "value_dist": 0.8623875379562378, "value_other_env": 0.8802266120910645, "value_corner": 0.835628867149353, "value_row": 0.8573323488235474, "value_any": 0.8802445530891418, "value_bot": 0.8574662208557129, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12500.png", "entropy": 0.07814644277095795} +{"ts": "2026-03-20T20:22:41.787660Z", "loop": 12510, "env_steps": 7686144000, "exact_value_avg": 0.8612596988677979, "regret_dist": 0.0023209606297314167, "regret_other_env": 0.0038678771816194057, "regret_corner": 5.85615680392948e-07, "regret_row": 0.0013922892976552248, "regret_any": 0.0038866407703608274, "regret_bot": 0.0026618284173309803, "value_dist": 0.8612596988677979, "value_other_env": 0.8783470392227173, "value_corner": 0.8356287479400635, "value_row": 0.8572342991828918, "value_any": 0.8783639073371887, "value_bot": 0.8559647798538208, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12510.png", "entropy": 0.07876715064048767} +{"ts": "2026-03-20T20:22:50.370370Z", "loop": 12520, "env_steps": 7692288000, "exact_value_avg": 0.8556302785873413, "regret_dist": 0.00795035995543003, "regret_other_env": 0.013249612413346767, "regret_corner": 1.4806787476118188e-06, "regret_row": 0.004017818719148636, "regret_any": 0.013356069102883339, "regret_bot": 0.022109996527433395, "value_dist": 0.8556302785873413, "value_other_env": 0.868965208530426, "value_corner": 0.8356278538703918, "value_row": 0.8546088933944702, "value_any": 0.8688945174217224, "value_bot": 0.8365166783332825, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12520.png", "entropy": 0.08282329142093658} +{"ts": "2026-03-20T20:22:58.952160Z", "loop": 12530, "env_steps": 7698432000, "exact_value_avg": 0.86003577709198, "regret_dist": 0.0035448623821139336, "regret_other_env": 0.005907698534429073, "regret_corner": 6.079674221837195e-07, "regret_row": 0.005502671003341675, "regret_any": 0.005925199948251247, "regret_bot": 0.0042510502971708775, "value_dist": 0.86003577709198, "value_other_env": 0.8763071298599243, "value_corner": 0.8356287479400635, "value_row": 0.8531240224838257, "value_any": 0.8763253688812256, "value_bot": 0.8543756604194641, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12530.png", "entropy": 0.08450465649366379} +{"ts": "2026-03-20T20:23:07.526074Z", "loop": 12540, "env_steps": 7704576000, "exact_value_avg": 0.862093448638916, "regret_dist": 0.0014872790779918432, "regret_other_env": 0.0024775827769190073, "regret_corner": 1.8234055687571527e-06, "regret_row": 0.0033520900178700686, "regret_any": 0.0024998013395816088, "regret_bot": 0.0017862641252577305, "value_dist": 0.862093448638916, "value_other_env": 0.8797373175621033, "value_corner": 0.835627555847168, "value_row": 0.855274498462677, "value_any": 0.8797507286071777, "value_bot": 0.8568403720855713, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12540.png", "entropy": 0.0866977870464325} +{"ts": "2026-03-20T20:23:16.103256Z", "loop": 12550, "env_steps": 7710720000, "exact_value_avg": 0.862970232963562, "regret_dist": 0.0006104212370701134, "regret_other_env": 0.0010167283471673727, "regret_corner": 9.60628199209168e-07, "regret_row": 0.0038149161264300346, "regret_any": 0.001031582592986524, "regret_bot": 0.0010019363835453987, "value_dist": 0.862970232963562, "value_other_env": 0.8811981678009033, "value_corner": 0.8356282711029053, "value_row": 0.8548117876052856, "value_any": 0.8812189698219299, "value_bot": 0.8576247692108154, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12550.png", "entropy": 0.08717554807662964} +{"ts": "2026-03-20T20:23:24.683231Z", "loop": 12560, "env_steps": 7716864000, "exact_value_avg": 0.8618550300598145, "regret_dist": 0.0017256836872547865, "regret_other_env": 0.0028750705532729626, "regret_corner": 1.603365035407478e-06, "regret_row": 0.013019077479839325, "regret_any": 0.0028750731144100428, "regret_bot": 0.0009106376674026251, "value_dist": 0.8618550300598145, "value_other_env": 0.8793398141860962, "value_corner": 0.8356277346611023, "value_row": 0.8456076383590698, "value_any": 0.8793755173683167, "value_bot": 0.857715904712677, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12560.png", "entropy": 0.08482450991868973} +{"ts": "2026-03-20T20:23:33.265707Z", "loop": 12570, "env_steps": 7723008000, "exact_value_avg": 0.8623995780944824, "regret_dist": 0.001181058119982481, "regret_other_env": 0.001965730683878064, "regret_corner": 4.049142262374517e-06, "regret_row": 0.005577609874308109, "regret_any": 0.0019860491156578064, "regret_bot": 0.002013478195294738, "value_dist": 0.8623995780944824, "value_other_env": 0.8802491426467896, "value_corner": 0.8356252908706665, "value_row": 0.8530489802360535, "value_any": 0.8802645802497864, "value_bot": 0.8566131591796875, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12570.png", "entropy": 0.08703196048736572} +{"ts": "2026-03-20T20:23:41.848731Z", "loop": 12580, "env_steps": 7729152000, "exact_value_avg": 0.8624544143676758, "regret_dist": 0.0011262726038694382, "regret_other_env": 0.0018724154215306044, "regret_corner": 7.058183655317407e-06, "regret_row": 0.0024862505961209536, "regret_any": 0.001894343295134604, "regret_bot": 0.0028950627893209457, "value_dist": 0.8624544143676758, "value_other_env": 0.8803424835205078, "value_corner": 0.835622251033783, "value_row": 0.8561403751373291, "value_any": 0.8803562521934509, "value_bot": 0.8557315468788147, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12580.png", "entropy": 0.08759042620658875} +{"ts": "2026-03-20T20:23:50.427112Z", "loop": 12590, "env_steps": 7735296000, "exact_value_avg": 0.8624598383903503, "regret_dist": 0.0011208272771909833, "regret_other_env": 0.0018654284067451954, "regret_corner": 3.925462806364521e-06, "regret_row": 0.0013701460557058454, "regret_any": 0.0018877357942983508, "regret_bot": 0.005142156966030598, "value_dist": 0.8624598383903503, "value_other_env": 0.8803494572639465, "value_corner": 0.8356253504753113, "value_row": 0.8572564721107483, "value_any": 0.880362868309021, "value_bot": 0.8534845113754272, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12590.png", "entropy": 0.08822492510080338} +{"ts": "2026-03-20T20:23:59.010012Z", "loop": 12600, "env_steps": 7741440000, "exact_value_avg": 0.8624232411384583, "regret_dist": 0.0011574741220101714, "regret_other_env": 0.0019262594869360328, "regret_corner": 4.29600504503469e-06, "regret_row": 0.001275758957490325, "regret_any": 0.001948281074874103, "regret_bot": 0.0033142792526632547, "value_dist": 0.8624232411384583, "value_other_env": 0.8802886009216309, "value_corner": 0.8356250524520874, "value_row": 0.8573509454727173, "value_any": 0.8803023099899292, "value_bot": 0.8553123474121094, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12600.png", "entropy": 0.08770216256380081} +{"ts": "2026-03-20T20:24:07.593404Z", "loop": 12610, "env_steps": 7747584000, "exact_value_avg": 0.8610423803329468, "regret_dist": 0.0025383022148162127, "regret_other_env": 0.004199427552521229, "regret_corner": 4.6613815356977284e-05, "regret_row": 0.006210045889019966, "regret_any": 0.004223306197673082, "regret_bot": 0.0026343814097344875, "value_dist": 0.8610423803329468, "value_other_env": 0.878015398979187, "value_corner": 0.8355827331542969, "value_row": 0.8524165749549866, "value_any": 0.8780273199081421, "value_bot": 0.855992317199707, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12610.png", "entropy": 0.08917096257209778} +{"ts": "2026-03-20T20:24:16.174646Z", "loop": 12620, "env_steps": 7753728000, "exact_value_avg": 0.8620364665985107, "regret_dist": 0.0015442389994859695, "regret_other_env": 0.002342579886317253, "regret_corner": 0.00034672769834287465, "regret_row": 0.002306252019479871, "regret_any": 0.0023644971661269665, "regret_bot": 0.001425290829502046, "value_dist": 0.8620364665985107, "value_other_env": 0.8798723220825195, "value_corner": 0.835282564163208, "value_row": 0.856320321559906, "value_any": 0.8798861503601074, "value_bot": 0.8572013974189758, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12620.png", "entropy": 0.09005608409643173} +{"ts": "2026-03-20T20:24:24.760016Z", "loop": 12630, "env_steps": 7759872000, "exact_value_avg": 0.8632113933563232, "regret_dist": 0.0003693281323648989, "regret_other_env": 0.000498532666824758, "regret_corner": 0.00017552128701936454, "regret_row": 0.00041938680806197226, "regret_any": 0.000512505997903645, "regret_bot": 0.0006913461838848889, "value_dist": 0.8632113933563232, "value_other_env": 0.8817163705825806, "value_corner": 0.8354538679122925, "value_row": 0.8582071661949158, "value_any": 0.8817380666732788, "value_bot": 0.8579353094100952, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12630.png", "entropy": 0.08960992097854614} +{"ts": "2026-03-20T20:24:33.351323Z", "loop": 12640, "env_steps": 7766016000, "exact_value_avg": 0.8634897470474243, "regret_dist": 9.089444938581437e-05, "regret_other_env": 0.0001398976455675438, "regret_corner": 1.7389655113220215e-05, "regret_row": 0.00011552363866940141, "regret_any": 0.000139732044772245, "regret_bot": 0.0001853732392191887, "value_dist": 0.8634897470474243, "value_other_env": 0.8820750117301941, "value_corner": 0.835611879825592, "value_row": 0.8585111498832703, "value_any": 0.8821108937263489, "value_bot": 0.8584412932395935, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12640.png", "entropy": 0.0895853191614151} +{"ts": "2026-03-20T20:24:41.937338Z", "loop": 12650, "env_steps": 7772160000, "exact_value_avg": 0.8623533248901367, "regret_dist": 0.001227382104843855, "regret_other_env": 0.0020278478041291237, "regret_corner": 2.668351044121664e-05, "regret_row": 0.0011358025949448347, "regret_any": 0.0020260598976165056, "regret_bot": 0.009159300476312637, "value_dist": 0.8623533248901367, "value_other_env": 0.8801869750022888, "value_corner": 0.8356026411056519, "value_row": 0.8574908375740051, "value_any": 0.8802245259284973, "value_bot": 0.8494672775268555, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12650.png", "entropy": 0.10164603590965271} +{"ts": "2026-03-20T20:24:50.518166Z", "loop": 12660, "env_steps": 7778304000, "exact_value_avg": 0.8626513481140137, "regret_dist": 0.0009293926414102316, "regret_other_env": 0.0015114268753677607, "regret_corner": 5.6341294111916795e-05, "regret_row": 0.0004378791491035372, "regret_any": 0.0015095982234925032, "regret_bot": 0.0025936600286513567, "value_dist": 0.8626513481140137, "value_other_env": 0.8807035088539124, "value_corner": 0.8355729579925537, "value_row": 0.8581887483596802, "value_any": 0.8807410597801208, "value_bot": 0.8560330271720886, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12660.png", "entropy": 0.09958425909280777} +{"ts": "2026-03-20T20:24:59.104347Z", "loop": 12670, "env_steps": 7784448000, "exact_value_avg": 0.863139271736145, "regret_dist": 0.00044146980508230627, "regret_other_env": 0.0006635828758589923, "regret_corner": 0.00010830015526153147, "regret_row": 0.00033748202258720994, "regret_any": 0.0006627477705478668, "regret_bot": 0.0007544331019744277, "value_dist": 0.863139271736145, "value_other_env": 0.8815513253211975, "value_corner": 0.8355209827423096, "value_row": 0.8582891821861267, "value_any": 0.8815878629684448, "value_bot": 0.8578721880912781, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12670.png", "entropy": 0.10346898436546326} +{"ts": "2026-03-20T20:25:07.686263Z", "loop": 12680, "env_steps": 7790592000, "exact_value_avg": 0.8624460697174072, "regret_dist": 0.0011345773236826062, "regret_other_env": 0.0016581225208938122, "regret_corner": 0.000349259382346645, "regret_row": 0.0010245884768664837, "regret_any": 0.0016561453230679035, "regret_bot": 0.002216893248260021, "value_dist": 0.8624460697174072, "value_other_env": 0.8805567026138306, "value_corner": 0.8352800607681274, "value_row": 0.857602059841156, "value_any": 0.8805944323539734, "value_bot": 0.8564097881317139, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12680.png", "entropy": 0.11719168722629547} +{"ts": "2026-03-20T20:25:16.262562Z", "loop": 12690, "env_steps": 7796736000, "exact_value_avg": 0.8608556985855103, "regret_dist": 0.002724939025938511, "regret_other_env": 0.004370387643575668, "regret_corner": 0.00025676540099084377, "regret_row": 0.0016440910985693336, "regret_any": 0.004364647436887026, "regret_bot": 0.0030007450841367245, "value_dist": 0.8608556985855103, "value_other_env": 0.8778444528579712, "value_corner": 0.8353725671768188, "value_row": 0.8569825887680054, "value_any": 0.8778859972953796, "value_bot": 0.8556258678436279, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12690.png", "entropy": 0.11262548714876175} +{"ts": "2026-03-20T20:25:24.847105Z", "loop": 12700, "env_steps": 7802880000, "exact_value_avg": 0.8630568981170654, "regret_dist": 0.0005238174926489592, "regret_other_env": 0.0008625588961876929, "regret_corner": 1.570532731420826e-05, "regret_row": 0.000973785063251853, "regret_any": 0.0008613877580501139, "regret_bot": 0.0011829485883936286, "value_dist": 0.8630568981170654, "value_other_env": 0.8813523054122925, "value_corner": 0.8356136679649353, "value_row": 0.8576528429985046, "value_any": 0.8813892602920532, "value_bot": 0.8574436902999878, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12700.png", "entropy": 0.09088689833879471} +{"ts": "2026-03-20T20:25:33.433296Z", "loop": 12710, "env_steps": 7809024000, "exact_value_avg": 0.862372875213623, "regret_dist": 0.0012078353902325034, "regret_other_env": 0.0019681660924106836, "regret_corner": 6.73393442411907e-05, "regret_row": 0.0050353906117379665, "regret_any": 0.0019652782939374447, "regret_bot": 0.0009707885910756886, "value_dist": 0.862372875213623, "value_other_env": 0.8802467584609985, "value_corner": 0.835561990737915, "value_row": 0.85359126329422, "value_any": 0.8802853226661682, "value_bot": 0.8576558232307434, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12710.png", "entropy": 0.08678510040044785} +{"ts": "2026-03-20T20:25:42.015244Z", "loop": 12720, "env_steps": 7815168000, "exact_value_avg": 0.8633246421813965, "regret_dist": 0.0002560084976721555, "regret_other_env": 0.00041987892473116517, "regret_corner": 1.020282525132643e-05, "regret_row": 0.0003823665319941938, "regret_any": 0.00041932970634661615, "regret_bot": 0.0004816496220882982, "value_dist": 0.8633246421813965, "value_other_env": 0.8817949891090393, "value_corner": 0.8356191515922546, "value_row": 0.8582442402839661, "value_any": 0.8818312883377075, "value_bot": 0.858144998550415, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12720.png", "entropy": 0.08819709718227386} +{"ts": "2026-03-20T20:25:50.598919Z", "loop": 12730, "env_steps": 7821312000, "exact_value_avg": 0.8634829521179199, "regret_dist": 9.764648712007329e-05, "regret_other_env": 0.000157621456310153, "regret_corner": 7.684032425459009e-06, "regret_row": 0.00011723231000360101, "regret_any": 0.00015748523583170027, "regret_bot": 0.00031227595172822475, "value_dist": 0.8634829521179199, "value_other_env": 0.882057249546051, "value_corner": 0.8356215953826904, "value_row": 0.858509361743927, "value_any": 0.8820931315422058, "value_bot": 0.8583144545555115, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12730.png", "entropy": 0.08982347697019577} +{"ts": "2026-03-20T20:25:59.180359Z", "loop": 12740, "env_steps": 7827456000, "exact_value_avg": 0.8634763956069946, "regret_dist": 0.00010428956738905981, "regret_other_env": 0.00017038370424415916, "regret_corner": 5.148351647221716e-06, "regret_row": 6.635441968683153e-05, "regret_any": 0.00017165309691336006, "regret_bot": 0.0005157473497092724, "value_dist": 0.8634763956069946, "value_other_env": 0.8820444941520691, "value_corner": 0.8356242179870605, "value_row": 0.8585602641105652, "value_any": 0.8820788860321045, "value_bot": 0.858110785484314, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12740.png", "entropy": 0.09146676957607269} +{"ts": "2026-03-20T20:26:07.771006Z", "loop": 12750, "env_steps": 7833600000, "exact_value_avg": 0.8620117902755737, "regret_dist": 0.0015688902931287885, "regret_other_env": 0.0026136639062315226, "regret_corner": 1.7295282077611773e-06, "regret_row": 0.0016996811609715223, "regret_any": 0.002636644756421447, "regret_bot": 0.012298496440052986, "value_dist": 0.8620117902755737, "value_other_env": 0.879601240158081, "value_corner": 0.835627555847168, "value_row": 0.8569269180297852, "value_any": 0.8796139359474182, "value_bot": 0.8463281393051147, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12750.png", "entropy": 0.0925285592675209} +{"ts": "2026-03-20T20:26:16.351680Z", "loop": 12760, "env_steps": 7839744000, "exact_value_avg": 0.8632156848907471, "regret_dist": 0.0003649677964858711, "regret_other_env": 0.0006040374864824116, "regret_corner": 6.363292868627468e-06, "regret_row": 0.0003910650557372719, "regret_any": 0.0006284276023507118, "regret_bot": 0.00160241371486336, "value_dist": 0.8632156848907471, "value_other_env": 0.8816108107566833, "value_corner": 0.8356229662895203, "value_row": 0.8582356572151184, "value_any": 0.8816222548484802, "value_bot": 0.8570241928100586, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12760.png", "entropy": 0.086543008685112} +{"ts": "2026-03-20T20:26:24.934868Z", "loop": 12770, "env_steps": 7845888000, "exact_value_avg": 0.862303614616394, "regret_dist": 0.0012770984321832657, "regret_other_env": 0.0020961996633559465, "regret_corner": 4.8446658183820546e-05, "regret_row": 0.0019458651077002287, "regret_any": 0.002120273420587182, "regret_bot": 0.0019262970890849829, "value_dist": 0.862303614616394, "value_other_env": 0.8801186680793762, "value_corner": 0.8355808854103088, "value_row": 0.8566807508468628, "value_any": 0.8801303505897522, "value_bot": 0.8567003607749939, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12770.png", "entropy": 0.08524620532989502} +{"ts": "2026-03-20T20:26:33.516461Z", "loop": 12780, "env_steps": 7852032000, "exact_value_avg": 0.86182701587677, "regret_dist": 0.0017536442028358579, "regret_other_env": 0.0028947058599442244, "regret_corner": 4.205157529213466e-05, "regret_row": 0.003023264231160283, "regret_any": 0.0029205516912043095, "regret_bot": 0.003043264616280794, "value_dist": 0.86182701587677, "value_other_env": 0.8793201446533203, "value_corner": 0.8355872631072998, "value_row": 0.8556033968925476, "value_any": 0.879330039024353, "value_bot": 0.8555833697319031, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12780.png", "entropy": 0.08621900528669357} +{"ts": "2026-03-20T20:26:42.093744Z", "loop": 12790, "env_steps": 7858176000, "exact_value_avg": 0.8629755973815918, "regret_dist": 0.0006051099044270813, "regret_other_env": 0.001003362936899066, "regret_corner": 7.730226570856757e-06, "regret_row": 0.0009086246718652546, "regret_any": 0.0010312753729522228, "regret_bot": 0.001863644807599485, "value_dist": 0.8629755973815918, "value_other_env": 0.881211519241333, "value_corner": 0.8356215357780457, "value_row": 0.8577179312705994, "value_any": 0.8812192678451538, "value_bot": 0.8567630648612976, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12790.png", "entropy": 0.08279816806316376} +{"ts": "2026-03-20T20:26:50.681189Z", "loop": 12800, "env_steps": 7864320000, "exact_value_avg": 0.8631511330604553, "regret_dist": 0.0004295038525015116, "regret_other_env": 0.0007131290622055531, "regret_corner": 4.066030214744387e-06, "regret_row": 0.0014923225389793515, "regret_any": 0.0007370737730525434, "regret_bot": 0.001622925279662013, "value_dist": 0.8631511330604553, "value_other_env": 0.8815016746520996, "value_corner": 0.8356252312660217, "value_row": 0.857134222984314, "value_any": 0.8815135359764099, "value_bot": 0.8570036888122559, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12800.png", "entropy": 0.08511144667863846} +{"ts": "2026-03-20T20:26:59.266046Z", "loop": 12810, "env_steps": 7870464000, "exact_value_avg": 0.862812876701355, "regret_dist": 0.0007677684770897031, "regret_other_env": 0.0012764377752318978, "regret_corner": 4.764397999679204e-06, "regret_row": 0.0021412272471934557, "regret_any": 0.0012992741540074348, "regret_bot": 0.0040687560103833675, "value_dist": 0.862812876701355, "value_other_env": 0.8809384703636169, "value_corner": 0.8356245756149292, "value_row": 0.8564854264259338, "value_any": 0.8809513449668884, "value_bot": 0.8545579314231873, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12810.png", "entropy": 0.09332985430955887} +{"ts": "2026-03-20T20:27:07.845498Z", "loop": 12820, "env_steps": 7876608000, "exact_value_avg": 0.8619797229766846, "regret_dist": 0.0016009814571589231, "regret_other_env": 0.0026645020116120577, "regret_corner": 5.7006877796084154e-06, "regret_row": 0.004107439890503883, "regret_any": 0.002686093794181943, "regret_bot": 0.006361162289977074, "value_dist": 0.8619797229766846, "value_other_env": 0.8795503973960876, "value_corner": 0.8356236815452576, "value_row": 0.8545191884040833, "value_any": 0.8795644640922546, "value_bot": 0.852265477180481, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12820.png", "entropy": 0.09474251419305801} +{"ts": "2026-03-20T20:27:16.429206Z", "loop": 12830, "env_steps": 7882752000, "exact_value_avg": 0.8634613752365112, "regret_dist": 0.00011934951908187941, "regret_other_env": 0.0001961909292731434, "regret_corner": 4.087388788320823e-06, "regret_row": 0.0002191343082813546, "regret_any": 0.0002137761184712872, "regret_bot": 0.0007708302582614124, "value_dist": 0.8634613752365112, "value_other_env": 0.8820187449455261, "value_corner": 0.8356252312660217, "value_row": 0.8584074974060059, "value_any": 0.8820368051528931, "value_bot": 0.8578557372093201, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12830.png", "entropy": 0.0879652351140976} +{"ts": "2026-03-20T20:27:25.008522Z", "loop": 12840, "env_steps": 7888896000, "exact_value_avg": 0.8631191253662109, "regret_dist": 0.00046156448661349714, "regret_other_env": 0.0007331262459047139, "regret_corner": 5.422185131465085e-05, "regret_row": 0.0013940390199422836, "regret_any": 0.0007564850966446102, "regret_bot": 0.0013859522296115756, "value_dist": 0.8631191253662109, "value_other_env": 0.8814817667007446, "value_corner": 0.8355751633644104, "value_row": 0.8572326302528381, "value_any": 0.8814941644668579, "value_bot": 0.8572407960891724, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12840.png", "entropy": 0.08255585283041} +{"ts": "2026-03-20T20:27:33.588931Z", "loop": 12850, "env_steps": 7895040000, "exact_value_avg": 0.8623676300048828, "regret_dist": 0.0012131341500207782, "regret_other_env": 0.0018407618626952171, "regret_corner": 0.00027169237728230655, "regret_row": 0.004474875051528215, "regret_any": 0.0018622963689267635, "regret_bot": 0.0020954078063368797, "value_dist": 0.8623676300048828, "value_other_env": 0.8803741335868835, "value_corner": 0.835357666015625, "value_row": 0.854151725769043, "value_any": 0.8803882598876953, "value_bot": 0.8565312027931213, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12850.png", "entropy": 0.08421894162893295} +{"ts": "2026-03-20T20:27:42.167495Z", "loop": 12860, "env_steps": 7901184000, "exact_value_avg": 0.8628487586975098, "regret_dist": 0.0007319874712266028, "regret_other_env": 0.0012014353414997458, "regret_corner": 2.7815502107841894e-05, "regret_row": 0.004756081383675337, "regret_any": 0.001216622651554644, "regret_bot": 0.0013301802100613713, "value_dist": 0.8628487586975098, "value_other_env": 0.8810135126113892, "value_corner": 0.8356015682220459, "value_row": 0.8538706302642822, "value_any": 0.8810340166091919, "value_bot": 0.8572964668273926, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12860.png", "entropy": 0.085316002368927} +{"ts": "2026-03-20T20:27:50.744269Z", "loop": 12870, "env_steps": 7907328000, "exact_value_avg": 0.863189697265625, "regret_dist": 0.00039100373396649957, "regret_other_env": 0.0006411416688933969, "regret_corner": 1.5796722436789423e-05, "regret_row": 0.0012735736090689898, "regret_any": 0.0006614503799937665, "regret_bot": 0.0012398811522871256, "value_dist": 0.863189697265625, "value_other_env": 0.8815737962722778, "value_corner": 0.8356135487556458, "value_row": 0.8573530316352844, "value_any": 0.8815891146659851, "value_bot": 0.8573867082595825, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12870.png", "entropy": 0.08686648309230804} +{"ts": "2026-03-20T20:27:59.325296Z", "loop": 12880, "env_steps": 7913472000, "exact_value_avg": 0.863447904586792, "regret_dist": 0.0001327733334619552, "regret_other_env": 0.00021585161448456347, "regret_corner": 8.155902833095752e-06, "regret_row": 0.00021221800125204027, "regret_any": 0.00021891394862905145, "regret_bot": 0.00046125889639370143, "value_dist": 0.863447904586792, "value_other_env": 0.8819990158081055, "value_corner": 0.835621178150177, "value_row": 0.8584144115447998, "value_any": 0.8820316791534424, "value_bot": 0.8581653833389282, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12880.png", "entropy": 0.08969911932945251} +{"ts": "2026-03-20T20:28:07.907892Z", "loop": 12890, "env_steps": 7919616000, "exact_value_avg": 0.8634337186813354, "regret_dist": 0.0001469279668526724, "regret_other_env": 0.00023660084116272628, "regret_corner": 1.2418628102750517e-05, "regret_row": 0.00024974296684376895, "regret_any": 0.0002385543193668127, "regret_bot": 0.0003853224916383624, "value_dist": 0.8634337186813354, "value_other_env": 0.8819782733917236, "value_corner": 0.835616946220398, "value_row": 0.8583768606185913, "value_any": 0.8820120692253113, "value_bot": 0.8582413196563721, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12890.png", "entropy": 0.08913012593984604} +{"ts": "2026-03-20T20:28:16.491195Z", "loop": 12900, "env_steps": 7925760000, "exact_value_avg": 0.8633286952972412, "regret_dist": 0.00025203695986419916, "regret_other_env": 0.0004162720579188317, "regret_corner": 5.684296411345713e-06, "regret_row": 0.00034495623549446464, "regret_any": 0.0004336554557085037, "regret_bot": 0.0008726688683964312, "value_dist": 0.8633286952972412, "value_other_env": 0.8817986249923706, "value_corner": 0.8356236815452576, "value_row": 0.8582817316055298, "value_any": 0.8818169832229614, "value_bot": 0.8577540516853333, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12900.png", "entropy": 0.08581069856882095} +{"ts": "2026-03-20T20:28:25.077578Z", "loop": 12910, "env_steps": 7931904000, "exact_value_avg": 0.8631488084793091, "regret_dist": 0.00043179470230825245, "regret_other_env": 0.0007168914889916778, "regret_corner": 4.149476808379404e-06, "regret_row": 0.00037235402851365507, "regret_any": 0.0007404701318591833, "regret_bot": 0.001518814591690898, "value_dist": 0.8631488084793091, "value_other_env": 0.8814979195594788, "value_corner": 0.8356251120567322, "value_row": 0.8582543134689331, "value_any": 0.8815101981163025, "value_bot": 0.8571078777313232, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12910.png", "entropy": 0.08639361709356308} +{"ts": "2026-03-20T20:28:33.659702Z", "loop": 12920, "env_steps": 7938048000, "exact_value_avg": 0.8620415925979614, "regret_dist": 0.001539092161692679, "regret_other_env": 0.0025632570032030344, "regret_corner": 2.844631808329723e-06, "regret_row": 0.0007101588416844606, "regret_any": 0.0025879992172122, "regret_bot": 0.0035794221330434084, "value_dist": 0.8620415925979614, "value_other_env": 0.8796516060829163, "value_corner": 0.8356265425682068, "value_row": 0.857916533946991, "value_any": 0.8796626329421997, "value_bot": 0.8550472259521484, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12920.png", "entropy": 0.087689109146595} +{"ts": "2026-03-20T20:28:42.247632Z", "loop": 12930, "env_steps": 7944192000, "exact_value_avg": 0.8625377416610718, "regret_dist": 0.0010428924579173326, "regret_other_env": 0.0017312155105173588, "regret_corner": 1.040796450979542e-05, "regret_row": 0.0008576723630540073, "regret_any": 0.0017579634441062808, "regret_bot": 0.002537165069952607, "value_dist": 0.8625377416610718, "value_other_env": 0.8804836273193359, "value_corner": 0.8356189131736755, "value_row": 0.8577690124511719, "value_any": 0.880492627620697, "value_bot": 0.8560894131660461, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12930.png", "entropy": 0.08675379306077957} +{"ts": "2026-03-20T20:28:50.828890Z", "loop": 12940, "env_steps": 7950336000, "exact_value_avg": 0.8630192279815674, "regret_dist": 0.000561489025130868, "regret_other_env": 0.0009135340806096792, "regret_corner": 3.342131822137162e-05, "regret_row": 0.0004928765119984746, "regret_any": 0.0009368551545776427, "regret_bot": 0.0014373994199559093, "value_dist": 0.8630192279815674, "value_other_env": 0.8813014030456543, "value_corner": 0.8355958461761475, "value_row": 0.8581337332725525, "value_any": 0.8813138008117676, "value_bot": 0.8571892380714417, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12940.png", "entropy": 0.08408159762620926} +{"ts": "2026-03-20T20:28:59.408412Z", "loop": 12950, "env_steps": 7956480000, "exact_value_avg": 0.8633806109428406, "regret_dist": 0.00020004833640996367, "regret_other_env": 0.0003052622778341174, "regret_corner": 4.222740972181782e-05, "regret_row": 0.0003076876455452293, "regret_any": 0.0003241000522393733, "regret_bot": 0.0007998865330591798, "value_dist": 0.8633806109428406, "value_other_env": 0.8819096088409424, "value_corner": 0.8355870842933655, "value_row": 0.8583189845085144, "value_any": 0.881926417350769, "value_bot": 0.8578267097473145, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12950.png", "entropy": 0.08617899566888809} +{"ts": "2026-03-20T20:29:07.991229Z", "loop": 12960, "env_steps": 7962624000, "exact_value_avg": 0.8634025454521179, "regret_dist": 0.00017812903388403356, "regret_other_env": 0.00029324088245630264, "regret_corner": 5.461276032292517e-06, "regret_row": 3.400851346668787e-05, "regret_any": 0.0002936780801974237, "regret_bot": 0.0005872977781109512, "value_dist": 0.8634025454521179, "value_other_env": 0.8819215893745422, "value_corner": 0.8356238603591919, "value_row": 0.8585926294326782, "value_any": 0.881956934928894, "value_bot": 0.8580393195152283, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12960.png", "entropy": 0.08904370665550232} +{"ts": "2026-03-20T20:29:16.572969Z", "loop": 12970, "env_steps": 7968768000, "exact_value_avg": 0.8627668619155884, "regret_dist": 0.0008138825069181621, "regret_other_env": 0.0013545640977099538, "regret_corner": 2.860029781004414e-06, "regret_row": 3.428264972171746e-05, "regret_any": 0.0013535763137042522, "regret_bot": 0.002451977925375104, "value_dist": 0.8627668619155884, "value_other_env": 0.8808603286743164, "value_corner": 0.835626482963562, "value_row": 0.8585924506187439, "value_any": 0.880897045135498, "value_bot": 0.8561747074127197, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12970.png", "entropy": 0.08843390643596649} +{"ts": "2026-03-20T20:29:25.152117Z", "loop": 12980, "env_steps": 7974912000, "exact_value_avg": 0.8618121147155762, "regret_dist": 0.001768638612702489, "regret_other_env": 0.002946156309917569, "regret_corner": 2.361834276598529e-06, "regret_row": 3.840114732156508e-05, "regret_any": 0.00294676935300231, "regret_bot": 0.011671177111566067, "value_dist": 0.8618121147155762, "value_other_env": 0.8792687654495239, "value_corner": 0.835627019405365, "value_row": 0.8585882782936096, "value_any": 0.8793038129806519, "value_bot": 0.846955418586731, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12980.png", "entropy": 0.09071195870637894} +{"ts": "2026-03-20T20:29:33.729416Z", "loop": 12990, "env_steps": 7981056000, "exact_value_avg": 0.8602779507637024, "regret_dist": 0.0033027376048266888, "regret_other_env": 0.005503697320818901, "regret_corner": 1.2973945331395953e-06, "regret_row": 0.00011199666914762929, "regret_any": 0.005507347173988819, "regret_bot": 0.02154463715851307, "value_dist": 0.8602779507637024, "value_other_env": 0.8767111897468567, "value_corner": 0.8356280326843262, "value_row": 0.858514666557312, "value_any": 0.8767433166503906, "value_bot": 0.8370819687843323, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_12990.png", "entropy": 0.09441885352134705} +{"ts": "2026-03-20T20:29:42.309763Z", "loop": 13000, "env_steps": 7987200000, "exact_value_avg": 0.8630057573318481, "regret_dist": 0.0005749235861003399, "regret_other_env": 0.0009558359743095934, "regret_corner": 3.554920567694353e-06, "regret_row": 3.672996172099374e-05, "regret_any": 0.0009652827284298837, "regret_bot": 0.002238799585029483, "value_dist": 0.8630057573318481, "value_other_env": 0.8812590837478638, "value_corner": 0.8356257677078247, "value_row": 0.8585899472236633, "value_any": 0.8812853693962097, "value_bot": 0.8563878536224365, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13000.png", "entropy": 0.09014400094747543} +{"ts": "2026-03-20T20:29:50.891029Z", "loop": 13010, "env_steps": 7993344000, "exact_value_avg": 0.8629796504974365, "regret_dist": 0.0006010804791003466, "regret_other_env": 0.000998023897409439, "regret_corner": 5.665421667799819e-06, "regret_row": 4.822801201953553e-05, "regret_any": 0.0010211284970864654, "regret_bot": 0.002138062147423625, "value_dist": 0.8629796504974365, "value_other_env": 0.8812168836593628, "value_corner": 0.8356236815452576, "value_row": 0.8585783839225769, "value_any": 0.8812294602394104, "value_bot": 0.8564885854721069, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13010.png", "entropy": 0.08348125964403152} +{"ts": "2026-03-20T20:29:59.470310Z", "loop": 13020, "env_steps": 7999488000, "exact_value_avg": 0.8629451990127563, "regret_dist": 0.0006355019868351519, "regret_other_env": 0.001037877518683672, "regret_corner": 3.193865268258378e-05, "regret_row": 0.00044228925253264606, "regret_any": 0.0010609858436509967, "regret_bot": 0.0017772065475583076, "value_dist": 0.8629451990127563, "value_other_env": 0.8811770081520081, "value_corner": 0.8355973958969116, "value_row": 0.8581843376159668, "value_any": 0.8811896443367004, "value_bot": 0.8568494319915771, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13020.png", "entropy": 0.07736509293317795} +{"ts": "2026-03-20T20:30:08.055619Z", "loop": 13030, "env_steps": 8005632000, "exact_value_avg": 0.8619872331619263, "regret_dist": 0.0015934903640300035, "regret_other_env": 0.002592242555692792, "regret_corner": 9.536197467241436e-05, "regret_row": 0.0026307529769837856, "regret_any": 0.002615645295009017, "regret_bot": 0.0023657609708607197, "value_dist": 0.8619872331619263, "value_other_env": 0.8796226382255554, "value_corner": 0.8355339765548706, "value_row": 0.8559958338737488, "value_any": 0.8796349763870239, "value_bot": 0.8562607765197754, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13030.png", "entropy": 0.07865665853023529} +{"ts": "2026-03-20T20:30:16.637588Z", "loop": 13040, "env_steps": 8011776000, "exact_value_avg": 0.8602417707443237, "regret_dist": 0.0033389285672456026, "regret_other_env": 0.0054775686003267765, "regret_corner": 0.00013096829934511334, "regret_row": 0.008626995608210564, "regret_any": 0.00549952732399106, "regret_bot": 0.00241776998154819, "value_dist": 0.8602417707443237, "value_other_env": 0.8767372965812683, "value_corner": 0.8354983329772949, "value_row": 0.8499996066093445, "value_any": 0.8767511248588562, "value_bot": 0.8562089204788208, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13040.png", "entropy": 0.08186239004135132} +{"ts": "2026-03-20T20:30:25.217340Z", "loop": 13050, "env_steps": 8017920000, "exact_value_avg": 0.8624961972236633, "regret_dist": 0.0010844981297850609, "regret_other_env": 0.0018000378040596843, "regret_corner": 1.118828913604375e-05, "regret_row": 0.0005005437997169793, "regret_any": 0.0018238109769299626, "regret_bot": 0.002683976199477911, "value_dist": 0.8624961972236633, "value_other_env": 0.8804147839546204, "value_corner": 0.8356181979179382, "value_row": 0.8581260442733765, "value_any": 0.880426824092865, "value_bot": 0.8559426665306091, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13050.png", "entropy": 0.07605157792568207} +{"ts": "2026-03-20T20:30:33.792221Z", "loop": 13060, "env_steps": 8024064000, "exact_value_avg": 0.8630778789520264, "regret_dist": 0.0005028391606174409, "regret_other_env": 0.0008306600502692163, "regret_corner": 1.1107822501799092e-05, "regret_row": 0.0004510892613325268, "regret_any": 0.0008553955121897161, "regret_bot": 0.0015669137937948108, "value_dist": 0.8630778789520264, "value_other_env": 0.8813842535018921, "value_corner": 0.835618257522583, "value_row": 0.85817551612854, "value_any": 0.8813952207565308, "value_bot": 0.8570597171783447, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13060.png", "entropy": 0.0761016383767128} +{"ts": "2026-03-20T20:30:42.374551Z", "loop": 13070, "env_steps": 8030208000, "exact_value_avg": 0.8605543375015259, "regret_dist": 0.003026376012712717, "regret_other_env": 0.005025651305913925, "regret_corner": 2.7462841899250634e-05, "regret_row": 0.0074973632581532, "regret_any": 0.005074216518551111, "regret_bot": 0.0006190254352986813, "value_dist": 0.8605543375015259, "value_other_env": 0.8771892189979553, "value_corner": 0.8356018662452698, "value_row": 0.8511292934417725, "value_any": 0.8771764636039734, "value_bot": 0.8580076098442078, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13070.png", "entropy": 0.08262764662504196} +{"ts": "2026-03-20T20:30:50.954248Z", "loop": 13080, "env_steps": 8036352000, "exact_value_avg": 0.8633286952972412, "regret_dist": 0.0002520371344871819, "regret_other_env": 0.0004191787156742066, "regret_corner": 1.3247132528704242e-06, "regret_row": 6.894301623106003e-05, "regret_any": 0.0004192270280327648, "regret_bot": 0.0003539200988598168, "value_dist": 0.8633286952972412, "value_other_env": 0.8817957043647766, "value_corner": 0.8356279730796814, "value_row": 0.8585576415061951, "value_any": 0.8818314075469971, "value_bot": 0.8582726120948792, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13080.png", "entropy": 0.07867911458015442} +{"ts": "2026-03-20T20:30:59.542532Z", "loop": 13090, "env_steps": 8042496000, "exact_value_avg": 0.857900857925415, "regret_dist": 0.005679829511791468, "regret_other_env": 0.009466211311519146, "regret_corner": 2.558032861088577e-07, "regret_row": 0.00039046478923410177, "regret_any": 0.009452090598642826, "regret_bot": 0.020730212330818176, "value_dist": 0.857900857925415, "value_other_env": 0.8727486729621887, "value_corner": 0.8356290459632874, "value_row": 0.8582361936569214, "value_any": 0.872798502445221, "value_bot": 0.8378964066505432, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13090.png", "entropy": 0.09250954538583755} +{"ts": "2026-03-20T20:31:08.130817Z", "loop": 13100, "env_steps": 8048640000, "exact_value_avg": 0.8632340431213379, "regret_dist": 0.00034661623067222536, "regret_other_env": 0.0005711279227398336, "regret_corner": 9.848674380918965e-06, "regret_row": 0.00013646103616338223, "regret_any": 0.0005703342612832785, "regret_bot": 0.0016738345148041844, "value_dist": 0.8632340431213379, "value_other_env": 0.8816437125205994, "value_corner": 0.8356194496154785, "value_row": 0.8584901690483093, "value_any": 0.8816802501678467, "value_bot": 0.8569527864456177, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13100.png", "entropy": 0.09102083742618561} +{"ts": "2026-03-20T20:31:16.711256Z", "loop": 13110, "env_steps": 8054784000, "exact_value_avg": 0.8623751401901245, "regret_dist": 0.0012056156992912292, "regret_other_env": 0.0019431919790804386, "regret_corner": 9.92511777440086e-05, "regret_row": 0.011976374313235283, "regret_any": 0.0019613613840192556, "regret_bot": 0.0014789249980822206, "value_dist": 0.8623751401901245, "value_other_env": 0.8802717328071594, "value_corner": 0.8355300426483154, "value_row": 0.846650242805481, "value_any": 0.8802892565727234, "value_bot": 0.857147753238678, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13110.png", "entropy": 0.09438130259513855} +{"ts": "2026-03-20T20:31:25.296016Z", "loop": 13120, "env_steps": 8060928000, "exact_value_avg": 0.8619431257247925, "regret_dist": 0.0016375385457649827, "regret_other_env": 0.0026839517522603273, "regret_corner": 6.791850319132209e-05, "regret_row": 0.003247292013838887, "regret_any": 0.002706127241253853, "regret_bot": 0.0017275202553719282, "value_dist": 0.8619431257247925, "value_other_env": 0.8795309066772461, "value_corner": 0.8355613946914673, "value_row": 0.8553794026374817, "value_any": 0.8795444965362549, "value_bot": 0.8568991422653198, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13120.png", "entropy": 0.08482295274734497} +{"ts": "2026-03-20T20:31:33.879544Z", "loop": 13130, "env_steps": 8067072000, "exact_value_avg": 0.8607802391052246, "regret_dist": 0.002800476038828492, "regret_other_env": 0.004618347156792879, "regret_corner": 7.366935460595414e-05, "regret_row": 0.01084843184798956, "regret_any": 0.004637542646378279, "regret_bot": 0.0015799273969605565, "value_dist": 0.8607802391052246, "value_other_env": 0.8775964975357056, "value_corner": 0.8355556726455688, "value_row": 0.8477782011032104, "value_any": 0.8776130676269531, "value_bot": 0.8570467829704285, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13130.png", "entropy": 0.08283617347478867} +{"ts": "2026-03-20T20:31:42.453427Z", "loop": 13140, "env_steps": 8073216000, "exact_value_avg": 0.859470009803772, "regret_dist": 0.0041105845011770725, "regret_other_env": 0.006789021659642458, "regret_corner": 9.292811591876671e-05, "regret_row": 0.011477232910692692, "regret_any": 0.00681393314152956, "regret_bot": 0.003232324728742242, "value_dist": 0.859470009803772, "value_other_env": 0.8754258155822754, "value_corner": 0.8355363607406616, "value_row": 0.8471494317054749, "value_any": 0.8754366636276245, "value_bot": 0.8553943037986755, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13140.png", "entropy": 0.0831858441233635} +{"ts": "2026-03-20T20:31:51.035176Z", "loop": 13150, "env_steps": 8079360000, "exact_value_avg": 0.8630579710006714, "regret_dist": 0.0005227251094765961, "regret_other_env": 0.0008683279156684875, "regret_corner": 4.320840162108652e-06, "regret_row": 0.0005350799765437841, "regret_any": 0.0008916914230212569, "regret_bot": 0.0013311582151800394, "value_dist": 0.8630579710006714, "value_other_env": 0.8813465237617493, "value_corner": 0.8356249928474426, "value_row": 0.8580915927886963, "value_any": 0.8813589215278625, "value_bot": 0.8572955131530762, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13150.png", "entropy": 0.07459311932325363} +{"ts": "2026-03-20T20:31:59.618314Z", "loop": 13160, "env_steps": 8085504000, "exact_value_avg": 0.8620163202285767, "regret_dist": 0.0015643746592104435, "regret_other_env": 0.002604388166218996, "regret_corner": 4.3541194827412255e-06, "regret_row": 0.0020431315060704947, "regret_any": 0.0026299108285456896, "regret_bot": 0.003309250110760331, "value_dist": 0.8620163202285767, "value_other_env": 0.879610538482666, "value_corner": 0.8356249332427979, "value_row": 0.8565834760665894, "value_any": 0.8796206712722778, "value_bot": 0.8553173542022705, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13160.png", "entropy": 0.07634694874286652} +{"ts": "2026-03-20T20:32:08.202168Z", "loop": 13170, "env_steps": 8091648000, "exact_value_avg": 0.8608566522598267, "regret_dist": 0.002724063117057085, "regret_other_env": 0.0045303720980882645, "regret_corner": 1.4599661881220527e-05, "regret_row": 0.0038418862968683243, "regret_any": 0.0045548090711236, "regret_bot": 0.003089434700086713, "value_dist": 0.8608566522598267, "value_other_env": 0.877684473991394, "value_corner": 0.8356147408485413, "value_row": 0.8547847867012024, "value_any": 0.8776957988739014, "value_bot": 0.8555371761322021, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13170.png", "entropy": 0.07872480154037476} +{"ts": "2026-03-20T20:32:16.780068Z", "loop": 13180, "env_steps": 8097792000, "exact_value_avg": 0.8605241775512695, "regret_dist": 0.0030565205961465836, "regret_other_env": 0.005005424842238426, "regret_corner": 0.00013316373224370182, "regret_row": 0.00418698787689209, "regret_any": 0.005025949794799089, "regret_bot": 0.0020589404739439487, "value_dist": 0.8605241775512695, "value_other_env": 0.877209484577179, "value_corner": 0.835496187210083, "value_row": 0.8544396162033081, "value_any": 0.8772246837615967, "value_bot": 0.8565676212310791, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13180.png", "entropy": 0.08416059613227844} +{"ts": "2026-03-20T20:32:25.360829Z", "loop": 13190, "env_steps": 8103936000, "exact_value_avg": 0.8634187579154968, "regret_dist": 0.00016188067093025893, "regret_other_env": 0.00025497874594293535, "regret_corner": 2.2233527488424443e-05, "regret_row": 0.0001822364138206467, "regret_any": 0.00026389252161607146, "regret_bot": 0.0004730178334284574, "value_dist": 0.8634187579154968, "value_other_env": 0.881959855556488, "value_corner": 0.8356070518493652, "value_row": 0.8584443926811218, "value_any": 0.8819867372512817, "value_bot": 0.8581536412239075, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13190.png", "entropy": 0.07825718820095062} +{"ts": "2026-03-20T20:32:33.944203Z", "loop": 13200, "env_steps": 8110080000, "exact_value_avg": 0.863426923751831, "regret_dist": 0.0001537378557259217, "regret_other_env": 0.0002557386760599911, "regret_corner": 7.366140835074475e-07, "regret_row": 8.719978359295055e-05, "regret_any": 0.0002635318669490516, "regret_bot": 0.000662637350615114, "value_dist": 0.863426923751831, "value_other_env": 0.8819591403007507, "value_corner": 0.8356285691261292, "value_row": 0.858539342880249, "value_any": 0.8819870948791504, "value_bot": 0.857964038848877, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13200.png", "entropy": 0.0797252506017685} +{"ts": "2026-03-20T20:32:42.528134Z", "loop": 13210, "env_steps": 8116224000, "exact_value_avg": 0.861522912979126, "regret_dist": 0.0020578699186444283, "regret_other_env": 0.003429256146773696, "regret_corner": 7.902582979113504e-07, "regret_row": 0.0030086650513112545, "regret_any": 0.0034485275391489267, "regret_bot": 0.0037339110858738422, "value_dist": 0.861522912979126, "value_other_env": 0.8787856698036194, "value_corner": 0.8356285691261292, "value_row": 0.8556180000305176, "value_any": 0.8788021206855774, "value_bot": 0.8548927903175354, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13210.png", "entropy": 0.07764054089784622} +{"ts": "2026-03-20T20:32:51.108309Z", "loop": 13220, "env_steps": 8122368000, "exact_value_avg": 0.8619213700294495, "regret_dist": 0.0016592864412814379, "regret_other_env": 0.0027653344441205263, "regret_corner": 2.1408003192391334e-07, "regret_row": 0.008162284269928932, "regret_any": 0.002770406659692526, "regret_bot": 0.001465345500037074, "value_dist": 0.8619213700294495, "value_other_env": 0.8794495463371277, "value_corner": 0.8356291055679321, "value_row": 0.850464403629303, "value_any": 0.879480242729187, "value_bot": 0.8571613430976868, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13220.png", "entropy": 0.08165927231311798} +{"ts": "2026-03-20T20:32:59.687397Z", "loop": 13230, "env_steps": 8128512000, "exact_value_avg": 0.8626866340637207, "regret_dist": 0.0008940271218307316, "regret_other_env": 0.0014897400978952646, "regret_corner": 4.574656600198068e-07, "regret_row": 0.001907154219225049, "regret_any": 0.0014878168003633618, "regret_bot": 0.0011097777169197798, "value_dist": 0.8626866340637207, "value_other_env": 0.8807251453399658, "value_corner": 0.835628867149353, "value_row": 0.8567193746566772, "value_any": 0.8807628154754639, "value_bot": 0.8575168251991272, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13230.png", "entropy": 0.08629398047924042} +{"ts": "2026-03-20T20:33:08.269994Z", "loop": 13240, "env_steps": 8134656000, "exact_value_avg": 0.8632272481918335, "regret_dist": 0.0003534556017257273, "regret_other_env": 0.0005886104772798717, "regret_corner": 7.232030725390359e-07, "regret_row": 0.0007088552811183035, "regret_any": 0.0005879466771148145, "regret_bot": 0.0005009597516618669, "value_dist": 0.8632272481918335, "value_other_env": 0.881626307964325, "value_corner": 0.8356286287307739, "value_row": 0.8579177260398865, "value_any": 0.8816627264022827, "value_bot": 0.8581256866455078, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13240.png", "entropy": 0.08390849828720093} +{"ts": "2026-03-20T20:33:16.854866Z", "loop": 13250, "env_steps": 8140800000, "exact_value_avg": 0.8628976941108704, "regret_dist": 0.0006829912890680134, "regret_other_env": 0.0011379647767171264, "regret_corner": 5.309780704010336e-07, "regret_row": 0.0010254484368488193, "regret_any": 0.0011365707032382488, "regret_bot": 0.0009475418482907116, "value_dist": 0.8628976941108704, "value_other_env": 0.8810769319534302, "value_corner": 0.8356288075447083, "value_row": 0.8576012253761292, "value_any": 0.8811140656471252, "value_bot": 0.8576791286468506, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13250.png", "entropy": 0.08457663655281067} +{"ts": "2026-03-20T20:33:25.439223Z", "loop": 13260, "env_steps": 8146944000, "exact_value_avg": 0.8634710311889648, "regret_dist": 0.0001096764681278728, "regret_other_env": 0.00018108975200448185, "regret_corner": 2.55654276770656e-06, "regret_row": 1.79526032297872e-05, "regret_any": 0.00018087000353261828, "regret_bot": 0.00025397917488589883, "value_dist": 0.8634710311889648, "value_other_env": 0.8820338249206543, "value_corner": 0.8356267809867859, "value_row": 0.8586087226867676, "value_any": 0.8820697665214539, "value_bot": 0.8583726286888123, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13260.png", "entropy": 0.08419615775346756} +{"ts": "2026-03-20T20:33:34.017953Z", "loop": 13270, "env_steps": 8153088000, "exact_value_avg": 0.8635073900222778, "regret_dist": 7.32807966414839e-05, "regret_other_env": 0.00010915044549619779, "regret_corner": 1.9476316083455458e-05, "regret_row": 9.54722345340997e-05, "regret_any": 0.00010911937715718523, "regret_bot": 0.00011529637413332239, "value_dist": 0.8635073900222778, "value_other_env": 0.8821057081222534, "value_corner": 0.8356098532676697, "value_row": 0.85853111743927, "value_any": 0.8821415305137634, "value_bot": 0.8585113286972046, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13270.png", "entropy": 0.08217856287956238} +{"ts": "2026-03-20T20:33:42.603355Z", "loop": 13280, "env_steps": 8159232000, "exact_value_avg": 0.8613729476928711, "regret_dist": 0.0022077253088355064, "regret_other_env": 0.003619461553171277, "regret_corner": 9.012073860503733e-05, "regret_row": 0.010121445171535015, "regret_any": 0.0036285575479269028, "regret_bot": 0.0022855219431221485, "value_dist": 0.8613729476928711, "value_other_env": 0.8785954713821411, "value_corner": 0.8355391621589661, "value_row": 0.8485051393508911, "value_any": 0.8786220550537109, "value_bot": 0.8563411831855774, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13280.png", "entropy": 0.09261424839496613} +{"ts": "2026-03-20T20:33:51.179204Z", "loop": 13290, "env_steps": 8165376000, "exact_value_avg": 0.8632335662841797, "regret_dist": 0.00034702903940342367, "regret_other_env": 0.0005745177040807903, "regret_corner": 5.79605512029957e-06, "regret_row": 0.00024348375154659152, "regret_any": 0.0005739090265706182, "regret_bot": 0.0007283797604031861, "value_dist": 0.8632335662841797, "value_other_env": 0.8816403150558472, "value_corner": 0.8356235027313232, "value_row": 0.8583831787109375, "value_any": 0.8816767334938049, "value_bot": 0.8578982949256897, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13290.png", "entropy": 0.08325492590665817} +{"ts": "2026-03-20T20:33:59.763346Z", "loop": 13300, "env_steps": 8171520000, "exact_value_avg": 0.8631364107131958, "regret_dist": 0.0004443263460416347, "regret_other_env": 0.0007400087779387832, "regret_corner": 8.026759132917505e-07, "regret_row": 8.777325274422765e-05, "regret_any": 0.0007389542879536748, "regret_bot": 0.0006938657024875283, "value_dist": 0.8631364107131958, "value_other_env": 0.8814749121665955, "value_corner": 0.8356285691261292, "value_row": 0.8585388660430908, "value_any": 0.8815116882324219, "value_bot": 0.8579328060150146, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13300.png", "entropy": 0.08310003578662872} +{"ts": "2026-03-20T20:34:08.348490Z", "loop": 13310, "env_steps": 8177664000, "exact_value_avg": 0.8629969358444214, "regret_dist": 0.0005838114884682, "regret_other_env": 0.0009713012259453535, "regret_corner": 2.5769077183213085e-06, "regret_row": 0.0001876319875009358, "regret_any": 0.0009705101256258786, "regret_bot": 0.0008587315096519887, "value_dist": 0.8629969358444214, "value_other_env": 0.8812435865402222, "value_corner": 0.8356267809867859, "value_row": 0.858439028263092, "value_any": 0.8812800049781799, "value_bot": 0.8577678799629211, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13310.png", "entropy": 0.08289756625890732} +{"ts": "2026-03-20T20:34:16.935916Z", "loop": 13320, "env_steps": 8183808000, "exact_value_avg": 0.863301694393158, "regret_dist": 0.0002789257268887013, "regret_other_env": 0.00046213867608457804, "regret_corner": 4.106263531866716e-06, "regret_row": 4.1138220694847405e-05, "regret_any": 0.0004614864883478731, "regret_bot": 0.0005603961762972176, "value_dist": 0.863301694393158, "value_other_env": 0.8817526698112488, "value_corner": 0.8356252312660217, "value_row": 0.8585854768753052, "value_any": 0.8817891478538513, "value_bot": 0.8580662608146667, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13320.png", "entropy": 0.0817728042602539} +{"ts": "2026-03-20T20:34:25.521264Z", "loop": 13330, "env_steps": 8189952000, "exact_value_avg": 0.8623172044754028, "regret_dist": 0.0012635125312954187, "regret_other_env": 0.0020805185195058584, "regret_corner": 3.8003425288479775e-05, "regret_row": 0.0037461575120687485, "regret_any": 0.00208164076320827, "regret_bot": 0.0011555218370631337, "value_dist": 0.8623172044754028, "value_other_env": 0.8801344037055969, "value_corner": 0.8355913162231445, "value_row": 0.8548804521560669, "value_any": 0.8801689743995667, "value_bot": 0.8574711680412292, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13330.png", "entropy": 0.08571619540452957} +{"ts": "2026-03-20T20:34:34.100578Z", "loop": 13340, "env_steps": 8196096000, "exact_value_avg": 0.863038182258606, "regret_dist": 0.0005424581468105316, "regret_other_env": 0.0008947442984208465, "regret_corner": 1.4028947589395102e-05, "regret_row": 0.00025526134413667023, "regret_any": 0.0008935208898037672, "regret_bot": 0.0013477019965648651, "value_dist": 0.863038182258606, "value_other_env": 0.8813201189041138, "value_corner": 0.835615336894989, "value_row": 0.8583714365959167, "value_any": 0.8813570737838745, "value_bot": 0.8572788834571838, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13340.png", "entropy": 0.0806511715054512} +{"ts": "2026-03-20T20:34:42.690431Z", "loop": 13350, "env_steps": 8202240000, "exact_value_avg": 0.8631000518798828, "regret_dist": 0.00048070549382828176, "regret_other_env": 0.0008001062087714672, "regret_corner": 1.6043584309954895e-06, "regret_row": 2.388750908721704e-05, "regret_any": 0.0007989247678779066, "regret_bot": 0.0010940993670374155, "value_dist": 0.8631000518798828, "value_other_env": 0.8814148306846619, "value_corner": 0.8356277346611023, "value_row": 0.85860276222229, "value_any": 0.8814516663551331, "value_bot": 0.8575324416160583, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13350.png", "entropy": 0.08313733339309692} +{"ts": "2026-03-20T20:34:51.274238Z", "loop": 13360, "env_steps": 8208384000, "exact_value_avg": 0.8629811406135559, "regret_dist": 0.0005995433311909437, "regret_other_env": 0.0009986964287236333, "regret_corner": 8.136034352901333e-07, "regret_row": 0.0008957155514508486, "regret_any": 0.001003958168439567, "regret_bot": 0.0010024624643847346, "value_dist": 0.8629811406135559, "value_other_env": 0.8812161684036255, "value_corner": 0.8356285095214844, "value_row": 0.8577309250831604, "value_any": 0.8812466859817505, "value_bot": 0.8576241731643677, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13360.png", "entropy": 0.08085595071315765} +{"ts": "2026-03-20T20:34:59.854522Z", "loop": 13370, "env_steps": 8214528000, "exact_value_avg": 0.8629555702209473, "regret_dist": 0.0006251654704101384, "regret_other_env": 0.0009875398827716708, "regret_corner": 8.160372817656025e-05, "regret_row": 0.0011743971845135093, "regret_any": 0.001010364736430347, "regret_bot": 0.001856330200098455, "value_dist": 0.8629555702209473, "value_other_env": 0.8812273740768433, "value_corner": 0.8355477452278137, "value_row": 0.8574521541595459, "value_any": 0.88124018907547, "value_bot": 0.8567702770233154, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13370.png", "entropy": 0.08204177767038345} +{"ts": "2026-03-20T20:35:08.437842Z", "loop": 13380, "env_steps": 8220672000, "exact_value_avg": 0.8613466024398804, "regret_dist": 0.0022341907024383545, "regret_other_env": 0.0015949915396049619, "regret_corner": 0.003192989155650139, "regret_row": 0.0019120696233585477, "regret_any": 0.0016168084694072604, "regret_bot": 0.001863194047473371, "value_dist": 0.8613466024398804, "value_other_env": 0.880620002746582, "value_corner": 0.8324363231658936, "value_row": 0.8567146062850952, "value_any": 0.8806338310241699, "value_bot": 0.8567634224891663, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13380.png", "entropy": 0.08267217129468918} +{"ts": "2026-03-20T20:35:17.018286Z", "loop": 13390, "env_steps": 8226816000, "exact_value_avg": 0.8632940053939819, "regret_dist": 0.00028667855076491833, "regret_other_env": 0.0004208367026876658, "regret_corner": 8.54412792250514e-05, "regret_row": 0.0008870839956216514, "regret_any": 0.00044341973261907697, "regret_bot": 0.0009437752305530012, "value_dist": 0.8632940053939819, "value_other_env": 0.8817940354347229, "value_corner": 0.8355438709259033, "value_row": 0.8577396273612976, "value_any": 0.8818072080612183, "value_bot": 0.8576828837394714, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13390.png", "entropy": 0.08142977207899094} +{"ts": "2026-03-20T20:35:25.605879Z", "loop": 13400, "env_steps": 8232960000, "exact_value_avg": 0.8634599447250366, "regret_dist": 0.00012069263902958483, "regret_other_env": 0.00018201135389972478, "regret_corner": 2.8714539439533837e-05, "regret_row": 4.265113966539502e-05, "regret_any": 0.00018383450515102595, "regret_bot": 0.00035534874768927693, "value_dist": 0.8634599447250366, "value_other_env": 0.8820328712463379, "value_corner": 0.8356005549430847, "value_row": 0.8585839867591858, "value_any": 0.8820667862892151, "value_bot": 0.8582713603973389, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13400.png", "entropy": 0.09238822758197784} +{"ts": "2026-03-20T20:35:34.183436Z", "loop": 13410, "env_steps": 8239104000, "exact_value_avg": 0.8634054660797119, "regret_dist": 0.00017517532978672534, "regret_other_env": 0.0002826145209837705, "regret_corner": 1.4016529348737095e-05, "regret_row": 2.8121561626903713e-05, "regret_any": 0.0002844401460606605, "regret_bot": 0.0006192004657350481, "value_dist": 0.8634054660797119, "value_other_env": 0.881932258605957, "value_corner": 0.8356152772903442, "value_row": 0.858598530292511, "value_any": 0.8819661736488342, "value_bot": 0.8580074310302734, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13410.png", "entropy": 0.09233779460191727} +{"ts": "2026-03-20T20:35:42.770086Z", "loop": 13420, "env_steps": 8245248000, "exact_value_avg": 0.8633917570114136, "regret_dist": 0.00018896959954872727, "regret_other_env": 0.0003076030407100916, "regret_corner": 1.1019409612345044e-05, "regret_row": 1.913010964926798e-05, "regret_any": 0.00032790828845463693, "regret_bot": 0.0012513037072494626, "value_dist": 0.8633917570114136, "value_other_env": 0.8819073438644409, "value_corner": 0.8356183767318726, "value_row": 0.8586075305938721, "value_any": 0.881922721862793, "value_bot": 0.8573752641677856, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13420.png", "entropy": 0.0912732183933258} +{"ts": "2026-03-20T20:35:51.354913Z", "loop": 13430, "env_steps": 8251392000, "exact_value_avg": 0.8629094362258911, "regret_dist": 0.0006711929454468191, "regret_other_env": 0.001111502991989255, "regret_corner": 1.0727842891355976e-05, "regret_row": 4.743951649288647e-05, "regret_any": 0.0011342355282977223, "regret_bot": 0.0035867614205926657, "value_dist": 0.8629094362258911, "value_other_env": 0.8811033368110657, "value_corner": 0.8356186151504517, "value_row": 0.8585792183876038, "value_any": 0.8811163306236267, "value_bot": 0.8550398945808411, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13430.png", "entropy": 0.09107266366481781} +{"ts": "2026-03-20T20:35:59.941434Z", "loop": 13440, "env_steps": 8257536000, "exact_value_avg": 0.8630262613296509, "regret_dist": 0.0005544269224628806, "regret_other_env": 0.0008230636594817042, "regret_corner": 0.00015147180238272995, "regret_row": 0.0004911791766062379, "regret_any": 0.0008460714016109705, "regret_bot": 0.0012169801630079746, "value_dist": 0.8630262613296509, "value_other_env": 0.8813918232917786, "value_corner": 0.835477888584137, "value_row": 0.8581354022026062, "value_any": 0.8814045786857605, "value_bot": 0.857409656047821, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13440.png", "entropy": 0.10007955133914948} +{"ts": "2026-03-20T20:36:08.525288Z", "loop": 13450, "env_steps": 8263680000, "exact_value_avg": 0.861992597579956, "regret_dist": 0.0015881250146776438, "regret_other_env": 0.002036544494330883, "regret_corner": 0.0009154956205748022, "regret_row": 0.0025449604727327824, "regret_any": 0.0020423291716724634, "regret_bot": 0.0007173581980168819, "value_dist": 0.861992597579956, "value_other_env": 0.8801783919334412, "value_corner": 0.8347138166427612, "value_row": 0.8560816645622253, "value_any": 0.8802083134651184, "value_bot": 0.8579093217849731, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13450.png", "entropy": 0.12264970690011978} +{"ts": "2026-03-20T20:36:17.109176Z", "loop": 13460, "env_steps": 8269824000, "exact_value_avg": 0.8630430102348328, "regret_dist": 0.0005376280751079321, "regret_other_env": 0.0007274477393366396, "regret_corner": 0.0002528985496610403, "regret_row": 0.000715843343641609, "regret_any": 0.0007459186017513275, "regret_bot": 0.0010819511953741312, "value_dist": 0.8630430102348328, "value_other_env": 0.8814874291419983, "value_corner": 0.8353763818740845, "value_row": 0.8579108715057373, "value_any": 0.8815046548843384, "value_bot": 0.8575446605682373, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13460.png", "entropy": 0.1122300773859024} +{"ts": "2026-03-20T20:36:25.693584Z", "loop": 13470, "env_steps": 8275968000, "exact_value_avg": 0.8626984357833862, "regret_dist": 0.0008822640520520508, "regret_other_env": 0.0011952734785154462, "regret_corner": 0.0004127497668378055, "regret_row": 0.0010473934235051274, "regret_any": 0.0012178018223494291, "regret_bot": 0.002111832844093442, "value_dist": 0.8626984357833862, "value_other_env": 0.881019651889801, "value_corner": 0.8352165818214417, "value_row": 0.857579231262207, "value_any": 0.8810327649116516, "value_bot": 0.8565148115158081, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13470.png", "entropy": 0.11873310804367065} +{"ts": "2026-03-20T20:36:34.280163Z", "loop": 13480, "env_steps": 8282112000, "exact_value_avg": 0.8609479665756226, "regret_dist": 0.0026326680090278387, "regret_other_env": 0.00301167881116271, "regret_corner": 0.0020641516894102097, "regret_row": 0.0037799119018018246, "regret_any": 0.003025901271030307, "regret_bot": 0.0020549253094941378, "value_dist": 0.8609479665756226, "value_other_env": 0.8792031407356262, "value_corner": 0.8335651755332947, "value_row": 0.854846715927124, "value_any": 0.8792246580123901, "value_bot": 0.8565716743469238, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13480.png", "entropy": 0.14208999276161194} +{"ts": "2026-03-20T20:36:42.858871Z", "loop": 13490, "env_steps": 8288256000, "exact_value_avg": 0.8616968989372253, "regret_dist": 0.0018838347168639302, "regret_other_env": 0.002607154194265604, "regret_corner": 0.0007988552679307759, "regret_row": 0.003958939574658871, "regret_any": 0.0026312374975532293, "regret_bot": 0.0024925777688622475, "value_dist": 0.8616968989372253, "value_other_env": 0.8796077370643616, "value_corner": 0.8348305225372314, "value_row": 0.8546676635742188, "value_any": 0.8796193599700928, "value_bot": 0.8561339974403381, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13490.png", "entropy": 0.12498446553945541} +{"ts": "2026-03-20T20:36:51.436826Z", "loop": 13500, "env_steps": 8294400000, "exact_value_avg": 0.8606221079826355, "regret_dist": 0.0029586064629256725, "regret_other_env": 0.004895183257758617, "regret_corner": 5.374054308049381e-05, "regret_row": 0.0005198671133257449, "regret_any": 0.004921039566397667, "regret_bot": 0.00908324308693409, "value_dist": 0.8606221079826355, "value_other_env": 0.8773196935653687, "value_corner": 0.8355755805969238, "value_row": 0.8581067323684692, "value_any": 0.8773295879364014, "value_bot": 0.8495433926582336, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13500.png", "entropy": 0.10278745740652084} +{"ts": "2026-03-20T20:37:00.015313Z", "loop": 13510, "env_steps": 8300544000, "exact_value_avg": 0.8631044030189514, "regret_dist": 0.0004762991738971323, "regret_other_env": 0.0007716036634519696, "regret_corner": 3.3342344977427274e-05, "regret_row": 0.0003734033089131117, "regret_any": 0.0007949391729198396, "regret_bot": 0.0023848165292292833, "value_dist": 0.8631044030189514, "value_other_env": 0.8814433217048645, "value_corner": 0.8355960249900818, "value_row": 0.8582532405853271, "value_any": 0.881455659866333, "value_bot": 0.8562418222427368, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13510.png", "entropy": 0.09363172948360443} +{"ts": "2026-03-20T20:37:08.598921Z", "loop": 13520, "env_steps": 8306688000, "exact_value_avg": 0.8604757785797119, "regret_dist": 0.003104879753664136, "regret_other_env": 0.005072411149740219, "regret_corner": 0.00015358180098701268, "regret_row": 0.012615000829100609, "regret_any": 0.005089116748422384, "regret_bot": 0.0012046948540955782, "value_dist": 0.8604757785797119, "value_other_env": 0.8771424889564514, "value_corner": 0.8354756832122803, "value_row": 0.8460115790367126, "value_any": 0.8771615028381348, "value_bot": 0.8574219346046448, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13520.png", "entropy": 0.09277243167161942} +{"ts": "2026-03-20T20:37:17.177175Z", "loop": 13530, "env_steps": 8312832000, "exact_value_avg": 0.8634132146835327, "regret_dist": 0.00016747282643336803, "regret_other_env": 0.0002763692755252123, "regret_corner": 4.12811868955032e-06, "regret_row": 2.047672387561761e-05, "regret_any": 0.00030039582634344697, "regret_bot": 0.001300428993999958, "value_dist": 0.8634132146835327, "value_other_env": 0.8819385170936584, "value_corner": 0.8356252312660217, "value_row": 0.8586061000823975, "value_any": 0.8819502592086792, "value_bot": 0.8573262095451355, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13530.png", "entropy": 0.0848548412322998} +{"ts": "2026-03-20T20:37:25.763793Z", "loop": 13540, "env_steps": 8318976000, "exact_value_avg": 0.8633568286895752, "regret_dist": 0.0002237894805148244, "regret_other_env": 0.0003725771384779364, "regret_corner": 6.079674221837195e-07, "regret_row": 0.00021399403340183198, "regret_any": 0.0003965477808378637, "regret_bot": 0.0013647361192852259, "value_dist": 0.8633568286895752, "value_other_env": 0.8818422555923462, "value_corner": 0.8356287479400635, "value_row": 0.8584126234054565, "value_any": 0.8818540573120117, "value_bot": 0.8572618365287781, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13540.png", "entropy": 0.08741645514965057} +{"ts": "2026-03-20T20:37:34.350517Z", "loop": 13550, "env_steps": 8325120000, "exact_value_avg": 0.8632187247276306, "regret_dist": 0.0003619579365476966, "regret_other_env": 0.0006030062795616686, "regret_corner": 3.854433998640161e-07, "regret_row": 0.0008871546015143394, "regret_any": 0.0006267849821597338, "regret_bot": 0.001541143748909235, "value_dist": 0.8632187247276306, "value_other_env": 0.8816118836402893, "value_corner": 0.8356289267539978, "value_row": 0.8577393889427185, "value_any": 0.8816238045692444, "value_bot": 0.8570855259895325, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13550.png", "entropy": 0.08626675605773926} +{"ts": "2026-03-20T20:37:42.933555Z", "loop": 13560, "env_steps": 8331264000, "exact_value_avg": 0.8630778789520264, "regret_dist": 0.0005028141313232481, "regret_other_env": 0.0008380209328606725, "regret_corner": 3.973643192267673e-09, "regret_row": 0.002062026411294937, "regret_any": 0.0008615318802185357, "regret_bot": 0.001996799372136593, "value_dist": 0.8630778789520264, "value_other_env": 0.8813768625259399, "value_corner": 0.8356293439865112, "value_row": 0.8565645813941956, "value_any": 0.8813890218734741, "value_bot": 0.8566298484802246, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13560.png", "entropy": 0.0870826467871666} +{"ts": "2026-03-20T20:37:51.514992Z", "loop": 13570, "env_steps": 8337408000, "exact_value_avg": 0.8590340614318848, "regret_dist": 0.004546656738966703, "regret_other_env": 0.007577836979180574, "regret_corner": -1.1374553565701717e-07, "regret_row": 0.037142254412174225, "regret_any": 0.007601858116686344, "regret_bot": 0.006890668999403715, "value_dist": 0.8590340614318848, "value_other_env": 0.8746370673179626, "value_corner": 0.8356294631958008, "value_row": 0.8214843273162842, "value_any": 0.8746487498283386, "value_bot": 0.8517359495162964, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13570.png", "entropy": 0.08207693696022034} +{"ts": "2026-03-20T20:38:00.094357Z", "loop": 13580, "env_steps": 8343552000, "exact_value_avg": 0.8621682524681091, "regret_dist": 0.0014124134322628379, "regret_other_env": 0.0023537552915513515, "regret_corner": 4.0034456105786376e-07, "regret_row": 0.00046941591426730156, "regret_any": 0.002380324760451913, "regret_bot": 0.013409891165792942, "value_dist": 0.8621682524681091, "value_other_env": 0.8798611164093018, "value_corner": 0.8356289267539978, "value_row": 0.858157217502594, "value_any": 0.8798703551292419, "value_bot": 0.845216691493988, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13580.png", "entropy": 0.08518935739994049} +{"ts": "2026-03-20T20:38:08.671677Z", "loop": 13590, "env_steps": 8349696000, "exact_value_avg": 0.863398551940918, "regret_dist": 0.00018206806271336973, "regret_other_env": 0.00030149967642500997, "regret_corner": 2.920627821367816e-06, "regret_row": 3.786312663578428e-05, "regret_any": 0.0003122853231616318, "regret_bot": 0.0012203053338453174, "value_dist": 0.863398551940918, "value_other_env": 0.8819133639335632, "value_corner": 0.8356263637542725, "value_row": 0.8585887551307678, "value_any": 0.8819383382797241, "value_bot": 0.8574063181877136, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13590.png", "entropy": 0.0870676338672638} +{"ts": "2026-03-20T20:38:17.252093Z", "loop": 13600, "env_steps": 8355840000, "exact_value_avg": 0.8628897666931152, "regret_dist": 0.000690928369294852, "regret_other_env": 0.0011343605583533645, "regret_corner": 2.5780003852560185e-05, "regret_row": 0.003499672980979085, "regret_any": 0.0011328010587021708, "regret_bot": 0.0007217081147246063, "value_dist": 0.8628897666931152, "value_other_env": 0.8810805082321167, "value_corner": 0.8356035947799683, "value_row": 0.8551269173622131, "value_any": 0.8811178207397461, "value_bot": 0.8579049706459045, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13600.png", "entropy": 0.08919883519411087} +{"ts": "2026-03-20T20:38:25.831905Z", "loop": 13610, "env_steps": 8361984000, "exact_value_avg": 0.8614850044250488, "regret_dist": 0.0020956997759640217, "regret_other_env": 0.003447827650234103, "regret_corner": 6.750722968718037e-05, "regret_row": 0.005613934248685837, "regret_any": 0.003459497122094035, "regret_bot": 0.00035950119490735233, "value_dist": 0.8614850044250488, "value_other_env": 0.8787670731544495, "value_corner": 0.8355618119239807, "value_row": 0.8530126810073853, "value_any": 0.8787911534309387, "value_bot": 0.858267068862915, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13610.png", "entropy": 0.08771142363548279} +{"ts": "2026-03-20T20:38:34.414790Z", "loop": 13620, "env_steps": 8368128000, "exact_value_avg": 0.8634455800056458, "regret_dist": 0.00013513118028640747, "regret_other_env": 0.00022375832486432046, "regret_corner": 2.190470922869281e-06, "regret_row": 0.00018042275041807443, "regret_any": 0.00024117690918501467, "regret_bot": 0.0007129039731808007, "value_dist": 0.8634455800056458, "value_other_env": 0.8819911479949951, "value_corner": 0.8356271386146545, "value_row": 0.8584462404251099, "value_any": 0.8820094466209412, "value_bot": 0.8579137325286865, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13620.png", "entropy": 0.07633792608976364} +{"ts": "2026-03-20T20:38:43.004473Z", "loop": 13630, "env_steps": 8374272000, "exact_value_avg": 0.8632562160491943, "regret_dist": 0.0003245683910790831, "regret_other_env": 0.0005396611522883177, "regret_corner": 1.9292037904961035e-06, "regret_row": 0.0005614259862340987, "regret_any": 0.0005633113905787468, "regret_bot": 0.0015575251309201121, "value_dist": 0.8632562160491943, "value_other_env": 0.8816753029823303, "value_corner": 0.8356274366378784, "value_row": 0.8580651879310608, "value_any": 0.881687343120575, "value_bot": 0.8570691347122192, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13630.png", "entropy": 0.07833127677440643} +{"ts": "2026-03-20T20:38:51.591219Z", "loop": 13640, "env_steps": 8380416000, "exact_value_avg": 0.8629566431045532, "regret_dist": 0.0006240678485482931, "regret_other_env": 0.0010387186193838716, "regret_corner": 2.0916263565595727e-06, "regret_row": 0.000934473006054759, "regret_any": 0.0010618718806654215, "regret_bot": 0.0020520733669400215, "value_dist": 0.8629566431045532, "value_other_env": 0.8811761736869812, "value_corner": 0.8356271982192993, "value_row": 0.8576921820640564, "value_any": 0.881188690662384, "value_bot": 0.8565745949745178, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13640.png", "entropy": 0.07928057014942169} +{"ts": "2026-03-20T20:39:00.174268Z", "loop": 13650, "env_steps": 8386560000, "exact_value_avg": 0.861042857170105, "regret_dist": 0.002537870081141591, "regret_other_env": 0.004218060988932848, "regret_corner": 1.7583372027729638e-05, "regret_row": 0.0033218672033399343, "regret_any": 0.0042395759373903275, "regret_bot": 0.004076692275702953, "value_dist": 0.861042857170105, "value_other_env": 0.8779968619346619, "value_corner": 0.8356117606163025, "value_row": 0.8553047776222229, "value_any": 0.8780110478401184, "value_bot": 0.8545499444007874, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13650.png", "entropy": 0.0798991471529007} +{"ts": "2026-03-20T20:39:08.757103Z", "loop": 13660, "env_steps": 8392704000, "exact_value_avg": 0.8610506057739258, "regret_dist": 0.002530038822442293, "regret_other_env": 0.0042051887139678, "regret_corner": 1.731415613903664e-05, "regret_row": 0.0028807141352444887, "regret_any": 0.004225683398544788, "regret_bot": 0.0035209828056395054, "value_dist": 0.8610506057739258, "value_other_env": 0.8780096769332886, "value_corner": 0.8356119990348816, "value_row": 0.8557459712028503, "value_any": 0.8780249357223511, "value_bot": 0.8551056385040283, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13660.png", "entropy": 0.08202609419822693} +{"ts": "2026-03-20T20:39:17.342265Z", "loop": 13670, "env_steps": 8398848000, "exact_value_avg": 0.8608112335205078, "regret_dist": 0.0027694369200617075, "regret_other_env": 0.004600992891937494, "regret_corner": 2.2102396542322822e-05, "regret_row": 0.003890938824042678, "regret_any": 0.004621212836354971, "regret_bot": 0.0024927775375545025, "value_dist": 0.8608112335205078, "value_other_env": 0.87761390209198, "value_corner": 0.8356071710586548, "value_row": 0.8547356724739075, "value_any": 0.8776293992996216, "value_bot": 0.8561338186264038, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13670.png", "entropy": 0.0846962034702301} +{"ts": "2026-03-20T20:39:25.932799Z", "loop": 13680, "env_steps": 8404992000, "exact_value_avg": 0.8629986047744751, "regret_dist": 0.0005821137456223369, "regret_other_env": 0.0009660474024713039, "regret_corner": 6.213287633727305e-06, "regret_row": 0.0005292610148899257, "regret_any": 0.0009890703950077295, "regret_bot": 0.0013392773689702153, "value_dist": 0.8629986047744751, "value_other_env": 0.8812488317489624, "value_corner": 0.8356231451034546, "value_row": 0.8580973744392395, "value_any": 0.8812615871429443, "value_bot": 0.8572874069213867, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13680.png", "entropy": 0.08368320763111115} +{"ts": "2026-03-20T20:39:34.526898Z", "loop": 13690, "env_steps": 8411136000, "exact_value_avg": 0.8634775876998901, "regret_dist": 0.00010308279888704419, "regret_other_env": 0.00016985028923954815, "regret_corner": 2.9315551728359424e-06, "regret_row": 7.327709317905828e-05, "regret_any": 0.00018334353808313608, "regret_bot": 0.0006938435253687203, "value_dist": 0.8634775876998901, "value_other_env": 0.8820450305938721, "value_corner": 0.8356263637542725, "value_row": 0.858553409576416, "value_any": 0.8820672035217285, "value_bot": 0.8579328060150146, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13690.png", "entropy": 0.08588052541017532} +{"ts": "2026-03-20T20:39:43.113578Z", "loop": 13700, "env_steps": 8417280000, "exact_value_avg": 0.8633289337158203, "regret_dist": 0.000251737714279443, "regret_other_env": 0.00041865682578645647, "regret_corner": 1.3589859690910089e-06, "regret_row": 6.45444670226425e-05, "regret_any": 0.00042778244824148715, "regret_bot": 0.0012421361170709133, "value_dist": 0.8633289337158203, "value_other_env": 0.8817961812019348, "value_corner": 0.8356279730796814, "value_row": 0.8585621118545532, "value_any": 0.8818227648735046, "value_bot": 0.8573845028877258, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13700.png", "entropy": 0.08814902603626251} +{"ts": "2026-03-20T20:39:51.697707Z", "loop": 13710, "env_steps": 8423424000, "exact_value_avg": 0.862328290939331, "regret_dist": 0.001252361573278904, "regret_other_env": 0.0020806288812309504, "regret_corner": 9.960433089872822e-06, "regret_row": 0.00017989182379096746, "regret_any": 0.0020987484604120255, "regret_bot": 0.008684102445840836, "value_dist": 0.862328290939331, "value_other_env": 0.8801341652870178, "value_corner": 0.8356193900108337, "value_row": 0.8584467768669128, "value_any": 0.8801518678665161, "value_bot": 0.8499425649642944, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13710.png", "entropy": 0.09148573130369186} +{"ts": "2026-03-20T20:40:00.276222Z", "loop": 13720, "env_steps": 8429568000, "exact_value_avg": 0.8625855445861816, "regret_dist": 0.0009951700922101736, "regret_other_env": 0.0016281579155474901, "regret_corner": 4.568845179164782e-05, "regret_row": 0.0003925426281057298, "regret_any": 0.0016423554625362158, "regret_bot": 0.003804377280175686, "value_dist": 0.8625855445861816, "value_other_env": 0.8805866837501526, "value_corner": 0.8355836868286133, "value_row": 0.8582341074943542, "value_any": 0.8806082606315613, "value_bot": 0.8548222780227661, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13720.png", "entropy": 0.10072201490402222} +{"ts": "2026-03-20T20:40:08.860061Z", "loop": 13730, "env_steps": 8435712000, "exact_value_avg": 0.8628311157226562, "regret_dist": 0.000749589002225548, "regret_other_env": 0.0011307857930660248, "regret_corner": 0.0001777937141014263, "regret_row": 0.0009790090844035149, "regret_any": 0.0011421506060287356, "regret_bot": 0.0018545315833762288, "value_dist": 0.8628311157226562, "value_other_env": 0.8810840845108032, "value_corner": 0.8354515433311462, "value_row": 0.8576476573944092, "value_any": 0.8811084628105164, "value_bot": 0.8567721247673035, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13730.png", "entropy": 0.10986553877592087} +{"ts": "2026-03-20T20:40:17.442668Z", "loop": 13740, "env_steps": 8441856000, "exact_value_avg": 0.8630645275115967, "regret_dist": 0.0005161918234080076, "regret_other_env": 0.0008281198679469526, "regret_corner": 4.829963290831074e-05, "regret_row": 0.0004997607902623713, "regret_any": 0.000849227246362716, "regret_bot": 0.001635708729736507, "value_dist": 0.8630645275115967, "value_other_env": 0.8813867568969727, "value_corner": 0.8355810046195984, "value_row": 0.8581268787384033, "value_any": 0.8814013600349426, "value_bot": 0.8569909930229187, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13740.png", "entropy": 0.09979526698589325} +{"ts": "2026-03-20T20:40:26.030252Z", "loop": 13750, "env_steps": 8448000000, "exact_value_avg": 0.8631914854049683, "regret_dist": 0.0003891952510457486, "regret_other_env": 0.0006392647046595812, "regret_corner": 1.4091035154706333e-05, "regret_row": 0.00041886611143127084, "regret_any": 0.0006607467657886446, "regret_bot": 0.00139424588996917, "value_dist": 0.8631914854049683, "value_other_env": 0.8815755844116211, "value_corner": 0.8356152176856995, "value_row": 0.8582077026367188, "value_any": 0.8815898299217224, "value_bot": 0.8572324514389038, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13750.png", "entropy": 0.09204212576150894} +{"ts": "2026-03-20T20:40:34.613650Z", "loop": 13760, "env_steps": 8454144000, "exact_value_avg": 0.8631982803344727, "regret_dist": 0.0003824046580120921, "regret_other_env": 0.0006238462519831955, "regret_corner": 2.0242234313627705e-05, "regret_row": 0.0004904669476673007, "regret_any": 0.000640680780634284, "regret_bot": 0.0010845125652849674, "value_dist": 0.8631982803344727, "value_other_env": 0.8815910220146179, "value_corner": 0.8356090784072876, "value_row": 0.8581361174583435, "value_any": 0.8816099166870117, "value_bot": 0.857542097568512, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13760.png", "entropy": 0.09149263054132462} +{"ts": "2026-03-20T20:40:43.203683Z", "loop": 13770, "env_steps": 8460288000, "exact_value_avg": 0.8615256547927856, "regret_dist": 0.0020550377666950226, "regret_other_env": 0.0034215759951621294, "regret_corner": 5.229810994933359e-06, "regret_row": 0.003614118555560708, "regret_any": 0.003432484110817313, "regret_bot": 0.003810327500104904, "value_dist": 0.8615256547927856, "value_other_env": 0.8787932991981506, "value_corner": 0.835624098777771, "value_row": 0.8550125360488892, "value_any": 0.8788180947303772, "value_bot": 0.8548163175582886, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13770.png", "entropy": 0.08098772168159485} +{"ts": "2026-03-20T20:40:51.785632Z", "loop": 13780, "env_steps": 8466432000, "exact_value_avg": 0.8627601861953735, "regret_dist": 0.0008204837795346975, "regret_other_env": 0.001360864145681262, "regret_corner": 9.913246685755439e-06, "regret_row": 0.0007032712455838919, "regret_any": 0.0013632271438837051, "regret_bot": 0.0016056755557656288, "value_dist": 0.8627601861953735, "value_other_env": 0.8808539509773254, "value_corner": 0.8356194496154785, "value_row": 0.8579233288764954, "value_any": 0.8808873891830444, "value_bot": 0.8570209741592407, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13780.png", "entropy": 0.08625448495149612} +{"ts": "2026-03-20T20:41:00.369631Z", "loop": 13790, "env_steps": 8472576000, "exact_value_avg": 0.8625305891036987, "regret_dist": 0.0010500604985281825, "regret_other_env": 0.001741790329106152, "regret_corner": 1.2465815416362602e-05, "regret_row": 0.0006857701810076833, "regret_any": 0.0017435492482036352, "regret_bot": 0.001984270289540291, "value_dist": 0.8625305891036987, "value_other_env": 0.8804731369018555, "value_corner": 0.8356168270111084, "value_row": 0.8579408526420593, "value_any": 0.8805070519447327, "value_bot": 0.8566423654556274, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13790.png", "entropy": 0.08906928449869156} +{"ts": "2026-03-20T20:41:08.952547Z", "loop": 13800, "env_steps": 8478720000, "exact_value_avg": 0.8623671531677246, "regret_dist": 0.0012135833967477083, "regret_other_env": 0.002010064898058772, "regret_corner": 1.886089739855379e-05, "regret_row": 0.0005874946364201605, "regret_any": 0.0020270037930458784, "regret_bot": 0.003004165831953287, "value_dist": 0.8623671531677246, "value_other_env": 0.8802047967910767, "value_corner": 0.8356105089187622, "value_row": 0.858039140701294, "value_any": 0.8802236318588257, "value_bot": 0.855622410774231, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13800.png", "entropy": 0.0933375433087349} +{"ts": "2026-03-20T20:41:17.534144Z", "loop": 13810, "env_steps": 8484864000, "exact_value_avg": 0.8630719780921936, "regret_dist": 0.000508698751218617, "regret_other_env": 0.0008368476992473006, "regret_corner": 1.647522185521666e-05, "regret_row": 0.0002737493487074971, "regret_any": 0.0008578754495829344, "regret_bot": 0.0017906130524352193, "value_dist": 0.8630719780921936, "value_other_env": 0.8813780546188354, "value_corner": 0.8356128334999084, "value_row": 0.8583528995513916, "value_any": 0.881392776966095, "value_bot": 0.8568360209465027, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13810.png", "entropy": 0.09393075853586197} +{"ts": "2026-03-20T20:41:26.116486Z", "loop": 13820, "env_steps": 8491008000, "exact_value_avg": 0.8632153272628784, "regret_dist": 0.00036533211823552847, "regret_other_env": 0.0005718558095395565, "regret_corner": 5.554656308959238e-05, "regret_row": 0.0004501250514294952, "regret_any": 0.0005950832855887711, "regret_bot": 0.0015013242373242974, "value_dist": 0.8632153272628784, "value_other_env": 0.8816429972648621, "value_corner": 0.8355737328529358, "value_row": 0.8581764698028564, "value_any": 0.8816554546356201, "value_bot": 0.8571253418922424, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13820.png", "entropy": 0.10141655802726746} +{"ts": "2026-03-20T20:41:34.700557Z", "loop": 13830, "env_steps": 8497152000, "exact_value_avg": 0.8632413148880005, "regret_dist": 0.0003393346269149333, "regret_other_env": 0.0005497813108377159, "regret_corner": 2.3664535547140986e-05, "regret_row": 0.00032891533919610083, "regret_any": 0.0005732813151553273, "regret_bot": 0.0013613849878311157, "value_dist": 0.8632413148880005, "value_other_env": 0.881665050983429, "value_corner": 0.8356056809425354, "value_row": 0.8582977652549744, "value_any": 0.8816773295402527, "value_bot": 0.8572651743888855, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13830.png", "entropy": 0.0922270342707634} +{"ts": "2026-03-20T20:41:43.279804Z", "loop": 13840, "env_steps": 8503296000, "exact_value_avg": 0.863258957862854, "regret_dist": 0.00032172215287573636, "regret_other_env": 0.0005280678742565215, "regret_corner": 1.2203555343148764e-05, "regret_row": 0.00010124815162271261, "regret_any": 0.0005518046673387289, "regret_bot": 0.0019541154615581036, "value_dist": 0.863258957862854, "value_other_env": 0.881686806678772, "value_corner": 0.8356171250343323, "value_row": 0.8585253953933716, "value_any": 0.8816987872123718, "value_bot": 0.8566725850105286, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13840.png", "entropy": 0.09309307485818863} +{"ts": "2026-03-20T20:41:51.867998Z", "loop": 13850, "env_steps": 8509440000, "exact_value_avg": 0.8631718158721924, "regret_dist": 0.0004088847490493208, "regret_other_env": 0.0006773303612135351, "regret_corner": 6.2162680478650145e-06, "regret_row": 7.703321898588911e-05, "regret_any": 0.0007009904365986586, "regret_bot": 0.002562702400609851, "value_dist": 0.8631718158721924, "value_other_env": 0.8815375566482544, "value_corner": 0.8356230854988098, "value_row": 0.8585495352745056, "value_any": 0.881549596786499, "value_bot": 0.8560639023780823, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13850.png", "entropy": 0.09146051853895187} +{"ts": "2026-03-20T20:42:00.455298Z", "loop": 13860, "env_steps": 8515584000, "exact_value_avg": 0.8632089495658875, "regret_dist": 0.00037171292933635414, "regret_other_env": 0.0006085523054935038, "regret_corner": 1.6453863281640224e-05, "regret_row": 0.0001856427697930485, "regret_any": 0.0006322474800981581, "regret_bot": 0.002348768524825573, "value_dist": 0.8632089495658875, "value_other_env": 0.8816062808036804, "value_corner": 0.8356128334999084, "value_row": 0.8584409356117249, "value_any": 0.881618320941925, "value_bot": 0.8562778830528259, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13860.png", "entropy": 0.09006696194410324} +{"ts": "2026-03-20T20:42:09.045298Z", "loop": 13870, "env_steps": 8521728000, "exact_value_avg": 0.8630862236022949, "regret_dist": 0.000494521576911211, "regret_other_env": 0.0008134528761729598, "regret_corner": 1.612454798305407e-05, "regret_row": 0.00015234928287100047, "regret_any": 0.0008371717412956059, "regret_bot": 0.0032851984724402428, "value_dist": 0.8630862236022949, "value_other_env": 0.8814014792442322, "value_corner": 0.8356132507324219, "value_row": 0.8584742546081543, "value_any": 0.881413459777832, "value_bot": 0.855341374874115, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13870.png", "entropy": 0.08890219032764435} +{"ts": "2026-03-20T20:42:17.631742Z", "loop": 13880, "env_steps": 8527872000, "exact_value_avg": 0.8626265525817871, "regret_dist": 0.0009540673927403986, "regret_other_env": 0.0015809325268492103, "regret_corner": 1.3769667020824272e-05, "regret_row": 0.00014972830831538886, "regret_any": 0.001605359953828156, "regret_bot": 0.005791775416582823, "value_dist": 0.8626265525817871, "value_other_env": 0.8806338906288147, "value_corner": 0.8356155157089233, "value_row": 0.8584769368171692, "value_any": 0.8806452751159668, "value_bot": 0.8528348803520203, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13880.png", "entropy": 0.09246228635311127} +{"ts": "2026-03-20T20:42:26.209210Z", "loop": 13890, "env_steps": 8534016000, "exact_value_avg": 0.8607281446456909, "regret_dist": 0.0028525751549750566, "regret_other_env": 0.0047439164482057095, "regret_corner": 1.556326969875954e-05, "regret_row": 0.00016962591325864196, "regret_any": 0.0047868420369923115, "regret_bot": 0.013963038101792336, "value_dist": 0.8607281446456909, "value_other_env": 0.8774709701538086, "value_corner": 0.8356137871742249, "value_row": 0.8584570288658142, "value_any": 0.8774637579917908, "value_bot": 0.844663679599762, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13890.png", "entropy": 0.09726087003946304} +{"ts": "2026-03-20T20:42:34.792462Z", "loop": 13900, "env_steps": 8540160000, "exact_value_avg": 0.8624547123908997, "regret_dist": 0.0011259906459599733, "regret_other_env": 0.0018560661701485515, "regret_corner": 3.087719596805982e-05, "regret_row": 0.0001596279616933316, "regret_any": 0.001882013282738626, "regret_bot": 0.00610617408528924, "value_dist": 0.8624547123908997, "value_other_env": 0.880358874797821, "value_corner": 0.8355984091758728, "value_row": 0.8584670424461365, "value_any": 0.8803685903549194, "value_bot": 0.8525204658508301, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13900.png", "entropy": 0.10023301094770432} +{"ts": "2026-03-20T20:42:43.377532Z", "loop": 13910, "env_steps": 8546304000, "exact_value_avg": 0.8631668090820312, "regret_dist": 0.00041393315768800676, "regret_other_env": 0.000670374371111393, "regret_corner": 2.9271346647874452e-05, "regret_row": 0.0002496835368219763, "regret_any": 0.0006907968781888485, "regret_bot": 0.0020766654051840305, "value_dist": 0.8631668090820312, "value_other_env": 0.8815444707870483, "value_corner": 0.8356000781059265, "value_row": 0.8583769798278809, "value_any": 0.8815597891807556, "value_bot": 0.8565499782562256, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13910.png", "entropy": 0.09032905101776123} +{"ts": "2026-03-20T20:42:51.965098Z", "loop": 13920, "env_steps": 8552448000, "exact_value_avg": 0.8625317811965942, "regret_dist": 0.001048872945830226, "regret_other_env": 0.0017103715799748898, "regret_corner": 5.6624910939717665e-05, "regret_row": 0.0003659897483885288, "regret_any": 0.0017172194784507155, "regret_bot": 0.0022354358807206154, "value_dist": 0.8625317811965942, "value_other_env": 0.8805045485496521, "value_corner": 0.8355726599693298, "value_row": 0.8582606315612793, "value_any": 0.8805333375930786, "value_bot": 0.856391191482544, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13920.png", "entropy": 0.09392670542001724} +{"ts": "2026-03-20T20:43:00.547054Z", "loop": 13930, "env_steps": 8558592000, "exact_value_avg": 0.8622453212738037, "regret_dist": 0.0013353711692616343, "regret_other_env": 0.002138886135071516, "regret_corner": 0.00013009857502765954, "regret_row": 0.0007559149526059628, "regret_any": 0.002136561321094632, "regret_bot": 0.0043668486177921295, "value_dist": 0.8622453212738037, "value_other_env": 0.8800760507583618, "value_corner": 0.8354991674423218, "value_row": 0.8578707575798035, "value_any": 0.8801140785217285, "value_bot": 0.8542597889900208, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13930.png", "entropy": 0.09731008857488632} +{"ts": "2026-03-20T20:43:09.124734Z", "loop": 13940, "env_steps": 8564736000, "exact_value_avg": 0.8617880344390869, "regret_dist": 0.0017926819855347276, "regret_other_env": 0.0026867177803069353, "regret_corner": 0.0004516278859227896, "regret_row": 0.002103593898937106, "regret_any": 0.0026827387046068907, "regret_bot": 0.011012638919055462, "value_dist": 0.8617880344390869, "value_other_env": 0.8795281648635864, "value_corner": 0.8351776599884033, "value_row": 0.8565230369567871, "value_any": 0.8795678615570068, "value_bot": 0.847614049911499, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13940.png", "entropy": 0.10181118547916412} +{"ts": "2026-03-20T20:43:17.704574Z", "loop": 13950, "env_steps": 8570880000, "exact_value_avg": 0.8618127107620239, "regret_dist": 0.0017680232413113117, "regret_other_env": 0.00269654905423522, "regret_corner": 0.000375234114471823, "regret_row": 0.0019367597997188568, "regret_any": 0.0026925711426883936, "regret_bot": 0.012814016081392765, "value_dist": 0.8618127107620239, "value_other_env": 0.8795183300971985, "value_corner": 0.8352540731430054, "value_row": 0.8566898703575134, "value_any": 0.8795579671859741, "value_bot": 0.8458126187324524, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13950.png", "entropy": 0.10188000649213791} +{"ts": "2026-03-20T20:43:26.286900Z", "loop": 13960, "env_steps": 8577024000, "exact_value_avg": 0.8630419969558716, "regret_dist": 0.000538657302968204, "regret_other_env": 0.0008795204339548945, "regret_corner": 2.7362506443751045e-05, "regret_row": 0.00029472706955857575, "regret_any": 0.0008787154802121222, "regret_bot": 0.0033061872236430645, "value_dist": 0.8630419969558716, "value_other_env": 0.8813353180885315, "value_corner": 0.8356019854545593, "value_row": 0.8583319187164307, "value_any": 0.8813719153404236, "value_bot": 0.855320394039154, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13960.png", "entropy": 0.0932840034365654} +{"ts": "2026-03-20T20:43:34.871576Z", "loop": 13970, "env_steps": 8583168000, "exact_value_avg": 0.86298668384552, "regret_dist": 0.0005940155824646354, "regret_other_env": 0.0009783533168956637, "regret_corner": 1.75088662217604e-05, "regret_row": 0.0004070678842253983, "regret_any": 0.0009915713453665376, "regret_bot": 0.003564879298210144, "value_dist": 0.86298668384552, "value_other_env": 0.8812365531921387, "value_corner": 0.8356118202209473, "value_row": 0.858219563961029, "value_any": 0.881259024143219, "value_bot": 0.8550618290901184, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13970.png", "entropy": 0.08917480707168579} +{"ts": "2026-03-20T20:43:43.453865Z", "loop": 13980, "env_steps": 8589312000, "exact_value_avg": 0.8630423545837402, "regret_dist": 0.0005383479292504489, "regret_other_env": 0.0008522499701939523, "regret_corner": 6.749480962753296e-05, "regret_row": 0.0007121788221411407, "regret_any": 0.0008675797726027668, "regret_bot": 0.00215536099858582, "value_dist": 0.8630423545837402, "value_other_env": 0.8813626766204834, "value_corner": 0.8355618119239807, "value_row": 0.8579144477844238, "value_any": 0.8813830614089966, "value_bot": 0.8564713001251221, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13980.png", "entropy": 0.0919322818517685} +{"ts": "2026-03-20T20:43:52.032324Z", "loop": 13990, "env_steps": 8595456000, "exact_value_avg": 0.8625555038452148, "regret_dist": 0.0010251995408907533, "regret_other_env": 0.0015977949369698763, "regret_corner": 0.00016630640311632305, "regret_row": 0.0014511438785120845, "regret_any": 0.0016157440841197968, "regret_bot": 0.0021185518708080053, "value_dist": 0.8625555038452148, "value_other_env": 0.880617082118988, "value_corner": 0.8354629874229431, "value_row": 0.8571754693984985, "value_any": 0.8806349039077759, "value_bot": 0.8565080761909485, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_13990.png", "entropy": 0.09498037397861481} +{"ts": "2026-03-20T20:44:00.613566Z", "loop": 14000, "env_steps": 8601600000, "exact_value_avg": 0.8615946769714355, "regret_dist": 0.001985996961593628, "regret_other_env": 0.002701240126043558, "regret_corner": 0.0009131322731263936, "regret_row": 0.003270514076575637, "regret_any": 0.0027190265245735645, "regret_bot": 0.002395551884546876, "value_dist": 0.8615946769714355, "value_other_env": 0.8795136213302612, "value_corner": 0.8347161412239075, "value_row": 0.8553560972213745, "value_any": 0.8795315623283386, "value_bot": 0.8562310934066772, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14000.png", "entropy": 0.10585545748472214} +{"ts": "2026-03-20T20:44:09.192624Z", "loop": 14010, "env_steps": 8607744000, "exact_value_avg": 0.8625036478042603, "regret_dist": 0.0010770905064418912, "regret_other_env": 0.0013965939870104194, "regret_corner": 0.0005978351109661162, "regret_row": 0.0015121400356292725, "regret_any": 0.0014139001723378897, "regret_bot": 0.002726042876020074, "value_dist": 0.8625036478042603, "value_other_env": 0.8808183073997498, "value_corner": 0.8350315690040588, "value_row": 0.8571144342422485, "value_any": 0.8808367252349854, "value_bot": 0.8559005856513977, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14010.png", "entropy": 0.10357517004013062} +{"ts": "2026-03-20T20:44:17.773502Z", "loop": 14020, "env_steps": 8613888000, "exact_value_avg": 0.8630130290985107, "regret_dist": 0.0005676253349520266, "regret_other_env": 0.0009069882798939943, "regret_corner": 5.858093936694786e-05, "regret_row": 0.0005429311422631145, "regret_any": 0.0009290968882851303, "regret_bot": 0.0029624728485941887, "value_dist": 0.8630130290985107, "value_other_env": 0.8813078999519348, "value_corner": 0.835570752620697, "value_row": 0.8580837249755859, "value_any": 0.8813214302062988, "value_bot": 0.8556641340255737, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14020.png", "entropy": 0.08973277360200882} +{"ts": "2026-03-20T20:44:26.362648Z", "loop": 14030, "env_steps": 8620032000, "exact_value_avg": 0.8629105091094971, "regret_dist": 0.0006701394449919462, "regret_other_env": 0.0010875186417251825, "regret_corner": 4.4070682633901015e-05, "regret_row": 0.0005916497320868075, "regret_any": 0.0011102539720013738, "regret_bot": 0.00318654696457088, "value_dist": 0.8629105091094971, "value_other_env": 0.8811273574829102, "value_corner": 0.8355852365493774, "value_row": 0.8580349683761597, "value_any": 0.8811403512954712, "value_bot": 0.855440080165863, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14030.png", "entropy": 0.08900145441293716} +{"ts": "2026-03-20T20:44:34.947813Z", "loop": 14040, "env_steps": 8626176000, "exact_value_avg": 0.8610632419586182, "regret_dist": 0.0025175237096846104, "regret_other_env": 0.0040440247394144535, "regret_corner": 0.00022777171398047358, "regret_row": 0.006465752609074116, "regret_any": 0.0040633948519825935, "regret_bot": 0.002048193709924817, "value_dist": 0.8610632419586182, "value_other_env": 0.8781708478927612, "value_corner": 0.8354015946388245, "value_row": 0.8521608114242554, "value_any": 0.8781871795654297, "value_bot": 0.8565784692764282, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14040.png", "entropy": 0.09411439299583435} +{"ts": "2026-03-20T20:44:43.535190Z", "loop": 14050, "env_steps": 8632320000, "exact_value_avg": 0.8628858327865601, "regret_dist": 0.0006949075032025576, "regret_other_env": 0.0011266747023910284, "regret_corner": 4.7256551624741405e-05, "regret_row": 0.0007259371923282743, "regret_any": 0.0011491806944832206, "regret_bot": 0.0024650453124195337, "value_dist": 0.8628858327865601, "value_other_env": 0.8810881972312927, "value_corner": 0.8355820775032043, "value_row": 0.8579006791114807, "value_any": 0.8811013698577881, "value_bot": 0.8561615347862244, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14050.png", "entropy": 0.09025373309850693} +{"ts": "2026-03-20T20:44:52.117673Z", "loop": 14060, "env_steps": 8638464000, "exact_value_avg": 0.8630611896514893, "regret_dist": 0.0005195482517592609, "regret_other_env": 0.0008433347684331238, "regret_corner": 3.386835305718705e-05, "regret_row": 0.0003689382574521005, "regret_any": 0.000858468993101269, "regret_bot": 0.0030959262512624264, "value_dist": 0.8630611896514893, "value_other_env": 0.8813715577125549, "value_corner": 0.8355954885482788, "value_row": 0.8582576513290405, "value_any": 0.8813921213150024, "value_bot": 0.8555306792259216, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14060.png", "entropy": 0.09463507682085037} +{"ts": "2026-03-20T20:45:00.698500Z", "loop": 14070, "env_steps": 8644608000, "exact_value_avg": 0.8628427982330322, "regret_dist": 0.0007379293674603105, "regret_other_env": 0.0012210382847115397, "regret_corner": 1.3266007954371162e-05, "regret_row": 0.00017580913845449686, "regret_any": 0.0012194688897579908, "regret_bot": 0.004368819296360016, "value_dist": 0.8628427982330322, "value_other_env": 0.8809938430786133, "value_corner": 0.8356161117553711, "value_row": 0.8584508299827576, "value_any": 0.8810310959815979, "value_bot": 0.8542578220367432, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14070.png", "entropy": 0.09356173872947693} +{"ts": "2026-03-20T20:45:09.281341Z", "loop": 14080, "env_steps": 8650752000, "exact_value_avg": 0.8608257174491882, "regret_dist": 0.0027550410013645887, "regret_other_env": 0.004585689399391413, "regret_corner": 9.068350664165337e-06, "regret_row": 0.0026316181756556034, "regret_any": 0.004585247952491045, "regret_bot": 0.009309905581176281, "value_dist": 0.8608257174491882, "value_other_env": 0.877629280090332, "value_corner": 0.8356202840805054, "value_row": 0.8559949994087219, "value_any": 0.8776654005050659, "value_bot": 0.8493167757987976, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14080.png", "entropy": 0.09032983332872391} +{"ts": "2026-03-20T20:45:17.861764Z", "loop": 14090, "env_steps": 8656896000, "exact_value_avg": 0.8592689037322998, "regret_dist": 0.004311768338084221, "regret_other_env": 0.006420232821255922, "regret_corner": 0.0011490712640807033, "regret_row": 0.0010956820333376527, "regret_any": 0.006424080580472946, "regret_bot": 0.02638130635023117, "value_dist": 0.8592689037322998, "value_other_env": 0.8757946491241455, "value_corner": 0.8344802856445312, "value_row": 0.857530951499939, "value_any": 0.8758265376091003, "value_bot": 0.832245409488678, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14090.png", "entropy": 0.10578785091638565} +{"ts": "2026-03-20T20:45:26.444168Z", "loop": 14100, "env_steps": 8663040000, "exact_value_avg": 0.8628215789794922, "regret_dist": 0.0007591158500872552, "regret_other_env": 0.0009767061565071344, "regret_corner": 0.00043273024493828416, "regret_row": 0.0005579373682849109, "regret_any": 0.0009756454965099692, "regret_bot": 0.0026022749952971935, "value_dist": 0.8628215789794922, "value_other_env": 0.8812381625175476, "value_corner": 0.8351966142654419, "value_row": 0.8580687046051025, "value_any": 0.881274938583374, "value_bot": 0.8560243248939514, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14100.png", "entropy": 0.10280079394578934} +{"ts": "2026-03-20T20:45:35.024628Z", "loop": 14110, "env_steps": 8669184000, "exact_value_avg": 0.8634337186813354, "regret_dist": 0.00014698041195515543, "regret_other_env": 0.00024348519218619913, "regret_corner": 2.2232534320210107e-06, "regret_row": 0.00026844412786886096, "regret_any": 0.0002532430225983262, "regret_bot": 0.0006108206580393016, "value_dist": 0.8634337186813354, "value_other_env": 0.8819713592529297, "value_corner": 0.8356270790100098, "value_row": 0.8583582043647766, "value_any": 0.8819974064826965, "value_bot": 0.8580158352851868, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14110.png", "entropy": 0.07391093671321869} +{"ts": "2026-03-20T20:45:43.607653Z", "loop": 14120, "env_steps": 8675328000, "exact_value_avg": 0.8607107400894165, "regret_dist": 0.0028699550312012434, "regret_other_env": 0.004782085306942463, "regret_corner": 1.7598272279428784e-06, "regret_row": 0.004923834931105375, "regret_any": 0.004905642941594124, "regret_bot": 0.00142183480784297, "value_dist": 0.8607107400894165, "value_other_env": 0.8774328231811523, "value_corner": 0.835627555847168, "value_row": 0.8537027835845947, "value_any": 0.8773449659347534, "value_bot": 0.857204794883728, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14120.png", "entropy": 0.07302530854940414} +{"ts": "2026-03-20T20:45:52.185972Z", "loop": 14130, "env_steps": 8681472000, "exact_value_avg": 0.8623183965682983, "regret_dist": 0.0012623099610209465, "regret_other_env": 0.00210376875475049, "regret_corner": 1.216928211533741e-07, "regret_row": 0.001329165417701006, "regret_any": 0.002127783838659525, "regret_bot": 0.0015201113419607282, "value_dist": 0.8623183965682983, "value_other_env": 0.8801111578941345, "value_corner": 0.8356291651725769, "value_row": 0.8572973608970642, "value_any": 0.8801228404045105, "value_bot": 0.8571065068244934, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14130.png", "entropy": 0.06811948865652084} +{"ts": "2026-03-20T20:46:00.764651Z", "loop": 14140, "env_steps": 8687616000, "exact_value_avg": 0.8623528480529785, "regret_dist": 0.0012278227368369699, "regret_other_env": 0.002046322450041771, "regret_corner": 7.301569127093899e-08, "regret_row": 0.000942331156693399, "regret_any": 0.002071310067549348, "regret_bot": 0.001598807517439127, "value_dist": 0.8623528480529785, "value_other_env": 0.8801685571670532, "value_corner": 0.8356292247772217, "value_row": 0.857684314250946, "value_any": 0.8801792860031128, "value_bot": 0.8570278882980347, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14140.png", "entropy": 0.06684659421443939} +{"ts": "2026-03-20T20:46:09.342864Z", "loop": 14150, "env_steps": 8693760000, "exact_value_avg": 0.8632029294967651, "regret_dist": 0.0003778024693019688, "regret_other_env": 0.0006297283689491451, "regret_corner": -8.642673776648735e-08, "regret_row": 0.0002496745146345347, "regret_any": 0.0006565195508301258, "regret_bot": 0.0012338182423263788, "value_dist": 0.8632029294967651, "value_other_env": 0.8815851807594299, "value_corner": 0.8356294631958008, "value_row": 0.8583769798278809, "value_any": 0.8815941214561462, "value_bot": 0.8573927879333496, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14150.png", "entropy": 0.06628221273422241} +{"ts": "2026-03-20T20:46:17.923853Z", "loop": 14160, "env_steps": 8699904000, "exact_value_avg": 0.8625277280807495, "regret_dist": 0.0010529359569773078, "regret_other_env": 0.0017547920579090714, "regret_corner": 1.514951435410694e-07, "regret_row": 0.0005525435553863645, "regret_any": 0.0018280392978340387, "regret_bot": 0.001084828400053084, "value_dist": 0.8625277280807495, "value_other_env": 0.8804600834846497, "value_corner": 0.8356291651725769, "value_row": 0.8580740094184875, "value_any": 0.8804225921630859, "value_bot": 0.8575417995452881, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14160.png", "entropy": 0.06797468662261963} +{"ts": "2026-03-20T20:46:26.512081Z", "loop": 14170, "env_steps": 8706048000, "exact_value_avg": 0.8633707761764526, "regret_dist": 0.00020991686324123293, "regret_other_env": 0.00034972335561178625, "regret_corner": 2.0712614912099525e-07, "regret_row": 0.0004246178432367742, "regret_any": 0.00037297833478078246, "regret_bot": 0.0007545762928202748, "value_dist": 0.8633707761764526, "value_other_env": 0.8818651437759399, "value_corner": 0.8356291055679321, "value_row": 0.8582019805908203, "value_any": 0.8818776607513428, "value_bot": 0.8578720092773438, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14170.png", "entropy": 0.06778765469789505} +{"ts": "2026-03-20T20:46:35.094169Z", "loop": 14180, "env_steps": 8712192000, "exact_value_avg": 0.8634685277938843, "regret_dist": 0.0001121643726946786, "regret_other_env": 0.00018660583009477705, "regret_corner": 5.021691436013498e-07, "regret_row": 0.0002735628222580999, "regret_any": 0.00019758910639211535, "regret_bot": 0.0005071396590210497, "value_dist": 0.8634685277938843, "value_other_env": 0.8820282816886902, "value_corner": 0.8356288075447083, "value_row": 0.8583530783653259, "value_any": 0.882053017616272, "value_bot": 0.8581194877624512, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14180.png", "entropy": 0.06766984611749649} +{"ts": "2026-03-20T20:46:43.681226Z", "loop": 14190, "env_steps": 8718336000, "exact_value_avg": 0.8634833097457886, "regret_dist": 9.735474304761738e-05, "regret_other_env": 0.00016212246555369347, "regret_corner": 2.0315250992553047e-07, "regret_row": 1.1527808965183794e-05, "regret_any": 0.00018013683438766748, "regret_bot": 0.0008362515945918858, "value_dist": 0.8634833097457886, "value_other_env": 0.8820527791976929, "value_corner": 0.8356291055679321, "value_row": 0.8586151003837585, "value_any": 0.8820704817771912, "value_bot": 0.857790470123291, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14190.png", "entropy": 0.06888720393180847} +{"ts": "2026-03-20T20:46:52.266144Z", "loop": 14200, "env_steps": 8724480000, "exact_value_avg": 0.8628472089767456, "regret_dist": 0.0007335434202104807, "regret_other_env": 0.0012223769444972277, "regret_corner": 2.9305618909347686e-07, "regret_row": 1.5256349797709845e-05, "regret_any": 0.0012552376138046384, "regret_bot": 0.005652931053191423, "value_dist": 0.8628472089767456, "value_other_env": 0.8809925317764282, "value_corner": 0.8356290459632874, "value_row": 0.8586114048957825, "value_any": 0.8809953927993774, "value_bot": 0.8529737591743469, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14200.png", "entropy": 0.07589972764253616} +{"ts": "2026-03-20T20:47:00.857549Z", "loop": 14210, "env_steps": 8730624000, "exact_value_avg": 0.8629711866378784, "regret_dist": 0.0006094452692195773, "regret_other_env": 0.0010150824673473835, "regret_corner": 9.89437126008852e-07, "regret_row": 7.747294148430228e-06, "regret_any": 0.0010429549729451537, "regret_bot": 0.005794363562017679, "value_dist": 0.8629711866378784, "value_other_env": 0.8811997771263123, "value_corner": 0.8356282711029053, "value_row": 0.8586188554763794, "value_any": 0.8812076449394226, "value_bot": 0.8528322577476501, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14210.png", "entropy": 0.07625673711299896} +{"ts": "2026-03-20T20:47:09.437416Z", "loop": 14220, "env_steps": 8736768000, "exact_value_avg": 0.8630551099777222, "regret_dist": 0.000525621057022363, "regret_other_env": 0.0008661409956403077, "regret_corner": 1.48410608744598e-05, "regret_row": 7.719428685959429e-05, "regret_any": 0.0008900464163161814, "regret_bot": 0.003434001235291362, "value_dist": 0.8630551099777222, "value_other_env": 0.8813487887382507, "value_corner": 0.8356144428253174, "value_row": 0.8585494160652161, "value_any": 0.8813605904579163, "value_bot": 0.8551926016807556, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14220.png", "entropy": 0.07781895250082016} +{"ts": "2026-03-20T20:47:18.017053Z", "loop": 14230, "env_steps": 8742912000, "exact_value_avg": 0.8632494211196899, "regret_dist": 0.0003312053740955889, "regret_other_env": 0.0005494902725331485, "regret_corner": 3.7779411741212243e-06, "regret_row": 6.964428030187264e-05, "regret_any": 0.0005733345169574022, "regret_bot": 0.0020134674850851297, "value_dist": 0.8632494211196899, "value_other_env": 0.8816653490066528, "value_corner": 0.8356255292892456, "value_row": 0.8585569262504578, "value_any": 0.8816772699356079, "value_bot": 0.8566132187843323, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14230.png", "entropy": 0.07315590232610703} +{"ts": "2026-03-20T20:47:26.599406Z", "loop": 14240, "env_steps": 8749056000, "exact_value_avg": 0.8630174398422241, "regret_dist": 0.0005632067332044244, "regret_other_env": 0.0009381390991620719, "regret_corner": 8.081397027126513e-07, "regret_row": 5.3977153584128246e-05, "regret_any": 0.0009619382326491177, "regret_bot": 0.0030821373220533133, "value_dist": 0.8630174398422241, "value_other_env": 0.8812767267227173, "value_corner": 0.8356285691261292, "value_row": 0.8585726618766785, "value_any": 0.8812886476516724, "value_bot": 0.8555445671081543, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14240.png", "entropy": 0.0741380974650383} +{"ts": "2026-03-20T20:47:35.180224Z", "loop": 14250, "env_steps": 8755200000, "exact_value_avg": 0.8626619577407837, "regret_dist": 0.0009186991374008358, "regret_other_env": 0.0015310108428820968, "regret_corner": 2.3146471050949913e-07, "regret_row": 2.021121144935023e-05, "regret_any": 0.0015545181231573224, "regret_bot": 0.004135881084948778, "value_dist": 0.8626619577407837, "value_other_env": 0.8806838393211365, "value_corner": 0.8356291055679321, "value_row": 0.8586063981056213, "value_any": 0.8806961178779602, "value_bot": 0.8544907569885254, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14250.png", "entropy": 0.07427094131708145} +{"ts": "2026-03-20T20:47:43.758901Z", "loop": 14260, "env_steps": 8761344000, "exact_value_avg": 0.8625063300132751, "regret_dist": 0.0010743944440037012, "regret_other_env": 0.0017906648572534323, "regret_corner": -1.1424224233280711e-08, "regret_row": 7.096696208463982e-05, "regret_any": 0.0018136485014110804, "regret_bot": 0.0034808721393346786, "value_dist": 0.8625063300132751, "value_other_env": 0.8804242610931396, "value_corner": 0.835629403591156, "value_row": 0.8585556149482727, "value_any": 0.880436897277832, "value_bot": 0.8551458120346069, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14260.png", "entropy": 0.07363705337047577} +{"ts": "2026-03-20T20:47:52.340650Z", "loop": 14270, "env_steps": 8767488000, "exact_value_avg": 0.8632317185401917, "regret_dist": 0.0003488893562462181, "regret_other_env": 0.0005813799216412008, "regret_corner": 1.534819631388018e-07, "regret_row": 9.614048030925915e-05, "regret_any": 0.0006053088582120836, "regret_bot": 0.001682774513028562, "value_dist": 0.8632317185401917, "value_other_env": 0.881633460521698, "value_corner": 0.8356291055679321, "value_row": 0.8585304617881775, "value_any": 0.8816453218460083, "value_bot": 0.8569438457489014, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14270.png", "entropy": 0.06631173193454742} +{"ts": "2026-03-20T20:48:00.928057Z", "loop": 14280, "env_steps": 8773632000, "exact_value_avg": 0.8614689111709595, "regret_dist": 0.0021118181757628918, "regret_other_env": 0.0035165157169103622, "regret_corner": 4.771848580276128e-06, "regret_row": 0.0009533686679787934, "regret_any": 0.0035570093896239996, "regret_bot": 0.004224839154630899, "value_dist": 0.8614689111709595, "value_other_env": 0.8786983489990234, "value_corner": 0.835624635219574, "value_row": 0.8576732277870178, "value_any": 0.8786936402320862, "value_bot": 0.854401707649231, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14280.png", "entropy": 0.06968680024147034} +{"ts": "2026-03-20T20:48:09.509809Z", "loop": 14290, "env_steps": 8779776000, "exact_value_avg": 0.8605664968490601, "regret_dist": 0.0030142036266624928, "regret_other_env": 0.005021593999117613, "regret_corner": 3.117819687759038e-06, "regret_row": 0.0029855817556381226, "regret_any": 0.005064711440354586, "regret_bot": 0.007719892077147961, "value_dist": 0.8605664968490601, "value_other_env": 0.8771933317184448, "value_corner": 0.8356261849403381, "value_row": 0.8556410074234009, "value_any": 0.8771858811378479, "value_bot": 0.8509067893028259, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14290.png", "entropy": 0.06927936524152756} +{"ts": "2026-03-20T20:48:18.098214Z", "loop": 14300, "env_steps": 8785920000, "exact_value_avg": 0.8628687858581543, "regret_dist": 0.0007119267829693854, "regret_other_env": 0.0011849402217194438, "regret_corner": 2.406537760180072e-06, "regret_row": 0.0016581839881837368, "regret_any": 0.0012121424078941345, "regret_bot": 0.002457513241097331, "value_dist": 0.8628687858581543, "value_other_env": 0.8810299038887024, "value_corner": 0.8356269001960754, "value_row": 0.8569685220718384, "value_any": 0.8810384273529053, "value_bot": 0.8561691641807556, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14300.png", "entropy": 0.06547503173351288} +{"ts": "2026-03-20T20:48:26.685722Z", "loop": 14310, "env_steps": 8792064000, "exact_value_avg": 0.8631751537322998, "regret_dist": 0.0004055271565448493, "regret_other_env": 0.0006758033996447921, "regret_corner": 1.1275212585815098e-07, "regret_row": 5.7324901717947796e-05, "regret_any": 0.0006995397270657122, "regret_bot": 0.002243563998490572, "value_dist": 0.8631751537322998, "value_other_env": 0.8815391063690186, "value_corner": 0.8356291651725769, "value_row": 0.858569324016571, "value_any": 0.8815510869026184, "value_bot": 0.8563831448554993, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14310.png", "entropy": 0.07347005605697632} +{"ts": "2026-03-20T20:48:35.269747Z", "loop": 14320, "env_steps": 8798208000, "exact_value_avg": 0.8628950119018555, "regret_dist": 0.0006856295512989163, "regret_other_env": 0.001142527093179524, "regret_corner": 2.831220911048149e-07, "regret_row": 6.941123137949035e-05, "regret_any": 0.0011666225036606193, "regret_bot": 0.005246688146144152, "value_dist": 0.8628950119018555, "value_other_env": 0.8810723423957825, "value_corner": 0.8356290459632874, "value_row": 0.8585572838783264, "value_any": 0.8810840249061584, "value_bot": 0.8533799052238464, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14320.png", "entropy": 0.07597414404153824} +{"ts": "2026-03-20T20:48:43.852341Z", "loop": 14330, "env_steps": 8804352000, "exact_value_avg": 0.8634047508239746, "regret_dist": 0.00017591455252841115, "regret_other_env": 0.0002923412248492241, "regret_corner": 1.274546093554818e-06, "regret_row": 5.523797153728083e-05, "regret_any": 0.00031639105873182416, "regret_bot": 0.001315712695941329, "value_dist": 0.8634047508239746, "value_other_env": 0.8819225430488586, "value_corner": 0.8356280326843262, "value_row": 0.8585713505744934, "value_any": 0.8819342255592346, "value_bot": 0.8573108911514282, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14330.png", "entropy": 0.06823308765888214} +{"ts": "2026-03-20T20:48:52.435415Z", "loop": 14340, "env_steps": 8810496000, "exact_value_avg": 0.86262047290802, "regret_dist": 0.0009601910132914782, "regret_other_env": 0.0015980033203959465, "regret_corner": 3.4724673696473474e-06, "regret_row": 0.0026077323127537966, "regret_any": 0.001622428884729743, "regret_bot": 0.0022130869328975677, "value_dist": 0.86262047290802, "value_other_env": 0.8806169033050537, "value_corner": 0.8356258869171143, "value_row": 0.8560189604759216, "value_any": 0.8806281685829163, "value_bot": 0.8564135432243347, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14340.png", "entropy": 0.06646119803190231} +{"ts": "2026-03-20T20:49:01.015913Z", "loop": 14350, "env_steps": 8816640000, "exact_value_avg": 0.8625556230545044, "regret_dist": 0.0010250553023070097, "regret_other_env": 0.001702142646536231, "regret_corner": 9.423991286894307e-06, "regret_row": 0.001282022218219936, "regret_any": 0.0017300904728472233, "regret_bot": 0.0028487863019108772, "value_dist": 0.8625556230545044, "value_other_env": 0.8805127143859863, "value_corner": 0.8356199264526367, "value_row": 0.8573446273803711, "value_any": 0.8805205225944519, "value_bot": 0.8557778596878052, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14350.png", "entropy": 0.06721065193414688} +{"ts": "2026-03-20T20:49:09.600434Z", "loop": 14360, "env_steps": 8822784000, "exact_value_avg": 0.8634207248687744, "regret_dist": 0.00016003586642909795, "regret_other_env": 0.00026489756419323385, "regret_corner": 2.7433038667368237e-06, "regret_row": 1.9312084987177514e-05, "regret_any": 0.00028897568699903786, "regret_bot": 0.0012806584127247334, "value_dist": 0.8634207248687744, "value_other_env": 0.8819500207901001, "value_corner": 0.8356266021728516, "value_row": 0.8586074113845825, "value_any": 0.8819616436958313, "value_bot": 0.8573459386825562, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14360.png", "entropy": 0.06778056174516678} +{"ts": "2026-03-20T20:49:18.184383Z", "loop": 14370, "env_steps": 8828928000, "exact_value_avg": 0.8633313775062561, "regret_dist": 0.00024927675258368254, "regret_other_env": 0.00041122635593637824, "regret_corner": 6.352365289785666e-06, "regret_row": 4.933273157803342e-05, "regret_any": 0.0004351652169134468, "regret_bot": 0.0013728251215070486, "value_dist": 0.8633313775062561, "value_other_env": 0.881803572177887, "value_corner": 0.8356229662895203, "value_row": 0.8585772514343262, "value_any": 0.8818154335021973, "value_bot": 0.8572537899017334, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14370.png", "entropy": 0.06693270057439804} +{"ts": "2026-03-20T20:49:26.766358Z", "loop": 14380, "env_steps": 8835072000, "exact_value_avg": 0.8632130026817322, "regret_dist": 0.00036769889993593097, "regret_other_env": 0.0006088074878789485, "regret_corner": 6.035963906469988e-06, "regret_row": 8.571129728807136e-05, "regret_any": 0.000632795796263963, "regret_bot": 0.0018867510370910168, "value_dist": 0.8632130026817322, "value_other_env": 0.8816061019897461, "value_corner": 0.8356232643127441, "value_row": 0.8585408329963684, "value_any": 0.8816177845001221, "value_bot": 0.8567399382591248, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14380.png", "entropy": 0.06740479171276093} +{"ts": "2026-03-20T20:49:35.346493Z", "loop": 14390, "env_steps": 8841216000, "exact_value_avg": 0.8623157739639282, "regret_dist": 0.0012648551492020488, "regret_other_env": 0.002081885002553463, "regret_corner": 3.931026003556326e-05, "regret_row": 0.00018846879538614303, "regret_any": 0.0021048684138804674, "regret_bot": 0.0033633948769420385, "value_dist": 0.8623157739639282, "value_other_env": 0.8801329731941223, "value_corner": 0.8355900049209595, "value_row": 0.8584381937980652, "value_any": 0.8801457285881042, "value_bot": 0.8552632331848145, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14390.png", "entropy": 0.0778219923377037} +{"ts": "2026-03-20T20:49:43.921255Z", "loop": 14400, "env_steps": 8847360000, "exact_value_avg": 0.8628472089767456, "regret_dist": 0.0007335245609283447, "regret_other_env": 0.0012034369865432382, "regret_corner": 2.8655927962972783e-05, "regret_row": 6.0322199715301394e-05, "regret_any": 0.0012269859435036778, "regret_bot": 0.0034563445951789618, "value_dist": 0.8628472089767456, "value_other_env": 0.8810114860534668, "value_corner": 0.835600733757019, "value_row": 0.8585663437843323, "value_any": 0.8810235857963562, "value_bot": 0.8551703095436096, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14400.png", "entropy": 0.08157327026128769} +{"ts": "2026-03-20T20:49:52.506689Z", "loop": 14410, "env_steps": 8853504000, "exact_value_avg": 0.8630982637405396, "regret_dist": 0.0004823532362934202, "regret_other_env": 0.0007685234886594117, "regret_corner": 5.3097806812729686e-05, "regret_row": 0.0013980257790535688, "regret_any": 0.0007719920831732452, "regret_bot": 0.0018119520973414183, "value_dist": 0.8630982637405396, "value_other_env": 0.8814463019371033, "value_corner": 0.8355762362480164, "value_row": 0.8572285771369934, "value_any": 0.8814785480499268, "value_bot": 0.8568146228790283, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14410.png", "entropy": 0.0896034762263298} +{"ts": "2026-03-20T20:50:01.090898Z", "loop": 14420, "env_steps": 8859648000, "exact_value_avg": 0.8634883761405945, "regret_dist": 9.232280717696995e-05, "regret_other_env": 0.00014656447456218302, "regret_corner": 1.0960301551676821e-05, "regret_row": 2.316091922693886e-05, "regret_any": 0.00014815788017585874, "regret_bot": 0.00042463545105420053, "value_dist": 0.8634883761405945, "value_other_env": 0.8820683360099792, "value_corner": 0.8356183767318726, "value_row": 0.8586035370826721, "value_any": 0.8821024298667908, "value_bot": 0.8582019805908203, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14420.png", "entropy": 0.07529309391975403} +{"ts": "2026-03-20T20:50:09.681027Z", "loop": 14430, "env_steps": 8865792000, "exact_value_avg": 0.8633073568344116, "regret_dist": 0.0002733552537392825, "regret_other_env": 0.0004500614304561168, "regret_corner": 8.295973202621099e-06, "regret_row": 5.051845801062882e-05, "regret_any": 0.00047091656597331166, "regret_bot": 0.0007264224695973098, "value_dist": 0.8633073568344116, "value_other_env": 0.881764829158783, "value_corner": 0.8356210589408875, "value_row": 0.8585760593414307, "value_any": 0.8817797303199768, "value_bot": 0.8579001426696777, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14430.png", "entropy": 0.06775426119565964} +{"ts": "2026-03-20T20:50:18.262207Z", "loop": 14440, "env_steps": 8871936000, "exact_value_avg": 0.863471269607544, "regret_dist": 0.00010941806976916268, "regret_other_env": 0.00018164321954827756, "regret_corner": 1.080334186553955e-06, "regret_row": 5.4004967751097865e-06, "regret_any": 0.00019409475498832762, "regret_bot": 0.0005856706411577761, "value_dist": 0.863471269607544, "value_other_env": 0.8820332288742065, "value_corner": 0.8356282114982605, "value_row": 0.8586212992668152, "value_any": 0.882056474685669, "value_bot": 0.858040988445282, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14440.png", "entropy": 0.06606543809175491} +{"ts": "2026-03-20T20:50:26.845965Z", "loop": 14450, "env_steps": 8878080000, "exact_value_avg": 0.863373875617981, "regret_dist": 0.00020679747103713453, "regret_other_env": 0.00034346338361501694, "regret_corner": 1.7985702243095147e-06, "regret_row": 1.9231572878197767e-05, "regret_any": 0.00036264763912186027, "regret_bot": 0.0006363303400576115, "value_dist": 0.863373875617981, "value_other_env": 0.8818714022636414, "value_corner": 0.835627555847168, "value_row": 0.8586074113845825, "value_any": 0.8818879723548889, "value_bot": 0.8579903244972229, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14450.png", "entropy": 0.06503152847290039} +{"ts": "2026-03-20T20:50:35.424944Z", "loop": 14460, "env_steps": 8884224000, "exact_value_avg": 0.863365888595581, "regret_dist": 0.00021479418501257896, "regret_other_env": 0.0003572061541490257, "regret_corner": 1.1761983387259534e-06, "regret_row": 1.96325945580611e-05, "regret_any": 0.0003642199153546244, "regret_bot": 0.0003314536588732153, "value_dist": 0.863365888595581, "value_other_env": 0.881857693195343, "value_corner": 0.8356281518936157, "value_row": 0.8586070537567139, "value_any": 0.8818864226341248, "value_bot": 0.858295202255249, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14460.png", "entropy": 0.06410112231969833} +{"ts": "2026-03-20T20:50:44.011018Z", "loop": 14470, "env_steps": 8890368000, "exact_value_avg": 0.8635214567184448, "regret_dist": 5.9242807765258476e-05, "regret_other_env": 9.838998084887862e-05, "regret_corner": 5.220373964220926e-07, "regret_row": 6.226427558431169e-06, "regret_any": 9.94546280708164e-05, "regret_bot": 0.0003155218146275729, "value_dist": 0.8635214567184448, "value_other_env": 0.8821165561676025, "value_corner": 0.8356288075447083, "value_row": 0.8586203455924988, "value_any": 0.8821511268615723, "value_bot": 0.858311116695404, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14470.png", "entropy": 0.06366277486085892} +{"ts": "2026-03-20T20:50:52.590881Z", "loop": 14480, "env_steps": 8896512000, "exact_value_avg": 0.8633826971054077, "regret_dist": 0.0001979338558157906, "regret_other_env": 0.0003296927025076002, "regret_corner": 2.95539706485215e-07, "regret_row": 8.360363608517218e-06, "regret_any": 0.0003299970703665167, "regret_bot": 0.001226984546519816, "value_dist": 0.8633826971054077, "value_other_env": 0.8818851709365845, "value_corner": 0.8356289863586426, "value_row": 0.8586181998252869, "value_any": 0.881920576095581, "value_bot": 0.8573996424674988, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14480.png", "entropy": 0.06586314737796783} +{"ts": "2026-03-20T20:51:01.167582Z", "loop": 14490, "env_steps": 8902656000, "exact_value_avg": 0.8590365052223206, "regret_dist": 0.004544172901660204, "regret_other_env": 0.007573655340820551, "regret_corner": -5.06639494801675e-08, "regret_row": 0.004227832891047001, "regret_any": 0.007582217454910278, "regret_bot": 0.0058824955485761166, "value_dist": 0.8590365052223206, "value_other_env": 0.8746411800384521, "value_corner": 0.835629403591156, "value_row": 0.854398787021637, "value_any": 0.8746684193611145, "value_bot": 0.8527441620826721, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14490.png", "entropy": 0.07352917641401291} +{"ts": "2026-03-20T20:51:09.749964Z", "loop": 14500, "env_steps": 8908800000, "exact_value_avg": 0.8612728714942932, "regret_dist": 0.002307858318090439, "regret_other_env": 0.003846420906484127, "regret_corner": 1.390775139498146e-08, "regret_row": 0.007647317368537188, "regret_any": 0.00384107930585742, "regret_bot": 0.0014408617280423641, "value_dist": 0.8612728714942932, "value_other_env": 0.8783684372901917, "value_corner": 0.835629403591156, "value_row": 0.8509793281555176, "value_any": 0.8784095048904419, "value_bot": 0.8571857810020447, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14500.png", "entropy": 0.07283928990364075} +{"ts": "2026-03-20T20:51:18.325910Z", "loop": 14510, "env_steps": 8914944000, "exact_value_avg": 0.8624922037124634, "regret_dist": 0.001088534714654088, "regret_other_env": 0.0018142465269193053, "regret_corner": -3.327926023644068e-08, "regret_row": 0.004186677280813456, "regret_any": 0.0018115377752110362, "regret_bot": 0.0016140538500621915, "value_dist": 0.8624922037124634, "value_other_env": 0.8804006576538086, "value_corner": 0.835629403591156, "value_row": 0.8544399738311768, "value_any": 0.880439043045044, "value_bot": 0.8570125699043274, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14510.png", "entropy": 0.07445688545703888} +{"ts": "2026-03-20T20:51:26.916228Z", "loop": 14520, "env_steps": 8921088000, "exact_value_avg": 0.8627432584762573, "regret_dist": 0.0008373787277378142, "regret_other_env": 0.0013955625472590327, "regret_corner": 1.0281802076406166e-07, "regret_row": 0.0008259190362878144, "regret_any": 0.0013934719609096646, "regret_bot": 0.0030378890223801136, "value_dist": 0.8627432584762573, "value_other_env": 0.8808192610740662, "value_corner": 0.8356291651725769, "value_row": 0.8578007221221924, "value_any": 0.8808571100234985, "value_bot": 0.8555887341499329, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14520.png", "entropy": 0.0744757279753685} +{"ts": "2026-03-20T20:51:35.500494Z", "loop": 14530, "env_steps": 8927232000, "exact_value_avg": 0.8633295297622681, "regret_dist": 0.0002511323255021125, "regret_other_env": 0.00041846378007903695, "regret_corner": 1.3510387475434982e-07, "regret_row": 0.0001113119869842194, "regret_any": 0.00041800623876042664, "regret_bot": 0.00035992031916975975, "value_dist": 0.8633295297622681, "value_other_env": 0.8817964792251587, "value_corner": 0.8356291651725769, "value_row": 0.8585153222084045, "value_any": 0.8818325996398926, "value_bot": 0.8582667112350464, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14530.png", "entropy": 0.06771893799304962} +{"ts": "2026-03-20T20:51:44.083393Z", "loop": 14540, "env_steps": 8933376000, "exact_value_avg": 0.8635066747665405, "regret_dist": 7.400891627185047e-05, "regret_other_env": 0.00012322599650360644, "regret_corner": 1.8328428552649711e-07, "regret_row": 1.2440075806807727e-05, "regret_any": 0.00012308749137446284, "regret_bot": 0.0002451423788443208, "value_dist": 0.8635066747665405, "value_other_env": 0.8820916414260864, "value_corner": 0.8356291055679321, "value_row": 0.8586142659187317, "value_any": 0.8821275234222412, "value_bot": 0.8583815097808838, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14540.png", "entropy": 0.06360197067260742} +{"ts": "2026-03-20T20:51:52.666990Z", "loop": 14550, "env_steps": 8939520000, "exact_value_avg": 0.8633617162704468, "regret_dist": 0.00021894092787988484, "regret_other_env": 0.00036463694414123893, "regret_corner": 3.968676196564047e-07, "regret_row": 0.00017269303498324007, "regret_any": 0.0003641340881586075, "regret_bot": 0.0006337391678243876, "value_dist": 0.8633617162704468, "value_other_env": 0.8818501830101013, "value_corner": 0.8356289267539978, "value_row": 0.8584538698196411, "value_any": 0.8818864822387695, "value_bot": 0.8579928278923035, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14550.png", "entropy": 0.06832607090473175} +{"ts": "2026-03-20T20:52:01.251336Z", "loop": 14560, "env_steps": 8945664000, "exact_value_avg": 0.8634538650512695, "regret_dist": 0.00012678968778345734, "regret_other_env": 0.0002112316869897768, "regret_corner": 1.2665987014770508e-07, "regret_row": 3.855738395941444e-05, "regret_any": 0.0002109281049342826, "regret_bot": 0.0006687875720672309, "value_dist": 0.8634538650512695, "value_other_env": 0.882003664970398, "value_corner": 0.8356291651725769, "value_row": 0.8585879802703857, "value_any": 0.8820396661758423, "value_bot": 0.8579578399658203, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14560.png", "entropy": 0.06852240115404129} +{"ts": "2026-03-20T20:52:09.835656Z", "loop": 14570, "env_steps": 8951808000, "exact_value_avg": 0.8634539842605591, "regret_dist": 0.00012664857786148787, "regret_other_env": 0.00021094782277941704, "regret_corner": 1.9967556852407142e-07, "regret_row": 1.0696775461838115e-05, "regret_any": 0.00021065276814624667, "regret_bot": 0.0010908804833889008, "value_dist": 0.8634539842605591, "value_other_env": 0.882003903388977, "value_corner": 0.8356291055679321, "value_row": 0.8586159348487854, "value_any": 0.8820399641990662, "value_bot": 0.8575357794761658, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14570.png", "entropy": 0.06822464615106583} +{"ts": "2026-03-20T20:52:18.417209Z", "loop": 14580, "env_steps": 8957952000, "exact_value_avg": 0.8634937405586243, "regret_dist": 8.692606934346259e-05, "regret_other_env": 0.0001446350506739691, "regret_corner": 3.6259493185752945e-07, "regret_row": 2.7709340429282747e-05, "regret_any": 0.00014540308620780706, "regret_bot": 0.00037378616980277, "value_dist": 0.8634937405586243, "value_other_env": 0.8820701837539673, "value_corner": 0.8356289267539978, "value_row": 0.8585988879203796, "value_any": 0.8821051716804504, "value_bot": 0.8582528233528137, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14580.png", "entropy": 0.06390378624200821} +{"ts": "2026-03-20T20:52:26.996947Z", "loop": 14590, "env_steps": 8964096000, "exact_value_avg": 0.8626989126205444, "regret_dist": 0.0008818577043712139, "regret_other_env": 0.0014688954688608646, "regret_corner": 1.3008714176976355e-06, "regret_row": 0.0005766338435932994, "regret_any": 0.0015149159589782357, "regret_bot": 0.002018580911681056, "value_dist": 0.8626989126205444, "value_other_env": 0.880746066570282, "value_corner": 0.8356280326843262, "value_row": 0.8580499291419983, "value_any": 0.8807356357574463, "value_bot": 0.8566080331802368, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14590.png", "entropy": 0.06480331718921661} +{"ts": "2026-03-20T20:52:35.577889Z", "loop": 14600, "env_steps": 8970240000, "exact_value_avg": 0.8613178730010986, "regret_dist": 0.0022628207225352526, "regret_other_env": 0.003771090181544423, "regret_corner": 4.162391178397229e-07, "regret_row": 0.00043923623161390424, "regret_any": 0.003791689407080412, "regret_bot": 0.006055476143956184, "value_dist": 0.8613178730010986, "value_other_env": 0.8784438371658325, "value_corner": 0.835628867149353, "value_row": 0.8581873774528503, "value_any": 0.8784589171409607, "value_bot": 0.8525711894035339, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14600.png", "entropy": 0.06373534351587296} +{"ts": "2026-03-20T20:52:44.157146Z", "loop": 14610, "env_steps": 8976384000, "exact_value_avg": 0.8629698157310486, "regret_dist": 0.0006109211826696992, "regret_other_env": 0.0010170591995120049, "regret_corner": 1.714130348773324e-06, "regret_row": 0.0007333728135563433, "regret_any": 0.0010405171196907759, "regret_bot": 0.0015343604609370232, "value_dist": 0.8629698157310486, "value_other_env": 0.8811978697776794, "value_corner": 0.8356276154518127, "value_row": 0.8578932881355286, "value_any": 0.8812100887298584, "value_bot": 0.8570922613143921, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14610.png", "entropy": 0.06508229672908783} +{"ts": "2026-03-20T20:52:52.741288Z", "loop": 14620, "env_steps": 8982528000, "exact_value_avg": 0.8632839918136597, "regret_dist": 0.0002967342152260244, "regret_other_env": 0.0004920142237097025, "regret_corner": 3.814200681517832e-06, "regret_row": 0.0004798629379365593, "regret_any": 0.0005152284866198897, "regret_bot": 0.0011485576396808028, "value_dist": 0.8632839918136597, "value_other_env": 0.8817229270935059, "value_corner": 0.8356255292892456, "value_row": 0.8581467866897583, "value_any": 0.8817353248596191, "value_bot": 0.8574780821800232, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14620.png", "entropy": 0.06602415442466736} +{"ts": "2026-03-20T20:53:01.328410Z", "loop": 14630, "env_steps": 8988672000, "exact_value_avg": 0.8633465766906738, "regret_dist": 0.0002340553910471499, "regret_other_env": 0.0003884786565322429, "regret_corner": 2.4204452984122327e-06, "regret_row": 0.0008374712197110057, "regret_any": 0.00041169318137690425, "regret_bot": 0.0011998808477073908, "value_dist": 0.8633465766906738, "value_other_env": 0.8818263411521912, "value_corner": 0.8356269001960754, "value_row": 0.857789158821106, "value_any": 0.8818389177322388, "value_bot": 0.8574267625808716, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14630.png", "entropy": 0.06744275242090225} +{"ts": "2026-03-20T20:53:09.912333Z", "loop": 14640, "env_steps": 8994816000, "exact_value_avg": 0.8634915351867676, "regret_dist": 8.916069782571867e-05, "regret_other_env": 0.0001470514398533851, "regret_corner": 2.32458137361391e-06, "regret_row": 0.00010534605826251209, "regret_any": 0.00014777833712287247, "regret_bot": 0.000444728706497699, "value_dist": 0.8634915351867676, "value_other_env": 0.8820677995681763, "value_corner": 0.835627019405365, "value_row": 0.8585213422775269, "value_any": 0.8821028470993042, "value_bot": 0.858181893825531, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14640.png", "entropy": 0.07068372517824173} +{"ts": "2026-03-20T20:53:18.496411Z", "loop": 14650, "env_steps": 9000960000, "exact_value_avg": 0.8634762167930603, "regret_dist": 0.00010443640348967165, "regret_other_env": 0.00017277750885114074, "regret_corner": 1.924733396663214e-06, "regret_row": 0.00016962646623142064, "regret_any": 0.0001736688573146239, "regret_bot": 0.0004776721470989287, "value_dist": 0.8634762167930603, "value_other_env": 0.8820420503616333, "value_corner": 0.8356274366378784, "value_row": 0.8584570288658142, "value_any": 0.8820769190788269, "value_bot": 0.858148992061615, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14650.png", "entropy": 0.07159934937953949} +{"ts": "2026-03-20T20:53:27.081640Z", "loop": 14660, "env_steps": 9007104000, "exact_value_avg": 0.8634911775588989, "regret_dist": 8.953511132858694e-05, "regret_other_env": 0.0001484436943428591, "regret_corner": 1.1722247563739074e-06, "regret_row": 9.182045323541388e-05, "regret_any": 0.00014839864161331207, "regret_bot": 0.0005110866040922701, "value_dist": 0.8634911775588989, "value_other_env": 0.8820664286613464, "value_corner": 0.8356281518936157, "value_row": 0.8585348129272461, "value_any": 0.8821021914482117, "value_bot": 0.8581156134605408, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14660.png", "entropy": 0.07199303805828094} +{"ts": "2026-03-20T20:53:35.661221Z", "loop": 14670, "env_steps": 9013248000, "exact_value_avg": 0.8634980320930481, "regret_dist": 8.266165241366252e-05, "regret_other_env": 0.00013751974620390683, "regret_corner": 3.7451587786563323e-07, "regret_row": 2.1836387531948276e-05, "regret_any": 0.0001373408013023436, "regret_bot": 0.0004573877085931599, "value_dist": 0.8634980320930481, "value_other_env": 0.8820773363113403, "value_corner": 0.8356289267539978, "value_row": 0.8586048483848572, "value_any": 0.8821132183074951, "value_bot": 0.8581692576408386, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14670.png", "entropy": 0.07325606793165207} +{"ts": "2026-03-20T20:53:44.245895Z", "loop": 14680, "env_steps": 9019392000, "exact_value_avg": 0.8634268641471863, "regret_dist": 0.0001538015203550458, "regret_other_env": 0.00025606300914660096, "regret_corner": 4.092852350368048e-07, "regret_row": 3.557029049261473e-05, "regret_any": 0.00025573966559022665, "regret_bot": 0.0007144508417695761, "value_dist": 0.8634268641471863, "value_other_env": 0.8819587826728821, "value_corner": 0.8356289267539978, "value_row": 0.8585910201072693, "value_any": 0.881994903087616, "value_bot": 0.8579121828079224, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14680.png", "entropy": 0.07487361878156662} +{"ts": "2026-03-20T20:53:52.823368Z", "loop": 14690, "env_steps": 9025536000, "exact_value_avg": 0.8634549975395203, "regret_dist": 0.0001256842806469649, "regret_other_env": 0.00020922542898915708, "regret_corner": 3.7252905826790084e-07, "regret_row": 3.486957575660199e-05, "regret_any": 0.0002089414483634755, "regret_bot": 0.000540008011739701, "value_dist": 0.8634549975395203, "value_other_env": 0.8820056915283203, "value_corner": 0.8356289267539978, "value_row": 0.8585917949676514, "value_any": 0.8820416331291199, "value_bot": 0.8580866456031799, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14690.png", "entropy": 0.07408168166875839} +{"ts": "2026-03-20T20:54:01.410548Z", "loop": 14700, "env_steps": 9031680000, "exact_value_avg": 0.8635033369064331, "regret_dist": 7.738724525552243e-05, "regret_other_env": 0.0001278575073229149, "regret_corner": 1.6818445374156e-06, "regret_row": 0.0003903231117874384, "regret_any": 0.00012778198288287967, "regret_bot": 0.00021637076861225069, "value_dist": 0.8635033369064331, "value_other_env": 0.8820870518684387, "value_corner": 0.8356276750564575, "value_row": 0.8582363128662109, "value_any": 0.8821228742599487, "value_bot": 0.8584102392196655, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14700.png", "entropy": 0.06933644413948059} +{"ts": "2026-03-20T20:54:09.993608Z", "loop": 14710, "env_steps": 9037824000, "exact_value_avg": 0.8625717163085938, "regret_dist": 0.0010090229334309697, "regret_other_env": 0.001679420587606728, "regret_corner": 3.426273906370625e-06, "regret_row": 0.002626629313454032, "regret_any": 0.0016884715296328068, "regret_bot": 0.0005875062197446823, "value_dist": 0.8625717163085938, "value_other_env": 0.8805354833602905, "value_corner": 0.8356258869171143, "value_row": 0.8560000061988831, "value_any": 0.8805621266365051, "value_bot": 0.858039140701294, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14710.png", "entropy": 0.0705145075917244} +{"ts": "2026-03-20T20:54:18.576125Z", "loop": 14720, "env_steps": 9043968000, "exact_value_avg": 0.8629632592201233, "regret_dist": 0.0006174013251438737, "regret_other_env": 0.001028183614835143, "regret_corner": 1.2278557051104144e-06, "regret_row": 0.0010962196392938495, "regret_any": 0.0010509395506232977, "regret_bot": 0.002107810229063034, "value_dist": 0.8629632592201233, "value_other_env": 0.8811866641044617, "value_corner": 0.8356280326843262, "value_row": 0.857530415058136, "value_any": 0.8811996579170227, "value_bot": 0.8565188050270081, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14720.png", "entropy": 0.06978486478328705} +{"ts": "2026-03-20T20:54:27.162274Z", "loop": 14730, "env_steps": 9050112000, "exact_value_avg": 0.8628286719322205, "regret_dist": 0.0007520184153690934, "regret_other_env": 0.0012532086111605167, "regret_corner": 2.3295483231322578e-07, "regret_row": 0.0002338321355637163, "regret_any": 0.0012738644145429134, "regret_bot": 0.003313633380457759, "value_dist": 0.8628286719322205, "value_other_env": 0.8809616565704346, "value_corner": 0.8356291055679321, "value_row": 0.8583928346633911, "value_any": 0.880976676940918, "value_bot": 0.8553130030632019, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14730.png", "entropy": 0.07150615006685257} +{"ts": "2026-03-20T20:54:35.744073Z", "loop": 14740, "env_steps": 9056256000, "exact_value_avg": 0.8622846007347107, "regret_dist": 0.0012960819294676185, "regret_other_env": 0.0021600681357085705, "regret_corner": 1.023213087592012e-07, "regret_row": 0.0019429860403761268, "regret_any": 0.002181975869461894, "regret_bot": 0.004493730142712593, "value_dist": 0.8622846007347107, "value_other_env": 0.8800548315048218, "value_corner": 0.8356292247772217, "value_row": 0.8566836714744568, "value_any": 0.8800686001777649, "value_bot": 0.854132890701294, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14740.png", "entropy": 0.07066691666841507} +{"ts": "2026-03-20T20:54:44.325280Z", "loop": 14750, "env_steps": 9062400000, "exact_value_avg": 0.8630253076553345, "regret_dist": 0.0005553559167310596, "regret_other_env": 0.0009254319011233747, "regret_corner": 2.4189552050302154e-07, "regret_row": 0.00015430354687850922, "regret_any": 0.0009484281181357801, "regret_bot": 0.0030831920448690653, "value_dist": 0.8630253076553345, "value_other_env": 0.8812893629074097, "value_corner": 0.8356290459632874, "value_row": 0.8584722876548767, "value_any": 0.8813021779060364, "value_bot": 0.8555434346199036, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14750.png", "entropy": 0.07177770137786865} +{"ts": "2026-03-20T20:54:52.913684Z", "loop": 14760, "env_steps": 9068544000, "exact_value_avg": 0.862488865852356, "regret_dist": 0.001091807964257896, "regret_other_env": 0.0018192464485764503, "regret_corner": 6.501873599518149e-07, "regret_row": 0.0010026802774518728, "regret_any": 0.0018412127392366529, "regret_bot": 0.004269860219210386, "value_dist": 0.862488865852356, "value_other_env": 0.8803956508636475, "value_corner": 0.8356286883354187, "value_row": 0.8576239943504333, "value_any": 0.8804094195365906, "value_bot": 0.8543567657470703, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14760.png", "entropy": 0.06720437854528427} +{"ts": "2026-03-20T20:55:01.489229Z", "loop": 14770, "env_steps": 9074688000, "exact_value_avg": 0.8599872589111328, "regret_dist": 0.0035935291089117527, "regret_other_env": 0.005975459702312946, "regret_corner": 2.0632645828300156e-05, "regret_row": 0.004272210877388716, "regret_any": 0.006170331966131926, "regret_bot": 0.001819293713197112, "value_dist": 0.8599872589111328, "value_other_env": 0.8762394785881042, "value_corner": 0.835608720779419, "value_row": 0.8543544411659241, "value_any": 0.8760802149772644, "value_bot": 0.8568073511123657, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14770.png", "entropy": 0.07445206493139267} +{"ts": "2026-03-20T20:55:10.075327Z", "loop": 14780, "env_steps": 9080832000, "exact_value_avg": 0.8632512092590332, "regret_dist": 0.0003294455527793616, "regret_other_env": 0.000542645575478673, "regret_corner": 9.64552236837335e-06, "regret_row": 0.0006662766099907458, "regret_any": 0.0005639359005726874, "regret_bot": 0.001041777548380196, "value_dist": 0.8632512092590332, "value_other_env": 0.8816722631454468, "value_corner": 0.8356196284294128, "value_row": 0.8579603433609009, "value_any": 0.8816866874694824, "value_bot": 0.8575847744941711, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14780.png", "entropy": 0.07068678736686707} +{"ts": "2026-03-20T20:55:18.661043Z", "loop": 14790, "env_steps": 9086976000, "exact_value_avg": 0.8633216619491577, "regret_dist": 0.00025904917856678367, "regret_other_env": 0.0004279805871192366, "regret_corner": 5.6520107136748265e-06, "regret_row": 0.000511243415530771, "regret_any": 0.00044408778194338083, "regret_bot": 0.0011018001241609454, "value_dist": 0.8633216619491577, "value_other_env": 0.8817868828773499, "value_corner": 0.8356237411499023, "value_row": 0.8581154346466064, "value_any": 0.881806492805481, "value_bot": 0.8575248718261719, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14790.png", "entropy": 0.07021301984786987} +{"ts": "2026-03-20T20:55:27.246711Z", "loop": 14800, "env_steps": 9093120000, "exact_value_avg": 0.8600269556045532, "regret_dist": 0.0035537071526050568, "regret_other_env": 0.005906595848500729, "regret_corner": 2.4373830456170253e-05, "regret_row": 0.008327004499733448, "regret_any": 0.005973207764327526, "regret_bot": 0.0025707362219691277, "value_dist": 0.8600269556045532, "value_other_env": 0.8763082027435303, "value_corner": 0.8356049656867981, "value_row": 0.850299596786499, "value_any": 0.8762773871421814, "value_bot": 0.8560558557510376, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14800.png", "entropy": 0.07709949463605881} +{"ts": "2026-03-20T20:55:35.826142Z", "loop": 14810, "env_steps": 9099264000, "exact_value_avg": 0.8607703447341919, "regret_dist": 0.002810309873893857, "regret_other_env": 0.004658808000385761, "regret_corner": 3.756235309992917e-05, "regret_row": 0.0077192592434585094, "regret_any": 0.004676163196563721, "regret_bot": 0.004169527906924486, "value_dist": 0.8607703447341919, "value_other_env": 0.8775560855865479, "value_corner": 0.835591733455658, "value_row": 0.8509073853492737, "value_any": 0.8775744438171387, "value_bot": 0.8544571399688721, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14810.png", "entropy": 0.07393571734428406} +{"ts": "2026-03-20T20:55:44.416678Z", "loop": 14820, "env_steps": 9105408000, "exact_value_avg": 0.8630436658859253, "regret_dist": 0.000537042273208499, "regret_other_env": 0.0008918381063267589, "regret_corner": 4.848341177421389e-06, "regret_row": 0.0014662346802651882, "regret_any": 0.0008948157192207873, "regret_bot": 0.0024346401914954185, "value_dist": 0.8630436658859253, "value_other_env": 0.8813230395317078, "value_corner": 0.8356244564056396, "value_row": 0.8571603894233704, "value_any": 0.8813557624816895, "value_bot": 0.8561919927597046, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14820.png", "entropy": 0.07146243751049042} +{"ts": "2026-03-20T20:55:53.000108Z", "loop": 14830, "env_steps": 9111552000, "exact_value_avg": 0.8633922338485718, "regret_dist": 0.00018839197582565248, "regret_other_env": 0.0003113891580142081, "regret_corner": 3.896157068083994e-06, "regret_row": 0.00041879198397509754, "regret_any": 0.0003113558341283351, "regret_bot": 0.0008498250972479582, "value_dist": 0.8633922338485718, "value_other_env": 0.8819034099578857, "value_corner": 0.835625410079956, "value_row": 0.8582078218460083, "value_any": 0.8819392323493958, "value_bot": 0.8577767610549927, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14830.png", "entropy": 0.0750831812620163} +{"ts": "2026-03-20T20:56:01.586462Z", "loop": 14840, "env_steps": 9117696000, "exact_value_avg": 0.8633590936660767, "regret_dist": 0.00022155723127070814, "regret_other_env": 0.0003647443372756243, "regret_corner": 6.7765517997031566e-06, "regret_row": 0.000548378040548414, "regret_any": 0.0003649597056210041, "regret_bot": 0.0007715040701441467, "value_dist": 0.8633590936660767, "value_other_env": 0.8818501234054565, "value_corner": 0.8356224894523621, "value_row": 0.8580782413482666, "value_any": 0.8818856477737427, "value_bot": 0.8578552007675171, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14840.png", "entropy": 0.07678119838237762} +{"ts": "2026-03-20T20:56:10.184016Z", "loop": 14850, "env_steps": 9123840000, "exact_value_avg": 0.863182544708252, "regret_dist": 0.00039812721661292017, "regret_other_env": 0.0006592273130081594, "regret_corner": 6.4770383687573485e-06, "regret_row": 0.0007640824187546968, "regret_any": 0.0006635320605710149, "regret_bot": 0.0015362236881628633, "value_dist": 0.863182544708252, "value_other_env": 0.8815556764602661, "value_corner": 0.8356228470802307, "value_row": 0.8578625917434692, "value_any": 0.881587028503418, "value_bot": 0.857090413570404, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14850.png", "entropy": 0.07665982842445374} +{"ts": "2026-03-20T20:56:18.779081Z", "loop": 14860, "env_steps": 9129984000, "exact_value_avg": 0.8633086681365967, "regret_dist": 0.00027201996999792755, "regret_other_env": 0.0004506734840106219, "regret_corner": 4.03970489060157e-06, "regret_row": 0.0007381551549769938, "regret_any": 0.00045078268158249557, "regret_bot": 0.001100968918763101, "value_dist": 0.8633086681365967, "value_other_env": 0.8817642331123352, "value_corner": 0.8356252312660217, "value_row": 0.8578884601593018, "value_any": 0.8817997574806213, "value_bot": 0.8575255870819092, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14860.png", "entropy": 0.07694931328296661} +{"ts": "2026-03-20T20:56:27.375822Z", "loop": 14870, "env_steps": 9136128000, "exact_value_avg": 0.8633750081062317, "regret_dist": 0.00020562225836329162, "regret_other_env": 0.00034009639057330787, "regret_corner": 3.911058229277842e-06, "regret_row": 0.0006146146333776414, "regret_any": 0.00034004758344963193, "regret_bot": 0.0011060773395001888, "value_dist": 0.8633750081062317, "value_other_env": 0.8818747401237488, "value_corner": 0.8356253504753113, "value_row": 0.8580120205879211, "value_any": 0.8819105625152588, "value_bot": 0.8575205206871033, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14870.png", "entropy": 0.07735758274793625} +{"ts": "2026-03-20T20:56:35.958629Z", "loop": 14880, "env_steps": 9142272000, "exact_value_avg": 0.8626691102981567, "regret_dist": 0.0009115582215599716, "regret_other_env": 0.0015131084946915507, "regret_corner": 9.232760021404829e-06, "regret_row": 0.003872901201248169, "regret_any": 0.0015148116508498788, "regret_bot": 0.002482649404555559, "value_dist": 0.8626691102981567, "value_other_env": 0.8807017207145691, "value_corner": 0.835620105266571, "value_row": 0.8547536730766296, "value_any": 0.8807358145713806, "value_bot": 0.8561440110206604, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14880.png", "entropy": 0.07647401094436646} +{"ts": "2026-03-20T20:56:44.541622Z", "loop": 14890, "env_steps": 9148416000, "exact_value_avg": 0.863198459148407, "regret_dist": 0.0003822196158580482, "regret_other_env": 0.0006342001142911613, "regret_corner": 4.248818186169956e-06, "regret_row": 0.001415296457707882, "regret_any": 0.0006338623934425414, "regret_bot": 0.001767043024301529, "value_dist": 0.863198459148407, "value_other_env": 0.881580650806427, "value_corner": 0.8356250524520874, "value_row": 0.8572112917900085, "value_any": 0.8816167116165161, "value_bot": 0.856859564781189, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14890.png", "entropy": 0.07826360315084457} +{"ts": "2026-03-20T20:56:53.125202Z", "loop": 14900, "env_steps": 9154560000, "exact_value_avg": 0.8630444407463074, "regret_dist": 0.000536243082024157, "regret_other_env": 0.0008922970155254006, "regret_corner": 2.162158580176765e-06, "regret_row": 0.0025113197043538094, "regret_any": 0.0009055135888047516, "regret_bot": 0.0027713754680007696, "value_dist": 0.8630444407463074, "value_other_env": 0.8813225626945496, "value_corner": 0.8356271386146545, "value_row": 0.8561153411865234, "value_any": 0.8813450932502747, "value_bot": 0.8558552861213684, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14900.png", "entropy": 0.07548724114894867} +{"ts": "2026-03-20T20:57:01.705359Z", "loop": 14910, "env_steps": 9160704000, "exact_value_avg": 0.8615488409996033, "regret_dist": 0.002031841082498431, "regret_other_env": 0.003383955452591181, "regret_corner": 3.669659463412245e-06, "regret_row": 0.00324759678915143, "regret_any": 0.003403946990147233, "regret_bot": 0.007469810079783201, "value_dist": 0.8615488409996033, "value_other_env": 0.8788309097290039, "value_corner": 0.8356256484985352, "value_row": 0.855379045009613, "value_any": 0.8788466453552246, "value_bot": 0.8511567711830139, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14910.png", "entropy": 0.07437025755643845} +{"ts": "2026-03-20T20:57:10.294746Z", "loop": 14920, "env_steps": 9166848000, "exact_value_avg": 0.8617530465126038, "regret_dist": 0.0018276345217600465, "regret_other_env": 0.0030428259633481503, "regret_corner": 4.847348009207053e-06, "regret_row": 0.0007627595332451165, "regret_any": 0.0030656843446195126, "regret_bot": 0.007199335377663374, "value_dist": 0.8617530465126038, "value_other_env": 0.8791720271110535, "value_corner": 0.8356244564056396, "value_row": 0.8578639030456543, "value_any": 0.879184901714325, "value_bot": 0.8514272570610046, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14920.png", "entropy": 0.07685546576976776} +{"ts": "2026-03-20T20:57:18.876056Z", "loop": 14930, "env_steps": 9172992000, "exact_value_avg": 0.8633232116699219, "regret_dist": 0.0002574945683591068, "regret_other_env": 0.00042373655014671385, "regret_corner": 8.131563845381606e-06, "regret_row": 0.0004292177618481219, "regret_any": 0.00044742130558006465, "regret_bot": 0.001674920436926186, "value_dist": 0.8633232116699219, "value_other_env": 0.8817911744117737, "value_corner": 0.835621178150177, "value_row": 0.8581973910331726, "value_any": 0.8818031549453735, "value_bot": 0.8569517731666565, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14930.png", "entropy": 0.08150812983512878} +{"ts": "2026-03-20T20:57:27.461644Z", "loop": 14940, "env_steps": 9179136000, "exact_value_avg": 0.8626174330711365, "regret_dist": 0.0009633015724830329, "regret_other_env": 0.0015487192431464791, "regret_corner": 8.517504465999082e-05, "regret_row": 0.001951139885932207, "regret_any": 0.001570619991980493, "regret_bot": 0.0013787661446258426, "value_dist": 0.8626174330711365, "value_other_env": 0.880666196346283, "value_corner": 0.8355441689491272, "value_row": 0.8566754460334778, "value_any": 0.8806799650192261, "value_bot": 0.8572478294372559, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14940.png", "entropy": 0.08557789027690887} +{"ts": "2026-03-20T20:57:36.040999Z", "loop": 14950, "env_steps": 9185280000, "exact_value_avg": 0.860826849937439, "regret_dist": 0.002753817941993475, "regret_other_env": 0.0040229386650025845, "regret_corner": 0.0008501366246491671, "regret_row": 0.004442930221557617, "regret_any": 0.004036351107060909, "regret_bot": 0.0010379160521551967, "value_dist": 0.860826849937439, "value_other_env": 0.8781919479370117, "value_corner": 0.8347792029380798, "value_row": 0.8541837334632874, "value_any": 0.8782142400741577, "value_bot": 0.8575886487960815, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14950.png", "entropy": 0.11009636521339417} +{"ts": "2026-03-20T20:57:44.616541Z", "loop": 14960, "env_steps": 9191424000, "exact_value_avg": 0.8624699711799622, "regret_dist": 0.001110751647502184, "regret_other_env": 0.0013471072306856513, "regret_corner": 0.0007562180981040001, "regret_row": 0.0014482784317806363, "regret_any": 0.001359493238851428, "regret_bot": 0.001035856083035469, "value_dist": 0.8624699711799622, "value_other_env": 0.8808677792549133, "value_corner": 0.8348731398582458, "value_row": 0.8571783304214478, "value_any": 0.8808910846710205, "value_bot": 0.8575907349586487, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14960.png", "entropy": 0.11230719089508057} +{"ts": "2026-03-20T20:57:53.198774Z", "loop": 14970, "env_steps": 9197568000, "exact_value_avg": 0.8627048134803772, "regret_dist": 0.0008758657495491207, "regret_other_env": 0.0012544902274385095, "regret_corner": 0.00030792903271503747, "regret_row": 0.001442993525415659, "regret_any": 0.0012712894240394235, "regret_bot": 0.0010386282810941339, "value_dist": 0.8627048134803772, "value_other_env": 0.8809604048728943, "value_corner": 0.8353213667869568, "value_row": 0.8571836352348328, "value_any": 0.8809792995452881, "value_bot": 0.8575880527496338, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14970.png", "entropy": 0.09263689070940018} +{"ts": "2026-03-20T20:58:01.785289Z", "loop": 14980, "env_steps": 9203712000, "exact_value_avg": 0.863487720489502, "regret_dist": 9.302971739089116e-05, "regret_other_env": 0.0001377837179461494, "regret_corner": 2.5898716558003798e-05, "regret_row": 5.834296462126076e-05, "regret_any": 0.00014447384455706924, "regret_bot": 0.0005764093366451561, "value_dist": 0.863487720489502, "value_other_env": 0.882077157497406, "value_corner": 0.8356033563613892, "value_row": 0.8585683107376099, "value_any": 0.8821061253547668, "value_bot": 0.8580502271652222, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14980.png", "entropy": 0.0787760391831398} +{"ts": "2026-03-20T20:58:10.360438Z", "loop": 14990, "env_steps": 9209856000, "exact_value_avg": 0.8634775876998901, "regret_dist": 0.00010308919445378706, "regret_other_env": 0.0001589711755514145, "regret_corner": 1.9266208255430683e-05, "regret_row": 6.776415830245242e-05, "regret_any": 0.00015926381456665695, "regret_bot": 0.0001553906186018139, "value_dist": 0.8634775876998901, "value_other_env": 0.882055938243866, "value_corner": 0.835610032081604, "value_row": 0.8585588335990906, "value_any": 0.8820914030075073, "value_bot": 0.8584712743759155, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_14990.png", "entropy": 0.0762145146727562} +{"ts": "2026-03-20T20:58:18.937867Z", "loop": 15000, "env_steps": 9216000000, "exact_value_avg": 0.8621384501457214, "regret_dist": 0.0014422397362068295, "regret_other_env": 0.002349164104089141, "regret_corner": 8.185307524399832e-05, "regret_row": 0.0015070369699969888, "regret_any": 0.002355368575081229, "regret_bot": 6.769272295059636e-05, "value_dist": 0.8621384501457214, "value_other_env": 0.8798657059669495, "value_corner": 0.8355474472045898, "value_row": 0.857119619846344, "value_any": 0.8798952102661133, "value_bot": 0.8585589528083801, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15000.png", "entropy": 0.08220019936561584} +{"ts": "2026-03-20T20:58:27.520466Z", "loop": 15010, "env_steps": 9222144000, "exact_value_avg": 0.863463282585144, "regret_dist": 0.00011738570174202323, "regret_other_env": 0.00019100426288787276, "regret_corner": 6.9578491093125194e-06, "regret_row": 0.00014418462524190545, "regret_any": 0.00019084916857536882, "regret_bot": 5.5502579925814644e-05, "value_dist": 0.863463282585144, "value_other_env": 0.8820238709449768, "value_corner": 0.8356223702430725, "value_row": 0.8584824800491333, "value_any": 0.8820598125457764, "value_bot": 0.8585711717605591, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15010.png", "entropy": 0.07515502721071243} +{"ts": "2026-03-20T20:58:36.102214Z", "loop": 15020, "env_steps": 9228288000, "exact_value_avg": 0.8634530305862427, "regret_dist": 0.00012765855353791267, "regret_other_env": 0.00021079066209495068, "regret_corner": 2.960364099635626e-06, "regret_row": 0.00018547709623817354, "regret_any": 0.00021054831449873745, "regret_bot": 0.00015012432413641363, "value_dist": 0.8634530305862427, "value_other_env": 0.8820040822029114, "value_corner": 0.8356263637542725, "value_row": 0.8584411144256592, "value_any": 0.8820400834083557, "value_bot": 0.858476459980011, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15020.png", "entropy": 0.07297059148550034} +{"ts": "2026-03-20T20:58:44.684434Z", "loop": 15030, "env_steps": 9234432000, "exact_value_avg": 0.8631207346916199, "regret_dist": 0.0004599280364345759, "regret_other_env": 0.000764493306633085, "regret_corner": 3.080070200667251e-06, "regret_row": 0.0008960640407167375, "regret_any": 0.000763632298912853, "regret_bot": 0.003964009694755077, "value_dist": 0.8631207346916199, "value_other_env": 0.881450355052948, "value_corner": 0.8356262445449829, "value_row": 0.8577305674552917, "value_any": 0.8814868927001953, "value_bot": 0.8546625971794128, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15030.png", "entropy": 0.07397602498531342} +{"ts": "2026-03-20T20:58:53.266578Z", "loop": 15040, "env_steps": 9240576000, "exact_value_avg": 0.8625954389572144, "regret_dist": 0.0009852094808593392, "regret_other_env": 0.0016417262377217412, "regret_corner": 4.3412052264102385e-07, "regret_row": 0.0004893702571280301, "regret_any": 0.0016400371678173542, "regret_bot": 0.0026778061874210835, "value_dist": 0.8625954389572144, "value_other_env": 0.8805731534957886, "value_corner": 0.835628867149353, "value_row": 0.8581372499465942, "value_any": 0.8806105852127075, "value_bot": 0.8559488654136658, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15040.png", "entropy": 0.07312964648008347} +{"ts": "2026-03-20T20:59:01.852442Z", "loop": 15050, "env_steps": 9246720000, "exact_value_avg": 0.8617938756942749, "regret_dist": 0.0017867874121293426, "regret_other_env": 0.0029777539893984795, "regret_corner": 3.372629748810141e-07, "regret_row": 0.0008020249078981578, "regret_any": 0.0029750382527709007, "regret_bot": 0.0033937254920601845, "value_dist": 0.8617938756942749, "value_other_env": 0.8792371153831482, "value_corner": 0.8356289267539978, "value_row": 0.8578245639801025, "value_any": 0.8792755603790283, "value_bot": 0.8552328944206238, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15050.png", "entropy": 0.073048897087574} +{"ts": "2026-03-20T20:59:10.432812Z", "loop": 15060, "env_steps": 9252864000, "exact_value_avg": 0.8619728684425354, "regret_dist": 0.0016078130574896932, "regret_other_env": 0.002679631346836686, "regret_corner": 8.543332796762115e-08, "regret_row": 0.00022315043315757066, "regret_any": 0.0026763929054141045, "regret_bot": 0.0031549755949527025, "value_dist": 0.8619728684425354, "value_other_env": 0.8795352578163147, "value_corner": 0.8356292247772217, "value_row": 0.8584035038948059, "value_any": 0.879574179649353, "value_bot": 0.855471670627594, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15060.png", "entropy": 0.07608292996883392} +{"ts": "2026-03-20T20:59:19.018507Z", "loop": 15070, "env_steps": 9259008000, "exact_value_avg": 0.8613485097885132, "regret_dist": 0.0022321383003145456, "regret_other_env": 0.0037197088822722435, "regret_corner": 7.823110195204208e-07, "regret_row": 7.057953189359978e-05, "regret_any": 0.0037150534335523844, "regret_bot": 0.007310848217457533, "value_dist": 0.8613485097885132, "value_other_env": 0.8784951567649841, "value_corner": 0.8356285691261292, "value_row": 0.8585560917854309, "value_any": 0.8785355687141418, "value_bot": 0.8513157367706299, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15070.png", "entropy": 0.08015360683202744} +{"ts": "2026-03-20T20:59:27.599967Z", "loop": 15080, "env_steps": 9265152000, "exact_value_avg": 0.8625448942184448, "regret_dist": 0.0010357628343626857, "regret_other_env": 0.00172418134752661, "regret_corner": 3.135204451609752e-06, "regret_row": 2.928565845650155e-05, "regret_any": 0.0017219536239281297, "regret_bot": 0.003654884174466133, "value_dist": 0.8625448942184448, "value_other_env": 0.8804906606674194, "value_corner": 0.8356261849403381, "value_row": 0.8585973381996155, "value_any": 0.8805286288261414, "value_bot": 0.8549717664718628, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15080.png", "entropy": 0.08392095565795898} +{"ts": "2026-03-20T20:59:36.178860Z", "loop": 15090, "env_steps": 9271296000, "exact_value_avg": 0.8633894920349121, "regret_dist": 0.00019114097813144326, "regret_other_env": 0.00031597912311553955, "regret_corner": 3.883739736920688e-06, "regret_row": 6.621967622777447e-05, "regret_any": 0.00031556771136820316, "regret_bot": 0.0007475488819181919, "value_dist": 0.8633894920349121, "value_other_env": 0.881898820400238, "value_corner": 0.8356253504753113, "value_row": 0.8585604429244995, "value_any": 0.8819349408149719, "value_bot": 0.8578791618347168, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15090.png", "entropy": 0.08429958671331406} +{"ts": "2026-03-20T20:59:44.761496Z", "loop": 15100, "env_steps": 9277440000, "exact_value_avg": 0.8633794784545898, "regret_dist": 0.00020118533575441688, "regret_other_env": 0.00033232566784136, "regret_corner": 4.474818979360862e-06, "regret_row": 0.00010220322292298079, "regret_any": 0.0003319505194667727, "regret_bot": 0.0007166503928601742, "value_dist": 0.8633794784545898, "value_other_env": 0.8818825483322144, "value_corner": 0.8356248736381531, "value_row": 0.8585243821144104, "value_any": 0.8819186687469482, "value_bot": 0.8579099178314209, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15100.png", "entropy": 0.08467628061771393} +{"ts": "2026-03-20T20:59:53.360228Z", "loop": 15110, "env_steps": 9283584000, "exact_value_avg": 0.8618395328521729, "regret_dist": 0.0017411933513358235, "regret_other_env": 0.0028952420689165592, "regret_corner": 1.0119875696545932e-05, "regret_row": 0.00026183240697719157, "regret_any": 0.0028929233085364103, "regret_bot": 0.004904184956103563, "value_dist": 0.8618395328521729, "value_other_env": 0.8793196678161621, "value_corner": 0.8356192111968994, "value_row": 0.8583648204803467, "value_any": 0.8793576955795288, "value_bot": 0.8537224531173706, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15110.png", "entropy": 0.08769634366035461} +{"ts": "2026-03-20T21:00:01.952800Z", "loop": 15120, "env_steps": 9289728000, "exact_value_avg": 0.8633202314376831, "regret_dist": 0.0002604852488730103, "regret_other_env": 0.0004236069798935205, "regret_corner": 1.580268144607544e-05, "regret_row": 0.00027483515441417694, "regret_any": 0.0004237504326738417, "regret_bot": 0.0007332818931899965, "value_dist": 0.8633202314376831, "value_other_env": 0.8817912936210632, "value_corner": 0.8356135487556458, "value_row": 0.8583518266677856, "value_any": 0.8818268179893494, "value_bot": 0.8578932881355286, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15120.png", "entropy": 0.08658869564533234} +{"ts": "2026-03-20T21:00:10.537066Z", "loop": 15130, "env_steps": 9295872000, "exact_value_avg": 0.863345742225647, "regret_dist": 0.00023492955369874835, "regret_other_env": 0.0003790975024458021, "regret_corner": 1.86776123882737e-05, "regret_row": 0.0008303125505335629, "regret_any": 0.0003787892637774348, "regret_bot": 0.00016691593918949366, "value_dist": 0.863345742225647, "value_other_env": 0.8818358182907104, "value_corner": 0.8356106281280518, "value_row": 0.857796311378479, "value_any": 0.8818718194961548, "value_bot": 0.8584597110748291, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15130.png", "entropy": 0.08060455322265625} +{"ts": "2026-03-20T21:00:19.119313Z", "loop": 15140, "env_steps": 9302016000, "exact_value_avg": 0.8630144596099854, "regret_dist": 0.0005662565818056464, "regret_other_env": 0.0009382779244333506, "regret_corner": 8.22444781078957e-06, "regret_row": 0.0013716345420107245, "regret_any": 0.0009396534296683967, "regret_bot": 0.0005599101423285902, "value_dist": 0.8630144596099854, "value_other_env": 0.8812766075134277, "value_corner": 0.8356211185455322, "value_row": 0.8572550415992737, "value_any": 0.8813109397888184, "value_bot": 0.8580666780471802, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15140.png", "entropy": 0.07786373049020767} +{"ts": "2026-03-20T21:00:27.698230Z", "loop": 15150, "env_steps": 9308160000, "exact_value_avg": 0.8584005832672119, "regret_dist": 0.0051801144145429134, "regret_other_env": 0.008620320819318295, "regret_corner": 1.9805134797934443e-05, "regret_row": 0.014798041433095932, "regret_any": 0.008631846867501736, "regret_bot": 0.0038494232576340437, "value_dist": 0.8584005832672119, "value_other_env": 0.8735945820808411, "value_corner": 0.835609495639801, "value_row": 0.843828558921814, "value_any": 0.8736187815666199, "value_bot": 0.8547771573066711, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15150.png", "entropy": 0.07859376072883606} +{"ts": "2026-03-20T21:00:36.276218Z", "loop": 15160, "env_steps": 9314304000, "exact_value_avg": 0.863006591796875, "regret_dist": 0.0005740956985391676, "regret_other_env": 0.0009540359023958445, "regret_corner": 4.1852395042951684e-06, "regret_row": 0.0012448601191863418, "regret_any": 0.0009758330998010933, "regret_bot": 0.0020149117335677147, "value_dist": 0.863006591796875, "value_other_env": 0.8812608122825623, "value_corner": 0.8356251120567322, "value_row": 0.8573818206787109, "value_any": 0.8812747597694397, "value_bot": 0.8566117286682129, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15160.png", "entropy": 0.07564219832420349} +{"ts": "2026-03-20T21:00:44.859179Z", "loop": 15170, "env_steps": 9320448000, "exact_value_avg": 0.8629570007324219, "regret_dist": 0.0006236917688511312, "regret_other_env": 0.0010386123321950436, "regret_corner": 1.3108056009514257e-06, "regret_row": 0.00026711641112342477, "regret_any": 0.001061008544638753, "regret_bot": 0.0029140126425772905, "value_dist": 0.8629570007324219, "value_other_env": 0.881176233291626, "value_corner": 0.8356280326843262, "value_row": 0.8583595752716064, "value_any": 0.8811895847320557, "value_bot": 0.8557125926017761, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15170.png", "entropy": 0.07690118998289108} +{"ts": "2026-03-20T21:00:53.446137Z", "loop": 15180, "env_steps": 9326592000, "exact_value_avg": 0.8623241186141968, "regret_dist": 0.0012565160868689418, "regret_other_env": 0.0020936981309205294, "regret_corner": 7.430712685163599e-07, "regret_row": 8.89290458871983e-05, "regret_any": 0.0021242962684482336, "regret_bot": 0.005737456493079662, "value_dist": 0.8623241186141968, "value_other_env": 0.8801211714744568, "value_corner": 0.8356285691261292, "value_row": 0.8585376739501953, "value_any": 0.8801262974739075, "value_bot": 0.8528891801834106, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15180.png", "entropy": 0.07505350559949875} +{"ts": "2026-03-20T21:01:02.023287Z", "loop": 15190, "env_steps": 9332736000, "exact_value_avg": 0.862322211265564, "regret_dist": 0.0012584271607920527, "regret_other_env": 0.002096408512443304, "regret_corner": 1.4548501212630072e-06, "regret_row": 8.496853843098506e-05, "regret_any": 0.0021198049653321505, "regret_bot": 0.005933820735663176, "value_dist": 0.862322211265564, "value_other_env": 0.8801184892654419, "value_corner": 0.8356278538703918, "value_row": 0.8585416674613953, "value_any": 0.8801308274269104, "value_bot": 0.852692723274231, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15190.png", "entropy": 0.07698892802000046} +{"ts": "2026-03-20T21:01:10.603391Z", "loop": 15200, "env_steps": 9338880000, "exact_value_avg": 0.8625421524047852, "regret_dist": 0.00103852862957865, "regret_other_env": 0.0017288441304117441, "regret_corner": 3.055234856219613e-06, "regret_row": 2.979748933285009e-05, "regret_any": 0.0017282391199842095, "regret_bot": 0.005557592026889324, "value_dist": 0.8625421524047852, "value_other_env": 0.8804860711097717, "value_corner": 0.8356262445449829, "value_row": 0.8585968017578125, "value_any": 0.8805223107337952, "value_bot": 0.8530691266059875, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15200.png", "entropy": 0.07888761907815933} +{"ts": "2026-03-20T21:01:19.184911Z", "loop": 15210, "env_steps": 9345024000, "exact_value_avg": 0.8616254329681396, "regret_dist": 0.0019552388694137335, "regret_other_env": 0.0032406712416559458, "regret_corner": 2.7090312869404443e-05, "regret_row": 3.3548203646205366e-05, "regret_any": 0.0032374148722738028, "regret_bot": 0.008377190679311752, "value_dist": 0.8616254329681396, "value_other_env": 0.8789742588996887, "value_corner": 0.8356022238731384, "value_row": 0.8585931658744812, "value_any": 0.8790132403373718, "value_bot": 0.8502494692802429, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15210.png", "entropy": 0.09070482850074768} +{"ts": "2026-03-20T21:01:27.768805Z", "loop": 15220, "env_steps": 9351168000, "exact_value_avg": 0.8629883527755737, "regret_dist": 0.0005923060816712677, "regret_other_env": 0.0009142726776190102, "regret_corner": 0.00010935615136986598, "regret_row": 8.545147284166887e-05, "regret_any": 0.0009129689424298704, "regret_bot": 0.0027462774887681007, "value_dist": 0.8629883527755737, "value_other_env": 0.8813005685806274, "value_corner": 0.8355199694633484, "value_row": 0.8585411310195923, "value_any": 0.881337583065033, "value_bot": 0.8558803200721741, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15220.png", "entropy": 0.09947797656059265} +{"ts": "2026-03-20T21:01:36.346411Z", "loop": 15230, "env_steps": 9357312000, "exact_value_avg": 0.8625487089157104, "regret_dist": 0.0010319476714357734, "regret_other_env": 0.0016478613251820207, "regret_corner": 0.00010807713260874152, "regret_row": 8.741874626139179e-05, "regret_any": 0.001645522192120552, "regret_bot": 0.004453793168067932, "value_dist": 0.8625487089157104, "value_other_env": 0.8805670142173767, "value_corner": 0.8355212211608887, "value_row": 0.8585391640663147, "value_any": 0.8806050419807434, "value_bot": 0.854172945022583, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15230.png", "entropy": 0.09973064810037613} +{"ts": "2026-03-20T21:01:44.926521Z", "loop": 15240, "env_steps": 9363456000, "exact_value_avg": 0.8627305030822754, "regret_dist": 0.0008501301053911448, "regret_other_env": 0.0013914101291447878, "regret_corner": 3.821005520876497e-05, "regret_row": 3.28083369822707e-05, "regret_any": 0.0013895017327740788, "regret_bot": 0.004393219947814941, "value_dist": 0.8627305030822754, "value_other_env": 0.8808233737945557, "value_corner": 0.8355910778045654, "value_row": 0.8585938215255737, "value_any": 0.8808611035346985, "value_bot": 0.8542333841323853, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15240.png", "entropy": 0.09229259192943573} +{"ts": "2026-03-20T21:01:53.513075Z", "loop": 15250, "env_steps": 9369600000, "exact_value_avg": 0.8630164861679077, "regret_dist": 0.0005641215830110013, "regret_other_env": 0.0008004296687431633, "regret_corner": 0.00020965935254935175, "regret_row": 0.00017368012049701065, "regret_any": 0.000799461267888546, "regret_bot": 0.002061307430267334, "value_dist": 0.8630164861679077, "value_other_env": 0.8814144134521484, "value_corner": 0.8354196548461914, "value_row": 0.8584529757499695, "value_any": 0.8814511299133301, "value_bot": 0.8565652966499329, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15250.png", "entropy": 0.10701465606689453} +{"ts": "2026-03-20T21:02:02.101693Z", "loop": 15260, "env_steps": 9375744000, "exact_value_avg": 0.8629240989685059, "regret_dist": 0.0006566127995029092, "regret_other_env": 0.00077677215449512, "regret_corner": 0.0004763737670145929, "regret_row": 0.00042347426642663777, "regret_any": 0.0007757707498967648, "regret_bot": 0.001326757250353694, "value_dist": 0.8629240989685059, "value_other_env": 0.881438136100769, "value_corner": 0.8351529836654663, "value_row": 0.858203113079071, "value_any": 0.8814747929573059, "value_bot": 0.8572998642921448, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15260.png", "entropy": 0.11633375287055969} +{"ts": "2026-03-20T21:02:10.684944Z", "loop": 15270, "env_steps": 9381888000, "exact_value_avg": 0.8622884750366211, "regret_dist": 0.001292172004468739, "regret_other_env": 0.0017320882761850953, "regret_corner": 0.0006322975386865437, "regret_row": 0.0007595574716106057, "regret_any": 0.0017295728903263807, "regret_bot": 0.0031102830544114113, "value_dist": 0.8622884750366211, "value_other_env": 0.8804828524589539, "value_corner": 0.8349969387054443, "value_row": 0.8578670620918274, "value_any": 0.8805209994316101, "value_bot": 0.8555163741111755, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15270.png", "entropy": 0.12217409163713455} +{"ts": "2026-03-20T21:02:19.261273Z", "loop": 15280, "env_steps": 9388032000, "exact_value_avg": 0.8626835942268372, "regret_dist": 0.0008971220813691616, "regret_other_env": 0.0014694191049784422, "regret_corner": 3.867646228172816e-05, "regret_row": 9.341767872683704e-05, "regret_any": 0.0014678231673315167, "regret_bot": 0.003880358999595046, "value_dist": 0.8626835942268372, "value_other_env": 0.8807454705238342, "value_corner": 0.835590660572052, "value_row": 0.8585332632064819, "value_any": 0.8807827234268188, "value_bot": 0.8547462821006775, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15280.png", "entropy": 0.09263728559017181} +{"ts": "2026-03-20T21:02:27.838712Z", "loop": 15290, "env_steps": 9394176000, "exact_value_avg": 0.8626333475112915, "regret_dist": 0.0009473584359511733, "regret_other_env": 0.0015708946157246828, "regret_corner": 1.2054046237608418e-05, "regret_row": 0.0002229874226031825, "regret_any": 0.0015778631204739213, "regret_bot": 0.005845146253705025, "value_dist": 0.8626333475112915, "value_other_env": 0.8806440234184265, "value_corner": 0.8356173038482666, "value_row": 0.8584035634994507, "value_any": 0.8806727528572083, "value_bot": 0.8527815341949463, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15290.png", "entropy": 0.08620225638151169} +{"ts": "2026-03-20T21:02:36.420619Z", "loop": 15300, "env_steps": 9400320000, "exact_value_avg": 0.8629863262176514, "regret_dist": 0.0005944106378592551, "regret_other_env": 0.0009838417172431946, "regret_corner": 1.0263920557918027e-05, "regret_row": 0.0006556943990290165, "regret_any": 0.0009944227058440447, "regret_bot": 0.0012483629398047924, "value_dist": 0.8629863262176514, "value_other_env": 0.8812310695648193, "value_corner": 0.8356190919876099, "value_row": 0.8579709529876709, "value_any": 0.8812561631202698, "value_bot": 0.8573783040046692, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15300.png", "entropy": 0.08241215348243713} +{"ts": "2026-03-20T21:02:45.001059Z", "loop": 15310, "env_steps": 9406464000, "exact_value_avg": 0.8630085587501526, "regret_dist": 0.0005721429479308426, "regret_other_env": 0.0009478144347667694, "regret_corner": 8.635720405436587e-06, "regret_row": 0.0008258960442617536, "regret_any": 0.000950026442296803, "regret_bot": 0.0006113608251325786, "value_dist": 0.8630085587501526, "value_other_env": 0.8812670111656189, "value_corner": 0.8356207609176636, "value_row": 0.8578008413314819, "value_any": 0.8813006281852722, "value_bot": 0.8580152988433838, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15310.png", "entropy": 0.07982850074768066} +{"ts": "2026-03-20T21:02:53.582878Z", "loop": 15320, "env_steps": 9412608000, "exact_value_avg": 0.8632878065109253, "regret_dist": 0.00029286000062711537, "regret_other_env": 0.000485079362988472, "regret_corner": 4.5309466258913744e-06, "regret_row": 0.0004055845784023404, "regret_any": 0.0004861511988565326, "regret_bot": 0.0005737004685215652, "value_dist": 0.8632878065109253, "value_other_env": 0.881729781627655, "value_corner": 0.8356248140335083, "value_row": 0.8582210540771484, "value_any": 0.8817644119262695, "value_bot": 0.8580529093742371, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15320.png", "entropy": 0.0768948495388031} +{"ts": "2026-03-20T21:03:02.162398Z", "loop": 15330, "env_steps": 9418752000, "exact_value_avg": 0.8634744882583618, "regret_dist": 0.0001062317387550138, "regret_other_env": 0.00017594093515072018, "regret_corner": 1.6679367718097637e-06, "regret_row": 4.546411946648732e-05, "regret_any": 0.0001758122816681862, "regret_bot": 0.0004935602191835642, "value_dist": 0.8634744882583618, "value_other_env": 0.882038950920105, "value_corner": 0.8356276750564575, "value_row": 0.8585811257362366, "value_any": 0.882074773311615, "value_bot": 0.8581330180168152, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15330.png", "entropy": 0.07735051959753036} +{"ts": "2026-03-20T21:03:10.748294Z", "loop": 15340, "env_steps": 9424896000, "exact_value_avg": 0.8635109663009644, "regret_dist": 6.968942034291103e-05, "regret_other_env": 0.00011437877401476726, "regret_corner": 2.6553871066425927e-06, "regret_row": 5.172025703359395e-05, "regret_any": 0.0001142390028689988, "regret_bot": 0.00029212425579316914, "value_dist": 0.8635109663009644, "value_other_env": 0.882100522518158, "value_corner": 0.8356266617774963, "value_row": 0.8585749268531799, "value_any": 0.8821364045143127, "value_bot": 0.858334481716156, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15340.png", "entropy": 0.07772871106863022} +{"ts": "2026-03-20T21:03:19.328408Z", "loop": 15350, "env_steps": 9431040000, "exact_value_avg": 0.863492488861084, "regret_dist": 8.811778388917446e-05, "regret_other_env": 0.00014471290342044085, "regret_corner": 3.2251082302536815e-06, "regret_row": 3.5701916203834116e-05, "regret_any": 0.00014451832976192236, "regret_bot": 0.0005291494308039546, "value_dist": 0.863492488861084, "value_other_env": 0.8820701241493225, "value_corner": 0.8356260657310486, "value_row": 0.8585909605026245, "value_any": 0.8821060657501221, "value_bot": 0.858097493648529, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15350.png", "entropy": 0.07959423214197159} +{"ts": "2026-03-20T21:03:27.908149Z", "loop": 15360, "env_steps": 9437184000, "exact_value_avg": 0.8633534908294678, "regret_dist": 0.00022723761503584683, "regret_other_env": 0.00037359207635745406, "regret_corner": 7.705887583142612e-06, "regret_row": 0.00013463162758853287, "regret_any": 0.0003730881726369262, "regret_bot": 0.001641243463382125, "value_dist": 0.8633534908294678, "value_other_env": 0.8818413019180298, "value_corner": 0.8356215953826904, "value_row": 0.8584920167922974, "value_any": 0.8818775415420532, "value_bot": 0.856985330581665, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15360.png", "entropy": 0.08316770195960999} +{"ts": "2026-03-20T21:03:36.489780Z", "loop": 15370, "env_steps": 9443328000, "exact_value_avg": 0.8627427816390991, "regret_dist": 0.0008378592901863158, "regret_other_env": 0.0013727163895964622, "regret_corner": 3.557354284566827e-05, "regret_row": 0.0011489815078675747, "regret_any": 0.0013710627099499106, "regret_bot": 0.006326969247311354, "value_dist": 0.8627427816390991, "value_other_env": 0.8808421492576599, "value_corner": 0.8355937004089355, "value_row": 0.857477605342865, "value_any": 0.8808795213699341, "value_bot": 0.852299690246582, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15370.png", "entropy": 0.0931764543056488} +{"ts": "2026-03-20T21:03:45.068228Z", "loop": 15380, "env_steps": 9449472000, "exact_value_avg": 0.8631119728088379, "regret_dist": 0.0004686623578891158, "regret_other_env": 0.0007370872190222144, "regret_corner": 6.602505891351029e-05, "regret_row": 0.00027460927958600223, "regret_any": 0.0007361029274761677, "regret_bot": 0.003310464322566986, "value_dist": 0.8631119728088379, "value_other_env": 0.8814777731895447, "value_corner": 0.8355632424354553, "value_row": 0.85835200548172, "value_any": 0.8815144896507263, "value_bot": 0.855316162109375, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15380.png", "entropy": 0.09819678962230682} +{"ts": "2026-03-20T21:03:53.653232Z", "loop": 15390, "env_steps": 9455616000, "exact_value_avg": 0.8632011413574219, "regret_dist": 0.00037956255255267024, "regret_other_env": 0.0006191501743160188, "regret_corner": 2.018113991653081e-05, "regret_row": 5.181860615266487e-05, "regret_any": 0.0006182908546179533, "regret_bot": 0.003304719924926758, "value_dist": 0.8632011413574219, "value_other_env": 0.8815957307815552, "value_corner": 0.8356091380119324, "value_row": 0.8585747480392456, "value_any": 0.8816323280334473, "value_bot": 0.8553218841552734, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15390.png", "entropy": 0.08901650458574295} +{"ts": "2026-03-20T21:04:02.239922Z", "loop": 15400, "env_steps": 9461760000, "exact_value_avg": 0.8634670376777649, "regret_dist": 0.00011368770356057212, "regret_other_env": 0.00018758604710455984, "regret_corner": 2.8401614144968335e-06, "regret_row": 3.286590799689293e-05, "regret_any": 0.00018734126933850348, "regret_bot": 0.0007527937996201217, "value_dist": 0.8634670376777649, "value_other_env": 0.882027268409729, "value_corner": 0.8356265425682068, "value_row": 0.8585937023162842, "value_any": 0.8820632696151733, "value_bot": 0.8578738570213318, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15400.png", "entropy": 0.08062134683132172} +{"ts": "2026-03-20T21:04:10.826516Z", "loop": 15410, "env_steps": 9467904000, "exact_value_avg": 0.8632141351699829, "regret_dist": 0.0003665591066237539, "regret_other_env": 0.0006097689038142562, "regret_corner": 1.744429368955025e-06, "regret_row": 0.00011015362542821094, "regret_any": 0.0006093466654419899, "regret_bot": 0.001505840802565217, "value_dist": 0.8632141351699829, "value_other_env": 0.8816050887107849, "value_corner": 0.8356276154518127, "value_row": 0.8585163950920105, "value_any": 0.8816412091255188, "value_bot": 0.8571207523345947, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15410.png", "entropy": 0.07713141292333603} +{"ts": "2026-03-20T21:04:19.413057Z", "loop": 15420, "env_steps": 9474048000, "exact_value_avg": 0.8624343872070312, "regret_dist": 0.0011462736874818802, "regret_other_env": 0.0019099813653156161, "regret_corner": 7.122755505406531e-07, "regret_row": 0.0001960896624950692, "regret_any": 0.0019103295635432005, "regret_bot": 0.004690512083470821, "value_dist": 0.8624343872070312, "value_other_env": 0.8803048729896545, "value_corner": 0.8356286287307739, "value_row": 0.8584305644035339, "value_any": 0.8803403377532959, "value_bot": 0.8539361953735352, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15420.png", "entropy": 0.07713001221418381} +{"ts": "2026-03-20T21:04:28.000603Z", "loop": 15430, "env_steps": 9480192000, "exact_value_avg": 0.8611671328544617, "regret_dist": 0.0024135431740432978, "regret_other_env": 0.004022430628538132, "regret_corner": 2.115965003213205e-07, "regret_row": 0.0003568301035556942, "regret_any": 0.004030593205243349, "regret_bot": 0.008537035435438156, "value_dist": 0.8611671328544617, "value_other_env": 0.8781924247741699, "value_corner": 0.8356291055679321, "value_row": 0.8582698702812195, "value_any": 0.8782200217247009, "value_bot": 0.8500896096229553, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15430.png", "entropy": 0.07393354922533035} +{"ts": "2026-03-20T21:04:36.583880Z", "loop": 15440, "env_steps": 9486336000, "exact_value_avg": 0.8612504601478577, "regret_dist": 0.0023302275221794844, "regret_other_env": 0.0038837005849927664, "regret_corner": 1.7384689243726825e-08, "regret_row": 0.0007626818842254579, "regret_any": 0.0038844977971166372, "regret_bot": 0.011727315373718739, "value_dist": 0.8612504601478577, "value_other_env": 0.8783311247825623, "value_corner": 0.835629403591156, "value_row": 0.8578639030456543, "value_any": 0.8783660531044006, "value_bot": 0.8468992710113525, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15440.png", "entropy": 0.07380641996860504} +{"ts": "2026-03-20T21:04:45.164970Z", "loop": 15450, "env_steps": 9492480000, "exact_value_avg": 0.8620903491973877, "regret_dist": 0.001490304246544838, "regret_other_env": 0.0024821266997605562, "regret_corner": 2.570450533312396e-06, "regret_row": 0.0001023984732455574, "regret_any": 0.002478682203218341, "regret_bot": 0.011175764724612236, "value_dist": 0.8620903491973877, "value_other_env": 0.8797327280044556, "value_corner": 0.8356267809867859, "value_row": 0.8585242033004761, "value_any": 0.8797719478607178, "value_bot": 0.847450852394104, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15450.png", "entropy": 0.08110252767801285} +{"ts": "2026-03-20T21:04:53.751389Z", "loop": 15460, "env_steps": 9498624000, "exact_value_avg": 0.8622980117797852, "regret_dist": 0.001282708952203393, "regret_other_env": 0.0017584788147360086, "regret_corner": 0.0005690540419891477, "regret_row": 0.0005428321892395616, "regret_any": 0.0017578736878931522, "regret_bot": 0.005372645333409309, "value_dist": 0.8622980117797852, "value_other_env": 0.8804564476013184, "value_corner": 0.8350602984428406, "value_row": 0.8580837845802307, "value_any": 0.8804928064346313, "value_bot": 0.853253960609436, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15460.png", "entropy": 0.08351341634988785} +{"ts": "2026-03-20T21:05:02.331550Z", "loop": 15470, "env_steps": 9504768000, "exact_value_avg": 0.8564135432243347, "regret_dist": 0.0071671511977910995, "regret_other_env": 0.00957749504595995, "regret_corner": 0.0035516342613846064, "regret_row": 0.013997215777635574, "regret_any": 0.009594270028173923, "regret_bot": 0.04510969668626785, "value_dist": 0.8564135432243347, "value_other_env": 0.8726373910903931, "value_corner": 0.83207768201828, "value_row": 0.8446294069290161, "value_any": 0.8726563453674316, "value_bot": 0.8135169744491577, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15470.png", "entropy": 0.11341773718595505} +{"ts": "2026-03-20T21:05:10.906765Z", "loop": 15480, "env_steps": 9510912000, "exact_value_avg": 0.8633878231048584, "regret_dist": 0.0001929031132021919, "regret_other_env": 0.0002895249635912478, "regret_corner": 4.7970315790735185e-05, "regret_row": 0.0003677327767945826, "regret_any": 0.00028961137286387384, "regret_bot": 0.00014303972420748323, "value_dist": 0.8633878231048584, "value_other_env": 0.8819254040718079, "value_corner": 0.835581362247467, "value_row": 0.8582589626312256, "value_any": 0.8819609880447388, "value_bot": 0.8584835529327393, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15480.png", "entropy": 0.08433617651462555} +{"ts": "2026-03-20T21:05:19.488855Z", "loop": 15490, "env_steps": 9517056000, "exact_value_avg": 0.8634543418884277, "regret_dist": 0.00012638219050131738, "regret_other_env": 0.00018424667359795421, "regret_corner": 3.958543311455287e-05, "regret_row": 0.00017136365931946784, "regret_any": 0.0001842329656938091, "regret_bot": 0.0002822148962877691, "value_dist": 0.8634543418884277, "value_other_env": 0.8820306658744812, "value_corner": 0.8355897665023804, "value_row": 0.8584553003311157, "value_any": 0.8820663690567017, "value_bot": 0.8583443760871887, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15490.png", "entropy": 0.08196136355400085} +{"ts": "2026-03-20T21:05:28.070372Z", "loop": 15500, "env_steps": 9523200000, "exact_value_avg": 0.8632954359054565, "regret_dist": 0.00028531200950965285, "regret_other_env": 0.0004199969407636672, "regret_corner": 8.328458352480084e-05, "regret_row": 0.0005426088464446366, "regret_any": 0.0004290249780751765, "regret_bot": 0.0006626082467846572, "value_dist": 0.8632954359054565, "value_other_env": 0.8817949295043945, "value_corner": 0.8355460166931152, "value_row": 0.8580840826034546, "value_any": 0.8818215727806091, "value_bot": 0.857964038848877, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15500.png", "entropy": 0.08404650539159775} +{"ts": "2026-03-20T21:05:36.649114Z", "loop": 15510, "env_steps": 9529344000, "exact_value_avg": 0.8628256320953369, "regret_dist": 0.0007550388691015542, "regret_other_env": 0.0011017934884876013, "regret_corner": 0.00023490688181482255, "regret_row": 0.002734463894739747, "regret_any": 0.0011104217264801264, "regret_bot": 0.0007529967115260661, "value_dist": 0.8628256320953369, "value_other_env": 0.8811130523681641, "value_corner": 0.8353943824768066, "value_row": 0.8558921813964844, "value_any": 0.8811401128768921, "value_bot": 0.8578736186027527, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15510.png", "entropy": 0.0878152921795845} +{"ts": "2026-03-20T21:05:45.231311Z", "loop": 15520, "env_steps": 9535488000, "exact_value_avg": 0.8632434606552124, "regret_dist": 0.0003372090286575258, "regret_other_env": 0.0005181274609640241, "regret_corner": 6.583134381799027e-05, "regret_row": 0.00070462457370013, "regret_any": 0.000518952845595777, "regret_bot": 0.00042566683259792626, "value_dist": 0.8632434606552124, "value_other_env": 0.8816967606544495, "value_corner": 0.8355634212493896, "value_row": 0.8579219579696655, "value_any": 0.8817316293716431, "value_bot": 0.8582009673118591, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15520.png", "entropy": 0.08480039238929749} +{"ts": "2026-03-20T21:05:53.811228Z", "loop": 15530, "env_steps": 9541632000, "exact_value_avg": 0.8632716536521912, "regret_dist": 0.0003090416139457375, "regret_other_env": 0.00049990025581792, "regret_corner": 2.2753578377887607e-05, "regret_row": 0.00022394109691958874, "regret_any": 0.0005048211314715445, "regret_bot": 0.0004506521509028971, "value_dist": 0.8632716536521912, "value_other_env": 0.881714940071106, "value_corner": 0.835606575012207, "value_row": 0.858402669429779, "value_any": 0.8817458748817444, "value_bot": 0.8581759929656982, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15530.png", "entropy": 0.08395999670028687} +{"ts": "2026-03-20T21:06:07.709620Z", "loop": 15540, "env_steps": 9547776000, "exact_value_avg": 0.8632038831710815, "regret_dist": 0.00037680158857256174, "regret_other_env": 0.000620582839474082, "regret_corner": 1.1129677659482695e-05, "regret_row": 0.0008025839342735708, "regret_any": 0.0006238875794224441, "regret_bot": 0.00042300467612221837, "value_dist": 0.8632038831710815, "value_other_env": 0.8815942406654358, "value_corner": 0.8356181979179382, "value_row": 0.8578240275382996, "value_any": 0.8816266655921936, "value_bot": 0.858203649520874, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15540.png", "entropy": 0.08132684230804443} +{"ts": "2026-03-20T21:06:16.290767Z", "loop": 15550, "env_steps": 9553920000, "exact_value_avg": 0.8629757165908813, "regret_dist": 0.0006049062358215451, "regret_other_env": 0.000997656723484397, "regret_corner": 1.5780329704284668e-05, "regret_row": 0.0012490779627114534, "regret_any": 0.001006699283607304, "regret_bot": 0.0010611553443595767, "value_dist": 0.8629757165908813, "value_other_env": 0.8812171816825867, "value_corner": 0.8356135487556458, "value_row": 0.8573775291442871, "value_any": 0.881243884563446, "value_bot": 0.8575654625892639, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15550.png", "entropy": 0.08575981855392456} +{"ts": "2026-03-20T21:06:24.870045Z", "loop": 15560, "env_steps": 9560064000, "exact_value_avg": 0.8610800504684448, "regret_dist": 0.0025006968062371016, "regret_other_env": 0.004090530332177877, "regret_corner": 0.00011594643729040399, "regret_row": 0.0024007803294807673, "regret_any": 0.004193949978798628, "regret_bot": 0.00023417070042341948, "value_dist": 0.8610800504684448, "value_other_env": 0.8781243562698364, "value_corner": 0.8355133533477783, "value_row": 0.856225848197937, "value_any": 0.8780567049980164, "value_bot": 0.8583924770355225, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15560.png", "entropy": 0.08804740011692047} +{"ts": "2026-03-20T21:06:33.444749Z", "loop": 15570, "env_steps": 9566208000, "exact_value_avg": 0.8632540702819824, "regret_dist": 0.00032668703352101147, "regret_other_env": 0.000510391837451607, "regret_corner": 5.112986036692746e-05, "regret_row": 0.0005045354482717812, "regret_any": 0.0005136476247571409, "regret_bot": 0.0004508083511609584, "value_dist": 0.8632540702819824, "value_other_env": 0.8817045092582703, "value_corner": 0.835578203201294, "value_row": 0.8581221103668213, "value_any": 0.8817369937896729, "value_bot": 0.8581758141517639, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15570.png", "entropy": 0.08648338913917542} +{"ts": "2026-03-20T21:06:42.026109Z", "loop": 15580, "env_steps": 9572352000, "exact_value_avg": 0.8625571727752686, "regret_dist": 0.00102343934122473, "regret_other_env": 0.001641768729314208, "regret_corner": 9.594510629540309e-05, "regret_row": 0.002052163239568472, "regret_any": 0.0016515182796865702, "regret_bot": 0.0007064237724989653, "value_dist": 0.8625571727752686, "value_other_env": 0.8805730938911438, "value_corner": 0.8355333209037781, "value_row": 0.8565744757652283, "value_any": 0.8805991411209106, "value_bot": 0.857920229434967, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15580.png", "entropy": 0.0896071270108223} +{"ts": "2026-03-20T21:06:50.604618Z", "loop": 15590, "env_steps": 9578496000, "exact_value_avg": 0.8630284667015076, "regret_dist": 0.0005522291758097708, "regret_other_env": 0.0008853876497596502, "regret_corner": 5.249133027973585e-05, "regret_row": 0.0008778144838288426, "regret_any": 0.0009060585289262235, "regret_bot": 0.0011800109641626477, "value_dist": 0.8630284667015076, "value_other_env": 0.8813295364379883, "value_corner": 0.8355767726898193, "value_row": 0.8577488660812378, "value_any": 0.8813444972038269, "value_bot": 0.8574466109275818, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15590.png", "entropy": 0.08786628395318985} +{"ts": "2026-03-20T21:06:59.189539Z", "loop": 15600, "env_steps": 9584640000, "exact_value_avg": 0.8633216619491577, "regret_dist": 0.0002591166412457824, "regret_other_env": 0.0004174357163719833, "regret_corner": 2.1637977624777704e-05, "regret_row": 0.0003241138474550098, "regret_any": 0.00042712566209957004, "regret_bot": 0.001031215419061482, "value_dist": 0.8633216619491577, "value_other_env": 0.8817974925041199, "value_corner": 0.8356077075004578, "value_row": 0.8583025336265564, "value_any": 0.8818234801292419, "value_bot": 0.8575954437255859, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15600.png", "entropy": 0.08690806478261948} +{"ts": "2026-03-20T21:07:07.766589Z", "loop": 15610, "env_steps": 9590784000, "exact_value_avg": 0.863330602645874, "regret_dist": 0.0002500339469406754, "regret_other_env": 0.0004119078512303531, "regret_corner": 7.223090051411418e-06, "regret_row": 0.00036907961475662887, "regret_any": 0.0004124281113035977, "regret_bot": 0.0012663248926401138, "value_dist": 0.863330602645874, "value_other_env": 0.8818029165267944, "value_corner": 0.8356220722198486, "value_row": 0.8582575917243958, "value_any": 0.8818381428718567, "value_bot": 0.8573603630065918, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15610.png", "entropy": 0.08563138544559479} +{"ts": "2026-03-20T21:07:16.344387Z", "loop": 15620, "env_steps": 9596928000, "exact_value_avg": 0.8625308871269226, "regret_dist": 0.0010498068295419216, "regret_other_env": 0.0017470548627898097, "regret_corner": 3.9344035940303e-06, "regret_row": 5.8255183830624446e-05, "regret_any": 0.0017448202706873417, "regret_bot": 0.007175945211201906, "value_dist": 0.8625308871269226, "value_other_env": 0.8804678320884705, "value_corner": 0.8356253504753113, "value_row": 0.8585683703422546, "value_any": 0.8805058002471924, "value_bot": 0.8514506816864014, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15620.png", "entropy": 0.08628738671541214} +{"ts": "2026-03-20T21:07:24.926047Z", "loop": 15630, "env_steps": 9603072000, "exact_value_avg": 0.8633506298065186, "regret_dist": 0.00023007221170701087, "regret_other_env": 0.0003794012009166181, "regret_corner": 6.078680598875508e-06, "regret_row": 0.00011445509153418243, "regret_any": 0.0003790701739490032, "regret_bot": 0.0015455294633284211, "value_dist": 0.8633506298065186, "value_other_env": 0.8818355202674866, "value_corner": 0.8356232047080994, "value_row": 0.8585121631622314, "value_any": 0.8818714618682861, "value_bot": 0.8570810556411743, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15630.png", "entropy": 0.08535265922546387} +{"ts": "2026-03-20T21:07:33.513201Z", "loop": 15640, "env_steps": 9609216000, "exact_value_avg": 0.8633426427841187, "regret_dist": 0.00023799952759873122, "regret_other_env": 0.0003869181964546442, "regret_corner": 1.462151703890413e-05, "regret_row": 0.00038652532384730875, "regret_any": 0.0003877688432112336, "regret_bot": 0.0006411982467398047, "value_dist": 0.8633426427841187, "value_other_env": 0.8818278908729553, "value_corner": 0.8356146812438965, "value_row": 0.8582400679588318, "value_any": 0.8818628787994385, "value_bot": 0.8579853773117065, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15640.png", "entropy": 0.0865573137998581} +{"ts": "2026-03-20T21:07:42.096000Z", "loop": 15650, "env_steps": 9615360000, "exact_value_avg": 0.8627452850341797, "regret_dist": 0.0008353315643034875, "regret_other_env": 0.0013764931354671717, "regret_corner": 2.358903657295741e-05, "regret_row": 0.0014872899046167731, "regret_any": 0.0013828661758452654, "regret_bot": 0.001557611976750195, "value_dist": 0.8627452850341797, "value_other_env": 0.8808383345603943, "value_corner": 0.8356057405471802, "value_row": 0.8571394085884094, "value_any": 0.8808677196502686, "value_bot": 0.8570689558982849, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15650.png", "entropy": 0.08858375251293182} +{"ts": "2026-03-20T21:07:50.680798Z", "loop": 15660, "env_steps": 9621504000, "exact_value_avg": 0.8625243902206421, "regret_dist": 0.0010563379619270563, "regret_other_env": 0.0017593210795894265, "regret_corner": 1.8631419607118005e-06, "regret_row": 1.5570900359307416e-05, "regret_any": 0.0017570570344105363, "regret_bot": 0.006168416701257229, "value_dist": 0.8625243902206421, "value_other_env": 0.8804555535316467, "value_corner": 0.8356274962425232, "value_row": 0.8586111068725586, "value_any": 0.8804935216903687, "value_bot": 0.8524582386016846, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15660.png", "entropy": 0.08602038025856018} +{"ts": "2026-03-20T21:07:59.260403Z", "loop": 15670, "env_steps": 9627648000, "exact_value_avg": 0.8625453114509583, "regret_dist": 0.0010354021796956658, "regret_other_env": 0.0017203650204464793, "regret_corner": 7.957717571116518e-06, "regret_row": 2.469316495989915e-05, "regret_any": 0.0017192972591146827, "regret_bot": 0.006517971400171518, "value_dist": 0.8625453114509583, "value_other_env": 0.8804945349693298, "value_corner": 0.8356213569641113, "value_row": 0.8586019277572632, "value_any": 0.8805313110351562, "value_bot": 0.8521086573600769, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15670.png", "entropy": 0.08979035168886185} +{"ts": "2026-03-20T21:08:07.842443Z", "loop": 15680, "env_steps": 9633792000, "exact_value_avg": 0.8627791404724121, "regret_dist": 0.0008014612249098718, "regret_other_env": 0.0012460871366783977, "regret_corner": 0.000134522226289846, "regret_row": 0.00017648366338107735, "regret_any": 0.0012477749260142446, "regret_bot": 0.004844651557505131, "value_dist": 0.8627791404724121, "value_other_env": 0.8809687495231628, "value_corner": 0.8354947566986084, "value_row": 0.858450174331665, "value_any": 0.8810027837753296, "value_bot": 0.8537819385528564, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15680.png", "entropy": 0.10397317260503769} +{"ts": "2026-03-20T21:08:16.426006Z", "loop": 15690, "env_steps": 9639936000, "exact_value_avg": 0.863006055355072, "regret_dist": 0.0005746036185882986, "regret_other_env": 0.0007453602156601846, "regret_corner": 0.0003184686356689781, "regret_row": 0.0004346317145973444, "regret_any": 0.0007456945022568107, "regret_bot": 0.0017704240744933486, "value_dist": 0.863006055355072, "value_other_env": 0.8814694881439209, "value_corner": 0.8353108167648315, "value_row": 0.8581920266151428, "value_any": 0.8815049529075623, "value_bot": 0.8568561673164368, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15690.png", "entropy": 0.10903412848711014} +{"ts": "2026-03-20T21:08:25.006440Z", "loop": 15700, "env_steps": 9646080000, "exact_value_avg": 0.8630692958831787, "regret_dist": 0.0005114303203299642, "regret_other_env": 0.0007239719270728528, "regret_corner": 0.00019261788111180067, "regret_row": 0.0004619804094545543, "regret_any": 0.000724347191862762, "regret_bot": 0.0019569620490074158, "value_dist": 0.8630692958831787, "value_other_env": 0.88149094581604, "value_corner": 0.8354367017745972, "value_row": 0.8581646084785461, "value_any": 0.8815262317657471, "value_bot": 0.8566696643829346, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15700.png", "entropy": 0.10158960521221161} +{"ts": "2026-03-20T21:08:33.588492Z", "loop": 15710, "env_steps": 9652224000, "exact_value_avg": 0.8629500269889832, "regret_dist": 0.0006306683062575758, "regret_other_env": 0.0009693422471173108, "regret_corner": 0.0001226574240718037, "regret_row": 0.0002001961402129382, "regret_any": 0.0009680217481218278, "regret_bot": 0.0035009512212127447, "value_dist": 0.8629500269889832, "value_other_env": 0.881245493888855, "value_corner": 0.8355067372322083, "value_row": 0.8584264516830444, "value_any": 0.8812825679779053, "value_bot": 0.8551256060600281, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15710.png", "entropy": 0.09732676297426224} +{"ts": "2026-03-20T21:08:42.174633Z", "loop": 15720, "env_steps": 9658368000, "exact_value_avg": 0.8627814054489136, "regret_dist": 0.0007992653409019113, "regret_other_env": 0.0012970315292477608, "regret_corner": 5.261600381345488e-05, "regret_row": 0.00021314584591891617, "regret_any": 0.0012953958939760923, "regret_bot": 0.005569396074861288, "value_dist": 0.8627814054489136, "value_other_env": 0.8809178471565247, "value_corner": 0.8355767130851746, "value_row": 0.8584134578704834, "value_any": 0.880955159664154, "value_bot": 0.8530572652816772, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15720.png", "entropy": 0.09023947268724442} +{"ts": "2026-03-20T21:08:50.759086Z", "loop": 15730, "env_steps": 9664512000, "exact_value_avg": 0.8630121350288391, "regret_dist": 0.0005685215000994503, "regret_other_env": 0.0008904468268156052, "regret_corner": 8.563350274926051e-05, "regret_row": 0.0010888043325394392, "regret_any": 0.0008907929877750576, "regret_bot": 0.0019341069273650646, "value_dist": 0.8630121350288391, "value_other_env": 0.8813244104385376, "value_corner": 0.835543692111969, "value_row": 0.8575378060340881, "value_any": 0.8813598155975342, "value_bot": 0.8566924929618835, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15730.png", "entropy": 0.0932953953742981} +{"ts": "2026-03-20T21:08:59.349140Z", "loop": 15740, "env_steps": 9670656000, "exact_value_avg": 0.8634181022644043, "regret_dist": 0.000162590789841488, "regret_other_env": 0.0002413459005765617, "regret_corner": 4.4458112824941054e-05, "regret_row": 0.0001240224955836311, "regret_any": 0.00024117229622788727, "regret_bot": 0.0005168133648112416, "value_dist": 0.8634181022644043, "value_other_env": 0.8819735646247864, "value_corner": 0.8355849385261536, "value_row": 0.8585025668144226, "value_any": 0.8820094466209412, "value_bot": 0.8581098914146423, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15740.png", "entropy": 0.08693443238735199} +{"ts": "2026-03-20T21:09:07.931106Z", "loop": 15750, "env_steps": 9676800000, "exact_value_avg": 0.8634703159332275, "regret_dist": 0.0001103551039705053, "regret_other_env": 0.00017148899496532977, "regret_corner": 1.8654267478268594e-05, "regret_row": 4.9405025492887944e-05, "regret_any": 0.00017151761858258396, "regret_bot": 0.00045949441846460104, "value_dist": 0.8634703159332275, "value_other_env": 0.8820434212684631, "value_corner": 0.8356106877326965, "value_row": 0.8585772514343262, "value_any": 0.8820791244506836, "value_bot": 0.8581671118736267, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15750.png", "entropy": 0.08474101126194} +{"ts": "2026-03-20T21:09:16.513183Z", "loop": 15760, "env_steps": 9682944000, "exact_value_avg": 0.863437831401825, "regret_dist": 0.00014282962365541607, "regret_other_env": 0.00023452474852092564, "regret_corner": 5.286932264425559e-06, "regret_row": 3.485114939394407e-05, "regret_any": 0.000236539141042158, "regret_bot": 0.0008531003259122372, "value_dist": 0.863437831401825, "value_other_env": 0.8819803595542908, "value_corner": 0.8356240391731262, "value_row": 0.8585917949676514, "value_any": 0.8820140361785889, "value_bot": 0.8577734231948853, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15760.png", "entropy": 0.08292970806360245} +{"ts": "2026-03-20T21:09:25.096875Z", "loop": 15770, "env_steps": 9689088000, "exact_value_avg": 0.8632502555847168, "regret_dist": 0.00033039861591532826, "regret_other_env": 0.0005461121909320354, "regret_corner": 6.828209279774455e-06, "regret_row": 0.0008141551516018808, "regret_any": 0.0005584530299529433, "regret_bot": 0.001222830032929778, "value_dist": 0.8632502555847168, "value_other_env": 0.881668746471405, "value_corner": 0.8356224298477173, "value_row": 0.8578124642372131, "value_any": 0.8816921710968018, "value_bot": 0.8574036955833435, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15770.png", "entropy": 0.07945232093334198} +{"ts": "2026-03-20T21:09:33.679573Z", "loop": 15780, "env_steps": 9695232000, "exact_value_avg": 0.8629481792449951, "regret_dist": 0.0006325665162876248, "regret_other_env": 0.0010377467842772603, "regret_corner": 2.479603062965907e-05, "regret_row": 0.0018152996199205518, "regret_any": 0.001045874785631895, "regret_bot": 0.0008010048768483102, "value_dist": 0.8629481792449951, "value_other_env": 0.8811771869659424, "value_corner": 0.8356045484542847, "value_row": 0.8568112850189209, "value_any": 0.8812047243118286, "value_bot": 0.8578255772590637, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15780.png", "entropy": 0.08028901368379593} +{"ts": "2026-03-20T21:09:42.260924Z", "loop": 15790, "env_steps": 9701376000, "exact_value_avg": 0.8625463247299194, "regret_dist": 0.0010344048496335745, "regret_other_env": 0.0016983775421977043, "regret_corner": 3.8445494283223525e-05, "regret_row": 0.0021304297260940075, "regret_any": 0.0017210827209055424, "regret_bot": 0.001242276863195002, "value_dist": 0.8625463247299194, "value_other_env": 0.880516529083252, "value_corner": 0.8355908989906311, "value_row": 0.8564961552619934, "value_any": 0.8805295825004578, "value_bot": 0.8573843836784363, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15790.png", "entropy": 0.07925701141357422} +{"ts": "2026-03-20T21:09:50.838179Z", "loop": 15800, "env_steps": 9707520000, "exact_value_avg": 0.8632553815841675, "regret_dist": 0.00032532113255001605, "regret_other_env": 0.0005150721408426762, "regret_corner": 4.0694576455280185e-05, "regret_row": 0.0003530220128595829, "regret_any": 0.000536397157702595, "regret_bot": 0.0011172846425324678, "value_dist": 0.8632553815841675, "value_other_env": 0.881699800491333, "value_corner": 0.8355886340141296, "value_row": 0.8582735657691956, "value_any": 0.8817142248153687, "value_bot": 0.8575093150138855, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15800.png", "entropy": 0.07916782796382904} +{"ts": "2026-03-20T21:09:59.424952Z", "loop": 15810, "env_steps": 9713664000, "exact_value_avg": 0.8630445003509521, "regret_dist": 0.0005361725925467908, "regret_other_env": 0.0008441467653028667, "regret_corner": 7.421126065310091e-05, "regret_row": 0.0008266569930128753, "regret_any": 0.0008525997982360423, "regret_bot": 0.0006120548932813108, "value_dist": 0.8630445003509521, "value_other_env": 0.8813707232475281, "value_corner": 0.8355550765991211, "value_row": 0.8578000068664551, "value_any": 0.8813980221748352, "value_bot": 0.8580145239830017, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15810.png", "entropy": 0.0806027501821518} +{"ts": "2026-03-20T21:10:08.010903Z", "loop": 15820, "env_steps": 9719808000, "exact_value_avg": 0.8623104691505432, "regret_dist": 0.0012702634558081627, "regret_other_env": 0.0020593167282640934, "regret_corner": 8.66835325723514e-05, "regret_row": 0.0017121006967499852, "regret_any": 0.002082263585180044, "regret_bot": 0.0003116144798696041, "value_dist": 0.8623104691505432, "value_other_env": 0.880155622959137, "value_corner": 0.8355426788330078, "value_row": 0.8569145202636719, "value_any": 0.8801683187484741, "value_bot": 0.8583149909973145, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15820.png", "entropy": 0.0785258486866951} +{"ts": "2026-03-20T21:10:16.593566Z", "loop": 15830, "env_steps": 9725952000, "exact_value_avg": 0.8626531362533569, "regret_dist": 0.0009275380289182067, "regret_other_env": 0.0014990083873271942, "regret_corner": 7.033249130472541e-05, "regret_row": 0.0014323013601824641, "regret_any": 0.001510328147560358, "regret_bot": 0.00023100005637388676, "value_dist": 0.8626531362533569, "value_other_env": 0.8807159066200256, "value_corner": 0.8355590105056763, "value_row": 0.8571942448616028, "value_any": 0.880740225315094, "value_bot": 0.8583956360816956, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15830.png", "entropy": 0.07852856069803238} +{"ts": "2026-03-20T21:10:25.175567Z", "loop": 15840, "env_steps": 9732096000, "exact_value_avg": 0.8634616136550903, "regret_dist": 0.00011910397734027356, "regret_other_env": 0.00019465218065306544, "regret_corner": 5.7816509979602415e-06, "regret_row": 9.317930380348116e-05, "regret_any": 0.00019622490799520165, "regret_bot": 0.00041536588105373085, "value_dist": 0.8634616136550903, "value_other_env": 0.8820202350616455, "value_corner": 0.8356235027313232, "value_row": 0.8585334420204163, "value_any": 0.8820543885231018, "value_bot": 0.8582112193107605, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15840.png", "entropy": 0.07495548576116562} +{"ts": "2026-03-20T21:10:33.759199Z", "loop": 15850, "env_steps": 9738240000, "exact_value_avg": 0.8632784485816956, "regret_dist": 0.0003022505552507937, "regret_other_env": 0.0004926869296468794, "regret_corner": 1.6595920897088945e-05, "regret_row": 0.000641082355286926, "regret_any": 0.0004964881227351725, "regret_bot": 0.0002874851052183658, "value_dist": 0.8632784485816956, "value_other_env": 0.8817222118377686, "value_corner": 0.8356127142906189, "value_row": 0.8579856157302856, "value_any": 0.8817541003227234, "value_bot": 0.858339250087738, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15850.png", "entropy": 0.07880573719739914} +{"ts": "2026-03-20T21:10:42.340761Z", "loop": 15860, "env_steps": 9744384000, "exact_value_avg": 0.8625051975250244, "regret_dist": 0.0010754752438515425, "regret_other_env": 0.0017788797849789262, "regret_corner": 2.0368397599668242e-05, "regret_row": 0.0007880004704929888, "regret_any": 0.0017867541173473, "regret_bot": 0.004537869244813919, "value_dist": 0.8625051975250244, "value_other_env": 0.8804359436035156, "value_corner": 0.835608959197998, "value_row": 0.8578385710716248, "value_any": 0.8804637789726257, "value_bot": 0.8540887832641602, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15860.png", "entropy": 0.087583526968956} +{"ts": "2026-03-20T21:10:50.922624Z", "loop": 15870, "env_steps": 9750528000, "exact_value_avg": 0.8613584041595459, "regret_dist": 0.0022223088890314102, "regret_other_env": 0.0036994258407503366, "regret_corner": 6.633500561292749e-06, "regret_row": 5.8003264712169766e-05, "regret_any": 0.0036941200960427523, "regret_bot": 0.01198744960129261, "value_dist": 0.8613584041595459, "value_other_env": 0.8785154223442078, "value_corner": 0.8356227278709412, "value_row": 0.8585686683654785, "value_any": 0.878556489944458, "value_bot": 0.8466391563415527, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15870.png", "entropy": 0.08535347878932953} +{"ts": "2026-03-20T21:10:59.500677Z", "loop": 15880, "env_steps": 9756672000, "exact_value_avg": 0.862026035785675, "regret_dist": 0.001554688555188477, "regret_other_env": 0.0025873861741274595, "regret_corner": 5.642076757794712e-06, "regret_row": 3.536731674103066e-05, "regret_any": 0.002583650406450033, "regret_bot": 0.009836613200604916, "value_dist": 0.862026035785675, "value_other_env": 0.879627525806427, "value_corner": 0.8356237411499023, "value_row": 0.8585911989212036, "value_any": 0.8796669244766235, "value_bot": 0.8487899899482727, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15880.png", "entropy": 0.08327166736125946} +{"ts": "2026-03-20T21:11:08.083753Z", "loop": 15890, "env_steps": 9762816000, "exact_value_avg": 0.8621206879615784, "regret_dist": 0.0014599920250475407, "regret_other_env": 0.0024074234534054995, "regret_corner": 3.88448461308144e-05, "regret_row": 0.00017636368284001946, "regret_any": 0.002405705861747265, "regret_bot": 0.006857294589281082, "value_dist": 0.8621206879615784, "value_other_env": 0.8798074722290039, "value_corner": 0.8355904817581177, "value_row": 0.8584502935409546, "value_any": 0.8798449039459229, "value_bot": 0.8517693281173706, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15890.png", "entropy": 0.09396036714315414} +{"ts": "2026-03-20T21:11:16.660407Z", "loop": 15900, "env_steps": 9768960000, "exact_value_avg": 0.8621832132339478, "regret_dist": 0.0013974640751257539, "regret_other_env": 0.002210509730502963, "regret_corner": 0.00017789553385227919, "regret_row": 0.00034751713974401355, "regret_any": 0.0022093544248491526, "regret_bot": 0.0066420757211744785, "value_dist": 0.8621832132339478, "value_other_env": 0.880004346370697, "value_corner": 0.8354514241218567, "value_row": 0.8582791090011597, "value_any": 0.880041241645813, "value_bot": 0.8519845604896545, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15900.png", "entropy": 0.10534317791461945} +{"ts": "2026-03-20T21:11:25.238414Z", "loop": 15910, "env_steps": 9775104000, "exact_value_avg": 0.8625858426094055, "regret_dist": 0.000994818052276969, "regret_other_env": 0.0014863236574456096, "regret_corner": 0.00025755964452400804, "regret_row": 0.0004921923973597586, "regret_any": 0.0014851675368845463, "regret_bot": 0.003171344753354788, "value_dist": 0.8625858426094055, "value_other_env": 0.880728542804718, "value_corner": 0.835371732711792, "value_row": 0.8581345081329346, "value_any": 0.8807653784751892, "value_bot": 0.8554553389549255, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15910.png", "entropy": 0.11040148884057999} +{"ts": "2026-03-20T21:11:33.821823Z", "loop": 15920, "env_steps": 9781248000, "exact_value_avg": 0.8633530735969543, "regret_dist": 0.00022758202976547182, "regret_other_env": 0.0003675288171507418, "regret_corner": 1.766185050655622e-05, "regret_row": 4.0549082768848166e-05, "regret_any": 0.00037341201095841825, "regret_bot": 0.001098009292036295, "value_dist": 0.8633530735969543, "value_other_env": 0.8818473219871521, "value_corner": 0.8356116414070129, "value_row": 0.8585861325263977, "value_any": 0.8818771839141846, "value_bot": 0.857528567314148, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15920.png", "entropy": 0.08617280423641205} +{"ts": "2026-03-20T21:11:42.405054Z", "loop": 15930, "env_steps": 9787392000, "exact_value_avg": 0.863446831703186, "regret_dist": 0.00013386353384703398, "regret_other_env": 0.0002163635945180431, "regret_corner": 1.0113418284163345e-05, "regret_row": 3.0419410904869437e-05, "regret_any": 0.00021741628006566316, "regret_bot": 0.000658100179862231, "value_dist": 0.863446831703186, "value_other_env": 0.8819985389709473, "value_corner": 0.8356192111968994, "value_row": 0.8585962057113647, "value_any": 0.8820331692695618, "value_bot": 0.8579685688018799, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15930.png", "entropy": 0.08488256484270096} +{"ts": "2026-03-20T21:11:50.997452Z", "loop": 15940, "env_steps": 9793536000, "exact_value_avg": 0.8634405136108398, "regret_dist": 0.00014019633817952126, "regret_other_env": 0.00022794048709329218, "regret_corner": 8.580089343013242e-06, "regret_row": 6.81106757838279e-05, "regret_any": 0.0002323578082723543, "regret_bot": 0.0006915635312907398, "value_dist": 0.8634405136108398, "value_other_env": 0.8819869756698608, "value_corner": 0.8356208205223083, "value_row": 0.8585584759712219, "value_any": 0.8820182085037231, "value_bot": 0.8579350709915161, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15940.png", "entropy": 0.08198963105678558} +{"ts": "2026-03-20T21:11:59.576539Z", "loop": 15950, "env_steps": 9799680000, "exact_value_avg": 0.8632192611694336, "regret_dist": 0.00036143901525065303, "regret_other_env": 0.0005947205936536193, "regret_corner": 1.1516611266415566e-05, "regret_row": 0.0005167992785573006, "regret_any": 0.0006136576412245631, "regret_bot": 0.000968943175394088, "value_dist": 0.8632192611694336, "value_other_env": 0.8816201686859131, "value_corner": 0.8356177806854248, "value_row": 0.8581098914146423, "value_any": 0.881636917591095, "value_bot": 0.8576576709747314, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15950.png", "entropy": 0.07943487912416458} +{"ts": "2026-03-20T21:12:08.167214Z", "loop": 15960, "env_steps": 9805824000, "exact_value_avg": 0.8632824420928955, "regret_dist": 0.00029828562401235104, "regret_other_env": 0.00048341407091356814, "regret_corner": 2.0592910004779696e-05, "regret_row": 0.00045556691475212574, "regret_any": 0.0004947163979522884, "regret_bot": 0.0007418151944875717, "value_dist": 0.8632824420928955, "value_other_env": 0.8817314505577087, "value_corner": 0.835608720779419, "value_row": 0.8581711053848267, "value_any": 0.8817558884620667, "value_bot": 0.8578847646713257, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15960.png", "entropy": 0.08182810246944427} +{"ts": "2026-03-20T21:12:16.751139Z", "loop": 15970, "env_steps": 9811968000, "exact_value_avg": 0.8634473085403442, "regret_dist": 0.00013337767450138927, "regret_other_env": 0.00021076823759358376, "regret_corner": 1.729180439724587e-05, "regret_row": 0.00010995819320669398, "regret_any": 0.00021258863853290677, "regret_bot": 0.00048376721679233015, "value_dist": 0.8634473085403442, "value_other_env": 0.8820041418075562, "value_corner": 0.8356119990348816, "value_row": 0.8585166931152344, "value_any": 0.8820379972457886, "value_bot": 0.8581429123878479, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15970.png", "entropy": 0.08255816996097565} +{"ts": "2026-03-20T21:12:25.331522Z", "loop": 15980, "env_steps": 9818112000, "exact_value_avg": 0.863448977470398, "regret_dist": 0.0001317520800512284, "regret_other_env": 0.00021071895025670528, "regret_corner": 1.3301770195539575e-05, "regret_row": 3.163787187077105e-05, "regret_any": 0.00021071513765491545, "regret_bot": 0.0006119251484051347, "value_dist": 0.863448977470398, "value_other_env": 0.8820042014122009, "value_corner": 0.8356160521507263, "value_row": 0.8585949540138245, "value_any": 0.8820399045944214, "value_bot": 0.858014702796936, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15980.png", "entropy": 0.0853838324546814} +{"ts": "2026-03-20T21:12:33.915709Z", "loop": 15990, "env_steps": 9824256000, "exact_value_avg": 0.8630578517913818, "regret_dist": 0.0005227542715147138, "regret_other_env": 0.0008025554707273841, "regret_corner": 0.00010305246541975066, "regret_row": 0.00017365194798912853, "regret_any": 0.0008015027269721031, "regret_bot": 0.0023173484951257706, "value_dist": 0.8630578517913818, "value_other_env": 0.8814123272895813, "value_corner": 0.8355262279510498, "value_row": 0.8584530353546143, "value_any": 0.8814491033554077, "value_bot": 0.8563092350959778, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_15990.png", "entropy": 0.09761692583560944} +{"ts": "2026-03-20T21:12:42.499588Z", "loop": 16000, "env_steps": 9830400000, "exact_value_avg": 0.8628506064414978, "regret_dist": 0.0007300915312953293, "regret_other_env": 0.0010338504798710346, "regret_corner": 0.00027445307932794094, "regret_row": 0.0004278969136066735, "regret_any": 0.001032558036968112, "regret_bot": 0.001873744884505868, "value_dist": 0.8628506064414978, "value_other_env": 0.8811810612678528, "value_corner": 0.8353549242019653, "value_row": 0.8581987619400024, "value_any": 0.8812180161476135, "value_bot": 0.856752872467041, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_16000.png", "entropy": 0.10597506165504456} +{"ts": "2026-03-20T21:12:51.078706Z", "loop": 16010, "env_steps": 9836544000, "exact_value_avg": 0.8630024194717407, "regret_dist": 0.0005782231455668807, "regret_other_env": 0.0007966647972352803, "regret_corner": 0.0002505605516489595, "regret_row": 0.00038923724787309766, "regret_any": 0.0007965668919496238, "regret_bot": 0.0009507395443506539, "value_dist": 0.8630024194717407, "value_other_env": 0.8814181685447693, "value_corner": 0.8353788256645203, "value_row": 0.8582373261451721, "value_any": 0.8814541101455688, "value_bot": 0.8576759696006775, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_16010.png", "entropy": 0.10339713841676712} +{"ts": "2026-03-20T21:12:59.658023Z", "loop": 16020, "env_steps": 9842688000, "exact_value_avg": 0.8628635406494141, "regret_dist": 0.0007171043544076383, "regret_other_env": 0.0009730415767990053, "regret_corner": 0.0003331984335090965, "regret_row": 0.0008055843645706773, "regret_any": 0.0009745334973558784, "regret_bot": 0.0005809710128232837, "value_dist": 0.8628635406494141, "value_other_env": 0.8812418580055237, "value_corner": 0.8352961540222168, "value_row": 0.8578210473060608, "value_any": 0.8812761306762695, "value_bot": 0.8580456376075745, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_16020.png", "entropy": 0.1021730825304985} +{"ts": "2026-03-20T21:13:08.245628Z", "loop": 16030, "env_steps": 9848832000, "exact_value_avg": 0.8619967699050903, "regret_dist": 0.001583944307640195, "regret_other_env": 0.0020459715742617846, "regret_corner": 0.0008909032330848277, "regret_row": 0.0019984201062470675, "regret_any": 0.002061588456854224, "regret_bot": 0.0015671110013499856, "value_dist": 0.8619967699050903, "value_other_env": 0.8801689147949219, "value_corner": 0.8347383737564087, "value_row": 0.8566281795501709, "value_any": 0.8801890015602112, "value_bot": 0.8570595383644104, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_16030.png", "entropy": 0.11347989737987518} +{"ts": "2026-03-20T21:13:16.834765Z", "loop": 16040, "env_steps": 9854976000, "exact_value_avg": 0.8629848957061768, "regret_dist": 0.0005957952234894037, "regret_other_env": 0.0009332327172160149, "regret_corner": 8.963893196778372e-05, "regret_row": 0.0008469726890325546, "regret_any": 0.0009498727158643305, "regret_bot": 0.0009450537618249655, "value_dist": 0.8629848957061768, "value_other_env": 0.8812816143035889, "value_corner": 0.835539698600769, "value_row": 0.8577796220779419, "value_any": 0.8813007473945618, "value_bot": 0.8576816320419312, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_16040.png", "entropy": 0.08860744535923004} +{"ts": "2026-03-20T21:13:25.416933Z", "loop": 16050, "env_steps": 9861120000, "exact_value_avg": 0.8628718852996826, "regret_dist": 0.0007088236161507666, "regret_other_env": 0.0011664903722703457, "regret_corner": 2.2323431039694697e-05, "regret_row": 0.0011125686578452587, "regret_any": 0.0011835217010229826, "regret_bot": 0.0007618138333782554, "value_dist": 0.8628718852996826, "value_other_env": 0.8810483813285828, "value_corner": 0.8356069922447205, "value_row": 0.8575140237808228, "value_any": 0.8810670971870422, "value_bot": 0.8578647971153259, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_16050.png", "entropy": 0.07827599346637726} +{"ts": "2026-03-20T21:13:34.007428Z", "loop": 16060, "env_steps": 9867264000, "exact_value_avg": 0.8625289797782898, "regret_dist": 0.001051718951202929, "regret_other_env": 0.0017393020680174232, "regret_corner": 2.03440595214488e-05, "regret_row": 0.002148070139810443, "regret_any": 0.0017607773188501596, "regret_bot": 0.001028636354021728, "value_dist": 0.8625289797782898, "value_other_env": 0.8804755806922913, "value_corner": 0.835608959197998, "value_row": 0.8564785718917847, "value_any": 0.8804898262023926, "value_bot": 0.8575979471206665, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_16060.png", "entropy": 0.0757472887635231} +{"ts": "2026-03-20T21:13:42.596772Z", "loop": 16070, "env_steps": 9873408000, "exact_value_avg": 0.8624913096427917, "regret_dist": 0.0010893932776525617, "regret_other_env": 0.001799003453925252, "regret_corner": 2.497782406862825e-05, "regret_row": 0.0028006830252707005, "regret_any": 0.0018217971082776785, "regret_bot": 0.0011038979282602668, "value_dist": 0.8624913096427917, "value_other_env": 0.8804158568382263, "value_corner": 0.8356043696403503, "value_row": 0.8558258414268494, "value_any": 0.8804288506507874, "value_bot": 0.85752272605896, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_16070.png", "entropy": 0.07361704111099243} +{"ts": "2026-03-20T21:13:51.178273Z", "loop": 16080, "env_steps": 9879552000, "exact_value_avg": 0.8629004955291748, "regret_dist": 0.0006801719428040087, "regret_other_env": 0.0011275458382442594, "regret_corner": 9.111066901823506e-06, "regret_row": 0.0019410999957472086, "regret_any": 0.0011503659188747406, "regret_bot": 0.001315930625423789, "value_dist": 0.8629004955291748, "value_other_env": 0.8810873031616211, "value_corner": 0.8356202244758606, "value_row": 0.8566855192184448, "value_any": 0.8811002373695374, "value_bot": 0.8573107123374939, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_16080.png", "entropy": 0.07039261609315872} +{"ts": "2026-03-20T21:13:59.751531Z", "loop": 16090, "env_steps": 9885696000, "exact_value_avg": 0.8632538914680481, "regret_dist": 0.0003268655273132026, "regret_other_env": 0.0005405055126175284, "regret_corner": 6.40551297692582e-06, "regret_row": 0.0006879906286485493, "regret_any": 0.0005635216948576272, "regret_bot": 0.0009971316903829575, "value_dist": 0.8632538914680481, "value_other_env": 0.8816744089126587, "value_corner": 0.8356229662895203, "value_row": 0.8579385876655579, "value_any": 0.8816870450973511, "value_bot": 0.8576295375823975, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_16090.png", "entropy": 0.0684414654970169} +{"ts": "2026-03-20T21:14:08.329004Z", "loop": 16100, "env_steps": 9891840000, "exact_value_avg": 0.8633561134338379, "regret_dist": 0.00022461829939857125, "regret_other_env": 0.00037189386785030365, "regret_corner": 3.704925575220841e-06, "regret_row": 0.0003974863502662629, "regret_any": 0.0003953166597057134, "regret_bot": 0.0011861039092764258, "value_dist": 0.8633561134338379, "value_other_env": 0.8818430304527283, "value_corner": 0.8356256484985352, "value_row": 0.8582291603088379, "value_any": 0.8818552494049072, "value_bot": 0.8574405312538147, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_16100.png", "entropy": 0.0704428106546402} +{"ts": "2026-03-20T21:14:16.909044Z", "loop": 16110, "env_steps": 9897984000, "exact_value_avg": 0.8633888959884644, "regret_dist": 0.00019181575044058263, "regret_other_env": 0.0003140099288430065, "regret_corner": 8.524458280589897e-06, "regret_row": 0.00033802958205342293, "regret_any": 0.00033153907861560583, "regret_bot": 0.0009230102295987308, "value_dist": 0.8633888959884644, "value_other_env": 0.8819008469581604, "value_corner": 0.8356208205223083, "value_row": 0.8582886457443237, "value_any": 0.8819190859794617, "value_bot": 0.8577035069465637, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_16110.png", "entropy": 0.07413005828857422} +{"ts": "2026-03-20T21:14:25.495028Z", "loop": 16120, "env_steps": 9904128000, "exact_value_avg": 0.8631771802902222, "regret_dist": 0.00040350083145312965, "regret_other_env": 0.0006493376567959785, "regret_corner": 3.474553523119539e-05, "regret_row": 0.0007668650359846652, "regret_any": 0.0006680226069875062, "regret_bot": 0.0008186065242625773, "value_dist": 0.8631771802902222, "value_other_env": 0.8815655708312988, "value_corner": 0.8355945944786072, "value_row": 0.8578598499298096, "value_any": 0.8815825581550598, "value_bot": 0.8578080534934998, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_16120.png", "entropy": 0.07679405063390732} +{"ts": "2026-03-20T21:14:34.076976Z", "loop": 16130, "env_steps": 9910272000, "exact_value_avg": 0.8601557612419128, "regret_dist": 0.003424924798309803, "regret_other_env": 0.005529853515326977, "regret_corner": 0.00026753099518828094, "regret_row": 0.012286321260035038, "regret_any": 0.005530999042093754, "regret_bot": 0.000454244262073189, "value_dist": 0.8601557612419128, "value_other_env": 0.8766850233078003, "value_corner": 0.8353617787361145, "value_row": 0.8463402390480042, "value_any": 0.87671959400177, "value_bot": 0.8581724166870117, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_16130.png", "entropy": 0.09358932822942734} +{"ts": "2026-03-20T21:14:42.663924Z", "loop": 16140, "env_steps": 9916416000, "exact_value_avg": 0.8622145056724548, "regret_dist": 0.0013661866541951895, "regret_other_env": 0.002245646435767412, "regret_corner": 4.699677447206341e-05, "regret_row": 0.0014792883303016424, "regret_any": 0.0022469668183475733, "regret_bot": 0.0004074660537298769, "value_dist": 0.8622145056724548, "value_other_env": 0.8799692392349243, "value_corner": 0.8355823159217834, "value_row": 0.8571473956108093, "value_any": 0.8800036311149597, "value_bot": 0.8582192063331604, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_16140.png", "entropy": 0.08323831111192703} +{"ts": "2026-03-20T21:14:51.249883Z", "loop": 16150, "env_steps": 9922560000, "exact_value_avg": 0.8628033399581909, "regret_dist": 0.0007773975958116353, "regret_other_env": 0.001280023017898202, "regret_corner": 2.3459395379177295e-05, "regret_row": 0.0011067806044593453, "regret_any": 0.0012813740177080035, "regret_bot": 0.00045001113903708756, "value_dist": 0.8628033399581909, "value_other_env": 0.8809348940849304, "value_corner": 0.8356059193611145, "value_row": 0.8575198650360107, "value_any": 0.8809691667556763, "value_bot": 0.8581765294075012, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_16150.png", "entropy": 0.07825029641389847} +{"ts": "2026-03-20T21:14:59.832747Z", "loop": 16160, "env_steps": 9928704000, "exact_value_avg": 0.8633264303207397, "regret_dist": 0.0002542152942623943, "regret_other_env": 0.0004097707860637456, "regret_corner": 2.0881991076748818e-05, "regret_row": 0.0005174351972527802, "regret_any": 0.0004095875774510205, "regret_bot": 0.00019748079648707062, "value_dist": 0.8633264303207397, "value_other_env": 0.8818050622940063, "value_corner": 0.8356084823608398, "value_row": 0.8581091165542603, "value_any": 0.8818410634994507, "value_bot": 0.8584291338920593, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_16160.png", "entropy": 0.0764169916510582} +{"ts": "2026-03-20T21:15:08.425627Z", "loop": 16170, "env_steps": 9934848000, "exact_value_avg": 0.8633573055267334, "regret_dist": 0.00022335592075251043, "regret_other_env": 0.0003667371638584882, "regret_corner": 8.28405245556496e-06, "regret_row": 0.00046101666521281004, "regret_any": 0.00036760777584277093, "regret_bot": 0.00021019649284426123, "value_dist": 0.8633573055267334, "value_other_env": 0.8818480968475342, "value_corner": 0.8356210589408875, "value_row": 0.8581656217575073, "value_any": 0.8818829655647278, "value_bot": 0.8584164381027222, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_16170.png", "entropy": 0.07150305807590485} +{"ts": "2026-03-20T21:15:17.006365Z", "loop": 16180, "env_steps": 9940992000, "exact_value_avg": 0.8632296323776245, "regret_dist": 0.00035102420952171087, "regret_other_env": 0.000580855121370405, "regret_corner": 6.277859483816428e-06, "regret_row": 0.0005825167754665017, "regret_any": 0.0005866552819497883, "regret_bot": 0.0002504355798009783, "value_dist": 0.8632296323776245, "value_other_env": 0.881633996963501, "value_corner": 0.8356230854988098, "value_row": 0.8580441474914551, "value_any": 0.8816639184951782, "value_bot": 0.8583762049674988, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_16180.png", "entropy": 0.07126651704311371} +{"ts": "2026-03-20T21:15:25.594128Z", "loop": 16190, "env_steps": 9947136000, "exact_value_avg": 0.8592522740364075, "regret_dist": 0.00432838499546051, "regret_other_env": 0.00719398632645607, "regret_corner": 2.9982627893332392e-05, "regret_row": 0.0026974903885275126, "regret_any": 0.007639618124812841, "regret_bot": 0.0011474655475467443, "value_dist": 0.8592522740364075, "value_other_env": 0.8750209212303162, "value_corner": 0.8355993032455444, "value_row": 0.8559291958808899, "value_any": 0.8746110200881958, "value_bot": 0.8574791550636292, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_16190.png", "entropy": 0.08056645095348358} +{"ts": "2026-03-20T21:15:34.167402Z", "loop": 16200, "env_steps": 9953280000, "exact_value_avg": 0.8629077672958374, "regret_dist": 0.0006729150773026049, "regret_other_env": 0.0011030635796487331, "regret_corner": 2.769232014543377e-05, "regret_row": 0.0012091943062841892, "regret_any": 0.0011024919804185629, "regret_bot": 0.00029405576060526073, "value_dist": 0.8629077672958374, "value_other_env": 0.8811118006706238, "value_corner": 0.8356015682220459, "value_row": 0.8574174046516418, "value_any": 0.881148099899292, "value_bot": 0.8583325743675232, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_16200.png", "entropy": 0.08216255158185959} +{"ts": "2026-03-20T21:15:42.749818Z", "loop": 16210, "env_steps": 9959424000, "exact_value_avg": 0.8625785112380981, "regret_dist": 0.001002253033220768, "regret_other_env": 0.0016289055347442627, "regret_corner": 6.227394624147564e-05, "regret_row": 0.0013677184469997883, "regret_any": 0.0016280339332297444, "regret_bot": 0.00026031912420876324, "value_dist": 0.8625785112380981, "value_other_env": 0.8805860280990601, "value_corner": 0.835567057132721, "value_row": 0.8572589159011841, "value_any": 0.8806226253509521, "value_bot": 0.8583663105964661, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_16210.png", "entropy": 0.0891745537519455} +{"ts": "2026-03-20T21:15:51.331352Z", "loop": 16220, "env_steps": 9965568000, "exact_value_avg": 0.8631893396377563, "regret_dist": 0.0003913172986358404, "regret_other_env": 0.0006321385153569281, "regret_corner": 3.008544626936782e-05, "regret_row": 0.0006610692944377661, "regret_any": 0.0006313180783763528, "regret_bot": 0.00014039187226444483, "value_dist": 0.8631893396377563, "value_other_env": 0.8815827965736389, "value_corner": 0.8355992436408997, "value_row": 0.8579655885696411, "value_any": 0.8816192746162415, "value_bot": 0.8584861755371094, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_16220.png", "entropy": 0.08197901397943497} +{"ts": "2026-03-20T21:15:59.913190Z", "loop": 16230, "env_steps": 9971712000, "exact_value_avg": 0.8634911775588989, "regret_dist": 8.946408343035728e-05, "regret_other_env": 0.00014477685908786952, "regret_corner": 6.494919944088906e-06, "regret_row": 8.468690793961287e-05, "regret_any": 0.00014624094183091074, "regret_bot": 0.00041872551082633436, "value_dist": 0.8634911775588989, "value_other_env": 0.8820700645446777, "value_corner": 0.8356228470802307, "value_row": 0.8585419058799744, "value_any": 0.8821043372154236, "value_bot": 0.8582078814506531, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_16230.png", "entropy": 0.07695797830820084} +{"ts": "2026-03-20T21:16:08.495482Z", "loop": 16240, "env_steps": 9977856000, "exact_value_avg": 0.8634834289550781, "regret_dist": 9.723291441332549e-05, "regret_other_env": 0.00015696362243033946, "regret_corner": 7.636845111846924e-06, "regret_row": 3.1518979085376486e-05, "regret_any": 0.0001582362747285515, "regret_bot": 0.0004968286957591772, "value_dist": 0.8634834289550781, "value_other_env": 0.8820579051971436, "value_corner": 0.83562171459198, "value_row": 0.8585950136184692, "value_any": 0.8820923566818237, "value_bot": 0.8581297397613525, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_16240.png", "entropy": 0.07879608869552612} +{"ts": "2026-03-20T21:16:17.077311Z", "loop": 16250, "env_steps": 9984000000, "exact_value_avg": 0.8634936809539795, "regret_dist": 8.6916537838988e-05, "regret_other_env": 0.00014252273831516504, "regret_corner": 3.5072368973487755e-06, "regret_row": 2.8245105568203144e-05, "regret_any": 0.00014342711074277759, "regret_bot": 0.0004460797063075006, "value_dist": 0.8634936809539795, "value_other_env": 0.8820723295211792, "value_corner": 0.8356257677078247, "value_row": 0.8585984110832214, "value_any": 0.882107138633728, "value_bot": 0.8581805229187012, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_16250.png", "entropy": 0.074060820043087} +{"ts": "2026-03-20T21:16:25.659862Z", "loop": 16260, "env_steps": 9990144000, "exact_value_avg": 0.8629598021507263, "regret_dist": 0.0006208818522281945, "regret_other_env": 0.0010322503512725234, "regret_corner": 3.82910184271168e-06, "regret_row": 0.00011088007886428386, "regret_any": 0.0010307313641533256, "regret_bot": 0.003927306737750769, "value_dist": 0.8629598021507263, "value_other_env": 0.8811826109886169, "value_corner": 0.8356255292892456, "value_row": 0.858515739440918, "value_any": 0.8812198042869568, "value_bot": 0.8546993136405945, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_16260.png", "entropy": 0.07050278037786484} +{"ts": "2026-03-20T21:16:34.240414Z", "loop": 16270, "env_steps": 9996288000, "exact_value_avg": 0.862179160118103, "regret_dist": 0.0014015259221196175, "regret_other_env": 0.0023349039256572723, "regret_corner": 1.458823703615053e-06, "regret_row": 9.368585779157002e-06, "regret_any": 0.002331441966816783, "regret_bot": 0.0080694779753685, "value_dist": 0.862179160118103, "value_other_env": 0.8798799514770508, "value_corner": 0.8356278538703918, "value_row": 0.8586171865463257, "value_any": 0.879919171333313, "value_bot": 0.8505571484565735, "action_probs_image_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094/action_probs/img_16270.png", "entropy": 0.06999049335718155} diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/eval.log b/control_al_0.6_g_0.98_id_94_seed_9806094/eval.log new file mode 100644 index 0000000000000000000000000000000000000000..011d092a6037a7c7b659a210548da44a58315dac --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/eval.log @@ -0,0 +1,2103 @@ +[2026-03-20T17:23:27.541441Z] Loop 0: Reg: 0.7276, AltReg: 0.7214, CorReg: 0.7369, TopReg: 0.7426, AllReg: 0.7214, BotRReg: 0.7354, OV: 0.1359, AltV: 0.1608, CorV: 0.0987, TopV: 0.1160, BotRV: 0.1232, AllV: 0.1609 +[2026-03-20T17:23:28.491625Z] Loop 1: Reg: 0.7271, AltReg: 0.7215, CorReg: 0.7355, TopReg: 0.7418, AllReg: 0.7214, BotRReg: 0.7364, OV: 0.1365, AltV: 0.1607, CorV: 0.1001, TopV: 0.1169, BotRV: 0.1222, AllV: 0.1608 +[2026-03-20T17:23:29.379967Z] Loop 2: Reg: 0.7265, AltReg: 0.7215, CorReg: 0.7341, TopReg: 0.7409, AllReg: 0.7214, BotRReg: 0.7373, OV: 0.1371, AltV: 0.1607, CorV: 0.1015, TopV: 0.1177, BotRV: 0.1213, AllV: 0.1608 +[2026-03-20T17:23:30.266832Z] Loop 3: Reg: 0.7260, AltReg: 0.7215, CorReg: 0.7327, TopReg: 0.7401, AllReg: 0.7215, BotRReg: 0.7382, OV: 0.1376, AltV: 0.1607, CorV: 0.1029, TopV: 0.1185, BotRV: 0.1205, AllV: 0.1608 +[2026-03-20T17:23:31.154638Z] Loop 4: Reg: 0.7255, AltReg: 0.7215, CorReg: 0.7313, TopReg: 0.7393, AllReg: 0.7215, BotRReg: 0.7390, OV: 0.1381, AltV: 0.1607, CorV: 0.1043, TopV: 0.1193, BotRV: 0.1196, AllV: 0.1608 +[2026-03-20T17:23:32.044040Z] Loop 5: Reg: 0.7249, AltReg: 0.7216, CorReg: 0.7300, TopReg: 0.7385, AllReg: 0.7215, BotRReg: 0.7399, OV: 0.1386, AltV: 0.1606, CorV: 0.1056, TopV: 0.1201, BotRV: 0.1188, AllV: 0.1607 +[2026-03-20T17:23:32.930876Z] Loop 6: Reg: 0.7244, AltReg: 0.7216, CorReg: 0.7286, TopReg: 0.7377, AllReg: 0.7215, BotRReg: 0.7407, OV: 0.1392, AltV: 0.1606, CorV: 0.1070, TopV: 0.1209, BotRV: 0.1179, AllV: 0.1607 +[2026-03-20T17:23:33.820307Z] Loop 7: Reg: 0.7239, AltReg: 0.7216, CorReg: 0.7272, TopReg: 0.7369, AllReg: 0.7216, BotRReg: 0.7415, OV: 0.1397, AltV: 0.1606, CorV: 0.1084, TopV: 0.1217, BotRV: 0.1171, AllV: 0.1607 +[2026-03-20T17:23:34.708060Z] Loop 8: Reg: 0.7233, AltReg: 0.7217, CorReg: 0.7258, TopReg: 0.7361, AllReg: 0.7216, BotRReg: 0.7424, OV: 0.1402, AltV: 0.1605, CorV: 0.1098, TopV: 0.1225, BotRV: 0.1163, AllV: 0.1606 +[2026-03-20T17:23:35.596193Z] Loop 9: Reg: 0.7228, AltReg: 0.7217, CorReg: 0.7244, TopReg: 0.7353, AllReg: 0.7217, BotRReg: 0.7432, OV: 0.1408, AltV: 0.1605, CorV: 0.1112, TopV: 0.1233, BotRV: 0.1154, AllV: 0.1606 +[2026-03-20T17:23:36.483194Z] Loop 10: Reg: 0.7222, AltReg: 0.7218, CorReg: 0.7229, TopReg: 0.7345, AllReg: 0.7217, BotRReg: 0.7440, OV: 0.1414, AltV: 0.1605, CorV: 0.1127, TopV: 0.1241, BotRV: 0.1146, AllV: 0.1605 +[2026-03-20T17:23:37.373608Z] Loop 11: Reg: 0.7217, AltReg: 0.7218, CorReg: 0.7214, TopReg: 0.7337, AllReg: 0.7217, BotRReg: 0.7449, OV: 0.1419, AltV: 0.1604, CorV: 0.1142, TopV: 0.1250, BotRV: 0.1137, AllV: 0.1605 +[2026-03-20T17:23:38.262646Z] Loop 12: Reg: 0.7211, AltReg: 0.7218, CorReg: 0.7199, TopReg: 0.7328, AllReg: 0.7218, BotRReg: 0.7458, OV: 0.1425, AltV: 0.1604, CorV: 0.1157, TopV: 0.1258, BotRV: 0.1129, AllV: 0.1605 +[2026-03-20T17:23:39.150505Z] Loop 13: Reg: 0.7205, AltReg: 0.7219, CorReg: 0.7183, TopReg: 0.7320, AllReg: 0.7218, BotRReg: 0.7466, OV: 0.1431, AltV: 0.1603, CorV: 0.1173, TopV: 0.1267, BotRV: 0.1120, AllV: 0.1604 +[2026-03-20T17:23:40.038714Z] Loop 14: Reg: 0.7199, AltReg: 0.7219, CorReg: 0.7167, TopReg: 0.7311, AllReg: 0.7219, BotRReg: 0.7475, OV: 0.1437, AltV: 0.1603, CorV: 0.1189, TopV: 0.1275, BotRV: 0.1112, AllV: 0.1603 +[2026-03-20T17:23:40.925771Z] Loop 15: Reg: 0.7192, AltReg: 0.7220, CorReg: 0.7150, TopReg: 0.7302, AllReg: 0.7220, BotRReg: 0.7484, OV: 0.1444, AltV: 0.1602, CorV: 0.1206, TopV: 0.1284, BotRV: 0.1103, AllV: 0.1603 +[2026-03-20T17:23:41.812185Z] Loop 16: Reg: 0.7186, AltReg: 0.7221, CorReg: 0.7133, TopReg: 0.7293, AllReg: 0.7220, BotRReg: 0.7493, OV: 0.1450, AltV: 0.1602, CorV: 0.1223, TopV: 0.1293, BotRV: 0.1094, AllV: 0.1602 +[2026-03-20T17:23:42.699158Z] Loop 17: Reg: 0.7179, AltReg: 0.7221, CorReg: 0.7116, TopReg: 0.7283, AllReg: 0.7221, BotRReg: 0.7502, OV: 0.1457, AltV: 0.1601, CorV: 0.1241, TopV: 0.1303, BotRV: 0.1084, AllV: 0.1602 +[2026-03-20T17:23:43.587091Z] Loop 18: Reg: 0.7172, AltReg: 0.7222, CorReg: 0.7097, TopReg: 0.7274, AllReg: 0.7222, BotRReg: 0.7511, OV: 0.1464, AltV: 0.1600, CorV: 0.1259, TopV: 0.1313, BotRV: 0.1075, AllV: 0.1601 +[2026-03-20T17:23:44.476386Z] Loop 19: Reg: 0.7165, AltReg: 0.7223, CorReg: 0.7078, TopReg: 0.7263, AllReg: 0.7222, BotRReg: 0.7521, OV: 0.1471, AltV: 0.1600, CorV: 0.1278, TopV: 0.1323, BotRV: 0.1065, AllV: 0.1600 +[2026-03-20T17:23:45.364994Z] Loop 20: Reg: 0.7157, AltReg: 0.7223, CorReg: 0.7059, TopReg: 0.7253, AllReg: 0.7223, BotRReg: 0.7531, OV: 0.1478, AltV: 0.1599, CorV: 0.1298, TopV: 0.1333, BotRV: 0.1055, AllV: 0.1599 +[2026-03-20T17:23:46.252286Z] Loop 21: Reg: 0.7150, AltReg: 0.7224, CorReg: 0.7038, TopReg: 0.7242, AllReg: 0.7224, BotRReg: 0.7541, OV: 0.1486, AltV: 0.1598, CorV: 0.1318, TopV: 0.1344, BotRV: 0.1045, AllV: 0.1599 +[2026-03-20T17:23:47.140846Z] Loop 22: Reg: 0.7142, AltReg: 0.7225, CorReg: 0.7016, TopReg: 0.7231, AllReg: 0.7225, BotRReg: 0.7552, OV: 0.1494, AltV: 0.1597, CorV: 0.1340, TopV: 0.1355, BotRV: 0.1035, AllV: 0.1598 +[2026-03-20T17:23:48.029214Z] Loop 23: Reg: 0.7133, AltReg: 0.7226, CorReg: 0.6994, TopReg: 0.7219, AllReg: 0.7226, BotRReg: 0.7562, OV: 0.1503, AltV: 0.1596, CorV: 0.1363, TopV: 0.1367, BotRV: 0.1024, AllV: 0.1597 +[2026-03-20T17:23:48.914453Z] Loop 24: Reg: 0.7124, AltReg: 0.7227, CorReg: 0.6970, TopReg: 0.7207, AllReg: 0.7227, BotRReg: 0.7573, OV: 0.1511, AltV: 0.1595, CorV: 0.1386, TopV: 0.1379, BotRV: 0.1013, AllV: 0.1595 +[2026-03-20T17:23:49.799727Z] Loop 25: Reg: 0.7115, AltReg: 0.7228, CorReg: 0.6945, TopReg: 0.7195, AllReg: 0.7228, BotRReg: 0.7585, OV: 0.1521, AltV: 0.1594, CorV: 0.1411, TopV: 0.1391, BotRV: 0.1001, AllV: 0.1594 +[2026-03-20T17:23:50.687775Z] Loop 26: Reg: 0.7106, AltReg: 0.7230, CorReg: 0.6919, TopReg: 0.7182, AllReg: 0.7229, BotRReg: 0.7597, OV: 0.1530, AltV: 0.1593, CorV: 0.1437, TopV: 0.1404, BotRV: 0.0990, AllV: 0.1593 +[2026-03-20T17:23:51.575438Z] Loop 27: Reg: 0.7095, AltReg: 0.7231, CorReg: 0.6892, TopReg: 0.7168, AllReg: 0.7231, BotRReg: 0.7609, OV: 0.1540, AltV: 0.1591, CorV: 0.1464, TopV: 0.1418, BotRV: 0.0978, AllV: 0.1592 +[2026-03-20T17:23:52.462217Z] Loop 28: Reg: 0.7085, AltReg: 0.7232, CorReg: 0.6863, TopReg: 0.7154, AllReg: 0.7232, BotRReg: 0.7621, OV: 0.1551, AltV: 0.1590, CorV: 0.1493, TopV: 0.1432, BotRV: 0.0965, AllV: 0.1590 +[2026-03-20T17:23:53.351059Z] Loop 29: Reg: 0.7074, AltReg: 0.7234, CorReg: 0.6833, TopReg: 0.7139, AllReg: 0.7234, BotRReg: 0.7634, OV: 0.1562, AltV: 0.1588, CorV: 0.1523, TopV: 0.1447, BotRV: 0.0952, AllV: 0.1589 +[2026-03-20T17:23:54.239984Z] Loop 30: Reg: 0.7062, AltReg: 0.7236, CorReg: 0.6801, TopReg: 0.7124, AllReg: 0.7235, BotRReg: 0.7647, OV: 0.1574, AltV: 0.1587, CorV: 0.1555, TopV: 0.1462, BotRV: 0.0939, AllV: 0.1587 +[2026-03-20T17:23:55.127268Z] Loop 31: Reg: 0.7050, AltReg: 0.7237, CorReg: 0.6768, TopReg: 0.7109, AllReg: 0.7237, BotRReg: 0.7660, OV: 0.1586, AltV: 0.1585, CorV: 0.1588, TopV: 0.1477, BotRV: 0.0926, AllV: 0.1585 +[2026-03-20T17:23:56.015399Z] Loop 32: Reg: 0.7037, AltReg: 0.7239, CorReg: 0.6734, TopReg: 0.7093, AllReg: 0.7239, BotRReg: 0.7674, OV: 0.1599, AltV: 0.1583, CorV: 0.1622, TopV: 0.1493, BotRV: 0.0913, AllV: 0.1583 +[2026-03-20T17:23:56.903045Z] Loop 33: Reg: 0.7024, AltReg: 0.7241, CorReg: 0.6699, TopReg: 0.7077, AllReg: 0.7241, BotRReg: 0.7687, OV: 0.1612, AltV: 0.1581, CorV: 0.1657, TopV: 0.1509, BotRV: 0.0899, AllV: 0.1581 +[2026-03-20T17:23:57.790926Z] Loop 34: Reg: 0.7011, AltReg: 0.7243, CorReg: 0.6662, TopReg: 0.7060, AllReg: 0.7243, BotRReg: 0.7701, OV: 0.1625, AltV: 0.1579, CorV: 0.1695, TopV: 0.1526, BotRV: 0.0885, AllV: 0.1579 +[2026-03-20T17:23:58.678966Z] Loop 35: Reg: 0.6996, AltReg: 0.7246, CorReg: 0.6622, TopReg: 0.7043, AllReg: 0.7246, BotRReg: 0.7716, OV: 0.1640, AltV: 0.1576, CorV: 0.1734, TopV: 0.1544, BotRV: 0.0870, AllV: 0.1577 +[2026-03-20T17:23:59.566457Z] Loop 36: Reg: 0.6981, AltReg: 0.7248, CorReg: 0.6580, TopReg: 0.7024, AllReg: 0.7249, BotRReg: 0.7731, OV: 0.1655, AltV: 0.1574, CorV: 0.1776, TopV: 0.1562, BotRV: 0.0855, AllV: 0.1574 +[2026-03-20T17:24:00.453712Z] Loop 37: Reg: 0.6965, AltReg: 0.7251, CorReg: 0.6535, TopReg: 0.7005, AllReg: 0.7252, BotRReg: 0.7747, OV: 0.1671, AltV: 0.1571, CorV: 0.1822, TopV: 0.1581, BotRV: 0.0840, AllV: 0.1571 +[2026-03-20T17:24:01.340554Z] Loop 38: Reg: 0.6947, AltReg: 0.7255, CorReg: 0.6487, TopReg: 0.6985, AllReg: 0.7255, BotRReg: 0.7763, OV: 0.1688, AltV: 0.1568, CorV: 0.1870, TopV: 0.1601, BotRV: 0.0823, AllV: 0.1568 +[2026-03-20T17:24:02.227511Z] Loop 39: Reg: 0.6929, AltReg: 0.7258, CorReg: 0.6436, TopReg: 0.6964, AllReg: 0.7258, BotRReg: 0.7780, OV: 0.1707, AltV: 0.1564, CorV: 0.1921, TopV: 0.1622, BotRV: 0.0806, AllV: 0.1564 +[2026-03-20T17:24:03.114839Z] Loop 40: Reg: 0.6909, AltReg: 0.7262, CorReg: 0.6380, TopReg: 0.6941, AllReg: 0.7262, BotRReg: 0.7798, OV: 0.1727, AltV: 0.1560, CorV: 0.1976, TopV: 0.1645, BotRV: 0.0789, AllV: 0.1561 +[2026-03-20T17:24:04.004352Z] Loop 41: Reg: 0.6888, AltReg: 0.7266, CorReg: 0.6320, TopReg: 0.6917, AllReg: 0.7266, BotRReg: 0.7816, OV: 0.1748, AltV: 0.1556, CorV: 0.2036, TopV: 0.1669, BotRV: 0.0770, AllV: 0.1556 +[2026-03-20T17:24:04.894027Z] Loop 42: Reg: 0.6865, AltReg: 0.7271, CorReg: 0.6256, TopReg: 0.6892, AllReg: 0.7271, BotRReg: 0.7835, OV: 0.1771, AltV: 0.1552, CorV: 0.2100, TopV: 0.1694, BotRV: 0.0751, AllV: 0.1552 +[2026-03-20T17:24:05.785220Z] Loop 43: Reg: 0.6840, AltReg: 0.7276, CorReg: 0.6186, TopReg: 0.6865, AllReg: 0.7276, BotRReg: 0.7856, OV: 0.1796, AltV: 0.1546, CorV: 0.2170, TopV: 0.1721, BotRV: 0.0731, AllV: 0.1546 +[2026-03-20T17:24:06.674225Z] Loop 44: Reg: 0.6814, AltReg: 0.7281, CorReg: 0.6112, TopReg: 0.6838, AllReg: 0.7282, BotRReg: 0.7876, OV: 0.1822, AltV: 0.1541, CorV: 0.2244, TopV: 0.1748, BotRV: 0.0710, AllV: 0.1541 +[2026-03-20T17:24:07.561505Z] Loop 45: Reg: 0.6786, AltReg: 0.7288, CorReg: 0.6033, TopReg: 0.6809, AllReg: 0.7288, BotRReg: 0.7898, OV: 0.1850, AltV: 0.1534, CorV: 0.2323, TopV: 0.1777, BotRV: 0.0688, AllV: 0.1534 +[2026-03-20T17:24:08.446744Z] Loop 46: Reg: 0.6756, AltReg: 0.7294, CorReg: 0.5949, TopReg: 0.6780, AllReg: 0.7295, BotRReg: 0.7919, OV: 0.1880, AltV: 0.1528, CorV: 0.2407, TopV: 0.1806, BotRV: 0.0667, AllV: 0.1528 +[2026-03-20T17:24:09.333217Z] Loop 47: Reg: 0.6725, AltReg: 0.7302, CorReg: 0.5859, TopReg: 0.6749, AllReg: 0.7302, BotRReg: 0.7942, OV: 0.1911, AltV: 0.1520, CorV: 0.2498, TopV: 0.1837, BotRV: 0.0645, AllV: 0.1520 +[2026-03-20T17:24:10.221535Z] Loop 48: Reg: 0.6691, AltReg: 0.7310, CorReg: 0.5763, TopReg: 0.6717, AllReg: 0.7311, BotRReg: 0.7964, OV: 0.1945, AltV: 0.1512, CorV: 0.2594, TopV: 0.1869, BotRV: 0.0622, AllV: 0.1512 +[2026-03-20T17:24:11.109663Z] Loop 49: Reg: 0.6655, AltReg: 0.7319, CorReg: 0.5660, TopReg: 0.6684, AllReg: 0.7320, BotRReg: 0.7987, OV: 0.1980, AltV: 0.1503, CorV: 0.2696, TopV: 0.1903, BotRV: 0.0599, AllV: 0.1503 +[2026-03-20T17:24:11.996972Z] Loop 50: Reg: 0.6618, AltReg: 0.7329, CorReg: 0.5552, TopReg: 0.6649, AllReg: 0.7329, BotRReg: 0.8011, OV: 0.2018, AltV: 0.1493, CorV: 0.2805, TopV: 0.1938, BotRV: 0.0575, AllV: 0.1493 +[2026-03-20T17:24:12.883477Z] Loop 51: Reg: 0.6578, AltReg: 0.7339, CorReg: 0.5436, TopReg: 0.6612, AllReg: 0.7340, BotRReg: 0.8035, OV: 0.2058, AltV: 0.1483, CorV: 0.2920, TopV: 0.1974, BotRV: 0.0551, AllV: 0.1483 +[2026-03-20T17:24:13.771406Z] Loop 52: Reg: 0.6536, AltReg: 0.7351, CorReg: 0.5313, TopReg: 0.6575, AllReg: 0.7352, BotRReg: 0.8060, OV: 0.2100, AltV: 0.1471, CorV: 0.3043, TopV: 0.2011, BotRV: 0.0526, AllV: 0.1471 +[2026-03-20T17:24:14.660329Z] Loop 53: Reg: 0.6491, AltReg: 0.7364, CorReg: 0.5182, TopReg: 0.6537, AllReg: 0.7364, BotRReg: 0.8085, OV: 0.2145, AltV: 0.1458, CorV: 0.3174, TopV: 0.2050, BotRV: 0.0502, AllV: 0.1458 +[2026-03-20T17:24:15.549027Z] Loop 54: Reg: 0.6444, AltReg: 0.7378, CorReg: 0.5043, TopReg: 0.6497, AllReg: 0.7379, BotRReg: 0.8109, OV: 0.2192, AltV: 0.1444, CorV: 0.3313, TopV: 0.2089, BotRV: 0.0477, AllV: 0.1444 +[2026-03-20T17:24:16.436766Z] Loop 55: Reg: 0.6394, AltReg: 0.7393, CorReg: 0.4895, TopReg: 0.6457, AllReg: 0.7394, BotRReg: 0.8135, OV: 0.2242, AltV: 0.1429, CorV: 0.3461, TopV: 0.2130, BotRV: 0.0452, AllV: 0.1429 +[2026-03-20T17:24:17.325273Z] Loop 56: Reg: 0.6341, AltReg: 0.7410, CorReg: 0.4737, TopReg: 0.6415, AllReg: 0.7411, BotRReg: 0.8160, OV: 0.2295, AltV: 0.1412, CorV: 0.3619, TopV: 0.2171, BotRV: 0.0427, AllV: 0.1412 +[2026-03-20T17:24:18.213310Z] Loop 57: Reg: 0.6284, AltReg: 0.7428, CorReg: 0.4568, TopReg: 0.6372, AllReg: 0.7429, BotRReg: 0.8185, OV: 0.2351, AltV: 0.1394, CorV: 0.3788, TopV: 0.2215, BotRV: 0.0401, AllV: 0.1393 +[2026-03-20T17:24:19.102157Z] Loop 58: Reg: 0.6225, AltReg: 0.7449, CorReg: 0.4390, TopReg: 0.6328, AllReg: 0.7449, BotRReg: 0.8211, OV: 0.2411, AltV: 0.1374, CorV: 0.3966, TopV: 0.2258, BotRV: 0.0376, AllV: 0.1373 +[2026-03-20T17:24:19.990368Z] Loop 59: Reg: 0.6164, AltReg: 0.7470, CorReg: 0.4205, TopReg: 0.6285, AllReg: 0.7471, BotRReg: 0.8235, OV: 0.2472, AltV: 0.1352, CorV: 0.4151, TopV: 0.2301, BotRV: 0.0351, AllV: 0.1352 +[2026-03-20T17:24:20.881651Z] Loop 60: Reg: 0.6102, AltReg: 0.7493, CorReg: 0.4015, TopReg: 0.6243, AllReg: 0.7494, BotRReg: 0.8259, OV: 0.2534, AltV: 0.1329, CorV: 0.4341, TopV: 0.2343, BotRV: 0.0327, AllV: 0.1329 +[2026-03-20T17:24:21.770498Z] Loop 61: Reg: 0.6039, AltReg: 0.7517, CorReg: 0.3823, TopReg: 0.6203, AllReg: 0.7518, BotRReg: 0.8282, OV: 0.2597, AltV: 0.1305, CorV: 0.4534, TopV: 0.2383, BotRV: 0.0305, AllV: 0.1305 +[2026-03-20T17:24:22.657882Z] Loop 62: Reg: 0.5975, AltReg: 0.7542, CorReg: 0.3625, TopReg: 0.6165, AllReg: 0.7543, BotRReg: 0.8303, OV: 0.2660, AltV: 0.1280, CorV: 0.4731, TopV: 0.2422, BotRV: 0.0283, AllV: 0.1279 +[2026-03-20T17:24:23.546969Z] Loop 63: Reg: 0.5912, AltReg: 0.7569, CorReg: 0.3426, TopReg: 0.6129, AllReg: 0.7570, BotRReg: 0.8324, OV: 0.2724, AltV: 0.1253, CorV: 0.4930, TopV: 0.2457, BotRV: 0.0262, AllV: 0.1253 +[2026-03-20T17:24:24.437782Z] Loop 64: Reg: 0.5848, AltReg: 0.7597, CorReg: 0.3225, TopReg: 0.6097, AllReg: 0.7598, BotRReg: 0.8344, OV: 0.2788, AltV: 0.1226, CorV: 0.5132, TopV: 0.2489, BotRV: 0.0243, AllV: 0.1225 +[2026-03-20T17:24:25.326637Z] Loop 65: Reg: 0.5784, AltReg: 0.7625, CorReg: 0.3023, TopReg: 0.6068, AllReg: 0.7626, BotRReg: 0.8362, OV: 0.2851, AltV: 0.1197, CorV: 0.5333, TopV: 0.2519, BotRV: 0.0224, AllV: 0.1196 +[2026-03-20T17:24:26.215677Z] Loop 66: Reg: 0.5722, AltReg: 0.7655, CorReg: 0.2823, TopReg: 0.6041, AllReg: 0.7656, BotRReg: 0.8380, OV: 0.2914, AltV: 0.1167, CorV: 0.5534, TopV: 0.2545, BotRV: 0.0207, AllV: 0.1166 +[2026-03-20T17:24:27.106157Z] Loop 67: Reg: 0.5662, AltReg: 0.7685, CorReg: 0.2626, TopReg: 0.6017, AllReg: 0.7686, BotRReg: 0.8396, OV: 0.2974, AltV: 0.1137, CorV: 0.5730, TopV: 0.2569, BotRV: 0.0190, AllV: 0.1136 +[2026-03-20T17:24:27.995598Z] Loop 68: Reg: 0.5604, AltReg: 0.7716, CorReg: 0.2437, TopReg: 0.5998, AllReg: 0.7717, BotRReg: 0.8411, OV: 0.3032, AltV: 0.1107, CorV: 0.5919, TopV: 0.2588, BotRV: 0.0175, AllV: 0.1106 +[2026-03-20T17:24:28.887152Z] Loop 69: Reg: 0.5550, AltReg: 0.7746, CorReg: 0.2257, TopReg: 0.5985, AllReg: 0.7746, BotRReg: 0.8425, OV: 0.3086, AltV: 0.1077, CorV: 0.6099, TopV: 0.2602, BotRV: 0.0162, AllV: 0.1076 +[2026-03-20T17:24:29.776267Z] Loop 70: Reg: 0.5500, AltReg: 0.7775, CorReg: 0.2089, TopReg: 0.5976, AllReg: 0.7775, BotRReg: 0.8437, OV: 0.3136, AltV: 0.1048, CorV: 0.6267, TopV: 0.2610, BotRV: 0.0149, AllV: 0.1047 +[2026-03-20T17:24:30.666075Z] Loop 71: Reg: 0.5454, AltReg: 0.7803, CorReg: 0.1932, TopReg: 0.5971, AllReg: 0.7803, BotRReg: 0.8447, OV: 0.3181, AltV: 0.1020, CorV: 0.6424, TopV: 0.2615, BotRV: 0.0139, AllV: 0.1019 +[2026-03-20T17:24:31.553760Z] Loop 72: Reg: 0.5413, AltReg: 0.7829, CorReg: 0.1788, TopReg: 0.5968, AllReg: 0.7830, BotRReg: 0.8457, OV: 0.3223, AltV: 0.0993, CorV: 0.6568, TopV: 0.2618, BotRV: 0.0129, AllV: 0.0992 +[2026-03-20T17:24:32.442027Z] Loop 73: Reg: 0.5375, AltReg: 0.7854, CorReg: 0.1657, TopReg: 0.5967, AllReg: 0.7855, BotRReg: 0.8466, OV: 0.3260, AltV: 0.0968, CorV: 0.6699, TopV: 0.2619, BotRV: 0.0120, AllV: 0.0967 +[2026-03-20T17:24:33.331696Z] Loop 74: Reg: 0.5342, AltReg: 0.7878, CorReg: 0.1537, TopReg: 0.5968, AllReg: 0.7879, BotRReg: 0.8474, OV: 0.3294, AltV: 0.0944, CorV: 0.6819, TopV: 0.2618, BotRV: 0.0113, AllV: 0.0944 +[2026-03-20T17:24:34.221090Z] Loop 75: Reg: 0.5312, AltReg: 0.7900, CorReg: 0.1430, TopReg: 0.5972, AllReg: 0.7901, BotRReg: 0.8480, OV: 0.3324, AltV: 0.0922, CorV: 0.6926, TopV: 0.2615, BotRV: 0.0106, AllV: 0.0922 +[2026-03-20T17:24:35.108258Z] Loop 76: Reg: 0.5286, AltReg: 0.7920, CorReg: 0.1336, TopReg: 0.5977, AllReg: 0.7921, BotRReg: 0.8486, OV: 0.3350, AltV: 0.0903, CorV: 0.7020, TopV: 0.2610, BotRV: 0.0100, AllV: 0.0902 +[2026-03-20T17:24:35.994433Z] Loop 77: Reg: 0.5264, AltReg: 0.7937, CorReg: 0.1253, TopReg: 0.5987, AllReg: 0.7938, BotRReg: 0.8491, OV: 0.3372, AltV: 0.0885, CorV: 0.7103, TopV: 0.2599, BotRV: 0.0096, AllV: 0.0884 +[2026-03-20T17:24:36.881987Z] Loop 78: Reg: 0.5244, AltReg: 0.7954, CorReg: 0.1179, TopReg: 0.5999, AllReg: 0.7955, BotRReg: 0.8495, OV: 0.3392, AltV: 0.0868, CorV: 0.7177, TopV: 0.2587, BotRV: 0.0092, AllV: 0.0868 +[2026-03-20T17:24:37.771472Z] Loop 79: Reg: 0.5227, AltReg: 0.7969, CorReg: 0.1114, TopReg: 0.6012, AllReg: 0.7969, BotRReg: 0.8498, OV: 0.3409, AltV: 0.0854, CorV: 0.7242, TopV: 0.2574, BotRV: 0.0088, AllV: 0.0853 +[2026-03-20T17:24:38.661651Z] Loop 80: Reg: 0.5212, AltReg: 0.7981, CorReg: 0.1059, TopReg: 0.6025, AllReg: 0.7982, BotRReg: 0.8501, OV: 0.3423, AltV: 0.0841, CorV: 0.7297, TopV: 0.2561, BotRV: 0.0086, AllV: 0.0840 +[2026-03-20T17:24:39.557474Z] Loop 81: Reg: 0.5200, AltReg: 0.7993, CorReg: 0.1010, TopReg: 0.6041, AllReg: 0.7994, BotRReg: 0.8503, OV: 0.3436, AltV: 0.0829, CorV: 0.7347, TopV: 0.2545, BotRV: 0.0083, AllV: 0.0829 +[2026-03-20T17:24:40.446667Z] Loop 82: Reg: 0.5189, AltReg: 0.8003, CorReg: 0.0967, TopReg: 0.6053, AllReg: 0.8004, BotRReg: 0.8505, OV: 0.3447, AltV: 0.0819, CorV: 0.7389, TopV: 0.2533, BotRV: 0.0081, AllV: 0.0818 +[2026-03-20T17:24:41.336051Z] Loop 83: Reg: 0.5180, AltReg: 0.8013, CorReg: 0.0930, TopReg: 0.6065, AllReg: 0.8013, BotRReg: 0.8507, OV: 0.3456, AltV: 0.0810, CorV: 0.7426, TopV: 0.2521, BotRV: 0.0079, AllV: 0.0809 +[2026-03-20T17:24:42.225749Z] Loop 84: Reg: 0.5172, AltReg: 0.8020, CorReg: 0.0900, TopReg: 0.6079, AllReg: 0.8021, BotRReg: 0.8508, OV: 0.3464, AltV: 0.0802, CorV: 0.7456, TopV: 0.2507, BotRV: 0.0078, AllV: 0.0801 +[2026-03-20T17:24:43.114654Z] Loop 85: Reg: 0.5166, AltReg: 0.8027, CorReg: 0.0874, TopReg: 0.6095, AllReg: 0.8028, BotRReg: 0.8509, OV: 0.3470, AltV: 0.0795, CorV: 0.7482, TopV: 0.2492, BotRV: 0.0077, AllV: 0.0795 +[2026-03-20T17:24:44.002877Z] Loop 86: Reg: 0.5161, AltReg: 0.8033, CorReg: 0.0853, TopReg: 0.6114, AllReg: 0.8033, BotRReg: 0.8509, OV: 0.3475, AltV: 0.0790, CorV: 0.7503, TopV: 0.2473, BotRV: 0.0077, AllV: 0.0789 +[2026-03-20T17:24:44.891654Z] Loop 87: Reg: 0.5157, AltReg: 0.8038, CorReg: 0.0835, TopReg: 0.6137, AllReg: 0.8039, BotRReg: 0.8509, OV: 0.3479, AltV: 0.0784, CorV: 0.7521, TopV: 0.2449, BotRV: 0.0077, AllV: 0.0784 +[2026-03-20T17:24:45.779412Z] Loop 88: Reg: 0.5153, AltReg: 0.8043, CorReg: 0.0819, TopReg: 0.6162, AllReg: 0.8043, BotRReg: 0.8509, OV: 0.3483, AltV: 0.0779, CorV: 0.7538, TopV: 0.2424, BotRV: 0.0077, AllV: 0.0779 +[2026-03-20T17:24:46.668026Z] Loop 89: Reg: 0.5150, AltReg: 0.8047, CorReg: 0.0803, TopReg: 0.6180, AllReg: 0.8048, BotRReg: 0.8509, OV: 0.3486, AltV: 0.0775, CorV: 0.7554, TopV: 0.2406, BotRV: 0.0077, AllV: 0.0774 +[2026-03-20T17:24:47.557573Z] Loop 90: Reg: 0.5146, AltReg: 0.8052, CorReg: 0.0788, TopReg: 0.6189, AllReg: 0.8053, BotRReg: 0.8510, OV: 0.3489, AltV: 0.0770, CorV: 0.7568, TopV: 0.2397, BotRV: 0.0076, AllV: 0.0770 +[2026-03-20T17:24:48.446437Z] Loop 91: Reg: 0.5144, AltReg: 0.8056, CorReg: 0.0776, TopReg: 0.6196, AllReg: 0.8056, BotRReg: 0.8511, OV: 0.3492, AltV: 0.0767, CorV: 0.7581, TopV: 0.2390, BotRV: 0.0075, AllV: 0.0766 +[2026-03-20T17:24:49.333406Z] Loop 92: Reg: 0.5141, AltReg: 0.8059, CorReg: 0.0764, TopReg: 0.6194, AllReg: 0.8060, BotRReg: 0.8512, OV: 0.3495, AltV: 0.0763, CorV: 0.7592, TopV: 0.2392, BotRV: 0.0074, AllV: 0.0763 +[2026-03-20T17:24:50.223507Z] Loop 93: Reg: 0.5139, AltReg: 0.8062, CorReg: 0.0754, TopReg: 0.6183, AllReg: 0.8063, BotRReg: 0.8514, OV: 0.3497, AltV: 0.0760, CorV: 0.7602, TopV: 0.2403, BotRV: 0.0072, AllV: 0.0760 +[2026-03-20T17:24:51.111910Z] Loop 94: Reg: 0.5137, AltReg: 0.8065, CorReg: 0.0746, TopReg: 0.6181, AllReg: 0.8065, BotRReg: 0.8515, OV: 0.3499, AltV: 0.0758, CorV: 0.7610, TopV: 0.2406, BotRV: 0.0071, AllV: 0.0757 +[2026-03-20T17:24:51.998784Z] Loop 95: Reg: 0.5136, AltReg: 0.8067, CorReg: 0.0739, TopReg: 0.6179, AllReg: 0.8068, BotRReg: 0.8516, OV: 0.3500, AltV: 0.0755, CorV: 0.7617, TopV: 0.2407, BotRV: 0.0070, AllV: 0.0755 +[2026-03-20T17:24:52.886845Z] Loop 96: Reg: 0.5135, AltReg: 0.8069, CorReg: 0.0733, TopReg: 0.6168, AllReg: 0.8070, BotRReg: 0.8517, OV: 0.3501, AltV: 0.0753, CorV: 0.7623, TopV: 0.2418, BotRV: 0.0069, AllV: 0.0752 +[2026-03-20T17:24:53.774066Z] Loop 97: Reg: 0.5134, AltReg: 0.8071, CorReg: 0.0729, TopReg: 0.6167, AllReg: 0.8072, BotRReg: 0.8518, OV: 0.3502, AltV: 0.0751, CorV: 0.7628, TopV: 0.2419, BotRV: 0.0068, AllV: 0.0751 +[2026-03-20T17:24:54.662868Z] Loop 98: Reg: 0.5134, AltReg: 0.8072, CorReg: 0.0725, TopReg: 0.6162, AllReg: 0.8073, BotRReg: 0.8519, OV: 0.3502, AltV: 0.0750, CorV: 0.7631, TopV: 0.2424, BotRV: 0.0068, AllV: 0.0749 +[2026-03-20T17:24:55.551815Z] Loop 99: Reg: 0.5133, AltReg: 0.8074, CorReg: 0.0721, TopReg: 0.6169, AllReg: 0.8075, BotRReg: 0.8519, OV: 0.3503, AltV: 0.0748, CorV: 0.7635, TopV: 0.2417, BotRV: 0.0068, AllV: 0.0748 +[2026-03-20T17:24:56.443710Z] Loop 100: Reg: 0.5132, AltReg: 0.8075, CorReg: 0.0718, TopReg: 0.6176, AllReg: 0.8076, BotRReg: 0.8519, OV: 0.3504, AltV: 0.0747, CorV: 0.7638, TopV: 0.2411, BotRV: 0.0068, AllV: 0.0747 +[2026-03-20T17:24:57.332163Z] Loop 101: Reg: 0.5132, AltReg: 0.8076, CorReg: 0.0715, TopReg: 0.6190, AllReg: 0.8077, BotRReg: 0.8518, OV: 0.3504, AltV: 0.0746, CorV: 0.7641, TopV: 0.2396, BotRV: 0.0068, AllV: 0.0746 +[2026-03-20T17:24:58.223249Z] Loop 102: Reg: 0.5131, AltReg: 0.8077, CorReg: 0.0713, TopReg: 0.6194, AllReg: 0.8078, BotRReg: 0.8518, OV: 0.3505, AltV: 0.0745, CorV: 0.7644, TopV: 0.2393, BotRV: 0.0068, AllV: 0.0745 +[2026-03-20T17:24:59.112046Z] Loop 103: Reg: 0.5131, AltReg: 0.8078, CorReg: 0.0711, TopReg: 0.6202, AllReg: 0.8079, BotRReg: 0.8518, OV: 0.3505, AltV: 0.0744, CorV: 0.7646, TopV: 0.2385, BotRV: 0.0068, AllV: 0.0744 +[2026-03-20T17:25:00.000765Z] Loop 104: Reg: 0.5131, AltReg: 0.8078, CorReg: 0.0709, TopReg: 0.6199, AllReg: 0.8079, BotRReg: 0.8518, OV: 0.3505, AltV: 0.0744, CorV: 0.7647, TopV: 0.2387, BotRV: 0.0068, AllV: 0.0743 +[2026-03-20T17:25:00.890101Z] Loop 105: Reg: 0.5130, AltReg: 0.8079, CorReg: 0.0707, TopReg: 0.6206, AllReg: 0.8080, BotRReg: 0.8518, OV: 0.3505, AltV: 0.0743, CorV: 0.7649, TopV: 0.2380, BotRV: 0.0068, AllV: 0.0743 +[2026-03-20T17:25:01.780822Z] Loop 106: Reg: 0.5130, AltReg: 0.8080, CorReg: 0.0706, TopReg: 0.6205, AllReg: 0.8081, BotRReg: 0.8518, OV: 0.3506, AltV: 0.0742, CorV: 0.7650, TopV: 0.2381, BotRV: 0.0068, AllV: 0.0742 +[2026-03-20T17:25:02.670368Z] Loop 107: Reg: 0.5130, AltReg: 0.8080, CorReg: 0.0704, TopReg: 0.6216, AllReg: 0.8081, BotRReg: 0.8518, OV: 0.3506, AltV: 0.0742, CorV: 0.7652, TopV: 0.2370, BotRV: 0.0068, AllV: 0.0741 +[2026-03-20T17:25:03.557197Z] Loop 108: Reg: 0.5130, AltReg: 0.8081, CorReg: 0.0702, TopReg: 0.6212, AllReg: 0.8082, BotRReg: 0.8518, OV: 0.3506, AltV: 0.0741, CorV: 0.7654, TopV: 0.2375, BotRV: 0.0068, AllV: 0.0741 +[2026-03-20T17:25:04.446159Z] Loop 109: Reg: 0.5130, AltReg: 0.8082, CorReg: 0.0701, TopReg: 0.6208, AllReg: 0.8083, BotRReg: 0.8519, OV: 0.3506, AltV: 0.0740, CorV: 0.7655, TopV: 0.2379, BotRV: 0.0067, AllV: 0.0740 +[2026-03-20T17:25:05.334549Z] Loop 110: Reg: 0.5129, AltReg: 0.8082, CorReg: 0.0700, TopReg: 0.6211, AllReg: 0.8083, BotRReg: 0.8519, OV: 0.3506, AltV: 0.0740, CorV: 0.7656, TopV: 0.2376, BotRV: 0.0067, AllV: 0.0739 +[2026-03-20T17:25:06.222977Z] Loop 111: Reg: 0.5129, AltReg: 0.8083, CorReg: 0.0699, TopReg: 0.6209, AllReg: 0.8084, BotRReg: 0.8519, OV: 0.3507, AltV: 0.0739, CorV: 0.7657, TopV: 0.2378, BotRV: 0.0067, AllV: 0.0739 +[2026-03-20T17:25:07.110739Z] Loop 112: Reg: 0.5129, AltReg: 0.8083, CorReg: 0.0698, TopReg: 0.6201, AllReg: 0.8084, BotRReg: 0.8520, OV: 0.3507, AltV: 0.0739, CorV: 0.7658, TopV: 0.2385, BotRV: 0.0067, AllV: 0.0739 +[2026-03-20T17:25:07.999137Z] Loop 113: Reg: 0.5129, AltReg: 0.8083, CorReg: 0.0698, TopReg: 0.6200, AllReg: 0.8084, BotRReg: 0.8520, OV: 0.3506, AltV: 0.0739, CorV: 0.7658, TopV: 0.2386, BotRV: 0.0066, AllV: 0.0738 +[2026-03-20T17:25:08.887752Z] Loop 114: Reg: 0.5129, AltReg: 0.8084, CorReg: 0.0697, TopReg: 0.6205, AllReg: 0.8084, BotRReg: 0.8520, OV: 0.3507, AltV: 0.0739, CorV: 0.7659, TopV: 0.2381, BotRV: 0.0067, AllV: 0.0738 +[2026-03-20T17:25:09.776321Z] Loop 115: Reg: 0.5129, AltReg: 0.8084, CorReg: 0.0697, TopReg: 0.6202, AllReg: 0.8085, BotRReg: 0.8520, OV: 0.3507, AltV: 0.0738, CorV: 0.7659, TopV: 0.2384, BotRV: 0.0066, AllV: 0.0738 +[2026-03-20T17:25:10.665199Z] Loop 116: Reg: 0.5129, AltReg: 0.8084, CorReg: 0.0697, TopReg: 0.6198, AllReg: 0.8085, BotRReg: 0.8520, OV: 0.3507, AltV: 0.0738, CorV: 0.7659, TopV: 0.2389, BotRV: 0.0066, AllV: 0.0738 +[2026-03-20T17:25:11.553950Z] Loop 117: Reg: 0.5129, AltReg: 0.8084, CorReg: 0.0697, TopReg: 0.6191, AllReg: 0.8085, BotRReg: 0.8521, OV: 0.3506, AltV: 0.0738, CorV: 0.7659, TopV: 0.2396, BotRV: 0.0066, AllV: 0.0737 +[2026-03-20T17:25:12.441026Z] Loop 118: Reg: 0.5130, AltReg: 0.8084, CorReg: 0.0698, TopReg: 0.6178, AllReg: 0.8085, BotRReg: 0.8522, OV: 0.3506, AltV: 0.0738, CorV: 0.7659, TopV: 0.2408, BotRV: 0.0065, AllV: 0.0737 +[2026-03-20T17:25:13.329354Z] Loop 119: Reg: 0.5131, AltReg: 0.8085, CorReg: 0.0700, TopReg: 0.6157, AllReg: 0.8085, BotRReg: 0.8523, OV: 0.3505, AltV: 0.0738, CorV: 0.7657, TopV: 0.2429, BotRV: 0.0063, AllV: 0.0737 +[2026-03-20T17:25:14.217920Z] Loop 120: Reg: 0.5133, AltReg: 0.8085, CorReg: 0.0704, TopReg: 0.6127, AllReg: 0.8086, BotRReg: 0.8525, OV: 0.3503, AltV: 0.0737, CorV: 0.7652, TopV: 0.2459, BotRV: 0.0062, AllV: 0.0737 +[2026-03-20T17:25:15.112442Z] Loop 121: Reg: 0.5133, AltReg: 0.8085, CorReg: 0.0705, TopReg: 0.6120, AllReg: 0.8086, BotRReg: 0.8525, OV: 0.3503, AltV: 0.0737, CorV: 0.7651, TopV: 0.2467, BotRV: 0.0061, AllV: 0.0737 +[2026-03-20T17:25:15.999857Z] Loop 122: Reg: 0.5133, AltReg: 0.8085, CorReg: 0.0704, TopReg: 0.6127, AllReg: 0.8086, BotRReg: 0.8525, OV: 0.3503, AltV: 0.0737, CorV: 0.7652, TopV: 0.2459, BotRV: 0.0062, AllV: 0.0737 +[2026-03-20T17:25:16.888793Z] Loop 123: Reg: 0.5132, AltReg: 0.8085, CorReg: 0.0703, TopReg: 0.6133, AllReg: 0.8086, BotRReg: 0.8524, OV: 0.3504, AltV: 0.0737, CorV: 0.7654, TopV: 0.2453, BotRV: 0.0062, AllV: 0.0737 +[2026-03-20T17:25:17.778257Z] Loop 124: Reg: 0.5131, AltReg: 0.8085, CorReg: 0.0700, TopReg: 0.6155, AllReg: 0.8086, BotRReg: 0.8523, OV: 0.3505, AltV: 0.0737, CorV: 0.7657, TopV: 0.2432, BotRV: 0.0063, AllV: 0.0737 +[2026-03-20T17:25:18.667693Z] Loop 125: Reg: 0.5130, AltReg: 0.8085, CorReg: 0.0697, TopReg: 0.6173, AllReg: 0.8086, BotRReg: 0.8522, OV: 0.3506, AltV: 0.0737, CorV: 0.7659, TopV: 0.2413, BotRV: 0.0064, AllV: 0.0737 +[2026-03-20T17:25:19.556831Z] Loop 126: Reg: 0.5129, AltReg: 0.8085, CorReg: 0.0696, TopReg: 0.6187, AllReg: 0.8086, BotRReg: 0.8521, OV: 0.3506, AltV: 0.0737, CorV: 0.7660, TopV: 0.2400, BotRV: 0.0065, AllV: 0.0737 +[2026-03-20T17:25:20.445278Z] Loop 127: Reg: 0.5129, AltReg: 0.8085, CorReg: 0.0694, TopReg: 0.6212, AllReg: 0.8086, BotRReg: 0.8520, OV: 0.3507, AltV: 0.0737, CorV: 0.7662, TopV: 0.2374, BotRV: 0.0067, AllV: 0.0737 +[2026-03-20T17:25:21.333965Z] Loop 128: Reg: 0.5128, AltReg: 0.8085, CorReg: 0.0693, TopReg: 0.6239, AllReg: 0.8086, BotRReg: 0.8518, OV: 0.3507, AltV: 0.0737, CorV: 0.7663, TopV: 0.2347, BotRV: 0.0068, AllV: 0.0737 +[2026-03-20T17:25:22.223932Z] Loop 129: Reg: 0.5129, AltReg: 0.8085, CorReg: 0.0694, TopReg: 0.6273, AllReg: 0.8086, BotRReg: 0.8516, OV: 0.3507, AltV: 0.0737, CorV: 0.7663, TopV: 0.2313, BotRV: 0.0070, AllV: 0.0736 +[2026-03-20T17:25:23.112939Z] Loop 130: Reg: 0.5129, AltReg: 0.8085, CorReg: 0.0694, TopReg: 0.6282, AllReg: 0.8086, BotRReg: 0.8515, OV: 0.3507, AltV: 0.0737, CorV: 0.7662, TopV: 0.2304, BotRV: 0.0071, AllV: 0.0736 +[2026-03-20T17:25:24.002277Z] Loop 131: Reg: 0.5129, AltReg: 0.8085, CorReg: 0.0694, TopReg: 0.6281, AllReg: 0.8086, BotRReg: 0.8515, OV: 0.3507, AltV: 0.0737, CorV: 0.7662, TopV: 0.2305, BotRV: 0.0071, AllV: 0.0736 +[2026-03-20T17:25:24.891733Z] Loop 132: Reg: 0.5129, AltReg: 0.8086, CorReg: 0.0693, TopReg: 0.6275, AllReg: 0.8086, BotRReg: 0.8516, OV: 0.3507, AltV: 0.0737, CorV: 0.7663, TopV: 0.2311, BotRV: 0.0070, AllV: 0.0736 +[2026-03-20T17:25:25.780594Z] Loop 133: Reg: 0.5129, AltReg: 0.8086, CorReg: 0.0694, TopReg: 0.6290, AllReg: 0.8086, BotRReg: 0.8515, OV: 0.3507, AltV: 0.0736, CorV: 0.7662, TopV: 0.2296, BotRV: 0.0071, AllV: 0.0736 +[2026-03-20T17:25:26.667898Z] Loop 134: Reg: 0.5129, AltReg: 0.8086, CorReg: 0.0694, TopReg: 0.6293, AllReg: 0.8087, BotRReg: 0.8515, OV: 0.3507, AltV: 0.0736, CorV: 0.7662, TopV: 0.2293, BotRV: 0.0071, AllV: 0.0736 +[2026-03-20T17:25:27.555482Z] Loop 135: Reg: 0.5129, AltReg: 0.8086, CorReg: 0.0695, TopReg: 0.6303, AllReg: 0.8087, BotRReg: 0.8514, OV: 0.3506, AltV: 0.0736, CorV: 0.7661, TopV: 0.2284, BotRV: 0.0072, AllV: 0.0736 +[2026-03-20T17:25:28.443511Z] Loop 136: Reg: 0.5130, AltReg: 0.8086, CorReg: 0.0695, TopReg: 0.6308, AllReg: 0.8087, BotRReg: 0.8514, OV: 0.3506, AltV: 0.0736, CorV: 0.7661, TopV: 0.2279, BotRV: 0.0072, AllV: 0.0736 +[2026-03-20T17:25:29.332785Z] Loop 137: Reg: 0.5130, AltReg: 0.8086, CorReg: 0.0695, TopReg: 0.6309, AllReg: 0.8087, BotRReg: 0.8514, OV: 0.3506, AltV: 0.0736, CorV: 0.7661, TopV: 0.2277, BotRV: 0.0072, AllV: 0.0736 +[2026-03-20T17:25:30.220689Z] Loop 138: Reg: 0.5130, AltReg: 0.8086, CorReg: 0.0695, TopReg: 0.6307, AllReg: 0.8087, BotRReg: 0.8514, OV: 0.3506, AltV: 0.0736, CorV: 0.7661, TopV: 0.2279, BotRV: 0.0072, AllV: 0.0736 +[2026-03-20T17:25:31.108421Z] Loop 139: Reg: 0.5129, AltReg: 0.8086, CorReg: 0.0694, TopReg: 0.6303, AllReg: 0.8087, BotRReg: 0.8514, OV: 0.3506, AltV: 0.0736, CorV: 0.7662, TopV: 0.2283, BotRV: 0.0072, AllV: 0.0736 +[2026-03-20T17:25:31.997253Z] Loop 140: Reg: 0.5129, AltReg: 0.8086, CorReg: 0.0694, TopReg: 0.6304, AllReg: 0.8087, BotRReg: 0.8514, OV: 0.3506, AltV: 0.0736, CorV: 0.7662, TopV: 0.2282, BotRV: 0.0072, AllV: 0.0736 +[2026-03-20T17:25:32.886041Z] Loop 141: Reg: 0.5130, AltReg: 0.8086, CorReg: 0.0695, TopReg: 0.6310, AllReg: 0.8087, BotRReg: 0.8514, OV: 0.3506, AltV: 0.0736, CorV: 0.7661, TopV: 0.2276, BotRV: 0.0072, AllV: 0.0736 +[2026-03-20T17:25:33.775512Z] Loop 142: Reg: 0.5130, AltReg: 0.8086, CorReg: 0.0695, TopReg: 0.6311, AllReg: 0.8087, BotRReg: 0.8514, OV: 0.3506, AltV: 0.0736, CorV: 0.7661, TopV: 0.2275, BotRV: 0.0073, AllV: 0.0736 +[2026-03-20T17:25:34.664800Z] Loop 143: Reg: 0.5129, AltReg: 0.8086, CorReg: 0.0694, TopReg: 0.6307, AllReg: 0.8087, BotRReg: 0.8514, OV: 0.3506, AltV: 0.0736, CorV: 0.7662, TopV: 0.2279, BotRV: 0.0072, AllV: 0.0736 +[2026-03-20T17:25:35.553403Z] Loop 144: Reg: 0.5129, AltReg: 0.8086, CorReg: 0.0694, TopReg: 0.6304, AllReg: 0.8087, BotRReg: 0.8514, OV: 0.3506, AltV: 0.0736, CorV: 0.7662, TopV: 0.2282, BotRV: 0.0072, AllV: 0.0736 +[2026-03-20T17:25:36.442567Z] Loop 145: Reg: 0.5129, AltReg: 0.8086, CorReg: 0.0693, TopReg: 0.6292, AllReg: 0.8087, BotRReg: 0.8515, OV: 0.3507, AltV: 0.0736, CorV: 0.7663, TopV: 0.2294, BotRV: 0.0071, AllV: 0.0736 +[2026-03-20T17:25:37.332842Z] Loop 146: Reg: 0.5129, AltReg: 0.8086, CorReg: 0.0693, TopReg: 0.6279, AllReg: 0.8087, BotRReg: 0.8516, OV: 0.3507, AltV: 0.0736, CorV: 0.7664, TopV: 0.2307, BotRV: 0.0070, AllV: 0.0736 +[2026-03-20T17:25:38.223130Z] Loop 147: Reg: 0.5128, AltReg: 0.8086, CorReg: 0.0692, TopReg: 0.6261, AllReg: 0.8087, BotRReg: 0.8517, OV: 0.3508, AltV: 0.0736, CorV: 0.7664, TopV: 0.2326, BotRV: 0.0069, AllV: 0.0736 +[2026-03-20T17:25:39.112774Z] Loop 148: Reg: 0.5128, AltReg: 0.8086, CorReg: 0.0692, TopReg: 0.6237, AllReg: 0.8086, BotRReg: 0.8518, OV: 0.3508, AltV: 0.0736, CorV: 0.7664, TopV: 0.2350, BotRV: 0.0068, AllV: 0.0736 +[2026-03-20T17:25:40.003403Z] Loop 149: Reg: 0.5128, AltReg: 0.8086, CorReg: 0.0692, TopReg: 0.6226, AllReg: 0.8086, BotRReg: 0.8519, OV: 0.3508, AltV: 0.0737, CorV: 0.7664, TopV: 0.2361, BotRV: 0.0067, AllV: 0.0736 +[2026-03-20T17:25:40.894008Z] Loop 150: Reg: 0.5129, AltReg: 0.8086, CorReg: 0.0693, TopReg: 0.6205, AllReg: 0.8086, BotRReg: 0.8520, OV: 0.3507, AltV: 0.0737, CorV: 0.7663, TopV: 0.2381, BotRV: 0.0066, AllV: 0.0736 +[2026-03-20T17:25:41.783539Z] Loop 151: Reg: 0.5129, AltReg: 0.8086, CorReg: 0.0694, TopReg: 0.6195, AllReg: 0.8086, BotRReg: 0.8521, OV: 0.3507, AltV: 0.0737, CorV: 0.7662, TopV: 0.2391, BotRV: 0.0065, AllV: 0.0736 +[2026-03-20T17:25:42.672500Z] Loop 152: Reg: 0.5129, AltReg: 0.8086, CorReg: 0.0694, TopReg: 0.6193, AllReg: 0.8086, BotRReg: 0.8521, OV: 0.3507, AltV: 0.0737, CorV: 0.7662, TopV: 0.2393, BotRV: 0.0065, AllV: 0.0736 +[2026-03-20T17:25:43.561691Z] Loop 153: Reg: 0.5129, AltReg: 0.8086, CorReg: 0.0694, TopReg: 0.6194, AllReg: 0.8086, BotRReg: 0.8521, OV: 0.3507, AltV: 0.0737, CorV: 0.7662, TopV: 0.2392, BotRV: 0.0065, AllV: 0.0736 +[2026-03-20T17:25:44.451088Z] Loop 154: Reg: 0.5129, AltReg: 0.8086, CorReg: 0.0693, TopReg: 0.6203, AllReg: 0.8086, BotRReg: 0.8520, OV: 0.3507, AltV: 0.0737, CorV: 0.7663, TopV: 0.2384, BotRV: 0.0066, AllV: 0.0736 +[2026-03-20T17:25:45.342280Z] Loop 155: Reg: 0.5128, AltReg: 0.8086, CorReg: 0.0693, TopReg: 0.6214, AllReg: 0.8086, BotRReg: 0.8520, OV: 0.3507, AltV: 0.0737, CorV: 0.7664, TopV: 0.2372, BotRV: 0.0067, AllV: 0.0736 +[2026-03-20T17:25:46.232518Z] Loop 156: Reg: 0.5128, AltReg: 0.8086, CorReg: 0.0692, TopReg: 0.6235, AllReg: 0.8086, BotRReg: 0.8519, OV: 0.3508, AltV: 0.0736, CorV: 0.7664, TopV: 0.2352, BotRV: 0.0068, AllV: 0.0736 +[2026-03-20T17:25:47.122390Z] Loop 157: Reg: 0.5128, AltReg: 0.8086, CorReg: 0.0692, TopReg: 0.6231, AllReg: 0.8086, BotRReg: 0.8519, OV: 0.3508, AltV: 0.0737, CorV: 0.7664, TopV: 0.2355, BotRV: 0.0068, AllV: 0.0736 +[2026-03-20T17:25:48.011230Z] Loop 158: Reg: 0.5128, AltReg: 0.8086, CorReg: 0.0692, TopReg: 0.6240, AllReg: 0.8086, BotRReg: 0.8518, OV: 0.3508, AltV: 0.0736, CorV: 0.7665, TopV: 0.2346, BotRV: 0.0068, AllV: 0.0736 +[2026-03-20T17:25:48.899893Z] Loop 159: Reg: 0.5128, AltReg: 0.8086, CorReg: 0.0692, TopReg: 0.6264, AllReg: 0.8087, BotRReg: 0.8517, OV: 0.3508, AltV: 0.0736, CorV: 0.7664, TopV: 0.2322, BotRV: 0.0070, AllV: 0.0736 +[2026-03-20T17:25:49.788937Z] Loop 160: Reg: 0.5129, AltReg: 0.8086, CorReg: 0.0693, TopReg: 0.6286, AllReg: 0.8087, BotRReg: 0.8515, OV: 0.3507, AltV: 0.0736, CorV: 0.7663, TopV: 0.2300, BotRV: 0.0071, AllV: 0.0736 +[2026-03-20T17:25:50.677566Z] Loop 161: Reg: 0.5129, AltReg: 0.8086, CorReg: 0.0694, TopReg: 0.6302, AllReg: 0.8087, BotRReg: 0.8514, OV: 0.3507, AltV: 0.0736, CorV: 0.7663, TopV: 0.2285, BotRV: 0.0072, AllV: 0.0736 +[2026-03-20T17:25:51.567481Z] Loop 162: Reg: 0.5130, AltReg: 0.8086, CorReg: 0.0695, TopReg: 0.6317, AllReg: 0.8087, BotRReg: 0.8513, OV: 0.3506, AltV: 0.0736, CorV: 0.7661, TopV: 0.2270, BotRV: 0.0073, AllV: 0.0735 +[2026-03-20T17:25:52.457179Z] Loop 163: Reg: 0.5130, AltReg: 0.8086, CorReg: 0.0696, TopReg: 0.6330, AllReg: 0.8087, BotRReg: 0.8513, OV: 0.3505, AltV: 0.0736, CorV: 0.7660, TopV: 0.2257, BotRV: 0.0074, AllV: 0.0735 +[2026-03-20T17:25:53.345064Z] Loop 164: Reg: 0.5131, AltReg: 0.8087, CorReg: 0.0698, TopReg: 0.6340, AllReg: 0.8087, BotRReg: 0.8512, OV: 0.3505, AltV: 0.0736, CorV: 0.7659, TopV: 0.2246, BotRV: 0.0074, AllV: 0.0735 +[2026-03-20T17:25:54.231144Z] Loop 165: Reg: 0.5131, AltReg: 0.8087, CorReg: 0.0697, TopReg: 0.6339, AllReg: 0.8087, BotRReg: 0.8512, OV: 0.3505, AltV: 0.0735, CorV: 0.7659, TopV: 0.2247, BotRV: 0.0074, AllV: 0.0735 +[2026-03-20T17:25:55.120625Z] Loop 166: Reg: 0.5130, AltReg: 0.8087, CorReg: 0.0696, TopReg: 0.6330, AllReg: 0.8087, BotRReg: 0.8513, OV: 0.3505, AltV: 0.0736, CorV: 0.7660, TopV: 0.2256, BotRV: 0.0074, AllV: 0.0735 +[2026-03-20T17:25:56.008795Z] Loop 167: Reg: 0.5130, AltReg: 0.8087, CorReg: 0.0695, TopReg: 0.6322, AllReg: 0.8087, BotRReg: 0.8513, OV: 0.3506, AltV: 0.0736, CorV: 0.7661, TopV: 0.2264, BotRV: 0.0073, AllV: 0.0735 +[2026-03-20T17:25:56.899739Z] Loop 168: Reg: 0.5129, AltReg: 0.8086, CorReg: 0.0693, TopReg: 0.6306, AllReg: 0.8087, BotRReg: 0.8514, OV: 0.3507, AltV: 0.0736, CorV: 0.7663, TopV: 0.2281, BotRV: 0.0072, AllV: 0.0735 +[2026-03-20T17:25:57.789301Z] Loop 169: Reg: 0.5129, AltReg: 0.8086, CorReg: 0.0692, TopReg: 0.6290, AllReg: 0.8087, BotRReg: 0.8515, OV: 0.3507, AltV: 0.0736, CorV: 0.7664, TopV: 0.2297, BotRV: 0.0071, AllV: 0.0735 +[2026-03-20T17:25:58.679457Z] Loop 170: Reg: 0.5128, AltReg: 0.8086, CorReg: 0.0692, TopReg: 0.6282, AllReg: 0.8087, BotRReg: 0.8516, OV: 0.3507, AltV: 0.0736, CorV: 0.7665, TopV: 0.2304, BotRV: 0.0071, AllV: 0.0735 +[2026-03-20T17:25:59.567467Z] Loop 171: Reg: 0.5128, AltReg: 0.8086, CorReg: 0.0691, TopReg: 0.6273, AllReg: 0.8087, BotRReg: 0.8516, OV: 0.3508, AltV: 0.0736, CorV: 0.7665, TopV: 0.2313, BotRV: 0.0070, AllV: 0.0735 +[2026-03-20T17:26:00.457472Z] Loop 172: Reg: 0.5128, AltReg: 0.8086, CorReg: 0.0691, TopReg: 0.6248, AllReg: 0.8087, BotRReg: 0.8518, OV: 0.3508, AltV: 0.0736, CorV: 0.7666, TopV: 0.2339, BotRV: 0.0068, AllV: 0.0736 +[2026-03-20T17:26:01.347989Z] Loop 173: Reg: 0.5128, AltReg: 0.8086, CorReg: 0.0691, TopReg: 0.6214, AllReg: 0.8087, BotRReg: 0.8520, OV: 0.3508, AltV: 0.0736, CorV: 0.7665, TopV: 0.2372, BotRV: 0.0066, AllV: 0.0736 +[2026-03-20T17:26:02.237702Z] Loop 174: Reg: 0.5129, AltReg: 0.8086, CorReg: 0.0693, TopReg: 0.6185, AllReg: 0.8087, BotRReg: 0.8522, OV: 0.3507, AltV: 0.0736, CorV: 0.7663, TopV: 0.2401, BotRV: 0.0065, AllV: 0.0736 +[2026-03-20T17:26:03.126438Z] Loop 175: Reg: 0.5131, AltReg: 0.8086, CorReg: 0.0698, TopReg: 0.6145, AllReg: 0.8087, BotRReg: 0.8524, OV: 0.3505, AltV: 0.0736, CorV: 0.7658, TopV: 0.2441, BotRV: 0.0062, AllV: 0.0736 +[2026-03-20T17:26:04.016052Z] Loop 176: Reg: 0.5134, AltReg: 0.8086, CorReg: 0.0706, TopReg: 0.6104, AllReg: 0.8087, BotRReg: 0.8526, OV: 0.3502, AltV: 0.0736, CorV: 0.7650, TopV: 0.2482, BotRV: 0.0060, AllV: 0.0735 +[2026-03-20T17:26:04.906896Z] Loop 177: Reg: 0.5139, AltReg: 0.8087, CorReg: 0.0718, TopReg: 0.6057, AllReg: 0.8087, BotRReg: 0.8529, OV: 0.3496, AltV: 0.0735, CorV: 0.7638, TopV: 0.2530, BotRV: 0.0058, AllV: 0.0735 +[2026-03-20T17:26:05.797574Z] Loop 178: Reg: 0.5143, AltReg: 0.8087, CorReg: 0.0726, TopReg: 0.6032, AllReg: 0.8088, BotRReg: 0.8530, OV: 0.3493, AltV: 0.0735, CorV: 0.7630, TopV: 0.2555, BotRV: 0.0056, AllV: 0.0735 +[2026-03-20T17:26:06.688038Z] Loop 179: Reg: 0.5145, AltReg: 0.8087, CorReg: 0.0731, TopReg: 0.6018, AllReg: 0.8088, BotRReg: 0.8531, OV: 0.3491, AltV: 0.0735, CorV: 0.7625, TopV: 0.2568, BotRV: 0.0055, AllV: 0.0735 +[2026-03-20T17:26:07.579518Z] Loop 180: Reg: 0.5145, AltReg: 0.8087, CorReg: 0.0732, TopReg: 0.6015, AllReg: 0.8088, BotRReg: 0.8531, OV: 0.3491, AltV: 0.0735, CorV: 0.7624, TopV: 0.2571, BotRV: 0.0055, AllV: 0.0735 +[2026-03-20T17:26:08.471497Z] Loop 181: Reg: 0.5146, AltReg: 0.8087, CorReg: 0.0734, TopReg: 0.6011, AllReg: 0.8088, BotRReg: 0.8531, OV: 0.3490, AltV: 0.0735, CorV: 0.7623, TopV: 0.2575, BotRV: 0.0055, AllV: 0.0735 +[2026-03-20T17:26:09.361626Z] Loop 182: Reg: 0.5143, AltReg: 0.8087, CorReg: 0.0726, TopReg: 0.6033, AllReg: 0.8088, BotRReg: 0.8530, OV: 0.3493, AltV: 0.0735, CorV: 0.7630, TopV: 0.2553, BotRV: 0.0056, AllV: 0.0735 +[2026-03-20T17:26:10.251699Z] Loop 183: Reg: 0.5137, AltReg: 0.8087, CorReg: 0.0712, TopReg: 0.6078, AllReg: 0.8087, BotRReg: 0.8528, OV: 0.3499, AltV: 0.0736, CorV: 0.7644, TopV: 0.2509, BotRV: 0.0059, AllV: 0.0735 +[2026-03-20T17:26:11.142932Z] Loop 184: Reg: 0.5132, AltReg: 0.8086, CorReg: 0.0701, TopReg: 0.6128, AllReg: 0.8087, BotRReg: 0.8525, OV: 0.3503, AltV: 0.0736, CorV: 0.7655, TopV: 0.2458, BotRV: 0.0061, AllV: 0.0735 +[2026-03-20T17:26:12.031624Z] Loop 185: Reg: 0.5129, AltReg: 0.8086, CorReg: 0.0694, TopReg: 0.6180, AllReg: 0.8087, BotRReg: 0.8522, OV: 0.3507, AltV: 0.0736, CorV: 0.7663, TopV: 0.2406, BotRV: 0.0064, AllV: 0.0735 +[2026-03-20T17:26:12.920490Z] Loop 186: Reg: 0.5128, AltReg: 0.8086, CorReg: 0.0690, TopReg: 0.6232, AllReg: 0.8087, BotRReg: 0.8519, OV: 0.3508, AltV: 0.0736, CorV: 0.7666, TopV: 0.2354, BotRV: 0.0067, AllV: 0.0735 +[2026-03-20T17:26:13.810909Z] Loop 187: Reg: 0.5128, AltReg: 0.8086, CorReg: 0.0690, TopReg: 0.6266, AllReg: 0.8087, BotRReg: 0.8517, OV: 0.3508, AltV: 0.0736, CorV: 0.7666, TopV: 0.2321, BotRV: 0.0069, AllV: 0.0735 +[2026-03-20T17:26:14.702100Z] Loop 188: Reg: 0.5129, AltReg: 0.8087, CorReg: 0.0692, TopReg: 0.6295, AllReg: 0.8087, BotRReg: 0.8515, OV: 0.3507, AltV: 0.0736, CorV: 0.7664, TopV: 0.2292, BotRV: 0.0071, AllV: 0.0735 +[2026-03-20T17:26:15.591585Z] Loop 189: Reg: 0.5130, AltReg: 0.8087, CorReg: 0.0695, TopReg: 0.6328, AllReg: 0.8088, BotRReg: 0.8513, OV: 0.3506, AltV: 0.0735, CorV: 0.7661, TopV: 0.2258, BotRV: 0.0073, AllV: 0.0735 +[2026-03-20T17:26:16.480276Z] Loop 190: Reg: 0.5132, AltReg: 0.8087, CorReg: 0.0699, TopReg: 0.6357, AllReg: 0.8088, BotRReg: 0.8511, OV: 0.3504, AltV: 0.0735, CorV: 0.7657, TopV: 0.2229, BotRV: 0.0075, AllV: 0.0735 +[2026-03-20T17:26:17.368374Z] Loop 191: Reg: 0.5133, AltReg: 0.8087, CorReg: 0.0702, TopReg: 0.6371, AllReg: 0.8088, BotRReg: 0.8510, OV: 0.3503, AltV: 0.0735, CorV: 0.7655, TopV: 0.2215, BotRV: 0.0076, AllV: 0.0734 +[2026-03-20T17:26:18.257565Z] Loop 192: Reg: 0.5133, AltReg: 0.8087, CorReg: 0.0701, TopReg: 0.6370, AllReg: 0.8088, BotRReg: 0.8510, OV: 0.3503, AltV: 0.0735, CorV: 0.7655, TopV: 0.2216, BotRV: 0.0076, AllV: 0.0734 +[2026-03-20T17:26:19.146814Z] Loop 193: Reg: 0.5132, AltReg: 0.8087, CorReg: 0.0700, TopReg: 0.6365, AllReg: 0.8088, BotRReg: 0.8511, OV: 0.3503, AltV: 0.0735, CorV: 0.7657, TopV: 0.2221, BotRV: 0.0076, AllV: 0.0734 +[2026-03-20T17:26:20.037850Z] Loop 194: Reg: 0.5131, AltReg: 0.8087, CorReg: 0.0697, TopReg: 0.6350, AllReg: 0.8088, BotRReg: 0.8512, OV: 0.3505, AltV: 0.0735, CorV: 0.7660, TopV: 0.2237, BotRV: 0.0075, AllV: 0.0734 +[2026-03-20T17:26:20.927443Z] Loop 195: Reg: 0.5129, AltReg: 0.8087, CorReg: 0.0692, TopReg: 0.6316, AllReg: 0.8088, BotRReg: 0.8514, OV: 0.3507, AltV: 0.0735, CorV: 0.7664, TopV: 0.2270, BotRV: 0.0072, AllV: 0.0734 +[2026-03-20T17:26:21.817898Z] Loop 196: Reg: 0.5128, AltReg: 0.8087, CorReg: 0.0689, TopReg: 0.6268, AllReg: 0.8088, BotRReg: 0.8517, OV: 0.3508, AltV: 0.0735, CorV: 0.7667, TopV: 0.2318, BotRV: 0.0069, AllV: 0.0735 +[2026-03-20T17:26:22.708630Z] Loop 197: Reg: 0.5128, AltReg: 0.8087, CorReg: 0.0689, TopReg: 0.6222, AllReg: 0.8088, BotRReg: 0.8520, OV: 0.3508, AltV: 0.0735, CorV: 0.7667, TopV: 0.2364, BotRV: 0.0066, AllV: 0.0735 +[2026-03-20T17:26:23.600020Z] Loop 198: Reg: 0.5129, AltReg: 0.8087, CorReg: 0.0692, TopReg: 0.6181, AllReg: 0.8088, BotRReg: 0.8522, OV: 0.3507, AltV: 0.0735, CorV: 0.7664, TopV: 0.2406, BotRV: 0.0064, AllV: 0.0734 +[2026-03-20T17:26:24.489460Z] Loop 199: Reg: 0.5131, AltReg: 0.8087, CorReg: 0.0696, TopReg: 0.6147, AllReg: 0.8088, BotRReg: 0.8524, OV: 0.3505, AltV: 0.0735, CorV: 0.7660, TopV: 0.2439, BotRV: 0.0062, AllV: 0.0734 +[2026-03-20T17:26:25.377973Z] Loop 200: Reg: 0.5133, AltReg: 0.8088, CorReg: 0.0700, TopReg: 0.6122, AllReg: 0.8088, BotRReg: 0.8526, OV: 0.3503, AltV: 0.0735, CorV: 0.7656, TopV: 0.2464, BotRV: 0.0061, AllV: 0.0734 +[2026-03-20T17:26:26.265908Z] Loop 201: Reg: 0.5135, AltReg: 0.8088, CorReg: 0.0705, TopReg: 0.6099, AllReg: 0.8089, BotRReg: 0.8527, OV: 0.3501, AltV: 0.0734, CorV: 0.7651, TopV: 0.2487, BotRV: 0.0059, AllV: 0.0734 +[2026-03-20T17:26:27.154834Z] Loop 202: Reg: 0.5136, AltReg: 0.8088, CorReg: 0.0707, TopReg: 0.6090, AllReg: 0.8089, BotRReg: 0.8527, OV: 0.3500, AltV: 0.0734, CorV: 0.7649, TopV: 0.2497, BotRV: 0.0059, AllV: 0.0734 +[2026-03-20T17:26:28.045999Z] Loop 203: Reg: 0.5137, AltReg: 0.8088, CorReg: 0.0711, TopReg: 0.6076, AllReg: 0.8089, BotRReg: 0.8528, OV: 0.3498, AltV: 0.0734, CorV: 0.7645, TopV: 0.2510, BotRV: 0.0058, AllV: 0.0733 +[2026-03-20T17:26:28.935388Z] Loop 204: Reg: 0.5138, AltReg: 0.8088, CorReg: 0.0711, TopReg: 0.6074, AllReg: 0.8089, BotRReg: 0.8528, OV: 0.3498, AltV: 0.0734, CorV: 0.7645, TopV: 0.2512, BotRV: 0.0058, AllV: 0.0733 +[2026-03-20T17:26:29.824995Z] Loop 205: Reg: 0.5137, AltReg: 0.8088, CorReg: 0.0709, TopReg: 0.6083, AllReg: 0.8089, BotRReg: 0.8528, OV: 0.3499, AltV: 0.0734, CorV: 0.7648, TopV: 0.2503, BotRV: 0.0058, AllV: 0.0733 +[2026-03-20T17:26:30.715725Z] Loop 206: Reg: 0.5135, AltReg: 0.8089, CorReg: 0.0705, TopReg: 0.6096, AllReg: 0.8089, BotRReg: 0.8527, OV: 0.3501, AltV: 0.0734, CorV: 0.7651, TopV: 0.2490, BotRV: 0.0059, AllV: 0.0733 +[2026-03-20T17:26:31.605967Z] Loop 207: Reg: 0.5133, AltReg: 0.8089, CorReg: 0.0699, TopReg: 0.6126, AllReg: 0.8089, BotRReg: 0.8526, OV: 0.3503, AltV: 0.0734, CorV: 0.7658, TopV: 0.2460, BotRV: 0.0061, AllV: 0.0733 +[2026-03-20T17:26:32.495535Z] Loop 208: Reg: 0.5130, AltReg: 0.8089, CorReg: 0.0692, TopReg: 0.6163, AllReg: 0.8089, BotRReg: 0.8524, OV: 0.3506, AltV: 0.0734, CorV: 0.7664, TopV: 0.2423, BotRV: 0.0063, AllV: 0.0733 +[2026-03-20T17:26:33.385672Z] Loop 209: Reg: 0.5128, AltReg: 0.8089, CorReg: 0.0688, TopReg: 0.6197, AllReg: 0.8089, BotRReg: 0.8522, OV: 0.3507, AltV: 0.0733, CorV: 0.7668, TopV: 0.2389, BotRV: 0.0065, AllV: 0.0733 +[2026-03-20T17:26:34.274144Z] Loop 210: Reg: 0.5127, AltReg: 0.8089, CorReg: 0.0685, TopReg: 0.6236, AllReg: 0.8090, BotRReg: 0.8519, OV: 0.3508, AltV: 0.0733, CorV: 0.7671, TopV: 0.2351, BotRV: 0.0067, AllV: 0.0733 +[2026-03-20T17:26:35.161741Z] Loop 211: Reg: 0.5127, AltReg: 0.8089, CorReg: 0.0685, TopReg: 0.6258, AllReg: 0.8090, BotRReg: 0.8518, OV: 0.3509, AltV: 0.0733, CorV: 0.7672, TopV: 0.2328, BotRV: 0.0068, AllV: 0.0733 +[2026-03-20T17:26:36.052623Z] Loop 212: Reg: 0.5127, AltReg: 0.8089, CorReg: 0.0685, TopReg: 0.6276, AllReg: 0.8090, BotRReg: 0.8517, OV: 0.3508, AltV: 0.0733, CorV: 0.7672, TopV: 0.2310, BotRV: 0.0069, AllV: 0.0733 +[2026-03-20T17:26:36.944530Z] Loop 213: Reg: 0.5128, AltReg: 0.8089, CorReg: 0.0685, TopReg: 0.6291, AllReg: 0.8090, BotRReg: 0.8516, OV: 0.3508, AltV: 0.0733, CorV: 0.7671, TopV: 0.2295, BotRV: 0.0070, AllV: 0.0732 +[2026-03-20T17:26:37.836126Z] Loop 214: Reg: 0.5128, AltReg: 0.8089, CorReg: 0.0686, TopReg: 0.6302, AllReg: 0.8090, BotRReg: 0.8516, OV: 0.3508, AltV: 0.0733, CorV: 0.7671, TopV: 0.2284, BotRV: 0.0071, AllV: 0.0732 +[2026-03-20T17:26:38.726676Z] Loop 215: Reg: 0.5128, AltReg: 0.8089, CorReg: 0.0686, TopReg: 0.6308, AllReg: 0.8090, BotRReg: 0.8515, OV: 0.3508, AltV: 0.0733, CorV: 0.7671, TopV: 0.2279, BotRV: 0.0071, AllV: 0.0732 +[2026-03-20T17:26:39.617535Z] Loop 216: Reg: 0.5128, AltReg: 0.8089, CorReg: 0.0685, TopReg: 0.6301, AllReg: 0.8090, BotRReg: 0.8516, OV: 0.3508, AltV: 0.0733, CorV: 0.7671, TopV: 0.2285, BotRV: 0.0071, AllV: 0.0732 +[2026-03-20T17:26:40.506731Z] Loop 217: Reg: 0.5128, AltReg: 0.8090, CorReg: 0.0685, TopReg: 0.6299, AllReg: 0.8090, BotRReg: 0.8516, OV: 0.3508, AltV: 0.0733, CorV: 0.7671, TopV: 0.2287, BotRV: 0.0070, AllV: 0.0732 +[2026-03-20T17:26:41.396629Z] Loop 218: Reg: 0.5127, AltReg: 0.8090, CorReg: 0.0684, TopReg: 0.6285, AllReg: 0.8090, BotRReg: 0.8517, OV: 0.3508, AltV: 0.0733, CorV: 0.7672, TopV: 0.2301, BotRV: 0.0070, AllV: 0.0732 +[2026-03-20T17:26:42.284777Z] Loop 219: Reg: 0.5127, AltReg: 0.8090, CorReg: 0.0684, TopReg: 0.6288, AllReg: 0.8090, BotRReg: 0.8517, OV: 0.3508, AltV: 0.0733, CorV: 0.7672, TopV: 0.2298, BotRV: 0.0070, AllV: 0.0732 +[2026-03-20T17:26:43.175200Z] Loop 220: Reg: 0.5128, AltReg: 0.8090, CorReg: 0.0685, TopReg: 0.6300, AllReg: 0.8090, BotRReg: 0.8516, OV: 0.3508, AltV: 0.0732, CorV: 0.7672, TopV: 0.2287, BotRV: 0.0070, AllV: 0.0732 +[2026-03-20T17:26:44.064294Z] Loop 221: Reg: 0.5128, AltReg: 0.8090, CorReg: 0.0684, TopReg: 0.6295, AllReg: 0.8090, BotRReg: 0.8516, OV: 0.3508, AltV: 0.0732, CorV: 0.7672, TopV: 0.2291, BotRV: 0.0070, AllV: 0.0732 +[2026-03-20T17:26:44.953750Z] Loop 222: Reg: 0.5127, AltReg: 0.8090, CorReg: 0.0684, TopReg: 0.6282, AllReg: 0.8090, BotRReg: 0.8517, OV: 0.3509, AltV: 0.0733, CorV: 0.7673, TopV: 0.2305, BotRV: 0.0069, AllV: 0.0732 +[2026-03-20T17:26:45.841303Z] Loop 223: Reg: 0.5127, AltReg: 0.8090, CorReg: 0.0684, TopReg: 0.6281, AllReg: 0.8090, BotRReg: 0.8517, OV: 0.3509, AltV: 0.0732, CorV: 0.7673, TopV: 0.2305, BotRV: 0.0069, AllV: 0.0732 +[2026-03-20T17:26:46.730773Z] Loop 224: Reg: 0.5127, AltReg: 0.8090, CorReg: 0.0684, TopReg: 0.6289, AllReg: 0.8090, BotRReg: 0.8517, OV: 0.3508, AltV: 0.0732, CorV: 0.7672, TopV: 0.2297, BotRV: 0.0070, AllV: 0.0732 +[2026-03-20T17:26:47.619181Z] Loop 225: Reg: 0.5127, AltReg: 0.8090, CorReg: 0.0684, TopReg: 0.6293, AllReg: 0.8090, BotRReg: 0.8516, OV: 0.3508, AltV: 0.0732, CorV: 0.7672, TopV: 0.2293, BotRV: 0.0070, AllV: 0.0732 +[2026-03-20T17:26:48.508051Z] Loop 226: Reg: 0.5127, AltReg: 0.8090, CorReg: 0.0684, TopReg: 0.6285, AllReg: 0.8090, BotRReg: 0.8517, OV: 0.3508, AltV: 0.0733, CorV: 0.7672, TopV: 0.2301, BotRV: 0.0070, AllV: 0.0732 +[2026-03-20T17:26:49.395618Z] Loop 227: Reg: 0.5127, AltReg: 0.8090, CorReg: 0.0683, TopReg: 0.6262, AllReg: 0.8090, BotRReg: 0.8518, OV: 0.3509, AltV: 0.0733, CorV: 0.7673, TopV: 0.2324, BotRV: 0.0068, AllV: 0.0732 +[2026-03-20T17:26:50.285552Z] Loop 228: Reg: 0.5127, AltReg: 0.8089, CorReg: 0.0684, TopReg: 0.6242, AllReg: 0.8090, BotRReg: 0.8519, OV: 0.3509, AltV: 0.0733, CorV: 0.7673, TopV: 0.2345, BotRV: 0.0067, AllV: 0.0732 +[2026-03-20T17:26:51.174495Z] Loop 229: Reg: 0.5128, AltReg: 0.8089, CorReg: 0.0685, TopReg: 0.6219, AllReg: 0.8090, BotRReg: 0.8521, OV: 0.3508, AltV: 0.0733, CorV: 0.7671, TopV: 0.2367, BotRV: 0.0066, AllV: 0.0732 +[2026-03-20T17:26:52.063540Z] Loop 230: Reg: 0.5129, AltReg: 0.8089, CorReg: 0.0687, TopReg: 0.6191, AllReg: 0.8090, BotRReg: 0.8522, OV: 0.3507, AltV: 0.0733, CorV: 0.7669, TopV: 0.2395, BotRV: 0.0064, AllV: 0.0732 +[2026-03-20T17:26:52.952806Z] Loop 231: Reg: 0.5130, AltReg: 0.8090, CorReg: 0.0690, TopReg: 0.6169, AllReg: 0.8090, BotRReg: 0.8524, OV: 0.3506, AltV: 0.0733, CorV: 0.7667, TopV: 0.2417, BotRV: 0.0063, AllV: 0.0732 +[2026-03-20T17:26:53.841802Z] Loop 232: Reg: 0.5129, AltReg: 0.8090, CorReg: 0.0689, TopReg: 0.6172, AllReg: 0.8090, BotRReg: 0.8523, OV: 0.3506, AltV: 0.0733, CorV: 0.7667, TopV: 0.2415, BotRV: 0.0063, AllV: 0.0732 +[2026-03-20T17:26:54.734627Z] Loop 233: Reg: 0.5129, AltReg: 0.8090, CorReg: 0.0688, TopReg: 0.6183, AllReg: 0.8090, BotRReg: 0.8523, OV: 0.3507, AltV: 0.0733, CorV: 0.7669, TopV: 0.2403, BotRV: 0.0064, AllV: 0.0732 +[2026-03-20T17:26:55.624170Z] Loop 234: Reg: 0.5129, AltReg: 0.8090, CorReg: 0.0687, TopReg: 0.6189, AllReg: 0.8090, BotRReg: 0.8522, OV: 0.3507, AltV: 0.0733, CorV: 0.7669, TopV: 0.2398, BotRV: 0.0064, AllV: 0.0732 +[2026-03-20T17:26:56.514724Z] Loop 235: Reg: 0.5128, AltReg: 0.8090, CorReg: 0.0685, TopReg: 0.6211, AllReg: 0.8090, BotRReg: 0.8521, OV: 0.3508, AltV: 0.0732, CorV: 0.7671, TopV: 0.2376, BotRV: 0.0065, AllV: 0.0732 +[2026-03-20T17:26:57.404695Z] Loop 236: Reg: 0.5127, AltReg: 0.8090, CorReg: 0.0684, TopReg: 0.6218, AllReg: 0.8090, BotRReg: 0.8521, OV: 0.3508, AltV: 0.0732, CorV: 0.7672, TopV: 0.2368, BotRV: 0.0066, AllV: 0.0732 +[2026-03-20T17:26:58.294672Z] Loop 237: Reg: 0.5127, AltReg: 0.8090, CorReg: 0.0683, TopReg: 0.6228, AllReg: 0.8091, BotRReg: 0.8520, OV: 0.3509, AltV: 0.0732, CorV: 0.7673, TopV: 0.2358, BotRV: 0.0066, AllV: 0.0732 +[2026-03-20T17:26:59.185050Z] Loop 238: Reg: 0.5127, AltReg: 0.8090, CorReg: 0.0684, TopReg: 0.6225, AllReg: 0.8091, BotRReg: 0.8520, OV: 0.3508, AltV: 0.0732, CorV: 0.7673, TopV: 0.2361, BotRV: 0.0066, AllV: 0.0732 +[2026-03-20T17:27:00.074556Z] Loop 239: Reg: 0.5127, AltReg: 0.8090, CorReg: 0.0683, TopReg: 0.6235, AllReg: 0.8091, BotRReg: 0.8520, OV: 0.3509, AltV: 0.0732, CorV: 0.7673, TopV: 0.2351, BotRV: 0.0066, AllV: 0.0732 +[2026-03-20T17:27:00.965873Z] Loop 240: Reg: 0.5127, AltReg: 0.8090, CorReg: 0.0682, TopReg: 0.6246, AllReg: 0.8091, BotRReg: 0.8519, OV: 0.3509, AltV: 0.0732, CorV: 0.7674, TopV: 0.2340, BotRV: 0.0067, AllV: 0.0732 +[2026-03-20T17:27:01.856361Z] Loop 241: Reg: 0.5127, AltReg: 0.8090, CorReg: 0.0682, TopReg: 0.6264, AllReg: 0.8091, BotRReg: 0.8518, OV: 0.3509, AltV: 0.0732, CorV: 0.7674, TopV: 0.2323, BotRV: 0.0068, AllV: 0.0732 +[2026-03-20T17:27:02.745316Z] Loop 242: Reg: 0.5127, AltReg: 0.8090, CorReg: 0.0682, TopReg: 0.6265, AllReg: 0.8091, BotRReg: 0.8518, OV: 0.3509, AltV: 0.0732, CorV: 0.7674, TopV: 0.2321, BotRV: 0.0068, AllV: 0.0732 +[2026-03-20T17:27:03.633295Z] Loop 243: Reg: 0.5127, AltReg: 0.8090, CorReg: 0.0682, TopReg: 0.6252, AllReg: 0.8091, BotRReg: 0.8519, OV: 0.3509, AltV: 0.0732, CorV: 0.7674, TopV: 0.2334, BotRV: 0.0067, AllV: 0.0732 +[2026-03-20T17:27:04.524792Z] Loop 244: Reg: 0.5127, AltReg: 0.8090, CorReg: 0.0682, TopReg: 0.6258, AllReg: 0.8091, BotRReg: 0.8519, OV: 0.3509, AltV: 0.0732, CorV: 0.7674, TopV: 0.2328, BotRV: 0.0068, AllV: 0.0732 +[2026-03-20T17:27:05.417172Z] Loop 245: Reg: 0.5127, AltReg: 0.8090, CorReg: 0.0682, TopReg: 0.6268, AllReg: 0.8091, BotRReg: 0.8518, OV: 0.3509, AltV: 0.0732, CorV: 0.7674, TopV: 0.2318, BotRV: 0.0068, AllV: 0.0732 +[2026-03-20T17:27:06.307450Z] Loop 246: Reg: 0.5127, AltReg: 0.8090, CorReg: 0.0682, TopReg: 0.6275, AllReg: 0.8091, BotRReg: 0.8518, OV: 0.3509, AltV: 0.0732, CorV: 0.7674, TopV: 0.2311, BotRV: 0.0069, AllV: 0.0732 +[2026-03-20T17:27:07.196268Z] Loop 247: Reg: 0.5127, AltReg: 0.8090, CorReg: 0.0683, TopReg: 0.6289, AllReg: 0.8091, BotRReg: 0.8517, OV: 0.3509, AltV: 0.0732, CorV: 0.7674, TopV: 0.2298, BotRV: 0.0070, AllV: 0.0732 +[2026-03-20T17:27:08.084407Z] Loop 248: Reg: 0.5127, AltReg: 0.8090, CorReg: 0.0683, TopReg: 0.6292, AllReg: 0.8091, BotRReg: 0.8516, OV: 0.3509, AltV: 0.0732, CorV: 0.7674, TopV: 0.2294, BotRV: 0.0070, AllV: 0.0731 +[2026-03-20T17:27:08.972232Z] Loop 249: Reg: 0.5127, AltReg: 0.8090, CorReg: 0.0683, TopReg: 0.6303, AllReg: 0.8091, BotRReg: 0.8516, OV: 0.3508, AltV: 0.0732, CorV: 0.7673, TopV: 0.2284, BotRV: 0.0070, AllV: 0.0731 +[2026-03-20T17:27:09.861880Z] Loop 250: Reg: 0.5128, AltReg: 0.8091, CorReg: 0.0684, TopReg: 0.6319, AllReg: 0.8091, BotRReg: 0.8515, OV: 0.3508, AltV: 0.0732, CorV: 0.7672, TopV: 0.2267, BotRV: 0.0071, AllV: 0.0731 +[2026-03-20T17:27:11.604853Z] Loop 252: Reg: 0.5129, AltReg: 0.8091, CorReg: 0.0686, TopReg: 0.6339, AllReg: 0.8092, BotRReg: 0.8514, OV: 0.3507, AltV: 0.0731, CorV: 0.7671, TopV: 0.2247, BotRV: 0.0073, AllV: 0.0731 +[2026-03-20T17:27:13.345073Z] Loop 254: Reg: 0.5128, AltReg: 0.8091, CorReg: 0.0685, TopReg: 0.6333, AllReg: 0.8092, BotRReg: 0.8514, OV: 0.3507, AltV: 0.0731, CorV: 0.7672, TopV: 0.2253, BotRV: 0.0072, AllV: 0.0731 +[2026-03-20T17:27:15.087049Z] Loop 256: Reg: 0.5128, AltReg: 0.8091, CorReg: 0.0684, TopReg: 0.6329, AllReg: 0.8092, BotRReg: 0.8514, OV: 0.3508, AltV: 0.0731, CorV: 0.7672, TopV: 0.2257, BotRV: 0.0072, AllV: 0.0731 +[2026-03-20T17:27:16.828094Z] Loop 258: Reg: 0.5128, AltReg: 0.8091, CorReg: 0.0684, TopReg: 0.6325, AllReg: 0.8092, BotRReg: 0.8515, OV: 0.3508, AltV: 0.0731, CorV: 0.7673, TopV: 0.2261, BotRV: 0.0072, AllV: 0.0731 +[2026-03-20T17:27:18.571609Z] Loop 260: Reg: 0.5127, AltReg: 0.8091, CorReg: 0.0681, TopReg: 0.6268, AllReg: 0.8091, BotRReg: 0.8518, OV: 0.3509, AltV: 0.0731, CorV: 0.7675, TopV: 0.2319, BotRV: 0.0068, AllV: 0.0731 +[2026-03-20T17:27:20.316410Z] Loop 262: Reg: 0.5127, AltReg: 0.8091, CorReg: 0.0681, TopReg: 0.6239, AllReg: 0.8091, BotRReg: 0.8520, OV: 0.3509, AltV: 0.0731, CorV: 0.7675, TopV: 0.2347, BotRV: 0.0066, AllV: 0.0731 +[2026-03-20T17:27:22.060209Z] Loop 264: Reg: 0.5128, AltReg: 0.8091, CorReg: 0.0684, TopReg: 0.6201, AllReg: 0.8091, BotRReg: 0.8522, OV: 0.3508, AltV: 0.0731, CorV: 0.7672, TopV: 0.2385, BotRV: 0.0064, AllV: 0.0731 +[2026-03-20T17:27:23.803144Z] Loop 266: Reg: 0.5130, AltReg: 0.8091, CorReg: 0.0689, TopReg: 0.6162, AllReg: 0.8091, BotRReg: 0.8524, OV: 0.3506, AltV: 0.0731, CorV: 0.7668, TopV: 0.2424, BotRV: 0.0062, AllV: 0.0731 +[2026-03-20T17:27:25.545549Z] Loop 268: Reg: 0.5129, AltReg: 0.8091, CorReg: 0.0686, TopReg: 0.6181, AllReg: 0.8092, BotRReg: 0.8523, OV: 0.3507, AltV: 0.0731, CorV: 0.7670, TopV: 0.2405, BotRV: 0.0063, AllV: 0.0731 +[2026-03-20T17:27:27.287993Z] Loop 270: Reg: 0.5128, AltReg: 0.8091, CorReg: 0.0683, TopReg: 0.6202, AllReg: 0.8092, BotRReg: 0.8522, OV: 0.3508, AltV: 0.0731, CorV: 0.7673, TopV: 0.2384, BotRV: 0.0064, AllV: 0.0731 +[2026-03-20T17:27:29.030490Z] Loop 272: Reg: 0.5127, AltReg: 0.8091, CorReg: 0.0680, TopReg: 0.6245, AllReg: 0.8092, BotRReg: 0.8520, OV: 0.3509, AltV: 0.0731, CorV: 0.7676, TopV: 0.2341, BotRV: 0.0067, AllV: 0.0731 +[2026-03-20T17:27:30.772937Z] Loop 274: Reg: 0.5127, AltReg: 0.8091, CorReg: 0.0680, TopReg: 0.6288, AllReg: 0.8092, BotRReg: 0.8517, OV: 0.3509, AltV: 0.0731, CorV: 0.7676, TopV: 0.2299, BotRV: 0.0069, AllV: 0.0730 +[2026-03-20T17:27:32.515567Z] Loop 276: Reg: 0.5127, AltReg: 0.8091, CorReg: 0.0681, TopReg: 0.6313, AllReg: 0.8092, BotRReg: 0.8516, OV: 0.3509, AltV: 0.0731, CorV: 0.7675, TopV: 0.2273, BotRV: 0.0071, AllV: 0.0730 +[2026-03-20T17:27:34.255231Z] Loop 278: Reg: 0.5127, AltReg: 0.8091, CorReg: 0.0681, TopReg: 0.6314, AllReg: 0.8092, BotRReg: 0.8515, OV: 0.3509, AltV: 0.0731, CorV: 0.7675, TopV: 0.2272, BotRV: 0.0071, AllV: 0.0730 +[2026-03-20T17:27:35.997284Z] Loop 280: Reg: 0.5127, AltReg: 0.8091, CorReg: 0.0680, TopReg: 0.6263, AllReg: 0.8092, BotRReg: 0.8519, OV: 0.3509, AltV: 0.0731, CorV: 0.7676, TopV: 0.2323, BotRV: 0.0068, AllV: 0.0731 +[2026-03-20T17:27:37.736818Z] Loop 282: Reg: 0.5128, AltReg: 0.8091, CorReg: 0.0683, TopReg: 0.6202, AllReg: 0.8092, BotRReg: 0.8522, OV: 0.3508, AltV: 0.0731, CorV: 0.7673, TopV: 0.2385, BotRV: 0.0064, AllV: 0.0731 +[2026-03-20T17:27:39.478908Z] Loop 284: Reg: 0.5129, AltReg: 0.8091, CorReg: 0.0686, TopReg: 0.6176, AllReg: 0.8092, BotRReg: 0.8524, OV: 0.3507, AltV: 0.0731, CorV: 0.7670, TopV: 0.2410, BotRV: 0.0063, AllV: 0.0731 +[2026-03-20T17:27:41.222902Z] Loop 286: Reg: 0.5128, AltReg: 0.8091, CorReg: 0.0683, TopReg: 0.6207, AllReg: 0.8092, BotRReg: 0.8522, OV: 0.3508, AltV: 0.0731, CorV: 0.7674, TopV: 0.2379, BotRV: 0.0064, AllV: 0.0731 +[2026-03-20T17:27:42.965268Z] Loop 288: Reg: 0.5127, AltReg: 0.8091, CorReg: 0.0680, TopReg: 0.6270, AllReg: 0.8092, BotRReg: 0.8518, OV: 0.3509, AltV: 0.0731, CorV: 0.7677, TopV: 0.2317, BotRV: 0.0068, AllV: 0.0731 +[2026-03-20T17:27:44.710584Z] Loop 290: Reg: 0.5128, AltReg: 0.8091, CorReg: 0.0682, TopReg: 0.6323, AllReg: 0.8092, BotRReg: 0.8515, OV: 0.3508, AltV: 0.0731, CorV: 0.7675, TopV: 0.2263, BotRV: 0.0071, AllV: 0.0730 +[2026-03-20T17:27:46.453673Z] Loop 292: Reg: 0.5131, AltReg: 0.8092, CorReg: 0.0689, TopReg: 0.6384, AllReg: 0.8093, BotRReg: 0.8511, OV: 0.3505, AltV: 0.0730, CorV: 0.7667, TopV: 0.2202, BotRV: 0.0075, AllV: 0.0730 +[2026-03-20T17:27:48.195527Z] Loop 294: Reg: 0.5133, AltReg: 0.8092, CorReg: 0.0694, TopReg: 0.6407, AllReg: 0.8093, BotRReg: 0.8509, OV: 0.3503, AltV: 0.0730, CorV: 0.7662, TopV: 0.2179, BotRV: 0.0077, AllV: 0.0730 +[2026-03-20T17:27:49.937337Z] Loop 296: Reg: 0.5129, AltReg: 0.8092, CorReg: 0.0684, TopReg: 0.6352, AllReg: 0.8092, BotRReg: 0.8513, OV: 0.3507, AltV: 0.0730, CorV: 0.7672, TopV: 0.2235, BotRV: 0.0073, AllV: 0.0730 +[2026-03-20T17:27:51.679955Z] Loop 298: Reg: 0.5127, AltReg: 0.8091, CorReg: 0.0680, TopReg: 0.6275, AllReg: 0.8092, BotRReg: 0.8518, OV: 0.3509, AltV: 0.0731, CorV: 0.7677, TopV: 0.2312, BotRV: 0.0068, AllV: 0.0731 +[2026-03-20T17:27:53.421052Z] Loop 300: Reg: 0.5127, AltReg: 0.8091, CorReg: 0.0682, TopReg: 0.6214, AllReg: 0.8092, BotRReg: 0.8522, OV: 0.3508, AltV: 0.0731, CorV: 0.7674, TopV: 0.2373, BotRV: 0.0065, AllV: 0.0731 +[2026-03-20T17:27:55.160712Z] Loop 302: Reg: 0.5129, AltReg: 0.8091, CorReg: 0.0687, TopReg: 0.6166, AllReg: 0.8092, BotRReg: 0.8524, OV: 0.3506, AltV: 0.0731, CorV: 0.7669, TopV: 0.2420, BotRV: 0.0062, AllV: 0.0731 +[2026-03-20T17:27:56.902660Z] Loop 304: Reg: 0.5131, AltReg: 0.8091, CorReg: 0.0691, TopReg: 0.6145, AllReg: 0.8092, BotRReg: 0.8525, OV: 0.3505, AltV: 0.0731, CorV: 0.7665, TopV: 0.2442, BotRV: 0.0061, AllV: 0.0731 +[2026-03-20T17:27:58.644506Z] Loop 306: Reg: 0.5130, AltReg: 0.8091, CorReg: 0.0688, TopReg: 0.6164, AllReg: 0.8091, BotRReg: 0.8524, OV: 0.3506, AltV: 0.0731, CorV: 0.7668, TopV: 0.2423, BotRV: 0.0062, AllV: 0.0731 +[2026-03-20T17:28:00.386759Z] Loop 308: Reg: 0.5127, AltReg: 0.8091, CorReg: 0.0681, TopReg: 0.6227, AllReg: 0.8091, BotRReg: 0.8521, OV: 0.3509, AltV: 0.0732, CorV: 0.7675, TopV: 0.2359, BotRV: 0.0066, AllV: 0.0731 +[2026-03-20T17:28:02.131092Z] Loop 310: Reg: 0.5127, AltReg: 0.8091, CorReg: 0.0682, TopReg: 0.6307, AllReg: 0.8092, BotRReg: 0.8516, OV: 0.3509, AltV: 0.0731, CorV: 0.7675, TopV: 0.2279, BotRV: 0.0070, AllV: 0.0731 +[2026-03-20T17:28:03.875077Z] Loop 312: Reg: 0.5131, AltReg: 0.8091, CorReg: 0.0691, TopReg: 0.6385, AllReg: 0.8092, BotRReg: 0.8511, OV: 0.3505, AltV: 0.0731, CorV: 0.7665, TopV: 0.2202, BotRV: 0.0075, AllV: 0.0730 +[2026-03-20T17:28:05.619978Z] Loop 314: Reg: 0.5136, AltReg: 0.8092, CorReg: 0.0703, TopReg: 0.6439, AllReg: 0.8093, BotRReg: 0.8507, OV: 0.3499, AltV: 0.0730, CorV: 0.7653, TopV: 0.2147, BotRV: 0.0079, AllV: 0.0730 +[2026-03-20T17:28:07.362826Z] Loop 316: Reg: 0.5132, AltReg: 0.8092, CorReg: 0.0693, TopReg: 0.6398, AllReg: 0.8092, BotRReg: 0.8510, OV: 0.3504, AltV: 0.0731, CorV: 0.7663, TopV: 0.2189, BotRV: 0.0076, AllV: 0.0730 +[2026-03-20T17:28:09.105859Z] Loop 318: Reg: 0.5128, AltReg: 0.8091, CorReg: 0.0684, TopReg: 0.6337, AllReg: 0.8092, BotRReg: 0.8514, OV: 0.3508, AltV: 0.0731, CorV: 0.7672, TopV: 0.2249, BotRV: 0.0072, AllV: 0.0731 +[2026-03-20T17:28:10.849570Z] Loop 320: Reg: 0.5127, AltReg: 0.8090, CorReg: 0.0681, TopReg: 0.6277, AllReg: 0.8091, BotRReg: 0.8517, OV: 0.3509, AltV: 0.0732, CorV: 0.7675, TopV: 0.2309, BotRV: 0.0069, AllV: 0.0731 +[2026-03-20T17:28:12.592578Z] Loop 322: Reg: 0.5128, AltReg: 0.8090, CorReg: 0.0684, TopReg: 0.6205, AllReg: 0.8091, BotRReg: 0.8522, OV: 0.3508, AltV: 0.0732, CorV: 0.7673, TopV: 0.2381, BotRV: 0.0065, AllV: 0.0732 +[2026-03-20T17:28:14.336388Z] Loop 324: Reg: 0.5130, AltReg: 0.8090, CorReg: 0.0690, TopReg: 0.6158, AllReg: 0.8091, BotRReg: 0.8524, OV: 0.3506, AltV: 0.0732, CorV: 0.7667, TopV: 0.2428, BotRV: 0.0062, AllV: 0.0732 +[2026-03-20T17:28:16.078297Z] Loop 326: Reg: 0.5134, AltReg: 0.8090, CorReg: 0.0700, TopReg: 0.6104, AllReg: 0.8091, BotRReg: 0.8527, OV: 0.3502, AltV: 0.0732, CorV: 0.7656, TopV: 0.2482, BotRV: 0.0059, AllV: 0.0732 +[2026-03-20T17:28:17.822500Z] Loop 328: Reg: 0.5140, AltReg: 0.8090, CorReg: 0.0715, TopReg: 0.6052, AllReg: 0.8091, BotRReg: 0.8530, OV: 0.3495, AltV: 0.0732, CorV: 0.7641, TopV: 0.2534, BotRV: 0.0056, AllV: 0.0731 +[2026-03-20T17:28:19.565900Z] Loop 330: Reg: 0.5137, AltReg: 0.8090, CorReg: 0.0707, TopReg: 0.6079, AllReg: 0.8091, BotRReg: 0.8528, OV: 0.3499, AltV: 0.0732, CorV: 0.7649, TopV: 0.2507, BotRV: 0.0058, AllV: 0.0732 +[2026-03-20T17:28:21.310255Z] Loop 332: Reg: 0.5130, AltReg: 0.8090, CorReg: 0.0691, TopReg: 0.6153, AllReg: 0.8091, BotRReg: 0.8524, OV: 0.3506, AltV: 0.0732, CorV: 0.7665, TopV: 0.2433, BotRV: 0.0062, AllV: 0.0732 +[2026-03-20T17:28:23.054711Z] Loop 334: Reg: 0.5127, AltReg: 0.8090, CorReg: 0.0682, TopReg: 0.6241, AllReg: 0.8090, BotRReg: 0.8519, OV: 0.3509, AltV: 0.0732, CorV: 0.7674, TopV: 0.2345, BotRV: 0.0067, AllV: 0.0732 +[2026-03-20T17:28:24.798733Z] Loop 336: Reg: 0.5128, AltReg: 0.8090, CorReg: 0.0686, TopReg: 0.6334, AllReg: 0.8091, BotRReg: 0.8514, OV: 0.3507, AltV: 0.0732, CorV: 0.7671, TopV: 0.2252, BotRV: 0.0073, AllV: 0.0732 +[2026-03-20T17:28:26.542672Z] Loop 338: Reg: 0.5133, AltReg: 0.8091, CorReg: 0.0696, TopReg: 0.6398, AllReg: 0.8091, BotRReg: 0.8509, OV: 0.3503, AltV: 0.0732, CorV: 0.7660, TopV: 0.2188, BotRV: 0.0077, AllV: 0.0731 +[2026-03-20T17:28:28.283140Z] Loop 340: Reg: 0.5135, AltReg: 0.8091, CorReg: 0.0700, TopReg: 0.6416, AllReg: 0.8091, BotRReg: 0.8508, OV: 0.3501, AltV: 0.0732, CorV: 0.7656, TopV: 0.2170, BotRV: 0.0078, AllV: 0.0731 +[2026-03-20T17:28:30.025602Z] Loop 342: Reg: 0.5134, AltReg: 0.8090, CorReg: 0.0699, TopReg: 0.6406, AllReg: 0.8091, BotRReg: 0.8509, OV: 0.3502, AltV: 0.0732, CorV: 0.7658, TopV: 0.2181, BotRV: 0.0078, AllV: 0.0731 +[2026-03-20T17:28:31.767044Z] Loop 344: Reg: 0.5131, AltReg: 0.8090, CorReg: 0.0692, TopReg: 0.6370, AllReg: 0.8090, BotRReg: 0.8511, OV: 0.3505, AltV: 0.0732, CorV: 0.7664, TopV: 0.2216, BotRV: 0.0075, AllV: 0.0732 +[2026-03-20T17:28:33.508074Z] Loop 346: Reg: 0.5128, AltReg: 0.8089, CorReg: 0.0687, TopReg: 0.6328, AllReg: 0.8090, BotRReg: 0.8514, OV: 0.3507, AltV: 0.0733, CorV: 0.7669, TopV: 0.2259, BotRV: 0.0073, AllV: 0.0733 +[2026-03-20T17:28:35.249693Z] Loop 348: Reg: 0.5128, AltReg: 0.8089, CorReg: 0.0686, TopReg: 0.6302, AllReg: 0.8089, BotRReg: 0.8515, OV: 0.3508, AltV: 0.0734, CorV: 0.7670, TopV: 0.2284, BotRV: 0.0071, AllV: 0.0733 +[2026-03-20T17:28:36.992402Z] Loop 350: Reg: 0.5127, AltReg: 0.8088, CorReg: 0.0685, TopReg: 0.6265, AllReg: 0.8089, BotRReg: 0.8518, OV: 0.3509, AltV: 0.0734, CorV: 0.7672, TopV: 0.2322, BotRV: 0.0069, AllV: 0.0733 +[2026-03-20T17:28:38.735464Z] Loop 352: Reg: 0.5127, AltReg: 0.8088, CorReg: 0.0687, TopReg: 0.6211, AllReg: 0.8089, BotRReg: 0.8521, OV: 0.3508, AltV: 0.0734, CorV: 0.7670, TopV: 0.2375, BotRV: 0.0066, AllV: 0.0734 +[2026-03-20T17:28:40.478540Z] Loop 354: Reg: 0.5128, AltReg: 0.8088, CorReg: 0.0689, TopReg: 0.6191, AllReg: 0.8089, BotRReg: 0.8522, OV: 0.3508, AltV: 0.0734, CorV: 0.7668, TopV: 0.2396, BotRV: 0.0064, AllV: 0.0734 +[2026-03-20T17:28:42.221290Z] Loop 356: Reg: 0.5128, AltReg: 0.8088, CorReg: 0.0688, TopReg: 0.6197, AllReg: 0.8088, BotRReg: 0.8521, OV: 0.3508, AltV: 0.0734, CorV: 0.7668, TopV: 0.2389, BotRV: 0.0065, AllV: 0.0734 +[2026-03-20T17:28:43.965175Z] Loop 358: Reg: 0.5128, AltReg: 0.8088, CorReg: 0.0689, TopReg: 0.6188, AllReg: 0.8088, BotRReg: 0.8522, OV: 0.3508, AltV: 0.0735, CorV: 0.7667, TopV: 0.2398, BotRV: 0.0064, AllV: 0.0734 +[2026-03-20T17:28:45.709409Z] Loop 360: Reg: 0.5128, AltReg: 0.8088, CorReg: 0.0689, TopReg: 0.6190, AllReg: 0.8088, BotRReg: 0.8522, OV: 0.3508, AltV: 0.0735, CorV: 0.7667, TopV: 0.2397, BotRV: 0.0065, AllV: 0.0734 +[2026-03-20T17:28:47.452782Z] Loop 362: Reg: 0.5127, AltReg: 0.8088, CorReg: 0.0687, TopReg: 0.6209, AllReg: 0.8088, BotRReg: 0.8521, OV: 0.3508, AltV: 0.0734, CorV: 0.7669, TopV: 0.2378, BotRV: 0.0066, AllV: 0.0734 +[2026-03-20T17:28:49.194936Z] Loop 364: Reg: 0.5127, AltReg: 0.8088, CorReg: 0.0686, TopReg: 0.6220, AllReg: 0.8089, BotRReg: 0.8520, OV: 0.3509, AltV: 0.0734, CorV: 0.7670, TopV: 0.2366, BotRV: 0.0066, AllV: 0.0734 +[2026-03-20T17:28:50.937500Z] Loop 366: Reg: 0.5127, AltReg: 0.8088, CorReg: 0.0685, TopReg: 0.6256, AllReg: 0.8089, BotRReg: 0.8518, OV: 0.3509, AltV: 0.0734, CorV: 0.7672, TopV: 0.2330, BotRV: 0.0068, AllV: 0.0734 +[2026-03-20T17:28:52.680113Z] Loop 368: Reg: 0.5128, AltReg: 0.8089, CorReg: 0.0687, TopReg: 0.6314, AllReg: 0.8089, BotRReg: 0.8514, OV: 0.3508, AltV: 0.0734, CorV: 0.7670, TopV: 0.2273, BotRV: 0.0072, AllV: 0.0733 +[2026-03-20T17:28:54.429161Z] Loop 370: Reg: 0.5130, AltReg: 0.8089, CorReg: 0.0691, TopReg: 0.6355, AllReg: 0.8090, BotRReg: 0.8512, OV: 0.3506, AltV: 0.0733, CorV: 0.7665, TopV: 0.2231, BotRV: 0.0074, AllV: 0.0733 +[2026-03-20T17:28:56.171263Z] Loop 372: Reg: 0.5132, AltReg: 0.8089, CorReg: 0.0696, TopReg: 0.6387, AllReg: 0.8090, BotRReg: 0.8510, OV: 0.3504, AltV: 0.0733, CorV: 0.7660, TopV: 0.2200, BotRV: 0.0076, AllV: 0.0732 +[2026-03-20T17:28:57.913956Z] Loop 374: Reg: 0.5131, AltReg: 0.8089, CorReg: 0.0694, TopReg: 0.6375, AllReg: 0.8090, BotRReg: 0.8511, OV: 0.3505, AltV: 0.0733, CorV: 0.7662, TopV: 0.2212, BotRV: 0.0076, AllV: 0.0732 +[2026-03-20T17:28:59.658744Z] Loop 376: Reg: 0.5129, AltReg: 0.8089, CorReg: 0.0689, TopReg: 0.6345, AllReg: 0.8090, BotRReg: 0.8513, OV: 0.3507, AltV: 0.0733, CorV: 0.7667, TopV: 0.2241, BotRV: 0.0074, AllV: 0.0733 +[2026-03-20T17:29:01.401430Z] Loop 378: Reg: 0.5127, AltReg: 0.8089, CorReg: 0.0685, TopReg: 0.6291, AllReg: 0.8089, BotRReg: 0.8516, OV: 0.3509, AltV: 0.0734, CorV: 0.7671, TopV: 0.2295, BotRV: 0.0070, AllV: 0.0733 +[2026-03-20T17:29:03.146137Z] Loop 380: Reg: 0.5127, AltReg: 0.8088, CorReg: 0.0685, TopReg: 0.6239, AllReg: 0.8089, BotRReg: 0.8519, OV: 0.3509, AltV: 0.0734, CorV: 0.7672, TopV: 0.2348, BotRV: 0.0067, AllV: 0.0733 +[2026-03-20T17:29:04.888057Z] Loop 382: Reg: 0.5128, AltReg: 0.8088, CorReg: 0.0688, TopReg: 0.6185, AllReg: 0.8089, BotRReg: 0.8522, OV: 0.3508, AltV: 0.0734, CorV: 0.7668, TopV: 0.2401, BotRV: 0.0064, AllV: 0.0734 +[2026-03-20T17:29:06.634248Z] Loop 384: Reg: 0.5131, AltReg: 0.8088, CorReg: 0.0694, TopReg: 0.6145, AllReg: 0.8089, BotRReg: 0.8525, OV: 0.3505, AltV: 0.0734, CorV: 0.7662, TopV: 0.2442, BotRV: 0.0062, AllV: 0.0733 +[2026-03-20T17:29:08.378260Z] Loop 386: Reg: 0.5131, AltReg: 0.8088, CorReg: 0.0695, TopReg: 0.6139, AllReg: 0.8089, BotRReg: 0.8525, OV: 0.3505, AltV: 0.0734, CorV: 0.7661, TopV: 0.2447, BotRV: 0.0061, AllV: 0.0733 +[2026-03-20T17:29:10.118790Z] Loop 388: Reg: 0.5129, AltReg: 0.8088, CorReg: 0.0691, TopReg: 0.6161, AllReg: 0.8089, BotRReg: 0.8524, OV: 0.3506, AltV: 0.0734, CorV: 0.7665, TopV: 0.2425, BotRV: 0.0063, AllV: 0.0734 +[2026-03-20T17:29:11.861054Z] Loop 390: Reg: 0.5127, AltReg: 0.8088, CorReg: 0.0686, TopReg: 0.6204, AllReg: 0.8089, BotRReg: 0.8521, OV: 0.3508, AltV: 0.0734, CorV: 0.7670, TopV: 0.2383, BotRV: 0.0065, AllV: 0.0734 +[2026-03-20T17:29:13.604859Z] Loop 392: Reg: 0.5127, AltReg: 0.8088, CorReg: 0.0685, TopReg: 0.6218, AllReg: 0.8089, BotRReg: 0.8520, OV: 0.3509, AltV: 0.0734, CorV: 0.7671, TopV: 0.2369, BotRV: 0.0066, AllV: 0.0733 +[2026-03-20T17:29:15.345834Z] Loop 394: Reg: 0.5127, AltReg: 0.8088, CorReg: 0.0684, TopReg: 0.6254, AllReg: 0.8089, BotRReg: 0.8518, OV: 0.3509, AltV: 0.0734, CorV: 0.7672, TopV: 0.2333, BotRV: 0.0068, AllV: 0.0733 +[2026-03-20T17:29:17.092216Z] Loop 396: Reg: 0.5127, AltReg: 0.8088, CorReg: 0.0684, TopReg: 0.6263, AllReg: 0.8089, BotRReg: 0.8518, OV: 0.3509, AltV: 0.0734, CorV: 0.7672, TopV: 0.2324, BotRV: 0.0069, AllV: 0.0733 +[2026-03-20T17:29:18.832306Z] Loop 398: Reg: 0.5127, AltReg: 0.8088, CorReg: 0.0684, TopReg: 0.6244, AllReg: 0.8089, BotRReg: 0.8519, OV: 0.3509, AltV: 0.0734, CorV: 0.7672, TopV: 0.2342, BotRV: 0.0068, AllV: 0.0734 +[2026-03-20T17:29:20.573884Z] Loop 400: Reg: 0.5127, AltReg: 0.8088, CorReg: 0.0685, TopReg: 0.6214, AllReg: 0.8089, BotRReg: 0.8521, OV: 0.3509, AltV: 0.0734, CorV: 0.7671, TopV: 0.2372, BotRV: 0.0066, AllV: 0.0733 +[2026-03-20T17:29:22.315912Z] Loop 402: Reg: 0.5130, AltReg: 0.8088, CorReg: 0.0693, TopReg: 0.6145, AllReg: 0.8089, BotRReg: 0.8525, OV: 0.3505, AltV: 0.0734, CorV: 0.7663, TopV: 0.2441, BotRV: 0.0062, AllV: 0.0733 +[2026-03-20T17:29:24.057799Z] Loop 404: Reg: 0.5132, AltReg: 0.8088, CorReg: 0.0698, TopReg: 0.6123, AllReg: 0.8089, BotRReg: 0.8526, OV: 0.3504, AltV: 0.0734, CorV: 0.7659, TopV: 0.2464, BotRV: 0.0060, AllV: 0.0733 +[2026-03-20T17:29:25.799389Z] Loop 406: Reg: 0.5129, AltReg: 0.8088, CorReg: 0.0691, TopReg: 0.6161, AllReg: 0.8089, BotRReg: 0.8524, OV: 0.3506, AltV: 0.0734, CorV: 0.7665, TopV: 0.2425, BotRV: 0.0063, AllV: 0.0733 +[2026-03-20T17:29:27.542382Z] Loop 408: Reg: 0.5127, AltReg: 0.8088, CorReg: 0.0684, TopReg: 0.6227, AllReg: 0.8089, BotRReg: 0.8520, OV: 0.3509, AltV: 0.0734, CorV: 0.7672, TopV: 0.2360, BotRV: 0.0066, AllV: 0.0733 +[2026-03-20T17:29:29.283962Z] Loop 410: Reg: 0.5127, AltReg: 0.8089, CorReg: 0.0684, TopReg: 0.6291, AllReg: 0.8089, BotRReg: 0.8516, OV: 0.3509, AltV: 0.0734, CorV: 0.7672, TopV: 0.2295, BotRV: 0.0070, AllV: 0.0733 +[2026-03-20T17:29:31.024957Z] Loop 412: Reg: 0.5129, AltReg: 0.8089, CorReg: 0.0689, TopReg: 0.6345, AllReg: 0.8090, BotRReg: 0.8512, OV: 0.3507, AltV: 0.0733, CorV: 0.7667, TopV: 0.2242, BotRV: 0.0074, AllV: 0.0733 +[2026-03-20T17:29:32.765854Z] Loop 414: Reg: 0.5130, AltReg: 0.8089, CorReg: 0.0692, TopReg: 0.6362, AllReg: 0.8090, BotRReg: 0.8511, OV: 0.3506, AltV: 0.0733, CorV: 0.7664, TopV: 0.2224, BotRV: 0.0075, AllV: 0.0733 +[2026-03-20T17:29:34.507897Z] Loop 416: Reg: 0.5129, AltReg: 0.8089, CorReg: 0.0689, TopReg: 0.6347, AllReg: 0.8090, BotRReg: 0.8512, OV: 0.3507, AltV: 0.0733, CorV: 0.7667, TopV: 0.2240, BotRV: 0.0074, AllV: 0.0733 +[2026-03-20T17:29:36.248192Z] Loop 418: Reg: 0.5128, AltReg: 0.8089, CorReg: 0.0686, TopReg: 0.6318, AllReg: 0.8090, BotRReg: 0.8514, OV: 0.3508, AltV: 0.0733, CorV: 0.7670, TopV: 0.2268, BotRV: 0.0072, AllV: 0.0733 +[2026-03-20T17:29:37.990216Z] Loop 420: Reg: 0.5127, AltReg: 0.8089, CorReg: 0.0685, TopReg: 0.6299, AllReg: 0.8089, BotRReg: 0.8515, OV: 0.3509, AltV: 0.0733, CorV: 0.7672, TopV: 0.2287, BotRV: 0.0071, AllV: 0.0733 +[2026-03-20T17:29:39.731881Z] Loop 422: Reg: 0.5127, AltReg: 0.8089, CorReg: 0.0684, TopReg: 0.6292, AllReg: 0.8089, BotRReg: 0.8516, OV: 0.3509, AltV: 0.0733, CorV: 0.7672, TopV: 0.2294, BotRV: 0.0070, AllV: 0.0733 +[2026-03-20T17:29:41.476061Z] Loop 424: Reg: 0.5127, AltReg: 0.8089, CorReg: 0.0684, TopReg: 0.6296, AllReg: 0.8089, BotRReg: 0.8516, OV: 0.3509, AltV: 0.0733, CorV: 0.7672, TopV: 0.2290, BotRV: 0.0071, AllV: 0.0733 +[2026-03-20T17:29:43.217876Z] Loop 426: Reg: 0.5127, AltReg: 0.8089, CorReg: 0.0684, TopReg: 0.6290, AllReg: 0.8089, BotRReg: 0.8516, OV: 0.3509, AltV: 0.0733, CorV: 0.7673, TopV: 0.2296, BotRV: 0.0070, AllV: 0.0733 +[2026-03-20T17:29:44.959052Z] Loop 428: Reg: 0.5126, AltReg: 0.8089, CorReg: 0.0683, TopReg: 0.6274, AllReg: 0.8089, BotRReg: 0.8517, OV: 0.3509, AltV: 0.0734, CorV: 0.7673, TopV: 0.2313, BotRV: 0.0069, AllV: 0.0733 +[2026-03-20T17:29:46.701428Z] Loop 430: Reg: 0.5126, AltReg: 0.8088, CorReg: 0.0683, TopReg: 0.6257, AllReg: 0.8089, BotRReg: 0.8518, OV: 0.3509, AltV: 0.0734, CorV: 0.7673, TopV: 0.2329, BotRV: 0.0068, AllV: 0.0733 +[2026-03-20T17:29:48.445704Z] Loop 432: Reg: 0.5127, AltReg: 0.8088, CorReg: 0.0684, TopReg: 0.6277, AllReg: 0.8089, BotRReg: 0.8517, OV: 0.3509, AltV: 0.0734, CorV: 0.7672, TopV: 0.2310, BotRV: 0.0070, AllV: 0.0733 +[2026-03-20T17:29:50.190076Z] Loop 434: Reg: 0.5127, AltReg: 0.8088, CorReg: 0.0685, TopReg: 0.6300, AllReg: 0.8089, BotRReg: 0.8515, OV: 0.3509, AltV: 0.0734, CorV: 0.7671, TopV: 0.2286, BotRV: 0.0071, AllV: 0.0733 +[2026-03-20T17:29:51.935161Z] Loop 436: Reg: 0.5127, AltReg: 0.8088, CorReg: 0.0686, TopReg: 0.6304, AllReg: 0.8089, BotRReg: 0.8515, OV: 0.3509, AltV: 0.0734, CorV: 0.7671, TopV: 0.2283, BotRV: 0.0071, AllV: 0.0733 +[2026-03-20T17:29:53.679818Z] Loop 438: Reg: 0.5127, AltReg: 0.8088, CorReg: 0.0685, TopReg: 0.6289, AllReg: 0.8089, BotRReg: 0.8516, OV: 0.3509, AltV: 0.0734, CorV: 0.7671, TopV: 0.2297, BotRV: 0.0071, AllV: 0.0734 +[2026-03-20T17:29:55.422401Z] Loop 440: Reg: 0.5127, AltReg: 0.8088, CorReg: 0.0685, TopReg: 0.6292, AllReg: 0.8089, BotRReg: 0.8516, OV: 0.3509, AltV: 0.0734, CorV: 0.7671, TopV: 0.2295, BotRV: 0.0071, AllV: 0.0734 +[2026-03-20T17:29:57.165512Z] Loop 442: Reg: 0.5127, AltReg: 0.8088, CorReg: 0.0686, TopReg: 0.6305, AllReg: 0.8089, BotRReg: 0.8515, OV: 0.3509, AltV: 0.0734, CorV: 0.7671, TopV: 0.2281, BotRV: 0.0071, AllV: 0.0733 +[2026-03-20T17:29:58.909835Z] Loop 444: Reg: 0.5128, AltReg: 0.8089, CorReg: 0.0687, TopReg: 0.6326, AllReg: 0.8089, BotRReg: 0.8514, OV: 0.3508, AltV: 0.0734, CorV: 0.7669, TopV: 0.2260, BotRV: 0.0073, AllV: 0.0733 +[2026-03-20T17:30:00.653667Z] Loop 446: Reg: 0.5129, AltReg: 0.8089, CorReg: 0.0689, TopReg: 0.6342, AllReg: 0.8090, BotRReg: 0.8513, OV: 0.3507, AltV: 0.0733, CorV: 0.7667, TopV: 0.2244, BotRV: 0.0074, AllV: 0.0733 +[2026-03-20T17:30:02.398818Z] Loop 448: Reg: 0.5128, AltReg: 0.8089, CorReg: 0.0687, TopReg: 0.6333, AllReg: 0.8090, BotRReg: 0.8513, OV: 0.3508, AltV: 0.0733, CorV: 0.7669, TopV: 0.2253, BotRV: 0.0073, AllV: 0.0733 +[2026-03-20T17:30:04.147493Z] Loop 450: Reg: 0.5127, AltReg: 0.8089, CorReg: 0.0684, TopReg: 0.6298, AllReg: 0.8089, BotRReg: 0.8515, OV: 0.3509, AltV: 0.0734, CorV: 0.7672, TopV: 0.2288, BotRV: 0.0071, AllV: 0.0733 +[2026-03-20T17:30:05.889389Z] Loop 452: Reg: 0.5126, AltReg: 0.8088, CorReg: 0.0683, TopReg: 0.6263, AllReg: 0.8089, BotRReg: 0.8518, OV: 0.3510, AltV: 0.0734, CorV: 0.7673, TopV: 0.2324, BotRV: 0.0069, AllV: 0.0733 +[2026-03-20T17:30:07.631661Z] Loop 454: Reg: 0.5126, AltReg: 0.8088, CorReg: 0.0684, TopReg: 0.6226, AllReg: 0.8089, BotRReg: 0.8520, OV: 0.3509, AltV: 0.0734, CorV: 0.7673, TopV: 0.2361, BotRV: 0.0067, AllV: 0.0733 +[2026-03-20T17:30:09.375420Z] Loop 456: Reg: 0.5127, AltReg: 0.8088, CorReg: 0.0684, TopReg: 0.6215, AllReg: 0.8089, BotRReg: 0.8520, OV: 0.3509, AltV: 0.0734, CorV: 0.7672, TopV: 0.2372, BotRV: 0.0066, AllV: 0.0734 +[2026-03-20T17:30:11.118995Z] Loop 458: Reg: 0.5126, AltReg: 0.8088, CorReg: 0.0684, TopReg: 0.6235, AllReg: 0.8089, BotRReg: 0.8519, OV: 0.3510, AltV: 0.0734, CorV: 0.7673, TopV: 0.2351, BotRV: 0.0067, AllV: 0.0734 +[2026-03-20T17:30:12.861697Z] Loop 460: Reg: 0.5126, AltReg: 0.8088, CorReg: 0.0684, TopReg: 0.6253, AllReg: 0.8089, BotRReg: 0.8518, OV: 0.3510, AltV: 0.0734, CorV: 0.7673, TopV: 0.2333, BotRV: 0.0068, AllV: 0.0734 +[2026-03-20T17:30:14.605134Z] Loop 462: Reg: 0.5126, AltReg: 0.8088, CorReg: 0.0684, TopReg: 0.6238, AllReg: 0.8089, BotRReg: 0.8519, OV: 0.3509, AltV: 0.0734, CorV: 0.7672, TopV: 0.2349, BotRV: 0.0067, AllV: 0.0734 +[2026-03-20T17:30:16.347781Z] Loop 464: Reg: 0.5126, AltReg: 0.8088, CorReg: 0.0684, TopReg: 0.6231, AllReg: 0.8089, BotRReg: 0.8519, OV: 0.3509, AltV: 0.0734, CorV: 0.7672, TopV: 0.2355, BotRV: 0.0067, AllV: 0.0734 +[2026-03-20T17:30:18.091037Z] Loop 466: Reg: 0.5127, AltReg: 0.8088, CorReg: 0.0685, TopReg: 0.6216, AllReg: 0.8089, BotRReg: 0.8520, OV: 0.3509, AltV: 0.0734, CorV: 0.7671, TopV: 0.2370, BotRV: 0.0066, AllV: 0.0734 +[2026-03-20T17:30:19.835555Z] Loop 468: Reg: 0.5127, AltReg: 0.8088, CorReg: 0.0685, TopReg: 0.6222, AllReg: 0.8088, BotRReg: 0.8520, OV: 0.3509, AltV: 0.0734, CorV: 0.7671, TopV: 0.2364, BotRV: 0.0066, AllV: 0.0734 +[2026-03-20T17:30:21.579969Z] Loop 470: Reg: 0.5127, AltReg: 0.8087, CorReg: 0.0685, TopReg: 0.6226, AllReg: 0.8088, BotRReg: 0.8520, OV: 0.3509, AltV: 0.0735, CorV: 0.7671, TopV: 0.2360, BotRV: 0.0067, AllV: 0.0734 +[2026-03-20T17:30:23.324252Z] Loop 472: Reg: 0.5127, AltReg: 0.8087, CorReg: 0.0686, TopReg: 0.6219, AllReg: 0.8088, BotRReg: 0.8520, OV: 0.3509, AltV: 0.0735, CorV: 0.7671, TopV: 0.2367, BotRV: 0.0066, AllV: 0.0734 +[2026-03-20T17:30:25.065755Z] Loop 474: Reg: 0.5127, AltReg: 0.8087, CorReg: 0.0686, TopReg: 0.6226, AllReg: 0.8088, BotRReg: 0.8519, OV: 0.3509, AltV: 0.0735, CorV: 0.7671, TopV: 0.2360, BotRV: 0.0067, AllV: 0.0735 +[2026-03-20T17:30:26.807808Z] Loop 476: Reg: 0.5127, AltReg: 0.8087, CorReg: 0.0687, TopReg: 0.6204, AllReg: 0.8088, BotRReg: 0.8521, OV: 0.3509, AltV: 0.0735, CorV: 0.7669, TopV: 0.2382, BotRV: 0.0066, AllV: 0.0735 +[2026-03-20T17:30:28.549766Z] Loop 478: Reg: 0.5128, AltReg: 0.8087, CorReg: 0.0691, TopReg: 0.6170, AllReg: 0.8088, BotRReg: 0.8522, OV: 0.3507, AltV: 0.0735, CorV: 0.7665, TopV: 0.2417, BotRV: 0.0064, AllV: 0.0735 +[2026-03-20T17:30:30.295464Z] Loop 480: Reg: 0.5129, AltReg: 0.8087, CorReg: 0.0691, TopReg: 0.6163, AllReg: 0.8088, BotRReg: 0.8523, OV: 0.3507, AltV: 0.0735, CorV: 0.7665, TopV: 0.2423, BotRV: 0.0063, AllV: 0.0735 +[2026-03-20T17:30:32.038534Z] Loop 482: Reg: 0.5127, AltReg: 0.8087, CorReg: 0.0686, TopReg: 0.6213, AllReg: 0.8088, BotRReg: 0.8520, OV: 0.3509, AltV: 0.0735, CorV: 0.7670, TopV: 0.2373, BotRV: 0.0066, AllV: 0.0735 +[2026-03-20T17:30:33.780506Z] Loop 484: Reg: 0.5126, AltReg: 0.8087, CorReg: 0.0685, TopReg: 0.6258, AllReg: 0.8088, BotRReg: 0.8518, OV: 0.3509, AltV: 0.0735, CorV: 0.7671, TopV: 0.2328, BotRV: 0.0069, AllV: 0.0734 +[2026-03-20T17:30:35.523136Z] Loop 486: Reg: 0.5127, AltReg: 0.8088, CorReg: 0.0685, TopReg: 0.6285, AllReg: 0.8088, BotRReg: 0.8516, OV: 0.3509, AltV: 0.0734, CorV: 0.7671, TopV: 0.2301, BotRV: 0.0070, AllV: 0.0734 +[2026-03-20T17:30:37.266212Z] Loop 488: Reg: 0.5126, AltReg: 0.8088, CorReg: 0.0684, TopReg: 0.6272, AllReg: 0.8089, BotRReg: 0.8517, OV: 0.3510, AltV: 0.0734, CorV: 0.7673, TopV: 0.2314, BotRV: 0.0069, AllV: 0.0734 +[2026-03-20T17:30:39.008868Z] Loop 490: Reg: 0.5126, AltReg: 0.8088, CorReg: 0.0683, TopReg: 0.6265, AllReg: 0.8089, BotRReg: 0.8517, OV: 0.3510, AltV: 0.0734, CorV: 0.7674, TopV: 0.2321, BotRV: 0.0069, AllV: 0.0733 +[2026-03-20T17:30:40.752712Z] Loop 492: Reg: 0.5126, AltReg: 0.8089, CorReg: 0.0682, TopReg: 0.6263, AllReg: 0.8089, BotRReg: 0.8518, OV: 0.3510, AltV: 0.0734, CorV: 0.7674, TopV: 0.2323, BotRV: 0.0069, AllV: 0.0733 +[2026-03-20T17:30:42.496618Z] Loop 494: Reg: 0.5126, AltReg: 0.8089, CorReg: 0.0682, TopReg: 0.6260, AllReg: 0.8089, BotRReg: 0.8518, OV: 0.3510, AltV: 0.0733, CorV: 0.7675, TopV: 0.2326, BotRV: 0.0068, AllV: 0.0733 +[2026-03-20T17:30:44.239623Z] Loop 496: Reg: 0.5126, AltReg: 0.8089, CorReg: 0.0681, TopReg: 0.6266, AllReg: 0.8090, BotRReg: 0.8517, OV: 0.3510, AltV: 0.0733, CorV: 0.7675, TopV: 0.2321, BotRV: 0.0069, AllV: 0.0733 +[2026-03-20T17:30:45.982539Z] Loop 498: Reg: 0.5126, AltReg: 0.8089, CorReg: 0.0682, TopReg: 0.6283, AllReg: 0.8090, BotRReg: 0.8516, OV: 0.3510, AltV: 0.0733, CorV: 0.7675, TopV: 0.2304, BotRV: 0.0070, AllV: 0.0733 +[2026-03-20T17:30:47.726267Z] Loop 500: Reg: 0.5126, AltReg: 0.8089, CorReg: 0.0681, TopReg: 0.6272, AllReg: 0.8090, BotRReg: 0.8517, OV: 0.3510, AltV: 0.0733, CorV: 0.7675, TopV: 0.2314, BotRV: 0.0069, AllV: 0.0733 +[2026-03-20T17:30:52.027301Z] Loop 505: Reg: 0.5126, AltReg: 0.8089, CorReg: 0.0682, TopReg: 0.6216, AllReg: 0.8090, BotRReg: 0.8521, OV: 0.3510, AltV: 0.0733, CorV: 0.7675, TopV: 0.2370, BotRV: 0.0066, AllV: 0.0733 +[2026-03-20T17:30:56.330561Z] Loop 510: Reg: 0.5126, AltReg: 0.8089, CorReg: 0.0681, TopReg: 0.6222, AllReg: 0.8090, BotRReg: 0.8520, OV: 0.3510, AltV: 0.0733, CorV: 0.7675, TopV: 0.2364, BotRV: 0.0066, AllV: 0.0732 +[2026-03-20T17:31:00.631211Z] Loop 515: Reg: 0.5126, AltReg: 0.8089, CorReg: 0.0681, TopReg: 0.6302, AllReg: 0.8090, BotRReg: 0.8516, OV: 0.3510, AltV: 0.0733, CorV: 0.7675, TopV: 0.2285, BotRV: 0.0071, AllV: 0.0732 +[2026-03-20T17:31:04.927613Z] Loop 520: Reg: 0.5126, AltReg: 0.8089, CorReg: 0.0680, TopReg: 0.6283, AllReg: 0.8090, BotRReg: 0.8516, OV: 0.3510, AltV: 0.0733, CorV: 0.7676, TopV: 0.2304, BotRV: 0.0070, AllV: 0.0732 +[2026-03-20T17:31:09.228463Z] Loop 525: Reg: 0.5126, AltReg: 0.8089, CorReg: 0.0680, TopReg: 0.6248, AllReg: 0.8090, BotRReg: 0.8518, OV: 0.3510, AltV: 0.0733, CorV: 0.7676, TopV: 0.2338, BotRV: 0.0068, AllV: 0.0733 +[2026-03-20T17:31:13.530091Z] Loop 530: Reg: 0.5126, AltReg: 0.8089, CorReg: 0.0681, TopReg: 0.6226, AllReg: 0.8090, BotRReg: 0.8520, OV: 0.3510, AltV: 0.0733, CorV: 0.7676, TopV: 0.2360, BotRV: 0.0067, AllV: 0.0733 +[2026-03-20T17:31:17.830933Z] Loop 535: Reg: 0.5128, AltReg: 0.8090, CorReg: 0.0684, TopReg: 0.6342, AllReg: 0.8091, BotRReg: 0.8513, OV: 0.3508, AltV: 0.0732, CorV: 0.7672, TopV: 0.2244, BotRV: 0.0074, AllV: 0.0732 +[2026-03-20T17:31:22.132190Z] Loop 540: Reg: 0.5128, AltReg: 0.8090, CorReg: 0.0686, TopReg: 0.6359, AllReg: 0.8091, BotRReg: 0.8512, OV: 0.3507, AltV: 0.0732, CorV: 0.7670, TopV: 0.2227, BotRV: 0.0075, AllV: 0.0732 +[2026-03-20T17:31:26.433711Z] Loop 545: Reg: 0.5126, AltReg: 0.8090, CorReg: 0.0680, TopReg: 0.6300, AllReg: 0.8091, BotRReg: 0.8516, OV: 0.3510, AltV: 0.0732, CorV: 0.7676, TopV: 0.2287, BotRV: 0.0071, AllV: 0.0732 +[2026-03-20T17:31:30.734314Z] Loop 550: Reg: 0.5127, AltReg: 0.8090, CorReg: 0.0683, TopReg: 0.6339, AllReg: 0.8091, BotRReg: 0.8513, OV: 0.3509, AltV: 0.0732, CorV: 0.7673, TopV: 0.2247, BotRV: 0.0073, AllV: 0.0732 +[2026-03-20T17:31:35.037387Z] Loop 555: Reg: 0.5126, AltReg: 0.8090, CorReg: 0.0681, TopReg: 0.6315, AllReg: 0.8091, BotRReg: 0.8515, OV: 0.3510, AltV: 0.0732, CorV: 0.7675, TopV: 0.2271, BotRV: 0.0072, AllV: 0.0732 +[2026-03-20T17:31:39.335057Z] Loop 560: Reg: 0.5125, AltReg: 0.8089, CorReg: 0.0679, TopReg: 0.6259, AllReg: 0.8090, BotRReg: 0.8518, OV: 0.3511, AltV: 0.0733, CorV: 0.7678, TopV: 0.2327, BotRV: 0.0068, AllV: 0.0732 +[2026-03-20T17:31:43.635034Z] Loop 565: Reg: 0.5125, AltReg: 0.8089, CorReg: 0.0680, TopReg: 0.6231, AllReg: 0.8090, BotRReg: 0.8519, OV: 0.3510, AltV: 0.0733, CorV: 0.7676, TopV: 0.2355, BotRV: 0.0067, AllV: 0.0733 +[2026-03-20T17:31:47.933729Z] Loop 570: Reg: 0.5127, AltReg: 0.8088, CorReg: 0.0684, TopReg: 0.6186, AllReg: 0.8089, BotRReg: 0.8522, OV: 0.3509, AltV: 0.0734, CorV: 0.7672, TopV: 0.2401, BotRV: 0.0064, AllV: 0.0733 +[2026-03-20T17:31:52.233514Z] Loop 575: Reg: 0.5125, AltReg: 0.8089, CorReg: 0.0680, TopReg: 0.6274, AllReg: 0.8090, BotRReg: 0.8517, OV: 0.3511, AltV: 0.0733, CorV: 0.7677, TopV: 0.2312, BotRV: 0.0070, AllV: 0.0733 +[2026-03-20T17:31:56.535563Z] Loop 580: Reg: 0.5131, AltReg: 0.8090, CorReg: 0.0692, TopReg: 0.6393, AllReg: 0.8091, BotRReg: 0.8509, OV: 0.3505, AltV: 0.0732, CorV: 0.7664, TopV: 0.2193, BotRV: 0.0077, AllV: 0.0732 +[2026-03-20T17:32:00.836417Z] Loop 585: Reg: 0.5125, AltReg: 0.8089, CorReg: 0.0680, TopReg: 0.6280, AllReg: 0.8090, BotRReg: 0.8516, OV: 0.3511, AltV: 0.0733, CorV: 0.7677, TopV: 0.2306, BotRV: 0.0070, AllV: 0.0733 +[2026-03-20T17:32:05.138611Z] Loop 590: Reg: 0.5125, AltReg: 0.8088, CorReg: 0.0681, TopReg: 0.6227, AllReg: 0.8089, BotRReg: 0.8519, OV: 0.3511, AltV: 0.0734, CorV: 0.7676, TopV: 0.2359, BotRV: 0.0067, AllV: 0.0734 +[2026-03-20T17:32:09.442476Z] Loop 595: Reg: 0.5126, AltReg: 0.8088, CorReg: 0.0682, TopReg: 0.6211, AllReg: 0.8088, BotRReg: 0.8520, OV: 0.3510, AltV: 0.0734, CorV: 0.7674, TopV: 0.2375, BotRV: 0.0066, AllV: 0.0734 +[2026-03-20T17:32:13.743079Z] Loop 600: Reg: 0.5125, AltReg: 0.8088, CorReg: 0.0682, TopReg: 0.6282, AllReg: 0.8088, BotRReg: 0.8516, OV: 0.3511, AltV: 0.0734, CorV: 0.7675, TopV: 0.2304, BotRV: 0.0070, AllV: 0.0734 +[2026-03-20T17:32:18.043511Z] Loop 605: Reg: 0.5131, AltReg: 0.8089, CorReg: 0.0694, TopReg: 0.6390, AllReg: 0.8089, BotRReg: 0.8509, OV: 0.3505, AltV: 0.0734, CorV: 0.7662, TopV: 0.2197, BotRV: 0.0077, AllV: 0.0733 +[2026-03-20T17:32:22.347401Z] Loop 610: Reg: 0.5130, AltReg: 0.8088, CorReg: 0.0693, TopReg: 0.6380, AllReg: 0.8089, BotRReg: 0.8510, OV: 0.3506, AltV: 0.0734, CorV: 0.7663, TopV: 0.2206, BotRV: 0.0077, AllV: 0.0734 +[2026-03-20T17:32:26.648618Z] Loop 615: Reg: 0.5125, AltReg: 0.8087, CorReg: 0.0683, TopReg: 0.6268, AllReg: 0.8087, BotRReg: 0.8516, OV: 0.3511, AltV: 0.0736, CorV: 0.7673, TopV: 0.2319, BotRV: 0.0070, AllV: 0.0735 +[2026-03-20T17:32:30.956272Z] Loop 620: Reg: 0.5129, AltReg: 0.8086, CorReg: 0.0693, TopReg: 0.6136, AllReg: 0.8087, BotRReg: 0.8524, OV: 0.3507, AltV: 0.0736, CorV: 0.7663, TopV: 0.2450, BotRV: 0.0062, AllV: 0.0735 +[2026-03-20T17:32:35.260380Z] Loop 625: Reg: 0.5125, AltReg: 0.8086, CorReg: 0.0684, TopReg: 0.6222, AllReg: 0.8087, BotRReg: 0.8519, OV: 0.3511, AltV: 0.0736, CorV: 0.7673, TopV: 0.2364, BotRV: 0.0067, AllV: 0.0736 +[2026-03-20T17:32:39.562859Z] Loop 630: Reg: 0.5126, AltReg: 0.8087, CorReg: 0.0684, TopReg: 0.6314, AllReg: 0.8088, BotRReg: 0.8514, OV: 0.3510, AltV: 0.0735, CorV: 0.7672, TopV: 0.2273, BotRV: 0.0073, AllV: 0.0735 +[2026-03-20T17:32:43.867202Z] Loop 635: Reg: 0.5126, AltReg: 0.8088, CorReg: 0.0684, TopReg: 0.6334, AllReg: 0.8089, BotRReg: 0.8513, OV: 0.3509, AltV: 0.0734, CorV: 0.7673, TopV: 0.2253, BotRV: 0.0074, AllV: 0.0734 +[2026-03-20T17:32:48.171683Z] Loop 640: Reg: 0.5125, AltReg: 0.8088, CorReg: 0.0680, TopReg: 0.6297, AllReg: 0.8089, BotRReg: 0.8515, OV: 0.3511, AltV: 0.0734, CorV: 0.7676, TopV: 0.2289, BotRV: 0.0071, AllV: 0.0734 +[2026-03-20T17:32:52.477683Z] Loop 645: Reg: 0.5125, AltReg: 0.8087, CorReg: 0.0680, TopReg: 0.6223, AllReg: 0.8088, BotRReg: 0.8519, OV: 0.3511, AltV: 0.0735, CorV: 0.7676, TopV: 0.2364, BotRV: 0.0067, AllV: 0.0734 +[2026-03-20T17:32:56.781518Z] Loop 650: Reg: 0.5125, AltReg: 0.8087, CorReg: 0.0682, TopReg: 0.6201, AllReg: 0.8088, BotRReg: 0.8520, OV: 0.3511, AltV: 0.0735, CorV: 0.7674, TopV: 0.2385, BotRV: 0.0066, AllV: 0.0735 +[2026-03-20T17:33:01.086113Z] Loop 655: Reg: 0.5124, AltReg: 0.8088, CorReg: 0.0680, TopReg: 0.6290, AllReg: 0.8088, BotRReg: 0.8515, OV: 0.3511, AltV: 0.0735, CorV: 0.7677, TopV: 0.2296, BotRV: 0.0071, AllV: 0.0734 +[2026-03-20T17:33:05.385237Z] Loop 660: Reg: 0.5124, AltReg: 0.8088, CorReg: 0.0678, TopReg: 0.6250, AllReg: 0.8088, BotRReg: 0.8518, OV: 0.3512, AltV: 0.0734, CorV: 0.7678, TopV: 0.2337, BotRV: 0.0068, AllV: 0.0734 +[2026-03-20T17:33:09.686163Z] Loop 665: Reg: 0.5124, AltReg: 0.8088, CorReg: 0.0677, TopReg: 0.6236, AllReg: 0.8089, BotRReg: 0.8519, OV: 0.3512, AltV: 0.0734, CorV: 0.7679, TopV: 0.2350, BotRV: 0.0068, AllV: 0.0734 +[2026-03-20T17:33:13.991557Z] Loop 670: Reg: 0.5129, AltReg: 0.8089, CorReg: 0.0688, TopReg: 0.6387, AllReg: 0.8090, BotRReg: 0.8509, OV: 0.3507, AltV: 0.0733, CorV: 0.7668, TopV: 0.2199, BotRV: 0.0077, AllV: 0.0732 +[2026-03-20T17:33:18.292773Z] Loop 675: Reg: 0.5129, AltReg: 0.8089, CorReg: 0.0689, TopReg: 0.6395, AllReg: 0.8090, BotRReg: 0.8509, OV: 0.3506, AltV: 0.0733, CorV: 0.7667, TopV: 0.2191, BotRV: 0.0077, AllV: 0.0732 +[2026-03-20T17:33:22.590835Z] Loop 680: Reg: 0.5129, AltReg: 0.8088, CorReg: 0.0690, TopReg: 0.6123, AllReg: 0.8089, BotRReg: 0.8525, OV: 0.3507, AltV: 0.0734, CorV: 0.7666, TopV: 0.2463, BotRV: 0.0061, AllV: 0.0734 +[2026-03-20T17:33:26.891859Z] Loop 685: Reg: 0.5131, AltReg: 0.8089, CorReg: 0.0695, TopReg: 0.6096, AllReg: 0.8089, BotRReg: 0.8527, OV: 0.3505, AltV: 0.0734, CorV: 0.7661, TopV: 0.2491, BotRV: 0.0060, AllV: 0.0733 +[2026-03-20T17:33:31.194062Z] Loop 690: Reg: 0.5126, AltReg: 0.8089, CorReg: 0.0683, TopReg: 0.6153, AllReg: 0.8090, BotRReg: 0.8524, OV: 0.3509, AltV: 0.0733, CorV: 0.7674, TopV: 0.2433, BotRV: 0.0063, AllV: 0.0733 +[2026-03-20T17:33:35.496186Z] Loop 695: Reg: 0.5123, AltReg: 0.8089, CorReg: 0.0673, TopReg: 0.6259, AllReg: 0.8090, BotRReg: 0.8518, OV: 0.3513, AltV: 0.0733, CorV: 0.7683, TopV: 0.2327, BotRV: 0.0069, AllV: 0.0732 +[2026-03-20T17:33:39.801196Z] Loop 700: Reg: 0.5127, AltReg: 0.8090, CorReg: 0.0683, TopReg: 0.6384, AllReg: 0.8091, BotRReg: 0.8510, OV: 0.3508, AltV: 0.0732, CorV: 0.7673, TopV: 0.2203, BotRV: 0.0076, AllV: 0.0732 +[2026-03-20T17:33:44.108403Z] Loop 705: Reg: 0.5123, AltReg: 0.8089, CorReg: 0.0673, TopReg: 0.6285, AllReg: 0.8090, BotRReg: 0.8516, OV: 0.3513, AltV: 0.0733, CorV: 0.7683, TopV: 0.2301, BotRV: 0.0070, AllV: 0.0733 +[2026-03-20T17:33:48.413467Z] Loop 710: Reg: 0.5123, AltReg: 0.8088, CorReg: 0.0675, TopReg: 0.6257, AllReg: 0.8089, BotRReg: 0.8517, OV: 0.3513, AltV: 0.0734, CorV: 0.7681, TopV: 0.2329, BotRV: 0.0069, AllV: 0.0734 +[2026-03-20T17:33:52.721899Z] Loop 715: Reg: 0.5123, AltReg: 0.8087, CorReg: 0.0676, TopReg: 0.6257, AllReg: 0.8088, BotRReg: 0.8517, OV: 0.3513, AltV: 0.0735, CorV: 0.7680, TopV: 0.2329, BotRV: 0.0069, AllV: 0.0735 +[2026-03-20T17:33:57.028616Z] Loop 720: Reg: 0.5125, AltReg: 0.8086, CorReg: 0.0683, TopReg: 0.6164, AllReg: 0.8087, BotRReg: 0.8522, OV: 0.3511, AltV: 0.0736, CorV: 0.7673, TopV: 0.2422, BotRV: 0.0064, AllV: 0.0736 +[2026-03-20T17:34:01.333471Z] Loop 725: Reg: 0.5127, AltReg: 0.8086, CorReg: 0.0687, TopReg: 0.6135, AllReg: 0.8087, BotRReg: 0.8524, OV: 0.3509, AltV: 0.0736, CorV: 0.7669, TopV: 0.2451, BotRV: 0.0062, AllV: 0.0736 +[2026-03-20T17:34:05.636454Z] Loop 730: Reg: 0.5123, AltReg: 0.8086, CorReg: 0.0678, TopReg: 0.6217, AllReg: 0.8087, BotRReg: 0.8519, OV: 0.3513, AltV: 0.0736, CorV: 0.7679, TopV: 0.2370, BotRV: 0.0067, AllV: 0.0736 +[2026-03-20T17:34:09.938650Z] Loop 735: Reg: 0.5122, AltReg: 0.8086, CorReg: 0.0676, TopReg: 0.6271, AllReg: 0.8087, BotRReg: 0.8516, OV: 0.3513, AltV: 0.0736, CorV: 0.7680, TopV: 0.2316, BotRV: 0.0070, AllV: 0.0735 +[2026-03-20T17:34:14.243219Z] Loop 740: Reg: 0.5122, AltReg: 0.8087, CorReg: 0.0675, TopReg: 0.6249, AllReg: 0.8087, BotRReg: 0.8517, OV: 0.3514, AltV: 0.0735, CorV: 0.7682, TopV: 0.2337, BotRV: 0.0069, AllV: 0.0735 +[2026-03-20T17:34:18.547758Z] Loop 745: Reg: 0.5123, AltReg: 0.8087, CorReg: 0.0679, TopReg: 0.6174, AllReg: 0.8087, BotRReg: 0.8522, OV: 0.3512, AltV: 0.0736, CorV: 0.7678, TopV: 0.2413, BotRV: 0.0064, AllV: 0.0735 +[2026-03-20T17:34:22.854574Z] Loop 750: Reg: 0.5130, AltReg: 0.8086, CorReg: 0.0694, TopReg: 0.6088, AllReg: 0.8087, BotRReg: 0.8526, OV: 0.3506, AltV: 0.0736, CorV: 0.7662, TopV: 0.2499, BotRV: 0.0060, AllV: 0.0736 +[2026-03-20T17:34:27.157345Z] Loop 755: Reg: 0.5125, AltReg: 0.8085, CorReg: 0.0685, TopReg: 0.6132, AllReg: 0.8086, BotRReg: 0.8524, OV: 0.3510, AltV: 0.0737, CorV: 0.7671, TopV: 0.2454, BotRV: 0.0062, AllV: 0.0736 +[2026-03-20T17:34:31.460671Z] Loop 760: Reg: 0.5122, AltReg: 0.8086, CorReg: 0.0678, TopReg: 0.6307, AllReg: 0.8086, BotRReg: 0.8514, OV: 0.3513, AltV: 0.0737, CorV: 0.7678, TopV: 0.2280, BotRV: 0.0073, AllV: 0.0736 +[2026-03-20T17:34:35.761784Z] Loop 765: Reg: 0.5129, AltReg: 0.8086, CorReg: 0.0693, TopReg: 0.6396, AllReg: 0.8087, BotRReg: 0.8508, OV: 0.3507, AltV: 0.0736, CorV: 0.7663, TopV: 0.2190, BotRV: 0.0079, AllV: 0.0736 +[2026-03-20T17:34:40.064169Z] Loop 770: Reg: 0.5121, AltReg: 0.8084, CorReg: 0.0676, TopReg: 0.6242, AllReg: 0.8085, BotRReg: 0.8517, OV: 0.3515, AltV: 0.0738, CorV: 0.7680, TopV: 0.2344, BotRV: 0.0069, AllV: 0.0738 +[2026-03-20T17:34:44.369659Z] Loop 775: Reg: 0.5127, AltReg: 0.8083, CorReg: 0.0694, TopReg: 0.6098, AllReg: 0.8084, BotRReg: 0.8525, OV: 0.3508, AltV: 0.0739, CorV: 0.7663, TopV: 0.2488, BotRV: 0.0061, AllV: 0.0738 +[2026-03-20T17:34:48.673122Z] Loop 780: Reg: 0.5121, AltReg: 0.8084, CorReg: 0.0677, TopReg: 0.6216, AllReg: 0.8084, BotRReg: 0.8518, OV: 0.3515, AltV: 0.0739, CorV: 0.7679, TopV: 0.2371, BotRV: 0.0068, AllV: 0.0738 +[2026-03-20T17:34:52.974365Z] Loop 785: Reg: 0.5126, AltReg: 0.8085, CorReg: 0.0687, TopReg: 0.6381, AllReg: 0.8086, BotRReg: 0.8508, OV: 0.3510, AltV: 0.0737, CorV: 0.7670, TopV: 0.2205, BotRV: 0.0078, AllV: 0.0736 +[2026-03-20T17:34:57.274983Z] Loop 790: Reg: 0.5124, AltReg: 0.8086, CorReg: 0.0682, TopReg: 0.6366, AllReg: 0.8086, BotRReg: 0.8510, OV: 0.3512, AltV: 0.0737, CorV: 0.7674, TopV: 0.2220, BotRV: 0.0077, AllV: 0.0736 +[2026-03-20T17:35:01.580034Z] Loop 795: Reg: 0.5120, AltReg: 0.8084, CorReg: 0.0672, TopReg: 0.6226, AllReg: 0.8085, BotRReg: 0.8518, OV: 0.3516, AltV: 0.0738, CorV: 0.7684, TopV: 0.2360, BotRV: 0.0068, AllV: 0.0737 +[2026-03-20T17:35:05.881729Z] Loop 800: Reg: 0.5127, AltReg: 0.8085, CorReg: 0.0690, TopReg: 0.6088, AllReg: 0.8085, BotRReg: 0.8526, OV: 0.3509, AltV: 0.0738, CorV: 0.7666, TopV: 0.2498, BotRV: 0.0061, AllV: 0.0737 +[2026-03-20T17:35:10.185546Z] Loop 805: Reg: 0.5125, AltReg: 0.8085, CorReg: 0.0686, TopReg: 0.6096, AllReg: 0.8086, BotRReg: 0.8525, OV: 0.3510, AltV: 0.0737, CorV: 0.7670, TopV: 0.2490, BotRV: 0.0061, AllV: 0.0737 +[2026-03-20T17:35:14.486063Z] Loop 810: Reg: 0.5124, AltReg: 0.8087, CorReg: 0.0679, TopReg: 0.6379, AllReg: 0.8087, BotRReg: 0.8509, OV: 0.3512, AltV: 0.0736, CorV: 0.7677, TopV: 0.2207, BotRV: 0.0077, AllV: 0.0735 +[2026-03-20T17:35:18.790058Z] Loop 815: Reg: 0.5129, AltReg: 0.8087, CorReg: 0.0693, TopReg: 0.6439, AllReg: 0.8088, BotRReg: 0.8505, OV: 0.3506, AltV: 0.0735, CorV: 0.7663, TopV: 0.2147, BotRV: 0.0081, AllV: 0.0735 +[2026-03-20T17:35:23.093185Z] Loop 820: Reg: 0.5121, AltReg: 0.8083, CorReg: 0.0678, TopReg: 0.6147, AllReg: 0.8084, BotRReg: 0.8522, OV: 0.3515, AltV: 0.0739, CorV: 0.7678, TopV: 0.2440, BotRV: 0.0064, AllV: 0.0738 +[2026-03-20T17:35:27.400516Z] Loop 825: Reg: 0.5129, AltReg: 0.8083, CorReg: 0.0698, TopReg: 0.6057, AllReg: 0.8083, BotRReg: 0.8527, OV: 0.3507, AltV: 0.0739, CorV: 0.7659, TopV: 0.2529, BotRV: 0.0059, AllV: 0.0739 +[2026-03-20T17:35:31.709300Z] Loop 830: Reg: 0.5121, AltReg: 0.8083, CorReg: 0.0679, TopReg: 0.6136, AllReg: 0.8083, BotRReg: 0.8523, OV: 0.3515, AltV: 0.0740, CorV: 0.7678, TopV: 0.2450, BotRV: 0.0064, AllV: 0.0739 +[2026-03-20T17:35:36.012698Z] Loop 835: Reg: 0.5117, AltReg: 0.8083, CorReg: 0.0669, TopReg: 0.6225, AllReg: 0.8084, BotRReg: 0.8517, OV: 0.3519, AltV: 0.0739, CorV: 0.7688, TopV: 0.2361, BotRV: 0.0069, AllV: 0.0739 +[2026-03-20T17:35:40.317107Z] Loop 840: Reg: 0.5117, AltReg: 0.8084, CorReg: 0.0667, TopReg: 0.6288, AllReg: 0.8085, BotRReg: 0.8514, OV: 0.3519, AltV: 0.0738, CorV: 0.7689, TopV: 0.2298, BotRV: 0.0072, AllV: 0.0738 +[2026-03-20T17:35:44.619996Z] Loop 845: Reg: 0.5116, AltReg: 0.8084, CorReg: 0.0665, TopReg: 0.6240, AllReg: 0.8084, BotRReg: 0.8517, OV: 0.3520, AltV: 0.0739, CorV: 0.7691, TopV: 0.2346, BotRV: 0.0069, AllV: 0.0738 +[2026-03-20T17:35:48.925555Z] Loop 850: Reg: 0.5117, AltReg: 0.8083, CorReg: 0.0668, TopReg: 0.6179, AllReg: 0.8084, BotRReg: 0.8521, OV: 0.3519, AltV: 0.0739, CorV: 0.7689, TopV: 0.2407, BotRV: 0.0066, AllV: 0.0739 +[2026-03-20T17:35:53.231739Z] Loop 855: Reg: 0.5115, AltReg: 0.8084, CorReg: 0.0662, TopReg: 0.6233, AllReg: 0.8084, BotRReg: 0.8517, OV: 0.3521, AltV: 0.0739, CorV: 0.7694, TopV: 0.2353, BotRV: 0.0069, AllV: 0.0738 +[2026-03-20T17:35:57.541399Z] Loop 860: Reg: 0.5115, AltReg: 0.8084, CorReg: 0.0660, TopReg: 0.6197, AllReg: 0.8085, BotRReg: 0.8520, OV: 0.3521, AltV: 0.0738, CorV: 0.7697, TopV: 0.2390, BotRV: 0.0067, AllV: 0.0737 +[2026-03-20T17:36:01.844921Z] Loop 865: Reg: 0.5118, AltReg: 0.8085, CorReg: 0.0669, TopReg: 0.6111, AllReg: 0.8085, BotRReg: 0.8524, OV: 0.3517, AltV: 0.0738, CorV: 0.7687, TopV: 0.2476, BotRV: 0.0062, AllV: 0.0737 +[2026-03-20T17:36:06.149186Z] Loop 870: Reg: 0.5112, AltReg: 0.8085, CorReg: 0.0654, TopReg: 0.6211, AllReg: 0.8085, BotRReg: 0.8519, OV: 0.3523, AltV: 0.0738, CorV: 0.7702, TopV: 0.2375, BotRV: 0.0068, AllV: 0.0737 +[2026-03-20T17:36:10.455780Z] Loop 875: Reg: 0.5112, AltReg: 0.8085, CorReg: 0.0651, TopReg: 0.6295, AllReg: 0.8086, BotRReg: 0.8514, OV: 0.3524, AltV: 0.0737, CorV: 0.7705, TopV: 0.2291, BotRV: 0.0073, AllV: 0.0737 +[2026-03-20T17:36:14.759130Z] Loop 880: Reg: 0.5113, AltReg: 0.8085, CorReg: 0.0655, TopReg: 0.6150, AllReg: 0.8085, BotRReg: 0.8522, OV: 0.3523, AltV: 0.0737, CorV: 0.7701, TopV: 0.2436, BotRV: 0.0064, AllV: 0.0737 +[2026-03-20T17:36:19.064861Z] Loop 885: Reg: 0.5113, AltReg: 0.8085, CorReg: 0.0654, TopReg: 0.6141, AllReg: 0.8086, BotRReg: 0.8523, OV: 0.3523, AltV: 0.0737, CorV: 0.7702, TopV: 0.2446, BotRV: 0.0063, AllV: 0.0737 +[2026-03-20T17:36:23.365966Z] Loop 890: Reg: 0.5114, AltReg: 0.8087, CorReg: 0.0654, TopReg: 0.6398, AllReg: 0.8088, BotRReg: 0.8508, OV: 0.3522, AltV: 0.0735, CorV: 0.7702, TopV: 0.2188, BotRV: 0.0078, AllV: 0.0735 +[2026-03-20T17:36:27.667502Z] Loop 895: Reg: 0.5112, AltReg: 0.8086, CorReg: 0.0650, TopReg: 0.6389, AllReg: 0.8087, BotRReg: 0.8508, OV: 0.3524, AltV: 0.0736, CorV: 0.7706, TopV: 0.2198, BotRV: 0.0078, AllV: 0.0735 +[2026-03-20T17:36:31.967664Z] Loop 900: Reg: 0.5110, AltReg: 0.8084, CorReg: 0.0650, TopReg: 0.6125, AllReg: 0.8085, BotRReg: 0.8523, OV: 0.3525, AltV: 0.0738, CorV: 0.7707, TopV: 0.2462, BotRV: 0.0063, AllV: 0.0738 +[2026-03-20T17:36:36.270271Z] Loop 905: Reg: 0.5105, AltReg: 0.8084, CorReg: 0.0636, TopReg: 0.6231, AllReg: 0.8085, BotRReg: 0.8517, OV: 0.3531, AltV: 0.0738, CorV: 0.7720, TopV: 0.2355, BotRV: 0.0070, AllV: 0.0738 +[2026-03-20T17:36:40.568580Z] Loop 910: Reg: 0.5119, AltReg: 0.8087, CorReg: 0.0666, TopReg: 0.6486, AllReg: 0.8087, BotRReg: 0.8500, OV: 0.3517, AltV: 0.0735, CorV: 0.7690, TopV: 0.2100, BotRV: 0.0086, AllV: 0.0735 +[2026-03-20T17:36:44.871856Z] Loop 915: Reg: 0.5102, AltReg: 0.8085, CorReg: 0.0628, TopReg: 0.6288, AllReg: 0.8086, BotRReg: 0.8515, OV: 0.3534, AltV: 0.0737, CorV: 0.7728, TopV: 0.2298, BotRV: 0.0072, AllV: 0.0737 +[2026-03-20T17:36:49.180355Z] Loop 920: Reg: 0.5105, AltReg: 0.8084, CorReg: 0.0636, TopReg: 0.6145, AllReg: 0.8085, BotRReg: 0.8523, OV: 0.3531, AltV: 0.0738, CorV: 0.7720, TopV: 0.2441, BotRV: 0.0064, AllV: 0.0738 +[2026-03-20T17:36:53.487307Z] Loop 925: Reg: 0.5101, AltReg: 0.8084, CorReg: 0.0625, TopReg: 0.6334, AllReg: 0.8085, BotRReg: 0.8512, OV: 0.3535, AltV: 0.0738, CorV: 0.7732, TopV: 0.2252, BotRV: 0.0074, AllV: 0.0737 +[2026-03-20T17:36:57.792645Z] Loop 930: Reg: 0.5105, AltReg: 0.8085, CorReg: 0.0636, TopReg: 0.6438, AllReg: 0.8086, BotRReg: 0.8505, OV: 0.3530, AltV: 0.0737, CorV: 0.7721, TopV: 0.2148, BotRV: 0.0081, AllV: 0.0737 +[2026-03-20T17:37:02.102305Z] Loop 935: Reg: 0.5095, AltReg: 0.8082, CorReg: 0.0614, TopReg: 0.6215, AllReg: 0.8083, BotRReg: 0.8517, OV: 0.3541, AltV: 0.0740, CorV: 0.7742, TopV: 0.2372, BotRV: 0.0069, AllV: 0.0740 +[2026-03-20T17:37:06.408677Z] Loop 940: Reg: 0.5091, AltReg: 0.8081, CorReg: 0.0607, TopReg: 0.6237, AllReg: 0.8082, BotRReg: 0.8516, OV: 0.3544, AltV: 0.0741, CorV: 0.7750, TopV: 0.2350, BotRV: 0.0070, AllV: 0.0740 +[2026-03-20T17:37:10.714123Z] Loop 945: Reg: 0.5089, AltReg: 0.8081, CorReg: 0.0600, TopReg: 0.6201, AllReg: 0.8082, BotRReg: 0.8518, OV: 0.3547, AltV: 0.0741, CorV: 0.7757, TopV: 0.2385, BotRV: 0.0068, AllV: 0.0741 +[2026-03-20T17:37:15.016847Z] Loop 950: Reg: 0.5089, AltReg: 0.8080, CorReg: 0.0602, TopReg: 0.6126, AllReg: 0.8081, BotRReg: 0.8522, OV: 0.3547, AltV: 0.0742, CorV: 0.7755, TopV: 0.2460, BotRV: 0.0064, AllV: 0.0741 +[2026-03-20T17:37:19.319584Z] Loop 955: Reg: 0.5085, AltReg: 0.8080, CorReg: 0.0592, TopReg: 0.6406, AllReg: 0.8081, BotRReg: 0.8506, OV: 0.3551, AltV: 0.0742, CorV: 0.7764, TopV: 0.2181, BotRV: 0.0080, AllV: 0.0741 +[2026-03-20T17:37:23.623196Z] Loop 960: Reg: 0.5076, AltReg: 0.8077, CorReg: 0.0574, TopReg: 0.6286, AllReg: 0.8078, BotRReg: 0.8512, OV: 0.3560, AltV: 0.0745, CorV: 0.7783, TopV: 0.2300, BotRV: 0.0074, AllV: 0.0744 +[2026-03-20T17:37:27.927500Z] Loop 965: Reg: 0.5073, AltReg: 0.8075, CorReg: 0.0569, TopReg: 0.6182, AllReg: 0.8076, BotRReg: 0.8517, OV: 0.3563, AltV: 0.0747, CorV: 0.7788, TopV: 0.2404, BotRV: 0.0069, AllV: 0.0747 +[2026-03-20T17:37:32.231490Z] Loop 970: Reg: 0.5065, AltReg: 0.8074, CorReg: 0.0552, TopReg: 0.6235, AllReg: 0.8075, BotRReg: 0.8514, OV: 0.3571, AltV: 0.0748, CorV: 0.7804, TopV: 0.2352, BotRV: 0.0072, AllV: 0.0748 +[2026-03-20T17:37:36.534845Z] Loop 975: Reg: 0.5058, AltReg: 0.8072, CorReg: 0.0537, TopReg: 0.6296, AllReg: 0.8073, BotRReg: 0.8510, OV: 0.3578, AltV: 0.0750, CorV: 0.7819, TopV: 0.2290, BotRV: 0.0076, AllV: 0.0750 +[2026-03-20T17:37:40.838464Z] Loop 980: Reg: 0.5051, AltReg: 0.8070, CorReg: 0.0523, TopReg: 0.6357, AllReg: 0.8071, BotRReg: 0.8506, OV: 0.3584, AltV: 0.0752, CorV: 0.7833, TopV: 0.2230, BotRV: 0.0081, AllV: 0.0752 +[2026-03-20T17:37:45.140140Z] Loop 985: Reg: 0.5043, AltReg: 0.8068, CorReg: 0.0505, TopReg: 0.6187, AllReg: 0.8069, BotRReg: 0.8514, OV: 0.3593, AltV: 0.0754, CorV: 0.7851, TopV: 0.2399, BotRV: 0.0073, AllV: 0.0754 +[2026-03-20T17:37:49.443346Z] Loop 990: Reg: 0.5032, AltReg: 0.8064, CorReg: 0.0483, TopReg: 0.6266, AllReg: 0.8065, BotRReg: 0.8509, OV: 0.3604, AltV: 0.0758, CorV: 0.7873, TopV: 0.2320, BotRV: 0.0077, AllV: 0.0757 +[2026-03-20T17:37:53.744462Z] Loop 995: Reg: 0.5055, AltReg: 0.8062, CorReg: 0.0543, TopReg: 0.6673, AllReg: 0.8063, BotRReg: 0.8482, OV: 0.3581, AltV: 0.0760, CorV: 0.7813, TopV: 0.1913, BotRV: 0.0104, AllV: 0.0760 +[2026-03-20T17:37:58.045674Z] Loop 1000: Reg: 0.5050, AltReg: 0.8063, CorReg: 0.0531, TopReg: 0.5850, AllReg: 0.8064, BotRReg: 0.8526, OV: 0.3586, AltV: 0.0759, CorV: 0.7826, TopV: 0.2736, BotRV: 0.0060, AllV: 0.0759 +[2026-03-20T17:38:02.346791Z] Loop 1005: Reg: 0.5002, AltReg: 0.8048, CorReg: 0.0433, TopReg: 0.6435, AllReg: 0.8049, BotRReg: 0.8495, OV: 0.3634, AltV: 0.0774, CorV: 0.7923, TopV: 0.2151, BotRV: 0.0092, AllV: 0.0774 +[2026-03-20T17:38:06.649023Z] Loop 1010: Reg: 0.4993, AltReg: 0.8047, CorReg: 0.0411, TopReg: 0.6118, AllReg: 0.8048, BotRReg: 0.8510, OV: 0.3643, AltV: 0.0775, CorV: 0.7945, TopV: 0.2468, BotRV: 0.0076, AllV: 0.0775 +[2026-03-20T17:38:10.953820Z] Loop 1015: Reg: 0.4975, AltReg: 0.8038, CorReg: 0.0381, TopReg: 0.6112, AllReg: 0.8039, BotRReg: 0.8507, OV: 0.3660, AltV: 0.0784, CorV: 0.7975, TopV: 0.2474, BotRV: 0.0079, AllV: 0.0783 +[2026-03-20T17:38:15.255932Z] Loop 1020: Reg: 0.4955, AltReg: 0.8019, CorReg: 0.0358, TopReg: 0.6472, AllReg: 0.8020, BotRReg: 0.8481, OV: 0.3681, AltV: 0.0803, CorV: 0.7998, TopV: 0.2114, BotRV: 0.0105, AllV: 0.0802 +[2026-03-20T17:38:19.560070Z] Loop 1025: Reg: 0.4948, AltReg: 0.8023, CorReg: 0.0336, TopReg: 0.5972, AllReg: 0.8024, BotRReg: 0.8505, OV: 0.3688, AltV: 0.0799, CorV: 0.8021, TopV: 0.2614, BotRV: 0.0081, AllV: 0.0798 +[2026-03-20T17:38:23.864128Z] Loop 1030: Reg: 0.4941, AltReg: 0.7985, CorReg: 0.0374, TopReg: 0.6774, AllReg: 0.7986, BotRReg: 0.8446, OV: 0.3695, AltV: 0.0837, CorV: 0.7982, TopV: 0.1812, BotRV: 0.0140, AllV: 0.0836 +[2026-03-20T17:38:28.169911Z] Loop 1035: Reg: 0.4889, AltReg: 0.7990, CorReg: 0.0237, TopReg: 0.6124, AllReg: 0.7991, BotRReg: 0.8485, OV: 0.3747, AltV: 0.0832, CorV: 0.8119, TopV: 0.2463, BotRV: 0.0102, AllV: 0.0832 +[2026-03-20T17:38:32.470783Z] Loop 1040: Reg: 0.4882, AltReg: 0.7984, CorReg: 0.0228, TopReg: 0.5891, AllReg: 0.7985, BotRReg: 0.8488, OV: 0.3754, AltV: 0.0838, CorV: 0.8128, TopV: 0.2696, BotRV: 0.0098, AllV: 0.0838 +[2026-03-20T17:38:36.770969Z] Loop 1045: Reg: 0.4827, AltReg: 0.7929, CorReg: 0.0174, TopReg: 0.6331, AllReg: 0.7930, BotRReg: 0.8445, OV: 0.3809, AltV: 0.0893, CorV: 0.8182, TopV: 0.2255, BotRV: 0.0141, AllV: 0.0892 +[2026-03-20T17:38:41.072610Z] Loop 1050: Reg: 0.4808, AltReg: 0.7879, CorReg: 0.0202, TopReg: 0.6646, AllReg: 0.7880, BotRReg: 0.8400, OV: 0.3828, AltV: 0.0943, CorV: 0.8154, TopV: 0.1941, BotRV: 0.0186, AllV: 0.0943 +[2026-03-20T17:38:45.373878Z] Loop 1055: Reg: 0.4776, AltReg: 0.7878, CorReg: 0.0122, TopReg: 0.6147, AllReg: 0.7880, BotRReg: 0.8423, OV: 0.3860, AltV: 0.0944, CorV: 0.8234, TopV: 0.2439, BotRV: 0.0163, AllV: 0.0943 +[2026-03-20T17:38:49.676411Z] Loop 1060: Reg: 0.4848, AltReg: 0.7946, CorReg: 0.0200, TopReg: 0.5286, AllReg: 0.7947, BotRReg: 0.8476, OV: 0.3788, AltV: 0.0876, CorV: 0.8156, TopV: 0.3300, BotRV: 0.0110, AllV: 0.0875 +[2026-03-20T17:38:53.979546Z] Loop 1065: Reg: 0.4751, AltReg: 0.7751, CorReg: 0.0252, TopReg: 0.6771, AllReg: 0.7752, BotRReg: 0.8320, OV: 0.3884, AltV: 0.1071, CorV: 0.8104, TopV: 0.1815, BotRV: 0.0267, AllV: 0.1070 +[2026-03-20T17:38:58.283637Z] Loop 1070: Reg: 0.4708, AltReg: 0.7798, CorReg: 0.0074, TopReg: 0.5790, AllReg: 0.7799, BotRReg: 0.8392, OV: 0.3927, AltV: 0.1024, CorV: 0.8283, TopV: 0.2796, BotRV: 0.0194, AllV: 0.1023 +[2026-03-20T17:39:02.587012Z] Loop 1075: Reg: 0.4664, AltReg: 0.7726, CorReg: 0.0071, TopReg: 0.6024, AllReg: 0.7727, BotRReg: 0.8354, OV: 0.3972, AltV: 0.1096, CorV: 0.8285, TopV: 0.2562, BotRV: 0.0233, AllV: 0.1095 +[2026-03-20T17:39:06.889552Z] Loop 1080: Reg: 0.4633, AltReg: 0.7676, CorReg: 0.0069, TopReg: 0.6041, AllReg: 0.7677, BotRReg: 0.8331, OV: 0.4003, AltV: 0.1147, CorV: 0.8287, TopV: 0.2546, BotRV: 0.0255, AllV: 0.1145 +[2026-03-20T17:39:11.192218Z] Loop 1085: Reg: 0.4600, AltReg: 0.7618, CorReg: 0.0074, TopReg: 0.6030, AllReg: 0.7620, BotRReg: 0.8309, OV: 0.4036, AltV: 0.1204, CorV: 0.8283, TopV: 0.2556, BotRV: 0.0277, AllV: 0.1203 +[2026-03-20T17:39:15.496526Z] Loop 1090: Reg: 0.4580, AltReg: 0.7595, CorReg: 0.0058, TopReg: 0.5657, AllReg: 0.7597, BotRReg: 0.8316, OV: 0.4056, AltV: 0.1227, CorV: 0.8299, TopV: 0.2930, BotRV: 0.0270, AllV: 0.1226 +[2026-03-20T17:39:19.798648Z] Loop 1095: Reg: 0.4555, AltReg: 0.7472, CorReg: 0.0179, TopReg: 0.6223, AllReg: 0.7474, BotRReg: 0.8264, OV: 0.4081, AltV: 0.1350, CorV: 0.8178, TopV: 0.2363, BotRV: 0.0322, AllV: 0.1349 +[2026-03-20T17:39:24.103441Z] Loop 1100: Reg: 0.4577, AltReg: 0.7594, CorReg: 0.0053, TopReg: 0.5099, AllReg: 0.7595, BotRReg: 0.8350, OV: 0.4058, AltV: 0.1228, CorV: 0.8303, TopV: 0.3487, BotRV: 0.0236, AllV: 0.1227 +[2026-03-20T17:39:28.412509Z] Loop 1105: Reg: 0.4501, AltReg: 0.7401, CorReg: 0.0149, TopReg: 0.6209, AllReg: 0.7403, BotRReg: 0.8263, OV: 0.4135, AltV: 0.1421, CorV: 0.8207, TopV: 0.2378, BotRV: 0.0323, AllV: 0.1419 +[2026-03-20T17:39:32.715162Z] Loop 1110: Reg: 0.4437, AltReg: 0.7360, CorReg: 0.0052, TopReg: 0.5525, AllReg: 0.7362, BotRReg: 0.8290, OV: 0.4199, AltV: 0.1462, CorV: 0.8304, TopV: 0.3061, BotRV: 0.0296, AllV: 0.1460 +[2026-03-20T17:39:37.020378Z] Loop 1115: Reg: 0.4394, AltReg: 0.7255, CorReg: 0.0102, TopReg: 0.5772, AllReg: 0.7257, BotRReg: 0.8261, OV: 0.4242, AltV: 0.1567, CorV: 0.8255, TopV: 0.2814, BotRV: 0.0325, AllV: 0.1566 +[2026-03-20T17:39:41.322529Z] Loop 1120: Reg: 0.4386, AltReg: 0.7286, CorReg: 0.0037, TopReg: 0.5003, AllReg: 0.7288, BotRReg: 0.8294, OV: 0.4250, AltV: 0.1536, CorV: 0.8319, TopV: 0.3584, BotRV: 0.0293, AllV: 0.1535 +[2026-03-20T17:39:45.628021Z] Loop 1125: Reg: 0.4297, AltReg: 0.7100, CorReg: 0.0093, TopReg: 0.5522, AllReg: 0.7103, BotRReg: 0.8242, OV: 0.4338, AltV: 0.1722, CorV: 0.8264, TopV: 0.3064, BotRV: 0.0344, AllV: 0.1720 +[2026-03-20T17:39:49.933067Z] Loop 1130: Reg: 0.4255, AltReg: 0.7024, CorReg: 0.0101, TopReg: 0.5461, AllReg: 0.7027, BotRReg: 0.8233, OV: 0.4381, AltV: 0.1798, CorV: 0.8255, TopV: 0.3126, BotRV: 0.0353, AllV: 0.1796 +[2026-03-20T17:39:54.237261Z] Loop 1135: Reg: 0.4230, AltReg: 0.7032, CorReg: 0.0025, TopReg: 0.4837, AllReg: 0.7035, BotRReg: 0.8262, OV: 0.4406, AltV: 0.1790, CorV: 0.8331, TopV: 0.3749, BotRV: 0.0325, AllV: 0.1788 +[2026-03-20T17:39:58.544192Z] Loop 1140: Reg: 0.4162, AltReg: 0.6872, CorReg: 0.0097, TopReg: 0.5230, AllReg: 0.6875, BotRReg: 0.8227, OV: 0.4474, AltV: 0.1950, CorV: 0.8259, TopV: 0.3357, BotRV: 0.0359, AllV: 0.1948 +[2026-03-20T17:40:02.853712Z] Loop 1145: Reg: 0.4108, AltReg: 0.6819, CorReg: 0.0042, TopReg: 0.4921, AllReg: 0.6822, BotRReg: 0.8237, OV: 0.4527, AltV: 0.2003, CorV: 0.8314, TopV: 0.3666, BotRV: 0.0349, AllV: 0.2000 +[2026-03-20T17:40:07.163648Z] Loop 1150: Reg: 0.4078, AltReg: 0.6781, CorReg: 0.0022, TopReg: 0.4793, AllReg: 0.6784, BotRReg: 0.8241, OV: 0.4558, AltV: 0.2041, CorV: 0.8334, TopV: 0.3793, BotRV: 0.0345, AllV: 0.2038 +[2026-03-20T17:40:11.468747Z] Loop 1155: Reg: 0.4040, AltReg: 0.6713, CorReg: 0.0032, TopReg: 0.4866, AllReg: 0.6716, BotRReg: 0.8225, OV: 0.4595, AltV: 0.2109, CorV: 0.8325, TopV: 0.3720, BotRV: 0.0361, AllV: 0.2107 +[2026-03-20T17:40:15.778026Z] Loop 1160: Reg: 0.4052, AltReg: 0.6748, CorReg: 0.0009, TopReg: 0.4472, AllReg: 0.6751, BotRReg: 0.8254, OV: 0.4583, AltV: 0.2074, CorV: 0.8347, TopV: 0.4114, BotRV: 0.0332, AllV: 0.2071 +[2026-03-20T17:40:20.084242Z] Loop 1165: Reg: 0.3993, AltReg: 0.6647, CorReg: 0.0012, TopReg: 0.4763, AllReg: 0.6650, BotRReg: 0.8225, OV: 0.4643, AltV: 0.2175, CorV: 0.8344, TopV: 0.3824, BotRV: 0.0361, AllV: 0.2173 +[2026-03-20T17:40:24.391568Z] Loop 1170: Reg: 0.4037, AltReg: 0.6717, CorReg: 0.0017, TopReg: 0.5174, AllReg: 0.6720, BotRReg: 0.8215, OV: 0.4598, AltV: 0.2105, CorV: 0.8339, TopV: 0.3412, BotRV: 0.0372, AllV: 0.2102 +[2026-03-20T17:40:28.700230Z] Loop 1175: Reg: 0.3992, AltReg: 0.6650, CorReg: 0.0003, TopReg: 0.4503, AllReg: 0.6653, BotRReg: 0.8260, OV: 0.4644, AltV: 0.2172, CorV: 0.8353, TopV: 0.4083, BotRV: 0.0326, AllV: 0.2169 +[2026-03-20T17:40:33.005339Z] Loop 1180: Reg: 0.3937, AltReg: 0.6560, CorReg: 0.0002, TopReg: 0.4406, AllReg: 0.6563, BotRReg: 0.8238, OV: 0.4699, AltV: 0.2262, CorV: 0.8354, TopV: 0.4181, BotRV: 0.0348, AllV: 0.2259 +[2026-03-20T17:40:37.307895Z] Loop 1185: Reg: 0.3914, AltReg: 0.6521, CorReg: 0.0002, TopReg: 0.4360, AllReg: 0.6524, BotRReg: 0.8229, OV: 0.4722, AltV: 0.2301, CorV: 0.8354, TopV: 0.4226, BotRV: 0.0357, AllV: 0.2298 +[2026-03-20T17:40:41.612104Z] Loop 1190: Reg: 0.3886, AltReg: 0.6473, CorReg: 0.0005, TopReg: 0.4390, AllReg: 0.6476, BotRReg: 0.8211, OV: 0.4750, AltV: 0.2349, CorV: 0.8351, TopV: 0.4196, BotRV: 0.0375, AllV: 0.2346 +[2026-03-20T17:40:45.920588Z] Loop 1195: Reg: 0.3931, AltReg: 0.6525, CorReg: 0.0039, TopReg: 0.4658, AllReg: 0.6528, BotRReg: 0.8199, OV: 0.4705, AltV: 0.2297, CorV: 0.8317, TopV: 0.3928, BotRV: 0.0388, AllV: 0.2294 +[2026-03-20T17:40:50.227088Z] Loop 1200: Reg: 0.3863, AltReg: 0.6436, CorReg: 0.0003, TopReg: 0.4364, AllReg: 0.6439, BotRReg: 0.8212, OV: 0.4773, AltV: 0.2386, CorV: 0.8354, TopV: 0.4222, BotRV: 0.0374, AllV: 0.2383 +[2026-03-20T17:40:54.529553Z] Loop 1205: Reg: 0.3882, AltReg: 0.6470, CorReg: 0.0001, TopReg: 0.4315, AllReg: 0.6473, BotRReg: 0.8259, OV: 0.4753, AltV: 0.2352, CorV: 0.8355, TopV: 0.4271, BotRV: 0.0327, AllV: 0.2349 +[2026-03-20T17:40:58.831611Z] Loop 1210: Reg: 0.3971, AltReg: 0.6604, CorReg: 0.0021, TopReg: 0.4948, AllReg: 0.6607, BotRReg: 0.8197, OV: 0.4665, AltV: 0.2218, CorV: 0.8336, TopV: 0.3638, BotRV: 0.0389, AllV: 0.2215 +[2026-03-20T17:41:03.136173Z] Loop 1215: Reg: 0.3895, AltReg: 0.6490, CorReg: 0.0004, TopReg: 0.4543, AllReg: 0.6493, BotRReg: 0.8201, OV: 0.4741, AltV: 0.2333, CorV: 0.8353, TopV: 0.4044, BotRV: 0.0385, AllV: 0.2330 +[2026-03-20T17:41:07.439830Z] Loop 1220: Reg: 0.3933, AltReg: 0.6554, CorReg: 0.0002, TopReg: 0.4263, AllReg: 0.6557, BotRReg: 0.8338, OV: 0.4702, AltV: 0.2268, CorV: 0.8354, TopV: 0.4324, BotRV: 0.0248, AllV: 0.2265 +[2026-03-20T17:41:11.743004Z] Loop 1225: Reg: 0.3833, AltReg: 0.6388, CorReg: 0.0000, TopReg: 0.4324, AllReg: 0.6391, BotRReg: 0.8220, OV: 0.4803, AltV: 0.2434, CorV: 0.8356, TopV: 0.4262, BotRV: 0.0366, AllV: 0.2431 +[2026-03-20T17:41:16.048248Z] Loop 1230: Reg: 0.3864, AltReg: 0.6427, CorReg: 0.0020, TopReg: 0.4418, AllReg: 0.6431, BotRReg: 0.8196, OV: 0.4772, AltV: 0.2395, CorV: 0.8337, TopV: 0.4168, BotRV: 0.0390, AllV: 0.2392 +[2026-03-20T17:41:20.353474Z] Loop 1235: Reg: 0.3830, AltReg: 0.6379, CorReg: 0.0007, TopReg: 0.4338, AllReg: 0.6383, BotRReg: 0.8199, OV: 0.4805, AltV: 0.2443, CorV: 0.8350, TopV: 0.4249, BotRV: 0.0387, AllV: 0.2440 +[2026-03-20T17:41:24.658405Z] Loop 1240: Reg: 0.3826, AltReg: 0.6372, CorReg: 0.0007, TopReg: 0.4293, AllReg: 0.6375, BotRReg: 0.8200, OV: 0.4810, AltV: 0.2451, CorV: 0.8350, TopV: 0.4293, BotRV: 0.0386, AllV: 0.2448 +[2026-03-20T17:41:28.966056Z] Loop 1245: Reg: 0.3824, AltReg: 0.6369, CorReg: 0.0008, TopReg: 0.4229, AllReg: 0.6372, BotRReg: 0.8201, OV: 0.4811, AltV: 0.2453, CorV: 0.8348, TopV: 0.4358, BotRV: 0.0385, AllV: 0.2450 +[2026-03-20T17:41:33.275827Z] Loop 1250: Reg: 0.3817, AltReg: 0.6360, CorReg: 0.0003, TopReg: 0.4213, AllReg: 0.6363, BotRReg: 0.8204, OV: 0.4819, AltV: 0.2462, CorV: 0.8353, TopV: 0.4373, BotRV: 0.0383, AllV: 0.2459 +[2026-03-20T17:41:37.585524Z] Loop 1255: Reg: 0.3812, AltReg: 0.6353, CorReg: 0.0001, TopReg: 0.4172, AllReg: 0.6357, BotRReg: 0.8213, OV: 0.4824, AltV: 0.2469, CorV: 0.8355, TopV: 0.4414, BotRV: 0.0373, AllV: 0.2466 +[2026-03-20T17:41:41.895114Z] Loop 1260: Reg: 0.3857, AltReg: 0.6428, CorReg: 0.0000, TopReg: 0.4128, AllReg: 0.6431, BotRReg: 0.8292, OV: 0.4779, AltV: 0.2394, CorV: 0.8356, TopV: 0.4458, BotRV: 0.0294, AllV: 0.2391 +[2026-03-20T17:41:46.201665Z] Loop 1265: Reg: 0.3812, AltReg: 0.6353, CorReg: 0.0000, TopReg: 0.4264, AllReg: 0.6356, BotRReg: 0.8219, OV: 0.4824, AltV: 0.2469, CorV: 0.8356, TopV: 0.4323, BotRV: 0.0368, AllV: 0.2466 +[2026-03-20T17:41:50.509570Z] Loop 1270: Reg: 0.3935, AltReg: 0.6514, CorReg: 0.0066, TopReg: 0.4617, AllReg: 0.6517, BotRReg: 0.8195, OV: 0.4701, AltV: 0.2308, CorV: 0.8291, TopV: 0.3969, BotRV: 0.0391, AllV: 0.2305 +[2026-03-20T17:41:54.818001Z] Loop 1275: Reg: 0.3855, AltReg: 0.6412, CorReg: 0.0020, TopReg: 0.4397, AllReg: 0.6415, BotRReg: 0.8196, OV: 0.4781, AltV: 0.2411, CorV: 0.8337, TopV: 0.4189, BotRV: 0.0390, AllV: 0.2408 +[2026-03-20T17:41:59.127219Z] Loop 1280: Reg: 0.3814, AltReg: 0.6356, CorReg: 0.0000, TopReg: 0.4126, AllReg: 0.6359, BotRReg: 0.8315, OV: 0.4822, AltV: 0.2466, CorV: 0.8356, TopV: 0.4461, BotRV: 0.0271, AllV: 0.2463 +[2026-03-20T17:42:03.433219Z] Loop 1285: Reg: 0.3808, AltReg: 0.6347, CorReg: 0.0000, TopReg: 0.4124, AllReg: 0.6351, BotRReg: 0.8310, OV: 0.4827, AltV: 0.2475, CorV: 0.8356, TopV: 0.4462, BotRV: 0.0277, AllV: 0.2472 +[2026-03-20T17:42:07.740735Z] Loop 1290: Reg: 0.3810, AltReg: 0.6349, CorReg: 0.0001, TopReg: 0.4244, AllReg: 0.6352, BotRReg: 0.8204, OV: 0.4826, AltV: 0.2473, CorV: 0.8355, TopV: 0.4342, BotRV: 0.0382, AllV: 0.2470 +[2026-03-20T17:42:12.048360Z] Loop 1295: Reg: 0.3952, AltReg: 0.6542, CorReg: 0.0067, TopReg: 0.4711, AllReg: 0.6545, BotRReg: 0.8195, OV: 0.4683, AltV: 0.2280, CorV: 0.8289, TopV: 0.3875, BotRV: 0.0391, AllV: 0.2277 +[2026-03-20T17:42:16.357032Z] Loop 1300: Reg: 0.3807, AltReg: 0.6344, CorReg: 0.0001, TopReg: 0.4226, AllReg: 0.6347, BotRReg: 0.8202, OV: 0.4829, AltV: 0.2478, CorV: 0.8356, TopV: 0.4360, BotRV: 0.0385, AllV: 0.2475 +[2026-03-20T17:42:20.664602Z] Loop 1305: Reg: 0.3792, AltReg: 0.6319, CorReg: 0.0000, TopReg: 0.4124, AllReg: 0.6323, BotRReg: 0.8273, OV: 0.4844, AltV: 0.2503, CorV: 0.8356, TopV: 0.4462, BotRV: 0.0314, AllV: 0.2500 +[2026-03-20T17:42:24.974655Z] Loop 1310: Reg: 0.3802, AltReg: 0.6337, CorReg: 0.0001, TopReg: 0.4201, AllReg: 0.6340, BotRReg: 0.8202, OV: 0.4834, AltV: 0.2485, CorV: 0.8356, TopV: 0.4386, BotRV: 0.0384, AllV: 0.2482 +[2026-03-20T17:42:29.283435Z] Loop 1315: Reg: 0.3793, AltReg: 0.6321, CorReg: 0.0000, TopReg: 0.4150, AllReg: 0.6324, BotRReg: 0.8215, OV: 0.4843, AltV: 0.2501, CorV: 0.8356, TopV: 0.4436, BotRV: 0.0371, AllV: 0.2498 +[2026-03-20T17:42:33.589248Z] Loop 1320: Reg: 0.3788, AltReg: 0.6313, CorReg: 0.0000, TopReg: 0.4121, AllReg: 0.6317, BotRReg: 0.8294, OV: 0.4848, AltV: 0.2509, CorV: 0.8356, TopV: 0.4465, BotRV: 0.0292, AllV: 0.2506 +[2026-03-20T17:42:37.893863Z] Loop 1325: Reg: 0.3830, AltReg: 0.6383, CorReg: 0.0001, TopReg: 0.4095, AllReg: 0.6387, BotRReg: 0.8368, OV: 0.4805, AltV: 0.2439, CorV: 0.8356, TopV: 0.4491, BotRV: 0.0219, AllV: 0.2436 +[2026-03-20T17:42:42.199702Z] Loop 1330: Reg: 0.3831, AltReg: 0.6384, CorReg: 0.0001, TopReg: 0.4085, AllReg: 0.6388, BotRReg: 0.8368, OV: 0.4805, AltV: 0.2438, CorV: 0.8356, TopV: 0.4501, BotRV: 0.0218, AllV: 0.2435 +[2026-03-20T17:42:46.512312Z] Loop 1335: Reg: 0.3788, AltReg: 0.6313, CorReg: 0.0000, TopReg: 0.4119, AllReg: 0.6316, BotRReg: 0.8297, OV: 0.4848, AltV: 0.2510, CorV: 0.8356, TopV: 0.4467, BotRV: 0.0289, AllV: 0.2506 +[2026-03-20T17:42:50.824266Z] Loop 1340: Reg: 0.3789, AltReg: 0.6315, CorReg: 0.0000, TopReg: 0.4141, AllReg: 0.6318, BotRReg: 0.8219, OV: 0.4847, AltV: 0.2507, CorV: 0.8356, TopV: 0.4445, BotRV: 0.0368, AllV: 0.2504 +[2026-03-20T17:42:55.127063Z] Loop 1345: Reg: 0.3806, AltReg: 0.6343, CorReg: 0.0001, TopReg: 0.4201, AllReg: 0.6346, BotRReg: 0.8200, OV: 0.4830, AltV: 0.2479, CorV: 0.8356, TopV: 0.4385, BotRV: 0.0386, AllV: 0.2476 +[2026-03-20T17:42:59.433507Z] Loop 1350: Reg: 0.3810, AltReg: 0.6349, CorReg: 0.0001, TopReg: 0.4197, AllReg: 0.6353, BotRReg: 0.8198, OV: 0.4826, AltV: 0.2473, CorV: 0.8356, TopV: 0.4389, BotRV: 0.0388, AllV: 0.2470 +[2026-03-20T17:43:03.737305Z] Loop 1355: Reg: 0.3786, AltReg: 0.6310, CorReg: 0.0001, TopReg: 0.4135, AllReg: 0.6313, BotRReg: 0.8201, OV: 0.4850, AltV: 0.2512, CorV: 0.8356, TopV: 0.4451, BotRV: 0.0385, AllV: 0.2509 +[2026-03-20T17:43:08.040658Z] Loop 1360: Reg: 0.3779, AltReg: 0.6297, CorReg: 0.0000, TopReg: 0.4027, AllReg: 0.6301, BotRReg: 0.8230, OV: 0.4857, AltV: 0.2525, CorV: 0.8356, TopV: 0.4559, BotRV: 0.0356, AllV: 0.2522 +[2026-03-20T17:43:12.345924Z] Loop 1365: Reg: 0.3800, AltReg: 0.6332, CorReg: 0.0001, TopReg: 0.4008, AllReg: 0.6336, BotRReg: 0.8291, OV: 0.4836, AltV: 0.2490, CorV: 0.8356, TopV: 0.4578, BotRV: 0.0296, AllV: 0.2487 +[2026-03-20T17:43:16.652999Z] Loop 1370: Reg: 0.3775, AltReg: 0.6291, CorReg: 0.0000, TopReg: 0.4085, AllReg: 0.6294, BotRReg: 0.8237, OV: 0.4861, AltV: 0.2532, CorV: 0.8356, TopV: 0.4501, BotRV: 0.0349, AllV: 0.2528 +[2026-03-20T17:43:20.956586Z] Loop 1375: Reg: 0.3781, AltReg: 0.6301, CorReg: 0.0000, TopReg: 0.4127, AllReg: 0.6304, BotRReg: 0.8203, OV: 0.4855, AltV: 0.2521, CorV: 0.8356, TopV: 0.4459, BotRV: 0.0383, AllV: 0.2518 +[2026-03-20T17:43:25.259473Z] Loop 1380: Reg: 0.3785, AltReg: 0.6308, CorReg: 0.0001, TopReg: 0.4137, AllReg: 0.6311, BotRReg: 0.8199, OV: 0.4851, AltV: 0.2514, CorV: 0.8356, TopV: 0.4450, BotRV: 0.0387, AllV: 0.2511 +[2026-03-20T17:43:29.568640Z] Loop 1385: Reg: 0.3784, AltReg: 0.6307, CorReg: 0.0001, TopReg: 0.4140, AllReg: 0.6310, BotRReg: 0.8198, OV: 0.4851, AltV: 0.2515, CorV: 0.8355, TopV: 0.4446, BotRV: 0.0389, AllV: 0.2512 +[2026-03-20T17:43:33.876032Z] Loop 1390: Reg: 0.3774, AltReg: 0.6290, CorReg: 0.0000, TopReg: 0.4018, AllReg: 0.6294, BotRReg: 0.8242, OV: 0.4861, AltV: 0.2532, CorV: 0.8356, TopV: 0.4568, BotRV: 0.0344, AllV: 0.2529 +[2026-03-20T17:43:38.182654Z] Loop 1395: Reg: 0.3788, AltReg: 0.6312, CorReg: 0.0001, TopReg: 0.4005, AllReg: 0.6316, BotRReg: 0.8305, OV: 0.4848, AltV: 0.2510, CorV: 0.8356, TopV: 0.4581, BotRV: 0.0281, AllV: 0.2507 +[2026-03-20T17:43:42.487550Z] Loop 1400: Reg: 0.3823, AltReg: 0.6371, CorReg: 0.0002, TopReg: 0.4012, AllReg: 0.6374, BotRReg: 0.8364, OV: 0.4812, AltV: 0.2451, CorV: 0.8354, TopV: 0.4574, BotRV: 0.0223, AllV: 0.2448 +[2026-03-20T17:43:46.789951Z] Loop 1405: Reg: 0.3776, AltReg: 0.6294, CorReg: 0.0000, TopReg: 0.4098, AllReg: 0.6297, BotRReg: 0.8270, OV: 0.4859, AltV: 0.2528, CorV: 0.8356, TopV: 0.4488, BotRV: 0.0316, AllV: 0.2525 +[2026-03-20T17:43:51.092995Z] Loop 1410: Reg: 0.3777, AltReg: 0.6295, CorReg: 0.0000, TopReg: 0.4122, AllReg: 0.6298, BotRReg: 0.8232, OV: 0.4859, AltV: 0.2528, CorV: 0.8356, TopV: 0.4464, BotRV: 0.0355, AllV: 0.2524 +[2026-03-20T17:43:55.401472Z] Loop 1415: Reg: 0.3787, AltReg: 0.6312, CorReg: 0.0000, TopReg: 0.4147, AllReg: 0.6316, BotRReg: 0.8203, OV: 0.4848, AltV: 0.2510, CorV: 0.8356, TopV: 0.4439, BotRV: 0.0383, AllV: 0.2507 +[2026-03-20T17:43:59.706745Z] Loop 1420: Reg: 0.3778, AltReg: 0.6297, CorReg: 0.0000, TopReg: 0.4129, AllReg: 0.6300, BotRReg: 0.8210, OV: 0.4858, AltV: 0.2525, CorV: 0.8356, TopV: 0.4457, BotRV: 0.0377, AllV: 0.2522 +[2026-03-20T17:44:04.015775Z] Loop 1425: Reg: 0.3776, AltReg: 0.6293, CorReg: 0.0000, TopReg: 0.4115, AllReg: 0.6296, BotRReg: 0.8258, OV: 0.4860, AltV: 0.2529, CorV: 0.8356, TopV: 0.4471, BotRV: 0.0329, AllV: 0.2526 +[2026-03-20T17:44:08.325205Z] Loop 1430: Reg: 0.3795, AltReg: 0.6324, CorReg: 0.0001, TopReg: 0.4030, AllReg: 0.6328, BotRReg: 0.8344, OV: 0.4841, AltV: 0.2498, CorV: 0.8355, TopV: 0.4557, BotRV: 0.0242, AllV: 0.2495 +[2026-03-20T17:44:12.634678Z] Loop 1435: Reg: 0.3788, AltReg: 0.6313, CorReg: 0.0001, TopReg: 0.4006, AllReg: 0.6317, BotRReg: 0.8332, OV: 0.4848, AltV: 0.2509, CorV: 0.8355, TopV: 0.4580, BotRV: 0.0255, AllV: 0.2506 +[2026-03-20T17:44:16.940567Z] Loop 1440: Reg: 0.3768, AltReg: 0.6281, CorReg: 0.0000, TopReg: 0.4104, AllReg: 0.6284, BotRReg: 0.8207, OV: 0.4867, AltV: 0.2542, CorV: 0.8356, TopV: 0.4482, BotRV: 0.0379, AllV: 0.2538 +[2026-03-20T17:44:21.244392Z] Loop 1445: Reg: 0.3779, AltReg: 0.6299, CorReg: 0.0000, TopReg: 0.4132, AllReg: 0.6302, BotRReg: 0.8196, OV: 0.4856, AltV: 0.2523, CorV: 0.8356, TopV: 0.4454, BotRV: 0.0391, AllV: 0.2520 +[2026-03-20T17:44:25.550382Z] Loop 1450: Reg: 0.3821, AltReg: 0.6364, CorReg: 0.0005, TopReg: 0.4213, AllReg: 0.6368, BotRReg: 0.8194, OV: 0.4815, AltV: 0.2458, CorV: 0.8352, TopV: 0.4373, BotRV: 0.0392, AllV: 0.2455 +[2026-03-20T17:44:29.860502Z] Loop 1455: Reg: 0.3796, AltReg: 0.6325, CorReg: 0.0002, TopReg: 0.4162, AllReg: 0.6328, BotRReg: 0.8195, OV: 0.4840, AltV: 0.2497, CorV: 0.8354, TopV: 0.4424, BotRV: 0.0392, AllV: 0.2494 +[2026-03-20T17:44:34.163867Z] Loop 1460: Reg: 0.3762, AltReg: 0.6270, CorReg: 0.0000, TopReg: 0.3997, AllReg: 0.6273, BotRReg: 0.8197, OV: 0.4874, AltV: 0.2552, CorV: 0.8356, TopV: 0.4590, BotRV: 0.0389, AllV: 0.2549 +[2026-03-20T17:44:38.465902Z] Loop 1465: Reg: 0.3772, AltReg: 0.6287, CorReg: 0.0000, TopReg: 0.3995, AllReg: 0.6291, BotRReg: 0.8217, OV: 0.4863, AltV: 0.2535, CorV: 0.8356, TopV: 0.4591, BotRV: 0.0369, AllV: 0.2532 +[2026-03-20T17:44:42.770834Z] Loop 1470: Reg: 0.3813, AltReg: 0.6353, CorReg: 0.0003, TopReg: 0.4028, AllReg: 0.6356, BotRReg: 0.8349, OV: 0.4823, AltV: 0.2469, CorV: 0.8354, TopV: 0.4559, BotRV: 0.0237, AllV: 0.2466 +[2026-03-20T17:44:47.076480Z] Loop 1475: Reg: 0.3820, AltReg: 0.6361, CorReg: 0.0008, TopReg: 0.3995, AllReg: 0.6365, BotRReg: 0.8373, OV: 0.4816, AltV: 0.2461, CorV: 0.8349, TopV: 0.4591, BotRV: 0.0213, AllV: 0.2458 +[2026-03-20T17:44:51.382018Z] Loop 1480: Reg: 0.3780, AltReg: 0.6298, CorReg: 0.0002, TopReg: 0.4075, AllReg: 0.6301, BotRReg: 0.8323, OV: 0.4856, AltV: 0.2524, CorV: 0.8354, TopV: 0.4511, BotRV: 0.0263, AllV: 0.2521 +[2026-03-20T17:44:55.687566Z] Loop 1485: Reg: 0.3779, AltReg: 0.6298, CorReg: 0.0000, TopReg: 0.4132, AllReg: 0.6301, BotRReg: 0.8202, OV: 0.4857, AltV: 0.2524, CorV: 0.8356, TopV: 0.4454, BotRV: 0.0385, AllV: 0.2521 +[2026-03-20T17:44:59.992108Z] Loop 1490: Reg: 0.3800, AltReg: 0.6333, CorReg: 0.0000, TopReg: 0.4171, AllReg: 0.6337, BotRReg: 0.8195, OV: 0.4836, AltV: 0.2489, CorV: 0.8356, TopV: 0.4415, BotRV: 0.0392, AllV: 0.2486 +[2026-03-20T17:45:04.300656Z] Loop 1495: Reg: 0.3809, AltReg: 0.6348, CorReg: 0.0001, TopReg: 0.4189, AllReg: 0.6351, BotRReg: 0.8194, OV: 0.4827, AltV: 0.2475, CorV: 0.8356, TopV: 0.4397, BotRV: 0.0392, AllV: 0.2471 +[2026-03-20T17:45:08.607319Z] Loop 1500: Reg: 0.3810, AltReg: 0.6348, CorReg: 0.0002, TopReg: 0.4177, AllReg: 0.6351, BotRReg: 0.8194, OV: 0.4826, AltV: 0.2474, CorV: 0.8354, TopV: 0.4409, BotRV: 0.0392, AllV: 0.2471 +[2026-03-20T17:45:12.914440Z] Loop 1505: Reg: 0.3787, AltReg: 0.6310, CorReg: 0.0002, TopReg: 0.4127, AllReg: 0.6313, BotRReg: 0.8194, OV: 0.4849, AltV: 0.2512, CorV: 0.8354, TopV: 0.4459, BotRV: 0.0392, AllV: 0.2509 +[2026-03-20T17:45:17.218935Z] Loop 1510: Reg: 0.3767, AltReg: 0.6277, CorReg: 0.0001, TopReg: 0.4023, AllReg: 0.6281, BotRReg: 0.8194, OV: 0.4869, AltV: 0.2545, CorV: 0.8355, TopV: 0.4564, BotRV: 0.0392, AllV: 0.2542 +[2026-03-20T17:45:21.523398Z] Loop 1515: Reg: 0.3766, AltReg: 0.6276, CorReg: 0.0001, TopReg: 0.4008, AllReg: 0.6279, BotRReg: 0.8195, OV: 0.4870, AltV: 0.2547, CorV: 0.8356, TopV: 0.4578, BotRV: 0.0392, AllV: 0.2543 +[2026-03-20T17:45:25.833212Z] Loop 1520: Reg: 0.3769, AltReg: 0.6281, CorReg: 0.0000, TopReg: 0.4000, AllReg: 0.6285, BotRReg: 0.8195, OV: 0.4867, AltV: 0.2541, CorV: 0.8356, TopV: 0.4586, BotRV: 0.0391, AllV: 0.2538 +[2026-03-20T17:45:30.136599Z] Loop 1525: Reg: 0.3769, AltReg: 0.6281, CorReg: 0.0000, TopReg: 0.3991, AllReg: 0.6285, BotRReg: 0.8196, OV: 0.4867, AltV: 0.2541, CorV: 0.8356, TopV: 0.4595, BotRV: 0.0390, AllV: 0.2538 +[2026-03-20T17:45:34.444731Z] Loop 1530: Reg: 0.3773, AltReg: 0.6288, CorReg: 0.0000, TopReg: 0.4001, AllReg: 0.6292, BotRReg: 0.8208, OV: 0.4863, AltV: 0.2534, CorV: 0.8356, TopV: 0.4585, BotRV: 0.0378, AllV: 0.2531 +[2026-03-20T17:45:38.754856Z] Loop 1535: Reg: 0.3758, AltReg: 0.6264, CorReg: 0.0000, TopReg: 0.3985, AllReg: 0.6267, BotRReg: 0.8214, OV: 0.4878, AltV: 0.2559, CorV: 0.8356, TopV: 0.4602, BotRV: 0.0372, AllV: 0.2555 +[2026-03-20T17:45:43.062537Z] Loop 1540: Reg: 0.3763, AltReg: 0.6272, CorReg: 0.0001, TopReg: 0.3989, AllReg: 0.6275, BotRReg: 0.8293, OV: 0.4872, AltV: 0.2550, CorV: 0.8356, TopV: 0.4597, BotRV: 0.0293, AllV: 0.2547 +[2026-03-20T17:45:47.369131Z] Loop 1545: Reg: 0.3763, AltReg: 0.6271, CorReg: 0.0000, TopReg: 0.4032, AllReg: 0.6275, BotRReg: 0.8253, OV: 0.4873, AltV: 0.2551, CorV: 0.8356, TopV: 0.4554, BotRV: 0.0333, AllV: 0.2548 +[2026-03-20T17:45:51.673111Z] Loop 1550: Reg: 0.3762, AltReg: 0.6270, CorReg: 0.0000, TopReg: 0.4061, AllReg: 0.6274, BotRReg: 0.8209, OV: 0.4874, AltV: 0.2552, CorV: 0.8356, TopV: 0.4525, BotRV: 0.0377, AllV: 0.2549 +[2026-03-20T17:45:55.976841Z] Loop 1555: Reg: 0.3765, AltReg: 0.6274, CorReg: 0.0000, TopReg: 0.4091, AllReg: 0.6278, BotRReg: 0.8196, OV: 0.4871, AltV: 0.2548, CorV: 0.8356, TopV: 0.4495, BotRV: 0.0390, AllV: 0.2545 +[2026-03-20T17:46:00.278832Z] Loop 1560: Reg: 0.3760, AltReg: 0.6266, CorReg: 0.0000, TopReg: 0.4033, AllReg: 0.6270, BotRReg: 0.8195, OV: 0.4876, AltV: 0.2556, CorV: 0.8356, TopV: 0.4553, BotRV: 0.0391, AllV: 0.2553 +[2026-03-20T17:46:04.582023Z] Loop 1565: Reg: 0.3766, AltReg: 0.6277, CorReg: 0.0001, TopReg: 0.4075, AllReg: 0.6280, BotRReg: 0.8194, OV: 0.4869, AltV: 0.2545, CorV: 0.8356, TopV: 0.4511, BotRV: 0.0392, AllV: 0.2542 +[2026-03-20T17:46:08.885801Z] Loop 1570: Reg: 0.3768, AltReg: 0.6277, CorReg: 0.0004, TopReg: 0.4030, AllReg: 0.6281, BotRReg: 0.8194, OV: 0.4868, AltV: 0.2545, CorV: 0.8352, TopV: 0.4556, BotRV: 0.0392, AllV: 0.2542 +[2026-03-20T17:46:13.190810Z] Loop 1575: Reg: 0.3777, AltReg: 0.6288, CorReg: 0.0012, TopReg: 0.4028, AllReg: 0.6291, BotRReg: 0.8194, OV: 0.4858, AltV: 0.2534, CorV: 0.8345, TopV: 0.4559, BotRV: 0.0392, AllV: 0.2531 +[2026-03-20T17:46:17.497229Z] Loop 1580: Reg: 0.3767, AltReg: 0.6275, CorReg: 0.0004, TopReg: 0.4019, AllReg: 0.6279, BotRReg: 0.8194, OV: 0.4869, AltV: 0.2547, CorV: 0.8353, TopV: 0.4567, BotRV: 0.0392, AllV: 0.2544 +[2026-03-20T17:46:21.800482Z] Loop 1585: Reg: 0.3761, AltReg: 0.6268, CorReg: 0.0001, TopReg: 0.4011, AllReg: 0.6272, BotRReg: 0.8194, OV: 0.4874, AltV: 0.2554, CorV: 0.8355, TopV: 0.4575, BotRV: 0.0392, AllV: 0.2550 +[2026-03-20T17:46:26.107866Z] Loop 1590: Reg: 0.3759, AltReg: 0.6265, CorReg: 0.0000, TopReg: 0.3986, AllReg: 0.6269, BotRReg: 0.8196, OV: 0.4876, AltV: 0.2557, CorV: 0.8356, TopV: 0.4600, BotRV: 0.0390, AllV: 0.2554 +[2026-03-20T17:46:30.415512Z] Loop 1595: Reg: 0.3772, AltReg: 0.6287, CorReg: 0.0000, TopReg: 0.3997, AllReg: 0.6290, BotRReg: 0.8262, OV: 0.4864, AltV: 0.2536, CorV: 0.8356, TopV: 0.4589, BotRV: 0.0325, AllV: 0.2532 +[2026-03-20T17:46:34.720569Z] Loop 1600: Reg: 0.3778, AltReg: 0.6296, CorReg: 0.0000, TopReg: 0.4002, AllReg: 0.6300, BotRReg: 0.8342, OV: 0.4858, AltV: 0.2526, CorV: 0.8356, TopV: 0.4584, BotRV: 0.0244, AllV: 0.2523 +[2026-03-20T17:46:39.025668Z] Loop 1605: Reg: 0.3769, AltReg: 0.6282, CorReg: 0.0000, TopReg: 0.3985, AllReg: 0.6285, BotRReg: 0.8346, OV: 0.4867, AltV: 0.2541, CorV: 0.8356, TopV: 0.4602, BotRV: 0.0240, AllV: 0.2537 +[2026-03-20T17:46:43.331149Z] Loop 1610: Reg: 0.3774, AltReg: 0.6290, CorReg: 0.0001, TopReg: 0.3983, AllReg: 0.6293, BotRReg: 0.8369, OV: 0.4862, AltV: 0.2533, CorV: 0.8355, TopV: 0.4603, BotRV: 0.0218, AllV: 0.2529 +[2026-03-20T17:46:47.634559Z] Loop 1615: Reg: 0.3774, AltReg: 0.6289, CorReg: 0.0001, TopReg: 0.3984, AllReg: 0.6293, BotRReg: 0.8368, OV: 0.4862, AltV: 0.2533, CorV: 0.8355, TopV: 0.4602, BotRV: 0.0218, AllV: 0.2530 +[2026-03-20T17:46:51.937903Z] Loop 1620: Reg: 0.3791, AltReg: 0.6316, CorReg: 0.0003, TopReg: 0.3989, AllReg: 0.6320, BotRReg: 0.8381, OV: 0.4845, AltV: 0.2506, CorV: 0.8353, TopV: 0.4598, BotRV: 0.0205, AllV: 0.2503 +[2026-03-20T17:46:56.241159Z] Loop 1625: Reg: 0.3770, AltReg: 0.6283, CorReg: 0.0001, TopReg: 0.4012, AllReg: 0.6287, BotRReg: 0.8353, OV: 0.4865, AltV: 0.2539, CorV: 0.8355, TopV: 0.4575, BotRV: 0.0233, AllV: 0.2536 +[2026-03-20T17:47:00.546935Z] Loop 1630: Reg: 0.3766, AltReg: 0.6277, CorReg: 0.0001, TopReg: 0.4028, AllReg: 0.6280, BotRReg: 0.8306, OV: 0.4870, AltV: 0.2545, CorV: 0.8356, TopV: 0.4558, BotRV: 0.0280, AllV: 0.2542 +[2026-03-20T17:47:04.851639Z] Loop 1635: Reg: 0.3762, AltReg: 0.6269, CorReg: 0.0000, TopReg: 0.4029, AllReg: 0.6273, BotRReg: 0.8232, OV: 0.4874, AltV: 0.2553, CorV: 0.8356, TopV: 0.4557, BotRV: 0.0354, AllV: 0.2550 +[2026-03-20T17:47:09.155889Z] Loop 1640: Reg: 0.3765, AltReg: 0.6274, CorReg: 0.0000, TopReg: 0.4063, AllReg: 0.6278, BotRReg: 0.8196, OV: 0.4871, AltV: 0.2548, CorV: 0.8356, TopV: 0.4524, BotRV: 0.0390, AllV: 0.2545 +[2026-03-20T17:47:13.460015Z] Loop 1645: Reg: 0.3760, AltReg: 0.6267, CorReg: 0.0000, TopReg: 0.4010, AllReg: 0.6270, BotRReg: 0.8195, OV: 0.4876, AltV: 0.2555, CorV: 0.8356, TopV: 0.4576, BotRV: 0.0392, AllV: 0.2552 +[2026-03-20T17:47:17.765940Z] Loop 1650: Reg: 0.3758, AltReg: 0.6263, CorReg: 0.0000, TopReg: 0.3990, AllReg: 0.6266, BotRReg: 0.8195, OV: 0.4878, AltV: 0.2559, CorV: 0.8356, TopV: 0.4597, BotRV: 0.0391, AllV: 0.2556 +[2026-03-20T17:47:22.067795Z] Loop 1655: Reg: 0.3759, AltReg: 0.6265, CorReg: 0.0000, TopReg: 0.3997, AllReg: 0.6268, BotRReg: 0.8195, OV: 0.4877, AltV: 0.2558, CorV: 0.8356, TopV: 0.4589, BotRV: 0.0392, AllV: 0.2554 +[2026-03-20T17:47:26.370560Z] Loop 1660: Reg: 0.3767, AltReg: 0.6277, CorReg: 0.0002, TopReg: 0.4017, AllReg: 0.6281, BotRReg: 0.8194, OV: 0.4869, AltV: 0.2545, CorV: 0.8354, TopV: 0.4569, BotRV: 0.0392, AllV: 0.2542 +[2026-03-20T17:47:30.675560Z] Loop 1665: Reg: 0.3788, AltReg: 0.6307, CorReg: 0.0011, TopReg: 0.4025, AllReg: 0.6310, BotRReg: 0.8194, OV: 0.4847, AltV: 0.2515, CorV: 0.8345, TopV: 0.4561, BotRV: 0.0392, AllV: 0.2512 +[2026-03-20T17:47:34.981710Z] Loop 1670: Reg: 0.3769, AltReg: 0.6280, CorReg: 0.0001, TopReg: 0.4013, AllReg: 0.6284, BotRReg: 0.8195, OV: 0.4867, AltV: 0.2542, CorV: 0.8355, TopV: 0.4573, BotRV: 0.0391, AllV: 0.2539 +[2026-03-20T17:47:39.288076Z] Loop 1675: Reg: 0.3771, AltReg: 0.6284, CorReg: 0.0000, TopReg: 0.3998, AllReg: 0.6288, BotRReg: 0.8198, OV: 0.4865, AltV: 0.2538, CorV: 0.8356, TopV: 0.4588, BotRV: 0.0388, AllV: 0.2535 +[2026-03-20T17:47:43.593578Z] Loop 1680: Reg: 0.3765, AltReg: 0.6275, CorReg: 0.0000, TopReg: 0.3993, AllReg: 0.6279, BotRReg: 0.8196, OV: 0.4870, AltV: 0.2547, CorV: 0.8356, TopV: 0.4594, BotRV: 0.0390, AllV: 0.2544 +[2026-03-20T17:47:47.899186Z] Loop 1685: Reg: 0.3767, AltReg: 0.6277, CorReg: 0.0002, TopReg: 0.4016, AllReg: 0.6280, BotRReg: 0.8194, OV: 0.4869, AltV: 0.2545, CorV: 0.8354, TopV: 0.4570, BotRV: 0.0392, AllV: 0.2542 +[2026-03-20T17:47:52.203525Z] Loop 1690: Reg: 0.3808, AltReg: 0.6336, CorReg: 0.0016, TopReg: 0.4092, AllReg: 0.6340, BotRReg: 0.8194, OV: 0.4828, AltV: 0.2486, CorV: 0.8341, TopV: 0.4495, BotRV: 0.0392, AllV: 0.2483 +[2026-03-20T17:47:56.511865Z] Loop 1695: Reg: 0.3768, AltReg: 0.6280, CorReg: 0.0001, TopReg: 0.4047, AllReg: 0.6283, BotRReg: 0.8194, OV: 0.4867, AltV: 0.2542, CorV: 0.8355, TopV: 0.4539, BotRV: 0.0392, AllV: 0.2539 +[2026-03-20T17:48:00.815218Z] Loop 1700: Reg: 0.3759, AltReg: 0.6265, CorReg: 0.0000, TopReg: 0.4003, AllReg: 0.6269, BotRReg: 0.8194, OV: 0.4877, AltV: 0.2557, CorV: 0.8356, TopV: 0.4583, BotRV: 0.0392, AllV: 0.2554 +[2026-03-20T17:48:05.121506Z] Loop 1705: Reg: 0.3755, AltReg: 0.6258, CorReg: 0.0000, TopReg: 0.3982, AllReg: 0.6262, BotRReg: 0.8195, OV: 0.4881, AltV: 0.2564, CorV: 0.8356, TopV: 0.4604, BotRV: 0.0391, AllV: 0.2561 +[2026-03-20T17:48:09.427268Z] Loop 1710: Reg: 0.3755, AltReg: 0.6258, CorReg: 0.0000, TopReg: 0.3982, AllReg: 0.6261, BotRReg: 0.8196, OV: 0.4881, AltV: 0.2564, CorV: 0.8356, TopV: 0.4604, BotRV: 0.0391, AllV: 0.2561 +[2026-03-20T17:48:13.733453Z] Loop 1715: Reg: 0.3755, AltReg: 0.6258, CorReg: 0.0000, TopReg: 0.3982, AllReg: 0.6262, BotRReg: 0.8195, OV: 0.4881, AltV: 0.2564, CorV: 0.8356, TopV: 0.4604, BotRV: 0.0391, AllV: 0.2561 +[2026-03-20T17:48:18.038235Z] Loop 1720: Reg: 0.3755, AltReg: 0.6258, CorReg: 0.0000, TopReg: 0.3982, AllReg: 0.6262, BotRReg: 0.8196, OV: 0.4881, AltV: 0.2564, CorV: 0.8356, TopV: 0.4604, BotRV: 0.0391, AllV: 0.2561 +[2026-03-20T17:48:22.342613Z] Loop 1725: Reg: 0.3769, AltReg: 0.6281, CorReg: 0.0000, TopReg: 0.4008, AllReg: 0.6284, BotRReg: 0.8211, OV: 0.4867, AltV: 0.2541, CorV: 0.8356, TopV: 0.4578, BotRV: 0.0375, AllV: 0.2538 +[2026-03-20T17:48:26.650022Z] Loop 1730: Reg: 0.3785, AltReg: 0.6308, CorReg: 0.0001, TopReg: 0.4038, AllReg: 0.6311, BotRReg: 0.8311, OV: 0.4851, AltV: 0.2514, CorV: 0.8356, TopV: 0.4548, BotRV: 0.0276, AllV: 0.2511 +[2026-03-20T17:48:30.953871Z] Loop 1735: Reg: 0.3758, AltReg: 0.6263, CorReg: 0.0000, TopReg: 0.3982, AllReg: 0.6267, BotRReg: 0.8260, OV: 0.4878, AltV: 0.2559, CorV: 0.8356, TopV: 0.4604, BotRV: 0.0327, AllV: 0.2556 +[2026-03-20T17:48:35.257432Z] Loop 1740: Reg: 0.3757, AltReg: 0.6261, CorReg: 0.0000, TopReg: 0.3988, AllReg: 0.6265, BotRReg: 0.8223, OV: 0.4879, AltV: 0.2561, CorV: 0.8356, TopV: 0.4599, BotRV: 0.0363, AllV: 0.2558 +[2026-03-20T17:48:39.562911Z] Loop 1745: Reg: 0.3759, AltReg: 0.6265, CorReg: 0.0000, TopReg: 0.3996, AllReg: 0.6269, BotRReg: 0.8243, OV: 0.4877, AltV: 0.2557, CorV: 0.8356, TopV: 0.4591, BotRV: 0.0343, AllV: 0.2554 +[2026-03-20T17:48:43.864125Z] Loop 1750: Reg: 0.3761, AltReg: 0.6267, CorReg: 0.0001, TopReg: 0.3991, AllReg: 0.6271, BotRReg: 0.8268, OV: 0.4875, AltV: 0.2555, CorV: 0.8356, TopV: 0.4595, BotRV: 0.0318, AllV: 0.2552 +[2026-03-20T17:48:48.170028Z] Loop 1755: Reg: 0.3771, AltReg: 0.6285, CorReg: 0.0001, TopReg: 0.3983, AllReg: 0.6288, BotRReg: 0.8339, OV: 0.4865, AltV: 0.2537, CorV: 0.8355, TopV: 0.4603, BotRV: 0.0247, AllV: 0.2534 +[2026-03-20T17:48:52.476189Z] Loop 1760: Reg: 0.3767, AltReg: 0.6278, CorReg: 0.0001, TopReg: 0.3983, AllReg: 0.6281, BotRReg: 0.8322, OV: 0.4869, AltV: 0.2545, CorV: 0.8356, TopV: 0.4603, BotRV: 0.0264, AllV: 0.2541 +[2026-03-20T17:48:56.781435Z] Loop 1765: Reg: 0.3807, AltReg: 0.6343, CorReg: 0.0003, TopReg: 0.3995, AllReg: 0.6347, BotRReg: 0.8364, OV: 0.4829, AltV: 0.2479, CorV: 0.8354, TopV: 0.4591, BotRV: 0.0222, AllV: 0.2476 +[2026-03-20T17:49:01.086832Z] Loop 1770: Reg: 0.3789, AltReg: 0.6313, CorReg: 0.0002, TopReg: 0.3995, AllReg: 0.6317, BotRReg: 0.8353, OV: 0.4847, AltV: 0.2509, CorV: 0.8355, TopV: 0.4591, BotRV: 0.0234, AllV: 0.2506 +[2026-03-20T17:49:05.392911Z] Loop 1775: Reg: 0.3756, AltReg: 0.6259, CorReg: 0.0000, TopReg: 0.3982, AllReg: 0.6263, BotRReg: 0.8216, OV: 0.4880, AltV: 0.2563, CorV: 0.8356, TopV: 0.4604, BotRV: 0.0370, AllV: 0.2560 +[2026-03-20T17:49:09.698740Z] Loop 1780: Reg: 0.3755, AltReg: 0.6259, CorReg: 0.0000, TopReg: 0.3991, AllReg: 0.6262, BotRReg: 0.8194, OV: 0.4881, AltV: 0.2564, CorV: 0.8356, TopV: 0.4596, BotRV: 0.0392, AllV: 0.2560 +[2026-03-20T17:49:14.007697Z] Loop 1785: Reg: 0.3777, AltReg: 0.6294, CorReg: 0.0000, TopReg: 0.4132, AllReg: 0.6298, BotRReg: 0.8194, OV: 0.4859, AltV: 0.2528, CorV: 0.8356, TopV: 0.4454, BotRV: 0.0393, AllV: 0.2525 +[2026-03-20T17:49:18.311578Z] Loop 1790: Reg: 0.3818, AltReg: 0.6360, CorReg: 0.0006, TopReg: 0.4190, AllReg: 0.6363, BotRReg: 0.8194, OV: 0.4818, AltV: 0.2462, CorV: 0.8351, TopV: 0.4396, BotRV: 0.0393, AllV: 0.2459 +[2026-03-20T17:49:22.614869Z] Loop 1795: Reg: 0.3789, AltReg: 0.6314, CorReg: 0.0002, TopReg: 0.4150, AllReg: 0.6317, BotRReg: 0.8194, OV: 0.4847, AltV: 0.2508, CorV: 0.8354, TopV: 0.4436, BotRV: 0.0393, AllV: 0.2505 +[2026-03-20T17:49:26.921162Z] Loop 1800: Reg: 0.3759, AltReg: 0.6265, CorReg: 0.0000, TopReg: 0.3997, AllReg: 0.6269, BotRReg: 0.8194, OV: 0.4877, AltV: 0.2557, CorV: 0.8356, TopV: 0.4589, BotRV: 0.0392, AllV: 0.2554 +[2026-03-20T17:49:31.229089Z] Loop 1805: Reg: 0.3755, AltReg: 0.6258, CorReg: 0.0000, TopReg: 0.3982, AllReg: 0.6261, BotRReg: 0.8194, OV: 0.4881, AltV: 0.2564, CorV: 0.8356, TopV: 0.4604, BotRV: 0.0392, AllV: 0.2561 +[2026-03-20T17:49:35.538010Z] Loop 1810: Reg: 0.3756, AltReg: 0.6260, CorReg: 0.0000, TopReg: 0.3983, AllReg: 0.6264, BotRReg: 0.8195, OV: 0.4880, AltV: 0.2562, CorV: 0.8356, TopV: 0.4603, BotRV: 0.0392, AllV: 0.2559 +[2026-03-20T17:49:39.845610Z] Loop 1815: Reg: 0.3760, AltReg: 0.6267, CorReg: 0.0000, TopReg: 0.3991, AllReg: 0.6271, BotRReg: 0.8198, OV: 0.4875, AltV: 0.2555, CorV: 0.8356, TopV: 0.4595, BotRV: 0.0388, AllV: 0.2552 +[2026-03-20T17:49:44.158727Z] Loop 1820: Reg: 0.3773, AltReg: 0.6288, CorReg: 0.0001, TopReg: 0.4020, AllReg: 0.6291, BotRReg: 0.8234, OV: 0.4863, AltV: 0.2534, CorV: 0.8356, TopV: 0.4566, BotRV: 0.0352, AllV: 0.2531 +[2026-03-20T17:49:48.469298Z] Loop 1825: Reg: 0.3787, AltReg: 0.6310, CorReg: 0.0001, TopReg: 0.4032, AllReg: 0.6314, BotRReg: 0.8328, OV: 0.4849, AltV: 0.2512, CorV: 0.8355, TopV: 0.4555, BotRV: 0.0258, AllV: 0.2509 +[2026-03-20T17:49:52.782402Z] Loop 1830: Reg: 0.3769, AltReg: 0.6281, CorReg: 0.0001, TopReg: 0.3987, AllReg: 0.6285, BotRReg: 0.8323, OV: 0.4866, AltV: 0.2541, CorV: 0.8355, TopV: 0.4599, BotRV: 0.0264, AllV: 0.2538 +[2026-03-20T17:49:57.087648Z] Loop 1835: Reg: 0.3758, AltReg: 0.6264, CorReg: 0.0001, TopReg: 0.3985, AllReg: 0.6267, BotRReg: 0.8247, OV: 0.4877, AltV: 0.2559, CorV: 0.8356, TopV: 0.4601, BotRV: 0.0340, AllV: 0.2555 +[2026-03-20T17:50:01.393625Z] Loop 1840: Reg: 0.3773, AltReg: 0.6288, CorReg: 0.0000, TopReg: 0.4131, AllReg: 0.6291, BotRReg: 0.8195, OV: 0.4863, AltV: 0.2534, CorV: 0.8356, TopV: 0.4455, BotRV: 0.0391, AllV: 0.2531 +[2026-03-20T17:50:05.697918Z] Loop 1845: Reg: 0.3785, AltReg: 0.6308, CorReg: 0.0000, TopReg: 0.4161, AllReg: 0.6312, BotRReg: 0.8194, OV: 0.4851, AltV: 0.2514, CorV: 0.8356, TopV: 0.4426, BotRV: 0.0392, AllV: 0.2511 +[2026-03-20T17:50:10.001611Z] Loop 1850: Reg: 0.3781, AltReg: 0.6301, CorReg: 0.0000, TopReg: 0.4151, AllReg: 0.6305, BotRReg: 0.8194, OV: 0.4855, AltV: 0.2521, CorV: 0.8356, TopV: 0.4435, BotRV: 0.0392, AllV: 0.2518 +[2026-03-20T17:50:14.311118Z] Loop 1855: Reg: 0.3774, AltReg: 0.6290, CorReg: 0.0000, TopReg: 0.4131, AllReg: 0.6294, BotRReg: 0.8194, OV: 0.4861, AltV: 0.2532, CorV: 0.8356, TopV: 0.4455, BotRV: 0.0392, AllV: 0.2529 +[2026-03-20T17:50:18.621012Z] Loop 1860: Reg: 0.3774, AltReg: 0.6289, CorReg: 0.0000, TopReg: 0.4117, AllReg: 0.6293, BotRReg: 0.8194, OV: 0.4862, AltV: 0.2533, CorV: 0.8356, TopV: 0.4469, BotRV: 0.0393, AllV: 0.2530 +[2026-03-20T17:50:22.926215Z] Loop 1865: Reg: 0.3762, AltReg: 0.6270, CorReg: 0.0000, TopReg: 0.4017, AllReg: 0.6274, BotRReg: 0.8194, OV: 0.4873, AltV: 0.2552, CorV: 0.8356, TopV: 0.4569, BotRV: 0.0393, AllV: 0.2549 +[2026-03-20T17:50:27.231812Z] Loop 1870: Reg: 0.3760, AltReg: 0.6267, CorReg: 0.0001, TopReg: 0.3997, AllReg: 0.6270, BotRReg: 0.8194, OV: 0.4876, AltV: 0.2555, CorV: 0.8356, TopV: 0.4589, BotRV: 0.0392, AllV: 0.2552 +[2026-03-20T17:50:31.538140Z] Loop 1875: Reg: 0.3758, AltReg: 0.6262, CorReg: 0.0000, TopReg: 0.3988, AllReg: 0.6266, BotRReg: 0.8194, OV: 0.4878, AltV: 0.2560, CorV: 0.8356, TopV: 0.4598, BotRV: 0.0392, AllV: 0.2557 +[2026-03-20T17:50:35.844788Z] Loop 1880: Reg: 0.3758, AltReg: 0.6263, CorReg: 0.0000, TopReg: 0.3984, AllReg: 0.6266, BotRReg: 0.8194, OV: 0.4878, AltV: 0.2560, CorV: 0.8356, TopV: 0.4602, BotRV: 0.0392, AllV: 0.2556 +[2026-03-20T17:50:40.151002Z] Loop 1885: Reg: 0.3761, AltReg: 0.6269, CorReg: 0.0000, TopReg: 0.3988, AllReg: 0.6272, BotRReg: 0.8195, OV: 0.4874, AltV: 0.2553, CorV: 0.8356, TopV: 0.4598, BotRV: 0.0392, AllV: 0.2550 +[2026-03-20T17:50:44.453632Z] Loop 1890: Reg: 0.3756, AltReg: 0.6260, CorReg: 0.0000, TopReg: 0.3983, AllReg: 0.6263, BotRReg: 0.8194, OV: 0.4880, AltV: 0.2563, CorV: 0.8356, TopV: 0.4604, BotRV: 0.0392, AllV: 0.2559 +[2026-03-20T17:50:48.759607Z] Loop 1895: Reg: 0.3757, AltReg: 0.6261, CorReg: 0.0000, TopReg: 0.3985, AllReg: 0.6265, BotRReg: 0.8194, OV: 0.4879, AltV: 0.2561, CorV: 0.8356, TopV: 0.4601, BotRV: 0.0392, AllV: 0.2558 +[2026-03-20T17:50:53.065398Z] Loop 1900: Reg: 0.3759, AltReg: 0.6265, CorReg: 0.0000, TopReg: 0.3992, AllReg: 0.6269, BotRReg: 0.8194, OV: 0.4876, AltV: 0.2557, CorV: 0.8356, TopV: 0.4594, BotRV: 0.0392, AllV: 0.2554 +[2026-03-20T17:50:57.368703Z] Loop 1905: Reg: 0.3760, AltReg: 0.6266, CorReg: 0.0000, TopReg: 0.3988, AllReg: 0.6270, BotRReg: 0.8194, OV: 0.4876, AltV: 0.2556, CorV: 0.8356, TopV: 0.4598, BotRV: 0.0392, AllV: 0.2553 +[2026-03-20T17:51:01.678510Z] Loop 1910: Reg: 0.3763, AltReg: 0.6271, CorReg: 0.0000, TopReg: 0.3990, AllReg: 0.6274, BotRReg: 0.8195, OV: 0.4873, AltV: 0.2551, CorV: 0.8356, TopV: 0.4597, BotRV: 0.0391, AllV: 0.2548 +[2026-03-20T17:51:05.982734Z] Loop 1915: Reg: 0.3760, AltReg: 0.6266, CorReg: 0.0000, TopReg: 0.3987, AllReg: 0.6269, BotRReg: 0.8195, OV: 0.4876, AltV: 0.2556, CorV: 0.8356, TopV: 0.4599, BotRV: 0.0391, AllV: 0.2553 +[2026-03-20T17:51:10.290598Z] Loop 1920: Reg: 0.3755, AltReg: 0.6258, CorReg: 0.0001, TopReg: 0.3983, AllReg: 0.6261, BotRReg: 0.8196, OV: 0.4881, AltV: 0.2564, CorV: 0.8356, TopV: 0.4604, BotRV: 0.0390, AllV: 0.2561 +[2026-03-20T17:51:14.598385Z] Loop 1925: Reg: 0.3754, AltReg: 0.6256, CorReg: 0.0001, TopReg: 0.3981, AllReg: 0.6259, BotRReg: 0.8197, OV: 0.4882, AltV: 0.2566, CorV: 0.8356, TopV: 0.4605, BotRV: 0.0389, AllV: 0.2563 +[2026-03-20T17:51:18.905719Z] Loop 1930: Reg: 0.3755, AltReg: 0.6258, CorReg: 0.0001, TopReg: 0.3984, AllReg: 0.6261, BotRReg: 0.8195, OV: 0.4881, AltV: 0.2564, CorV: 0.8355, TopV: 0.4602, BotRV: 0.0391, AllV: 0.2561 +[2026-03-20T17:51:23.212604Z] Loop 1935: Reg: 0.3756, AltReg: 0.6260, CorReg: 0.0001, TopReg: 0.3991, AllReg: 0.6264, BotRReg: 0.8195, OV: 0.4879, AltV: 0.2562, CorV: 0.8355, TopV: 0.4595, BotRV: 0.0392, AllV: 0.2559 +[2026-03-20T17:51:27.522566Z] Loop 1940: Reg: 0.3755, AltReg: 0.6258, CorReg: 0.0002, TopReg: 0.3982, AllReg: 0.6261, BotRReg: 0.8202, OV: 0.4880, AltV: 0.2564, CorV: 0.8355, TopV: 0.4604, BotRV: 0.0384, AllV: 0.2561 +[2026-03-20T17:51:31.832125Z] Loop 1945: Reg: 0.3755, AltReg: 0.6258, CorReg: 0.0001, TopReg: 0.3983, AllReg: 0.6261, BotRReg: 0.8198, OV: 0.4881, AltV: 0.2564, CorV: 0.8355, TopV: 0.4603, BotRV: 0.0388, AllV: 0.2561 +[2026-03-20T17:51:36.136099Z] Loop 1950: Reg: 0.3756, AltReg: 0.6258, CorReg: 0.0001, TopReg: 0.3984, AllReg: 0.6262, BotRReg: 0.8199, OV: 0.4880, AltV: 0.2564, CorV: 0.8355, TopV: 0.4602, BotRV: 0.0387, AllV: 0.2561 +[2026-03-20T17:51:40.441397Z] Loop 1955: Reg: 0.3756, AltReg: 0.6259, CorReg: 0.0002, TopReg: 0.3984, AllReg: 0.6262, BotRReg: 0.8203, OV: 0.4880, AltV: 0.2564, CorV: 0.8355, TopV: 0.4603, BotRV: 0.0383, AllV: 0.2560 +[2026-03-20T17:51:44.743117Z] Loop 1960: Reg: 0.3756, AltReg: 0.6259, CorReg: 0.0002, TopReg: 0.3982, AllReg: 0.6262, BotRReg: 0.8212, OV: 0.4880, AltV: 0.2563, CorV: 0.8354, TopV: 0.4604, BotRV: 0.0375, AllV: 0.2560 +[2026-03-20T17:51:49.045995Z] Loop 1965: Reg: 0.3755, AltReg: 0.6257, CorReg: 0.0001, TopReg: 0.3982, AllReg: 0.6261, BotRReg: 0.8204, OV: 0.4881, AltV: 0.2565, CorV: 0.8355, TopV: 0.4605, BotRV: 0.0382, AllV: 0.2562 +[2026-03-20T17:51:53.351434Z] Loop 1970: Reg: 0.3754, AltReg: 0.6256, CorReg: 0.0001, TopReg: 0.3981, AllReg: 0.6260, BotRReg: 0.8200, OV: 0.4882, AltV: 0.2566, CorV: 0.8355, TopV: 0.4605, BotRV: 0.0386, AllV: 0.2563 +[2026-03-20T17:51:57.655826Z] Loop 1975: Reg: 0.3755, AltReg: 0.6258, CorReg: 0.0002, TopReg: 0.3981, AllReg: 0.6261, BotRReg: 0.8223, OV: 0.4880, AltV: 0.2564, CorV: 0.8354, TopV: 0.4605, BotRV: 0.0363, AllV: 0.2561 +[2026-03-20T17:52:01.961682Z] Loop 1980: Reg: 0.3757, AltReg: 0.6260, CorReg: 0.0002, TopReg: 0.3982, AllReg: 0.6263, BotRReg: 0.8241, OV: 0.4879, AltV: 0.2562, CorV: 0.8354, TopV: 0.4604, BotRV: 0.0346, AllV: 0.2559 +[2026-03-20T17:52:06.268653Z] Loop 1985: Reg: 0.3776, AltReg: 0.6291, CorReg: 0.0004, TopReg: 0.4001, AllReg: 0.6294, BotRReg: 0.8345, OV: 0.4860, AltV: 0.2531, CorV: 0.8353, TopV: 0.4585, BotRV: 0.0242, AllV: 0.2528 +[2026-03-20T17:52:10.576374Z] Loop 1990: Reg: 0.3789, AltReg: 0.6312, CorReg: 0.0005, TopReg: 0.4024, AllReg: 0.6315, BotRReg: 0.8358, OV: 0.4847, AltV: 0.2510, CorV: 0.8352, TopV: 0.4562, BotRV: 0.0228, AllV: 0.2507 +[2026-03-20T17:52:14.885892Z] Loop 1995: Reg: 0.3772, AltReg: 0.6285, CorReg: 0.0002, TopReg: 0.4006, AllReg: 0.6288, BotRReg: 0.8322, OV: 0.4864, AltV: 0.2537, CorV: 0.8354, TopV: 0.4580, BotRV: 0.0265, AllV: 0.2534 +[2026-03-20T17:52:19.195531Z] Loop 2000: Reg: 0.3760, AltReg: 0.6266, CorReg: 0.0001, TopReg: 0.3986, AllReg: 0.6269, BotRReg: 0.8270, OV: 0.4876, AltV: 0.2556, CorV: 0.8355, TopV: 0.4600, BotRV: 0.0316, AllV: 0.2553 +[2026-03-20T17:52:27.770837Z] Loop 2010: Reg: 0.3753, AltReg: 0.6255, CorReg: 0.0001, TopReg: 0.3981, AllReg: 0.6259, BotRReg: 0.8199, OV: 0.4882, AltV: 0.2567, CorV: 0.8355, TopV: 0.4605, BotRV: 0.0387, AllV: 0.2564 +[2026-03-20T17:52:36.336333Z] Loop 2020: Reg: 0.3755, AltReg: 0.6258, CorReg: 0.0001, TopReg: 0.3982, AllReg: 0.6261, BotRReg: 0.8228, OV: 0.4881, AltV: 0.2565, CorV: 0.8355, TopV: 0.4604, BotRV: 0.0358, AllV: 0.2561 +[2026-03-20T17:52:44.902875Z] Loop 2030: Reg: 0.3754, AltReg: 0.6256, CorReg: 0.0000, TopReg: 0.3982, AllReg: 0.6259, BotRReg: 0.8194, OV: 0.4882, AltV: 0.2566, CorV: 0.8356, TopV: 0.4605, BotRV: 0.0392, AllV: 0.2563 +[2026-03-20T17:52:53.478260Z] Loop 2040: Reg: 0.3755, AltReg: 0.6258, CorReg: 0.0000, TopReg: 0.3991, AllReg: 0.6262, BotRReg: 0.8194, OV: 0.4881, AltV: 0.2564, CorV: 0.8356, TopV: 0.4596, BotRV: 0.0392, AllV: 0.2561 +[2026-03-20T17:53:02.049354Z] Loop 2050: Reg: 0.3757, AltReg: 0.6261, CorReg: 0.0001, TopReg: 0.4005, AllReg: 0.6265, BotRReg: 0.8195, OV: 0.4879, AltV: 0.2561, CorV: 0.8356, TopV: 0.4581, BotRV: 0.0391, AllV: 0.2558 +[2026-03-20T17:53:10.619676Z] Loop 2060: Reg: 0.3759, AltReg: 0.6265, CorReg: 0.0001, TopReg: 0.4025, AllReg: 0.6268, BotRReg: 0.8194, OV: 0.4877, AltV: 0.2557, CorV: 0.8356, TopV: 0.4561, BotRV: 0.0392, AllV: 0.2554 +[2026-03-20T17:53:19.188858Z] Loop 2070: Reg: 0.3754, AltReg: 0.6257, CorReg: 0.0001, TopReg: 0.3982, AllReg: 0.6260, BotRReg: 0.8198, OV: 0.4882, AltV: 0.2566, CorV: 0.8356, TopV: 0.4605, BotRV: 0.0388, AllV: 0.2562 +[2026-03-20T17:53:27.756916Z] Loop 2080: Reg: 0.3753, AltReg: 0.6255, CorReg: 0.0001, TopReg: 0.3981, AllReg: 0.6259, BotRReg: 0.8195, OV: 0.4882, AltV: 0.2567, CorV: 0.8356, TopV: 0.4605, BotRV: 0.0391, AllV: 0.2564 +[2026-03-20T17:53:36.328479Z] Loop 2090: Reg: 0.3754, AltReg: 0.6256, CorReg: 0.0001, TopReg: 0.3981, AllReg: 0.6259, BotRReg: 0.8194, OV: 0.4882, AltV: 0.2566, CorV: 0.8356, TopV: 0.4605, BotRV: 0.0392, AllV: 0.2563 +[2026-03-20T17:53:44.902362Z] Loop 2100: Reg: 0.3754, AltReg: 0.6256, CorReg: 0.0001, TopReg: 0.3981, AllReg: 0.6260, BotRReg: 0.8213, OV: 0.4882, AltV: 0.2566, CorV: 0.8355, TopV: 0.4605, BotRV: 0.0373, AllV: 0.2563 +[2026-03-20T17:53:53.477887Z] Loop 2110: Reg: 0.3793, AltReg: 0.6318, CorReg: 0.0006, TopReg: 0.3993, AllReg: 0.6321, BotRReg: 0.8368, OV: 0.4842, AltV: 0.2504, CorV: 0.8350, TopV: 0.4593, BotRV: 0.0219, AllV: 0.2501 +[2026-03-20T17:54:02.051163Z] Loop 2120: Reg: 0.3756, AltReg: 0.6260, CorReg: 0.0001, TopReg: 0.3981, AllReg: 0.6264, BotRReg: 0.8262, OV: 0.4879, AltV: 0.2562, CorV: 0.8355, TopV: 0.4605, BotRV: 0.0324, AllV: 0.2559 +[2026-03-20T17:54:10.628020Z] Loop 2130: Reg: 0.3754, AltReg: 0.6256, CorReg: 0.0001, TopReg: 0.3981, AllReg: 0.6260, BotRReg: 0.8207, OV: 0.4882, AltV: 0.2566, CorV: 0.8356, TopV: 0.4605, BotRV: 0.0379, AllV: 0.2563 +[2026-03-20T17:54:19.202557Z] Loop 2140: Reg: 0.3776, AltReg: 0.6291, CorReg: 0.0002, TopReg: 0.3986, AllReg: 0.6295, BotRReg: 0.8353, OV: 0.4860, AltV: 0.2531, CorV: 0.8354, TopV: 0.4600, BotRV: 0.0233, AllV: 0.2528 +[2026-03-20T17:54:27.778716Z] Loop 2150: Reg: 0.3756, AltReg: 0.6259, CorReg: 0.0001, TopReg: 0.3981, AllReg: 0.6263, BotRReg: 0.8244, OV: 0.4880, AltV: 0.2563, CorV: 0.8356, TopV: 0.4605, BotRV: 0.0342, AllV: 0.2560 +[2026-03-20T17:54:36.351643Z] Loop 2160: Reg: 0.3762, AltReg: 0.6269, CorReg: 0.0001, TopReg: 0.3984, AllReg: 0.6272, BotRReg: 0.8308, OV: 0.4874, AltV: 0.2553, CorV: 0.8355, TopV: 0.4603, BotRV: 0.0278, AllV: 0.2550 +[2026-03-20T17:54:44.932922Z] Loop 2170: Reg: 0.3772, AltReg: 0.6285, CorReg: 0.0003, TopReg: 0.3993, AllReg: 0.6289, BotRReg: 0.8344, OV: 0.4863, AltV: 0.2537, CorV: 0.8353, TopV: 0.4593, BotRV: 0.0242, AllV: 0.2534 +[2026-03-20T17:54:53.510400Z] Loop 2180: Reg: 0.3753, AltReg: 0.6255, CorReg: 0.0001, TopReg: 0.3981, AllReg: 0.6259, BotRReg: 0.8196, OV: 0.4882, AltV: 0.2567, CorV: 0.8355, TopV: 0.4605, BotRV: 0.0390, AllV: 0.2564 +[2026-03-20T17:55:02.085248Z] Loop 2190: Reg: 0.3754, AltReg: 0.6256, CorReg: 0.0001, TopReg: 0.3983, AllReg: 0.6260, BotRReg: 0.8194, OV: 0.4882, AltV: 0.2566, CorV: 0.8356, TopV: 0.4603, BotRV: 0.0393, AllV: 0.2562 +[2026-03-20T17:55:10.660992Z] Loop 2200: Reg: 0.3760, AltReg: 0.6266, CorReg: 0.0001, TopReg: 0.4003, AllReg: 0.6270, BotRReg: 0.8194, OV: 0.4876, AltV: 0.2556, CorV: 0.8356, TopV: 0.4583, BotRV: 0.0393, AllV: 0.2553 +[2026-03-20T17:55:19.235538Z] Loop 2210: Reg: 0.3770, AltReg: 0.6283, CorReg: 0.0001, TopReg: 0.4029, AllReg: 0.6287, BotRReg: 0.8193, OV: 0.4866, AltV: 0.2539, CorV: 0.8355, TopV: 0.4557, BotRV: 0.0393, AllV: 0.2536 +[2026-03-20T17:55:27.807287Z] Loop 2220: Reg: 0.3773, AltReg: 0.6288, CorReg: 0.0001, TopReg: 0.4014, AllReg: 0.6291, BotRReg: 0.8193, OV: 0.4863, AltV: 0.2534, CorV: 0.8355, TopV: 0.4572, BotRV: 0.0393, AllV: 0.2531 +[2026-03-20T17:55:36.378966Z] Loop 2230: Reg: 0.3755, AltReg: 0.6258, CorReg: 0.0001, TopReg: 0.3982, AllReg: 0.6262, BotRReg: 0.8194, OV: 0.4881, AltV: 0.2564, CorV: 0.8356, TopV: 0.4604, BotRV: 0.0393, AllV: 0.2561 +[2026-03-20T17:55:44.954923Z] Loop 2240: Reg: 0.3752, AltReg: 0.6253, CorReg: 0.0001, TopReg: 0.3981, AllReg: 0.6256, BotRReg: 0.8194, OV: 0.4884, AltV: 0.2569, CorV: 0.8355, TopV: 0.4606, BotRV: 0.0393, AllV: 0.2566 +[2026-03-20T17:55:53.525090Z] Loop 2250: Reg: 0.3754, AltReg: 0.6256, CorReg: 0.0001, TopReg: 0.3981, AllReg: 0.6260, BotRReg: 0.8193, OV: 0.4882, AltV: 0.2566, CorV: 0.8355, TopV: 0.4606, BotRV: 0.0393, AllV: 0.2563 +[2026-03-20T17:56:02.109517Z] Loop 2260: Reg: 0.3756, AltReg: 0.6259, CorReg: 0.0002, TopReg: 0.3982, AllReg: 0.6262, BotRReg: 0.8194, OV: 0.4880, AltV: 0.2564, CorV: 0.8355, TopV: 0.4604, BotRV: 0.0393, AllV: 0.2560 +[2026-03-20T17:56:10.684955Z] Loop 2270: Reg: 0.3758, AltReg: 0.6262, CorReg: 0.0002, TopReg: 0.3987, AllReg: 0.6265, BotRReg: 0.8194, OV: 0.4878, AltV: 0.2560, CorV: 0.8355, TopV: 0.4599, BotRV: 0.0393, AllV: 0.2557 +[2026-03-20T17:56:19.260289Z] Loop 2280: Reg: 0.3759, AltReg: 0.6264, CorReg: 0.0002, TopReg: 0.3988, AllReg: 0.6268, BotRReg: 0.8194, OV: 0.4877, AltV: 0.2558, CorV: 0.8355, TopV: 0.4598, BotRV: 0.0393, AllV: 0.2555 +[2026-03-20T17:56:27.834160Z] Loop 2290: Reg: 0.3760, AltReg: 0.6265, CorReg: 0.0002, TopReg: 0.3987, AllReg: 0.6269, BotRReg: 0.8193, OV: 0.4876, AltV: 0.2557, CorV: 0.8355, TopV: 0.4599, BotRV: 0.0393, AllV: 0.2554 +[2026-03-20T17:56:36.408700Z] Loop 2300: Reg: 0.3759, AltReg: 0.6265, CorReg: 0.0001, TopReg: 0.3984, AllReg: 0.6268, BotRReg: 0.8193, OV: 0.4877, AltV: 0.2558, CorV: 0.8355, TopV: 0.4602, BotRV: 0.0393, AllV: 0.2554 +[2026-03-20T17:56:44.987860Z] Loop 2310: Reg: 0.3767, AltReg: 0.6277, CorReg: 0.0001, TopReg: 0.3991, AllReg: 0.6281, BotRReg: 0.8193, OV: 0.4869, AltV: 0.2545, CorV: 0.8355, TopV: 0.4595, BotRV: 0.0393, AllV: 0.2542 +[2026-03-20T17:56:53.569714Z] Loop 2320: Reg: 0.3757, AltReg: 0.6261, CorReg: 0.0001, TopReg: 0.3982, AllReg: 0.6265, BotRReg: 0.8193, OV: 0.4879, AltV: 0.2561, CorV: 0.8355, TopV: 0.4604, BotRV: 0.0393, AllV: 0.2558 +[2026-03-20T17:57:02.143918Z] Loop 2330: Reg: 0.3787, AltReg: 0.6312, CorReg: 0.0001, TopReg: 0.4023, AllReg: 0.6315, BotRReg: 0.8193, OV: 0.4848, AltV: 0.2511, CorV: 0.8355, TopV: 0.4563, BotRV: 0.0393, AllV: 0.2507 +[2026-03-20T17:57:10.720757Z] Loop 2340: Reg: 0.3793, AltReg: 0.6321, CorReg: 0.0001, TopReg: 0.4026, AllReg: 0.6325, BotRReg: 0.8193, OV: 0.4843, AltV: 0.2501, CorV: 0.8355, TopV: 0.4561, BotRV: 0.0393, AllV: 0.2498 +[2026-03-20T17:57:19.292423Z] Loop 2350: Reg: 0.3761, AltReg: 0.6267, CorReg: 0.0001, TopReg: 0.4003, AllReg: 0.6271, BotRReg: 0.8196, OV: 0.4875, AltV: 0.2555, CorV: 0.8355, TopV: 0.4584, BotRV: 0.0390, AllV: 0.2552 +[2026-03-20T17:57:27.866417Z] Loop 2360: Reg: 0.3756, AltReg: 0.6260, CorReg: 0.0001, TopReg: 0.3979, AllReg: 0.6263, BotRReg: 0.8199, OV: 0.4880, AltV: 0.2562, CorV: 0.8355, TopV: 0.4607, BotRV: 0.0387, AllV: 0.2560 +[2026-03-20T17:57:36.435301Z] Loop 2370: Reg: 0.3755, AltReg: 0.6256, CorReg: 0.0003, TopReg: 0.3981, AllReg: 0.6260, BotRReg: 0.8243, OV: 0.4881, AltV: 0.2566, CorV: 0.8354, TopV: 0.4605, BotRV: 0.0343, AllV: 0.2563 +[2026-03-20T17:57:45.010450Z] Loop 2380: Reg: 0.3756, AltReg: 0.6257, CorReg: 0.0003, TopReg: 0.3982, AllReg: 0.6261, BotRReg: 0.8250, OV: 0.4880, AltV: 0.2565, CorV: 0.8353, TopV: 0.4605, BotRV: 0.0336, AllV: 0.2561 +[2026-03-20T17:57:53.583943Z] Loop 2390: Reg: 0.3802, AltReg: 0.6322, CorReg: 0.0023, TopReg: 0.4078, AllReg: 0.6325, BotRReg: 0.8371, OV: 0.4833, AltV: 0.2500, CorV: 0.8333, TopV: 0.4509, BotRV: 0.0216, AllV: 0.2497 +[2026-03-20T17:58:02.156138Z] Loop 2400: Reg: 0.3759, AltReg: 0.6264, CorReg: 0.0003, TopReg: 0.3983, AllReg: 0.6267, BotRReg: 0.8304, OV: 0.4877, AltV: 0.2559, CorV: 0.8354, TopV: 0.4603, BotRV: 0.0283, AllV: 0.2555 +[2026-03-20T17:58:10.731493Z] Loop 2410: Reg: 0.3755, AltReg: 0.6256, CorReg: 0.0002, TopReg: 0.3982, AllReg: 0.6260, BotRReg: 0.8247, OV: 0.4881, AltV: 0.2566, CorV: 0.8354, TopV: 0.4604, BotRV: 0.0339, AllV: 0.2563 +[2026-03-20T17:58:19.308044Z] Loop 2420: Reg: 0.3755, AltReg: 0.6258, CorReg: 0.0002, TopReg: 0.3987, AllReg: 0.6261, BotRReg: 0.8251, OV: 0.4880, AltV: 0.2565, CorV: 0.8354, TopV: 0.4599, BotRV: 0.0335, AllV: 0.2561 +[2026-03-20T17:58:27.883253Z] Loop 2430: Reg: 0.3754, AltReg: 0.6255, CorReg: 0.0002, TopReg: 0.3983, AllReg: 0.6258, BotRReg: 0.8237, OV: 0.4882, AltV: 0.2567, CorV: 0.8354, TopV: 0.4603, BotRV: 0.0350, AllV: 0.2564 +[2026-03-20T17:58:36.455149Z] Loop 2440: Reg: 0.3757, AltReg: 0.6260, CorReg: 0.0002, TopReg: 0.3990, AllReg: 0.6264, BotRReg: 0.8276, OV: 0.4879, AltV: 0.2562, CorV: 0.8354, TopV: 0.4597, BotRV: 0.0310, AllV: 0.2559 +[2026-03-20T17:58:45.033743Z] Loop 2450: Reg: 0.3754, AltReg: 0.6255, CorReg: 0.0002, TopReg: 0.3984, AllReg: 0.6258, BotRReg: 0.8236, OV: 0.4882, AltV: 0.2567, CorV: 0.8355, TopV: 0.4602, BotRV: 0.0351, AllV: 0.2564 +[2026-03-20T17:58:53.616057Z] Loop 2460: Reg: 0.3752, AltReg: 0.6252, CorReg: 0.0002, TopReg: 0.3982, AllReg: 0.6255, BotRReg: 0.8198, OV: 0.4884, AltV: 0.2570, CorV: 0.8354, TopV: 0.4604, BotRV: 0.0388, AllV: 0.2567 +[2026-03-20T17:59:02.195673Z] Loop 2470: Reg: 0.3768, AltReg: 0.6279, CorReg: 0.0001, TopReg: 0.4059, AllReg: 0.6282, BotRReg: 0.8260, OV: 0.4868, AltV: 0.2543, CorV: 0.8355, TopV: 0.4528, BotRV: 0.0326, AllV: 0.2541 +[2026-03-20T17:59:10.769792Z] Loop 2480: Reg: 0.3762, AltReg: 0.6268, CorReg: 0.0003, TopReg: 0.4008, AllReg: 0.6272, BotRReg: 0.8286, OV: 0.4874, AltV: 0.2554, CorV: 0.8353, TopV: 0.4578, BotRV: 0.0300, AllV: 0.2551 +[2026-03-20T17:59:19.339576Z] Loop 2490: Reg: 0.3803, AltReg: 0.6321, CorReg: 0.0025, TopReg: 0.4093, AllReg: 0.6325, BotRReg: 0.8354, OV: 0.4833, AltV: 0.2501, CorV: 0.8331, TopV: 0.4494, BotRV: 0.0232, AllV: 0.2498 +[2026-03-20T17:59:27.911141Z] Loop 2500: Reg: 0.3770, AltReg: 0.6279, CorReg: 0.0007, TopReg: 0.4020, AllReg: 0.6282, BotRReg: 0.8314, OV: 0.4866, AltV: 0.2544, CorV: 0.8349, TopV: 0.4566, BotRV: 0.0272, AllV: 0.2540 +[2026-03-20T17:59:36.481686Z] Loop 2510: Reg: 0.3753, AltReg: 0.6254, CorReg: 0.0002, TopReg: 0.3983, AllReg: 0.6257, BotRReg: 0.8214, OV: 0.4883, AltV: 0.2569, CorV: 0.8355, TopV: 0.4604, BotRV: 0.0372, AllV: 0.2565 +[2026-03-20T17:59:45.055312Z] Loop 2520: Reg: 0.3752, AltReg: 0.6253, CorReg: 0.0002, TopReg: 0.3982, AllReg: 0.6256, BotRReg: 0.8193, OV: 0.4884, AltV: 0.2570, CorV: 0.8354, TopV: 0.4605, BotRV: 0.0393, AllV: 0.2566 +[2026-03-20T17:59:53.629278Z] Loop 2530: Reg: 0.3758, AltReg: 0.6263, CorReg: 0.0001, TopReg: 0.3999, AllReg: 0.6267, BotRReg: 0.8192, OV: 0.4877, AltV: 0.2559, CorV: 0.8355, TopV: 0.4587, BotRV: 0.0394, AllV: 0.2556 +[2026-03-20T18:00:02.213822Z] Loop 2540: Reg: 0.3771, AltReg: 0.6284, CorReg: 0.0002, TopReg: 0.4013, AllReg: 0.6287, BotRReg: 0.8192, OV: 0.4865, AltV: 0.2538, CorV: 0.8355, TopV: 0.4573, BotRV: 0.0394, AllV: 0.2535 +[2026-03-20T18:00:10.802568Z] Loop 2550: Reg: 0.3784, AltReg: 0.6306, CorReg: 0.0001, TopReg: 0.4017, AllReg: 0.6309, BotRReg: 0.8192, OV: 0.4852, AltV: 0.2516, CorV: 0.8355, TopV: 0.4570, BotRV: 0.0394, AllV: 0.2513 +[2026-03-20T18:00:19.379273Z] Loop 2560: Reg: 0.3760, AltReg: 0.6266, CorReg: 0.0002, TopReg: 0.4016, AllReg: 0.6269, BotRReg: 0.8193, OV: 0.4876, AltV: 0.2556, CorV: 0.8355, TopV: 0.4570, BotRV: 0.0393, AllV: 0.2553 +[2026-03-20T18:00:27.958821Z] Loop 2570: Reg: 0.3765, AltReg: 0.6274, CorReg: 0.0002, TopReg: 0.4019, AllReg: 0.6277, BotRReg: 0.8201, OV: 0.4871, AltV: 0.2548, CorV: 0.8354, TopV: 0.4567, BotRV: 0.0385, AllV: 0.2546 +[2026-03-20T18:00:36.536126Z] Loop 2580: Reg: 0.3765, AltReg: 0.6273, CorReg: 0.0002, TopReg: 0.4018, AllReg: 0.6276, BotRReg: 0.8200, OV: 0.4871, AltV: 0.2549, CorV: 0.8354, TopV: 0.4568, BotRV: 0.0387, AllV: 0.2546 +[2026-03-20T18:00:45.115520Z] Loop 2590: Reg: 0.3760, AltReg: 0.6267, CorReg: 0.0001, TopReg: 0.4014, AllReg: 0.6270, BotRReg: 0.8192, OV: 0.4875, AltV: 0.2555, CorV: 0.8355, TopV: 0.4573, BotRV: 0.0394, AllV: 0.2552 +[2026-03-20T18:00:53.688603Z] Loop 2600: Reg: 0.3772, AltReg: 0.6287, CorReg: 0.0001, TopReg: 0.4021, AllReg: 0.6290, BotRReg: 0.8192, OV: 0.4863, AltV: 0.2536, CorV: 0.8355, TopV: 0.4566, BotRV: 0.0394, AllV: 0.2532 +[2026-03-20T18:01:02.266507Z] Loop 2610: Reg: 0.3765, AltReg: 0.6274, CorReg: 0.0001, TopReg: 0.4015, AllReg: 0.6278, BotRReg: 0.8192, OV: 0.4871, AltV: 0.2548, CorV: 0.8355, TopV: 0.4571, BotRV: 0.0394, AllV: 0.2545 +[2026-03-20T18:01:10.840192Z] Loop 2620: Reg: 0.3759, AltReg: 0.6264, CorReg: 0.0001, TopReg: 0.4012, AllReg: 0.6267, BotRReg: 0.8192, OV: 0.4877, AltV: 0.2558, CorV: 0.8355, TopV: 0.4575, BotRV: 0.0394, AllV: 0.2555 +[2026-03-20T18:01:19.414870Z] Loop 2630: Reg: 0.3759, AltReg: 0.6265, CorReg: 0.0001, TopReg: 0.4014, AllReg: 0.6269, BotRReg: 0.8192, OV: 0.4876, AltV: 0.2557, CorV: 0.8355, TopV: 0.4573, BotRV: 0.0394, AllV: 0.2554 +[2026-03-20T18:01:27.988389Z] Loop 2640: Reg: 0.3777, AltReg: 0.6294, CorReg: 0.0001, TopReg: 0.4022, AllReg: 0.6298, BotRReg: 0.8192, OV: 0.4859, AltV: 0.2528, CorV: 0.8356, TopV: 0.4564, BotRV: 0.0394, AllV: 0.2525 +[2026-03-20T18:01:36.567199Z] Loop 2650: Reg: 0.3757, AltReg: 0.6260, CorReg: 0.0002, TopReg: 0.4007, AllReg: 0.6264, BotRReg: 0.8194, OV: 0.4879, AltV: 0.2562, CorV: 0.8355, TopV: 0.4580, BotRV: 0.0392, AllV: 0.2559 +[2026-03-20T18:01:45.148717Z] Loop 2660: Reg: 0.3775, AltReg: 0.6290, CorReg: 0.0002, TopReg: 0.4058, AllReg: 0.6293, BotRReg: 0.8220, OV: 0.4861, AltV: 0.2532, CorV: 0.8354, TopV: 0.4529, BotRV: 0.0367, AllV: 0.2530 +[2026-03-20T18:01:53.724508Z] Loop 2670: Reg: 0.3752, AltReg: 0.6253, CorReg: 0.0002, TopReg: 0.3982, AllReg: 0.6256, BotRReg: 0.8195, OV: 0.4883, AltV: 0.2569, CorV: 0.8354, TopV: 0.4604, BotRV: 0.0391, AllV: 0.2566 +[2026-03-20T18:02:02.300022Z] Loop 2680: Reg: 0.3750, AltReg: 0.6249, CorReg: 0.0002, TopReg: 0.3981, AllReg: 0.6253, BotRReg: 0.8193, OV: 0.4885, AltV: 0.2573, CorV: 0.8354, TopV: 0.4605, BotRV: 0.0394, AllV: 0.2570 +[2026-03-20T18:02:10.875169Z] Loop 2690: Reg: 0.3750, AltReg: 0.6248, CorReg: 0.0003, TopReg: 0.3981, AllReg: 0.6252, BotRReg: 0.8193, OV: 0.4885, AltV: 0.2574, CorV: 0.8353, TopV: 0.4605, BotRV: 0.0393, AllV: 0.2570 +[2026-03-20T18:02:19.451353Z] Loop 2700: Reg: 0.3752, AltReg: 0.6249, CorReg: 0.0006, TopReg: 0.3980, AllReg: 0.6253, BotRReg: 0.8204, OV: 0.4884, AltV: 0.2573, CorV: 0.8351, TopV: 0.4606, BotRV: 0.0382, AllV: 0.2570 +[2026-03-20T18:02:28.028872Z] Loop 2710: Reg: 0.3759, AltReg: 0.6259, CorReg: 0.0009, TopReg: 0.3982, AllReg: 0.6262, BotRReg: 0.8282, OV: 0.4877, AltV: 0.2563, CorV: 0.8348, TopV: 0.4604, BotRV: 0.0304, AllV: 0.2560 +[2026-03-20T18:02:36.610575Z] Loop 2720: Reg: 0.3790, AltReg: 0.6312, CorReg: 0.0008, TopReg: 0.4056, AllReg: 0.6315, BotRReg: 0.8373, OV: 0.4846, AltV: 0.2510, CorV: 0.8348, TopV: 0.4531, BotRV: 0.0214, AllV: 0.2508 +[2026-03-20T18:02:45.187500Z] Loop 2730: Reg: 0.3770, AltReg: 0.6280, CorReg: 0.0006, TopReg: 0.4008, AllReg: 0.6283, BotRReg: 0.8357, OV: 0.4865, AltV: 0.2542, CorV: 0.8350, TopV: 0.4578, BotRV: 0.0229, AllV: 0.2540 +[2026-03-20T18:02:53.765742Z] Loop 2740: Reg: 0.3757, AltReg: 0.6259, CorReg: 0.0003, TopReg: 0.3983, AllReg: 0.6263, BotRReg: 0.8286, OV: 0.4879, AltV: 0.2563, CorV: 0.8353, TopV: 0.4604, BotRV: 0.0300, AllV: 0.2560 +[2026-03-20T18:03:02.342411Z] Loop 2750: Reg: 0.3753, AltReg: 0.6252, CorReg: 0.0004, TopReg: 0.3982, AllReg: 0.6256, BotRReg: 0.8224, OV: 0.4883, AltV: 0.2570, CorV: 0.8352, TopV: 0.4604, BotRV: 0.0362, AllV: 0.2567 +[2026-03-20T18:03:10.914140Z] Loop 2760: Reg: 0.3755, AltReg: 0.6257, CorReg: 0.0002, TopReg: 0.3988, AllReg: 0.6261, BotRReg: 0.8250, OV: 0.4881, AltV: 0.2565, CorV: 0.8354, TopV: 0.4598, BotRV: 0.0337, AllV: 0.2562 +[2026-03-20T18:03:19.483523Z] Loop 2770: Reg: 0.3772, AltReg: 0.6285, CorReg: 0.0003, TopReg: 0.4057, AllReg: 0.6288, BotRReg: 0.8336, OV: 0.4864, AltV: 0.2537, CorV: 0.8354, TopV: 0.4530, BotRV: 0.0250, AllV: 0.2534 +[2026-03-20T18:03:28.053602Z] Loop 2780: Reg: 0.3752, AltReg: 0.6252, CorReg: 0.0003, TopReg: 0.3982, AllReg: 0.6255, BotRReg: 0.8198, OV: 0.4884, AltV: 0.2570, CorV: 0.8353, TopV: 0.4604, BotRV: 0.0388, AllV: 0.2567 +[2026-03-20T18:03:36.625739Z] Loop 2790: Reg: 0.3753, AltReg: 0.6254, CorReg: 0.0002, TopReg: 0.3984, AllReg: 0.6257, BotRReg: 0.8193, OV: 0.4883, AltV: 0.2568, CorV: 0.8355, TopV: 0.4603, BotRV: 0.0394, AllV: 0.2565 +[2026-03-20T18:03:45.198577Z] Loop 2800: Reg: 0.3772, AltReg: 0.6285, CorReg: 0.0002, TopReg: 0.4135, AllReg: 0.6288, BotRReg: 0.8192, OV: 0.4864, AltV: 0.2538, CorV: 0.8354, TopV: 0.4452, BotRV: 0.0394, AllV: 0.2534 +[2026-03-20T18:03:53.773247Z] Loop 2810: Reg: 0.3805, AltReg: 0.6339, CorReg: 0.0003, TopReg: 0.4223, AllReg: 0.6343, BotRReg: 0.8193, OV: 0.4831, AltV: 0.2483, CorV: 0.8354, TopV: 0.4363, BotRV: 0.0394, AllV: 0.2480 +[2026-03-20T18:04:02.343824Z] Loop 2820: Reg: 0.3772, AltReg: 0.6286, CorReg: 0.0003, TopReg: 0.4139, AllReg: 0.6289, BotRReg: 0.8193, OV: 0.4863, AltV: 0.2537, CorV: 0.8354, TopV: 0.4448, BotRV: 0.0394, AllV: 0.2533 +[2026-03-20T18:04:10.914458Z] Loop 2830: Reg: 0.3775, AltReg: 0.6291, CorReg: 0.0001, TopReg: 0.4061, AllReg: 0.6294, BotRReg: 0.8191, OV: 0.4861, AltV: 0.2531, CorV: 0.8355, TopV: 0.4526, BotRV: 0.0395, AllV: 0.2528 +[2026-03-20T18:04:19.491530Z] Loop 2840: Reg: 0.3757, AltReg: 0.6260, CorReg: 0.0002, TopReg: 0.4004, AllReg: 0.6264, BotRReg: 0.8192, OV: 0.4879, AltV: 0.2562, CorV: 0.8354, TopV: 0.4583, BotRV: 0.0394, AllV: 0.2559 +[2026-03-20T18:04:28.063301Z] Loop 2850: Reg: 0.3750, AltReg: 0.6249, CorReg: 0.0003, TopReg: 0.3980, AllReg: 0.6252, BotRReg: 0.8192, OV: 0.4885, AltV: 0.2573, CorV: 0.8354, TopV: 0.4606, BotRV: 0.0394, AllV: 0.2570 +[2026-03-20T18:04:36.638211Z] Loop 2860: Reg: 0.3750, AltReg: 0.6248, CorReg: 0.0002, TopReg: 0.3978, AllReg: 0.6252, BotRReg: 0.8193, OV: 0.4886, AltV: 0.2574, CorV: 0.8354, TopV: 0.4608, BotRV: 0.0394, AllV: 0.2571 +[2026-03-20T18:04:45.215819Z] Loop 2870: Reg: 0.3750, AltReg: 0.6248, CorReg: 0.0002, TopReg: 0.3981, AllReg: 0.6252, BotRReg: 0.8192, OV: 0.4886, AltV: 0.2574, CorV: 0.8354, TopV: 0.4605, BotRV: 0.0394, AllV: 0.2571 +[2026-03-20T18:04:53.792978Z] Loop 2880: Reg: 0.3750, AltReg: 0.6248, CorReg: 0.0003, TopReg: 0.3981, AllReg: 0.6251, BotRReg: 0.8192, OV: 0.4886, AltV: 0.2575, CorV: 0.8353, TopV: 0.4605, BotRV: 0.0394, AllV: 0.2571 +[2026-03-20T18:05:02.364290Z] Loop 2890: Reg: 0.3750, AltReg: 0.6247, CorReg: 0.0004, TopReg: 0.3982, AllReg: 0.6251, BotRReg: 0.8192, OV: 0.4886, AltV: 0.2575, CorV: 0.8353, TopV: 0.4605, BotRV: 0.0395, AllV: 0.2572 +[2026-03-20T18:05:10.936220Z] Loop 2900: Reg: 0.3751, AltReg: 0.6248, CorReg: 0.0005, TopReg: 0.3980, AllReg: 0.6252, BotRReg: 0.8190, OV: 0.4885, AltV: 0.2574, CorV: 0.8352, TopV: 0.4606, BotRV: 0.0396, AllV: 0.2571 +[2026-03-20T18:05:19.509228Z] Loop 2910: Reg: 0.3752, AltReg: 0.6250, CorReg: 0.0005, TopReg: 0.3980, AllReg: 0.6254, BotRReg: 0.8191, OV: 0.4884, AltV: 0.2572, CorV: 0.8352, TopV: 0.4606, BotRV: 0.0395, AllV: 0.2569 +[2026-03-20T18:05:28.083934Z] Loop 2920: Reg: 0.3756, AltReg: 0.6256, CorReg: 0.0006, TopReg: 0.3990, AllReg: 0.6260, BotRReg: 0.8191, OV: 0.4880, AltV: 0.2566, CorV: 0.8350, TopV: 0.4596, BotRV: 0.0395, AllV: 0.2563 +[2026-03-20T18:05:36.658076Z] Loop 2930: Reg: 0.3759, AltReg: 0.6260, CorReg: 0.0007, TopReg: 0.4003, AllReg: 0.6264, BotRReg: 0.8190, OV: 0.4877, AltV: 0.2562, CorV: 0.8349, TopV: 0.4584, BotRV: 0.0396, AllV: 0.2559 +[2026-03-20T18:05:45.233367Z] Loop 2940: Reg: 0.3752, AltReg: 0.6248, CorReg: 0.0009, TopReg: 0.3981, AllReg: 0.6251, BotRReg: 0.8189, OV: 0.4884, AltV: 0.2575, CorV: 0.8347, TopV: 0.4605, BotRV: 0.0397, AllV: 0.2571 +[2026-03-20T18:05:53.810599Z] Loop 2950: Reg: 0.3753, AltReg: 0.6245, CorReg: 0.0015, TopReg: 0.3983, AllReg: 0.6249, BotRReg: 0.8187, OV: 0.4883, AltV: 0.2577, CorV: 0.8341, TopV: 0.4603, BotRV: 0.0399, AllV: 0.2574 +[2026-03-20T18:06:02.382513Z] Loop 2960: Reg: 0.3749, AltReg: 0.6240, CorReg: 0.0012, TopReg: 0.3979, AllReg: 0.6243, BotRReg: 0.8186, OV: 0.4887, AltV: 0.2583, CorV: 0.8344, TopV: 0.4607, BotRV: 0.0401, AllV: 0.2579 +[2026-03-20T18:06:10.952490Z] Loop 2970: Reg: 0.3749, AltReg: 0.6238, CorReg: 0.0015, TopReg: 0.3979, AllReg: 0.6242, BotRReg: 0.8185, OV: 0.4887, AltV: 0.2584, CorV: 0.8341, TopV: 0.4607, BotRV: 0.0401, AllV: 0.2581 +[2026-03-20T18:06:19.521652Z] Loop 2980: Reg: 0.3751, AltReg: 0.6239, CorReg: 0.0017, TopReg: 0.3995, AllReg: 0.6243, BotRReg: 0.8181, OV: 0.4885, AltV: 0.2583, CorV: 0.8339, TopV: 0.4591, BotRV: 0.0405, AllV: 0.2580 +[2026-03-20T18:06:28.094604Z] Loop 2990: Reg: 0.3745, AltReg: 0.6227, CorReg: 0.0021, TopReg: 0.4017, AllReg: 0.6231, BotRReg: 0.8154, OV: 0.4891, AltV: 0.2595, CorV: 0.8336, TopV: 0.4569, BotRV: 0.0432, AllV: 0.2592 +[2026-03-20T18:06:36.670806Z] Loop 3000: Reg: 0.3726, AltReg: 0.6168, CorReg: 0.0063, TopReg: 0.4020, AllReg: 0.6171, BotRReg: 0.8113, OV: 0.4910, AltV: 0.2654, CorV: 0.8293, TopV: 0.4566, BotRV: 0.0473, AllV: 0.2651 +[2026-03-20T18:06:45.243077Z] Loop 3010: Reg: 0.3670, AltReg: 0.5945, CorReg: 0.0256, TopReg: 0.4107, AllReg: 0.5949, BotRReg: 0.7819, OV: 0.4966, AltV: 0.2877, CorV: 0.8100, TopV: 0.4479, BotRV: 0.0768, AllV: 0.2873 +[2026-03-20T18:06:53.820836Z] Loop 3020: Reg: 0.3636, AltReg: 0.5658, CorReg: 0.0603, TopReg: 0.4283, AllReg: 0.5661, BotRReg: 0.7276, OV: 0.5000, AltV: 0.3164, CorV: 0.7753, TopV: 0.4303, BotRV: 0.1311, AllV: 0.3161 +[2026-03-20T18:07:02.394703Z] Loop 3030: Reg: 0.3597, AltReg: 0.5634, CorReg: 0.0541, TopReg: 0.4246, AllReg: 0.5637, BotRReg: 0.7297, OV: 0.5039, AltV: 0.3188, CorV: 0.7816, TopV: 0.4340, BotRV: 0.1290, AllV: 0.3185 +[2026-03-20T18:07:10.983906Z] Loop 3040: Reg: 0.3573, AltReg: 0.5535, CorReg: 0.0629, TopReg: 0.4329, AllReg: 0.5537, BotRReg: 0.7010, OV: 0.5063, AltV: 0.3287, CorV: 0.7727, TopV: 0.4257, BotRV: 0.1576, AllV: 0.3285 +[2026-03-20T18:07:19.561143Z] Loop 3050: Reg: 0.3556, AltReg: 0.5491, CorReg: 0.0652, TopReg: 0.4393, AllReg: 0.5492, BotRReg: 0.6827, OV: 0.5080, AltV: 0.3331, CorV: 0.7704, TopV: 0.4193, BotRV: 0.1759, AllV: 0.3330 +[2026-03-20T18:07:28.141095Z] Loop 3060: Reg: 0.3545, AltReg: 0.5545, CorReg: 0.0544, TopReg: 0.4372, AllReg: 0.5547, BotRReg: 0.6988, OV: 0.5091, AltV: 0.3277, CorV: 0.7812, TopV: 0.4214, BotRV: 0.1598, AllV: 0.3276 +[2026-03-20T18:07:36.729406Z] Loop 3070: Reg: 0.3493, AltReg: 0.5493, CorReg: 0.0494, TopReg: 0.4362, AllReg: 0.5494, BotRReg: 0.6700, OV: 0.5143, AltV: 0.3329, CorV: 0.7862, TopV: 0.4224, BotRV: 0.1887, AllV: 0.3329 +[2026-03-20T18:07:45.308781Z] Loop 3080: Reg: 0.3492, AltReg: 0.5398, CorReg: 0.0633, TopReg: 0.4444, AllReg: 0.5399, BotRReg: 0.6573, OV: 0.5144, AltV: 0.3424, CorV: 0.7723, TopV: 0.4142, BotRV: 0.2013, AllV: 0.3424 +[2026-03-20T18:07:53.883062Z] Loop 3090: Reg: 0.3437, AltReg: 0.5405, CorReg: 0.0484, TopReg: 0.4511, AllReg: 0.5406, BotRReg: 0.6576, OV: 0.5199, AltV: 0.3417, CorV: 0.7872, TopV: 0.4075, BotRV: 0.2010, AllV: 0.3416 +[2026-03-20T18:08:02.455562Z] Loop 3100: Reg: 0.3377, AltReg: 0.5263, CorReg: 0.0549, TopReg: 0.4552, AllReg: 0.5263, BotRReg: 0.6151, OV: 0.5258, AltV: 0.3559, CorV: 0.7807, TopV: 0.4034, BotRV: 0.2435, AllV: 0.3560 +[2026-03-20T18:08:11.027345Z] Loop 3110: Reg: 0.3336, AltReg: 0.5252, CorReg: 0.0462, TopReg: 0.4315, AllReg: 0.5252, BotRReg: 0.6321, OV: 0.5300, AltV: 0.3570, CorV: 0.7895, TopV: 0.4271, BotRV: 0.2265, AllV: 0.3570 +[2026-03-20T18:08:19.607797Z] Loop 3120: Reg: 0.3035, AltReg: 0.4751, CorReg: 0.0461, TopReg: 0.4206, AllReg: 0.4751, BotRReg: 0.5074, OV: 0.5601, AltV: 0.4071, CorV: 0.7895, TopV: 0.4380, BotRV: 0.3512, AllV: 0.4072 +[2026-03-20T18:08:28.186515Z] Loop 3130: Reg: 0.2744, AltReg: 0.4370, CorReg: 0.0305, TopReg: 0.3724, AllReg: 0.4371, BotRReg: 0.4955, OV: 0.5892, AltV: 0.4452, CorV: 0.8052, TopV: 0.4862, BotRV: 0.3631, AllV: 0.4451 +[2026-03-20T18:08:36.762579Z] Loop 3140: Reg: 0.2499, AltReg: 0.3914, CorReg: 0.0378, TopReg: 0.3565, AllReg: 0.3915, BotRReg: 0.4404, OV: 0.6136, AltV: 0.4908, CorV: 0.7978, TopV: 0.5021, BotRV: 0.4182, AllV: 0.4907 +[2026-03-20T18:08:45.348039Z] Loop 3150: Reg: 0.2377, AltReg: 0.3692, CorReg: 0.0405, TopReg: 0.3720, AllReg: 0.3694, BotRReg: 0.4197, OV: 0.6259, AltV: 0.5131, CorV: 0.7951, TopV: 0.4867, BotRV: 0.4389, AllV: 0.5129 +[2026-03-20T18:08:53.921650Z] Loop 3160: Reg: 0.2133, AltReg: 0.3340, CorReg: 0.0324, TopReg: 0.3308, AllReg: 0.3342, BotRReg: 0.3912, OV: 0.6502, AltV: 0.5482, CorV: 0.8033, TopV: 0.5278, BotRV: 0.4674, AllV: 0.5481 +[2026-03-20T18:09:02.500192Z] Loop 3170: Reg: 0.1944, AltReg: 0.3021, CorReg: 0.0328, TopReg: 0.3366, AllReg: 0.3021, BotRReg: 0.3439, OV: 0.6692, AltV: 0.5802, CorV: 0.8028, TopV: 0.5220, BotRV: 0.5147, AllV: 0.5801 +[2026-03-20T18:09:11.076705Z] Loop 3180: Reg: 0.1666, AltReg: 0.2567, CorReg: 0.0315, TopReg: 0.3222, AllReg: 0.2566, BotRReg: 0.2701, OV: 0.6970, AltV: 0.6255, CorV: 0.8041, TopV: 0.5365, BotRV: 0.5885, AllV: 0.6256 +[2026-03-20T18:09:19.647879Z] Loop 3190: Reg: 0.1457, AltReg: 0.2218, CorReg: 0.0315, TopReg: 0.3136, AllReg: 0.2218, BotRReg: 0.2179, OV: 0.7179, AltV: 0.6604, CorV: 0.8041, TopV: 0.5451, BotRV: 0.6408, AllV: 0.6605 +[2026-03-20T18:09:28.223939Z] Loop 3200: Reg: 0.1318, AltReg: 0.2030, CorReg: 0.0251, TopReg: 0.2697, AllReg: 0.2030, BotRReg: 0.2092, OV: 0.7317, AltV: 0.6792, CorV: 0.8105, TopV: 0.5889, BotRV: 0.6494, AllV: 0.6793 +[2026-03-20T18:09:36.806743Z] Loop 3210: Reg: 0.1204, AltReg: 0.1853, CorReg: 0.0229, TopReg: 0.2610, AllReg: 0.1853, BotRReg: 0.1533, OV: 0.7432, AltV: 0.6969, CorV: 0.8127, TopV: 0.5976, BotRV: 0.7054, AllV: 0.6970 +[2026-03-20T18:09:45.389183Z] Loop 3220: Reg: 0.1047, AltReg: 0.1637, CorReg: 0.0162, TopReg: 0.2469, AllReg: 0.1637, BotRReg: 0.1405, OV: 0.7589, AltV: 0.7185, CorV: 0.8195, TopV: 0.6117, BotRV: 0.7181, AllV: 0.7186 +[2026-03-20T18:09:53.967048Z] Loop 3230: Reg: 0.0979, AltReg: 0.1512, CorReg: 0.0179, TopReg: 0.2227, AllReg: 0.1512, BotRReg: 0.1258, OV: 0.7657, AltV: 0.7310, CorV: 0.8178, TopV: 0.6359, BotRV: 0.7328, AllV: 0.7310 +[2026-03-20T18:10:02.546175Z] Loop 3240: Reg: 0.0992, AltReg: 0.1503, CorReg: 0.0225, TopReg: 0.2271, AllReg: 0.1502, BotRReg: 0.1278, OV: 0.7644, AltV: 0.7319, CorV: 0.8131, TopV: 0.6315, BotRV: 0.7308, AllV: 0.7320 +[2026-03-20T18:10:11.131030Z] Loop 3250: Reg: 0.0893, AltReg: 0.1416, CorReg: 0.0109, TopReg: 0.1901, AllReg: 0.1416, BotRReg: 0.1380, OV: 0.7743, AltV: 0.7406, CorV: 0.8248, TopV: 0.6685, BotRV: 0.7206, AllV: 0.7406 +[2026-03-20T18:10:19.702347Z] Loop 3260: Reg: 0.0846, AltReg: 0.1311, CorReg: 0.0150, TopReg: 0.2056, AllReg: 0.1310, BotRReg: 0.1174, OV: 0.7789, AltV: 0.7511, CorV: 0.8206, TopV: 0.6530, BotRV: 0.7412, AllV: 0.7512 +[2026-03-20T18:10:28.274303Z] Loop 3270: Reg: 0.0789, AltReg: 0.1238, CorReg: 0.0114, TopReg: 0.1962, AllReg: 0.1239, BotRReg: 0.0832, OV: 0.7847, AltV: 0.7584, CorV: 0.8242, TopV: 0.6625, BotRV: 0.7755, AllV: 0.7584 +[2026-03-20T18:10:36.846807Z] Loop 3280: Reg: 0.0706, AltReg: 0.1109, CorReg: 0.0102, TopReg: 0.1389, AllReg: 0.1109, BotRReg: 0.0971, OV: 0.7930, AltV: 0.7714, CorV: 0.8254, TopV: 0.7198, BotRV: 0.7615, AllV: 0.7713 +[2026-03-20T18:10:45.422965Z] Loop 3290: Reg: 0.0668, AltReg: 0.1040, CorReg: 0.0108, TopReg: 0.2035, AllReg: 0.1040, BotRReg: 0.0623, OV: 0.7968, AltV: 0.7782, CorV: 0.8248, TopV: 0.6551, BotRV: 0.7963, AllV: 0.7782 +[2026-03-20T18:10:54.006085Z] Loop 3300: Reg: 0.0617, AltReg: 0.0977, CorReg: 0.0079, TopReg: 0.1489, AllReg: 0.0977, BotRReg: 0.0653, OV: 0.8018, AltV: 0.7846, CorV: 0.8278, TopV: 0.7098, BotRV: 0.7933, AllV: 0.7845 +[2026-03-20T18:11:02.585066Z] Loop 3310: Reg: 0.0563, AltReg: 0.0886, CorReg: 0.0079, TopReg: 0.1593, AllReg: 0.0887, BotRReg: 0.0735, OV: 0.8073, AltV: 0.7936, CorV: 0.8277, TopV: 0.6993, BotRV: 0.7851, AllV: 0.7936 +[2026-03-20T18:11:11.167813Z] Loop 3320: Reg: 0.0552, AltReg: 0.0861, CorReg: 0.0090, TopReg: 0.1489, AllReg: 0.0860, BotRReg: 0.0570, OV: 0.8084, AltV: 0.7962, CorV: 0.8267, TopV: 0.7097, BotRV: 0.8016, AllV: 0.7962 +[2026-03-20T18:11:19.744050Z] Loop 3330: Reg: 0.0559, AltReg: 0.0871, CorReg: 0.0091, TopReg: 0.1473, AllReg: 0.0872, BotRReg: 0.0567, OV: 0.8076, AltV: 0.7951, CorV: 0.8265, TopV: 0.7114, BotRV: 0.8019, AllV: 0.7951 +[2026-03-20T18:11:28.324689Z] Loop 3340: Reg: 0.0490, AltReg: 0.0746, CorReg: 0.0106, TopReg: 0.1348, AllReg: 0.0747, BotRReg: 0.0447, OV: 0.8146, AltV: 0.8076, CorV: 0.8251, TopV: 0.7239, BotRV: 0.8139, AllV: 0.8076 +[2026-03-20T18:11:36.898777Z] Loop 3350: Reg: 0.0439, AltReg: 0.0689, CorReg: 0.0064, TopReg: 0.1394, AllReg: 0.0690, BotRReg: 0.0474, OV: 0.8197, AltV: 0.8133, CorV: 0.8293, TopV: 0.7193, BotRV: 0.8112, AllV: 0.8133 +[2026-03-20T18:11:45.478023Z] Loop 3360: Reg: 0.0422, AltReg: 0.0668, CorReg: 0.0054, TopReg: 0.1369, AllReg: 0.0668, BotRReg: 0.0536, OV: 0.8213, AltV: 0.8154, CorV: 0.8302, TopV: 0.7217, BotRV: 0.8050, AllV: 0.8154 +[2026-03-20T18:11:54.051955Z] Loop 3370: Reg: 0.0413, AltReg: 0.0658, CorReg: 0.0046, TopReg: 0.0936, AllReg: 0.0658, BotRReg: 0.0703, OV: 0.8223, AltV: 0.8164, CorV: 0.8311, TopV: 0.7650, BotRV: 0.7884, AllV: 0.8164 +[2026-03-20T18:12:02.632760Z] Loop 3380: Reg: 0.0395, AltReg: 0.0626, CorReg: 0.0048, TopReg: 0.1130, AllReg: 0.0626, BotRReg: 0.0431, OV: 0.8241, AltV: 0.8196, CorV: 0.8308, TopV: 0.7457, BotRV: 0.8155, AllV: 0.8197 +[2026-03-20T18:12:11.217953Z] Loop 3390: Reg: 0.0362, AltReg: 0.0563, CorReg: 0.0061, TopReg: 0.1070, AllReg: 0.0563, BotRReg: 0.0379, OV: 0.8274, AltV: 0.8259, CorV: 0.8296, TopV: 0.7516, BotRV: 0.8207, AllV: 0.8259 +[2026-03-20T18:12:19.795811Z] Loop 3400: Reg: 0.0390, AltReg: 0.0629, CorReg: 0.0032, TopReg: 0.0810, AllReg: 0.0629, BotRReg: 0.0526, OV: 0.8246, AltV: 0.8193, CorV: 0.8324, TopV: 0.7777, BotRV: 0.8061, AllV: 0.8193 +[2026-03-20T18:12:28.377404Z] Loop 3410: Reg: 0.0391, AltReg: 0.0630, CorReg: 0.0032, TopReg: 0.1018, AllReg: 0.0632, BotRReg: 0.0711, OV: 0.8245, AltV: 0.8192, CorV: 0.8325, TopV: 0.7569, BotRV: 0.7875, AllV: 0.8190 +[2026-03-20T18:12:36.958439Z] Loop 3420: Reg: 0.0310, AltReg: 0.0495, CorReg: 0.0032, TopReg: 0.0995, AllReg: 0.0495, BotRReg: 0.0446, OV: 0.8326, AltV: 0.8327, CorV: 0.8324, TopV: 0.7592, BotRV: 0.8140, AllV: 0.8327 +[2026-03-20T18:12:45.543040Z] Loop 3430: Reg: 0.0372, AltReg: 0.0587, CorReg: 0.0050, TopReg: 0.1031, AllReg: 0.0587, BotRReg: 0.0440, OV: 0.8264, AltV: 0.8235, CorV: 0.8306, TopV: 0.7556, BotRV: 0.8146, AllV: 0.8235 +[2026-03-20T18:12:54.126833Z] Loop 3440: Reg: 0.0264, AltReg: 0.0419, CorReg: 0.0032, TopReg: 0.0746, AllReg: 0.0419, BotRReg: 0.0304, OV: 0.8372, AltV: 0.8404, CorV: 0.8324, TopV: 0.7840, BotRV: 0.8282, AllV: 0.8404 +[2026-03-20T18:13:02.706457Z] Loop 3450: Reg: 0.0278, AltReg: 0.0447, CorReg: 0.0025, TopReg: 0.1068, AllReg: 0.0448, BotRReg: 0.0356, OV: 0.8358, AltV: 0.8375, CorV: 0.8331, TopV: 0.7518, BotRV: 0.8230, AllV: 0.8375 +[2026-03-20T18:13:11.292227Z] Loop 3460: Reg: 0.0247, AltReg: 0.0391, CorReg: 0.0032, TopReg: 0.0714, AllReg: 0.0392, BotRReg: 0.0296, OV: 0.8388, AltV: 0.8431, CorV: 0.8324, TopV: 0.7873, BotRV: 0.8291, AllV: 0.8431 +[2026-03-20T18:13:19.869796Z] Loop 3470: Reg: 0.0289, AltReg: 0.0439, CorReg: 0.0065, TopReg: 0.0933, AllReg: 0.0439, BotRReg: 0.0211, OV: 0.8347, AltV: 0.8383, CorV: 0.8292, TopV: 0.7653, BotRV: 0.8375, AllV: 0.8383 +[2026-03-20T18:13:28.446554Z] Loop 3480: Reg: 0.0256, AltReg: 0.0392, CorReg: 0.0053, TopReg: 0.0891, AllReg: 0.0392, BotRReg: 0.0193, OV: 0.8380, AltV: 0.8430, CorV: 0.8304, TopV: 0.7695, BotRV: 0.8393, AllV: 0.8430 +[2026-03-20T18:13:37.026769Z] Loop 3490: Reg: 0.0279, AltReg: 0.0432, CorReg: 0.0049, TopReg: 0.1178, AllReg: 0.0433, BotRReg: 0.0219, OV: 0.8357, AltV: 0.8390, CorV: 0.8307, TopV: 0.7408, BotRV: 0.8368, AllV: 0.8389 +[2026-03-20T18:13:45.604667Z] Loop 3500: Reg: 0.0305, AltReg: 0.0471, CorReg: 0.0057, TopReg: 0.1094, AllReg: 0.0470, BotRReg: 0.0344, OV: 0.8331, AltV: 0.8351, CorV: 0.8299, TopV: 0.7493, BotRV: 0.8242, AllV: 0.8352 +[2026-03-20T18:13:54.182030Z] Loop 3510: Reg: 0.0229, AltReg: 0.0369, CorReg: 0.0020, TopReg: 0.0463, AllReg: 0.0370, BotRReg: 0.0349, OV: 0.8407, AltV: 0.8453, CorV: 0.8336, TopV: 0.8123, BotRV: 0.8237, AllV: 0.8453 +[2026-03-20T18:14:02.756582Z] Loop 3520: Reg: 0.0216, AltReg: 0.0346, CorReg: 0.0022, TopReg: 0.0516, AllReg: 0.0347, BotRReg: 0.0337, OV: 0.8419, AltV: 0.8476, CorV: 0.8335, TopV: 0.8071, BotRV: 0.8249, AllV: 0.8476 +[2026-03-20T18:14:11.336428Z] Loop 3530: Reg: 0.0200, AltReg: 0.0321, CorReg: 0.0018, TopReg: 0.0704, AllReg: 0.0321, BotRReg: 0.0209, OV: 0.8436, AltV: 0.8501, CorV: 0.8338, TopV: 0.7882, BotRV: 0.8377, AllV: 0.8501 +[2026-03-20T18:14:19.911825Z] Loop 3540: Reg: 0.0217, AltReg: 0.0355, CorReg: 0.0010, TopReg: 0.0486, AllReg: 0.0355, BotRReg: 0.0326, OV: 0.8419, AltV: 0.8467, CorV: 0.8347, TopV: 0.8100, BotRV: 0.8260, AllV: 0.8468 +[2026-03-20T18:14:28.486626Z] Loop 3550: Reg: 0.0216, AltReg: 0.0331, CorReg: 0.0043, TopReg: 0.0467, AllReg: 0.0332, BotRReg: 0.0368, OV: 0.8420, AltV: 0.8491, CorV: 0.8313, TopV: 0.8119, BotRV: 0.8218, AllV: 0.8491 +[2026-03-20T18:14:37.069399Z] Loop 3560: Reg: 0.0205, AltReg: 0.0327, CorReg: 0.0022, TopReg: 0.0511, AllReg: 0.0328, BotRReg: 0.0183, OV: 0.8431, AltV: 0.8495, CorV: 0.8334, TopV: 0.8075, BotRV: 0.8403, AllV: 0.8495 +[2026-03-20T18:14:45.643180Z] Loop 3570: Reg: 0.0177, AltReg: 0.0284, CorReg: 0.0018, TopReg: 0.0623, AllReg: 0.0284, BotRReg: 0.0193, OV: 0.8458, AltV: 0.8538, CorV: 0.8338, TopV: 0.7963, BotRV: 0.8394, AllV: 0.8538 +[2026-03-20T18:14:54.218915Z] Loop 3580: Reg: 0.0157, AltReg: 0.0249, CorReg: 0.0020, TopReg: 0.0458, AllReg: 0.0249, BotRReg: 0.0152, OV: 0.8479, AltV: 0.8573, CorV: 0.8337, TopV: 0.8128, BotRV: 0.8434, AllV: 0.8573 +[2026-03-20T18:15:02.795223Z] Loop 3590: Reg: 0.0171, AltReg: 0.0268, CorReg: 0.0026, TopReg: 0.0399, AllReg: 0.0268, BotRReg: 0.0184, OV: 0.8465, AltV: 0.8554, CorV: 0.8331, TopV: 0.8188, BotRV: 0.8403, AllV: 0.8555 +[2026-03-20T18:15:11.365683Z] Loop 3600: Reg: 0.0150, AltReg: 0.0241, CorReg: 0.0013, TopReg: 0.0291, AllReg: 0.0241, BotRReg: 0.0229, OV: 0.8486, AltV: 0.8581, CorV: 0.8343, TopV: 0.8296, BotRV: 0.8358, AllV: 0.8581 +[2026-03-20T18:15:19.948434Z] Loop 3610: Reg: 0.0144, AltReg: 0.0227, CorReg: 0.0019, TopReg: 0.0320, AllReg: 0.0228, BotRReg: 0.0204, OV: 0.8492, AltV: 0.8595, CorV: 0.8338, TopV: 0.8266, BotRV: 0.8382, AllV: 0.8595 +[2026-03-20T18:15:28.526843Z] Loop 3620: Reg: 0.0149, AltReg: 0.0238, CorReg: 0.0015, TopReg: 0.0340, AllReg: 0.0239, BotRReg: 0.0177, OV: 0.8487, AltV: 0.8584, CorV: 0.8341, TopV: 0.8246, BotRV: 0.8409, AllV: 0.8584 +[2026-03-20T18:15:37.102871Z] Loop 3630: Reg: 0.0148, AltReg: 0.0242, CorReg: 0.0006, TopReg: 0.0313, AllReg: 0.0243, BotRReg: 0.0221, OV: 0.8488, AltV: 0.8580, CorV: 0.8351, TopV: 0.8273, BotRV: 0.8365, AllV: 0.8580 +[2026-03-20T18:15:45.681843Z] Loop 3640: Reg: 0.0126, AltReg: 0.0203, CorReg: 0.0010, TopReg: 0.0290, AllReg: 0.0203, BotRReg: 0.0158, OV: 0.8510, AltV: 0.8619, CorV: 0.8347, TopV: 0.8297, BotRV: 0.8429, AllV: 0.8619 +[2026-03-20T18:15:54.261965Z] Loop 3650: Reg: 0.0148, AltReg: 0.0233, CorReg: 0.0020, TopReg: 0.0305, AllReg: 0.0233, BotRReg: 0.0260, OV: 0.8488, AltV: 0.8590, CorV: 0.8336, TopV: 0.8281, BotRV: 0.8326, AllV: 0.8590 +[2026-03-20T18:16:02.839471Z] Loop 3660: Reg: 0.0126, AltReg: 0.0206, CorReg: 0.0007, TopReg: 0.0247, AllReg: 0.0206, BotRReg: 0.0189, OV: 0.8510, AltV: 0.8617, CorV: 0.8350, TopV: 0.8339, BotRV: 0.8397, AllV: 0.8617 +[2026-03-20T18:16:11.421718Z] Loop 3670: Reg: 0.0117, AltReg: 0.0188, CorReg: 0.0010, TopReg: 0.0315, AllReg: 0.0188, BotRReg: 0.0088, OV: 0.8519, AltV: 0.8634, CorV: 0.8346, TopV: 0.8272, BotRV: 0.8499, AllV: 0.8635 +[2026-03-20T18:16:20.001764Z] Loop 3680: Reg: 0.0118, AltReg: 0.0193, CorReg: 0.0006, TopReg: 0.0270, AllReg: 0.0193, BotRReg: 0.0167, OV: 0.8518, AltV: 0.8629, CorV: 0.8350, TopV: 0.8316, BotRV: 0.8420, AllV: 0.8629 +[2026-03-20T18:16:28.575865Z] Loop 3690: Reg: 0.0120, AltReg: 0.0194, CorReg: 0.0009, TopReg: 0.0258, AllReg: 0.0195, BotRReg: 0.0199, OV: 0.8516, AltV: 0.8628, CorV: 0.8348, TopV: 0.8328, BotRV: 0.8388, AllV: 0.8628 +[2026-03-20T18:16:37.151510Z] Loop 3700: Reg: 0.0101, AltReg: 0.0160, CorReg: 0.0011, TopReg: 0.0204, AllReg: 0.0160, BotRReg: 0.0145, OV: 0.8535, AltV: 0.8662, CorV: 0.8345, TopV: 0.8382, BotRV: 0.8441, AllV: 0.8662 +[2026-03-20T18:16:45.726725Z] Loop 3710: Reg: 0.0114, AltReg: 0.0186, CorReg: 0.0005, TopReg: 0.0231, AllReg: 0.0186, BotRReg: 0.0217, OV: 0.8522, AltV: 0.8636, CorV: 0.8351, TopV: 0.8355, BotRV: 0.8369, AllV: 0.8636 +[2026-03-20T18:16:54.304542Z] Loop 3720: Reg: 0.0106, AltReg: 0.0161, CorReg: 0.0023, TopReg: 0.0271, AllReg: 0.0162, BotRReg: 0.0107, OV: 0.8530, AltV: 0.8661, CorV: 0.8333, TopV: 0.8315, BotRV: 0.8479, AllV: 0.8661 +[2026-03-20T18:17:02.880514Z] Loop 3730: Reg: 0.0100, AltReg: 0.0162, CorReg: 0.0007, TopReg: 0.0190, AllReg: 0.0162, BotRReg: 0.0108, OV: 0.8536, AltV: 0.8660, CorV: 0.8349, TopV: 0.8396, BotRV: 0.8478, AllV: 0.8660 +[2026-03-20T18:17:11.457903Z] Loop 3740: Reg: 0.0110, AltReg: 0.0180, CorReg: 0.0006, TopReg: 0.0349, AllReg: 0.0180, BotRReg: 0.0121, OV: 0.8526, AltV: 0.8642, CorV: 0.8351, TopV: 0.8238, BotRV: 0.8465, AllV: 0.8643 +[2026-03-20T18:17:20.030367Z] Loop 3750: Reg: 0.0154, AltReg: 0.0251, CorReg: 0.0009, TopReg: 0.0496, AllReg: 0.0252, BotRReg: 0.0254, OV: 0.8482, AltV: 0.8571, CorV: 0.8347, TopV: 0.8090, BotRV: 0.8333, AllV: 0.8570 +[2026-03-20T18:17:28.606610Z] Loop 3760: Reg: 0.0142, AltReg: 0.0224, CorReg: 0.0020, TopReg: 0.0267, AllReg: 0.0224, BotRReg: 0.0148, OV: 0.8493, AltV: 0.8598, CorV: 0.8337, TopV: 0.8319, BotRV: 0.8438, AllV: 0.8598 +[2026-03-20T18:17:37.184632Z] Loop 3770: Reg: 0.0134, AltReg: 0.0221, CorReg: 0.0003, TopReg: 0.0242, AllReg: 0.0222, BotRReg: 0.0299, OV: 0.8502, AltV: 0.8601, CorV: 0.8354, TopV: 0.8344, BotRV: 0.8287, AllV: 0.8600 +[2026-03-20T18:17:45.763776Z] Loop 3780: Reg: 0.0116, AltReg: 0.0179, CorReg: 0.0022, TopReg: 0.0273, AllReg: 0.0179, BotRReg: 0.0150, OV: 0.8519, AltV: 0.8643, CorV: 0.8335, TopV: 0.8314, BotRV: 0.8437, AllV: 0.8643 +[2026-03-20T18:17:54.341718Z] Loop 3790: Reg: 0.0090, AltReg: 0.0138, CorReg: 0.0018, TopReg: 0.0232, AllReg: 0.0138, BotRReg: 0.0084, OV: 0.8546, AltV: 0.8684, CorV: 0.8338, TopV: 0.8354, BotRV: 0.8502, AllV: 0.8684 +[2026-03-20T18:18:02.919983Z] Loop 3800: Reg: 0.0085, AltReg: 0.0133, CorReg: 0.0012, TopReg: 0.0254, AllReg: 0.0134, BotRReg: 0.0083, OV: 0.8551, AltV: 0.8689, CorV: 0.8344, TopV: 0.8332, BotRV: 0.8503, AllV: 0.8689 +[2026-03-20T18:18:11.495570Z] Loop 3810: Reg: 0.0074, AltReg: 0.0120, CorReg: 0.0005, TopReg: 0.0167, AllReg: 0.0120, BotRReg: 0.0081, OV: 0.8562, AltV: 0.8702, CorV: 0.8352, TopV: 0.8419, BotRV: 0.8506, AllV: 0.8702 +[2026-03-20T18:18:20.070895Z] Loop 3820: Reg: 0.0113, AltReg: 0.0182, CorReg: 0.0010, TopReg: 0.0261, AllReg: 0.0182, BotRReg: 0.0213, OV: 0.8523, AltV: 0.8640, CorV: 0.8347, TopV: 0.8325, BotRV: 0.8373, AllV: 0.8640 +[2026-03-20T18:18:28.645749Z] Loop 3830: Reg: 0.0108, AltReg: 0.0177, CorReg: 0.0004, TopReg: 0.0278, AllReg: 0.0178, BotRReg: 0.0230, OV: 0.8528, AltV: 0.8645, CorV: 0.8352, TopV: 0.8308, BotRV: 0.8356, AllV: 0.8644 +[2026-03-20T18:18:37.222568Z] Loop 3840: Reg: 0.0103, AltReg: 0.0152, CorReg: 0.0028, TopReg: 0.0232, AllReg: 0.0152, BotRReg: 0.0128, OV: 0.8533, AltV: 0.8670, CorV: 0.8328, TopV: 0.8355, BotRV: 0.8458, AllV: 0.8670 +[2026-03-20T18:18:45.798630Z] Loop 3850: Reg: 0.0080, AltReg: 0.0129, CorReg: 0.0006, TopReg: 0.0306, AllReg: 0.0130, BotRReg: 0.0065, OV: 0.8556, AltV: 0.8693, CorV: 0.8350, TopV: 0.8280, BotRV: 0.8521, AllV: 0.8693 +[2026-03-20T18:18:54.373251Z] Loop 3860: Reg: 0.0078, AltReg: 0.0127, CorReg: 0.0004, TopReg: 0.0222, AllReg: 0.0128, BotRReg: 0.0103, OV: 0.8558, AltV: 0.8695, CorV: 0.8353, TopV: 0.8364, BotRV: 0.8484, AllV: 0.8695 +[2026-03-20T18:19:02.951025Z] Loop 3870: Reg: 0.0102, AltReg: 0.0158, CorReg: 0.0018, TopReg: 0.0256, AllReg: 0.0158, BotRReg: 0.0158, OV: 0.8534, AltV: 0.8664, CorV: 0.8338, TopV: 0.8331, BotRV: 0.8428, AllV: 0.8665 +[2026-03-20T18:19:11.523054Z] Loop 3880: Reg: 0.0108, AltReg: 0.0167, CorReg: 0.0021, TopReg: 0.0498, AllReg: 0.0168, BotRReg: 0.0050, OV: 0.8528, AltV: 0.8655, CorV: 0.8336, TopV: 0.8088, BotRV: 0.8537, AllV: 0.8655 +[2026-03-20T18:19:20.095253Z] Loop 3890: Reg: 0.0077, AltReg: 0.0126, CorReg: 0.0005, TopReg: 0.0186, AllReg: 0.0126, BotRReg: 0.0128, OV: 0.8558, AltV: 0.8697, CorV: 0.8351, TopV: 0.8400, BotRV: 0.8458, AllV: 0.8696 +[2026-03-20T18:19:28.673643Z] Loop 3900: Reg: 0.0068, AltReg: 0.0111, CorReg: 0.0003, TopReg: 0.0171, AllReg: 0.0111, BotRReg: 0.0083, OV: 0.8568, AltV: 0.8711, CorV: 0.8353, TopV: 0.8416, BotRV: 0.8503, AllV: 0.8711 +[2026-03-20T18:19:37.250575Z] Loop 3910: Reg: 0.0135, AltReg: 0.0223, CorReg: 0.0003, TopReg: 0.0190, AllReg: 0.0225, BotRReg: 0.0344, OV: 0.8501, AltV: 0.8599, CorV: 0.8354, TopV: 0.8396, BotRV: 0.8242, AllV: 0.8597 +[2026-03-20T18:19:45.824972Z] Loop 3920: Reg: 0.0133, AltReg: 0.0214, CorReg: 0.0012, TopReg: 0.0211, AllReg: 0.0214, BotRReg: 0.0308, OV: 0.8503, AltV: 0.8609, CorV: 0.8345, TopV: 0.8375, BotRV: 0.8278, AllV: 0.8609 +[2026-03-20T18:19:54.404492Z] Loop 3930: Reg: 0.0155, AltReg: 0.0257, CorReg: 0.0002, TopReg: 0.0163, AllReg: 0.0259, BotRReg: 0.0545, OV: 0.8481, AltV: 0.8565, CorV: 0.8354, TopV: 0.8424, BotRV: 0.8042, AllV: 0.8564 +[2026-03-20T18:20:02.985076Z] Loop 3940: Reg: 0.0065, AltReg: 0.0103, CorReg: 0.0007, TopReg: 0.0143, AllReg: 0.0103, BotRReg: 0.0084, OV: 0.8571, AltV: 0.8719, CorV: 0.8349, TopV: 0.8443, BotRV: 0.8502, AllV: 0.8719 +[2026-03-20T18:20:11.569959Z] Loop 3950: Reg: 0.0099, AltReg: 0.0158, CorReg: 0.0011, TopReg: 0.0499, AllReg: 0.0159, BotRReg: 0.0039, OV: 0.8537, AltV: 0.8665, CorV: 0.8345, TopV: 0.8087, BotRV: 0.8548, AllV: 0.8664 +[2026-03-20T18:20:20.150293Z] Loop 3960: Reg: 0.0073, AltReg: 0.0120, CorReg: 0.0003, TopReg: 0.0142, AllReg: 0.0120, BotRReg: 0.0132, OV: 0.8563, AltV: 0.8703, CorV: 0.8354, TopV: 0.8444, BotRV: 0.8455, AllV: 0.8703 +[2026-03-20T18:20:28.725985Z] Loop 3970: Reg: 0.0069, AltReg: 0.0113, CorReg: 0.0003, TopReg: 0.0125, AllReg: 0.0113, BotRReg: 0.0134, OV: 0.8567, AltV: 0.8709, CorV: 0.8353, TopV: 0.8462, BotRV: 0.8453, AllV: 0.8709 +[2026-03-20T18:20:37.312799Z] Loop 3980: Reg: 0.0089, AltReg: 0.0135, CorReg: 0.0020, TopReg: 0.0218, AllReg: 0.0135, BotRReg: 0.0172, OV: 0.8547, AltV: 0.8687, CorV: 0.8337, TopV: 0.8368, BotRV: 0.8414, AllV: 0.8687 +[2026-03-20T18:20:45.897769Z] Loop 3990: Reg: 0.0076, AltReg: 0.0126, CorReg: 0.0002, TopReg: 0.0113, AllReg: 0.0126, BotRReg: 0.0138, OV: 0.8559, AltV: 0.8696, CorV: 0.8354, TopV: 0.8473, BotRV: 0.8448, AllV: 0.8697 +[2026-03-20T18:20:54.478230Z] Loop 4000: Reg: 0.0113, AltReg: 0.0185, CorReg: 0.0004, TopReg: 0.0133, AllReg: 0.0186, BotRReg: 0.0261, OV: 0.8523, AltV: 0.8637, CorV: 0.8352, TopV: 0.8453, BotRV: 0.8325, AllV: 0.8636 +[2026-03-20T18:21:03.054104Z] Loop 4010: Reg: 0.0096, AltReg: 0.0151, CorReg: 0.0013, TopReg: 0.0286, AllReg: 0.0152, BotRReg: 0.0058, OV: 0.8540, AltV: 0.8671, CorV: 0.8343, TopV: 0.8300, BotRV: 0.8528, AllV: 0.8670 +[2026-03-20T18:21:11.633156Z] Loop 4020: Reg: 0.0063, AltReg: 0.0105, CorReg: 0.0001, TopReg: 0.0125, AllReg: 0.0105, BotRReg: 0.0091, OV: 0.8573, AltV: 0.8718, CorV: 0.8355, TopV: 0.8461, BotRV: 0.8495, AllV: 0.8718 +[2026-03-20T18:21:20.210296Z] Loop 4030: Reg: 0.0076, AltReg: 0.0125, CorReg: 0.0002, TopReg: 0.0125, AllReg: 0.0125, BotRReg: 0.0186, OV: 0.8560, AltV: 0.8697, CorV: 0.8354, TopV: 0.8461, BotRV: 0.8400, AllV: 0.8697 +[2026-03-20T18:21:28.788809Z] Loop 4040: Reg: 0.0054, AltReg: 0.0089, CorReg: 0.0001, TopReg: 0.0107, AllReg: 0.0090, BotRReg: 0.0080, OV: 0.8582, AltV: 0.8733, CorV: 0.8355, TopV: 0.8479, BotRV: 0.8506, AllV: 0.8733 +[2026-03-20T18:21:37.368835Z] Loop 4050: Reg: 0.0064, AltReg: 0.0105, CorReg: 0.0002, TopReg: 0.0161, AllReg: 0.0105, BotRReg: 0.0060, OV: 0.8572, AltV: 0.8717, CorV: 0.8354, TopV: 0.8425, BotRV: 0.8526, AllV: 0.8718 +[2026-03-20T18:21:45.948788Z] Loop 4060: Reg: 0.0055, AltReg: 0.0090, CorReg: 0.0002, TopReg: 0.0109, AllReg: 0.0091, BotRReg: 0.0054, OV: 0.8581, AltV: 0.8732, CorV: 0.8354, TopV: 0.8478, BotRV: 0.8532, AllV: 0.8732 +[2026-03-20T18:21:54.525447Z] Loop 4070: Reg: 0.0050, AltReg: 0.0081, CorReg: 0.0002, TopReg: 0.0098, AllReg: 0.0081, BotRReg: 0.0060, OV: 0.8586, AltV: 0.8741, CorV: 0.8354, TopV: 0.8488, BotRV: 0.8526, AllV: 0.8741 +[2026-03-20T18:22:03.105215Z] Loop 4080: Reg: 0.0057, AltReg: 0.0092, CorReg: 0.0004, TopReg: 0.0212, AllReg: 0.0092, BotRReg: 0.0065, OV: 0.8579, AltV: 0.8730, CorV: 0.8352, TopV: 0.8375, BotRV: 0.8522, AllV: 0.8730 +[2026-03-20T18:22:11.683147Z] Loop 4090: Reg: 0.0072, AltReg: 0.0110, CorReg: 0.0016, TopReg: 0.0175, AllReg: 0.0110, BotRReg: 0.0148, OV: 0.8563, AltV: 0.8712, CorV: 0.8340, TopV: 0.8411, BotRV: 0.8438, AllV: 0.8712 +[2026-03-20T18:22:20.266074Z] Loop 4100: Reg: 0.0136, AltReg: 0.0226, CorReg: 0.0001, TopReg: 0.0408, AllReg: 0.0227, BotRReg: 0.0265, OV: 0.8500, AltV: 0.8596, CorV: 0.8355, TopV: 0.8179, BotRV: 0.8321, AllV: 0.8596 +[2026-03-20T18:22:28.842947Z] Loop 4110: Reg: 0.0092, AltReg: 0.0147, CorReg: 0.0008, TopReg: 0.0349, AllReg: 0.0149, BotRReg: 0.0048, OV: 0.8544, AltV: 0.8675, CorV: 0.8348, TopV: 0.8237, BotRV: 0.8538, AllV: 0.8673 +[2026-03-20T18:22:37.422492Z] Loop 4120: Reg: 0.0085, AltReg: 0.0140, CorReg: 0.0001, TopReg: 0.0215, AllReg: 0.0141, BotRReg: 0.0185, OV: 0.8551, AltV: 0.8682, CorV: 0.8355, TopV: 0.8372, BotRV: 0.8401, AllV: 0.8682 +[2026-03-20T18:22:46.001139Z] Loop 4130: Reg: 0.0048, AltReg: 0.0078, CorReg: 0.0003, TopReg: 0.0081, AllReg: 0.0078, BotRReg: 0.0075, OV: 0.8588, AltV: 0.8744, CorV: 0.8353, TopV: 0.8505, BotRV: 0.8511, AllV: 0.8744 +[2026-03-20T18:22:54.578732Z] Loop 4140: Reg: 0.0064, AltReg: 0.0103, CorReg: 0.0005, TopReg: 0.0128, AllReg: 0.0103, BotRReg: 0.0048, OV: 0.8572, AltV: 0.8719, CorV: 0.8352, TopV: 0.8458, BotRV: 0.8538, AllV: 0.8719 +[2026-03-20T18:23:03.156445Z] Loop 4150: Reg: 0.0044, AltReg: 0.0072, CorReg: 0.0003, TopReg: 0.0069, AllReg: 0.0072, BotRReg: 0.0060, OV: 0.8591, AltV: 0.8750, CorV: 0.8353, TopV: 0.8518, BotRV: 0.8526, AllV: 0.8750 +[2026-03-20T18:23:11.739774Z] Loop 4160: Reg: 0.0051, AltReg: 0.0081, CorReg: 0.0006, TopReg: 0.0075, AllReg: 0.0081, BotRReg: 0.0065, OV: 0.8585, AltV: 0.8741, CorV: 0.8350, TopV: 0.8511, BotRV: 0.8521, AllV: 0.8741 +[2026-03-20T18:23:20.315135Z] Loop 4170: Reg: 0.0062, AltReg: 0.0100, CorReg: 0.0005, TopReg: 0.0102, AllReg: 0.0100, BotRReg: 0.0100, OV: 0.8574, AltV: 0.8722, CorV: 0.8351, TopV: 0.8484, BotRV: 0.8486, AllV: 0.8722 +[2026-03-20T18:23:28.890092Z] Loop 4180: Reg: 0.0050, AltReg: 0.0082, CorReg: 0.0003, TopReg: 0.0070, AllReg: 0.0082, BotRReg: 0.0088, OV: 0.8586, AltV: 0.8740, CorV: 0.8354, TopV: 0.8517, BotRV: 0.8498, AllV: 0.8741 +[2026-03-20T18:23:37.470706Z] Loop 4190: Reg: 0.0086, AltReg: 0.0129, CorReg: 0.0022, TopReg: 0.0113, AllReg: 0.0129, BotRReg: 0.0213, OV: 0.8550, AltV: 0.8693, CorV: 0.8334, TopV: 0.8473, BotRV: 0.8373, AllV: 0.8693 +[2026-03-20T18:23:46.052880Z] Loop 4200: Reg: 0.0082, AltReg: 0.0113, CorReg: 0.0035, TopReg: 0.0134, AllReg: 0.0114, BotRReg: 0.0153, OV: 0.8554, AltV: 0.8709, CorV: 0.8321, TopV: 0.8452, BotRV: 0.8433, AllV: 0.8709 +[2026-03-20T18:23:54.642004Z] Loop 4210: Reg: 0.0093, AltReg: 0.0150, CorReg: 0.0008, TopReg: 0.0502, AllReg: 0.0151, BotRReg: 0.0108, OV: 0.8543, AltV: 0.8672, CorV: 0.8349, TopV: 0.8084, BotRV: 0.8478, AllV: 0.8672 +[2026-03-20T18:24:03.225375Z] Loop 4220: Reg: 0.0050, AltReg: 0.0082, CorReg: 0.0001, TopReg: 0.0063, AllReg: 0.0082, BotRReg: 0.0092, OV: 0.8586, AltV: 0.8740, CorV: 0.8355, TopV: 0.8524, BotRV: 0.8494, AllV: 0.8740 +[2026-03-20T18:24:11.809332Z] Loop 4230: Reg: 0.0051, AltReg: 0.0083, CorReg: 0.0002, TopReg: 0.0131, AllReg: 0.0083, BotRReg: 0.0053, OV: 0.8585, AltV: 0.8739, CorV: 0.8354, TopV: 0.8456, BotRV: 0.8533, AllV: 0.8740 +[2026-03-20T18:24:20.396966Z] Loop 4240: Reg: 0.0062, AltReg: 0.0102, CorReg: 0.0003, TopReg: 0.0085, AllReg: 0.0102, BotRReg: 0.0091, OV: 0.8573, AltV: 0.8720, CorV: 0.8353, TopV: 0.8501, BotRV: 0.8495, AllV: 0.8720 +[2026-03-20T18:24:28.982997Z] Loop 4250: Reg: 0.0059, AltReg: 0.0095, CorReg: 0.0005, TopReg: 0.0169, AllReg: 0.0096, BotRReg: 0.0029, OV: 0.8577, AltV: 0.8727, CorV: 0.8351, TopV: 0.8417, BotRV: 0.8557, AllV: 0.8727 +[2026-03-20T18:24:37.574850Z] Loop 4260: Reg: 0.0054, AltReg: 0.0085, CorReg: 0.0007, TopReg: 0.0097, AllReg: 0.0085, BotRReg: 0.0068, OV: 0.8582, AltV: 0.8737, CorV: 0.8349, TopV: 0.8489, BotRV: 0.8518, AllV: 0.8737 +[2026-03-20T18:24:46.155437Z] Loop 4270: Reg: 0.0049, AltReg: 0.0079, CorReg: 0.0003, TopReg: 0.0063, AllReg: 0.0079, BotRReg: 0.0083, OV: 0.8587, AltV: 0.8743, CorV: 0.8353, TopV: 0.8524, BotRV: 0.8503, AllV: 0.8744 +[2026-03-20T18:24:54.735593Z] Loop 4280: Reg: 0.0047, AltReg: 0.0078, CorReg: 0.0001, TopReg: 0.0052, AllReg: 0.0078, BotRReg: 0.0062, OV: 0.8589, AltV: 0.8744, CorV: 0.8356, TopV: 0.8534, BotRV: 0.8524, AllV: 0.8744 +[2026-03-20T18:25:03.317485Z] Loop 4290: Reg: 0.0037, AltReg: 0.0060, CorReg: 0.0002, TopReg: 0.0078, AllReg: 0.0060, BotRReg: 0.0048, OV: 0.8599, AltV: 0.8762, CorV: 0.8354, TopV: 0.8508, BotRV: 0.8538, AllV: 0.8762 +[2026-03-20T18:25:11.901192Z] Loop 4300: Reg: 0.0037, AltReg: 0.0060, CorReg: 0.0003, TopReg: 0.0071, AllReg: 0.0060, BotRReg: 0.0029, OV: 0.8599, AltV: 0.8763, CorV: 0.8353, TopV: 0.8515, BotRV: 0.8558, AllV: 0.8762 +[2026-03-20T18:25:20.489518Z] Loop 4310: Reg: 0.0037, AltReg: 0.0061, CorReg: 0.0001, TopReg: 0.0049, AllReg: 0.0061, BotRReg: 0.0061, OV: 0.8599, AltV: 0.8761, CorV: 0.8355, TopV: 0.8537, BotRV: 0.8525, AllV: 0.8762 +[2026-03-20T18:25:29.064457Z] Loop 4320: Reg: 0.0043, AltReg: 0.0066, CorReg: 0.0008, TopReg: 0.0154, AllReg: 0.0066, BotRReg: 0.0028, OV: 0.8593, AltV: 0.8756, CorV: 0.8348, TopV: 0.8432, BotRV: 0.8558, AllV: 0.8756 +[2026-03-20T18:25:37.649233Z] Loop 4330: Reg: 0.0063, AltReg: 0.0105, CorReg: 0.0000, TopReg: 0.0115, AllReg: 0.0105, BotRReg: 0.0143, OV: 0.8573, AltV: 0.8717, CorV: 0.8356, TopV: 0.8471, BotRV: 0.8444, AllV: 0.8717 +[2026-03-20T18:25:46.229430Z] Loop 4340: Reg: 0.0052, AltReg: 0.0083, CorReg: 0.0006, TopReg: 0.0080, AllReg: 0.0084, BotRReg: 0.0025, OV: 0.8584, AltV: 0.8739, CorV: 0.8350, TopV: 0.8506, BotRV: 0.8561, AllV: 0.8738 +[2026-03-20T18:25:54.809901Z] Loop 4350: Reg: 0.0035, AltReg: 0.0057, CorReg: 0.0003, TopReg: 0.0061, AllReg: 0.0057, BotRReg: 0.0042, OV: 0.8601, AltV: 0.8766, CorV: 0.8353, TopV: 0.8525, BotRV: 0.8545, AllV: 0.8766 +[2026-03-20T18:26:03.397075Z] Loop 4360: Reg: 0.0090, AltReg: 0.0149, CorReg: 0.0001, TopReg: 0.0369, AllReg: 0.0149, BotRReg: 0.0083, OV: 0.8546, AltV: 0.8673, CorV: 0.8356, TopV: 0.8217, BotRV: 0.8503, AllV: 0.8674 +[2026-03-20T18:26:11.973625Z] Loop 4370: Reg: 0.0054, AltReg: 0.0089, CorReg: 0.0003, TopReg: 0.0212, AllReg: 0.0090, BotRReg: 0.0036, OV: 0.8582, AltV: 0.8734, CorV: 0.8354, TopV: 0.8374, BotRV: 0.8550, AllV: 0.8733 +[2026-03-20T18:26:20.553969Z] Loop 4380: Reg: 0.0047, AltReg: 0.0074, CorReg: 0.0006, TopReg: 0.0081, AllReg: 0.0074, BotRReg: 0.0043, OV: 0.8589, AltV: 0.8748, CorV: 0.8350, TopV: 0.8505, BotRV: 0.8544, AllV: 0.8748 +[2026-03-20T18:26:29.136716Z] Loop 4390: Reg: 0.0040, AltReg: 0.0063, CorReg: 0.0004, TopReg: 0.0063, AllReg: 0.0064, BotRReg: 0.0036, OV: 0.8596, AltV: 0.8759, CorV: 0.8352, TopV: 0.8523, BotRV: 0.8550, AllV: 0.8759 +[2026-03-20T18:26:37.719542Z] Loop 4400: Reg: 0.0054, AltReg: 0.0089, CorReg: 0.0002, TopReg: 0.0112, AllReg: 0.0089, BotRReg: 0.0093, OV: 0.8582, AltV: 0.8733, CorV: 0.8354, TopV: 0.8475, BotRV: 0.8493, AllV: 0.8733 +[2026-03-20T18:26:46.303015Z] Loop 4410: Reg: 0.0052, AltReg: 0.0073, CorReg: 0.0021, TopReg: 0.0120, AllReg: 0.0073, BotRReg: 0.0084, OV: 0.8584, AltV: 0.8749, CorV: 0.8335, TopV: 0.8466, BotRV: 0.8502, AllV: 0.8749 +[2026-03-20T18:26:54.886340Z] Loop 4420: Reg: 0.0032, AltReg: 0.0053, CorReg: 0.0001, TopReg: 0.0037, AllReg: 0.0053, BotRReg: 0.0045, OV: 0.8604, AltV: 0.8769, CorV: 0.8356, TopV: 0.8549, BotRV: 0.8541, AllV: 0.8769 +[2026-03-20T18:27:03.466425Z] Loop 4430: Reg: 0.0039, AltReg: 0.0065, CorReg: 0.0001, TopReg: 0.0048, AllReg: 0.0065, BotRReg: 0.0061, OV: 0.8596, AltV: 0.8757, CorV: 0.8355, TopV: 0.8538, BotRV: 0.8525, AllV: 0.8758 +[2026-03-20T18:27:12.052350Z] Loop 4440: Reg: 0.0052, AltReg: 0.0083, CorReg: 0.0006, TopReg: 0.0062, AllReg: 0.0083, BotRReg: 0.0121, OV: 0.8583, AltV: 0.8739, CorV: 0.8350, TopV: 0.8524, BotRV: 0.8465, AllV: 0.8739 +[2026-03-20T18:27:20.643908Z] Loop 4450: Reg: 0.0071, AltReg: 0.0112, CorReg: 0.0009, TopReg: 0.0504, AllReg: 0.0112, BotRReg: 0.0072, OV: 0.8565, AltV: 0.8710, CorV: 0.8347, TopV: 0.8082, BotRV: 0.8514, AllV: 0.8710 +[2026-03-20T18:27:29.224231Z] Loop 4460: Reg: 0.0037, AltReg: 0.0061, CorReg: 0.0001, TopReg: 0.0054, AllReg: 0.0062, BotRReg: 0.0074, OV: 0.8599, AltV: 0.8761, CorV: 0.8355, TopV: 0.8532, BotRV: 0.8513, AllV: 0.8761 +[2026-03-20T18:27:37.806111Z] Loop 4470: Reg: 0.0041, AltReg: 0.0068, CorReg: 0.0001, TopReg: 0.0040, AllReg: 0.0068, BotRReg: 0.0077, OV: 0.8595, AltV: 0.8755, CorV: 0.8356, TopV: 0.8546, BotRV: 0.8509, AllV: 0.8755 +[2026-03-20T18:27:46.387989Z] Loop 4480: Reg: 0.0044, AltReg: 0.0072, CorReg: 0.0001, TopReg: 0.0041, AllReg: 0.0072, BotRReg: 0.0117, OV: 0.8592, AltV: 0.8750, CorV: 0.8356, TopV: 0.8545, BotRV: 0.8469, AllV: 0.8750 +[2026-03-20T18:27:54.964673Z] Loop 4490: Reg: 0.0036, AltReg: 0.0056, CorReg: 0.0006, TopReg: 0.0049, AllReg: 0.0056, BotRReg: 0.0078, OV: 0.8600, AltV: 0.8766, CorV: 0.8350, TopV: 0.8537, BotRV: 0.8508, AllV: 0.8766 +[2026-03-20T18:28:03.542320Z] Loop 4500: Reg: 0.0028, AltReg: 0.0045, CorReg: 0.0002, TopReg: 0.0073, AllReg: 0.0046, BotRReg: 0.0021, OV: 0.8608, AltV: 0.8777, CorV: 0.8354, TopV: 0.8513, BotRV: 0.8565, AllV: 0.8776 +[2026-03-20T18:28:12.130341Z] Loop 4510: Reg: 0.0038, AltReg: 0.0062, CorReg: 0.0000, TopReg: 0.0128, AllReg: 0.0063, BotRReg: 0.0036, OV: 0.8598, AltV: 0.8760, CorV: 0.8356, TopV: 0.8458, BotRV: 0.8551, AllV: 0.8760 +[2026-03-20T18:28:20.707495Z] Loop 4520: Reg: 0.0031, AltReg: 0.0050, CorReg: 0.0001, TopReg: 0.0067, AllReg: 0.0051, BotRReg: 0.0024, OV: 0.8605, AltV: 0.8772, CorV: 0.8355, TopV: 0.8519, BotRV: 0.8563, AllV: 0.8772 +[2026-03-20T18:28:29.287868Z] Loop 4530: Reg: 0.0030, AltReg: 0.0049, CorReg: 0.0001, TopReg: 0.0051, AllReg: 0.0050, BotRReg: 0.0032, OV: 0.8606, AltV: 0.8773, CorV: 0.8356, TopV: 0.8535, BotRV: 0.8554, AllV: 0.8773 +[2026-03-20T18:28:37.873878Z] Loop 4540: Reg: 0.0040, AltReg: 0.0065, CorReg: 0.0001, TopReg: 0.0050, AllReg: 0.0066, BotRReg: 0.0058, OV: 0.8596, AltV: 0.8757, CorV: 0.8355, TopV: 0.8537, BotRV: 0.8529, AllV: 0.8757 +[2026-03-20T18:28:46.462482Z] Loop 4550: Reg: 0.0045, AltReg: 0.0075, CorReg: 0.0002, TopReg: 0.0057, AllReg: 0.0075, BotRReg: 0.0091, OV: 0.8590, AltV: 0.8748, CorV: 0.8354, TopV: 0.8529, BotRV: 0.8495, AllV: 0.8747 +[2026-03-20T18:28:55.044947Z] Loop 4560: Reg: 0.0028, AltReg: 0.0044, CorReg: 0.0005, TopReg: 0.0053, AllReg: 0.0044, BotRReg: 0.0050, OV: 0.8608, AltV: 0.8778, CorV: 0.8352, TopV: 0.8534, BotRV: 0.8536, AllV: 0.8779 +[2026-03-20T18:29:03.629793Z] Loop 4570: Reg: 0.0034, AltReg: 0.0055, CorReg: 0.0002, TopReg: 0.0061, AllReg: 0.0055, BotRReg: 0.0088, OV: 0.8602, AltV: 0.8768, CorV: 0.8354, TopV: 0.8525, BotRV: 0.8498, AllV: 0.8768 +[2026-03-20T18:29:12.212257Z] Loop 4580: Reg: 0.0057, AltReg: 0.0094, CorReg: 0.0001, TopReg: 0.0084, AllReg: 0.0095, BotRReg: 0.0122, OV: 0.8579, AltV: 0.8728, CorV: 0.8356, TopV: 0.8503, BotRV: 0.8464, AllV: 0.8727 +[2026-03-20T18:29:20.800496Z] Loop 4590: Reg: 0.0038, AltReg: 0.0064, CorReg: 0.0000, TopReg: 0.0097, AllReg: 0.0064, BotRReg: 0.0066, OV: 0.8597, AltV: 0.8758, CorV: 0.8356, TopV: 0.8490, BotRV: 0.8520, AllV: 0.8758 +[2026-03-20T18:29:29.385195Z] Loop 4600: Reg: 0.0043, AltReg: 0.0070, CorReg: 0.0003, TopReg: 0.0074, AllReg: 0.0071, BotRReg: 0.0040, OV: 0.8593, AltV: 0.8752, CorV: 0.8353, TopV: 0.8512, BotRV: 0.8546, AllV: 0.8751 +[2026-03-20T18:29:37.968496Z] Loop 4610: Reg: 0.0038, AltReg: 0.0062, CorReg: 0.0000, TopReg: 0.0077, AllReg: 0.0063, BotRReg: 0.0087, OV: 0.8598, AltV: 0.8760, CorV: 0.8356, TopV: 0.8510, BotRV: 0.8499, AllV: 0.8760 +[2026-03-20T18:29:46.553909Z] Loop 4620: Reg: 0.0044, AltReg: 0.0072, CorReg: 0.0001, TopReg: 0.0046, AllReg: 0.0074, BotRReg: 0.0052, OV: 0.8592, AltV: 0.8750, CorV: 0.8355, TopV: 0.8540, BotRV: 0.8534, AllV: 0.8749 +[2026-03-20T18:29:55.136071Z] Loop 4630: Reg: 0.0064, AltReg: 0.0106, CorReg: 0.0000, TopReg: 0.0208, AllReg: 0.0106, BotRReg: 0.0150, OV: 0.8572, AltV: 0.8716, CorV: 0.8356, TopV: 0.8378, BotRV: 0.8436, AllV: 0.8716 +[2026-03-20T18:30:03.714244Z] Loop 4640: Reg: 0.0043, AltReg: 0.0070, CorReg: 0.0004, TopReg: 0.0123, AllReg: 0.0070, BotRReg: 0.0057, OV: 0.8592, AltV: 0.8752, CorV: 0.8352, TopV: 0.8463, BotRV: 0.8529, AllV: 0.8752 +[2026-03-20T18:30:12.298018Z] Loop 4650: Reg: 0.0036, AltReg: 0.0058, CorReg: 0.0003, TopReg: 0.0070, AllReg: 0.0059, BotRReg: 0.0093, OV: 0.8600, AltV: 0.8764, CorV: 0.8353, TopV: 0.8517, BotRV: 0.8494, AllV: 0.8764 +[2026-03-20T18:30:20.886641Z] Loop 4660: Reg: 0.0031, AltReg: 0.0050, CorReg: 0.0004, TopReg: 0.0030, AllReg: 0.0050, BotRReg: 0.0024, OV: 0.8604, AltV: 0.8772, CorV: 0.8352, TopV: 0.8556, BotRV: 0.8563, AllV: 0.8773 +[2026-03-20T18:30:29.467119Z] Loop 4670: Reg: 0.0020, AltReg: 0.0033, CorReg: 0.0001, TopReg: 0.0031, AllReg: 0.0033, BotRReg: 0.0026, OV: 0.8615, AltV: 0.8789, CorV: 0.8355, TopV: 0.8556, BotRV: 0.8560, AllV: 0.8789 +[2026-03-20T18:30:38.048068Z] Loop 4680: Reg: 0.0036, AltReg: 0.0054, CorReg: 0.0010, TopReg: 0.0213, AllReg: 0.0054, BotRReg: 0.0023, OV: 0.8599, AltV: 0.8768, CorV: 0.8346, TopV: 0.8374, BotRV: 0.8563, AllV: 0.8768 +[2026-03-20T18:30:46.631802Z] Loop 4690: Reg: 0.0031, AltReg: 0.0050, CorReg: 0.0002, TopReg: 0.0043, AllReg: 0.0050, BotRReg: 0.0077, OV: 0.8605, AltV: 0.8772, CorV: 0.8354, TopV: 0.8544, BotRV: 0.8510, AllV: 0.8773 +[2026-03-20T18:30:55.218367Z] Loop 4700: Reg: 0.0024, AltReg: 0.0039, CorReg: 0.0001, TopReg: 0.0039, AllReg: 0.0039, BotRReg: 0.0053, OV: 0.8612, AltV: 0.8783, CorV: 0.8355, TopV: 0.8547, BotRV: 0.8534, AllV: 0.8783 +[2026-03-20T18:31:03.802698Z] Loop 4710: Reg: 0.0045, AltReg: 0.0061, CorReg: 0.0020, TopReg: 0.0139, AllReg: 0.0061, BotRReg: 0.0062, OV: 0.8591, AltV: 0.8761, CorV: 0.8336, TopV: 0.8447, BotRV: 0.8524, AllV: 0.8762 +[2026-03-20T18:31:12.391057Z] Loop 4720: Reg: 0.0048, AltReg: 0.0077, CorReg: 0.0004, TopReg: 0.0054, AllReg: 0.0077, BotRReg: 0.0125, OV: 0.8588, AltV: 0.8745, CorV: 0.8352, TopV: 0.8533, BotRV: 0.8461, AllV: 0.8745 +[2026-03-20T18:31:20.974313Z] Loop 4730: Reg: 0.0022, AltReg: 0.0035, CorReg: 0.0004, TopReg: 0.0031, AllReg: 0.0035, BotRReg: 0.0031, OV: 0.8614, AltV: 0.8788, CorV: 0.8353, TopV: 0.8555, BotRV: 0.8555, AllV: 0.8788 +[2026-03-20T18:31:29.554950Z] Loop 4740: Reg: 0.0058, AltReg: 0.0094, CorReg: 0.0006, TopReg: 0.0173, AllReg: 0.0094, BotRReg: 0.0174, OV: 0.8577, AltV: 0.8729, CorV: 0.8351, TopV: 0.8413, BotRV: 0.8412, AllV: 0.8729 +[2026-03-20T18:31:38.137759Z] Loop 4750: Reg: 0.0019, AltReg: 0.0029, CorReg: 0.0004, TopReg: 0.0029, AllReg: 0.0030, BotRReg: 0.0019, OV: 0.8617, AltV: 0.8793, CorV: 0.8353, TopV: 0.8557, BotRV: 0.8567, AllV: 0.8793 +[2026-03-20T18:31:46.739429Z] Loop 4760: Reg: 0.0034, AltReg: 0.0056, CorReg: 0.0001, TopReg: 0.0054, AllReg: 0.0056, BotRReg: 0.0091, OV: 0.8602, AltV: 0.8766, CorV: 0.8355, TopV: 0.8532, BotRV: 0.8495, AllV: 0.8766 +[2026-03-20T18:31:55.316693Z] Loop 4770: Reg: 0.0032, AltReg: 0.0049, CorReg: 0.0007, TopReg: 0.0062, AllReg: 0.0049, BotRReg: 0.0052, OV: 0.8604, AltV: 0.8773, CorV: 0.8349, TopV: 0.8524, BotRV: 0.8534, AllV: 0.8774 +[2026-03-20T18:32:03.897566Z] Loop 4780: Reg: 0.0029, AltReg: 0.0045, CorReg: 0.0005, TopReg: 0.0054, AllReg: 0.0045, BotRReg: 0.0050, OV: 0.8607, AltV: 0.8777, CorV: 0.8351, TopV: 0.8532, BotRV: 0.8536, AllV: 0.8778 +[2026-03-20T18:32:12.477106Z] Loop 4790: Reg: 0.0023, AltReg: 0.0039, CorReg: 0.0001, TopReg: 0.0040, AllReg: 0.0039, BotRReg: 0.0045, OV: 0.8612, AltV: 0.8783, CorV: 0.8356, TopV: 0.8547, BotRV: 0.8542, AllV: 0.8784 +[2026-03-20T18:32:21.053648Z] Loop 4800: Reg: 0.0052, AltReg: 0.0085, CorReg: 0.0002, TopReg: 0.0086, AllReg: 0.0086, BotRReg: 0.0125, OV: 0.8584, AltV: 0.8737, CorV: 0.8355, TopV: 0.8500, BotRV: 0.8461, AllV: 0.8736 +[2026-03-20T18:32:29.650346Z] Loop 4810: Reg: 0.0038, AltReg: 0.0063, CorReg: 0.0000, TopReg: 0.0034, AllReg: 0.0063, BotRReg: 0.0096, OV: 0.8598, AltV: 0.8759, CorV: 0.8356, TopV: 0.8552, BotRV: 0.8491, AllV: 0.8759 +[2026-03-20T18:32:38.230521Z] Loop 4820: Reg: 0.0017, AltReg: 0.0028, CorReg: 0.0001, TopReg: 0.0030, AllReg: 0.0028, BotRReg: 0.0024, OV: 0.8619, AltV: 0.8794, CorV: 0.8355, TopV: 0.8557, BotRV: 0.8562, AllV: 0.8794 +[2026-03-20T18:32:46.817366Z] Loop 4830: Reg: 0.0028, AltReg: 0.0040, CorReg: 0.0009, TopReg: 0.0091, AllReg: 0.0040, BotRReg: 0.0022, OV: 0.8608, AltV: 0.8782, CorV: 0.8347, TopV: 0.8495, BotRV: 0.8564, AllV: 0.8782 +[2026-03-20T18:32:55.401484Z] Loop 4840: Reg: 0.0035, AltReg: 0.0057, CorReg: 0.0002, TopReg: 0.0114, AllReg: 0.0058, BotRReg: 0.0016, OV: 0.8601, AltV: 0.8765, CorV: 0.8354, TopV: 0.8472, BotRV: 0.8570, AllV: 0.8765 +[2026-03-20T18:33:03.977219Z] Loop 4850: Reg: 0.0022, AltReg: 0.0035, CorReg: 0.0004, TopReg: 0.0040, AllReg: 0.0035, BotRReg: 0.0032, OV: 0.8613, AltV: 0.8787, CorV: 0.8353, TopV: 0.8546, BotRV: 0.8554, AllV: 0.8787 +[2026-03-20T18:33:12.566112Z] Loop 4860: Reg: 0.0026, AltReg: 0.0042, CorReg: 0.0003, TopReg: 0.0040, AllReg: 0.0042, BotRReg: 0.0060, OV: 0.8610, AltV: 0.8781, CorV: 0.8353, TopV: 0.8546, BotRV: 0.8526, AllV: 0.8781 +[2026-03-20T18:33:21.152258Z] Loop 4870: Reg: 0.0046, AltReg: 0.0076, CorReg: 0.0000, TopReg: 0.0251, AllReg: 0.0076, BotRReg: 0.0050, OV: 0.8590, AltV: 0.8746, CorV: 0.8356, TopV: 0.8335, BotRV: 0.8537, AllV: 0.8746 +[2026-03-20T18:33:29.739330Z] Loop 4880: Reg: 0.0024, AltReg: 0.0034, CorReg: 0.0009, TopReg: 0.0030, AllReg: 0.0034, BotRReg: 0.0032, OV: 0.8612, AltV: 0.8788, CorV: 0.8347, TopV: 0.8557, BotRV: 0.8554, AllV: 0.8788 +[2026-03-20T18:33:38.331973Z] Loop 4890: Reg: 0.0016, AltReg: 0.0026, CorReg: 0.0002, TopReg: 0.0031, AllReg: 0.0026, BotRReg: 0.0021, OV: 0.8619, AltV: 0.8796, CorV: 0.8354, TopV: 0.8555, BotRV: 0.8565, AllV: 0.8796 +[2026-03-20T18:33:46.916014Z] Loop 4900: Reg: 0.0022, AltReg: 0.0036, CorReg: 0.0001, TopReg: 0.0058, AllReg: 0.0036, BotRReg: 0.0026, OV: 0.8614, AltV: 0.8786, CorV: 0.8355, TopV: 0.8528, BotRV: 0.8560, AllV: 0.8786 +[2026-03-20T18:33:55.499470Z] Loop 4910: Reg: 0.0037, AltReg: 0.0060, CorReg: 0.0002, TopReg: 0.0121, AllReg: 0.0061, BotRReg: 0.0128, OV: 0.8599, AltV: 0.8762, CorV: 0.8355, TopV: 0.8465, BotRV: 0.8458, AllV: 0.8762 +[2026-03-20T18:34:04.079182Z] Loop 4920: Reg: 0.0026, AltReg: 0.0043, CorReg: 0.0001, TopReg: 0.0071, AllReg: 0.0043, BotRReg: 0.0030, OV: 0.8610, AltV: 0.8779, CorV: 0.8356, TopV: 0.8515, BotRV: 0.8556, AllV: 0.8779 +[2026-03-20T18:34:12.660647Z] Loop 4930: Reg: 0.0036, AltReg: 0.0060, CorReg: 0.0000, TopReg: 0.0079, AllReg: 0.0060, BotRReg: 0.0067, OV: 0.8600, AltV: 0.8763, CorV: 0.8356, TopV: 0.8507, BotRV: 0.8519, AllV: 0.8763 +[2026-03-20T18:34:21.248397Z] Loop 4940: Reg: 0.0026, AltReg: 0.0042, CorReg: 0.0001, TopReg: 0.0021, AllReg: 0.0043, BotRReg: 0.0055, OV: 0.8610, AltV: 0.8780, CorV: 0.8356, TopV: 0.8566, BotRV: 0.8531, AllV: 0.8780 +[2026-03-20T18:34:29.829751Z] Loop 4950: Reg: 0.0049, AltReg: 0.0080, CorReg: 0.0002, TopReg: 0.0071, AllReg: 0.0081, BotRReg: 0.0078, OV: 0.8587, AltV: 0.8742, CorV: 0.8354, TopV: 0.8515, BotRV: 0.8508, AllV: 0.8742 +[2026-03-20T18:34:38.416413Z] Loop 4960: Reg: 0.0036, AltReg: 0.0057, CorReg: 0.0005, TopReg: 0.0068, AllReg: 0.0057, BotRReg: 0.0075, OV: 0.8600, AltV: 0.8765, CorV: 0.8352, TopV: 0.8518, BotRV: 0.8511, AllV: 0.8765 +[2026-03-20T18:34:46.999001Z] Loop 4970: Reg: 0.0020, AltReg: 0.0031, CorReg: 0.0004, TopReg: 0.0038, AllReg: 0.0032, BotRReg: 0.0023, OV: 0.8615, AltV: 0.8791, CorV: 0.8353, TopV: 0.8548, BotRV: 0.8563, AllV: 0.8790 +[2026-03-20T18:34:55.583829Z] Loop 4980: Reg: 0.0021, AltReg: 0.0035, CorReg: 0.0001, TopReg: 0.0035, AllReg: 0.0035, BotRReg: 0.0022, OV: 0.8615, AltV: 0.8788, CorV: 0.8356, TopV: 0.8552, BotRV: 0.8564, AllV: 0.8787 +[2026-03-20T18:35:04.169300Z] Loop 4990: Reg: 0.0031, AltReg: 0.0052, CorReg: 0.0001, TopReg: 0.0037, AllReg: 0.0052, BotRReg: 0.0051, OV: 0.8605, AltV: 0.8771, CorV: 0.8355, TopV: 0.8549, BotRV: 0.8535, AllV: 0.8770 +[2026-03-20T18:35:12.756568Z] Loop 5000: Reg: 0.0043, AltReg: 0.0070, CorReg: 0.0002, TopReg: 0.0053, AllReg: 0.0071, BotRReg: 0.0070, OV: 0.8593, AltV: 0.8752, CorV: 0.8354, TopV: 0.8533, BotRV: 0.8516, AllV: 0.8752 +[2026-03-20T18:35:21.345071Z] Loop 5010: Reg: 0.0061, AltReg: 0.0097, CorReg: 0.0007, TopReg: 0.0215, AllReg: 0.0097, BotRReg: 0.0180, OV: 0.8575, AltV: 0.8726, CorV: 0.8350, TopV: 0.8371, BotRV: 0.8406, AllV: 0.8726 +[2026-03-20T18:35:29.925974Z] Loop 5020: Reg: 0.0043, AltReg: 0.0056, CorReg: 0.0024, TopReg: 0.0115, AllReg: 0.0056, BotRReg: 0.0095, OV: 0.8592, AltV: 0.8766, CorV: 0.8332, TopV: 0.8471, BotRV: 0.8491, AllV: 0.8766 +[2026-03-20T18:35:38.507038Z] Loop 5030: Reg: 0.0021, AltReg: 0.0035, CorReg: 0.0000, TopReg: 0.0039, AllReg: 0.0035, BotRReg: 0.0028, OV: 0.8615, AltV: 0.8787, CorV: 0.8356, TopV: 0.8547, BotRV: 0.8558, AllV: 0.8788 +[2026-03-20T18:35:47.092003Z] Loop 5040: Reg: 0.0022, AltReg: 0.0037, CorReg: 0.0000, TopReg: 0.0045, AllReg: 0.0037, BotRReg: 0.0026, OV: 0.8613, AltV: 0.8785, CorV: 0.8356, TopV: 0.8541, BotRV: 0.8560, AllV: 0.8785 +[2026-03-20T18:35:55.675255Z] Loop 5050: Reg: 0.0032, AltReg: 0.0053, CorReg: 0.0001, TopReg: 0.0078, AllReg: 0.0053, BotRReg: 0.0140, OV: 0.8604, AltV: 0.8769, CorV: 0.8356, TopV: 0.8508, BotRV: 0.8447, AllV: 0.8769 +[2026-03-20T18:36:04.259123Z] Loop 5060: Reg: 0.0025, AltReg: 0.0039, CorReg: 0.0003, TopReg: 0.0026, AllReg: 0.0039, BotRReg: 0.0033, OV: 0.8611, AltV: 0.8783, CorV: 0.8354, TopV: 0.8561, BotRV: 0.8553, AllV: 0.8783 +[2026-03-20T18:36:12.848842Z] Loop 5070: Reg: 0.0024, AltReg: 0.0039, CorReg: 0.0001, TopReg: 0.0023, AllReg: 0.0040, BotRReg: 0.0060, OV: 0.8612, AltV: 0.8783, CorV: 0.8355, TopV: 0.8563, BotRV: 0.8527, AllV: 0.8783 +[2026-03-20T18:36:21.427176Z] Loop 5080: Reg: 0.0044, AltReg: 0.0073, CorReg: 0.0000, TopReg: 0.0169, AllReg: 0.0074, BotRReg: 0.0109, OV: 0.8592, AltV: 0.8749, CorV: 0.8356, TopV: 0.8418, BotRV: 0.8477, AllV: 0.8749 +[2026-03-20T18:36:30.001062Z] Loop 5090: Reg: 0.0073, AltReg: 0.0105, CorReg: 0.0026, TopReg: 0.0180, AllReg: 0.0105, BotRReg: 0.0302, OV: 0.8562, AltV: 0.8717, CorV: 0.8331, TopV: 0.8406, BotRV: 0.8284, AllV: 0.8717 +[2026-03-20T18:36:38.577427Z] Loop 5100: Reg: 0.0040, AltReg: 0.0066, CorReg: 0.0000, TopReg: 0.0138, AllReg: 0.0066, BotRReg: 0.0086, OV: 0.8596, AltV: 0.8756, CorV: 0.8356, TopV: 0.8448, BotRV: 0.8501, AllV: 0.8757 +[2026-03-20T18:36:47.163857Z] Loop 5110: Reg: 0.0058, AltReg: 0.0095, CorReg: 0.0002, TopReg: 0.0202, AllReg: 0.0096, BotRReg: 0.0091, OV: 0.8578, AltV: 0.8727, CorV: 0.8354, TopV: 0.8384, BotRV: 0.8496, AllV: 0.8727 +[2026-03-20T18:36:55.752928Z] Loop 5120: Reg: 0.0019, AltReg: 0.0031, CorReg: 0.0000, TopReg: 0.0048, AllReg: 0.0032, BotRReg: 0.0035, OV: 0.8617, AltV: 0.8791, CorV: 0.8356, TopV: 0.8538, BotRV: 0.8551, AllV: 0.8791 +[2026-03-20T18:37:04.336404Z] Loop 5130: Reg: 0.0024, AltReg: 0.0040, CorReg: 0.0000, TopReg: 0.0059, AllReg: 0.0040, BotRReg: 0.0056, OV: 0.8612, AltV: 0.8782, CorV: 0.8356, TopV: 0.8527, BotRV: 0.8530, AllV: 0.8782 +[2026-03-20T18:37:12.917545Z] Loop 5140: Reg: 0.0024, AltReg: 0.0040, CorReg: 0.0001, TopReg: 0.0028, AllReg: 0.0040, BotRReg: 0.0080, OV: 0.8612, AltV: 0.8782, CorV: 0.8356, TopV: 0.8558, BotRV: 0.8506, AllV: 0.8783 +[2026-03-20T18:37:21.497300Z] Loop 5150: Reg: 0.0015, AltReg: 0.0024, CorReg: 0.0002, TopReg: 0.0019, AllReg: 0.0024, BotRReg: 0.0035, OV: 0.8621, AltV: 0.8798, CorV: 0.8355, TopV: 0.8567, BotRV: 0.8551, AllV: 0.8799 +[2026-03-20T18:37:30.078564Z] Loop 5160: Reg: 0.0068, AltReg: 0.0096, CorReg: 0.0026, TopReg: 0.0121, AllReg: 0.0096, BotRReg: 0.0139, OV: 0.8568, AltV: 0.8726, CorV: 0.8330, TopV: 0.8465, BotRV: 0.8447, AllV: 0.8727 +[2026-03-20T18:37:38.661076Z] Loop 5170: Reg: 0.0016, AltReg: 0.0027, CorReg: 0.0000, TopReg: 0.0045, AllReg: 0.0027, BotRReg: 0.0023, OV: 0.8620, AltV: 0.8795, CorV: 0.8356, TopV: 0.8541, BotRV: 0.8563, AllV: 0.8795 +[2026-03-20T18:37:47.241384Z] Loop 5180: Reg: 0.0031, AltReg: 0.0051, CorReg: 0.0000, TopReg: 0.0023, AllReg: 0.0051, BotRReg: 0.0093, OV: 0.8605, AltV: 0.8771, CorV: 0.8356, TopV: 0.8564, BotRV: 0.8493, AllV: 0.8771 +[2026-03-20T18:37:55.815925Z] Loop 5190: Reg: 0.0023, AltReg: 0.0038, CorReg: 0.0000, TopReg: 0.0030, AllReg: 0.0038, BotRReg: 0.0053, OV: 0.8613, AltV: 0.8784, CorV: 0.8356, TopV: 0.8556, BotRV: 0.8533, AllV: 0.8784 +[2026-03-20T18:38:04.393954Z] Loop 5200: Reg: 0.0018, AltReg: 0.0029, CorReg: 0.0001, TopReg: 0.0095, AllReg: 0.0030, BotRReg: 0.0020, OV: 0.8618, AltV: 0.8793, CorV: 0.8355, TopV: 0.8491, BotRV: 0.8566, AllV: 0.8793 +[2026-03-20T18:38:12.987848Z] Loop 5210: Reg: 0.0027, AltReg: 0.0045, CorReg: 0.0001, TopReg: 0.0020, AllReg: 0.0046, BotRReg: 0.0138, OV: 0.8608, AltV: 0.8777, CorV: 0.8355, TopV: 0.8567, BotRV: 0.8448, AllV: 0.8777 +[2026-03-20T18:38:21.572203Z] Loop 5220: Reg: 0.0019, AltReg: 0.0029, CorReg: 0.0003, TopReg: 0.0031, AllReg: 0.0029, BotRReg: 0.0018, OV: 0.8617, AltV: 0.8793, CorV: 0.8353, TopV: 0.8555, BotRV: 0.8569, AllV: 0.8793 +[2026-03-20T18:38:30.157640Z] Loop 5230: Reg: 0.0034, AltReg: 0.0056, CorReg: 0.0000, TopReg: 0.0172, AllReg: 0.0057, BotRReg: 0.0068, OV: 0.8602, AltV: 0.8766, CorV: 0.8356, TopV: 0.8414, BotRV: 0.8518, AllV: 0.8766 +[2026-03-20T18:38:38.738197Z] Loop 5240: Reg: 0.0034, AltReg: 0.0054, CorReg: 0.0006, TopReg: 0.0115, AllReg: 0.0054, BotRReg: 0.0020, OV: 0.8601, AltV: 0.8768, CorV: 0.8351, TopV: 0.8471, BotRV: 0.8566, AllV: 0.8768 +[2026-03-20T18:38:47.318231Z] Loop 5250: Reg: 0.0022, AltReg: 0.0037, CorReg: 0.0001, TopReg: 0.0039, AllReg: 0.0037, BotRReg: 0.0069, OV: 0.8613, AltV: 0.8786, CorV: 0.8355, TopV: 0.8547, BotRV: 0.8517, AllV: 0.8786 +[2026-03-20T18:38:55.901299Z] Loop 5260: Reg: 0.0037, AltReg: 0.0061, CorReg: 0.0001, TopReg: 0.0033, AllReg: 0.0061, BotRReg: 0.0170, OV: 0.8599, AltV: 0.8761, CorV: 0.8356, TopV: 0.8553, BotRV: 0.8416, AllV: 0.8762 +[2026-03-20T18:39:04.483600Z] Loop 5270: Reg: 0.0040, AltReg: 0.0065, CorReg: 0.0003, TopReg: 0.0172, AllReg: 0.0066, BotRReg: 0.0016, OV: 0.8596, AltV: 0.8757, CorV: 0.8353, TopV: 0.8415, BotRV: 0.8570, AllV: 0.8757 +[2026-03-20T18:39:13.061297Z] Loop 5280: Reg: 0.0025, AltReg: 0.0040, CorReg: 0.0001, TopReg: 0.0032, AllReg: 0.0041, BotRReg: 0.0040, OV: 0.8611, AltV: 0.8782, CorV: 0.8355, TopV: 0.8554, BotRV: 0.8546, AllV: 0.8782 +[2026-03-20T18:39:21.646504Z] Loop 5290: Reg: 0.0014, AltReg: 0.0023, CorReg: 0.0001, TopReg: 0.0016, AllReg: 0.0024, BotRReg: 0.0038, OV: 0.8621, AltV: 0.8799, CorV: 0.8355, TopV: 0.8570, BotRV: 0.8548, AllV: 0.8799 +[2026-03-20T18:39:30.228607Z] Loop 5300: Reg: 0.0031, AltReg: 0.0048, CorReg: 0.0005, TopReg: 0.0027, AllReg: 0.0048, BotRReg: 0.0114, OV: 0.8605, AltV: 0.8774, CorV: 0.8351, TopV: 0.8559, BotRV: 0.8472, AllV: 0.8774 +[2026-03-20T18:39:38.807897Z] Loop 5310: Reg: 0.0016, AltReg: 0.0025, CorReg: 0.0002, TopReg: 0.0021, AllReg: 0.0026, BotRReg: 0.0018, OV: 0.8620, AltV: 0.8797, CorV: 0.8354, TopV: 0.8565, BotRV: 0.8568, AllV: 0.8797 +[2026-03-20T18:39:47.387597Z] Loop 5320: Reg: 0.0094, AltReg: 0.0156, CorReg: 0.0000, TopReg: 0.0280, AllReg: 0.0157, BotRReg: 0.0317, OV: 0.8542, AltV: 0.8666, CorV: 0.8356, TopV: 0.8306, BotRV: 0.8269, AllV: 0.8666 +[2026-03-20T18:39:55.969401Z] Loop 5330: Reg: 0.0060, AltReg: 0.0097, CorReg: 0.0004, TopReg: 0.0041, AllReg: 0.0098, BotRReg: 0.0041, OV: 0.8576, AltV: 0.8725, CorV: 0.8352, TopV: 0.8546, BotRV: 0.8545, AllV: 0.8725 +[2026-03-20T18:40:04.552906Z] Loop 5340: Reg: 0.0032, AltReg: 0.0053, CorReg: 0.0001, TopReg: 0.0097, AllReg: 0.0053, BotRReg: 0.0054, OV: 0.8603, AltV: 0.8769, CorV: 0.8355, TopV: 0.8489, BotRV: 0.8532, AllV: 0.8769 +[2026-03-20T18:40:13.140288Z] Loop 5350: Reg: 0.0024, AltReg: 0.0036, CorReg: 0.0007, TopReg: 0.0037, AllReg: 0.0036, BotRReg: 0.0040, OV: 0.8611, AltV: 0.8786, CorV: 0.8349, TopV: 0.8549, BotRV: 0.8546, AllV: 0.8787 +[2026-03-20T18:40:21.727118Z] Loop 5360: Reg: 0.0019, AltReg: 0.0030, CorReg: 0.0002, TopReg: 0.0031, AllReg: 0.0030, BotRReg: 0.0014, OV: 0.8617, AltV: 0.8792, CorV: 0.8354, TopV: 0.8555, BotRV: 0.8573, AllV: 0.8792 +[2026-03-20T18:40:30.318952Z] Loop 5370: Reg: 0.0040, AltReg: 0.0064, CorReg: 0.0003, TopReg: 0.0143, AllReg: 0.0065, BotRReg: 0.0032, OV: 0.8596, AltV: 0.8758, CorV: 0.8354, TopV: 0.8444, BotRV: 0.8554, AllV: 0.8758 +[2026-03-20T18:40:38.895524Z] Loop 5380: Reg: 0.0015, AltReg: 0.0024, CorReg: 0.0001, TopReg: 0.0026, AllReg: 0.0024, BotRReg: 0.0018, OV: 0.8621, AltV: 0.8798, CorV: 0.8355, TopV: 0.8560, BotRV: 0.8568, AllV: 0.8798 +[2026-03-20T18:40:47.471974Z] Loop 5390: Reg: 0.0012, AltReg: 0.0020, CorReg: 0.0001, TopReg: 0.0014, AllReg: 0.0020, BotRReg: 0.0022, OV: 0.8624, AltV: 0.8803, CorV: 0.8356, TopV: 0.8573, BotRV: 0.8564, AllV: 0.8803 +[2026-03-20T18:40:56.052851Z] Loop 5400: Reg: 0.0016, AltReg: 0.0027, CorReg: 0.0001, TopReg: 0.0041, AllReg: 0.0027, BotRReg: 0.0033, OV: 0.8619, AltV: 0.8795, CorV: 0.8356, TopV: 0.8545, BotRV: 0.8553, AllV: 0.8795 +[2026-03-20T18:41:04.635325Z] Loop 5410: Reg: 0.0019, AltReg: 0.0029, CorReg: 0.0003, TopReg: 0.0025, AllReg: 0.0029, BotRReg: 0.0020, OV: 0.8617, AltV: 0.8793, CorV: 0.8353, TopV: 0.8562, BotRV: 0.8566, AllV: 0.8793 +[2026-03-20T18:41:13.223719Z] Loop 5420: Reg: 0.0068, AltReg: 0.0112, CorReg: 0.0003, TopReg: 0.0056, AllReg: 0.0112, BotRReg: 0.0157, OV: 0.8567, AltV: 0.8710, CorV: 0.8353, TopV: 0.8530, BotRV: 0.8429, AllV: 0.8710 +[2026-03-20T18:41:21.808642Z] Loop 5430: Reg: 0.0036, AltReg: 0.0058, CorReg: 0.0003, TopReg: 0.0037, AllReg: 0.0059, BotRReg: 0.0067, OV: 0.8599, AltV: 0.8764, CorV: 0.8353, TopV: 0.8549, BotRV: 0.8520, AllV: 0.8764 +[2026-03-20T18:41:30.386392Z] Loop 5440: Reg: 0.0014, AltReg: 0.0023, CorReg: 0.0001, TopReg: 0.0032, AllReg: 0.0023, BotRReg: 0.0022, OV: 0.8621, AltV: 0.8799, CorV: 0.8355, TopV: 0.8554, BotRV: 0.8564, AllV: 0.8799 +[2026-03-20T18:41:38.966692Z] Loop 5450: Reg: 0.0020, AltReg: 0.0032, CorReg: 0.0001, TopReg: 0.0033, AllReg: 0.0032, BotRReg: 0.0018, OV: 0.8616, AltV: 0.8790, CorV: 0.8355, TopV: 0.8553, BotRV: 0.8569, AllV: 0.8790 +[2026-03-20T18:41:47.547174Z] Loop 5460: Reg: 0.0040, AltReg: 0.0063, CorReg: 0.0006, TopReg: 0.0056, AllReg: 0.0063, BotRReg: 0.0025, OV: 0.8596, AltV: 0.8759, CorV: 0.8351, TopV: 0.8531, BotRV: 0.8561, AllV: 0.8759 +[2026-03-20T18:41:56.132011Z] Loop 5470: Reg: 0.0026, AltReg: 0.0042, CorReg: 0.0003, TopReg: 0.0063, AllReg: 0.0042, BotRReg: 0.0063, OV: 0.8609, AltV: 0.8780, CorV: 0.8354, TopV: 0.8524, BotRV: 0.8523, AllV: 0.8780 +[2026-03-20T18:42:04.712135Z] Loop 5480: Reg: 0.0016, AltReg: 0.0026, CorReg: 0.0002, TopReg: 0.0033, AllReg: 0.0026, BotRReg: 0.0030, OV: 0.8620, AltV: 0.8796, CorV: 0.8354, TopV: 0.8554, BotRV: 0.8557, AllV: 0.8796 +[2026-03-20T18:42:13.295067Z] Loop 5490: Reg: 0.0036, AltReg: 0.0054, CorReg: 0.0009, TopReg: 0.0035, AllReg: 0.0054, BotRReg: 0.0032, OV: 0.8600, AltV: 0.8768, CorV: 0.8347, TopV: 0.8551, BotRV: 0.8555, AllV: 0.8768 +[2026-03-20T18:42:21.879750Z] Loop 5500: Reg: 0.0018, AltReg: 0.0029, CorReg: 0.0002, TopReg: 0.0045, AllReg: 0.0029, BotRReg: 0.0033, OV: 0.8618, AltV: 0.8793, CorV: 0.8354, TopV: 0.8542, BotRV: 0.8553, AllV: 0.8793 +[2026-03-20T18:42:30.458556Z] Loop 5510: Reg: 0.0021, AltReg: 0.0034, CorReg: 0.0002, TopReg: 0.0029, AllReg: 0.0034, BotRReg: 0.0022, OV: 0.8614, AltV: 0.8788, CorV: 0.8354, TopV: 0.8557, BotRV: 0.8565, AllV: 0.8788 +[2026-03-20T18:42:39.037736Z] Loop 5520: Reg: 0.0029, AltReg: 0.0046, CorReg: 0.0002, TopReg: 0.0049, AllReg: 0.0046, BotRReg: 0.0020, OV: 0.8607, AltV: 0.8776, CorV: 0.8354, TopV: 0.8537, BotRV: 0.8566, AllV: 0.8776 +[2026-03-20T18:42:47.620725Z] Loop 5530: Reg: 0.0036, AltReg: 0.0060, CorReg: 0.0000, TopReg: 0.0100, AllReg: 0.0061, BotRReg: 0.0124, OV: 0.8600, AltV: 0.8762, CorV: 0.8356, TopV: 0.8486, BotRV: 0.8462, AllV: 0.8762 +[2026-03-20T18:42:56.197038Z] Loop 5540: Reg: 0.0011, AltReg: 0.0018, CorReg: 0.0001, TopReg: 0.0018, AllReg: 0.0019, BotRReg: 0.0018, OV: 0.8624, AltV: 0.8804, CorV: 0.8356, TopV: 0.8569, BotRV: 0.8568, AllV: 0.8804 +[2026-03-20T18:43:04.777441Z] Loop 5550: Reg: 0.0019, AltReg: 0.0031, CorReg: 0.0002, TopReg: 0.0027, AllReg: 0.0031, BotRReg: 0.0014, OV: 0.8617, AltV: 0.8791, CorV: 0.8355, TopV: 0.8560, BotRV: 0.8572, AllV: 0.8791 +[2026-03-20T18:43:13.365383Z] Loop 5560: Reg: 0.0019, AltReg: 0.0030, CorReg: 0.0002, TopReg: 0.0024, AllReg: 0.0030, BotRReg: 0.0014, OV: 0.8617, AltV: 0.8792, CorV: 0.8354, TopV: 0.8562, BotRV: 0.8573, AllV: 0.8793 +[2026-03-20T18:43:21.945440Z] Loop 5570: Reg: 0.0020, AltReg: 0.0033, CorReg: 0.0000, TopReg: 0.0073, AllReg: 0.0033, BotRReg: 0.0039, OV: 0.8616, AltV: 0.8789, CorV: 0.8356, TopV: 0.8514, BotRV: 0.8547, AllV: 0.8789 +[2026-03-20T18:43:30.526261Z] Loop 5580: Reg: 0.0149, AltReg: 0.0239, CorReg: 0.0014, TopReg: 0.0494, AllReg: 0.0241, BotRReg: 0.0013, OV: 0.8487, AltV: 0.8583, CorV: 0.8342, TopV: 0.8093, BotRV: 0.8573, AllV: 0.8582 +[2026-03-20T18:43:39.112874Z] Loop 5590: Reg: 0.0077, AltReg: 0.0127, CorReg: 0.0001, TopReg: 0.0454, AllReg: 0.0128, BotRReg: 0.0092, OV: 0.8559, AltV: 0.8695, CorV: 0.8355, TopV: 0.8132, BotRV: 0.8495, AllV: 0.8695 +[2026-03-20T18:43:47.692266Z] Loop 5600: Reg: 0.0032, AltReg: 0.0051, CorReg: 0.0005, TopReg: 0.0055, AllReg: 0.0051, BotRReg: 0.0120, OV: 0.8603, AltV: 0.8771, CorV: 0.8351, TopV: 0.8531, BotRV: 0.8466, AllV: 0.8771 +[2026-03-20T18:43:56.270522Z] Loop 5610: Reg: 0.0042, AltReg: 0.0061, CorReg: 0.0015, TopReg: 0.0088, AllReg: 0.0061, BotRReg: 0.0056, OV: 0.8593, AltV: 0.8761, CorV: 0.8341, TopV: 0.8499, BotRV: 0.8530, AllV: 0.8761 +[2026-03-20T18:44:04.864896Z] Loop 5620: Reg: 0.0019, AltReg: 0.0030, CorReg: 0.0003, TopReg: 0.0022, AllReg: 0.0031, BotRReg: 0.0062, OV: 0.8616, AltV: 0.8792, CorV: 0.8354, TopV: 0.8564, BotRV: 0.8524, AllV: 0.8792 +[2026-03-20T18:44:13.445954Z] Loop 5630: Reg: 0.0026, AltReg: 0.0042, CorReg: 0.0002, TopReg: 0.0026, AllReg: 0.0043, BotRReg: 0.0101, OV: 0.8610, AltV: 0.8780, CorV: 0.8354, TopV: 0.8560, BotRV: 0.8485, AllV: 0.8780 +[2026-03-20T18:44:22.027691Z] Loop 5640: Reg: 0.0017, AltReg: 0.0027, CorReg: 0.0002, TopReg: 0.0020, AllReg: 0.0027, BotRReg: 0.0028, OV: 0.8619, AltV: 0.8795, CorV: 0.8354, TopV: 0.8567, BotRV: 0.8558, AllV: 0.8795 +[2026-03-20T18:44:30.610145Z] Loop 5650: Reg: 0.0013, AltReg: 0.0021, CorReg: 0.0000, TopReg: 0.0012, AllReg: 0.0021, BotRReg: 0.0022, OV: 0.8623, AltV: 0.8801, CorV: 0.8356, TopV: 0.8575, BotRV: 0.8564, AllV: 0.8801 +[2026-03-20T18:44:39.196308Z] Loop 5660: Reg: 0.0013, AltReg: 0.0021, CorReg: 0.0000, TopReg: 0.0016, AllReg: 0.0022, BotRReg: 0.0021, OV: 0.8623, AltV: 0.8801, CorV: 0.8356, TopV: 0.8571, BotRV: 0.8565, AllV: 0.8801 +[2026-03-20T18:44:47.775808Z] Loop 5670: Reg: 0.0011, AltReg: 0.0017, CorReg: 0.0000, TopReg: 0.0010, AllReg: 0.0018, BotRReg: 0.0033, OV: 0.8625, AltV: 0.8805, CorV: 0.8356, TopV: 0.8576, BotRV: 0.8554, AllV: 0.8805 +[2026-03-20T18:44:56.364115Z] Loop 5680: Reg: 0.0015, AltReg: 0.0021, CorReg: 0.0005, TopReg: 0.0015, AllReg: 0.0021, BotRReg: 0.0032, OV: 0.8621, AltV: 0.8801, CorV: 0.8351, TopV: 0.8572, BotRV: 0.8554, AllV: 0.8801 +[2026-03-20T18:45:04.960155Z] Loop 5690: Reg: 0.0028, AltReg: 0.0039, CorReg: 0.0010, TopReg: 0.0027, AllReg: 0.0039, BotRReg: 0.0074, OV: 0.8608, AltV: 0.8783, CorV: 0.8346, TopV: 0.8559, BotRV: 0.8513, AllV: 0.8783 +[2026-03-20T18:45:13.548623Z] Loop 5700: Reg: 0.0010, AltReg: 0.0016, CorReg: 0.0000, TopReg: 0.0011, AllReg: 0.0016, BotRReg: 0.0024, OV: 0.8626, AltV: 0.8806, CorV: 0.8356, TopV: 0.8575, BotRV: 0.8562, AllV: 0.8806 +[2026-03-20T18:45:22.135750Z] Loop 5710: Reg: 0.0042, AltReg: 0.0068, CorReg: 0.0002, TopReg: 0.0156, AllReg: 0.0069, BotRReg: 0.0023, OV: 0.8594, AltV: 0.8754, CorV: 0.8354, TopV: 0.8430, BotRV: 0.8563, AllV: 0.8754 +[2026-03-20T18:45:30.715632Z] Loop 5720: Reg: 0.0022, AltReg: 0.0036, CorReg: 0.0000, TopReg: 0.0034, AllReg: 0.0036, BotRReg: 0.0047, OV: 0.8614, AltV: 0.8786, CorV: 0.8356, TopV: 0.8552, BotRV: 0.8539, AllV: 0.8786 +[2026-03-20T18:45:39.297051Z] Loop 5730: Reg: 0.0022, AltReg: 0.0037, CorReg: 0.0000, TopReg: 0.0068, AllReg: 0.0038, BotRReg: 0.0039, OV: 0.8613, AltV: 0.8785, CorV: 0.8356, TopV: 0.8518, BotRV: 0.8547, AllV: 0.8785 +[2026-03-20T18:45:47.885226Z] Loop 5740: Reg: 0.0026, AltReg: 0.0043, CorReg: 0.0000, TopReg: 0.0058, AllReg: 0.0043, BotRReg: 0.0054, OV: 0.8610, AltV: 0.8779, CorV: 0.8356, TopV: 0.8528, BotRV: 0.8532, AllV: 0.8780 +[2026-03-20T18:45:56.464391Z] Loop 5750: Reg: 0.0016, AltReg: 0.0027, CorReg: 0.0000, TopReg: 0.0050, AllReg: 0.0027, BotRReg: 0.0021, OV: 0.8620, AltV: 0.8795, CorV: 0.8356, TopV: 0.8536, BotRV: 0.8565, AllV: 0.8796 +[2026-03-20T18:46:05.044211Z] Loop 5760: Reg: 0.0019, AltReg: 0.0025, CorReg: 0.0009, TopReg: 0.0033, AllReg: 0.0025, BotRReg: 0.0021, OV: 0.8617, AltV: 0.8797, CorV: 0.8347, TopV: 0.8553, BotRV: 0.8566, AllV: 0.8797 +[2026-03-20T18:46:13.632808Z] Loop 5770: Reg: 0.0012, AltReg: 0.0019, CorReg: 0.0002, TopReg: 0.0017, AllReg: 0.0020, BotRReg: 0.0020, OV: 0.8623, AltV: 0.8803, CorV: 0.8354, TopV: 0.8569, BotRV: 0.8566, AllV: 0.8803 +[2026-03-20T18:46:22.220797Z] Loop 5780: Reg: 0.0020, AltReg: 0.0033, CorReg: 0.0002, TopReg: 0.0021, AllReg: 0.0033, BotRReg: 0.0056, OV: 0.8615, AltV: 0.8789, CorV: 0.8355, TopV: 0.8565, BotRV: 0.8530, AllV: 0.8790 +[2026-03-20T18:46:30.807336Z] Loop 5790: Reg: 0.0034, AltReg: 0.0055, CorReg: 0.0004, TopReg: 0.0044, AllReg: 0.0055, BotRReg: 0.0087, OV: 0.8601, AltV: 0.8768, CorV: 0.8352, TopV: 0.8542, BotRV: 0.8499, AllV: 0.8768 +[2026-03-20T18:46:39.390855Z] Loop 5800: Reg: 0.0010, AltReg: 0.0016, CorReg: 0.0002, TopReg: 0.0023, AllReg: 0.0016, BotRReg: 0.0017, OV: 0.8626, AltV: 0.8806, CorV: 0.8355, TopV: 0.8563, BotRV: 0.8570, AllV: 0.8807 +[2026-03-20T18:46:47.969709Z] Loop 5810: Reg: 0.0010, AltReg: 0.0016, CorReg: 0.0000, TopReg: 0.0011, AllReg: 0.0017, BotRReg: 0.0022, OV: 0.8626, AltV: 0.8806, CorV: 0.8356, TopV: 0.8575, BotRV: 0.8564, AllV: 0.8806 +[2026-03-20T18:46:56.557186Z] Loop 5820: Reg: 0.0062, AltReg: 0.0103, CorReg: 0.0000, TopReg: 0.0071, AllReg: 0.0103, BotRReg: 0.0317, OV: 0.8574, AltV: 0.8719, CorV: 0.8356, TopV: 0.8515, BotRV: 0.8269, AllV: 0.8719 +[2026-03-20T18:47:05.136272Z] Loop 5830: Reg: 0.0010, AltReg: 0.0017, CorReg: 0.0000, TopReg: 0.0010, AllReg: 0.0017, BotRReg: 0.0012, OV: 0.8626, AltV: 0.8805, CorV: 0.8356, TopV: 0.8576, BotRV: 0.8574, AllV: 0.8805 +[2026-03-20T18:47:13.728970Z] Loop 5840: Reg: 0.0020, AltReg: 0.0033, CorReg: 0.0002, TopReg: 0.0013, AllReg: 0.0033, BotRReg: 0.0019, OV: 0.8615, AltV: 0.8790, CorV: 0.8354, TopV: 0.8573, BotRV: 0.8567, AllV: 0.8790 +[2026-03-20T18:47:22.327253Z] Loop 5850: Reg: 0.0026, AltReg: 0.0043, CorReg: 0.0000, TopReg: 0.0048, AllReg: 0.0044, BotRReg: 0.0062, OV: 0.8610, AltV: 0.8779, CorV: 0.8356, TopV: 0.8538, BotRV: 0.8525, AllV: 0.8779 +[2026-03-20T18:47:30.936117Z] Loop 5860: Reg: 0.0019, AltReg: 0.0031, CorReg: 0.0000, TopReg: 0.0022, AllReg: 0.0032, BotRReg: 0.0032, OV: 0.8617, AltV: 0.8791, CorV: 0.8356, TopV: 0.8565, BotRV: 0.8555, AllV: 0.8791 +[2026-03-20T18:47:39.535333Z] Loop 5870: Reg: 0.0009, AltReg: 0.0014, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0015, BotRReg: 0.0018, OV: 0.8627, AltV: 0.8808, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8569, AllV: 0.8808 +[2026-03-20T18:47:48.135716Z] Loop 5880: Reg: 0.0014, AltReg: 0.0023, CorReg: 0.0000, TopReg: 0.0011, AllReg: 0.0023, BotRReg: 0.0043, OV: 0.8622, AltV: 0.8800, CorV: 0.8356, TopV: 0.8576, BotRV: 0.8543, AllV: 0.8800 +[2026-03-20T18:47:56.728159Z] Loop 5890: Reg: 0.0011, AltReg: 0.0017, CorReg: 0.0001, TopReg: 0.0021, AllReg: 0.0017, BotRReg: 0.0026, OV: 0.8625, AltV: 0.8805, CorV: 0.8355, TopV: 0.8566, BotRV: 0.8560, AllV: 0.8805 +[2026-03-20T18:48:05.321047Z] Loop 5900: Reg: 0.0012, AltReg: 0.0019, CorReg: 0.0001, TopReg: 0.0013, AllReg: 0.0019, BotRReg: 0.0029, OV: 0.8624, AltV: 0.8803, CorV: 0.8355, TopV: 0.8573, BotRV: 0.8557, AllV: 0.8804 +[2026-03-20T18:48:13.919518Z] Loop 5910: Reg: 0.0026, AltReg: 0.0043, CorReg: 0.0001, TopReg: 0.0023, AllReg: 0.0043, BotRReg: 0.0100, OV: 0.8610, AltV: 0.8779, CorV: 0.8356, TopV: 0.8563, BotRV: 0.8486, AllV: 0.8780 +[2026-03-20T18:48:22.516479Z] Loop 5920: Reg: 0.0027, AltReg: 0.0045, CorReg: 0.0001, TopReg: 0.0017, AllReg: 0.0045, BotRReg: 0.0061, OV: 0.8609, AltV: 0.8778, CorV: 0.8355, TopV: 0.8569, BotRV: 0.8526, AllV: 0.8778 +[2026-03-20T18:48:31.119058Z] Loop 5930: Reg: 0.0022, AltReg: 0.0034, CorReg: 0.0003, TopReg: 0.0015, AllReg: 0.0034, BotRReg: 0.0055, OV: 0.8614, AltV: 0.8788, CorV: 0.8353, TopV: 0.8571, BotRV: 0.8532, AllV: 0.8788 +[2026-03-20T18:48:39.716188Z] Loop 5940: Reg: 0.0017, AltReg: 0.0025, CorReg: 0.0005, TopReg: 0.0025, AllReg: 0.0025, BotRReg: 0.0032, OV: 0.8619, AltV: 0.8797, CorV: 0.8351, TopV: 0.8561, BotRV: 0.8554, AllV: 0.8797 +[2026-03-20T18:48:48.315515Z] Loop 5950: Reg: 0.0024, AltReg: 0.0039, CorReg: 0.0001, TopReg: 0.0027, AllReg: 0.0039, BotRReg: 0.0101, OV: 0.8612, AltV: 0.8784, CorV: 0.8355, TopV: 0.8560, BotRV: 0.8485, AllV: 0.8784 +[2026-03-20T18:48:56.922035Z] Loop 5960: Reg: 0.0016, AltReg: 0.0025, CorReg: 0.0004, TopReg: 0.0013, AllReg: 0.0025, BotRReg: 0.0030, OV: 0.8620, AltV: 0.8798, CorV: 0.8353, TopV: 0.8573, BotRV: 0.8557, AllV: 0.8798 +[2026-03-20T18:49:05.517272Z] Loop 5970: Reg: 0.0015, AltReg: 0.0022, CorReg: 0.0006, TopReg: 0.0014, AllReg: 0.0022, BotRReg: 0.0024, OV: 0.8620, AltV: 0.8801, CorV: 0.8350, TopV: 0.8572, BotRV: 0.8562, AllV: 0.8801 +[2026-03-20T18:49:14.112556Z] Loop 5980: Reg: 0.0046, AltReg: 0.0072, CorReg: 0.0006, TopReg: 0.0112, AllReg: 0.0073, BotRReg: 0.0034, OV: 0.8590, AltV: 0.8750, CorV: 0.8350, TopV: 0.8474, BotRV: 0.8552, AllV: 0.8750 +[2026-03-20T18:49:22.709480Z] Loop 5990: Reg: 0.0036, AltReg: 0.0060, CorReg: 0.0001, TopReg: 0.0039, AllReg: 0.0060, BotRReg: 0.0058, OV: 0.8600, AltV: 0.8763, CorV: 0.8356, TopV: 0.8547, BotRV: 0.8528, AllV: 0.8762 +[2026-03-20T18:49:31.298961Z] Loop 6000: Reg: 0.0014, AltReg: 0.0022, CorReg: 0.0002, TopReg: 0.0023, AllReg: 0.0022, BotRReg: 0.0026, OV: 0.8622, AltV: 0.8800, CorV: 0.8354, TopV: 0.8564, BotRV: 0.8560, AllV: 0.8800 +[2026-03-20T18:49:39.902339Z] Loop 6010: Reg: 0.0035, AltReg: 0.0057, CorReg: 0.0001, TopReg: 0.0058, AllReg: 0.0057, BotRReg: 0.0208, OV: 0.8601, AltV: 0.8765, CorV: 0.8355, TopV: 0.8529, BotRV: 0.8378, AllV: 0.8765 +[2026-03-20T18:49:48.505615Z] Loop 6020: Reg: 0.0013, AltReg: 0.0021, CorReg: 0.0000, TopReg: 0.0019, AllReg: 0.0021, BotRReg: 0.0040, OV: 0.8623, AltV: 0.8801, CorV: 0.8356, TopV: 0.8567, BotRV: 0.8546, AllV: 0.8801 +[2026-03-20T18:49:57.094226Z] Loop 6030: Reg: 0.0036, AltReg: 0.0061, CorReg: 0.0000, TopReg: 0.0023, AllReg: 0.0061, BotRReg: 0.0098, OV: 0.8599, AltV: 0.8762, CorV: 0.8356, TopV: 0.8563, BotRV: 0.8488, AllV: 0.8761 +[2026-03-20T18:50:05.698554Z] Loop 6040: Reg: 0.0043, AltReg: 0.0072, CorReg: 0.0000, TopReg: 0.0077, AllReg: 0.0073, BotRReg: 0.0275, OV: 0.8592, AltV: 0.8750, CorV: 0.8356, TopV: 0.8509, BotRV: 0.8312, AllV: 0.8750 +[2026-03-20T18:50:14.290589Z] Loop 6050: Reg: 0.0013, AltReg: 0.0022, CorReg: 0.0000, TopReg: 0.0028, AllReg: 0.0023, BotRReg: 0.0033, OV: 0.8622, AltV: 0.8800, CorV: 0.8356, TopV: 0.8558, BotRV: 0.8553, AllV: 0.8800 +[2026-03-20T18:50:22.887136Z] Loop 6060: Reg: 0.0019, AltReg: 0.0032, CorReg: 0.0001, TopReg: 0.0015, AllReg: 0.0034, BotRReg: 0.0013, OV: 0.8616, AltV: 0.8790, CorV: 0.8356, TopV: 0.8571, BotRV: 0.8573, AllV: 0.8789 +[2026-03-20T18:50:31.489912Z] Loop 6070: Reg: 0.0012, AltReg: 0.0019, CorReg: 0.0000, TopReg: 0.0009, AllReg: 0.0020, BotRReg: 0.0016, OV: 0.8624, AltV: 0.8803, CorV: 0.8356, TopV: 0.8577, BotRV: 0.8570, AllV: 0.8803 +[2026-03-20T18:50:40.083565Z] Loop 6080: Reg: 0.0010, AltReg: 0.0017, CorReg: 0.0000, TopReg: 0.0009, AllReg: 0.0017, BotRReg: 0.0026, OV: 0.8625, AltV: 0.8805, CorV: 0.8356, TopV: 0.8577, BotRV: 0.8560, AllV: 0.8805 +[2026-03-20T18:50:48.681159Z] Loop 6090: Reg: 0.0015, AltReg: 0.0025, CorReg: 0.0000, TopReg: 0.0013, AllReg: 0.0025, BotRReg: 0.0049, OV: 0.8621, AltV: 0.8797, CorV: 0.8356, TopV: 0.8574, BotRV: 0.8537, AllV: 0.8798 +[2026-03-20T18:50:57.287307Z] Loop 6100: Reg: 0.0026, AltReg: 0.0043, CorReg: 0.0000, TopReg: 0.0198, AllReg: 0.0044, BotRReg: 0.0015, OV: 0.8610, AltV: 0.8780, CorV: 0.8356, TopV: 0.8388, BotRV: 0.8572, AllV: 0.8779 +[2026-03-20T18:51:05.880107Z] Loop 6110: Reg: 0.0027, AltReg: 0.0044, CorReg: 0.0000, TopReg: 0.0032, AllReg: 0.0045, BotRReg: 0.0081, OV: 0.8609, AltV: 0.8778, CorV: 0.8356, TopV: 0.8554, BotRV: 0.8505, AllV: 0.8778 +[2026-03-20T18:51:14.475891Z] Loop 6120: Reg: 0.0014, AltReg: 0.0023, CorReg: 0.0000, TopReg: 0.0024, AllReg: 0.0024, BotRReg: 0.0027, OV: 0.8622, AltV: 0.8799, CorV: 0.8356, TopV: 0.8563, BotRV: 0.8560, AllV: 0.8799 +[2026-03-20T18:51:23.069926Z] Loop 6130: Reg: 0.0012, AltReg: 0.0019, CorReg: 0.0001, TopReg: 0.0010, AllReg: 0.0019, BotRReg: 0.0022, OV: 0.8624, AltV: 0.8803, CorV: 0.8356, TopV: 0.8576, BotRV: 0.8564, AllV: 0.8803 +[2026-03-20T18:51:31.662752Z] Loop 6140: Reg: 0.0015, AltReg: 0.0023, CorReg: 0.0003, TopReg: 0.0014, AllReg: 0.0023, BotRReg: 0.0026, OV: 0.8621, AltV: 0.8800, CorV: 0.8353, TopV: 0.8572, BotRV: 0.8560, AllV: 0.8800 +[2026-03-20T18:51:40.262386Z] Loop 6150: Reg: 0.0048, AltReg: 0.0070, CorReg: 0.0014, TopReg: 0.0050, AllReg: 0.0070, BotRReg: 0.0143, OV: 0.8588, AltV: 0.8752, CorV: 0.8343, TopV: 0.8537, BotRV: 0.8443, AllV: 0.8752 +[2026-03-20T18:51:48.855956Z] Loop 6160: Reg: 0.0077, AltReg: 0.0124, CorReg: 0.0005, TopReg: 0.0124, AllReg: 0.0125, BotRReg: 0.0174, OV: 0.8559, AltV: 0.8698, CorV: 0.8351, TopV: 0.8463, BotRV: 0.8413, AllV: 0.8698 +[2026-03-20T18:51:57.449275Z] Loop 6170: Reg: 0.0024, AltReg: 0.0036, CorReg: 0.0006, TopReg: 0.0023, AllReg: 0.0036, BotRReg: 0.0103, OV: 0.8612, AltV: 0.8786, CorV: 0.8351, TopV: 0.8563, BotRV: 0.8483, AllV: 0.8786 +[2026-03-20T18:52:06.041086Z] Loop 6180: Reg: 0.0022, AltReg: 0.0033, CorReg: 0.0005, TopReg: 0.0033, AllReg: 0.0034, BotRReg: 0.0056, OV: 0.8614, AltV: 0.8789, CorV: 0.8351, TopV: 0.8553, BotRV: 0.8531, AllV: 0.8789 +[2026-03-20T18:52:14.635949Z] Loop 6190: Reg: 0.0011, AltReg: 0.0017, CorReg: 0.0001, TopReg: 0.0010, AllReg: 0.0018, BotRReg: 0.0019, OV: 0.8625, AltV: 0.8805, CorV: 0.8356, TopV: 0.8576, BotRV: 0.8567, AllV: 0.8805 +[2026-03-20T18:52:23.233058Z] Loop 6200: Reg: 0.0025, AltReg: 0.0041, CorReg: 0.0001, TopReg: 0.0045, AllReg: 0.0042, BotRReg: 0.0018, OV: 0.8611, AltV: 0.8781, CorV: 0.8356, TopV: 0.8541, BotRV: 0.8569, AllV: 0.8781 +[2026-03-20T18:52:31.828737Z] Loop 6210: Reg: 0.0020, AltReg: 0.0034, CorReg: 0.0000, TopReg: 0.0026, AllReg: 0.0034, BotRReg: 0.0054, OV: 0.8616, AltV: 0.8789, CorV: 0.8356, TopV: 0.8560, BotRV: 0.8532, AllV: 0.8789 +[2026-03-20T18:52:40.427076Z] Loop 6220: Reg: 0.0022, AltReg: 0.0036, CorReg: 0.0000, TopReg: 0.0033, AllReg: 0.0036, BotRReg: 0.0060, OV: 0.8614, AltV: 0.8786, CorV: 0.8356, TopV: 0.8553, BotRV: 0.8526, AllV: 0.8786 +[2026-03-20T18:52:49.022094Z] Loop 6230: Reg: 0.0049, AltReg: 0.0081, CorReg: 0.0000, TopReg: 0.0053, AllReg: 0.0082, BotRReg: 0.0161, OV: 0.8587, AltV: 0.8741, CorV: 0.8356, TopV: 0.8534, BotRV: 0.8426, AllV: 0.8741 +[2026-03-20T18:52:57.616652Z] Loop 6240: Reg: 0.0012, AltReg: 0.0019, CorReg: 0.0000, TopReg: 0.0012, AllReg: 0.0019, BotRReg: 0.0029, OV: 0.8624, AltV: 0.8803, CorV: 0.8356, TopV: 0.8574, BotRV: 0.8557, AllV: 0.8803 +[2026-03-20T18:53:06.211059Z] Loop 6250: Reg: 0.0091, AltReg: 0.0151, CorReg: 0.0001, TopReg: 0.0060, AllReg: 0.0151, BotRReg: 0.0309, OV: 0.8545, AltV: 0.8671, CorV: 0.8355, TopV: 0.8526, BotRV: 0.8278, AllV: 0.8671 +[2026-03-20T18:53:14.801974Z] Loop 6260: Reg: 0.0127, AltReg: 0.0149, CorReg: 0.0093, TopReg: 0.0186, AllReg: 0.0149, BotRReg: 0.0199, OV: 0.8509, AltV: 0.8673, CorV: 0.8263, TopV: 0.8400, BotRV: 0.8387, AllV: 0.8673 +[2026-03-20T18:53:23.398503Z] Loop 6270: Reg: 0.0021, AltReg: 0.0034, CorReg: 0.0002, TopReg: 0.0011, AllReg: 0.0034, BotRReg: 0.0085, OV: 0.8615, AltV: 0.8789, CorV: 0.8354, TopV: 0.8576, BotRV: 0.8501, AllV: 0.8789 +[2026-03-20T18:53:31.992918Z] Loop 6280: Reg: 0.0025, AltReg: 0.0040, CorReg: 0.0001, TopReg: 0.0119, AllReg: 0.0042, BotRReg: 0.0025, OV: 0.8611, AltV: 0.8782, CorV: 0.8355, TopV: 0.8467, BotRV: 0.8561, AllV: 0.8781 +[2026-03-20T18:53:40.585677Z] Loop 6290: Reg: 0.0020, AltReg: 0.0034, CorReg: 0.0000, TopReg: 0.0040, AllReg: 0.0034, BotRReg: 0.0027, OV: 0.8616, AltV: 0.8788, CorV: 0.8356, TopV: 0.8546, BotRV: 0.8559, AllV: 0.8788 +[2026-03-20T18:53:49.176802Z] Loop 6300: Reg: 0.0035, AltReg: 0.0058, CorReg: 0.0000, TopReg: 0.0105, AllReg: 0.0058, BotRReg: 0.0056, OV: 0.8601, AltV: 0.8765, CorV: 0.8356, TopV: 0.8481, BotRV: 0.8530, AllV: 0.8764 +[2026-03-20T18:53:57.777850Z] Loop 6310: Reg: 0.0020, AltReg: 0.0033, CorReg: 0.0000, TopReg: 0.0122, AllReg: 0.0033, BotRReg: 0.0017, OV: 0.8616, AltV: 0.8789, CorV: 0.8356, TopV: 0.8464, BotRV: 0.8570, AllV: 0.8789 +[2026-03-20T18:54:06.373523Z] Loop 6320: Reg: 0.0045, AltReg: 0.0073, CorReg: 0.0003, TopReg: 0.0047, AllReg: 0.0074, BotRReg: 0.0072, OV: 0.8591, AltV: 0.8749, CorV: 0.8354, TopV: 0.8539, BotRV: 0.8514, AllV: 0.8749 +[2026-03-20T18:54:14.964237Z] Loop 6330: Reg: 0.0019, AltReg: 0.0029, CorReg: 0.0004, TopReg: 0.0033, AllReg: 0.0029, BotRReg: 0.0026, OV: 0.8617, AltV: 0.8793, CorV: 0.8353, TopV: 0.8553, BotRV: 0.8561, AllV: 0.8793 +[2026-03-20T18:54:23.559637Z] Loop 6340: Reg: 0.0023, AltReg: 0.0036, CorReg: 0.0003, TopReg: 0.0065, AllReg: 0.0036, BotRReg: 0.0063, OV: 0.8613, AltV: 0.8786, CorV: 0.8354, TopV: 0.8521, BotRV: 0.8523, AllV: 0.8786 +[2026-03-20T18:54:32.154932Z] Loop 6350: Reg: 0.0020, AltReg: 0.0030, CorReg: 0.0005, TopReg: 0.0030, AllReg: 0.0031, BotRReg: 0.0034, OV: 0.8616, AltV: 0.8792, CorV: 0.8352, TopV: 0.8556, BotRV: 0.8553, AllV: 0.8792 +[2026-03-20T18:54:40.749638Z] Loop 6360: Reg: 0.0018, AltReg: 0.0025, CorReg: 0.0007, TopReg: 0.0025, AllReg: 0.0025, BotRReg: 0.0023, OV: 0.8618, AltV: 0.8797, CorV: 0.8350, TopV: 0.8562, BotRV: 0.8563, AllV: 0.8797 +[2026-03-20T18:54:49.346499Z] Loop 6370: Reg: 0.0008, AltReg: 0.0013, CorReg: 0.0000, TopReg: 0.0008, AllReg: 0.0013, BotRReg: 0.0016, OV: 0.8628, AltV: 0.8809, CorV: 0.8356, TopV: 0.8578, BotRV: 0.8570, AllV: 0.8809 +[2026-03-20T18:54:57.946555Z] Loop 6380: Reg: 0.0010, AltReg: 0.0017, CorReg: 0.0000, TopReg: 0.0020, AllReg: 0.0017, BotRReg: 0.0016, OV: 0.8626, AltV: 0.8805, CorV: 0.8356, TopV: 0.8566, BotRV: 0.8570, AllV: 0.8805 +[2026-03-20T18:55:06.541464Z] Loop 6390: Reg: 0.0030, AltReg: 0.0049, CorReg: 0.0000, TopReg: 0.0107, AllReg: 0.0049, BotRReg: 0.0031, OV: 0.8606, AltV: 0.8773, CorV: 0.8356, TopV: 0.8479, BotRV: 0.8556, AllV: 0.8773 +[2026-03-20T18:55:15.137113Z] Loop 6400: Reg: 0.0022, AltReg: 0.0036, CorReg: 0.0001, TopReg: 0.0083, AllReg: 0.0036, BotRReg: 0.0012, OV: 0.8614, AltV: 0.8786, CorV: 0.8355, TopV: 0.8503, BotRV: 0.8574, AllV: 0.8786 +[2026-03-20T18:55:23.732486Z] Loop 6410: Reg: 0.0013, AltReg: 0.0021, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0021, BotRReg: 0.0036, OV: 0.8623, AltV: 0.8801, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8551, AllV: 0.8801 +[2026-03-20T18:55:32.325380Z] Loop 6420: Reg: 0.0034, AltReg: 0.0057, CorReg: 0.0000, TopReg: 0.0068, AllReg: 0.0058, BotRReg: 0.0116, OV: 0.8602, AltV: 0.8765, CorV: 0.8356, TopV: 0.8519, BotRV: 0.8470, AllV: 0.8765 +[2026-03-20T18:55:40.921444Z] Loop 6430: Reg: 0.0021, AltReg: 0.0034, CorReg: 0.0000, TopReg: 0.0023, AllReg: 0.0035, BotRReg: 0.0058, OV: 0.8615, AltV: 0.8788, CorV: 0.8356, TopV: 0.8563, BotRV: 0.8529, AllV: 0.8788 +[2026-03-20T18:55:49.523721Z] Loop 6440: Reg: 0.0019, AltReg: 0.0032, CorReg: 0.0000, TopReg: 0.0036, AllReg: 0.0032, BotRReg: 0.0038, OV: 0.8617, AltV: 0.8790, CorV: 0.8356, TopV: 0.8551, BotRV: 0.8548, AllV: 0.8790 +[2026-03-20T18:55:58.121516Z] Loop 6450: Reg: 0.0027, AltReg: 0.0045, CorReg: 0.0000, TopReg: 0.0028, AllReg: 0.0045, BotRReg: 0.0052, OV: 0.8609, AltV: 0.8777, CorV: 0.8356, TopV: 0.8558, BotRV: 0.8534, AllV: 0.8777 +[2026-03-20T18:56:06.717003Z] Loop 6460: Reg: 0.0083, AltReg: 0.0121, CorReg: 0.0026, TopReg: 0.0214, AllReg: 0.0121, BotRReg: 0.0173, OV: 0.8553, AltV: 0.8701, CorV: 0.8330, TopV: 0.8372, BotRV: 0.8413, AllV: 0.8702 +[2026-03-20T18:56:15.316530Z] Loop 6470: Reg: 0.0074, AltReg: 0.0124, CorReg: 0.0000, TopReg: 0.0154, AllReg: 0.0124, BotRReg: 0.0120, OV: 0.8562, AltV: 0.8699, CorV: 0.8356, TopV: 0.8433, BotRV: 0.8467, AllV: 0.8699 +[2026-03-20T18:56:23.909065Z] Loop 6480: Reg: 0.0032, AltReg: 0.0051, CorReg: 0.0004, TopReg: 0.0026, AllReg: 0.0051, BotRReg: 0.0089, OV: 0.8603, AltV: 0.8771, CorV: 0.8352, TopV: 0.8561, BotRV: 0.8498, AllV: 0.8771 +[2026-03-20T18:56:32.500374Z] Loop 6490: Reg: 0.0023, AltReg: 0.0035, CorReg: 0.0006, TopReg: 0.0154, AllReg: 0.0035, BotRReg: 0.0018, OV: 0.8612, AltV: 0.8787, CorV: 0.8350, TopV: 0.8432, BotRV: 0.8568, AllV: 0.8787 +[2026-03-20T18:56:41.095391Z] Loop 6500: Reg: 0.0024, AltReg: 0.0039, CorReg: 0.0001, TopReg: 0.0009, AllReg: 0.0039, BotRReg: 0.0095, OV: 0.8612, AltV: 0.8783, CorV: 0.8356, TopV: 0.8577, BotRV: 0.8492, AllV: 0.8784 +[2026-03-20T18:56:49.692366Z] Loop 6510: Reg: 0.0054, AltReg: 0.0090, CorReg: 0.0000, TopReg: 0.0068, AllReg: 0.0090, BotRReg: 0.0112, OV: 0.8582, AltV: 0.8732, CorV: 0.8356, TopV: 0.8518, BotRV: 0.8474, AllV: 0.8733 +[2026-03-20T18:56:58.287678Z] Loop 6520: Reg: 0.0016, AltReg: 0.0026, CorReg: 0.0001, TopReg: 0.0053, AllReg: 0.0026, BotRReg: 0.0013, OV: 0.8620, AltV: 0.8796, CorV: 0.8355, TopV: 0.8533, BotRV: 0.8573, AllV: 0.8797 +[2026-03-20T18:57:06.886418Z] Loop 6530: Reg: 0.0026, AltReg: 0.0041, CorReg: 0.0004, TopReg: 0.0135, AllReg: 0.0042, BotRReg: 0.0009, OV: 0.8609, AltV: 0.8781, CorV: 0.8352, TopV: 0.8451, BotRV: 0.8578, AllV: 0.8781 +[2026-03-20T18:57:15.488470Z] Loop 6540: Reg: 0.0022, AltReg: 0.0034, CorReg: 0.0002, TopReg: 0.0079, AllReg: 0.0035, BotRReg: 0.0016, OV: 0.8614, AltV: 0.8788, CorV: 0.8354, TopV: 0.8507, BotRV: 0.8570, AllV: 0.8787 +[2026-03-20T18:57:24.093010Z] Loop 6550: Reg: 0.0013, AltReg: 0.0020, CorReg: 0.0001, TopReg: 0.0013, AllReg: 0.0021, BotRReg: 0.0045, OV: 0.8623, AltV: 0.8802, CorV: 0.8356, TopV: 0.8573, BotRV: 0.8542, AllV: 0.8802 +[2026-03-20T18:57:32.687215Z] Loop 6560: Reg: 0.0020, AltReg: 0.0028, CorReg: 0.0009, TopReg: 0.0024, AllReg: 0.0029, BotRReg: 0.0068, OV: 0.8615, AltV: 0.8794, CorV: 0.8347, TopV: 0.8563, BotRV: 0.8518, AllV: 0.8794 +[2026-03-20T18:57:41.286877Z] Loop 6570: Reg: 0.0076, AltReg: 0.0081, CorReg: 0.0068, TopReg: 0.0170, AllReg: 0.0081, BotRReg: 0.0180, OV: 0.8560, AltV: 0.8741, CorV: 0.8288, TopV: 0.8416, BotRV: 0.8407, AllV: 0.8741 +[2026-03-20T18:57:49.886355Z] Loop 6580: Reg: 0.0011, AltReg: 0.0019, CorReg: 0.0001, TopReg: 0.0090, AllReg: 0.0019, BotRReg: 0.0009, OV: 0.8624, AltV: 0.8803, CorV: 0.8356, TopV: 0.8496, BotRV: 0.8578, AllV: 0.8804 +[2026-03-20T18:57:58.482552Z] Loop 6590: Reg: 0.0014, AltReg: 0.0022, CorReg: 0.0001, TopReg: 0.0059, AllReg: 0.0022, BotRReg: 0.0009, OV: 0.8622, AltV: 0.8800, CorV: 0.8356, TopV: 0.8527, BotRV: 0.8578, AllV: 0.8800 +[2026-03-20T18:58:07.075710Z] Loop 6600: Reg: 0.0016, AltReg: 0.0026, CorReg: 0.0001, TopReg: 0.0037, AllReg: 0.0026, BotRReg: 0.0037, OV: 0.8620, AltV: 0.8796, CorV: 0.8355, TopV: 0.8549, BotRV: 0.8549, AllV: 0.8797 +[2026-03-20T18:58:15.674059Z] Loop 6610: Reg: 0.0011, AltReg: 0.0018, CorReg: 0.0001, TopReg: 0.0019, AllReg: 0.0018, BotRReg: 0.0020, OV: 0.8624, AltV: 0.8804, CorV: 0.8355, TopV: 0.8567, BotRV: 0.8566, AllV: 0.8804 +[2026-03-20T18:58:24.266431Z] Loop 6620: Reg: 0.0010, AltReg: 0.0016, CorReg: 0.0001, TopReg: 0.0043, AllReg: 0.0016, BotRReg: 0.0014, OV: 0.8626, AltV: 0.8807, CorV: 0.8355, TopV: 0.8543, BotRV: 0.8572, AllV: 0.8807 +[2026-03-20T18:58:32.867800Z] Loop 6630: Reg: 0.0026, AltReg: 0.0043, CorReg: 0.0000, TopReg: 0.0025, AllReg: 0.0043, BotRReg: 0.0100, OV: 0.8610, AltV: 0.8779, CorV: 0.8356, TopV: 0.8561, BotRV: 0.8487, AllV: 0.8779 +[2026-03-20T18:58:41.467212Z] Loop 6640: Reg: 0.0026, AltReg: 0.0043, CorReg: 0.0001, TopReg: 0.0036, AllReg: 0.0044, BotRReg: 0.0067, OV: 0.8610, AltV: 0.8779, CorV: 0.8356, TopV: 0.8551, BotRV: 0.8519, AllV: 0.8778 +[2026-03-20T18:58:50.065685Z] Loop 6650: Reg: 0.0009, AltReg: 0.0015, CorReg: 0.0001, TopReg: 0.0014, AllReg: 0.0015, BotRReg: 0.0015, OV: 0.8627, AltV: 0.8807, CorV: 0.8355, TopV: 0.8573, BotRV: 0.8571, AllV: 0.8807 +[2026-03-20T18:58:58.662919Z] Loop 6660: Reg: 0.0009, AltReg: 0.0014, CorReg: 0.0001, TopReg: 0.0016, AllReg: 0.0014, BotRReg: 0.0026, OV: 0.8627, AltV: 0.8809, CorV: 0.8355, TopV: 0.8570, BotRV: 0.8560, AllV: 0.8809 +[2026-03-20T18:59:07.263071Z] Loop 6670: Reg: 0.0092, AltReg: 0.0154, CorReg: 0.0000, TopReg: 0.0107, AllReg: 0.0154, BotRReg: 0.0465, OV: 0.8543, AltV: 0.8668, CorV: 0.8356, TopV: 0.8480, BotRV: 0.8122, AllV: 0.8668 +[2026-03-20T18:59:15.863177Z] Loop 6680: Reg: 0.0015, AltReg: 0.0025, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0026, BotRReg: 0.0033, OV: 0.8621, AltV: 0.8797, CorV: 0.8356, TopV: 0.8580, BotRV: 0.8553, AllV: 0.8796 +[2026-03-20T18:59:24.461349Z] Loop 6690: Reg: 0.0013, AltReg: 0.0022, CorReg: 0.0000, TopReg: 0.0006, AllReg: 0.0022, BotRReg: 0.0022, OV: 0.8623, AltV: 0.8800, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8564, AllV: 0.8800 +[2026-03-20T18:59:33.057141Z] Loop 6700: Reg: 0.0013, AltReg: 0.0022, CorReg: 0.0000, TopReg: 0.0016, AllReg: 0.0023, BotRReg: 0.0026, OV: 0.8622, AltV: 0.8800, CorV: 0.8356, TopV: 0.8570, BotRV: 0.8561, AllV: 0.8800 +[2026-03-20T18:59:41.648537Z] Loop 6710: Reg: 0.0015, AltReg: 0.0024, CorReg: 0.0000, TopReg: 0.0012, AllReg: 0.0025, BotRReg: 0.0031, OV: 0.8621, AltV: 0.8798, CorV: 0.8356, TopV: 0.8574, BotRV: 0.8555, AllV: 0.8798 +[2026-03-20T18:59:50.241561Z] Loop 6720: Reg: 0.0016, AltReg: 0.0026, CorReg: 0.0000, TopReg: 0.0014, AllReg: 0.0027, BotRReg: 0.0033, OV: 0.8620, AltV: 0.8796, CorV: 0.8356, TopV: 0.8573, BotRV: 0.8553, AllV: 0.8796 +[2026-03-20T18:59:58.841503Z] Loop 6730: Reg: 0.0012, AltReg: 0.0020, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0020, BotRReg: 0.0028, OV: 0.8624, AltV: 0.8802, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8558, AllV: 0.8803 +[2026-03-20T19:00:07.436980Z] Loop 6740: Reg: 0.0008, AltReg: 0.0013, CorReg: 0.0000, TopReg: 0.0020, AllReg: 0.0013, BotRReg: 0.0012, OV: 0.8628, AltV: 0.8809, CorV: 0.8356, TopV: 0.8566, BotRV: 0.8574, AllV: 0.8809 +[2026-03-20T19:00:16.035035Z] Loop 6750: Reg: 0.0008, AltReg: 0.0013, CorReg: 0.0000, TopReg: 0.0018, AllReg: 0.0013, BotRReg: 0.0013, OV: 0.8628, AltV: 0.8809, CorV: 0.8356, TopV: 0.8568, BotRV: 0.8574, AllV: 0.8809 +[2026-03-20T19:00:24.636580Z] Loop 6760: Reg: 0.0015, AltReg: 0.0024, CorReg: 0.0001, TopReg: 0.0053, AllReg: 0.0024, BotRReg: 0.0015, OV: 0.8621, AltV: 0.8798, CorV: 0.8356, TopV: 0.8533, BotRV: 0.8572, AllV: 0.8798 +[2026-03-20T19:00:33.234589Z] Loop 6770: Reg: 0.0013, AltReg: 0.0020, CorReg: 0.0003, TopReg: 0.0014, AllReg: 0.0020, BotRReg: 0.0028, OV: 0.8622, AltV: 0.8802, CorV: 0.8354, TopV: 0.8572, BotRV: 0.8558, AllV: 0.8802 +[2026-03-20T19:00:41.836925Z] Loop 6780: Reg: 0.0016, AltReg: 0.0027, CorReg: 0.0000, TopReg: 0.0010, AllReg: 0.0027, BotRReg: 0.0050, OV: 0.8619, AltV: 0.8795, CorV: 0.8356, TopV: 0.8576, BotRV: 0.8536, AllV: 0.8795 +[2026-03-20T19:00:50.432097Z] Loop 6790: Reg: 0.0016, AltReg: 0.0027, CorReg: 0.0000, TopReg: 0.0016, AllReg: 0.0027, BotRReg: 0.0044, OV: 0.8620, AltV: 0.8795, CorV: 0.8356, TopV: 0.8570, BotRV: 0.8542, AllV: 0.8795 +[2026-03-20T19:00:59.023559Z] Loop 6800: Reg: 0.0052, AltReg: 0.0086, CorReg: 0.0000, TopReg: 0.0111, AllReg: 0.0087, BotRReg: 0.0103, OV: 0.8584, AltV: 0.8736, CorV: 0.8356, TopV: 0.8475, BotRV: 0.8483, AllV: 0.8736 +[2026-03-20T19:01:07.618068Z] Loop 6810: Reg: 0.0071, AltReg: 0.0104, CorReg: 0.0021, TopReg: 0.0091, AllReg: 0.0104, BotRReg: 0.0136, OV: 0.8565, AltV: 0.8718, CorV: 0.8335, TopV: 0.8495, BotRV: 0.8451, AllV: 0.8719 +[2026-03-20T19:01:16.207707Z] Loop 6820: Reg: 0.0099, AltReg: 0.0165, CorReg: 0.0001, TopReg: 0.0096, AllReg: 0.0166, BotRReg: 0.0214, OV: 0.8536, AltV: 0.8657, CorV: 0.8356, TopV: 0.8490, BotRV: 0.8373, AllV: 0.8657 +[2026-03-20T19:01:24.799384Z] Loop 6830: Reg: 0.0008, AltReg: 0.0013, CorReg: 0.0000, TopReg: 0.0029, AllReg: 0.0013, BotRReg: 0.0019, OV: 0.8628, AltV: 0.8809, CorV: 0.8356, TopV: 0.8557, BotRV: 0.8567, AllV: 0.8809 +[2026-03-20T19:01:33.391561Z] Loop 6840: Reg: 0.0008, AltReg: 0.0012, CorReg: 0.0000, TopReg: 0.0012, AllReg: 0.0013, BotRReg: 0.0012, OV: 0.8628, AltV: 0.8810, CorV: 0.8356, TopV: 0.8574, BotRV: 0.8575, AllV: 0.8810 +[2026-03-20T19:01:41.988591Z] Loop 6850: Reg: 0.0009, AltReg: 0.0016, CorReg: 0.0000, TopReg: 0.0019, AllReg: 0.0016, BotRReg: 0.0011, OV: 0.8626, AltV: 0.8807, CorV: 0.8356, TopV: 0.8567, BotRV: 0.8575, AllV: 0.8807 +[2026-03-20T19:01:50.585924Z] Loop 6860: Reg: 0.0007, AltReg: 0.0011, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0011, BotRReg: 0.0017, OV: 0.8629, AltV: 0.8811, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8569, AllV: 0.8811 +[2026-03-20T19:01:59.182193Z] Loop 6870: Reg: 0.0017, AltReg: 0.0028, CorReg: 0.0000, TopReg: 0.0015, AllReg: 0.0028, BotRReg: 0.0070, OV: 0.8619, AltV: 0.8795, CorV: 0.8356, TopV: 0.8571, BotRV: 0.8516, AllV: 0.8795 +[2026-03-20T19:02:07.774725Z] Loop 6880: Reg: 0.0009, AltReg: 0.0015, CorReg: 0.0000, TopReg: 0.0009, AllReg: 0.0015, BotRReg: 0.0021, OV: 0.8627, AltV: 0.8808, CorV: 0.8356, TopV: 0.8577, BotRV: 0.8565, AllV: 0.8808 +[2026-03-20T19:02:16.380539Z] Loop 6890: Reg: 0.0009, AltReg: 0.0015, CorReg: 0.0000, TopReg: 0.0012, AllReg: 0.0015, BotRReg: 0.0021, OV: 0.8627, AltV: 0.8807, CorV: 0.8356, TopV: 0.8574, BotRV: 0.8565, AllV: 0.8807 +[2026-03-20T19:02:24.980734Z] Loop 6900: Reg: 0.0010, AltReg: 0.0017, CorReg: 0.0000, TopReg: 0.0016, AllReg: 0.0017, BotRReg: 0.0020, OV: 0.8626, AltV: 0.8805, CorV: 0.8356, TopV: 0.8571, BotRV: 0.8567, AllV: 0.8806 +[2026-03-20T19:02:33.575013Z] Loop 6910: Reg: 0.0007, AltReg: 0.0011, CorReg: 0.0000, TopReg: 0.0008, AllReg: 0.0011, BotRReg: 0.0015, OV: 0.8629, AltV: 0.8811, CorV: 0.8356, TopV: 0.8578, BotRV: 0.8571, AllV: 0.8811 +[2026-03-20T19:02:42.168871Z] Loop 6920: Reg: 0.0008, AltReg: 0.0013, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0013, BotRReg: 0.0022, OV: 0.8628, AltV: 0.8810, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8564, AllV: 0.8810 +[2026-03-20T19:02:50.763845Z] Loop 6930: Reg: 0.0024, AltReg: 0.0040, CorReg: 0.0000, TopReg: 0.0047, AllReg: 0.0040, BotRReg: 0.0078, OV: 0.8612, AltV: 0.8782, CorV: 0.8356, TopV: 0.8539, BotRV: 0.8509, AllV: 0.8782 +[2026-03-20T19:02:59.362492Z] Loop 6940: Reg: 0.0020, AltReg: 0.0032, CorReg: 0.0000, TopReg: 0.0049, AllReg: 0.0033, BotRReg: 0.0024, OV: 0.8616, AltV: 0.8790, CorV: 0.8356, TopV: 0.8537, BotRV: 0.8562, AllV: 0.8790 +[2026-03-20T19:03:07.957531Z] Loop 6950: Reg: 0.0018, AltReg: 0.0029, CorReg: 0.0001, TopReg: 0.0030, AllReg: 0.0029, BotRReg: 0.0017, OV: 0.8618, AltV: 0.8793, CorV: 0.8355, TopV: 0.8556, BotRV: 0.8569, AllV: 0.8793 +[2026-03-20T19:03:16.558833Z] Loop 6960: Reg: 0.0019, AltReg: 0.0032, CorReg: 0.0000, TopReg: 0.0041, AllReg: 0.0033, BotRReg: 0.0048, OV: 0.8616, AltV: 0.8790, CorV: 0.8356, TopV: 0.8546, BotRV: 0.8538, AllV: 0.8790 +[2026-03-20T19:03:25.154020Z] Loop 6970: Reg: 0.0026, AltReg: 0.0044, CorReg: 0.0000, TopReg: 0.0081, AllReg: 0.0044, BotRReg: 0.0040, OV: 0.8609, AltV: 0.8778, CorV: 0.8356, TopV: 0.8505, BotRV: 0.8547, AllV: 0.8778 +[2026-03-20T19:03:33.754200Z] Loop 6980: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0010, BotRReg: 0.0013, OV: 0.8630, AltV: 0.8812, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8573, AllV: 0.8813 +[2026-03-20T19:03:42.354185Z] Loop 6990: Reg: 0.0010, AltReg: 0.0016, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0016, BotRReg: 0.0024, OV: 0.8626, AltV: 0.8806, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8563, AllV: 0.8807 +[2026-03-20T19:03:50.952206Z] Loop 7000: Reg: 0.0015, AltReg: 0.0025, CorReg: 0.0000, TopReg: 0.0021, AllReg: 0.0025, BotRReg: 0.0027, OV: 0.8621, AltV: 0.8798, CorV: 0.8356, TopV: 0.8565, BotRV: 0.8559, AllV: 0.8798 +[2026-03-20T19:03:59.546552Z] Loop 7010: Reg: 0.0012, AltReg: 0.0020, CorReg: 0.0000, TopReg: 0.0010, AllReg: 0.0021, BotRReg: 0.0033, OV: 0.8624, AltV: 0.8802, CorV: 0.8356, TopV: 0.8576, BotRV: 0.8553, AllV: 0.8802 +[2026-03-20T19:04:08.136173Z] Loop 7020: Reg: 0.0013, AltReg: 0.0022, CorReg: 0.0001, TopReg: 0.0033, AllReg: 0.0022, BotRReg: 0.0019, OV: 0.8622, AltV: 0.8801, CorV: 0.8355, TopV: 0.8553, BotRV: 0.8567, AllV: 0.8801 +[2026-03-20T19:04:16.730943Z] Loop 7030: Reg: 0.0032, AltReg: 0.0050, CorReg: 0.0005, TopReg: 0.0186, AllReg: 0.0050, BotRReg: 0.0021, OV: 0.8604, AltV: 0.8772, CorV: 0.8352, TopV: 0.8400, BotRV: 0.8565, AllV: 0.8772 +[2026-03-20T19:04:25.326240Z] Loop 7040: Reg: 0.0019, AltReg: 0.0031, CorReg: 0.0001, TopReg: 0.0022, AllReg: 0.0031, BotRReg: 0.0073, OV: 0.8617, AltV: 0.8791, CorV: 0.8355, TopV: 0.8564, BotRV: 0.8513, AllV: 0.8791 +[2026-03-20T19:04:33.926753Z] Loop 7050: Reg: 0.0018, AltReg: 0.0028, CorReg: 0.0002, TopReg: 0.0026, AllReg: 0.0028, BotRReg: 0.0042, OV: 0.8618, AltV: 0.8794, CorV: 0.8354, TopV: 0.8560, BotRV: 0.8544, AllV: 0.8794 +[2026-03-20T19:04:42.519855Z] Loop 7060: Reg: 0.0051, AltReg: 0.0085, CorReg: 0.0000, TopReg: 0.0059, AllReg: 0.0086, BotRReg: 0.0249, OV: 0.8585, AltV: 0.8737, CorV: 0.8356, TopV: 0.8528, BotRV: 0.8337, AllV: 0.8737 +[2026-03-20T19:04:51.113233Z] Loop 7070: Reg: 0.0013, AltReg: 0.0022, CorReg: 0.0000, TopReg: 0.0023, AllReg: 0.0022, BotRReg: 0.0018, OV: 0.8623, AltV: 0.8801, CorV: 0.8356, TopV: 0.8563, BotRV: 0.8568, AllV: 0.8801 +[2026-03-20T19:04:59.713915Z] Loop 7080: Reg: 0.0020, AltReg: 0.0033, CorReg: 0.0000, TopReg: 0.0044, AllReg: 0.0034, BotRReg: 0.0017, OV: 0.8616, AltV: 0.8789, CorV: 0.8356, TopV: 0.8543, BotRV: 0.8569, AllV: 0.8789 +[2026-03-20T19:05:08.311155Z] Loop 7090: Reg: 0.0009, AltReg: 0.0015, CorReg: 0.0000, TopReg: 0.0017, AllReg: 0.0015, BotRReg: 0.0015, OV: 0.8627, AltV: 0.8807, CorV: 0.8356, TopV: 0.8569, BotRV: 0.8571, AllV: 0.8808 +[2026-03-20T19:05:16.908808Z] Loop 7100: Reg: 0.0008, AltReg: 0.0012, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0013, BotRReg: 0.0020, OV: 0.8628, AltV: 0.8810, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8566, AllV: 0.8810 +[2026-03-20T19:05:25.510689Z] Loop 7110: Reg: 0.0007, AltReg: 0.0011, CorReg: 0.0000, TopReg: 0.0006, AllReg: 0.0011, BotRReg: 0.0016, OV: 0.8629, AltV: 0.8811, CorV: 0.8356, TopV: 0.8580, BotRV: 0.8570, AllV: 0.8811 +[2026-03-20T19:05:34.119237Z] Loop 7120: Reg: 0.0007, AltReg: 0.0012, CorReg: 0.0000, TopReg: 0.0015, AllReg: 0.0012, BotRReg: 0.0012, OV: 0.8629, AltV: 0.8810, CorV: 0.8356, TopV: 0.8572, BotRV: 0.8574, AllV: 0.8810 +[2026-03-20T19:05:42.717212Z] Loop 7130: Reg: 0.0009, AltReg: 0.0015, CorReg: 0.0000, TopReg: 0.0027, AllReg: 0.0015, BotRReg: 0.0011, OV: 0.8627, AltV: 0.8807, CorV: 0.8356, TopV: 0.8559, BotRV: 0.8576, AllV: 0.8807 +[2026-03-20T19:05:51.311811Z] Loop 7140: Reg: 0.0009, AltReg: 0.0014, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0014, BotRReg: 0.0010, OV: 0.8627, AltV: 0.8808, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8576, AllV: 0.8808 +[2026-03-20T19:05:59.909473Z] Loop 7150: Reg: 0.0024, AltReg: 0.0039, CorReg: 0.0001, TopReg: 0.0017, AllReg: 0.0040, BotRReg: 0.0015, OV: 0.8612, AltV: 0.8783, CorV: 0.8355, TopV: 0.8570, BotRV: 0.8571, AllV: 0.8783 +[2026-03-20T19:06:08.508642Z] Loop 7160: Reg: 0.0012, AltReg: 0.0021, CorReg: 0.0000, TopReg: 0.0028, AllReg: 0.0021, BotRReg: 0.0029, OV: 0.8623, AltV: 0.8802, CorV: 0.8356, TopV: 0.8558, BotRV: 0.8557, AllV: 0.8802 +[2026-03-20T19:06:17.103560Z] Loop 7170: Reg: 0.0032, AltReg: 0.0053, CorReg: 0.0000, TopReg: 0.0058, AllReg: 0.0053, BotRReg: 0.0113, OV: 0.8604, AltV: 0.8769, CorV: 0.8356, TopV: 0.8528, BotRV: 0.8474, AllV: 0.8769 +[2026-03-20T19:06:25.702633Z] Loop 7180: Reg: 0.0020, AltReg: 0.0033, CorReg: 0.0000, TopReg: 0.0046, AllReg: 0.0034, BotRReg: 0.0075, OV: 0.8616, AltV: 0.8789, CorV: 0.8356, TopV: 0.8541, BotRV: 0.8512, AllV: 0.8789 +[2026-03-20T19:06:34.298054Z] Loop 7190: Reg: 0.0089, AltReg: 0.0143, CorReg: 0.0007, TopReg: 0.0130, AllReg: 0.0145, BotRReg: 0.0215, OV: 0.8547, AltV: 0.8679, CorV: 0.8349, TopV: 0.8456, BotRV: 0.8371, AllV: 0.8678 +[2026-03-20T19:06:42.891899Z] Loop 7200: Reg: 0.0012, AltReg: 0.0020, CorReg: 0.0000, TopReg: 0.0010, AllReg: 0.0020, BotRReg: 0.0059, OV: 0.8624, AltV: 0.8802, CorV: 0.8356, TopV: 0.8577, BotRV: 0.8527, AllV: 0.8802 +[2026-03-20T19:06:51.488108Z] Loop 7210: Reg: 0.0009, AltReg: 0.0015, CorReg: 0.0000, TopReg: 0.0009, AllReg: 0.0016, BotRReg: 0.0044, OV: 0.8626, AltV: 0.8807, CorV: 0.8356, TopV: 0.8578, BotRV: 0.8542, AllV: 0.8807 +[2026-03-20T19:07:00.094332Z] Loop 7220: Reg: 0.0028, AltReg: 0.0047, CorReg: 0.0000, TopReg: 0.0117, AllReg: 0.0047, BotRReg: 0.0026, OV: 0.8607, AltV: 0.8775, CorV: 0.8356, TopV: 0.8469, BotRV: 0.8561, AllV: 0.8775 +[2026-03-20T19:07:08.692483Z] Loop 7230: Reg: 0.0064, AltReg: 0.0106, CorReg: 0.0001, TopReg: 0.0051, AllReg: 0.0105, BotRReg: 0.0071, OV: 0.8572, AltV: 0.8717, CorV: 0.8355, TopV: 0.8536, BotRV: 0.8515, AllV: 0.8717 +[2026-03-20T19:07:17.285645Z] Loop 7240: Reg: 0.0013, AltReg: 0.0018, CorReg: 0.0004, TopReg: 0.0012, AllReg: 0.0018, BotRReg: 0.0008, OV: 0.8623, AltV: 0.8804, CorV: 0.8352, TopV: 0.8574, BotRV: 0.8579, AllV: 0.8804 +[2026-03-20T19:07:25.883086Z] Loop 7250: Reg: 0.0009, AltReg: 0.0012, CorReg: 0.0004, TopReg: 0.0012, AllReg: 0.0013, BotRReg: 0.0013, OV: 0.8627, AltV: 0.8810, CorV: 0.8352, TopV: 0.8574, BotRV: 0.8573, AllV: 0.8810 +[2026-03-20T19:07:34.477858Z] Loop 7260: Reg: 0.0011, AltReg: 0.0017, CorReg: 0.0001, TopReg: 0.0017, AllReg: 0.0018, BotRReg: 0.0018, OV: 0.8625, AltV: 0.8805, CorV: 0.8355, TopV: 0.8570, BotRV: 0.8568, AllV: 0.8805 +[2026-03-20T19:07:43.075115Z] Loop 7270: Reg: 0.0011, AltReg: 0.0017, CorReg: 0.0000, TopReg: 0.0013, AllReg: 0.0018, BotRReg: 0.0035, OV: 0.8625, AltV: 0.8805, CorV: 0.8356, TopV: 0.8573, BotRV: 0.8551, AllV: 0.8805 +[2026-03-20T19:07:51.666576Z] Loop 7280: Reg: 0.0013, AltReg: 0.0022, CorReg: 0.0000, TopReg: 0.0023, AllReg: 0.0022, BotRReg: 0.0047, OV: 0.8623, AltV: 0.8801, CorV: 0.8356, TopV: 0.8563, BotRV: 0.8539, AllV: 0.8801 +[2026-03-20T19:08:00.259603Z] Loop 7290: Reg: 0.0029, AltReg: 0.0049, CorReg: 0.0000, TopReg: 0.0050, AllReg: 0.0049, BotRReg: 0.0072, OV: 0.8606, AltV: 0.8773, CorV: 0.8356, TopV: 0.8537, BotRV: 0.8515, AllV: 0.8773 +[2026-03-20T19:08:08.852101Z] Loop 7300: Reg: 0.0020, AltReg: 0.0034, CorReg: 0.0000, TopReg: 0.0161, AllReg: 0.0034, BotRReg: 0.0016, OV: 0.8615, AltV: 0.8788, CorV: 0.8356, TopV: 0.8425, BotRV: 0.8570, AllV: 0.8788 +[2026-03-20T19:08:17.446953Z] Loop 7310: Reg: 0.0011, AltReg: 0.0018, CorReg: 0.0000, TopReg: 0.0043, AllReg: 0.0018, BotRReg: 0.0013, OV: 0.8625, AltV: 0.8804, CorV: 0.8356, TopV: 0.8543, BotRV: 0.8574, AllV: 0.8804 +[2026-03-20T19:08:26.043695Z] Loop 7320: Reg: 0.0009, AltReg: 0.0016, CorReg: 0.0000, TopReg: 0.0020, AllReg: 0.0016, BotRReg: 0.0014, OV: 0.8626, AltV: 0.8806, CorV: 0.8356, TopV: 0.8566, BotRV: 0.8572, AllV: 0.8807 +[2026-03-20T19:08:34.635646Z] Loop 7330: Reg: 0.0008, AltReg: 0.0013, CorReg: 0.0000, TopReg: 0.0011, AllReg: 0.0013, BotRReg: 0.0008, OV: 0.8628, AltV: 0.8809, CorV: 0.8356, TopV: 0.8575, BotRV: 0.8578, AllV: 0.8809 +[2026-03-20T19:08:43.239314Z] Loop 7340: Reg: 0.0005, AltReg: 0.0009, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0009, BotRReg: 0.0010, OV: 0.8631, AltV: 0.8814, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8576, AllV: 0.8814 +[2026-03-20T19:08:51.835777Z] Loop 7350: Reg: 0.0013, AltReg: 0.0022, CorReg: 0.0000, TopReg: 0.0020, AllReg: 0.0022, BotRReg: 0.0034, OV: 0.8622, AltV: 0.8800, CorV: 0.8356, TopV: 0.8567, BotRV: 0.8552, AllV: 0.8800 +[2026-03-20T19:09:00.430383Z] Loop 7360: Reg: 0.0018, AltReg: 0.0030, CorReg: 0.0000, TopReg: 0.0050, AllReg: 0.0030, BotRReg: 0.0053, OV: 0.8618, AltV: 0.8793, CorV: 0.8356, TopV: 0.8536, BotRV: 0.8533, AllV: 0.8793 +[2026-03-20T19:09:09.027647Z] Loop 7370: Reg: 0.0012, AltReg: 0.0020, CorReg: 0.0000, TopReg: 0.0024, AllReg: 0.0020, BotRReg: 0.0030, OV: 0.8624, AltV: 0.8802, CorV: 0.8356, TopV: 0.8563, BotRV: 0.8557, AllV: 0.8802 +[2026-03-20T19:09:17.622930Z] Loop 7380: Reg: 0.0008, AltReg: 0.0013, CorReg: 0.0000, TopReg: 0.0009, AllReg: 0.0014, BotRReg: 0.0024, OV: 0.8628, AltV: 0.8809, CorV: 0.8356, TopV: 0.8578, BotRV: 0.8562, AllV: 0.8809 +[2026-03-20T19:09:26.217382Z] Loop 7390: Reg: 0.0007, AltReg: 0.0011, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0011, BotRReg: 0.0023, OV: 0.8629, AltV: 0.8811, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8564, AllV: 0.8811 +[2026-03-20T19:09:34.812371Z] Loop 7400: Reg: 0.0020, AltReg: 0.0031, CorReg: 0.0004, TopReg: 0.0039, AllReg: 0.0031, BotRReg: 0.0023, OV: 0.8616, AltV: 0.8791, CorV: 0.8353, TopV: 0.8548, BotRV: 0.8563, AllV: 0.8791 +[2026-03-20T19:09:43.408035Z] Loop 7410: Reg: 0.0021, AltReg: 0.0033, CorReg: 0.0003, TopReg: 0.0142, AllReg: 0.0033, BotRReg: 0.0024, OV: 0.8615, AltV: 0.8790, CorV: 0.8354, TopV: 0.8445, BotRV: 0.8562, AllV: 0.8790 +[2026-03-20T19:09:52.003512Z] Loop 7420: Reg: 0.0010, AltReg: 0.0017, CorReg: 0.0001, TopReg: 0.0041, AllReg: 0.0017, BotRReg: 0.0029, OV: 0.8625, AltV: 0.8806, CorV: 0.8355, TopV: 0.8546, BotRV: 0.8558, AllV: 0.8806 +[2026-03-20T19:10:00.599578Z] Loop 7430: Reg: 0.0012, AltReg: 0.0018, CorReg: 0.0003, TopReg: 0.0016, AllReg: 0.0018, BotRReg: 0.0052, OV: 0.8624, AltV: 0.8804, CorV: 0.8353, TopV: 0.8570, BotRV: 0.8534, AllV: 0.8804 +[2026-03-20T19:10:09.204034Z] Loop 7440: Reg: 0.0013, AltReg: 0.0021, CorReg: 0.0001, TopReg: 0.0005, AllReg: 0.0022, BotRReg: 0.0078, OV: 0.8623, AltV: 0.8801, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8508, AllV: 0.8801 +[2026-03-20T19:10:17.805023Z] Loop 7450: Reg: 0.0010, AltReg: 0.0015, CorReg: 0.0001, TopReg: 0.0015, AllReg: 0.0015, BotRReg: 0.0048, OV: 0.8626, AltV: 0.8807, CorV: 0.8355, TopV: 0.8571, BotRV: 0.8538, AllV: 0.8807 +[2026-03-20T19:10:26.406688Z] Loop 7460: Reg: 0.0006, AltReg: 0.0009, CorReg: 0.0000, TopReg: 0.0010, AllReg: 0.0009, BotRReg: 0.0017, OV: 0.8630, AltV: 0.8813, CorV: 0.8356, TopV: 0.8576, BotRV: 0.8570, AllV: 0.8813 +[2026-03-20T19:10:35.012012Z] Loop 7470: Reg: 0.0009, AltReg: 0.0014, CorReg: 0.0001, TopReg: 0.0018, AllReg: 0.0015, BotRReg: 0.0009, OV: 0.8627, AltV: 0.8808, CorV: 0.8356, TopV: 0.8569, BotRV: 0.8578, AllV: 0.8808 +[2026-03-20T19:10:43.609556Z] Loop 7480: Reg: 0.0010, AltReg: 0.0016, CorReg: 0.0002, TopReg: 0.0009, AllReg: 0.0016, BotRReg: 0.0011, OV: 0.8626, AltV: 0.8807, CorV: 0.8355, TopV: 0.8577, BotRV: 0.8576, AllV: 0.8807 +[2026-03-20T19:10:52.205065Z] Loop 7490: Reg: 0.0019, AltReg: 0.0030, CorReg: 0.0004, TopReg: 0.0031, AllReg: 0.0030, BotRReg: 0.0012, OV: 0.8617, AltV: 0.8792, CorV: 0.8353, TopV: 0.8555, BotRV: 0.8574, AllV: 0.8792 +[2026-03-20T19:11:00.804572Z] Loop 7500: Reg: 0.0015, AltReg: 0.0023, CorReg: 0.0003, TopReg: 0.0041, AllReg: 0.0024, BotRReg: 0.0015, OV: 0.8621, AltV: 0.8799, CorV: 0.8353, TopV: 0.8545, BotRV: 0.8571, AllV: 0.8799 +[2026-03-20T19:11:09.402704Z] Loop 7510: Reg: 0.0030, AltReg: 0.0046, CorReg: 0.0007, TopReg: 0.0062, AllReg: 0.0046, BotRReg: 0.0031, OV: 0.8606, AltV: 0.8777, CorV: 0.8349, TopV: 0.8524, BotRV: 0.8556, AllV: 0.8777 +[2026-03-20T19:11:17.997805Z] Loop 7520: Reg: 0.0016, AltReg: 0.0026, CorReg: 0.0001, TopReg: 0.0063, AllReg: 0.0026, BotRReg: 0.0023, OV: 0.8620, AltV: 0.8796, CorV: 0.8355, TopV: 0.8523, BotRV: 0.8563, AllV: 0.8796 +[2026-03-20T19:11:26.590941Z] Loop 7530: Reg: 0.0018, AltReg: 0.0029, CorReg: 0.0000, TopReg: 0.0079, AllReg: 0.0029, BotRReg: 0.0044, OV: 0.8618, AltV: 0.8793, CorV: 0.8356, TopV: 0.8508, BotRV: 0.8542, AllV: 0.8793 +[2026-03-20T19:11:35.185894Z] Loop 7540: Reg: 0.0013, AltReg: 0.0020, CorReg: 0.0002, TopReg: 0.0016, AllReg: 0.0020, BotRReg: 0.0016, OV: 0.8623, AltV: 0.8803, CorV: 0.8354, TopV: 0.8570, BotRV: 0.8570, AllV: 0.8803 +[2026-03-20T19:11:43.785864Z] Loop 7550: Reg: 0.0023, AltReg: 0.0038, CorReg: 0.0002, TopReg: 0.0041, AllReg: 0.0038, BotRReg: 0.0007, OV: 0.8612, AltV: 0.8784, CorV: 0.8355, TopV: 0.8546, BotRV: 0.8579, AllV: 0.8784 +[2026-03-20T19:11:52.391603Z] Loop 7560: Reg: 0.0008, AltReg: 0.0013, CorReg: 0.0002, TopReg: 0.0012, AllReg: 0.0013, BotRReg: 0.0017, OV: 0.8627, AltV: 0.8810, CorV: 0.8354, TopV: 0.8574, BotRV: 0.8569, AllV: 0.8810 +[2026-03-20T19:12:00.994439Z] Loop 7570: Reg: 0.0023, AltReg: 0.0035, CorReg: 0.0005, TopReg: 0.0040, AllReg: 0.0035, BotRReg: 0.0045, OV: 0.8613, AltV: 0.8787, CorV: 0.8351, TopV: 0.8547, BotRV: 0.8542, AllV: 0.8788 +[2026-03-20T19:12:09.593609Z] Loop 7580: Reg: 0.0011, AltReg: 0.0018, CorReg: 0.0000, TopReg: 0.0023, AllReg: 0.0018, BotRReg: 0.0016, OV: 0.8625, AltV: 0.8804, CorV: 0.8356, TopV: 0.8563, BotRV: 0.8570, AllV: 0.8805 +[2026-03-20T19:12:18.187513Z] Loop 7590: Reg: 0.0007, AltReg: 0.0012, CorReg: 0.0000, TopReg: 0.0017, AllReg: 0.0012, BotRReg: 0.0014, OV: 0.8629, AltV: 0.8811, CorV: 0.8356, TopV: 0.8569, BotRV: 0.8572, AllV: 0.8811 +[2026-03-20T19:12:26.784249Z] Loop 7600: Reg: 0.0011, AltReg: 0.0019, CorReg: 0.0000, TopReg: 0.0012, AllReg: 0.0019, BotRReg: 0.0073, OV: 0.8625, AltV: 0.8803, CorV: 0.8356, TopV: 0.8574, BotRV: 0.8513, AllV: 0.8804 +[2026-03-20T19:12:35.385029Z] Loop 7610: Reg: 0.0015, AltReg: 0.0018, CorReg: 0.0012, TopReg: 0.0014, AllReg: 0.0018, BotRReg: 0.0027, OV: 0.8620, AltV: 0.8805, CorV: 0.8344, TopV: 0.8572, BotRV: 0.8560, AllV: 0.8805 +[2026-03-20T19:12:43.976877Z] Loop 7620: Reg: 0.0009, AltReg: 0.0014, CorReg: 0.0002, TopReg: 0.0010, AllReg: 0.0014, BotRReg: 0.0028, OV: 0.8627, AltV: 0.8808, CorV: 0.8355, TopV: 0.8576, BotRV: 0.8558, AllV: 0.8808 +[2026-03-20T19:12:52.571653Z] Loop 7630: Reg: 0.0007, AltReg: 0.0012, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0013, BotRReg: 0.0031, OV: 0.8628, AltV: 0.8810, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8555, AllV: 0.8810 +[2026-03-20T19:13:01.168985Z] Loop 7640: Reg: 0.0012, AltReg: 0.0020, CorReg: 0.0000, TopReg: 0.0018, AllReg: 0.0021, BotRReg: 0.0022, OV: 0.8623, AltV: 0.8802, CorV: 0.8356, TopV: 0.8569, BotRV: 0.8564, AllV: 0.8802 +[2026-03-20T19:13:09.773047Z] Loop 7650: Reg: 0.0036, AltReg: 0.0053, CorReg: 0.0009, TopReg: 0.0070, AllReg: 0.0054, BotRReg: 0.0019, OV: 0.8600, AltV: 0.8769, CorV: 0.8347, TopV: 0.8516, BotRV: 0.8567, AllV: 0.8769 +[2026-03-20T19:13:18.368305Z] Loop 7660: Reg: 0.0008, AltReg: 0.0011, CorReg: 0.0002, TopReg: 0.0008, AllReg: 0.0012, BotRReg: 0.0023, OV: 0.8628, AltV: 0.8811, CorV: 0.8355, TopV: 0.8578, BotRV: 0.8564, AllV: 0.8811 +[2026-03-20T19:13:26.965569Z] Loop 7670: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0000, TopReg: 0.0019, AllReg: 0.0011, BotRReg: 0.0014, OV: 0.8630, AltV: 0.8812, CorV: 0.8356, TopV: 0.8567, BotRV: 0.8572, AllV: 0.8812 +[2026-03-20T19:13:35.566701Z] Loop 7680: Reg: 0.0009, AltReg: 0.0015, CorReg: 0.0000, TopReg: 0.0036, AllReg: 0.0015, BotRReg: 0.0005, OV: 0.8627, AltV: 0.8807, CorV: 0.8356, TopV: 0.8551, BotRV: 0.8581, AllV: 0.8807 +[2026-03-20T19:13:44.173698Z] Loop 7690: Reg: 0.0029, AltReg: 0.0049, CorReg: 0.0001, TopReg: 0.0088, AllReg: 0.0049, BotRReg: 0.0093, OV: 0.8606, AltV: 0.8773, CorV: 0.8356, TopV: 0.8498, BotRV: 0.8493, AllV: 0.8774 +[2026-03-20T19:13:52.771475Z] Loop 7700: Reg: 0.0008, AltReg: 0.0013, CorReg: 0.0000, TopReg: 0.0031, AllReg: 0.0013, BotRReg: 0.0008, OV: 0.8628, AltV: 0.8809, CorV: 0.8356, TopV: 0.8556, BotRV: 0.8579, AllV: 0.8810 +[2026-03-20T19:14:01.371053Z] Loop 7710: Reg: 0.0007, AltReg: 0.0012, CorReg: 0.0000, TopReg: 0.0017, AllReg: 0.0012, BotRReg: 0.0014, OV: 0.8629, AltV: 0.8811, CorV: 0.8356, TopV: 0.8569, BotRV: 0.8573, AllV: 0.8811 +[2026-03-20T19:14:09.971813Z] Loop 7720: Reg: 0.0006, AltReg: 0.0009, CorReg: 0.0000, TopReg: 0.0008, AllReg: 0.0009, BotRReg: 0.0014, OV: 0.8630, AltV: 0.8813, CorV: 0.8356, TopV: 0.8578, BotRV: 0.8572, AllV: 0.8813 +[2026-03-20T19:14:18.571113Z] Loop 7730: Reg: 0.0022, AltReg: 0.0032, CorReg: 0.0007, TopReg: 0.0033, AllReg: 0.0032, BotRReg: 0.0042, OV: 0.8614, AltV: 0.8790, CorV: 0.8349, TopV: 0.8553, BotRV: 0.8544, AllV: 0.8791 +[2026-03-20T19:14:27.170008Z] Loop 7740: Reg: 0.0096, AltReg: 0.0150, CorReg: 0.0015, TopReg: 0.0264, AllReg: 0.0151, BotRReg: 0.0225, OV: 0.8540, AltV: 0.8672, CorV: 0.8341, TopV: 0.8322, BotRV: 0.8361, AllV: 0.8672 +[2026-03-20T19:14:35.772671Z] Loop 7750: Reg: 0.0013, AltReg: 0.0018, CorReg: 0.0005, TopReg: 0.0018, AllReg: 0.0018, BotRReg: 0.0023, OV: 0.8623, AltV: 0.8804, CorV: 0.8352, TopV: 0.8568, BotRV: 0.8563, AllV: 0.8804 +[2026-03-20T19:14:44.368821Z] Loop 7760: Reg: 0.0025, AltReg: 0.0041, CorReg: 0.0000, TopReg: 0.0047, AllReg: 0.0041, BotRReg: 0.0066, OV: 0.8611, AltV: 0.8781, CorV: 0.8356, TopV: 0.8540, BotRV: 0.8520, AllV: 0.8781 +[2026-03-20T19:14:52.961153Z] Loop 7770: Reg: 0.0024, AltReg: 0.0039, CorReg: 0.0000, TopReg: 0.0043, AllReg: 0.0040, BotRReg: 0.0067, OV: 0.8612, AltV: 0.8783, CorV: 0.8356, TopV: 0.8543, BotRV: 0.8520, AllV: 0.8783 +[2026-03-20T19:15:01.563903Z] Loop 7780: Reg: 0.0007, AltReg: 0.0011, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0011, BotRReg: 0.0016, OV: 0.8629, AltV: 0.8811, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8571, AllV: 0.8811 +[2026-03-20T19:15:10.166329Z] Loop 7790: Reg: 0.0014, AltReg: 0.0023, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0024, BotRReg: 0.0010, OV: 0.8622, AltV: 0.8799, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8577, AllV: 0.8799 +[2026-03-20T19:15:18.759808Z] Loop 7800: Reg: 0.0025, AltReg: 0.0042, CorReg: 0.0000, TopReg: 0.0042, AllReg: 0.0042, BotRReg: 0.0077, OV: 0.8611, AltV: 0.8781, CorV: 0.8356, TopV: 0.8544, BotRV: 0.8509, AllV: 0.8781 +[2026-03-20T19:15:27.349200Z] Loop 7810: Reg: 0.0018, AltReg: 0.0030, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0030, BotRReg: 0.0074, OV: 0.8618, AltV: 0.8792, CorV: 0.8356, TopV: 0.8580, BotRV: 0.8513, AllV: 0.8792 +[2026-03-20T19:15:35.945053Z] Loop 7820: Reg: 0.0043, AltReg: 0.0060, CorReg: 0.0016, TopReg: 0.0040, AllReg: 0.0060, BotRReg: 0.0045, OV: 0.8593, AltV: 0.8762, CorV: 0.8340, TopV: 0.8546, BotRV: 0.8541, AllV: 0.8762 +[2026-03-20T19:15:44.541858Z] Loop 7830: Reg: 0.0037, AltReg: 0.0055, CorReg: 0.0010, TopReg: 0.0063, AllReg: 0.0055, BotRReg: 0.0074, OV: 0.8598, AltV: 0.8767, CorV: 0.8346, TopV: 0.8523, BotRV: 0.8512, AllV: 0.8767 +[2026-03-20T19:15:53.139528Z] Loop 7840: Reg: 0.0029, AltReg: 0.0049, CorReg: 0.0000, TopReg: 0.0029, AllReg: 0.0049, BotRReg: 0.0092, OV: 0.8607, AltV: 0.8774, CorV: 0.8356, TopV: 0.8557, BotRV: 0.8495, AllV: 0.8774 +[2026-03-20T19:16:01.741019Z] Loop 7850: Reg: 0.0034, AltReg: 0.0057, CorReg: 0.0000, TopReg: 0.0038, AllReg: 0.0057, BotRReg: 0.0098, OV: 0.8602, AltV: 0.8766, CorV: 0.8356, TopV: 0.8548, BotRV: 0.8488, AllV: 0.8766 +[2026-03-20T19:16:10.333267Z] Loop 7860: Reg: 0.0028, AltReg: 0.0045, CorReg: 0.0001, TopReg: 0.0196, AllReg: 0.0045, BotRReg: 0.0040, OV: 0.8608, AltV: 0.8777, CorV: 0.8355, TopV: 0.8390, BotRV: 0.8546, AllV: 0.8777 +[2026-03-20T19:16:18.936032Z] Loop 7870: Reg: 0.0112, AltReg: 0.0187, CorReg: 0.0000, TopReg: 0.0175, AllReg: 0.0188, BotRReg: 0.0441, OV: 0.8523, AltV: 0.8635, CorV: 0.8356, TopV: 0.8411, BotRV: 0.8145, AllV: 0.8635 +[2026-03-20T19:16:27.531476Z] Loop 7880: Reg: 0.0036, AltReg: 0.0046, CorReg: 0.0022, TopReg: 0.0064, AllReg: 0.0046, BotRReg: 0.0046, OV: 0.8600, AltV: 0.8777, CorV: 0.8335, TopV: 0.8522, BotRV: 0.8541, AllV: 0.8777 +[2026-03-20T19:16:36.127994Z] Loop 7890: Reg: 0.0013, AltReg: 0.0021, CorReg: 0.0000, TopReg: 0.0024, AllReg: 0.0021, BotRReg: 0.0010, OV: 0.8623, AltV: 0.8801, CorV: 0.8356, TopV: 0.8562, BotRV: 0.8576, AllV: 0.8802 +[2026-03-20T19:16:44.722979Z] Loop 7900: Reg: 0.0032, AltReg: 0.0053, CorReg: 0.0000, TopReg: 0.0012, AllReg: 0.0056, BotRReg: 0.0009, OV: 0.8604, AltV: 0.8770, CorV: 0.8356, TopV: 0.8575, BotRV: 0.8578, AllV: 0.8766 +[2026-03-20T19:16:53.324683Z] Loop 7910: Reg: 0.0014, AltReg: 0.0024, CorReg: 0.0000, TopReg: 0.0013, AllReg: 0.0024, BotRReg: 0.0008, OV: 0.8622, AltV: 0.8799, CorV: 0.8356, TopV: 0.8573, BotRV: 0.8578, AllV: 0.8798 +[2026-03-20T19:17:01.917438Z] Loop 7920: Reg: 0.0046, AltReg: 0.0076, CorReg: 0.0000, TopReg: 0.0032, AllReg: 0.0077, BotRReg: 0.0220, OV: 0.8590, AltV: 0.8746, CorV: 0.8356, TopV: 0.8554, BotRV: 0.8366, AllV: 0.8745 +[2026-03-20T19:17:10.508689Z] Loop 7930: Reg: 0.0019, AltReg: 0.0031, CorReg: 0.0000, TopReg: 0.0141, AllReg: 0.0031, BotRReg: 0.0020, OV: 0.8617, AltV: 0.8791, CorV: 0.8356, TopV: 0.8445, BotRV: 0.8566, AllV: 0.8791 +[2026-03-20T19:17:19.099288Z] Loop 7940: Reg: 0.0013, AltReg: 0.0021, CorReg: 0.0000, TopReg: 0.0065, AllReg: 0.0021, BotRReg: 0.0020, OV: 0.8623, AltV: 0.8801, CorV: 0.8356, TopV: 0.8521, BotRV: 0.8566, AllV: 0.8801 +[2026-03-20T19:17:27.695564Z] Loop 7950: Reg: 0.0025, AltReg: 0.0042, CorReg: 0.0001, TopReg: 0.0018, AllReg: 0.0042, BotRReg: 0.0141, OV: 0.8611, AltV: 0.8780, CorV: 0.8356, TopV: 0.8568, BotRV: 0.8445, AllV: 0.8781 +[2026-03-20T19:17:36.289264Z] Loop 7960: Reg: 0.0041, AltReg: 0.0050, CorReg: 0.0028, TopReg: 0.0017, AllReg: 0.0051, BotRReg: 0.0119, OV: 0.8595, AltV: 0.8772, CorV: 0.8329, TopV: 0.8569, BotRV: 0.8467, AllV: 0.8772 +[2026-03-20T19:17:44.895093Z] Loop 7970: Reg: 0.0016, AltReg: 0.0026, CorReg: 0.0000, TopReg: 0.0006, AllReg: 0.0026, BotRReg: 0.0104, OV: 0.8620, AltV: 0.8796, CorV: 0.8356, TopV: 0.8580, BotRV: 0.8483, AllV: 0.8797 +[2026-03-20T19:17:53.500279Z] Loop 7980: Reg: 0.0026, AltReg: 0.0043, CorReg: 0.0000, TopReg: 0.0077, AllReg: 0.0043, BotRReg: 0.0091, OV: 0.8610, AltV: 0.8779, CorV: 0.8356, TopV: 0.8509, BotRV: 0.8495, AllV: 0.8780 +[2026-03-20T19:18:02.094373Z] Loop 7990: Reg: 0.0007, AltReg: 0.0011, CorReg: 0.0001, TopReg: 0.0004, AllReg: 0.0012, BotRReg: 0.0017, OV: 0.8629, AltV: 0.8811, CorV: 0.8355, TopV: 0.8582, BotRV: 0.8570, AllV: 0.8811 +[2026-03-20T19:18:10.690144Z] Loop 8000: Reg: 0.0028, AltReg: 0.0042, CorReg: 0.0006, TopReg: 0.0015, AllReg: 0.0042, BotRReg: 0.0010, OV: 0.8608, AltV: 0.8780, CorV: 0.8350, TopV: 0.8571, BotRV: 0.8577, AllV: 0.8780 +[2026-03-20T19:18:19.284874Z] Loop 8010: Reg: 0.0014, AltReg: 0.0024, CorReg: 0.0000, TopReg: 0.0019, AllReg: 0.0024, BotRReg: 0.0023, OV: 0.8621, AltV: 0.8798, CorV: 0.8356, TopV: 0.8567, BotRV: 0.8563, AllV: 0.8799 +[2026-03-20T19:18:27.878237Z] Loop 8020: Reg: 0.0023, AltReg: 0.0038, CorReg: 0.0000, TopReg: 0.0045, AllReg: 0.0038, BotRReg: 0.0062, OV: 0.8613, AltV: 0.8784, CorV: 0.8356, TopV: 0.8541, BotRV: 0.8525, AllV: 0.8784 +[2026-03-20T19:18:36.473260Z] Loop 8030: Reg: 0.0068, AltReg: 0.0113, CorReg: 0.0001, TopReg: 0.0283, AllReg: 0.0113, BotRReg: 0.0121, OV: 0.8568, AltV: 0.8709, CorV: 0.8356, TopV: 0.8303, BotRV: 0.8465, AllV: 0.8709 +[2026-03-20T19:18:45.064974Z] Loop 8040: Reg: 0.0032, AltReg: 0.0037, CorReg: 0.0025, TopReg: 0.0053, AllReg: 0.0037, BotRReg: 0.0059, OV: 0.8604, AltV: 0.8785, CorV: 0.8331, TopV: 0.8533, BotRV: 0.8527, AllV: 0.8785 +[2026-03-20T19:18:53.657861Z] Loop 8050: Reg: 0.0077, AltReg: 0.0125, CorReg: 0.0006, TopReg: 0.0525, AllReg: 0.0126, BotRReg: 0.0011, OV: 0.8558, AltV: 0.8697, CorV: 0.8351, TopV: 0.8061, BotRV: 0.8575, AllV: 0.8697 +[2026-03-20T19:19:02.249528Z] Loop 8060: Reg: 0.0013, AltReg: 0.0022, CorReg: 0.0000, TopReg: 0.0032, AllReg: 0.0022, BotRReg: 0.0039, OV: 0.8623, AltV: 0.8800, CorV: 0.8356, TopV: 0.8554, BotRV: 0.8547, AllV: 0.8800 +[2026-03-20T19:19:10.827916Z] Loop 8070: Reg: 0.0021, AltReg: 0.0034, CorReg: 0.0000, TopReg: 0.0034, AllReg: 0.0035, BotRReg: 0.0042, OV: 0.8615, AltV: 0.8788, CorV: 0.8356, TopV: 0.8552, BotRV: 0.8544, AllV: 0.8788 +[2026-03-20T19:19:19.408330Z] Loop 8080: Reg: 0.0010, AltReg: 0.0016, CorReg: 0.0000, TopReg: 0.0046, AllReg: 0.0016, BotRReg: 0.0027, OV: 0.8626, AltV: 0.8806, CorV: 0.8356, TopV: 0.8540, BotRV: 0.8559, AllV: 0.8806 +[2026-03-20T19:19:27.988010Z] Loop 8090: Reg: 0.0033, AltReg: 0.0055, CorReg: 0.0000, TopReg: 0.0226, AllReg: 0.0055, BotRReg: 0.0078, OV: 0.8603, AltV: 0.8767, CorV: 0.8356, TopV: 0.8360, BotRV: 0.8508, AllV: 0.8767 +[2026-03-20T19:19:36.565632Z] Loop 8100: Reg: 0.0028, AltReg: 0.0046, CorReg: 0.0002, TopReg: 0.0030, AllReg: 0.0046, BotRReg: 0.0178, OV: 0.8608, AltV: 0.8777, CorV: 0.8355, TopV: 0.8556, BotRV: 0.8409, AllV: 0.8777 +[2026-03-20T19:19:45.148143Z] Loop 8110: Reg: 0.0013, AltReg: 0.0017, CorReg: 0.0006, TopReg: 0.0012, AllReg: 0.0017, BotRReg: 0.0036, OV: 0.8623, AltV: 0.8805, CorV: 0.8350, TopV: 0.8574, BotRV: 0.8550, AllV: 0.8805 +[2026-03-20T19:19:53.733228Z] Loop 8120: Reg: 0.0027, AltReg: 0.0031, CorReg: 0.0021, TopReg: 0.0032, AllReg: 0.0032, BotRReg: 0.0063, OV: 0.8609, AltV: 0.8791, CorV: 0.8335, TopV: 0.8554, BotRV: 0.8523, AllV: 0.8791 +[2026-03-20T19:20:02.316052Z] Loop 8130: Reg: 0.0025, AltReg: 0.0034, CorReg: 0.0013, TopReg: 0.0036, AllReg: 0.0034, BotRReg: 0.0081, OV: 0.8610, AltV: 0.8788, CorV: 0.8343, TopV: 0.8550, BotRV: 0.8505, AllV: 0.8788 +[2026-03-20T19:20:10.892072Z] Loop 8140: Reg: 0.0013, AltReg: 0.0022, CorReg: 0.0000, TopReg: 0.0025, AllReg: 0.0022, BotRReg: 0.0050, OV: 0.8623, AltV: 0.8801, CorV: 0.8356, TopV: 0.8562, BotRV: 0.8536, AllV: 0.8801 +[2026-03-20T19:20:19.471174Z] Loop 8150: Reg: 0.0048, AltReg: 0.0079, CorReg: 0.0000, TopReg: 0.0032, AllReg: 0.0081, BotRReg: 0.0251, OV: 0.8588, AltV: 0.8743, CorV: 0.8356, TopV: 0.8554, BotRV: 0.8335, AllV: 0.8742 +[2026-03-20T19:20:28.050435Z] Loop 8160: Reg: 0.0011, AltReg: 0.0019, CorReg: 0.0000, TopReg: 0.0034, AllReg: 0.0019, BotRReg: 0.0028, OV: 0.8624, AltV: 0.8803, CorV: 0.8356, TopV: 0.8552, BotRV: 0.8558, AllV: 0.8803 +[2026-03-20T19:20:36.635583Z] Loop 8170: Reg: 0.0014, AltReg: 0.0024, CorReg: 0.0000, TopReg: 0.0038, AllReg: 0.0024, BotRReg: 0.0048, OV: 0.8622, AltV: 0.8799, CorV: 0.8356, TopV: 0.8548, BotRV: 0.8538, AllV: 0.8799 +[2026-03-20T19:20:45.214958Z] Loop 8180: Reg: 0.0023, AltReg: 0.0038, CorReg: 0.0000, TopReg: 0.0027, AllReg: 0.0039, BotRReg: 0.0135, OV: 0.8613, AltV: 0.8784, CorV: 0.8356, TopV: 0.8559, BotRV: 0.8451, AllV: 0.8784 +[2026-03-20T19:20:53.797949Z] Loop 8190: Reg: 0.0020, AltReg: 0.0032, CorReg: 0.0001, TopReg: 0.0013, AllReg: 0.0032, BotRReg: 0.0128, OV: 0.8616, AltV: 0.8790, CorV: 0.8355, TopV: 0.8574, BotRV: 0.8459, AllV: 0.8790 +[2026-03-20T19:21:02.380940Z] Loop 8200: Reg: 0.0040, AltReg: 0.0039, CorReg: 0.0042, TopReg: 0.0063, AllReg: 0.0039, BotRReg: 0.0068, OV: 0.8596, AltV: 0.8783, CorV: 0.8315, TopV: 0.8523, BotRV: 0.8518, AllV: 0.8783 +[2026-03-20T19:21:10.965328Z] Loop 8210: Reg: 0.0014, AltReg: 0.0020, CorReg: 0.0004, TopReg: 0.0009, AllReg: 0.0020, BotRReg: 0.0034, OV: 0.8622, AltV: 0.8802, CorV: 0.8353, TopV: 0.8577, BotRV: 0.8552, AllV: 0.8802 +[2026-03-20T19:21:19.554566Z] Loop 8220: Reg: 0.0025, AltReg: 0.0042, CorReg: 0.0001, TopReg: 0.0040, AllReg: 0.0042, BotRReg: 0.0079, OV: 0.8611, AltV: 0.8781, CorV: 0.8356, TopV: 0.8546, BotRV: 0.8507, AllV: 0.8781 +[2026-03-20T19:21:28.143458Z] Loop 8230: Reg: 0.0028, AltReg: 0.0045, CorReg: 0.0001, TopReg: 0.0064, AllReg: 0.0045, BotRReg: 0.0059, OV: 0.8608, AltV: 0.8777, CorV: 0.8355, TopV: 0.8522, BotRV: 0.8527, AllV: 0.8777 +[2026-03-20T19:21:36.723865Z] Loop 8240: Reg: 0.0009, AltReg: 0.0015, CorReg: 0.0001, TopReg: 0.0011, AllReg: 0.0015, BotRReg: 0.0022, OV: 0.8626, AltV: 0.8807, CorV: 0.8356, TopV: 0.8575, BotRV: 0.8564, AllV: 0.8807 +[2026-03-20T19:21:45.300605Z] Loop 8250: Reg: 0.0045, AltReg: 0.0069, CorReg: 0.0009, TopReg: 0.0089, AllReg: 0.0070, BotRReg: 0.0013, OV: 0.8591, AltV: 0.8753, CorV: 0.8347, TopV: 0.8497, BotRV: 0.8573, AllV: 0.8752 +[2026-03-20T19:21:53.882304Z] Loop 8260: Reg: 0.0009, AltReg: 0.0015, CorReg: 0.0000, TopReg: 0.0008, AllReg: 0.0015, BotRReg: 0.0026, OV: 0.8627, AltV: 0.8808, CorV: 0.8356, TopV: 0.8578, BotRV: 0.8561, AllV: 0.8808 +[2026-03-20T19:22:02.464470Z] Loop 8270: Reg: 0.0014, AltReg: 0.0023, CorReg: 0.0000, TopReg: 0.0088, AllReg: 0.0024, BotRReg: 0.0022, OV: 0.8622, AltV: 0.8799, CorV: 0.8356, TopV: 0.8498, BotRV: 0.8564, AllV: 0.8799 +[2026-03-20T19:22:11.044349Z] Loop 8280: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0000, TopReg: 0.0011, AllReg: 0.0010, BotRReg: 0.0017, OV: 0.8630, AltV: 0.8812, CorV: 0.8356, TopV: 0.8576, BotRV: 0.8570, AllV: 0.8812 +[2026-03-20T19:22:19.623893Z] Loop 8290: Reg: 0.0074, AltReg: 0.0123, CorReg: 0.0000, TopReg: 0.0087, AllReg: 0.0125, BotRReg: 0.0286, OV: 0.8562, AltV: 0.8699, CorV: 0.8356, TopV: 0.8499, BotRV: 0.8300, AllV: 0.8698 +[2026-03-20T19:22:28.200121Z] Loop 8300: Reg: 0.0007, AltReg: 0.0012, CorReg: 0.0000, TopReg: 0.0008, AllReg: 0.0012, BotRReg: 0.0019, OV: 0.8628, AltV: 0.8810, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8567, AllV: 0.8810 +[2026-03-20T19:22:36.781795Z] Loop 8310: Reg: 0.0012, AltReg: 0.0020, CorReg: 0.0000, TopReg: 0.0018, AllReg: 0.0020, BotRReg: 0.0041, OV: 0.8624, AltV: 0.8802, CorV: 0.8356, TopV: 0.8568, BotRV: 0.8545, AllV: 0.8802 +[2026-03-20T19:22:45.360072Z] Loop 8320: Reg: 0.0006, AltReg: 0.0009, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0009, BotRReg: 0.0011, OV: 0.8630, AltV: 0.8813, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8575, AllV: 0.8813 +[2026-03-20T19:22:53.943148Z] Loop 8330: Reg: 0.0009, AltReg: 0.0014, CorReg: 0.0000, TopReg: 0.0076, AllReg: 0.0014, BotRReg: 0.0004, OV: 0.8627, AltV: 0.8808, CorV: 0.8356, TopV: 0.8510, BotRV: 0.8582, AllV: 0.8808 +[2026-03-20T19:23:02.521954Z] Loop 8340: Reg: 0.0011, AltReg: 0.0018, CorReg: 0.0000, TopReg: 0.0015, AllReg: 0.0018, BotRReg: 0.0017, OV: 0.8625, AltV: 0.8804, CorV: 0.8356, TopV: 0.8571, BotRV: 0.8569, AllV: 0.8804 +[2026-03-20T19:23:11.096507Z] Loop 8350: Reg: 0.0012, AltReg: 0.0021, CorReg: 0.0000, TopReg: 0.0038, AllReg: 0.0021, BotRReg: 0.0025, OV: 0.8623, AltV: 0.8801, CorV: 0.8356, TopV: 0.8548, BotRV: 0.8561, AllV: 0.8802 +[2026-03-20T19:23:19.678897Z] Loop 8360: Reg: 0.0004, AltReg: 0.0007, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0007, BotRReg: 0.0017, OV: 0.8632, AltV: 0.8815, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8569, AllV: 0.8816 +[2026-03-20T19:23:28.263643Z] Loop 8370: Reg: 0.0014, AltReg: 0.0024, CorReg: 0.0001, TopReg: 0.0016, AllReg: 0.0024, BotRReg: 0.0039, OV: 0.8621, AltV: 0.8798, CorV: 0.8356, TopV: 0.8570, BotRV: 0.8547, AllV: 0.8799 +[2026-03-20T19:23:36.840529Z] Loop 8380: Reg: 0.0009, AltReg: 0.0015, CorReg: 0.0002, TopReg: 0.0016, AllReg: 0.0015, BotRReg: 0.0019, OV: 0.8626, AltV: 0.8807, CorV: 0.8355, TopV: 0.8570, BotRV: 0.8567, AllV: 0.8808 +[2026-03-20T19:23:45.421267Z] Loop 8390: Reg: 0.0006, AltReg: 0.0009, CorReg: 0.0003, TopReg: 0.0008, AllReg: 0.0009, BotRReg: 0.0019, OV: 0.8629, AltV: 0.8813, CorV: 0.8353, TopV: 0.8578, BotRV: 0.8567, AllV: 0.8813 +[2026-03-20T19:23:54.012942Z] Loop 8400: Reg: 0.0004, AltReg: 0.0007, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0007, BotRReg: 0.0016, OV: 0.8632, AltV: 0.8815, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8571, AllV: 0.8815 +[2026-03-20T19:24:02.597474Z] Loop 8410: Reg: 0.0011, AltReg: 0.0018, CorReg: 0.0001, TopReg: 0.0038, AllReg: 0.0018, BotRReg: 0.0015, OV: 0.8625, AltV: 0.8804, CorV: 0.8356, TopV: 0.8548, BotRV: 0.8572, AllV: 0.8804 +[2026-03-20T19:24:11.176805Z] Loop 8420: Reg: 0.0013, AltReg: 0.0020, CorReg: 0.0001, TopReg: 0.0038, AllReg: 0.0020, BotRReg: 0.0008, OV: 0.8623, AltV: 0.8802, CorV: 0.8356, TopV: 0.8549, BotRV: 0.8578, AllV: 0.8802 +[2026-03-20T19:24:19.766692Z] Loop 8430: Reg: 0.0005, AltReg: 0.0008, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0008, BotRReg: 0.0005, OV: 0.8631, AltV: 0.8815, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8581, AllV: 0.8815 +[2026-03-20T19:24:28.352085Z] Loop 8440: Reg: 0.0005, AltReg: 0.0008, CorReg: 0.0000, TopReg: 0.0011, AllReg: 0.0008, BotRReg: 0.0011, OV: 0.8631, AltV: 0.8815, CorV: 0.8356, TopV: 0.8575, BotRV: 0.8575, AllV: 0.8815 +[2026-03-20T19:24:36.937013Z] Loop 8450: Reg: 0.0005, AltReg: 0.0009, CorReg: 0.0000, TopReg: 0.0016, AllReg: 0.0009, BotRReg: 0.0012, OV: 0.8630, AltV: 0.8813, CorV: 0.8356, TopV: 0.8570, BotRV: 0.8575, AllV: 0.8813 +[2026-03-20T19:24:45.521405Z] Loop 8460: Reg: 0.0008, AltReg: 0.0013, CorReg: 0.0000, TopReg: 0.0032, AllReg: 0.0013, BotRReg: 0.0009, OV: 0.8628, AltV: 0.8809, CorV: 0.8356, TopV: 0.8554, BotRV: 0.8577, AllV: 0.8809 +[2026-03-20T19:24:54.103113Z] Loop 8470: Reg: 0.0012, AltReg: 0.0020, CorReg: 0.0000, TopReg: 0.0020, AllReg: 0.0020, BotRReg: 0.0025, OV: 0.8624, AltV: 0.8802, CorV: 0.8356, TopV: 0.8566, BotRV: 0.8561, AllV: 0.8802 +[2026-03-20T19:25:02.689083Z] Loop 8480: Reg: 0.0014, AltReg: 0.0023, CorReg: 0.0000, TopReg: 0.0006, AllReg: 0.0023, BotRReg: 0.0009, OV: 0.8622, AltV: 0.8799, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8577, AllV: 0.8800 +[2026-03-20T19:25:11.271300Z] Loop 8490: Reg: 0.0005, AltReg: 0.0009, CorReg: 0.0000, TopReg: 0.0008, AllReg: 0.0009, BotRReg: 0.0006, OV: 0.8631, AltV: 0.8813, CorV: 0.8356, TopV: 0.8578, BotRV: 0.8580, AllV: 0.8814 +[2026-03-20T19:25:19.856990Z] Loop 8500: Reg: 0.0003, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0006, BotRReg: 0.0012, OV: 0.8632, AltV: 0.8817, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8575, AllV: 0.8817 +[2026-03-20T19:25:28.450417Z] Loop 8510: Reg: 0.0004, AltReg: 0.0007, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0007, BotRReg: 0.0017, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8569, AllV: 0.8816 +[2026-03-20T19:25:37.034280Z] Loop 8520: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0006, BotRReg: 0.0015, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8572, AllV: 0.8816 +[2026-03-20T19:25:45.617975Z] Loop 8530: Reg: 0.0012, AltReg: 0.0020, CorReg: 0.0000, TopReg: 0.0008, AllReg: 0.0021, BotRReg: 0.0032, OV: 0.8624, AltV: 0.8802, CorV: 0.8356, TopV: 0.8578, BotRV: 0.8554, AllV: 0.8802 +[2026-03-20T19:25:54.199998Z] Loop 8540: Reg: 0.0003, AltReg: 0.0005, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0005, BotRReg: 0.0010, OV: 0.8633, AltV: 0.8817, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8577, AllV: 0.8817 +[2026-03-20T19:26:02.787211Z] Loop 8550: Reg: 0.0009, AltReg: 0.0015, CorReg: 0.0001, TopReg: 0.0014, AllReg: 0.0016, BotRReg: 0.0009, OV: 0.8626, AltV: 0.8807, CorV: 0.8356, TopV: 0.8572, BotRV: 0.8578, AllV: 0.8807 +[2026-03-20T19:26:11.371898Z] Loop 8560: Reg: 0.0014, AltReg: 0.0024, CorReg: 0.0000, TopReg: 0.0006, AllReg: 0.0024, BotRReg: 0.0050, OV: 0.8622, AltV: 0.8798, CorV: 0.8356, TopV: 0.8580, BotRV: 0.8536, AllV: 0.8799 +[2026-03-20T19:26:19.955305Z] Loop 8570: Reg: 0.0009, AltReg: 0.0015, CorReg: 0.0000, TopReg: 0.0014, AllReg: 0.0015, BotRReg: 0.0027, OV: 0.8627, AltV: 0.8808, CorV: 0.8356, TopV: 0.8573, BotRV: 0.8559, AllV: 0.8808 +[2026-03-20T19:26:28.542766Z] Loop 8580: Reg: 0.0032, AltReg: 0.0054, CorReg: 0.0000, TopReg: 0.0260, AllReg: 0.0054, BotRReg: 0.0039, OV: 0.8603, AltV: 0.8768, CorV: 0.8356, TopV: 0.8326, BotRV: 0.8547, AllV: 0.8768 +[2026-03-20T19:26:37.120021Z] Loop 8590: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0007, BotRReg: 0.0015, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8571, AllV: 0.8816 +[2026-03-20T19:26:45.706890Z] Loop 8600: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0006, BotRReg: 0.0013, OV: 0.8632, AltV: 0.8817, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8573, AllV: 0.8817 +[2026-03-20T19:26:54.289447Z] Loop 8610: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0001, TopReg: 0.0005, AllReg: 0.0006, BotRReg: 0.0008, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8578, AllV: 0.8817 +[2026-03-20T19:27:02.875698Z] Loop 8620: Reg: 0.0007, AltReg: 0.0010, CorReg: 0.0002, TopReg: 0.0009, AllReg: 0.0010, BotRReg: 0.0013, OV: 0.8629, AltV: 0.8812, CorV: 0.8355, TopV: 0.8578, BotRV: 0.8573, AllV: 0.8812 +[2026-03-20T19:27:11.463553Z] Loop 8630: Reg: 0.0011, AltReg: 0.0017, CorReg: 0.0003, TopReg: 0.0012, AllReg: 0.0017, BotRReg: 0.0022, OV: 0.8624, AltV: 0.8805, CorV: 0.8354, TopV: 0.8574, BotRV: 0.8564, AllV: 0.8805 +[2026-03-20T19:27:20.052013Z] Loop 8640: Reg: 0.0013, AltReg: 0.0020, CorReg: 0.0002, TopReg: 0.0015, AllReg: 0.0020, BotRReg: 0.0024, OV: 0.8623, AltV: 0.8803, CorV: 0.8354, TopV: 0.8571, BotRV: 0.8562, AllV: 0.8803 +[2026-03-20T19:27:28.634191Z] Loop 8650: Reg: 0.0004, AltReg: 0.0007, CorReg: 0.0001, TopReg: 0.0007, AllReg: 0.0007, BotRReg: 0.0007, OV: 0.8631, AltV: 0.8815, CorV: 0.8356, TopV: 0.8580, BotRV: 0.8579, AllV: 0.8816 +[2026-03-20T19:27:37.218026Z] Loop 8660: Reg: 0.0002, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0004, BotRReg: 0.0004, OV: 0.8633, AltV: 0.8819, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8582, AllV: 0.8819 +[2026-03-20T19:27:45.803180Z] Loop 8670: Reg: 0.0003, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0004, BotRReg: 0.0010, OV: 0.8633, AltV: 0.8818, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8576, AllV: 0.8818 +[2026-03-20T19:27:54.386459Z] Loop 8680: Reg: 0.0006, AltReg: 0.0009, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0009, BotRReg: 0.0025, OV: 0.8630, AltV: 0.8813, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8562, AllV: 0.8813 +[2026-03-20T19:28:02.971284Z] Loop 8690: Reg: 0.0015, AltReg: 0.0025, CorReg: 0.0000, TopReg: 0.0012, AllReg: 0.0025, BotRReg: 0.0071, OV: 0.8621, AltV: 0.8798, CorV: 0.8356, TopV: 0.8574, BotRV: 0.8515, AllV: 0.8798 +[2026-03-20T19:28:11.545454Z] Loop 8700: Reg: 0.0012, AltReg: 0.0020, CorReg: 0.0000, TopReg: 0.0011, AllReg: 0.0020, BotRReg: 0.0058, OV: 0.8624, AltV: 0.8802, CorV: 0.8356, TopV: 0.8575, BotRV: 0.8529, AllV: 0.8802 +[2026-03-20T19:28:20.123961Z] Loop 8710: Reg: 0.0005, AltReg: 0.0008, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0008, BotRReg: 0.0020, OV: 0.8631, AltV: 0.8814, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8566, AllV: 0.8814 +[2026-03-20T19:28:28.713140Z] Loop 8720: Reg: 0.0010, AltReg: 0.0017, CorReg: 0.0000, TopReg: 0.0006, AllReg: 0.0017, BotRReg: 0.0037, OV: 0.8626, AltV: 0.8805, CorV: 0.8356, TopV: 0.8580, BotRV: 0.8549, AllV: 0.8806 +[2026-03-20T19:28:37.289657Z] Loop 8730: Reg: 0.0009, AltReg: 0.0016, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0016, BotRReg: 0.0034, OV: 0.8626, AltV: 0.8807, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8552, AllV: 0.8807 +[2026-03-20T19:28:45.878505Z] Loop 8740: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0006, BotRReg: 0.0010, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8576, AllV: 0.8816 +[2026-03-20T19:28:54.460412Z] Loop 8750: Reg: 0.0004, AltReg: 0.0007, CorReg: 0.0000, TopReg: 0.0009, AllReg: 0.0007, BotRReg: 0.0003, OV: 0.8631, AltV: 0.8815, CorV: 0.8356, TopV: 0.8577, BotRV: 0.8583, AllV: 0.8815 +[2026-03-20T19:29:03.043780Z] Loop 8760: Reg: 0.0008, AltReg: 0.0013, CorReg: 0.0000, TopReg: 0.0031, AllReg: 0.0013, BotRReg: 0.0004, OV: 0.8628, AltV: 0.8809, CorV: 0.8356, TopV: 0.8556, BotRV: 0.8582, AllV: 0.8810 +[2026-03-20T19:29:11.622841Z] Loop 8770: Reg: 0.0017, AltReg: 0.0029, CorReg: 0.0000, TopReg: 0.0018, AllReg: 0.0029, BotRReg: 0.0086, OV: 0.8619, AltV: 0.8793, CorV: 0.8356, TopV: 0.8568, BotRV: 0.8500, AllV: 0.8793 +[2026-03-20T19:29:20.212914Z] Loop 8780: Reg: 0.0007, AltReg: 0.0012, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0012, BotRReg: 0.0034, OV: 0.8629, AltV: 0.8810, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8553, AllV: 0.8810 +[2026-03-20T19:29:28.806860Z] Loop 8790: Reg: 0.0016, AltReg: 0.0026, CorReg: 0.0000, TopReg: 0.0021, AllReg: 0.0027, BotRReg: 0.0070, OV: 0.8620, AltV: 0.8796, CorV: 0.8356, TopV: 0.8566, BotRV: 0.8516, AllV: 0.8796 +[2026-03-20T19:29:37.396647Z] Loop 8800: Reg: 0.0017, AltReg: 0.0028, CorReg: 0.0000, TopReg: 0.0006, AllReg: 0.0028, BotRReg: 0.0128, OV: 0.8619, AltV: 0.8794, CorV: 0.8356, TopV: 0.8580, BotRV: 0.8458, AllV: 0.8795 +[2026-03-20T19:29:45.982517Z] Loop 8810: Reg: 0.0039, AltReg: 0.0064, CorReg: 0.0000, TopReg: 0.0015, AllReg: 0.0065, BotRReg: 0.0274, OV: 0.8597, AltV: 0.8758, CorV: 0.8356, TopV: 0.8572, BotRV: 0.8312, AllV: 0.8758 +[2026-03-20T19:29:54.562469Z] Loop 8820: Reg: 0.0009, AltReg: 0.0014, CorReg: 0.0000, TopReg: 0.0006, AllReg: 0.0015, BotRReg: 0.0024, OV: 0.8627, AltV: 0.8808, CorV: 0.8356, TopV: 0.8580, BotRV: 0.8562, AllV: 0.8808 +[2026-03-20T19:30:03.145252Z] Loop 8830: Reg: 0.0007, AltReg: 0.0012, CorReg: 0.0000, TopReg: 0.0006, AllReg: 0.0012, BotRReg: 0.0025, OV: 0.8629, AltV: 0.8811, CorV: 0.8356, TopV: 0.8580, BotRV: 0.8561, AllV: 0.8811 +[2026-03-20T19:30:11.729350Z] Loop 8840: Reg: 0.0010, AltReg: 0.0017, CorReg: 0.0001, TopReg: 0.0011, AllReg: 0.0017, BotRReg: 0.0037, OV: 0.8625, AltV: 0.8805, CorV: 0.8356, TopV: 0.8576, BotRV: 0.8549, AllV: 0.8805 +[2026-03-20T19:30:20.309733Z] Loop 8850: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0000, TopReg: 0.0006, AllReg: 0.0010, BotRReg: 0.0026, OV: 0.8630, AltV: 0.8812, CorV: 0.8356, TopV: 0.8580, BotRV: 0.8560, AllV: 0.8812 +[2026-03-20T19:30:28.893859Z] Loop 8860: Reg: 0.0012, AltReg: 0.0020, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0021, BotRReg: 0.0063, OV: 0.8624, AltV: 0.8802, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8523, AllV: 0.8802 +[2026-03-20T19:30:37.474623Z] Loop 8870: Reg: 0.0008, AltReg: 0.0012, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0013, BotRReg: 0.0042, OV: 0.8628, AltV: 0.8810, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8545, AllV: 0.8810 +[2026-03-20T19:30:46.065527Z] Loop 8880: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0001, TopReg: 0.0016, AllReg: 0.0006, BotRReg: 0.0014, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8570, BotRV: 0.8572, AllV: 0.8816 +[2026-03-20T19:30:54.648202Z] Loop 8890: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0006, BotRReg: 0.0014, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8572, AllV: 0.8816 +[2026-03-20T19:31:03.228811Z] Loop 8900: Reg: 0.0007, AltReg: 0.0012, CorReg: 0.0000, TopReg: 0.0011, AllReg: 0.0012, BotRReg: 0.0011, OV: 0.8629, AltV: 0.8811, CorV: 0.8356, TopV: 0.8575, BotRV: 0.8575, AllV: 0.8811 +[2026-03-20T19:31:11.810306Z] Loop 8910: Reg: 0.0018, AltReg: 0.0029, CorReg: 0.0001, TopReg: 0.0064, AllReg: 0.0029, BotRReg: 0.0013, OV: 0.8618, AltV: 0.8793, CorV: 0.8355, TopV: 0.8522, BotRV: 0.8574, AllV: 0.8793 +[2026-03-20T19:31:20.393910Z] Loop 8920: Reg: 0.0005, AltReg: 0.0008, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0009, BotRReg: 0.0017, OV: 0.8631, AltV: 0.8814, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8569, AllV: 0.8814 +[2026-03-20T19:31:28.973659Z] Loop 8930: Reg: 0.0007, AltReg: 0.0012, CorReg: 0.0000, TopReg: 0.0006, AllReg: 0.0012, BotRReg: 0.0020, OV: 0.8629, AltV: 0.8810, CorV: 0.8356, TopV: 0.8580, BotRV: 0.8567, AllV: 0.8810 +[2026-03-20T19:31:37.563639Z] Loop 8940: Reg: 0.0005, AltReg: 0.0008, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0009, BotRReg: 0.0018, OV: 0.8631, AltV: 0.8814, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8568, AllV: 0.8814 +[2026-03-20T19:31:46.148331Z] Loop 8950: Reg: 0.0009, AltReg: 0.0015, CorReg: 0.0001, TopReg: 0.0027, AllReg: 0.0015, BotRReg: 0.0015, OV: 0.8627, AltV: 0.8807, CorV: 0.8356, TopV: 0.8559, BotRV: 0.8571, AllV: 0.8808 +[2026-03-20T19:31:54.733812Z] Loop 8960: Reg: 0.0017, AltReg: 0.0027, CorReg: 0.0000, TopReg: 0.0073, AllReg: 0.0028, BotRReg: 0.0020, OV: 0.8619, AltV: 0.8795, CorV: 0.8356, TopV: 0.8513, BotRV: 0.8566, AllV: 0.8795 +[2026-03-20T19:32:03.313939Z] Loop 8970: Reg: 0.0005, AltReg: 0.0009, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0009, BotRReg: 0.0017, OV: 0.8631, AltV: 0.8813, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8570, AllV: 0.8813 +[2026-03-20T19:32:11.895604Z] Loop 8980: Reg: 0.0012, AltReg: 0.0020, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0020, BotRReg: 0.0037, OV: 0.8624, AltV: 0.8802, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8549, AllV: 0.8802 +[2026-03-20T19:32:20.480212Z] Loop 8990: Reg: 0.0019, AltReg: 0.0031, CorReg: 0.0000, TopReg: 0.0115, AllReg: 0.0031, BotRReg: 0.0018, OV: 0.8617, AltV: 0.8792, CorV: 0.8356, TopV: 0.8471, BotRV: 0.8568, AllV: 0.8792 +[2026-03-20T19:32:29.058241Z] Loop 9000: Reg: 0.0008, AltReg: 0.0013, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0013, BotRReg: 0.0027, OV: 0.8628, AltV: 0.8809, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8559, AllV: 0.8810 +[2026-03-20T19:32:37.644992Z] Loop 9010: Reg: 0.0010, AltReg: 0.0017, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0017, BotRReg: 0.0042, OV: 0.8626, AltV: 0.8805, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8544, AllV: 0.8805 +[2026-03-20T19:32:46.227252Z] Loop 9020: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0010, BotRReg: 0.0036, OV: 0.8630, AltV: 0.8812, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8550, AllV: 0.8813 +[2026-03-20T19:32:54.820959Z] Loop 9030: Reg: 0.0015, AltReg: 0.0025, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0026, BotRReg: 0.0083, OV: 0.8620, AltV: 0.8797, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8504, AllV: 0.8797 +[2026-03-20T19:33:03.404236Z] Loop 9040: Reg: 0.0012, AltReg: 0.0018, CorReg: 0.0003, TopReg: 0.0040, AllReg: 0.0018, BotRReg: 0.0037, OV: 0.8624, AltV: 0.8805, CorV: 0.8353, TopV: 0.8546, BotRV: 0.8550, AllV: 0.8805 +[2026-03-20T19:33:11.985466Z] Loop 9050: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0011, AllReg: 0.0007, BotRReg: 0.0009, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8576, BotRV: 0.8577, AllV: 0.8816 +[2026-03-20T19:33:20.566334Z] Loop 9060: Reg: 0.0014, AltReg: 0.0023, CorReg: 0.0000, TopReg: 0.0015, AllReg: 0.0024, BotRReg: 0.0042, OV: 0.8622, AltV: 0.8799, CorV: 0.8356, TopV: 0.8571, BotRV: 0.8545, AllV: 0.8799 +[2026-03-20T19:33:29.145045Z] Loop 9070: Reg: 0.0044, AltReg: 0.0074, CorReg: 0.0000, TopReg: 0.0188, AllReg: 0.0074, BotRReg: 0.0070, OV: 0.8591, AltV: 0.8748, CorV: 0.8356, TopV: 0.8398, BotRV: 0.8516, AllV: 0.8748 +[2026-03-20T19:33:37.729104Z] Loop 9080: Reg: 0.0033, AltReg: 0.0055, CorReg: 0.0000, TopReg: 0.0127, AllReg: 0.0055, BotRReg: 0.0046, OV: 0.8603, AltV: 0.8767, CorV: 0.8356, TopV: 0.8459, BotRV: 0.8541, AllV: 0.8768 +[2026-03-20T19:33:46.318867Z] Loop 9090: Reg: 0.0012, AltReg: 0.0019, CorReg: 0.0000, TopReg: 0.0011, AllReg: 0.0020, BotRReg: 0.0036, OV: 0.8624, AltV: 0.8803, CorV: 0.8356, TopV: 0.8575, BotRV: 0.8550, AllV: 0.8803 +[2026-03-20T19:33:54.904468Z] Loop 9100: Reg: 0.0008, AltReg: 0.0013, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0014, BotRReg: 0.0034, OV: 0.8628, AltV: 0.8809, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8552, AllV: 0.8809 +[2026-03-20T19:34:03.492844Z] Loop 9110: Reg: 0.0012, AltReg: 0.0018, CorReg: 0.0001, TopReg: 0.0010, AllReg: 0.0018, BotRReg: 0.0038, OV: 0.8624, AltV: 0.8804, CorV: 0.8355, TopV: 0.8576, BotRV: 0.8548, AllV: 0.8804 +[2026-03-20T19:34:12.073369Z] Loop 9120: Reg: 0.0011, AltReg: 0.0019, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0019, BotRReg: 0.0053, OV: 0.8624, AltV: 0.8803, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8533, AllV: 0.8803 +[2026-03-20T19:34:20.654796Z] Loop 9130: Reg: 0.0010, AltReg: 0.0016, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0017, BotRReg: 0.0053, OV: 0.8626, AltV: 0.8806, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8533, AllV: 0.8806 +[2026-03-20T19:34:29.239640Z] Loop 9140: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0001, TopReg: 0.0006, AllReg: 0.0010, BotRReg: 0.0012, OV: 0.8629, AltV: 0.8812, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8574, AllV: 0.8812 +[2026-03-20T19:34:37.822301Z] Loop 9150: Reg: 0.0009, AltReg: 0.0015, CorReg: 0.0001, TopReg: 0.0010, AllReg: 0.0015, BotRReg: 0.0017, OV: 0.8626, AltV: 0.8808, CorV: 0.8355, TopV: 0.8576, BotRV: 0.8570, AllV: 0.8808 +[2026-03-20T19:34:46.403938Z] Loop 9160: Reg: 0.0027, AltReg: 0.0045, CorReg: 0.0000, TopReg: 0.0023, AllReg: 0.0046, BotRReg: 0.0100, OV: 0.8608, AltV: 0.8777, CorV: 0.8356, TopV: 0.8563, BotRV: 0.8486, AllV: 0.8777 +[2026-03-20T19:34:54.984545Z] Loop 9170: Reg: 0.0013, AltReg: 0.0021, CorReg: 0.0001, TopReg: 0.0024, AllReg: 0.0021, BotRReg: 0.0030, OV: 0.8623, AltV: 0.8801, CorV: 0.8355, TopV: 0.8562, BotRV: 0.8557, AllV: 0.8801 +[2026-03-20T19:35:03.575979Z] Loop 9180: Reg: 0.0011, AltReg: 0.0017, CorReg: 0.0002, TopReg: 0.0021, AllReg: 0.0017, BotRReg: 0.0026, OV: 0.8625, AltV: 0.8805, CorV: 0.8355, TopV: 0.8565, BotRV: 0.8560, AllV: 0.8805 +[2026-03-20T19:35:12.158636Z] Loop 9190: Reg: 0.0028, AltReg: 0.0030, CorReg: 0.0023, TopReg: 0.0061, AllReg: 0.0031, BotRReg: 0.0039, OV: 0.8608, AltV: 0.8792, CorV: 0.8333, TopV: 0.8525, BotRV: 0.8547, AllV: 0.8792 +[2026-03-20T19:35:20.741641Z] Loop 9200: Reg: 0.0015, AltReg: 0.0023, CorReg: 0.0003, TopReg: 0.0026, AllReg: 0.0023, BotRReg: 0.0065, OV: 0.8621, AltV: 0.8800, CorV: 0.8353, TopV: 0.8561, BotRV: 0.8521, AllV: 0.8800 +[2026-03-20T19:35:29.322899Z] Loop 9210: Reg: 0.0027, AltReg: 0.0037, CorReg: 0.0011, TopReg: 0.0079, AllReg: 0.0038, BotRReg: 0.0083, OV: 0.8609, AltV: 0.8785, CorV: 0.8345, TopV: 0.8508, BotRV: 0.8503, AllV: 0.8785 +[2026-03-20T19:35:37.902412Z] Loop 9220: Reg: 0.0013, AltReg: 0.0017, CorReg: 0.0007, TopReg: 0.0047, AllReg: 0.0017, BotRReg: 0.0023, OV: 0.8623, AltV: 0.8806, CorV: 0.8349, TopV: 0.8539, BotRV: 0.8563, AllV: 0.8806 +[2026-03-20T19:35:46.481032Z] Loop 9230: Reg: 0.0054, AltReg: 0.0072, CorReg: 0.0027, TopReg: 0.0154, AllReg: 0.0073, BotRReg: 0.0016, OV: 0.8582, AltV: 0.8750, CorV: 0.8329, TopV: 0.8432, BotRV: 0.8571, AllV: 0.8750 +[2026-03-20T19:35:55.058612Z] Loop 9240: Reg: 0.0003, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0006, AllReg: 0.0006, BotRReg: 0.0011, OV: 0.8632, AltV: 0.8817, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8576, AllV: 0.8817 +[2026-03-20T19:36:03.649235Z] Loop 9250: Reg: 0.0016, AltReg: 0.0027, CorReg: 0.0000, TopReg: 0.0129, AllReg: 0.0028, BotRReg: 0.0017, OV: 0.8619, AltV: 0.8795, CorV: 0.8356, TopV: 0.8457, BotRV: 0.8569, AllV: 0.8795 +[2026-03-20T19:36:12.239950Z] Loop 9260: Reg: 0.0007, AltReg: 0.0011, CorReg: 0.0000, TopReg: 0.0006, AllReg: 0.0012, BotRReg: 0.0005, OV: 0.8629, AltV: 0.8811, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8581, AllV: 0.8811 +[2026-03-20T19:36:20.826614Z] Loop 9270: Reg: 0.0019, AltReg: 0.0032, CorReg: 0.0000, TopReg: 0.0015, AllReg: 0.0032, BotRReg: 0.0020, OV: 0.8617, AltV: 0.8791, CorV: 0.8356, TopV: 0.8571, BotRV: 0.8566, AllV: 0.8791 +[2026-03-20T19:36:29.404871Z] Loop 9280: Reg: 0.0011, AltReg: 0.0017, CorReg: 0.0000, TopReg: 0.0013, AllReg: 0.0018, BotRReg: 0.0013, OV: 0.8625, AltV: 0.8805, CorV: 0.8356, TopV: 0.8573, BotRV: 0.8573, AllV: 0.8805 +[2026-03-20T19:36:37.985956Z] Loop 9290: Reg: 0.0054, AltReg: 0.0089, CorReg: 0.0002, TopReg: 0.0104, AllReg: 0.0089, BotRReg: 0.0098, OV: 0.8582, AltV: 0.8734, CorV: 0.8354, TopV: 0.8482, BotRV: 0.8489, AllV: 0.8734 +[2026-03-20T19:36:46.570065Z] Loop 9300: Reg: 0.0012, AltReg: 0.0020, CorReg: 0.0000, TopReg: 0.0019, AllReg: 0.0020, BotRReg: 0.0016, OV: 0.8624, AltV: 0.8802, CorV: 0.8356, TopV: 0.8567, BotRV: 0.8570, AllV: 0.8802 +[2026-03-20T19:36:55.149043Z] Loop 9310: Reg: 0.0009, AltReg: 0.0015, CorReg: 0.0000, TopReg: 0.0022, AllReg: 0.0015, BotRReg: 0.0030, OV: 0.8627, AltV: 0.8808, CorV: 0.8356, TopV: 0.8564, BotRV: 0.8556, AllV: 0.8808 +[2026-03-20T19:37:03.731364Z] Loop 9320: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0010, BotRReg: 0.0020, OV: 0.8630, AltV: 0.8813, CorV: 0.8356, TopV: 0.8580, BotRV: 0.8566, AllV: 0.8813 +[2026-03-20T19:37:12.318946Z] Loop 9330: Reg: 0.0050, AltReg: 0.0082, CorReg: 0.0001, TopReg: 0.0083, AllReg: 0.0082, BotRReg: 0.0135, OV: 0.8586, AltV: 0.8740, CorV: 0.8356, TopV: 0.8504, BotRV: 0.8452, AllV: 0.8740 +[2026-03-20T19:37:20.900359Z] Loop 9340: Reg: 0.0018, AltReg: 0.0029, CorReg: 0.0000, TopReg: 0.0015, AllReg: 0.0029, BotRReg: 0.0036, OV: 0.8618, AltV: 0.8793, CorV: 0.8356, TopV: 0.8572, BotRV: 0.8551, AllV: 0.8793 +[2026-03-20T19:37:29.491287Z] Loop 9350: Reg: 0.0011, AltReg: 0.0018, CorReg: 0.0000, TopReg: 0.0011, AllReg: 0.0018, BotRReg: 0.0017, OV: 0.8625, AltV: 0.8804, CorV: 0.8356, TopV: 0.8576, BotRV: 0.8569, AllV: 0.8804 +[2026-03-20T19:37:38.068096Z] Loop 9360: Reg: 0.0008, AltReg: 0.0014, CorReg: 0.0000, TopReg: 0.0021, AllReg: 0.0014, BotRReg: 0.0011, OV: 0.8627, AltV: 0.8808, CorV: 0.8356, TopV: 0.8565, BotRV: 0.8575, AllV: 0.8809 +[2026-03-20T19:37:46.649283Z] Loop 9370: Reg: 0.0013, AltReg: 0.0021, CorReg: 0.0000, TopReg: 0.0013, AllReg: 0.0021, BotRReg: 0.0017, OV: 0.8623, AltV: 0.8801, CorV: 0.8356, TopV: 0.8573, BotRV: 0.8569, AllV: 0.8801 +[2026-03-20T19:37:55.224164Z] Loop 9380: Reg: 0.0020, AltReg: 0.0033, CorReg: 0.0000, TopReg: 0.0025, AllReg: 0.0033, BotRReg: 0.0033, OV: 0.8616, AltV: 0.8789, CorV: 0.8356, TopV: 0.8561, BotRV: 0.8553, AllV: 0.8789 +[2026-03-20T19:38:03.808310Z] Loop 9390: Reg: 0.0004, AltReg: 0.0007, CorReg: 0.0000, TopReg: 0.0009, AllReg: 0.0007, BotRReg: 0.0025, OV: 0.8632, AltV: 0.8815, CorV: 0.8356, TopV: 0.8577, BotRV: 0.8561, AllV: 0.8815 +[2026-03-20T19:38:12.395667Z] Loop 9400: Reg: 0.0005, AltReg: 0.0008, CorReg: 0.0000, TopReg: 0.0018, AllReg: 0.0008, BotRReg: 0.0012, OV: 0.8631, AltV: 0.8814, CorV: 0.8356, TopV: 0.8568, BotRV: 0.8574, AllV: 0.8815 +[2026-03-20T19:38:20.978101Z] Loop 9410: Reg: 0.0010, AltReg: 0.0016, CorReg: 0.0000, TopReg: 0.0033, AllReg: 0.0016, BotRReg: 0.0022, OV: 0.8626, AltV: 0.8806, CorV: 0.8356, TopV: 0.8553, BotRV: 0.8564, AllV: 0.8807 +[2026-03-20T19:38:29.559794Z] Loop 9420: Reg: 0.0009, AltReg: 0.0013, CorReg: 0.0002, TopReg: 0.0007, AllReg: 0.0014, BotRReg: 0.0007, OV: 0.8627, AltV: 0.8809, CorV: 0.8354, TopV: 0.8579, BotRV: 0.8579, AllV: 0.8809 +[2026-03-20T19:38:38.147450Z] Loop 9430: Reg: 0.0018, AltReg: 0.0030, CorReg: 0.0000, TopReg: 0.0124, AllReg: 0.0030, BotRReg: 0.0026, OV: 0.8618, AltV: 0.8792, CorV: 0.8356, TopV: 0.8462, BotRV: 0.8560, AllV: 0.8793 +[2026-03-20T19:38:46.728363Z] Loop 9440: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0003, BotRReg: 0.0012, OV: 0.8634, AltV: 0.8819, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8574, AllV: 0.8819 +[2026-03-20T19:38:55.310883Z] Loop 9450: Reg: 0.0002, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0003, BotRReg: 0.0008, OV: 0.8634, AltV: 0.8820, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8578, AllV: 0.8820 +[2026-03-20T19:39:03.898458Z] Loop 9460: Reg: 0.0006, AltReg: 0.0009, CorReg: 0.0001, TopReg: 0.0005, AllReg: 0.0009, BotRReg: 0.0005, OV: 0.8630, AltV: 0.8813, CorV: 0.8355, TopV: 0.8582, BotRV: 0.8581, AllV: 0.8813 +[2026-03-20T19:39:12.483992Z] Loop 9470: Reg: 0.0004, AltReg: 0.0007, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0007, BotRReg: 0.0015, OV: 0.8631, AltV: 0.8815, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8572, AllV: 0.8815 +[2026-03-20T19:39:21.070042Z] Loop 9480: Reg: 0.0013, AltReg: 0.0022, CorReg: 0.0000, TopReg: 0.0033, AllReg: 0.0023, BotRReg: 0.0036, OV: 0.8622, AltV: 0.8800, CorV: 0.8356, TopV: 0.8553, BotRV: 0.8551, AllV: 0.8800 +[2026-03-20T19:39:29.653531Z] Loop 9490: Reg: 0.0010, AltReg: 0.0017, CorReg: 0.0000, TopReg: 0.0011, AllReg: 0.0017, BotRReg: 0.0030, OV: 0.8626, AltV: 0.8805, CorV: 0.8356, TopV: 0.8575, BotRV: 0.8556, AllV: 0.8805 +[2026-03-20T19:39:38.238495Z] Loop 9500: Reg: 0.0013, AltReg: 0.0022, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0022, BotRReg: 0.0054, OV: 0.8622, AltV: 0.8800, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8532, AllV: 0.8800 +[2026-03-20T19:39:46.820458Z] Loop 9510: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0006, BotRReg: 0.0012, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8574, AllV: 0.8816 +[2026-03-20T19:39:55.409069Z] Loop 9520: Reg: 0.0004, AltReg: 0.0007, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0007, BotRReg: 0.0006, OV: 0.8632, AltV: 0.8815, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8580, AllV: 0.8816 +[2026-03-20T19:40:03.990796Z] Loop 9530: Reg: 0.0017, AltReg: 0.0028, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0028, BotRReg: 0.0053, OV: 0.8619, AltV: 0.8795, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8533, AllV: 0.8795 +[2026-03-20T19:40:12.572502Z] Loop 9540: Reg: 0.0018, AltReg: 0.0030, CorReg: 0.0000, TopReg: 0.0006, AllReg: 0.0031, BotRReg: 0.0044, OV: 0.8618, AltV: 0.8792, CorV: 0.8356, TopV: 0.8580, BotRV: 0.8543, AllV: 0.8792 +[2026-03-20T19:40:21.155976Z] Loop 9550: Reg: 0.0016, AltReg: 0.0026, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0026, BotRReg: 0.0072, OV: 0.8620, AltV: 0.8796, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8515, AllV: 0.8796 +[2026-03-20T19:40:29.740493Z] Loop 9560: Reg: 0.0039, AltReg: 0.0065, CorReg: 0.0000, TopReg: 0.0108, AllReg: 0.0066, BotRReg: 0.0102, OV: 0.8597, AltV: 0.8757, CorV: 0.8356, TopV: 0.8478, BotRV: 0.8485, AllV: 0.8757 +[2026-03-20T19:40:38.321288Z] Loop 9570: Reg: 0.0009, AltReg: 0.0015, CorReg: 0.0001, TopReg: 0.0012, AllReg: 0.0015, BotRReg: 0.0040, OV: 0.8627, AltV: 0.8807, CorV: 0.8356, TopV: 0.8574, BotRV: 0.8546, AllV: 0.8807 +[2026-03-20T19:40:46.900329Z] Loop 9580: Reg: 0.0022, AltReg: 0.0027, CorReg: 0.0015, TopReg: 0.0041, AllReg: 0.0027, BotRReg: 0.0021, OV: 0.8614, AltV: 0.8796, CorV: 0.8342, TopV: 0.8545, BotRV: 0.8566, AllV: 0.8796 +[2026-03-20T19:40:55.480473Z] Loop 9590: Reg: 0.0026, AltReg: 0.0035, CorReg: 0.0014, TopReg: 0.0059, AllReg: 0.0035, BotRReg: 0.0033, OV: 0.8610, AltV: 0.8787, CorV: 0.8343, TopV: 0.8528, BotRV: 0.8553, AllV: 0.8788 +[2026-03-20T19:41:04.061514Z] Loop 9600: Reg: 0.0070, AltReg: 0.0116, CorReg: 0.0000, TopReg: 0.0235, AllReg: 0.0116, BotRReg: 0.0085, OV: 0.8566, AltV: 0.8706, CorV: 0.8356, TopV: 0.8351, BotRV: 0.8502, AllV: 0.8706 +[2026-03-20T19:41:12.639808Z] Loop 9610: Reg: 0.0003, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0004, BotRReg: 0.0002, OV: 0.8633, AltV: 0.8818, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8584, AllV: 0.8818 +[2026-03-20T19:41:21.220583Z] Loop 9620: Reg: 0.0009, AltReg: 0.0014, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0016, BotRReg: 0.0002, OV: 0.8627, AltV: 0.8808, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8585, AllV: 0.8806 +[2026-03-20T19:41:29.798597Z] Loop 9630: Reg: 0.0007, AltReg: 0.0011, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0011, BotRReg: 0.0001, OV: 0.8629, AltV: 0.8811, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8585, AllV: 0.8811 +[2026-03-20T19:41:38.377917Z] Loop 9640: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0006, BotRReg: 0.0007, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8579, AllV: 0.8816 +[2026-03-20T19:41:46.964983Z] Loop 9650: Reg: 0.0003, AltReg: 0.0005, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0005, BotRReg: 0.0006, OV: 0.8633, AltV: 0.8818, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8580, AllV: 0.8818 +[2026-03-20T19:41:55.550258Z] Loop 9660: Reg: 0.0044, AltReg: 0.0074, CorReg: 0.0000, TopReg: 0.0131, AllReg: 0.0074, BotRReg: 0.0046, OV: 0.8592, AltV: 0.8748, CorV: 0.8356, TopV: 0.8456, BotRV: 0.8541, AllV: 0.8749 +[2026-03-20T19:42:04.135900Z] Loop 9670: Reg: 0.0002, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0004, BotRReg: 0.0005, OV: 0.8634, AltV: 0.8818, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8582, AllV: 0.8819 +[2026-03-20T19:42:12.722427Z] Loop 9680: Reg: 0.0064, AltReg: 0.0106, CorReg: 0.0002, TopReg: 0.0150, AllReg: 0.0111, BotRReg: 0.0001, OV: 0.8571, AltV: 0.8716, CorV: 0.8355, TopV: 0.8437, BotRV: 0.8585, AllV: 0.8711 +[2026-03-20T19:42:21.307597Z] Loop 9690: Reg: 0.0001, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0002, BotRReg: 0.0002, OV: 0.8635, AltV: 0.8820, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8584, AllV: 0.8820 +[2026-03-20T19:42:29.893626Z] Loop 9700: Reg: 0.0005, AltReg: 0.0009, CorReg: 0.0000, TopReg: 0.0012, AllReg: 0.0009, BotRReg: 0.0011, OV: 0.8631, AltV: 0.8814, CorV: 0.8356, TopV: 0.8574, BotRV: 0.8575, AllV: 0.8814 +[2026-03-20T19:42:38.470481Z] Loop 9710: Reg: 0.0011, AltReg: 0.0018, CorReg: 0.0000, TopReg: 0.0034, AllReg: 0.0018, BotRReg: 0.0024, OV: 0.8625, AltV: 0.8804, CorV: 0.8356, TopV: 0.8553, BotRV: 0.8563, AllV: 0.8805 +[2026-03-20T19:42:47.050086Z] Loop 9720: Reg: 0.0003, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0006, BotRReg: 0.0017, OV: 0.8632, AltV: 0.8817, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8569, AllV: 0.8817 +[2026-03-20T19:42:55.640185Z] Loop 9730: Reg: 0.0022, AltReg: 0.0037, CorReg: 0.0000, TopReg: 0.0016, AllReg: 0.0037, BotRReg: 0.0040, OV: 0.8614, AltV: 0.8785, CorV: 0.8356, TopV: 0.8570, BotRV: 0.8547, AllV: 0.8785 +[2026-03-20T19:43:04.220019Z] Loop 9740: Reg: 0.0019, AltReg: 0.0031, CorReg: 0.0002, TopReg: 0.0010, AllReg: 0.0031, BotRReg: 0.0019, OV: 0.8617, AltV: 0.8791, CorV: 0.8355, TopV: 0.8576, BotRV: 0.8568, AllV: 0.8791 +[2026-03-20T19:43:12.803283Z] Loop 9750: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0003, BotRReg: 0.0002, OV: 0.8634, AltV: 0.8820, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8584, AllV: 0.8820 +[2026-03-20T19:43:21.384274Z] Loop 9760: Reg: 0.0016, AltReg: 0.0025, CorReg: 0.0003, TopReg: 0.0034, AllReg: 0.0025, BotRReg: 0.0006, OV: 0.8620, AltV: 0.8797, CorV: 0.8354, TopV: 0.8552, BotRV: 0.8580, AllV: 0.8798 +[2026-03-20T19:43:29.966644Z] Loop 9770: Reg: 0.0006, AltReg: 0.0009, CorReg: 0.0002, TopReg: 0.0009, AllReg: 0.0009, BotRReg: 0.0010, OV: 0.8630, AltV: 0.8813, CorV: 0.8355, TopV: 0.8577, BotRV: 0.8576, AllV: 0.8814 +[2026-03-20T19:43:38.549772Z] Loop 9780: Reg: 0.0014, AltReg: 0.0018, CorReg: 0.0007, TopReg: 0.0016, AllReg: 0.0018, BotRReg: 0.0023, OV: 0.8622, AltV: 0.8804, CorV: 0.8349, TopV: 0.8571, BotRV: 0.8564, AllV: 0.8804 +[2026-03-20T19:43:47.131752Z] Loop 9790: Reg: 0.0029, AltReg: 0.0041, CorReg: 0.0010, TopReg: 0.0036, AllReg: 0.0041, BotRReg: 0.0045, OV: 0.8607, AltV: 0.8781, CorV: 0.8346, TopV: 0.8550, BotRV: 0.8541, AllV: 0.8782 +[2026-03-20T19:43:55.712746Z] Loop 9800: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0001, TopReg: 0.0005, AllReg: 0.0010, BotRReg: 0.0014, OV: 0.8630, AltV: 0.8812, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8573, AllV: 0.8813 +[2026-03-20T19:44:04.293885Z] Loop 9810: Reg: 0.0018, AltReg: 0.0029, CorReg: 0.0001, TopReg: 0.0038, AllReg: 0.0029, BotRReg: 0.0003, OV: 0.8618, AltV: 0.8794, CorV: 0.8355, TopV: 0.8548, BotRV: 0.8584, AllV: 0.8793 +[2026-03-20T19:44:12.882865Z] Loop 9820: Reg: 0.0006, AltReg: 0.0008, CorReg: 0.0002, TopReg: 0.0006, AllReg: 0.0008, BotRReg: 0.0013, OV: 0.8630, AltV: 0.8814, CorV: 0.8355, TopV: 0.8580, BotRV: 0.8574, AllV: 0.8814 +[2026-03-20T19:44:21.467584Z] Loop 9830: Reg: 0.0003, AltReg: 0.0005, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0005, BotRReg: 0.0011, OV: 0.8633, AltV: 0.8817, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8575, AllV: 0.8818 +[2026-03-20T19:44:30.055727Z] Loop 9840: Reg: 0.0003, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0015, AllReg: 0.0004, BotRReg: 0.0006, OV: 0.8633, AltV: 0.8818, CorV: 0.8356, TopV: 0.8572, BotRV: 0.8581, AllV: 0.8818 +[2026-03-20T19:44:38.642761Z] Loop 9850: Reg: 0.0009, AltReg: 0.0015, CorReg: 0.0000, TopReg: 0.0076, AllReg: 0.0015, BotRReg: 0.0011, OV: 0.8627, AltV: 0.8807, CorV: 0.8356, TopV: 0.8510, BotRV: 0.8576, AllV: 0.8807 +[2026-03-20T19:44:47.224747Z] Loop 9860: Reg: 0.0008, AltReg: 0.0013, CorReg: 0.0000, TopReg: 0.0038, AllReg: 0.0014, BotRReg: 0.0012, OV: 0.8628, AltV: 0.8809, CorV: 0.8356, TopV: 0.8548, BotRV: 0.8574, AllV: 0.8809 +[2026-03-20T19:44:55.800147Z] Loop 9870: Reg: 0.0003, AltReg: 0.0005, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0005, BotRReg: 0.0014, OV: 0.8633, AltV: 0.8817, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8572, AllV: 0.8818 +[2026-03-20T19:45:04.384604Z] Loop 9880: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0003, BotRReg: 0.0007, OV: 0.8634, AltV: 0.8819, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8579, AllV: 0.8819 +[2026-03-20T19:45:12.968783Z] Loop 9890: Reg: 0.0004, AltReg: 0.0007, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0007, BotRReg: 0.0016, OV: 0.8632, AltV: 0.8815, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8570, AllV: 0.8816 +[2026-03-20T19:45:21.552457Z] Loop 9900: Reg: 0.0010, AltReg: 0.0017, CorReg: 0.0000, TopReg: 0.0024, AllReg: 0.0017, BotRReg: 0.0031, OV: 0.8626, AltV: 0.8805, CorV: 0.8356, TopV: 0.8563, BotRV: 0.8555, AllV: 0.8806 +[2026-03-20T19:45:30.135178Z] Loop 9910: Reg: 0.0023, AltReg: 0.0038, CorReg: 0.0000, TopReg: 0.0024, AllReg: 0.0038, BotRReg: 0.0082, OV: 0.8613, AltV: 0.8784, CorV: 0.8356, TopV: 0.8562, BotRV: 0.8504, AllV: 0.8785 +[2026-03-20T19:45:38.719170Z] Loop 9920: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0006, BotRReg: 0.0020, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8567, AllV: 0.8816 +[2026-03-20T19:45:47.314227Z] Loop 9930: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0003, BotRReg: 0.0007, OV: 0.8634, AltV: 0.8819, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8579, AllV: 0.8819 +[2026-03-20T19:45:55.905545Z] Loop 9940: Reg: 0.0002, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0004, BotRReg: 0.0013, OV: 0.8634, AltV: 0.8818, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8574, AllV: 0.8818 +[2026-03-20T19:46:04.491537Z] Loop 9950: Reg: 0.0007, AltReg: 0.0011, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0011, BotRReg: 0.0023, OV: 0.8629, AltV: 0.8811, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8563, AllV: 0.8811 +[2026-03-20T19:46:13.080682Z] Loop 9960: Reg: 0.0022, AltReg: 0.0036, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0037, BotRReg: 0.0061, OV: 0.8614, AltV: 0.8786, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8525, AllV: 0.8786 +[2026-03-20T19:46:21.673451Z] Loop 9970: Reg: 0.0025, AltReg: 0.0041, CorReg: 0.0000, TopReg: 0.0023, AllReg: 0.0041, BotRReg: 0.0044, OV: 0.8611, AltV: 0.8781, CorV: 0.8356, TopV: 0.8564, BotRV: 0.8542, AllV: 0.8781 +[2026-03-20T19:46:30.253871Z] Loop 9980: Reg: 0.0016, AltReg: 0.0026, CorReg: 0.0001, TopReg: 0.0064, AllReg: 0.0026, BotRReg: 0.0016, OV: 0.8620, AltV: 0.8796, CorV: 0.8355, TopV: 0.8523, BotRV: 0.8570, AllV: 0.8796 +[2026-03-20T19:46:38.834708Z] Loop 9990: Reg: 0.0009, AltReg: 0.0015, CorReg: 0.0000, TopReg: 0.0006, AllReg: 0.0015, BotRReg: 0.0042, OV: 0.8627, AltV: 0.8807, CorV: 0.8356, TopV: 0.8580, BotRV: 0.8544, AllV: 0.8808 +[2026-03-20T19:46:47.419305Z] Loop 10000: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0011, BotRReg: 0.0040, OV: 0.8629, AltV: 0.8812, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8546, AllV: 0.8812 +[2026-03-20T19:46:55.997987Z] Loop 10010: Reg: 0.0004, AltReg: 0.0007, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0007, BotRReg: 0.0013, OV: 0.8631, AltV: 0.8815, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8573, AllV: 0.8815 +[2026-03-20T19:47:04.583775Z] Loop 10020: Reg: 0.0003, AltReg: 0.0005, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0005, BotRReg: 0.0007, OV: 0.8633, AltV: 0.8817, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8580, AllV: 0.8817 +[2026-03-20T19:47:13.165344Z] Loop 10030: Reg: 0.0009, AltReg: 0.0014, CorReg: 0.0000, TopReg: 0.0006, AllReg: 0.0014, BotRReg: 0.0036, OV: 0.8627, AltV: 0.8808, CorV: 0.8356, TopV: 0.8580, BotRV: 0.8550, AllV: 0.8808 +[2026-03-20T19:47:21.751501Z] Loop 10040: Reg: 0.0004, AltReg: 0.0007, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0007, BotRReg: 0.0004, OV: 0.8632, AltV: 0.8815, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8582, AllV: 0.8816 +[2026-03-20T19:47:30.329794Z] Loop 10050: Reg: 0.0031, AltReg: 0.0052, CorReg: 0.0000, TopReg: 0.0017, AllReg: 0.0057, BotRReg: 0.0004, OV: 0.8605, AltV: 0.8770, CorV: 0.8356, TopV: 0.8569, BotRV: 0.8583, AllV: 0.8766 +[2026-03-20T19:47:38.908123Z] Loop 10060: Reg: 0.0004, AltReg: 0.0007, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0007, BotRReg: 0.0001, OV: 0.8632, AltV: 0.8815, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8585, AllV: 0.8816 +[2026-03-20T19:47:47.489466Z] Loop 10070: Reg: 0.0006, AltReg: 0.0011, CorReg: 0.0000, TopReg: 0.0010, AllReg: 0.0011, BotRReg: 0.0006, OV: 0.8629, AltV: 0.8811, CorV: 0.8356, TopV: 0.8577, BotRV: 0.8581, AllV: 0.8812 +[2026-03-20T19:47:56.072577Z] Loop 10080: Reg: 0.0010, AltReg: 0.0017, CorReg: 0.0000, TopReg: 0.0015, AllReg: 0.0017, BotRReg: 0.0021, OV: 0.8626, AltV: 0.8805, CorV: 0.8356, TopV: 0.8571, BotRV: 0.8566, AllV: 0.8805 +[2026-03-20T19:48:04.654920Z] Loop 10090: Reg: 0.0018, AltReg: 0.0030, CorReg: 0.0000, TopReg: 0.0021, AllReg: 0.0030, BotRReg: 0.0046, OV: 0.8618, AltV: 0.8792, CorV: 0.8356, TopV: 0.8565, BotRV: 0.8541, AllV: 0.8792 +[2026-03-20T19:48:13.233560Z] Loop 10100: Reg: 0.0012, AltReg: 0.0020, CorReg: 0.0000, TopReg: 0.0018, AllReg: 0.0021, BotRReg: 0.0026, OV: 0.8624, AltV: 0.8802, CorV: 0.8356, TopV: 0.8569, BotRV: 0.8560, AllV: 0.8802 +[2026-03-20T19:48:21.816926Z] Loop 10110: Reg: 0.0011, AltReg: 0.0018, CorReg: 0.0000, TopReg: 0.0008, AllReg: 0.0018, BotRReg: 0.0027, OV: 0.8625, AltV: 0.8805, CorV: 0.8356, TopV: 0.8578, BotRV: 0.8559, AllV: 0.8805 +[2026-03-20T19:48:30.403612Z] Loop 10120: Reg: 0.0002, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0003, BotRReg: 0.0007, OV: 0.8634, AltV: 0.8820, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8580, AllV: 0.8820 +[2026-03-20T19:48:38.990076Z] Loop 10130: Reg: 0.0003, AltReg: 0.0005, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0005, BotRReg: 0.0004, OV: 0.8632, AltV: 0.8817, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8583, AllV: 0.8817 +[2026-03-20T19:48:47.572678Z] Loop 10140: Reg: 0.0009, AltReg: 0.0015, CorReg: 0.0000, TopReg: 0.0022, AllReg: 0.0015, BotRReg: 0.0006, OV: 0.8626, AltV: 0.8807, CorV: 0.8356, TopV: 0.8565, BotRV: 0.8581, AllV: 0.8807 +[2026-03-20T19:48:56.150977Z] Loop 10150: Reg: 0.0007, AltReg: 0.0012, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0012, BotRReg: 0.0021, OV: 0.8629, AltV: 0.8810, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8565, AllV: 0.8811 +[2026-03-20T19:49:04.728029Z] Loop 10160: Reg: 0.0017, AltReg: 0.0029, CorReg: 0.0000, TopReg: 0.0013, AllReg: 0.0029, BotRReg: 0.0079, OV: 0.8619, AltV: 0.8794, CorV: 0.8356, TopV: 0.8573, BotRV: 0.8507, AllV: 0.8794 +[2026-03-20T19:49:13.310419Z] Loop 10170: Reg: 0.0002, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0004, BotRReg: 0.0003, OV: 0.8634, AltV: 0.8819, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8583, AllV: 0.8819 +[2026-03-20T19:49:21.893270Z] Loop 10180: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0006, AllReg: 0.0003, BotRReg: 0.0002, OV: 0.8634, AltV: 0.8819, CorV: 0.8356, TopV: 0.8580, BotRV: 0.8584, AllV: 0.8819 +[2026-03-20T19:49:30.481820Z] Loop 10190: Reg: 0.0003, AltReg: 0.0005, CorReg: 0.0000, TopReg: 0.0013, AllReg: 0.0005, BotRReg: 0.0006, OV: 0.8633, AltV: 0.8817, CorV: 0.8356, TopV: 0.8574, BotRV: 0.8580, AllV: 0.8817 +[2026-03-20T19:49:39.074856Z] Loop 10200: Reg: 0.0002, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0004, BotRReg: 0.0011, OV: 0.8633, AltV: 0.8818, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8576, AllV: 0.8818 +[2026-03-20T19:49:47.662241Z] Loop 10210: Reg: 0.0002, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0004, BotRReg: 0.0007, OV: 0.8633, AltV: 0.8818, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8579, AllV: 0.8818 +[2026-03-20T19:49:56.246077Z] Loop 10220: Reg: 0.0028, AltReg: 0.0047, CorReg: 0.0000, TopReg: 0.0029, AllReg: 0.0047, BotRReg: 0.0163, OV: 0.8608, AltV: 0.8775, CorV: 0.8356, TopV: 0.8557, BotRV: 0.8423, AllV: 0.8776 +[2026-03-20T19:50:04.830717Z] Loop 10230: Reg: 0.0006, AltReg: 0.0009, CorReg: 0.0000, TopReg: 0.0006, AllReg: 0.0009, BotRReg: 0.0015, OV: 0.8630, AltV: 0.8813, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8571, AllV: 0.8813 +[2026-03-20T19:50:13.413793Z] Loop 10240: Reg: 0.0009, AltReg: 0.0014, CorReg: 0.0000, TopReg: 0.0078, AllReg: 0.0014, BotRReg: 0.0016, OV: 0.8627, AltV: 0.8808, CorV: 0.8356, TopV: 0.8509, BotRV: 0.8570, AllV: 0.8808 +[2026-03-20T19:50:21.992502Z] Loop 10250: Reg: 0.0012, AltReg: 0.0020, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0020, BotRReg: 0.0041, OV: 0.8624, AltV: 0.8802, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8545, AllV: 0.8803 +[2026-03-20T19:50:30.569547Z] Loop 10260: Reg: 0.0007, AltReg: 0.0011, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0011, BotRReg: 0.0024, OV: 0.8629, AltV: 0.8811, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8562, AllV: 0.8811 +[2026-03-20T19:50:39.154863Z] Loop 10270: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0006, BotRReg: 0.0010, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8576, AllV: 0.8816 +[2026-03-20T19:50:47.738402Z] Loop 10280: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0010, BotRReg: 0.0014, OV: 0.8630, AltV: 0.8812, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8573, AllV: 0.8813 +[2026-03-20T19:50:56.319530Z] Loop 10290: Reg: 0.0029, AltReg: 0.0048, CorReg: 0.0000, TopReg: 0.0034, AllReg: 0.0048, BotRReg: 0.0077, OV: 0.8607, AltV: 0.8774, CorV: 0.8356, TopV: 0.8552, BotRV: 0.8509, AllV: 0.8774 +[2026-03-20T19:51:04.906320Z] Loop 10300: Reg: 0.0021, AltReg: 0.0035, CorReg: 0.0000, TopReg: 0.0133, AllReg: 0.0035, BotRReg: 0.0025, OV: 0.8615, AltV: 0.8787, CorV: 0.8356, TopV: 0.8453, BotRV: 0.8561, AllV: 0.8788 +[2026-03-20T19:51:13.498359Z] Loop 10310: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0003, BotRReg: 0.0003, OV: 0.8634, AltV: 0.8820, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8583, AllV: 0.8820 +[2026-03-20T19:51:22.093506Z] Loop 10320: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0003, BotRReg: 0.0003, OV: 0.8634, AltV: 0.8819, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8583, AllV: 0.8819 +[2026-03-20T19:51:30.684404Z] Loop 10330: Reg: 0.0005, AltReg: 0.0009, CorReg: 0.0000, TopReg: 0.0008, AllReg: 0.0009, BotRReg: 0.0006, OV: 0.8631, AltV: 0.8814, CorV: 0.8356, TopV: 0.8578, BotRV: 0.8581, AllV: 0.8814 +[2026-03-20T19:51:39.273701Z] Loop 10340: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0003, BotRReg: 0.0007, OV: 0.8634, AltV: 0.8820, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8579, AllV: 0.8820 +[2026-03-20T19:51:47.858342Z] Loop 10350: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0010, BotRReg: 0.0015, OV: 0.8630, AltV: 0.8812, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8572, AllV: 0.8812 +[2026-03-20T19:51:56.442430Z] Loop 10360: Reg: 0.0004, AltReg: 0.0007, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0007, BotRReg: 0.0012, OV: 0.8632, AltV: 0.8815, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8575, AllV: 0.8816 +[2026-03-20T19:52:05.023691Z] Loop 10370: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0006, BotRReg: 0.0011, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8576, AllV: 0.8817 +[2026-03-20T19:52:13.604353Z] Loop 10380: Reg: 0.0009, AltReg: 0.0016, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0016, BotRReg: 0.0020, OV: 0.8626, AltV: 0.8807, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8566, AllV: 0.8807 +[2026-03-20T19:52:22.189717Z] Loop 10390: Reg: 0.0007, AltReg: 0.0011, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0011, BotRReg: 0.0015, OV: 0.8629, AltV: 0.8811, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8571, AllV: 0.8811 +[2026-03-20T19:52:30.771917Z] Loop 10400: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0004, BotRReg: 0.0011, OV: 0.8634, AltV: 0.8819, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8575, AllV: 0.8819 +[2026-03-20T19:52:39.359269Z] Loop 10410: Reg: 0.0011, AltReg: 0.0018, CorReg: 0.0000, TopReg: 0.0066, AllReg: 0.0019, BotRReg: 0.0007, OV: 0.8625, AltV: 0.8804, CorV: 0.8356, TopV: 0.8521, BotRV: 0.8580, AllV: 0.8804 +[2026-03-20T19:52:47.940980Z] Loop 10420: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0003, BotRReg: 0.0005, OV: 0.8634, AltV: 0.8819, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8581, AllV: 0.8819 +[2026-03-20T19:52:56.521359Z] Loop 10430: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0006, AllReg: 0.0006, BotRReg: 0.0012, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8574, AllV: 0.8816 +[2026-03-20T19:53:05.101011Z] Loop 10440: Reg: 0.0015, AltReg: 0.0025, CorReg: 0.0000, TopReg: 0.0086, AllReg: 0.0025, BotRReg: 0.0025, OV: 0.8621, AltV: 0.8797, CorV: 0.8356, TopV: 0.8501, BotRV: 0.8561, AllV: 0.8798 +[2026-03-20T19:53:13.690386Z] Loop 10450: Reg: 0.0003, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0004, BotRReg: 0.0007, OV: 0.8633, AltV: 0.8818, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8579, AllV: 0.8818 +[2026-03-20T19:53:22.271650Z] Loop 10460: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0001, TopReg: 0.0005, AllReg: 0.0006, BotRReg: 0.0008, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8578, AllV: 0.8816 +[2026-03-20T19:53:30.849873Z] Loop 10470: Reg: 0.0010, AltReg: 0.0014, CorReg: 0.0005, TopReg: 0.0013, AllReg: 0.0014, BotRReg: 0.0008, OV: 0.8625, AltV: 0.8808, CorV: 0.8352, TopV: 0.8573, BotRV: 0.8578, AllV: 0.8808 +[2026-03-20T19:53:39.436260Z] Loop 10480: Reg: 0.0010, AltReg: 0.0014, CorReg: 0.0005, TopReg: 0.0014, AllReg: 0.0014, BotRReg: 0.0008, OV: 0.8626, AltV: 0.8809, CorV: 0.8351, TopV: 0.8572, BotRV: 0.8578, AllV: 0.8809 +[2026-03-20T19:53:48.022163Z] Loop 10490: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0001, TopReg: 0.0004, AllReg: 0.0007, BotRReg: 0.0027, OV: 0.8631, AltV: 0.8816, CorV: 0.8355, TopV: 0.8582, BotRV: 0.8559, AllV: 0.8816 +[2026-03-20T19:53:56.610342Z] Loop 10500: Reg: 0.0007, AltReg: 0.0011, CorReg: 0.0000, TopReg: 0.0006, AllReg: 0.0011, BotRReg: 0.0073, OV: 0.8629, AltV: 0.8811, CorV: 0.8356, TopV: 0.8580, BotRV: 0.8513, AllV: 0.8811 +[2026-03-20T19:54:05.195908Z] Loop 10510: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0011, AllReg: 0.0006, BotRReg: 0.0019, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8575, BotRV: 0.8567, AllV: 0.8816 +[2026-03-20T19:54:13.776532Z] Loop 10520: Reg: 0.0007, AltReg: 0.0010, CorReg: 0.0001, TopReg: 0.0025, AllReg: 0.0010, BotRReg: 0.0010, OV: 0.8629, AltV: 0.8812, CorV: 0.8355, TopV: 0.8561, BotRV: 0.8576, AllV: 0.8812 +[2026-03-20T19:54:22.354582Z] Loop 10530: Reg: 0.0005, AltReg: 0.0008, CorReg: 0.0001, TopReg: 0.0020, AllReg: 0.0008, BotRReg: 0.0008, OV: 0.8631, AltV: 0.8814, CorV: 0.8355, TopV: 0.8566, BotRV: 0.8578, AllV: 0.8814 +[2026-03-20T19:54:30.933039Z] Loop 10540: Reg: 0.0003, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0009, AllReg: 0.0006, BotRReg: 0.0003, OV: 0.8632, AltV: 0.8817, CorV: 0.8356, TopV: 0.8577, BotRV: 0.8584, AllV: 0.8817 +[2026-03-20T19:54:39.517247Z] Loop 10550: Reg: 0.0054, AltReg: 0.0088, CorReg: 0.0003, TopReg: 0.0141, AllReg: 0.0088, BotRReg: 0.0005, OV: 0.8582, AltV: 0.8734, CorV: 0.8353, TopV: 0.8446, BotRV: 0.8581, AllV: 0.8734 +[2026-03-20T19:54:48.093913Z] Loop 10560: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0003, BotRReg: 0.0005, OV: 0.8634, AltV: 0.8819, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8582, AllV: 0.8819 +[2026-03-20T19:54:56.679788Z] Loop 10570: Reg: 0.0006, AltReg: 0.0011, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0011, BotRReg: 0.0016, OV: 0.8629, AltV: 0.8812, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8570, AllV: 0.8812 +[2026-03-20T19:55:05.264602Z] Loop 10580: Reg: 0.0005, AltReg: 0.0009, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0009, BotRReg: 0.0013, OV: 0.8630, AltV: 0.8813, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8573, AllV: 0.8813 +[2026-03-20T19:55:13.844349Z] Loop 10590: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0003, BotRReg: 0.0005, OV: 0.8634, AltV: 0.8819, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8582, AllV: 0.8819 +[2026-03-20T19:55:22.425151Z] Loop 10600: Reg: 0.0006, AltReg: 0.0009, CorReg: 0.0000, TopReg: 0.0006, AllReg: 0.0010, BotRReg: 0.0043, OV: 0.8630, AltV: 0.8813, CorV: 0.8356, TopV: 0.8580, BotRV: 0.8543, AllV: 0.8813 +[2026-03-20T19:55:31.012324Z] Loop 10610: Reg: 0.0020, AltReg: 0.0034, CorReg: 0.0000, TopReg: 0.0127, AllReg: 0.0034, BotRReg: 0.0077, OV: 0.8616, AltV: 0.8788, CorV: 0.8356, TopV: 0.8459, BotRV: 0.8509, AllV: 0.8789 +[2026-03-20T19:55:39.590792Z] Loop 10620: Reg: 0.0027, AltReg: 0.0045, CorReg: 0.0000, TopReg: 0.0202, AllReg: 0.0045, BotRReg: 0.0061, OV: 0.8609, AltV: 0.8777, CorV: 0.8356, TopV: 0.8385, BotRV: 0.8525, AllV: 0.8777 +[2026-03-20T19:55:48.168738Z] Loop 10630: Reg: 0.0004, AltReg: 0.0007, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0007, BotRReg: 0.0020, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8566, AllV: 0.8816 +[2026-03-20T19:55:56.752998Z] Loop 10640: Reg: 0.0020, AltReg: 0.0034, CorReg: 0.0000, TopReg: 0.0018, AllReg: 0.0034, BotRReg: 0.0240, OV: 0.8615, AltV: 0.8788, CorV: 0.8356, TopV: 0.8568, BotRV: 0.8347, AllV: 0.8788 +[2026-03-20T19:56:05.337287Z] Loop 10650: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0000, TopReg: 0.0031, AllReg: 0.0010, BotRReg: 0.0012, OV: 0.8630, AltV: 0.8812, CorV: 0.8356, TopV: 0.8556, BotRV: 0.8574, AllV: 0.8812 +[2026-03-20T19:56:13.923704Z] Loop 10660: Reg: 0.0003, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0006, BotRReg: 0.0004, OV: 0.8632, AltV: 0.8817, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8582, AllV: 0.8817 +[2026-03-20T19:56:22.507243Z] Loop 10670: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0006, BotRReg: 0.0005, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8582, AllV: 0.8816 +[2026-03-20T19:56:31.093427Z] Loop 10680: Reg: 0.0003, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0004, BotRReg: 0.0002, OV: 0.8633, AltV: 0.8818, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8584, AllV: 0.8818 +[2026-03-20T19:56:39.676050Z] Loop 10690: Reg: 0.0004, AltReg: 0.0007, CorReg: 0.0000, TopReg: 0.0011, AllReg: 0.0007, BotRReg: 0.0006, OV: 0.8632, AltV: 0.8815, CorV: 0.8356, TopV: 0.8576, BotRV: 0.8581, AllV: 0.8815 +[2026-03-20T19:56:48.262191Z] Loop 10700: Reg: 0.0009, AltReg: 0.0014, CorReg: 0.0001, TopReg: 0.0021, AllReg: 0.0015, BotRReg: 0.0014, OV: 0.8627, AltV: 0.8808, CorV: 0.8355, TopV: 0.8565, BotRV: 0.8573, AllV: 0.8808 +[2026-03-20T19:56:56.847163Z] Loop 10710: Reg: 0.0026, AltReg: 0.0040, CorReg: 0.0005, TopReg: 0.0041, AllReg: 0.0041, BotRReg: 0.0031, OV: 0.8609, AltV: 0.8782, CorV: 0.8351, TopV: 0.8546, BotRV: 0.8555, AllV: 0.8782 +[2026-03-20T19:57:05.429176Z] Loop 10720: Reg: 0.0031, AltReg: 0.0052, CorReg: 0.0000, TopReg: 0.0173, AllReg: 0.0053, BotRReg: 0.0047, OV: 0.8604, AltV: 0.8770, CorV: 0.8356, TopV: 0.8413, BotRV: 0.8539, AllV: 0.8770 +[2026-03-20T19:57:14.014198Z] Loop 10730: Reg: 0.0014, AltReg: 0.0024, CorReg: 0.0000, TopReg: 0.0013, AllReg: 0.0024, BotRReg: 0.0031, OV: 0.8622, AltV: 0.8798, CorV: 0.8356, TopV: 0.8573, BotRV: 0.8555, AllV: 0.8798 +[2026-03-20T19:57:22.600241Z] Loop 10740: Reg: 0.0003, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0006, BotRReg: 0.0012, OV: 0.8632, AltV: 0.8817, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8574, AllV: 0.8817 +[2026-03-20T19:57:31.189531Z] Loop 10750: Reg: 0.0004, AltReg: 0.0007, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0007, BotRReg: 0.0009, OV: 0.8632, AltV: 0.8815, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8577, AllV: 0.8815 +[2026-03-20T19:57:39.776009Z] Loop 10760: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0010, BotRReg: 0.0011, OV: 0.8630, AltV: 0.8812, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8575, AllV: 0.8812 +[2026-03-20T19:57:48.359983Z] Loop 10770: Reg: 0.0021, AltReg: 0.0035, CorReg: 0.0000, TopReg: 0.0133, AllReg: 0.0035, BotRReg: 0.0021, OV: 0.8615, AltV: 0.8787, CorV: 0.8356, TopV: 0.8453, BotRV: 0.8566, AllV: 0.8787 +[2026-03-20T19:57:56.937122Z] Loop 10780: Reg: 0.0008, AltReg: 0.0013, CorReg: 0.0000, TopReg: 0.0012, AllReg: 0.0013, BotRReg: 0.0022, OV: 0.8628, AltV: 0.8809, CorV: 0.8356, TopV: 0.8574, BotRV: 0.8564, AllV: 0.8809 +[2026-03-20T19:58:05.520384Z] Loop 10790: Reg: 0.0008, AltReg: 0.0013, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0014, BotRReg: 0.0022, OV: 0.8628, AltV: 0.8809, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8565, AllV: 0.8809 +[2026-03-20T19:58:14.102075Z] Loop 10800: Reg: 0.0007, AltReg: 0.0012, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0012, BotRReg: 0.0018, OV: 0.8629, AltV: 0.8810, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8568, AllV: 0.8810 +[2026-03-20T19:58:22.686081Z] Loop 10810: Reg: 0.0006, AltReg: 0.0009, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0010, BotRReg: 0.0017, OV: 0.8630, AltV: 0.8813, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8569, AllV: 0.8813 +[2026-03-20T19:58:31.273100Z] Loop 10820: Reg: 0.0024, AltReg: 0.0041, CorReg: 0.0000, TopReg: 0.0041, AllReg: 0.0041, BotRReg: 0.0124, OV: 0.8611, AltV: 0.8781, CorV: 0.8356, TopV: 0.8545, BotRV: 0.8462, AllV: 0.8782 +[2026-03-20T19:58:39.853407Z] Loop 10830: Reg: 0.0008, AltReg: 0.0013, CorReg: 0.0000, TopReg: 0.0006, AllReg: 0.0013, BotRReg: 0.0022, OV: 0.8628, AltV: 0.8809, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8564, AllV: 0.8809 +[2026-03-20T19:58:48.432154Z] Loop 10840: Reg: 0.0024, AltReg: 0.0039, CorReg: 0.0000, TopReg: 0.0036, AllReg: 0.0040, BotRReg: 0.0049, OV: 0.8612, AltV: 0.8783, CorV: 0.8356, TopV: 0.8550, BotRV: 0.8538, AllV: 0.8783 +[2026-03-20T19:58:57.007354Z] Loop 10850: Reg: 0.0022, AltReg: 0.0037, CorReg: 0.0000, TopReg: 0.0031, AllReg: 0.0037, BotRReg: 0.0041, OV: 0.8614, AltV: 0.8785, CorV: 0.8356, TopV: 0.8555, BotRV: 0.8546, AllV: 0.8785 +[2026-03-20T19:59:05.583778Z] Loop 10860: Reg: 0.0007, AltReg: 0.0012, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0012, BotRReg: 0.0016, OV: 0.8629, AltV: 0.8810, CorV: 0.8356, TopV: 0.8580, BotRV: 0.8570, AllV: 0.8810 +[2026-03-20T19:59:14.168289Z] Loop 10870: Reg: 0.0003, AltReg: 0.0005, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0005, BotRReg: 0.0015, OV: 0.8633, AltV: 0.8817, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8571, AllV: 0.8817 +[2026-03-20T19:59:22.748396Z] Loop 10880: Reg: 0.0003, AltReg: 0.0005, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0005, BotRReg: 0.0017, OV: 0.8633, AltV: 0.8817, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8569, AllV: 0.8817 +[2026-03-20T19:59:31.336491Z] Loop 10890: Reg: 0.0009, AltReg: 0.0015, CorReg: 0.0000, TopReg: 0.0041, AllReg: 0.0016, BotRReg: 0.0013, OV: 0.8627, AltV: 0.8807, CorV: 0.8356, TopV: 0.8545, BotRV: 0.8574, AllV: 0.8807 +[2026-03-20T19:59:39.917646Z] Loop 10900: Reg: 0.0005, AltReg: 0.0008, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0008, BotRReg: 0.0013, OV: 0.8631, AltV: 0.8814, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8574, AllV: 0.8814 +[2026-03-20T19:59:48.505271Z] Loop 10910: Reg: 0.0018, AltReg: 0.0029, CorReg: 0.0001, TopReg: 0.0022, AllReg: 0.0030, BotRReg: 0.0023, OV: 0.8618, AltV: 0.8793, CorV: 0.8356, TopV: 0.8565, BotRV: 0.8564, AllV: 0.8793 +[2026-03-20T19:59:57.087532Z] Loop 10920: Reg: 0.0032, AltReg: 0.0053, CorReg: 0.0001, TopReg: 0.0140, AllReg: 0.0053, BotRReg: 0.0022, OV: 0.8604, AltV: 0.8769, CorV: 0.8355, TopV: 0.8446, BotRV: 0.8565, AllV: 0.8769 +[2026-03-20T20:00:05.668985Z] Loop 10930: Reg: 0.0009, AltReg: 0.0015, CorReg: 0.0000, TopReg: 0.0009, AllReg: 0.0015, BotRReg: 0.0019, OV: 0.8627, AltV: 0.8807, CorV: 0.8356, TopV: 0.8578, BotRV: 0.8568, AllV: 0.8808 +[2026-03-20T20:00:14.249969Z] Loop 10940: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0007, BotRReg: 0.0013, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8573, AllV: 0.8816 +[2026-03-20T20:00:22.836061Z] Loop 10950: Reg: 0.0005, AltReg: 0.0008, CorReg: 0.0000, TopReg: 0.0006, AllReg: 0.0008, BotRReg: 0.0005, OV: 0.8631, AltV: 0.8814, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8581, AllV: 0.8815 +[2026-03-20T20:00:31.418118Z] Loop 10960: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0010, BotRReg: 0.0003, OV: 0.8630, AltV: 0.8812, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8583, AllV: 0.8812 +[2026-03-20T20:00:39.999094Z] Loop 10970: Reg: 0.0007, AltReg: 0.0011, CorReg: 0.0000, TopReg: 0.0008, AllReg: 0.0011, BotRReg: 0.0003, OV: 0.8629, AltV: 0.8811, CorV: 0.8356, TopV: 0.8578, BotRV: 0.8583, AllV: 0.8812 +[2026-03-20T20:00:48.579785Z] Loop 10980: Reg: 0.0025, AltReg: 0.0041, CorReg: 0.0001, TopReg: 0.0083, AllReg: 0.0041, BotRReg: 0.0005, OV: 0.8611, AltV: 0.8781, CorV: 0.8356, TopV: 0.8503, BotRV: 0.8582, AllV: 0.8781 +[2026-03-20T20:00:57.159228Z] Loop 10990: Reg: 0.0001, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0002, BotRReg: 0.0005, OV: 0.8634, AltV: 0.8820, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8581, AllV: 0.8820 +[2026-03-20T20:01:05.741101Z] Loop 11000: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0003, BotRReg: 0.0004, OV: 0.8634, AltV: 0.8819, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8582, AllV: 0.8820 +[2026-03-20T20:01:14.321437Z] Loop 11010: Reg: 0.0003, AltReg: 0.0005, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0005, BotRReg: 0.0005, OV: 0.8633, AltV: 0.8817, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8581, AllV: 0.8817 +[2026-03-20T20:01:22.912437Z] Loop 11020: Reg: 0.0028, AltReg: 0.0047, CorReg: 0.0000, TopReg: 0.0031, AllReg: 0.0046, BotRReg: 0.0060, OV: 0.8608, AltV: 0.8776, CorV: 0.8356, TopV: 0.8555, BotRV: 0.8526, AllV: 0.8776 +[2026-03-20T20:01:31.496747Z] Loop 11030: Reg: 0.0005, AltReg: 0.0009, CorReg: 0.0000, TopReg: 0.0008, AllReg: 0.0009, BotRReg: 0.0011, OV: 0.8631, AltV: 0.8813, CorV: 0.8356, TopV: 0.8578, BotRV: 0.8575, AllV: 0.8814 +[2026-03-20T20:01:40.077956Z] Loop 11040: Reg: 0.0007, AltReg: 0.0012, CorReg: 0.0000, TopReg: 0.0056, AllReg: 0.0012, BotRReg: 0.0003, OV: 0.8628, AltV: 0.8810, CorV: 0.8356, TopV: 0.8530, BotRV: 0.8583, AllV: 0.8810 +[2026-03-20T20:01:48.663085Z] Loop 11050: Reg: 0.0001, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0002, BotRReg: 0.0010, OV: 0.8634, AltV: 0.8820, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8576, AllV: 0.8820 +[2026-03-20T20:01:57.243559Z] Loop 11060: Reg: 0.0018, AltReg: 0.0030, CorReg: -0.0000, TopReg: 0.0061, AllReg: 0.0030, BotRReg: 0.0059, OV: 0.8618, AltV: 0.8792, CorV: 0.8356, TopV: 0.8525, BotRV: 0.8527, AllV: 0.8792 +[2026-03-20T20:02:05.824683Z] Loop 11070: Reg: 0.0003, AltReg: 0.0005, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0005, BotRReg: 0.0010, OV: 0.8633, AltV: 0.8817, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8576, AllV: 0.8817 +[2026-03-20T20:02:14.407762Z] Loop 11080: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0003, BotRReg: 0.0006, OV: 0.8634, AltV: 0.8819, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8580, AllV: 0.8819 +[2026-03-20T20:02:22.999051Z] Loop 11090: Reg: 0.0007, AltReg: 0.0011, CorReg: 0.0000, TopReg: 0.0016, AllReg: 0.0011, BotRReg: 0.0021, OV: 0.8629, AltV: 0.8811, CorV: 0.8356, TopV: 0.8570, BotRV: 0.8566, AllV: 0.8812 +[2026-03-20T20:02:31.588705Z] Loop 11100: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0010, BotRReg: 0.0023, OV: 0.8630, AltV: 0.8812, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8563, AllV: 0.8813 +[2026-03-20T20:02:40.174606Z] Loop 11110: Reg: 0.0010, AltReg: 0.0017, CorReg: 0.0000, TopReg: 0.0019, AllReg: 0.0017, BotRReg: 0.0014, OV: 0.8625, AltV: 0.8805, CorV: 0.8356, TopV: 0.8567, BotRV: 0.8572, AllV: 0.8805 +[2026-03-20T20:02:48.756264Z] Loop 11120: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0000, TopReg: 0.0015, AllReg: 0.0010, BotRReg: 0.0006, OV: 0.8630, AltV: 0.8812, CorV: 0.8356, TopV: 0.8571, BotRV: 0.8581, AllV: 0.8813 +[2026-03-20T20:02:57.333232Z] Loop 11130: Reg: 0.0019, AltReg: 0.0030, CorReg: 0.0003, TopReg: 0.0125, AllReg: 0.0030, BotRReg: 0.0008, OV: 0.8617, AltV: 0.8792, CorV: 0.8354, TopV: 0.8461, BotRV: 0.8578, AllV: 0.8793 +[2026-03-20T20:03:05.912218Z] Loop 11140: Reg: 0.0003, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0006, BotRReg: 0.0005, OV: 0.8632, AltV: 0.8817, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8581, AllV: 0.8817 +[2026-03-20T20:03:14.493699Z] Loop 11150: Reg: 0.0025, AltReg: 0.0042, CorReg: 0.0000, TopReg: 0.0198, AllReg: 0.0042, BotRReg: 0.0034, OV: 0.8610, AltV: 0.8780, CorV: 0.8356, TopV: 0.8388, BotRV: 0.8553, AllV: 0.8780 +[2026-03-20T20:03:23.071591Z] Loop 11160: Reg: 0.0013, AltReg: 0.0022, CorReg: 0.0000, TopReg: 0.0046, AllReg: 0.0022, BotRReg: 0.0053, OV: 0.8622, AltV: 0.8800, CorV: 0.8356, TopV: 0.8540, BotRV: 0.8533, AllV: 0.8800 +[2026-03-20T20:03:31.649381Z] Loop 11170: Reg: 0.0013, AltReg: 0.0021, CorReg: 0.0000, TopReg: 0.0020, AllReg: 0.0021, BotRReg: 0.0072, OV: 0.8623, AltV: 0.8801, CorV: 0.8356, TopV: 0.8566, BotRV: 0.8515, AllV: 0.8801 +[2026-03-20T20:03:40.225784Z] Loop 11180: Reg: 0.0012, AltReg: 0.0020, CorReg: 0.0000, TopReg: 0.0073, AllReg: 0.0020, BotRReg: 0.0013, OV: 0.8624, AltV: 0.8802, CorV: 0.8356, TopV: 0.8514, BotRV: 0.8573, AllV: 0.8802 +[2026-03-20T20:03:48.803197Z] Loop 11190: Reg: 0.0009, AltReg: 0.0014, CorReg: 0.0001, TopReg: 0.0023, AllReg: 0.0014, BotRReg: 0.0015, OV: 0.8627, AltV: 0.8808, CorV: 0.8356, TopV: 0.8564, BotRV: 0.8571, AllV: 0.8808 +[2026-03-20T20:03:57.383534Z] Loop 11200: Reg: 0.0007, AltReg: 0.0011, CorReg: 0.0001, TopReg: 0.0010, AllReg: 0.0011, BotRReg: 0.0015, OV: 0.8629, AltV: 0.8812, CorV: 0.8356, TopV: 0.8577, BotRV: 0.8571, AllV: 0.8812 +[2026-03-20T20:04:05.965275Z] Loop 11210: Reg: 0.0004, AltReg: 0.0007, CorReg: 0.0001, TopReg: 0.0005, AllReg: 0.0007, BotRReg: 0.0012, OV: 0.8631, AltV: 0.8815, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8574, AllV: 0.8816 +[2026-03-20T20:04:14.545911Z] Loop 11220: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0006, BotRReg: 0.0023, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8563, AllV: 0.8817 +[2026-03-20T20:04:23.127236Z] Loop 11230: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0000, TopReg: 0.0011, AllReg: 0.0010, BotRReg: 0.0015, OV: 0.8630, AltV: 0.8813, CorV: 0.8356, TopV: 0.8575, BotRV: 0.8572, AllV: 0.8813 +[2026-03-20T20:04:31.708660Z] Loop 11240: Reg: 0.0043, AltReg: 0.0071, CorReg: 0.0002, TopReg: 0.0057, AllReg: 0.0071, BotRReg: 0.0071, OV: 0.8592, AltV: 0.8751, CorV: 0.8354, TopV: 0.8529, BotRV: 0.8515, AllV: 0.8751 +[2026-03-20T20:04:40.294184Z] Loop 11250: Reg: 0.0010, AltReg: 0.0016, CorReg: 0.0000, TopReg: 0.0006, AllReg: 0.0016, BotRReg: 0.0016, OV: 0.8626, AltV: 0.8806, CorV: 0.8356, TopV: 0.8580, BotRV: 0.8570, AllV: 0.8806 +[2026-03-20T20:04:48.873517Z] Loop 11260: Reg: 0.0008, AltReg: 0.0013, CorReg: 0.0001, TopReg: 0.0005, AllReg: 0.0013, BotRReg: 0.0011, OV: 0.8628, AltV: 0.8810, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8575, AllV: 0.8810 +[2026-03-20T20:04:57.453484Z] Loop 11270: Reg: 0.0005, AltReg: 0.0008, CorReg: 0.0001, TopReg: 0.0006, AllReg: 0.0008, BotRReg: 0.0008, OV: 0.8631, AltV: 0.8814, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8578, AllV: 0.8814 +[2026-03-20T20:05:06.044440Z] Loop 11280: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0003, BotRReg: 0.0007, OV: 0.8634, AltV: 0.8819, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8580, AllV: 0.8820 +[2026-03-20T20:05:14.626185Z] Loop 11290: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0003, BotRReg: 0.0007, OV: 0.8634, AltV: 0.8819, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8579, AllV: 0.8819 +[2026-03-20T20:05:23.205411Z] Loop 11300: Reg: 0.0004, AltReg: 0.0007, CorReg: 0.0000, TopReg: 0.0011, AllReg: 0.0007, BotRReg: 0.0010, OV: 0.8632, AltV: 0.8815, CorV: 0.8356, TopV: 0.8575, BotRV: 0.8577, AllV: 0.8816 +[2026-03-20T20:05:31.785085Z] Loop 11310: Reg: 0.0029, AltReg: 0.0048, CorReg: 0.0000, TopReg: 0.0063, AllReg: 0.0048, BotRReg: 0.0265, OV: 0.8607, AltV: 0.8774, CorV: 0.8356, TopV: 0.8524, BotRV: 0.8321, AllV: 0.8775 +[2026-03-20T20:05:40.368304Z] Loop 11320: Reg: 0.0006, AltReg: 0.0009, CorReg: 0.0000, TopReg: 0.0021, AllReg: 0.0009, BotRReg: 0.0017, OV: 0.8630, AltV: 0.8813, CorV: 0.8356, TopV: 0.8566, BotRV: 0.8569, AllV: 0.8813 +[2026-03-20T20:05:48.947460Z] Loop 11330: Reg: 0.0003, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0004, BotRReg: 0.0006, OV: 0.8633, AltV: 0.8818, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8581, AllV: 0.8818 +[2026-03-20T20:05:57.530142Z] Loop 11340: Reg: 0.0027, AltReg: 0.0045, CorReg: 0.0000, TopReg: 0.0074, AllReg: 0.0045, BotRReg: 0.0106, OV: 0.8609, AltV: 0.8777, CorV: 0.8356, TopV: 0.8513, BotRV: 0.8480, AllV: 0.8778 +[2026-03-20T20:06:06.112524Z] Loop 11350: Reg: 0.0008, AltReg: 0.0014, CorReg: 0.0000, TopReg: 0.0027, AllReg: 0.0014, BotRReg: 0.0019, OV: 0.8627, AltV: 0.8808, CorV: 0.8356, TopV: 0.8559, BotRV: 0.8567, AllV: 0.8808 +[2026-03-20T20:06:14.693181Z] Loop 11360: Reg: 0.0015, AltReg: 0.0024, CorReg: 0.0000, TopReg: 0.0037, AllReg: 0.0024, BotRReg: 0.0031, OV: 0.8621, AltV: 0.8798, CorV: 0.8356, TopV: 0.8549, BotRV: 0.8555, AllV: 0.8798 +[2026-03-20T20:06:23.270522Z] Loop 11370: Reg: 0.0005, AltReg: 0.0008, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0008, BotRReg: 0.0004, OV: 0.8631, AltV: 0.8814, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8582, AllV: 0.8814 +[2026-03-20T20:06:31.864340Z] Loop 11380: Reg: 0.0005, AltReg: 0.0008, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0008, BotRReg: 0.0006, OV: 0.8631, AltV: 0.8814, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8580, AllV: 0.8815 +[2026-03-20T20:06:40.447375Z] Loop 11390: Reg: 0.0010, AltReg: 0.0015, CorReg: 0.0002, TopReg: 0.0006, AllReg: 0.0015, BotRReg: 0.0025, OV: 0.8626, AltV: 0.8807, CorV: 0.8355, TopV: 0.8581, BotRV: 0.8561, AllV: 0.8808 +[2026-03-20T20:06:49.030655Z] Loop 11400: Reg: 0.0018, AltReg: 0.0029, CorReg: 0.0001, TopReg: 0.0010, AllReg: 0.0029, BotRReg: 0.0077, OV: 0.8618, AltV: 0.8793, CorV: 0.8355, TopV: 0.8576, BotRV: 0.8509, AllV: 0.8793 +[2026-03-20T20:06:57.617689Z] Loop 11410: Reg: 0.0010, AltReg: 0.0016, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0017, BotRReg: 0.0059, OV: 0.8626, AltV: 0.8806, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8527, AllV: 0.8806 +[2026-03-20T20:07:06.198856Z] Loop 11420: Reg: 0.0007, AltReg: 0.0012, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0012, BotRReg: 0.0021, OV: 0.8629, AltV: 0.8811, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8565, AllV: 0.8811 +[2026-03-20T20:07:14.781201Z] Loop 11430: Reg: 0.0007, AltReg: 0.0012, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0012, BotRReg: 0.0014, OV: 0.8628, AltV: 0.8810, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8572, AllV: 0.8810 +[2026-03-20T20:07:23.361397Z] Loop 11440: Reg: 0.0032, AltReg: 0.0041, CorReg: 0.0019, TopReg: 0.0140, AllReg: 0.0041, BotRReg: 0.0066, OV: 0.8604, AltV: 0.8781, CorV: 0.8337, TopV: 0.8446, BotRV: 0.8521, AllV: 0.8781 +[2026-03-20T20:07:31.938657Z] Loop 11450: Reg: 0.0009, AltReg: 0.0013, CorReg: 0.0003, TopReg: 0.0030, AllReg: 0.0013, BotRReg: 0.0022, OV: 0.8627, AltV: 0.8809, CorV: 0.8353, TopV: 0.8557, BotRV: 0.8564, AllV: 0.8809 +[2026-03-20T20:07:40.517557Z] Loop 11460: Reg: 0.0016, AltReg: 0.0026, CorReg: 0.0001, TopReg: 0.0137, AllReg: 0.0026, BotRReg: 0.0007, OV: 0.8620, AltV: 0.8796, CorV: 0.8356, TopV: 0.8449, BotRV: 0.8580, AllV: 0.8797 +[2026-03-20T20:07:49.095835Z] Loop 11470: Reg: 0.0024, AltReg: 0.0039, CorReg: 0.0001, TopReg: 0.0127, AllReg: 0.0039, BotRReg: 0.0008, OV: 0.8612, AltV: 0.8783, CorV: 0.8355, TopV: 0.8459, BotRV: 0.8578, AllV: 0.8784 +[2026-03-20T20:07:57.678505Z] Loop 11480: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0001, TopReg: 0.0009, AllReg: 0.0010, BotRReg: 0.0017, OV: 0.8630, AltV: 0.8812, CorV: 0.8356, TopV: 0.8577, BotRV: 0.8569, AllV: 0.8812 +[2026-03-20T20:08:06.264427Z] Loop 11490: Reg: 0.0019, AltReg: 0.0030, CorReg: 0.0002, TopReg: 0.0020, AllReg: 0.0030, BotRReg: 0.0124, OV: 0.8617, AltV: 0.8792, CorV: 0.8354, TopV: 0.8567, BotRV: 0.8463, AllV: 0.8792 +[2026-03-20T20:08:14.841625Z] Loop 11500: Reg: 0.0010, AltReg: 0.0016, CorReg: 0.0000, TopReg: 0.0018, AllReg: 0.0016, BotRReg: 0.0055, OV: 0.8626, AltV: 0.8806, CorV: 0.8356, TopV: 0.8569, BotRV: 0.8532, AllV: 0.8806 +[2026-03-20T20:08:23.427916Z] Loop 11510: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0000, TopReg: 0.0012, AllReg: 0.0010, BotRReg: 0.0025, OV: 0.8630, AltV: 0.8812, CorV: 0.8356, TopV: 0.8575, BotRV: 0.8561, AllV: 0.8812 +[2026-03-20T20:08:32.006374Z] Loop 11520: Reg: 0.0008, AltReg: 0.0013, CorReg: 0.0000, TopReg: 0.0029, AllReg: 0.0014, BotRReg: 0.0024, OV: 0.8628, AltV: 0.8809, CorV: 0.8356, TopV: 0.8558, BotRV: 0.8563, AllV: 0.8809 +[2026-03-20T20:08:40.588402Z] Loop 11530: Reg: 0.0023, AltReg: 0.0038, CorReg: 0.0000, TopReg: 0.0085, AllReg: 0.0039, BotRReg: 0.0116, OV: 0.8613, AltV: 0.8784, CorV: 0.8356, TopV: 0.8501, BotRV: 0.8471, AllV: 0.8784 +[2026-03-20T20:08:49.164354Z] Loop 11540: Reg: 0.0013, AltReg: 0.0021, CorReg: 0.0000, TopReg: 0.0029, AllReg: 0.0022, BotRReg: 0.0050, OV: 0.8623, AltV: 0.8801, CorV: 0.8356, TopV: 0.8557, BotRV: 0.8536, AllV: 0.8801 +[2026-03-20T20:08:57.744392Z] Loop 11550: Reg: 0.0008, AltReg: 0.0014, CorReg: 0.0000, TopReg: 0.0025, AllReg: 0.0014, BotRReg: 0.0026, OV: 0.8628, AltV: 0.8809, CorV: 0.8356, TopV: 0.8561, BotRV: 0.8560, AllV: 0.8809 +[2026-03-20T20:09:06.330578Z] Loop 11560: Reg: 0.0008, AltReg: 0.0014, CorReg: 0.0000, TopReg: 0.0009, AllReg: 0.0014, BotRReg: 0.0015, OV: 0.8627, AltV: 0.8808, CorV: 0.8356, TopV: 0.8577, BotRV: 0.8571, AllV: 0.8808 +[2026-03-20T20:09:14.916364Z] Loop 11570: Reg: 0.0015, AltReg: 0.0024, CorReg: 0.0000, TopReg: 0.0009, AllReg: 0.0024, BotRReg: 0.0018, OV: 0.8621, AltV: 0.8798, CorV: 0.8356, TopV: 0.8577, BotRV: 0.8569, AllV: 0.8798 +[2026-03-20T20:09:23.498850Z] Loop 11580: Reg: 0.0017, AltReg: 0.0029, CorReg: 0.0000, TopReg: 0.0012, AllReg: 0.0029, BotRReg: 0.0020, OV: 0.8619, AltV: 0.8794, CorV: 0.8356, TopV: 0.8574, BotRV: 0.8567, AllV: 0.8794 +[2026-03-20T20:09:32.083387Z] Loop 11590: Reg: 0.0009, AltReg: 0.0015, CorReg: 0.0000, TopReg: 0.0015, AllReg: 0.0015, BotRReg: 0.0022, OV: 0.8627, AltV: 0.8808, CorV: 0.8356, TopV: 0.8571, BotRV: 0.8564, AllV: 0.8808 +[2026-03-20T20:09:40.670231Z] Loop 11600: Reg: 0.0011, AltReg: 0.0019, CorReg: 0.0000, TopReg: 0.0025, AllReg: 0.0019, BotRReg: 0.0030, OV: 0.8624, AltV: 0.8803, CorV: 0.8356, TopV: 0.8561, BotRV: 0.8557, AllV: 0.8803 +[2026-03-20T20:09:49.258036Z] Loop 11610: Reg: 0.0048, AltReg: 0.0080, CorReg: 0.0000, TopReg: 0.0167, AllReg: 0.0080, BotRReg: 0.0348, OV: 0.8588, AltV: 0.8742, CorV: 0.8356, TopV: 0.8419, BotRV: 0.8239, AllV: 0.8743 +[2026-03-20T20:09:57.839040Z] Loop 11620: Reg: 0.0003, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0006, BotRReg: 0.0008, OV: 0.8632, AltV: 0.8817, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8578, AllV: 0.8817 +[2026-03-20T20:10:06.427649Z] Loop 11630: Reg: 0.0015, AltReg: 0.0023, CorReg: 0.0001, TopReg: 0.0032, AllReg: 0.0023, BotRReg: 0.0029, OV: 0.8621, AltV: 0.8799, CorV: 0.8355, TopV: 0.8554, BotRV: 0.8557, AllV: 0.8799 +[2026-03-20T20:10:15.028708Z] Loop 11640: Reg: 0.0013, AltReg: 0.0020, CorReg: 0.0002, TopReg: 0.0036, AllReg: 0.0020, BotRReg: 0.0025, OV: 0.8623, AltV: 0.8802, CorV: 0.8354, TopV: 0.8550, BotRV: 0.8562, AllV: 0.8803 +[2026-03-20T20:10:23.611521Z] Loop 11650: Reg: 0.0008, AltReg: 0.0013, CorReg: 0.0000, TopReg: 0.0012, AllReg: 0.0013, BotRReg: 0.0019, OV: 0.8628, AltV: 0.8810, CorV: 0.8356, TopV: 0.8574, BotRV: 0.8567, AllV: 0.8810 +[2026-03-20T20:10:32.193278Z] Loop 11660: Reg: 0.0007, AltReg: 0.0012, CorReg: 0.0000, TopReg: 0.0012, AllReg: 0.0012, BotRReg: 0.0016, OV: 0.8628, AltV: 0.8810, CorV: 0.8356, TopV: 0.8574, BotRV: 0.8570, AllV: 0.8810 +[2026-03-20T20:10:40.772127Z] Loop 11670: Reg: 0.0010, AltReg: 0.0017, CorReg: 0.0000, TopReg: 0.0014, AllReg: 0.0018, BotRReg: 0.0027, OV: 0.8625, AltV: 0.8805, CorV: 0.8356, TopV: 0.8572, BotRV: 0.8559, AllV: 0.8805 +[2026-03-20T20:10:49.356443Z] Loop 11680: Reg: 0.0014, AltReg: 0.0023, CorReg: 0.0000, TopReg: 0.0018, AllReg: 0.0023, BotRReg: 0.0030, OV: 0.8622, AltV: 0.8799, CorV: 0.8356, TopV: 0.8568, BotRV: 0.8556, AllV: 0.8799 +[2026-03-20T20:10:57.934686Z] Loop 11690: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0010, BotRReg: 0.0012, OV: 0.8630, AltV: 0.8812, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8574, AllV: 0.8812 +[2026-03-20T20:11:06.519102Z] Loop 11700: Reg: 0.0060, AltReg: 0.0099, CorReg: 0.0000, TopReg: 0.0181, AllReg: 0.0099, BotRReg: 0.0062, OV: 0.8576, AltV: 0.8723, CorV: 0.8356, TopV: 0.8406, BotRV: 0.8524, AllV: 0.8723 +[2026-03-20T20:11:15.099712Z] Loop 11710: Reg: 0.0009, AltReg: 0.0016, CorReg: 0.0000, TopReg: 0.0006, AllReg: 0.0016, BotRReg: 0.0023, OV: 0.8626, AltV: 0.8806, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8563, AllV: 0.8807 +[2026-03-20T20:11:23.676774Z] Loop 11720: Reg: 0.0003, AltReg: 0.0005, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0005, BotRReg: 0.0008, OV: 0.8633, AltV: 0.8817, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8579, AllV: 0.8817 +[2026-03-20T20:11:32.256908Z] Loop 11730: Reg: 0.0019, AltReg: 0.0031, CorReg: 0.0000, TopReg: 0.0057, AllReg: 0.0031, BotRReg: 0.0011, OV: 0.8617, AltV: 0.8792, CorV: 0.8356, TopV: 0.8529, BotRV: 0.8575, AllV: 0.8792 +[2026-03-20T20:11:40.836564Z] Loop 11740: Reg: 0.0006, AltReg: 0.0009, CorReg: 0.0000, TopReg: 0.0008, AllReg: 0.0009, BotRReg: 0.0005, OV: 0.8630, AltV: 0.8813, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8581, AllV: 0.8813 +[2026-03-20T20:11:49.417038Z] Loop 11750: Reg: 0.0004, AltReg: 0.0007, CorReg: 0.0000, TopReg: 0.0006, AllReg: 0.0007, BotRReg: 0.0013, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8580, BotRV: 0.8573, AllV: 0.8816 +[2026-03-20T20:11:58.002800Z] Loop 11760: Reg: 0.0019, AltReg: 0.0030, CorReg: 0.0002, TopReg: 0.0023, AllReg: 0.0030, BotRReg: 0.0091, OV: 0.8617, AltV: 0.8792, CorV: 0.8354, TopV: 0.8563, BotRV: 0.8495, AllV: 0.8793 +[2026-03-20T20:12:06.581605Z] Loop 11770: Reg: 0.0037, AltReg: 0.0052, CorReg: 0.0014, TopReg: 0.0090, AllReg: 0.0052, BotRReg: 0.0057, OV: 0.8599, AltV: 0.8770, CorV: 0.8342, TopV: 0.8496, BotRV: 0.8529, AllV: 0.8770 +[2026-03-20T20:12:15.167702Z] Loop 11780: Reg: 0.0039, AltReg: 0.0062, CorReg: 0.0004, TopReg: 0.0069, AllReg: 0.0062, BotRReg: 0.0055, OV: 0.8597, AltV: 0.8760, CorV: 0.8352, TopV: 0.8518, BotRV: 0.8532, AllV: 0.8761 +[2026-03-20T20:12:23.743537Z] Loop 11790: Reg: 0.0007, AltReg: 0.0011, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0012, BotRReg: 0.0042, OV: 0.8629, AltV: 0.8811, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8545, AllV: 0.8811 +[2026-03-20T20:12:32.326527Z] Loop 11800: Reg: 0.0012, AltReg: 0.0019, CorReg: 0.0002, TopReg: 0.0014, AllReg: 0.0019, BotRReg: 0.0063, OV: 0.8624, AltV: 0.8804, CorV: 0.8354, TopV: 0.8572, BotRV: 0.8523, AllV: 0.8804 +[2026-03-20T20:12:40.911500Z] Loop 11810: Reg: 0.0002, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0004, BotRReg: 0.0006, OV: 0.8634, AltV: 0.8818, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8580, AllV: 0.8819 +[2026-03-20T20:12:49.502359Z] Loop 11820: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0008, AllReg: 0.0006, BotRReg: 0.0006, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8578, BotRV: 0.8580, AllV: 0.8816 +[2026-03-20T20:12:58.087913Z] Loop 11830: Reg: 0.0066, AltReg: 0.0110, CorReg: 0.0000, TopReg: 0.0024, AllReg: 0.0111, BotRReg: 0.0273, OV: 0.8570, AltV: 0.8712, CorV: 0.8356, TopV: 0.8562, BotRV: 0.8313, AllV: 0.8711 +[2026-03-20T20:13:06.669922Z] Loop 11840: Reg: 0.0015, AltReg: 0.0026, CorReg: 0.0000, TopReg: 0.0015, AllReg: 0.0026, BotRReg: 0.0013, OV: 0.8620, AltV: 0.8796, CorV: 0.8356, TopV: 0.8571, BotRV: 0.8573, AllV: 0.8797 +[2026-03-20T20:13:15.248102Z] Loop 11850: Reg: 0.0012, AltReg: 0.0020, CorReg: 0.0000, TopReg: 0.0021, AllReg: 0.0020, BotRReg: 0.0007, OV: 0.8624, AltV: 0.8803, CorV: 0.8356, TopV: 0.8566, BotRV: 0.8579, AllV: 0.8803 +[2026-03-20T20:13:23.826803Z] Loop 11860: Reg: 0.0003, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0004, BotRReg: 0.0003, OV: 0.8633, AltV: 0.8818, CorV: 0.8356, TopV: 0.8580, BotRV: 0.8584, AllV: 0.8818 +[2026-03-20T20:13:32.411237Z] Loop 11870: Reg: 0.0005, AltReg: 0.0008, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0008, BotRReg: 0.0016, OV: 0.8631, AltV: 0.8814, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8570, AllV: 0.8815 +[2026-03-20T20:13:40.991553Z] Loop 11880: Reg: 0.0016, AltReg: 0.0026, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0027, BotRReg: 0.0037, OV: 0.8620, AltV: 0.8796, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8549, AllV: 0.8796 +[2026-03-20T20:13:49.575363Z] Loop 11890: Reg: 0.0016, AltReg: 0.0026, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0026, BotRReg: 0.0043, OV: 0.8620, AltV: 0.8796, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8543, AllV: 0.8796 +[2026-03-20T20:13:58.157585Z] Loop 11900: Reg: 0.0003, AltReg: 0.0005, CorReg: 0.0000, TopReg: 0.0010, AllReg: 0.0005, BotRReg: 0.0004, OV: 0.8633, AltV: 0.8817, CorV: 0.8356, TopV: 0.8576, BotRV: 0.8583, AllV: 0.8818 +[2026-03-20T20:14:06.743702Z] Loop 11910: Reg: 0.0008, AltReg: 0.0014, CorReg: 0.0000, TopReg: 0.0086, AllReg: 0.0014, BotRReg: 0.0004, OV: 0.8627, AltV: 0.8808, CorV: 0.8356, TopV: 0.8500, BotRV: 0.8582, AllV: 0.8809 +[2026-03-20T20:14:15.327326Z] Loop 11920: Reg: 0.0003, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0012, AllReg: 0.0006, BotRReg: 0.0009, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8574, BotRV: 0.8577, AllV: 0.8817 +[2026-03-20T20:14:23.906488Z] Loop 11930: Reg: 0.0005, AltReg: 0.0008, CorReg: 0.0000, TopReg: 0.0010, AllReg: 0.0008, BotRReg: 0.0017, OV: 0.8631, AltV: 0.8815, CorV: 0.8356, TopV: 0.8577, BotRV: 0.8569, AllV: 0.8815 +[2026-03-20T20:14:32.491670Z] Loop 11940: Reg: 0.0007, AltReg: 0.0010, CorReg: 0.0002, TopReg: 0.0018, AllReg: 0.0010, BotRReg: 0.0017, OV: 0.8629, AltV: 0.8812, CorV: 0.8354, TopV: 0.8568, BotRV: 0.8570, AllV: 0.8813 +[2026-03-20T20:14:41.074906Z] Loop 11950: Reg: 0.0041, AltReg: 0.0030, CorReg: 0.0058, TopReg: 0.0122, AllReg: 0.0030, BotRReg: 0.0028, OV: 0.8595, AltV: 0.8792, CorV: 0.8299, TopV: 0.8464, BotRV: 0.8558, AllV: 0.8792 +[2026-03-20T20:14:49.653896Z] Loop 11960: Reg: 0.0005, AltReg: 0.0007, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0007, BotRReg: 0.0023, OV: 0.8631, AltV: 0.8815, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8563, AllV: 0.8815 +[2026-03-20T20:14:58.241622Z] Loop 11970: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0010, AllReg: 0.0006, BotRReg: 0.0012, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8576, BotRV: 0.8575, AllV: 0.8816 +[2026-03-20T20:15:06.827564Z] Loop 11980: Reg: 0.0005, AltReg: 0.0008, CorReg: 0.0000, TopReg: 0.0012, AllReg: 0.0008, BotRReg: 0.0004, OV: 0.8631, AltV: 0.8814, CorV: 0.8356, TopV: 0.8574, BotRV: 0.8582, AllV: 0.8815 +[2026-03-20T20:15:15.419698Z] Loop 11990: Reg: 0.0005, AltReg: 0.0009, CorReg: 0.0000, TopReg: 0.0012, AllReg: 0.0009, BotRReg: 0.0003, OV: 0.8630, AltV: 0.8813, CorV: 0.8356, TopV: 0.8574, BotRV: 0.8583, AllV: 0.8813 +[2026-03-20T20:15:24.003855Z] Loop 12000: Reg: 0.0010, AltReg: 0.0017, CorReg: 0.0000, TopReg: 0.0015, AllReg: 0.0017, BotRReg: 0.0003, OV: 0.8626, AltV: 0.8805, CorV: 0.8356, TopV: 0.8571, BotRV: 0.8583, AllV: 0.8805 +[2026-03-20T20:15:32.595088Z] Loop 12010: Reg: 0.0002, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0004, BotRReg: 0.0004, OV: 0.8634, AltV: 0.8818, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8583, AllV: 0.8819 +[2026-03-20T20:15:41.175179Z] Loop 12020: Reg: 0.0019, AltReg: 0.0031, CorReg: 0.0000, TopReg: 0.0017, AllReg: 0.0031, BotRReg: 0.0143, OV: 0.8617, AltV: 0.8791, CorV: 0.8356, TopV: 0.8569, BotRV: 0.8444, AllV: 0.8791 +[2026-03-20T20:15:49.759337Z] Loop 12030: Reg: 0.0029, AltReg: 0.0049, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0049, BotRReg: 0.0237, OV: 0.8606, AltV: 0.8773, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8349, AllV: 0.8774 +[2026-03-20T20:15:58.343160Z] Loop 12040: Reg: 0.0017, AltReg: 0.0029, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0029, BotRReg: 0.0156, OV: 0.8619, AltV: 0.8793, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8430, AllV: 0.8794 +[2026-03-20T20:16:06.931745Z] Loop 12050: Reg: 0.0003, AltReg: 0.0005, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0005, BotRReg: 0.0018, OV: 0.8633, AltV: 0.8817, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8569, AllV: 0.8818 +[2026-03-20T20:16:15.512688Z] Loop 12060: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0003, BotRReg: 0.0008, OV: 0.8634, AltV: 0.8819, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8578, AllV: 0.8820 +[2026-03-20T20:16:24.092263Z] Loop 12070: Reg: 0.0004, AltReg: 0.0007, CorReg: 0.0000, TopReg: 0.0011, AllReg: 0.0007, BotRReg: 0.0005, OV: 0.8631, AltV: 0.8815, CorV: 0.8356, TopV: 0.8575, BotRV: 0.8582, AllV: 0.8815 +[2026-03-20T20:16:32.675218Z] Loop 12080: Reg: 0.0011, AltReg: 0.0018, CorReg: 0.0000, TopReg: 0.0022, AllReg: 0.0018, BotRReg: 0.0003, OV: 0.8625, AltV: 0.8805, CorV: 0.8356, TopV: 0.8564, BotRV: 0.8583, AllV: 0.8805 +[2026-03-20T20:16:41.260600Z] Loop 12090: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0003, BotRReg: 0.0006, OV: 0.8634, AltV: 0.8819, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8581, AllV: 0.8819 +[2026-03-20T20:16:49.849761Z] Loop 12100: Reg: 0.0005, AltReg: 0.0008, CorReg: 0.0000, TopReg: 0.0009, AllReg: 0.0008, BotRReg: 0.0019, OV: 0.8631, AltV: 0.8814, CorV: 0.8356, TopV: 0.8577, BotRV: 0.8567, AllV: 0.8814 +[2026-03-20T20:16:58.439602Z] Loop 12110: Reg: 0.0021, AltReg: 0.0033, CorReg: 0.0002, TopReg: 0.0081, AllReg: 0.0033, BotRReg: 0.0086, OV: 0.8615, AltV: 0.8789, CorV: 0.8354, TopV: 0.8505, BotRV: 0.8500, AllV: 0.8789 +[2026-03-20T20:17:07.024275Z] Loop 12120: Reg: 0.0067, AltReg: 0.0111, CorReg: 0.0001, TopReg: 0.0193, AllReg: 0.0111, BotRReg: 0.0425, OV: 0.8569, AltV: 0.8711, CorV: 0.8355, TopV: 0.8393, BotRV: 0.8162, AllV: 0.8712 +[2026-03-20T20:17:15.603710Z] Loop 12130: Reg: 0.0035, AltReg: 0.0059, CorReg: 0.0000, TopReg: 0.0090, AllReg: 0.0059, BotRReg: 0.0129, OV: 0.8600, AltV: 0.8763, CorV: 0.8356, TopV: 0.8497, BotRV: 0.8458, AllV: 0.8764 +[2026-03-20T20:17:24.187484Z] Loop 12140: Reg: 0.0021, AltReg: 0.0034, CorReg: 0.0000, TopReg: 0.0044, AllReg: 0.0034, BotRReg: 0.0052, OV: 0.8615, AltV: 0.8788, CorV: 0.8356, TopV: 0.8542, BotRV: 0.8534, AllV: 0.8788 +[2026-03-20T20:17:32.767298Z] Loop 12150: Reg: 0.0018, AltReg: 0.0026, CorReg: 0.0006, TopReg: 0.0038, AllReg: 0.0026, BotRReg: 0.0051, OV: 0.8618, AltV: 0.8796, CorV: 0.8350, TopV: 0.8548, BotRV: 0.8535, AllV: 0.8796 +[2026-03-20T20:17:41.344275Z] Loop 12160: Reg: 0.0025, AltReg: 0.0027, CorReg: 0.0021, TopReg: 0.0065, AllReg: 0.0027, BotRReg: 0.0039, OV: 0.8611, AltV: 0.8795, CorV: 0.8335, TopV: 0.8521, BotRV: 0.8548, AllV: 0.8795 +[2026-03-20T20:17:49.927242Z] Loop 12170: Reg: 0.0012, AltReg: 0.0016, CorReg: 0.0006, TopReg: 0.0027, AllReg: 0.0016, BotRReg: 0.0024, OV: 0.8624, AltV: 0.8806, CorV: 0.8350, TopV: 0.8560, BotRV: 0.8562, AllV: 0.8806 +[2026-03-20T20:17:58.509348Z] Loop 12180: Reg: 0.0009, AltReg: 0.0013, CorReg: 0.0003, TopReg: 0.0021, AllReg: 0.0013, BotRReg: 0.0027, OV: 0.8627, AltV: 0.8809, CorV: 0.8353, TopV: 0.8565, BotRV: 0.8559, AllV: 0.8809 +[2026-03-20T20:18:07.095463Z] Loop 12190: Reg: 0.0071, AltReg: 0.0049, CorReg: 0.0104, TopReg: 0.0130, AllReg: 0.0049, BotRReg: 0.0081, OV: 0.8564, AltV: 0.8773, CorV: 0.8252, TopV: 0.8456, BotRV: 0.8506, AllV: 0.8773 +[2026-03-20T20:18:15.682753Z] Loop 12200: Reg: 0.0045, AltReg: 0.0075, CorReg: 0.0002, TopReg: 0.0249, AllReg: 0.0075, BotRReg: 0.0061, OV: 0.8590, AltV: 0.8748, CorV: 0.8355, TopV: 0.8337, BotRV: 0.8525, AllV: 0.8748 +[2026-03-20T20:18:24.265844Z] Loop 12210: Reg: 0.0034, AltReg: 0.0057, CorReg: 0.0000, TopReg: 0.0221, AllReg: 0.0057, BotRReg: 0.0038, OV: 0.8601, AltV: 0.8765, CorV: 0.8356, TopV: 0.8365, BotRV: 0.8549, AllV: 0.8765 +[2026-03-20T20:18:32.846521Z] Loop 12220: Reg: 0.0003, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0010, AllReg: 0.0004, BotRReg: 0.0004, OV: 0.8633, AltV: 0.8818, CorV: 0.8356, TopV: 0.8577, BotRV: 0.8583, AllV: 0.8818 +[2026-03-20T20:18:41.431506Z] Loop 12230: Reg: 0.0008, AltReg: 0.0013, CorReg: 0.0000, TopReg: 0.0027, AllReg: 0.0013, BotRReg: 0.0006, OV: 0.8628, AltV: 0.8809, CorV: 0.8356, TopV: 0.8559, BotRV: 0.8580, AllV: 0.8809 +[2026-03-20T20:18:50.012347Z] Loop 12240: Reg: 0.0022, AltReg: 0.0036, CorReg: 0.0000, TopReg: 0.0121, AllReg: 0.0036, BotRReg: 0.0015, OV: 0.8614, AltV: 0.8786, CorV: 0.8356, TopV: 0.8465, BotRV: 0.8571, AllV: 0.8787 +[2026-03-20T20:18:58.591847Z] Loop 12250: Reg: 0.0011, AltReg: 0.0018, CorReg: 0.0000, TopReg: 0.0073, AllReg: 0.0019, BotRReg: 0.0011, OV: 0.8625, AltV: 0.8804, CorV: 0.8356, TopV: 0.8514, BotRV: 0.8576, AllV: 0.8804 +[2026-03-20T20:19:07.171613Z] Loop 12260: Reg: 0.0004, AltReg: 0.0007, CorReg: 0.0000, TopReg: 0.0018, AllReg: 0.0007, BotRReg: 0.0008, OV: 0.8631, AltV: 0.8815, CorV: 0.8356, TopV: 0.8569, BotRV: 0.8578, AllV: 0.8815 +[2026-03-20T20:19:15.753220Z] Loop 12270: Reg: 0.0004, AltReg: 0.0007, CorReg: 0.0000, TopReg: 0.0016, AllReg: 0.0007, BotRReg: 0.0004, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8570, BotRV: 0.8582, AllV: 0.8816 +[2026-03-20T20:19:24.338545Z] Loop 12280: Reg: 0.0008, AltReg: 0.0013, CorReg: 0.0000, TopReg: 0.0029, AllReg: 0.0013, BotRReg: 0.0010, OV: 0.8628, AltV: 0.8809, CorV: 0.8356, TopV: 0.8557, BotRV: 0.8576, AllV: 0.8810 +[2026-03-20T20:19:32.919855Z] Loop 12290: Reg: 0.0017, AltReg: 0.0029, CorReg: 0.0000, TopReg: 0.0043, AllReg: 0.0029, BotRReg: 0.0024, OV: 0.8619, AltV: 0.8793, CorV: 0.8356, TopV: 0.8543, BotRV: 0.8563, AllV: 0.8794 +[2026-03-20T20:19:41.500571Z] Loop 12300: Reg: 0.0001, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0002, BotRReg: 0.0005, OV: 0.8635, AltV: 0.8820, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8581, AllV: 0.8821 +[2026-03-20T20:19:50.079978Z] Loop 12310: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0006, BotRReg: 0.0003, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8583, AllV: 0.8816 +[2026-03-20T20:19:58.667730Z] Loop 12320: Reg: 0.0014, AltReg: 0.0023, CorReg: 0.0000, TopReg: 0.0023, AllReg: 0.0023, BotRReg: 0.0035, OV: 0.8622, AltV: 0.8799, CorV: 0.8356, TopV: 0.8564, BotRV: 0.8551, AllV: 0.8799 +[2026-03-20T20:20:07.248976Z] Loop 12330: Reg: 0.0059, AltReg: 0.0098, CorReg: 0.0000, TopReg: 0.0159, AllReg: 0.0100, BotRReg: 0.0357, OV: 0.8577, AltV: 0.8724, CorV: 0.8356, TopV: 0.8428, BotRV: 0.8230, AllV: 0.8722 +[2026-03-20T20:20:15.823589Z] Loop 12340: Reg: 0.0031, AltReg: 0.0052, CorReg: 0.0000, TopReg: 0.0088, AllReg: 0.0052, BotRReg: 0.0048, OV: 0.8605, AltV: 0.8770, CorV: 0.8356, TopV: 0.8499, BotRV: 0.8538, AllV: 0.8770 +[2026-03-20T20:20:24.410755Z] Loop 12350: Reg: 0.0003, AltReg: 0.0005, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0005, BotRReg: 0.0011, OV: 0.8633, AltV: 0.8817, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8576, AllV: 0.8817 +[2026-03-20T20:20:32.995776Z] Loop 12360: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0003, BotRReg: 0.0014, OV: 0.8634, AltV: 0.8819, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8572, AllV: 0.8819 +[2026-03-20T20:20:41.582966Z] Loop 12370: Reg: 0.0002, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0004, BotRReg: 0.0014, OV: 0.8634, AltV: 0.8819, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8572, AllV: 0.8819 +[2026-03-20T20:20:50.173022Z] Loop 12380: Reg: 0.0006, AltReg: 0.0009, CorReg: 0.0000, TopReg: 0.0012, AllReg: 0.0010, BotRReg: 0.0008, OV: 0.8630, AltV: 0.8813, CorV: 0.8356, TopV: 0.8574, BotRV: 0.8578, AllV: 0.8813 +[2026-03-20T20:20:58.766036Z] Loop 12390: Reg: 0.0022, AltReg: 0.0035, CorReg: 0.0001, TopReg: 0.0125, AllReg: 0.0036, BotRReg: 0.0008, OV: 0.8614, AltV: 0.8787, CorV: 0.8356, TopV: 0.8462, BotRV: 0.8578, AllV: 0.8787 +[2026-03-20T20:21:07.366450Z] Loop 12400: Reg: 0.0019, AltReg: 0.0031, CorReg: 0.0001, TopReg: 0.0073, AllReg: 0.0031, BotRReg: 0.0013, OV: 0.8617, AltV: 0.8791, CorV: 0.8356, TopV: 0.8513, BotRV: 0.8573, AllV: 0.8791 +[2026-03-20T20:21:15.961696Z] Loop 12410: Reg: 0.0013, AltReg: 0.0022, CorReg: 0.0000, TopReg: 0.0031, AllReg: 0.0023, BotRReg: 0.0035, OV: 0.8622, AltV: 0.8800, CorV: 0.8356, TopV: 0.8555, BotRV: 0.8551, AllV: 0.8800 +[2026-03-20T20:21:24.563570Z] Loop 12420: Reg: 0.0010, AltReg: 0.0016, CorReg: 0.0000, TopReg: 0.0006, AllReg: 0.0016, BotRReg: 0.0053, OV: 0.8626, AltV: 0.8806, CorV: 0.8356, TopV: 0.8580, BotRV: 0.8533, AllV: 0.8806 +[2026-03-20T20:21:33.145024Z] Loop 12430: Reg: 0.0007, AltReg: 0.0011, CorReg: 0.0001, TopReg: 0.0005, AllReg: 0.0011, BotRReg: 0.0032, OV: 0.8629, AltV: 0.8811, CorV: 0.8355, TopV: 0.8581, BotRV: 0.8554, AllV: 0.8811 +[2026-03-20T20:21:41.727746Z] Loop 12440: Reg: 0.0005, AltReg: 0.0009, CorReg: 0.0001, TopReg: 0.0006, AllReg: 0.0009, BotRReg: 0.0024, OV: 0.8630, AltV: 0.8813, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8563, AllV: 0.8814 +[2026-03-20T20:21:50.309179Z] Loop 12450: Reg: 0.0009, AltReg: 0.0015, CorReg: 0.0001, TopReg: 0.0004, AllReg: 0.0015, BotRReg: 0.0038, OV: 0.8626, AltV: 0.8807, CorV: 0.8355, TopV: 0.8582, BotRV: 0.8548, AllV: 0.8808 +[2026-03-20T20:21:58.890519Z] Loop 12460: Reg: 0.0022, AltReg: 0.0029, CorReg: 0.0011, TopReg: 0.0008, AllReg: 0.0029, BotRReg: 0.0057, OV: 0.8614, AltV: 0.8793, CorV: 0.8345, TopV: 0.8579, BotRV: 0.8529, AllV: 0.8793 +[2026-03-20T20:22:07.466980Z] Loop 12470: Reg: 0.0011, AltReg: 0.0014, CorReg: 0.0006, TopReg: 0.0014, AllReg: 0.0014, BotRReg: 0.0018, OV: 0.8625, AltV: 0.8808, CorV: 0.8350, TopV: 0.8572, BotRV: 0.8568, AllV: 0.8808 +[2026-03-20T20:22:16.040262Z] Loop 12480: Reg: 0.0013, AltReg: 0.0022, CorReg: 0.0001, TopReg: 0.0072, AllReg: 0.0022, BotRReg: 0.0008, OV: 0.8622, AltV: 0.8800, CorV: 0.8355, TopV: 0.8515, BotRV: 0.8579, AllV: 0.8801 +[2026-03-20T20:22:24.619994Z] Loop 12490: Reg: 0.0005, AltReg: 0.0009, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0009, BotRReg: 0.0005, OV: 0.8631, AltV: 0.8814, CorV: 0.8356, TopV: 0.8580, BotRV: 0.8581, AllV: 0.8814 +[2026-03-20T20:22:33.201689Z] Loop 12500: Reg: 0.0012, AltReg: 0.0020, CorReg: 0.0000, TopReg: 0.0013, AllReg: 0.0020, BotRReg: 0.0012, OV: 0.8624, AltV: 0.8802, CorV: 0.8356, TopV: 0.8573, BotRV: 0.8575, AllV: 0.8802 +[2026-03-20T20:22:41.787660Z] Loop 12510: Reg: 0.0023, AltReg: 0.0039, CorReg: 0.0000, TopReg: 0.0014, AllReg: 0.0039, BotRReg: 0.0027, OV: 0.8613, AltV: 0.8783, CorV: 0.8356, TopV: 0.8572, BotRV: 0.8560, AllV: 0.8784 +[2026-03-20T20:22:50.370370Z] Loop 12520: Reg: 0.0080, AltReg: 0.0132, CorReg: 0.0000, TopReg: 0.0040, AllReg: 0.0134, BotRReg: 0.0221, OV: 0.8556, AltV: 0.8690, CorV: 0.8356, TopV: 0.8546, BotRV: 0.8365, AllV: 0.8689 +[2026-03-20T20:22:58.952160Z] Loop 12530: Reg: 0.0035, AltReg: 0.0059, CorReg: 0.0000, TopReg: 0.0055, AllReg: 0.0059, BotRReg: 0.0043, OV: 0.8600, AltV: 0.8763, CorV: 0.8356, TopV: 0.8531, BotRV: 0.8544, AllV: 0.8763 +[2026-03-20T20:23:07.526074Z] Loop 12540: Reg: 0.0015, AltReg: 0.0025, CorReg: 0.0000, TopReg: 0.0034, AllReg: 0.0025, BotRReg: 0.0018, OV: 0.8621, AltV: 0.8797, CorV: 0.8356, TopV: 0.8553, BotRV: 0.8568, AllV: 0.8798 +[2026-03-20T20:23:16.103256Z] Loop 12550: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0000, TopReg: 0.0038, AllReg: 0.0010, BotRReg: 0.0010, OV: 0.8630, AltV: 0.8812, CorV: 0.8356, TopV: 0.8548, BotRV: 0.8576, AllV: 0.8812 +[2026-03-20T20:23:24.683231Z] Loop 12560: Reg: 0.0017, AltReg: 0.0029, CorReg: 0.0000, TopReg: 0.0130, AllReg: 0.0029, BotRReg: 0.0009, OV: 0.8619, AltV: 0.8793, CorV: 0.8356, TopV: 0.8456, BotRV: 0.8577, AllV: 0.8794 +[2026-03-20T20:23:33.265707Z] Loop 12570: Reg: 0.0012, AltReg: 0.0020, CorReg: 0.0000, TopReg: 0.0056, AllReg: 0.0020, BotRReg: 0.0020, OV: 0.8624, AltV: 0.8802, CorV: 0.8356, TopV: 0.8530, BotRV: 0.8566, AllV: 0.8803 +[2026-03-20T20:23:41.848731Z] Loop 12580: Reg: 0.0011, AltReg: 0.0019, CorReg: 0.0000, TopReg: 0.0025, AllReg: 0.0019, BotRReg: 0.0029, OV: 0.8625, AltV: 0.8803, CorV: 0.8356, TopV: 0.8561, BotRV: 0.8557, AllV: 0.8804 +[2026-03-20T20:23:50.427112Z] Loop 12590: Reg: 0.0011, AltReg: 0.0019, CorReg: 0.0000, TopReg: 0.0014, AllReg: 0.0019, BotRReg: 0.0051, OV: 0.8625, AltV: 0.8803, CorV: 0.8356, TopV: 0.8573, BotRV: 0.8535, AllV: 0.8804 +[2026-03-20T20:23:59.010012Z] Loop 12600: Reg: 0.0012, AltReg: 0.0019, CorReg: 0.0000, TopReg: 0.0013, AllReg: 0.0019, BotRReg: 0.0033, OV: 0.8624, AltV: 0.8803, CorV: 0.8356, TopV: 0.8574, BotRV: 0.8553, AllV: 0.8803 +[2026-03-20T20:24:07.593404Z] Loop 12610: Reg: 0.0025, AltReg: 0.0042, CorReg: 0.0000, TopReg: 0.0062, AllReg: 0.0042, BotRReg: 0.0026, OV: 0.8610, AltV: 0.8780, CorV: 0.8356, TopV: 0.8524, BotRV: 0.8560, AllV: 0.8780 +[2026-03-20T20:24:16.174646Z] Loop 12620: Reg: 0.0015, AltReg: 0.0023, CorReg: 0.0003, TopReg: 0.0023, AllReg: 0.0024, BotRReg: 0.0014, OV: 0.8620, AltV: 0.8799, CorV: 0.8353, TopV: 0.8563, BotRV: 0.8572, AllV: 0.8799 +[2026-03-20T20:24:24.760016Z] Loop 12630: Reg: 0.0004, AltReg: 0.0005, CorReg: 0.0002, TopReg: 0.0004, AllReg: 0.0005, BotRReg: 0.0007, OV: 0.8632, AltV: 0.8817, CorV: 0.8355, TopV: 0.8582, BotRV: 0.8579, AllV: 0.8817 +[2026-03-20T20:24:33.351323Z] Loop 12640: Reg: 0.0001, AltReg: 0.0001, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0001, BotRReg: 0.0002, OV: 0.8635, AltV: 0.8821, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8584, AllV: 0.8821 +[2026-03-20T20:24:41.937338Z] Loop 12650: Reg: 0.0012, AltReg: 0.0020, CorReg: 0.0000, TopReg: 0.0011, AllReg: 0.0020, BotRReg: 0.0092, OV: 0.8624, AltV: 0.8802, CorV: 0.8356, TopV: 0.8575, BotRV: 0.8495, AllV: 0.8802 +[2026-03-20T20:24:50.518166Z] Loop 12660: Reg: 0.0009, AltReg: 0.0015, CorReg: 0.0001, TopReg: 0.0004, AllReg: 0.0015, BotRReg: 0.0026, OV: 0.8627, AltV: 0.8807, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8560, AllV: 0.8807 +[2026-03-20T20:24:59.104347Z] Loop 12670: Reg: 0.0004, AltReg: 0.0007, CorReg: 0.0001, TopReg: 0.0003, AllReg: 0.0007, BotRReg: 0.0008, OV: 0.8631, AltV: 0.8816, CorV: 0.8355, TopV: 0.8583, BotRV: 0.8579, AllV: 0.8816 +[2026-03-20T20:25:07.686263Z] Loop 12680: Reg: 0.0011, AltReg: 0.0017, CorReg: 0.0003, TopReg: 0.0010, AllReg: 0.0017, BotRReg: 0.0022, OV: 0.8624, AltV: 0.8806, CorV: 0.8353, TopV: 0.8576, BotRV: 0.8564, AllV: 0.8806 +[2026-03-20T20:25:16.262562Z] Loop 12690: Reg: 0.0027, AltReg: 0.0044, CorReg: 0.0003, TopReg: 0.0016, AllReg: 0.0044, BotRReg: 0.0030, OV: 0.8609, AltV: 0.8778, CorV: 0.8354, TopV: 0.8570, BotRV: 0.8556, AllV: 0.8779 +[2026-03-20T20:25:24.847105Z] Loop 12700: Reg: 0.0005, AltReg: 0.0009, CorReg: 0.0000, TopReg: 0.0010, AllReg: 0.0009, BotRReg: 0.0012, OV: 0.8631, AltV: 0.8814, CorV: 0.8356, TopV: 0.8577, BotRV: 0.8574, AllV: 0.8814 +[2026-03-20T20:25:33.433296Z] Loop 12710: Reg: 0.0012, AltReg: 0.0020, CorReg: 0.0001, TopReg: 0.0050, AllReg: 0.0020, BotRReg: 0.0010, OV: 0.8624, AltV: 0.8802, CorV: 0.8356, TopV: 0.8536, BotRV: 0.8577, AllV: 0.8803 +[2026-03-20T20:25:42.015244Z] Loop 12720: Reg: 0.0003, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0004, BotRReg: 0.0005, OV: 0.8633, AltV: 0.8818, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8581, AllV: 0.8818 +[2026-03-20T20:25:50.598919Z] Loop 12730: Reg: 0.0001, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0002, BotRReg: 0.0003, OV: 0.8635, AltV: 0.8821, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8583, AllV: 0.8821 +[2026-03-20T20:25:59.180359Z] Loop 12740: Reg: 0.0001, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0002, BotRReg: 0.0005, OV: 0.8635, AltV: 0.8820, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8581, AllV: 0.8821 +[2026-03-20T20:26:07.771006Z] Loop 12750: Reg: 0.0016, AltReg: 0.0026, CorReg: 0.0000, TopReg: 0.0017, AllReg: 0.0026, BotRReg: 0.0123, OV: 0.8620, AltV: 0.8796, CorV: 0.8356, TopV: 0.8569, BotRV: 0.8463, AllV: 0.8796 +[2026-03-20T20:26:16.351680Z] Loop 12760: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0006, BotRReg: 0.0016, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8570, AllV: 0.8816 +[2026-03-20T20:26:24.934868Z] Loop 12770: Reg: 0.0013, AltReg: 0.0021, CorReg: 0.0000, TopReg: 0.0019, AllReg: 0.0021, BotRReg: 0.0019, OV: 0.8623, AltV: 0.8801, CorV: 0.8356, TopV: 0.8567, BotRV: 0.8567, AllV: 0.8801 +[2026-03-20T20:26:33.516461Z] Loop 12780: Reg: 0.0018, AltReg: 0.0029, CorReg: 0.0000, TopReg: 0.0030, AllReg: 0.0029, BotRReg: 0.0030, OV: 0.8618, AltV: 0.8793, CorV: 0.8356, TopV: 0.8556, BotRV: 0.8556, AllV: 0.8793 +[2026-03-20T20:26:42.093744Z] Loop 12790: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0000, TopReg: 0.0009, AllReg: 0.0010, BotRReg: 0.0019, OV: 0.8630, AltV: 0.8812, CorV: 0.8356, TopV: 0.8577, BotRV: 0.8568, AllV: 0.8812 +[2026-03-20T20:26:50.681189Z] Loop 12800: Reg: 0.0004, AltReg: 0.0007, CorReg: 0.0000, TopReg: 0.0015, AllReg: 0.0007, BotRReg: 0.0016, OV: 0.8632, AltV: 0.8815, CorV: 0.8356, TopV: 0.8571, BotRV: 0.8570, AllV: 0.8815 +[2026-03-20T20:26:59.266046Z] Loop 12810: Reg: 0.0008, AltReg: 0.0013, CorReg: 0.0000, TopReg: 0.0021, AllReg: 0.0013, BotRReg: 0.0041, OV: 0.8628, AltV: 0.8809, CorV: 0.8356, TopV: 0.8565, BotRV: 0.8546, AllV: 0.8810 +[2026-03-20T20:27:07.845498Z] Loop 12820: Reg: 0.0016, AltReg: 0.0027, CorReg: 0.0000, TopReg: 0.0041, AllReg: 0.0027, BotRReg: 0.0064, OV: 0.8620, AltV: 0.8796, CorV: 0.8356, TopV: 0.8545, BotRV: 0.8523, AllV: 0.8796 +[2026-03-20T20:27:16.429206Z] Loop 12830: Reg: 0.0001, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0002, BotRReg: 0.0008, OV: 0.8635, AltV: 0.8820, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8579, AllV: 0.8820 +[2026-03-20T20:27:25.008522Z] Loop 12840: Reg: 0.0005, AltReg: 0.0007, CorReg: 0.0001, TopReg: 0.0014, AllReg: 0.0008, BotRReg: 0.0014, OV: 0.8631, AltV: 0.8815, CorV: 0.8356, TopV: 0.8572, BotRV: 0.8572, AllV: 0.8815 +[2026-03-20T20:27:33.588931Z] Loop 12850: Reg: 0.0012, AltReg: 0.0018, CorReg: 0.0003, TopReg: 0.0045, AllReg: 0.0019, BotRReg: 0.0021, OV: 0.8624, AltV: 0.8804, CorV: 0.8354, TopV: 0.8542, BotRV: 0.8565, AllV: 0.8804 +[2026-03-20T20:27:42.167495Z] Loop 12860: Reg: 0.0007, AltReg: 0.0012, CorReg: 0.0000, TopReg: 0.0048, AllReg: 0.0012, BotRReg: 0.0013, OV: 0.8628, AltV: 0.8810, CorV: 0.8356, TopV: 0.8539, BotRV: 0.8573, AllV: 0.8810 +[2026-03-20T20:27:50.744269Z] Loop 12870: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0013, AllReg: 0.0007, BotRReg: 0.0012, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8574, BotRV: 0.8574, AllV: 0.8816 +[2026-03-20T20:27:59.325296Z] Loop 12880: Reg: 0.0001, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0002, BotRReg: 0.0005, OV: 0.8634, AltV: 0.8820, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8582, AllV: 0.8820 +[2026-03-20T20:28:07.907892Z] Loop 12890: Reg: 0.0001, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0002, BotRReg: 0.0004, OV: 0.8634, AltV: 0.8820, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8582, AllV: 0.8820 +[2026-03-20T20:28:16.491195Z] Loop 12900: Reg: 0.0003, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0004, BotRReg: 0.0009, OV: 0.8633, AltV: 0.8818, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8578, AllV: 0.8818 +[2026-03-20T20:28:25.077578Z] Loop 12910: Reg: 0.0004, AltReg: 0.0007, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0007, BotRReg: 0.0015, OV: 0.8631, AltV: 0.8815, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8571, AllV: 0.8815 +[2026-03-20T20:28:33.659702Z] Loop 12920: Reg: 0.0015, AltReg: 0.0026, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0026, BotRReg: 0.0036, OV: 0.8620, AltV: 0.8797, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8550, AllV: 0.8797 +[2026-03-20T20:28:42.247632Z] Loop 12930: Reg: 0.0010, AltReg: 0.0017, CorReg: 0.0000, TopReg: 0.0009, AllReg: 0.0018, BotRReg: 0.0025, OV: 0.8625, AltV: 0.8805, CorV: 0.8356, TopV: 0.8578, BotRV: 0.8561, AllV: 0.8805 +[2026-03-20T20:28:50.828890Z] Loop 12940: Reg: 0.0006, AltReg: 0.0009, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0009, BotRReg: 0.0014, OV: 0.8630, AltV: 0.8813, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8572, AllV: 0.8813 +[2026-03-20T20:28:59.408412Z] Loop 12950: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0003, BotRReg: 0.0008, OV: 0.8634, AltV: 0.8819, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8578, AllV: 0.8819 +[2026-03-20T20:29:07.991229Z] Loop 12960: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0003, BotRReg: 0.0006, OV: 0.8634, AltV: 0.8819, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8580, AllV: 0.8820 +[2026-03-20T20:29:16.572969Z] Loop 12970: Reg: 0.0008, AltReg: 0.0014, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0014, BotRReg: 0.0025, OV: 0.8628, AltV: 0.8809, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8562, AllV: 0.8809 +[2026-03-20T20:29:25.152117Z] Loop 12980: Reg: 0.0018, AltReg: 0.0029, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0029, BotRReg: 0.0117, OV: 0.8618, AltV: 0.8793, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8470, AllV: 0.8793 +[2026-03-20T20:29:33.729416Z] Loop 12990: Reg: 0.0033, AltReg: 0.0055, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0055, BotRReg: 0.0215, OV: 0.8603, AltV: 0.8767, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8371, AllV: 0.8767 +[2026-03-20T20:29:42.309763Z] Loop 13000: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0010, BotRReg: 0.0022, OV: 0.8630, AltV: 0.8813, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8564, AllV: 0.8813 +[2026-03-20T20:29:50.891029Z] Loop 13010: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0010, BotRReg: 0.0021, OV: 0.8630, AltV: 0.8812, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8565, AllV: 0.8812 +[2026-03-20T20:29:59.470310Z] Loop 13020: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0011, BotRReg: 0.0018, OV: 0.8629, AltV: 0.8812, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8568, AllV: 0.8812 +[2026-03-20T20:30:08.055619Z] Loop 13030: Reg: 0.0016, AltReg: 0.0026, CorReg: 0.0001, TopReg: 0.0026, AllReg: 0.0026, BotRReg: 0.0024, OV: 0.8620, AltV: 0.8796, CorV: 0.8355, TopV: 0.8560, BotRV: 0.8563, AllV: 0.8796 +[2026-03-20T20:30:16.637588Z] Loop 13040: Reg: 0.0033, AltReg: 0.0055, CorReg: 0.0001, TopReg: 0.0086, AllReg: 0.0055, BotRReg: 0.0024, OV: 0.8602, AltV: 0.8767, CorV: 0.8355, TopV: 0.8500, BotRV: 0.8562, AllV: 0.8768 +[2026-03-20T20:30:25.217340Z] Loop 13050: Reg: 0.0011, AltReg: 0.0018, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0018, BotRReg: 0.0027, OV: 0.8625, AltV: 0.8804, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8559, AllV: 0.8804 +[2026-03-20T20:30:33.792221Z] Loop 13060: Reg: 0.0005, AltReg: 0.0008, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0009, BotRReg: 0.0016, OV: 0.8631, AltV: 0.8814, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8571, AllV: 0.8814 +[2026-03-20T20:30:42.374551Z] Loop 13070: Reg: 0.0030, AltReg: 0.0050, CorReg: 0.0000, TopReg: 0.0075, AllReg: 0.0051, BotRReg: 0.0006, OV: 0.8606, AltV: 0.8772, CorV: 0.8356, TopV: 0.8511, BotRV: 0.8580, AllV: 0.8772 +[2026-03-20T20:30:50.954248Z] Loop 13080: Reg: 0.0003, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0004, BotRReg: 0.0004, OV: 0.8633, AltV: 0.8818, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8583, AllV: 0.8818 +[2026-03-20T20:30:59.542532Z] Loop 13090: Reg: 0.0057, AltReg: 0.0095, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0095, BotRReg: 0.0207, OV: 0.8579, AltV: 0.8727, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8379, AllV: 0.8728 +[2026-03-20T20:31:08.130817Z] Loop 13100: Reg: 0.0003, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0006, BotRReg: 0.0017, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8570, AllV: 0.8817 +[2026-03-20T20:31:16.711256Z] Loop 13110: Reg: 0.0012, AltReg: 0.0019, CorReg: 0.0001, TopReg: 0.0120, AllReg: 0.0020, BotRReg: 0.0015, OV: 0.8624, AltV: 0.8803, CorV: 0.8355, TopV: 0.8467, BotRV: 0.8571, AllV: 0.8803 +[2026-03-20T20:31:25.296016Z] Loop 13120: Reg: 0.0016, AltReg: 0.0027, CorReg: 0.0001, TopReg: 0.0032, AllReg: 0.0027, BotRReg: 0.0017, OV: 0.8619, AltV: 0.8795, CorV: 0.8356, TopV: 0.8554, BotRV: 0.8569, AllV: 0.8795 +[2026-03-20T20:31:33.879544Z] Loop 13130: Reg: 0.0028, AltReg: 0.0046, CorReg: 0.0001, TopReg: 0.0108, AllReg: 0.0046, BotRReg: 0.0016, OV: 0.8608, AltV: 0.8776, CorV: 0.8356, TopV: 0.8478, BotRV: 0.8570, AllV: 0.8776 +[2026-03-20T20:31:42.453427Z] Loop 13140: Reg: 0.0041, AltReg: 0.0068, CorReg: 0.0001, TopReg: 0.0115, AllReg: 0.0068, BotRReg: 0.0032, OV: 0.8595, AltV: 0.8754, CorV: 0.8355, TopV: 0.8471, BotRV: 0.8554, AllV: 0.8754 +[2026-03-20T20:31:51.035176Z] Loop 13150: Reg: 0.0005, AltReg: 0.0009, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0009, BotRReg: 0.0013, OV: 0.8631, AltV: 0.8813, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8573, AllV: 0.8814 +[2026-03-20T20:31:59.618314Z] Loop 13160: Reg: 0.0016, AltReg: 0.0026, CorReg: 0.0000, TopReg: 0.0020, AllReg: 0.0026, BotRReg: 0.0033, OV: 0.8620, AltV: 0.8796, CorV: 0.8356, TopV: 0.8566, BotRV: 0.8553, AllV: 0.8796 +[2026-03-20T20:32:08.202168Z] Loop 13170: Reg: 0.0027, AltReg: 0.0045, CorReg: 0.0000, TopReg: 0.0038, AllReg: 0.0046, BotRReg: 0.0031, OV: 0.8609, AltV: 0.8777, CorV: 0.8356, TopV: 0.8548, BotRV: 0.8555, AllV: 0.8777 +[2026-03-20T20:32:16.780068Z] Loop 13180: Reg: 0.0031, AltReg: 0.0050, CorReg: 0.0001, TopReg: 0.0042, AllReg: 0.0050, BotRReg: 0.0021, OV: 0.8605, AltV: 0.8772, CorV: 0.8355, TopV: 0.8544, BotRV: 0.8566, AllV: 0.8772 +[2026-03-20T20:32:25.360829Z] Loop 13190: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0003, BotRReg: 0.0005, OV: 0.8634, AltV: 0.8820, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8582, AllV: 0.8820 +[2026-03-20T20:32:33.944203Z] Loop 13200: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0003, BotRReg: 0.0007, OV: 0.8634, AltV: 0.8820, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8580, AllV: 0.8820 +[2026-03-20T20:32:42.528134Z] Loop 13210: Reg: 0.0021, AltReg: 0.0034, CorReg: 0.0000, TopReg: 0.0030, AllReg: 0.0034, BotRReg: 0.0037, OV: 0.8615, AltV: 0.8788, CorV: 0.8356, TopV: 0.8556, BotRV: 0.8549, AllV: 0.8788 +[2026-03-20T20:32:51.108309Z] Loop 13220: Reg: 0.0017, AltReg: 0.0028, CorReg: 0.0000, TopReg: 0.0082, AllReg: 0.0028, BotRReg: 0.0015, OV: 0.8619, AltV: 0.8794, CorV: 0.8356, TopV: 0.8505, BotRV: 0.8572, AllV: 0.8795 +[2026-03-20T20:32:59.687397Z] Loop 13230: Reg: 0.0009, AltReg: 0.0015, CorReg: 0.0000, TopReg: 0.0019, AllReg: 0.0015, BotRReg: 0.0011, OV: 0.8627, AltV: 0.8807, CorV: 0.8356, TopV: 0.8567, BotRV: 0.8575, AllV: 0.8808 +[2026-03-20T20:33:08.269994Z] Loop 13240: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0006, BotRReg: 0.0005, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8581, AllV: 0.8817 +[2026-03-20T20:33:16.854866Z] Loop 13250: Reg: 0.0007, AltReg: 0.0011, CorReg: 0.0000, TopReg: 0.0010, AllReg: 0.0011, BotRReg: 0.0009, OV: 0.8629, AltV: 0.8811, CorV: 0.8356, TopV: 0.8576, BotRV: 0.8577, AllV: 0.8811 +[2026-03-20T20:33:25.439223Z] Loop 13260: Reg: 0.0001, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0002, BotRReg: 0.0003, OV: 0.8635, AltV: 0.8820, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8584, AllV: 0.8821 +[2026-03-20T20:33:34.017953Z] Loop 13270: Reg: 0.0001, AltReg: 0.0001, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0001, BotRReg: 0.0001, OV: 0.8635, AltV: 0.8821, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8585, AllV: 0.8821 +[2026-03-20T20:33:42.603355Z] Loop 13280: Reg: 0.0022, AltReg: 0.0036, CorReg: 0.0001, TopReg: 0.0101, AllReg: 0.0036, BotRReg: 0.0023, OV: 0.8614, AltV: 0.8786, CorV: 0.8355, TopV: 0.8485, BotRV: 0.8563, AllV: 0.8786 +[2026-03-20T20:33:51.179204Z] Loop 13290: Reg: 0.0003, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0006, BotRReg: 0.0007, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8579, AllV: 0.8817 +[2026-03-20T20:33:59.763346Z] Loop 13300: Reg: 0.0004, AltReg: 0.0007, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0007, BotRReg: 0.0007, OV: 0.8631, AltV: 0.8815, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8579, AllV: 0.8815 +[2026-03-20T20:34:08.348490Z] Loop 13310: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0010, BotRReg: 0.0009, OV: 0.8630, AltV: 0.8812, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8578, AllV: 0.8813 +[2026-03-20T20:34:16.935916Z] Loop 13320: Reg: 0.0003, AltReg: 0.0005, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0005, BotRReg: 0.0006, OV: 0.8633, AltV: 0.8818, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8581, AllV: 0.8818 +[2026-03-20T20:34:25.521264Z] Loop 13330: Reg: 0.0013, AltReg: 0.0021, CorReg: 0.0000, TopReg: 0.0037, AllReg: 0.0021, BotRReg: 0.0012, OV: 0.8623, AltV: 0.8801, CorV: 0.8356, TopV: 0.8549, BotRV: 0.8575, AllV: 0.8802 +[2026-03-20T20:34:34.100578Z] Loop 13340: Reg: 0.0005, AltReg: 0.0009, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0009, BotRReg: 0.0013, OV: 0.8630, AltV: 0.8813, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8573, AllV: 0.8814 +[2026-03-20T20:34:42.690431Z] Loop 13350: Reg: 0.0005, AltReg: 0.0008, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0008, BotRReg: 0.0011, OV: 0.8631, AltV: 0.8814, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8575, AllV: 0.8815 +[2026-03-20T20:34:51.274238Z] Loop 13360: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0000, TopReg: 0.0009, AllReg: 0.0010, BotRReg: 0.0010, OV: 0.8630, AltV: 0.8812, CorV: 0.8356, TopV: 0.8577, BotRV: 0.8576, AllV: 0.8812 +[2026-03-20T20:34:59.854522Z] Loop 13370: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0001, TopReg: 0.0012, AllReg: 0.0010, BotRReg: 0.0019, OV: 0.8630, AltV: 0.8812, CorV: 0.8355, TopV: 0.8575, BotRV: 0.8568, AllV: 0.8812 +[2026-03-20T20:35:08.437842Z] Loop 13380: Reg: 0.0022, AltReg: 0.0016, CorReg: 0.0032, TopReg: 0.0019, AllReg: 0.0016, BotRReg: 0.0019, OV: 0.8613, AltV: 0.8806, CorV: 0.8324, TopV: 0.8567, BotRV: 0.8568, AllV: 0.8806 +[2026-03-20T20:35:17.018286Z] Loop 13390: Reg: 0.0003, AltReg: 0.0004, CorReg: 0.0001, TopReg: 0.0009, AllReg: 0.0004, BotRReg: 0.0009, OV: 0.8633, AltV: 0.8818, CorV: 0.8355, TopV: 0.8577, BotRV: 0.8577, AllV: 0.8818 +[2026-03-20T20:35:25.605879Z] Loop 13400: Reg: 0.0001, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0002, BotRReg: 0.0004, OV: 0.8635, AltV: 0.8820, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8583, AllV: 0.8821 +[2026-03-20T20:35:34.183436Z] Loop 13410: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0003, BotRReg: 0.0006, OV: 0.8634, AltV: 0.8819, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8580, AllV: 0.8820 +[2026-03-20T20:35:42.770086Z] Loop 13420: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0003, BotRReg: 0.0013, OV: 0.8634, AltV: 0.8819, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8574, AllV: 0.8819 +[2026-03-20T20:35:51.354913Z] Loop 13430: Reg: 0.0007, AltReg: 0.0011, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0011, BotRReg: 0.0036, OV: 0.8629, AltV: 0.8811, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8550, AllV: 0.8811 +[2026-03-20T20:35:59.941434Z] Loop 13440: Reg: 0.0006, AltReg: 0.0008, CorReg: 0.0002, TopReg: 0.0005, AllReg: 0.0008, BotRReg: 0.0012, OV: 0.8630, AltV: 0.8814, CorV: 0.8355, TopV: 0.8581, BotRV: 0.8574, AllV: 0.8814 +[2026-03-20T20:36:08.525288Z] Loop 13450: Reg: 0.0016, AltReg: 0.0020, CorReg: 0.0009, TopReg: 0.0025, AllReg: 0.0020, BotRReg: 0.0007, OV: 0.8620, AltV: 0.8802, CorV: 0.8347, TopV: 0.8561, BotRV: 0.8579, AllV: 0.8802 +[2026-03-20T20:36:17.109176Z] Loop 13460: Reg: 0.0005, AltReg: 0.0007, CorReg: 0.0003, TopReg: 0.0007, AllReg: 0.0007, BotRReg: 0.0011, OV: 0.8630, AltV: 0.8815, CorV: 0.8354, TopV: 0.8579, BotRV: 0.8575, AllV: 0.8815 +[2026-03-20T20:36:25.693584Z] Loop 13470: Reg: 0.0009, AltReg: 0.0012, CorReg: 0.0004, TopReg: 0.0010, AllReg: 0.0012, BotRReg: 0.0021, OV: 0.8627, AltV: 0.8810, CorV: 0.8352, TopV: 0.8576, BotRV: 0.8565, AllV: 0.8810 +[2026-03-20T20:36:34.280163Z] Loop 13480: Reg: 0.0026, AltReg: 0.0030, CorReg: 0.0021, TopReg: 0.0038, AllReg: 0.0030, BotRReg: 0.0021, OV: 0.8609, AltV: 0.8792, CorV: 0.8336, TopV: 0.8548, BotRV: 0.8566, AllV: 0.8792 +[2026-03-20T20:36:42.858871Z] Loop 13490: Reg: 0.0019, AltReg: 0.0026, CorReg: 0.0008, TopReg: 0.0040, AllReg: 0.0026, BotRReg: 0.0025, OV: 0.8617, AltV: 0.8796, CorV: 0.8348, TopV: 0.8547, BotRV: 0.8561, AllV: 0.8796 +[2026-03-20T20:36:51.436826Z] Loop 13500: Reg: 0.0030, AltReg: 0.0049, CorReg: 0.0001, TopReg: 0.0005, AllReg: 0.0049, BotRReg: 0.0091, OV: 0.8606, AltV: 0.8773, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8495, AllV: 0.8773 +[2026-03-20T20:37:00.015313Z] Loop 13510: Reg: 0.0005, AltReg: 0.0008, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0008, BotRReg: 0.0024, OV: 0.8631, AltV: 0.8814, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8562, AllV: 0.8815 +[2026-03-20T20:37:08.598921Z] Loop 13520: Reg: 0.0031, AltReg: 0.0051, CorReg: 0.0002, TopReg: 0.0126, AllReg: 0.0051, BotRReg: 0.0012, OV: 0.8605, AltV: 0.8771, CorV: 0.8355, TopV: 0.8460, BotRV: 0.8574, AllV: 0.8772 +[2026-03-20T20:37:17.177175Z] Loop 13530: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0003, BotRReg: 0.0013, OV: 0.8634, AltV: 0.8819, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8573, AllV: 0.8820 +[2026-03-20T20:37:25.763793Z] Loop 13540: Reg: 0.0002, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0004, BotRReg: 0.0014, OV: 0.8634, AltV: 0.8818, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8573, AllV: 0.8819 +[2026-03-20T20:37:34.350517Z] Loop 13550: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0009, AllReg: 0.0006, BotRReg: 0.0015, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8577, BotRV: 0.8571, AllV: 0.8816 +[2026-03-20T20:37:42.933555Z] Loop 13560: Reg: 0.0005, AltReg: 0.0008, CorReg: 0.0000, TopReg: 0.0021, AllReg: 0.0009, BotRReg: 0.0020, OV: 0.8631, AltV: 0.8814, CorV: 0.8356, TopV: 0.8566, BotRV: 0.8566, AllV: 0.8814 +[2026-03-20T20:37:51.514992Z] Loop 13570: Reg: 0.0045, AltReg: 0.0076, CorReg: -0.0000, TopReg: 0.0371, AllReg: 0.0076, BotRReg: 0.0069, OV: 0.8590, AltV: 0.8746, CorV: 0.8356, TopV: 0.8215, BotRV: 0.8517, AllV: 0.8746 +[2026-03-20T20:38:00.094357Z] Loop 13580: Reg: 0.0014, AltReg: 0.0024, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0024, BotRReg: 0.0134, OV: 0.8622, AltV: 0.8799, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8452, AllV: 0.8799 +[2026-03-20T20:38:08.671677Z] Loop 13590: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0003, BotRReg: 0.0012, OV: 0.8634, AltV: 0.8819, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8574, AllV: 0.8819 +[2026-03-20T20:38:17.252093Z] Loop 13600: Reg: 0.0007, AltReg: 0.0011, CorReg: 0.0000, TopReg: 0.0035, AllReg: 0.0011, BotRReg: 0.0007, OV: 0.8629, AltV: 0.8811, CorV: 0.8356, TopV: 0.8551, BotRV: 0.8579, AllV: 0.8811 +[2026-03-20T20:38:25.831905Z] Loop 13610: Reg: 0.0021, AltReg: 0.0034, CorReg: 0.0001, TopReg: 0.0056, AllReg: 0.0035, BotRReg: 0.0004, OV: 0.8615, AltV: 0.8788, CorV: 0.8356, TopV: 0.8530, BotRV: 0.8583, AllV: 0.8788 +[2026-03-20T20:38:34.414790Z] Loop 13620: Reg: 0.0001, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0002, BotRReg: 0.0007, OV: 0.8634, AltV: 0.8820, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8579, AllV: 0.8820 +[2026-03-20T20:38:43.004473Z] Loop 13630: Reg: 0.0003, AltReg: 0.0005, CorReg: 0.0000, TopReg: 0.0006, AllReg: 0.0006, BotRReg: 0.0016, OV: 0.8633, AltV: 0.8817, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8571, AllV: 0.8817 +[2026-03-20T20:38:51.591219Z] Loop 13640: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0000, TopReg: 0.0009, AllReg: 0.0011, BotRReg: 0.0021, OV: 0.8630, AltV: 0.8812, CorV: 0.8356, TopV: 0.8577, BotRV: 0.8566, AllV: 0.8812 +[2026-03-20T20:39:00.174268Z] Loop 13650: Reg: 0.0025, AltReg: 0.0042, CorReg: 0.0000, TopReg: 0.0033, AllReg: 0.0042, BotRReg: 0.0041, OV: 0.8610, AltV: 0.8780, CorV: 0.8356, TopV: 0.8553, BotRV: 0.8545, AllV: 0.8780 +[2026-03-20T20:39:08.757103Z] Loop 13660: Reg: 0.0025, AltReg: 0.0042, CorReg: 0.0000, TopReg: 0.0029, AllReg: 0.0042, BotRReg: 0.0035, OV: 0.8611, AltV: 0.8780, CorV: 0.8356, TopV: 0.8557, BotRV: 0.8551, AllV: 0.8780 +[2026-03-20T20:39:17.342265Z] Loop 13670: Reg: 0.0028, AltReg: 0.0046, CorReg: 0.0000, TopReg: 0.0039, AllReg: 0.0046, BotRReg: 0.0025, OV: 0.8608, AltV: 0.8776, CorV: 0.8356, TopV: 0.8547, BotRV: 0.8561, AllV: 0.8776 +[2026-03-20T20:39:25.932799Z] Loop 13680: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0010, BotRReg: 0.0013, OV: 0.8630, AltV: 0.8812, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8573, AllV: 0.8813 +[2026-03-20T20:39:34.526898Z] Loop 13690: Reg: 0.0001, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0002, BotRReg: 0.0007, OV: 0.8635, AltV: 0.8820, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8579, AllV: 0.8821 +[2026-03-20T20:39:43.113578Z] Loop 13700: Reg: 0.0003, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0004, BotRReg: 0.0012, OV: 0.8633, AltV: 0.8818, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8574, AllV: 0.8818 +[2026-03-20T20:39:51.697707Z] Loop 13710: Reg: 0.0013, AltReg: 0.0021, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0021, BotRReg: 0.0087, OV: 0.8623, AltV: 0.8801, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8499, AllV: 0.8802 +[2026-03-20T20:40:00.276222Z] Loop 13720: Reg: 0.0010, AltReg: 0.0016, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0016, BotRReg: 0.0038, OV: 0.8626, AltV: 0.8806, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8548, AllV: 0.8806 +[2026-03-20T20:40:08.860061Z] Loop 13730: Reg: 0.0007, AltReg: 0.0011, CorReg: 0.0002, TopReg: 0.0010, AllReg: 0.0011, BotRReg: 0.0019, OV: 0.8628, AltV: 0.8811, CorV: 0.8355, TopV: 0.8576, BotRV: 0.8568, AllV: 0.8811 +[2026-03-20T20:40:17.442668Z] Loop 13740: Reg: 0.0005, AltReg: 0.0008, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0008, BotRReg: 0.0016, OV: 0.8631, AltV: 0.8814, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8570, AllV: 0.8814 +[2026-03-20T20:40:26.030252Z] Loop 13750: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0007, BotRReg: 0.0014, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8572, AllV: 0.8816 +[2026-03-20T20:40:34.613650Z] Loop 13760: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0006, BotRReg: 0.0011, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8575, AllV: 0.8816 +[2026-03-20T20:40:43.203683Z] Loop 13770: Reg: 0.0021, AltReg: 0.0034, CorReg: 0.0000, TopReg: 0.0036, AllReg: 0.0034, BotRReg: 0.0038, OV: 0.8615, AltV: 0.8788, CorV: 0.8356, TopV: 0.8550, BotRV: 0.8548, AllV: 0.8788 +[2026-03-20T20:40:51.785632Z] Loop 13780: Reg: 0.0008, AltReg: 0.0014, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0014, BotRReg: 0.0016, OV: 0.8628, AltV: 0.8809, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8570, AllV: 0.8809 +[2026-03-20T20:41:00.369631Z] Loop 13790: Reg: 0.0011, AltReg: 0.0017, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0017, BotRReg: 0.0020, OV: 0.8625, AltV: 0.8805, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8566, AllV: 0.8805 +[2026-03-20T20:41:08.952547Z] Loop 13800: Reg: 0.0012, AltReg: 0.0020, CorReg: 0.0000, TopReg: 0.0006, AllReg: 0.0020, BotRReg: 0.0030, OV: 0.8624, AltV: 0.8802, CorV: 0.8356, TopV: 0.8580, BotRV: 0.8556, AllV: 0.8802 +[2026-03-20T20:41:17.534144Z] Loop 13810: Reg: 0.0005, AltReg: 0.0008, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0009, BotRReg: 0.0018, OV: 0.8631, AltV: 0.8814, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8568, AllV: 0.8814 +[2026-03-20T20:41:26.116486Z] Loop 13820: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0001, TopReg: 0.0005, AllReg: 0.0006, BotRReg: 0.0015, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8571, AllV: 0.8817 +[2026-03-20T20:41:34.700557Z] Loop 13830: Reg: 0.0003, AltReg: 0.0005, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0006, BotRReg: 0.0014, OV: 0.8632, AltV: 0.8817, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8573, AllV: 0.8817 +[2026-03-20T20:41:43.279804Z] Loop 13840: Reg: 0.0003, AltReg: 0.0005, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0006, BotRReg: 0.0020, OV: 0.8633, AltV: 0.8817, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8567, AllV: 0.8817 +[2026-03-20T20:41:51.867998Z] Loop 13850: Reg: 0.0004, AltReg: 0.0007, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0007, BotRReg: 0.0026, OV: 0.8632, AltV: 0.8815, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8561, AllV: 0.8815 +[2026-03-20T20:42:00.455298Z] Loop 13860: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0006, BotRReg: 0.0023, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8563, AllV: 0.8816 +[2026-03-20T20:42:09.045298Z] Loop 13870: Reg: 0.0005, AltReg: 0.0008, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0008, BotRReg: 0.0033, OV: 0.8631, AltV: 0.8814, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8553, AllV: 0.8814 +[2026-03-20T20:42:17.631742Z] Loop 13880: Reg: 0.0010, AltReg: 0.0016, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0016, BotRReg: 0.0058, OV: 0.8626, AltV: 0.8806, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8528, AllV: 0.8806 +[2026-03-20T20:42:26.209210Z] Loop 13890: Reg: 0.0029, AltReg: 0.0047, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0048, BotRReg: 0.0140, OV: 0.8607, AltV: 0.8775, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8447, AllV: 0.8775 +[2026-03-20T20:42:34.792462Z] Loop 13900: Reg: 0.0011, AltReg: 0.0019, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0019, BotRReg: 0.0061, OV: 0.8625, AltV: 0.8804, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8525, AllV: 0.8804 +[2026-03-20T20:42:43.377532Z] Loop 13910: Reg: 0.0004, AltReg: 0.0007, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0007, BotRReg: 0.0021, OV: 0.8632, AltV: 0.8815, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8565, AllV: 0.8816 +[2026-03-20T20:42:51.965098Z] Loop 13920: Reg: 0.0010, AltReg: 0.0017, CorReg: 0.0001, TopReg: 0.0004, AllReg: 0.0017, BotRReg: 0.0022, OV: 0.8625, AltV: 0.8805, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8564, AllV: 0.8805 +[2026-03-20T20:43:00.547054Z] Loop 13930: Reg: 0.0013, AltReg: 0.0021, CorReg: 0.0001, TopReg: 0.0008, AllReg: 0.0021, BotRReg: 0.0044, OV: 0.8622, AltV: 0.8801, CorV: 0.8355, TopV: 0.8579, BotRV: 0.8543, AllV: 0.8801 +[2026-03-20T20:43:09.124734Z] Loop 13940: Reg: 0.0018, AltReg: 0.0027, CorReg: 0.0005, TopReg: 0.0021, AllReg: 0.0027, BotRReg: 0.0110, OV: 0.8618, AltV: 0.8795, CorV: 0.8352, TopV: 0.8565, BotRV: 0.8476, AllV: 0.8796 +[2026-03-20T20:43:17.704574Z] Loop 13950: Reg: 0.0018, AltReg: 0.0027, CorReg: 0.0004, TopReg: 0.0019, AllReg: 0.0027, BotRReg: 0.0128, OV: 0.8618, AltV: 0.8795, CorV: 0.8353, TopV: 0.8567, BotRV: 0.8458, AllV: 0.8796 +[2026-03-20T20:43:26.286900Z] Loop 13960: Reg: 0.0005, AltReg: 0.0009, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0009, BotRReg: 0.0033, OV: 0.8630, AltV: 0.8813, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8553, AllV: 0.8814 +[2026-03-20T20:43:34.871576Z] Loop 13970: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0010, BotRReg: 0.0036, OV: 0.8630, AltV: 0.8812, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8551, AllV: 0.8813 +[2026-03-20T20:43:43.453865Z] Loop 13980: Reg: 0.0005, AltReg: 0.0009, CorReg: 0.0001, TopReg: 0.0007, AllReg: 0.0009, BotRReg: 0.0022, OV: 0.8630, AltV: 0.8814, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8565, AllV: 0.8814 +[2026-03-20T20:43:52.032324Z] Loop 13990: Reg: 0.0010, AltReg: 0.0016, CorReg: 0.0002, TopReg: 0.0015, AllReg: 0.0016, BotRReg: 0.0021, OV: 0.8626, AltV: 0.8806, CorV: 0.8355, TopV: 0.8572, BotRV: 0.8565, AllV: 0.8806 +[2026-03-20T20:44:00.613566Z] Loop 14000: Reg: 0.0020, AltReg: 0.0027, CorReg: 0.0009, TopReg: 0.0033, AllReg: 0.0027, BotRReg: 0.0024, OV: 0.8616, AltV: 0.8795, CorV: 0.8347, TopV: 0.8554, BotRV: 0.8562, AllV: 0.8795 +[2026-03-20T20:44:09.192624Z] Loop 14010: Reg: 0.0011, AltReg: 0.0014, CorReg: 0.0006, TopReg: 0.0015, AllReg: 0.0014, BotRReg: 0.0027, OV: 0.8625, AltV: 0.8808, CorV: 0.8350, TopV: 0.8571, BotRV: 0.8559, AllV: 0.8808 +[2026-03-20T20:44:17.773502Z] Loop 14020: Reg: 0.0006, AltReg: 0.0009, CorReg: 0.0001, TopReg: 0.0005, AllReg: 0.0009, BotRReg: 0.0030, OV: 0.8630, AltV: 0.8813, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8557, AllV: 0.8813 +[2026-03-20T20:44:26.362648Z] Loop 14030: Reg: 0.0007, AltReg: 0.0011, CorReg: 0.0000, TopReg: 0.0006, AllReg: 0.0011, BotRReg: 0.0032, OV: 0.8629, AltV: 0.8811, CorV: 0.8356, TopV: 0.8580, BotRV: 0.8554, AllV: 0.8811 +[2026-03-20T20:44:34.947813Z] Loop 14040: Reg: 0.0025, AltReg: 0.0040, CorReg: 0.0002, TopReg: 0.0065, AllReg: 0.0041, BotRReg: 0.0020, OV: 0.8611, AltV: 0.8782, CorV: 0.8354, TopV: 0.8522, BotRV: 0.8566, AllV: 0.8782 +[2026-03-20T20:44:43.535190Z] Loop 14050: Reg: 0.0007, AltReg: 0.0011, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0011, BotRReg: 0.0025, OV: 0.8629, AltV: 0.8811, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8562, AllV: 0.8811 +[2026-03-20T20:44:52.117673Z] Loop 14060: Reg: 0.0005, AltReg: 0.0008, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0009, BotRReg: 0.0031, OV: 0.8631, AltV: 0.8814, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8555, AllV: 0.8814 +[2026-03-20T20:45:00.698500Z] Loop 14070: Reg: 0.0007, AltReg: 0.0012, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0012, BotRReg: 0.0044, OV: 0.8628, AltV: 0.8810, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8543, AllV: 0.8810 +[2026-03-20T20:45:09.281341Z] Loop 14080: Reg: 0.0028, AltReg: 0.0046, CorReg: 0.0000, TopReg: 0.0026, AllReg: 0.0046, BotRReg: 0.0093, OV: 0.8608, AltV: 0.8776, CorV: 0.8356, TopV: 0.8560, BotRV: 0.8493, AllV: 0.8777 +[2026-03-20T20:45:17.861764Z] Loop 14090: Reg: 0.0043, AltReg: 0.0064, CorReg: 0.0011, TopReg: 0.0011, AllReg: 0.0064, BotRReg: 0.0264, OV: 0.8593, AltV: 0.8758, CorV: 0.8345, TopV: 0.8575, BotRV: 0.8322, AllV: 0.8758 +[2026-03-20T20:45:26.444168Z] Loop 14100: Reg: 0.0008, AltReg: 0.0010, CorReg: 0.0004, TopReg: 0.0006, AllReg: 0.0010, BotRReg: 0.0026, OV: 0.8628, AltV: 0.8812, CorV: 0.8352, TopV: 0.8581, BotRV: 0.8560, AllV: 0.8813 +[2026-03-20T20:45:35.024628Z] Loop 14110: Reg: 0.0001, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0003, BotRReg: 0.0006, OV: 0.8634, AltV: 0.8820, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8580, AllV: 0.8820 +[2026-03-20T20:45:43.607653Z] Loop 14120: Reg: 0.0029, AltReg: 0.0048, CorReg: 0.0000, TopReg: 0.0049, AllReg: 0.0049, BotRReg: 0.0014, OV: 0.8607, AltV: 0.8774, CorV: 0.8356, TopV: 0.8537, BotRV: 0.8572, AllV: 0.8773 +[2026-03-20T20:45:52.185972Z] Loop 14130: Reg: 0.0013, AltReg: 0.0021, CorReg: 0.0000, TopReg: 0.0013, AllReg: 0.0021, BotRReg: 0.0015, OV: 0.8623, AltV: 0.8801, CorV: 0.8356, TopV: 0.8573, BotRV: 0.8571, AllV: 0.8801 +[2026-03-20T20:46:00.764651Z] Loop 14140: Reg: 0.0012, AltReg: 0.0020, CorReg: 0.0000, TopReg: 0.0009, AllReg: 0.0021, BotRReg: 0.0016, OV: 0.8624, AltV: 0.8802, CorV: 0.8356, TopV: 0.8577, BotRV: 0.8570, AllV: 0.8802 +[2026-03-20T20:46:09.342864Z] Loop 14150: Reg: 0.0004, AltReg: 0.0006, CorReg: -0.0000, TopReg: 0.0002, AllReg: 0.0007, BotRReg: 0.0012, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8574, AllV: 0.8816 +[2026-03-20T20:46:17.923853Z] Loop 14160: Reg: 0.0011, AltReg: 0.0018, CorReg: 0.0000, TopReg: 0.0006, AllReg: 0.0018, BotRReg: 0.0011, OV: 0.8625, AltV: 0.8805, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8575, AllV: 0.8804 +[2026-03-20T20:46:26.512081Z] Loop 14170: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0004, BotRReg: 0.0008, OV: 0.8634, AltV: 0.8819, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8579, AllV: 0.8819 +[2026-03-20T20:46:35.094169Z] Loop 14180: Reg: 0.0001, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0002, BotRReg: 0.0005, OV: 0.8635, AltV: 0.8820, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8581, AllV: 0.8821 +[2026-03-20T20:46:43.681226Z] Loop 14190: Reg: 0.0001, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0002, BotRReg: 0.0008, OV: 0.8635, AltV: 0.8821, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8578, AllV: 0.8821 +[2026-03-20T20:46:52.266144Z] Loop 14200: Reg: 0.0007, AltReg: 0.0012, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0013, BotRReg: 0.0057, OV: 0.8628, AltV: 0.8810, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8530, AllV: 0.8810 +[2026-03-20T20:47:00.857549Z] Loop 14210: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0010, BotRReg: 0.0058, OV: 0.8630, AltV: 0.8812, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8528, AllV: 0.8812 +[2026-03-20T20:47:09.437416Z] Loop 14220: Reg: 0.0005, AltReg: 0.0009, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0009, BotRReg: 0.0034, OV: 0.8631, AltV: 0.8813, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8552, AllV: 0.8814 +[2026-03-20T20:47:18.017053Z] Loop 14230: Reg: 0.0003, AltReg: 0.0005, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0006, BotRReg: 0.0020, OV: 0.8632, AltV: 0.8817, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8566, AllV: 0.8817 +[2026-03-20T20:47:26.599406Z] Loop 14240: Reg: 0.0006, AltReg: 0.0009, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0010, BotRReg: 0.0031, OV: 0.8630, AltV: 0.8813, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8555, AllV: 0.8813 +[2026-03-20T20:47:35.180224Z] Loop 14250: Reg: 0.0009, AltReg: 0.0015, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0016, BotRReg: 0.0041, OV: 0.8627, AltV: 0.8807, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8545, AllV: 0.8807 +[2026-03-20T20:47:43.758901Z] Loop 14260: Reg: 0.0011, AltReg: 0.0018, CorReg: -0.0000, TopReg: 0.0001, AllReg: 0.0018, BotRReg: 0.0035, OV: 0.8625, AltV: 0.8804, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8551, AllV: 0.8804 +[2026-03-20T20:47:52.340650Z] Loop 14270: Reg: 0.0003, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0006, BotRReg: 0.0017, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8569, AllV: 0.8816 +[2026-03-20T20:48:00.928057Z] Loop 14280: Reg: 0.0021, AltReg: 0.0035, CorReg: 0.0000, TopReg: 0.0010, AllReg: 0.0036, BotRReg: 0.0042, OV: 0.8615, AltV: 0.8787, CorV: 0.8356, TopV: 0.8577, BotRV: 0.8544, AllV: 0.8787 +[2026-03-20T20:48:09.509809Z] Loop 14290: Reg: 0.0030, AltReg: 0.0050, CorReg: 0.0000, TopReg: 0.0030, AllReg: 0.0051, BotRReg: 0.0077, OV: 0.8606, AltV: 0.8772, CorV: 0.8356, TopV: 0.8556, BotRV: 0.8509, AllV: 0.8772 +[2026-03-20T20:48:18.098214Z] Loop 14300: Reg: 0.0007, AltReg: 0.0012, CorReg: 0.0000, TopReg: 0.0017, AllReg: 0.0012, BotRReg: 0.0025, OV: 0.8629, AltV: 0.8810, CorV: 0.8356, TopV: 0.8570, BotRV: 0.8562, AllV: 0.8810 +[2026-03-20T20:48:26.685722Z] Loop 14310: Reg: 0.0004, AltReg: 0.0007, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0007, BotRReg: 0.0022, OV: 0.8632, AltV: 0.8815, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8564, AllV: 0.8816 +[2026-03-20T20:48:35.269747Z] Loop 14320: Reg: 0.0007, AltReg: 0.0011, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0012, BotRReg: 0.0052, OV: 0.8629, AltV: 0.8811, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8534, AllV: 0.8811 +[2026-03-20T20:48:43.852341Z] Loop 14330: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0003, BotRReg: 0.0013, OV: 0.8634, AltV: 0.8819, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8573, AllV: 0.8819 +[2026-03-20T20:48:52.435415Z] Loop 14340: Reg: 0.0010, AltReg: 0.0016, CorReg: 0.0000, TopReg: 0.0026, AllReg: 0.0016, BotRReg: 0.0022, OV: 0.8626, AltV: 0.8806, CorV: 0.8356, TopV: 0.8560, BotRV: 0.8564, AllV: 0.8806 +[2026-03-20T20:49:01.015913Z] Loop 14350: Reg: 0.0010, AltReg: 0.0017, CorReg: 0.0000, TopReg: 0.0013, AllReg: 0.0017, BotRReg: 0.0028, OV: 0.8626, AltV: 0.8805, CorV: 0.8356, TopV: 0.8573, BotRV: 0.8558, AllV: 0.8805 +[2026-03-20T20:49:09.600434Z] Loop 14360: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0003, BotRReg: 0.0013, OV: 0.8634, AltV: 0.8820, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8573, AllV: 0.8820 +[2026-03-20T20:49:18.184383Z] Loop 14370: Reg: 0.0002, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0004, BotRReg: 0.0014, OV: 0.8633, AltV: 0.8818, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8573, AllV: 0.8818 +[2026-03-20T20:49:26.766358Z] Loop 14380: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0006, BotRReg: 0.0019, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8567, AllV: 0.8816 +[2026-03-20T20:49:35.346493Z] Loop 14390: Reg: 0.0013, AltReg: 0.0021, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0021, BotRReg: 0.0034, OV: 0.8623, AltV: 0.8801, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8553, AllV: 0.8801 +[2026-03-20T20:49:43.921255Z] Loop 14400: Reg: 0.0007, AltReg: 0.0012, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0012, BotRReg: 0.0035, OV: 0.8628, AltV: 0.8810, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8552, AllV: 0.8810 +[2026-03-20T20:49:52.506689Z] Loop 14410: Reg: 0.0005, AltReg: 0.0008, CorReg: 0.0001, TopReg: 0.0014, AllReg: 0.0008, BotRReg: 0.0018, OV: 0.8631, AltV: 0.8814, CorV: 0.8356, TopV: 0.8572, BotRV: 0.8568, AllV: 0.8815 +[2026-03-20T20:50:01.090898Z] Loop 14420: Reg: 0.0001, AltReg: 0.0001, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0001, BotRReg: 0.0004, OV: 0.8635, AltV: 0.8821, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8582, AllV: 0.8821 +[2026-03-20T20:50:09.681027Z] Loop 14430: Reg: 0.0003, AltReg: 0.0005, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0005, BotRReg: 0.0007, OV: 0.8633, AltV: 0.8818, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8579, AllV: 0.8818 +[2026-03-20T20:50:18.262207Z] Loop 14440: Reg: 0.0001, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0002, BotRReg: 0.0006, OV: 0.8635, AltV: 0.8820, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8580, AllV: 0.8821 +[2026-03-20T20:50:26.845965Z] Loop 14450: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0004, BotRReg: 0.0006, OV: 0.8634, AltV: 0.8819, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8580, AllV: 0.8819 +[2026-03-20T20:50:35.424944Z] Loop 14460: Reg: 0.0002, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0004, BotRReg: 0.0003, OV: 0.8634, AltV: 0.8819, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8583, AllV: 0.8819 +[2026-03-20T20:50:44.011018Z] Loop 14470: Reg: 0.0001, AltReg: 0.0001, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0001, BotRReg: 0.0003, OV: 0.8635, AltV: 0.8821, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8583, AllV: 0.8822 +[2026-03-20T20:50:52.590881Z] Loop 14480: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0003, BotRReg: 0.0012, OV: 0.8634, AltV: 0.8819, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8574, AllV: 0.8819 +[2026-03-20T20:51:01.167582Z] Loop 14490: Reg: 0.0045, AltReg: 0.0076, CorReg: -0.0000, TopReg: 0.0042, AllReg: 0.0076, BotRReg: 0.0059, OV: 0.8590, AltV: 0.8746, CorV: 0.8356, TopV: 0.8544, BotRV: 0.8527, AllV: 0.8747 +[2026-03-20T20:51:09.749964Z] Loop 14500: Reg: 0.0023, AltReg: 0.0038, CorReg: 0.0000, TopReg: 0.0076, AllReg: 0.0038, BotRReg: 0.0014, OV: 0.8613, AltV: 0.8784, CorV: 0.8356, TopV: 0.8510, BotRV: 0.8572, AllV: 0.8784 +[2026-03-20T20:51:18.325910Z] Loop 14510: Reg: 0.0011, AltReg: 0.0018, CorReg: -0.0000, TopReg: 0.0042, AllReg: 0.0018, BotRReg: 0.0016, OV: 0.8625, AltV: 0.8804, CorV: 0.8356, TopV: 0.8544, BotRV: 0.8570, AllV: 0.8804 +[2026-03-20T20:51:26.916228Z] Loop 14520: Reg: 0.0008, AltReg: 0.0014, CorReg: 0.0000, TopReg: 0.0008, AllReg: 0.0014, BotRReg: 0.0030, OV: 0.8627, AltV: 0.8808, CorV: 0.8356, TopV: 0.8578, BotRV: 0.8556, AllV: 0.8809 +[2026-03-20T20:51:35.500494Z] Loop 14530: Reg: 0.0003, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0004, BotRReg: 0.0004, OV: 0.8633, AltV: 0.8818, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8583, AllV: 0.8818 +[2026-03-20T20:51:44.083393Z] Loop 14540: Reg: 0.0001, AltReg: 0.0001, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0001, BotRReg: 0.0002, OV: 0.8635, AltV: 0.8821, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8584, AllV: 0.8821 +[2026-03-20T20:51:52.666990Z] Loop 14550: Reg: 0.0002, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0004, BotRReg: 0.0006, OV: 0.8634, AltV: 0.8819, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8580, AllV: 0.8819 +[2026-03-20T20:52:01.251336Z] Loop 14560: Reg: 0.0001, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0002, BotRReg: 0.0007, OV: 0.8635, AltV: 0.8820, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8580, AllV: 0.8820 +[2026-03-20T20:52:09.835656Z] Loop 14570: Reg: 0.0001, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0002, BotRReg: 0.0011, OV: 0.8635, AltV: 0.8820, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8575, AllV: 0.8820 +[2026-03-20T20:52:18.417209Z] Loop 14580: Reg: 0.0001, AltReg: 0.0001, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0001, BotRReg: 0.0004, OV: 0.8635, AltV: 0.8821, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8583, AllV: 0.8821 +[2026-03-20T20:52:26.996947Z] Loop 14590: Reg: 0.0009, AltReg: 0.0015, CorReg: 0.0000, TopReg: 0.0006, AllReg: 0.0015, BotRReg: 0.0020, OV: 0.8627, AltV: 0.8807, CorV: 0.8356, TopV: 0.8580, BotRV: 0.8566, AllV: 0.8807 +[2026-03-20T20:52:35.577889Z] Loop 14600: Reg: 0.0023, AltReg: 0.0038, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0038, BotRReg: 0.0061, OV: 0.8613, AltV: 0.8784, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8526, AllV: 0.8785 +[2026-03-20T20:52:44.157146Z] Loop 14610: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0010, BotRReg: 0.0015, OV: 0.8630, AltV: 0.8812, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8571, AllV: 0.8812 +[2026-03-20T20:52:52.741288Z] Loop 14620: Reg: 0.0003, AltReg: 0.0005, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0005, BotRReg: 0.0011, OV: 0.8633, AltV: 0.8817, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8575, AllV: 0.8817 +[2026-03-20T20:53:01.328410Z] Loop 14630: Reg: 0.0002, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0008, AllReg: 0.0004, BotRReg: 0.0012, OV: 0.8633, AltV: 0.8818, CorV: 0.8356, TopV: 0.8578, BotRV: 0.8574, AllV: 0.8818 +[2026-03-20T20:53:09.912333Z] Loop 14640: Reg: 0.0001, AltReg: 0.0001, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0001, BotRReg: 0.0004, OV: 0.8635, AltV: 0.8821, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8582, AllV: 0.8821 +[2026-03-20T20:53:18.496411Z] Loop 14650: Reg: 0.0001, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0002, BotRReg: 0.0005, OV: 0.8635, AltV: 0.8820, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8581, AllV: 0.8821 +[2026-03-20T20:53:27.081640Z] Loop 14660: Reg: 0.0001, AltReg: 0.0001, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0001, BotRReg: 0.0005, OV: 0.8635, AltV: 0.8821, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8581, AllV: 0.8821 +[2026-03-20T20:53:35.661221Z] Loop 14670: Reg: 0.0001, AltReg: 0.0001, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0001, BotRReg: 0.0005, OV: 0.8635, AltV: 0.8821, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8582, AllV: 0.8821 +[2026-03-20T20:53:44.245895Z] Loop 14680: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0003, BotRReg: 0.0007, OV: 0.8634, AltV: 0.8820, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8579, AllV: 0.8820 +[2026-03-20T20:53:52.823368Z] Loop 14690: Reg: 0.0001, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0002, BotRReg: 0.0005, OV: 0.8635, AltV: 0.8820, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8581, AllV: 0.8820 +[2026-03-20T20:54:01.410548Z] Loop 14700: Reg: 0.0001, AltReg: 0.0001, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0001, BotRReg: 0.0002, OV: 0.8635, AltV: 0.8821, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8584, AllV: 0.8821 +[2026-03-20T20:54:09.993608Z] Loop 14710: Reg: 0.0010, AltReg: 0.0017, CorReg: 0.0000, TopReg: 0.0026, AllReg: 0.0017, BotRReg: 0.0006, OV: 0.8626, AltV: 0.8805, CorV: 0.8356, TopV: 0.8560, BotRV: 0.8580, AllV: 0.8806 +[2026-03-20T20:54:18.576125Z] Loop 14720: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0000, TopReg: 0.0011, AllReg: 0.0011, BotRReg: 0.0021, OV: 0.8630, AltV: 0.8812, CorV: 0.8356, TopV: 0.8575, BotRV: 0.8565, AllV: 0.8812 +[2026-03-20T20:54:27.162274Z] Loop 14730: Reg: 0.0008, AltReg: 0.0013, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0013, BotRReg: 0.0033, OV: 0.8628, AltV: 0.8810, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8553, AllV: 0.8810 +[2026-03-20T20:54:35.744073Z] Loop 14740: Reg: 0.0013, AltReg: 0.0022, CorReg: 0.0000, TopReg: 0.0019, AllReg: 0.0022, BotRReg: 0.0045, OV: 0.8623, AltV: 0.8801, CorV: 0.8356, TopV: 0.8567, BotRV: 0.8541, AllV: 0.8801 +[2026-03-20T20:54:44.325280Z] Loop 14750: Reg: 0.0006, AltReg: 0.0009, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0009, BotRReg: 0.0031, OV: 0.8630, AltV: 0.8813, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8555, AllV: 0.8813 +[2026-03-20T20:54:52.913684Z] Loop 14760: Reg: 0.0011, AltReg: 0.0018, CorReg: 0.0000, TopReg: 0.0010, AllReg: 0.0018, BotRReg: 0.0043, OV: 0.8625, AltV: 0.8804, CorV: 0.8356, TopV: 0.8576, BotRV: 0.8544, AllV: 0.8804 +[2026-03-20T20:55:01.489229Z] Loop 14770: Reg: 0.0036, AltReg: 0.0060, CorReg: 0.0000, TopReg: 0.0043, AllReg: 0.0062, BotRReg: 0.0018, OV: 0.8600, AltV: 0.8762, CorV: 0.8356, TopV: 0.8544, BotRV: 0.8568, AllV: 0.8761 +[2026-03-20T20:55:10.075327Z] Loop 14780: Reg: 0.0003, AltReg: 0.0005, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0006, BotRReg: 0.0010, OV: 0.8633, AltV: 0.8817, CorV: 0.8356, TopV: 0.8580, BotRV: 0.8576, AllV: 0.8817 +[2026-03-20T20:55:18.661043Z] Loop 14790: Reg: 0.0003, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0004, BotRReg: 0.0011, OV: 0.8633, AltV: 0.8818, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8575, AllV: 0.8818 +[2026-03-20T20:55:27.246711Z] Loop 14800: Reg: 0.0036, AltReg: 0.0059, CorReg: 0.0000, TopReg: 0.0083, AllReg: 0.0060, BotRReg: 0.0026, OV: 0.8600, AltV: 0.8763, CorV: 0.8356, TopV: 0.8503, BotRV: 0.8561, AllV: 0.8763 +[2026-03-20T20:55:35.826142Z] Loop 14810: Reg: 0.0028, AltReg: 0.0047, CorReg: 0.0000, TopReg: 0.0077, AllReg: 0.0047, BotRReg: 0.0042, OV: 0.8608, AltV: 0.8776, CorV: 0.8356, TopV: 0.8509, BotRV: 0.8545, AllV: 0.8776 +[2026-03-20T20:55:44.416678Z] Loop 14820: Reg: 0.0005, AltReg: 0.0009, CorReg: 0.0000, TopReg: 0.0015, AllReg: 0.0009, BotRReg: 0.0024, OV: 0.8630, AltV: 0.8813, CorV: 0.8356, TopV: 0.8572, BotRV: 0.8562, AllV: 0.8814 +[2026-03-20T20:55:53.000108Z] Loop 14830: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0003, BotRReg: 0.0008, OV: 0.8634, AltV: 0.8819, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8578, AllV: 0.8819 +[2026-03-20T20:56:01.586462Z] Loop 14840: Reg: 0.0002, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0004, BotRReg: 0.0008, OV: 0.8634, AltV: 0.8819, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8579, AllV: 0.8819 +[2026-03-20T20:56:10.184016Z] Loop 14850: Reg: 0.0004, AltReg: 0.0007, CorReg: 0.0000, TopReg: 0.0008, AllReg: 0.0007, BotRReg: 0.0015, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8571, AllV: 0.8816 +[2026-03-20T20:56:18.779081Z] Loop 14860: Reg: 0.0003, AltReg: 0.0005, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0005, BotRReg: 0.0011, OV: 0.8633, AltV: 0.8818, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8575, AllV: 0.8818 +[2026-03-20T20:56:27.375822Z] Loop 14870: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0006, AllReg: 0.0003, BotRReg: 0.0011, OV: 0.8634, AltV: 0.8819, CorV: 0.8356, TopV: 0.8580, BotRV: 0.8575, AllV: 0.8819 +[2026-03-20T20:56:35.958629Z] Loop 14880: Reg: 0.0009, AltReg: 0.0015, CorReg: 0.0000, TopReg: 0.0039, AllReg: 0.0015, BotRReg: 0.0025, OV: 0.8627, AltV: 0.8807, CorV: 0.8356, TopV: 0.8548, BotRV: 0.8561, AllV: 0.8807 +[2026-03-20T20:56:44.541622Z] Loop 14890: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0014, AllReg: 0.0006, BotRReg: 0.0018, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8572, BotRV: 0.8569, AllV: 0.8816 +[2026-03-20T20:56:53.125202Z] Loop 14900: Reg: 0.0005, AltReg: 0.0009, CorReg: 0.0000, TopReg: 0.0025, AllReg: 0.0009, BotRReg: 0.0028, OV: 0.8630, AltV: 0.8813, CorV: 0.8356, TopV: 0.8561, BotRV: 0.8559, AllV: 0.8813 +[2026-03-20T20:57:01.705359Z] Loop 14910: Reg: 0.0020, AltReg: 0.0034, CorReg: 0.0000, TopReg: 0.0032, AllReg: 0.0034, BotRReg: 0.0075, OV: 0.8615, AltV: 0.8788, CorV: 0.8356, TopV: 0.8554, BotRV: 0.8512, AllV: 0.8788 +[2026-03-20T20:57:10.294746Z] Loop 14920: Reg: 0.0018, AltReg: 0.0030, CorReg: 0.0000, TopReg: 0.0008, AllReg: 0.0031, BotRReg: 0.0072, OV: 0.8618, AltV: 0.8792, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8514, AllV: 0.8792 +[2026-03-20T20:57:18.876056Z] Loop 14930: Reg: 0.0003, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0004, BotRReg: 0.0017, OV: 0.8633, AltV: 0.8818, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8570, AllV: 0.8818 +[2026-03-20T20:57:27.461644Z] Loop 14940: Reg: 0.0010, AltReg: 0.0015, CorReg: 0.0001, TopReg: 0.0020, AllReg: 0.0016, BotRReg: 0.0014, OV: 0.8626, AltV: 0.8807, CorV: 0.8355, TopV: 0.8567, BotRV: 0.8572, AllV: 0.8807 +[2026-03-20T20:57:36.040999Z] Loop 14950: Reg: 0.0028, AltReg: 0.0040, CorReg: 0.0009, TopReg: 0.0044, AllReg: 0.0040, BotRReg: 0.0010, OV: 0.8608, AltV: 0.8782, CorV: 0.8348, TopV: 0.8542, BotRV: 0.8576, AllV: 0.8782 +[2026-03-20T20:57:44.616541Z] Loop 14960: Reg: 0.0011, AltReg: 0.0013, CorReg: 0.0008, TopReg: 0.0014, AllReg: 0.0014, BotRReg: 0.0010, OV: 0.8625, AltV: 0.8809, CorV: 0.8349, TopV: 0.8572, BotRV: 0.8576, AllV: 0.8809 +[2026-03-20T20:57:53.198774Z] Loop 14970: Reg: 0.0009, AltReg: 0.0013, CorReg: 0.0003, TopReg: 0.0014, AllReg: 0.0013, BotRReg: 0.0010, OV: 0.8627, AltV: 0.8810, CorV: 0.8353, TopV: 0.8572, BotRV: 0.8576, AllV: 0.8810 +[2026-03-20T20:58:01.785289Z] Loop 14980: Reg: 0.0001, AltReg: 0.0001, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0001, BotRReg: 0.0006, OV: 0.8635, AltV: 0.8821, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8581, AllV: 0.8821 +[2026-03-20T20:58:10.360438Z] Loop 14990: Reg: 0.0001, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0002, BotRReg: 0.0002, OV: 0.8635, AltV: 0.8821, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8585, AllV: 0.8821 +[2026-03-20T20:58:18.937867Z] Loop 15000: Reg: 0.0014, AltReg: 0.0023, CorReg: 0.0001, TopReg: 0.0015, AllReg: 0.0024, BotRReg: 0.0001, OV: 0.8621, AltV: 0.8799, CorV: 0.8355, TopV: 0.8571, BotRV: 0.8586, AllV: 0.8799 +[2026-03-20T20:58:27.520466Z] Loop 15010: Reg: 0.0001, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0002, BotRReg: 0.0001, OV: 0.8635, AltV: 0.8820, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8586, AllV: 0.8821 +[2026-03-20T20:58:36.102214Z] Loop 15020: Reg: 0.0001, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0002, BotRReg: 0.0002, OV: 0.8635, AltV: 0.8820, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8585, AllV: 0.8820 +[2026-03-20T20:58:44.684434Z] Loop 15030: Reg: 0.0005, AltReg: 0.0008, CorReg: 0.0000, TopReg: 0.0009, AllReg: 0.0008, BotRReg: 0.0040, OV: 0.8631, AltV: 0.8815, CorV: 0.8356, TopV: 0.8577, BotRV: 0.8547, AllV: 0.8815 +[2026-03-20T20:58:53.266578Z] Loop 15040: Reg: 0.0010, AltReg: 0.0016, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0016, BotRReg: 0.0027, OV: 0.8626, AltV: 0.8806, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8559, AllV: 0.8806 +[2026-03-20T20:59:01.852442Z] Loop 15050: Reg: 0.0018, AltReg: 0.0030, CorReg: 0.0000, TopReg: 0.0008, AllReg: 0.0030, BotRReg: 0.0034, OV: 0.8618, AltV: 0.8792, CorV: 0.8356, TopV: 0.8578, BotRV: 0.8552, AllV: 0.8793 +[2026-03-20T20:59:10.432812Z] Loop 15060: Reg: 0.0016, AltReg: 0.0027, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0027, BotRReg: 0.0032, OV: 0.8620, AltV: 0.8795, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8555, AllV: 0.8796 +[2026-03-20T20:59:19.018507Z] Loop 15070: Reg: 0.0022, AltReg: 0.0037, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0037, BotRReg: 0.0073, OV: 0.8613, AltV: 0.8785, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8513, AllV: 0.8785 +[2026-03-20T20:59:27.599967Z] Loop 15080: Reg: 0.0010, AltReg: 0.0017, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0017, BotRReg: 0.0037, OV: 0.8625, AltV: 0.8805, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8550, AllV: 0.8805 +[2026-03-20T20:59:36.178860Z] Loop 15090: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0003, BotRReg: 0.0007, OV: 0.8634, AltV: 0.8819, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8579, AllV: 0.8819 +[2026-03-20T20:59:44.761496Z] Loop 15100: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0003, BotRReg: 0.0007, OV: 0.8634, AltV: 0.8819, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8579, AllV: 0.8819 +[2026-03-20T20:59:53.360228Z] Loop 15110: Reg: 0.0017, AltReg: 0.0029, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0029, BotRReg: 0.0049, OV: 0.8618, AltV: 0.8793, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8537, AllV: 0.8794 +[2026-03-20T21:00:01.952800Z] Loop 15120: Reg: 0.0003, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0004, BotRReg: 0.0007, OV: 0.8633, AltV: 0.8818, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8579, AllV: 0.8818 +[2026-03-20T21:00:10.537066Z] Loop 15130: Reg: 0.0002, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0008, AllReg: 0.0004, BotRReg: 0.0002, OV: 0.8633, AltV: 0.8818, CorV: 0.8356, TopV: 0.8578, BotRV: 0.8585, AllV: 0.8819 +[2026-03-20T21:00:19.119313Z] Loop 15140: Reg: 0.0006, AltReg: 0.0009, CorReg: 0.0000, TopReg: 0.0014, AllReg: 0.0009, BotRReg: 0.0006, OV: 0.8630, AltV: 0.8813, CorV: 0.8356, TopV: 0.8573, BotRV: 0.8581, AllV: 0.8813 +[2026-03-20T21:00:27.698230Z] Loop 15150: Reg: 0.0052, AltReg: 0.0086, CorReg: 0.0000, TopReg: 0.0148, AllReg: 0.0086, BotRReg: 0.0038, OV: 0.8584, AltV: 0.8736, CorV: 0.8356, TopV: 0.8438, BotRV: 0.8548, AllV: 0.8736 +[2026-03-20T21:00:36.276218Z] Loop 15160: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0000, TopReg: 0.0012, AllReg: 0.0010, BotRReg: 0.0020, OV: 0.8630, AltV: 0.8813, CorV: 0.8356, TopV: 0.8574, BotRV: 0.8566, AllV: 0.8813 +[2026-03-20T21:00:44.859179Z] Loop 15170: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0011, BotRReg: 0.0029, OV: 0.8630, AltV: 0.8812, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8557, AllV: 0.8812 +[2026-03-20T21:00:53.446137Z] Loop 15180: Reg: 0.0013, AltReg: 0.0021, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0021, BotRReg: 0.0057, OV: 0.8623, AltV: 0.8801, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8529, AllV: 0.8801 +[2026-03-20T21:01:02.023287Z] Loop 15190: Reg: 0.0013, AltReg: 0.0021, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0021, BotRReg: 0.0059, OV: 0.8623, AltV: 0.8801, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8527, AllV: 0.8801 +[2026-03-20T21:01:10.603391Z] Loop 15200: Reg: 0.0010, AltReg: 0.0017, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0017, BotRReg: 0.0056, OV: 0.8625, AltV: 0.8805, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8531, AllV: 0.8805 +[2026-03-20T21:01:19.184911Z] Loop 15210: Reg: 0.0020, AltReg: 0.0032, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0032, BotRReg: 0.0084, OV: 0.8616, AltV: 0.8790, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8502, AllV: 0.8790 +[2026-03-20T21:01:27.768805Z] Loop 15220: Reg: 0.0006, AltReg: 0.0009, CorReg: 0.0001, TopReg: 0.0001, AllReg: 0.0009, BotRReg: 0.0027, OV: 0.8630, AltV: 0.8813, CorV: 0.8355, TopV: 0.8585, BotRV: 0.8559, AllV: 0.8813 +[2026-03-20T21:01:36.346411Z] Loop 15230: Reg: 0.0010, AltReg: 0.0016, CorReg: 0.0001, TopReg: 0.0001, AllReg: 0.0016, BotRReg: 0.0045, OV: 0.8625, AltV: 0.8806, CorV: 0.8355, TopV: 0.8585, BotRV: 0.8542, AllV: 0.8806 +[2026-03-20T21:01:44.926521Z] Loop 15240: Reg: 0.0009, AltReg: 0.0014, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0014, BotRReg: 0.0044, OV: 0.8627, AltV: 0.8808, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8542, AllV: 0.8809 +[2026-03-20T21:01:53.513075Z] Loop 15250: Reg: 0.0006, AltReg: 0.0008, CorReg: 0.0002, TopReg: 0.0002, AllReg: 0.0008, BotRReg: 0.0021, OV: 0.8630, AltV: 0.8814, CorV: 0.8354, TopV: 0.8585, BotRV: 0.8566, AllV: 0.8815 +[2026-03-20T21:02:02.101693Z] Loop 15260: Reg: 0.0007, AltReg: 0.0008, CorReg: 0.0005, TopReg: 0.0004, AllReg: 0.0008, BotRReg: 0.0013, OV: 0.8629, AltV: 0.8814, CorV: 0.8352, TopV: 0.8582, BotRV: 0.8573, AllV: 0.8815 +[2026-03-20T21:02:10.684944Z] Loop 15270: Reg: 0.0013, AltReg: 0.0017, CorReg: 0.0006, TopReg: 0.0008, AllReg: 0.0017, BotRReg: 0.0031, OV: 0.8623, AltV: 0.8805, CorV: 0.8350, TopV: 0.8579, BotRV: 0.8555, AllV: 0.8805 +[2026-03-20T21:02:19.261273Z] Loop 15280: Reg: 0.0009, AltReg: 0.0015, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0015, BotRReg: 0.0039, OV: 0.8627, AltV: 0.8807, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8547, AllV: 0.8808 +[2026-03-20T21:02:27.838712Z] Loop 15290: Reg: 0.0009, AltReg: 0.0016, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0016, BotRReg: 0.0058, OV: 0.8626, AltV: 0.8806, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8528, AllV: 0.8807 +[2026-03-20T21:02:36.420619Z] Loop 15300: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0010, BotRReg: 0.0012, OV: 0.8630, AltV: 0.8812, CorV: 0.8356, TopV: 0.8580, BotRV: 0.8574, AllV: 0.8813 +[2026-03-20T21:02:45.001059Z] Loop 15310: Reg: 0.0006, AltReg: 0.0009, CorReg: 0.0000, TopReg: 0.0008, AllReg: 0.0010, BotRReg: 0.0006, OV: 0.8630, AltV: 0.8813, CorV: 0.8356, TopV: 0.8578, BotRV: 0.8580, AllV: 0.8813 +[2026-03-20T21:02:53.582878Z] Loop 15320: Reg: 0.0003, AltReg: 0.0005, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0005, BotRReg: 0.0006, OV: 0.8633, AltV: 0.8817, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8581, AllV: 0.8818 +[2026-03-20T21:03:02.162398Z] Loop 15330: Reg: 0.0001, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0002, BotRReg: 0.0005, OV: 0.8635, AltV: 0.8820, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8581, AllV: 0.8821 +[2026-03-20T21:03:10.748294Z] Loop 15340: Reg: 0.0001, AltReg: 0.0001, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0001, BotRReg: 0.0003, OV: 0.8635, AltV: 0.8821, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8583, AllV: 0.8821 +[2026-03-20T21:03:19.328408Z] Loop 15350: Reg: 0.0001, AltReg: 0.0001, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0001, BotRReg: 0.0005, OV: 0.8635, AltV: 0.8821, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8581, AllV: 0.8821 +[2026-03-20T21:03:27.908149Z] Loop 15360: Reg: 0.0002, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0004, BotRReg: 0.0016, OV: 0.8634, AltV: 0.8818, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8570, AllV: 0.8819 +[2026-03-20T21:03:36.489780Z] Loop 15370: Reg: 0.0008, AltReg: 0.0014, CorReg: 0.0000, TopReg: 0.0011, AllReg: 0.0014, BotRReg: 0.0063, OV: 0.8627, AltV: 0.8808, CorV: 0.8356, TopV: 0.8575, BotRV: 0.8523, AllV: 0.8809 +[2026-03-20T21:03:45.068228Z] Loop 15380: Reg: 0.0005, AltReg: 0.0007, CorReg: 0.0001, TopReg: 0.0003, AllReg: 0.0007, BotRReg: 0.0033, OV: 0.8631, AltV: 0.8815, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8553, AllV: 0.8815 +[2026-03-20T21:03:53.653232Z] Loop 15390: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0006, BotRReg: 0.0033, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8553, AllV: 0.8816 +[2026-03-20T21:04:02.239922Z] Loop 15400: Reg: 0.0001, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0002, BotRReg: 0.0008, OV: 0.8635, AltV: 0.8820, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8579, AllV: 0.8821 +[2026-03-20T21:04:10.826516Z] Loop 15410: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0006, BotRReg: 0.0015, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8571, AllV: 0.8816 +[2026-03-20T21:04:19.413057Z] Loop 15420: Reg: 0.0011, AltReg: 0.0019, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0019, BotRReg: 0.0047, OV: 0.8624, AltV: 0.8803, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8539, AllV: 0.8803 +[2026-03-20T21:04:28.000603Z] Loop 15430: Reg: 0.0024, AltReg: 0.0040, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0040, BotRReg: 0.0085, OV: 0.8612, AltV: 0.8782, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8501, AllV: 0.8782 +[2026-03-20T21:04:36.583880Z] Loop 15440: Reg: 0.0023, AltReg: 0.0039, CorReg: 0.0000, TopReg: 0.0008, AllReg: 0.0039, BotRReg: 0.0117, OV: 0.8613, AltV: 0.8783, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8469, AllV: 0.8784 +[2026-03-20T21:04:45.164970Z] Loop 15450: Reg: 0.0015, AltReg: 0.0025, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0025, BotRReg: 0.0112, OV: 0.8621, AltV: 0.8797, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8475, AllV: 0.8798 +[2026-03-20T21:04:53.751389Z] Loop 15460: Reg: 0.0013, AltReg: 0.0018, CorReg: 0.0006, TopReg: 0.0005, AllReg: 0.0018, BotRReg: 0.0054, OV: 0.8623, AltV: 0.8805, CorV: 0.8351, TopV: 0.8581, BotRV: 0.8533, AllV: 0.8805 +[2026-03-20T21:05:02.331550Z] Loop 15470: Reg: 0.0072, AltReg: 0.0096, CorReg: 0.0036, TopReg: 0.0140, AllReg: 0.0096, BotRReg: 0.0451, OV: 0.8564, AltV: 0.8726, CorV: 0.8321, TopV: 0.8446, BotRV: 0.8135, AllV: 0.8727 +[2026-03-20T21:05:10.906765Z] Loop 15480: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0003, BotRReg: 0.0001, OV: 0.8634, AltV: 0.8819, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8585, AllV: 0.8820 +[2026-03-20T21:05:19.488855Z] Loop 15490: Reg: 0.0001, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0002, BotRReg: 0.0003, OV: 0.8635, AltV: 0.8820, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8583, AllV: 0.8821 +[2026-03-20T21:05:28.070372Z] Loop 15500: Reg: 0.0003, AltReg: 0.0004, CorReg: 0.0001, TopReg: 0.0005, AllReg: 0.0004, BotRReg: 0.0007, OV: 0.8633, AltV: 0.8818, CorV: 0.8355, TopV: 0.8581, BotRV: 0.8580, AllV: 0.8818 +[2026-03-20T21:05:36.649114Z] Loop 15510: Reg: 0.0008, AltReg: 0.0011, CorReg: 0.0002, TopReg: 0.0027, AllReg: 0.0011, BotRReg: 0.0008, OV: 0.8628, AltV: 0.8811, CorV: 0.8354, TopV: 0.8559, BotRV: 0.8579, AllV: 0.8811 +[2026-03-20T21:05:45.231311Z] Loop 15520: Reg: 0.0003, AltReg: 0.0005, CorReg: 0.0001, TopReg: 0.0007, AllReg: 0.0005, BotRReg: 0.0004, OV: 0.8632, AltV: 0.8817, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8582, AllV: 0.8817 +[2026-03-20T21:05:53.811228Z] Loop 15530: Reg: 0.0003, AltReg: 0.0005, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0005, BotRReg: 0.0005, OV: 0.8633, AltV: 0.8817, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8582, AllV: 0.8817 +[2026-03-20T21:06:07.709620Z] Loop 15540: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0008, AllReg: 0.0006, BotRReg: 0.0004, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8578, BotRV: 0.8582, AllV: 0.8816 +[2026-03-20T21:06:16.290767Z] Loop 15550: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0000, TopReg: 0.0012, AllReg: 0.0010, BotRReg: 0.0011, OV: 0.8630, AltV: 0.8812, CorV: 0.8356, TopV: 0.8574, BotRV: 0.8576, AllV: 0.8812 +[2026-03-20T21:06:24.870045Z] Loop 15560: Reg: 0.0025, AltReg: 0.0041, CorReg: 0.0001, TopReg: 0.0024, AllReg: 0.0042, BotRReg: 0.0002, OV: 0.8611, AltV: 0.8781, CorV: 0.8355, TopV: 0.8562, BotRV: 0.8584, AllV: 0.8781 +[2026-03-20T21:06:33.444749Z] Loop 15570: Reg: 0.0003, AltReg: 0.0005, CorReg: 0.0001, TopReg: 0.0005, AllReg: 0.0005, BotRReg: 0.0005, OV: 0.8633, AltV: 0.8817, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8582, AllV: 0.8817 +[2026-03-20T21:06:42.026109Z] Loop 15580: Reg: 0.0010, AltReg: 0.0016, CorReg: 0.0001, TopReg: 0.0021, AllReg: 0.0017, BotRReg: 0.0007, OV: 0.8626, AltV: 0.8806, CorV: 0.8355, TopV: 0.8566, BotRV: 0.8579, AllV: 0.8806 +[2026-03-20T21:06:50.604618Z] Loop 15590: Reg: 0.0006, AltReg: 0.0009, CorReg: 0.0001, TopReg: 0.0009, AllReg: 0.0009, BotRReg: 0.0012, OV: 0.8630, AltV: 0.8813, CorV: 0.8356, TopV: 0.8577, BotRV: 0.8574, AllV: 0.8813 +[2026-03-20T21:06:59.189539Z] Loop 15600: Reg: 0.0003, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0004, BotRReg: 0.0010, OV: 0.8633, AltV: 0.8818, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8576, AllV: 0.8818 +[2026-03-20T21:07:07.766589Z] Loop 15610: Reg: 0.0003, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0004, BotRReg: 0.0013, OV: 0.8633, AltV: 0.8818, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8574, AllV: 0.8818 +[2026-03-20T21:07:16.344387Z] Loop 15620: Reg: 0.0010, AltReg: 0.0017, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0017, BotRReg: 0.0072, OV: 0.8625, AltV: 0.8805, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8515, AllV: 0.8805 +[2026-03-20T21:07:24.926047Z] Loop 15630: Reg: 0.0002, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0004, BotRReg: 0.0015, OV: 0.8634, AltV: 0.8818, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8571, AllV: 0.8819 +[2026-03-20T21:07:33.513201Z] Loop 15640: Reg: 0.0002, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0004, BotRReg: 0.0006, OV: 0.8633, AltV: 0.8818, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8580, AllV: 0.8819 +[2026-03-20T21:07:42.096000Z] Loop 15650: Reg: 0.0008, AltReg: 0.0014, CorReg: 0.0000, TopReg: 0.0015, AllReg: 0.0014, BotRReg: 0.0016, OV: 0.8627, AltV: 0.8808, CorV: 0.8356, TopV: 0.8571, BotRV: 0.8571, AllV: 0.8809 +[2026-03-20T21:07:50.680798Z] Loop 15660: Reg: 0.0011, AltReg: 0.0018, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0018, BotRReg: 0.0062, OV: 0.8625, AltV: 0.8805, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8525, AllV: 0.8805 +[2026-03-20T21:07:59.260403Z] Loop 15670: Reg: 0.0010, AltReg: 0.0017, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0017, BotRReg: 0.0065, OV: 0.8625, AltV: 0.8805, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8521, AllV: 0.8805 +[2026-03-20T21:08:07.842443Z] Loop 15680: Reg: 0.0008, AltReg: 0.0012, CorReg: 0.0001, TopReg: 0.0002, AllReg: 0.0012, BotRReg: 0.0048, OV: 0.8628, AltV: 0.8810, CorV: 0.8355, TopV: 0.8585, BotRV: 0.8538, AllV: 0.8810 +[2026-03-20T21:08:16.426006Z] Loop 15690: Reg: 0.0006, AltReg: 0.0007, CorReg: 0.0003, TopReg: 0.0004, AllReg: 0.0007, BotRReg: 0.0018, OV: 0.8630, AltV: 0.8815, CorV: 0.8353, TopV: 0.8582, BotRV: 0.8569, AllV: 0.8815 +[2026-03-20T21:08:25.006440Z] Loop 15700: Reg: 0.0005, AltReg: 0.0007, CorReg: 0.0002, TopReg: 0.0005, AllReg: 0.0007, BotRReg: 0.0020, OV: 0.8631, AltV: 0.8815, CorV: 0.8354, TopV: 0.8582, BotRV: 0.8567, AllV: 0.8815 +[2026-03-20T21:08:33.588492Z] Loop 15710: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0001, TopReg: 0.0002, AllReg: 0.0010, BotRReg: 0.0035, OV: 0.8630, AltV: 0.8812, CorV: 0.8355, TopV: 0.8584, BotRV: 0.8551, AllV: 0.8813 +[2026-03-20T21:08:42.174633Z] Loop 15720: Reg: 0.0008, AltReg: 0.0013, CorReg: 0.0001, TopReg: 0.0002, AllReg: 0.0013, BotRReg: 0.0056, OV: 0.8628, AltV: 0.8809, CorV: 0.8356, TopV: 0.8584, BotRV: 0.8531, AllV: 0.8810 +[2026-03-20T21:08:50.759086Z] Loop 15730: Reg: 0.0006, AltReg: 0.0009, CorReg: 0.0001, TopReg: 0.0011, AllReg: 0.0009, BotRReg: 0.0019, OV: 0.8630, AltV: 0.8813, CorV: 0.8355, TopV: 0.8575, BotRV: 0.8567, AllV: 0.8814 +[2026-03-20T21:08:59.349140Z] Loop 15740: Reg: 0.0002, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0002, BotRReg: 0.0005, OV: 0.8634, AltV: 0.8820, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8581, AllV: 0.8820 +[2026-03-20T21:09:07.931106Z] Loop 15750: Reg: 0.0001, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0002, BotRReg: 0.0005, OV: 0.8635, AltV: 0.8820, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8582, AllV: 0.8821 +[2026-03-20T21:09:16.513183Z] Loop 15760: Reg: 0.0001, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0002, BotRReg: 0.0009, OV: 0.8634, AltV: 0.8820, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8578, AllV: 0.8820 +[2026-03-20T21:09:25.096875Z] Loop 15770: Reg: 0.0003, AltReg: 0.0005, CorReg: 0.0000, TopReg: 0.0008, AllReg: 0.0006, BotRReg: 0.0012, OV: 0.8633, AltV: 0.8817, CorV: 0.8356, TopV: 0.8578, BotRV: 0.8574, AllV: 0.8817 +[2026-03-20T21:09:33.679573Z] Loop 15780: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0000, TopReg: 0.0018, AllReg: 0.0010, BotRReg: 0.0008, OV: 0.8629, AltV: 0.8812, CorV: 0.8356, TopV: 0.8568, BotRV: 0.8578, AllV: 0.8812 +[2026-03-20T21:09:42.260924Z] Loop 15790: Reg: 0.0010, AltReg: 0.0017, CorReg: 0.0000, TopReg: 0.0021, AllReg: 0.0017, BotRReg: 0.0012, OV: 0.8625, AltV: 0.8805, CorV: 0.8356, TopV: 0.8565, BotRV: 0.8574, AllV: 0.8805 +[2026-03-20T21:09:50.838179Z] Loop 15800: Reg: 0.0003, AltReg: 0.0005, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0005, BotRReg: 0.0011, OV: 0.8633, AltV: 0.8817, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8575, AllV: 0.8817 +[2026-03-20T21:09:59.424952Z] Loop 15810: Reg: 0.0005, AltReg: 0.0008, CorReg: 0.0001, TopReg: 0.0008, AllReg: 0.0009, BotRReg: 0.0006, OV: 0.8630, AltV: 0.8814, CorV: 0.8356, TopV: 0.8578, BotRV: 0.8580, AllV: 0.8814 +[2026-03-20T21:10:08.010903Z] Loop 15820: Reg: 0.0013, AltReg: 0.0021, CorReg: 0.0001, TopReg: 0.0017, AllReg: 0.0021, BotRReg: 0.0003, OV: 0.8623, AltV: 0.8802, CorV: 0.8355, TopV: 0.8569, BotRV: 0.8583, AllV: 0.8802 +[2026-03-20T21:10:16.593566Z] Loop 15830: Reg: 0.0009, AltReg: 0.0015, CorReg: 0.0001, TopReg: 0.0014, AllReg: 0.0015, BotRReg: 0.0002, OV: 0.8627, AltV: 0.8807, CorV: 0.8356, TopV: 0.8572, BotRV: 0.8584, AllV: 0.8807 +[2026-03-20T21:10:25.175567Z] Loop 15840: Reg: 0.0001, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0002, BotRReg: 0.0004, OV: 0.8635, AltV: 0.8820, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8582, AllV: 0.8821 +[2026-03-20T21:10:33.759199Z] Loop 15850: Reg: 0.0003, AltReg: 0.0005, CorReg: 0.0000, TopReg: 0.0006, AllReg: 0.0005, BotRReg: 0.0003, OV: 0.8633, AltV: 0.8817, CorV: 0.8356, TopV: 0.8580, BotRV: 0.8583, AllV: 0.8818 +[2026-03-20T21:10:42.340761Z] Loop 15860: Reg: 0.0011, AltReg: 0.0018, CorReg: 0.0000, TopReg: 0.0008, AllReg: 0.0018, BotRReg: 0.0045, OV: 0.8625, AltV: 0.8804, CorV: 0.8356, TopV: 0.8578, BotRV: 0.8541, AllV: 0.8805 +[2026-03-20T21:10:50.922624Z] Loop 15870: Reg: 0.0022, AltReg: 0.0037, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0037, BotRReg: 0.0120, OV: 0.8614, AltV: 0.8785, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8466, AllV: 0.8786 +[2026-03-20T21:10:59.500677Z] Loop 15880: Reg: 0.0016, AltReg: 0.0026, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0026, BotRReg: 0.0098, OV: 0.8620, AltV: 0.8796, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8488, AllV: 0.8797 +[2026-03-20T21:11:08.083753Z] Loop 15890: Reg: 0.0015, AltReg: 0.0024, CorReg: 0.0000, TopReg: 0.0002, AllReg: 0.0024, BotRReg: 0.0069, OV: 0.8621, AltV: 0.8798, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8518, AllV: 0.8798 +[2026-03-20T21:11:16.660407Z] Loop 15900: Reg: 0.0014, AltReg: 0.0022, CorReg: 0.0002, TopReg: 0.0003, AllReg: 0.0022, BotRReg: 0.0066, OV: 0.8622, AltV: 0.8800, CorV: 0.8355, TopV: 0.8583, BotRV: 0.8520, AllV: 0.8800 +[2026-03-20T21:11:25.238414Z] Loop 15910: Reg: 0.0010, AltReg: 0.0015, CorReg: 0.0003, TopReg: 0.0005, AllReg: 0.0015, BotRReg: 0.0032, OV: 0.8626, AltV: 0.8807, CorV: 0.8354, TopV: 0.8581, BotRV: 0.8555, AllV: 0.8808 +[2026-03-20T21:11:33.821823Z] Loop 15920: Reg: 0.0002, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0004, BotRReg: 0.0011, OV: 0.8634, AltV: 0.8818, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8575, AllV: 0.8819 +[2026-03-20T21:11:42.405054Z] Loop 15930: Reg: 0.0001, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0002, BotRReg: 0.0007, OV: 0.8634, AltV: 0.8820, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8580, AllV: 0.8820 +[2026-03-20T21:11:50.997452Z] Loop 15940: Reg: 0.0001, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0002, BotRReg: 0.0007, OV: 0.8634, AltV: 0.8820, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8579, AllV: 0.8820 +[2026-03-20T21:11:59.576539Z] Loop 15950: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0006, BotRReg: 0.0010, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8577, AllV: 0.8816 +[2026-03-20T21:12:08.167214Z] Loop 15960: Reg: 0.0003, AltReg: 0.0005, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0005, BotRReg: 0.0007, OV: 0.8633, AltV: 0.8817, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8579, AllV: 0.8818 +[2026-03-20T21:12:16.751139Z] Loop 15970: Reg: 0.0001, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0002, BotRReg: 0.0005, OV: 0.8634, AltV: 0.8820, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8581, AllV: 0.8820 +[2026-03-20T21:12:25.331522Z] Loop 15980: Reg: 0.0001, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0002, BotRReg: 0.0006, OV: 0.8634, AltV: 0.8820, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8580, AllV: 0.8820 +[2026-03-20T21:12:33.915709Z] Loop 15990: Reg: 0.0005, AltReg: 0.0008, CorReg: 0.0001, TopReg: 0.0002, AllReg: 0.0008, BotRReg: 0.0023, OV: 0.8631, AltV: 0.8814, CorV: 0.8355, TopV: 0.8585, BotRV: 0.8563, AllV: 0.8814 +[2026-03-20T21:12:42.499588Z] Loop 16000: Reg: 0.0007, AltReg: 0.0010, CorReg: 0.0003, TopReg: 0.0004, AllReg: 0.0010, BotRReg: 0.0019, OV: 0.8629, AltV: 0.8812, CorV: 0.8354, TopV: 0.8582, BotRV: 0.8568, AllV: 0.8812 +[2026-03-20T21:12:51.078706Z] Loop 16010: Reg: 0.0006, AltReg: 0.0008, CorReg: 0.0003, TopReg: 0.0004, AllReg: 0.0008, BotRReg: 0.0010, OV: 0.8630, AltV: 0.8814, CorV: 0.8354, TopV: 0.8582, BotRV: 0.8577, AllV: 0.8815 +[2026-03-20T21:12:59.658023Z] Loop 16020: Reg: 0.0007, AltReg: 0.0010, CorReg: 0.0003, TopReg: 0.0008, AllReg: 0.0010, BotRReg: 0.0006, OV: 0.8629, AltV: 0.8812, CorV: 0.8353, TopV: 0.8578, BotRV: 0.8580, AllV: 0.8813 +[2026-03-20T21:13:08.245628Z] Loop 16030: Reg: 0.0016, AltReg: 0.0020, CorReg: 0.0009, TopReg: 0.0020, AllReg: 0.0021, BotRReg: 0.0016, OV: 0.8620, AltV: 0.8802, CorV: 0.8347, TopV: 0.8566, BotRV: 0.8571, AllV: 0.8802 +[2026-03-20T21:13:16.834765Z] Loop 16040: Reg: 0.0006, AltReg: 0.0009, CorReg: 0.0001, TopReg: 0.0008, AllReg: 0.0009, BotRReg: 0.0009, OV: 0.8630, AltV: 0.8813, CorV: 0.8355, TopV: 0.8578, BotRV: 0.8577, AllV: 0.8813 +[2026-03-20T21:13:25.416933Z] Loop 16050: Reg: 0.0007, AltReg: 0.0012, CorReg: 0.0000, TopReg: 0.0011, AllReg: 0.0012, BotRReg: 0.0008, OV: 0.8629, AltV: 0.8810, CorV: 0.8356, TopV: 0.8575, BotRV: 0.8579, AllV: 0.8811 +[2026-03-20T21:13:34.007428Z] Loop 16060: Reg: 0.0011, AltReg: 0.0017, CorReg: 0.0000, TopReg: 0.0021, AllReg: 0.0018, BotRReg: 0.0010, OV: 0.8625, AltV: 0.8805, CorV: 0.8356, TopV: 0.8565, BotRV: 0.8576, AllV: 0.8805 +[2026-03-20T21:13:42.596772Z] Loop 16070: Reg: 0.0011, AltReg: 0.0018, CorReg: 0.0000, TopReg: 0.0028, AllReg: 0.0018, BotRReg: 0.0011, OV: 0.8625, AltV: 0.8804, CorV: 0.8356, TopV: 0.8558, BotRV: 0.8575, AllV: 0.8804 +[2026-03-20T21:13:51.178273Z] Loop 16080: Reg: 0.0007, AltReg: 0.0011, CorReg: 0.0000, TopReg: 0.0019, AllReg: 0.0012, BotRReg: 0.0013, OV: 0.8629, AltV: 0.8811, CorV: 0.8356, TopV: 0.8567, BotRV: 0.8573, AllV: 0.8811 +[2026-03-20T21:13:59.751531Z] Loop 16090: Reg: 0.0003, AltReg: 0.0005, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0006, BotRReg: 0.0010, OV: 0.8633, AltV: 0.8817, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8576, AllV: 0.8817 +[2026-03-20T21:14:08.329004Z] Loop 16100: Reg: 0.0002, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0004, AllReg: 0.0004, BotRReg: 0.0012, OV: 0.8634, AltV: 0.8818, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8574, AllV: 0.8819 +[2026-03-20T21:14:16.909044Z] Loop 16110: Reg: 0.0002, AltReg: 0.0003, CorReg: 0.0000, TopReg: 0.0003, AllReg: 0.0003, BotRReg: 0.0009, OV: 0.8634, AltV: 0.8819, CorV: 0.8356, TopV: 0.8583, BotRV: 0.8577, AllV: 0.8819 +[2026-03-20T21:14:25.495028Z] Loop 16120: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0008, AllReg: 0.0007, BotRReg: 0.0008, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8579, BotRV: 0.8578, AllV: 0.8816 +[2026-03-20T21:14:34.076976Z] Loop 16130: Reg: 0.0034, AltReg: 0.0055, CorReg: 0.0003, TopReg: 0.0123, AllReg: 0.0055, BotRReg: 0.0005, OV: 0.8602, AltV: 0.8767, CorV: 0.8354, TopV: 0.8463, BotRV: 0.8582, AllV: 0.8767 +[2026-03-20T21:14:42.663924Z] Loop 16140: Reg: 0.0014, AltReg: 0.0022, CorReg: 0.0000, TopReg: 0.0015, AllReg: 0.0022, BotRReg: 0.0004, OV: 0.8622, AltV: 0.8800, CorV: 0.8356, TopV: 0.8571, BotRV: 0.8582, AllV: 0.8800 +[2026-03-20T21:14:51.249883Z] Loop 16150: Reg: 0.0008, AltReg: 0.0013, CorReg: 0.0000, TopReg: 0.0011, AllReg: 0.0013, BotRReg: 0.0005, OV: 0.8628, AltV: 0.8809, CorV: 0.8356, TopV: 0.8575, BotRV: 0.8582, AllV: 0.8810 +[2026-03-20T21:14:59.832747Z] Loop 16160: Reg: 0.0003, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0004, BotRReg: 0.0002, OV: 0.8633, AltV: 0.8818, CorV: 0.8356, TopV: 0.8581, BotRV: 0.8584, AllV: 0.8818 +[2026-03-20T21:15:08.425627Z] Loop 16170: Reg: 0.0002, AltReg: 0.0004, CorReg: 0.0000, TopReg: 0.0005, AllReg: 0.0004, BotRReg: 0.0002, OV: 0.8634, AltV: 0.8818, CorV: 0.8356, TopV: 0.8582, BotRV: 0.8584, AllV: 0.8819 +[2026-03-20T21:15:17.006365Z] Loop 16180: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0006, AllReg: 0.0006, BotRReg: 0.0003, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8580, BotRV: 0.8584, AllV: 0.8817 +[2026-03-20T21:15:25.594128Z] Loop 16190: Reg: 0.0043, AltReg: 0.0072, CorReg: 0.0000, TopReg: 0.0027, AllReg: 0.0076, BotRReg: 0.0011, OV: 0.8593, AltV: 0.8750, CorV: 0.8356, TopV: 0.8559, BotRV: 0.8575, AllV: 0.8746 +[2026-03-20T21:15:34.167402Z] Loop 16200: Reg: 0.0007, AltReg: 0.0011, CorReg: 0.0000, TopReg: 0.0012, AllReg: 0.0011, BotRReg: 0.0003, OV: 0.8629, AltV: 0.8811, CorV: 0.8356, TopV: 0.8574, BotRV: 0.8583, AllV: 0.8811 +[2026-03-20T21:15:42.749818Z] Loop 16210: Reg: 0.0010, AltReg: 0.0016, CorReg: 0.0001, TopReg: 0.0014, AllReg: 0.0016, BotRReg: 0.0003, OV: 0.8626, AltV: 0.8806, CorV: 0.8356, TopV: 0.8573, BotRV: 0.8584, AllV: 0.8806 +[2026-03-20T21:15:51.331352Z] Loop 16220: Reg: 0.0004, AltReg: 0.0006, CorReg: 0.0000, TopReg: 0.0007, AllReg: 0.0006, BotRReg: 0.0001, OV: 0.8632, AltV: 0.8816, CorV: 0.8356, TopV: 0.8580, BotRV: 0.8585, AllV: 0.8816 +[2026-03-20T21:15:59.913190Z] Loop 16230: Reg: 0.0001, AltReg: 0.0001, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0001, BotRReg: 0.0004, OV: 0.8635, AltV: 0.8821, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8582, AllV: 0.8821 +[2026-03-20T21:16:08.495482Z] Loop 16240: Reg: 0.0001, AltReg: 0.0002, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0002, BotRReg: 0.0005, OV: 0.8635, AltV: 0.8821, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8581, AllV: 0.8821 +[2026-03-20T21:16:17.077311Z] Loop 16250: Reg: 0.0001, AltReg: 0.0001, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0001, BotRReg: 0.0004, OV: 0.8635, AltV: 0.8821, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8582, AllV: 0.8821 +[2026-03-20T21:16:25.659862Z] Loop 16260: Reg: 0.0006, AltReg: 0.0010, CorReg: 0.0000, TopReg: 0.0001, AllReg: 0.0010, BotRReg: 0.0039, OV: 0.8630, AltV: 0.8812, CorV: 0.8356, TopV: 0.8585, BotRV: 0.8547, AllV: 0.8812 +[2026-03-20T21:16:34.240414Z] Loop 16270: Reg: 0.0014, AltReg: 0.0023, CorReg: 0.0000, TopReg: 0.0000, AllReg: 0.0023, BotRReg: 0.0081, OV: 0.8622, AltV: 0.8799, CorV: 0.8356, TopV: 0.8586, BotRV: 0.8506, AllV: 0.8799 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/latest_train.json b/control_al_0.6_g_0.98_id_94_seed_9806094/latest_train.json new file mode 100644 index 0000000000000000000000000000000000000000..47c359d60632a3fa225c555b32c6306de25798ff --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/latest_train.json @@ -0,0 +1,12 @@ +{ + "ts": "2026-03-20T21:16:38.537931Z", + "loop": 16275, + "env_steps": 9999974399, + "loss": 0.0168222077190876, + "avg_return": 0.8619512915611267, + "regret": 0.0014015259221196175, + "entropy": 0.08619251847267151, + "lr": 5e-05, + "discount_rate": 0.98, + "num_rollout_steps": 64 +} \ No newline at end of file diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/lvl_rngs.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/lvl_rngs.npy new file mode 100644 index 0000000000000000000000000000000000000000..b70399c026de4199b8a64cc14539217c71b2bcf7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/lvl_rngs.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6183e64cc3b584529150d39e75c608e2c0a26a091f470f0cc5c908719fd6d21 +size 130336 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/optimizer_state.tar.gz b/control_al_0.6_g_0.98_id_94_seed_9806094/optimizer_state.tar.gz new file mode 100644 index 0000000000000000000000000000000000000000..5197c2f1543f4d94aa8c2b854e5277c3eb8480ef --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/optimizer_state.tar.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:918e3e66d7e3cac5f0f691777677b74c01ea060a5e41fcfa7ff5c8b59c254efb +size 2655284832 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00000.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00000.npy new file mode 100644 index 0000000000000000000000000000000000000000..7694fbd06b8061f01f292d8770a1285d9bf4e592 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00000.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa2be9fecba97f84aa33141841dadaa65bd41226bfb5ee288944c06c60747e32 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00001.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00001.npy new file mode 100644 index 0000000000000000000000000000000000000000..c1e034c900ae1b82a208dcc128f21af770202fcb --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00001.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf6e7358130caf0aa201ed323de446eb9ecce65cc15b05f4949caa6ac6bdeba5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00002.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00002.npy new file mode 100644 index 0000000000000000000000000000000000000000..9a07d4b985921a40e39c50aced4492b51959f891 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00002.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69057b2663f95537c465bcbd571a39018f35770dd8fec4793eb2116ac0601f58 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00003.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00003.npy new file mode 100644 index 0000000000000000000000000000000000000000..66f3a33a13c2ff157e3986cb43308f1c365c0121 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00003.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a634e068138bc05e34f7dd1ecb7d6bee83dedbe99fd96fa2350c130769217b4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00004.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00004.npy new file mode 100644 index 0000000000000000000000000000000000000000..006e6597e9260fe8f4a0ea840608a941d4aae296 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00004.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a44485d0c6f2ab5ad055f92f802f3b20b00e649530d195f79978e12de2ef7339 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00005.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00005.npy new file mode 100644 index 0000000000000000000000000000000000000000..c2fe03102a40ab96331576fdbb40e29108771611 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00005.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa3612a250150eb50717bed7ee8f1bac0da09ca33bd0a94b4dfd915d179f8ddb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00006.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00006.npy new file mode 100644 index 0000000000000000000000000000000000000000..f893b1d1a7d4eff1b34e4d735029d43f6dd03448 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00006.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34d52ca035d4e8d02ec4b96fb67de3b025c0fa824be3a4536cd1b7148831fac0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00007.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00007.npy new file mode 100644 index 0000000000000000000000000000000000000000..58c0e0b5a7a416e40e8a7190393c0eb0d0b1e25c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00007.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ceee8ebdb873a2caf80f3b9d51b2d77830cdf882544cb28608f656f029cc176 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00008.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00008.npy new file mode 100644 index 0000000000000000000000000000000000000000..8ca994413f7a823ed90291201b9d4f9972c85aed --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00008.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce617083a87857b3fa3085e8c75b8af589d2ae28d55d3023961a45b026c60341 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00009.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00009.npy new file mode 100644 index 0000000000000000000000000000000000000000..9c7a5e9b8c3c0dfabf5685f75c1bf57b8d12bf76 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00009.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e68f4fb02d8f5f78cb08c4f2971f61440a68d97b42529fd90dd184de96e4594b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00010.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00010.npy new file mode 100644 index 0000000000000000000000000000000000000000..53fc41920760eb6549bdd0fad2cc62a677c8e322 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00010.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd847142dbecfc288e2ea477417bd5e69399e340c70a1fb679ca74f11f21a6b8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00011.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00011.npy new file mode 100644 index 0000000000000000000000000000000000000000..039026c60ccbd4e86cccd43ad20c4ba379440325 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00011.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bbae0742fd3ddc49d0baf55646c47518b7f567207582cfb86d14ee2f88c4aaa +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00012.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00012.npy new file mode 100644 index 0000000000000000000000000000000000000000..3c6197a2f44caafe249251f93e6d62aa2fa5b996 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00012.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05b6a20652df17b881c91dfab08d8d57c157580da07da454784fd97e33d0d42e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00013.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00013.npy new file mode 100644 index 0000000000000000000000000000000000000000..2dbedb0e18409db8d70aecc9505d6bdf79a0dc39 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00013.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49427cbc0cfd10c118f923a1cf6d2ffe4940c7c4561d45f1f477ea1edfa7dd9f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00014.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00014.npy new file mode 100644 index 0000000000000000000000000000000000000000..0447f367c2b2764a4439ae380dca2a5de377db22 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00014.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4298612460c5d1ecdb47863cca19f5730441e7253665b54ea6692eeedee59170 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00015.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00015.npy new file mode 100644 index 0000000000000000000000000000000000000000..103d18b3ff2333df5f5c70101d23479cdc015e98 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00015.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58301acce903ad54e3bc11c810a59358c61917740bb40b3eba18e674c78b5964 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00016.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00016.npy new file mode 100644 index 0000000000000000000000000000000000000000..946687b316e18494f873e5fbc21f43f63805040c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00016.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5243b17e57f9b1993abdc422feef48bb60b7b1c7d4b1c8a71f4e173a8e6b26a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00017.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00017.npy new file mode 100644 index 0000000000000000000000000000000000000000..7e357199be1b0a21a39fbc6e83db57e43f64aa9c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00017.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4318d7c2de48ef2337d2ff330fea81cfd95583907706f3484ecd5b7204ea8ce1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00018.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00018.npy new file mode 100644 index 0000000000000000000000000000000000000000..08d5d9f021b7bbb1493aa47a7656bd822573c13a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00018.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c5b4e861fbb479999a9960c292426a136873412b2eca531baf4cb5f8bcb840e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00019.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00019.npy new file mode 100644 index 0000000000000000000000000000000000000000..92b1bf8a137ddfaf6fdc1c6f8932037e362d90ec --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00019.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f662a936a5333c91c1c468e603ff17816d1e436a41f8fdd0f5551741cbc2b4a3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00020.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00020.npy new file mode 100644 index 0000000000000000000000000000000000000000..34a9cb8d5389b9db99b8039a0a62b45ecb397ed6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00020.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f0f5ee27d15a2958a1fc61dd2367f9d2210d4c5aa21a7a5a03100727ac2e7fa +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00021.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00021.npy new file mode 100644 index 0000000000000000000000000000000000000000..375ccb93913d839a3fc50f406d9f52028222d1fe --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00021.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8210c5e6197a561ffdbbedfb673762f0bdf6cbf2bec083a3fbeb696c571c5e41 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00022.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00022.npy new file mode 100644 index 0000000000000000000000000000000000000000..bf8ca89f8f37cc1b29e0906cfe3a9a0bceba6003 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00022.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:051331b8462d6b396c7e8ee82352d7c7c80cd549988b65c351d36f2307c5ff52 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00023.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00023.npy new file mode 100644 index 0000000000000000000000000000000000000000..8cb21a56ad1877181b7813e4e704ac9f21125990 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00023.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d2264e73df5d1e40151068d985e5738959c4385aea247dfd8d2feec60feee12 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00024.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00024.npy new file mode 100644 index 0000000000000000000000000000000000000000..402cf800d4f1c5588b2596ad2504330a35e676e7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00024.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6895a49b1b1ede57a7836aaaade70d6750ef2d8e52e42179ffa442de16ce9021 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00025.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00025.npy new file mode 100644 index 0000000000000000000000000000000000000000..121dbb032dd40c53f2cc3077a1339b92c2ebfc1a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00025.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f90af8472804e4ac95e62db6d31dc21ec0037e56dd330b6adff89e2a65541376 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00026.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00026.npy new file mode 100644 index 0000000000000000000000000000000000000000..d7f1931a72536467d51f2eda8c441eec4112b42c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00026.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f635e45ba9279b99ba9347ee1f7b4a4c5565c750f98f2d10e3ce52ce7738fb5b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00027.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00027.npy new file mode 100644 index 0000000000000000000000000000000000000000..da9c0c421c90babf79656efccefef3460ffe9bf4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00027.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48bd8c305ea1b0df4af330d0121ea24303b925e883bddbb9ef7210ca037d0412 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00028.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00028.npy new file mode 100644 index 0000000000000000000000000000000000000000..a1c5b8686f5b20ad1dd4e79863735652c083a6ef --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00028.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c262de6862f323f39ae6ac1e9c50284a09e4b288befaaddeb5ec2045fc318eb8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00029.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00029.npy new file mode 100644 index 0000000000000000000000000000000000000000..0e19c687a8a3f794a59f6e8b962df940f77f51be --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00029.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c4917ef22ce48829429f15ca23273f385fba0757985a88be91f2ebbb8268246 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00030.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00030.npy new file mode 100644 index 0000000000000000000000000000000000000000..da6dcf7ecdf5388f22363cbc0d5a30914aa1f663 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00030.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3caf925b8a46593eaa161cd4bdbc759a6cb1e3ebc7a36b63014ca938a246e92 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00031.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00031.npy new file mode 100644 index 0000000000000000000000000000000000000000..403ad5760bf8073b61aa317001b9d81ea51e84f9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00031.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85a3028744b0651df369bd97bd0921e18556feb5cf8a40d0105562df7ab0a88d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00032.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00032.npy new file mode 100644 index 0000000000000000000000000000000000000000..ec10eace87602b9e2bff884058677a00318d146b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00032.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:604e4c140d63442b4ba90e86122ea18dfdbb4b8fd6b4e506fd03bfae617df7b3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00033.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00033.npy new file mode 100644 index 0000000000000000000000000000000000000000..a628a4ff0cf7ee749dbbb23ddb8eee0ee534165d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00033.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:613a1a924d196e1f59a8b289cb423ae9844901b496e8f91a5b4b43457ccd8b2c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00034.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00034.npy new file mode 100644 index 0000000000000000000000000000000000000000..95c2a39ae0034cb2d629d4f25476dcdff64b7394 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00034.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1f102a10369c45614b62036465c33715c5b06a0ffe21af33b267f13aa66bde7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00035.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00035.npy new file mode 100644 index 0000000000000000000000000000000000000000..81394859db3983099447666b57198a593a89105c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00035.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:650901b945303990d15505571412e11dc2c58bbef41e76bc86d21c2064fab648 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00036.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00036.npy new file mode 100644 index 0000000000000000000000000000000000000000..eec800c961b076a505119f293bdc07c284b887e0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00036.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93fc71c6dd98a9cd58e4c68bde5ce983117b6d0e5cea0c0697ce2fd0c66ac42c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00037.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00037.npy new file mode 100644 index 0000000000000000000000000000000000000000..c68d24dd52dbb662fc90f4368744f233b2777cfc --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00037.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4200a76b59649fdad5e7cc82c5c5ef4d4a9f10a942b40c2b4cd41dfb257588da +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00038.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00038.npy new file mode 100644 index 0000000000000000000000000000000000000000..24b2991564478504bbd82147c0012c41bc4aa2ab --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00038.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73a9a586f741faab10c9c2a16634a6a4143d0a37a8adb422a38875f79cf37945 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00039.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00039.npy new file mode 100644 index 0000000000000000000000000000000000000000..f72dccb1c4f6a5fa502def6bf69a5de0905079a5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00039.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81ca7c11ea7bed00adf561b6342d946436535cd2201f5b395244f82149ec8933 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00040.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00040.npy new file mode 100644 index 0000000000000000000000000000000000000000..cb6134d77b0730168aae806f9a32c6b33e124d2c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00040.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb8ec6e8ad5c97e21289e98fee5f4f9fc8b56143e684c72b31a3268f35f9950f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00041.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00041.npy new file mode 100644 index 0000000000000000000000000000000000000000..d2c099cd7e74ad7f39b83cd9c1dfa9a1bfee7619 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00041.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1005200f1dfe1c57bb6a04fc0fe80b54af7679a68388d034ae678383d7d0d37a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00042.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00042.npy new file mode 100644 index 0000000000000000000000000000000000000000..6414c2188ad7b427864e1b23f0feef7222591172 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00042.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c6f9b5fa61bb8c5dbad9476bb879d84e8f0f053ce8a4effc49308d0df719494 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00043.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00043.npy new file mode 100644 index 0000000000000000000000000000000000000000..885267fb5cafbff508481e8c9c591cb3fd820a9c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00043.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9384213f871a513fa072fc265413add890e1dd7946d2026502919d18bcfedd92 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00044.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00044.npy new file mode 100644 index 0000000000000000000000000000000000000000..b30382234238bc151af532f901c42af7b030cbe0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00044.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b826c969ac97c93ff898e4900eee0662bbf1d959d3f9fab18e05506cc1942444 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00045.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00045.npy new file mode 100644 index 0000000000000000000000000000000000000000..cf5883ea50974c3b13eaf502d11f8e11a62fa7fe --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00045.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afffc4a2adcd3cdd8487c6a5b02509e131a32e47fdf7dd372ea24b4808be19cf +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00046.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00046.npy new file mode 100644 index 0000000000000000000000000000000000000000..c0e1f54be30e70caa0e28f90a1afd6f371cb0712 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00046.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1972f8127563098756141fdc59511e510ce1297c3d946beaad78ede9712f4d7e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00047.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00047.npy new file mode 100644 index 0000000000000000000000000000000000000000..49d153bfb9803245c5dde09c7acba7d74b1cfaaf --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00047.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35a13bf35ee7cea40ba13cd296bb5285f8d3ff6d5b546bccdfb22bf4ae858144 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00048.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00048.npy new file mode 100644 index 0000000000000000000000000000000000000000..0b14ad1828b65b23d13dce03a8a5fb12da7a4a3a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00048.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d69a6b86763d2a6c002ea066f66094daa91eff65db53fc085e4dc3ad8586c204 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00049.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00049.npy new file mode 100644 index 0000000000000000000000000000000000000000..969204163583febf9ad4aa3cc8bebecacee9547f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00049.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcee7b719e8422e9b5c27b00d6c4918b21752a7d304d9facda9678e7c6687055 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00050.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00050.npy new file mode 100644 index 0000000000000000000000000000000000000000..17402c3742bc423abe3dbe6530e94ae7bf2eb680 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00050.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5290b87ff8da1b965c2ae1354eb55bc1b2b08f830bd9a1127170e56a6bc954e6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00051.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00051.npy new file mode 100644 index 0000000000000000000000000000000000000000..adc938bdab6b677ae8a48c21a4c5103a5a77348f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00051.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d03a5731b3538b5b63eeb425e8db93bab5c294d463ff249f9b2100e08b6a1a7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00052.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00052.npy new file mode 100644 index 0000000000000000000000000000000000000000..7c90645e7c0e45e4fae613365ce6d29cd17a97de --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00052.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:319557783b8b8f4d5aa7d1fad7208e593d203282f8289c5dd84b2617090680e2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00053.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00053.npy new file mode 100644 index 0000000000000000000000000000000000000000..26ca991568292748fab9b73e408f24df28eece47 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00053.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0928d43e608d8f853d5910be6a0cc5b1374420c21d8f451e01e0a28e3648915 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00054.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00054.npy new file mode 100644 index 0000000000000000000000000000000000000000..7585b6e4cb5a5e61c8fb7dc0b3592ff52cbf8853 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00054.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1907db5a2ffb5f85a46e602ee4d6641a35a5646390cb5c4bae8a93df2395a6c9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00055.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00055.npy new file mode 100644 index 0000000000000000000000000000000000000000..14a80118508dd950205fbde6dd7dc346baf684f8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00055.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:283f179e570c0d96bec39e9c3d3af7985793096c55382837d3c3f5a9f3afa48d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00056.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00056.npy new file mode 100644 index 0000000000000000000000000000000000000000..d42170aef795f892dbfd1f02bdaedc5784a18585 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00056.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80cf25c90cb9b43a0df324aa78b3359d1c796e113da3b0409b42c06c2c2c243b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00057.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00057.npy new file mode 100644 index 0000000000000000000000000000000000000000..02426eafe55e25597be7b98f87e83908f87aef97 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00057.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f784c02a859a4157c28457b708253f7e6bc69931668a4c4a33e04998f91ccba6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00058.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00058.npy new file mode 100644 index 0000000000000000000000000000000000000000..dcc884b9d2eacd99e5e88ad2f4a9427c66651882 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00058.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c284bdacfe10a19053937651ff4f35fe141dd4051a1e7b6930c334b30556b2d8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00059.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00059.npy new file mode 100644 index 0000000000000000000000000000000000000000..827d4f373af8c649d1cfc54d811dc7b4e46614c3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00059.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed22eb9d45ece977de4ce7bfea5041b26a752a3dc7e0bd2791cd3739de4e5447 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00060.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00060.npy new file mode 100644 index 0000000000000000000000000000000000000000..9327113742dda643e073edd1af2604cce8ac5143 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00060.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94cc31b23a9245fd8eaaba5ce72c8bfb645f2b5b09db103ddbf7bd8df3097b82 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00061.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00061.npy new file mode 100644 index 0000000000000000000000000000000000000000..eee0858b71b9a1eb549b684c2f1d4fcdb6c0f819 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00061.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e67b02362c07f359e8f24ce11b519bdf2074c31b47a8ce00f3a260af161efebc +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00062.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00062.npy new file mode 100644 index 0000000000000000000000000000000000000000..bf09a92021827ce64b318786c10ee070bf23ce27 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00062.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a0b064d09887c22c186fe2c45dc84a2d386fa02dd4b1cef81625bbd7d038d12 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00063.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00063.npy new file mode 100644 index 0000000000000000000000000000000000000000..c253678b4f79e682eae0bb4fa95fdd33a3ce4f73 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00063.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1984130536feb9e1e894689f03affc67bdd1f1dcfc12c8ca6cee1d5463c3910 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00064.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00064.npy new file mode 100644 index 0000000000000000000000000000000000000000..c8c8a8c470b9aa25a7db49accebf83b0915b5f71 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00064.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1480c88f55b6d299ae3e3aeef6343a3c3f9d66cc250176060e396fc083be312 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00065.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00065.npy new file mode 100644 index 0000000000000000000000000000000000000000..030aaaa788853688045375d8026cd7ed88efd7fa --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00065.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5eefbc8fb0094a4f55f5416711fdcd2b4957b78fa6763279b860638d3d8a756a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00066.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00066.npy new file mode 100644 index 0000000000000000000000000000000000000000..a51d94010dfb520fec87de308a98bc620777a0da --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00066.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d503fc0ea50891458c1ccd5fd70a58e219145b826a34f865454cae59222c5601 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00067.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00067.npy new file mode 100644 index 0000000000000000000000000000000000000000..a4bf0a270904c9100d38be3998e42cc702aa3b90 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00067.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b30eaf5cfe34c886d60fe85fc860262c88460152c469973db228ef104ad103e1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00068.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00068.npy new file mode 100644 index 0000000000000000000000000000000000000000..f464bd679c7494f325e59ebe5b5aa9e715385537 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00068.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3aff734d9006a4564f4d7711b6ca32d78731abe0ce2c1aca7cedca2e75f7a0c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00069.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00069.npy new file mode 100644 index 0000000000000000000000000000000000000000..76c76e210a847c72a7a3a36a0c73af34cbe84271 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00069.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e43e5795abcb9f32fe8a3ca39bb396cdf2a82dde18a36f1be69fb2e67a9ee5cc +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00070.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00070.npy new file mode 100644 index 0000000000000000000000000000000000000000..dd4e0e6641543a570b4768daaa35e64c3297474b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00070.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b4b685fab83e9b1df3362463a8a04b267f52bd0f95e0b29f0263b2a83c01a40 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00071.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00071.npy new file mode 100644 index 0000000000000000000000000000000000000000..d9338c953c79786df529ee742d2b66c0a1bbb132 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00071.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dd8321f846e925ad6620536fd2a982aa5a1b0719773aca137cff967428302af +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00072.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00072.npy new file mode 100644 index 0000000000000000000000000000000000000000..eeb8f3cf16e032d56f8cf6f89fbff4bda8f13f9d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00072.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaf5a22c271ee0ea9842373db2fd78a768888d0dfad7029a74e79f2c767d3a6f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00073.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00073.npy new file mode 100644 index 0000000000000000000000000000000000000000..b387dcc70ef6878ab2f15d87b80573ffab7635bb --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00073.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50824487b8bfbbd53d6bd2398bd5c17f3f1fa6c1ff7187f995a1ab92a1b8a830 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00074.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00074.npy new file mode 100644 index 0000000000000000000000000000000000000000..987c2d656061eda829a33481201e59a1f1206aa7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00074.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26da0a0a6c46a2fb89ac8c1e22b275635ad8e2783c6a6d33bb33db0cc0734f15 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00075.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00075.npy new file mode 100644 index 0000000000000000000000000000000000000000..c6f9ece94ba3f87f4cacd28b49c0d16b5eb7f9cc --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00075.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:360adbdc67d7e1ddc77b43a7af23dd03b0da1b5deb8df16ff1f518a2af1370a1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00076.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00076.npy new file mode 100644 index 0000000000000000000000000000000000000000..59822dff18dbc74b8f31d9680931c0e4439e4d7e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00076.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57c930d43358078f415775744c121aeb6d7a593c916da903f1c03eeca6e2d58f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00077.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00077.npy new file mode 100644 index 0000000000000000000000000000000000000000..b8c4fb006c6ed3a77438fe04464ee81274c9e377 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00077.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1c6a6cf25bd73bfd64a6d61f1e006efc85aaf23d7d1053b73e87084aabde546 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00078.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00078.npy new file mode 100644 index 0000000000000000000000000000000000000000..b4651ac68adf7ea3f6b62bbf485ae54af51b0fbc --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00078.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd7ed77e627f2b6af45f7b34925ad22111091b9a283892825994749019943ce1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00079.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00079.npy new file mode 100644 index 0000000000000000000000000000000000000000..cb74c19b8ea393c27ee4e688f5e049d13417bd46 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00079.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8780a38be7a2fb748da900dddd1e9df231190cb16239636c29708ccb6314d7f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00080.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00080.npy new file mode 100644 index 0000000000000000000000000000000000000000..9335dadefc03c3fdcfa623527b8b72be14c6876d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00080.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f23070433d355206e9c2d239d6de3b9b4469f5a13dd34b6c25a18937c6c400b5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00081.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00081.npy new file mode 100644 index 0000000000000000000000000000000000000000..1b4178cd0311c38f33a519a9131e0344230825f4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00081.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:123363477022ce5a66da5c1c6a02e7f353398ee7e32efb8239408b366007e8bc +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00082.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00082.npy new file mode 100644 index 0000000000000000000000000000000000000000..821a1a56902a0263bf52c1b1d83711e12a35bd04 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00082.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f3b9309b65b82b55870003bd55b013f1e42f704f4d0f76616500ac0ae0ef0ef +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00083.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00083.npy new file mode 100644 index 0000000000000000000000000000000000000000..661a80869e857aa042dc288fe5a0b1a6202d6fe2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00083.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5199705bfbaaef6b63a987b41f303e168b8eee34b49d3f4adabed509fd39d6dd +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00084.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00084.npy new file mode 100644 index 0000000000000000000000000000000000000000..2e62227c8e26139cc27f3e8ec537e39fa5c2bead --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00084.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb04a125bc7d7220f71a6b1c1b4d654bb00e94f43d3f9a0502f0638a955d3e84 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00085.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00085.npy new file mode 100644 index 0000000000000000000000000000000000000000..44adf1ee7a00d8553a750081e2b9dee352373a00 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00085.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bafe358b20c5199a382870ec9329b9ac5d793152d7c11711ae8dba3134c9350a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00086.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00086.npy new file mode 100644 index 0000000000000000000000000000000000000000..560db12479d467abcd292d33d67b5255f15b81c9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00086.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbe7ebe6664471ab0d32e2b0e69b1a9f59a10e5c862be2006b3f1266c384cc2c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00087.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00087.npy new file mode 100644 index 0000000000000000000000000000000000000000..0856b731568a3fdc1e155a8887ece62166bcf33c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00087.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1712e4a6dbded27ee00e65d2886a872ef96b74e1b369ce06147a43da4857925 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00088.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00088.npy new file mode 100644 index 0000000000000000000000000000000000000000..f28a8c7c961ece6f2bda36c8ce2cc5fded7dab2d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00088.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32a4ead17e9a506e2424c767f14cfb1dcc4e42130ef1bd9e86c2942345ccf1e9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00089.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00089.npy new file mode 100644 index 0000000000000000000000000000000000000000..51479406cf28c6673bb5ef69faebe50d95386220 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00089.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:908bdbcf0027317ceaa31dda2b369a399362290f5345367eab649133088c01f2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00090.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00090.npy new file mode 100644 index 0000000000000000000000000000000000000000..15481f0dd6d3f0f1981027c3864d28f51c3e64c6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00090.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a66ac767486d3b1e0da55ffe7551cf53aefeb9dd362f272b86d4813d8ba74fab +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00091.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00091.npy new file mode 100644 index 0000000000000000000000000000000000000000..de5012488628f6972cdb4667a551e75f71d3e5f3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00091.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9815b6fd8bd1fcfe8a8d27162e0fd86a0427070d932c409eb247a37fcf279d17 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00092.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00092.npy new file mode 100644 index 0000000000000000000000000000000000000000..0adaeedca6d7a096e89d72c1a0aa6f3a638c1115 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00092.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7e61c4ea410dfff7223414ca18e9c23c3940a668e7c7c3471f5422554ea8773 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00093.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00093.npy new file mode 100644 index 0000000000000000000000000000000000000000..d87266a47ea0b926478267e827f0b7de41c4790d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00093.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:120653ef74c79548bfe04ea4df4d546fd53758d792ce693a3d2042e4b47fd258 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00094.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00094.npy new file mode 100644 index 0000000000000000000000000000000000000000..45c583d0047f587f1d80f613cafdcf43adc4b743 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00094.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ed8e72d5c92842a5ab4de73f779ac60048f69cb5ae38ad34ca7b7d358af3093 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00095.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00095.npy new file mode 100644 index 0000000000000000000000000000000000000000..63dd4b6c0ea42f02f02bb3c179ce3a8f57e3ebc3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00095.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4729eb5edf74fcb0987da311779cab890a140eb3b65b71be0e13fa72bc3f192 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00096.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00096.npy new file mode 100644 index 0000000000000000000000000000000000000000..62901dde0cf7e92d7fef335a9238535582c65a80 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00096.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4619324b20a5d53e00b8e1ada93fa1d0e6e4f2ac5bee75b5a67323c04c35f14d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00097.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00097.npy new file mode 100644 index 0000000000000000000000000000000000000000..883f34c2a3674f21c0bbda73eaa95ee50d7126aa --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00097.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf27a3f956afdab8da63e8ee1c0a536fce183cab2a6c13ab551d099fcdaab6a0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00098.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00098.npy new file mode 100644 index 0000000000000000000000000000000000000000..7eafa61140d89e3fa1938cc72ab38cf2dac352f6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00098.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21956c3e39607e7ef3c875c88799a6fde010d5ca0ed5e6fef99ccb1912026088 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00099.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00099.npy new file mode 100644 index 0000000000000000000000000000000000000000..fc49168897d73d52d37923e8de50cc378e00c90d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00099.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:735878c295fec00358ec847848194c6ae7ecd3457c1b0f430f9b4b8e453b7670 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00100.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00100.npy new file mode 100644 index 0000000000000000000000000000000000000000..5296f55ebf8ef42b78113a2781fd109895031fce --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00100.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:875eedbee6ce12d26848eff84a1200a3b66d8a01dc99bd08ff506afedfe831d0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00101.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00101.npy new file mode 100644 index 0000000000000000000000000000000000000000..15b5fca60a6176a9502fb82838bda2dc93cae904 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00101.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:670e2477a969985d04bf8d0e7e032fb63fa040108ac6f0531fb53b8fb1eeeee0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00102.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00102.npy new file mode 100644 index 0000000000000000000000000000000000000000..48bc1d789224c5b26d3aca7451df762b413df386 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00102.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6eebec0738f504e907fd0c8c34d2f5c04f3e08c4a80c0db8bde5688300416ea3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00103.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00103.npy new file mode 100644 index 0000000000000000000000000000000000000000..7e73604a3bb09be4b180176c08d4c61b4d20e584 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00103.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8312516d0811447e064d2171307d3d22ba10b8d2a4fc720ad89c9da11cf759dd +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00104.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00104.npy new file mode 100644 index 0000000000000000000000000000000000000000..b7b8a5c2f099cd29d1added16ccf487d846283b2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00104.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80580fd67a8beeb8f6eff240b33dc00719331a7285a6dd7ecfc6484f18263b63 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00105.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00105.npy new file mode 100644 index 0000000000000000000000000000000000000000..a768e48e58b49bffce0b2df3ee39624aa038ea6d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00105.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b77e790b538e3de0e686b2b74dc665251b1a87873493f96edca3f106a870ea58 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00106.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00106.npy new file mode 100644 index 0000000000000000000000000000000000000000..8ee5c1db413760af1c85795e035f491ca8b38861 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00106.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb7e43866f5335cdcf0fac793ff85877c43f89a089b6e7a94e32a3b0f1c45039 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00107.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00107.npy new file mode 100644 index 0000000000000000000000000000000000000000..1c5b85af8c3550c2bb9af591dabdabc7aa5c776c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00107.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf7b6d566c5e354a28702114da7aeeacfb7de11b73078ffbfff9ae65c47be04e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00108.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00108.npy new file mode 100644 index 0000000000000000000000000000000000000000..6616327038caf0cd55aed13c49624daf2c48b7da --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00108.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0f2bd496d3e0c06e4bbb30393c06565552527450465fc6ed689419ef471172a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00109.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00109.npy new file mode 100644 index 0000000000000000000000000000000000000000..ddefa2be35c4a1603e3da37d49cfdf4fafb879b1 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00109.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:803606b580b18f4765301b86e34d73bc7d9c2b7d2d02d3db0c040ce6b4a761bc +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00110.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00110.npy new file mode 100644 index 0000000000000000000000000000000000000000..2de6bcd83a7b97181447e9fac1cf267ebc245561 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00110.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11068d8ffbe438883f0abd192bd7b6444c8f5a1ea5e1dcbcb5b71db22493d8c5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00111.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00111.npy new file mode 100644 index 0000000000000000000000000000000000000000..31fcebef5cea67f6e07db690bf7d56836048b185 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00111.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b4f6395d81c0c2517bcca129324bfbc1c261abb725f66d5a150b22106735dc9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00112.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00112.npy new file mode 100644 index 0000000000000000000000000000000000000000..d7a70dcc4fd431c724ee6687361bf7c4dc8fae13 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00112.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46f85bc15b372d390bb5d99dcc4a5a574fec96ca51fbcb6120bf65c0b7ec8a9a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00113.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00113.npy new file mode 100644 index 0000000000000000000000000000000000000000..d84192fb8b4f0d14785e6403e4997d4303a7f3c9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00113.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b05ef48317ec9d5bf9f946725584ae0b0f1e259713bb47e2b4746dcf4b71fc15 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00114.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00114.npy new file mode 100644 index 0000000000000000000000000000000000000000..61c19b84c19132493477a20e855ccf2cb816500f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00114.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2f856e8e077354f3466f633a4524764f0244299af7c6a58beead6f838f3e776 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00115.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00115.npy new file mode 100644 index 0000000000000000000000000000000000000000..d0e11cc358b8c758ae72f21fdf5cc290adfc2e80 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00115.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf0357d1589789869b2a7ec928fa3b6ceb9cae74f0d4f3bbf75257774aa80897 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00116.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00116.npy new file mode 100644 index 0000000000000000000000000000000000000000..909d3dedd86ed95d15e4a2c08dab98b417b20f16 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00116.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acb1c12c46c223ec1d80710e1b06a7671c7d27d900d301231e85424a5a6da60f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00117.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00117.npy new file mode 100644 index 0000000000000000000000000000000000000000..1727cfc1a36e655ffadc99ffcc8459dec15498f7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00117.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53682b99b58e9a2f93329071b896e4c891ff1be6d140866eb95e4a69fc879942 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00118.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00118.npy new file mode 100644 index 0000000000000000000000000000000000000000..a6cd58174bb2790d7b611c7da7b7ee94df7b9d4f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00118.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c003a4359e08fc717d7281527910ead85f2d4fab523952625e8e2f9f4a31c3c8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00119.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00119.npy new file mode 100644 index 0000000000000000000000000000000000000000..ab71336340325ab57649051384d3c4967b529419 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00119.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eda8319c8313d89e12ea23c0add56a85f6cdaa171a2ca3c894aa5ff23c17c50c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00120.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00120.npy new file mode 100644 index 0000000000000000000000000000000000000000..6d5adb932a0801a4cb21c26f6f37180c9bd7922c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00120.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81988980bdb8b7a48e9a94a16ceef55b49e8a8ce7fa1c8a318f06fac36a9ceca +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00121.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00121.npy new file mode 100644 index 0000000000000000000000000000000000000000..3620d1f04de898fe1b19dfcf773e9605733e740e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00121.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fec653d75665770f2a024d9274a9ad4f194187c1c689507d19a60dc2f0b441c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00122.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00122.npy new file mode 100644 index 0000000000000000000000000000000000000000..ebf1c49b5fb6c2251e643f4aec930a335493a754 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00122.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78e103d18b80e9b59113d574804910f30b91465387910c235a786f819e11cdb2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00123.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00123.npy new file mode 100644 index 0000000000000000000000000000000000000000..a38fcf0db08dcc426894ca58d55707f772029655 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00123.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4362e280c34582dd80a4cd953c304fbd02f40fb5250c3367f5b2d5b48fcf4ac2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00124.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00124.npy new file mode 100644 index 0000000000000000000000000000000000000000..bcd180a1ba21b074be1ee19aeb7c1ce29d972883 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00124.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c59711063b0bdb4194847a420580be51c69974e4df06aa44b879c3140e1e569e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00125.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00125.npy new file mode 100644 index 0000000000000000000000000000000000000000..4d045ada7746d437fe00f60ef2d02ef9b4d56a84 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00125.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef0ae503f6a5beacf3a58507a199a29bb202e8b782bd2ebe3c4c03f38066ea14 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00126.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00126.npy new file mode 100644 index 0000000000000000000000000000000000000000..c3cb4064b6baaea9e55c2e85fc8c70aa2ecb56ac --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00126.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e8f0743d0c22b52eb408eac90d20253c9fd518db474768bb0814ccf9f265c6d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00127.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00127.npy new file mode 100644 index 0000000000000000000000000000000000000000..87a2acfbacbca588e222e33c087fa8feb2890a52 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00127.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:463431cdcc0d79c84958e7d5a07e4357fd5be9b31256bd4fc0a4bc91433f66ce +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00128.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00128.npy new file mode 100644 index 0000000000000000000000000000000000000000..71a404f8891562d070dd93afd5259ab818e98e87 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00128.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef4e2bf097875426e116fee5e2a863951c6e807d39acc7751e5bec41cd86bcd0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00129.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00129.npy new file mode 100644 index 0000000000000000000000000000000000000000..d90ba9b5a66077b5dac28951422c7ddad5f7fc78 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00129.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d2e01632d0805986a8c47205613c0b2f2ab8b6ff133b209b62d3c52cc4e39ed +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00130.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00130.npy new file mode 100644 index 0000000000000000000000000000000000000000..3d7468513820ee5cc437c6729f6eaa697b668c1d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00130.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dfe7479d85f4b9736bbea9e0449cc06f8dfc488e019c3aaac603e5a757f8597 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00131.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00131.npy new file mode 100644 index 0000000000000000000000000000000000000000..51c6f04ce8f0afbddb8e8e3c4f08ccd2235c479c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00131.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cdab09e84df34ba766dc9d0e4b94a61b9f6d4ef0f3082c9dd963dc94180e236 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00132.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00132.npy new file mode 100644 index 0000000000000000000000000000000000000000..785c1b19f28e38758cf735ff6bde73bcc2ba0d17 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00132.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7e268e1f2df8768df460a1a467fa521c473a13967f94628adf8092461457880 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00133.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00133.npy new file mode 100644 index 0000000000000000000000000000000000000000..474d68660fd8dfedcab8bcad202385825cefca62 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00133.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2574e44bc99ceeaaedda53e4e360cf48fdbcad0791c8cb04d0a385d128aee1a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00134.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00134.npy new file mode 100644 index 0000000000000000000000000000000000000000..dd6aa50298ae86200b640da79326e4024adcce4e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00134.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd38dc4fce2526353419cd2320229aa26a826db4d7d2f92d7178bb2803374334 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00135.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00135.npy new file mode 100644 index 0000000000000000000000000000000000000000..e60f823176aa25ea1edda08997c23e1f998f0990 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00135.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bb70ca08690345af080e87aa912514ea4d5d6fbb9591a6e16dc41d6bbe2452a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00136.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00136.npy new file mode 100644 index 0000000000000000000000000000000000000000..d6b7dc97dd5f76602eacd5ed3230cb0c6b175b4f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00136.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:076877427ec917318e6bc683a31983fa980badc02efda9aad403a2301f2628ba +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00137.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00137.npy new file mode 100644 index 0000000000000000000000000000000000000000..70ee417314c43991e54fc64a7aca097545787605 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00137.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8a08749b5b1673c5ebd81cd52c50166d3b0ee72753cc4148bd57181d1019431 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00138.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00138.npy new file mode 100644 index 0000000000000000000000000000000000000000..f20b1a1f4a135026909fa7ab842b605fcfe156e7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00138.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:620a3ef0085f018fd7651c694afda5ef670cd747e61c566baae1994688d0aaea +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00139.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00139.npy new file mode 100644 index 0000000000000000000000000000000000000000..110e617584e59e7f104fa0ea3693ac8dc839a450 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00139.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca59fa4a399dbd098865afde35c34ee6e2989c6bc1e955ae232afa3588d06dd2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00140.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00140.npy new file mode 100644 index 0000000000000000000000000000000000000000..116b9d12f7cd4d6f4a82ea3a06cf774494de4964 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00140.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:455e5cc6c421d63b4742712efb8cd5d741361c031253be47c537d2827c562539 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00141.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00141.npy new file mode 100644 index 0000000000000000000000000000000000000000..2a33da752989091ce863d9f4519c2ce25f6dc932 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00141.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0455c896f110b61ae82d4670616830bf059316444cf6c8768c1e56abe1a28a00 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00142.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00142.npy new file mode 100644 index 0000000000000000000000000000000000000000..8422a1bdf3076e008b0371d85f3c03b8914605f4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00142.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a7def1db1830adac008bfb9315acd541f06d53fb8993fb69407ce5470937af6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00143.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00143.npy new file mode 100644 index 0000000000000000000000000000000000000000..86add37a9c7efdcd0094d54ce095b6ac6983bbf5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00143.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67b3e3a593b3f94ad9b2c30d740d1024412da5de52bd4f12d59b943e3fd6b759 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00144.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00144.npy new file mode 100644 index 0000000000000000000000000000000000000000..5c72bc4c65d88f0b6baedc8f86eed032ceaceb51 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00144.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4b65c85ccfe222deeef7c380f8f525dcd309e987162a20ac4a22d8a39859402 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00145.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00145.npy new file mode 100644 index 0000000000000000000000000000000000000000..733c622499db9bc4c18a459a5574d3401f4aaa2b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00145.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dc766154d508b593de7351d27c195a0ffff623366d9f9da9e62549915ebbe3f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00146.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00146.npy new file mode 100644 index 0000000000000000000000000000000000000000..72d79deaaffc7575c45c6b8d036ce755de33e6e3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00146.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99cbc3417f5e65f08b85fa7f2d875dffcc4cf2a10c779e9837df495ac10e961e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00147.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00147.npy new file mode 100644 index 0000000000000000000000000000000000000000..7012c55c5da429a3ba4505f8a5d8cfd3b8bb59b7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00147.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:273e05735059bab5839468fbfd10c71393a0d2d17b5a2f8c92c207cab49f94c4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00148.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00148.npy new file mode 100644 index 0000000000000000000000000000000000000000..a48a83e1648bf9de1662a9923d5011cef4d3a87a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00148.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a14a1d789b9812a3a0c3bdd2a0fb08f4503918dadbe21791157d1331ada84949 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00149.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00149.npy new file mode 100644 index 0000000000000000000000000000000000000000..03a9575d1eec754c410edb344fddd8b2726b1a0e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00149.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e49a1c8e35bc7c740514143b89a1fd6cc027be5f44d7daa52297b97b52fee197 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00150.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00150.npy new file mode 100644 index 0000000000000000000000000000000000000000..7fbd199cd6466aae49b2091ff04658d7a7c79b9e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00150.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2596dc2c94d7b911801fcc401c3e3afb83958a94bca531ea64fc5b8af27da7c3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00151.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00151.npy new file mode 100644 index 0000000000000000000000000000000000000000..9c9c07fd6c27093421a9bbb00a6ce6dab80d18b0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00151.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c76539e0b2b7abbe32829453e321559f8abe37591a29f0c692910f52445e2e5e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00152.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00152.npy new file mode 100644 index 0000000000000000000000000000000000000000..14711333fbfd001b7ee077b3fc44996d76cb29af --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00152.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3141c1d47229a59e96f35b1ed99bf6d7600e4333e8552b12051fdd81cc902c5a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00153.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00153.npy new file mode 100644 index 0000000000000000000000000000000000000000..1bbe49b505f813ee90440a5104ab9fe221761589 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00153.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccad260d5c210cf5950c9b7d3761c17aed71c4356fcc9df758ce43ae0bae4b0c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00154.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00154.npy new file mode 100644 index 0000000000000000000000000000000000000000..170fa95639d3b2a60bb4f311210e878100dd3e39 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00154.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:585cbc9b037be4747016f4080fcb7055ee4de4ab6b64f3d682165c9aa6be6014 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00155.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00155.npy new file mode 100644 index 0000000000000000000000000000000000000000..b2667624b553f32574a474e8b6081b61849f3af8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00155.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e4fcbf19610b6fa9ed3663f5a93ae7c1adce8862f1d8d73c1c8291843862ee7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00156.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00156.npy new file mode 100644 index 0000000000000000000000000000000000000000..d844389fab618ee9b65077c5dfe3666ab0dffcac --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00156.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d7c3b6db22daf8161459b37b547c485d76e645d4fa4ea7c8ba59d66949a91e8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00157.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00157.npy new file mode 100644 index 0000000000000000000000000000000000000000..c6fbbf5616b8952325fa8723ed4c6df3801cdfc5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00157.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d69e9a28ee320a51075858f5f4a3acc193b3c1b3980c1448e65ba2eb8f587df3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00158.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00158.npy new file mode 100644 index 0000000000000000000000000000000000000000..98de46c039206ce151c215d8a07956c622476003 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00158.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b70e59629628bfd90eab2e6f02d5598fe06217b5c19a2631e8af3daa596f70c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00159.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00159.npy new file mode 100644 index 0000000000000000000000000000000000000000..a02f91a91b928423b93de3b43c3d69401211d1cf --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00159.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d02ecfebfd279543c8960a5fa425e2ba953d51ea2a5667690cdd1f9783df6e86 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00160.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00160.npy new file mode 100644 index 0000000000000000000000000000000000000000..24135ba5a6fb037bddd99063ded8d5fe6b1f4087 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00160.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f0a85b26d3f1ded7f190d5a639f22901075e7dddb6404d4b5079e7fdab4b53c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00161.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00161.npy new file mode 100644 index 0000000000000000000000000000000000000000..2cee8683ca81d2f481cf5f8fc56549aadf4705cf --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00161.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b58363f494fe9d3b4bfb75de5166108d16bb5e1e2c97b791f76965232403f3d0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00162.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00162.npy new file mode 100644 index 0000000000000000000000000000000000000000..ab963c4c37cf67d5db38cad948a8578d1cd26af6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00162.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3969e617c12ad4f517834702aea5caddc6bb6adbba4ec48f3fc869e008a67e34 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00163.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00163.npy new file mode 100644 index 0000000000000000000000000000000000000000..0c6d12e178979eb67f7f060f22fabf2c9acc0219 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00163.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62d4004f614308bef574ff1902e5d4804d88586e68c5818ce067342aedde588a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00164.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00164.npy new file mode 100644 index 0000000000000000000000000000000000000000..1438ffd60e12b43b0f88f04bce68237ea722c7b0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00164.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb94ac27fe34c4fd7c89f0b8b44d84be32ae980be5a1cac4f9ef495b7c370a2e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00165.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00165.npy new file mode 100644 index 0000000000000000000000000000000000000000..7424ec39ddf4b87652c8635b1101f02b1457e306 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00165.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ee5548ea87598e47b835eab33c28ccd9f66adaf7a004efcb8bf10c57e273fef +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00166.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00166.npy new file mode 100644 index 0000000000000000000000000000000000000000..17093f3b0ecfdff62a85d301edbd5967dedc7e82 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00166.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f255ff4a3eb16e33016def617ad0dbfb3e3fb0e002d5768c6336e3d83409fc9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00167.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00167.npy new file mode 100644 index 0000000000000000000000000000000000000000..990c65e498e995e584d18b72b8aa915e6fa80a44 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00167.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cce49fc1258450e2bb77cefdfae4a33e74b5059006062857ddf9ebfd8b44856 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00168.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00168.npy new file mode 100644 index 0000000000000000000000000000000000000000..68c2501d098ab1e9a85989d0e26085548eb1d492 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00168.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b4a1f513dafdcff0b97b1b18ce29954245296abc1edf53a984093e315e3db56 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00169.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00169.npy new file mode 100644 index 0000000000000000000000000000000000000000..1e54dc27734d551bf9092196e9d0ab31a338e482 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00169.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad3163287f751b1d6ae718e0f831d2e1d0f944b2a18f5bafc984605062531783 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00170.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00170.npy new file mode 100644 index 0000000000000000000000000000000000000000..a7027939858205d17fd139785c0ecfa9f04e4671 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00170.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e9369af638edbc2246bef8ab0b5a5eeecc96bf630f3f44e64df91567d9182fc +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00171.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00171.npy new file mode 100644 index 0000000000000000000000000000000000000000..c6c8ac4481e0d4cb02378b77c15b611da089dcbc --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00171.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01ae8033d4bbe40963710e7a845c636ace33b07a59a6b7f6b9272c31a2aa3a26 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00172.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00172.npy new file mode 100644 index 0000000000000000000000000000000000000000..54ecdff8f04858eaab205a702ec2bf5f08492706 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00172.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:352b796046e990f66a60ff08c90701ceabdfae1da0dc171104331b98d1d304fb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00173.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00173.npy new file mode 100644 index 0000000000000000000000000000000000000000..67a539de829f9e43bac46d63f334bf45e0036c5e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00173.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa49d0697ce7d6514e6d92fa74b2b495bab5e3e26c9cf032a44e07abfa8dbc92 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00174.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00174.npy new file mode 100644 index 0000000000000000000000000000000000000000..4f9ea8c47f6eb89a11bfda424a1e40955471a7c5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00174.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e6d2c50ec97b67a21d452d334c11723a6a76970772d6fd11be6be24b5e22698 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00175.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00175.npy new file mode 100644 index 0000000000000000000000000000000000000000..a133a53dfe649dda17e56ed5fd9d6f04e55d4c39 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00175.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d9c2ccf15fe0bbb82cb90133b480d71dd6e2bf97ae1916a535766ab828a6422 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00176.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00176.npy new file mode 100644 index 0000000000000000000000000000000000000000..ff046c26a5f856e509f19e232caf931c2e42df3b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00176.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41c9a0e81ea8dd8517c1a980bfabb7556b389be7e363d4d955caa13c4c96eaf2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00177.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00177.npy new file mode 100644 index 0000000000000000000000000000000000000000..a9f81919561830f7edfce896aca58851ea251a66 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00177.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9723cfa8adcb5c364070675c4f7ea9b59b67c5c8121d27566c3515b0cc0ee92f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00178.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00178.npy new file mode 100644 index 0000000000000000000000000000000000000000..d58f8274b88e82c17848b4de995169a82603ff41 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00178.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8335cbb0c6b6ce0b72c38bd8d06550ad8b8f78510d71cba929123d893f51920e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00179.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00179.npy new file mode 100644 index 0000000000000000000000000000000000000000..b8e2e5e0f50077b8c6532b358a8de70b6176aa0d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00179.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e70aedcaa7354d49012a25c77e72e6cb7905e7d233a01bcc7d009c2d873fc52 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00180.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00180.npy new file mode 100644 index 0000000000000000000000000000000000000000..971d8c47d6e3c2abe94c69fa403467b97312fdf0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00180.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7ee35bfe9f3712fbf3bad9cf6ae9e7e4ee099545e78534cf68b26bc20e8ba0a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00181.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00181.npy new file mode 100644 index 0000000000000000000000000000000000000000..e8591fd55d54bcf92352a6c3a330c6845611add8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00181.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f037ce1d3c16092bc6a67735926c497f68bb62053bf9c243eb3789278db03bb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00182.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00182.npy new file mode 100644 index 0000000000000000000000000000000000000000..337fd950ff3e8a10dd2d4c90017a56e47dead231 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00182.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59f2cf4904b34314b01644b0375544b99f6f28c38a5c073059b9772820eac9cf +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00183.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00183.npy new file mode 100644 index 0000000000000000000000000000000000000000..b910df064f796b151be812cce4360a1e776d14d2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00183.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43335e4461f5729346c8ff3d97b0dcae550dd45ae4286e675be155827312b8f9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00184.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00184.npy new file mode 100644 index 0000000000000000000000000000000000000000..506d744ef6bb8c37ddb508e26ff650cb5f23f573 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00184.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64a7c43bf708ea3e4984ecb051d8713c3366df073d1cfa3cbbf5da3191917d18 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00185.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00185.npy new file mode 100644 index 0000000000000000000000000000000000000000..663a9f9faf6d087a5c2f00f51ba4361b09e9a44a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00185.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b1be46ee84f018d247bcad1457892f786b4d9d5a7e114c15d2280f7f30b1b9f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00186.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00186.npy new file mode 100644 index 0000000000000000000000000000000000000000..83e10752ca0da32fd91a87add8575c4fe76bcc50 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00186.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49d6da303b3ab855f7aa2afcdfdba0a2db010d7c99265e67a5c74f50e581c00f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00187.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00187.npy new file mode 100644 index 0000000000000000000000000000000000000000..5d402c741d4f3b41703d67e098ec4aae23f2099c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00187.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:601000e222792e85b790e9a666399e5ac8b1c5b63f4dbd5143bf145ec7ca5fd8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00188.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00188.npy new file mode 100644 index 0000000000000000000000000000000000000000..1d4ca4ef41916e97146842892efd69f088642927 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00188.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ef816616c3e561b19edfa2ae3f5352891b3c2c050943f72b76cd4716fe3154b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00189.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00189.npy new file mode 100644 index 0000000000000000000000000000000000000000..cd244623ecacefbc239ea61be96f03c800b39314 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00189.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98c36269a4f98a9bf3378607e5ac0af899265cb0b2256f43688af1af75b280b5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00190.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00190.npy new file mode 100644 index 0000000000000000000000000000000000000000..931dc3466420ebe918337c20d3594c2ece302780 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00190.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42dc50e01ccd041290d75301c54b9a94df650e37064574cab265e46b20d65d3d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00191.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00191.npy new file mode 100644 index 0000000000000000000000000000000000000000..87e7bc468f9ec9e12040ab11712d308099b2dea0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00191.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed14f3b5c1e4b5b6f9829c5d9c39a3d4ce28250c8fd8b246f1e7cb572353e4b2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00192.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00192.npy new file mode 100644 index 0000000000000000000000000000000000000000..23eade8a9d47cd0f407e6f794d9d75a34c032a3f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00192.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b27d77989c27c3f53e617919353e2bd6f4afb305b345e7a55f59fc5f34748801 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00193.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00193.npy new file mode 100644 index 0000000000000000000000000000000000000000..bc0dc30d0a49daa9a49f1ddfb0010d7095941609 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00193.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c752b5913e878bf3c342be1ae21dd0eafad6f72534d542fffe6881e8b08a01c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00194.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00194.npy new file mode 100644 index 0000000000000000000000000000000000000000..f44761923bb9b9f481d9b5a69969a1d72221f6be --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00194.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6539f50f779205f8b3437eb544b00687d2c74e7a8d3be763fbbf013829cda242 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00195.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00195.npy new file mode 100644 index 0000000000000000000000000000000000000000..d5aa0c40b071b0269c053536cbee8b867ea7d4a6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00195.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5feb4aceeeb62c6feb56e469e99f1ce648e5c529759aaefe9eb834c5694f4cc2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00196.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00196.npy new file mode 100644 index 0000000000000000000000000000000000000000..719cdc7bced7dd90f6749f6cfcb7b6e25e292e49 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00196.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bceb8094979bd52eb508da9423de4d19e2668e2ee2c06018fbaa5d125f216f57 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00197.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00197.npy new file mode 100644 index 0000000000000000000000000000000000000000..41fa1a10d3b9d51c8a9be43d07a2ac6b198261a5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00197.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:753d54f3bab784a05e0cc85a15835426c931c2094988b7805fb2ab3894cba8d6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00198.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00198.npy new file mode 100644 index 0000000000000000000000000000000000000000..c3c70514e69942cce322a03665fedfadcd3dab33 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00198.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10d4c7687449dc44269f38a53fd5912d429c471d8036528c760b65855abd3a26 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00199.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00199.npy new file mode 100644 index 0000000000000000000000000000000000000000..98c1971ba86acf5f4336738d48b2477c14e69a21 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00199.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ce4e15940a2eb6989632c8abec0be0c25466113b71dc7774f6453fd5d683160 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00200.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00200.npy new file mode 100644 index 0000000000000000000000000000000000000000..31e5bbddee783e74cff5f33de869fe7cde43161d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00200.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2eac9c39f01218ab761a6587d3d3e1c285de2dbbf94a284bf343ffb0bcdd5582 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00201.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00201.npy new file mode 100644 index 0000000000000000000000000000000000000000..55ea1d3dd3ff3ab9a90303168c31079bb4f86b92 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00201.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:967fda10781103e366e52600f2b004588ca51f13a177ae763028c5fe13782862 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00202.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00202.npy new file mode 100644 index 0000000000000000000000000000000000000000..a45db112853d570be61fd75a5d18b49e86165e4a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00202.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64ba8495f3fe7748175b38f5acdece0380f8904e422b17d1fe1ca1eee2c95773 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00203.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00203.npy new file mode 100644 index 0000000000000000000000000000000000000000..b781b5aee3adacb73edb10b32cfb1c757d43fed6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00203.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fb8fce7d811ec33313ff2325066f387a40c0edfc6b9d1807859e90602f2d144 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00204.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00204.npy new file mode 100644 index 0000000000000000000000000000000000000000..41f17867503c6f767a4529a5822a0c400eceb848 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00204.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10dcd03cc46f86fc0eb846b90f5e4d3e44b32c3be7e2a9f8b6369a171423749d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00205.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00205.npy new file mode 100644 index 0000000000000000000000000000000000000000..4dbaa68ad4a813bf0388f5b984f469de78202610 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00205.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e466f57ba00caec47e8c0c4a34dcaf38fc24d14e02ffad3cd7ee0ff8cb767d6e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00206.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00206.npy new file mode 100644 index 0000000000000000000000000000000000000000..0ce0a13e9cc6d0b65a24ead2d61f016fd5d6fe9f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00206.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:334e868ec5e47d9a2bf887862fba80a3b27ef9381489b071ab0ccd38d31c98bb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00207.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00207.npy new file mode 100644 index 0000000000000000000000000000000000000000..6bd3c96c35941cdd710302acb437408dd3660990 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00207.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5afc3fa12b05c923b221b66362d426681d101ec88588b97e4a6c81ddf5df25f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00208.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00208.npy new file mode 100644 index 0000000000000000000000000000000000000000..0236903c1c42f3e917ed7434fe7742800e8de840 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00208.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:350380e932af1f65f6a985a988b579381dde1321d2b25d93f2f33a3d7b60f37c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00209.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00209.npy new file mode 100644 index 0000000000000000000000000000000000000000..6f6877cb45bd03bbd305c3a58b0ad2ed176552a1 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00209.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04e239383a5ac26e8fe1dac16c44322e5e8f93dac9ce04641193218ccae0e917 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00210.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00210.npy new file mode 100644 index 0000000000000000000000000000000000000000..26c8204d5951d9cb90030e2daf87ba2cc5ba5d1d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00210.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82b61ba425e984703caff1729f428ffa337a1b9532dbff8a4e9653f80576feed +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00211.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00211.npy new file mode 100644 index 0000000000000000000000000000000000000000..bb41028a8e36f4e473b6de5084d50416dbf3c6f1 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00211.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:359698f755a054852839e3c45e7ca7c41e689375935804e4f0d6e5442f184ab8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00212.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00212.npy new file mode 100644 index 0000000000000000000000000000000000000000..53085871103edef3cf0ae43c03b2e6dfdeb32581 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00212.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd23abd0c99cf7417da31c07a493d981a9a74a84dd660ac5ca838fd61e02ca1e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00213.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00213.npy new file mode 100644 index 0000000000000000000000000000000000000000..4fb819b86433fc6b36426bb9623b88d031b9439c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00213.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5348558bab3c2c285296ed5ab522e87c0b1e22bb8e2d67f8a0380f312b54713f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00214.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00214.npy new file mode 100644 index 0000000000000000000000000000000000000000..9df2279e8d5826b1e41a66bf2b8c2e74aae8529f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00214.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae48753537b0ac7b27d18c02e5ac863010c4664f10994b9ff624510be88c8032 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00215.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00215.npy new file mode 100644 index 0000000000000000000000000000000000000000..f3270c8144beefcc1b6a3ae6018241f130d5108b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00215.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63190f86009bffe8f713d0bf040d37abf5289527fef1de78b0914c5cfdee9f6e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00216.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00216.npy new file mode 100644 index 0000000000000000000000000000000000000000..12329ba3d30f7cef68c4b94ecb6e25579780a0d3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00216.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:325cb358e8b50d4171d05adf344d6a34ab979f68da697819dc181d6faf95a99d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00217.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00217.npy new file mode 100644 index 0000000000000000000000000000000000000000..a405b4e8ad071f6d8d00ccf25919206bbfa0a9d7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00217.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f03cf1b411606dfd4d47957e5049c710fffb7beb688cc0ad65deaeff9d4d3fe +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00218.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00218.npy new file mode 100644 index 0000000000000000000000000000000000000000..2b5225e1897b5ca3f6f584ca8b8d1a1f801ebfd7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00218.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77eac584bb11da9cfb8908ef2e93b87fee55d9896896c85b3a210d67ca969ecf +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00219.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00219.npy new file mode 100644 index 0000000000000000000000000000000000000000..528394224ee10fb243039e7b2fc768ca89f48bad --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00219.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1011c58380ed7d68c276c30cb1a1eeab4e39092af10392cd9fe9129a362bd06 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00220.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00220.npy new file mode 100644 index 0000000000000000000000000000000000000000..21b58505f70af4a10ab85c9e182aaa14a50f524c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00220.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e37c9d7868df3c92665280e3c8acca74f097dfce57800b1c8b2f7674c6f7c2e1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00221.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00221.npy new file mode 100644 index 0000000000000000000000000000000000000000..c37bed0015f8c7a0111def9057ff056786b69bed --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00221.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0df99e98cdb7e240586282b477f3874c6d64f6694db265d3090f706ccda5905 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00222.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00222.npy new file mode 100644 index 0000000000000000000000000000000000000000..2ba9746f7864a87b3b0b6bea91314e70403bd075 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00222.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ec4b1f072bc4b87232eeceb6d51e5568cc9f9048e5b29676483832eb2653d99 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00223.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00223.npy new file mode 100644 index 0000000000000000000000000000000000000000..0f56953b9c35b0768f3131d4d07161b197a4df68 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00223.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d7a3a5786c95b5436f027a6167cc562e503585723ca163df0fe9cca2a4ff521 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00224.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00224.npy new file mode 100644 index 0000000000000000000000000000000000000000..7259ad5dc98490c8d92e8b415ec268e5da0fc367 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00224.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4d4cace02a795ff754c188c5126c9eb9492bb729bdf485f1a48ff32b43b8d3f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00225.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00225.npy new file mode 100644 index 0000000000000000000000000000000000000000..282e66da6865eadf8791f8eab75e5c7228865246 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00225.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14c2b400a0eef74d67304d001a5c035896836abf2bc8199cfe1e06c066bcfc91 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00226.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00226.npy new file mode 100644 index 0000000000000000000000000000000000000000..01ed3a7d54277fa22f627c91d19d677f6d64a214 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00226.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae18881f6d72f511754ab3e4ab2a806b7508227cdb7fedc7273c5ee247fdf322 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00227.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00227.npy new file mode 100644 index 0000000000000000000000000000000000000000..c6669ec20c2ec13f21f73e0eb5a06827e0fc0dda --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00227.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98eb00437105aee75e5bb39702baec4660da7fd3ee61973619d8fe514b87d3ac +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00228.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00228.npy new file mode 100644 index 0000000000000000000000000000000000000000..8189238a72e56c3dd4f24fee1fa233d625dac890 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00228.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00d0f21c27561af7be0097ba1e1569496bdec0d20432827841eec9259b2ee50f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00229.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00229.npy new file mode 100644 index 0000000000000000000000000000000000000000..4048a99e60ef3c5eafe86ab9c7b75873671d1681 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00229.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d5d07dbbf5b286e22210139dd466280265a9177c11e071f9c796bce4cf8de95 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00230.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00230.npy new file mode 100644 index 0000000000000000000000000000000000000000..744f1fe636a4fc8425ef163a20812bcea35ac4b9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00230.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18bc259586a37527ca72c8570e80157ff4b84e8a7074990d3d0c740ff51b4b9c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00231.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00231.npy new file mode 100644 index 0000000000000000000000000000000000000000..68f40f20926a24cf251569cd8bb8914b857244ff --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00231.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0c217c264c36b618422126591b23cccfd46f279047df19ced5dd19f8bca4b73 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00232.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00232.npy new file mode 100644 index 0000000000000000000000000000000000000000..4e25456a6f10e8afae04ac0a1fa58e6b73d027eb --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00232.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f96716d1c857ec94611321039f3ff3ce9aab50a3a56b5fd9d68e79922f9126df +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00233.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00233.npy new file mode 100644 index 0000000000000000000000000000000000000000..d21181c6e30923b1a67817f17c727e12e44769e7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00233.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f04ee6fea32b87f2c1b330808b18b0acf901eb091263541acc8bd728a497b09 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00234.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00234.npy new file mode 100644 index 0000000000000000000000000000000000000000..e2aaea55190f7a2387660174c64bef0d493ffaf6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00234.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74a59f9f0d1bb7eb8f2c49499d84c9616a011aff266491b01542c2b4edd21deb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00235.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00235.npy new file mode 100644 index 0000000000000000000000000000000000000000..c2e6bc4d5e00af1001eaea1d2aaa9f225b992f86 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00235.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dc6b8cc64272246d16f0294616434513e653735b69098860b495a0f4f2241c7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00236.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00236.npy new file mode 100644 index 0000000000000000000000000000000000000000..6e7ea038d3749753908e48ffde4cb720e62df3ea --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00236.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:733f95cc041cd434de84ad2f618bff31468dae85ed6fd033e9d57affa7f58065 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00237.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00237.npy new file mode 100644 index 0000000000000000000000000000000000000000..d0730774d3c9f18a4f8445984ea37020347df018 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00237.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd6239a33c8d48835876535106ee1c15f7c0590e1467932a2b8f33cab21837e0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00238.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00238.npy new file mode 100644 index 0000000000000000000000000000000000000000..e2ef1ca0c16cf451f1ad2709d270b8001a12745c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00238.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad7c56d079af3286e62a2e3d159bcc42383410beb30f5102896428c2aec0a134 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00239.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00239.npy new file mode 100644 index 0000000000000000000000000000000000000000..836f897fc368456a9b8ecc48c92533f4fa3193bc --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00239.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b82fea3acc3b284366799f0e21fca02d4981f7fa16a399da5a85a51b35166ee5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00240.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00240.npy new file mode 100644 index 0000000000000000000000000000000000000000..a7d54571eb458e8dbb049ba1e0eedeb8e4a7d3a4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00240.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:966886ded35cd788a13b63092e60327615efa3d3744f3d91995fe56ad88fb728 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00241.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00241.npy new file mode 100644 index 0000000000000000000000000000000000000000..9a50bf7477d4a6081562371dafbc697bc014e2f5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00241.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7cd5aef36cd73c6fd260b8f9efb80989abd78bd968a68ce4ff72d0e38939423 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00242.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00242.npy new file mode 100644 index 0000000000000000000000000000000000000000..18734277d62e4370423bd37ac424c94dc5c63c0c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00242.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bde6d8e9343f7dc213ab3689e91d67acc034a434f2ee7f800abc4ae07b785bec +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00243.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00243.npy new file mode 100644 index 0000000000000000000000000000000000000000..283dc327f2c7490ea02778df3997303713c7551a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00243.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:540fe412af41bab724a54f2f04be1b465dbf9734b2181f0ffbdd3d986427a7ee +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00244.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00244.npy new file mode 100644 index 0000000000000000000000000000000000000000..7edacb69dd904576627774d067f1ecb70d135a1f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00244.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57fc2d03df4887cefd95242e8f5665203a8c317c47fcaead362821122a27ae76 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00245.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00245.npy new file mode 100644 index 0000000000000000000000000000000000000000..d771e1fe89928f041364fabd85990ea07b218322 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00245.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd3f96a40394599b424d21e56136d2e129f674fddf862cf227185f6f964f6199 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00246.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00246.npy new file mode 100644 index 0000000000000000000000000000000000000000..9f2bf2aeb31c5979fdce2bb753006c99a5dd6934 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00246.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daf8be36e919c3b1ee0c39f4228fc7f36e5a3b9281a3f996e710dae86f2dfef8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00247.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00247.npy new file mode 100644 index 0000000000000000000000000000000000000000..64a58bfe1dbd4295620c9f867711fe388940f050 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00247.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5685f81d225039c2986b36e8fe3344f847870649238da884cee8043db4485e68 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00248.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00248.npy new file mode 100644 index 0000000000000000000000000000000000000000..c6c20373e4f8c35d12815954ecaacbe0bd1b1f13 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00248.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e6e56a2ab2396d55b8f1372f895caa2107a86b51a45b362da1a89c8284a95ec +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00249.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00249.npy new file mode 100644 index 0000000000000000000000000000000000000000..63cc5fa5627a4d54c9c068d581ddb13a03eb48fe --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00249.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5babdb4d0a88166383a29298e485398a10e2a6169661e38fb2a00aa4d7f82b5e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00250.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00250.npy new file mode 100644 index 0000000000000000000000000000000000000000..4ae1210e271e92f39fbe7881220ae68dd08c51d2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00250.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ca8317cb90419a42cd9172eb0f1cad72315f3ebdc755b940e17c0c59a05be06 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00252.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00252.npy new file mode 100644 index 0000000000000000000000000000000000000000..c3ee3da8c2917b216a39dc10a2f2cf95c467b517 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00252.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01dfd32239b0443ec1128a28fe84117c82e9a9139ef324007529e9efd4241215 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00254.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00254.npy new file mode 100644 index 0000000000000000000000000000000000000000..44eba1eb020f143cf99956ac81d62120a5ad8edc --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00254.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ba3ceada619decafafdc14f0f0cd7b0a81efadf5410570099adcba2c3ccbf79 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00256.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00256.npy new file mode 100644 index 0000000000000000000000000000000000000000..19e01d5a4ec36cbafa123ffa725d85582911e158 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00256.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62c5c88b67544eb2c1187df3493bbc274889be74635095ac20fba7beddbab75d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00258.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00258.npy new file mode 100644 index 0000000000000000000000000000000000000000..3102bf67474c80110e5c6b397a88d29567c03d01 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00258.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d70daa08cd14b020af741e8b582958a7f41c648b8660585d1ee89b44d722c3e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00260.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00260.npy new file mode 100644 index 0000000000000000000000000000000000000000..2ba7a1d3de80d5cccc48db9895fc780f4022cd40 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00260.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01eae549166b16552203a74c3ae54f4125a2b239cbb3f612b0287625721131be +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00262.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00262.npy new file mode 100644 index 0000000000000000000000000000000000000000..90da36f0b8231083fdf4e9a825babceeb54082db --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00262.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc12af22e03916d239b3c38882f737430dd082f390bb77ec97a4f76f2a0d1b13 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00264.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00264.npy new file mode 100644 index 0000000000000000000000000000000000000000..e13b9a2f650b7acadd9aec7a140b03806e5533ac --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00264.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cfc286e09797341a47a753f352d1a08a58c2b37dbc56ca5299e5643b6e9eda0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00266.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00266.npy new file mode 100644 index 0000000000000000000000000000000000000000..beec607ed9a8543f695eba903188deaf6b0513bd --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00266.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4178c1a84ed5d82293e0b7482b3510aa14cf83aab95fdc4329c51497d04f6299 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00268.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00268.npy new file mode 100644 index 0000000000000000000000000000000000000000..5877abb49b952ef560cda088b9c646acb028d783 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00268.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f796d73f3c7bb2f771d6f756fa658024b06248f6e7bfea8c87cda446e66fe794 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00270.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00270.npy new file mode 100644 index 0000000000000000000000000000000000000000..61dd9aa5b7c441dd30aafed38556d0ef16e47735 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00270.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9911385b839d11772f9f9d8d29d852e7634978312dc295ae5f4b21c020d78d74 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00272.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00272.npy new file mode 100644 index 0000000000000000000000000000000000000000..4924185a7b8c021e75f82c7a01cbf74799c5fc99 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00272.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:783253b3b764e731c56d4a85b0002147b9517d695416270208c2063f4864ad64 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00274.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00274.npy new file mode 100644 index 0000000000000000000000000000000000000000..a70453365d73d61a932d92294d0e7ff23d455b5a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00274.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa876ff069a434807a6357a8432835a36fa360460a8e4a798742599c2839ba9c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00276.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00276.npy new file mode 100644 index 0000000000000000000000000000000000000000..0841c2bc5c3ab05938f4ff6ebae255e3e1f84068 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00276.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0dd789adfbe313e686a41dd563de9bf3e285fa8a92213e91e11dfc2c9effc58 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00278.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00278.npy new file mode 100644 index 0000000000000000000000000000000000000000..7a884a4bc68437260aef37c645afc2ed0e1cdbb7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00278.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aebb25c1e747c7bec586a424e7747d1785ee52390553a66bbdbd740484c082d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00280.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00280.npy new file mode 100644 index 0000000000000000000000000000000000000000..51e52772d33bd063be72a36419c9d02cb7c52277 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00280.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee121c3942e8e3af3db081563af9335d6e31e25e894acbb95e55d9cf55c5891d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00282.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00282.npy new file mode 100644 index 0000000000000000000000000000000000000000..5da57127775c5043c1211121db4a2a9585c96d3d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00282.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31bcab72f4ad1ab641d688530af56a0144fa0a849c886844a2f6e14935c3e85e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00284.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00284.npy new file mode 100644 index 0000000000000000000000000000000000000000..db02810183a1c80e13f8c457820c40f181ab9c19 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00284.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0acd8e9d074dadd8457eaab820c1dd6ecfd83bc2df53485cbbdf8b111110ec1f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00286.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00286.npy new file mode 100644 index 0000000000000000000000000000000000000000..aba74db0d01b1fe7a703b56f4d7f9c68d1e57229 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00286.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d5b897c85f12ff4efa0e897235f07ab5e7cca06d554453d419b69c05d4e7f7f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00288.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00288.npy new file mode 100644 index 0000000000000000000000000000000000000000..d88238028fca66222a68b633cefaf5f6ba8a37fd --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00288.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:032c3e4496c51994ec6d7665f9634655d3cf51ae9626254855b2c2f685236e08 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00290.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00290.npy new file mode 100644 index 0000000000000000000000000000000000000000..f3c5a011e54604e47998b609419f1eabf766f427 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00290.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3353926731b47e86a21466a27633190d0d52c6844c27e5db74d1d9a4cae8bbe +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00292.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00292.npy new file mode 100644 index 0000000000000000000000000000000000000000..35579f3f2213fb7dd470a2740284216c4f9e1e40 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00292.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:502b2b27e3ffad7ba47d6b9164eed73b4b86bcd1eb6e99ce224c9dbc113b9faa +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00294.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00294.npy new file mode 100644 index 0000000000000000000000000000000000000000..949dbb68224b1def354cf5b61f11c77b7a58066c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00294.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50bb7cfcf6ec9b364f2f71a9c67664463d47656875466c5449b781a511f5b9ec +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00296.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00296.npy new file mode 100644 index 0000000000000000000000000000000000000000..0dd6c20a74634fad4939c643384a75887033ccc8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00296.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bf3a7b4ad70b6ae3719515b2cd6918e86d3b732d2ef93334f195d15df16f0e9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00298.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00298.npy new file mode 100644 index 0000000000000000000000000000000000000000..8fc4e838aa8db82c9774c503ff0a54a7d532c9c7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00298.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3040bd771fe60944c11b91578084c4810b0fcb94875ea9d2a9987aac0bb912e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00300.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00300.npy new file mode 100644 index 0000000000000000000000000000000000000000..74b224619b1f67ad63fb51ad2f8b17cd82762ea3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00300.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97597418d9fdc1c2cb23bd8f2fece2f1d7ac8a0c3abb268200c5abedcce92d09 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00302.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00302.npy new file mode 100644 index 0000000000000000000000000000000000000000..9335088bd2d2badea4d4e6e0ac48ae45359b9d3d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00302.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f27b1156b10caaebda38f608a47c182c955fd32fac9de8c389f466ee2358c99a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00304.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00304.npy new file mode 100644 index 0000000000000000000000000000000000000000..b2ea59fd10cfb7065540932021d4195b74cc39cb --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00304.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8202f859bbab66c786e65f426830a596e73008f8e5f83c4b9d499eb5ddf41c5e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00306.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00306.npy new file mode 100644 index 0000000000000000000000000000000000000000..612bee13c717c831efd3a679f5acaab4b62da818 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00306.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20e6dc1222904c13979121522c2d7eea49a372c6c751199af324c2ce5c92cb3c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00308.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00308.npy new file mode 100644 index 0000000000000000000000000000000000000000..267ec35877017e5796134ca92cc4690024ca1e28 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00308.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa8f75c4b9fb9476c986872245e1f54ded54cb2b8bf91ca14268fb448c4e7900 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00310.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00310.npy new file mode 100644 index 0000000000000000000000000000000000000000..9e5a3d32a88836ae49c27ebe00e93aa9fd8cb109 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00310.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43e027d744412230698ef32fbf3291467a677517438521bd6d272de4f38beb9f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00312.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00312.npy new file mode 100644 index 0000000000000000000000000000000000000000..bb394b1a93ba2c561f054cff97dab6ca323ade9a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00312.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38d145b581b9a8b4228ac367fd0906c1ffe585802553c79db990f1e0d32d7ed6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00314.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00314.npy new file mode 100644 index 0000000000000000000000000000000000000000..2c1f50e43a0722fe46d39dca37e81f13d3705e62 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00314.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af6cc899d0c3709c17fb008ac0b0f2b610ff0ac93f75fcc38bb4ab537913d8c6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00316.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00316.npy new file mode 100644 index 0000000000000000000000000000000000000000..d2fd0dae0a4bff91516e6eb9dfd567dc3a2cba28 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00316.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf8b7cd7effe23b85516fbe900e9f39219d5acb0967a916a5ccce8aeddb00337 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00318.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00318.npy new file mode 100644 index 0000000000000000000000000000000000000000..bc45d3c456b0fc07646de2e9f6b879bd25f46979 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00318.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95ea048dc0e0dacaaf770fdbfb106bad6b6dbd8de02aa076acbe658c53f49be3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00320.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00320.npy new file mode 100644 index 0000000000000000000000000000000000000000..16a297c236061ea7c3ac7f3435ae2494816dd441 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00320.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97934c3666e9fea62568ae263c1bd24b7b73bc8545b90c23ead083bcd8dc6f87 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00322.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00322.npy new file mode 100644 index 0000000000000000000000000000000000000000..b8b6556c141b91a52dd4d64f1033ec3c726ec59e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00322.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4ef1d37c2342c88d84eb2a0fea8bd42c53caff219ba5f74857b82d8d3f86101 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00324.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00324.npy new file mode 100644 index 0000000000000000000000000000000000000000..b0ddba9e638986a5ebe2381eec3364ad08f1cf8e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00324.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e917e42e0b964d21ae15fa01e934a3777545a8f8ebdbfd561da5c9e200d7ac65 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00326.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00326.npy new file mode 100644 index 0000000000000000000000000000000000000000..4a4c0b5b044a047b5009840b8e9a53a8f4c40cc5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00326.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:330874e3306128aa5530235557d25a06b02afebd186882b0818f9e5ab018891e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00328.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00328.npy new file mode 100644 index 0000000000000000000000000000000000000000..299de2ce1ae5b8580951bfc1f6f272903164af28 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00328.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98a30d250fcfa8bcad1d975261c48098c3d56f4a278e158070220238e2ded260 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00330.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00330.npy new file mode 100644 index 0000000000000000000000000000000000000000..f97541424e5c61771df4df95a1d27c9b63e4be7f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00330.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:196aef0d1d7750023e7e3686d8fb77df199bf2f48365e92e1f4f9d13f7f157ee +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00332.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00332.npy new file mode 100644 index 0000000000000000000000000000000000000000..ef1c3c7d940fb721a61d2ce56247fb92152b3e19 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00332.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:768f3bd9f2c9edf9ad302d8e4ad49af79813fbfcc35879aa9add84c24cc4d9b4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00334.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00334.npy new file mode 100644 index 0000000000000000000000000000000000000000..32c1cb91cbfb6da18a3a89044fcb331458da964c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00334.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3710b5c3bd304853442bcad491aa623bbd7f29ee09e0034c0c4f7ddc74f92f55 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00336.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00336.npy new file mode 100644 index 0000000000000000000000000000000000000000..2d04c974f7a375a7b321e9d30d9a5d34f27762cb --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00336.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd392b5014c361621fbeb7705d0c17974ee5f4b558bde9d55d84e3de2c98d9f3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00338.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00338.npy new file mode 100644 index 0000000000000000000000000000000000000000..763c053ee327e5c1c4e961fb9ae7bbbf07399127 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00338.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc7d6abe42cae84dcb1fe79cdde0ff94cfe1c302eb52050e3f741f200510a955 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00340.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00340.npy new file mode 100644 index 0000000000000000000000000000000000000000..4b164a3279d639f91fa72b094d450ff17d58dcfd --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00340.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afa638e94f62392a26b6f3f3a1bc32d46c7367804732535011148a65a8cb01a6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00342.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00342.npy new file mode 100644 index 0000000000000000000000000000000000000000..327ea5ff76c6b730b825a61cf00c88943e5709a6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00342.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19e11d0109b6b55d89121de3b4ef3498e3c8c57e7111ba6edc43a25c94ea99e8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00344.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00344.npy new file mode 100644 index 0000000000000000000000000000000000000000..08a22e42f0070b6e4260d70fce963d9b85dfcb87 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00344.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f736804e51107c53def5f446e673662896325d56228bdb91268dfca919ad815c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00346.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00346.npy new file mode 100644 index 0000000000000000000000000000000000000000..349e34bec03c6ed8264ea69266352a604b1404ed --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00346.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f73c1446ae209359c78d400dc56897393ba39ec8f6e99e3e2bab6d7d17ea9403 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00348.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00348.npy new file mode 100644 index 0000000000000000000000000000000000000000..92a898f12c24195ff8b5f21d1c1ed85bfbc1e7be --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00348.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78908ee09b2162b75a016ce949bcb0b45a7f908eb077a77a56425a7be7c6c231 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00350.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00350.npy new file mode 100644 index 0000000000000000000000000000000000000000..a56564f1da63f495d04331d9612a490d17e19d33 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00350.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20410fe4d15764654f9569adb9b74fc7b27108abb716722e67b2e559adb48f5d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00352.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00352.npy new file mode 100644 index 0000000000000000000000000000000000000000..b3669c95f9a27a7c964ee2b124257a6afe1e7cde --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00352.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67381504c54fbe6295800f894ec41cd258455859db8d0b7491efb9742aafe49a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00354.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00354.npy new file mode 100644 index 0000000000000000000000000000000000000000..6745a27eb23c64617585dcc431f700171fcce206 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00354.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:905cb6f709d98e23b0f3b660c89c383ad72be04ad6ed8e342538c95049d78593 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00356.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00356.npy new file mode 100644 index 0000000000000000000000000000000000000000..56c365d4982f6f49b7fa58ff6bec1e2e7720a2d3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00356.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c7e208d48d4b686dc62afa8ef0670089cc86403c7ef0fea3605fe275db7b324 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00358.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00358.npy new file mode 100644 index 0000000000000000000000000000000000000000..f84fc1aeef821a3f7848aed818257cd020fb9cb0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00358.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e45cd982920ad3f23639b2c0771a258ab19c7b9a3e44fb7b0b471f781cf05e9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00360.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00360.npy new file mode 100644 index 0000000000000000000000000000000000000000..931cccea2b624bba6f848c50795c0413bac77951 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00360.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee32c9848e1a988d0a9891fc03454a7bbc05be8e2d4488643c8fa88dbf26f0ae +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00362.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00362.npy new file mode 100644 index 0000000000000000000000000000000000000000..bf9aa01c16b5b0cc31d7f4e66829b2d9c8bb3efe --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00362.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69460e74415420d803a7f22fd56e6e18e0deca7955b9394ec1f4ae79b066e771 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00364.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00364.npy new file mode 100644 index 0000000000000000000000000000000000000000..552dd340d191ac8c106750b3b2c3a3f620bfdcae --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00364.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cc7892f7af7f28d210c754ff7761cbd17d33d73be35c7ade934941832199d8f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00366.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00366.npy new file mode 100644 index 0000000000000000000000000000000000000000..016364a7c86e72b23c4f88c918dc27bf1421c12d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00366.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10071332671361e88c96f88ffb78a9e889d00be72492771360efe0b782853154 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00368.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00368.npy new file mode 100644 index 0000000000000000000000000000000000000000..25a509bd0eb60922692d92032a68d031c72dd4a8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00368.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9eb22cd9e080f2432e9a45879fa80a3ab703ed6e65a9512ad8f44914b3b54a61 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00370.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00370.npy new file mode 100644 index 0000000000000000000000000000000000000000..342b7586ad15d7adcc18e57d57ce43d5dc067f63 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00370.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25a129f8d0f73902f4d12ee5d178a106aba7b29318a74b2a459996364eaded71 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00372.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00372.npy new file mode 100644 index 0000000000000000000000000000000000000000..268fd6cf325746622891a89cce52aa268c0bcbda --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00372.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f47f5f3f4031264b150d5b1747b1716dd75103b1723509b1844ad3dc73466ef0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00374.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00374.npy new file mode 100644 index 0000000000000000000000000000000000000000..f572e8ac4bdc602571d1cdd79e513c52389fb953 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00374.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee2353a749ed76844df6281342b3f7ced9f7849c5b2c6cb719b52d4d91e1c7d1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00376.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00376.npy new file mode 100644 index 0000000000000000000000000000000000000000..735b2cf21670512fa12284a2e818025ef8a09cd7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00376.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:348af68268b58d4de56f59a2524a91ff90d62233e8f189f944d12b47fbaac7aa +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00378.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00378.npy new file mode 100644 index 0000000000000000000000000000000000000000..e24d39f4a2757c17a30072459902f8f03bc52ad5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00378.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f41be1f359813ae9b705303bd63203dc89bed42070df850bce0e08251e3fe7d7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00380.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00380.npy new file mode 100644 index 0000000000000000000000000000000000000000..c8602b8bc5fb2181e54807d9f666800825ef753d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00380.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:617b9557fbfff085a43965959a25bd6077bace9086cf3fe0660ae354b4273f00 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00382.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00382.npy new file mode 100644 index 0000000000000000000000000000000000000000..4027ef0ae49784c0ece8c36b3b439c477cccfb1b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00382.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47d200ae972627fa0cc7dda5b09c0f6803d693f11d84d136f63446f266123b90 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00384.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00384.npy new file mode 100644 index 0000000000000000000000000000000000000000..d50b18ad089dfe61e0e2a09c64014295b240c7d8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00384.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d22febac2588684e9ff6de9c50c44815571806f3bc664ccf74131c1e628bafd +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00386.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00386.npy new file mode 100644 index 0000000000000000000000000000000000000000..fccf8050d1e2c0c1c0d3a173866cd09ed5ed2049 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00386.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe5ec142e7cf013dafc6fece899e24623a6a034e4c58bb38080c0d03e57494f6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00388.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00388.npy new file mode 100644 index 0000000000000000000000000000000000000000..301e1c7b48537e874664d012fc7d2b8a3de7ffff --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00388.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6219550daedddc7050c92baec8eea2b11d4b3d361905d87db7fad94bfecadff3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00390.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00390.npy new file mode 100644 index 0000000000000000000000000000000000000000..58d4c6bfa5b94ef03dbb597049a2faa9ecd00126 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00390.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee2428dd3342a6858a47117537d1b7017fd1715bcf162562b51b6bdcb38d978f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00392.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00392.npy new file mode 100644 index 0000000000000000000000000000000000000000..87e54b429e51608c0748159ad6e1b969a0187103 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00392.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c1d7002f1a36f75df2a7de28c23efb8d03a329bf731fccf3132dd573ca184bb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00394.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00394.npy new file mode 100644 index 0000000000000000000000000000000000000000..b2e7c53fc5a57dc6fda53390cfb9e511547921ea --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00394.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21234da4d823705c98ee36e108bcb8fd6e8b16ef5a733b04fdacebec4de47e3d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00396.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00396.npy new file mode 100644 index 0000000000000000000000000000000000000000..ed2d2fba98073e6aba308a2fd0f942c58a1aaafd --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00396.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12a5687bdfb0a15ce450a66873e1593b64017a2a84141ee04b0e55d9c8761791 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00398.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00398.npy new file mode 100644 index 0000000000000000000000000000000000000000..164de88772060567d627245ec7d3011de29df961 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00398.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f55df9e93df8c4df65af5f3afea6664a186333e2afc977e9d9b1c08563481af4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00400.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00400.npy new file mode 100644 index 0000000000000000000000000000000000000000..29caec26cfd3ba59548e1837e57f9d1973b40077 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00400.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e443131fd2f1c5c06663912d36f65c3bcfbebf9af32b5b0234dacab6484da80 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00402.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00402.npy new file mode 100644 index 0000000000000000000000000000000000000000..4e50d390d8dbb0276b5029dac49fab44e2303da9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00402.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0fa6c0df2875fe4d1974f9e837dd715f9023e430e4dfa2bde8efca64df77dba +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00404.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00404.npy new file mode 100644 index 0000000000000000000000000000000000000000..56ea8a3f6aa2c6d0dc943782eaa9aa761709506a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00404.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1093cfe7d585a900ae0ae764b58af0ecb63e0d9b9972e88dc06684a620807f8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00406.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00406.npy new file mode 100644 index 0000000000000000000000000000000000000000..4bdeb131e2c7cd6dc7ae4d0ae01086b6f3b51e2e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00406.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1abee2c37e9f6f77e70b6555b3bf0801aa86217fada2c16b5bc38a7345b3da21 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00408.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00408.npy new file mode 100644 index 0000000000000000000000000000000000000000..cee89d0edf9f49470629303dbe2f258f5576faee --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00408.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a72fa67b7600b261b462114acf4b83bc8a6250df8fc3579495a2c8643bf8b67 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00410.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00410.npy new file mode 100644 index 0000000000000000000000000000000000000000..4ab5fc70a7a8a8dc498efc45a43cbac9f5db77ad --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00410.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f03015b2e7b8790f0a961f4275f23b6716406f22720494df2bac9695336707a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00412.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00412.npy new file mode 100644 index 0000000000000000000000000000000000000000..a3b31bc611dbdb15dc28e5849d637ab4d33ce9c4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00412.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:beaa7e5492ee51595f58852ddd99d4b5a6568312212ac09886e9a33f1e3ec5e6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00414.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00414.npy new file mode 100644 index 0000000000000000000000000000000000000000..84c10417b63fd8682778097b75710da28cbde503 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00414.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1861fcec84547e1c0ce8b6204afc6526c4a8a3a07f7a7683c97dc2e3c43305ef +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00416.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00416.npy new file mode 100644 index 0000000000000000000000000000000000000000..2192da4149b95a2c8cd6509ab97c1dd0188f8fed --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00416.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c47c8a985f04eedb028197d3a88167119d50457a0c41c30d69b2cbc50203b429 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00418.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00418.npy new file mode 100644 index 0000000000000000000000000000000000000000..6f0bdd325bb5d19020ddff81a2860a825efd1066 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00418.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d27a95f3853210b4c4d2f3bee9c8fdd96927e1c3dbdb8f910811d6297b4d4197 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00420.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00420.npy new file mode 100644 index 0000000000000000000000000000000000000000..dbb344eac0c7f59fd7eaaf3e9da0d22cbb2c5003 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00420.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b51a3a4bf841dfd4b5c3cdc4047302696e31b5a1aef243e86c47235940897db0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00422.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00422.npy new file mode 100644 index 0000000000000000000000000000000000000000..84242fd06925df81315092b13a3ac3a9a086e8b7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00422.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25d79188fb7823005d85c24c0c63bcb945689a7403a9ed5f9adc6e07d0b2d0ff +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00424.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00424.npy new file mode 100644 index 0000000000000000000000000000000000000000..0b08592a9e073e0a17b71f896b188e0893a151da --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00424.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f423d75e482137160d68750eb64b18b4cb3da33254139bc5ca3cb2677a84ece5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00426.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00426.npy new file mode 100644 index 0000000000000000000000000000000000000000..7f07d6c93884e172ff9bc8ac673efce3fe4b66c2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00426.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6822ba68ea7722c3ffd9c680fe0f8672c69a5dbfd79e5139e5189561cd89eb99 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00428.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00428.npy new file mode 100644 index 0000000000000000000000000000000000000000..56691926633b315a18dbcd9493e72f417d911828 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00428.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c430680d4c30757a304e6d1ca06c36436147eaa3217a4ef38ad4eadaea999930 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00430.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00430.npy new file mode 100644 index 0000000000000000000000000000000000000000..4babf732612fdc60481004470775cf2a3274422a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00430.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27a4cb92d354dc7041d1d231639759b7db8d485972a4bc22a77f81cca7820200 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00432.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00432.npy new file mode 100644 index 0000000000000000000000000000000000000000..95b679e05b75194cf1f9dbdd0baf2c18013fa647 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00432.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:956f2523ec415870226add0f4e69f65cfac1e60ee2936325f113063f4015d591 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00434.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00434.npy new file mode 100644 index 0000000000000000000000000000000000000000..94dedae628add06d383b7c4b368beabfd0e41a8d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00434.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:225a05177d55ff2395cb4e48c42c8c2d06d8842f0324f42c0eb28eeaa961b8c0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00436.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00436.npy new file mode 100644 index 0000000000000000000000000000000000000000..2e1a0415627ac5bd3ad909c05b3ede37acf314a6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00436.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:600a7c7890e96eb320e7979d8cfd7973e667037f7b3b6442d119fe124f7e8b3e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00438.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00438.npy new file mode 100644 index 0000000000000000000000000000000000000000..6af8a77ebcc1672becb4927f94041c63fd61c228 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00438.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4be0e9d171f0f2f80e4826fe10ee43de96a02e56998297947f53707028ff819d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00440.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00440.npy new file mode 100644 index 0000000000000000000000000000000000000000..3880bfd75d37ba3e072759de46d7618815da51f2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00440.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a150675aec105a341ec6b3610cc89c12b3fb1c4c0d3ba39ac0f90a59bca2c78 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00442.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00442.npy new file mode 100644 index 0000000000000000000000000000000000000000..b605a315544575c0026b83988fcdcd2816a97c6d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00442.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d73f0ded55c46e68b32d5871839040ce0f2a1dda2f4f3c5527c12c0dffff8132 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00444.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00444.npy new file mode 100644 index 0000000000000000000000000000000000000000..65e405fc29550ac798db452bac0f341e989d09b7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00444.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68d8be4737eba7081e48936eaf18b137a5b4ce268e9abd05fc662200d37c5050 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00446.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00446.npy new file mode 100644 index 0000000000000000000000000000000000000000..33f38447d3e6e0d6841b023ecf6cae9be01415f8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00446.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddf5837fa455f120792c348e82a16e710e9168099c885ad570b20bc45fddfbbd +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00448.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00448.npy new file mode 100644 index 0000000000000000000000000000000000000000..f549259fa5332d1b13cada0ac7b00afced39087d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00448.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6ee2170db2389fb6c6e7d87154d3f58db4abff92da5deda9c5e87cd9d5a4cc6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00450.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00450.npy new file mode 100644 index 0000000000000000000000000000000000000000..8028e906a733d7c4502a13556e9c3449967c6486 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00450.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ab985c1e7e1a5ebbf60338a2ddbe841ad3d5af290659767fd13a27fd208d4c0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00452.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00452.npy new file mode 100644 index 0000000000000000000000000000000000000000..fe1188ac66895b0c52f74778f9a2d6e022c78c8d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00452.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5e7dab315e7632ebc0a3bef4b5f47ecf4ace2a1859824619c51552a4ac0bcc2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00454.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00454.npy new file mode 100644 index 0000000000000000000000000000000000000000..91b1fb64a9ac40ab138b3ebbd756410eb23e5a63 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00454.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4a24c6b8918045cf011fcbfde313c6a0b5d780be8e8a2678ffc9b6fac6e3cd9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00456.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00456.npy new file mode 100644 index 0000000000000000000000000000000000000000..12040222ae00a95995f3d0969e2793234f61940e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00456.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d31d6a33ef7b3a7ff41e716c51ec2f6743563642135d1bbc84bef928925aa66 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00458.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00458.npy new file mode 100644 index 0000000000000000000000000000000000000000..3b53349abb902703e9a425a5077d4b54fc3be249 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00458.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:687680b8671e6d54d885b350e82254ef4de15b7b62724d52e70c599348db6ca5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00460.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00460.npy new file mode 100644 index 0000000000000000000000000000000000000000..f36a857910d9e26d69f926fdd7bcf9049d8ef216 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00460.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a66243976f74b8306b4feea44de22b820be419c476321895d98cb0044499bd1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00462.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00462.npy new file mode 100644 index 0000000000000000000000000000000000000000..680fdf39a1568d291cecb5fc0c44bcbd16ef537f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00462.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f9479a37c5db6455db909540f127a0cd83f3ba6e194c96fd0047351ced08201 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00464.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00464.npy new file mode 100644 index 0000000000000000000000000000000000000000..98c6c08a91ae70202dde15e83d804ec5acfb6ed9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00464.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40a09f219c0a682ae50af88d470021792a380017efa1b5f7eaf7d7378f98ec2d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00466.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00466.npy new file mode 100644 index 0000000000000000000000000000000000000000..1f491fdfa94931379d558bfadd0bcd6bcf229c7e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00466.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cde4d8c684a592da58e44c5d1474b5621d83f0b169cc0292a939075683c160df +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00468.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00468.npy new file mode 100644 index 0000000000000000000000000000000000000000..9a7fc7d17a91903a5f22383b5649b515f82aa7e8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00468.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:227c8849fa30fcd3384aa305cea644123a1e246151b07a72b146242e17eb871c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00470.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00470.npy new file mode 100644 index 0000000000000000000000000000000000000000..53301f2ff261d9d3c72c3be6ef51ca924adc641b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00470.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fc373a1fa844375e012f0c4a6205bae4a91efd80d5e80b685d95b7eabcbb74f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00472.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00472.npy new file mode 100644 index 0000000000000000000000000000000000000000..43c0844ed6d6f851d16fb5ff2764a84639ff8006 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00472.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c99bb9e844ff0d7c245dee0b90935d141fe20abc7183e2f97da89035ed390b15 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00474.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00474.npy new file mode 100644 index 0000000000000000000000000000000000000000..05812cf134d4d2601359af9b1a3d89f7f196213d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00474.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f1354967f8425fea7f978b0bc53ecbc8ab3157d89ec7add96bc7a2adf892549 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00476.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00476.npy new file mode 100644 index 0000000000000000000000000000000000000000..2d4aa558f9b801d5d9ec946d15e922b0dd635878 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00476.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4396ab9226edcefe129a86692b0f1781d72d10ac0ccfe52b830506a7dcb0dd0b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00478.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00478.npy new file mode 100644 index 0000000000000000000000000000000000000000..7ad8abaf62eb552e1ac02b01cee7e6e5832b1919 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00478.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39a60910f7dbc1d5b7e37f3c824631035d874975671b1a42a93eb1f11e42e41e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00480.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00480.npy new file mode 100644 index 0000000000000000000000000000000000000000..f5b9f7d5e6f2f5cc09431a201ebe2c5629686838 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00480.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c5d418bc60e3d7ccaaf995502952df1d44228318d8af6375dd4dff29456e249 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00482.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00482.npy new file mode 100644 index 0000000000000000000000000000000000000000..d803ffc8264219371a3db1885b78163a90b9749f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00482.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3aa3e2fa8e1c958464d3b010f0c08f374e0f516a289c4a520439c76f6c66f18 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00484.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00484.npy new file mode 100644 index 0000000000000000000000000000000000000000..7725cd1cf74a4d29c672da75c0caf9178150162e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00484.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a574066eda2a581505f3fdb1a8160bd5d2128963ebf05b7186fe7381b0e0edc8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00486.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00486.npy new file mode 100644 index 0000000000000000000000000000000000000000..0e227e185f691936acf8dd6aa69605c214ed440c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00486.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07c26980bdf5101c3cbe57d58adc26b45b0bd240569cc1dec12f169eb794afdc +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00488.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00488.npy new file mode 100644 index 0000000000000000000000000000000000000000..f83d0da9a1aee753a260bf9b5032add96394074c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00488.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f94832f0a6303f4b0d52aad6fb1f97f7904983672518ff038d7647a207f6640b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00490.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00490.npy new file mode 100644 index 0000000000000000000000000000000000000000..b9c0cac0d1508dab012d27da2ed3cf1b1114c84b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00490.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e96716b7a711f45ccc4f6cebb2dd25cc993052c099d6f4bce9e209bc685c8168 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00492.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00492.npy new file mode 100644 index 0000000000000000000000000000000000000000..1d787bd7ae0e03bd41a3967f9430bb08121ae7e3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00492.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61f224a46114e98dc368155af8c1df577d7e63051f549276e828707bd347ee47 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00494.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00494.npy new file mode 100644 index 0000000000000000000000000000000000000000..a41adfe73f1442bef111584c45ecf5d181d7d91e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00494.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44ad1643bc6548f8f5fa4e569b86ba826c3a728150577504b5a2bdc7c57f6ad9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00496.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00496.npy new file mode 100644 index 0000000000000000000000000000000000000000..95e6cfc726b425176e40825456bf9cda14e90cd5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00496.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fac055842eedf46f7110d034e4b3c77d11ef3259017032a93e2b827bd595f96f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00498.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00498.npy new file mode 100644 index 0000000000000000000000000000000000000000..ee8e1bc298862fe45bd38dbf583fba833b162efc --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00498.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:772bc70fd4cbbf5cd42a581bbf88a9a6e5dd24955991772adbbb44f21e12174a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00500.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00500.npy new file mode 100644 index 0000000000000000000000000000000000000000..2212b50fbbcbba59d26888d29941c04f9eae9457 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00500.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4159250e7df2729947e249011b95bd03db3584428301663efa6c667fd435ef58 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00505.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00505.npy new file mode 100644 index 0000000000000000000000000000000000000000..ece161b8accefaa6bc9530f695cd6c2b6e966371 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00505.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f6bc575166bbb8f322ac126397516cdb964ee17516139285005a06d08e3ef87 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00510.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00510.npy new file mode 100644 index 0000000000000000000000000000000000000000..8dac0d0d030e3c8d9c277a20db9317b4061133ae --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00510.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d86635ff53d450e77ae15f0e790d72cfefe3b4dabadbc66c29f5b69696c1ef7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00515.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00515.npy new file mode 100644 index 0000000000000000000000000000000000000000..5f24b1cf91337a39a136e8fbec71727a78d4c991 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00515.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c1a8d3aae214762f21170b9690b35d3082de827ff05d77f5502d5a5efa71a7b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00520.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00520.npy new file mode 100644 index 0000000000000000000000000000000000000000..1d0d78533f5904381fbf54ff78694783fb1a948c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00520.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1c8a40e065f046da43e5a4fff786ed7f51ef3470cea25f5b56433106a6130c8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00525.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00525.npy new file mode 100644 index 0000000000000000000000000000000000000000..940af4a024e41f856e64452c770dc87d43afd772 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00525.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:231af8e277c1a9a0cb6c2e98cf5e2c2365b789e5907cf307530dec4690b359ac +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00530.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00530.npy new file mode 100644 index 0000000000000000000000000000000000000000..e56ea3f5f36e130e7e3bdb196a575445666ddd47 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00530.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a26fb673b470c50786c34a319ec675a53c67b4d1f5271c0ed15791a6cfe38a7c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00535.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00535.npy new file mode 100644 index 0000000000000000000000000000000000000000..7b578db465f4e751dec13042ec9a0ea0a3c2b0b8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00535.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc2fa581670001f3f9b3786487110734dc6f4660b93a4777e26d235be73f39af +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00540.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00540.npy new file mode 100644 index 0000000000000000000000000000000000000000..ec6f903d0ab432f535059b70596dcc780643c78c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00540.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bd9893bc59e39e0567523c31f231e314b9072201df0c17c85ba2a8cbbd765fa +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00545.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00545.npy new file mode 100644 index 0000000000000000000000000000000000000000..1c9e0c7853c92af476c0bdd6fcf418a070e62cfb --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00545.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b676a15741817f303322fc33aa0087d84d4d7a8f65beeaac59ef2e4ba5681e30 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00550.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00550.npy new file mode 100644 index 0000000000000000000000000000000000000000..cf5a4a3d3159c6e55560d605803cad07e3740ceb --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00550.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2b5335b92a2e215c052c8f878db185ea99ea88c98b9549c97111ea9b50efe31 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00555.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00555.npy new file mode 100644 index 0000000000000000000000000000000000000000..a7499ec6ec6a0e876962da37f8b11ce4ae6a2324 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00555.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b82026f5bd1766522ad414174ccd6c41363d14ad21a60fe2bc1663491c19b3a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00560.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00560.npy new file mode 100644 index 0000000000000000000000000000000000000000..10251428b97cb85d1d8ef79c068c1cea08cfcb63 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00560.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20d6b359c1908cce293d7c85c629bfbd23196ad75b258075302f775a0e535291 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00565.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00565.npy new file mode 100644 index 0000000000000000000000000000000000000000..eba8c3afcfc5cde21543d56c5c48e40c6d9c5ef8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00565.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cf30f19745ddeb75a5846591a715ea6ef192ec5c174cac465fba0a3df9efd77 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00570.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00570.npy new file mode 100644 index 0000000000000000000000000000000000000000..b8d95236631024eb8b3bf7d75e6396b95139c480 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00570.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7443f353249b99b0256d1faf88d779134510f40e5c7cc3087d73631f1a041076 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00575.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00575.npy new file mode 100644 index 0000000000000000000000000000000000000000..ed326f2017b1ba766e0169f96aa50d575d4daaa9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00575.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:513806b27627c88ca9d71ae38feb75aec15e36431b982b6037aa1cd2ebc060cf +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00580.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00580.npy new file mode 100644 index 0000000000000000000000000000000000000000..85a0350c828204fe33fd3636a99bd6e51627e6e5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00580.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e681dc5a1573bcfb9f8d3f842bbeed2e301d975a890ff224b13ae5c5fdcd4c8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00585.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00585.npy new file mode 100644 index 0000000000000000000000000000000000000000..e7fbe8af7446cf1460a1e8f26c9deda079cbffc5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00585.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18773a97844f25d740491f24655a4b78fb03df9bfcab6a9a977a45fba4f4bb4a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00590.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00590.npy new file mode 100644 index 0000000000000000000000000000000000000000..2238ea561b14793c5e8f3f4748a97f8a4df646b0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00590.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a02bbe75761830c5c6be41b3782f14a89a3560cf85c7e9819796816c7b44cef9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00595.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00595.npy new file mode 100644 index 0000000000000000000000000000000000000000..f4add5cd4b42d0bd063c750d6d3652c32ce54431 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00595.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72a692be852737795f67281261df1daab325215aa7e4852be01070ef91f4bf96 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00600.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00600.npy new file mode 100644 index 0000000000000000000000000000000000000000..17935b9c0043882d90693d881c9fd48ca1eddd00 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00600.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6584332ce44cb690239d8c3e2a2c0bb4cbc629eb64b0f88fe2ce57f27cd1a15f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00605.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00605.npy new file mode 100644 index 0000000000000000000000000000000000000000..0e3b6682a229e43331c1916c296353ab5c89d7de --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00605.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79ad1a87eca6c2f7609777abe22658382e2107e0ffc37a68c52d1e1297a651dd +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00610.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00610.npy new file mode 100644 index 0000000000000000000000000000000000000000..453db82c3bbd60aa9472e6c0229f61deef03198c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00610.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd89b42bff97914f8ffcb0811716fb49c6a734b333d3532620a063307ffdc4e9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00615.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00615.npy new file mode 100644 index 0000000000000000000000000000000000000000..fee6c87f0e43a66715beb434da40161378fc8b75 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00615.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:234c276b21fa4fb79a41993ac1b01f77971106395aa2ae2fb6349b4121961e91 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00620.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00620.npy new file mode 100644 index 0000000000000000000000000000000000000000..87d5aefab77c72b7289f697e4cb928147a214129 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00620.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd302a2e8ee63b3a3d5b8a8b1d94d43aa2408696002cb58c5a65f2ddbbe1f74b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00625.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00625.npy new file mode 100644 index 0000000000000000000000000000000000000000..8711041eb5bafb682d09dca53073bf29a08951ef --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00625.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76fa89079c40328e91c46ea7912ed0824a46e85fa8987113287e29d55505823b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00630.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00630.npy new file mode 100644 index 0000000000000000000000000000000000000000..3ece38448caa86f4c25e33a9c103b8741a175cf2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00630.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a7ad380d02acd7091998d46ea2cb6ef72589e6a5eefb79264acb78acef5b9b6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00635.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00635.npy new file mode 100644 index 0000000000000000000000000000000000000000..77125463c95a27f2fb618c9422ccdb33fbbfcd4c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00635.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71d8aa4502e048e1160393c7a38e2c873fc72ed52410313c99ca5fa539405927 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00640.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00640.npy new file mode 100644 index 0000000000000000000000000000000000000000..975adcdc8c42288a88bf9ac5eb71c44d97c26862 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00640.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfea547e5844d36df6826d916f683ea244b45aa7d08f177770b3475d5473a126 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00645.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00645.npy new file mode 100644 index 0000000000000000000000000000000000000000..9307ba56bd686bc9f00e64fe9c0d765a89387c14 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00645.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcb91ed4239b96e20ce1ba2dc0ce2185f869b636dd6dbf5fddff6ba2d9521597 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00650.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00650.npy new file mode 100644 index 0000000000000000000000000000000000000000..d1aebf2d3065a65e3279db8fc7eae1b06117bf0a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00650.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2066bff0d0d3059e6e4110f7ea5c51d20b73ecd2bc50c36aa1720d7fb1c8f61b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00655.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00655.npy new file mode 100644 index 0000000000000000000000000000000000000000..5afa9b19ffc17d7b740bc6842b525e4454421e3a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00655.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eacf8e0b5804c53d6555c448f66f9e050c4ce9adef5f50877600aca8b22159a5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00660.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00660.npy new file mode 100644 index 0000000000000000000000000000000000000000..5f3752632ad8c3839672134d61effb8a5e576fc7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00660.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e861179290d5836035de0d4806faef6e5455b1cb33546d1f782fe675d7e30c2f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00665.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00665.npy new file mode 100644 index 0000000000000000000000000000000000000000..f61d6643c2e7b9d827556d673a3ade859e49c012 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00665.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:422e3cde4c246c4f32befdccfd3269d52a53d79aa2281282b55f57002edc9d64 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00670.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00670.npy new file mode 100644 index 0000000000000000000000000000000000000000..a320325d1c1237dceb3d47ed8434893bd8a9e650 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00670.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a13328c978b82f979191eea9cde3be40f1db619e81d190d50d598f99edaeff9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00675.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00675.npy new file mode 100644 index 0000000000000000000000000000000000000000..16ffc171465b8a97716a1081e14d12a1b6ffd3d1 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00675.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e4077fe329b838b03b4b5d5dde769aaf758824fef0627e4072b4f97b5925fc2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00680.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00680.npy new file mode 100644 index 0000000000000000000000000000000000000000..64f08a492f8d048bc124f93051d4c94abefa22e1 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00680.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:061b30ea4e2b70f2d5c30ecc6b88879b32255e6d7ccc44b41479b49b852dadda +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00685.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00685.npy new file mode 100644 index 0000000000000000000000000000000000000000..d485eaa269350244f33e1a8c04c0e5f7ce86ab2f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00685.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6804aafbddb8d35ea3d711b18c1ab25405392714af88fe4f1fd1e4067555e8a0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00690.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00690.npy new file mode 100644 index 0000000000000000000000000000000000000000..a9e26825631bda1dd061808b2975bd75fa6aac6b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00690.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f323f183b41906b629b205a8d94cc07cfcc92c485271e43536ccf67e5e0bdfd7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00695.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00695.npy new file mode 100644 index 0000000000000000000000000000000000000000..0e5c25b5843cef9341a65939c5489e89b26524bd --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00695.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec770441f5cba3daaa4d66c168734094d5fe1b078cb9ffb4e66ad82474d43e18 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00700.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00700.npy new file mode 100644 index 0000000000000000000000000000000000000000..8aebc5efe2fba6fece324d82c319710695e8702e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00700.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dd3ce744ba955b871f9a50e5d4ee467c41edc6b079882e5ad51a9b5f99fa733 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00705.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00705.npy new file mode 100644 index 0000000000000000000000000000000000000000..bb45fbe4d03fc7eeebc38044bfe60f0970f63cd5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00705.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebd3cc6ae55a74d82253282dfba9e68e702050d9b1c1c728cf5ef765dfd926b5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00710.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00710.npy new file mode 100644 index 0000000000000000000000000000000000000000..85d404485d062a0378eb72a789eeeaeed571c040 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00710.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23b9a13df26a9754c9c6271b7f08be44c05bcb3a097c436c83c117633d43b840 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00715.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00715.npy new file mode 100644 index 0000000000000000000000000000000000000000..d3f26789a40778202eb571b1ebb23bbcf683280b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00715.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e667528a810caa40cf5d17273656bba4a44123747f3ce68c5ec9ef667de95c44 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00720.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00720.npy new file mode 100644 index 0000000000000000000000000000000000000000..cbac35d2edd5de1a8f48fcf2caf887c680504dc0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00720.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69128e0668d24d30a269de3882cf1f53866655a0b40b73cbb4d5e7f67f40bb44 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00725.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00725.npy new file mode 100644 index 0000000000000000000000000000000000000000..50694ee5e0183dcbec2dfa2c1848740645aa0d65 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00725.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65bc6e61e3e2ed80f4754509863c3c94cced6c5fdbde8e79e938d1b95e55c4fb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00730.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00730.npy new file mode 100644 index 0000000000000000000000000000000000000000..a43cd172c2768c840c59460dfb423a1edbd459e5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00730.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:260a64bb307410898044ddeab5f9390e7c589cb1a09c4cbe5c221575c40c3cb0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00735.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00735.npy new file mode 100644 index 0000000000000000000000000000000000000000..be9a50595e892bad72afab237f6b4debcc1ff201 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00735.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a644daa849177725f8baf145f793a30b3e35786688affa194eed9f342b112406 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00740.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00740.npy new file mode 100644 index 0000000000000000000000000000000000000000..1e2afcef2eb5d0ca685dce0c7d5508aa9a830268 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00740.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d077c43afa762dbfdeb85a860814a7dc2243858af0f062931dce7bcb78f2590b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00745.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00745.npy new file mode 100644 index 0000000000000000000000000000000000000000..b950ab737fe6ba3c51b1e842f1fd27b6634093cc --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00745.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25de91c3578e5a73c7b5db3df6594c3b87e79a647624d2c1c3e14b8bb5e7610b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00750.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00750.npy new file mode 100644 index 0000000000000000000000000000000000000000..5108d9361d23efa21003d325cecad9926c8043d0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00750.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3138d094664533ec5b040b47421a896970da39bf6561ba672b6c6e26b7b96b6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00755.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00755.npy new file mode 100644 index 0000000000000000000000000000000000000000..ed5ac89a36eb40219ebbc62c5d2cf127eee1909b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00755.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d65df789b44be6c31cfb345e8ba6548757f002739dc80a5641b1ff58af2599ef +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00760.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00760.npy new file mode 100644 index 0000000000000000000000000000000000000000..79bfa5ecf564e9a9677a0ed78041f1e94d9dccab --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00760.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19360a8dce8802d5009b1fdba0b945c08b3facec954456e5e7f5f014d483e2be +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00765.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00765.npy new file mode 100644 index 0000000000000000000000000000000000000000..6e5e62424469659a6c8fd29120c17da573101c18 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00765.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25b5463e12b3750152068767609b34bbaccfdbcab153f0cc9dad88d7da648861 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00770.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00770.npy new file mode 100644 index 0000000000000000000000000000000000000000..546704677139486119ed03da22c5a8268d01c064 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00770.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60e6cb5eb7e583def46f3205e1850bd2346bf210bd79f0e97e403b3d13da80d4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00775.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00775.npy new file mode 100644 index 0000000000000000000000000000000000000000..8a708fbb8b903458d8d4de47614e21dd1536246d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00775.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b80e618663c6a9365afb93fa97f2d7f1ce9410ee216190d6ad1a43b84739f2cc +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00780.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00780.npy new file mode 100644 index 0000000000000000000000000000000000000000..e44f69bdf4b6093b55703b5d31f48dc7c0f7a323 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00780.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8e0c8d91fa992f955812ddc96ab2566605a207a52f530e61dcde8f68e2999d9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00785.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00785.npy new file mode 100644 index 0000000000000000000000000000000000000000..e4595df6a8e0fbab9ca71448b15df3cc2e90fb82 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00785.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a3c722059dcd8c7daebc797eefa05a1ea1c3f9a64fd115067c7f999c6756d6b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00790.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00790.npy new file mode 100644 index 0000000000000000000000000000000000000000..ef1a7eab8b05336168e12398f206f6d797af8519 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00790.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1207f8fe48ff5b38e3fc263687d2d1307998d146bf624d2aa57d15e69653f111 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00795.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00795.npy new file mode 100644 index 0000000000000000000000000000000000000000..576f1185807b0b18022c39729f0613016d2da57e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00795.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce45f9f11b488f1c387d9f4c816dd13cdf90dbb729ef5c885bcdeb8d3316b734 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00800.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00800.npy new file mode 100644 index 0000000000000000000000000000000000000000..8e185b74da2942ac84f5425f786935f93e5b6c0a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00800.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d9dba1568c304d608e9a5664fdc678dfe4aad10071f48a05e645c5b16dcc7e9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00805.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00805.npy new file mode 100644 index 0000000000000000000000000000000000000000..16f47a9bdc024b120ef86cbbce3b38afb71ef66b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00805.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b009417f2dd8e9eb6a98f5efc880788fd38cc55e96400a9898ad56c25c953a73 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00810.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00810.npy new file mode 100644 index 0000000000000000000000000000000000000000..f2716754698d4d44288baf58dab965bc09fe410d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00810.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fd9d5ad858bd1459b013cda8c2f09c24639db19dcb380b9901d8c95cbafc84c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00815.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00815.npy new file mode 100644 index 0000000000000000000000000000000000000000..24ebe1b4abf61512d51c1166ecde23505461078d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00815.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ba45c51358644fbf0bd67b83b6f42ac988f0f654d679846490b214824112fef +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00820.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00820.npy new file mode 100644 index 0000000000000000000000000000000000000000..cc7a6b7195739cb15b300ac5410858dd90ae1645 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00820.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad4819bd88bb0c43091a25f6e3fdc691cc492ae2421c8ad9fbac224731290e6e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00825.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00825.npy new file mode 100644 index 0000000000000000000000000000000000000000..5c0ac39117aafb016ba7aab71fdf8d1b22d75652 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00825.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bcec130f3d628de2f04954131822ee5c339feb19b87480c686bf6f6aaecc774 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00830.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00830.npy new file mode 100644 index 0000000000000000000000000000000000000000..e9d162b3008219653b3a1fc0832199c971857a73 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00830.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bb6f2a30632dc2b47a86ad1d507a99f4fc9a96dce1ef28b54b3253d746441e3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00835.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00835.npy new file mode 100644 index 0000000000000000000000000000000000000000..8e9d334d4fe52857b1ef8796877f4d0687aacf9e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00835.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:634c3e8bbf039b526bdfa2bb9328b25093cddcf7bbc575d144410b001eb62be8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00840.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00840.npy new file mode 100644 index 0000000000000000000000000000000000000000..695c2c3151b245379ce686dd4ea0f60d47a09969 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00840.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c762f181681bf78eac26b1803727bb5a07657dfc2c7cffa96966d4fbc279843c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00845.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00845.npy new file mode 100644 index 0000000000000000000000000000000000000000..fda80615d54dfbaed196e4155f3f8940cc52b570 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00845.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:793f620648a869040ab516c3083b12be9396b5a0d8de95840b327d2e45fed3c1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00850.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00850.npy new file mode 100644 index 0000000000000000000000000000000000000000..ffc55c6dd14aaeabe1e3c72df78eaacd803c1930 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00850.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f4d0d5971efa54d938fe8b078ca8d7508074ffc646299d3a82500c6c7be101d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00855.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00855.npy new file mode 100644 index 0000000000000000000000000000000000000000..d8596b2e5f8eb14a03c1e4bad066cd3ae9f84f5e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00855.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9eea0598b9020927fc8455d62c441a61c425ab62949c405c9387b0a3ea63ec8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00860.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00860.npy new file mode 100644 index 0000000000000000000000000000000000000000..3e8e9978ec78f0d75b5577b7d5d4be8225c24206 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00860.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61aeb40275886bde467ace873870456ff5d42b94aec3df5043a72a006738b455 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00865.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00865.npy new file mode 100644 index 0000000000000000000000000000000000000000..6361f9baabdeba5b4d54f9aa328fa0c09600f703 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00865.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fdf5310b2457f82abe2838e67211ce6b803b39f10279fcce9e42ce5631fb21a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00870.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00870.npy new file mode 100644 index 0000000000000000000000000000000000000000..77648434753637b8d19d93c69c9c0a61c2aa0771 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00870.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a78f92c1f5f5a9a55b8dab5d3f384ce4a6c9e177408936862224f9739bbc6623 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00875.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00875.npy new file mode 100644 index 0000000000000000000000000000000000000000..74c985d505e4adc3ac3d7833ef6138b81c325389 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00875.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:232c4aa250925d3d7157f975a4ac98e2e7f7109857f9ab20eea0a65f73c7f890 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00880.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00880.npy new file mode 100644 index 0000000000000000000000000000000000000000..3cb01712ed05d87dc3f7cd27bc4b47e9aa8a0a16 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00880.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce125d603e3c73564fac41438b2410cafd83dea201e2c2ae3abb98e7196d5edc +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00885.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00885.npy new file mode 100644 index 0000000000000000000000000000000000000000..491d852732b54602b7d280bd1d0af913b8f393af --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00885.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a91b15316d58100bb9c7e3869ef37cd427e2fc3ef7af3b370a52bcc16da92ba5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00890.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00890.npy new file mode 100644 index 0000000000000000000000000000000000000000..ab94b5f0a97734dc64575961fc2e98c0e582f546 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00890.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:238848ac5e439253526a5b6a4c9030f5e957ff5ce20036a0448359754c7200de +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00895.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00895.npy new file mode 100644 index 0000000000000000000000000000000000000000..ca1126d39aafc77c0359bf11ac03bab7325a7d4e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00895.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9408a4e19a0164ef6495e0f417e9132c38515bdc1920f7f979a93c0f2cee6f6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00900.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00900.npy new file mode 100644 index 0000000000000000000000000000000000000000..7766072a78a47c48279cb42f16ff7e36f3c849cb --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00900.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47807e59a628922072dd2d9d9127eaaf8433810855eb26caa115f60a6b76e76b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00905.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00905.npy new file mode 100644 index 0000000000000000000000000000000000000000..1540ed16d2378e13fbb63e71f55fdf1b4107f955 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00905.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6274713d418f2a964ccc06214b453e1936ff8b4615a4e976ff22769dbaf6c630 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00910.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00910.npy new file mode 100644 index 0000000000000000000000000000000000000000..b1a8494e94dfde7b1448cdcdab4fca72631f57c2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00910.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:136f76f963691e081ae73e40e534b5d849497319d521f04652682894eebef37e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00915.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00915.npy new file mode 100644 index 0000000000000000000000000000000000000000..74b8ebed602080a67f3b48a989a0424ae75cf3d6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00915.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bc19b4b971e86500dd0bb86ef50cdcfed6252e40da19add965218d8b4dabc35 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00920.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00920.npy new file mode 100644 index 0000000000000000000000000000000000000000..72da806f87a135ba9228f7367c777d2afb3fbe69 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00920.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3534a37846727eaff2416e4a20de4e1a0009aaee23b4ee4a1433e4a3641b2bce +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00925.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00925.npy new file mode 100644 index 0000000000000000000000000000000000000000..eef07bd286a629e789342210851e3033303120bf --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00925.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0eaa9eb0ec37d77aaf25596de079dd08192ac67257884000b058a95312a1ef5a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00930.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00930.npy new file mode 100644 index 0000000000000000000000000000000000000000..bbdef4c9bf3f496af40a085377df16b39ec70d48 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00930.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2baa0918b4989d4c1fbcbdc7e9698c4f82b5474aedbbb4db43ef44f6b69ed017 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00935.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00935.npy new file mode 100644 index 0000000000000000000000000000000000000000..03d0334452482a59899076eb5c4cfa5e17d6ee10 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00935.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e51117761bad6a801e6eac28f8162c643cd767eb8802425b0312872f049acfe3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00940.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00940.npy new file mode 100644 index 0000000000000000000000000000000000000000..bc78a42b6e4167194bdfeb2171e0bc45d6fe2ba2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00940.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9885bf8e2906fd83178bee578f437104e30b593638bcc5c9436c19c9229de68 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00945.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00945.npy new file mode 100644 index 0000000000000000000000000000000000000000..0877543ae5ddd3fe80fe8e68c93f1c15fcf107ce --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00945.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a38ed6390c85ea859c9a884f34f01d33c8632db951e11b572f1cf726bc0d1412 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00950.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00950.npy new file mode 100644 index 0000000000000000000000000000000000000000..09e4d56dc879a64b13ef114a31c14df68cb8b0fb --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00950.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:047cc6540848b519c49424ad3de2e7f6c7173eef968ee937a2661e7d1471bb3e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00955.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00955.npy new file mode 100644 index 0000000000000000000000000000000000000000..f9a08d747fb011995cc2835bc6a504512c05498f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00955.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7e51e189f648b302e0c277e9d94b8a5b5f3895dfa8e8bfb20ba544154e4f05c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00960.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00960.npy new file mode 100644 index 0000000000000000000000000000000000000000..b9509f31143a81875cda92ba81996311f83b4f72 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00960.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00dff6ac12845277d3faabdcb90ad6587f000b1640400301e447206c1f2e2133 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00965.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00965.npy new file mode 100644 index 0000000000000000000000000000000000000000..01bcb96f0a78d548522f9f423a706b6104e9a81e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00965.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2600419d5841f4c023b2d24610314e6f861d81f372d0cffe775bbed8ebf8c6f2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00970.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00970.npy new file mode 100644 index 0000000000000000000000000000000000000000..c8b9f55bc4d50cf6e0603b67368e419f31b99de5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00970.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbb097c98f8c3be5e2ff601234237df5963a957b615e7eba5727131491919ba3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00975.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00975.npy new file mode 100644 index 0000000000000000000000000000000000000000..90c1776d3fb9a4ac58c8c21a0e49e8a998e6102f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00975.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd220af002f522b81ec27a70718c2ccb48edd9a27959a5b3bdcee9a027b0b87d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00980.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00980.npy new file mode 100644 index 0000000000000000000000000000000000000000..9d9a98bfb6e348373f1df22d45c165fb8b9e8e5e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00980.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f4ad4e2205ab695dd72713eb58c8d5609db3d88d27dddb53301854eab1df09a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00985.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00985.npy new file mode 100644 index 0000000000000000000000000000000000000000..d1d0f9672401acc4b5aa2f5f6b0aa45b87f51c0f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00985.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cb9c7ee0d5ceb33a15177099fc069c69bef5bdc100bcf6e4f03f95d5550e6f5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00990.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00990.npy new file mode 100644 index 0000000000000000000000000000000000000000..68dd868194ccb13e24d9b826f152890225cf7858 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00990.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65e656fa30c71b1c5e7653cbd23f3cf904629069dbb80aafc87ac6bd39441267 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00995.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00995.npy new file mode 100644 index 0000000000000000000000000000000000000000..847697c4bc010f2d7a4c4011706cd907f27a8fd2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_00995.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e5e7fe3237a54649bbb544fc9face1939b1f2d7ae74d323f421068975a74111 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01000.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01000.npy new file mode 100644 index 0000000000000000000000000000000000000000..eae14845e49c7f8c9cb9a3a8add54fc8413a7e6a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01000.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b44d0f56d748eee326ad84bfc3f1aabffb837ba13f6a1c850bda272574104e1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01005.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01005.npy new file mode 100644 index 0000000000000000000000000000000000000000..791f477bc602d57c184456d2f47af1331e6bc8d3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01005.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1778f489a4336793088bd7c5f6dbc4428f75c5d666215d3e0ffd38617d946ccd +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01010.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01010.npy new file mode 100644 index 0000000000000000000000000000000000000000..f35fe366ccd7077e747fc41a7e84efae75591aff --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01010.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d24d2919721a3a220c5cd5a145f764ca58777c0d6cf83300fb0f87efd8717ce0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01015.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01015.npy new file mode 100644 index 0000000000000000000000000000000000000000..6c69a3427b0d42f9f6c633e3ec3536c31b7bc28c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01015.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:374839cf21e3f518307ce9ba2e94ac3a8e819df9cdd2a85688f1348725c7644b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01020.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01020.npy new file mode 100644 index 0000000000000000000000000000000000000000..5fea1e1dd3c1892a117eb13490b106280a0c0e70 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01020.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36a78d618ccb40487495508b6bed89e672aba8ab18ce1ccaa22a59496c33ec60 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01025.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01025.npy new file mode 100644 index 0000000000000000000000000000000000000000..e053f23bbec0826dee348e69c68571c4b2e85f88 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01025.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0be7fdb8bff1a205cba04f318e04a209200bbc872c9a4579127c43b8ad976f5a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01030.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01030.npy new file mode 100644 index 0000000000000000000000000000000000000000..9d965822731163432cbcdf39d14865fa10ca5dc2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01030.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b78c2a01f66b665e0542fe2b4a4494141b6476d477637b8145a62d37b55c6093 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01035.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01035.npy new file mode 100644 index 0000000000000000000000000000000000000000..ceae3532f48060fee3b3460b95e8f9ebb10cf972 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01035.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa5bd1704eaccd1b3cb62e50b5a648985fa85925ce614e2e5d5f04d4904c9310 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01040.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01040.npy new file mode 100644 index 0000000000000000000000000000000000000000..f43def33cf99aa6dfb19050835224406db139a77 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01040.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5605dad4ba1dbf82fb49e5ff45a0bac149bc8ecf34c60bafcdd84d7cb93ab9fd +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01045.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01045.npy new file mode 100644 index 0000000000000000000000000000000000000000..00e159aa0f31189423a734caf09a7eff19e666dd --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01045.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd0e05aaa5552a5435f30dc09290629efc69f83d693de9e7859420cfbaae83b8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01050.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01050.npy new file mode 100644 index 0000000000000000000000000000000000000000..093859afebb13a693d24f697f6de8727bd7002dc --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01050.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:597faf3107fa6415bdc22778a1f2958bb0b9861479ea1ba8a7d114af73ea92d8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01055.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01055.npy new file mode 100644 index 0000000000000000000000000000000000000000..55bb974d419aae7cae7c17ccfc5374736ba69242 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01055.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4347baec2c0f9d99c947b66939259d699d1f368b07c7903d1d9f950dd1cbdc9e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01060.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01060.npy new file mode 100644 index 0000000000000000000000000000000000000000..1eb527d96ce8bd0c5e6c246fca4123c8de08c5bd --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01060.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc908d85789f6c8ed5ebb0f1ab2b629e8d0cf337eb374d90f331ddaeeac34725 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01065.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01065.npy new file mode 100644 index 0000000000000000000000000000000000000000..c62f4166faa25acc28bdceecd67398726b93af16 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01065.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf3bc449f700e19fac51b1d284b48723828040cbd86bdd135a968ceb97dafe58 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01070.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01070.npy new file mode 100644 index 0000000000000000000000000000000000000000..90baf4bb20c3129b6cc240bc51ebfd32a452d52c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01070.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36e93f93f6ce60c2a0d21d0caee4dbc09db7b5ca7db596289bfe40c36cca4504 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01075.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01075.npy new file mode 100644 index 0000000000000000000000000000000000000000..2b1354d175e2c950c2bc902a18c90f1aee6dcfa0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01075.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f4836307ac5c497993b3590102bdfe908c65bb7197c469f01e71bd367d85596 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01080.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01080.npy new file mode 100644 index 0000000000000000000000000000000000000000..cc142acc341dec434dbf2918655c0e231793663c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01080.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaf40c5a19a009adf049074f4b919594bb5a992234886e8bd2dc2971a6dc0bd4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01085.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01085.npy new file mode 100644 index 0000000000000000000000000000000000000000..c5517f39eb32a6c10bf5292ea824a85f2050a96d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01085.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5a2d934c71ccfac76c17edf827505494d4d01695fb0e727412709cd1f8077d6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01090.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01090.npy new file mode 100644 index 0000000000000000000000000000000000000000..44c1b2f1ade8fbdb09398c9d7bc1b71b6546559f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01090.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6a5873593f459db22bed1df491a6551c14ccfc72e0c696e78d53163c850a7b7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01095.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01095.npy new file mode 100644 index 0000000000000000000000000000000000000000..07a2e9ec8341dcface718e248fad237eb1c84d1f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01095.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a001496b6366e0a4597b23094708e3ec1fe797d7c4b08dee9d8a6bf18e07fca +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01100.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01100.npy new file mode 100644 index 0000000000000000000000000000000000000000..6dc11747ed2a598d7849f70efa7bcff867535bd3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01100.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e43839950a9556bfe51d1239ff4bb193cce5f58181e22c061a614a58df0af31 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01105.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01105.npy new file mode 100644 index 0000000000000000000000000000000000000000..bedd4e75fc654e356a514879fe9ddd618802005a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01105.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec14d3124740580963ba75eeb4530a6d1b9c29f3c621f9b4ac238a359602796b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01110.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01110.npy new file mode 100644 index 0000000000000000000000000000000000000000..f156f760053df8caf6f269416db29b9bae9899a1 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01110.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d3d5a161cf716171918a673cafd46fe3ac02eb814c3a48ddc325a54358f7d72 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01115.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01115.npy new file mode 100644 index 0000000000000000000000000000000000000000..690734baf275c327d7fe64532faaa618cb7a89e4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01115.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27067c19fa17af6c7ac3cf721aab048d32c9fcaaefd41a2ebc7126ad945fad4a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01120.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01120.npy new file mode 100644 index 0000000000000000000000000000000000000000..9ba0d4c58590ce97ec8e1eb171a218e37c1e2b74 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01120.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18a72aa4a4007f69b339060b61f76a3524bf4ab2a80ef1f6bbc5fa1e26019b33 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01125.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01125.npy new file mode 100644 index 0000000000000000000000000000000000000000..22fee2b3dcf8b8ab722468771535e1a4f2855342 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01125.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0f3fba260bef5a06648e633c96690cb410fbc88e7b2fa141d16e484d497b6e8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01130.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01130.npy new file mode 100644 index 0000000000000000000000000000000000000000..318e67a4aa76a4fb4e3e9ca6729bd5c47f9ccb33 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01130.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c8fa09dda4334651299564d94dd0fe6e23c76bd602460db55701062248de238 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01135.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01135.npy new file mode 100644 index 0000000000000000000000000000000000000000..b019e58e98e2c434970e09d292065e6063c1403f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01135.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:622efa8b9421ba6aefb9367209a4b707f523da5c1d85f823f69fe6a16d87b5b8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01140.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01140.npy new file mode 100644 index 0000000000000000000000000000000000000000..64535471fe006650c4902bb656884d529be14a52 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01140.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39af841a3de38990b9748c88969e8e1a07cd46fbac455f6df7bca97b3bdb61a4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01145.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01145.npy new file mode 100644 index 0000000000000000000000000000000000000000..53fe469dcbfcac390b150fe4810bffb004e0a31f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01145.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b2aac7a019a897f2b2ffe69ffce4a08a8af8b17859187563e943bcb52a7bfb8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01150.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01150.npy new file mode 100644 index 0000000000000000000000000000000000000000..459204fc93d81634324340ab1428a0e217fdea61 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01150.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a910cde28b31f4802e8b30bcb0555c66a881c8538bb05394f8860c215ed9e8f2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01155.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01155.npy new file mode 100644 index 0000000000000000000000000000000000000000..4485339882e23bd69a395e2f1f0ea09de4099139 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01155.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d30427f066ed5f5495a2db73f1ea147926a4d4be2fdc4d35a55d7d8275873f51 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01160.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01160.npy new file mode 100644 index 0000000000000000000000000000000000000000..085ab2fc608f69c49ee2dac6aff75a439dbfe393 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01160.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70903a9dab0b207e37da373734151bf9b02b1eaa5ea4be110d93d5d5ed28883e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01165.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01165.npy new file mode 100644 index 0000000000000000000000000000000000000000..caad1b641e337c7bbb10e378f065c3aaf6d1611a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01165.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cee52cf3c206cfd1a967011c02fb2ded9a53a0b956d6097cb6586a652c58f76 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01170.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01170.npy new file mode 100644 index 0000000000000000000000000000000000000000..00625a52013226b1f840327fdbe06001a95de3b2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01170.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47eb6a37cecedd9e419215e1e5e91d443eb557ea2cff78d05dc16a1f295408bc +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01175.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01175.npy new file mode 100644 index 0000000000000000000000000000000000000000..7dd48a93a7a0f3f18f2b4408bd1a3ebf5b35e05f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01175.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eed604863eb6b81d0a7298c87bc186dcfb10e005c7ab685023eef69bb3242431 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01180.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01180.npy new file mode 100644 index 0000000000000000000000000000000000000000..75ffd42666e3679d1f5d1a7e877168e79c548f2a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01180.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6260f25631708fe4acb2443cd4e9188febea648321b5d20b008f084fbf80bab5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01185.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01185.npy new file mode 100644 index 0000000000000000000000000000000000000000..bde3cf08964e293df17ff85d0eac1619f8590833 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01185.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dda81cd526d14bb638b4576cc402a2d7a7713135cfff436719faa96f8df82e9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01190.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01190.npy new file mode 100644 index 0000000000000000000000000000000000000000..38886870b598c02c53396f761cb7c8273fcaa2d5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01190.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a69c03d63c06030017562ed6e3b9d2fbde5f4ce3c556564f2ff2b36f0da52d6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01195.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01195.npy new file mode 100644 index 0000000000000000000000000000000000000000..f176d538be63aa306c395e644d8c71a15d50649c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01195.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c77fd81c82f42dcc3461f5182a6b18a4f3c9cd55875f8d201ecc3dc9516bfbdf +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01200.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01200.npy new file mode 100644 index 0000000000000000000000000000000000000000..7297a75d73f94d8be714954ffdee9e7cfc34a05c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01200.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6559d1d57bfebb5b33371c4aabfeb955d683a46d335a72e42813f408e41ead91 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01205.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01205.npy new file mode 100644 index 0000000000000000000000000000000000000000..38533eab55d343eba6a28d0985daab904e579576 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01205.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecd9accfca672e425a3aaafc87ba5ce85816fbf452d4f97428dd1ee28421a1fb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01210.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01210.npy new file mode 100644 index 0000000000000000000000000000000000000000..b7c5513e856f3c88a890cb1177c8fbae0f54b40d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01210.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6be6530b9c18ead2fc51e7fef3bcc56ad91ee88a57e04dc76abcc7d16ee04274 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01215.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01215.npy new file mode 100644 index 0000000000000000000000000000000000000000..e6c34b9f7be77f70469d55f61e5dd8becd0481ce --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01215.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:426d6b9dc8a99ae92738ba9873e72d9ff15cb156e20fa2145156b2997860355c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01220.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01220.npy new file mode 100644 index 0000000000000000000000000000000000000000..73b5f5fd7a0813a4bff86e299c52f3687f52ffd5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01220.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a7c6c2ec61a6100abf6c8d366e2783197cbb1f04595ce6b35a345428ed5497e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01225.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01225.npy new file mode 100644 index 0000000000000000000000000000000000000000..87650f97cc563d1a6ad7940b91b45bf89d065041 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01225.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4437a8077603aceb1417ad05520f71966d220beb72faa450f254df3302e998b9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01230.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01230.npy new file mode 100644 index 0000000000000000000000000000000000000000..bf8aef448f26009c7dea9a2a8c8e3b8f26a40c21 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01230.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c34671ca3774b8ecf52333d06ae560916e09a1786d3fa72603e5765c960bd94 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01235.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01235.npy new file mode 100644 index 0000000000000000000000000000000000000000..2df2c4b1b4d475922bba3fb4f0b8e59d46119740 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01235.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8233fc6a27d1403ee777a9ce674c3d29af7d36ce5b3f4482565e25655dca7417 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01240.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01240.npy new file mode 100644 index 0000000000000000000000000000000000000000..dcf029f46cfbbb7ba83fe70e6980723cce38bf5b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01240.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74027077cf2cfe9cdcb43de1ce20edb194e9a91e30494d870ede21a216051ceb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01245.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01245.npy new file mode 100644 index 0000000000000000000000000000000000000000..d67d66362f7b4338dd031489e43d77e631ce6322 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01245.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:176e74205a0f06aeffef6576f8f6a190ad2a7294fc7a2294b67a6e1084e91c88 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01250.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01250.npy new file mode 100644 index 0000000000000000000000000000000000000000..6598f6d648e9ce7d3bff67ea49241aecadbbeebc --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01250.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67fc05daffb9361db4acd62d86cd6f8f7c51d1b315a0dc54e94253f0e43c6ec2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01255.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01255.npy new file mode 100644 index 0000000000000000000000000000000000000000..d97e65e13f30fbc79bdc613900040fb1596a0ad9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01255.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d833cfa90d9de0e0c372cc6a7c64ced8322e18506af742a154508092a268b8fe +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01260.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01260.npy new file mode 100644 index 0000000000000000000000000000000000000000..7e1164c726068e2480127678ef14d4f1781744ec --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01260.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00b272c02c6bcfa4825542a115f258b8eb245c57821101d9c615188b07199abf +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01265.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01265.npy new file mode 100644 index 0000000000000000000000000000000000000000..9f31efbbb52b28241f155272ebc13b6f531ed5b8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01265.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df734b7780834489961c9a24fd1f1e606d28af9e507491e21f855e5125c5b76c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01270.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01270.npy new file mode 100644 index 0000000000000000000000000000000000000000..723d658034af1fbc27eef44f89bb4f59618ce8b4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01270.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea9b41e39bae86b51abb4870c975be40ccd09870a39ee4fd195b9fe8f63492c8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01275.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01275.npy new file mode 100644 index 0000000000000000000000000000000000000000..a25c8c5e64b77409d0b2be2107d6f60b06c3b80b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01275.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:380ccbe1a5cb4bf5cc576f89264e0d93b48a45382a17e17c93d36ace79da5544 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01280.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01280.npy new file mode 100644 index 0000000000000000000000000000000000000000..130280b65f6da3dc38af2104dd921e7f11eff834 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01280.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b3460982f20db2700c917269ac82e1634be724ef855ba2e441946fe90585cd1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01285.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01285.npy new file mode 100644 index 0000000000000000000000000000000000000000..d112148506f0234cb5b5438d78e25083c126c69c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01285.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c36191597029f5a6f76e9e4b6c43f6690b744b962ab5bba5c142ffd7e42308d8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01290.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01290.npy new file mode 100644 index 0000000000000000000000000000000000000000..5fa8718e7fbff13ea0514593a303350308dbc216 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01290.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f329ae355d5add919542a660aaf11c8e4c1b802bb78fbb806116ca16253ad71 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01295.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01295.npy new file mode 100644 index 0000000000000000000000000000000000000000..073f7953965085f62fb5e96417c0fa7c583927f3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01295.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f537c0f25a8b910a227674e7c926090def44385832ecb51ac0d247785beb2863 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01300.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01300.npy new file mode 100644 index 0000000000000000000000000000000000000000..aa3a5d2b2c4b869e66de19b71a66d8f48c3552b4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01300.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d782c72c43c043e5c8b9a2addaeda8b15b516e1c9e6d65b015e75de0e67c7d4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01305.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01305.npy new file mode 100644 index 0000000000000000000000000000000000000000..10ac93f99e6c7ae848f9cbc63d136e7b05085879 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01305.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d148cd2a700709fe76e91392a9cabe6e8bf46a9bced0fb14845e58c82943c8cb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01310.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01310.npy new file mode 100644 index 0000000000000000000000000000000000000000..a0d6462f68817a0f66fbaf392673435eece1652f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01310.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ebc30d5571826cb15aa6f27818225e66cf6e58acd624e11f084496d8792a0df +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01315.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01315.npy new file mode 100644 index 0000000000000000000000000000000000000000..2b456ebcf4dba376ebe5e5f9487ad06fcfcef863 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01315.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c55f75061fba7bb5cec0247fdc3a7732ebb722bd1b9e75e1c827cb2cee65ba9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01320.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01320.npy new file mode 100644 index 0000000000000000000000000000000000000000..4537ffd54b8ef0a227ae6bfd573fb205b14e5309 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01320.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:604138df6dee5ddd5660b0989600cdd56e3c743820f538637f1ee4048ad305a0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01325.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01325.npy new file mode 100644 index 0000000000000000000000000000000000000000..3e59e0c23769192ffb5a8225d7d212c226eac464 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01325.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ba0df09f8b1e38ea5c195d05e5471db7039d6666ff73afe65dc53933bf9478d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01330.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01330.npy new file mode 100644 index 0000000000000000000000000000000000000000..ee382b5d120a2c5c2d9b9ecf5189d38e0c2af0bb --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01330.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89b9a1a61686eb4489f42f6d2e52312718438f07200b16eee74143dc56f2e979 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01335.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01335.npy new file mode 100644 index 0000000000000000000000000000000000000000..4b40ccc2939109809cd53e523b977843765f9d47 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01335.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61ab368858433cb759149be20a3c07e3b81a619ff09e9b90e2dbdfe1565a2d7e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01340.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01340.npy new file mode 100644 index 0000000000000000000000000000000000000000..82b1aa44fff555a535fb26172b91aad2a3f6ff41 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01340.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76ab9c005b06215891ccd9057cb47878fedf1af670c8560d7405b307da5445ba +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01345.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01345.npy new file mode 100644 index 0000000000000000000000000000000000000000..5248abf82aa15d31cc2848a1e4efb3d225390afc --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01345.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:540cff874d6c8a247f75fe2a0d0f31229775bb09a1bfe2bb8fff00947330e55c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01350.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01350.npy new file mode 100644 index 0000000000000000000000000000000000000000..1edac5027849b8a72647e6c898bb0d9c5da7a829 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01350.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52664bce69ceb7207f41ba6b047528c46afd851e56aa3be69734555913dc2399 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01355.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01355.npy new file mode 100644 index 0000000000000000000000000000000000000000..b4d20dd61e092b43de408fd4056ecd91d471dede --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01355.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb0929caf47e37ec3dfdf17bc3298ab90fb77c2ddd2c16be9a8ec18768c06eaf +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01360.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01360.npy new file mode 100644 index 0000000000000000000000000000000000000000..fec84aeb96a47ab02fe01a8788ec19d7876209d2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01360.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4a5c8bb421009af47dfbc363b0cc52b778aa79712fe9829afefbaaabd88a49b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01365.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01365.npy new file mode 100644 index 0000000000000000000000000000000000000000..e4cbe2987481ec782a5e4522d9a085b91752d782 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01365.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c3bff2bed2949e42a83bfe04c83447efc524b624f78c4576ed0d6ad208efe4d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01370.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01370.npy new file mode 100644 index 0000000000000000000000000000000000000000..8e716e7b2516446e18ae5e0c2f986e5ddf11819c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01370.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30b29837fd37cb3688abc2e85b2a1ecdc6ed8e6e3035e2ff289068e5d35537b9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01375.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01375.npy new file mode 100644 index 0000000000000000000000000000000000000000..865b5fec1bd87b83c739b3a25afa78b6830151d8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01375.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c79342da723f9bc06fefbb8c31b703cce2253d9a16feb0b48f781e38e22bc6f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01380.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01380.npy new file mode 100644 index 0000000000000000000000000000000000000000..cec8b71ebcaf9a8cc1b7d6e383d5007cc17f8b28 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01380.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81fb78a7e5b443d372ee3432ed4894b785791a0e9daf48a1961cc86e65309b0d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01385.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01385.npy new file mode 100644 index 0000000000000000000000000000000000000000..e5b4db8df88a469ad033640573eb47dc5c6302e7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01385.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a1ecf29c78ceebb3e331c925a458c80f53110a7519ed057418dd5dc286edb56 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01390.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01390.npy new file mode 100644 index 0000000000000000000000000000000000000000..b1d349c18aec32c36288c5da4405d15c5f36791a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01390.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11a1557689081db335f2fcf7904c535ec967a77ec95896fd72e72d2af651e38c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01395.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01395.npy new file mode 100644 index 0000000000000000000000000000000000000000..e1ae950a990bc461909871224bee42636326b52d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01395.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9609468d93b8f3f0f8416477d368f53424a4fefa17643852070b5496a0702e7c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01400.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01400.npy new file mode 100644 index 0000000000000000000000000000000000000000..5f8e5ca21dba86b235b9abf04edccf4db8a0157d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01400.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3def7e28ece489d28ef1cf37261e6fbdd8b71f49cd06825af1f0bf2aeb1e060 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01405.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01405.npy new file mode 100644 index 0000000000000000000000000000000000000000..5af5d9784103f62ca42605cd27ef67c070728567 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01405.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc88caea79dca1f3943b513e3fc0d656ad9872f198f36953e96b21f933d6c1e3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01410.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01410.npy new file mode 100644 index 0000000000000000000000000000000000000000..43521130c73c654ee09e7373696dc3dbeeeed8d3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01410.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79e334a6f1939d9df258d5506247c5f24cc44a3e1d194e6ca2e2840a470196d8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01415.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01415.npy new file mode 100644 index 0000000000000000000000000000000000000000..37134f7bd56626df999df42a7cc7f82560c83473 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01415.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eabeebc33983ec2dc3e73d8a71684df3f39d403b83bb1b5a7d6d9cdecbccbbcb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01420.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01420.npy new file mode 100644 index 0000000000000000000000000000000000000000..ce7f9bca428ef198115bcc887f738fde1f31816c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01420.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99c5a0ac65ff032d43df009513a6e11e956b5fe9918559cb71090932abebc361 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01425.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01425.npy new file mode 100644 index 0000000000000000000000000000000000000000..fe35bf2bf02c045f3b277e9682f2e2b1fcddd67a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01425.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72be1bf44e85e07821bf4f6c7e0b357483de0101ddd1395b9ec7de2e72cf6cef +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01430.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01430.npy new file mode 100644 index 0000000000000000000000000000000000000000..507c5a66c03ae041392a1519243c4856887d08b9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01430.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3489406782ec9ac58fc65033deb9f57ceb60cc157a58069dd35e2b420adf29fd +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01435.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01435.npy new file mode 100644 index 0000000000000000000000000000000000000000..cd87635abcd4aea8a10f3973d56637dcebccc9ef --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01435.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ab6c98ffb1d459ffbd07608ebea78deff418a4b1f3ee3759a522852a87c5452 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01440.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01440.npy new file mode 100644 index 0000000000000000000000000000000000000000..6fd3fadd07d60e813a80cbbc0f1a0a5120808b0c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01440.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09ccc90e9ced9ed56d18d2363b115e23cf743e7d32eb6162ad50f9351a04363c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01445.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01445.npy new file mode 100644 index 0000000000000000000000000000000000000000..10987152910234bcf920b7c80643a78dc1c70256 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01445.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbb2f3367ab6d30544b9b3ca9cdc5ea144fab5fd9e7c4d32bc3d450982259089 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01450.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01450.npy new file mode 100644 index 0000000000000000000000000000000000000000..bef79c81ad091d0ea0464907c6179a2e564ca3ea --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01450.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e8fe50625968998c8414dfc28829b9ae0abb63d1eb4e22f95a9b5920b6dfa89 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01455.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01455.npy new file mode 100644 index 0000000000000000000000000000000000000000..3bb11a9c0df5db1b9a024613153c1e6f2f836a22 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01455.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:486031b4572ef3a392edba23988cd8742013fb210b4a6e1a516e13ff0e6f3922 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01460.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01460.npy new file mode 100644 index 0000000000000000000000000000000000000000..9d0bdbd07600efc3d6528dfbd843448ef647305a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01460.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef578bbbcaa8917b5359f6a55e54197ce2bfc4cec39c58f349e86cf19b385d65 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01465.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01465.npy new file mode 100644 index 0000000000000000000000000000000000000000..86ca54eb15731295dd30a66f6a8f3519d72b7df6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01465.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2068c6cdd19236106765b099d9fac7f776eb949be8f2b3278422517ecdcecdd +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01470.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01470.npy new file mode 100644 index 0000000000000000000000000000000000000000..049002d68fe1671df8d18ebee1396282f8124f49 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01470.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9893ad60dfe4a2e9dbf71338c75e243574f9c5bb114b64b8818c740c6866960 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01475.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01475.npy new file mode 100644 index 0000000000000000000000000000000000000000..cada56362486871e35bab350ec209a0ed3013673 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01475.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:767a5b1f2dbcd1828bc374867a6dc43d9078b20c59c63af727e23e5108f9facc +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01480.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01480.npy new file mode 100644 index 0000000000000000000000000000000000000000..2b8614aea27c1ee9e4fa2b340433f3b48930491b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01480.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b6a3c4fe661a50c85f83cecb0760450685679c1c0265c3ab9235fd6fa0307b6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01485.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01485.npy new file mode 100644 index 0000000000000000000000000000000000000000..a09728b503c8225b5e13280cf0bbea6ed40741a0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01485.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a46c4e75b8a390de5af6cec586a3bd173b9fb87c5c8a73adef8ac09fedb047b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01490.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01490.npy new file mode 100644 index 0000000000000000000000000000000000000000..80511c360cc82e2185882b7ac4ae23f8c0580166 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01490.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bb9c217436841c107e1c3124907ccf5ee5a95054b4ccdfa452dfd9b51a556a7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01495.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01495.npy new file mode 100644 index 0000000000000000000000000000000000000000..a6215ee074d27ba7597feb9e05983d15e93d1bc3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01495.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:520f415a26ebf1b0ad73b02f783018425b576218a51d177756ab83716e51e0d4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01500.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01500.npy new file mode 100644 index 0000000000000000000000000000000000000000..dff6e8b72307bb9b50e68771c8c22347f6b669e4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01500.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20efdb08de0a959b5c45c648e59040d7f97abfa2644618e517932ac3278d76e0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01505.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01505.npy new file mode 100644 index 0000000000000000000000000000000000000000..6c59a9150641120b18f5ef139ea1666a13df646b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01505.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3b0c37433a41d6ab2b113cfdb53c61267720f7428ce27a08175a983892fc923 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01510.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01510.npy new file mode 100644 index 0000000000000000000000000000000000000000..94e2803e2524bde0e8daa1fd9380b537083818a1 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01510.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73216e1930e1105cfe0187bdb0cbf72adf338e3fa84a8c41192330c347703a25 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01515.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01515.npy new file mode 100644 index 0000000000000000000000000000000000000000..522af48eb8573fe902ffbcc07ffe390da232f375 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01515.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6517e0fc4d2f3775dbfc5b40202eaa6dc35550604b7695a45fb22a7cc2cbce1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01520.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01520.npy new file mode 100644 index 0000000000000000000000000000000000000000..163f9fa257bde625388981360299858ad8151d7f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01520.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a461ade29b649c156d7319f8eb7f9f59aeeb6bd5b1f193260e2999f505f3ac81 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01525.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01525.npy new file mode 100644 index 0000000000000000000000000000000000000000..0a9f1cf0159b7fa5dcd5778d0d6eddad5c7a6f9e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01525.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d101dae89e8631f4269c6f64041895b52b544b260a94a0c2da24a93a806bd3f8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01530.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01530.npy new file mode 100644 index 0000000000000000000000000000000000000000..6a56b1426660e06ff8393f573bb6208d9f6782f8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01530.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7e422f99f47bfb62090b83c6005aabc58eb933aa8fd0f81a85b8bea0dad62b9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01535.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01535.npy new file mode 100644 index 0000000000000000000000000000000000000000..c951110e3a42b35f35b5e471735aa6773291d907 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01535.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0392b52e89f7e8dbe3b7c8b2acb9c372b4b594cbcc45dcb6761c0df96a02726 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01540.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01540.npy new file mode 100644 index 0000000000000000000000000000000000000000..2b2baf9ffaf7cba33438bc51c4334453af791ff5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01540.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3f396403dd552bb7b87ce6d399ad7491d8f9abaf85837f442292c9dc6294caa +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01545.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01545.npy new file mode 100644 index 0000000000000000000000000000000000000000..7b99044c1a1dd0c9488d206d36ddd1d4b35fb396 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01545.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17579c0931a95a51e85d35ce5b6b4a94bbd3900826ff8595fa90b73ce9723fd7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01550.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01550.npy new file mode 100644 index 0000000000000000000000000000000000000000..d11a2afcc0ba2f322c4cbe2cbaa3d33fb91a75af --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01550.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d475e768849e0ccc00eb2e9cbfa124c7ace9a740cd30e4aa016fd4e2093c6214 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01555.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01555.npy new file mode 100644 index 0000000000000000000000000000000000000000..74fdeb65a730b0815c24f6d2c22f8f26927b2b11 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01555.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc0d70e7431bcd818ebcea4db1d7cde38f9d5e9cccd6a062a76ba934be0dfe95 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01560.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01560.npy new file mode 100644 index 0000000000000000000000000000000000000000..4314094cc2cb838c0ca79e444ad35c66f43697b2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01560.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12c63521e946a580c5539fa44d8506fa3794258240251b9314a15fb29cefcb88 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01565.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01565.npy new file mode 100644 index 0000000000000000000000000000000000000000..055d190c08d104ba4603b568a0073de9215d7511 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01565.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:860371e40dbeaf9838e05cd9e04f51dbf749c8e9b8fd48a55a606a93e90bb7b9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01570.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01570.npy new file mode 100644 index 0000000000000000000000000000000000000000..992b6718796c52bc4ce40f1bb6475306bf68831e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01570.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fe30566636dc63c4aca4f241342cf222468994cd43f148221dbe3b8aaac42b1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01575.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01575.npy new file mode 100644 index 0000000000000000000000000000000000000000..f369d921130203282799b4fb37f447626333f529 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01575.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a723f0a3da8aacad6aa3c7b2476e4b1ec293a1268aae45d56ed033d85e477793 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01580.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01580.npy new file mode 100644 index 0000000000000000000000000000000000000000..f53343ba70cbdc0a413d7a2c28732ebe17964592 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01580.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42abc2ae66db99ccdbf2bc04ed6fa334fe178ec2580f69215c35fa3bc76db7b9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01585.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01585.npy new file mode 100644 index 0000000000000000000000000000000000000000..45ca02fb69ba97c9141e8fc5dd6a2a33b4d7c840 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01585.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3a2c5aff000ce63f4873bfde062e0ae634bde460bf9f57f64f5aa579a69a20f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01590.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01590.npy new file mode 100644 index 0000000000000000000000000000000000000000..66ef81583dcf4b4af250b8ae45941343bc08f49a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01590.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10cdf8ef72f1a7839f0e905023f81ba4ddc303473b3731b1eafb4810aef4e4e1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01595.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01595.npy new file mode 100644 index 0000000000000000000000000000000000000000..e7416bcb347e86df342d757c8d8e916d0ae414b1 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01595.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0810f86afb60330bfc5c749403a99ce4f49e11258a979a03748aaaf0d001a94f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01600.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01600.npy new file mode 100644 index 0000000000000000000000000000000000000000..5d6e67050f61b39b1c15ccc7259ee902a46dbed8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01600.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ab64c0f001733a41d1a24bfde61f817becbf6c13796a0665966404cb3d64fb5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01605.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01605.npy new file mode 100644 index 0000000000000000000000000000000000000000..b2ab76b5170ff48cb2fa08e163e5c571845890af --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01605.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:717e75f5ed0b4210f7d36ca80697f6954a56b72352c1b6cb5d677920e52ca8c4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01610.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01610.npy new file mode 100644 index 0000000000000000000000000000000000000000..f79fb6617043cc0ea08a26737466a3057fd10385 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01610.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ded80ca3a545cd9c8740cdfd9fef51a142e6a6bfbd731fadbbfb8cb35589b20 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01615.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01615.npy new file mode 100644 index 0000000000000000000000000000000000000000..54078277eac5e38f471d3f3cf663021fdc8b760c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01615.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72a4c632cef42011c02ac306878311582c83a046b0aa243ed345e7432196a05e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01620.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01620.npy new file mode 100644 index 0000000000000000000000000000000000000000..c4003a36c2559588c7abe3a1584a3b0e84dd13dc --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01620.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:729100c4637eb489e228d58ac27aa667215b94b0a002072dd255f5a775aa8f24 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01625.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01625.npy new file mode 100644 index 0000000000000000000000000000000000000000..fec15f1950215004afccb1aae0ade0444dcaff90 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01625.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5663aec545b031a2c4096dcfd8b1067f110b4afd94b994d7c1c25960bfec2e1a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01630.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01630.npy new file mode 100644 index 0000000000000000000000000000000000000000..65208b40ce7e34f52541b69d3890e54bbe8d2462 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01630.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73819fa81c60bf24f187c360d7507d3f986d7564a338c065a7606c423b09f18c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01635.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01635.npy new file mode 100644 index 0000000000000000000000000000000000000000..24879dbce3fd126d3d598caf1a324d848a08e933 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01635.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fdfba4f7025b479a7481c1145145430d7507d4bfdc9ed54c40794a114c38582 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01640.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01640.npy new file mode 100644 index 0000000000000000000000000000000000000000..24ada70432de22a199c11877e598795f0d2000a6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01640.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea92403cc8706f41583a6d89aca04b828094441f72a04d75e8ff2d11da2abde1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01645.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01645.npy new file mode 100644 index 0000000000000000000000000000000000000000..64bc7d316946fa154c921658abf08621fbe3c5f0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01645.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecea00069a356c1645a4a6d2ee7312bd7377ac83d4fe6e8fdadf16c73999f9ae +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01650.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01650.npy new file mode 100644 index 0000000000000000000000000000000000000000..0662141c7c2cc3861c56143d51a72adb66b540b5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01650.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5ac14c13be954110fd43383854424ecdfb0a7b419afa1a3b7a2727adcdc34db +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01655.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01655.npy new file mode 100644 index 0000000000000000000000000000000000000000..32c6a7ab3586bd12efde206f3f013f6630170288 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01655.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7398112564aa320edbf1245edd3f402be5ad9e6aafc5ab32c3b3f9bf929f6fa5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01660.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01660.npy new file mode 100644 index 0000000000000000000000000000000000000000..8524665fcece95fab87348a41e6db53ea72affb1 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01660.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04110ef477df8b43cbabdd3919ce82354f4b811e788db00bdd547d77fbd526b0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01665.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01665.npy new file mode 100644 index 0000000000000000000000000000000000000000..eb7afc123b6aa336beb67975e112e5b8a3672185 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01665.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c8608455dc3b5d0a408ae7fcc34478ea457c3d599ab347ebd9ff2468de8f0d7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01670.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01670.npy new file mode 100644 index 0000000000000000000000000000000000000000..4451889e00a07cd5e18df6d01c90fc1ce4daa768 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01670.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df02942967325c72899323edda05a75d5883c6a25620d442c8e792a8ebaca1df +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01675.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01675.npy new file mode 100644 index 0000000000000000000000000000000000000000..83d93ec1ca77bb3e9f96ec440b241abdbab04a5e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01675.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff77c315c64ab597e94b3dedb137da96b6058ae5b2780021ebeb6b0ba2a36475 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01680.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01680.npy new file mode 100644 index 0000000000000000000000000000000000000000..df121519999fe5f641b9502047f89dd88063958f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01680.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:326e265150a46869a43fccfdcd1a0e14a445f55e6b4c744c04e752cf1e6c0181 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01685.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01685.npy new file mode 100644 index 0000000000000000000000000000000000000000..5024e9f807b003e951a3e025ab412bca8372a826 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01685.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:925159f3bed50dfe92c553f01890ac0723d66f9993030d73c49086f2d2078f5e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01690.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01690.npy new file mode 100644 index 0000000000000000000000000000000000000000..62f6aafd41e7c154f3c4d70e567bd6a9cb5c49bd --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01690.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a297e3357dc65167a60bff60c7b75dfd666b5fd24473d82e778c8a9d00c35059 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01695.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01695.npy new file mode 100644 index 0000000000000000000000000000000000000000..d1667d1a7fa362dca589dec05c8c6e1ae5087515 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01695.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6a3918c98d9cba33c2288cade7df8d196f52ced023d9851e9a97fc894e1002c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01700.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01700.npy new file mode 100644 index 0000000000000000000000000000000000000000..39ed297ad94c1779d12dd71201c01724dea1a78b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01700.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c6077e5f6ada47ec8ab4240035db016a6cafd6c9a8274322aac2b2fbfb64d5b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01705.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01705.npy new file mode 100644 index 0000000000000000000000000000000000000000..355115690fd39bc010293a92664f3f9f8c6e71c7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01705.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fceb9fcd05884eaca8180edfa9a0c46cae9d1b88efb15915808ff76dc43037cb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01710.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01710.npy new file mode 100644 index 0000000000000000000000000000000000000000..5fb048a347ded7e8fed7ee226e6aef50ca193eca --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01710.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52dfd13f69ad0ac642ed4855c5df0f1288a5da01d3f8ff5a14d3b160113834be +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01715.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01715.npy new file mode 100644 index 0000000000000000000000000000000000000000..d9af4e5e163e3942a0cad088442a89c1573c56f5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01715.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e8e251b15b83cb6da4ac12826a0d1747429d4d76964afd619150a208a0a32c9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01720.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01720.npy new file mode 100644 index 0000000000000000000000000000000000000000..43bbcc675b4a79939fc5904511aec3ed774cf436 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01720.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84e0cee925fe3a6ea16011145e92cc5e50dbf35a6bce8cdcf87ac4472581c740 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01725.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01725.npy new file mode 100644 index 0000000000000000000000000000000000000000..63f00200061fd4d93e2fa8eebdc3968dad3f4070 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01725.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae2b9a78fc8879b2bd88491bcdbde30d661fd2f41e1eca0dcfd2031d8668ed5c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01730.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01730.npy new file mode 100644 index 0000000000000000000000000000000000000000..82989c07f79a9fd7214aaa1d330936f3aff411d6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01730.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b9cbaddc356ec63f54372012d19a64a4a3dd78d8b33bc6c5211c8c76cc56bd1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01735.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01735.npy new file mode 100644 index 0000000000000000000000000000000000000000..f44d4ede7534393f4f9166f6bdaef6053b59d58c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01735.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b70e13c850ceca344b5858d268a055f1d98df460bb778fcc6a06cc17f309c3e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01740.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01740.npy new file mode 100644 index 0000000000000000000000000000000000000000..5beba50c759bb527ad50848ad21e0de60a19a001 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01740.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1c704abc3a6855bee5313f5d69587f6429c74714b1bdc0e9330bbfb27e20fa8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01745.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01745.npy new file mode 100644 index 0000000000000000000000000000000000000000..49c130f3bf75d23d3817d3f25416f9255181aa2a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01745.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:253c00a2b2ebd5574ae54c5f0c9496fabbf3b29ec6f840e83614db848af6d8df +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01750.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01750.npy new file mode 100644 index 0000000000000000000000000000000000000000..6335b726b1e7feee4af261d3fbb3a9247e0fc886 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01750.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e168411e05053447cd198ce3db8600698953da3b44f61437f3b561a960ebcd7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01755.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01755.npy new file mode 100644 index 0000000000000000000000000000000000000000..b9d00ea5f87c23b7ffb8baf6c1c15fcbee40a85b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01755.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c8f6573fc993646f751be91dc70f0adc9e92640e079a29d5db7d16294d05996 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01760.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01760.npy new file mode 100644 index 0000000000000000000000000000000000000000..466591ae4adf5b0ee947a49ff31196d674cb0954 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01760.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:501a9c422a38e5c3143deca4c6f6864ee163a6f91034762bc074afabf2b56393 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01765.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01765.npy new file mode 100644 index 0000000000000000000000000000000000000000..7f330383053a1ba047b6de32dbf2b5bc61603ce5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01765.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4efd866f1a80055a666cf604e5a63507f0d0f14f06a23e0c8edb7e97d1146583 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01770.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01770.npy new file mode 100644 index 0000000000000000000000000000000000000000..161f802ae0bb9fd6d10cc0e64ed94cba2b9070ca --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01770.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c877ed5f7a15e71eed49dfe35022127f8ce68083044fc07bc124e7982ca7e66f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01775.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01775.npy new file mode 100644 index 0000000000000000000000000000000000000000..c0bd6ef6e1b8f36b2ac740b524a560f5ad87a767 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01775.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:def41e3eb82f7823c690a097de2b77bcd0a411a2ba214ae2e8ad45f425718464 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01780.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01780.npy new file mode 100644 index 0000000000000000000000000000000000000000..f55d151fe18e06093a7b31b4b2a5ea2eacf0e8f9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01780.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26edb872ffb77c9d6577bb4ab9a017758c4e3b90a9f744deeffdd714a6e5254c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01785.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01785.npy new file mode 100644 index 0000000000000000000000000000000000000000..bb1b238eeb64a2bdd527f88f64af156680ddd909 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01785.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff18cfc5ab822e2d1b2069f511569cd775fdf2a2d644ecf0be38f04c9a789c0d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01790.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01790.npy new file mode 100644 index 0000000000000000000000000000000000000000..c5a9c46bc6106d4097edc661c30a4dc51a690083 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01790.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdd307b6db5691b85892c9136a84d14a357a1976a18863a8a686bcd14857c9b5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01795.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01795.npy new file mode 100644 index 0000000000000000000000000000000000000000..198f733e56a2cce8a1fade0b90acab868614177c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01795.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02a1ecc77d87f035075968ec97b58362d11786d4fc3dc1b8732f95d5f7a6e503 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01800.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01800.npy new file mode 100644 index 0000000000000000000000000000000000000000..c851982d92fca0ef5c58c574142d0f455f7c9062 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01800.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a9ba150a3972778f815956ea87587ce5ae733f34b5e50df01941bd09cb5ea38 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01805.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01805.npy new file mode 100644 index 0000000000000000000000000000000000000000..4bdd6e5ac559c19b2f804d7c205725f788a9c681 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01805.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e769b8a4a35cabb102715ef3666a997ef4771f806e6d7372531686e6e4ae0001 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01810.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01810.npy new file mode 100644 index 0000000000000000000000000000000000000000..da1fa120386d9aa4693f0a59783bd6d1b42a21a7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01810.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4c12d08f7e2ab6254436790c851b10af9cf6082d826947e8388321a6795a06d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01815.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01815.npy new file mode 100644 index 0000000000000000000000000000000000000000..7e4aaf10de47788b5d8364b1a355421185edce0a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01815.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d618f0c81d01348ab49db7fc8a163c63a9f86920291f4e4b46532e428800eec3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01820.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01820.npy new file mode 100644 index 0000000000000000000000000000000000000000..a4a804c8365ba1ae73a0cd10fb0b39518efabedf --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01820.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a336cb0b8a5b3794a4f8a66bb8e08949b48b875c9bdf52b1fa279ceedac20c3e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01825.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01825.npy new file mode 100644 index 0000000000000000000000000000000000000000..324645f8b0ef6b6029d30e61f9d84fc83165585b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01825.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d365da3dca9c7c6fe5636aee06a3761c726c41a6d2ecfef49392233b2b75527d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01830.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01830.npy new file mode 100644 index 0000000000000000000000000000000000000000..e1151a436d1e2bc7acdd84b4ad18de30cef44fd8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01830.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c476b49f0bc6ae46a281da73a84d192614465530d0b80dd51370818862c7d21 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01835.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01835.npy new file mode 100644 index 0000000000000000000000000000000000000000..c1747664a4149375e20064c16026d14202ea58aa --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01835.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fca58d481d324d7c6ba48e8909366a7ba47e056de2a8338f0c7ac1037a3abdc9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01840.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01840.npy new file mode 100644 index 0000000000000000000000000000000000000000..124909823c45bb54ac8569884ce9fa3cd674166b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01840.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0904bb2e4e2842aa379c88324b8538f291ea9c7ca482fb40e1f1f3f5e91b0475 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01845.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01845.npy new file mode 100644 index 0000000000000000000000000000000000000000..80415539e41dd4f0f510cbee7655182a64126188 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01845.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:019fa772a4ff00b8aca7c2480d1af804803091a779cb06f38a1e80e29749a152 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01850.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01850.npy new file mode 100644 index 0000000000000000000000000000000000000000..d687d5c88636d55e9fb4cf3350048257df581aba --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01850.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54ecf4925aa9ffd25127242ddaf35d0199e9e02e2bfb51507aa84cac5ab3f506 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01855.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01855.npy new file mode 100644 index 0000000000000000000000000000000000000000..204dc473656bbd59a065e39cb78a02c41ff011e5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01855.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9be972ce7d6e2860e3b5d0f7a0b2330a3aebed92c7099a0bead06d81f7e4c872 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01860.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01860.npy new file mode 100644 index 0000000000000000000000000000000000000000..bd9a443ad110547d240b005d78739df235b412b7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01860.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a69fd7a1351c4a33f1996a91d3e56bb337095c4e579d40b02c5c5a540e4a7e71 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01865.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01865.npy new file mode 100644 index 0000000000000000000000000000000000000000..764d16b6b520154233178923f8ade2d57b240b62 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01865.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:295f429f19afb2cac32bfe29ebbe91032d62b83489d7c46ef1fa7bd0be235663 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01870.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01870.npy new file mode 100644 index 0000000000000000000000000000000000000000..ea13f176c82ffaa70e5538ef863ff1aa23b5a2d7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01870.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f410ba610d91d1a81210f9760e7c98947c4f5d9a3cb99d33b3390b850ae80684 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01875.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01875.npy new file mode 100644 index 0000000000000000000000000000000000000000..fc627319492e498b511013092f773a89db902c34 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01875.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:103b57fcb6a552bc9a0d0fca31c124558b876b8eb0a893e4bbb30088011330da +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01880.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01880.npy new file mode 100644 index 0000000000000000000000000000000000000000..f070a407ba18f7d46e9e5c0658edd8ad05b4adcc --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01880.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8bdabe8f5900f7bdf6a9b6b1f33c0df17064e5250da5d04e69e03b22a463c86 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01885.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01885.npy new file mode 100644 index 0000000000000000000000000000000000000000..8dc15dc32572d8f4ece5ef76e3dc2ac0ff15f51d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01885.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb049fe6897021f713caaa06351372b748f0f035a08b3a09220eeab6fd7b753c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01890.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01890.npy new file mode 100644 index 0000000000000000000000000000000000000000..c94948fcab5d096ccf7e36662000b11daf8f1be6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01890.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3be549cfbd0e77241fa9f217fb2d9121cd755c7b441a6d29b66866cb2902a4d6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01895.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01895.npy new file mode 100644 index 0000000000000000000000000000000000000000..a0da3612515f8ec3cf286159043d0986a8360b23 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01895.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d751af10f9cde35faf17c55f228e582541c9c39049b2c97911fbda053a8ca220 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01900.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01900.npy new file mode 100644 index 0000000000000000000000000000000000000000..0799c23eaf89bcff71156e57c566a3bfdfc990f0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01900.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:616d9deed2572793dae5ca0fb582d9397039a3bf4dcae8b54a26ea942e94cf8d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01905.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01905.npy new file mode 100644 index 0000000000000000000000000000000000000000..c8df0367c7d4d27615aef2da25fb30b7823ca9cf --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01905.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f562ded6d0e8809fa8c49ac0d9bf12c8aacae6fc3a6bea6dc6eacc9f2f8abda2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01910.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01910.npy new file mode 100644 index 0000000000000000000000000000000000000000..f6a223019f1a6dd0a9531a2e98c4fc3f0911e275 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01910.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:840c2be136fd850989f61aa960bb282ae7045aaca7d3891e6611aca96794e1e7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01915.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01915.npy new file mode 100644 index 0000000000000000000000000000000000000000..c15588f546c9fbe2fd90c1b1d5e80665353c2f36 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01915.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efde0c64202c1315bf3b47c0f5a9f5fe0873af8889e9cd5fc7b0746a6358b2dc +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01920.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01920.npy new file mode 100644 index 0000000000000000000000000000000000000000..93aab23c078b4dbf51fa469357012e5451926da1 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01920.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5880ce03786b4d2021af9810aaaa047c0d3ed6b53e0106bf3f2cd2cbb4725ec5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01925.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01925.npy new file mode 100644 index 0000000000000000000000000000000000000000..9252a569ae0f84512c8aa14261ca7c461795f6c8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01925.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c4fd3808c00a6ee2fce479a153e0e7113b0e4d18aaeaf76984483b01c3a5990 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01930.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01930.npy new file mode 100644 index 0000000000000000000000000000000000000000..1bca5893b58636b79a20d41af2220760fd31c817 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01930.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6455cb1db772679dad6aa1520fe11d9515af8cbfd368844b49e36805922677f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01935.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01935.npy new file mode 100644 index 0000000000000000000000000000000000000000..d2a4bba286dfb8a0cae1dcc7697e1bafc9314618 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01935.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0bb407fe6d4c0c3b98359d2ae7166a1857b1ee047fcb957fb83733da851c1cf +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01940.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01940.npy new file mode 100644 index 0000000000000000000000000000000000000000..3b14889d26050b104c44a9dbee99dfbc8aeeea1f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01940.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adc4aab3d24f7208a9879f1421dc4bb9814d31ac5928e8a7e0dc2130908f1deb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01945.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01945.npy new file mode 100644 index 0000000000000000000000000000000000000000..59a1493132c081f88cd9597633a68febb86745de --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01945.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3c0d55b9ab2b5658ff75d9601a88aa92e0e003e66ba28a10daabb2602de3bb8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01950.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01950.npy new file mode 100644 index 0000000000000000000000000000000000000000..c5421bb2c77b47363bab174d5b4793cf15d79a49 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01950.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a55b096e6696685d99193a4eaf6deb5da9f765887e410095d5d6ea5a6e0afe88 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01955.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01955.npy new file mode 100644 index 0000000000000000000000000000000000000000..47acb22ac7675a2fedd4629d2fd90d71cb6e286c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01955.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3b77409e8524af4095860710675c23fbb25b15b0f91697b5b4e3231a61b4619 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01960.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01960.npy new file mode 100644 index 0000000000000000000000000000000000000000..bcefe634d7680c285299f2a508ad2162b034094e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01960.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:682074d4e4285d57fc95e74575f3df20a8268d49bcc757aea32698d5f4bc4d20 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01965.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01965.npy new file mode 100644 index 0000000000000000000000000000000000000000..9a5226cba01cdc032fef0970ad7b0ac3fa53e56f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01965.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0931a6262467b1c7d2303eccb3bb4be0b18ee0d9339fe7fc6d2c06aa76e92cb8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01970.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01970.npy new file mode 100644 index 0000000000000000000000000000000000000000..126681c820c6f615293402ebcb267c749e71adc5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01970.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18be81ae8bcd0739139f194d5533c3473dc0258b642fd7102e64e3465434cdca +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01975.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01975.npy new file mode 100644 index 0000000000000000000000000000000000000000..0619d8631ceed300fbbd527d3a362077e3ef4b8f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01975.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1412a39680b2541dfb7dc95d020ba58bc6d4f89349a1db60490f5e9254b59802 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01980.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01980.npy new file mode 100644 index 0000000000000000000000000000000000000000..4fe5b5c71a0ae555eb1af57e558c4ae66629511c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01980.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b550d78c0d56a60565d44a35f93bcd14d86cc6721a901955e02f463e5cd6ddd3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01985.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01985.npy new file mode 100644 index 0000000000000000000000000000000000000000..6c7208583f09788a834448ea89b054a7d5c775a5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01985.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7fcd34eb477a382b4052feff79b65ccea1fbdcdccdb2577ce7aba2e4a3bad4b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01990.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01990.npy new file mode 100644 index 0000000000000000000000000000000000000000..a93219818326e7b814ca277e603b26908764cfcf --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01990.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53ff1f9335a8e013b7edf184e6229179e04c47531a0aee16bb0e8896c6a3b1ff +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01995.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01995.npy new file mode 100644 index 0000000000000000000000000000000000000000..aaa80d073d76b61f7397c22f9d59eafd04786617 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_01995.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e00581ade103882b8b5534748f586b89c7a933c8331928cd07dd7a34aa3b139 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02000.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02000.npy new file mode 100644 index 0000000000000000000000000000000000000000..f7dc20f8adff011d564d00deaeff635fd0435d50 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02000.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73a5d507e9361742ce21aab3285a5f7ec5a719b13c227760eb34afd847ec4b99 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02010.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02010.npy new file mode 100644 index 0000000000000000000000000000000000000000..ef4e9c5b561413e3d2846314b2f8b0192b49ca97 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02010.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90db85b2fc130a14c951077f5c4b0bd57e0d9e52b7af8ba18f87c5f5eedd9bcf +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02020.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02020.npy new file mode 100644 index 0000000000000000000000000000000000000000..38b01e392c9f0b0730fe08f7be9fda15ccfac406 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02020.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b2ca20d0733d315ed849c8685d46d2e3abb54f29be1fac4eb52e09e88c11f58 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02030.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02030.npy new file mode 100644 index 0000000000000000000000000000000000000000..056c5bf6288a541847ec100c6291defae9ef2520 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02030.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:295184bbb96f1183a6c44aea98afa56475b41129f760159e8cf825630631b59c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02040.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02040.npy new file mode 100644 index 0000000000000000000000000000000000000000..f2809b4ef7a0a0b6c7fb3e7305937872183be4fe --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02040.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91417daa1b158952d217c644553d260ff84076bc6311eb83c6cdc58e751f84a5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02050.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02050.npy new file mode 100644 index 0000000000000000000000000000000000000000..92c0892a835cb21c4de1aa0d1dda0186bdc821cc --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02050.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7047f4388c935a30c073a39a7d55493f84215dd40e4cb545243c7b683e41323 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02060.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02060.npy new file mode 100644 index 0000000000000000000000000000000000000000..0bd376eb21a74abb421a04809a33eb8e957642c9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02060.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a416435d6c73137e64dc4b20534dc8cd8514f3eb3883194a8a77a28768fdf65 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02070.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02070.npy new file mode 100644 index 0000000000000000000000000000000000000000..5b1fda51b3bc218c467469ecc91b34e46170f661 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02070.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a35d4cecce3eb9eaf3d54047deb37d130dc263e892eb2fc3c1ff18a4c9394888 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02080.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02080.npy new file mode 100644 index 0000000000000000000000000000000000000000..86aabcf4d2f753506de0511b5ac37543e5849a25 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02080.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dcb1678ff4d1543e339c2fc62ddb99a414a275cfcc600fd017dbdf517f7a411 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02090.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02090.npy new file mode 100644 index 0000000000000000000000000000000000000000..ad87e3478d7b0c50f82167de9ba7f433f54a1992 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02090.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d81719bbb364a65c59844c36f21f9cab697c30af9a0fd370c7a66570ca886f0f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02100.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02100.npy new file mode 100644 index 0000000000000000000000000000000000000000..b4cf0a888d718408a72c7be59602a26de36ba2a7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02100.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4389ba218c9283c61c7c35e0d5cc56151a89eec92048f5fb4c4dc9ad11468019 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02110.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02110.npy new file mode 100644 index 0000000000000000000000000000000000000000..d6ea66a8cd9e3958986eb006864561a671cdeb00 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02110.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:539bf6256676b5e723e94d68a52eb689a1875f5785c0af3c7660e16e7933305a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02120.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02120.npy new file mode 100644 index 0000000000000000000000000000000000000000..da1e4523476136aeee3132536b1213c41c5a87c0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02120.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a96135111c619d694131709ca5baced2b789e4b3a071affed80fc605b1e62d1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02130.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02130.npy new file mode 100644 index 0000000000000000000000000000000000000000..9ceb9c99edda3ffebec2a2186859cd71a47053d4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02130.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:988b96ef8a5fd281a5f75fa04c64f4dee8790746c07fe0fb2c96744afd37fd29 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02140.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02140.npy new file mode 100644 index 0000000000000000000000000000000000000000..2e5d8470b8e3add54af508e6ee0b0b14b6eb273e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02140.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2b296b3452abe95a188c48d058dbac0afda32dc6311e179f802acb212596e12 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02150.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02150.npy new file mode 100644 index 0000000000000000000000000000000000000000..7271d08a99fede8c67c2544708c234a42aa60146 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02150.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc38d878311fcfcb03173cda3f444c8eb51f8c8fdf968ffadcde2e55996b0ca3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02160.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02160.npy new file mode 100644 index 0000000000000000000000000000000000000000..d96d8dcbaa8f645c42451c62a0d0455dd65b7620 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02160.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52a032c18922642de61976f06e1433d1d307c04fca7309bef6d8582d1e5301ee +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02170.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02170.npy new file mode 100644 index 0000000000000000000000000000000000000000..7e9f8c27bc8e274d9c9df1b1217d71726ffddfb7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02170.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a07b31e87fa305463a1910e9d2ca768c3c425bafbbf0db640a5f8b91eb1b1dea +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02180.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02180.npy new file mode 100644 index 0000000000000000000000000000000000000000..f2a2516750023cfdfdcb6ed845724c7a2465e367 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02180.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8529e7cf2a020227f4a61f77e06b34a2c309640275c89abeb52683468abb13c2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02190.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02190.npy new file mode 100644 index 0000000000000000000000000000000000000000..e634386a8328afdaeb2044e90909398237d935df --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02190.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:344384ef8b2970b0a28dca2a481dd144ea6839c204878d951496ffe7ce94353c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02200.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02200.npy new file mode 100644 index 0000000000000000000000000000000000000000..794a998a735a97e4aaccc727f29a6e4cb265fd13 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02200.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69a403631ed409c9f31e77257e89a286a87b5690c6808a078c624ce3d0695e99 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02210.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02210.npy new file mode 100644 index 0000000000000000000000000000000000000000..e51194501cf5c2908e1d52250a972d6be358640e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02210.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6b0fb5cbaa469a0bc95c721287b78f255856266c6aaab0af3916ddf1624ff3f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02220.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02220.npy new file mode 100644 index 0000000000000000000000000000000000000000..c58f953be25b69ad04314f3255afa32eadafcc3e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02220.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2df2fa2d5c645993f24f39cf4fb770724877c1f274806368c12aa7ced4eef220 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02230.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02230.npy new file mode 100644 index 0000000000000000000000000000000000000000..21370b874e4df4800f7c8aa5f2855ed3bba627dd --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02230.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2285e2326c0958763ddbe88a38d2533c11f5cfb9e8016661eed30ed66b4df25 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02240.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02240.npy new file mode 100644 index 0000000000000000000000000000000000000000..8cf3f065d85d22be29d4ff6ed0d53c4e9b268107 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02240.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25142eb4f8158aafb03a66e9504f6f757e058b3c086206a055f006815ab488da +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02250.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02250.npy new file mode 100644 index 0000000000000000000000000000000000000000..2b0b67e40d5574ab77abb7f161287b3226d9f562 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02250.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2c6b38370a80ddf4f50bf4b1be50583e6ef4060f8e10bf6d366afaf0dd0d7bb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02260.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02260.npy new file mode 100644 index 0000000000000000000000000000000000000000..96506307a45e363c33c0b4073ddb1322706de05a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02260.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f5b8cdc5ac3375be9fdef992438064a97c1dee1da253a17ec32e5ea801bd41f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02270.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02270.npy new file mode 100644 index 0000000000000000000000000000000000000000..adf63bc2ee6e72cde93329bd79125f6005574d62 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02270.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8516e7652aa5615ba297025ffed01e76f45d8c9158fcbfcfb681aa13ec946de1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02280.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02280.npy new file mode 100644 index 0000000000000000000000000000000000000000..2a515480c1813df1ba5706d2b57f669a18659789 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02280.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c236aba528045910aace2611d350caebd929270f93a439b66387e23d1165c8d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02290.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02290.npy new file mode 100644 index 0000000000000000000000000000000000000000..a45e27210abf69e6ff74f1f7cd55a35881d2b95f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02290.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96070ccde8c3928c06bb879952867e30c686ba98542175d737b395bd3f22d529 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02300.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02300.npy new file mode 100644 index 0000000000000000000000000000000000000000..0d6c2c6328bf0c35ed96eae52e298c0ec5177ec7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02300.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cfe2d3f93c7e51e25373a89a99caf30f312075c8d4dcb426170897efa770ce8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02310.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02310.npy new file mode 100644 index 0000000000000000000000000000000000000000..0bd3f9091a7e093b87685b58ded334e2d89b4c02 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02310.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f0a002bd2425d136e4b5c1455cb731af2b4319d39a05794cc2ebedd17443d94 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02320.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02320.npy new file mode 100644 index 0000000000000000000000000000000000000000..636c991ce18ac2e9f84bdd20fd455b6c555b2ff9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02320.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e7435225aca8090d10a0f59b8e8e48e5e0e7a181e602bdfa7d4cb2e8d4297b4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02330.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02330.npy new file mode 100644 index 0000000000000000000000000000000000000000..64c5318610d664cbd2850cef6c4501525cc84637 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02330.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c66a641f459e7d1846baa7362c0ceb388d31ccf6207630abe85439e40d4dfcc0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02340.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02340.npy new file mode 100644 index 0000000000000000000000000000000000000000..efb9cc70946861115c21766598ef775295d2e296 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02340.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c43e0934c25d51db08583c9eb48dd014b9a82cc0ece97deb03b5461c347637f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02350.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02350.npy new file mode 100644 index 0000000000000000000000000000000000000000..3132ba817de39f7d2ad0235791fb0d3a72e6c463 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02350.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:deb8fbfc9fa1ce6a5af65fc8ba8aeba2362c8558427bf841a4910f3f61d6168a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02360.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02360.npy new file mode 100644 index 0000000000000000000000000000000000000000..dc07c93704e303358e8dd3338217506185c1ce3a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02360.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2e8dfc3f2b2679383fd23f48ae6cb17532ceed3277866fda0c4ad5788b20532 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02370.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02370.npy new file mode 100644 index 0000000000000000000000000000000000000000..4b167faf770fdfd6fd212a9dce0d122edf53ec41 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02370.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b154a04a8e8a84b4845abde9f8c62f3084a7195ec721831b3f7750e10e464fcf +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02380.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02380.npy new file mode 100644 index 0000000000000000000000000000000000000000..1ca721b95a7ede5d2c9c4cb17ccf955ba8405efb --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02380.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3691f83ae1c4855c5d31b123acc5b54df751041ea32a949ebfedb1651dc14279 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02390.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02390.npy new file mode 100644 index 0000000000000000000000000000000000000000..173c7a9be38d590c0fceaa03444835053dc2c9ab --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02390.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:305f2a92b33f924ed9a4ac2aae7c6f5e7618722dde4c0c4c712de628878402e4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02400.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02400.npy new file mode 100644 index 0000000000000000000000000000000000000000..985867689ce29bd214287f641c2ed480785c6209 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02400.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10b67b5ce854a361b9523f38e3fec38332b94892b80413c0956d7a966dcfdba3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02410.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02410.npy new file mode 100644 index 0000000000000000000000000000000000000000..e5e1fbc645e66b8c54b1c058ed5ca5ecb858e5d7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02410.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b72ac40042d591b7a1493566b6cb9a8a28b0a2a015d3942c42f1107b221911e2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02420.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02420.npy new file mode 100644 index 0000000000000000000000000000000000000000..6f16590335a8d21c2294aa57cbaf7ee418c2f7b7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02420.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f38b37681cce8846602c0a02d67ad1f189a281199e2983a8e4915eceddcad072 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02430.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02430.npy new file mode 100644 index 0000000000000000000000000000000000000000..6f7b0dc1c15cdb85b0e268640848be9edd264008 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02430.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:154cd8afe0c957534b570f7fe0cdc42c09d848c704170ad66d1ad8f85de431ed +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02440.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02440.npy new file mode 100644 index 0000000000000000000000000000000000000000..aef967eaecfac2235d572f440e537353be65a97a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02440.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e90d8f44cb5ba67c668ac5348d28372cb07356dde86e692dfebc4e2aa453402 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02450.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02450.npy new file mode 100644 index 0000000000000000000000000000000000000000..30c499fd3d02a054f7d74697f99b5427d7fdd0a2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02450.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58305ab992f54eec19d96211edefa9d2bd0120d9828385b8f472c1581c004ef5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02460.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02460.npy new file mode 100644 index 0000000000000000000000000000000000000000..638c047bb61388191d670de99542684bd59f83e6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02460.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a065d7386c81ece578cae7adc7addaa6a0f474941a779e841f0997eb7cc101f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02470.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02470.npy new file mode 100644 index 0000000000000000000000000000000000000000..7bed65a4097a02cbf0978c06a4d2152ea60fb7b5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02470.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:174a63bc00afd1dc2f8aef5ecd1bd82889f25569d052f1e07f80e480301a736c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02480.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02480.npy new file mode 100644 index 0000000000000000000000000000000000000000..60019f10327f5dae49488b272318dc482d3d584c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02480.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bcbcb30ebf7d128c501a043696cd2ac5c43746c0ac01e976728441387f882af +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02490.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02490.npy new file mode 100644 index 0000000000000000000000000000000000000000..2e462e94fdc2bf7889f9759714df01d708f850de --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02490.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:001860f5a42ad5338111e47123172bcf9a505a881990d412d3d1411bf2364058 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02500.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02500.npy new file mode 100644 index 0000000000000000000000000000000000000000..ca636a017594a09ad1b6025e09eb7ed1f90c17a5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02500.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34faf7e38b0acb6d20750ea9be5bca4530581bd83dfb72bd4c17fc98c82de89d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02510.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02510.npy new file mode 100644 index 0000000000000000000000000000000000000000..8b17dc011ea0cefdfafebc26bff024900b89da2f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02510.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ee4ab0ac83676745efa527efc333f74995ebec0d450d9f2a8c58d547d4fd744 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02520.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02520.npy new file mode 100644 index 0000000000000000000000000000000000000000..631afc5d8a68357980a2ab141a5bb6624d47459b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02520.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11aeddfb21e1a1b308a3e8f27b45cfa9e12c6ec4914c22719165b885ebda59f1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02530.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02530.npy new file mode 100644 index 0000000000000000000000000000000000000000..38b20be81d2c6029fbe9eb4178ee88733663fed4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02530.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f596cdbc4b064446a45806b41c533c1a46ad0b925e76bfc0c5712bdc3e51a60d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02540.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02540.npy new file mode 100644 index 0000000000000000000000000000000000000000..f1672b45a1cce6ea00480d9dcf2e1ec9a65598be --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02540.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:679b654004e6667846a06b35a75a76d98da1eaca5d41ea6886de3566bfd03e51 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02550.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02550.npy new file mode 100644 index 0000000000000000000000000000000000000000..0ff96aaa3a25283fe14981de74f58bba0ae3454b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02550.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09c9c3d2edf740277d2a7f17754c448135ef73b043c392cb7cc360c104f3f3c1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02560.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02560.npy new file mode 100644 index 0000000000000000000000000000000000000000..f7fba1da0a70fc763c3e3aca2870c1dc8ccf9fbd --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02560.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bb1b1c2908b1ff24d7dca8794e19ab0a09baa2e01d27075a8fb61998f7608bb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02570.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02570.npy new file mode 100644 index 0000000000000000000000000000000000000000..916d9b628a64dbade1d0097723b90a3941f5ce21 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02570.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb42b4066a105a1cb2df55fbd7591db8f92a49820fcf7f4313b0fdc492e6948b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02580.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02580.npy new file mode 100644 index 0000000000000000000000000000000000000000..83cf3d2c889762d2c5b5488359f90e1d63474160 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02580.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bfa3cfc1e7b1d967b1bdb38cb30e93f8ee4d749dc79e9b903af071a582ad00d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02590.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02590.npy new file mode 100644 index 0000000000000000000000000000000000000000..7731cb9553762ea538073cffab58d0c63e30158e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02590.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e9e954194a4b8e37b81b4b8d83c02a4a0cea2940f4e04a0253610e50ed1dd39 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02600.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02600.npy new file mode 100644 index 0000000000000000000000000000000000000000..fc2a3f3cbff00e7ae9fcb4284613ce6c0c2091fe --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02600.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1785d5d54fce0cf44216cc224aa38420c80a829d1455999a26b84196e9d2e75 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02610.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02610.npy new file mode 100644 index 0000000000000000000000000000000000000000..a92764fbc5464dbf8899cb89c7a5ecdb18db7a36 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02610.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b7a193cb10899fe40ee3480453cf25c4467dbdd936bb0da70a76387adb254eb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02620.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02620.npy new file mode 100644 index 0000000000000000000000000000000000000000..00b0f6a44669dcb4f19eef1840e52baabea02e6a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02620.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1eee3281620ce067aedd0c8848761554da85f432cd926638578ace2265967ff8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02630.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02630.npy new file mode 100644 index 0000000000000000000000000000000000000000..4bd6605e621dd09944a4e9306d2686bb56b63206 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02630.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:491a08d1d49b54b2cd03ec9cdb3215ed6b9fcde5c9f2133193cb6375673d5866 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02640.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02640.npy new file mode 100644 index 0000000000000000000000000000000000000000..516505b4573d80b588492f63345040c491734802 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02640.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0167bfdc97d101658e27cf47dcfcd88c2f2d7a7e5b17a46a8a9d578f012523e3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02650.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02650.npy new file mode 100644 index 0000000000000000000000000000000000000000..e2f924bd91f13551a5f92f6fd424f553516a2a72 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02650.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c31545752da365a4c18465e4f61acbdc332d9c5790d4503236c3554d3f1c917 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02660.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02660.npy new file mode 100644 index 0000000000000000000000000000000000000000..833fdce88500763401d2f33f0d7f3fa243944d44 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02660.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9f3cbfb30439008b5db5e9bd4868f3c1c99878871d6b36c8219dc2c9bce4440 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02670.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02670.npy new file mode 100644 index 0000000000000000000000000000000000000000..d6227e2e5a002e9a396e9b27491878fc50fcf6bb --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02670.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0c27739b6e1a1e03f6a0b3303f7efb0642efe04c202d5d0a121285686b48765 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02680.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02680.npy new file mode 100644 index 0000000000000000000000000000000000000000..e4ab3fd58ce9c89f201cc2946e95484dd2c4440c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02680.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a2f6dd0def9d81d6390d304f39205394c01966118f091dcf4eeb9716434d30a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02690.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02690.npy new file mode 100644 index 0000000000000000000000000000000000000000..f695e033409b272d7926685147691237658f49d6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02690.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dd16315f538936b925660279e2314301cf9be9aaa520144807ed866202fa52c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02700.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02700.npy new file mode 100644 index 0000000000000000000000000000000000000000..57fa68ab53a378617aa0b4102ecbdc2faee9ccd2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02700.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f226c01b9cc8aa1800454c3bafde78b8ebbb52ab0f6d6e7a817d64560fd40017 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02710.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02710.npy new file mode 100644 index 0000000000000000000000000000000000000000..a4c9364c472a4ec5427323e404a9e6d0f7a2a1ce --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02710.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96e2b0a12dd6262d1ead813d06c97dc6d2d42d16c0525d501617e6db1969bade +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02720.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02720.npy new file mode 100644 index 0000000000000000000000000000000000000000..c02bc888f2c5a059df70b10e15c1b6aabfcfb3d8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02720.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:908308e5e6b6330f1c5d8939a329ccbd5b26862b0160290b6decd961af691a79 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02730.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02730.npy new file mode 100644 index 0000000000000000000000000000000000000000..f46eed3a3454d4f53bcce9625babfa97187d7c57 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02730.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff648c994b4779ea06f5a890ebcb2383d9845fcd89ad64cf166fc0caee5fd1cb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02740.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02740.npy new file mode 100644 index 0000000000000000000000000000000000000000..f6fb7909a253b2fdfb90c767b9c25f4869aa9bac --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02740.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b42d3a099aefc10f893d28809845f1b4dbb8aaf35e3bc706bd9c50fa94f9cd1a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02750.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02750.npy new file mode 100644 index 0000000000000000000000000000000000000000..44175c4e030ed084f61dd861d4a473a3d930f5b0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02750.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96f264d160d853db4ad21844d0759450a9ea21bc0b3a84dcd1a2b56777f08300 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02760.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02760.npy new file mode 100644 index 0000000000000000000000000000000000000000..3b06abb4e9228b0e6523f0a407ae135e41716cff --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02760.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33beee8c94d236b2f456fed1275746ba0dc026179b400b9d226897b000d7e937 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02770.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02770.npy new file mode 100644 index 0000000000000000000000000000000000000000..b3570829cdddc85e81bfde976cdd0cb3a8708ece --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02770.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe21baba75daedb2483133002553f2d11bc9f5d7a9643b8432b13f41b3a9b953 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02780.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02780.npy new file mode 100644 index 0000000000000000000000000000000000000000..d7487aa195054a1ee666d6041f8ac0be4839237f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02780.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bafa642cdc80f83f1f86bf7299761b1712e3e97235a67d0f349bb492f126c546 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02790.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02790.npy new file mode 100644 index 0000000000000000000000000000000000000000..e164eafdad57c88e77e66a9c284e5380bf801e8c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02790.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3351ff214ab87cda0160003d5a458df9805fa30b5755a4127d1fa63828f897f7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02800.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02800.npy new file mode 100644 index 0000000000000000000000000000000000000000..8f1f9c58eca9bfbe5ea836bd48d09043552f71b2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02800.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ee2887b9950ac14c6cb37a54cf8c58f81d31bc4dfe212da54ee042f7d91697e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02810.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02810.npy new file mode 100644 index 0000000000000000000000000000000000000000..f4ed2c43e4a3e2b1fc637dbade24ccbd18965d58 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02810.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42e033639a7e36d00832fbe700b35e57ff8fac9e0f31c3c6b388b1d32e0dbb8d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02820.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02820.npy new file mode 100644 index 0000000000000000000000000000000000000000..73c257bf2763c055fd06aefe88058f6066ef7720 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02820.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:822548f3ee381cce505b7ca2238666befc02a7cfa6473d80d239fb7f52a372e1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02830.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02830.npy new file mode 100644 index 0000000000000000000000000000000000000000..1fc50dc2198a2b78f07f8ef1696e50c37d3ea457 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02830.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c4b938f8651596007e0b6510256e784735b496467eefd2f3e28d1aa2fddec4f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02840.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02840.npy new file mode 100644 index 0000000000000000000000000000000000000000..a8bbb9e954d94d9c182c3d10550fbbea580f8b39 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02840.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59dd4ea6195acdd140fc26097acb23b43df1c19dfa4c803c79dd2a2d2ef684dc +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02850.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02850.npy new file mode 100644 index 0000000000000000000000000000000000000000..7d1b61988524d75dd52e05af2602684c662325b1 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02850.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65a674b8072464fb2f3068931802368e01a2fe3a7c0c39a05b13cd363de08900 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02860.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02860.npy new file mode 100644 index 0000000000000000000000000000000000000000..5c04012fe8bc6f469691f154a3ce172cee2e78dd --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02860.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6d8ea27efb84f276a61a7387018898f2b91b1331a5a0ae8977dd975983dbd5b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02870.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02870.npy new file mode 100644 index 0000000000000000000000000000000000000000..316ee4d0170db426c9b6bfc0cbb07cceba78c3fc --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02870.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c4b48e07b259c61820d6b534dffe6f00a4b1c63df67bf64fc6e4f3ec9f194e2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02880.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02880.npy new file mode 100644 index 0000000000000000000000000000000000000000..798fc843f8afa30820eebd9908df1908053d693a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02880.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2f3afee233b28d0e4bc66909d5bf1809a5d6a6ac49fb34188f46b0cb7e927a0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02890.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02890.npy new file mode 100644 index 0000000000000000000000000000000000000000..2b283ba2687030458dd6ec78f2c7bf2d14ddb783 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02890.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4ae6c385ca60e97eb2d934447b4959e54dc99055b9308a715674fc7aa82c793 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02900.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02900.npy new file mode 100644 index 0000000000000000000000000000000000000000..0927c9436c5008101a9a08a8a55afed1c0a6210d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02900.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72fbbfd1fd0f465651a15ec3a2699523af1ba0df23c943b69561cdceee30abaf +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02910.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02910.npy new file mode 100644 index 0000000000000000000000000000000000000000..79ee02a42f10c76eb4eb313fe2292ff9593c4bff --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02910.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdfa0211ead50ca4bc0817accc937ee4395eb92e9a78a572eec33488899c4ee9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02920.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02920.npy new file mode 100644 index 0000000000000000000000000000000000000000..e277ef2c1c234b8b5e14e7b485fb46e59aef7253 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02920.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ade966a69aa89b04eb43ef0ede7ea018ac86fbe39b4534bd16e4cf082747431c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02930.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02930.npy new file mode 100644 index 0000000000000000000000000000000000000000..71326aceec690c117b3cf8688c219ca89b9eef6a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02930.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6273e78fb8bd608afd96790453962eaf94a7cc913ed701018eb509c3dd1c1da +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02940.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02940.npy new file mode 100644 index 0000000000000000000000000000000000000000..c9e00bd12461cfaf9a5908087ed2a460ac0480d8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02940.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b4f4b11b607df6dd57b31575987c42fc55650ef38151daca8e948db79537bf4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02950.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02950.npy new file mode 100644 index 0000000000000000000000000000000000000000..30c5c3998acfb713267fa26b9be9e12fbe6ed779 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02950.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2299daae8a9decbe6755d2981387e7dac4d404fa35fb7bb084eb50f34f60e346 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02960.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02960.npy new file mode 100644 index 0000000000000000000000000000000000000000..a7f4b837034a669cd3d8e3116c7535ace1668b85 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02960.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c87564c3c66f64ccff0ad0a5dec1baac613735e04807f861af5727650e0b298f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02970.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02970.npy new file mode 100644 index 0000000000000000000000000000000000000000..7dece78f0d0f94bf85ec4d25115ee9d112405b7c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02970.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd31607e08651ffa70c9d278960874514c0fdad255f7353eac7f7f623df85be4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02980.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02980.npy new file mode 100644 index 0000000000000000000000000000000000000000..2b6623502bd41922ba45f9833e95f07de9d2754d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02980.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5db84e9c0961f40ebbcbebc04c08ff3990573e520ac69ca2948719253bd46864 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02990.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02990.npy new file mode 100644 index 0000000000000000000000000000000000000000..469ba3d81e4148bdbdc20eb39745c2bb31edeedb --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_02990.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6893e4fb4d17e8669126189cdd73de620c4581900c4ac6e573c7cc0779d6e674 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03000.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03000.npy new file mode 100644 index 0000000000000000000000000000000000000000..cddeb7e18622e49f3958e25226f977fd0980233e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03000.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8666fa0a385506a2c906aa0441ba7002d40cc1dc7767c97232b5a79e1ac656ec +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03010.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03010.npy new file mode 100644 index 0000000000000000000000000000000000000000..30bfe552267a0f49aecae8d28f6a7eb6ca35a24f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03010.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c38a1d9f5069f962f396ee38b9cec527baa9f6031fe5ddf93028cca28d20a6d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03020.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03020.npy new file mode 100644 index 0000000000000000000000000000000000000000..6f9ee89f97189c8c7fc72baff44948746bfe53e9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03020.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e8f8b9bbce8637b6208513ab8c15effcfa91ccb77e7b9be3c1f82a37f9192a4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03030.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03030.npy new file mode 100644 index 0000000000000000000000000000000000000000..ca5c74d603a19973d23a065a4dfc6fa53198d393 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03030.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97451e57431dbfbd06317feba8daf1e687e97c75317a71552a73bf55d3d1e4d9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03040.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03040.npy new file mode 100644 index 0000000000000000000000000000000000000000..65ef40ec8a8237534ff83f77b3f035675a20f921 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03040.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fd5436a491f1bf449adeb9cda20d25179e375518a0f0455d900f4c7bf9671f8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03050.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03050.npy new file mode 100644 index 0000000000000000000000000000000000000000..1481e1bc3cd821ac2f73ef155d7ff30d7ada1559 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03050.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19cc40ece56520c7319de62a04cbb9c1d26ed46079a28bcbcaac22601b3e0dee +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03060.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03060.npy new file mode 100644 index 0000000000000000000000000000000000000000..484d437cdd021e51c2cf948bdab9b370ea77291e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03060.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:871c581d63245bd5da007a192d7d7103d9cf1dd976c7b427190feef5074b8e65 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03070.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03070.npy new file mode 100644 index 0000000000000000000000000000000000000000..d3e4ad8b24a540a69eb5694746df8dd6d8e1b3e8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03070.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:898a16eef4d91a1fdb72222bc9418e6306966217c5222fd91bc220dff32c9a36 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03080.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03080.npy new file mode 100644 index 0000000000000000000000000000000000000000..f2b50e11d38966d4c30c9daddb05284478139a18 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03080.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f4f6b04f371fdf991698113e465ae72bf27d64c8c54b04f3502c0cec06b6959 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03090.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03090.npy new file mode 100644 index 0000000000000000000000000000000000000000..ee7f9a79356deac1d714b7e258f81d16488932fd --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03090.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bad8ecb026297275d836ed34d8e241a0654319f71e17495979137acd83621e8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03100.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03100.npy new file mode 100644 index 0000000000000000000000000000000000000000..a4fb9e719402ab3cb27b9afc9284d83759ad7662 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03100.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e2209f3c77eca88245a008c3d71b0881130b03eedb1c103035ecde6f6bee131 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03110.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03110.npy new file mode 100644 index 0000000000000000000000000000000000000000..c309c727fc8a5a94e43ff78340a891203f505684 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03110.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ef9c4edf528af57a1b300c3e7f3762337ebb1f7855328324df0d745d30e524b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03120.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03120.npy new file mode 100644 index 0000000000000000000000000000000000000000..db52b948b87b3dee6f1b37f0677f78397e3c400d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03120.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2de3f2505984de35a1c30aee84557fe78c59755ff6849f74c8215e126fad015c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03130.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03130.npy new file mode 100644 index 0000000000000000000000000000000000000000..eecd1de8d20c0d1b996b77ae723414a8574a83c8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03130.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b735deb2dd8f1e82d486b98f50f535f9bf3f7b2d3a473ae54216ba76dc7f2798 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03140.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03140.npy new file mode 100644 index 0000000000000000000000000000000000000000..2cd95a4e6073979ffb33e5c32c439a4d563d8c02 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03140.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a29307c61bd00bf99dd67df68400f65502fde0c3979332422891f3c7004cc717 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03150.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03150.npy new file mode 100644 index 0000000000000000000000000000000000000000..11de8dd59392e2fa3ade35e6c23a91b74488a1b0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03150.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23418ee7ab98c2fa15ba049ba9a994a6de0c96231e842ef0b336c6fd3809c0cf +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03160.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03160.npy new file mode 100644 index 0000000000000000000000000000000000000000..60270ae03b447081ab1b7e5ec1fbd44e304af945 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03160.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:643c9ed070d66eba3c6dcacaaa9a253039878643bb8a6e27487c22ba615e4d5c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03170.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03170.npy new file mode 100644 index 0000000000000000000000000000000000000000..92112a63286cc0e87160f071779173e6690fdbac --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03170.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44135562ced28a3f63e30abdfa602b1fa72aa56cdeb09901ad1dd17bc04bee8a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03180.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03180.npy new file mode 100644 index 0000000000000000000000000000000000000000..eee918a2b5d025ea58d120b49a773aa2f96c957f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03180.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2ed2906752cf965e68fa287c3af5ea6c30012c600bb037a7aef227a823cb460 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03190.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03190.npy new file mode 100644 index 0000000000000000000000000000000000000000..d812f007a5088ae6f2feff4119971139bfdf75be --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03190.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b034d289b51920a701fabf1b5659dbd7b05603870c65d3af649f7007fc7e8692 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03200.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03200.npy new file mode 100644 index 0000000000000000000000000000000000000000..6e5a276a6ea881875455cfb90ad30d50f8b23fde --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03200.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d358f5d4ad1946065acd4e3f5a24c1b51840e0ac4387783cdf089508bf2d1c0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03210.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03210.npy new file mode 100644 index 0000000000000000000000000000000000000000..9b09c30a96105beaab0cd5b9dd5f4a6072c8d7bd --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03210.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95e2155aca65fb8c6f57d00e6fe1844fadfac98edeb24c2c25cfba1aa283d813 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03220.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03220.npy new file mode 100644 index 0000000000000000000000000000000000000000..154da2e6affd683c43e476e2106f64442c98626a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03220.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:836d6b21e55bbc4130b45c2b766536dd4118b11cfb048465cd63214538a68759 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03230.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03230.npy new file mode 100644 index 0000000000000000000000000000000000000000..bb5186d00fcf9f4ec3b39e7cc205701cf0ebc2e0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03230.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c624d96b34b98c2c5577750cdc71e8eb691237eb1e5d488eb39ca813af601282 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03240.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03240.npy new file mode 100644 index 0000000000000000000000000000000000000000..38b0ceb9ee382277a1acf26f7ef7ffb695cab101 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03240.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b192aade6096b4072e555095c873ff842442ff351fad3064a2772c48658cf963 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03250.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03250.npy new file mode 100644 index 0000000000000000000000000000000000000000..dbb980c0be635eb88db618d038e6cdaf5c760555 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03250.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bf127c2d49cb59ef8c240eb65b89588d076b9cdf6dffee8365e4d1fe47adb67 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03260.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03260.npy new file mode 100644 index 0000000000000000000000000000000000000000..6171c92c82a4d634faafe3c4489aca9cd7890c1d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03260.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da30b1d2d7b05957fe960e53aa6b2d050c062e69053a3c9650aa9feca6eeb4d2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03270.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03270.npy new file mode 100644 index 0000000000000000000000000000000000000000..e27eef79569252fdc9964ce3624a3f28c08c6c9a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03270.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f403d4deed083ed1290420674aacfefc5e4a894248ec6f134641a5f6e088924 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03280.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03280.npy new file mode 100644 index 0000000000000000000000000000000000000000..1240cdfc3373f6898afed384cd5c738195f27a0c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03280.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac445d793624c0bcda9156c2d29ab4b7063d176df50462790a0eb95aae072e3c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03290.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03290.npy new file mode 100644 index 0000000000000000000000000000000000000000..0343973ee5bf9dc3dd3edcd4d125aba4ea995ada --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03290.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b25bbbd255a3d15c9f7ee76397f878969098bcc585f7c733fbaeb74db453bf4b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03300.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03300.npy new file mode 100644 index 0000000000000000000000000000000000000000..f67d916ea73bfb161c8433a20a37dff2ad8c69c5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03300.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b38a54de613926c7954c06987636a2de2d425eb4fee4da59dd2d08d97cd0c064 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03310.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03310.npy new file mode 100644 index 0000000000000000000000000000000000000000..2319207a8fb7107765a523c20bf63915b7cc4bbc --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03310.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faa3978bb87b1c40000f8173daf5888db88b11598753566d28a409fa7898f690 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03320.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03320.npy new file mode 100644 index 0000000000000000000000000000000000000000..b165b5166b31754f8718a2d79e4c60e7369c8718 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03320.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d8836a394a8300ab7505fec7fcc1ed670bb621ffa12fa139586763d30cfabc6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03330.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03330.npy new file mode 100644 index 0000000000000000000000000000000000000000..a6908f7ae811a4c3edfe51e9204190745e59c1e9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03330.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58fad98feabf22b3b8c6d821336d6c033056b7b7806f555cb974c08129f88fdb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03340.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03340.npy new file mode 100644 index 0000000000000000000000000000000000000000..4e6ae44f571390dc77646b5b71b29db3d5f23f58 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03340.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d191575f9b13a54cff62bc3bd8a4c18ebd6bb10612646a6ffb1802b55de917b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03350.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03350.npy new file mode 100644 index 0000000000000000000000000000000000000000..192818b8a9d37882745ca2e95c8e1c26b0842e5b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03350.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f65e2fa6b5aa23b32dfcd3d9a214ea82f467e6b982264735d51546617f20210 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03360.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03360.npy new file mode 100644 index 0000000000000000000000000000000000000000..6f49ed2e65beba3bee20a09a9727c2d3396cba58 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03360.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa5f2ed8f96548d34c13c56a99fa396211cdfae251ae334bb41aabb7d5d26651 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03370.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03370.npy new file mode 100644 index 0000000000000000000000000000000000000000..51c31fa1e324dc612fe6725cb7485d72b8df8e31 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03370.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d28739c61c2ec9622308e9d3d3b2d2eff9a76dec5543c2e373cdc575253cc9b7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03380.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03380.npy new file mode 100644 index 0000000000000000000000000000000000000000..90a970f34d97bde0a5b73673f4508eb5b281ddc5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03380.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2253b70089c9cf02e8282a4e36abafea25caa721097e6a96200e8cc5c033354c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03390.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03390.npy new file mode 100644 index 0000000000000000000000000000000000000000..9b9596d4b294d60aeeefafde2e7b49ccfb7b0ddf --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03390.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:539ffa56a10db5e40f86d0e9f3b3ce28d11d8eda5308c436a6b3f3e9e4738105 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03400.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03400.npy new file mode 100644 index 0000000000000000000000000000000000000000..9732e2aedb517339377b5da27289e07e08271e3c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03400.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0658d3c33a4fbf10902ccc5b57ee3ad5a46c12a140da52de3f7a1cdb9cfc4a89 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03410.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03410.npy new file mode 100644 index 0000000000000000000000000000000000000000..19112af8f86afd06535b4330c3b824b2a40ca454 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03410.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d06894f8b6cc45b5ce52b52847c8f3871abd26c9ee3d2ebf62eb3a15ef23fe0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03420.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03420.npy new file mode 100644 index 0000000000000000000000000000000000000000..8d321473539fe0db4f3d249563b4abba2c496010 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03420.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b750091c6bd1866b7ca4f59733238bc56330020afcc6037a0b0881cdabeb1a9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03430.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03430.npy new file mode 100644 index 0000000000000000000000000000000000000000..f1e0c4303b826ab18d0ef211484e05054c3b2900 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03430.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca50467e0c479498f4fe57873d12ffbfb339ec5367624175d90137d4f97e5b4a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03440.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03440.npy new file mode 100644 index 0000000000000000000000000000000000000000..f8b4919110edee76f5fb1b5255f1f4852c2fd6b2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03440.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d5d561d36800d55fce59ed6cc1f43647b26b3c18c1617615c4deb4ab8a80605 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03450.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03450.npy new file mode 100644 index 0000000000000000000000000000000000000000..12655fed174dc62afc322024fbcc824f224ce2c9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03450.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a270b653ee7d696d292bf291e9db24b4da069a878b5732546d6598d11d8a424 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03460.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03460.npy new file mode 100644 index 0000000000000000000000000000000000000000..585a095761a1b667498b7d99d1eeac5fde180a3a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03460.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cfa954a8f3e369c49f028cfba2e24a0f23935a50f25c91c4200f13161cff95e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03470.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03470.npy new file mode 100644 index 0000000000000000000000000000000000000000..2a908f8b94f934e2d8a9df0f303f2dd5a1ff1ff3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03470.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:220c38dd638a67e7615d1bebf8154f3c3302bb561ea6436bdec83a47d8ee9cdc +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03480.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03480.npy new file mode 100644 index 0000000000000000000000000000000000000000..30e0d99eb4e003d910d20f0e235ae6e09400c2a5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03480.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c99654da61b007230c2fb5889f0c134be00efa2d47c6986877680749a2b750a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03490.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03490.npy new file mode 100644 index 0000000000000000000000000000000000000000..d4889d11a8c06b519d1344f3e41ee4240412768e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03490.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22b95bd9771b911a1ef11f83a80d67336e713c8fd77a92e572f10ed4326b265c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03500.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03500.npy new file mode 100644 index 0000000000000000000000000000000000000000..e8dae6d91421bb2ba2468d073a137521ad8536d2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03500.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2c95d66643ebadf0e40a3412d17dbf2142efa1dab9c4198283b53a7458e49d4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03510.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03510.npy new file mode 100644 index 0000000000000000000000000000000000000000..3986d8362d0dcfa4c381486e5b4f1dafad4021f9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03510.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67d7d2e825ae77a6d09dd5f10a35cc1b47a748436108dfddbbe4e1ff2c98d17f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03520.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03520.npy new file mode 100644 index 0000000000000000000000000000000000000000..2735f680fdca18580af2138d69bc2ac39ce7dc49 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03520.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:622ffa1f61a97848e218e2270181c5761253fe5b3234afbff2dd0cd01c60364d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03530.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03530.npy new file mode 100644 index 0000000000000000000000000000000000000000..5e2fb5bbf8af61e40beea72f4164507b8d03f0e0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03530.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e508ba0e3b1681f2d8801b91504de27f3dbf0ab890e3dcd81fc0b64937bbed00 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03540.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03540.npy new file mode 100644 index 0000000000000000000000000000000000000000..77f47635745bd7bf068f76031310d39ee2d0b60b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03540.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a2d6cddf4415fc3bbf80a0819931362f4959dac3d2d468c5e8fcb57f25ce9a1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03550.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03550.npy new file mode 100644 index 0000000000000000000000000000000000000000..63de6c0d19bb5d1dddb72ca8c5b256d36ba4d9d5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03550.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecd3b056a7b853901c3c1102ce2bfdffd5197faea80837aacfd5d94cd0615f0f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03560.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03560.npy new file mode 100644 index 0000000000000000000000000000000000000000..18b20ecfde373c73a524b3c0fd24eaa2eccb03f4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03560.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:323ff0dedc6248a85e40e796d4c3a163dc7e0cf2aefa0dce626b27862e23049f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03570.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03570.npy new file mode 100644 index 0000000000000000000000000000000000000000..d8765fffda56064fdcb9b42b2e74b5fc771b845e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03570.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcc1754954ae820e5aee18c68e34cd7e0c5c643168b981b1552bc1fe7b10466e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03580.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03580.npy new file mode 100644 index 0000000000000000000000000000000000000000..a8fab7db65036227afb1df19a08a3cdd7a814ed4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03580.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2014a791bd32ae434fcb0b8f154069ce05fa032de83c1591da2c1a87a1b1c722 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03590.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03590.npy new file mode 100644 index 0000000000000000000000000000000000000000..d89e496822eaf247d44366b84d7738ce0b9c8116 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03590.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85416c3fc7a200e97b5b9cdfd9dfaaec83bd8f14efd2a1274ab85336be999120 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03600.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03600.npy new file mode 100644 index 0000000000000000000000000000000000000000..1fa48892efdc1fea4b4a04eb459f5803aa74ebc2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03600.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e95a0c6bf2860d75549eeb0cdf137306aa7d22f893aca907610ab32f0054e88 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03610.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03610.npy new file mode 100644 index 0000000000000000000000000000000000000000..3c40c97a6f063d86420e71ef81f562af00bc4b4f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03610.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:584567fe8b63250ac17979d0bac0f31ba5603ba883d86bb6c17def817d4a7f27 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03620.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03620.npy new file mode 100644 index 0000000000000000000000000000000000000000..6602b547673ed89705a6f7271fb7a33ecf410112 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03620.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d21db39a50fa16825aa18d4ed2b23b63ebe68666aa94b8ec310ac0d2073b9eb5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03630.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03630.npy new file mode 100644 index 0000000000000000000000000000000000000000..1d7755a3e00330f2fc893c6feb70fa15ae97b63c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03630.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a831c7014850323f9798a833ddf1e97f9c1c9b18288a1abdb9ea2e532bc739a1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03640.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03640.npy new file mode 100644 index 0000000000000000000000000000000000000000..b9b5edf588a3bcd0ce7d9d3bf4f418d61a16e856 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03640.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c29ba8b3b74e566657d6ee54987fce2b46a43b4b536e451a72f0abd43dced0f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03650.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03650.npy new file mode 100644 index 0000000000000000000000000000000000000000..0163be522abd11b816460124e39b2964c36148db --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03650.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e679a6adf042bd8b1ae91c2dfb3f0d909ae77b899cd2749c26df4f6d040bd1f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03660.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03660.npy new file mode 100644 index 0000000000000000000000000000000000000000..27b2856481ae94594a64c92a2bc52532968e31aa --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03660.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:537359bcbb20e509d2dddbc511d69f7a4f14156f0b3200833b184a112dc0ddd2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03670.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03670.npy new file mode 100644 index 0000000000000000000000000000000000000000..eaac98e40ce627839d7673ad6adc0e1450bbc8d8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03670.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac5426926f42a95e0c7a008d7fa54c89baa5d0c7ea7511e466b43b7af2fcca64 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03680.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03680.npy new file mode 100644 index 0000000000000000000000000000000000000000..f16416b550a15e1875d47fd217cb6a26862fcb82 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03680.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f0bcd965e61f5824082a54f14dc6bacbb62b28db8487f0c870ce114ab9390e9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03690.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03690.npy new file mode 100644 index 0000000000000000000000000000000000000000..5b5cfdce41f2328b931749d8a21c2c55adb1f838 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03690.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a915d61eda9ef0068d08ef7f88014c6b82418687a68563889325174bac83ba7e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03700.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03700.npy new file mode 100644 index 0000000000000000000000000000000000000000..d4fd9db2a49562cad840e279df4cf3d6390f9a0d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03700.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96b6f84b1d81a240de391bb022e962b7e25db30f7cf0dfc8e60fae1073db5fc5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03710.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03710.npy new file mode 100644 index 0000000000000000000000000000000000000000..8747a979926277d9d8a2acc779f35d98d0495594 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03710.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05bee4be79bd2991765b93402766887bae229b933efe72355df5f70d7f7dfe33 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03720.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03720.npy new file mode 100644 index 0000000000000000000000000000000000000000..68e4ac9a23b139ea1e36d1e4a030ba54468fc18f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03720.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf8897ff869d557b4cfacebc6b3e88cd752d3a7987c3444b2e95a85f44c34a13 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03730.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03730.npy new file mode 100644 index 0000000000000000000000000000000000000000..d47d49653e9674546aaa147332616b51910b3a09 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03730.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5529b2ba6c8b09a780ead58588c36069ee790eee59cbdf506ce3e6f4ffd7f690 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03740.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03740.npy new file mode 100644 index 0000000000000000000000000000000000000000..4d15f892f79d5e62fb9d144dc80fc026d9b05876 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03740.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ae0c99ffbce8ebf8e6913bc5e7a8a0d9a6462afc5ed85097f4ee650407123c2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03750.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03750.npy new file mode 100644 index 0000000000000000000000000000000000000000..466170fa3cfc7a801e166af3c8d9deb20457673a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03750.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2de741f0165986bff61d20c1846be6315924271095faa8208c1116715eaff41 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03760.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03760.npy new file mode 100644 index 0000000000000000000000000000000000000000..7febe0e183f65d6df30540681a2978498970f23f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03760.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f211b409834d83738f753ea3017cc5aa2caac0ae62f3dc308ca9f14cb682d7dd +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03770.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03770.npy new file mode 100644 index 0000000000000000000000000000000000000000..0f8e1e347ad8ea616eb8f7c18e84dff177d2daf7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03770.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:468ffccf2c246ecf07314c97f6e1bc3fcbc1c9bb47bc19f736765b1f381b8311 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03780.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03780.npy new file mode 100644 index 0000000000000000000000000000000000000000..9fa3e9f665a2dc5b137a73171c728291bc73af31 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03780.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54ca25fb9d923653d7d9ee962ac8e2e7777ae2b357abb1d0d23d3453f0998eff +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03790.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03790.npy new file mode 100644 index 0000000000000000000000000000000000000000..e2a68eb556afd026fe6846a022d8c584636c9951 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03790.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3098b8d7b1823a541ba6d5c91fbbf3201b32ed1694f3fe33ce704f63017f7c4b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03800.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03800.npy new file mode 100644 index 0000000000000000000000000000000000000000..e894f152d8f3d2477e28534df08b05d3a7e9d364 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03800.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d73a00c548f8782abc71afb9385cb33bc99784e91585fcbd9930cd4f93c16c4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03810.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03810.npy new file mode 100644 index 0000000000000000000000000000000000000000..5f2d4eece2fade735636fd2ecf8f093d5d99004c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03810.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:946a402878673173d6ec0d0fb367e99fd153853f9d5d92db79240b681b220573 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03820.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03820.npy new file mode 100644 index 0000000000000000000000000000000000000000..2b5fd75a026080ca8382e56878b7dfb2a1e23ae0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03820.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fda83c57b1189b074d48c41e06a936e9db408bbc9eb17e22538a3e1f283ac128 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03830.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03830.npy new file mode 100644 index 0000000000000000000000000000000000000000..fdf2a19a3dc6514720e22aa97b398e8c0fad7738 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03830.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9716663c5f55d796942f7c5a5eea98f5f4e0cb27b433e2395a918d6913042f56 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03840.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03840.npy new file mode 100644 index 0000000000000000000000000000000000000000..e7750aa634d8b83c3d1899b8117c897369d7f4fd --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03840.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c956fc7de4212355fad8e867cd625abf539b431bfc465a54b0ffa0710d08b11f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03850.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03850.npy new file mode 100644 index 0000000000000000000000000000000000000000..7db566aa0675fe279e23e295c64124555ef9328e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03850.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e374b347a0e2cbd6808c87e74ca3440fd44130f733871bc5c6067112d56bcb5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03860.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03860.npy new file mode 100644 index 0000000000000000000000000000000000000000..411928dbc50cfff297a96a32a6928f3397d9e590 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03860.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20f52d3ab7de32cfd404e8602f9e118a9cdec80faab908901ce174662cb7ba9f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03870.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03870.npy new file mode 100644 index 0000000000000000000000000000000000000000..671c2cb454f719ad984e78f1ba239eedcb8e6dd8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03870.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb89a1b218f453ca5e21ae257d78b11dae1b39ed2589fb650b3342cc3b100b89 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03880.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03880.npy new file mode 100644 index 0000000000000000000000000000000000000000..82750df6341a5b94d5895fbc8e1f14372b965647 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03880.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14ccc34ac6f3118a0b2cc491004db793394879083e659511d305d57f93ef8c74 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03890.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03890.npy new file mode 100644 index 0000000000000000000000000000000000000000..26574fffd3be0002a2e572fb7473abce759ddd24 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03890.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cfc6509551203f2b373ec4cd711dcda60e08c6cc91ca6702705458192e9a6e7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03900.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03900.npy new file mode 100644 index 0000000000000000000000000000000000000000..0e256fb89bf6a453341844b5118aeec502d95eba --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03900.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d7093babae59490a879a74aedb601d272406698f47d7138867fc7e3f4bf7e07 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03910.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03910.npy new file mode 100644 index 0000000000000000000000000000000000000000..1f96b1c2b6c259adf6f76a2ed815b8f6c77b4688 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03910.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92ab1a55df8672de1ec5831b421605af834041a22b023b3c948f7b2e250d7d96 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03920.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03920.npy new file mode 100644 index 0000000000000000000000000000000000000000..7dfbd5dbb368960bb992164ee01b4addf2b76bc5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03920.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14fa462116155b73c2cd84c82fe12d1bcf6141235f0a5523af929cdc250ce1ac +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03930.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03930.npy new file mode 100644 index 0000000000000000000000000000000000000000..c54ee4b295b3e5ef66bc63ab814cdb877e51153b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03930.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd594545a927fef0f6bd6b57db935848fe4f93c8cfc8b22ca118c8d1b5c9fad3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03940.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03940.npy new file mode 100644 index 0000000000000000000000000000000000000000..19e1370c456d85311ab253e4e2751bad630a76f3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03940.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f355e39d3550dc507778dd6dcc66ba6f428a3e3fda09d81617082c0fac645ca7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03950.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03950.npy new file mode 100644 index 0000000000000000000000000000000000000000..c7ee5d25ba658d703e85faa2eb60c3d8e25ec40a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03950.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bad8fea705b430984a8c82c96cba0f35add0233d313fa1e37eb4adc21918e032 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03960.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03960.npy new file mode 100644 index 0000000000000000000000000000000000000000..07f976b518d3419c03bd8363c648176c67f9782b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03960.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62295fb4ab14a46e58deed42b295d1bc07678818e39a49c76721bba099889552 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03970.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03970.npy new file mode 100644 index 0000000000000000000000000000000000000000..0bd4ebd18098597963ca4dff1b0e98442084d588 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03970.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eeaed12e728ec2bdd7686787027caa02908c70204358392959a00e839b2bbbd6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03980.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03980.npy new file mode 100644 index 0000000000000000000000000000000000000000..28d3e301837d56ca822f808173819e345015fc13 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03980.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1ba8cc0eeb772b4df30931c6418b2c37995d0626dc849f99f39bd578ba700cf +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03990.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03990.npy new file mode 100644 index 0000000000000000000000000000000000000000..4dcfce9eae5bf8e30c2f49254f7eaf2cf05d75de --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_03990.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e82daa47f3632e120244980d70ddde9423df63a69477edfdc57efd8358b76d6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04000.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04000.npy new file mode 100644 index 0000000000000000000000000000000000000000..33f76354957396e146aaf27ad45f84f875cd6387 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04000.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a69d5d8077cea8833724fffb738cc28b7d3a3e82d173e56990279971fd0f08ce +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04010.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04010.npy new file mode 100644 index 0000000000000000000000000000000000000000..dfea060689fcd842ae41e5414a4e81c35f7edf50 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04010.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f18699f6a5ad32af41ae8a4aca302bf840919e632682361f3f8b57000791dfbf +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04020.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04020.npy new file mode 100644 index 0000000000000000000000000000000000000000..ddfa8ca5a89d2f37e3f573a2ec72546ed14a15d7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04020.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c2c4fded25d0658c5e039c82cfe1eefb0b04e105409e1fe2daaff9ce5f83158 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04030.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04030.npy new file mode 100644 index 0000000000000000000000000000000000000000..ca08aa3d59bfe8abba5ad8ce8f30c629d8e40761 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04030.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1f942f6bcb07245fd8dffcfe44cb52e2994d7301d09ef09f71ecae6f0c7d832 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04040.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04040.npy new file mode 100644 index 0000000000000000000000000000000000000000..f35a86c3da8f5f185998bbd936fe1b6f0d1b2778 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04040.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee803fee749975175a07f842abf5ec950e95bdf6843ab7e64fdc05bd470e8f73 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04050.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04050.npy new file mode 100644 index 0000000000000000000000000000000000000000..d89244695a84e114df1c89aa04b0c0b64351b8c9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04050.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0eb366bf13b67f2abc47de9d20282bf1b4d3eb41079f9affee525b685b598f1d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04060.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04060.npy new file mode 100644 index 0000000000000000000000000000000000000000..3c4082048b9cfae507f851a91e5b80940e62c132 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04060.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1af2841965a8436195793d7be3db12d89749f91462ceda46507258583efae930 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04070.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04070.npy new file mode 100644 index 0000000000000000000000000000000000000000..309befb501cce1d52b992459d3ee6b7d1b7ec98d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04070.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e853b1614de16fa59da62c6dd21dcdbd7648a9288e28b9092db5e38ad6a80a3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04080.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04080.npy new file mode 100644 index 0000000000000000000000000000000000000000..c050bc3cf0a4a3b8c17a913bc0754c00bc2bca13 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04080.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b4ce00447102cec62601491208ea95792eccd9cdd094aacd8063b6d416a9a4c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04090.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04090.npy new file mode 100644 index 0000000000000000000000000000000000000000..d1e695a2c273604a29ee4d780f3d9a61013f9962 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04090.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35d0c68c38fcde6f25d94024620740b1ea26bb704d3eaad178a1c7fdde84360c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04100.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04100.npy new file mode 100644 index 0000000000000000000000000000000000000000..d45388b56891febab40a5f67083d9c427d10760b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04100.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f0fd72795e509d2e1f439e0daaef9b6a960b7ff9e8ece2a3384739089cd0434 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04110.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04110.npy new file mode 100644 index 0000000000000000000000000000000000000000..a6abca0bb31c4005ebda323878065da3be016c8a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04110.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fafee1f35f304744913f957c54dfc306c8762865a032aac426a615a237918d72 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04120.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04120.npy new file mode 100644 index 0000000000000000000000000000000000000000..97ee334790927a0564fa275da507bd80d4a14a9c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04120.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17982fc3af01fe119e9a46c3c1c864ee20eb1a43449007c2dcfa00519dd61e99 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04130.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04130.npy new file mode 100644 index 0000000000000000000000000000000000000000..72402d3c180c551c1732184677fdfae468644531 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04130.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90ad1ed2ab2bdcdf22bca539c3f0a53f7976d968766f2eae9906307801f63014 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04140.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04140.npy new file mode 100644 index 0000000000000000000000000000000000000000..dec2e2e84876296811fe742c681b4037e78d2a4a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04140.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abf31182f02ccb10e05f906e9701f3c3bda9498558b8a0a7dc7232e9dea68c77 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04150.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04150.npy new file mode 100644 index 0000000000000000000000000000000000000000..1fa1a53466f9990858e3d247a41b4d9d62025838 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04150.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d698687e50555bf41051e11b3c421cf68efdb75f60945c4351dd82d59cce94da +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04160.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04160.npy new file mode 100644 index 0000000000000000000000000000000000000000..57ff1ffb05effcc6c57066acb3304c48515cc4b0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04160.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffc8cde10c626a1def44f96e3f32f48e036b90063eb5fee65f4a778458a22ded +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04170.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04170.npy new file mode 100644 index 0000000000000000000000000000000000000000..d6005dcb36f835b7eeaecfeda0e12fe7f17cc010 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04170.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a04a0758b9f50ed129e970701a79144fc92b0a1ec2437305953c0ec6698ee22e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04180.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04180.npy new file mode 100644 index 0000000000000000000000000000000000000000..55870ccd01df234c5bb1b5902b5bff3b209c9485 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04180.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0885eb61e30aad38eebae4ee4016d7dd7d15fca9350f707fff088e6f4155908d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04190.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04190.npy new file mode 100644 index 0000000000000000000000000000000000000000..68fd6f494122f4cf6a53b0de46f28ecd9921fae9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04190.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:726c645c2b8fb9cfb8d2ae0071770b8742d9b2a9195075f62a47111385336014 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04200.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04200.npy new file mode 100644 index 0000000000000000000000000000000000000000..849ba307e132861f8d70e96f51280f0a893c0ce8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04200.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79d150e549a087fc6adbf25edfd8b8a07768ecee2e12d988e605d00a598028f3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04210.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04210.npy new file mode 100644 index 0000000000000000000000000000000000000000..65676346455f91243555f7ac243517da6a6dd20e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04210.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:403c05b8c2c98006349c09b8bb579690cf3bc839e54fa4406907ea2b3b0dad4f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04220.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04220.npy new file mode 100644 index 0000000000000000000000000000000000000000..5d64a5e2b3e2e486f14ac89bb689f66cae539dd5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04220.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58d43603f10c25eed8c0b339480f096fff7da6408400bdb86b1295b5c6b52a35 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04230.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04230.npy new file mode 100644 index 0000000000000000000000000000000000000000..abea4fc577222917671c52e31d06384c913d488c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04230.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08d214323f2a543479fd446055a1f5a8d48b7aa9c6a7748cd29eba03cff6ef55 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04240.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04240.npy new file mode 100644 index 0000000000000000000000000000000000000000..0a1fbd2245dc98754decfd71f23759dad005dd71 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04240.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c68974fd035818649108b88b5e29dc403d55110e40491c6363182625e2939d05 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04250.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04250.npy new file mode 100644 index 0000000000000000000000000000000000000000..b08ec604323243109045ee93b36c254bfcef3a77 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04250.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3efac76e5136b81cdcca1e0884fc8da28c3d848897447fc3dac6d50c2bcb1f2a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04260.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04260.npy new file mode 100644 index 0000000000000000000000000000000000000000..3be446efdfa1ae0e149ea06f4494e14ebc75075b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04260.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20e66a8919f7ab67a807a778493484c0c6c2fd3750144380df78f9d4803b2823 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04270.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04270.npy new file mode 100644 index 0000000000000000000000000000000000000000..3d1bf964150fcc5423e9f8d5cf435efc80ab383b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04270.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:912b332633aee329f5a21c00769516dc135de8dc339c013079ff4a99ffed02f1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04280.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04280.npy new file mode 100644 index 0000000000000000000000000000000000000000..a0a2e1c73b5a9d17933584eee5fe188ca80dd7ba --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04280.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d4b13a9d3008f626e1a6b5e2e36c91e0ad80438ce25029208d59226a6c73e5f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04290.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04290.npy new file mode 100644 index 0000000000000000000000000000000000000000..656651d23d5cba411aa377adaa6f871b38d943a2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04290.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:935099ef6c3eb04bf6cb313ee0875efdaa999ad0a4387f7ae115da87ad75d75f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04300.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04300.npy new file mode 100644 index 0000000000000000000000000000000000000000..b4cc269ed5e91ffcd30a173a4a3844d1e4ad11ac --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04300.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97ffc669fecea94cc2a87e134878ab5679f4a3f0266c561759e1764e4fc3a2c4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04310.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04310.npy new file mode 100644 index 0000000000000000000000000000000000000000..7ddf92ccb2f671d03d5d1aff4917d535998b139c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04310.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be0e3139ad1d39c2353bf234faea3e5a567fc839f4783eee2f3aadecf40e2220 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04320.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04320.npy new file mode 100644 index 0000000000000000000000000000000000000000..0fc095123f97e4ca1d75b2bcc3256fa823e9b9fe --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04320.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36e32a90c28346e8aedcac1d9e863400d2dcc3f8605f0780db4a659dd65be10b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04330.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04330.npy new file mode 100644 index 0000000000000000000000000000000000000000..e75dcccd70639ddf4f2f09da0935b41fdcf06c26 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04330.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a254a9309d74ba029e19d2179e7ca1d6d80e93cb12237ae9e91fec73e466612c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04340.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04340.npy new file mode 100644 index 0000000000000000000000000000000000000000..40e69d2619153d3a5e880445b0e5f53ce5699043 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04340.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16830e60fab471b3b3e11179ff89fc0cbb1e912d0c0895eb36aeed09a765d5ff +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04350.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04350.npy new file mode 100644 index 0000000000000000000000000000000000000000..f488c4e337697ebf90e22e68cb5697ebf23c5dac --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04350.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb04c4141f19802bb89440e8172754f8432b197654357ab256840a5214f1d797 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04360.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04360.npy new file mode 100644 index 0000000000000000000000000000000000000000..6bbd9d22417b16134184acce7632868cfc471a2a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04360.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a740c6f1fafe83c1c19ddfc97a6f68a0ce0995a9b3cbe69217948d3fae5ffe87 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04370.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04370.npy new file mode 100644 index 0000000000000000000000000000000000000000..a58aeecf48cf2bcb3338a8e093475fb64fe881c2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04370.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3b2c0306d9370881f1302abf22b87fa1c5432faba7341f1bd0b21b67dff5c93 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04380.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04380.npy new file mode 100644 index 0000000000000000000000000000000000000000..71e4ed7abc039ace705cebda162831161bad6b03 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04380.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:721ff33ecc6c52627453e75181249cc701ef07823d70350cfbf8c55c8f9b666b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04390.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04390.npy new file mode 100644 index 0000000000000000000000000000000000000000..5f988275b691262d9155d9f652fc5f0dd4de4dc2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04390.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccd44efc95f99f982ca6913404cb2bfd17c32b4281e9c105b4aa9ce161c4b043 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04400.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04400.npy new file mode 100644 index 0000000000000000000000000000000000000000..23687f4f2515e1030432f139f092d5d00d290f75 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04400.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c148ee9e16c797b589a70e7756c4c98b978ddc8aca6ac526b77bc441c4954302 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04410.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04410.npy new file mode 100644 index 0000000000000000000000000000000000000000..bfc9e6fd377ec15054ab792fe8a6c551b93d8048 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04410.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b48dc3e5d3679bac031c7e660297a470ad43de42bcd26174f03739d1c8fbfb3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04420.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04420.npy new file mode 100644 index 0000000000000000000000000000000000000000..555e247e4fe9a68e875fff986939c2696f0caa94 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04420.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ea132c5b50a42331a6b4498481ce5ebd1540bfe23e47ce3f7c14c24479189ca +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04430.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04430.npy new file mode 100644 index 0000000000000000000000000000000000000000..0af7933d2c40ec7f1d678afa4bfae6fe9e2255a2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04430.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28853ec92dc2a3a7a0057011eed743cabbfa0b079ea5caa628faab7fce2d44d2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04440.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04440.npy new file mode 100644 index 0000000000000000000000000000000000000000..1238b7bbc719511e8fafeda655e54f5e69a6c97d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04440.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc79e885774f4238bcf7fbd444ef819c84b1dda3518ba42830f26fd1f284fedc +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04450.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04450.npy new file mode 100644 index 0000000000000000000000000000000000000000..69426fb608f6488738014e9c07d0c17115d97c1f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04450.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe49ed3bb92048d319e3f3c76d5a2aef1bdd0e2e44cb5fb952a37d732e21bf0c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04460.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04460.npy new file mode 100644 index 0000000000000000000000000000000000000000..cc40c6a29f1249371facd09b1bb4fdc237d17635 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04460.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6ff57fa5e1d7b20ad6ed92567e2e33c5653ce47960aafaf299111fe10fd9ab1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04470.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04470.npy new file mode 100644 index 0000000000000000000000000000000000000000..83dcf5d497647a5ad5fd2cd5b909dc0e14f08fb3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04470.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c295b14af0af54d03016cd0193c1438d3c3ea471a894c59003934cb84ef4e610 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04480.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04480.npy new file mode 100644 index 0000000000000000000000000000000000000000..2988996c7bfa295a948899109b7581500f12874a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04480.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60dd601c1bf0302ddb46afa3a22a6e7b099c6f415d7ce9dda797b3603e143be7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04490.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04490.npy new file mode 100644 index 0000000000000000000000000000000000000000..d00ae1cf2891bf0b576222083b3a22de9844539b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04490.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a73ccfc13584a56f5b3aa5f8c9afc1c23c98adb9a3a3d1a6fa560cb9a96cc7cb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04500.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04500.npy new file mode 100644 index 0000000000000000000000000000000000000000..4b8c8537813e6b034db08b721496a54de074e4e3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04500.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1c75370a04a0e08c4a5141d11fb7dc1e2aa4a39671e4587815eac6ee36975db +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04510.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04510.npy new file mode 100644 index 0000000000000000000000000000000000000000..c277e0622ccba54af5b80492c5a718695217fbf6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04510.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5310aec0a773c304de3a143829efc32a4971f700512a175898f815e09ed11ae1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04520.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04520.npy new file mode 100644 index 0000000000000000000000000000000000000000..cf768223aa841bd59d812b2521a8608bc3989c4c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04520.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7111de0fd7b2e2ccb45ef80b72fbc1dfb5b604c93531671213c383d263386b68 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04530.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04530.npy new file mode 100644 index 0000000000000000000000000000000000000000..b6caaaf8668e0f4bd1dc2fcb6b08f7c7adc5001b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04530.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bd2a6270d1737cb707fa0434640f75a47e6068ad4981b61e526990fd6d3e386 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04540.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04540.npy new file mode 100644 index 0000000000000000000000000000000000000000..662e0744fa7dcd4b553a57781b505de846b29851 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04540.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3359d867d1350175fe619ac333c48dc8b39b89c007ca47035229b87031ae3b16 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04550.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04550.npy new file mode 100644 index 0000000000000000000000000000000000000000..866996ea1060f894d7584eb20ffad4bc10251e74 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04550.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dabebbcffed84c0d80855145aa1f5da2fb56bb81866e769ea5a6b82e972b3dcf +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04560.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04560.npy new file mode 100644 index 0000000000000000000000000000000000000000..40e18546d04683e06d08212ff308adaf013f3297 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04560.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ea3c34280b3dfaf45f7500808e61d97775e614ba245235d8cd20b33a2b89c65 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04570.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04570.npy new file mode 100644 index 0000000000000000000000000000000000000000..bc5925d4deb949e6e618a3d4803ec4bbd76963d0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04570.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e5f49d75d8d46d66d1d38bd9613f8970dc75907d82b5d30b39368a93b7bf200 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04580.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04580.npy new file mode 100644 index 0000000000000000000000000000000000000000..9887dbcc71857343b122af878170ae721df8a23c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04580.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5380443c0601c1def8fa4c2b1a20aacad982a5612a2e2da87abd6669352313e1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04590.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04590.npy new file mode 100644 index 0000000000000000000000000000000000000000..9d2758cc484b8a51ea7abae7cb449c2394074da9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04590.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe828b19a571f565b9e4f5f300b4175aecffd5cfdd0a0a441b1eaa5aa64711d8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04600.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04600.npy new file mode 100644 index 0000000000000000000000000000000000000000..73c276a210b717ccf312b867f19040fc82279ed4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04600.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43bb48a98f218a5d4fe16d93852d101d5836ccaa44354b4314b489d643501652 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04610.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04610.npy new file mode 100644 index 0000000000000000000000000000000000000000..314a1c2837dab36f96c38eeb1d121d61e9d0cd61 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04610.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24ecccf23225bd9ecd99afb1b6ffb25484de28613130d495ff5b1b298636922b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04620.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04620.npy new file mode 100644 index 0000000000000000000000000000000000000000..95ee01be7146136c1c3d15bfd56305cfd8c70606 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04620.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61c3416d0cd584e29fc5a24c601f6a762691398a49a43056bf18070268d5a2d0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04630.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04630.npy new file mode 100644 index 0000000000000000000000000000000000000000..4a1dcc93cace35c69f645125fff8f01eff8750e4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04630.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43605df548cfb5dee1caf0a932dd729d916a66377367cbbfea871c0252d9d7c0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04640.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04640.npy new file mode 100644 index 0000000000000000000000000000000000000000..a52a077bd148fc2f1936b34811ea63c4411573d8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04640.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:950c888cd7d27ab143eebc046c7bb505e0718e3d43418bf1224592b45f6feaff +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04650.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04650.npy new file mode 100644 index 0000000000000000000000000000000000000000..a742c1e5c362951354f5044bc28872e9f0db60bc --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04650.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:677b2c0c2c999826f883e9e9551d6b59f018138737e26ca5d1ff89d11bb8515d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04660.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04660.npy new file mode 100644 index 0000000000000000000000000000000000000000..62d4dd2b13cdc4488c7f0255f490d408c0ca3f40 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04660.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:481e7c416fccdbd32468959028c18263487e41ae186cd34526f39c0281479c7d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04670.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04670.npy new file mode 100644 index 0000000000000000000000000000000000000000..149d04604ab9edac8cb84aee99717b5986f6058f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04670.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bd21dcc14b5a190d0a12e37515569db7702b6a4ba4cbe88dc7f32310639bf24 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04680.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04680.npy new file mode 100644 index 0000000000000000000000000000000000000000..62b52e9b4f12f38c06a59c4fdfb27aa48cc50574 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04680.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d48de1cb70d536855f74964184d12397b7f69c54d9078cb4150f41d206a16f24 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04690.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04690.npy new file mode 100644 index 0000000000000000000000000000000000000000..f95a1c619b083db91c0b9b7e87a7b960d6de67bb --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04690.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da83e96649fe2602a9802c117405cf9b8bfa75a31e62940b0c01c3939285ff4f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04700.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04700.npy new file mode 100644 index 0000000000000000000000000000000000000000..1d171f40728d295330c30a0425e628a004a3b0e7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04700.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6eaecc7f55c863d02106220c20378ec3d717c66114e157dc9e7a81f2df555967 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04710.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04710.npy new file mode 100644 index 0000000000000000000000000000000000000000..86fd3a23f79b88636f451d920c7a0c35814c9cd7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04710.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:865ebd70da30dcdc177f56fd2142a067082d650d53be9a3f8db1a2b07b62193d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04720.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04720.npy new file mode 100644 index 0000000000000000000000000000000000000000..36cbddc1cb79968dcdb279253ff969310ddb33b3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04720.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:451fb3ea40167328f0c1d4d79d579a886a03bb932d74ecae21e1f2622c611188 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04730.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04730.npy new file mode 100644 index 0000000000000000000000000000000000000000..2ab857d4b23378e6be5180374698f99d84d8eef5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04730.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e92d43a81ae9a4277d70f9089ad8cec6a4e520ba7768cdc44ce04099d0fd8ba2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04740.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04740.npy new file mode 100644 index 0000000000000000000000000000000000000000..216006b64a174e5c08b4cabf7cac88e2fac6dc40 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04740.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:168e1c7b6e0a97c941d65ce3eea0127c80be12195cd5251c234b401027dacb76 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04750.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04750.npy new file mode 100644 index 0000000000000000000000000000000000000000..372d0bed72101f1cf70ebcd142e385524aaa6969 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04750.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:566012c22d01c59a50fcbe137a403242cec9b3a06efde87e4a0c85c0fa75e30f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04760.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04760.npy new file mode 100644 index 0000000000000000000000000000000000000000..29442b6305baee4ef72fafd74235de2e409cd244 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04760.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01b0ae06a1c669f95253afe5e157986b5e956c21c5f794fe467668f02cfcecb7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04770.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04770.npy new file mode 100644 index 0000000000000000000000000000000000000000..bfed5d86945f94c4031e6203cb0e945c40be530a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04770.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ade12a78e1a8c30014b99bc07145ab4ba636b2df42f8de71de6f9e1c94b0d1e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04780.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04780.npy new file mode 100644 index 0000000000000000000000000000000000000000..cbccd9a3704e78132163d91b8bb4ae3a1b8954c5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04780.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:020ae4bf3bba74cd511bdff15cd043f07331e099ced618e77f99c61fa9cb3877 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04790.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04790.npy new file mode 100644 index 0000000000000000000000000000000000000000..5afd7e7c542dae058dd9afd8e9442737f29fda12 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04790.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46049e604bb8414d3819c6139dc046e5a0c24c10515130bd6cbb87ece030a3f3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04800.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04800.npy new file mode 100644 index 0000000000000000000000000000000000000000..476948c8abdf8ee5da3286ad5d605ef35acedf2e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04800.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87ccfb1bdcb05a424bf20ee7dda40b2218e6e950f8e42adba1d63d0cc316008c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04810.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04810.npy new file mode 100644 index 0000000000000000000000000000000000000000..46c620f660117574f090c477f1ebd88c7faec8f8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04810.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f3bfe4135679da97aea6562bd008d8107f9227a1449ef7a69a16e5980658bbb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04820.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04820.npy new file mode 100644 index 0000000000000000000000000000000000000000..9f15b13d47ee8b704504ef13d85006f11bdb8af1 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04820.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1e8ab85227e7ecaf18e70133d79ace32e8e4ff144f115ebdd7ff3b46bf7658e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04830.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04830.npy new file mode 100644 index 0000000000000000000000000000000000000000..b0943cd8575d5603424d437f7ae2e5a9ef4c7d93 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04830.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:947dfa6305b47788f0e3e54809f981b7f2973371d9bde0c4c57bed934e5b5ed8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04840.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04840.npy new file mode 100644 index 0000000000000000000000000000000000000000..523ec721401e72ea10890eda71ff050d2fc4a99a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04840.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04f18c4c68c6982e9a4237afdde1716cc0582faf7dec68b4a22874dbf96a6f8f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04850.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04850.npy new file mode 100644 index 0000000000000000000000000000000000000000..75781835a6ab86161fd1d6471346a41936ae29ca --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04850.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c73dd4705ba402edb76e6a5b41d19caa8b3272c9e757ab3252125b23c71bbdb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04860.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04860.npy new file mode 100644 index 0000000000000000000000000000000000000000..7f9683c7f5f53d5f719fc68aa01f732c1810b1e4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04860.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d13983066f0e25ec85de98af0c87d8cdb7e1633b5d1357f96dfdc49d1ca61a0a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04870.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04870.npy new file mode 100644 index 0000000000000000000000000000000000000000..a7b92df3fa7a2869a96e6cce8f77e0b16a0f6120 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04870.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98b5c96fdfda82b849326646fc118e2480aca56a0cd111a45220aac5e31b481f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04880.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04880.npy new file mode 100644 index 0000000000000000000000000000000000000000..c61810d404fb671139a0a2900365dc5521e4e51d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04880.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:927385aff647c3bfb9930b1e672c6add4da36295e292a741dcf22d02e8921ce4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04890.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04890.npy new file mode 100644 index 0000000000000000000000000000000000000000..2a5b123045e600a81c206c4ddb83ec2c8a9163d6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04890.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88c454b9f90700b1eecbabcf5c677d820540b8cea9e94509a6e8e4318099b095 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04900.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04900.npy new file mode 100644 index 0000000000000000000000000000000000000000..42f9d134a1fdfb4cf293da4e1dd5f0d5aa6e5c2a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04900.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c591ec621493b7b4155f7dd7d7e0bf8750346d221e81c5ad4dcc2c08d8620245 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04910.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04910.npy new file mode 100644 index 0000000000000000000000000000000000000000..2a7c0d58efa5a28b5f12ee4192d9d5a4ce108a3a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04910.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0eaa3d5047645406165fc8532970393c0054a5c79869f1a2097c8057848b61d6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04920.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04920.npy new file mode 100644 index 0000000000000000000000000000000000000000..b2386342150ffd048bc10a670bae9416edcdea3f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04920.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09c74769861f51f54cf9cf6ec1b959a8adf1ca766d9b6b0619b3a1f9c1ca011d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04930.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04930.npy new file mode 100644 index 0000000000000000000000000000000000000000..2b40028f9cd67fbf3c63e7b7270c35d5297b03f8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04930.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dec451a346519ba141bfdab0b68eb5a4ad0d3ad0574888338c88d14b2bb8db78 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04940.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04940.npy new file mode 100644 index 0000000000000000000000000000000000000000..3b7e363f535803dd23fe71bcd697f734ab714cf3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04940.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:819a46d7cd102108ecef57ae4b05f32d1346808a5432a98c7afa1c784b0a25d1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04950.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04950.npy new file mode 100644 index 0000000000000000000000000000000000000000..54dbe4d2cbf802fa41142dd0e0fa8f188e2fad0c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04950.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:badd1a30efaffca6a0cf663844545cbecf950c16b3cb50365d69a3529dc3c144 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04960.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04960.npy new file mode 100644 index 0000000000000000000000000000000000000000..dccdf484edb0bd81c7d6c416710fd09efd0f7af7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04960.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92e39e48bce18669b100a26eb432396233371b9474ce0809fff35cb28229dd7a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04970.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04970.npy new file mode 100644 index 0000000000000000000000000000000000000000..58ae87558b86e561049d5fc4c49b0e03e60287de --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04970.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a15e8773d506eb44110f8cf8b0a3c2523e1ef4fe729d45126d6e91fdb77903b7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04980.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04980.npy new file mode 100644 index 0000000000000000000000000000000000000000..ec735b2cc2eae51e10beac9c405b290049712b72 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04980.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1a8764bbdcde69a0d9233cd5882c4145c157544e28a18abf022c83d592c1fb7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04990.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04990.npy new file mode 100644 index 0000000000000000000000000000000000000000..0a2825100b3e0ba09e6971e37016da9bc68e7945 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_04990.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4160c3ed987cf2c1dcdcf42e494d971dacd5af0a723b10db3106bec7006f7381 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05000.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05000.npy new file mode 100644 index 0000000000000000000000000000000000000000..e5e041fdf9853dff4415f324d6caba150f90192e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05000.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fb7ae5b6fcaaddd750997d42197e03ef13fe91cc3c2de2f2e20f5e9fb508179 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05010.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05010.npy new file mode 100644 index 0000000000000000000000000000000000000000..777773e6ab23fae850dc0c3dc851f465b4d292d2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05010.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6d120df1363879dea798892dc3dbf77092934ea8ca43b01e806b79c16a05343 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05020.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05020.npy new file mode 100644 index 0000000000000000000000000000000000000000..ab195cf7f758c8278901141f16f6e81d1c188dec --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05020.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78f203a8bf0d366cde98097f3255768fb9d473878cc423ef4cc1a0f64fe3d141 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05030.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05030.npy new file mode 100644 index 0000000000000000000000000000000000000000..1384c9e7c5da3a0fb2668cc83b1bc1b13979d1f7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05030.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d1341552b6fa9e933142078d845c480186bca1e3dfff22f1bc260272b395794 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05040.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05040.npy new file mode 100644 index 0000000000000000000000000000000000000000..73546332fac0393a6fb332b240592fe473f00884 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05040.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faf6ebb9eb1430675bd925de0675fb272072949b02b99949b39fc31a2d7f75d1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05050.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05050.npy new file mode 100644 index 0000000000000000000000000000000000000000..918973cc14c58517891ba9a29956a2d611fe8d75 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05050.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9c62c58731c96ce53e636cee33e7ec850cc36d48fbb2dfedfa3154f887e97d3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05060.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05060.npy new file mode 100644 index 0000000000000000000000000000000000000000..aa1fd71129a27f57925047f2c539397f092af9a2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05060.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fba68558470f5cc7dedcc1d54288c10c8818e73693ba70ebe69ec3a42976137b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05070.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05070.npy new file mode 100644 index 0000000000000000000000000000000000000000..565c80eb6239d566e48c64c0842474ba0b1e5183 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05070.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a0c19a5630b74a52e63fe5faf1175ede515e7a0a9e432c5bc431b546aae9a33 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05080.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05080.npy new file mode 100644 index 0000000000000000000000000000000000000000..4f6aea88c6a0315935d698dc090f281772286462 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05080.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75510744a5122b1aad89fa29dfdcfdebf66594f4e2f99804f9984f9e6b79b3ed +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05090.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05090.npy new file mode 100644 index 0000000000000000000000000000000000000000..a32280d08e3e93f5a6cd617f8104724959259408 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05090.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:496f8df29c52120aa740a05db729272f03c89c701af2099df9917ca727ddb9c0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05100.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05100.npy new file mode 100644 index 0000000000000000000000000000000000000000..fd7476f119721a4d2b514d38226ea5ebbf90c2cb --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05100.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f094fa92389bdb504b83bc63b51d4d2a45eeb5db74f5631629becbaa286bd5ff +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05110.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05110.npy new file mode 100644 index 0000000000000000000000000000000000000000..bd28a5ca204e0ce7f9d274cf552313addf812aab --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05110.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:848c350b054da56a81d98e4fafc0c048ed4da28bdba56198c327e12a35443de6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05120.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05120.npy new file mode 100644 index 0000000000000000000000000000000000000000..19b1b86a7e1221409570528c1ae2458eb52fb1fa --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05120.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3b18770b27320a7976da27a959cdd76ee2f9e3de2e5184b6999d13a9da16944 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05130.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05130.npy new file mode 100644 index 0000000000000000000000000000000000000000..07b867b1d57f526936f39fb945766f14d530a08e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05130.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c06edae98b9e314715fcf7a660191ca923048f04654c0c0964410b18b5a97fa1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05140.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05140.npy new file mode 100644 index 0000000000000000000000000000000000000000..1daaf6d546b067eb3af99b97f1608c9168d73309 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05140.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa0f18ce7fa88e469460b198d5670c3cd3f4933561ad80f355691e0315a80bd1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05150.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05150.npy new file mode 100644 index 0000000000000000000000000000000000000000..0ec7a926ec29016796cc67a7d1bf4490e5586aa7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05150.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27c32473fcc21291d44e7763f7840add9f111e7b39932b1dc2ed59f8e4ac6c47 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05160.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05160.npy new file mode 100644 index 0000000000000000000000000000000000000000..e7384d11146b1eeae61ba77d73d278aca54e1e5b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05160.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86b052010df1a9cfb2f64a0598456ae734fc9bc02b1b6755d632196c7e87c3b0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05170.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05170.npy new file mode 100644 index 0000000000000000000000000000000000000000..f076c441db4d9fd44869c451c1068d8345cd2ec2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05170.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c9cfe1bbbaf427788898ee53fb849923413088bcd53ece76913f6833f5421d1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05180.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05180.npy new file mode 100644 index 0000000000000000000000000000000000000000..b9d844eb23ba616dc0a4bc3663c23217a67cc7de --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05180.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8567ed682e931196fc44e7f2bcf48ae384e05f02e31ce0a33e71318a20fea577 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05190.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05190.npy new file mode 100644 index 0000000000000000000000000000000000000000..aba9e2b86c3a7290e027cea6a56e4583adda76b5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05190.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7ef5587f42a76eb16773add3110db6a98dbe215943b677c08dde74e0f504c18 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05200.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05200.npy new file mode 100644 index 0000000000000000000000000000000000000000..0dbfb0b5243365c95653b1cb24acae4eed8d0ead --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05200.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f29327394bd55c11d9d998b9dd95ced69dfebe8c43a4c268648fa33c40d79ec +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05210.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05210.npy new file mode 100644 index 0000000000000000000000000000000000000000..fed556901d4b0c21df05a7fedd520550e5e2ba67 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05210.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ab329316235ca19d9042ac338bb9ed22695ed6c15cba1d3cc607b81ce2ffbab +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05220.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05220.npy new file mode 100644 index 0000000000000000000000000000000000000000..26b54ccce9611868287378e2c96f1acbf6d2022c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05220.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6a9afd71039122ae5e2b874279d1244bd9d066f515327d98fab116137840233 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05230.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05230.npy new file mode 100644 index 0000000000000000000000000000000000000000..8ec91cc1e3b3b3e55f4bf9eed9677334464d9854 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05230.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8896fa763f47974467383d972f89e3812f4329cec7368eec2039f98b47d8f396 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05240.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05240.npy new file mode 100644 index 0000000000000000000000000000000000000000..d2ae1e61a32a83f0787fa36d2f7b63d6e3ea2a59 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05240.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:244b62efa6fa4a0a72f57b13feb22aac9b24ae9b976a7c89a1f356c7f2071912 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05250.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05250.npy new file mode 100644 index 0000000000000000000000000000000000000000..7bc5027fe54999dc7ce7c2f8f42e5084f399ae2d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05250.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ca3b10ab2b02e231a0c33e6850ff52f86dff203c5fce4b7112b3f47737857cd +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05260.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05260.npy new file mode 100644 index 0000000000000000000000000000000000000000..cb0fc21e23e3672f5978db30995883061e02af6b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05260.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19aa01ab858a5da76e1074e7deee55a27d6aec00929e029da461f992c1d82a5c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05270.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05270.npy new file mode 100644 index 0000000000000000000000000000000000000000..84cb59c259aaa414aea60064cd04484cb0ffa0cf --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05270.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdb17c42150fbcd21fec41da27725611c0d73ca1c90a283ba5fbf8364ab09a30 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05280.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05280.npy new file mode 100644 index 0000000000000000000000000000000000000000..871050595d318908797638c77bf1627e746961df --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05280.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d7d028fab9d3af8f8030ce46d7f0cc1523d0f83d13237e99a304f9f2807c230 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05290.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05290.npy new file mode 100644 index 0000000000000000000000000000000000000000..0a1432b00c580a653e3bd73893890e8ee1ebce21 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05290.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a69acfe8bae9be8ec347d90e7af7473e81d689d4f3247c9e505a092d9534d96a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05300.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05300.npy new file mode 100644 index 0000000000000000000000000000000000000000..eff2a847e16cec1f379f7ea6bfaa4dea239ff6ac --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05300.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e58682d6b6c84398c6b78bdb3e2619a5570a9a616f53ee5ec720799ee89bd3b6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05310.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05310.npy new file mode 100644 index 0000000000000000000000000000000000000000..9f3f15354eac25c06597c7416435b700033285c7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05310.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce1dce0b90c0406d8ad9cc98bb0b84a83f06c22ddc8b4b6ef78b053d126c5fd2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05320.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05320.npy new file mode 100644 index 0000000000000000000000000000000000000000..b522d0cbebab9d239c63470183631a1c12ee2278 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05320.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7044a2091512c3eeb72346bc512c8258b01b868f4f66074c9173c7daf479c459 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05330.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05330.npy new file mode 100644 index 0000000000000000000000000000000000000000..5f4383f9d0f5fe60fd8c6f9c4b7717954423fb12 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05330.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f4cd3d7a0d17330242656db1f63253b0afcdd15c9b1fb0caba4dc58c38452c3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05340.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05340.npy new file mode 100644 index 0000000000000000000000000000000000000000..79f17311eb0ddea0b558e3c1fedae3e4ce50857c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05340.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:865f20efe1f31e3e8d924eb83ca3d8341d7c18ffd4fde35b43d27a9e95bf15b0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05350.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05350.npy new file mode 100644 index 0000000000000000000000000000000000000000..334da07487a216b2762b48ae73a650962eae67fc --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05350.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8457d3cdc03647404e5209380a3a3bfd365e9289f431146c23ffbd1ca5798956 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05360.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05360.npy new file mode 100644 index 0000000000000000000000000000000000000000..c18e11fe6a1e9667635b77332cc3823de4814e4c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05360.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f562761bed2a7b9ee2fa8ef513d18c8f6ae5ecf8810f96f1651484cd60c6e984 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05370.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05370.npy new file mode 100644 index 0000000000000000000000000000000000000000..313c7d01147b19ccef62b53a26ab622c41a17caa --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05370.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89e18b7111cdc563c7793f5d668565472c6a7815e26bd73729f9370f6d34957d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05380.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05380.npy new file mode 100644 index 0000000000000000000000000000000000000000..4013dc85b849cb05a05e90b45c23036847e6b9d4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05380.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5b4cc8982c1dad35d1b05b9dc3577c1a6854fffd94be01c64ff0e9270cc7d20 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05390.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05390.npy new file mode 100644 index 0000000000000000000000000000000000000000..5fc60352ffbaefa92406dfa449361edf51466194 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05390.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5aff155f03fb05162d4b93f90b4b232f7568c38dd0c497854f41b65751b63a42 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05400.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05400.npy new file mode 100644 index 0000000000000000000000000000000000000000..aa7433c1e62b059ec1a7e029b6de177314ecba28 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05400.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2967918565838523737b6c7fc0ba1373b9d4ec39e87d6d1a36c870a9bc588b00 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05410.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05410.npy new file mode 100644 index 0000000000000000000000000000000000000000..b9525fdae732dd3fd6d9d8ec74596afede695d08 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05410.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:419762d78d367d1a2001bdd2f462d901cef31faebfbbb69452e109af17d25744 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05420.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05420.npy new file mode 100644 index 0000000000000000000000000000000000000000..4c16ab8e4fe453a5f369c1ee6bae40a30c23be35 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05420.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65f8132210ca767b1f418348cf8dc4a87973218b0033279d188a07177da4fa05 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05430.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05430.npy new file mode 100644 index 0000000000000000000000000000000000000000..7a88ebd064c29aa04599de590bf8f63c4202b240 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05430.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b6f7dfe70bcca96e0960ccd7ecf61cc86e83f8ef8d5639ea25f7829122ef42e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05440.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05440.npy new file mode 100644 index 0000000000000000000000000000000000000000..c9356e1541b7163a96a392f85fa21ad42de8951f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05440.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afa86aa9bc61ea504e675635917d248ecc66e5a9fbdaa166116f7b01992f6986 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05450.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05450.npy new file mode 100644 index 0000000000000000000000000000000000000000..364a77449399a153883d1874adee6f0fc956a87d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05450.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bbf30330f269ecd706116ece77e424e1e9bdf9b55bf9f624344bc33faf042f0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05460.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05460.npy new file mode 100644 index 0000000000000000000000000000000000000000..757aac0ff87f528abd8a8a1924667011035624f0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05460.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c74441369593eeda5dfe9b510c3444d211f74e484621bddaff5ab009d3032dc +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05470.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05470.npy new file mode 100644 index 0000000000000000000000000000000000000000..e3f8f32fdc8e760188480fb21ff3dab13cf778f1 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05470.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb16fa4c007396a53b7e96cdd978d3a18930b43bd0625fcd563dec70fb4eb614 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05480.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05480.npy new file mode 100644 index 0000000000000000000000000000000000000000..527423c76c0f5605a7c969d6feb837c172395549 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05480.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b7a44a91cf8ef5744ec1ad11c062a3008861d440af4f99cceeac034d12aff88 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05490.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05490.npy new file mode 100644 index 0000000000000000000000000000000000000000..e5afd804369694532d445dd7cd71202bc5a0632d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05490.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4e0a4668ad010727e1be5be08dd059a7eba12cc2e46d5cc1f00a2597f2d5cb9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05500.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05500.npy new file mode 100644 index 0000000000000000000000000000000000000000..d9e53da897caa69c77b4250b78937243577a9366 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05500.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc12220f3118e18cd0725c75171322f0b4e452b568fc443bc91e47f6ebaf43f8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05510.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05510.npy new file mode 100644 index 0000000000000000000000000000000000000000..277b1cc798cfb2428aa36ad4c86a6c8f5153138a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05510.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:340317a89a971a77425a8a1b8ee377d249a2d561820741ad3ddd3f728921efe6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05520.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05520.npy new file mode 100644 index 0000000000000000000000000000000000000000..9e799e887f0b2f839c2049d67696e0d850f9f842 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05520.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:237a966393f2fc2c7d9d829473b424bba21f0531e5ba23e660da926754392eb4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05530.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05530.npy new file mode 100644 index 0000000000000000000000000000000000000000..db1f871a8467b6c1596170109b92bb3aa039832e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05530.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e27b24e98bd493f4cdea5fde4d2a4abdf70a504c27dd4a28b5f1119dec2679c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05540.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05540.npy new file mode 100644 index 0000000000000000000000000000000000000000..2fcf0699982525d91c879c5c37cb3c700d5a4df9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05540.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f47e3ed75b28346be46cf3c5b190b18f3710c39ef773451d0507c00246b93e5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05550.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05550.npy new file mode 100644 index 0000000000000000000000000000000000000000..2717ac1badb7babdfda365ca57756f02fd29e923 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05550.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ec7ac02aa66eed84e2ff6ec6f05c2eb2dd9511f4ac0ad7f46e5dd6ebc6ad25a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05560.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05560.npy new file mode 100644 index 0000000000000000000000000000000000000000..925917587a55e4a8a5bbded3f95ed8d64ff8e435 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05560.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:637660be09f05a367bfe466f85c92d38b084cf4dd244bd63860a627b46ba5ad1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05570.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05570.npy new file mode 100644 index 0000000000000000000000000000000000000000..41e2633fa2370c2ef8bc565984327d0dbc64184b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05570.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68183bf23a8ad925698cd5ae51c9842a2251835651ba31d982c9fa78b5f95d60 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05580.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05580.npy new file mode 100644 index 0000000000000000000000000000000000000000..f91b0adc25c788352eca566daa5f66b9052495f2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05580.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:335b159be9fcd775a2f55868b73e4478061d5c046a5ef33fe7bd5d95b1e13da9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05590.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05590.npy new file mode 100644 index 0000000000000000000000000000000000000000..5d339f3ea6b95440b202c60e4b0cb1dcbf840ed7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05590.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c002be9b95947bacd60ebdfe0bf9d4465e70cc0f517427641606af3dbf3c2953 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05600.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05600.npy new file mode 100644 index 0000000000000000000000000000000000000000..ecf9b945d524570d4577b1a9653816abb7e19257 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05600.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebd79593084ef6dc289c240561da72cd4e3d0fd3cc9781e245a0f5588687c755 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05610.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05610.npy new file mode 100644 index 0000000000000000000000000000000000000000..75fe23bb7536fcf6a45f887d76c9ed6c663b5f54 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05610.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbe320216298dd2e58b6b665a6fb771b54fee4f47fca6e1036573a5674dec4f4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05620.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05620.npy new file mode 100644 index 0000000000000000000000000000000000000000..8d01b8a991448975de49aa556a20b3d463615c7c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05620.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3964620f951f0cd9b59e5ca37918345a3dddbf61afa492c21cddcc25be7fa638 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05630.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05630.npy new file mode 100644 index 0000000000000000000000000000000000000000..4ff58385c0436c5525ec076808e6f40191f6dd5d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05630.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d10b1ae8af0479b489fe4111a4fb7bde947cd141fcf77dea38170876bb4ee5d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05640.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05640.npy new file mode 100644 index 0000000000000000000000000000000000000000..70681e95ea41e7c349e9c0bd1805c0a7c03605ef --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05640.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d79dad7effc8d2069b2753b06ff110e552e4c7515e05793b31333bfccf7fd207 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05650.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05650.npy new file mode 100644 index 0000000000000000000000000000000000000000..af0c2270368dc92aabc258e561ca8ee3e47e8a17 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05650.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b658c4f25532437a0ce73d978815f292443c15364e4c0c47a961f6591abba30d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05660.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05660.npy new file mode 100644 index 0000000000000000000000000000000000000000..b2e8d890d40fc57cc16d402e7d51c503ec27bcca --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05660.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1869254f4ffb0da188a6a89bb00177638fa88ec00d74e0e2a38f045a5c687c16 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05670.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05670.npy new file mode 100644 index 0000000000000000000000000000000000000000..ffc866897c7b42f013c8ddf3b7d3f837e08eb13b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05670.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e06a9c5e1725b95b1822730cc20f2a10a4ff4e7a705f94ea3cff733e8e18f391 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05680.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05680.npy new file mode 100644 index 0000000000000000000000000000000000000000..c05b1416123531dbaa819a61bab20eac46a31bba --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05680.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31c38f05f03dbc98afbe5064c9969cbb0c1cb53cbc084f28ede031aa8da9b679 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05690.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05690.npy new file mode 100644 index 0000000000000000000000000000000000000000..21380b2932c287b7dc7a73040898f72ae7e8db83 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05690.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6c7a50ae9d2a7278137b06227760a5c2f5917a2538181387fd12d4ff6f68b0f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05700.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05700.npy new file mode 100644 index 0000000000000000000000000000000000000000..1e9124ace3dc03ea8b1387c18548326c208d2f3f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05700.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5a6b7ff1229287ce749544bf1b8065f6d3de69e12e40c4d28249811a68ea444 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05710.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05710.npy new file mode 100644 index 0000000000000000000000000000000000000000..4fe92f80589eb02862f0481e7d6425ee8186c75b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05710.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75b464c7b5dcf5b826019d39628073c2dc04bd02a1e03bfd505435c85296106e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05720.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05720.npy new file mode 100644 index 0000000000000000000000000000000000000000..ef2355233adfca98b8ba0efacba9813e9fa6d43d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05720.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49553c998296a4ab527c19f448a3c02145544a4c2e1bcd0dfdd4070e3738b972 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05730.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05730.npy new file mode 100644 index 0000000000000000000000000000000000000000..b9e45df084a0a842f8b3619ba0534c7a81f30ecc --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05730.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2578f88549486450b9d02a1a5629cdc2ababbb26d0d51755275037fb425425d4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05740.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05740.npy new file mode 100644 index 0000000000000000000000000000000000000000..87d2e748694de86e000089a0c142d24876ba306d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05740.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e73225e337c18857fcbeddae1fa58c3d457a4ba13192830a665ef42dd925d282 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05750.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05750.npy new file mode 100644 index 0000000000000000000000000000000000000000..69d6bcc6b70b08f83a3d519a9abed0422f44d95d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05750.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39b3e302286a1a74f3f596bd45a8a82a9a306850778a8e7817bb5c7cc4ec71ef +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05760.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05760.npy new file mode 100644 index 0000000000000000000000000000000000000000..aab258a358003494d7691587a3dec0c3cc90b201 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05760.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3fb5ae826bf1ee506702c7e3cb56e9bee3c95b6fe4cde6dbb1143802748fa5e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05770.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05770.npy new file mode 100644 index 0000000000000000000000000000000000000000..cf4eb52434d23bc340b747db7b81bd3d790396a8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05770.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8dbd68911806b649307cf549654f0eb4c1470e56aea4bed3a65e5c84ea88bfcf +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05780.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05780.npy new file mode 100644 index 0000000000000000000000000000000000000000..23e0ffa5dcefe5ee2b795fc76e4663210972db81 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05780.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e2578c138abb590a983771937f367d4785c2a4585517b511df04ce350e65992 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05790.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05790.npy new file mode 100644 index 0000000000000000000000000000000000000000..b6af55b25a8953a4d9668ff1babb844a2d911bcb --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05790.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfcb0e2aec4f72625faf7c796a31f79328e055e848a0b8a9b707f2b591c439a6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05800.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05800.npy new file mode 100644 index 0000000000000000000000000000000000000000..73fe48178e7096238a9378b30acc7769c71991ee --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05800.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:238b18fb35f65e35ebbfc5c52f6482c2dfb89d8ff3a95948b20be66a932921a7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05810.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05810.npy new file mode 100644 index 0000000000000000000000000000000000000000..8b736ca8afa21bca7edbbeb3fc4818a39fbeeb8e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05810.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:139b861a0d5020bfbf21a1a1f2da12c11605eee55112de74912d859030c51e9d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05820.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05820.npy new file mode 100644 index 0000000000000000000000000000000000000000..36ed4acec78591655286207ea309adf459469439 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05820.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef6a31de1d11a1b0017e5dbf0c06567e1c2bf5de75dedc08797f791eee88f5ee +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05830.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05830.npy new file mode 100644 index 0000000000000000000000000000000000000000..1725351ebe352896cc6a1c2b29997c88d7c0d5bf --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05830.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26f54c33c542b17fd812a9a12c5d005af312b529c87dfda42ab4509dbc538677 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05840.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05840.npy new file mode 100644 index 0000000000000000000000000000000000000000..7511b6b9051bc74c7767c5723e07d9105b81ad7e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05840.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3e6420e0296d55eb4dfd7f15d286816eda6e3b748568a1f07938cdfb63cf09e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05850.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05850.npy new file mode 100644 index 0000000000000000000000000000000000000000..3401e69c25be62cbcf45d4c60846c5c64b9efb35 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05850.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bb68f3d8dacfbd0edda5ba4c6edbc42b55ef0c98e4bf7dfb0dd226b2981f5bd +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05860.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05860.npy new file mode 100644 index 0000000000000000000000000000000000000000..cf366b0b3f93b05880ca2c6d3e46c3b86dac18fa --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05860.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a27bd3b1ebbf455560d9a07cb02925a72a59b568fbbcd49766124b5b09ffe413 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05870.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05870.npy new file mode 100644 index 0000000000000000000000000000000000000000..b53e5c82999ae1415979ea41bf596183b65db01a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05870.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ee7fc808f10d101ed6e4cbce8601f5d7789bd949147110a205efefadb084629 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05880.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05880.npy new file mode 100644 index 0000000000000000000000000000000000000000..038955d8816d92984a08c187ae878f7e4a6a101f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05880.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f3065ee5ba9442dd3e8475fb741f422d9882f1e94e8bba9870f7414f7e284a6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05890.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05890.npy new file mode 100644 index 0000000000000000000000000000000000000000..bf7813079d227ff08546702a8eae77fe0132cdd5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05890.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:384db2d725525e62d2ee1cde861b116cc02dd9d05ed09a3815dab80bdd18fbff +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05900.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05900.npy new file mode 100644 index 0000000000000000000000000000000000000000..0ff4024e3b76ad1c7fe0497381bdafb35ad49310 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05900.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:097a5c2fc9528c1e23675bdded13dd3334ff6f27d2266f47d5f9f50853373a98 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05910.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05910.npy new file mode 100644 index 0000000000000000000000000000000000000000..13a86772356d00eada952daa70afd844fabdc721 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05910.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd6ffee8556473c60fcad09189f479cbe2cf4f8c6d6f3add3e1d6574674ce139 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05920.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05920.npy new file mode 100644 index 0000000000000000000000000000000000000000..c93ab3776896e5c180c01260675050906a6c15ce --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05920.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d13dd22bbf4f4c08023713170f2dc84295368ef02485c2b4faea9f0aed2721d7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05930.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05930.npy new file mode 100644 index 0000000000000000000000000000000000000000..1875c6997a22453525d1120a7d7357ca2e393763 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05930.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:457785e66204726419eaaf14c18edafbec2fe1ad56a6ba65d2d30568469aed89 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05940.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05940.npy new file mode 100644 index 0000000000000000000000000000000000000000..f82c1c1cdc68f11879f7beb932c4b6f2eae61233 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05940.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab58724599433b3ac19754f16206e7446d060e12a9c3be67ab21d9b084ce5014 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05950.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05950.npy new file mode 100644 index 0000000000000000000000000000000000000000..0e5c16e14a84e970bcb39be17edd616b380e38a9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05950.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f079edfe31decd80a6e3155188b4d99c6c06c7016278f97768627adfeddc8435 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05960.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05960.npy new file mode 100644 index 0000000000000000000000000000000000000000..6a1faf02bc4285158d06241b865d471e0f8c19da --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05960.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:296b9e6c015b029a33d2a347db383d78efb5151bef6492e7a9cd36e4127d9b32 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05970.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05970.npy new file mode 100644 index 0000000000000000000000000000000000000000..2bea4046249db4188cdc6fbc006f9bd7b9997eb7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05970.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8394944d1930b54190148d03be88b1f61da6a53776b0ac4f19c84c0415fde4b8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05980.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05980.npy new file mode 100644 index 0000000000000000000000000000000000000000..57fc139541189e4cc13d305dbea536ba1b30c621 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05980.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb6379f3b2be943999e30470011881b4e5cafa6a01f8264f9fe5e66127b9a790 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05990.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05990.npy new file mode 100644 index 0000000000000000000000000000000000000000..71825f6018007a4587d0ad0178c8e3768bdc2871 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_05990.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8556beb42be0b0528437092d3be0365a82de8267245324cabb5a33981f66ad1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06000.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06000.npy new file mode 100644 index 0000000000000000000000000000000000000000..2ce17193cbd15ba7e5245353888d95ae6532607f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06000.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5282c90d6d186921a6fbe16ef885fc38eb3548a8d601e4c68dca24fd877cbe2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06010.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06010.npy new file mode 100644 index 0000000000000000000000000000000000000000..9c67494bd7f17a640860be0f860f95eed746040b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06010.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3469da04b116529e1b52631962ba7db2b2a6506d25b26fb03b906114d9d35d45 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06020.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06020.npy new file mode 100644 index 0000000000000000000000000000000000000000..82b2bcab7f7de86f961e4f6bedc3501c9930d8e7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06020.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53dc71de68522725ba545f6e2ce1e2e2bf11d05685eec48b0a1a2d124c501f27 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06030.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06030.npy new file mode 100644 index 0000000000000000000000000000000000000000..9fc8857f4b23084fe99a9d28e6d036282e24b910 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06030.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75f94aa29862da9a577e594d04e825d6646a8ac9c61d7d8570538489920ad832 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06040.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06040.npy new file mode 100644 index 0000000000000000000000000000000000000000..10cb0a8326210303d327df52f2c8603ed7e0c1b0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06040.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ef8488f4ff0d72d3b21ddcf5b7a8bc965d406e9348531fe5e1b4dee1cffbcc6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06050.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06050.npy new file mode 100644 index 0000000000000000000000000000000000000000..024bb441675063b06f989d92817cfcba2a1da2c9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06050.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfa6c47de90a54560e14ccf049d63621a5a798470d1f4f4d9260ba526e456b4f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06060.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06060.npy new file mode 100644 index 0000000000000000000000000000000000000000..cff6226222a01bc35222da43690247d5481daeec --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06060.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfca1d8295feb283b57e1802023b01581e69c3e75a5dbcb0f52b956b5447ea62 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06070.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06070.npy new file mode 100644 index 0000000000000000000000000000000000000000..f1323a29d72479940659fe925ec76ab94b30a712 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06070.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98ac12ba8406675faf81f3ab0be78f66f07927dfa140a0018305e5bda36c926d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06080.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06080.npy new file mode 100644 index 0000000000000000000000000000000000000000..8b738c31c34b855504f8eca6ee5f00eb9d6aff74 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06080.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:637685a7a969b930243af538876705b2327180ebe6bd654f8d85eb6c8b7e8970 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06090.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06090.npy new file mode 100644 index 0000000000000000000000000000000000000000..d12fa5c5d7e2946497620b10757ded7f6ab889f6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06090.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:159d053fb4cb7df8e7bacf9c51b8db549cb8f9b17aa0123f2e9fefc5ac7ea6c2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06100.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06100.npy new file mode 100644 index 0000000000000000000000000000000000000000..934c43c9aca2481c7c86dd4b977456ad89b13d84 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06100.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:025ee976c1996cb016ef994bb8b53febffd02de1617ffd12943c34ad4c050aa3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06110.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06110.npy new file mode 100644 index 0000000000000000000000000000000000000000..86cc6ce49a28dcb4d923ce09d71aa737e1e2eddf --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06110.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6a71f0d149aab5614af651b199f4c344a6b2956c9cf8acc31613154fadb6d47 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06120.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06120.npy new file mode 100644 index 0000000000000000000000000000000000000000..a790f5f23a4022d3e54ef9a7c6223c5c7f4e76b5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06120.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a3eb833e74130026e347d5a10d5708ead214335d9f87c724317687dcd874340 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06130.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06130.npy new file mode 100644 index 0000000000000000000000000000000000000000..9bf74a5be3f7d93885377b6f950bc5411beab64d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06130.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f41d9a4f9d7d0f52f8ded33211b5af6a8f0fa77302c0d09ed6743f95621eb3e1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06140.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06140.npy new file mode 100644 index 0000000000000000000000000000000000000000..48e2862f1b49cc51fd74fc54c0414a404bb34eef --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06140.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2732cd30f63764245516380aac936bec92a044d31b9c9e718025233c22f5e72b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06150.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06150.npy new file mode 100644 index 0000000000000000000000000000000000000000..4f6b48b288b00a90d935f5b213cd6f8bbc666812 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06150.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f5815cc962ddd8458a0fb19cebcb3e4badf7f829810e5a7c43f477318f52660 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06160.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06160.npy new file mode 100644 index 0000000000000000000000000000000000000000..b1280e4eb70ca958eedaec5c0935539bc1e9cfca --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06160.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d875d7b2b454608c4c49ab4db86072e4f1395650c6930af15da172d1b4337cb0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06170.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06170.npy new file mode 100644 index 0000000000000000000000000000000000000000..a6669beb2cadcd92ee75f2e8d98acb37f03e6853 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06170.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa7addc683c57166f818308f9d52971698471cac2945cb9c0e0cd74291483e23 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06180.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06180.npy new file mode 100644 index 0000000000000000000000000000000000000000..02338f68e414f82200c9f2fadd23813a6bdf79c3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06180.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dde03655d0aece9c2960ec954d033d9f6b669a86d166fb11e9d441731209946b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06190.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06190.npy new file mode 100644 index 0000000000000000000000000000000000000000..af4ec92501ab29cf70df5d6d0beb5b1d4bc96abf --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06190.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc37a70a12c5ba0b231ff279cbe3b39efc22abfecd7d46c4d1e432877008fd0a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06200.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06200.npy new file mode 100644 index 0000000000000000000000000000000000000000..c6b8159ee6eb16aec93e73dc1343acc83a537f65 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06200.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd5db588f66d33dcce1fe6faf8df3cccc337eabf4cce58295ace42fc9fa7e7e8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06210.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06210.npy new file mode 100644 index 0000000000000000000000000000000000000000..6cf873c369691857fe1301bd6720ba9ef157f2cf --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06210.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56bc557069d4d994e7822ecfe99ea4f3e653dd087bbb573ca2b364157c313477 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06220.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06220.npy new file mode 100644 index 0000000000000000000000000000000000000000..39f8f6bba7ecb0b13a35a27d420cf41f1abb1aa5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06220.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2998058cb4528cac2dd7c294cae6580877bcd5e7b61defdf8812113fa9f510ec +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06230.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06230.npy new file mode 100644 index 0000000000000000000000000000000000000000..4c4d770d6e502c64406cbd3fc205f399e991c1c9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06230.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8768c03df88a7a0e25ecdaffe4a0ecde44a1e5bc2c7f307453819e08d3594310 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06240.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06240.npy new file mode 100644 index 0000000000000000000000000000000000000000..871c351e97b664dc3b721a5db363c0ab6150e81a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06240.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58d536a061bb022276ba5d2725c8336120072c71bd698dbce583b4b358d70810 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06250.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06250.npy new file mode 100644 index 0000000000000000000000000000000000000000..8ab71a6568dc446dd1ea4aa3f177627ad7a3a48e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06250.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:935dc9b26f8c28373689bef4cd6a6cab36e04571477b948709a27800583c390f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06260.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06260.npy new file mode 100644 index 0000000000000000000000000000000000000000..f66d4b869fbdc6566fe1054f83e4890f98ad2359 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06260.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c77410eb16db2bd8b77a7bdddc77ba6b2451af328e3198acb78ee1589d3b9ef +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06270.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06270.npy new file mode 100644 index 0000000000000000000000000000000000000000..36c117fcd81e60ecf72db12170e8328b0b9677c8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06270.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57d281831988cbca6935591468fd5b0e183db357afc92a3023c531a532c93fe3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06280.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06280.npy new file mode 100644 index 0000000000000000000000000000000000000000..28ec93f7cfa48dc56b41dc91e217956eca4e9786 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06280.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4bf356134552dfb309b4bd623946f041a670cb9d0e50759c3027d34c0d9d7ec +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06290.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06290.npy new file mode 100644 index 0000000000000000000000000000000000000000..3a6153b3fa194a9c6f39be4a853f2dbe50a5238e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06290.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ae356c4c073a1ef233b64d9730c80f6e72a53e84991c14c6d1c402f86e0a476 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06300.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06300.npy new file mode 100644 index 0000000000000000000000000000000000000000..775fd4e7a9b9360e3842334f0c2ea9e2c1d84d8e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06300.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45776c4a382e442b2c889493c984dbf5dc0c9c1eeed9f316906ff6ff1ea7c501 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06310.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06310.npy new file mode 100644 index 0000000000000000000000000000000000000000..9f97e2cc6e1b6f22483fa6e0ff804697a048206e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06310.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c482e783cf49eaf43da0866fde20c1efbfff2945a08ad0f5c9b8541572f8a80e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06320.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06320.npy new file mode 100644 index 0000000000000000000000000000000000000000..8769b9c4f6633b0aba128ca1f9e046480bb4c306 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06320.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48a25bb950e4b8db69b558219f5bf7a7f393ffdd296df759849b4365e4c66e5c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06330.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06330.npy new file mode 100644 index 0000000000000000000000000000000000000000..82d5aef409bbf205d5b11207babe694e53867564 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06330.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94698727eadaf0ce4f37390045ef06b7fafa2ee401c7bd4cc0cebe1f8237dc6d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06340.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06340.npy new file mode 100644 index 0000000000000000000000000000000000000000..207567c85ae78daf30fcc92e0dc889381bfa8479 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06340.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f1c961657a8f72e2d6e09e746c29dfe05924e53449e46229a881b72a0983db2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06350.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06350.npy new file mode 100644 index 0000000000000000000000000000000000000000..3182df00e833a9db025a9935fdd1e918378a48ec --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06350.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:213599167b743a34e59a1a0457840cd4d7d10c6cfe35f13fe1e97f25ef8a2a4e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06360.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06360.npy new file mode 100644 index 0000000000000000000000000000000000000000..d6bff95f195351a2a41fc80855eb6fede6b099b3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06360.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2103a721244ff262653b1a4a08156e3f3d7f507a1f67977f9aa6801b36151d05 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06370.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06370.npy new file mode 100644 index 0000000000000000000000000000000000000000..b236bc31e62f7661207031ea272e903a042b36fd --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06370.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:869c91857fc84906a045c9a4e704163c86b74c12391f9581569ccf3d6a090782 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06380.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06380.npy new file mode 100644 index 0000000000000000000000000000000000000000..c5795387999de6828a76a701d5cb2e45fc6f938d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06380.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb1c59611a3c70c6778372dc2508616d6518be077c81b4bf7ec8a23b5ec655e9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06390.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06390.npy new file mode 100644 index 0000000000000000000000000000000000000000..2cf069b17378bbeeb1ebc7269d8ba526e1a70654 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06390.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc25e571fef6e14595533c664990d79db1a057e32d3a08bff777f4b510efb58c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06400.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06400.npy new file mode 100644 index 0000000000000000000000000000000000000000..3dc40c3f8af87fd6a8acd79b433bd8907b786e07 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06400.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19a2adec0fbd74c58ce6d45cefbe0a87cb75ba17dcea49b4cf75cda190ec3fc1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06410.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06410.npy new file mode 100644 index 0000000000000000000000000000000000000000..e3b5840fc584bc4225fe31c9b715bb0d327e46e6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06410.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18fca8db50b86382f19dbba0119703f7ff5c72fa536f7b90c5f68f30606a509d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06420.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06420.npy new file mode 100644 index 0000000000000000000000000000000000000000..ca5b1894c72b2ed4fbd1a7909d8121c7c08073bc --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06420.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7a4f5cd2552b14ca2663b203922e5a19d430eefaac84f4a3185aaca25bbdb5c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06430.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06430.npy new file mode 100644 index 0000000000000000000000000000000000000000..68b7ba424fc3fb96e7f3ad1c6518404e71c43617 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06430.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37618edafebae717a93f39fb7897aa070013fecb9b5190fe4a537d94fdd1764f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06440.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06440.npy new file mode 100644 index 0000000000000000000000000000000000000000..6627a5985dce382ecc745fa2a45e8f7e905376a7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06440.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adc8a3e91ecccc38af7e42090504a51fd62d8f8109e057706c4c60592a1650ab +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06450.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06450.npy new file mode 100644 index 0000000000000000000000000000000000000000..0448a7c93f9745997d4d74b01ef0c6f8a25b90d1 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06450.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9484ecafd1d87155d88a57b27dbff916cec92cbdb9e6daffe77bec440cd95daa +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06460.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06460.npy new file mode 100644 index 0000000000000000000000000000000000000000..60b224e9da5e65d1c23d9cd4c221c1bccc46b131 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06460.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:089359da9883e65ea315e70b654f36eaca6c056d6bc4d5aa2d14b7eafe60ead3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06470.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06470.npy new file mode 100644 index 0000000000000000000000000000000000000000..8f4f0249140327b6efc63a4154638849658d562a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06470.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37673f3b710c9550da86615b1eff27bf590651f60883b0be00c8db24bbb25554 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06480.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06480.npy new file mode 100644 index 0000000000000000000000000000000000000000..211e9d6ad9129282fbee0d6740c62e943fdeccac --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06480.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3a86d6ec0ca49a43f2b1f481232a6a687d0f3b9bde453dcee63f4347336cc55 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06490.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06490.npy new file mode 100644 index 0000000000000000000000000000000000000000..0061f54063550e77b675d351f5064ee7aa86205f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06490.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:488b149f16ff68e08808cccd15dc35fc25a6730c77741a64a257300e88583b35 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06500.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06500.npy new file mode 100644 index 0000000000000000000000000000000000000000..1c84e760150d7ca29b216b0d27bd9cc05154547a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06500.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d9afdfaa1962c5c3233d2fb185c246a6faeaefe6f6a8a8b6a4074344b8d7f82 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06510.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06510.npy new file mode 100644 index 0000000000000000000000000000000000000000..642bfbfe944595397172b665211380df1140d415 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06510.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:492055d95e56787dde2561bee8baf97336c6bf0b305138f3158ac39249eb8eff +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06520.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06520.npy new file mode 100644 index 0000000000000000000000000000000000000000..3d290a649cfe23f65b78793fff885c33ced3af22 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06520.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:275db3dc10c4d398ebfcc6c3d66eb4e381ee3859c64cd37fa2b4fc8266b73b54 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06530.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06530.npy new file mode 100644 index 0000000000000000000000000000000000000000..7eca981abe5706243b96220df75f4833d8c8ab6b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06530.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68b90b4eb8897350103b90ddb92a528e71ceea0734b0d5222be9bc7fa70d9daf +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06540.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06540.npy new file mode 100644 index 0000000000000000000000000000000000000000..8daa23183f64ab1b4781b1adaf359c41a9761266 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06540.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b483aac31e09216820c955f8a3d2d508a334136afafb3afc07317236e731105f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06550.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06550.npy new file mode 100644 index 0000000000000000000000000000000000000000..308dcec7c3441a50c42301da3d9e4605a2556073 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06550.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cce2fb6c1cbcfd4b30de41bc8de255c7d0363c1de49df036d676dafa005aa4ba +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06560.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06560.npy new file mode 100644 index 0000000000000000000000000000000000000000..e8ae7a9f9991483eaaacb25eb93c49b882093f13 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06560.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76876071e64ba666f71a14efae6fa28634a8de0b1271a4c518cceeed6f1959ee +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06570.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06570.npy new file mode 100644 index 0000000000000000000000000000000000000000..5aff2e1295622aa27a94eccfc7e6e560227095ef --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06570.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fef696e4ffbff9c078022121c3c7ee2dc7cfc5e4ef7aececa99a90c688b80af +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06580.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06580.npy new file mode 100644 index 0000000000000000000000000000000000000000..7fbbf6c283f7f4c358f9452cfe499ce0558e79a1 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06580.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9739a5d9be1200852f26f24c46b21b8994462e4c9b3fbdbc7d9923fd084dd0f0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06590.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06590.npy new file mode 100644 index 0000000000000000000000000000000000000000..109c2487d8f88c0dfaffe50b3a8e107cf4dd0a49 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06590.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffc64ecf96c20334e960c969d8533fcf56073ef68c361354509025d34bf2cf2a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06600.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06600.npy new file mode 100644 index 0000000000000000000000000000000000000000..d248a28de9d98eca7e665ab32a4a354cdf3559e4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06600.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb1cd34e6930b64accd52bbc3acd0d2e3b7f993bf833193daab11175fdbd8f6b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06610.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06610.npy new file mode 100644 index 0000000000000000000000000000000000000000..7bdca2a307f3f63307d87e39be10744d46594996 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06610.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f643f30ddf678c7c97656a2b693ab4603f4e639e4f353a11e3e370e6432d90a5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06620.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06620.npy new file mode 100644 index 0000000000000000000000000000000000000000..8dfffadd973d715dca7ea4d2702cba659a579bc2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06620.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:779664962130b762981e509d05d2e19159fcb55cd4228f981413ae34f48d4b0b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06630.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06630.npy new file mode 100644 index 0000000000000000000000000000000000000000..51f4da3d0077baacb9951da70230fa870467bd10 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06630.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae488477bbd97909e26460857913e57f9587cced7aa3cdc9ab2f345e6e10dd1d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06640.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06640.npy new file mode 100644 index 0000000000000000000000000000000000000000..739ff63c2aa41ea8fd6806cfa834a3aca4d090d7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06640.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24d08f81d0fdb8bb23fe24c9de75c52f4cb17401e5279fe8a9b1de6652b5fce3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06650.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06650.npy new file mode 100644 index 0000000000000000000000000000000000000000..5868ede50ca89cb5845670aecf3f79f5813ee74e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06650.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7ae0f4412929ca4ddd7a809a4f4ea95b52b0a7350d3d3a8c71b11b7b59d7811 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06660.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06660.npy new file mode 100644 index 0000000000000000000000000000000000000000..e4df01e31da1416288e542d15e234166b8f4aa51 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06660.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f6a00e60b24941d588d01cbc90354c9bcc696080ca123d545740d7475ea4597 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06670.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06670.npy new file mode 100644 index 0000000000000000000000000000000000000000..4d5808f80cd5d4c6e097fb09480eaefdc3b28185 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06670.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75480222b3060e08cc50d4ba8ab9724ff000c44daa1084fb91f9361556b72010 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06680.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06680.npy new file mode 100644 index 0000000000000000000000000000000000000000..7691666c481fff3e6bff5812e497e2b0d8e0a690 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06680.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05805ff5540fa30dbee60884ad04c9ebcadf320f3ffe34643c02f19f8c453f36 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06690.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06690.npy new file mode 100644 index 0000000000000000000000000000000000000000..5a4110e7425e36e8cfeddee9c9b5c8abd0c2ac70 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06690.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11aaac24464cb9c11e095d65d84281be4c19c30f930b6488333f52958d6be6ca +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06700.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06700.npy new file mode 100644 index 0000000000000000000000000000000000000000..c7c3a968d0faf17d4ef90d291d6f54f8b92e1803 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06700.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:822323edff050cb398016b88a38320cadcc1f8c6fdb9627510dcf36a16b87dee +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06710.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06710.npy new file mode 100644 index 0000000000000000000000000000000000000000..9ba916e4ae7304c95120efc09255aa3fdc666228 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06710.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fade4e324017dd0c93215a897878a45490a61aba20af6f04df3b104d16f2c515 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06720.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06720.npy new file mode 100644 index 0000000000000000000000000000000000000000..02098e2ef9625e19f0defed75cdc927dfceec074 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06720.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d479160650983fead98952bd47876cc5b16de14bf15317b3c0f48f34d18208a4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06730.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06730.npy new file mode 100644 index 0000000000000000000000000000000000000000..55fc827db20150f878d227474b297fb38cae7660 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06730.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8701470b33de06d48401256a5b42d307771cd61ccde9f6fddb838a6aa354106d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06740.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06740.npy new file mode 100644 index 0000000000000000000000000000000000000000..7a5a484d801b47ce0094b6ecc7809b067e4ed55d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06740.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:365c6a34a9c103bc09ca4917933c686d3b536bb90a7f184decb8bf352c472fb4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06750.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06750.npy new file mode 100644 index 0000000000000000000000000000000000000000..01958c2e300879e21ad807979c6fb985f424694c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06750.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a9245348b3d025b5da6a399c3585ea6050fd3a1d5f839a0e2bbb686d8989b19 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06760.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06760.npy new file mode 100644 index 0000000000000000000000000000000000000000..ab5636c4c7313f5fe54c7256bf805831c9519b88 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06760.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9f96d3aa90ad215b29a90b94b6c660f635d384c8484fee33fd60287ce3eb820 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06770.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06770.npy new file mode 100644 index 0000000000000000000000000000000000000000..43f0d864fbbedde5c3a5f66ba09467b1f203de45 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06770.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e6d05e56624f2d837f8ff25886ad056c937581aa4054cdc1b1670f6e4623732 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06780.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06780.npy new file mode 100644 index 0000000000000000000000000000000000000000..4518f95ddfb08d237c51cd8a3dc3e5df94bc8c6e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06780.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62c1b3834aca063110e4cdeb670b5a833fff514660cd5466c2847d769506853f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06790.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06790.npy new file mode 100644 index 0000000000000000000000000000000000000000..9449bb57aefb9a1d01b4fd89476dbedf40dedc8f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06790.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0afd3a5c5fa23c1a04e679a22fd56324701877618c9e109078f561c0fcc193c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06800.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06800.npy new file mode 100644 index 0000000000000000000000000000000000000000..8b775d5ac5fb90fabb3662d7f89b620a5fdf7f23 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06800.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01494cefb45788727c40c3d2b093fc96796763a41e51b71a8a1fe4a89bde5dfc +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06810.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06810.npy new file mode 100644 index 0000000000000000000000000000000000000000..df4f433be50b70af49cb346b2316b8fd7c428e86 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06810.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e37cebb746cc30bd87f85dc48e40065321c81befe9692e92363b97f38596070f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06820.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06820.npy new file mode 100644 index 0000000000000000000000000000000000000000..59722cdbfd858b8d1b51a5f024f75407671176b2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06820.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28fdc856c3d4617c623acae28c1f1ec0e2fc9560e1a7e17ebfa5b73146a2a1b9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06830.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06830.npy new file mode 100644 index 0000000000000000000000000000000000000000..8b601267cf83da3d9709702e6baa1741edfded58 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06830.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ed5d61947e6de5e4969512179171ee3ddf1b35b2e1b595f4756debb1ad82122 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06840.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06840.npy new file mode 100644 index 0000000000000000000000000000000000000000..5cbc0ceb8bda90b1d2012728f02645a4c005a870 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06840.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e4a5685b315918846cff1d0f6c7f0f266fd3eb16cab1d988c73e9ee4adaa48d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06850.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06850.npy new file mode 100644 index 0000000000000000000000000000000000000000..0f9967f9acbe2d5d4221995d4d806a392a86c4ef --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06850.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96d71901910a41a617a768eab33e45f1c46d57c0c1687cdfc83c10e4e6cad2c0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06860.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06860.npy new file mode 100644 index 0000000000000000000000000000000000000000..f7c60e06f6dd3ddc47e8da091f630a03c7c2d9b8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06860.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:165f7c9f410d534179dedb60e4314173478a371dddca39f72180ce74b1d0e40e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06870.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06870.npy new file mode 100644 index 0000000000000000000000000000000000000000..84a642ec08c1e3a467736d3efd990b45c25c2ee6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06870.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da5f4bfa17c0dad5bf2d528f100e17b1691591f4a1edb435970af64031f83a0e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06880.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06880.npy new file mode 100644 index 0000000000000000000000000000000000000000..7b89491318ad27d68fbe2340c0dd1fa6a16e2391 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06880.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b477b2978c2ac32b80de084c3c54ff033a7cf2d49337e59879c63ccd0350b473 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06890.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06890.npy new file mode 100644 index 0000000000000000000000000000000000000000..8bcf611488f0a4e9acf7ee34f9f166d6fb33f534 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06890.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8183ec88d6a445baaf01512a62e258be449aa34aa578db65379a682fc25ad347 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06900.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06900.npy new file mode 100644 index 0000000000000000000000000000000000000000..733b820834ca3e69641a9b309ace7875d6c100aa --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06900.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d691015f3ca2d6dc5738a954fde355aa228acdd4c2255084d1a2afca440daa36 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06910.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06910.npy new file mode 100644 index 0000000000000000000000000000000000000000..d2ce366971ffc606fdfde27c7c7f64d2f9b955e4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06910.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22ffb250b71dfc1b072309ee1deedc5d9d09a95a0323ee1784ac9a07ecefd670 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06920.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06920.npy new file mode 100644 index 0000000000000000000000000000000000000000..c3de742fe87b0acf2743365f416b40c191f6f242 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06920.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c205eda9cc93d589b659d1c7f53537427600704c0e888536cb05cf701edeba1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06930.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06930.npy new file mode 100644 index 0000000000000000000000000000000000000000..e4bbceceaeca3eb4adb54c43ff6cc04230c3d8fc --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06930.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:431f769f7f45b944a6ad5e1a062398652082b8e732a42eeb49ac98eac83a63eb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06940.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06940.npy new file mode 100644 index 0000000000000000000000000000000000000000..07ca2cd0e0df700a9253ecd5656d7ae46674cc06 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06940.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f6afdfaedcdfb204b0d0948ff282bfb7d833f17eb836ed0a3ef37fd0ef514c8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06950.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06950.npy new file mode 100644 index 0000000000000000000000000000000000000000..748f7c13b34444748f919d79387efc18388def13 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06950.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d20ba31df547fb658d4e0a72135ea8692e67bddae7751cc1f8c60e6d69e638c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06960.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06960.npy new file mode 100644 index 0000000000000000000000000000000000000000..47a047e3eee588adf3394464979b4891381f0804 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06960.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3755aa626f0eee3f130b21c856b144f03287f038ffddea7c544850a8d83daae8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06970.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06970.npy new file mode 100644 index 0000000000000000000000000000000000000000..f4595ba7d283448ef4147344a0c701026a4544d3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06970.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59af8b6a582a7741a30aa8883d778a43101d1477399ca899642b61ba5426b92b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06980.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06980.npy new file mode 100644 index 0000000000000000000000000000000000000000..e46cfe5760731376a24d656617bc16aa7f0a8678 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06980.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0bf9c5b51d3abbf5c7bbf85ae1ce2993d19587b4bc7e40cf70615eec0aeee72 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06990.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06990.npy new file mode 100644 index 0000000000000000000000000000000000000000..6e91f9b15d291acc3847073887569157c9d6fbee --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_06990.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41525250a5e04c04e5c6a3bdda4129d80ddb3bb6714fe242d8c9a65c106e3f2e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07000.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07000.npy new file mode 100644 index 0000000000000000000000000000000000000000..66c8b803e61e3c75faea4e7eb096865924d747ee --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07000.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d747a2d01538a5a9f116b0dfc5c66223359ee304233143aaa8f538077968bb88 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07010.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07010.npy new file mode 100644 index 0000000000000000000000000000000000000000..d9570588a5c239e22af30590d9d1d49a695856c6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07010.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68779bcd7591df9035a07f2dc8d5536b996a96b4cc4930887d50a9841ff4c0cc +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07020.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07020.npy new file mode 100644 index 0000000000000000000000000000000000000000..8b75bd084a4a7a6e1f57f64cc555cc19ebbbd845 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07020.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a728d7f47b8437f6155c0a58f1eadb531d48c7aa149ea6b3451962ab30fac892 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07030.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07030.npy new file mode 100644 index 0000000000000000000000000000000000000000..4e0b44156310505a385c9478d201744119d1d832 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07030.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d60ba3dedecfa822b46adcff9ef9ca2db4866b3a5d4ecf3ff1221d18cdd56b56 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07040.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07040.npy new file mode 100644 index 0000000000000000000000000000000000000000..6508b3621614b25c546345ff1e4198db8e778363 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07040.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0319d07ea86b6d344d42c9aa686d9bd74cdd800f181b2adf651eac5e7332d787 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07050.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07050.npy new file mode 100644 index 0000000000000000000000000000000000000000..f6117585df02e65f7808c6e25a172ed7139a51c9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07050.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f7c34c2b9012055d2aedd814bf9e491e11850f640f4df00e1275b877b457c67 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07060.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07060.npy new file mode 100644 index 0000000000000000000000000000000000000000..52d14eaa2697cb44e8d01838236a89f0fa74197e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07060.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3aade262e21121783cc169697961597d5aaa6398c00afd4c29fa88a5f38905b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07070.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07070.npy new file mode 100644 index 0000000000000000000000000000000000000000..0220c72c022d49cee86fb705b3e4c560dd62019e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07070.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22c004bba24c9aad44740f41c57fc8f5b58cfca37af752c34c684c38d7009f8d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07080.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07080.npy new file mode 100644 index 0000000000000000000000000000000000000000..4efbc6d12fc6cd3e7da9b833190c89515e0c8e92 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07080.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:530725fa9a04d7d13abf70b4816215781df987eaae25fbfb3d5846d908eabe81 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07090.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07090.npy new file mode 100644 index 0000000000000000000000000000000000000000..14871fd159ec58df579c1313da540bae74844ac4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07090.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a0fd22516f8d66b53a7cfe0679a2fec8dd50c44fa99445997567e1f59de9e89 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07100.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07100.npy new file mode 100644 index 0000000000000000000000000000000000000000..79da6e72fdc766154407a300cf3bf4b8a26be8eb --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07100.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b72322722173fc7e5dd1f44ac85bff08eedeb830ae1ab5c42bae17aac364a211 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07110.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07110.npy new file mode 100644 index 0000000000000000000000000000000000000000..457e2d7e61829c3df70ae0caf99ed9bdcf1f9b3d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07110.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85cd997265fbb05fce46b6d93e81b3315274a3d5137cd9274ac02c21646c320b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07120.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07120.npy new file mode 100644 index 0000000000000000000000000000000000000000..89575a26919d506ca598455c36c2938f910f2796 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07120.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f3e1b552239dabbffd5985673972d3f1d04a056d73eb9799ddf034e4ebfe936 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07130.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07130.npy new file mode 100644 index 0000000000000000000000000000000000000000..32282f377fd7bcf427552bb5a11c11f923e95baf --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07130.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0279138ba21ad51a4ec69dc9ac6bcacdd296a1e92b1c060142f3dbf3b835687f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07140.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07140.npy new file mode 100644 index 0000000000000000000000000000000000000000..4fd127cea982a22534bec59bf4d6e8eeeb017794 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07140.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac40d04af93a07f9ec091d60bf97d4f7c9f500e16e1c55d732da831ca94104b5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07150.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07150.npy new file mode 100644 index 0000000000000000000000000000000000000000..13d54ab5d6d572b2ddac532aac9291bcbc8a82b0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07150.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86cf61b2e5b55ea860632b34923ecc553e282b0c87e658d7c32dac19926db2d1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07160.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07160.npy new file mode 100644 index 0000000000000000000000000000000000000000..b2f2df232e9d3929eacd16a8d17d7b4cdde68166 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07160.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe4c49e20675cef38a3f6ed58cdbb5dcfd362215e256568e60bcf4569030064c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07170.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07170.npy new file mode 100644 index 0000000000000000000000000000000000000000..ecd741fbaa4d6ff6ff2a8375dd2f0989e4a1e549 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07170.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0ea3d193ad8fd270f1a4829dc1e3c3da62fb9c08221a38075ed3ecc3516ff87 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07180.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07180.npy new file mode 100644 index 0000000000000000000000000000000000000000..179dc76e8468ecd4e6356e8fa755de9cbd15d11c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07180.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f9bc41a78eb94d92705009cc93cb6e0f0a5e1dff0369795c7997a0cdd9d9f4b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07190.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07190.npy new file mode 100644 index 0000000000000000000000000000000000000000..d3ffe579e51f10fea34e18290c0013dcd71fafcf --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07190.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d65534fc7b0c33a53562357edc471905c535e2698bc3f8583649ebcb2c826b0e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07200.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07200.npy new file mode 100644 index 0000000000000000000000000000000000000000..145c5f3b7565e0b60262d46a3de78c94e7063000 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07200.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d216258c6140bf926fb262203483feee924e40a4220f9ec28a29437a5acd3ee7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07210.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07210.npy new file mode 100644 index 0000000000000000000000000000000000000000..ff5d3f11902379847d37f3e6c9788bfc5df33cdc --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07210.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b458cdccd69a30670a5deecb5b1879e0c8c89b0042ec57faecc24621e0753a4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07220.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07220.npy new file mode 100644 index 0000000000000000000000000000000000000000..22465fe15ce83f2c5073260f0b946bc12914e3f0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07220.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9947f519af0839c0b6144e4b284bdf2da94046b59f574ff74ad32c56d6a5c156 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07230.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07230.npy new file mode 100644 index 0000000000000000000000000000000000000000..4dc78196c0bdfb38cea4d47902575c4fe69bcd84 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07230.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:942ccd640f91de869eb96c857a301058dacaa4ab52a5bb27fa934f3992c1f414 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07240.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07240.npy new file mode 100644 index 0000000000000000000000000000000000000000..33f9187cdb531679ede0a46af12862b2d39efefd --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07240.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dfeaffb964de56bfeae4a19555a1374fab0103d7097f263955364539b0825ee +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07250.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07250.npy new file mode 100644 index 0000000000000000000000000000000000000000..df569de40c7fadd5f19a57f7d0403057fddb466b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07250.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8c276ccf3df34d76c39204ee14380f1e09407908849791d1abc3633dde27118 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07260.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07260.npy new file mode 100644 index 0000000000000000000000000000000000000000..1631038481852b275e1c179ef1761d44d85e8640 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07260.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de7d03e49d1c4dafbcc416c4dfb662b0d04721c35c53b426828416b8f4d41b98 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07270.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07270.npy new file mode 100644 index 0000000000000000000000000000000000000000..f9da8e1392b467823a91a4c4fa3d5c135e8dd863 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07270.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91d381ab49c4477e80ff0461e9312453732d4346cd9456c9a4e2267055a44c3d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07280.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07280.npy new file mode 100644 index 0000000000000000000000000000000000000000..52b1e1e970d7789e2fdf2262bc98078eedb35f08 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07280.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed67e8ead51f8e654f49d709e9527060916ff1143e8b10825ef2114afb0c6293 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07290.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07290.npy new file mode 100644 index 0000000000000000000000000000000000000000..0025fb3f541c5dff49cb9ba94f2d1ac085eb113d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07290.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f7ed7965212ef247f0d3cb51635a6527677d7e62fa0576f778a6ec8232557f1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07300.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07300.npy new file mode 100644 index 0000000000000000000000000000000000000000..505795cc94fddff67543902f66d358008a058278 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07300.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a2a5d04aa20eeba279fa95ab59fb3230c2908b4c245fff21db528dbec1319f6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07310.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07310.npy new file mode 100644 index 0000000000000000000000000000000000000000..02801afe3106e4d49a6d5f86c743fe0853f1fd3c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07310.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e3f65375ed667270b63cc62f35e169d381ee0fe1bee92a07402f898e99a5223 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07320.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07320.npy new file mode 100644 index 0000000000000000000000000000000000000000..acb1693f6b1ecdb9dfa0526e519dae29f5cad039 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07320.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac742b0a6c03a23bbd323ae3183be9ccca0c83b61ebac7287f1302db308c9e26 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07330.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07330.npy new file mode 100644 index 0000000000000000000000000000000000000000..a1faef021c45c953510bd88a05236512cc17ea2f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07330.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b703b8c7e3a06e8f8a1913add05ed9588292cb4f7ba56216c89d7add86d9a41b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07340.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07340.npy new file mode 100644 index 0000000000000000000000000000000000000000..a74d080a84e33108d2797b31779c4a63ef23cc33 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07340.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ac8c35aaed576395c0befc80f254321d7407ae6a6c78f128675315fa5873901 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07350.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07350.npy new file mode 100644 index 0000000000000000000000000000000000000000..3d777bf75c8b86619bcf7886b5990ff3222a1a7b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07350.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8e034a667979f10233b03f6bb3c4cc02b0f0d661e01b846c882acb2ef442164 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07360.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07360.npy new file mode 100644 index 0000000000000000000000000000000000000000..b16c7463ab24ab571d14993cb23d45674070351f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07360.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bcd9f2fbbffec53b6aaed8953f3650c6eeaa1815e7b32e082bde1e277e069c8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07370.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07370.npy new file mode 100644 index 0000000000000000000000000000000000000000..ea9a40d37b402142979de7d1b06c9aab11b0cf1b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07370.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce5a2b8b554bb56d53d30eba88ec5b81ff1bbd41365f065d59ff6614471a605b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07380.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07380.npy new file mode 100644 index 0000000000000000000000000000000000000000..5e5b58189cd6e98eb5a5fa65d6f2437c41bc22d9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07380.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efb79f226963b7eb6219a1819fe7ac91d3e7e4af04b99b714bd051df0feccbdd +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07390.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07390.npy new file mode 100644 index 0000000000000000000000000000000000000000..e36386501d3b2805cfa62362490c4ce66b5b048e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07390.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00a86954ee68dd53aa31dce2083a6646904de3040f38510be048d58507b815ef +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07400.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07400.npy new file mode 100644 index 0000000000000000000000000000000000000000..cbb9225867454122eb71a5ce61c5e75936df08b0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07400.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f95cb4fc0ca54b922a3073fed9b018becfe4cd0109b7a8c747ad70c0d834a0e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07410.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07410.npy new file mode 100644 index 0000000000000000000000000000000000000000..3bf0ce1d1c0c432bcd94f361f085bfa5ca2a282f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07410.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:decdc82d37a9c56d2486303c4d0ba12fcdb9c7af7c804b2bf5b6cb68f8a41382 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07420.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07420.npy new file mode 100644 index 0000000000000000000000000000000000000000..14aad59f5353e41ae7ca7ee45eef9e46d71b44c5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07420.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d34cf70c3b08b68f7195d248601e0be838fb1271b3da25aa67ca336edbc4fe2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07430.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07430.npy new file mode 100644 index 0000000000000000000000000000000000000000..54a272d9eabe124c4583dc488c966978de46a328 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07430.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:097786c88499844753154b23206a3ab5da49e6cc13ca2678335a0c9ae963e831 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07440.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07440.npy new file mode 100644 index 0000000000000000000000000000000000000000..c37e95a39ea9b0a8d9af9e66aae9a7773ed25e22 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07440.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:039eadf088c3c82fba45eb2643fbd5da01a6a560b578f76f92ccab1ceba41e78 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07450.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07450.npy new file mode 100644 index 0000000000000000000000000000000000000000..9fc8be04f69215e43e5ff0792ae0c1931e6bc2db --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07450.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6b32c5faa563cae58c02d39438bad275b02e8db428362b130579fa431d4c7f2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07460.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07460.npy new file mode 100644 index 0000000000000000000000000000000000000000..d32db3f0ee22bbfb455e9b41ff827ed3f7c15e4d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07460.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee22137df112fc7067e3f00fc586520a2f6979855fb84e92438956fbd1a1de06 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07470.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07470.npy new file mode 100644 index 0000000000000000000000000000000000000000..fc35800a9240bc155e299699ad5b062654099993 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07470.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c2ff90b5a456b4143b8c32139d7a4aaa667bf9ef161ac38c660a6159ca169c5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07480.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07480.npy new file mode 100644 index 0000000000000000000000000000000000000000..7bc22630431edce191031194d36e503a255130c6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07480.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a62f30a84974cf809f2ecec29c6fd3ecb9a968386d6121a58044aab1d7433ed +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07490.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07490.npy new file mode 100644 index 0000000000000000000000000000000000000000..fe4ff4d7b2a017502b95796987a294fa80802e07 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07490.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd99916893ee2b3d56e4eed873f1b295749fad24f5ebe623d4fba925ca332c41 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07500.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07500.npy new file mode 100644 index 0000000000000000000000000000000000000000..254dfc4dd525787f116db86ec092c4af40db074f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07500.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b2f6d4bd76fdf15b7edfdf37ff0b810cb081d947db9633e5c1e84eddc34bd36 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07510.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07510.npy new file mode 100644 index 0000000000000000000000000000000000000000..adc16e9a309f49f19d0c34d53c5f4e42483d30e9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07510.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92e21d7367792f2c59db16558370a2c817fa54ef949b6629f914c0d6c821de0c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07520.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07520.npy new file mode 100644 index 0000000000000000000000000000000000000000..4358c534d2702f0c6d5ea22e7a8d6406748ecbb2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07520.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee690a49931d362cd1164fbc56027eae4f12ce438c2b7659f11b0346d159a0d2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07530.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07530.npy new file mode 100644 index 0000000000000000000000000000000000000000..74d79fd84eb5c9586bab7e1a2254a3159315011b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07530.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:510e431d90ffc425b37a9376d884ea99999325e87497f7adf7b47a34777503d6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07540.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07540.npy new file mode 100644 index 0000000000000000000000000000000000000000..a5c775cae24b90d62b02397b144c14737fa7f3c1 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07540.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20f7c48e40557d87d04e6f729e989431a9925b8f513defdec436cc6a8038e71b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07550.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07550.npy new file mode 100644 index 0000000000000000000000000000000000000000..9bee09c02bf31e184f6f1bc9cc836366f7a6401a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07550.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43211811f9bd172be7fcfa3722ce74d6dcabc8a7b02be29d1653c86f3ec9131c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07560.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07560.npy new file mode 100644 index 0000000000000000000000000000000000000000..196dc665589e4e6bf29e5c2bced840644f44d4fb --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07560.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e047536f230a22b059ad61ee612a16db30932e33b7041327808eab6ee6e91ab7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07570.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07570.npy new file mode 100644 index 0000000000000000000000000000000000000000..514ef18a74a89bf5bc645c5610daa929590dda80 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07570.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d99ade6e5b10c737d2e5204a8340041324e0a99d3ded450277ccc01fb9bd2638 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07580.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07580.npy new file mode 100644 index 0000000000000000000000000000000000000000..fc9a2c479648df656c2e57c772247843a00754a9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07580.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcf2194cb61b98fb84110eba87afda471bb8ee0edc2d57222bf96d04b6955754 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07590.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07590.npy new file mode 100644 index 0000000000000000000000000000000000000000..1462f2c06baf8f387941d1a8b0ddafff667d9c7a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07590.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53c933f45d53a7f02704759e011550803f08d203f15712857eca51a4a570daed +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07600.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07600.npy new file mode 100644 index 0000000000000000000000000000000000000000..7b4ea8f5c7649811878b751543682912848adcae --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07600.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f892566dcf618012e5bfc446a3e1ecc44e20cea34dd6d35bb64eea212c500904 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07610.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07610.npy new file mode 100644 index 0000000000000000000000000000000000000000..96be338a320d9de43682e6e54525f70625ed65dc --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07610.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cdb17a909755b1937068d6319d547a040026c2de463681b3910885f39c5befd +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07620.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07620.npy new file mode 100644 index 0000000000000000000000000000000000000000..7eb9854091d8b12522538bdfb576200dbb52cf0f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07620.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0f353d7bc32cb657431de472dfec1a7cdb44c7204a4b457b8133994f1efe37d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07630.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07630.npy new file mode 100644 index 0000000000000000000000000000000000000000..d921d87e3342d63b07ebc516f5712e21d438cf71 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07630.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3943f0a49504b4a8fe9690d1fdb728b9949d4dcbf4867182738881d08b93812d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07640.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07640.npy new file mode 100644 index 0000000000000000000000000000000000000000..4308767feaa413978ef417d789351364f945dfca --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07640.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee0cc0eaca49257b6751137a35ed20030800aee0078d47d508aa7816a8054f16 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07650.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07650.npy new file mode 100644 index 0000000000000000000000000000000000000000..8d3dafccc2194420403b720f1ce5676793130e81 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07650.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1661bf4625c6fd0eac2c0291587060197e87da38cb80cd19129f7f75297f42dc +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07660.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07660.npy new file mode 100644 index 0000000000000000000000000000000000000000..07c4774957a04e22de16c619fe7104d487c9708d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07660.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8bd02cbfe6eeb78fc1fe8113822873315694275306c4241ee91ec8c40e0e97d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07670.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07670.npy new file mode 100644 index 0000000000000000000000000000000000000000..8ee31bc6ec84ee1d02bbb2580cdbb3d6791416b8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07670.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:931750989254a64aa1f6b1723efdad0ea58fbcd51b05a35f2e51fb60d77494a8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07680.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07680.npy new file mode 100644 index 0000000000000000000000000000000000000000..14d01b6e42081fa9cd6df404745102c3e04cef92 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07680.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee4d4d6c42ea5735c53f09aeafbef9c6749e0020f0e49cec6bc4cc876f055111 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07690.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07690.npy new file mode 100644 index 0000000000000000000000000000000000000000..8d7ee52da771c90211f7c46357641a2caddf6c66 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07690.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d74789344106cf9974638196204c5680c8d4bda4ca0c2a4a68f8c9073ed4f4a4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07700.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07700.npy new file mode 100644 index 0000000000000000000000000000000000000000..fc75537d8cd7751eb1900f434138e558ab6d8580 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07700.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bbf8c055bc05fc0a0d1b30e6e657aebab15cc1b6d089dd9931dfa8e48b93332 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07710.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07710.npy new file mode 100644 index 0000000000000000000000000000000000000000..edc815de19f7c1a11b8cf15b9cdd8414b9e7e112 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07710.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d7a5231e28dbe5aea4ebc99468f351b5f4a7148175348aff9dfadbd16265c11 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07720.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07720.npy new file mode 100644 index 0000000000000000000000000000000000000000..600b81056c76f600d58860d92deba7542efd0e76 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07720.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dbdcdb20ef2c6a765551a140fe5989d1b73449c632fd048879b4fcd5b9c466b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07730.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07730.npy new file mode 100644 index 0000000000000000000000000000000000000000..a83eca8ec0aaf23a18b67d16222d4698ab2ddc93 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07730.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8424097b44ed9c9bea2aec537829039f0a3414436c9fe65a022917977a56e24 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07740.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07740.npy new file mode 100644 index 0000000000000000000000000000000000000000..59f36172414cba16d8c96358b908466134c534c1 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07740.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4249a6fcb95775d9920f6b217d8272b96744cb2e19a33a5566ada9f6cfef9585 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07750.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07750.npy new file mode 100644 index 0000000000000000000000000000000000000000..dd0d55bdd510de6fcdf2190bb896ece4e641e19c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07750.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8deddd3a09aba402feceb6c3a2b3dea9285d65a9e6758584a29c480833af5f66 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07760.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07760.npy new file mode 100644 index 0000000000000000000000000000000000000000..4ff4bd799642343ed3153f5000967f9881c44897 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07760.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a975669dfbe10cecac576383eb8bccc523fd97a422934f65f91c553de6c6de2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07770.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07770.npy new file mode 100644 index 0000000000000000000000000000000000000000..8eecd529c4dd0a108a0dbf7e11c9b4ea0a38887b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07770.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f40d58dbe884005a55eb75fbc05a430f1698108210d5dd9dd3dd61709a0ed047 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07780.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07780.npy new file mode 100644 index 0000000000000000000000000000000000000000..2091920e401e272b25f222a780a57c169151d42e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07780.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:438da765f7d587d09e5eb57c3030f071765735e7d2e5b9a14b863ed3e36dd342 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07790.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07790.npy new file mode 100644 index 0000000000000000000000000000000000000000..5dda1da0bf8c55a807e90a11f07687295dce34b6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07790.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bdd885b73e704591f3af786a91b6f7ebac603e1f868133a6025fdb02745d4ef +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07800.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07800.npy new file mode 100644 index 0000000000000000000000000000000000000000..4568f4e52fa44de2a9c7a7190f0a09ab2a2fa7c4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07800.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20c0fde5a7335aaf26bf35188e7218ee0d276b00f317863388be316f33bf6f28 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07810.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07810.npy new file mode 100644 index 0000000000000000000000000000000000000000..6ca9fda88cd78ea0e54b9d9a7c995c1db8a72de4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07810.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:928ba1e29d1d71ccebc5c895dd5c40ffd99ed614d921e526b7ccd575a26ff220 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07820.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07820.npy new file mode 100644 index 0000000000000000000000000000000000000000..5ada8a49db56ade144373acc2a4b0208d73c3d26 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07820.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbf16a2d48fbe46cca7a2f54b981fdec9c04239c9ff67852f04014328f3d5f24 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07830.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07830.npy new file mode 100644 index 0000000000000000000000000000000000000000..6df8161093916c1421ae32202cb6d72427c30994 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07830.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b1635f9b2e943dd59eb5cd638aeabc9266ac7d25cc5f1caf180980c0735805a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07840.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07840.npy new file mode 100644 index 0000000000000000000000000000000000000000..368df6c94e5ceacdaced945560746e9183df1940 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07840.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb76317cfc906fbab60e59cb9264964bf74d36ffb98a6fd2863ef6efa8e6b1f0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07850.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07850.npy new file mode 100644 index 0000000000000000000000000000000000000000..33c08f3c79525d4598edb630b0846f19aa438e29 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07850.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43fa31543706897d60cfb8511f9637d5083cab1c64c0827ea9b0253f8ae35d1d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07860.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07860.npy new file mode 100644 index 0000000000000000000000000000000000000000..d2020afb0d7ccdf778e90bf300262315756d75da --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07860.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7aadd282ff5dc8bc857e7994dec6f2cea71a44cb7c5c59a29f7f76c0b5309179 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07870.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07870.npy new file mode 100644 index 0000000000000000000000000000000000000000..efffd7d8004d832201532814365b3780b79c48ae --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07870.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dd394d85da2f55e02d83558a76715e4c750f3368f48db4cd6ce69e8f1a655f7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07880.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07880.npy new file mode 100644 index 0000000000000000000000000000000000000000..84f7ad2c58be88e0a2dada68e8609316b80b2e4d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07880.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4631d0d58b09aa1ecccfdbe410ad30ee91e5d212c6b342f780f5e5ed1dbdace1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07890.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07890.npy new file mode 100644 index 0000000000000000000000000000000000000000..0353fb7613a952f5631ea8a5140812566de949b3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07890.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea754c17a21a91b02016697288bbb140d6277927618f055a30b18eb1ef2dc4b2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07900.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07900.npy new file mode 100644 index 0000000000000000000000000000000000000000..44f6d24e5b70b713b41936c47b5ed415c0050a87 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07900.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7ca2fcc9bc4001a391b64bcabf6ebca1f07f54c24373935908539887d871299 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07910.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07910.npy new file mode 100644 index 0000000000000000000000000000000000000000..2047cf9a36741975f131b3ed6cce43557c181565 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07910.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c09f706a9b42014bfbcf025515881425d218918b1daf454494ddbf46405573fd +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07920.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07920.npy new file mode 100644 index 0000000000000000000000000000000000000000..bf209114949530b4c0d2be67e4422df48ba4fc61 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07920.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01b6508bed718b407149ce7ae1cbd9abeec0f60eb9502f9be501d2e28ea2904c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07930.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07930.npy new file mode 100644 index 0000000000000000000000000000000000000000..fd06915fdefaefbf4e06e8ad607bf1de93a3db76 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07930.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f1c27035eb49708e91ae83a0ce18541849e72c7fe1a6b8aa6cc2693920f9f82 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07940.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07940.npy new file mode 100644 index 0000000000000000000000000000000000000000..6e9339371bff1c11e3e071c9a23975219285ce72 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07940.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea30fd1b56d9fe16bbb5927f79ebe154faa36f7c414e644d33f2a7f764e6bb45 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07950.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07950.npy new file mode 100644 index 0000000000000000000000000000000000000000..28953c4d89b9bf92a820caf142ada7399e24502d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07950.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30a177f17d2531859f434437b6f1c0104d9b7e73409a3cb7363f4af2a2beda4e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07960.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07960.npy new file mode 100644 index 0000000000000000000000000000000000000000..8972e420abf233caacdf9117cba041c0158aec4a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07960.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efcc7950623b595011f187af11cb2b0cae58af8493f98333cc41e5ab360699a4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07970.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07970.npy new file mode 100644 index 0000000000000000000000000000000000000000..692bef762cfb9d9ba45e2f3f081a6054058ed9c0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07970.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4234dfb338e64a187df0ede2c891981b5c02d1f04e2330dbb9b430037bfbe62b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07980.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07980.npy new file mode 100644 index 0000000000000000000000000000000000000000..b7b86bba2811adccbab60fb2debe98afa77fe038 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07980.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e882f1ba072f58046208ff4a2977614e8dc6a4119b7159e06903b515314f087b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07990.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07990.npy new file mode 100644 index 0000000000000000000000000000000000000000..de6a78210793964c67f59560ec28eab96dcdf2ac --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_07990.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f678d45f633f8a1b8c168d5dc1095c3ab07fdf2b0f57b5a8e3731238e6183f2c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08000.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08000.npy new file mode 100644 index 0000000000000000000000000000000000000000..10d1a91fc220204a8a6d605f88dee201273dc8c2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08000.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b212ea2ab53c3c72830dc71dba627dab9222ad533b23d20a91b2757639f12cef +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08010.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08010.npy new file mode 100644 index 0000000000000000000000000000000000000000..3755aae663dc0a29498eee120dcee64a82790da0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08010.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbf8e88e0578c45325f60b0156c17f03093fd665cde371b561f169d6f0cd9aa5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08020.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08020.npy new file mode 100644 index 0000000000000000000000000000000000000000..6a419ee34cf57002a0e041f5fcfe27ff332fcb48 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08020.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d447b9a1172fa5b92caea5157b9e18ddf6f23f98e3cee9047abfce899ca5a7c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08030.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08030.npy new file mode 100644 index 0000000000000000000000000000000000000000..1d10b6184102edf3f3ad73d9d163aac7f6f76111 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08030.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ed8dd13fb64186111b59ecb2cfbd5eaccccb5890aeb638a0d3db6575e362a6d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08040.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08040.npy new file mode 100644 index 0000000000000000000000000000000000000000..94e2bf9a1362c1c1bde0643348025ef86b086883 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08040.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d760457c58346063bad44a059b852e431f6a286b0d8009a39b4ac17f972bea07 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08050.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08050.npy new file mode 100644 index 0000000000000000000000000000000000000000..4f45807f824bca20d8bcbb8624878ff35d3c0884 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08050.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3107107acf79c1f559396c1b632a7da877f66fcc737f32743539538564cee690 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08060.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08060.npy new file mode 100644 index 0000000000000000000000000000000000000000..96fb6010221f2b06d03058f25082871b0f92927d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08060.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:313775791e65c5419930bc9f55dcd317e05088e2b9e3a6169e56e819fccfbc3e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08070.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08070.npy new file mode 100644 index 0000000000000000000000000000000000000000..40aa4c3254d6cac675012b18f6b8d08920a70d53 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08070.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3e5ad9ecd6fdccbdac1858293e82ba3c27b6cfb5bb01b6d2250bfc82325ba58 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08080.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08080.npy new file mode 100644 index 0000000000000000000000000000000000000000..d5d29271d5dbd632cb55db13576e7a63e75ec690 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08080.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdbffa977ef6a98075e5d7985345486a54156fd12e80f9dc1bc7ba4a1f4191dd +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08090.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08090.npy new file mode 100644 index 0000000000000000000000000000000000000000..842ea905db9691b2c4d63666ea26182f6dbf0a3d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08090.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:150437316e877d94644ef665cb584d8d166e1b15e0d754a5ab6ddfde8e0595de +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08100.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08100.npy new file mode 100644 index 0000000000000000000000000000000000000000..b40644aad7751e4b183ee85575a3c60ded0f416c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08100.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:744b65d13e4779835096c8c3ed21e7b9496e558404367c24c5240c65ba1047be +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08110.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08110.npy new file mode 100644 index 0000000000000000000000000000000000000000..c881c4af125b9a06318165cd414ff45f64afbfe8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08110.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcdaf30a9fbca0c8f68fadfd6ec7d4ac9c6b89a64de44f307181493951a41b21 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08120.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08120.npy new file mode 100644 index 0000000000000000000000000000000000000000..dc3a9d8cc9c1e738dad489b2627b3596d07039e4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08120.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9d1a238e9e0851be916e161b317cf0eceea9cdf15bdcf13582138e58df9ff76 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08130.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08130.npy new file mode 100644 index 0000000000000000000000000000000000000000..ea8cd5493fc544643a8715dbb05880cc9f9cf275 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08130.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67179f7286120315934716f48326341f1b459f44edb8e321b5d216ba98f8935e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08140.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08140.npy new file mode 100644 index 0000000000000000000000000000000000000000..e234ece62c330a6355645206ebf5c2fa178ba7aa --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08140.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85a66e83c5e0c318efd0db9d2406ff00ee64446eb57f41576442413ba9630f53 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08150.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08150.npy new file mode 100644 index 0000000000000000000000000000000000000000..97ef646b395936c0c7496372ece22eeda330159c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08150.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c7674dcbce6cce9bb457e9c12667630c49e401fff1f71cd041220c8f38c1848 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08160.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08160.npy new file mode 100644 index 0000000000000000000000000000000000000000..87053927f2f737520fce17338d33e809e4109b31 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08160.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a67fbf7459bce2a57af35def1200598770966ac247c28e6c468f7822c6174ce1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08170.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08170.npy new file mode 100644 index 0000000000000000000000000000000000000000..d70f1359e8732f2dde157dc360ac6fdb51ba2a68 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08170.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:124be0ea4bd4da4ded6572d7eb192f55521ef0e4952892f85d636eb3380941fe +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08180.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08180.npy new file mode 100644 index 0000000000000000000000000000000000000000..58adfdd2c5089d53e2cb310491e3b6eaf5eabda6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08180.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1959a9511cd33c53de5c2285004526052fdf0596d942180b94ff6f66bf8d8911 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08190.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08190.npy new file mode 100644 index 0000000000000000000000000000000000000000..8eaf19609b5e12486db0fd9a698e43b37d4018f4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08190.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3501f5baaa7d3feffeb817931b423742ddb3a0bf704d8a6c2e8e5d788d7186c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08200.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08200.npy new file mode 100644 index 0000000000000000000000000000000000000000..eea66b68ab6402f240180985022765c6ed9df71f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08200.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcdfbf360daa84160e9c145facb42bd88bcc4705dfc45a9f1b239ff8e5dd85b9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08210.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08210.npy new file mode 100644 index 0000000000000000000000000000000000000000..7cb749262c651c4af2e713b55027bc348327d929 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08210.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63c0b6a80a82815d2d1c4abe33c9f8bc9c19ea59b210a1432c3e800cdd90b53c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08220.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08220.npy new file mode 100644 index 0000000000000000000000000000000000000000..65ffa87944b475cdd996b4d73c98a5099f53f647 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08220.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5030d44f2eb0612c4bfc1d01b100cd99d4e1f46a089e212a13e2ef11d6524674 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08230.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08230.npy new file mode 100644 index 0000000000000000000000000000000000000000..8cc7c78d3b0d3cbb24c3d53df5bcfe4a767ba95d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08230.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0e41b8b4567bed917bfdb8fae444d4536aa10b7dfd8604a631b4293e952fb90 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08240.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08240.npy new file mode 100644 index 0000000000000000000000000000000000000000..b82ab85e57a13fec294becf32384e4f1a626ff6c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08240.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dedb1a78826bd1fe69b4d1f247734070173e871bafcb7789625dbe002d3ac428 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08250.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08250.npy new file mode 100644 index 0000000000000000000000000000000000000000..861c57083ef2294b2f62e4e212b5e5627996475c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08250.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:148e1404a7c7fd89543774b8bcbcb2b80780293bc078a7ab2b5b53261bc842d7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08260.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08260.npy new file mode 100644 index 0000000000000000000000000000000000000000..e0bf50819fe8bdc86d9727be3b2d15fc3f69e054 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08260.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f49d80c13d7b7260f61f49b61ecb5af4491c61ba6993ed4e5fba6430880598c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08270.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08270.npy new file mode 100644 index 0000000000000000000000000000000000000000..b5ee37d1eacbcd6008dce0a6d8cb8ca1ebe869e6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08270.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:581b6f085d69fa0bca0fb9438ad9f0b61eae78a14b62f3bafc83f4ba4ead7c6d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08280.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08280.npy new file mode 100644 index 0000000000000000000000000000000000000000..75981f5b25b819098302d4feee6e0867cb3cdb39 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08280.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86c1b19ad4147c121e4d1a504ca2ecee01c71e6fa888d21bc6ab027bbf546fe5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08290.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08290.npy new file mode 100644 index 0000000000000000000000000000000000000000..0b93255bb6e8740b9cd2484f898facc2caa32b1a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08290.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b79a8b33f931a3f040d7123666e9e2875816cca050229470954245f79007d5e9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08300.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08300.npy new file mode 100644 index 0000000000000000000000000000000000000000..36b555d72d011db76f52624c8d68df0a622a23a8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08300.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:484cde2a7f80ac00e6016ea019c8484eaa97b071a3d5512c0c020e3cd097b7fd +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08310.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08310.npy new file mode 100644 index 0000000000000000000000000000000000000000..40b43a894b5afe2bce707337d81b09e585b9c8d0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08310.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a7860a2521efd392c1d2a6775d2f000e85e18d50481b042ec4afcba90fab187 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08320.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08320.npy new file mode 100644 index 0000000000000000000000000000000000000000..ae7a309693f5660e4ec64dcdf21e16c8920128a9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08320.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:237dc16b8da6fe7b714c17bb4f37541a4d10c37d50b50588d8be6acc5383d342 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08330.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08330.npy new file mode 100644 index 0000000000000000000000000000000000000000..090bda17948f3d8a30158c1c842d5e2fc3fd9d47 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08330.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58faa144cb0e8abc149dabb2860048a4011f49c814c05d8ffe42a95027dd4525 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08340.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08340.npy new file mode 100644 index 0000000000000000000000000000000000000000..dc89904f5e5791311eb58158ab21aac5cce24e1b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08340.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:060c33b95ef5a63b9e4d648a1c6b76c956809dc18f9f07eecf36c77930da9d67 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08350.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08350.npy new file mode 100644 index 0000000000000000000000000000000000000000..188b374b77b081b2a9b1969c8df6d4c2b78cdf19 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08350.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38a5cf21c26018f2d5dadcc82d45f12edd6177642f5614fc71310d2af6827e53 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08360.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08360.npy new file mode 100644 index 0000000000000000000000000000000000000000..f4e5408b776e2e0b1143b12fae495955e85694a8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08360.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2b43fcb6757be93ff439e9a844a607df445312993d3159d1b01646f051b715f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08370.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08370.npy new file mode 100644 index 0000000000000000000000000000000000000000..22fb72e70e26cc200d81d77d98396c2568004aa9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08370.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:050e6a045e342108254191ef2e72a7015979ac6a40ecb41e6f95c39401ada6b0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08380.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08380.npy new file mode 100644 index 0000000000000000000000000000000000000000..a8344dc70906b98cefc1e5cb84d003116da5dc58 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08380.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4705f89c08fe7daa77fe4e210d885a7561aeb6d3a5b2d9acebce0ddf595f9526 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08390.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08390.npy new file mode 100644 index 0000000000000000000000000000000000000000..18bdf15ec6d7a4508f40dce97d3777f7d13a7cee --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08390.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8709759b895a215f338b61a0b45b2640e1849fd475451371463cff562eb9f816 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08400.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08400.npy new file mode 100644 index 0000000000000000000000000000000000000000..1df04d0f09af0cc6ea814922016d9fa83c582ccf --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08400.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8be687f87457787648451198778ae04b5cd3dfc60553f8073ee6b83c72443da2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08410.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08410.npy new file mode 100644 index 0000000000000000000000000000000000000000..cec9be39fd062ffe02c119b6fae3c7064c7cf805 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08410.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a27e57804f9f7aef72bfc22d1998464eac5b780605ecd5e41013b04750a50bb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08420.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08420.npy new file mode 100644 index 0000000000000000000000000000000000000000..ae0d7a4ed234cf86345ce242302033087a4a6cbb --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08420.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c05329bd15e14d1ad47cfa45b8b7f0e674e35829332a440faf39c3725cb51fc8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08430.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08430.npy new file mode 100644 index 0000000000000000000000000000000000000000..af2b5bdc34ac46ecacf91211d5c1bff0cc4d4f53 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08430.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a540c9a18e548ecbc5299a1b0b60927e299cf612f61bb58eacd3a88b76b3f1b3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08440.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08440.npy new file mode 100644 index 0000000000000000000000000000000000000000..cc1684d31abac8d886a50e4c4e87536e1e6561dd --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08440.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:769aa23d749a51e64713f854e4b446f999f4ea48749b621348c889d1bc12dc3e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08450.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08450.npy new file mode 100644 index 0000000000000000000000000000000000000000..9e49cd6c672f708e504f16a3e68781149c86c595 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08450.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3366d44471afd810c09d55e895706c2ec25ce0c31b650d91bfc5d0c943b6ea4e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08460.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08460.npy new file mode 100644 index 0000000000000000000000000000000000000000..6afd515cfeafde5f0243517cfe41ff0f464fb640 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08460.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a336d747e66eee015e283256e9468667ea373118a11febf24f2a3724b523dc8a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08470.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08470.npy new file mode 100644 index 0000000000000000000000000000000000000000..b1d1a94affed90b296592dd8bb4c85fe5ca0b6cf --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08470.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cd11d210c751dbafd5a1c3c57274d704ba57fe301a1c3caab4ee8bad39899fb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08480.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08480.npy new file mode 100644 index 0000000000000000000000000000000000000000..383c23ebd008ed5132864cfc755013294651fba5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08480.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:872ab4553a8a4d6a51c6ae70fd8aaf5e6e7e3a7421a8471efa7c1d4e8b76b257 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08490.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08490.npy new file mode 100644 index 0000000000000000000000000000000000000000..05bb11aef6ef68cbf44a4697419ac88a66ef19d4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08490.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66dd862bcd329694076389b4c930d12d48c8a1c471ec86a861b40efab895d0e1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08500.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08500.npy new file mode 100644 index 0000000000000000000000000000000000000000..6d059f337cafecb1569122c013900d1847227c31 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08500.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bea61966f967913082cd26e11bbb5bee1a9938d98b4714f571325c195cd73649 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08510.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08510.npy new file mode 100644 index 0000000000000000000000000000000000000000..3055919776dbf36ed995b4012519a5a14cda7942 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08510.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:503498c8b526eee93fc499cd5528d22de18ce21f8dcfd298c4587817e573f962 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08520.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08520.npy new file mode 100644 index 0000000000000000000000000000000000000000..39108814d20dac5f6c07b1bf46c6d7c9ad89fddf --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08520.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dd3ccd6f9b30c3e8b618ba5eee73aa1951c8edc265f480e693cc939e9c479de +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08530.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08530.npy new file mode 100644 index 0000000000000000000000000000000000000000..edd6872debb261c0b59ec6f77ea7b467cd06b5a9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08530.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35022aa88f24a645d39f5e1055dafb359cb4fe3e57bf7125c87fdb2bade7af2d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08540.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08540.npy new file mode 100644 index 0000000000000000000000000000000000000000..b420869b8b46767091f6ff140cd3887a68422862 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08540.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c15631b4f46eadf15fd6ba842d4645882eec984a21dad7a0bb9cbf5b0d9fb101 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08550.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08550.npy new file mode 100644 index 0000000000000000000000000000000000000000..6bf890c5e28c05dd3479d700a116cd0ad447e726 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08550.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:782361ee5bd76c9d3d41d521aafa76ed66d1a0ffc28001e38dcf77fae58eb681 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08560.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08560.npy new file mode 100644 index 0000000000000000000000000000000000000000..bba6024503641c3fe8766572666f627af2460d8f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08560.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20dc81be963fc63c7599b76993cc4137eb0ff2474643bbfa1a86a4af35c1d72a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08570.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08570.npy new file mode 100644 index 0000000000000000000000000000000000000000..5c63d5c0d8adba706aff70d4b49430ce816a9b7f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08570.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecea98d2f0a5cc3c51be1c2867744045177c947fb27d58082ab25a0d06cb6560 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08580.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08580.npy new file mode 100644 index 0000000000000000000000000000000000000000..f9fd5434dc53e2242d6a6a211fd56be48c076142 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08580.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ec2476b89cfa7182e4cbab71e4856e1efa916a8d5c206a8357a97a3b46d9239 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08590.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08590.npy new file mode 100644 index 0000000000000000000000000000000000000000..9b1a1083acd86d25c7567bec16aa3f035fe74eea --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08590.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7349af239d700e6d1c2882d5515fbfd4ed2d169768e2a8ad069368e04f11601c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08600.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08600.npy new file mode 100644 index 0000000000000000000000000000000000000000..e30fa685648d2171f44f70ec8f4599abe3a2e6ae --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08600.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5622772ab37e486c9a0860b8287ad1c47a1cf54e4e21d94af755f7671f344876 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08610.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08610.npy new file mode 100644 index 0000000000000000000000000000000000000000..237da7b60ffc7ea11fa02ed1e7f7d1a09533ec62 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08610.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4460f0d5d058f4a1caff88a282b76b4a60e450ab6213f358dabc44764eda7fc1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08620.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08620.npy new file mode 100644 index 0000000000000000000000000000000000000000..e143263f822347fa3ad719c15146419247738f1c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08620.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d04b012ab1473fb1ec7e5bbb6af9f014fbd83cbcfee5a58d8a357614d110b609 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08630.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08630.npy new file mode 100644 index 0000000000000000000000000000000000000000..a068157a41de309e89a2c11d7d1cae705d593068 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08630.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e35232e4d42ee35e767a55bd9a80cb2077015e0de0b7ab8de89fcacaba5e60c0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08640.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08640.npy new file mode 100644 index 0000000000000000000000000000000000000000..9b41b88f36f3d19595a8f592714a2bb0888944ff --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08640.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31c089fd8983607ba3cad12e95fd404efe90315d8394b7d2785d14cc57c0a6d6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08650.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08650.npy new file mode 100644 index 0000000000000000000000000000000000000000..1f00ba80046b34b0c4d8c8e297edfaae3993fa40 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08650.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:effe2c7e13e00b0f5bd35765e7b7d516470dedc16763a109edf532495741c424 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08660.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08660.npy new file mode 100644 index 0000000000000000000000000000000000000000..b8c54203a2614d4d93db1585e76142eb72b980e8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08660.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7158e5bd13d0c68b4be86a0db4fbda0e76121c26c47ad0001371f823e5b3aca +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08670.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08670.npy new file mode 100644 index 0000000000000000000000000000000000000000..d1fba9b4db8a5e9495bd0898879ca27bf779016f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08670.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:423db1cc4e920141ea35d6259a452858852e1ce39871936829694f5910eccfee +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08680.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08680.npy new file mode 100644 index 0000000000000000000000000000000000000000..5bc246f279b502a7517c5fff21d6c6656dc19de6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08680.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02a79bcccb1873115220f788851c223997b675afe516b85bc8f012827707d5be +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08690.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08690.npy new file mode 100644 index 0000000000000000000000000000000000000000..ad2ebb751678ae423889b40e1e369ba7b5ab1ef8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08690.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1499adb0090e93fdb5fc9943defce30a7780748ecaf3cff864894bfb9c504209 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08700.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08700.npy new file mode 100644 index 0000000000000000000000000000000000000000..c784dd4d6cfca130a2329007df6d8d1864822a59 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08700.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:643d3bac502a5c9ae2083202610db4c7445a4be83a02d3696fa9ce7b4e5981f1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08710.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08710.npy new file mode 100644 index 0000000000000000000000000000000000000000..648f8dfbd30eb7f58689a3fbfbcfceb35ec2e25e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08710.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1c2a63e5e452967e7e8b6066ad39804be40e864acf8d9ef820092412a0ad693 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08720.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08720.npy new file mode 100644 index 0000000000000000000000000000000000000000..21ec21eaea75f7950f9325318ba19a33a38a0161 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08720.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:527493c3fd68b68ddc9f37e5b670b866ec891120d70160b6218853beb9f45b29 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08730.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08730.npy new file mode 100644 index 0000000000000000000000000000000000000000..d20877d376c102eae518d3670ac2b4114e9967bc --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08730.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7cd3e1d6c844fb866e943b6266a20576823700ac2b7e2360510acd2471479c5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08740.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08740.npy new file mode 100644 index 0000000000000000000000000000000000000000..d4a6d274041d96c60c4131523ade5cd13c23c3ec --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08740.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c28afb179b36ff421ffae05dec010328cb740c83c83828cc235deaba86be3f4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08750.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08750.npy new file mode 100644 index 0000000000000000000000000000000000000000..465fcc415b902482434ee67d4b567b9527b8b8ad --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08750.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5415a2321e9c5cd9281a84f98b7719de9a0d3de79de3477f33c4836f93c6f18c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08760.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08760.npy new file mode 100644 index 0000000000000000000000000000000000000000..68a093cab01af49500ad1e2d8115b0133a8df191 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08760.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b3b0f3b643af941050a2f9aca2058477f3973df656fac36be4c5c6fa94d5dcb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08770.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08770.npy new file mode 100644 index 0000000000000000000000000000000000000000..f87ae4390105c9dc8268dd04e07ed660c2d38591 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08770.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:375556af7697e65c34c63f589fbca886fc213bf9da93f0496ca04e8a0ba7b6b5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08780.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08780.npy new file mode 100644 index 0000000000000000000000000000000000000000..4932fb9b6e20fcd6db2c470e940fed96da202350 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08780.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fde6f174f1996432209531ff7854990d01acbe1b14748906276f39904f620a4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08790.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08790.npy new file mode 100644 index 0000000000000000000000000000000000000000..d87acd8c2fb910460c13c2255def1035d6ce28e8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08790.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35079818a30bcc6dd431cc7108546ae34d128f845f4f00a04a8c10912615672e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08800.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08800.npy new file mode 100644 index 0000000000000000000000000000000000000000..db8ab2408bc15552a1db470c34cab67c1f749952 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08800.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3c7d5fae2844396057d5dad8a34b004465ec8de6433364599994d3630329726 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08810.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08810.npy new file mode 100644 index 0000000000000000000000000000000000000000..ea5c77dc249418fabc6b9ce6e033ecaaf318f1d9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08810.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4fabdda38ba7444f9e025c0e5e1d09c963b45fa6fdf01afb02c84c9d17165bb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08820.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08820.npy new file mode 100644 index 0000000000000000000000000000000000000000..1b10fdee17d613678aa17e2d607eee0c3cf6e8bc --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08820.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f2e2f3f7563b474598960785f47a0586d3bb8409c4942c463eacb3e9a2f9305 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08830.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08830.npy new file mode 100644 index 0000000000000000000000000000000000000000..56fe4fdc5f1e197d24faedf357d4899d29b7f0fe --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08830.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed37981fff84c2f72db08d87d50ec7c6e12c2fe5edbb30e8e1cbf71145300488 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08840.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08840.npy new file mode 100644 index 0000000000000000000000000000000000000000..f64cef00367ee765e6195d19f38a7d091218b10e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08840.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29cef2f0844c61485eb58fbc9ac0d3b84f56cd54b40829dbafa23421ca65acf5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08850.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08850.npy new file mode 100644 index 0000000000000000000000000000000000000000..c7571a748963080066ede8e7415aeacda139c6c8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08850.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:618ad5a25219bbcf0d01e9088504f423fa6196656e6ce7fc0f237666dd86ff26 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08860.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08860.npy new file mode 100644 index 0000000000000000000000000000000000000000..a500474b311e7249f7e33b9f3db2300dbe95cd88 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08860.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06987ced4e4e078ac322e9e500ed30c812046d05142a6bc219b2d4b584194ae6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08870.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08870.npy new file mode 100644 index 0000000000000000000000000000000000000000..6d7c1118eeb13548782da438c82b95f6c3746935 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08870.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af6802e83235acb419f143ea39034e27ddcc54137dee622a0ba77f659ac5163c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08880.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08880.npy new file mode 100644 index 0000000000000000000000000000000000000000..5bd61261d3b03ddaeb7809a600428fbfe7a47c35 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08880.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80133e295e8675478da51a1b87cc055fec52f964898426c24f4fad5ffab3989b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08890.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08890.npy new file mode 100644 index 0000000000000000000000000000000000000000..e146b81e4f9f203284af678069ebdd3afd8cc5c8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08890.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09d9b36cb782b373b5219ff10a8cac53ed7ef458ba54aa07d437197e8a47e946 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08900.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08900.npy new file mode 100644 index 0000000000000000000000000000000000000000..ec19dbefda941793becefe19096de9e41062b1af --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08900.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d76ac0321867b44de3b1bf688126ac8e61e541d29be39578abb2a9b1521e829 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08910.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08910.npy new file mode 100644 index 0000000000000000000000000000000000000000..ab20c16ff47a3389963f95e4f6b814b58e67d59f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08910.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a2cef9e94ef25aebd2a57b3e17764c70e210103ef516fbae48e0b9094c099ca +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08920.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08920.npy new file mode 100644 index 0000000000000000000000000000000000000000..cb94d972befec32571fcf0251460c3dc5a85a72d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08920.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4350f484ff0c2095be4596b6dc5177b475389d3f083a79ec202bc90d29321093 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08930.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08930.npy new file mode 100644 index 0000000000000000000000000000000000000000..7657be642d2ddbac8d372cb4202479bb499a1c73 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08930.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e7915355456eb68f3bdf2b388eba77cb530f6478bf6b6f1f478339143d8306a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08940.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08940.npy new file mode 100644 index 0000000000000000000000000000000000000000..94fc72f86c2a4201f2c67ef2c5c3cb8671646fc4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08940.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c10819c8e19e3e24276cea756c87d6fd7ca37fd2a6aa11816dfdc1dc21f4a0c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08950.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08950.npy new file mode 100644 index 0000000000000000000000000000000000000000..cf2cf881a83de31afedd552cc8c2fd0ad5300245 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08950.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89d751b498df38cdd4033b44a635f16aa1d266d1ebc3443ad3ec01783bfe666d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08960.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08960.npy new file mode 100644 index 0000000000000000000000000000000000000000..8bd04a08bec8a51919c724a4628ad2dfcc7c700a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08960.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:296334bb3fb2a2f19f8d9c9df6b4529836aa11859aa61917353b2f1e8d66d83a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08970.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08970.npy new file mode 100644 index 0000000000000000000000000000000000000000..57741f16ef8f698385aa1b3eb7df190b841c01c7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08970.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04868408298e86d90345517b3b680a4b70e3efb99cc20a0619e4d4f7fa89a456 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08980.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08980.npy new file mode 100644 index 0000000000000000000000000000000000000000..cef48bd965f28f53ff72768ff8f5d5d3eac98d74 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08980.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7681f9cdf805e48be5fc2629a2671c6c6c77b82c65fc628db4ce0763b29539d0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08990.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08990.npy new file mode 100644 index 0000000000000000000000000000000000000000..f31ff405e42a2e4fc072ad81054187068ee9efc9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_08990.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:803affccf1b37997a192670553d5a043d758493cec6d32072d796a3bd971cafc +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09000.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09000.npy new file mode 100644 index 0000000000000000000000000000000000000000..add3c9074f7038fddf10cfa5ab43945bbb2d4d03 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09000.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04f2c2655b130c6a29eec38e595ae3f70baf852592031fa3beaf91d81f3ea89f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09010.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09010.npy new file mode 100644 index 0000000000000000000000000000000000000000..21600fed9553fe86ea9f452798683a19ec378f09 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09010.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84fee4f727fb9e0b217c969811e16f4844632179b9048426f35fae1666fdde0c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09020.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09020.npy new file mode 100644 index 0000000000000000000000000000000000000000..91bc9726ebd57ab4721e129b6b14aeb6958699df --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09020.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f816ad8bc74d4962e879e82675ce7b255b5f9dfb5d3b4c13e5f868a15fb7923 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09030.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09030.npy new file mode 100644 index 0000000000000000000000000000000000000000..e8a8fc4139ec108c67a4d14ed48132f8c955c8f7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09030.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b046efd11dabce56c8af7d623a8d4a11ec9451420b444e08031f15363146535 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09040.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09040.npy new file mode 100644 index 0000000000000000000000000000000000000000..935c8e1bf53c3428f14589d900993f13865a6cbc --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09040.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f5d65aa55fa3f48e4b42945a872e3cbea5a05dcafe284e7ceb7b965449f510c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09050.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09050.npy new file mode 100644 index 0000000000000000000000000000000000000000..ba1f6f8e4af8f02071dfa7a9d9728976bfe56ee0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09050.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7058d2f26133e4821da50adbe29a6757477b2ed8e4613e5e4773bfbd298d8648 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09060.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09060.npy new file mode 100644 index 0000000000000000000000000000000000000000..d3bd8562e3c40d1635513314a590e85c08e972ff --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09060.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b95b5f8160c8c9eb40822eec887aeef1c439e1a1aade0bfc90a0a7d3e398ee6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09070.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09070.npy new file mode 100644 index 0000000000000000000000000000000000000000..ebd35955e7f91b80fd3a26dad76ff51605a324fd --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09070.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acfd8d4e7b47b75ee7231f1b4feed717d95746410261683223f7bf3bf2da833e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09080.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09080.npy new file mode 100644 index 0000000000000000000000000000000000000000..bc0f597a002523af82a6d7c6a3df288ac810a9e3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09080.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f34d80494fe809271bcbef2d9dcbb04624b6fc9bfbd0fb04a2be2b50a8d619e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09090.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09090.npy new file mode 100644 index 0000000000000000000000000000000000000000..1e873fa59dfef4e8410795d92517ecfb8c335cbc --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09090.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4394315f28c1390746c945356309e69e9db2b8a1d96187dd8e1243aed11aaae9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09100.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09100.npy new file mode 100644 index 0000000000000000000000000000000000000000..b62a4a9c715bb2f53b35376882bee9422e01b4e0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09100.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0dced2ee76adac99b545199088ee90c6ee145b26807aa79edf6abd71dfc90ff +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09110.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09110.npy new file mode 100644 index 0000000000000000000000000000000000000000..7e19a9aa06e857db1bfedcc369f473616b443bbd --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09110.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f39c0d35ff034494d6dfcfc55db3a1756e6b4d4d3b1c9774f406a20b33f9b5bc +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09120.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09120.npy new file mode 100644 index 0000000000000000000000000000000000000000..fe27f15bac702746249475d9b03e6c36fadf04fe --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09120.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:187f3da2cd6505c48ae51fb40d0c8aae97820ab059ed87f4c50c16296e59dfec +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09130.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09130.npy new file mode 100644 index 0000000000000000000000000000000000000000..05baea1377371e84e1e8e80dd82fcdd63ffab94a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09130.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a996474386f5899f55a5018826d0493230d61cada65bf5b973a8c0c27932f7d2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09140.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09140.npy new file mode 100644 index 0000000000000000000000000000000000000000..97bb4de1f280f31056a45a1858c135a11c9b2c00 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09140.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d77e9502103efa44db9818d19a891c3df4e0ae5cf6ac523b4da20b8af8fa2f4b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09150.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09150.npy new file mode 100644 index 0000000000000000000000000000000000000000..d3fe7d8e15741d0352c462fad5952bd17527cfd1 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09150.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24a757e469af5b2758984f8888683be314b674ec78cfedfcf4af227d9c83c4f1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09160.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09160.npy new file mode 100644 index 0000000000000000000000000000000000000000..d45ad5b54c3b48c482765f5d52ba1c9fca7e7308 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09160.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1630cff15247b36a14ff4a9f18d19dc3fc364ba7ad46e5fd5c2c2da268162497 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09170.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09170.npy new file mode 100644 index 0000000000000000000000000000000000000000..5c992ed6f075405ccc60557bade1c5704d0e83bf --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09170.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ebaf5c428dda9e7c8799d68a33c9210a68691c3e485566915f8add5427086c2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09180.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09180.npy new file mode 100644 index 0000000000000000000000000000000000000000..e58b0a7d8e3b788c973f01ed84972e6f17486630 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09180.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b1be1c4b106b9f39ff339d0f810c9b6735c5706b889b468541e042d0348b4f4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09190.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09190.npy new file mode 100644 index 0000000000000000000000000000000000000000..4812d7281fde928e0f950b110c95747512dc0e06 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09190.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9118be066dd9968e60554b06fb0b6ef044375c5a829a632825464ec9fd40421 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09200.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09200.npy new file mode 100644 index 0000000000000000000000000000000000000000..f2fa7cabf80f6808f60fe7f067b62be5273cf95f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09200.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08fd5751479cd06d0e422b302da7a21326eeb093befc7ceb07ad55e711b8b66c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09210.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09210.npy new file mode 100644 index 0000000000000000000000000000000000000000..4b2be7bc1b31c194694170aada4940eca833b717 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09210.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71656080a2a3af2e22e9376afb9e5f736150e472e3eed7a26e1a65e5c08aa19e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09220.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09220.npy new file mode 100644 index 0000000000000000000000000000000000000000..962a75feead4889fcda598fb83035a1c67c3a9f5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09220.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48abe16d62cbd5332ed53d9bed8af1ce72bd61e185c9ca629c131f1c9832986d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09230.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09230.npy new file mode 100644 index 0000000000000000000000000000000000000000..2a6d8cfeea56bde1ccce7539a47f22afecdda45d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09230.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ffe83d948a89a9113c5124776b37dc49ef658ecd1d268cf039c578bc110bc3d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09240.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09240.npy new file mode 100644 index 0000000000000000000000000000000000000000..2c8e42576dcb2ffd4dd83792fa6d4508411362a6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09240.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af8c4fb58b3451550787dbb109b2dea739b673016c302a21fcff6f1de4386c88 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09250.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09250.npy new file mode 100644 index 0000000000000000000000000000000000000000..5773b69e3bf18c8b69221e9ccfe130536f0e5067 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09250.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c41354f21732e35979e89bd033f51e47e7dc85609a3e6f4e3ce363ab4d370edc +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09260.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09260.npy new file mode 100644 index 0000000000000000000000000000000000000000..3c1f7e8bfc874888beef005d5dc67f1c5d9c2ecf --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09260.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87737588c3972af057a6decaf2b4af6c0c2f9ee6de55e87f0fcd9f5339c2f7f6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09270.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09270.npy new file mode 100644 index 0000000000000000000000000000000000000000..7a0f436e1df8e9fd4eb917693fa6143be9c15e71 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09270.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1937bc22285187ac4f5256d604e5943d853d87351a76402e4091074f36bb61ff +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09280.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09280.npy new file mode 100644 index 0000000000000000000000000000000000000000..8490ffdd36dd220b1ed46d681a5df76a8bc4b2e5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09280.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8be16a5de1fa16f4b6995cdfc1691edc6d959b6c9218bd9f3d10152374c84a62 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09290.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09290.npy new file mode 100644 index 0000000000000000000000000000000000000000..0ddd40aa516e67a1ef43519f75b07790c6391f76 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09290.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c59d51bb664cb4acd2bbe9017b133417762f33b9cd86dc4a966d4e091d2c06f1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09300.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09300.npy new file mode 100644 index 0000000000000000000000000000000000000000..63dfe0b3c48956498a302a980c85e4e621f451ca --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09300.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dbbc7c4a357bef59061f907d1725919e60e3b6685d1503801d1a5de1208f6cc +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09310.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09310.npy new file mode 100644 index 0000000000000000000000000000000000000000..f24ba83c055e338a0885db5eb8e4689f13a83f01 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09310.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c63e8c14a2226de2630d222b055a79b0581c97b07d9f13fbfbe9a414667f1792 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09320.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09320.npy new file mode 100644 index 0000000000000000000000000000000000000000..e5a4ba30f737b51894bd262fa1b92365bf53f3fb --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09320.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d06121a75f77ca121cc09d0ab018ab8e652e81086813369f78e0c0ceffdcbeb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09330.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09330.npy new file mode 100644 index 0000000000000000000000000000000000000000..7b0bfae2bfaa66f5fc2a6f29812fa6d395d55e29 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09330.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3f6e567095e69fc63bab4d4a22baf3c714df3194fbf520370e21a57dcf2911f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09340.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09340.npy new file mode 100644 index 0000000000000000000000000000000000000000..76e760c9eeb9871673ff86fce57cf4617522f73f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09340.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:073ff541d20e2c3503a73f6a801d2c7221fb58d1840b722d3187be79ee9119aa +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09350.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09350.npy new file mode 100644 index 0000000000000000000000000000000000000000..4460bf0310a89b8dbd5c5442ec1556bb3953310d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09350.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c51dc18faf9993040dc273792164f06542a294d4342eae2899f4467c4b404783 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09360.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09360.npy new file mode 100644 index 0000000000000000000000000000000000000000..0ab4c5e00e9046c4382891d4db5b980f3dbda301 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09360.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b62db13025868fc0efa6cf176aca1603aa0388c265c8eb8185c7f49629c7699 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09370.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09370.npy new file mode 100644 index 0000000000000000000000000000000000000000..c19fc3eb7d2b1bc7058e7c94e6dcd6aae2934721 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09370.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00e3c66f4249efc48f43bffbdbaa9555b68e2675b0118c509f1d632592f53b9a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09380.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09380.npy new file mode 100644 index 0000000000000000000000000000000000000000..80f976278f32fd3ea34db816e03c5b6c7ec4a02e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09380.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b73ee61f973c549901da2b3ba24df61d273914d0beaed20f26f25be03e1515f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09390.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09390.npy new file mode 100644 index 0000000000000000000000000000000000000000..1c4c21accea01bce78da87b64e37cc7dd01a8bb6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09390.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54136ce4bba605d39565a8c03f3119a388ce616e623efa72266e718ca27a457a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09400.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09400.npy new file mode 100644 index 0000000000000000000000000000000000000000..a86e1416f28dffcff7ba0e72a44ffaf264e01d6f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09400.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03b18708515954c83ed61312d2e132b4d843db98a83d83e1f9dd9d9fb67ff2ce +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09410.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09410.npy new file mode 100644 index 0000000000000000000000000000000000000000..04c5716bff674349045440606ef0436215ea3bac --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09410.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85b57adfd7ce3125a8dea8ec2eff5b75805e569c9c0c711836acd0d645a39ab1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09420.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09420.npy new file mode 100644 index 0000000000000000000000000000000000000000..1db052935f4839a41a356dbd576d8517a627dd9e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09420.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d355a470de51f8b0395a71511049c52c5a0f4fd738a533979e15611053009eb5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09430.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09430.npy new file mode 100644 index 0000000000000000000000000000000000000000..3c8b907c0787ba58325eeb03bcf90a233e8988db --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09430.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:372caa9c666e65bb477df07a1a0544a6e0b53ed72833969746f98c41adb59b0b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09440.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09440.npy new file mode 100644 index 0000000000000000000000000000000000000000..3e85361f4e2f2780bb8bf276e825b10deff7c6a6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09440.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb888878a923b83c5420d5c6797d7d78e6859c464a576b0d923f486e6915355f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09450.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09450.npy new file mode 100644 index 0000000000000000000000000000000000000000..a42325c65839e7ae3bea1aa26230cc8de48889b9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09450.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3adb70dc2464a12204c4d895aa4345eeafd6a45152e1b5e4cc2f49b0529e6f5e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09460.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09460.npy new file mode 100644 index 0000000000000000000000000000000000000000..036a51225e36c2865f4407034c19ea5e7fc9d8b3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09460.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15a74eab7e18bd6f8a6170e5ea81bf28643fa415f09940b2f96c0475cd456d53 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09470.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09470.npy new file mode 100644 index 0000000000000000000000000000000000000000..c7a532a90c3e4fa17047af98d6851dc0ac061572 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09470.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31915f7b3f726e1dc587154da7aea85c3e943c457964cb03c771a831fa4e8b7e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09480.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09480.npy new file mode 100644 index 0000000000000000000000000000000000000000..9b1340b66f59c6401514a145a5924f0d5e91e497 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09480.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d6d4f910c708ed9113d5e39e4613808db17baa6bf73438835de268c10bedf70 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09490.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09490.npy new file mode 100644 index 0000000000000000000000000000000000000000..acc01f91cbd7dff25bf7cc99ff306ccfb2ca314f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09490.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d267dcb4c2847787488898a9850a8d91d2b817133777db8120408f2397c3966 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09500.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09500.npy new file mode 100644 index 0000000000000000000000000000000000000000..7af6d8c548ce6dd756250600e217c4c29e728032 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09500.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6051d7d9805e7dc569b7475dcf2c1a66de6ae871374f0d5faa6e9bcffdf2ef0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09510.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09510.npy new file mode 100644 index 0000000000000000000000000000000000000000..adc43d0c30126f3c347ac6a2376456fd053f1d6d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09510.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:861e3ce382b3e3f5aceba54d5941685323bd71a6ef31d09a29581b6963f2a256 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09520.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09520.npy new file mode 100644 index 0000000000000000000000000000000000000000..b75348b2138870ed12e7a62e7359f5690076f7e2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09520.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac62d97d51b22692ad0acc92936a5cbd09c03f1800c22de02eda3f68bc407d40 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09530.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09530.npy new file mode 100644 index 0000000000000000000000000000000000000000..42a020337c89d32774e3df74fdd583303948eb9f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09530.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:593899bb727d07b03b5b013a4a6c5a61c5f842a0f13577e205e52310b821337b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09540.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09540.npy new file mode 100644 index 0000000000000000000000000000000000000000..8bf5c2087fa3d9b4ddff36c18d88a93b80b869db --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09540.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8891b722aaa45982dd2468b068edd19bda7f29c1005a31a81f7fe241db5289bc +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09550.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09550.npy new file mode 100644 index 0000000000000000000000000000000000000000..6d6c24195ea864a763d006fbf90d7e9f504d4fde --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09550.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5fed5d50acb1bf044cd0301a932c6177e8e580dc631ec097c4744def100d710 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09560.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09560.npy new file mode 100644 index 0000000000000000000000000000000000000000..74024c2283173e62548259b159b79ad0bdaa0fdb --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09560.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ded15fdc35cace7eabfba1dcded5d8b2e1b47107503f0a893129820ae3dc5a10 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09570.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09570.npy new file mode 100644 index 0000000000000000000000000000000000000000..8ccdd3ca7caa7be441dac5a6d0031207b90c2031 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09570.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0b131870e5cebc7e0045a900930ab746b1508b51693df4f41f0146bc93fab30 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09580.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09580.npy new file mode 100644 index 0000000000000000000000000000000000000000..f7c8871fabdd7579eb2dd1a1118078eed54de6c0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09580.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0029ee52e199ea692e762ba7dee7d021139a5deedde74c0528139aa205960d96 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09590.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09590.npy new file mode 100644 index 0000000000000000000000000000000000000000..b4d0ac3a28eb2fccd34df90f7dd5f35c4d98fd98 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09590.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:734b6e53634aa27d034cc266fd816bb5f525ec0e7f2312e7f9dae938adacfcd6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09600.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09600.npy new file mode 100644 index 0000000000000000000000000000000000000000..b0b45b02b66f60212b95ca7b59dd5225f353595d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09600.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef0cc43ff900d9444f1ae3cba942607579077e6b24b0ae5d02d7437818abb8c3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09610.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09610.npy new file mode 100644 index 0000000000000000000000000000000000000000..f88429b0ee67007dd4f5527e5606ee1dde059630 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09610.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:758f3fb8096d042b31278668a5d95dab041a36372c0052bbf686709268357421 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09620.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09620.npy new file mode 100644 index 0000000000000000000000000000000000000000..066e8c293fe04b207a9bfd32212ecdd498d4feee --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09620.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec04da00a2a82b00723fc01ce83e26749eea23d9f8dc2a3ca7e110ab7ca3e115 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09630.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09630.npy new file mode 100644 index 0000000000000000000000000000000000000000..4d8d0794aa9e78beacc12ed48c9d2e4dcb14e913 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09630.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6ee15382e142917ab2bef71858480d4d1b7f91b09c9b6a4190239dd852eaf0f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09640.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09640.npy new file mode 100644 index 0000000000000000000000000000000000000000..d89876c86f43b72c02e856c2b3efc18882438004 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09640.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:077992c40599379e115c2a10dbadf198949661a0a597a9fe8d39a49647581edc +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09650.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09650.npy new file mode 100644 index 0000000000000000000000000000000000000000..6fefa10d1836d6578e22d0baae8d99f709aa0c29 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09650.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5ac7f2076cd9c677f392a7bdda147dcd95e43bd04595b5e254056b29dbcd46e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09660.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09660.npy new file mode 100644 index 0000000000000000000000000000000000000000..a874f19b7fef9c0668e4e9e7b5c1dda7bcabb36b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09660.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab9a8f603b36ba4fd8bfbc55e0574954363fd6eba24e582bac1455e6433ff506 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09670.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09670.npy new file mode 100644 index 0000000000000000000000000000000000000000..086d4fb4ad302c9de82d759873a00b6d92b52f1c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09670.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:075faafdc2d0267fa55b892394f2635eb2acc2bb43d5cbaa4cc66dbefeabcdf6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09680.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09680.npy new file mode 100644 index 0000000000000000000000000000000000000000..7f0ae0f47a731d42dbb7132c460f6d9f886daa91 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09680.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d5ed80eed3a8502996e3e8d31185b5b7daa187de4eecb042c3b1fb225bf34a1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09690.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09690.npy new file mode 100644 index 0000000000000000000000000000000000000000..33ce0e165382a9d71cc8549898fbd7f4454acee9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09690.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61241ccc10d5784b8a5a07065c18905c94ba2b7370783166837ffd3bf460a8c6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09700.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09700.npy new file mode 100644 index 0000000000000000000000000000000000000000..a27febf3a2fe3beceee1d90aa3416081ddcccca2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09700.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a7f86675cbb19942774c67cf8030dc3008cf1106e0e629f5cec41ca5f6e4b66 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09710.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09710.npy new file mode 100644 index 0000000000000000000000000000000000000000..e70e63e4772a8b9d7a741c4fdae355c29230f130 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09710.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:613e17ad247121f0d196439ffe74d54f036995efc4f695756c6ca5b8c9f3dcb7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09720.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09720.npy new file mode 100644 index 0000000000000000000000000000000000000000..0526bbe785e55c26c5923a30fe953e426a5e46b3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09720.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3266864ef6275835606257196c674ffd14d6fe227fe110c6e2d7e6d72baaf8a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09730.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09730.npy new file mode 100644 index 0000000000000000000000000000000000000000..ff386a0a3dc2de35e8653e96eff0eb3603cc6ce1 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09730.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44eba7630d68a3dd4b47bb6e13a48147aea5485b46ffbba79ed7b9baeac509ea +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09740.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09740.npy new file mode 100644 index 0000000000000000000000000000000000000000..d5ed14557ad24642620f4d5418e28d79871b87ff --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09740.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08ff21a1bf1fd8a2742049a951a43e276a7ec37343bcb4b22a6d1db7b6a18abe +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09750.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09750.npy new file mode 100644 index 0000000000000000000000000000000000000000..c9b10ea4ee72b1b96fb3e6e2f589ed36b17f7fe5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09750.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b07ae92887ed886fb51b85f8b04f1ff56f7520255e15323e878a1c14fb24071 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09760.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09760.npy new file mode 100644 index 0000000000000000000000000000000000000000..cda8761f7202f2fe1553f041ddd7889c8e98b142 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09760.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:296cddd65574aa6b724c878ada6b0af45b83e161ec15876e440a37bfc2ef445d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09770.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09770.npy new file mode 100644 index 0000000000000000000000000000000000000000..9ef12589364abe3bd21d698897b01e005a99a359 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09770.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6caa32002c8ffd8fda4e4ad860c3ee9a90ac9c9210301bf93b5571c7ebf848ae +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09780.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09780.npy new file mode 100644 index 0000000000000000000000000000000000000000..51b278afe64e8cb3a22f9f40efd119b9e6c089fe --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09780.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd3a9566f2d521d6dc75586a151884045aeb091349d47e00a428a355e8e43ba9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09790.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09790.npy new file mode 100644 index 0000000000000000000000000000000000000000..7c2444359427de3a898de3897b5686934d81f742 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09790.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a92ec200d2b0850ca2e7310df1f8d1a855a15ebd6d9c959286b7780627aee6b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09800.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09800.npy new file mode 100644 index 0000000000000000000000000000000000000000..e84aa0dc84fd492661ac7e3ccf717c95a4fea961 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09800.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07d431be1aaeae3990a0dfa21f584cbc50a0e00b478563ef29631dd62faa60db +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09810.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09810.npy new file mode 100644 index 0000000000000000000000000000000000000000..7652e6540cfd2d57e97e37313ce46570f5d7ea86 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09810.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e232c6dd2aa7ad0ff17527bb84def64a813585dd0c8d6be6f8a39b1c3e38fb2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09820.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09820.npy new file mode 100644 index 0000000000000000000000000000000000000000..82df94542adabf68cf89cd649e1c5040759da550 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09820.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ec629c59df0d1fa12ce2b660c3b34dd566b4326adb73895954b1bae552a00ff +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09830.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09830.npy new file mode 100644 index 0000000000000000000000000000000000000000..9f15383aaa4a33191383938cc407753175120207 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09830.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61d739d1c7fb4688ab3358aa39131f82cd8ce454afa3e083a622faf1a51e725d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09840.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09840.npy new file mode 100644 index 0000000000000000000000000000000000000000..bf2fc977a2a6ab54ec73583b438f23848a7cfd53 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09840.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54f3238053fed2d7ca74cfc61eb6590edf497ac6de55b73aa780bad65adf77b8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09850.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09850.npy new file mode 100644 index 0000000000000000000000000000000000000000..0b279f9eae6a7d38db983a2dca61b9f8d0736044 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09850.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4d86633d46165eef075e53473cc0109ae7c45dd449d0dc7238da70821c34c8e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09860.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09860.npy new file mode 100644 index 0000000000000000000000000000000000000000..12666f7520c8edeb05c154b4c0954b328d6aaa13 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09860.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87c249d5fd95b8190865bf9ccd1bcda077f99400d3eb842212d94d8978875066 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09870.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09870.npy new file mode 100644 index 0000000000000000000000000000000000000000..3ae575e1f2f738455d70341a9a246a33fc897196 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09870.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:989646f0001dc67a0fd024d0c32ed934fb2d9908564017c09c0725c37a5df70a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09880.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09880.npy new file mode 100644 index 0000000000000000000000000000000000000000..7d5d32b5a0596643544076ef2fd96d64ef6d03da --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09880.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e116a2b5d244c781564bd01e005d35a5bb0febb223c688e0ae26b8653f7eea98 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09890.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09890.npy new file mode 100644 index 0000000000000000000000000000000000000000..d705cbe0c094b12c3203cb5249baeffe48e066cf --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09890.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:018e7f10e6b08e0c9374254b6b63fbc440effb9e64db1c5af3ab4e871becfa75 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09900.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09900.npy new file mode 100644 index 0000000000000000000000000000000000000000..5295b2780e8ea49652232f423d9179b8d784f056 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09900.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b343261447f9d37bf041d3fd6c5f5333ed3a13c781d7bfdaf20e4c586dde539d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09910.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09910.npy new file mode 100644 index 0000000000000000000000000000000000000000..fa8c662754b127e569b383d2286c4843a0e88a47 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09910.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ba642cc562a131988e578d9bed5e648070e1958082249926567f0c809379b1e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09920.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09920.npy new file mode 100644 index 0000000000000000000000000000000000000000..c40938e381ce0db543e606a9982ab83056120274 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09920.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b2285065afbdc89e7e76a888a63fec95284131efdebf3c1dfef80aac4333a9c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09930.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09930.npy new file mode 100644 index 0000000000000000000000000000000000000000..32369f0aa8bde64d84ed93a6f56dc5d6efcb8568 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09930.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72a6092e9499fe36a3ec09452d8f21b727ebbd565d9d3407a63c8204ca5e5b9f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09940.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09940.npy new file mode 100644 index 0000000000000000000000000000000000000000..1b32d2ae1ee3f17aed562b1d17f65adab05acbb7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09940.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40b6a65361696a573249e5e1677e05b50f3113beaf35c50e192efae4e5284c0f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09950.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09950.npy new file mode 100644 index 0000000000000000000000000000000000000000..ff82b34d8b63ee9c5e7b7395204bf2bec4af8ebb --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09950.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15f8dfc05cb94d8a0fb772ea1bf2157c7d2d8c10dc7f6cc5f74efdc6c580e607 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09960.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09960.npy new file mode 100644 index 0000000000000000000000000000000000000000..693e17497c3570a40ac28ed4efee6223c8cf5566 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09960.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a97cf86e5b51e92faaa406c3505a2086d91c97444e2143cfd6912d52b130393e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09970.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09970.npy new file mode 100644 index 0000000000000000000000000000000000000000..e0f289d174b59d7c09ef4fb5a4e46c7b1e558c15 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09970.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a6912b122e00de4646dbd6a4f9faa0d28c4530c4bd579c72bbc31f1868979a1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09980.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09980.npy new file mode 100644 index 0000000000000000000000000000000000000000..dc349244a9fe476f8879bae13f5d01c4ce729685 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09980.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c84eb3ad00763b7110506144a65a0fb0bed6068a1c135b3a311ed76fb120c8a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09990.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09990.npy new file mode 100644 index 0000000000000000000000000000000000000000..0602cdf51d610df145c21d9358b05ea847fec025 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_09990.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:064cb412e240af3f80a18944c5bd911b0d305ba50ecae5a1cce7a8c3ab2ed40b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10000.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10000.npy new file mode 100644 index 0000000000000000000000000000000000000000..e5a2bd5df42851fff71bc530f311b8715da44472 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10000.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:049eda40d5ecda23e15e07f4fa6439ecd38d93ae29982f46752bf6202cbfafb8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10010.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10010.npy new file mode 100644 index 0000000000000000000000000000000000000000..0cc75254cf156d5ee14ba0634061b33157919a6c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10010.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a95914b625ffc4769adb7fab41e5934d57578812f49d18daf4b3a452f85db03 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10020.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10020.npy new file mode 100644 index 0000000000000000000000000000000000000000..102a5805610bc17b5c8f1485c6d2f1ba95e86f8d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10020.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0570a4dc5eb6a961f8184da9480dcf696774cb1ec4d8dd1ba16dd19547dde8c7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10030.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10030.npy new file mode 100644 index 0000000000000000000000000000000000000000..52ec0ccf9c356ef2da93a056f15259166fec20b3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10030.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cf236709616d72b49a8778268be5217741d768fba2dbc0089c3747db9b4a565 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10040.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10040.npy new file mode 100644 index 0000000000000000000000000000000000000000..def0a56957b5f579aac1792ba819edaa3f1b749f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10040.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8241928457bd4c88fb50f9fec0abbc30d762009491efde1127b2f54b47097c5a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10050.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10050.npy new file mode 100644 index 0000000000000000000000000000000000000000..375c025b419fa70dbede7b0b48f4079379386043 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10050.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77033a4ab76490ff042919d1abf4e8ccd89796503ced07a9557e18c26728b5a2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10060.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10060.npy new file mode 100644 index 0000000000000000000000000000000000000000..ed48cff59d831b533149b033005084eeb13463df --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10060.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b24b3cf76991e4fff663021c2c1cf77edecb0683165da0021ad03e3d8a794c2b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10070.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10070.npy new file mode 100644 index 0000000000000000000000000000000000000000..7643b5c90c70bcf9dc71bf5e6d65e08e2eb40219 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10070.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:417300e1b5551dc77adbe0396d35f9db27a4e517ee9847b8a98840f37c56643a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10080.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10080.npy new file mode 100644 index 0000000000000000000000000000000000000000..92cf55e9b6501cc724c51214c50e13077416ec02 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10080.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5b039d7cbbeab59097b9413523caf118f39ab91e6f4889221592ffa3805cc7a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10090.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10090.npy new file mode 100644 index 0000000000000000000000000000000000000000..666de50f44f8e79fa53e7f98e2f06a3a9279ecde --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10090.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:167672f906642e81568688b632d8f904a829dd0917738638b063414903152855 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10100.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10100.npy new file mode 100644 index 0000000000000000000000000000000000000000..2ad9009b2ae222ab5276db98143c0d354ca2563d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10100.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ece88e53a01817617a1b9ae2278080f1e9aba298f1acc9dad87f9a8ad26a6ac +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10110.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10110.npy new file mode 100644 index 0000000000000000000000000000000000000000..38ff4a7fb41e467c9cb921a5e287e2962fa85e61 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10110.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fae4f1844f1df62cebff49995f1e6335b6729bdd383b8f2ef4ff8f7e0e9288fd +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10120.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10120.npy new file mode 100644 index 0000000000000000000000000000000000000000..dd8ad360a12b07b62488930bf633a2cf1289162a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10120.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e176f2afac788a904aa225007d973a52519ee8a9acdff7621f0ae0500b06a0cb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10130.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10130.npy new file mode 100644 index 0000000000000000000000000000000000000000..4fb0209716e4505a3116b6cbe80656ffaaea8665 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10130.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9111f947877a549aa1bdf1b1a8d61129874073afaed4ea5ebbbce456c72771c0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10140.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10140.npy new file mode 100644 index 0000000000000000000000000000000000000000..ca935a94dfce56ea5e1e5a5fa2495a537e580942 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10140.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61902b27e27d4a8987f2d59995b1a7af2c529664a2abe6c0110ebe50403ba8fd +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10150.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10150.npy new file mode 100644 index 0000000000000000000000000000000000000000..aebeac3cb0cc3784e90bdfb637f1871fab336b57 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10150.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02e41552a9d4cca67b0eddf2ad15762f91d75ef150cf6ae9f74eaa33e114b8af +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10160.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10160.npy new file mode 100644 index 0000000000000000000000000000000000000000..f068d143526e7534276d6ce4a960a7b52980a2ca --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10160.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f663eb46edf563069f0e9387bd8809dd180c4374757e07cb22c845dcc3793680 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10170.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10170.npy new file mode 100644 index 0000000000000000000000000000000000000000..4f473e6cfa79d8255a009fafc27ffd8af304cd48 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10170.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91bd29cd57c80183b1a991eb46781840c4c3e4ae5853dd90a3ea1f65cccf17d4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10180.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10180.npy new file mode 100644 index 0000000000000000000000000000000000000000..618641227bb7163082a284f8419723059bc6c29e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10180.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d52967c7d5691310e4315444d5261fa49ff1cd85a2e01417788184a4f099dae +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10190.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10190.npy new file mode 100644 index 0000000000000000000000000000000000000000..7f30d1c7a05b7188d489c196ad6ed81ffa7b2379 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10190.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b8312c391188008216b5af02f741af26b7b7283862d977a1741b775f30bed55 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10200.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10200.npy new file mode 100644 index 0000000000000000000000000000000000000000..7ee74fc0b1fb5b97afc19d94afee88160874e9b1 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10200.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bfd905cb4296e3c07d1e640caab16392e6aab5e357f4f872ee10e947c2725df +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10210.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10210.npy new file mode 100644 index 0000000000000000000000000000000000000000..c7ddbe735fa9ff583f9246c75c43d991a26367d9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10210.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f3e878cf5e9edf9cb85779ea5b0d9f402b6ca47ab14fabbd47f8f15e0b574ec +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10220.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10220.npy new file mode 100644 index 0000000000000000000000000000000000000000..1a71e0524b576c6d35d699608ea4902c4140bd04 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10220.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02d186cf4f32b42f56f91de0b1c35103db31a37b6e76243e0caefd066f7bde81 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10230.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10230.npy new file mode 100644 index 0000000000000000000000000000000000000000..f3dc0679708e80c84fe461768a329b67dd8784ec --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10230.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63f57bdb9b68e1b0eed24408ab51de0cc6e19dcfa9ca02ba44735d924f98b696 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10240.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10240.npy new file mode 100644 index 0000000000000000000000000000000000000000..98e89d302a232ab3384f438a8545c0a19c38304a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10240.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c83a126ec01a9925c8dda96625fc25183f04c7ea12c430994c70c7f7b52bb924 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10250.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10250.npy new file mode 100644 index 0000000000000000000000000000000000000000..e1e53dad59dcdecde36247cd10aa37c75b092603 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10250.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b322eb800181c1c48ff8cb963282faf1bdf4ffc2031f5eb8ce32b146b5715f0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10260.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10260.npy new file mode 100644 index 0000000000000000000000000000000000000000..68ae98d77bfdd575dc5efc4b0005f51c0c8791c9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10260.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f8101b8f41a417a7229b1cd8778f5a0dd9deb382ec4d173f98937ab19c58c39 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10270.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10270.npy new file mode 100644 index 0000000000000000000000000000000000000000..16ec10e32ef8757c4cbf9a3c1a6b7ae7071a2650 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10270.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2b55b07d965cf8116e86d994ff7932e9fa7cbceb6d2db0078fdcaa42691c404 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10280.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10280.npy new file mode 100644 index 0000000000000000000000000000000000000000..2641c874be0022ee15541b30123bc7052a36cda1 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10280.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8da8653b4a8ac069b9f8b977266f954c75f62509bdd37de45b432c5bfe127cff +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10290.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10290.npy new file mode 100644 index 0000000000000000000000000000000000000000..3eb4ef9fe36b1720d88dc0f659c16721abc98b9f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10290.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2789a22d2dff42904eb15f89d5c4999ed3f6fe2357963f6de0b1854ab457362d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10300.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10300.npy new file mode 100644 index 0000000000000000000000000000000000000000..ff755c5028f8a1cea6590aaa687fc66d6fced102 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10300.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9d42c3e8e40c1ac9d850135f60e73cc73c0352c59e0eba26305fd345cf9a330 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10310.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10310.npy new file mode 100644 index 0000000000000000000000000000000000000000..ce1beadffd8dcc434d679029a6a36dd5b20ac0e6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10310.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dca109a8cf08d31988b34714ed30f33b60dc6760115b4ab778cf9e02275c58c1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10320.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10320.npy new file mode 100644 index 0000000000000000000000000000000000000000..c78a76691b273566b15869f23c7b0fabb4175735 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10320.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4d3dfd01cbe357a128770d09a60329f27367af0e60b5f6dacf44cec4ca94079 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10330.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10330.npy new file mode 100644 index 0000000000000000000000000000000000000000..d9769cff6d071c4744e3385b370900a8ce3b5649 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10330.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c852b2456d9ac5c825697efb1c0f4d431f7b159732dedb15c453e5bb7cbfc2f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10340.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10340.npy new file mode 100644 index 0000000000000000000000000000000000000000..a9096a4696a31b544dcf41a363ff0caef17de85b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10340.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfb7cc99669cb9c7ef0ccfe76df145bee270354e6a27681ba62b73f9b4209dbb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10350.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10350.npy new file mode 100644 index 0000000000000000000000000000000000000000..54b170a10eb868228d2fdd099551f0a31a32d30d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10350.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:786a54d935a864c11b884f7edb1e375488630b7067ee4eac2aed4c646d350add +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10360.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10360.npy new file mode 100644 index 0000000000000000000000000000000000000000..deaf3e30db27fe58466bf6ecd0ac386f65b4cb66 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10360.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b98d0e3a71fd5882e29e09256e414954a03133322aae40623507b64a0d01e6b7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10370.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10370.npy new file mode 100644 index 0000000000000000000000000000000000000000..f49f9e4fc95c07d052e9745eccececde8e2a8f5a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10370.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dfab2e297537bea8baaaa40bf14c6b0e9fe8b5ba27853b371e60a17c811c222 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10380.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10380.npy new file mode 100644 index 0000000000000000000000000000000000000000..a2ade032e18ce851d36b438474297523988aad9c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10380.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:551f7ddf069fd9d17de934df0906f2ccda71730685c39c84ef7524e4597e04e5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10390.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10390.npy new file mode 100644 index 0000000000000000000000000000000000000000..6110f3980715b6309b08e7d0db96ddfa0cc1566e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10390.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4374588834a553b2ab1c2b08e747bbd48e7ea94ee2d9c57065b092d47d65cfb2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10400.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10400.npy new file mode 100644 index 0000000000000000000000000000000000000000..f05f9984e0a3fc1794ae720c10b809875faa7782 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10400.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e51fae2a02657bdb0757ea503c489cd2ad82fb7696087cf46bcf06e2be6e7539 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10410.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10410.npy new file mode 100644 index 0000000000000000000000000000000000000000..34ccb257e07563149314e7dae6099b2aae52f80e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10410.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab0958dacca5e5f5890e9dfb55b6daf7fea77417b83f3d5ac4da66a69b626ae3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10420.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10420.npy new file mode 100644 index 0000000000000000000000000000000000000000..61e273b8ae367eb5bb7a7a40c0bf5dd426b19429 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10420.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e06e5d9403c49723ac01cb702bf1f6f2a4c8b8d25b3623c0a9dbbc147c486acb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10430.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10430.npy new file mode 100644 index 0000000000000000000000000000000000000000..789fbaf6c176219ae22526f2cfd93c4a18b9b86b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10430.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52fe27603ffe47fcb6a349de9cd82ebe24de14e0fce59d64a1ee40c796e3077b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10440.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10440.npy new file mode 100644 index 0000000000000000000000000000000000000000..23885a2a02fb902e0d616c5a60c58860b9a83c6b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10440.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56652ae31d6e2f13967e226936652d376428b39311c2ff03d6ccb6f481f31787 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10450.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10450.npy new file mode 100644 index 0000000000000000000000000000000000000000..d3c3262f7570f4694e98fafd5348b74682cce9de --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10450.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56994fd0fd48baecb05fbd8bd6c54d6a26d8c2dd3383f0d768fea064c455dbbe +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10460.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10460.npy new file mode 100644 index 0000000000000000000000000000000000000000..1d1c0dfb3625ba0c5d820235855679b149d4fa75 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10460.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e8ec9044a34a1fc2a6651ca330e55a6ea72b96aad9916b0ef6dfb5d2dd7e1a8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10470.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10470.npy new file mode 100644 index 0000000000000000000000000000000000000000..cc09207395cf9f7d08dac0d701454f3cb94856e9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10470.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f9c8b5d4cf78f82bf2136a0f38529f0feaeca2a358fe7ece9044dd8d783bb9a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10480.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10480.npy new file mode 100644 index 0000000000000000000000000000000000000000..8d0a75329498fd49d8a59714b82c8dee729b066c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10480.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f311fcc3b85c953749360119ead93cd9be646a898688b5a5003516124c58a246 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10490.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10490.npy new file mode 100644 index 0000000000000000000000000000000000000000..571a001e4d18c15a9a87dcbe47fd64ff48d56bb4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10490.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e64122dae93254254aca4590cf3d96b6db44cb667a5e361b10ff6921ac02b40e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10500.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10500.npy new file mode 100644 index 0000000000000000000000000000000000000000..cf7ff59ceee099f33d400207d88dc4fed684695b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10500.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:137fe4b70ec5933c12d7697cee4d643755d2fecda81fa15aefd59c22de82c671 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10510.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10510.npy new file mode 100644 index 0000000000000000000000000000000000000000..6263ad7a54d3ecf4534b8b248850eef1d5367211 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10510.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18ad76a04925ba411297b91bde932f7eb03e5f203a4c7c873bf60d1bb8fb9a3b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10520.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10520.npy new file mode 100644 index 0000000000000000000000000000000000000000..17f1aed42421a780fcb291ef87d6f594d2819e50 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10520.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7aba4c2b9267c7a6462778e3965773b9ded731a5b0051e277b4fb6ece8a4a849 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10530.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10530.npy new file mode 100644 index 0000000000000000000000000000000000000000..5a56ccb54b200ccbb5233c8246b65c4afb2888a8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10530.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88c05a52b3470b8fbf440608654fbc58cf8ec989f292ae9f3c7eba9372557c8b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10540.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10540.npy new file mode 100644 index 0000000000000000000000000000000000000000..8fa9868033f69c2f11d75f9dc753565c67b28b67 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10540.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40c01db92902bc5bd1285c045d1ff90bba03f7b52642a4c645949355d9318707 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10550.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10550.npy new file mode 100644 index 0000000000000000000000000000000000000000..4c50ffa14841669bce1f599de7ce18ed5084e6d4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10550.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5717ffffc32bd3c855591e3bf33903a6235076bc95a2c92d152967b879dfdad +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10560.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10560.npy new file mode 100644 index 0000000000000000000000000000000000000000..6c25a390f518c977295b6fb623d84c93886483c4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10560.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b1e82d8b3ede04e5d8aebe388ba5834f9c036849eb60f4de2a6e6e5b290b56d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10570.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10570.npy new file mode 100644 index 0000000000000000000000000000000000000000..11d5b2a3d29d129a8bdf77a3608c7263ad5bba54 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10570.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f481a45db1d3b67fd581dd90642621f8a913cefc41afef8a84a958ebd8585e3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10580.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10580.npy new file mode 100644 index 0000000000000000000000000000000000000000..0489b6a0be177dc1812a4b917e1f4cfdff9eae1d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10580.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a7570ee4e4476a5fa8b7b50ae4e4d79c94a70aaee0c1adea2b9522b799bf046 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10590.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10590.npy new file mode 100644 index 0000000000000000000000000000000000000000..56a57178fc69d43acbf35f7e3b61520681d55484 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10590.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b18b24bb7b7423420e832e8adf104e18e98842053fb119e45faf34be771f1d44 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10600.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10600.npy new file mode 100644 index 0000000000000000000000000000000000000000..12cd307c7eeb776c132ae1bc9f81d42408b89273 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10600.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da65cb1cab74006ce7e9ee0db499e54d9f41bef588172a9303d3e95184bb79bb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10610.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10610.npy new file mode 100644 index 0000000000000000000000000000000000000000..8c6e965c058d201b1cb61bfdfb21705471f1e4e3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10610.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a71cdf4efc34fe87595146541624d81d7ca080be365ead7900718d646ed1535f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10620.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10620.npy new file mode 100644 index 0000000000000000000000000000000000000000..ec658e9ada6afbe26254a60026cd974d8ebabc6e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10620.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6989e7024ccf3b54b2d3d4dfd4835c1ca2a35d8a48228ad08c7e6857ed7b84c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10630.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10630.npy new file mode 100644 index 0000000000000000000000000000000000000000..3c5ed1398ce7803f74e0af94274b1bfd7cf93cb8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10630.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e2a2c7d1fc1b2f64dbc55b72c1331450905934e3fe276e90b7dc6a7c86ce2cd +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10640.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10640.npy new file mode 100644 index 0000000000000000000000000000000000000000..ea39dde6573d86a8e12803e5d84a60b49b9e296f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10640.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d62343ac928763b4e7e84aaecfa166a0c4cad8a2a8efc33565c162abc7c14b18 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10650.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10650.npy new file mode 100644 index 0000000000000000000000000000000000000000..faf15445201633796a339f2c6030a11da11e2b47 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10650.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd1b3282b5da528dbbcef172dd6c9e06bd476668099fd1c1dde14843693a087c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10660.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10660.npy new file mode 100644 index 0000000000000000000000000000000000000000..76a5176c9b8bc82fbfcd89a58a89cec9416fd476 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10660.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef6530dd9c8d4022736e83d8546a9fab81840df38bd402122ea0ab6ba000655b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10670.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10670.npy new file mode 100644 index 0000000000000000000000000000000000000000..1d68e746970ceeea094c7b746c5d36beaa355a7b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10670.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da314d97a0cdd58c3a4ed4807c0e63cc0c3343c730ff3a1c794698700111d77d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10680.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10680.npy new file mode 100644 index 0000000000000000000000000000000000000000..9391a841e341efd1e2216bfc463fa642cde68fd5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10680.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:376c060efbe117b13bcee6d4b271dabb862116448412c4e76e20001c936d2619 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10690.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10690.npy new file mode 100644 index 0000000000000000000000000000000000000000..025e226a28c4884d8e8f82d9b2fd003df360e5a7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10690.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eabaf2c48bc75d22d2624098f1887de0d31ada32d689eeae046e7e4de10e66af +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10700.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10700.npy new file mode 100644 index 0000000000000000000000000000000000000000..e13421ebb4a412b8cee4a2784f0f5ec89967501b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10700.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20634759c4164fe5fe0e76b23ee6aae27e63ecf1f1357cda08bf9c5966b6741f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10710.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10710.npy new file mode 100644 index 0000000000000000000000000000000000000000..f33e075f5f33ef880113d3fdced755b853c7f1df --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10710.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:940f41f4f02b194b998bca63ed1a4d9c37896ef598b0612d66dfcf1b98ab92b5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10720.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10720.npy new file mode 100644 index 0000000000000000000000000000000000000000..6174f37ed8de99b74f1b81f23236cf8ce95a954f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10720.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32df21cc8fb058fc09ba3455344a458406801b0034af72cb35866bd2d02495f3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10730.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10730.npy new file mode 100644 index 0000000000000000000000000000000000000000..ff4bfce079466efaf65cffbcbf334c016090f735 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10730.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:987ed4f423451e55b9a4a1b842ae71bd2e52b17e7a5b01a4de64d17abccb692a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10740.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10740.npy new file mode 100644 index 0000000000000000000000000000000000000000..81074282cd472c0e96b470bdb5b9682f573c6c71 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10740.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9554c2de1e944e96b1a22eb7e54d5317145e7a4867247445a522bdb8367fef82 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10750.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10750.npy new file mode 100644 index 0000000000000000000000000000000000000000..8058413c88c5aa9bf3b7bf9393f0bf1637dd1dc0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10750.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:989962634b96a8771a2cd58edc40189d7840887e9ee9123e40d4466d6e319256 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10760.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10760.npy new file mode 100644 index 0000000000000000000000000000000000000000..c4a5623e243f8f4ef69fb71740624b67473be5b1 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10760.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96e853fa72b1cdfc4b4d3ce5faa179ebeb89ffe5161232b26bbb9f31e86db625 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10770.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10770.npy new file mode 100644 index 0000000000000000000000000000000000000000..07abcbfac768ae90702e4178e0f57f407887f500 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10770.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cf1b3d6d2c30d746590b30215973c7338f65fe6e00b36ec0f0b0cdd9ae9d9ea +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10780.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10780.npy new file mode 100644 index 0000000000000000000000000000000000000000..7eb2192664effd9642e084b46ed5d1e480933595 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10780.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:059bd53c9fffde67f60262573a5a43492086c0bc25d23cdb53a28aadb991a0d1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10790.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10790.npy new file mode 100644 index 0000000000000000000000000000000000000000..e989645d5851fbadcd73b9ad027ddc7da7ad1674 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10790.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7925fc3a65c8678a348acdf1b6bf95adc2635be19da2c68981ab6e43e943881 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10800.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10800.npy new file mode 100644 index 0000000000000000000000000000000000000000..48af6c6591b9fa9b1b45a7538b5bc5e139b0338d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10800.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ee945f2bf3856e9308fda3371eb2e87f3cbbc146790719b9318d6cb55e50ee8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10810.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10810.npy new file mode 100644 index 0000000000000000000000000000000000000000..e6434ff2368ab7d53e524838bd296695ba91b543 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10810.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3ac8a3765dede047e62ecee7f3be7ecb60840a34dc1770f076da207ed7a670b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10820.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10820.npy new file mode 100644 index 0000000000000000000000000000000000000000..e0e1b783a40b47f3e9923e51707f8a3186bf6d8c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10820.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:515b7e39cb9e2e054edf1d41284c3848f0c778d64046abb7dfe53c0612ef5718 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10830.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10830.npy new file mode 100644 index 0000000000000000000000000000000000000000..beeab773e07bd9c6cdf745753abbf234c4c6db0b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10830.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b85d47a6355deca8b599705b5cdbf05095ad185a73e9c6d0dfa63bd544f7ab4e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10840.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10840.npy new file mode 100644 index 0000000000000000000000000000000000000000..549267343ff22ab7b8713d8b8ba69b1cfc528a3f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10840.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:648edd49392fb01e95e47dafdcdd22a577f88fe166ec46328b4c44249353d3c8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10850.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10850.npy new file mode 100644 index 0000000000000000000000000000000000000000..ca120935c6fbfb601143539e2afe97bb409b5568 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10850.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc12a69fdb31758de3196736789c49d03d474ced809c2cf5f396a83435b426d8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10860.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10860.npy new file mode 100644 index 0000000000000000000000000000000000000000..465a3ce79cfbeae3dedb61644e71ae468a4ddc60 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10860.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:332ff04391623a684fe8bf7bbdf4ba9a8a4c4768d5c05de84872193ec30e451d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10870.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10870.npy new file mode 100644 index 0000000000000000000000000000000000000000..bea160d978fac5856cc40aea62263f6b6764145c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10870.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40db832364204dec9408ac49cec5ca90c968e22a709a83d215c3c9d89d1e7e76 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10880.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10880.npy new file mode 100644 index 0000000000000000000000000000000000000000..dda166c4069181dcfad4f8be12194fcc93e23cba --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10880.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6403c8634e9e29d353223c5d361b0afd683289504369bf9abe89351506ef5ada +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10890.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10890.npy new file mode 100644 index 0000000000000000000000000000000000000000..43c8043218cf4012e2e2c956ac4babc192faf5b5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10890.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe23e8b5942b8ffd87bbbb4922b73f5aa85ac01b56c28daa3f50299185940d0f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10900.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10900.npy new file mode 100644 index 0000000000000000000000000000000000000000..66d51eaba472524e3d67842f738878e0337136ee --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10900.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c01a8c2a4af8d64f584214005c20bd2035424b314cb3a65e99f99c9d8f3f63af +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10910.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10910.npy new file mode 100644 index 0000000000000000000000000000000000000000..79085b757400bc6a55d1c1eafbc3b4baae401096 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10910.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:549ea68a0193af2fa6cf5e2a7e6dbdec1ea75ce21ebe99115e14b8013498d30c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10920.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10920.npy new file mode 100644 index 0000000000000000000000000000000000000000..90600297ca69f6116d7d25de49c9895d88228ac6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10920.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfa1e9feb05b19e23d1c3d4c0d2699fe452e3c978788bb9b766e84377416e3b6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10930.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10930.npy new file mode 100644 index 0000000000000000000000000000000000000000..5541d919d0a6db6a0ec4ab407262978444b2d7d1 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10930.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:900d83ca07dbe0c2e8d4de677188021c8bf568415213cd19698373652be31ff4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10940.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10940.npy new file mode 100644 index 0000000000000000000000000000000000000000..2e7491945cb41cc5729e47979d7c0d44f8c9935b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10940.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fece3b930ab9de3177e33410146f03226f41a78fc7dd2a7129110df5d700a91a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10950.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10950.npy new file mode 100644 index 0000000000000000000000000000000000000000..02107ee6fb87efd03050a2e35c1ffc50b87e45a6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10950.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb4d97230b652ed19c0fab87ddeffc4d76b61b9284f796096db7d0ee7fe6bb6a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10960.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10960.npy new file mode 100644 index 0000000000000000000000000000000000000000..6f7e5f67ac8a842d56eeed4ab2fffa7c7b639e54 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10960.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb291c84ecb03f7f1ec82a193f382d7093c2e8ba288a7acff28c243b9303402e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10970.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10970.npy new file mode 100644 index 0000000000000000000000000000000000000000..eed8777a45c64437d481d45cc9f9fd60c9033206 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10970.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ceda3c69b2a9aceb78f8132ea1b7808e9e4e74fd4b73363250889006766fede +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10980.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10980.npy new file mode 100644 index 0000000000000000000000000000000000000000..2f792d805ccb6cc40392b5fc4b917c160438ae74 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10980.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5a327802e23b6fe6b80d4a345e8bdc90177ea999c386a6c12a41474c4a7840b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10990.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10990.npy new file mode 100644 index 0000000000000000000000000000000000000000..9f385604261061dce1c370a335a5b60d50a1f20f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_10990.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b17f986333c2bee3dff86be4884099fac7f8a30f870c7a3b8a7a1e8997415b5f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11000.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11000.npy new file mode 100644 index 0000000000000000000000000000000000000000..6e1b5f8253abc34bd8ddc06de07174da987d961b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11000.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:baca1c145b9f72d76f64756bc76fe3787099cf890e727c49c2b385bd68763480 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11010.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11010.npy new file mode 100644 index 0000000000000000000000000000000000000000..0ffb699e291f531c3a0f31a4e3ebf8c7eff6f27a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11010.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd7130327d147ed316e90fe9d7f710cf2461fbc71384ac7b9bd1c9bc7d2bce55 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11020.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11020.npy new file mode 100644 index 0000000000000000000000000000000000000000..64a79ff508ce308fd2c83194ebbb4819b5e04ced --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11020.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ce521a651eef3b81d23242d96fd4a8929680e3aaf6827f071541bc7f9779095 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11030.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11030.npy new file mode 100644 index 0000000000000000000000000000000000000000..a8f6ec4eacc64b9d197d943a186c7a3299a6b216 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11030.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac956119be8f5089ef80b0cefe4846180b3a7b4b10f557e6295931b3a2aeffdc +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11040.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11040.npy new file mode 100644 index 0000000000000000000000000000000000000000..8311aefae5b138f3b32c77b87d0bb474567687fb --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11040.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8586deed3b8665fc680689cf202d9af6f2e86a564af8d940c79742fb7f277a1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11050.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11050.npy new file mode 100644 index 0000000000000000000000000000000000000000..22f97376403e92f76e45249fbba5f43a13c2b9f5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11050.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e8a2e313dff352f533739a6f0c27073126fe509cbf4395d3a44be46ce8f31cd +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11060.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11060.npy new file mode 100644 index 0000000000000000000000000000000000000000..5c3963365a0d70308f7cab1e261bda992dfaaf7c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11060.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ede16458b7ebba61703f7a83c9c5b1b71fcfaf0b79c07a7ae792c93d5f5ede18 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11070.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11070.npy new file mode 100644 index 0000000000000000000000000000000000000000..73d5602b76c15b68c8eda8da9136d803690f2737 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11070.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0062dd927a6c8ed7ddc63fad8bc854c4f5c43f6525a73b9fc27805bfa88c61b4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11080.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11080.npy new file mode 100644 index 0000000000000000000000000000000000000000..21e69e7aad8ecdcd6c8855fb94632419b71e8243 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11080.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f382f43ceb2c916328b262cc9034c044ef1279b9243456f457ac0d6bdd4f87cd +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11090.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11090.npy new file mode 100644 index 0000000000000000000000000000000000000000..84b243b25a8dfd7c2d61b384435f7248ed5fdccc --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11090.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a10037ffad6447c78040215e77dad8f151447307232b124dbc9a35a01c14352 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11100.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11100.npy new file mode 100644 index 0000000000000000000000000000000000000000..7f37d9d72dd2ca95410c6685e23377f2798bc499 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11100.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a9158681b3fbda6e6fc45dfa7dfd3dccf7740c6492078ae28e86745ecc94ac5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11110.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11110.npy new file mode 100644 index 0000000000000000000000000000000000000000..c9ab601b66f11dd1d5d260f6816a27125320df8d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11110.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:233c40973e59a0e3b37766bf6892c803761d18d98faf517e1ddc01117eacd5dd +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11120.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11120.npy new file mode 100644 index 0000000000000000000000000000000000000000..a4945438ea1389a3421d754da21e09172247d860 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11120.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44081a50d717639584aca7dc32cee3d85f7a0ef9b8b2fe9c296739790dca9ae7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11130.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11130.npy new file mode 100644 index 0000000000000000000000000000000000000000..a6909ebed4aa47ae3d359571d4f0414ccbf3e168 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11130.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9838d8a549ec44394c5c2c9cb46643e9fb0e3c912c57a6904f909ce6b5b7ee90 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11140.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11140.npy new file mode 100644 index 0000000000000000000000000000000000000000..7859dd2e8862a44caf8348aea409b5093b06e5de --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11140.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81a3264f78db71d4559dc4d1f417780a002ee18c537fd749701bccb0941cd77d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11150.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11150.npy new file mode 100644 index 0000000000000000000000000000000000000000..5214854ef153c3cda62ba1061f5b587e8fa8c27f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11150.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:320779e86633a7f1303af8cf69714e6a2999521722682a875ad5cf165ac7d7c6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11160.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11160.npy new file mode 100644 index 0000000000000000000000000000000000000000..9dc4374512f7bd8926c372f8626a93c3fca31349 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11160.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be553350ce6f0d40cf298be973b14110a0ea3ca1155c02c84b31e62289ce6100 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11170.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11170.npy new file mode 100644 index 0000000000000000000000000000000000000000..f3e780656bdef338e57bb7e1d9959b24dc808d4d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11170.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9461526e72a8f30b17a0bed67f0c7f671364e3e53bbabc380f787ce6ae4f6160 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11180.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11180.npy new file mode 100644 index 0000000000000000000000000000000000000000..90821aceba7342d6754288e04a0d52f2744f20f9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11180.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a30befeb0bc97d1ec81bd65e56ab2371068b68e878f16ba677a59023433f1d3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11190.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11190.npy new file mode 100644 index 0000000000000000000000000000000000000000..9ede5552b02555ff1e28b8423f56a31939634ea2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11190.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d15529aa4b9b14717193a54a36363eb59d9ad307e00d56e7ca48894236ea23ed +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11200.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11200.npy new file mode 100644 index 0000000000000000000000000000000000000000..cd30ffd3e9a109b99854f9e33e61ac0d70655920 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11200.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93c3ee2a22921ee7ebdd59568a2889126c374df525de747489e497a9ea0f7f6b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11210.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11210.npy new file mode 100644 index 0000000000000000000000000000000000000000..c4f855639a354a55df42f46f2410aa620be47cfd --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11210.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3bed41855e56430ba975271224adafb547c43311a2108202dcd81b6f743fccc +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11220.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11220.npy new file mode 100644 index 0000000000000000000000000000000000000000..6460fcd5691cfa499063e44ae7ce4cef92304230 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11220.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ea4d686f91fe5b7f767f9d7f25e666a65de433eb378b390b77fca00b20c6be4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11230.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11230.npy new file mode 100644 index 0000000000000000000000000000000000000000..41cc053e3d064cacb00b6f5b6f7a8a9d114cbcdb --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11230.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a29f99744d472d9aba6afc58d407106cf7851ad405ae1b0e0f4b68ff1e6e7985 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11240.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11240.npy new file mode 100644 index 0000000000000000000000000000000000000000..71aaf498412530e962740615e5ad25fd2ce68a66 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11240.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef8146e0a5c7d5d1e9b90e5be9935f944143f8f0e1851ba2641ca45feb5fea5f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11250.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11250.npy new file mode 100644 index 0000000000000000000000000000000000000000..6381af0c3e950a6912d550742019730b38774d80 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11250.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b93a9ef3a0f082349e05a3d58ea1680db39d2bc812ea0971c08097b44743770c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11260.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11260.npy new file mode 100644 index 0000000000000000000000000000000000000000..32ae33f89da03a4318b3e432e5e6866f3b03f4aa --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11260.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49e72a55f0dd14a56d422f67ce3f7a2883ba2208a9e3bf2020952919f90701c8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11270.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11270.npy new file mode 100644 index 0000000000000000000000000000000000000000..a21108ac8cd85601e77d92f1949c3d26b848d3f6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11270.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b053acce9e3b60879ae67bccf2bced6114308f71f887c3e89977c819d6124486 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11280.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11280.npy new file mode 100644 index 0000000000000000000000000000000000000000..e8d492196efea91ec49e0510a1e4ea1b14cb40a8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11280.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e22b72fba3f4e0ac4aec5b6d966c80ab7160e0c75a3e607205b6c536d35d0de +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11290.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11290.npy new file mode 100644 index 0000000000000000000000000000000000000000..b9715243974bb83674aa75fb6958ba5a2a8d8fdb --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11290.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61f4296197afa9df94ef51aa0c90e4de75045627e33ca35e1fe97181277a0ea2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11300.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11300.npy new file mode 100644 index 0000000000000000000000000000000000000000..31f5ea89b91ab81ea6c4086f189c9aa2cb498c40 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11300.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42bec7c8fe0a4fb4c2ec27cacfcafddae7b8f109f71d045f8336ee96f00267e0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11310.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11310.npy new file mode 100644 index 0000000000000000000000000000000000000000..37beb841d3ecd8d865fb2ae3651f28bce152e541 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11310.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:891f60102966c15e1614f8d34e8632e7893473e6e830b972005652be9f44f34f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11320.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11320.npy new file mode 100644 index 0000000000000000000000000000000000000000..8faf6fc6ba4506569db90f7dd98beb29e6d537c2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11320.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed1117171efa342df927b9cc4dc35a954673f87cddd5dfd42bd3f0779f4d683b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11330.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11330.npy new file mode 100644 index 0000000000000000000000000000000000000000..b2127ac86ecf5361ed99cdb9caf724bf8dd6d81c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11330.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb0d280c359bb411e265aeba81748380b8b5487d95e924a8316b9aaf3366190c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11340.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11340.npy new file mode 100644 index 0000000000000000000000000000000000000000..848592016ef558abd93999fdc610cedce7343195 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11340.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39611b0e73f8ff0f8b8ed7cbb06ed6e70401677bd194ae20edbeced425a3943f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11350.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11350.npy new file mode 100644 index 0000000000000000000000000000000000000000..9f1c29e6370dd621c7b90566316ef0485f787974 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11350.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ff2406f05ce69049e3f3289cf8bf3cc6c7c8f82f1033fbf9d1c4b6f39e8f992 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11360.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11360.npy new file mode 100644 index 0000000000000000000000000000000000000000..55a291e8e696f344729942c43530f263195337b7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11360.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:764c525fd4ab9cdaafd0b4d6944a37b3d7b84f9fb494232065e0e564eb156810 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11370.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11370.npy new file mode 100644 index 0000000000000000000000000000000000000000..05be2977b801158d08bd414c76583db4ed144b80 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11370.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:260e7c71938d3b64203f32b014a0eff58a8a3cff3e0122eb78f806e27b612109 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11380.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11380.npy new file mode 100644 index 0000000000000000000000000000000000000000..cbded50ce6d08b32094dbb3ccf696254b2f6ea9b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11380.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a434f4f567fa2e6989814c81b17dff40126337f4bf063dd3dfc53a4a26286e2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11390.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11390.npy new file mode 100644 index 0000000000000000000000000000000000000000..ad5185b783e7baa0b31fc7b42fa55ba2f99707a5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11390.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f6a3cdb6d306208d1c1f45566e387ff1b0b67a961a8a62eccbb7065d36f2cc4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11400.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11400.npy new file mode 100644 index 0000000000000000000000000000000000000000..53d2b5300de855a6733f91675b94d54fe2385609 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11400.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37e7c1d8eb12f5b030bdab2b2557dd94462e39f2fbdd3de52518d7bc26a9f38f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11410.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11410.npy new file mode 100644 index 0000000000000000000000000000000000000000..1ed3a9ccce0d4e987b8e0bac4ab1a7eb262b905e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11410.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20c99256ca8ad4739afa41cadb206531fb07106382b5f88ccb9935305a6de1a7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11420.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11420.npy new file mode 100644 index 0000000000000000000000000000000000000000..72775d72e29683c2ca37e5b6d36477d632377de3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11420.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcbd6093291fc7200f99901885089903ac8f74144fa68d2211e78a4f3041276b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11430.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11430.npy new file mode 100644 index 0000000000000000000000000000000000000000..889ffa3f87a169787a3a939709047a1d0659b6b4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11430.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d68c39c9f7af78b2437e11ee4821415fc391636f77fd73c93a3486c3d98440af +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11440.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11440.npy new file mode 100644 index 0000000000000000000000000000000000000000..7f252be8f315207b8a4544cadcb40b2d1b928b81 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11440.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d3a75850d4d18691ff64eacdc4d5f2f477a513467880974cbe676f8c41af945 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11450.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11450.npy new file mode 100644 index 0000000000000000000000000000000000000000..9c882f4a22cf2ef56fd1981ab2c7edd9708c91a2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11450.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc6d3ea52cc79c610e067331531973fe0da38a60f9a7260f6bc781f57f824847 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11460.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11460.npy new file mode 100644 index 0000000000000000000000000000000000000000..696f425f9cebfa098707ac40b28a2010950f41d5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11460.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17b0bddf67fb5f7ff4cfa01ec964b29c89c06cebce738469560730acd4506283 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11470.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11470.npy new file mode 100644 index 0000000000000000000000000000000000000000..ff76f1131dc9090dd4cb866170b61ad9b961a3c9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11470.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2a6b5324dd1f54c4c72339d5de6031a563574de92557cbf92138def099bbb15 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11480.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11480.npy new file mode 100644 index 0000000000000000000000000000000000000000..dfd58aaf6356bae9d017aa87d10eb8074fb31c99 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11480.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0240f03da5d6ae9dcdb8793254f490ca631d3de227f6a1b684c5eb86273480d3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11490.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11490.npy new file mode 100644 index 0000000000000000000000000000000000000000..f41dc91b9ff9352d297368a2909327b7f770bf53 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11490.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5716d7098c92b2bff27afb7f4af9926521d6a28a4b28a3eed130a56b0944b387 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11500.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11500.npy new file mode 100644 index 0000000000000000000000000000000000000000..0dcb4bd6be6fef59b679cb3fb8074ed3581af35b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11500.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d53adfad0d05f25c909fca5a150b37305274f2b28a94f1d236a0e61c06e4e48 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11510.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11510.npy new file mode 100644 index 0000000000000000000000000000000000000000..c859b5f8bbb423f173711a57870d72680b994667 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11510.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe926078ad413cf13d9c6b39aabda8dfa3d5317ed62b7f2013436f045e4b662a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11520.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11520.npy new file mode 100644 index 0000000000000000000000000000000000000000..b159cc8d945a403b20d980a53054703ca86f0f33 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11520.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9e6dc6d4d75d98fd38bd43d97db9222e8347000985c918b105b6bc57c73ccaa +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11530.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11530.npy new file mode 100644 index 0000000000000000000000000000000000000000..811004d008626df57887e78ef15aaca109259291 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11530.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8e9e23c316b9881c51dd87e1afbba2317b1ec8a0d6b864b7b1a2469fb00ef7e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11540.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11540.npy new file mode 100644 index 0000000000000000000000000000000000000000..e00250d730db0bf9235d0cb1a509beb8a856e16b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11540.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05303a7e57e5de323f812251239c7080ebd0962036212a6b19c9ed361687c10d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11550.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11550.npy new file mode 100644 index 0000000000000000000000000000000000000000..6495bcf683385d9e0fc57f7b069b1bde9af43176 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11550.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3aab34b8f45dcadf9c45fc101fa45a2413cef3f5716b76e7d9b39eb06e03560d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11560.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11560.npy new file mode 100644 index 0000000000000000000000000000000000000000..de80d498e6f2e54a4ddca1435a39b1210702ba5c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11560.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7582b17300966be3b6535ff7bf2bc4b3ec8cbee54d64c79a1d85ee449fb62125 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11570.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11570.npy new file mode 100644 index 0000000000000000000000000000000000000000..84af700aecdef040399d0ebec6f9877d970643c6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11570.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f6b83a9b8f2465f0a24c28681c82121cdb2b92ebe6e25ab1e4857bd32abc37f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11580.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11580.npy new file mode 100644 index 0000000000000000000000000000000000000000..5f275ee5069320b92b7913a2ab382116288d8611 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11580.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b076e8b99ad46927d3c91d7e4c5dea917ec5c6bf0519b6a8eb6d26f3e828e92d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11590.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11590.npy new file mode 100644 index 0000000000000000000000000000000000000000..262f1ca69214d1a9406d348d70d28863cf7093c9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11590.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75c48fbbff3da4b3b9036c9f565fc6ef7f6e02e56883befef469c78bebc38f17 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11600.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11600.npy new file mode 100644 index 0000000000000000000000000000000000000000..4f4fe197da5412ad50cc42b67cfcd727167808c5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11600.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a07cae835701a75451d8dd2b7281b1d33696af02c9b8e8a96fb12508e3b7723 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11610.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11610.npy new file mode 100644 index 0000000000000000000000000000000000000000..59b9b6036258a9d7545ccb22fa5e940734e38ec0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11610.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29ddb7f32d4673d938bcf1d3a8d017131417534c46f28e1f6dc4fe4fb04443c3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11620.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11620.npy new file mode 100644 index 0000000000000000000000000000000000000000..f95ab787e96fc251aa8d051dd397d3a7400bb355 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11620.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30801d41e543070bc5e471f3727d8673f06bca720dd886bd2e0014594542d4c6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11630.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11630.npy new file mode 100644 index 0000000000000000000000000000000000000000..ea1ce11da312d183f772b710d2bd9598744160c0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11630.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0fdec3b5770cc2d398be4bd9d15513250bb6e1616cf5b2688f3d744a531efd1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11640.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11640.npy new file mode 100644 index 0000000000000000000000000000000000000000..dff9b23af1ec2118538c8ad957215af42a02bc5f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11640.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5ea21ffa38cec31111d898dfeee7c98ddf18f6f0bca9bbf0ef9ea684da4525f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11650.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11650.npy new file mode 100644 index 0000000000000000000000000000000000000000..de209f6522362b8d30933eb1ff1323061b268e7e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11650.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2d802f7bbe19c9d9d9e337630b0dd0236ab04c5cbf02baebee1d582940c6ce3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11660.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11660.npy new file mode 100644 index 0000000000000000000000000000000000000000..8c6969e8a7a4dacf651c872da1f7c88041a9bf15 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11660.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf72b2334df6c544851b3b8852642122b968274319116348491497db5e5a5052 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11670.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11670.npy new file mode 100644 index 0000000000000000000000000000000000000000..76c113ef7ea79d8d0b1085e876be4ae0952665f7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11670.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99d613232d07f64b1a1b74163e387fee10259694c15e643768ba8d69e32c58fd +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11680.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11680.npy new file mode 100644 index 0000000000000000000000000000000000000000..f9fd20de0308e5ce0117702eb30b02f3abd724ad --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11680.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17426e0ffdd0e06b025d86c2a5be7f2c62adb8dea579088cc6f535abd2c45ecb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11690.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11690.npy new file mode 100644 index 0000000000000000000000000000000000000000..8a247503d71e3cbcc05c63a6070ad39a446d0236 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11690.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00df6e1a0bfb01f9eecfd621c1745ba7f631b7ef1f79db55b13f5a93079e93e2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11700.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11700.npy new file mode 100644 index 0000000000000000000000000000000000000000..036badf1716484079b8501b7dce585480032faad --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11700.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42bb8028c4d69b051193b2eb37593673399f95a628ad93c11f6d86dc6425008b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11710.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11710.npy new file mode 100644 index 0000000000000000000000000000000000000000..75991b7b0ed136f2ddccbbbdbb9869c69c6436ef --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11710.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ec8bd9ea639b676e043f8eb5fca6f8dc37e11276663d18dad590e73fd5e2f6d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11720.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11720.npy new file mode 100644 index 0000000000000000000000000000000000000000..91cf9e41a2ddd04658e18859d63a550215862fed --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11720.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46246c36465d2beb62341f72a091f562bc3c98683e5f2c2c13bd96da224c8165 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11730.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11730.npy new file mode 100644 index 0000000000000000000000000000000000000000..c3106a2a0fa02e20af2dae6f150659a40735972b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11730.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d42bb54729358f6efd2e3de825e61506a0abbc916e271e8eb5793a76ab959fc +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11740.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11740.npy new file mode 100644 index 0000000000000000000000000000000000000000..ac913531b4b05661401bf06590b4092b0ffaac4e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11740.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d42ba15d57378061810abe219d41f856cbc517a0c5aaae62fc8f4b7ccb009f0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11750.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11750.npy new file mode 100644 index 0000000000000000000000000000000000000000..d20d38ff8aa78a1b316368b75b09ce9ea5c441ab --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11750.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:215263c9c5d514495048af5697b3af78447099dddd37a8006868ccdfc91368d8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11760.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11760.npy new file mode 100644 index 0000000000000000000000000000000000000000..6b40bcf88745b442b4363db153db7c3c0bc01563 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11760.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1d5994e719444508eebf04ea07750d66ad05b32039f36f3ab0bc6621022e9ed +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11770.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11770.npy new file mode 100644 index 0000000000000000000000000000000000000000..100f8267302ce870050a2ef6f7ee1ec7c4c93d3c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11770.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5a073c36f0c74f5d534008a346d9f92f20c01c669750686fa4e130275e804ec +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11780.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11780.npy new file mode 100644 index 0000000000000000000000000000000000000000..fced99b6d682eeafb7d46607be6c5eac0fd414cf --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11780.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5217e8d140e395ccaecb9cac5704b1c4d896a2f04d4e15260524e2f34050c81e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11790.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11790.npy new file mode 100644 index 0000000000000000000000000000000000000000..3cb0e312972e3207ef905e170210df1aeeddbf88 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11790.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:664c7e4f95dc51bd4024e42f46b82c71e25f77ae4f398e6342f291f8a66b67e0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11800.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11800.npy new file mode 100644 index 0000000000000000000000000000000000000000..41bcf9ab36b42218d020664856c0088d8cee2b74 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11800.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8314069064a6b85da142be9629d61acda58f15abb47aa2133ce61c8e690d91c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11810.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11810.npy new file mode 100644 index 0000000000000000000000000000000000000000..0fb3419a88b63ab01f6e1fef3ab5f97bd708a88a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11810.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8352d0049d65ca2b5c7f62983da85fe6a3fd744b867f5d13aee123f2ffa3ef69 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11820.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11820.npy new file mode 100644 index 0000000000000000000000000000000000000000..84db4c23f818393fdced4334e77b27ed202a0c9c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11820.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c24ffe6a73a15c6f743d1bdcca69717e9337af767e4c5cbafd47a54441c5aa2f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11830.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11830.npy new file mode 100644 index 0000000000000000000000000000000000000000..0d9def8ff4060f0c51314ba6d2fc76859d6949b0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11830.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c47bbff09eaa9791faf47921e201079dced89f4fccae6083b19099e18446d9e5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11840.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11840.npy new file mode 100644 index 0000000000000000000000000000000000000000..8e8f8b478b5554cdf668dc9c51b571044d267975 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11840.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f7b92336148b5b080f72ae48f028c0bd9413c14f9a7940483efdc30917006aa +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11850.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11850.npy new file mode 100644 index 0000000000000000000000000000000000000000..ff9795cd3a1393eba6d1e26d55703abd3b0f96b9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11850.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c05c808aa61ecb5428a7ae75c6d58ae0dd5783f2605468440e8764b982d04dcd +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11860.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11860.npy new file mode 100644 index 0000000000000000000000000000000000000000..e752c59d451746103f38c06c0b753b200807ec03 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11860.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:954cba73f212e191dbfcda1eba10780c38b5b83366c9b7b84cda7af1b75c03ed +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11870.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11870.npy new file mode 100644 index 0000000000000000000000000000000000000000..381c63b4b4409b15ce7ced05851aa438f9220345 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11870.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab31c9307d059b9a5ee3a9e45b55e8b9a8938559a9d86e3e2d01ca893847a30a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11880.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11880.npy new file mode 100644 index 0000000000000000000000000000000000000000..66f7acfbbb997b911a0bdbb6e45813499b4e1a86 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11880.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fa6067ece912441ba418af3a76617d588ff4c4c60ccf579d58d44ea16bd07c4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11890.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11890.npy new file mode 100644 index 0000000000000000000000000000000000000000..e198ad5085474d60c738127bd06a4663dd9fd975 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11890.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84d82fef5d0fb88d2da5ea7aa68fc2447bf4ba6896d9a2e93d5470721d1b4a5f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11900.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11900.npy new file mode 100644 index 0000000000000000000000000000000000000000..befc2f848c4685aa393f1e9b702f46f946ed79f6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11900.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce65c0a24b34c03fe7544fd8eb315dcbf6e42d40449f3a6a953d4ea5a6838ee0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11910.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11910.npy new file mode 100644 index 0000000000000000000000000000000000000000..a33ebf44256e0efc9b53545576fde623dda624cb --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11910.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca3d6606a8e609bb3a1ad0eefb8122e8efad16b82f19573d5178666c2d23ce7d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11920.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11920.npy new file mode 100644 index 0000000000000000000000000000000000000000..773d651fb59a60b697a048eef220981d6a5c2b9c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11920.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a81e200b875296d4dded38a988b4b9f9976e099762ee35b84263378a1243428 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11930.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11930.npy new file mode 100644 index 0000000000000000000000000000000000000000..7915df98aaa41e7bc1e0d491a8713fd1246770aa --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11930.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2f6b873390b35c029d56daea14d2def2e6cc925383d84fc2b8690063f1a5005 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11940.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11940.npy new file mode 100644 index 0000000000000000000000000000000000000000..f920009253d37c33906caec8772a46aa71fb5f62 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11940.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:993694fa0ee4d7453a2adde7d1d3b080dd7ac2cc112c6683e84d67b4479846d6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11950.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11950.npy new file mode 100644 index 0000000000000000000000000000000000000000..ad08017e1e27d39482813da823c861d687ef8f83 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11950.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f596313baeda500a96b00bf66e43fd347cde878d8de5ab9e60e3e87b2e0c7f59 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11960.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11960.npy new file mode 100644 index 0000000000000000000000000000000000000000..ff24ca97d676e746792fd76a5e245889fd4515d8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11960.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ebe8ac0a40efc393fb23a5285641ef9b0ff93458e03922b9435de4351184a8f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11970.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11970.npy new file mode 100644 index 0000000000000000000000000000000000000000..fd7f4061d133b8f95784c579f6992884efdbdf25 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11970.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:169736b5022017fa740fa9d73ffef183014e93ff987bd954c0096c7c2814e576 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11980.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11980.npy new file mode 100644 index 0000000000000000000000000000000000000000..3040813445df436ba19aa746cb0c0b07f3640680 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11980.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52b797c0d8d9e4348ba65358a86cce13c5883e5b7390402056916dde615aedbb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11990.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11990.npy new file mode 100644 index 0000000000000000000000000000000000000000..c2ff6b529ceca5436433da86c20daac892bc4143 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_11990.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a50ad08db52ed2841a11b50d1c5a02be2e683ac622ba377246eea88d6ab3169 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12000.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12000.npy new file mode 100644 index 0000000000000000000000000000000000000000..c5c4c2b289d4c069ef990a4b46302732dc3c1674 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12000.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10a4ecd73073ba25b65cc9ba647d301bfa403737024781b0c48376375f48c186 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12010.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12010.npy new file mode 100644 index 0000000000000000000000000000000000000000..c87bb27aabac40bf65f02cefdc177e983b03bbb4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12010.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13868d0d95175d243303def2ef05b3b91ce1e410907e24edb87bfc3654f7d28f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12020.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12020.npy new file mode 100644 index 0000000000000000000000000000000000000000..29d391f82653318dd02d3d495db2b161c521198e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12020.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e98499d820f9e4da31aafc92dc1327d91ee310f4e3e610d2a66a95c523b779e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12030.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12030.npy new file mode 100644 index 0000000000000000000000000000000000000000..2ab1ce8742744e5cded543f16de96b5ca1c76fc6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12030.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5eb444c4940808be39a852e2c03b1ad430f4142d082d6e4f05c39b70f33d5f2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12040.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12040.npy new file mode 100644 index 0000000000000000000000000000000000000000..9673812e81f8c25fe5ec116331e61d6a4b109d29 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12040.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c78c4a190e28a648e153f8ca189d63950fb6848211ad83edfac6730f3627a5f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12050.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12050.npy new file mode 100644 index 0000000000000000000000000000000000000000..50bdbabd5f84b9e996822c69c5cbc942d85e918d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12050.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91f8d4597e495d5d710a620871b6b4c3e4504bd872f3b22a870e30364f904c5e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12060.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12060.npy new file mode 100644 index 0000000000000000000000000000000000000000..67ffb921f1048ad2fe0ac8b6484ac3ddc5104252 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12060.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2ae3f1da55b969e45d626ad410f341a2063649139ac15fb22203668c4ac26a6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12070.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12070.npy new file mode 100644 index 0000000000000000000000000000000000000000..894c3ed24ab529cef6a558c3d0435d9235d33904 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12070.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9576c205966e51099de00a9b5726715f8c48ef524c91bcdcbe28b0639ba9ede0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12080.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12080.npy new file mode 100644 index 0000000000000000000000000000000000000000..09eaba720263ecdcba34cb318821c3bec8a0bc48 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12080.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:717731cd2a078a7f8bf3e4fffc8713d16e8bfb8ee69f436af683717a4f77a727 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12090.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12090.npy new file mode 100644 index 0000000000000000000000000000000000000000..4101e40a4149e6cbbc64d4a01f613acaa2d5ca6b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12090.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d2d5c8fa0450c8d83fc94553659a87a56c57330b893edf839dc47a3eff76e1b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12100.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12100.npy new file mode 100644 index 0000000000000000000000000000000000000000..072b2e0f56729494a9b7daf011004f1e666b218f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12100.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dea586e8358931ad283570f0fd3739a1e5349a808d6a8fab58d9729b10e7e5b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12110.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12110.npy new file mode 100644 index 0000000000000000000000000000000000000000..43d29ce77d3a07f734209a39ae73eaa92d625b6b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12110.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66939159b9f28510f7743789dd34c19a1cd89032d0c2d2da92e29e8f44852189 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12120.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12120.npy new file mode 100644 index 0000000000000000000000000000000000000000..f48c78eaa4a5dae04b77bf01cc06b4cef1ed86f4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12120.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb10af8d5bbc871b47155d97e9d1a6cef0282ce8569ea505a823a0eea6bddf32 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12130.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12130.npy new file mode 100644 index 0000000000000000000000000000000000000000..f4abe47a5ddc51c05b66d24f9680786fea611b93 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12130.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0097be1a28d7851a382ad90ccec8ad4f251cef7d83d7d56b64ce1ad208559c1e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12140.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12140.npy new file mode 100644 index 0000000000000000000000000000000000000000..17f944c9da05f2c6a574c06e19a4d993c1e5f154 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12140.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5c265b0ab1ab8ed41efe20233fd0245ce73504b1a6643db4e1ca804e4fef727 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12150.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12150.npy new file mode 100644 index 0000000000000000000000000000000000000000..6bd110e8b42b9b074ea2a26999702d87aa8fa12f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12150.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32dcc3339f858b2c205a24f46022d616797870cda1edb038daebc68fcb7d25f6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12160.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12160.npy new file mode 100644 index 0000000000000000000000000000000000000000..bbf631bb79d9036afe5792a43e9d67c018876855 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12160.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de965f5d6961c7f99828c32279ca59cd22245e21f405a78f7f2842a0470ce477 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12170.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12170.npy new file mode 100644 index 0000000000000000000000000000000000000000..f0bf96515aea028717af77a13a4f267419c664b7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12170.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62c9a9da5f0b00bafd98833e0805c73a8c0db73ad853fd9e50f098cd6b85e788 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12180.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12180.npy new file mode 100644 index 0000000000000000000000000000000000000000..26e3f81c317b050b904c2975cba64af92049fe18 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12180.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdab5f25ebac61348a4de0707940dacdb8e89d00956cf33c6f9575ba33bdf5ec +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12190.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12190.npy new file mode 100644 index 0000000000000000000000000000000000000000..60248fa086bb9a87b3067e6310fb7eb6e37966ef --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12190.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17114a80ba8cea22f4b4a8d5d7599df1faf6f8bc643a816b07c5159d515ebc87 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12200.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12200.npy new file mode 100644 index 0000000000000000000000000000000000000000..c9f2621b6b926876c5f57a2a06743f24a8581f52 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12200.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d5fda68c0e3cfb1dd65798b1f22592f2b12f119912811aa06a07ae15ae6b205 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12210.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12210.npy new file mode 100644 index 0000000000000000000000000000000000000000..607ac2b4ec5ad63a1e6e45df2a6666798020b0d3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12210.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbe6696e0280fe3d6f06d06f4fa5d0b86b1651c3c49684e29a87410d2491bd54 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12220.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12220.npy new file mode 100644 index 0000000000000000000000000000000000000000..32ebc7af2fe42236310c8db29cf7b9e82a1b3bb9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12220.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0725bc035ed9b71b4a05827c4ea3664d6d282efcc386b4938e01c379549104dd +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12230.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12230.npy new file mode 100644 index 0000000000000000000000000000000000000000..6210ec5a2983f579fa3eb62eaba1ad35d2aa5abb --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12230.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b64b535a8d908fd71b0650bd0023a861250a6310b69e6a8e1bb94e2eeee8aa8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12240.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12240.npy new file mode 100644 index 0000000000000000000000000000000000000000..de390a716398006ca134271240301a2eedd678a8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12240.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ee551f2491239354a12c34f0b9fe7825308884fbcae046edc5e79804d52b2ae +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12250.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12250.npy new file mode 100644 index 0000000000000000000000000000000000000000..5da6bae3c6b902ffb78f692263e73a6e38851643 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12250.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a629eccfc36e7c4b0a199b294fb86727fec53469474c8a33c9c70372dc4cdefd +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12260.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12260.npy new file mode 100644 index 0000000000000000000000000000000000000000..1c9c25d103da0004f654eaaad2bd1e30ab088b8e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12260.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0cfe4fcb41c06cfa47b62eb5dc020b1879126b7b8fb922318a84aafdb9baf0a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12270.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12270.npy new file mode 100644 index 0000000000000000000000000000000000000000..880255443c2a800cc53d24ddb5545dad9e9f35d4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12270.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f6e4b4acc83eebf8f6b4690088465bd5bda92dcb2173e146311f108ed1e5a0a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12280.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12280.npy new file mode 100644 index 0000000000000000000000000000000000000000..441bd15b763c664cd33019746ee2be4352157a5e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12280.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b4bc8a16677360dc7bd55e8282ba4969d990a5fccf00017a2d00d5a96182e03 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12290.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12290.npy new file mode 100644 index 0000000000000000000000000000000000000000..5c7b281cbadead17ba60c433162c8bb6e650ac85 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12290.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48b910f23c131871ee4aef3b7794c7950cad03c4b8aff0ffdedf062a85be3416 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12300.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12300.npy new file mode 100644 index 0000000000000000000000000000000000000000..674d53c07a62b63a15560fb41e1da79a7126645c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12300.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1016d7980a2caf0775ae1d113b5d16f15f5f9eeed8a997b0aaf41f7799fe212f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12310.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12310.npy new file mode 100644 index 0000000000000000000000000000000000000000..2f2e99cbf68732ce16ecff59ecfc74bbab486430 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12310.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf71f4df7b97bc315a4d3bea1b34cd7539252f480e026d007a76ca033df4a12f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12320.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12320.npy new file mode 100644 index 0000000000000000000000000000000000000000..fb3921b48c87fa8b6ea203b24d467ac6ecff8282 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12320.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f412ae00e0328963cfaf5701484e6601cc5a7076ba33abdd931458b83340ec6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12330.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12330.npy new file mode 100644 index 0000000000000000000000000000000000000000..4f85d928c6817f8bd5d6d6e27f033ab3f509aaed --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12330.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef67855344a1325eeb754a18b49389e784c575d4352bc9c7b3cd5b95c1a11b7c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12340.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12340.npy new file mode 100644 index 0000000000000000000000000000000000000000..504697db2d5b289e8170c2be4185b28178c575d9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12340.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5102687786fa8bfe2551f3b809c405f392feeea9f73ffd2a3c43d4891c60cc0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12350.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12350.npy new file mode 100644 index 0000000000000000000000000000000000000000..e5eed7dde5cc0175041c857a1aabcda33e6a4261 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12350.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:723f5554faf49a80fbbe76b4a6e097b71409ea802e49eccefb03f4d6e64c1e3d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12360.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12360.npy new file mode 100644 index 0000000000000000000000000000000000000000..f52ac4d368560c245fc59339c09bcca4478c62df --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12360.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0bf363b295b3970c5451cdab88128a78d24c65d59b6df1b38e8badfdb9e6671 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12370.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12370.npy new file mode 100644 index 0000000000000000000000000000000000000000..8a946d29f12fa6640704f27f185c34cb1007231b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12370.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7763c44c3dc14caf8b7600c96d880a65d16b672b5fef1a56cc7e899db3240582 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12380.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12380.npy new file mode 100644 index 0000000000000000000000000000000000000000..9358a70b12746d02ca06b1df6ca25bb5aad3c81f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12380.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30974a6b23b938f57fc31f5a62ca110aff38262d0064d52de11aa1294e6d02f2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12390.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12390.npy new file mode 100644 index 0000000000000000000000000000000000000000..dd8e4b22ab3593721dcf97c63ec3b3377d303222 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12390.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de7f3a0becba48e2f9e8370fd08769cbfa4c48b8e73a0567b2905fe0f7a930db +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12400.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12400.npy new file mode 100644 index 0000000000000000000000000000000000000000..739977e9d5f3e2c0e539d3dfe10178eda9aa825e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12400.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b93319f0584a787221b60249cb71fc77bf211396190a01a40999d039559badb0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12410.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12410.npy new file mode 100644 index 0000000000000000000000000000000000000000..235dbc640c6756a4dd260bbddff4a3076dd1f0b2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12410.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7af21c36f6586e0d9840485fd9ff0675af46d12c9b49ed10a4e0a4870d699290 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12420.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12420.npy new file mode 100644 index 0000000000000000000000000000000000000000..61945ddb5e70a1410923255e97ac98745b60af1a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12420.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a02b4fc72d1c9b5be224813068c92b47920aadfb1786a5530ac9509425f43bc +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12430.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12430.npy new file mode 100644 index 0000000000000000000000000000000000000000..cfdeab223f816f1283fded59b1ec865a792a0b82 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12430.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db2bcd7c824789668f542b088bb2c5b769f599a4fbd210a96050a8c57a6701cb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12440.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12440.npy new file mode 100644 index 0000000000000000000000000000000000000000..0485d80fcb9f79d462c8b6cd6436784759e21282 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12440.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd14d2c8974abeabfe28640f318a689f42e651e6c9955ae32123286109bdda7f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12450.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12450.npy new file mode 100644 index 0000000000000000000000000000000000000000..303fde20109f189e8368eeaf7cd53cdb651c2f51 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12450.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d69dac093b69d725545cf096b369167ede04865d1f1363c5d4926578af2d2f99 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12460.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12460.npy new file mode 100644 index 0000000000000000000000000000000000000000..e513dc3287e09c6721bcaae4605e5ccb039e434f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12460.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6fcec8249d38ad5ca70648b1ff3b952a9ee1eb5c87102d73498ac25a5fe6fcd +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12470.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12470.npy new file mode 100644 index 0000000000000000000000000000000000000000..df2637898596968854f8db40878704809dc89def --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12470.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fdbcf64bed574644b0df168373b941e19dcbba827863bd00c90f2a76acf5f9f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12480.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12480.npy new file mode 100644 index 0000000000000000000000000000000000000000..41c03f0df5d0108728b88d155cb2a7a64216a6f1 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12480.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b6938e274ca9734c4aac44c2347a55d77029fe7f6ec5c503ee2cdd8c475b176 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12490.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12490.npy new file mode 100644 index 0000000000000000000000000000000000000000..149b1ad383ff21c9bcbee38f002d0e8a4a52fc52 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12490.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:396a9f5641be016068b6dd77ca0550dce212a84c3d184fa21e2d5105b5c67b79 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12500.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12500.npy new file mode 100644 index 0000000000000000000000000000000000000000..6774dc29408c379d48513c4f776276a54b1ed797 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12500.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b9b73d7b78f0fb460a344c52e040b27451d8b03062c197369c0d040fc21902d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12510.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12510.npy new file mode 100644 index 0000000000000000000000000000000000000000..008a9d5e7e6b56ce0f3b4a6fa8015a4f21c7c471 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12510.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52948e5874c1be6d214b1f25c10d0ac77c3c8dffcc7fde6fa06f7b227941ec26 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12520.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12520.npy new file mode 100644 index 0000000000000000000000000000000000000000..35175bd8a7977a4f868476d845df4ed08566528e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12520.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99c729c9cead5eff9b918c5b5d153152c61fb20fc5b6b41faab399b937f82a9f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12530.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12530.npy new file mode 100644 index 0000000000000000000000000000000000000000..a402780ddcf6f9fa7919d07c879ac5339caf3609 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12530.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f2762d2a5e5be0bd12f667f34eb2862650bfc7f69b7a03c48fd1bf175d5d2aa +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12540.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12540.npy new file mode 100644 index 0000000000000000000000000000000000000000..770b9ffcbd59f3893b8163c3c78859b259be9812 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12540.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd685736a38caf28aeb7498204073fe85c322be8dcc3fbc3cf93511ed0f205a8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12550.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12550.npy new file mode 100644 index 0000000000000000000000000000000000000000..29db8e4e45a64345e9a6b6db9379d3e551266cdc --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12550.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26c27a80e11b3bf8e2c52d5d03a977fd466e473576ef2b5ebe9788682483e5d3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12560.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12560.npy new file mode 100644 index 0000000000000000000000000000000000000000..f898ae447801930aee979199890645df3fde72e6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12560.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77bea55dcba9dc7142926cbb6b5ab9eb0550fe7d5cf781ce4e8c37edfb2fa7f1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12570.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12570.npy new file mode 100644 index 0000000000000000000000000000000000000000..2c268f6a65ae21fff705745de43417a55f6c42ec --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12570.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32b26d16978378324f218dca64724c33db6b90814c0b950e73f048e0d3040e93 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12580.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12580.npy new file mode 100644 index 0000000000000000000000000000000000000000..a8b2d682e6967aba102ad4b0dadcc761aad93333 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12580.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:441d2c7aa4d6a80c6433ec83f62e68076ec922d3474bf874fc9427b97054b7a2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12590.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12590.npy new file mode 100644 index 0000000000000000000000000000000000000000..ee108a7339c8737cdf100263326ae27a4415dd0e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12590.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:366aec30bc66bd13ab611be6a5715175fbcba2adb80c4f1d73d83765b3636b0f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12600.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12600.npy new file mode 100644 index 0000000000000000000000000000000000000000..3e7452f2df3ebcccf4f999a27332e98d9bc0857a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12600.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc32f10bd6efe2db6bd888fbf256803b1e1f1517440551baf79e39acc4195cbe +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12610.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12610.npy new file mode 100644 index 0000000000000000000000000000000000000000..e22eed0527ac3b2445d624510f3250ce5b676d15 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12610.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d245eb269b05126dece56314de598cca66c458081f891219a5d73b2ae8f08eb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12620.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12620.npy new file mode 100644 index 0000000000000000000000000000000000000000..34fa116d382a22fe26fc01b77dba6ccaf6a9c544 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12620.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82250c8afbc02c817655b552245f9c42ea8298fd372a1826116198146ce9760b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12630.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12630.npy new file mode 100644 index 0000000000000000000000000000000000000000..d6ee32c1ceb8fa7e8e3a971177cdee766aa41591 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12630.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f7ea24c26934b3bd4e21fc5a65757434ba1b2aebaae3b00abf4674d81d83445 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12640.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12640.npy new file mode 100644 index 0000000000000000000000000000000000000000..0f8f77356dcc20e74e955ecf7c73c5c5ecdd8708 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12640.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2be70ee6b06f4fa450909b6d65fb57c052dc84083380cedd404539e0109963db +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12650.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12650.npy new file mode 100644 index 0000000000000000000000000000000000000000..c90c87bab623c7ad788f4c6ef008d668946fcd0e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12650.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2f915cd98a06398192cbba4ef24db360c2cd8752930c2e65ff90c9a155a371b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12660.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12660.npy new file mode 100644 index 0000000000000000000000000000000000000000..46043d4931a6e5e2df20ac5a68d7dea1f412cadc --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12660.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb82cef477ed311b2ff7d550e07fc58c76cca0ea8c498e08d0902245fae8c933 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12670.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12670.npy new file mode 100644 index 0000000000000000000000000000000000000000..9ed6628016ae9e71bb1442a90205f51f1f7bfecf --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12670.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de9386d5d72da91b73f196deccaf3fca8afa4769dc048ba2d8bfd2b1a803e684 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12680.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12680.npy new file mode 100644 index 0000000000000000000000000000000000000000..eb0cb487e2f0e50c28037df8f720783e842ed821 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12680.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9f74710a635fd0ee201616662c4fc7da8109c37e8a24720375aa6dcbc6237d1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12690.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12690.npy new file mode 100644 index 0000000000000000000000000000000000000000..c83d8e68c3794304dfca66b8c17ad889baa72ef0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12690.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b470cd6d17e99aa1d1c60373fff15fdaf54d697e1f1f337702cc36c07d5e0e21 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12700.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12700.npy new file mode 100644 index 0000000000000000000000000000000000000000..fdc6277d229a0daef0208f5e09d9c973c47f5c84 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12700.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3522450f08d79cf0b1bcae3ee21905ce3c4ecde74f97279a3801f971e5d22897 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12710.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12710.npy new file mode 100644 index 0000000000000000000000000000000000000000..ceaba9e34d1e8722c112140bd7dfea8dccbca69e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12710.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1beee378e4c033ed65129730a10853ff9684dc7b9b0d46708dcb0bb7d0d187b1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12720.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12720.npy new file mode 100644 index 0000000000000000000000000000000000000000..ba4337530e60b2f4d17263df609a040e84bd9cf0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12720.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60cff815b9314b54cee0e3a1d33d1d69009390517488b8ec406961c6b1f2186f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12730.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12730.npy new file mode 100644 index 0000000000000000000000000000000000000000..f22ec5daf477712bc1aec3b2e20559f775de1318 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12730.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d545bcfeeab4056ff93c55109f45b25f17ffa7d963dad5e610b565cee069153d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12740.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12740.npy new file mode 100644 index 0000000000000000000000000000000000000000..4e9c585d0b33f32ae43c247c9342e42f14ca2722 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12740.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7070d934b65cf431bb95f700ff14cc6362c82b71560c9b79a6bdf983ede75da +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12750.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12750.npy new file mode 100644 index 0000000000000000000000000000000000000000..f356addf3114126ab1710312653385136793d1c2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12750.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:225c9c6d180e8949f8d814c87871bc74d2cead4feaf28149be8965763b3e8fd8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12760.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12760.npy new file mode 100644 index 0000000000000000000000000000000000000000..5cabaea9ecfa533ae31cf001089b92c79be7789a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12760.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:212117fccee2ec382be4a86d937f48086a8959a0a6804a27d86ab2fe53a4f324 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12770.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12770.npy new file mode 100644 index 0000000000000000000000000000000000000000..0bc7da99fc87786cfbc442d9f6d15b05dfd28808 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12770.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f5faa52e603c03c7dbc070f2cd16f48398cc31d737580f2be0a1fbe5557b4e6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12780.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12780.npy new file mode 100644 index 0000000000000000000000000000000000000000..c29a482ddedb871bba09e27ef151636470312194 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12780.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:358fc03bd7de7572aec142ca187d9b698d59b7be9830e11a31392408f7995deb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12790.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12790.npy new file mode 100644 index 0000000000000000000000000000000000000000..5826e946319f3d4587cc26d0686e01f0718d05f6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12790.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec63922b6e944ebfa859561ee62c49020313c40a099e33f7840fe18fcaceb899 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12800.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12800.npy new file mode 100644 index 0000000000000000000000000000000000000000..79d0fdf1f22d802304e34a987d992d15681bfed9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12800.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd98da07f8479dbdbfc88a078f175e83de5cf5dbf609760bc12bf646d2ee131a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12810.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12810.npy new file mode 100644 index 0000000000000000000000000000000000000000..8aac1401b509030b9bd413dec4735209006015ff --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12810.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e37533c860c452dc8668c8537896895344887ba567d7b4e4e8c026fc05792f9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12820.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12820.npy new file mode 100644 index 0000000000000000000000000000000000000000..08d5375f8c0e060857154697d8de7254c48ecfb0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12820.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e5933fb763a4f809af216d30b9bd6ab731c73b1e5dd15a4c0fb533b6dc33542 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12830.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12830.npy new file mode 100644 index 0000000000000000000000000000000000000000..aac1f14c32fd790d8772c8bfe5e9019b632fe9f3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12830.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d603f7ca58483b945808d6d208323ee6548e1c94beb71c6225d0bf234a3fe1af +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12840.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12840.npy new file mode 100644 index 0000000000000000000000000000000000000000..1fd40afa09e4b74295b69db66e5303067cf0ef73 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12840.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ad4942eacaa52f6322e893ae3e6f10e87ee60772e5e23b5882f4be43dc79005 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12850.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12850.npy new file mode 100644 index 0000000000000000000000000000000000000000..af75c3d0ceee048fc2c588de6ec140135341b024 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12850.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:722effd42b628a691ceafc2ce6ad979ec16a9fc7aa12e79e1a6e432944098931 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12860.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12860.npy new file mode 100644 index 0000000000000000000000000000000000000000..ac233e36d317e3f33094a9f757cd97d81490e729 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12860.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:332002fa7241825a517061644b6b43644f74d5cc7ce4d2efcee74ac8d979c0a2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12870.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12870.npy new file mode 100644 index 0000000000000000000000000000000000000000..48531311f570a6a5fdfe242bdb57428828a7f6d0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12870.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1040ee5851562196e6f83914d2309a58d21fcc25d9e7f6a13c020d7d9c89c60 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12880.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12880.npy new file mode 100644 index 0000000000000000000000000000000000000000..dca0a388f9f0b41f366b1883694bb6df2dbfcb95 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12880.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87dd39f0558b0f16178547fdf98b98b6db5ba14a3affaf4edca9fa52620d868c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12890.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12890.npy new file mode 100644 index 0000000000000000000000000000000000000000..1296c842cf62f97a4d31beb6e3ed5be8d45bef72 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12890.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5b7781456c135af7fde993ad3e8b36a1f275ec3ab8f21268694faea52272add +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12900.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12900.npy new file mode 100644 index 0000000000000000000000000000000000000000..076b25c02991a7d6304956acd4c5fd77ebe8b028 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12900.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84164ce90d935e896402c0229be47c73e52ddca0f12be65274d76eef844eed27 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12910.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12910.npy new file mode 100644 index 0000000000000000000000000000000000000000..b68de075d09ff99d8e7ecd578140d0e6562410e4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12910.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cb9dbd2ff2e331f85873bd33bc11614674c6509108dabc4f362adf5d96c940a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12920.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12920.npy new file mode 100644 index 0000000000000000000000000000000000000000..61cef4b31b4a8323f1ce15d17c04f3d1472d9a05 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12920.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:858bd3a87228f523e52bec71a4a7ea6a0cec41a5fae13344caf804d8c9f96a9f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12930.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12930.npy new file mode 100644 index 0000000000000000000000000000000000000000..761d8185e9dcd70c73c8cde5c77ce323242da37a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12930.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c14dbafff9f0e6a087c057f655926ccf5a3f12bbf55c679f0ad8f1435143fdd +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12940.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12940.npy new file mode 100644 index 0000000000000000000000000000000000000000..3ae8f9e26ad09a39054c21a1a4eab844449da9c3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12940.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dbf5e073486076724701ea56c216831f8758dcd3b1998339b75076c960dd3a8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12950.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12950.npy new file mode 100644 index 0000000000000000000000000000000000000000..8cc476de1634a6fc7b6ff4c28b35084a18a85133 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12950.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19a3c562ecbf2b566b452113bfe3a4c90fc66b968c6fd0380deb679cf4959191 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12960.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12960.npy new file mode 100644 index 0000000000000000000000000000000000000000..9aeba157da3f68b38ab65b6e79f0a0c5e0c2ccb3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12960.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57a6decc2d8f6763aeb64f8a321890ab6cd6ad63303ffc04497c0aa79a2a478f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12970.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12970.npy new file mode 100644 index 0000000000000000000000000000000000000000..1f718e1c166737f8967ab797a1bfa26b6f278c70 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12970.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35a0bdc31251106581c568a1fecf0b362aa1d46707fb7e754044a5558ca4a963 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12980.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12980.npy new file mode 100644 index 0000000000000000000000000000000000000000..d68df2333615e2699d0d620f91e97720160b2380 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12980.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15856c5db0d6dd3c60c5966db93ece4f976bc41ffae4224274fadedeaf624c2e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12990.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12990.npy new file mode 100644 index 0000000000000000000000000000000000000000..62b1dbb10191dab383d6face80e6d5656d738ee4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_12990.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28e3ca45478ef7d30ca006302aeb9cd0db33db76aa64b93c64b9571e7180c3a9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13000.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13000.npy new file mode 100644 index 0000000000000000000000000000000000000000..a73aa75c424886458e9aba3ec5062bf273aef2c3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13000.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb18c7975f36b1e38d28e4ce027b19610017486ae04fa4823d978b9d3b92a813 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13010.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13010.npy new file mode 100644 index 0000000000000000000000000000000000000000..7d11db4b58d072cef43a5265663187346a709c61 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13010.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b93a4c93ce6858c8192887a6db758bb1f492cc576ac593f5b0dc65247df4896f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13020.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13020.npy new file mode 100644 index 0000000000000000000000000000000000000000..8fd0cc2e5a49e9b1c22caae6517997e7b9bf0b30 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13020.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61b116fb183cf323ff3514414bb424a90e676295d3a7de436969000440c85c7b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13030.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13030.npy new file mode 100644 index 0000000000000000000000000000000000000000..4b766355c47d41d214a4c158b03531542403df91 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13030.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd667fe94a42119cddfebb013a7d393e5f2ffc275afe8bdcb58544b7ad0189d4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13040.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13040.npy new file mode 100644 index 0000000000000000000000000000000000000000..dd9d55d7297c80e8bc1a3bca1cb8d969765e8d5c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13040.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba2ab77d594207970cbef1e45eda88e5d684c237dfa649bff2756be72f6408c5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13050.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13050.npy new file mode 100644 index 0000000000000000000000000000000000000000..9b555763f188d21a37f677bda8c220f039d23b3b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13050.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73fda00856bf140455efc073acb447c33ab9492aef21a94e8bf2230f6cad760c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13060.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13060.npy new file mode 100644 index 0000000000000000000000000000000000000000..134b0528c5db22eda52c0053a26f45f96f13d10a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13060.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59d5923ef544bf7ce138e3f898a5bf701937e9f801f2f2a7e6bc139f8d9d15e0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13070.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13070.npy new file mode 100644 index 0000000000000000000000000000000000000000..e4e0a940f9d07b9df4e197dcf52daf9f51a471f6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13070.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0f84a62fd5b1ec0232ed94dffc32302748118e70edd6fc55864325d822ca112 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13080.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13080.npy new file mode 100644 index 0000000000000000000000000000000000000000..dbd0a259933602e8af1c33d6e7bd77d608dccecf --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13080.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8dc26cd825f6c30c482f5dbf10733834fc57e90d2fe2dc0b71ada9e2257b4467 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13090.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13090.npy new file mode 100644 index 0000000000000000000000000000000000000000..0f34e49f51c59a9ab42c04b5e9682daf21eadd52 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13090.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21819128f4f3dd2ed758c014edc4937c03f27df531b36f1fc3be542caa5f2899 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13100.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13100.npy new file mode 100644 index 0000000000000000000000000000000000000000..cb28fff1c59caea7e32d7096ef2539398dd4b754 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13100.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe78522bfbcc5d526b8b598d86d2bc029ffefb3934a9c749e3d5e76266d0d9fc +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13110.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13110.npy new file mode 100644 index 0000000000000000000000000000000000000000..a8dd61419420cbf77c4e0b3d58a0a10225c57409 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13110.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c482fc4d775170495bd05b2ef903963b49b909d9b26b8b3746b39b9397dbbfa +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13120.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13120.npy new file mode 100644 index 0000000000000000000000000000000000000000..183c9d77dafc4c2e981044223d62fdce42612a6f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13120.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41c006c7971c6735e0567213d79aad7e293049c177689aaa5e0d22a6ebca71b4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13130.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13130.npy new file mode 100644 index 0000000000000000000000000000000000000000..7f93d57f541f7e8063aeee0a4b42b4b7ca4c1c95 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13130.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3e58d7e68c08bc092ea50852b947743695fca026c41ddc14640c64a76181041 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13140.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13140.npy new file mode 100644 index 0000000000000000000000000000000000000000..1e57128ff466fe0705b1e98c63dba21e119be9d8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13140.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ceea7e52bd5e09d8d53d10d26d3d071ee9545ae85901e2f188252f750377d4e8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13150.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13150.npy new file mode 100644 index 0000000000000000000000000000000000000000..12b854169a9b0cbc0b5e5d7668538c874a344900 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13150.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fc6b5f6dc632f510130e6636241d27db8edb23dd265f1821126b1b1c69c84c7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13160.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13160.npy new file mode 100644 index 0000000000000000000000000000000000000000..61db8e213c7138df040a7ce978fb927eeda27e7b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13160.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:854a79f19fd75ce4f75b8856fea2ccad0515b607064eb7e8e1a8c1664f4c28b8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13170.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13170.npy new file mode 100644 index 0000000000000000000000000000000000000000..26280adc26a4fa452b06fd6dc9376147a0a87034 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13170.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76a7cfcf92211083254f2a0f2e3032c8fa21dc9bf5b215b4dbb0e0726ccf4771 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13180.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13180.npy new file mode 100644 index 0000000000000000000000000000000000000000..2ad02f6df7d78813780f39073b41eebc25ed51fb --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13180.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0095d372cba69bdb0ccbd72bbdf2f49fc47dd9e11508e789602df01c8283c724 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13190.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13190.npy new file mode 100644 index 0000000000000000000000000000000000000000..1402f649174c8ff2feef5ad6c4146577bff477cd --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13190.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bee91200c7d5e0371ad9b8b6729c24bbe3c1417f3e6702471af87cb5c9ca650 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13200.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13200.npy new file mode 100644 index 0000000000000000000000000000000000000000..8fd239f48c9393164a850db52f93c45dbb950c81 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13200.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4a74c12705c870151d80c4aec013c5c8fcd7cb5a09a2e72e824f9eaa4d7b675 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13210.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13210.npy new file mode 100644 index 0000000000000000000000000000000000000000..16e82c271693b7e6fc80f77499620606997c19ec --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13210.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:844b022cb9c82db2be16dce1e8587924463caa01121b7d833026d9d36b4b6ac6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13220.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13220.npy new file mode 100644 index 0000000000000000000000000000000000000000..813f2e37c8e07ac89cc90d3b7c50ca9faed41fde --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13220.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c22c6021e9f68a972b2bc0c07e7589de5b643020561b0ccf8eefe9e28d6d6a4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13230.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13230.npy new file mode 100644 index 0000000000000000000000000000000000000000..89652a4432592fdeccb916a1dc8f02c46981df63 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13230.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d3e9e554d9bdc3893ef8f350ef80ee3e6d0bf76d376db667079809f2e016952 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13240.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13240.npy new file mode 100644 index 0000000000000000000000000000000000000000..07982f713647f6241b97229416fe9fd6b7ebe12a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13240.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd753316bc719b9dda7d3ebe4f3818467dee25912c6b1f3a427ec114a62b99d3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13250.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13250.npy new file mode 100644 index 0000000000000000000000000000000000000000..5645ba76b69cfb21f76d981836e4c0a4834f3ad9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13250.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d54ca568d918202da99a479cf734c6e1896f56d96a1421cb08a86855f7ffe2e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13260.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13260.npy new file mode 100644 index 0000000000000000000000000000000000000000..a5c45b7e33efc5ac709917e5479130c35c698b64 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13260.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e515887f3cfda4a4be1c5f16c2a058335da8e719fae7c1924c90a323303b304c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13270.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13270.npy new file mode 100644 index 0000000000000000000000000000000000000000..0257b3f66bd7044495bd34ebbde24fd956ebe861 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13270.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b5ba448ea8bae9bf526b2cf7e32f1550941b1a4062074ed02336c456050af2e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13280.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13280.npy new file mode 100644 index 0000000000000000000000000000000000000000..1fa5b9e16dad22034ca16ca4f7f26f4f467ec14e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13280.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3815370b7f850b6483eaef9f62fd3afb132d1e7d31ce451255140bb033321cc +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13290.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13290.npy new file mode 100644 index 0000000000000000000000000000000000000000..d15786bfbf0078b3849776a17d28d5075db7372e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13290.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2fe65c319ddc65db733a874deb62079f977efd54599c8fb0f13805d161fe7eb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13300.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13300.npy new file mode 100644 index 0000000000000000000000000000000000000000..09526504b115335f2d2ff4f611652faa3020abd0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13300.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4697ada6b1b64ad83737a0f7fd7f1c98f532ddb435ea6c342c1ab76b2a692008 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13310.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13310.npy new file mode 100644 index 0000000000000000000000000000000000000000..140d53b51a086627e82a51e44909103c636ad8e0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13310.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7888cd71c5f725b2c69726f0e6dc061e48b50049586b010e7c319d13bcae9d25 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13320.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13320.npy new file mode 100644 index 0000000000000000000000000000000000000000..020a54e68c7c0fa5eb2ea9b2ae374f01da514e05 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13320.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8555ce07b3fba9b20146ae5154835bf3b41f1bf43f4cca98dcd70547cfe4cbfb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13330.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13330.npy new file mode 100644 index 0000000000000000000000000000000000000000..b658b7509eaeefaf738f4036ff2cc3bcc7cb576d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13330.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4ebf91b0787b06014d502ca9a8f8a54c55e9eaf1e0af27eebfe3e82f1a62bad +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13340.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13340.npy new file mode 100644 index 0000000000000000000000000000000000000000..630f430cd5a6b2aca902d4e71189eb2be509ea8d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13340.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9601123cc64b0e2b55783c199b148f66e06e362d1b24ba31a9df741a95b3c65 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13350.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13350.npy new file mode 100644 index 0000000000000000000000000000000000000000..6aed52fb1478a9c25a301177541d182d5c449607 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13350.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60796bd6caf347f1d98a2880395e43ea33a2a90e570d5f473bff340db60b4326 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13360.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13360.npy new file mode 100644 index 0000000000000000000000000000000000000000..d20df40067c8efe2017e45fb40058288a5f1fc8a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13360.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f11502f3eaa9526d52273f043c85b4a28653ff3f19f354b5323efb4abf8e7bf7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13370.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13370.npy new file mode 100644 index 0000000000000000000000000000000000000000..24fa55a6040c91cb46b73c9574015dc6ecdead76 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13370.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bd8fea6d93d81536b120d5e97e65438d388f727d0acfaac5a2a4bb35aa467f7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13380.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13380.npy new file mode 100644 index 0000000000000000000000000000000000000000..f60240c931dc9450d773a6bcd4d658c2a124d53f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13380.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:051428e7c65719538749c73cd547c4c17cfa89f103013aa7dc4d68db2753516f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13390.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13390.npy new file mode 100644 index 0000000000000000000000000000000000000000..fcc284da7751672f492a8702c52e072bdde5e882 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13390.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:193975a356dc80b00352afdb265f35f0aac15ea3481cf7df1a4f078eff76f1f7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13400.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13400.npy new file mode 100644 index 0000000000000000000000000000000000000000..b728d54bf98ea73ea50b801f48d1e4a68ab3f8a1 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13400.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62a1c7a50ef444b141f8e7adf65db76af14a80f3f3713003421d9721e38a0af4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13410.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13410.npy new file mode 100644 index 0000000000000000000000000000000000000000..e6acb57221ecdc2dea1ac2a307f989c3ee7e70bc --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13410.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c69c010f9f4cb81c9fa941a03f84327764419b983360089c6b70a3410f1377cd +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13420.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13420.npy new file mode 100644 index 0000000000000000000000000000000000000000..1ff44a3fdde948c53734e9bba360c642915d2878 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13420.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b59f471bd6f6113d9df45da0a65082324adf1756ce1eeeea2b5394af709a881 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13430.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13430.npy new file mode 100644 index 0000000000000000000000000000000000000000..2222e7aadf409b684efc0223f3f3d75af9bb962f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13430.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38970054a64d43f00beec4e8db92773cd234a916433a0f0486881e14acf94095 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13440.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13440.npy new file mode 100644 index 0000000000000000000000000000000000000000..27024ffaecad44e2fec16071f16b63188c9b2b1c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13440.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22cdbacfffa26e5e7f50e48763491a2428e08f7b91d8987b3f8ab3ba8781f822 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13450.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13450.npy new file mode 100644 index 0000000000000000000000000000000000000000..d2b74f3495a068357f29d6178009090b81cf541a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13450.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab17c71276f5ae4f6424057ecc23e1620b77caa2ae805012d92f49ad1d26dedf +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13460.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13460.npy new file mode 100644 index 0000000000000000000000000000000000000000..f9ff9f37cc34849b64b66ccc92049b56a6734d8d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13460.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5823463e90590ea404fbf90ae4a83fd5476b02588cc80e9e5e21ec41f6e683c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13470.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13470.npy new file mode 100644 index 0000000000000000000000000000000000000000..9ea319c70657dfcaeb64c57456a972c777de454a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13470.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85ae47df9a7ec7d5ac8f7fd673742d40856cc7ab0b17cc90d80f39dd6ab9479b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13480.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13480.npy new file mode 100644 index 0000000000000000000000000000000000000000..7c79e0e76c4e5a14d1739e7aef9126fbec72e3da --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13480.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1f2e03fb284c9135e2f3ed9a4baed4dc69a748d4a55574404e61c4fbcdb4135 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13490.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13490.npy new file mode 100644 index 0000000000000000000000000000000000000000..9a998700ffce9de41e3033283f0f74b0d581b0e2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13490.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce633d0b38d40ffbafe7186e7f67bdde4093f4af193dad2c20723a5e6680dab1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13500.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13500.npy new file mode 100644 index 0000000000000000000000000000000000000000..0660f58b2be2c2c2991b7c0608e7d66a45ce0527 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13500.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04126c8993b3c2ab657a066f6b302f2f4fd3f65291fd724b3127d97ef3f69937 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13510.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13510.npy new file mode 100644 index 0000000000000000000000000000000000000000..1fb166200f191ad20a26f63e1b307c1e91dc2707 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13510.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8f1b5e5b662953fa82e15da370d370798c1cfcf802a90e0b81c48f6106df7a3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13520.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13520.npy new file mode 100644 index 0000000000000000000000000000000000000000..5adf2faff4deb03304efb1a2d7f03f89619dd81e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13520.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3a0df462e18e90a041c4661e6f4a229cce1f04f35a962f23ca6136b5670ae42 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13530.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13530.npy new file mode 100644 index 0000000000000000000000000000000000000000..624b458463ca23fd0d5605048b4f85ba30dee2fb --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13530.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:457cb727c7b2b037c2f0269741670621bb29027b7352ac8b3f264239162ca132 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13540.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13540.npy new file mode 100644 index 0000000000000000000000000000000000000000..51eace45771c5515d2656b34cf13269beb4fe64d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13540.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:198a770a4788adbe5b3b9f60e3a51271be854eeea515e3f4c076fcc67132a985 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13550.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13550.npy new file mode 100644 index 0000000000000000000000000000000000000000..6ceeff40e76c386256c58d671f8c9f44ab7e2623 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13550.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2160623682092f8e24284838f093d435d212d668ae6022596f5801d9760186c6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13560.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13560.npy new file mode 100644 index 0000000000000000000000000000000000000000..026e97ace86a7f449201ad46486794f0f8d25dff --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13560.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c144fdd31782211b75a7db75eb0d151d8bfe697a1cd234c8dc2f73114215d62b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13570.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13570.npy new file mode 100644 index 0000000000000000000000000000000000000000..ef34430c95f1a64780c6ecbcf5f6c5ae3c4e13c4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13570.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:448ee9cebdbdcc046df77668fa3fc3876027982cc1c1daad30a6adac0800c59b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13580.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13580.npy new file mode 100644 index 0000000000000000000000000000000000000000..a50c4c966b381804613970f5ff779b0fdfb582dc --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13580.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12cbd76f4670a813683f8a49a496e8d7f6cec8f514b1752b6c88287b9566e527 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13590.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13590.npy new file mode 100644 index 0000000000000000000000000000000000000000..24823d7efb7888216c9fb43b2dd856a2d1f0faeb --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13590.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48a41e0dccf9e7eb89166bb325d7f70a82c4d848f764b0b93d9200fb3c97123d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13600.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13600.npy new file mode 100644 index 0000000000000000000000000000000000000000..916979553499afd2ddb49563cd3d46d78d2641a7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13600.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b17131ce68a6955d69772b322486e9300c27a481743d124dbe28f2b64ccc4288 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13610.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13610.npy new file mode 100644 index 0000000000000000000000000000000000000000..5cc9c2af765e94f43d021e09ac486aa52d560e4e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13610.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06471ca562b12db7c7539c9d9bdd08847d18817b83a6a294ad8a2a793e540c62 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13620.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13620.npy new file mode 100644 index 0000000000000000000000000000000000000000..d961354ff646ce122c6d7bdf2c7ca6594e70df13 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13620.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78cc0cbd37f8285408f2b40293592d0efe8c1701cd80cc198596b081f010a066 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13630.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13630.npy new file mode 100644 index 0000000000000000000000000000000000000000..ca1c6e86ba52d078d80ea56ea0b86bf96ef5f5ed --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13630.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31de9d59d5a208f981b4dbf9a0a7a1a2780fc197392f5c7e8464a8cb35567759 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13640.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13640.npy new file mode 100644 index 0000000000000000000000000000000000000000..bc0039c6d9ccf9248efa19c250127bb6df42a90a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13640.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5298e283cb5e24a05b6c2535b1eb4220bdc50ab17578c70ad048b0c0e26db0d3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13650.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13650.npy new file mode 100644 index 0000000000000000000000000000000000000000..9ef5977cc6d8a6bf937a2fefec393e222c5ce21f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13650.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d88a630125dc65e7b0318602ca0952344b3707d9ff3a44f0dcdfc094b1bbf69f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13660.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13660.npy new file mode 100644 index 0000000000000000000000000000000000000000..fea6e36921f26278f13ac9f99079daae7eb3495a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13660.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f207e3a512787c9fe3adbb487530e7f03c4a6ad5b5b2ffde6b06981157db168 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13670.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13670.npy new file mode 100644 index 0000000000000000000000000000000000000000..d0b814fd148b954b01aff863b4f98b28086143fa --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13670.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7b0cec997770a863faf8054f43deeb6df65c86f04908e08b55012e9d78b7c8a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13680.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13680.npy new file mode 100644 index 0000000000000000000000000000000000000000..4f744b0e369b9ea4554fd055986a279affee6596 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13680.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fef3f439246d5e338da7d5f105521ab912391fe4b49d43919fe2e776f6b2451 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13690.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13690.npy new file mode 100644 index 0000000000000000000000000000000000000000..4fd76110dbdbf7775c6fce7df595fc39820651ee --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13690.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4de8439234567a52014e3075f19dd5e0cf634d4ab81320607b5e0c8150e105c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13700.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13700.npy new file mode 100644 index 0000000000000000000000000000000000000000..1a56b47d01db50347ce7a96860d01c3d2f65227d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13700.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d05ab5b4c39fda364df7a56d164cef54d29547086a47ea170bb4015a229d8a20 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13710.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13710.npy new file mode 100644 index 0000000000000000000000000000000000000000..2adee014d845d40dd1ac6026dac6ba9845193932 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13710.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9aae84aa90d7da9455eebdcd3f740160694c72e8c7fdf65a0d057007347459d4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13720.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13720.npy new file mode 100644 index 0000000000000000000000000000000000000000..328d9fb0a3bc4d9ca8aa2e29096524416696f23e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13720.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fb218795242b774b6f97f0993b8c71b9c0d9045a6b979c4b71215fe62197304 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13730.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13730.npy new file mode 100644 index 0000000000000000000000000000000000000000..ea46830101ad795d74f67e422f40f690f9badd4c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13730.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:771b3a75d35535e6b542d86a0edc934a85290788ec12aa1e5c5ff380381022e5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13740.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13740.npy new file mode 100644 index 0000000000000000000000000000000000000000..c98df891e6ec5b982db85d8d06e74b011d15c6a8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13740.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6bef7740044ed70aa7383c7c6e389e6f70d3bf9e394abd2495ea56e63ecb306 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13750.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13750.npy new file mode 100644 index 0000000000000000000000000000000000000000..4deb01bfcaaa88d35794c8d4258691206683531b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13750.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f144a5dfbbe52796b25d3d32ac9fa44347a1c6f10860ad96b7c342304b0b1add +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13760.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13760.npy new file mode 100644 index 0000000000000000000000000000000000000000..7b4bbbbc921ce028d8cb8ee96f6fa76d73b53347 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13760.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a721749cf786353d67c132ee2e6cea255f7fc5eb8f1a941a25c1a1b754975bd3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13770.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13770.npy new file mode 100644 index 0000000000000000000000000000000000000000..7da029adc70c39cb21f63c76a76c0a90dc1bb0ae --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13770.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f7692fdf841e75df823173ebe6a61a086bf2e5679e3a7ff2c6d59b84c18242b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13780.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13780.npy new file mode 100644 index 0000000000000000000000000000000000000000..b4ab4a9cf91cf08255f2c8b08867e069ad427fa3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13780.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:086771f9c28597c4335665db77915912f11e0bffdef7978c4dca41fba3c8e5a5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13790.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13790.npy new file mode 100644 index 0000000000000000000000000000000000000000..9374e384e74e76762f639684fc0c8641f5cc8875 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13790.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09e725ea7c7c22bca66f78f15eb9828faf56d09b35fc111606e554e0f6969d74 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13800.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13800.npy new file mode 100644 index 0000000000000000000000000000000000000000..c17435a3732bdf54242e38d0198cf90459a4c82a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13800.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b878fe095a6cec1c5c1d0be9f30d68ba4ba46ef4e3b667d665f41b0087ce495 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13810.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13810.npy new file mode 100644 index 0000000000000000000000000000000000000000..97b978f21c6339e6448aa8112c884c52778d77c9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13810.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd716c005cf08c84cb4d793ca721af8d8b67225e4d3f45cff85e1aad98c918b0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13820.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13820.npy new file mode 100644 index 0000000000000000000000000000000000000000..ab5d68181998b62344005066272a31d8f6cd7f0f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13820.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:329fac771d009b20d73e7a88da8ef7e5655b0eb1741f6318bd4fc00c3569ab31 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13830.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13830.npy new file mode 100644 index 0000000000000000000000000000000000000000..b4f810f3f3094216a2b96eb6b3ebfbc46cc21a9d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13830.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6bbd9c592fead59cb1a896c131884d522eb56cbb837827d360ab5592b420256 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13840.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13840.npy new file mode 100644 index 0000000000000000000000000000000000000000..5d1fddd062b152ac243014cdca8057a1890600f3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13840.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65e72ac46c8c0c726130cd9b99daf8604881fa3e86d8e3940b66ce231f371566 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13850.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13850.npy new file mode 100644 index 0000000000000000000000000000000000000000..e5e813a1df05484f889bc4d9b30bb36a1c29c382 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13850.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8e477345960cdea244fa87750ef2360a81593966fa580b7d4454deadb0cbe23 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13860.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13860.npy new file mode 100644 index 0000000000000000000000000000000000000000..22e915d98f6345a5a5e477c835dc10250a5835ce --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13860.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:074632d0024660bffb2cbb61ed7427599e280f1267d6c716d47b9ce1839360d2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13870.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13870.npy new file mode 100644 index 0000000000000000000000000000000000000000..eae61e5cddbeefd0ba205097bc66cab1c8c08059 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13870.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c7acbd742dec7d7076590d29804f28883185d98b46b46346368d0644843b801 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13880.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13880.npy new file mode 100644 index 0000000000000000000000000000000000000000..fc139c8c3c283aec3435a07d8994e05207e71c85 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13880.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbbb30e3360e612c70803e2e81c045120d4e92d78022869c3c5d1f72a85ef754 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13890.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13890.npy new file mode 100644 index 0000000000000000000000000000000000000000..8251a668d15829054a58bffebcee881f8d312c3e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13890.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4151281699a5665205df8c841a7275ef4cae8c7ef368ab4d026c5e99adee1378 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13900.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13900.npy new file mode 100644 index 0000000000000000000000000000000000000000..972e8a3b28defc73d7a559e86a594e46919c1e59 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13900.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:096f5bfe576087c82fc0201fb0841f080fb71362fb7901b7a565ba1cfce75a47 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13910.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13910.npy new file mode 100644 index 0000000000000000000000000000000000000000..d61e966b41f8d0371db1f20adf894642f90dcc3b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13910.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:049443928680a1ff69284f69b23c50abef0f4887e7a2fe0f63ca8da9af8f8de6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13920.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13920.npy new file mode 100644 index 0000000000000000000000000000000000000000..c5066c01c3958a906dcc8561a3e914ea25fdb86a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13920.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33303333e2926a581bf63187be2341f623dc370b4a933d1b8038f2a675c6df3e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13930.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13930.npy new file mode 100644 index 0000000000000000000000000000000000000000..4c5db1a0dce54332b4e07203a4ae1b7c4f05f880 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13930.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c88f0967386626b62ee303923189fc06bb84a8de8b007cd0d45d3ee7f8996cc +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13940.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13940.npy new file mode 100644 index 0000000000000000000000000000000000000000..4fb5cf841302df7010d93892b2e58d916542ff5c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13940.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd509855bd7edb45766dd2a1a52154f473bbb3cee133ea0fff10dbb974772714 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13950.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13950.npy new file mode 100644 index 0000000000000000000000000000000000000000..b84f2ed43004369c681481b3a9d10765c4a9a8e0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13950.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7a59cf7606dbb1986440b7f0012d4b7b5891ab6b0229ca20a506e45ddece162 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13960.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13960.npy new file mode 100644 index 0000000000000000000000000000000000000000..c0a225134283a39cd85bb894e9afc6098c898638 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13960.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a4714269ca7f6cc5b0a257ac8d9e932774217bdc45325944d6925ac8f93d78a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13970.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13970.npy new file mode 100644 index 0000000000000000000000000000000000000000..787364cc582e32b6bb5b70ad89c731bf850170be --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13970.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1991c415eae461cee58b55b704e97e705a528d09916911b8b033c268e950d2e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13980.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13980.npy new file mode 100644 index 0000000000000000000000000000000000000000..b6a5ff63ded6c217da57d048085bec7684e71daf --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13980.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1f96afb6a406f8083d641a54e0c03359f3ed660182d29769df3da677c4da506 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13990.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13990.npy new file mode 100644 index 0000000000000000000000000000000000000000..be858f1d8ad347c98c736b93c34581d8bc403ba6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_13990.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc044aeee8eb00c49b530fd9c95392bb9c34fc8cd6a033d86904b83d461ece56 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14000.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14000.npy new file mode 100644 index 0000000000000000000000000000000000000000..a03bba38ba00307e877b9adc67caf570791b0de8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14000.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f5b46356b902ca6bca67918bd808d87fcc6ad79cfaf291e4d49aee67549285d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14010.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14010.npy new file mode 100644 index 0000000000000000000000000000000000000000..9544e53615d4ec8363b2f6965de985f266a8a74e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14010.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2500293dee8eb401905c2461bff22fe77fa05fc4bf9d5bd085a8017692b7c874 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14020.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14020.npy new file mode 100644 index 0000000000000000000000000000000000000000..3315e1783554ec8cd53a30be6128c83f00d9973e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14020.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9795e596c510691880be03d331dde57a8588d2f993aff8edc9032c3f36753f05 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14030.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14030.npy new file mode 100644 index 0000000000000000000000000000000000000000..38717d9164cb334bbf1685951736602c29cbcd43 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14030.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b72ca771ffd1626b7667bdf10ef214928e4c716458707f2d01221516ee1ac8b4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14040.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14040.npy new file mode 100644 index 0000000000000000000000000000000000000000..6afd85c13cadbb6db856c9dbe83a5353a84bdf6c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14040.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae01b4da0b0b29533bc074976e5047347f2b6936261867146cf7d9772efb2078 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14050.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14050.npy new file mode 100644 index 0000000000000000000000000000000000000000..171a363ea6eeaabd0a163792fe428037498e57d6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14050.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65c1697ad34ddfe519561d75e685b45c48f7eb68ea6ac6a497c0d29f290f2af1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14060.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14060.npy new file mode 100644 index 0000000000000000000000000000000000000000..c3ae151e5f090f3a5a90d3d23a0f6916bf31b03b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14060.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41ad9a1f3b47a214670ebb4fd287bf3cf161a830747410190c4fb9cf4d1944bf +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14070.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14070.npy new file mode 100644 index 0000000000000000000000000000000000000000..c7a5f574839b282f1d912b97494d5820e86b1771 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14070.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23df8058f3a899848df73e1339188131b8186389302095f8ebee16978bf8dce4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14080.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14080.npy new file mode 100644 index 0000000000000000000000000000000000000000..375540824075cf8f46261a0bf57444fb4610bdbb --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14080.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc97069b06ffb995d8328c6bce3a0591b39d22415d73b104ab07a50290a20f49 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14090.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14090.npy new file mode 100644 index 0000000000000000000000000000000000000000..2ba12ee8507f2120a3de4297be50efa520cb96f1 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14090.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c648e84512225cdea571d270ce21f6d73d41ebd70d2e154e1f98acd5521d297a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14100.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14100.npy new file mode 100644 index 0000000000000000000000000000000000000000..fe1be516b3b95094442e68e35f9579e8e2fa7ae4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14100.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a9598f19f7ec2ca088ca6c51881ee40db8cc2e193cf8d44cc8b12a1de5174ec +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14110.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14110.npy new file mode 100644 index 0000000000000000000000000000000000000000..2f24a83fbb96660108b8d56c37946664fd7ad04a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14110.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d56add49644b6228031d13bf1f3eb44268be401c442daf607cb5de7b29e55bed +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14120.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14120.npy new file mode 100644 index 0000000000000000000000000000000000000000..9486c7ebd1307b2abf2701c808955c9104b81632 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14120.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8aba40c488d199c7a48a797101a75bd360a0b4b7ce7077901f2c64b744c40efe +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14130.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14130.npy new file mode 100644 index 0000000000000000000000000000000000000000..a45fcad3151c916d7890d9eb5e467960c0efb0ed --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14130.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fce4355a0065b06fcafd5de1a5e6539b32460b13f33e4b7d662c43f17c7c27f4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14140.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14140.npy new file mode 100644 index 0000000000000000000000000000000000000000..fd6cb39b8e542a8a4a40c02a0efde0ee344e2983 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14140.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e1f051d4d1f2402df0113647720d48c64165a6a39b8e4943d8d2ca9ebead377 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14150.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14150.npy new file mode 100644 index 0000000000000000000000000000000000000000..27193a1478d44e64be3310315a9e2dcbe1d0a615 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14150.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3cdc6d5b7de79e887fafd3907cd14841930bcb77bef06977c7d6ac96712f71d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14160.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14160.npy new file mode 100644 index 0000000000000000000000000000000000000000..e526556e6bd5257f99a87134899ef2caf1362abc --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14160.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e55eaed2dc1dd809b5793fa9d47353b2a45d774c5d6bee8bb79a4a807332dfa +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14170.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14170.npy new file mode 100644 index 0000000000000000000000000000000000000000..e81047cf35225a1e29289a4091436fbbc4d60b9f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14170.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:110e49f8fd14b44fc69eadacd1b9572e89075176ab7062b38583fb3ec8ff016c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14180.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14180.npy new file mode 100644 index 0000000000000000000000000000000000000000..54e482d856042e2304970a96785df6b5fc8d722e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14180.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:087f3baa8768c4d9662645889417bad66941810f00c963dd86a039c5da5d87d2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14190.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14190.npy new file mode 100644 index 0000000000000000000000000000000000000000..75d4e1b1bf79cfcf0bdaf6678bbeabd8d83a887c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14190.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc2ea8e6afdcf0e0fd9c55df8e74b3b934d2bc00998e496a5dbd2ec3e49c088b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14200.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14200.npy new file mode 100644 index 0000000000000000000000000000000000000000..d18bd64df85429e055a917485ea05b91500a4a09 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14200.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6264a3df167f9b55a3eb326f941a0d0360a6da8be450a3373d805ef501f5c62 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14210.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14210.npy new file mode 100644 index 0000000000000000000000000000000000000000..ee824b6394a4226e4ba4c3930648f89a74fc2101 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14210.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c6a065c710137032dd0dd9a255519b065aa6d500a8b3580243a8be347801ad9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14220.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14220.npy new file mode 100644 index 0000000000000000000000000000000000000000..7a7fb2048a8dc4a45b6336774e79c46b23dcda6d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14220.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c61d88d76ed6f0c8bb5a714f616ecfa607ef710520d6ac6caf781d78e045e40 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14230.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14230.npy new file mode 100644 index 0000000000000000000000000000000000000000..ed5f41e9a2e0895e928e2f82520d0a4d62397a77 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14230.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84d1785b8ef3aeeeda0d41c5ab3dcc096cb41926d0e2c38db10627ee5cfcf916 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14240.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14240.npy new file mode 100644 index 0000000000000000000000000000000000000000..b87e762e0bc56954e0f6a40c0264724dce4a0e25 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14240.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bc1bab38837e4c0227f00e2974a11bac869550421b803f1c1d8a06f7b6bf2b3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14250.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14250.npy new file mode 100644 index 0000000000000000000000000000000000000000..1d59d291970fab91ce141434741967bdab2a36cc --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14250.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0502659bdf983fba4a1037fe5e661bd4f1cb5db96264565b2dc1e79847facab +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14260.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14260.npy new file mode 100644 index 0000000000000000000000000000000000000000..c622178f16b233e5aff7bf6f065e38f56ae4ecdf --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14260.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc75a45b8855b3e58d6927d7382344d0767c50d7f38751e8bc9e9c8bc7d85f1c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14270.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14270.npy new file mode 100644 index 0000000000000000000000000000000000000000..f7654ce047bce90ba6d3ef3ee7f0f880455daa84 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14270.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:635de86d94778d6834d059f3edb1303d5204238065841569517e7513f40b5d42 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14280.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14280.npy new file mode 100644 index 0000000000000000000000000000000000000000..cca48ab283153307458d945a39c414f75948c2a8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14280.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7f67e53fa64be7d298ad3fd59fb2150a01d11476b3cd1d9ef92e9b9dea80e32 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14290.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14290.npy new file mode 100644 index 0000000000000000000000000000000000000000..a0b60208190c6af371e1ba91efde638f58ae47f3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14290.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e12abd77f8cc7a9dcee344a6d70cfa6c30bff409d50a26e154d15f6a87d9014 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14300.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14300.npy new file mode 100644 index 0000000000000000000000000000000000000000..c5d280942ce407f43851a8d64e7360020cfedf8a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14300.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0649394166da02b4e5d705161187661a395e160f3e662b1ad875465718a6008d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14310.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14310.npy new file mode 100644 index 0000000000000000000000000000000000000000..6d23dca9a964f146c06e10669b632734ddc5c330 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14310.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:241177524ecd1c7afcf3bf22a960ea73cfe0d4590626e3514d98c98efaab67fe +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14320.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14320.npy new file mode 100644 index 0000000000000000000000000000000000000000..748dbe2d060368edcc9b2cc42d94bedda96b1cf5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14320.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2954200de5da8ff2aa487598fe3a14605b8d8f9bee4591ee0eb0294110807eb5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14330.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14330.npy new file mode 100644 index 0000000000000000000000000000000000000000..9da8ac34e9c31f9ed0b632e36f5295edad5a66a5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14330.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2685512d4b8e1e6c5f9104310570234ba3eeed11bba4b23c1ed0c3060103889 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14340.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14340.npy new file mode 100644 index 0000000000000000000000000000000000000000..f71de5abea8b4fbbbd1c533edf4805c7fe7714e5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14340.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09f84cfceea07b861e22eb8e607832089d8091689e11506eaa696df761257714 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14350.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14350.npy new file mode 100644 index 0000000000000000000000000000000000000000..65708d51045a890b2395005923cdbe780891af7f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14350.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:490844f059e118e7e88787126608b9cca4f3396ac5386433fe0bc939cb3e4ca5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14360.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14360.npy new file mode 100644 index 0000000000000000000000000000000000000000..0868061455ce40ee56d9773846bb7a8bc773b142 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14360.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c7a9c0d2348eb5043d469fb6f60faf0c4beb5b7461cd74a1e7f8ce60fe7903a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14370.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14370.npy new file mode 100644 index 0000000000000000000000000000000000000000..9b3d1e7980177c5f7d16c37ca3577c9ae0a04f32 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14370.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:977a941eac227f4595cd4003ce6eb8e46efe1d0b4129b977107279206f028957 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14380.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14380.npy new file mode 100644 index 0000000000000000000000000000000000000000..c0065c26aefdf49e9253cf763d969ecd9bfdb1ef --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14380.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3efd0429ce3227914342b0a49864c2bc5c47d1e62452dea41d8a1a13da9f67dc +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14390.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14390.npy new file mode 100644 index 0000000000000000000000000000000000000000..0ffe5b9870bd122913b03e4cf9c104773561d733 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14390.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddc67ecaa668646320438b7438ecbbbfabea3f74a7dda9d4d054227cd33b33cf +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14400.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14400.npy new file mode 100644 index 0000000000000000000000000000000000000000..a1e369da99faebf89b2aaf690b405d9764254294 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14400.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bae258980946bc3f6256e85d2515d1aa27a684b36122318e18844a3fd873bb2b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14410.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14410.npy new file mode 100644 index 0000000000000000000000000000000000000000..740135806839ef7c950e1c500038e0643a4e1370 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14410.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ce9516caf2beeba0552aa21af1ebd6bbbe6c6e31645eb6a4a0d64c0a7bd6061 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14420.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14420.npy new file mode 100644 index 0000000000000000000000000000000000000000..457e9e90b69929f8060ee6b725d4799dcc97377c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14420.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:264085ed413e23e12cc0eff9610ebea054532fd455dfdd9ecfcf5c26bbce9cd3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14430.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14430.npy new file mode 100644 index 0000000000000000000000000000000000000000..7b6ef56596f6e0fb71da7d1f470722de08a158f3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14430.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daf7b7c87bf1a9272ac38c19313f7c7b9f5e4d9e6349032d9439224649f369e5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14440.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14440.npy new file mode 100644 index 0000000000000000000000000000000000000000..495ccac4560617ca8541aa384f897cd969e042ed --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14440.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fb1ff9d749895d20451d9481cd5130d30cab5babd1d306d49836f9e75399cb5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14450.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14450.npy new file mode 100644 index 0000000000000000000000000000000000000000..24f701f017b00906f3e603973ea96bf5861c621d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14450.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:520753c225585b9ad8f1bfd1de7fc3da0328efb736c403c47099997bee05f816 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14460.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14460.npy new file mode 100644 index 0000000000000000000000000000000000000000..5c5cfeb29fa6eb9ab2426b1bc2ef367bd4d34509 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14460.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:553c4a90df1e989644663321e4aebe4aca9734ae10878d34318dd79d0713e147 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14470.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14470.npy new file mode 100644 index 0000000000000000000000000000000000000000..8cd37b2716797dd3f5ae75945a5aff7dfac90bac --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14470.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd3c1e729fb2340c470de40b056a4b0e45ef318ce524dfce58e05825f5daa863 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14480.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14480.npy new file mode 100644 index 0000000000000000000000000000000000000000..f71f86c2bb39a5d5ae22a25a156e683c5b5083b2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14480.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6af3c81e2c5a690e72d6afae9bf83d88a6659e50514524716ebb262caa32ddf9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14490.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14490.npy new file mode 100644 index 0000000000000000000000000000000000000000..9da7a53c9664c6ce707431c0aa308077801ed911 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14490.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:196a81a0997e93a19cd448101a37d64efe0e6b9d4db08e92f957c0905122baa8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14500.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14500.npy new file mode 100644 index 0000000000000000000000000000000000000000..1dfd18e08c1dd6e77d7877391c3b89247bf4e989 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14500.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a65d2472eaf076c45c3279eafd98a816d6ae62a6a897b70d8b04312d45c71af6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14510.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14510.npy new file mode 100644 index 0000000000000000000000000000000000000000..645dd5b3e123e71874bdc69ab4e47560161eafd1 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14510.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7e8e4b698dfab25f1233a5a124ee7bf5843a1141d0befd22f7f3cba4c681773 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14520.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14520.npy new file mode 100644 index 0000000000000000000000000000000000000000..75cae3e583be55cec59f68c24923c40587ff9236 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14520.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2697e2fdb414d200f7a731693fb7f6d1f4c9d11b3808df7b3da337cf4eb7f11c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14530.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14530.npy new file mode 100644 index 0000000000000000000000000000000000000000..8262e1bf95abf1be1a009ae414259a7c74d005bb --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14530.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8367045429d7b0881db7cc41dee0b957c8cdd54a2f2e8d59543f0bbfa2ee88b9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14540.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14540.npy new file mode 100644 index 0000000000000000000000000000000000000000..a6d32650ff7c993a848fcc21e21e08c101eb3704 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14540.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0191a8d9ee3d3bca9440aea169d1ddd4add2598081f15082c98436f3482ef2c5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14550.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14550.npy new file mode 100644 index 0000000000000000000000000000000000000000..5ed6a54db3a69c5906a68bd43f210562c2d2b4e6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14550.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ae18dba49ad592952ecf67fbb87ac684ee0891b543cbe452946fa9464ad7937 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14560.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14560.npy new file mode 100644 index 0000000000000000000000000000000000000000..5b46513d803f4c98557e1d751737e6f3340da5ba --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14560.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8eb963a55e97d2a9ad46991389f689a92b1160d0ba14b2565a77e708227d5656 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14570.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14570.npy new file mode 100644 index 0000000000000000000000000000000000000000..3a6f36ea4d4d567cec9526149967f5db10c688ef --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14570.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76db96a8b9cf2463622a10653d9d0d727517ae50408fd8a33854902b826cba2e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14580.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14580.npy new file mode 100644 index 0000000000000000000000000000000000000000..4d17adab63b4096379f0e92e0a12df2a78250c0b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14580.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1048f3148918a8465dd60d8a77e72a1df7525658680a375ad5b51a18845ae9bb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14590.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14590.npy new file mode 100644 index 0000000000000000000000000000000000000000..b182045fbfa52a8f7f834e6b647669e31cb413b0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14590.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b909f156684949c1e60ff6cd48b6a5a73301010eb40e6f9f4050c11f52b9ca34 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14600.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14600.npy new file mode 100644 index 0000000000000000000000000000000000000000..c496b2f1574f02465d97800c67a2d9b6eda0b1b2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14600.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2cc14d13b4d63597dfc5470314f5e471cfe0b36655a6d4d7cc02a7a89593b34 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14610.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14610.npy new file mode 100644 index 0000000000000000000000000000000000000000..8b3dfb2f6d1939877a63defb769a55487e45380d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14610.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4432b29640ea2beeeb8a3cf837a586e52aef1b10eaba979e437a005dbb2b54a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14620.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14620.npy new file mode 100644 index 0000000000000000000000000000000000000000..64c765902393b0a4ab89efa90db18487f794f2d9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14620.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e29cdc3d3a4228b0f45dad7a5f3a44e5cbe82587946fcd5ef31536a992224096 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14630.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14630.npy new file mode 100644 index 0000000000000000000000000000000000000000..c5933e01d468fb0d531f11892c2842de18803dbe --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14630.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3509aad53bcf12542dd17abacbf1a4f56e37182411ddde588b964b4d250ae36 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14640.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14640.npy new file mode 100644 index 0000000000000000000000000000000000000000..406237550d67e98f8ec69f116ff0a76dc55dd920 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14640.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15c735e3e93abcf87ca393f2d756061d7d0c30ae28ffd7866eef73641ca3ca17 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14650.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14650.npy new file mode 100644 index 0000000000000000000000000000000000000000..6eda5ba51c129e4eccc134b4e4e3e5bf3a12a803 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14650.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d81c8fe59874206b6cc23f0d9e4d0628c7dffebf77f93e712d5a526912a784b9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14660.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14660.npy new file mode 100644 index 0000000000000000000000000000000000000000..0bfea75b3dd1aea8301bac5da53d961980954573 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14660.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7dc56d0f1f840df79930b98b91c2192f68c48c636dc2ff794fb7707a8e5028c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14670.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14670.npy new file mode 100644 index 0000000000000000000000000000000000000000..e6e365f6d9b5cf8c15384fc32b32ef097b98838e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14670.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e20a706d3df0bccab907adc827c7ac91c0aebf96ff5383797c2e0a9edc6949a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14680.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14680.npy new file mode 100644 index 0000000000000000000000000000000000000000..0daa487b5095d34440113314986172d1454f7249 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14680.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c44e15c75d10200fac68b0f1734c22ada5e0ef69aad9fca8033e6326bce8250b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14690.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14690.npy new file mode 100644 index 0000000000000000000000000000000000000000..2f142850fba7936462ad22f28042d1d2fce103f3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14690.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7189d5d0c0a82d4a3a727e9e93e8072b7f9a04b3913fee976e5b2b513c8467c3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14700.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14700.npy new file mode 100644 index 0000000000000000000000000000000000000000..b48fdf719beefeb98c9e9b7b53d706490c02ba85 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14700.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a46168a45afd6f1c32aad6de5da3c8203c7467799f43f30b2fba733cd32d4dd3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14710.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14710.npy new file mode 100644 index 0000000000000000000000000000000000000000..80cb9f311c688c1a82996f05685e8a3a36a1f8b7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14710.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78e4e3892eaffb3afbbb1b01df98667d8c091e4ee0e590fe4c8ac20e79377bc9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14720.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14720.npy new file mode 100644 index 0000000000000000000000000000000000000000..ba94ff4048c454d970c19d24932ff13b486d16a8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14720.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:830d6b67a621d62cb95f1da3c2474e1d5ab019537a46e8f1f1bde0e56afe5d08 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14730.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14730.npy new file mode 100644 index 0000000000000000000000000000000000000000..52fa4118dde7885c9bf94d35dc01e30a1bfe0c98 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14730.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f1973731397e75dda0eb9b2f8fb2dd50ee289009775cbbd8151de7002de8078 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14740.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14740.npy new file mode 100644 index 0000000000000000000000000000000000000000..262fe20a376adfc23653741f2219e60ce425e5b3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14740.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e0ba2a9b56cf565385487362e83d66452a7821bb04167599efdea9966dc0cf3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14750.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14750.npy new file mode 100644 index 0000000000000000000000000000000000000000..c50b42133604724c648f21273d71d54afdb596d6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14750.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e08c4d3fdf35938f51e5aa2b32e29d890674755e2e52f2bf3bf364cfb72013f9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14760.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14760.npy new file mode 100644 index 0000000000000000000000000000000000000000..100322358da06bca43776c2e54cf743b17b19467 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14760.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50cd35866c213beacc370210a1e1f24424ad5418cb7d285eba36bc9e4229ab98 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14770.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14770.npy new file mode 100644 index 0000000000000000000000000000000000000000..e0caf9feb2e5087f7ae0f3ca8eea007b3a9c8a05 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14770.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31bda2e3d1a5a733969771357c8cee820997e2d6ff54fe6da035cea4156ff2ab +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14780.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14780.npy new file mode 100644 index 0000000000000000000000000000000000000000..353f787f9de76e1a284dcf42e9706bef2c0f4276 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14780.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8d99f508754dfa0e4a74d6d582df39d6c59e3117505dfab9044ed8f0913010e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14790.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14790.npy new file mode 100644 index 0000000000000000000000000000000000000000..c1336b8fc650af9ae970401e2f0112235a5423ce --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14790.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f94a3844e3cf638c0ef095d7443e3f51d3adf4d80b173911b6a3464e0a3d241c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14800.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14800.npy new file mode 100644 index 0000000000000000000000000000000000000000..0adf6aac6a11da425a2b1800447d5870676b5a48 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14800.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34e2eb2ee77b54bacae093dceeb4bb8417d7361585e6a7150d8c105b2928cc9e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14810.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14810.npy new file mode 100644 index 0000000000000000000000000000000000000000..9f2e9721ae26597c8b042994bb84a42f2cde2963 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14810.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9466b386475ed6ea5bc984cb4fe0c7ce461a4099e59940126cc6690710d3972d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14820.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14820.npy new file mode 100644 index 0000000000000000000000000000000000000000..2ef9f217949c55127c0433f2a3f4e05e87d77c4b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14820.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c04b4f758e0b1430d21cfd47d71471b6d855babf59932c7502abf68dfce8cdff +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14830.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14830.npy new file mode 100644 index 0000000000000000000000000000000000000000..1bf5ce48441cbf1f50e0af1bb7d4d5e4d4f6f9b1 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14830.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f87ee0d9828226b5a0875fc3a564ffb41520cbadccae954f134eef250af758c2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14840.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14840.npy new file mode 100644 index 0000000000000000000000000000000000000000..4b20269e2eac386672afcf7ddf4e8e9c5548a1b3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14840.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:107cdacd5a86f7c258468f1b083ee848d77672615dce081cc716d73b26403b54 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14850.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14850.npy new file mode 100644 index 0000000000000000000000000000000000000000..51ce85a3bf58f6a45e88f63f440a2f1fd5dfcc96 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14850.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4b3a2669c92656d317bd894a331625869e726e3db8195394d314397faacec68 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14860.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14860.npy new file mode 100644 index 0000000000000000000000000000000000000000..16f7f7a32c295148f7b4fd446dcafc62f27b89e1 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14860.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47a0311e1d7d0621005f44c93e3d61aebc20c4f88c26a186c08fa34ad15c4acd +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14870.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14870.npy new file mode 100644 index 0000000000000000000000000000000000000000..c896f69079d1f0f6bc6f5a13dc4d86acd5de5f54 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14870.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:896c89846ad8b4bfd587cbe3c43645441e1bfbb3db5fcca98bb726e99e7b0876 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14880.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14880.npy new file mode 100644 index 0000000000000000000000000000000000000000..f9c28fffb70d78c561a529fb912216a02a8ccd5b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14880.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a33f73970b3cb522d70d8ff210a9e1a46d1109c6542f38d2312d7935ee245c38 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14890.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14890.npy new file mode 100644 index 0000000000000000000000000000000000000000..d3555022c31f58096dd48674ffd872abd321767e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14890.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afb5793348a553e358388af47f4dd38113745c75c80b15239b0707bd83a9b300 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14900.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14900.npy new file mode 100644 index 0000000000000000000000000000000000000000..47378591ff52dd0370b455b4c13b6fcfa92eb8ce --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14900.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f398fc7e519b5ff8f43759fa2d39ea539ab619cfaa5d3fa4db90424db4200a7a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14910.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14910.npy new file mode 100644 index 0000000000000000000000000000000000000000..f852c349307abbbf176133eb691cce3e2e96b112 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14910.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afe2f25235710fdcca709146077e282bcf467b22bb1240a63e2bf0bf8e801d96 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14920.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14920.npy new file mode 100644 index 0000000000000000000000000000000000000000..ece5971bef50e43e7de2f58312975344916e77ab --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14920.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0484b23f9a97311bfb93a86eaa90f53cfeceaa3cd1f4e70a6cf8f0c2b3cbfcb5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14930.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14930.npy new file mode 100644 index 0000000000000000000000000000000000000000..a5f5df5801b530399564d0816d10a995bba813ba --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14930.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5eb12fb3d91875ee36c394de279fa9917afb0acf4b82c09faa7e5224170f6b61 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14940.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14940.npy new file mode 100644 index 0000000000000000000000000000000000000000..0ba2c59103283a24d74c41abef54b211ccca21aa --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14940.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb28b84ff7fe4679250c5cc5387af38f65999bf89c9268f8cb0a62e3680072e7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14950.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14950.npy new file mode 100644 index 0000000000000000000000000000000000000000..3caf7029ed4d8525fab8014c457fa301e46886d4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14950.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77f9d92a5322cd838552f3aa93b19580c695196a897d27bddbd6cba5bd7ff418 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14960.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14960.npy new file mode 100644 index 0000000000000000000000000000000000000000..cdf4ad353c66a480ea8201e0e1a989e0c3cc678f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14960.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da01cee3e5bad579d076226b30a8699c7d1d1ab0bc6035f17e63214a0ff88283 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14970.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14970.npy new file mode 100644 index 0000000000000000000000000000000000000000..631dd9687dc1a4a962d587b99a0a647a5849fcca --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14970.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:717b452d7e53b0b9ab833f31fbed515db13e566701cf77511f022f527d3767d6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14980.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14980.npy new file mode 100644 index 0000000000000000000000000000000000000000..6e0390524a0f11a4ad33240abef212725edbe9c7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14980.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25f868a779236a99c7676937fe68de6aa062f8447e652d87022a28decd0abc36 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14990.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14990.npy new file mode 100644 index 0000000000000000000000000000000000000000..807f1bc13d0f36bf0971345cb40d8c666d375ad5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_14990.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eac02df72197a9403d9a28bf0a0752c3ec1a92f48cf2a1c6a65202d907d529b2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15000.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15000.npy new file mode 100644 index 0000000000000000000000000000000000000000..a946e090ec58452685a858666fc94bdd3470d920 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15000.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a76b267baac9aaf23c343ed45dfde1c0a12a9d1536a6b6291ad87e3d111ee4ce +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15010.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15010.npy new file mode 100644 index 0000000000000000000000000000000000000000..3319afec2c23f479e6ca2de85b6df3bb7faf00ff --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15010.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2346efdc6ca18089e839bfd94e8198c4692f93e2fecc64709a24c467a603dc3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15020.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15020.npy new file mode 100644 index 0000000000000000000000000000000000000000..17c6099669a7a901937d7ff289eb1b5aab520c13 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15020.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da6c4ea2fef2421db87648b53cc255e4ffbe445339d887a4b6c0352643ff9296 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15030.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15030.npy new file mode 100644 index 0000000000000000000000000000000000000000..296e00d8bc16099f3e124b02da7e3f469fecd97d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15030.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86379e1b1767b5468de6e62d667348c2d5f0ac4517dd8e905359e1cb60dfa379 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15040.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15040.npy new file mode 100644 index 0000000000000000000000000000000000000000..51d50bb1ed361ebc8e5046780f46fe0fcde7c214 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15040.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01e1468418e8a7cb5001632a1764fee030e68a7949d46b0db480acfc5d62855b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15050.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15050.npy new file mode 100644 index 0000000000000000000000000000000000000000..6eafc57bf97dcc4044835ad5c8eea508aa96f6f3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15050.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:350ec376985fb138d11e9443a8cd25c9bd0425719afd9519bfc561c9f2b262b9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15060.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15060.npy new file mode 100644 index 0000000000000000000000000000000000000000..5915f0238365bc1e0bbb002c5db6cd4c6676027b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15060.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef6aaa04e49cce7c9905ed16a063a8b4a7f8f3b8b2a13c288bb6060bbf85dd36 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15070.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15070.npy new file mode 100644 index 0000000000000000000000000000000000000000..b98fb557036ce46cc40e83790984f085bfa24144 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15070.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fd70cfd7ecfdcea6698e22e2959dcadf144e98aa4c327c2976673aac7717704 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15080.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15080.npy new file mode 100644 index 0000000000000000000000000000000000000000..f643311feb8b228552cf821d992f80198c93c877 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15080.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0a1fba95d2ffadee224bb022659e26dcd830f5202c3d762685a2f90f3c1a47a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15090.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15090.npy new file mode 100644 index 0000000000000000000000000000000000000000..2f02a11821e01ad04524a5940f31e389776e2c81 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15090.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc025c3170772304087ffdbba6909d02d589bb1bad1115ddad4d9f1ea2eb54f7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15100.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15100.npy new file mode 100644 index 0000000000000000000000000000000000000000..7220eb5c4b08382ce1a108dfa91bbbf041204481 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15100.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c48755d55c213de2bca96e357452708bcc027bf8d44b9fc7980db97e45e1001 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15110.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15110.npy new file mode 100644 index 0000000000000000000000000000000000000000..ad3492ee156d6141a81d0d589fe0823ce84555cb --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15110.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78842f9409f1acc5bd156e2fc1d65aad1c31b152fa3d3bb2604c1df44afe0c58 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15120.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15120.npy new file mode 100644 index 0000000000000000000000000000000000000000..c1acf7133717dba29d75b65c974ca8c5b12252bb --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15120.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abb16f8e05b8048a84f42298660ddeade4e0f487e953ad2467832949ff05df3a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15130.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15130.npy new file mode 100644 index 0000000000000000000000000000000000000000..fc55b9cecd535597aef4dad54dfa7c80b05eaea5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15130.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3ee285a92f08af9f6f03e37dfa345fb958a774919d334a6edd0feb47fe0a990 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15140.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15140.npy new file mode 100644 index 0000000000000000000000000000000000000000..e8af5ccfdb4af35c7b6e753d1860148a627f4164 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15140.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21f04e1bf5b171960d4f137aed16f4492a1c395bc9112726a81c97b14c8e9d73 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15150.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15150.npy new file mode 100644 index 0000000000000000000000000000000000000000..17e7b89108b15822a3dc87b359c6d09853030c84 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15150.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb71db72684cfe095668452bdeea0cfef3ffdf149c69196a4171d5abd3601e55 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15160.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15160.npy new file mode 100644 index 0000000000000000000000000000000000000000..286db7bd19a40b9ff7b13ebc30ad42170541ab8e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15160.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b90d3436552bbd5d884bee404c380573e59438814336fdb867f40feee48c960 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15170.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15170.npy new file mode 100644 index 0000000000000000000000000000000000000000..a894bbe05d7e72a25b2c4727516c0b8128bc80d0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15170.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7434b8beebd8980ae882fe6ae9d84b308505de18761f5d82e04c45deb3d16022 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15180.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15180.npy new file mode 100644 index 0000000000000000000000000000000000000000..7019b8a7957fbc14a1ffd5c26178278b53a14b52 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15180.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:760e72ddab7c54d96f8830cb9fec8a33d34684730028730a520ac822699531b7 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15190.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15190.npy new file mode 100644 index 0000000000000000000000000000000000000000..54389f2864e80ab30dd35dd1d247298611ae60c4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15190.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f1705d0298ec912c751c82ec904b4226cba315038ffce3cfb960c900bddbce5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15200.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15200.npy new file mode 100644 index 0000000000000000000000000000000000000000..b4c847dbe0c9ca08dbd48048840730f93465b928 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15200.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13568a012a38ad4325fb396f6e0940652f30754028fb8152f2d04e4ba6561526 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15210.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15210.npy new file mode 100644 index 0000000000000000000000000000000000000000..7045e67521f7a261fe9e77c6304fb56dc419db04 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15210.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:232384069d022b90718ee942de351c367517b201d113c3ba25af8ad233bd96b3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15220.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15220.npy new file mode 100644 index 0000000000000000000000000000000000000000..9b7d38d982343217732d38eb754062536598d711 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15220.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14b5df0d45f5c9ea03a14f310d083934cbcb3fd90636f93cd1f2d8b21c147d02 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15230.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15230.npy new file mode 100644 index 0000000000000000000000000000000000000000..460365488257606a926616f40116de88cc1e04fd --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15230.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab5097d0557348b95ecff1da05a2effb4b8a516541f0dc968767b31bd6eb14f2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15240.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15240.npy new file mode 100644 index 0000000000000000000000000000000000000000..971c860f5f17ae5193588b83c7b9e93ec4a6728a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15240.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70a346d3239cbbf2909ce90dae73d6bcc5eebdad1c994129826cf5166b38a016 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15250.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15250.npy new file mode 100644 index 0000000000000000000000000000000000000000..9449bb9f510890e145c80bd9b57cbd6f7d8eb772 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15250.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:567f5959b2cbb7f6346d59142fee364c8a9506e1a02d8e2564002633b0c2ac3b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15260.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15260.npy new file mode 100644 index 0000000000000000000000000000000000000000..ffc0f7f39bf1ecb070e31fb92aee058b5578f78e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15260.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66371881c3d270058750ee5155df5426c4d1fe84f68d8fffff074b69c399b266 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15270.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15270.npy new file mode 100644 index 0000000000000000000000000000000000000000..6cd30604d0bece93ba332f5c51ab2754ab3744f7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15270.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5772da2dedcd2d02aedb492017fe19f01e5151f58107f1d92ebc9bc5d72d39c5 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15280.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15280.npy new file mode 100644 index 0000000000000000000000000000000000000000..ffa62ebbe592c79bf0b06894d2f833fb73e40886 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15280.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48bd96683d81cf8fccc5792871bc1d09e2f98de7446c601ce1897a2d64602a56 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15290.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15290.npy new file mode 100644 index 0000000000000000000000000000000000000000..75c95cdf8e630da422ade7ddee5d9061b729ef00 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15290.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:878333bf61ad210ee0e418b86b068775b5879ee07b79aacc25f21e38c065031a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15300.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15300.npy new file mode 100644 index 0000000000000000000000000000000000000000..a473f8ea1790c91dafb579ce794e08fc949f8e3b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15300.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51ca606597ff57e4b976fcbdf4792229e37015c84917e325a497eeed557b4f07 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15310.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15310.npy new file mode 100644 index 0000000000000000000000000000000000000000..e8ca43175c65b0d3237a6d0557dfa70e4d475df5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15310.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcb6e61db14d2105262b68df026c3a909a9f7626dc2ddd64c70c8e2d03909bc1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15320.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15320.npy new file mode 100644 index 0000000000000000000000000000000000000000..28e977f64cd55dcabb19fe321cdac77be910528c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15320.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a5226b5701b42a2614fb21dc6c418652ea8e338065cf1d832a91884010ab51c +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15330.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15330.npy new file mode 100644 index 0000000000000000000000000000000000000000..bc8f042646c00b9b2ad90cd21ae3a30f17b26a2f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15330.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da6b860bf803d485d5217a873e4c52761cab116ac002289131858444c352f33b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15340.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15340.npy new file mode 100644 index 0000000000000000000000000000000000000000..8b3f30e27b867ce4a154043ab35c3536c4214b5c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15340.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1e80123a101007aa5de08024172410559bbbfe4d2143c78ac4ad8a68f67c731 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15350.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15350.npy new file mode 100644 index 0000000000000000000000000000000000000000..34e9961d303e1db0be5252fcc6f48c93f84c06b1 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15350.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73fd1291ac05442858cb3059780107507a35e0b9829fd428b8762fd38bdebc28 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15360.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15360.npy new file mode 100644 index 0000000000000000000000000000000000000000..d2b7edd7a4ee8b58bdc110b7d2f2a9f479cd7fb1 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15360.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5f5727432e1c33f34b004fe66b307750df0fef7939badda5362feaaa254e516 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15370.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15370.npy new file mode 100644 index 0000000000000000000000000000000000000000..29121048d740533a0e1850b94b9f2fabd65aa4e0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15370.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b46e0f7af71f397689da628958ffb148ca202cfa84451438b8fc8831a683666 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15380.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15380.npy new file mode 100644 index 0000000000000000000000000000000000000000..986d1aafaa20ab541d715a6831078ccdd96552f3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15380.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27b1d91f76a94b885af0b0e694a2d10fda37a505111f518749caeb1411f291eb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15390.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15390.npy new file mode 100644 index 0000000000000000000000000000000000000000..bb950a66a08cf1a3537c9aae2f32bff61d1c211e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15390.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00eec50aa849e2cb326715ae2db9318c71e79e18e86056b2afae2a9246606bcf +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15400.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15400.npy new file mode 100644 index 0000000000000000000000000000000000000000..2db734e36d4192c1e5eb1e4a082394b9259fe2cb --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15400.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d56d56d7d1818b74f576301b99a26bf49ac5b4f304b370aeb5d527e7a68f86b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15410.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15410.npy new file mode 100644 index 0000000000000000000000000000000000000000..1833fcdef6e8be2b9374d42ffd76fa5edf4f997d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15410.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9db2ac5a8fcd030272b5d70b93854f1186e6bead260ac371124038c616d5e86f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15420.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15420.npy new file mode 100644 index 0000000000000000000000000000000000000000..d959db24a96657526ebb560f5078af426eb52571 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15420.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fe87600f6894395b2cccab13101f8d7d4864b22878ba556dfb2dddf66c0cc66 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15430.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15430.npy new file mode 100644 index 0000000000000000000000000000000000000000..2b579b48eb7c33ef446311f01f079602a9a296c1 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15430.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ada6f7146973bb012ab80046f8ec19fbfde87180aa8184c7da48844daddb1791 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15440.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15440.npy new file mode 100644 index 0000000000000000000000000000000000000000..cb3cdcbbab2c12e08072cee5907ceadb9e855c5f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15440.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92ae91268cc5fe98940ac6a2ce2aba7558ae8492efb927bb9355f2b954092dc3 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15450.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15450.npy new file mode 100644 index 0000000000000000000000000000000000000000..b9005c15c38952fb314c15511c91aeedc27fdc81 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15450.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb2a5a79875e619b8b4a87c8e8e65ac816c52fe6722648275fb2660080d8b8fc +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15460.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15460.npy new file mode 100644 index 0000000000000000000000000000000000000000..1881477cae1a205493223e4c8e0e88bb426dcc50 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15460.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad4f48f51ed72e67215bd2fca36b62d88b3b1fe300a615096a6dd40976eb5839 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15470.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15470.npy new file mode 100644 index 0000000000000000000000000000000000000000..8e317e5f6b977806110b9426d76fe1eb707800b8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15470.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:712d2b6850bfca4ec8ba62ece680b0a4e9c062ea46ec4e7f2cec1d0b0223c58f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15480.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15480.npy new file mode 100644 index 0000000000000000000000000000000000000000..9e1386e666d9dffbf13948ea770fc9389a2379bf --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15480.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93541bde246a4a7727c85b3677796da038c37f347a309861c43541eaf4491568 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15490.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15490.npy new file mode 100644 index 0000000000000000000000000000000000000000..96247c29959ba947208388db81fc74b0291f634b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15490.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49834c9dc93f5d20dd2ff386b93944e852de95036f16cb0f2ffa047fe8358e71 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15500.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15500.npy new file mode 100644 index 0000000000000000000000000000000000000000..75c249fd88583b3ab928adeb72cc297a7fad1311 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15500.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68749c15f2aba75fe39b5645952396f297a561cb4549c51d82163e3a8cc273a6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15510.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15510.npy new file mode 100644 index 0000000000000000000000000000000000000000..1f4c5b4a63357afec7b84691a5739c86eb31574a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15510.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5cfc3b37111e0e5cde0c5f34ee342c20bce84d6a3f3b8638a9e51001b0857d1 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15520.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15520.npy new file mode 100644 index 0000000000000000000000000000000000000000..b9f36d08b9db43c218279d045aa2950bf1126336 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15520.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bb4ccc6cc65e11f61d40a0f8ea6d2d6038c719e1e04ba3416c1f716a85a8811 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15530.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15530.npy new file mode 100644 index 0000000000000000000000000000000000000000..3fef4be334ce65e6db78b0cf1cdd2486b041c00f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15530.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:294c4ba4afb4c385f14a0f89b5b406a13d59ab7b7e1422b07c8efc3e275101d2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15540.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15540.npy new file mode 100644 index 0000000000000000000000000000000000000000..f2ad87fb90cbe1e47321f22606ef9e88a8cdcef1 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15540.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55f546c6e62a30763acace6e655f50b480d51f0f2b29ef05dc2fdf34e5e1b91d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15550.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15550.npy new file mode 100644 index 0000000000000000000000000000000000000000..5e4fbaac701f68bd51341b198268814d251125bc --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15550.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bb451056d0a941ebe571ead56ded25feb1d096830f53ead5b9c98a05fa3be60 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15560.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15560.npy new file mode 100644 index 0000000000000000000000000000000000000000..c8c209d6cd77a763a58899bda6c1bbdd1fd839ef --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15560.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dff7c636ed01ab796d982401ddeec646ea06ee8fffee9da202c70a6d9487589 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15570.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15570.npy new file mode 100644 index 0000000000000000000000000000000000000000..ce0723f75017a1256d45c207ddbf42908573d43d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15570.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0de77d995c526ffa6fdf8e0cf7f10e26887f70ac5f444923a31720e37412cd4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15580.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15580.npy new file mode 100644 index 0000000000000000000000000000000000000000..7f9d28d8ba03abf6e08c32624b7b4dfba9541212 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15580.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:458bc8d064fb57c646df19e7fc8b611490cb5e5bf5deb6a5c996d5e86ccd8d49 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15590.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15590.npy new file mode 100644 index 0000000000000000000000000000000000000000..bffcfbbff7b921d4577040538564352f7809f6ad --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15590.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56f6399b757ffdb7527df27151f7b164857f2e79963954b522f03fc82b029397 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15600.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15600.npy new file mode 100644 index 0000000000000000000000000000000000000000..46c93703e50735441bc9e1fb3914fc54ecfdcf13 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15600.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69ba45bdd4e16ef1adc7e549ab6ce9c493d6b8ff9e5b52af3e7785c5b776d205 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15610.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15610.npy new file mode 100644 index 0000000000000000000000000000000000000000..bc9b7f7fb7d1e13f6791cac78b34367f86ade90e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15610.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8aef79de68d3ac25ae90efe7b4ac7bc382855941418d72ded2f9f89dbad70422 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15620.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15620.npy new file mode 100644 index 0000000000000000000000000000000000000000..6473dcf90bb798cc22da9179560792b5d0705ee4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15620.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdea2da6083b97ab6f426f2b51db48f92902e88c8cefc22526d9a6af90b09851 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15630.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15630.npy new file mode 100644 index 0000000000000000000000000000000000000000..28c300626885f88387bae29d6c17154af6a193a5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15630.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcb4cc2204ac9a6527157c437d730069b7bfa5f560a19013b5b1e362e9a4ccf4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15640.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15640.npy new file mode 100644 index 0000000000000000000000000000000000000000..1be35705a1a4cbfadc70b778f2e3c006e79df8c2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15640.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2734455a650f69bcd221c4d83a388b697c3a5c21baa9867465bcc039c37175b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15650.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15650.npy new file mode 100644 index 0000000000000000000000000000000000000000..34a2ff177cb42148f3ab28eded31bb76f923515e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15650.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96d7cc5857fc4e05aa7eb359e783341805427ce0679be7aedba7877160eee98d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15660.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15660.npy new file mode 100644 index 0000000000000000000000000000000000000000..bc7dc3f8706ef269b5559eaf5f0aec82ed927934 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15660.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c5d5592800ef310276b595f651e95451a26215b8b2f6d6fdc33ebfe4db6375e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15670.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15670.npy new file mode 100644 index 0000000000000000000000000000000000000000..903b460ce35352e1660324a3499ce722aa867245 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15670.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f9acdb17160fc50739328be131da236890b64832bae5166afb745d8ccd036e0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15680.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15680.npy new file mode 100644 index 0000000000000000000000000000000000000000..0d1fd788e1225028db9260c4403e06f1a151b40a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15680.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7ee3cb074af9140c5dd80da5e96d0f2916d4fda6ba5350a0ac1133f04702372 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15690.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15690.npy new file mode 100644 index 0000000000000000000000000000000000000000..4d992bb9a47c83a4fbb7b0af1d00d880764a1d85 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15690.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa06d13e8e99f0b4d978784db72d59108d0079fd853526711a0165b1b11b1ac2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15700.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15700.npy new file mode 100644 index 0000000000000000000000000000000000000000..a4bb1fd73bb049acf2be95053a54ad85424de2d4 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15700.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a832c8a38c92a4d2620f2b114385ba7b9a788810a927c36216af25b48c48de8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15710.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15710.npy new file mode 100644 index 0000000000000000000000000000000000000000..af1ede7c169a31cbbc587c95996dff44d932df8b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15710.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c507eadf929fc0e05204a031aa58fc293db15858934ea5865552a0d40a16093 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15720.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15720.npy new file mode 100644 index 0000000000000000000000000000000000000000..e841935ee6f634986694a9ec35ce1ac989a06a6d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15720.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:890edd93f9f199185f2da5e3349e8a8eef260bc1e71393828e1e5a5df37adc6e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15730.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15730.npy new file mode 100644 index 0000000000000000000000000000000000000000..f4c021ae14b689dfee0630b863215967fc6a9a2d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15730.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78a1994ce45e9a3185e2fa6a5b4b2b76effb3fb005b116e13b48cae4d1de5c22 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15740.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15740.npy new file mode 100644 index 0000000000000000000000000000000000000000..f3b4d196562c3432126a0ad721924a650bb344a0 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15740.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7df38456defd7b7b7e93f9cef960c03b53f0396bfc3cc3ade46f4881ff3008e9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15750.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15750.npy new file mode 100644 index 0000000000000000000000000000000000000000..3dc12a380c0daa95e3984b5b5e6d62412d9130a5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15750.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e84d22afff268760ad42ad4d79105c39cb7ee54d9fd3b5936c2002a17f2fb67f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15760.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15760.npy new file mode 100644 index 0000000000000000000000000000000000000000..dbbaed4734231161f999e7ef2a5866adca70f704 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15760.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9b6828a236e1421bf940feaa2ef5023a952ee32df5057271378575133de949d +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15770.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15770.npy new file mode 100644 index 0000000000000000000000000000000000000000..29a86ce09dd280883f93cf80f596e66cd4b7d98d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15770.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:836c0610eecdaca3ad78966767c7e3b840c724f91455c90a54086807d7883eba +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15780.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15780.npy new file mode 100644 index 0000000000000000000000000000000000000000..411124d3181c268f26663470a37905d76cf2be76 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15780.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b62a4d11a5a9d04f83b1250625758eee10ecdc582f042dfb287e01b9b8ef0551 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15790.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15790.npy new file mode 100644 index 0000000000000000000000000000000000000000..477c1e987d3d82f0a27d82890bbe953c09b18f5f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15790.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8ff317a9a6766ac2c935bb8a4b3bd58e2f36e97091741f17c91ee7c0206e9cd +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15800.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15800.npy new file mode 100644 index 0000000000000000000000000000000000000000..07fb880c90cd040767924a2794de4a85f302408e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15800.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc44530d9c81ea6aa169ac735aba4c037d0d074c3cc3d30ac0e9fb4635fa8cf6 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15810.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15810.npy new file mode 100644 index 0000000000000000000000000000000000000000..cb5a3cbac15536e95c93763b433a7c39e21a7cb1 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15810.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2873728d6eaffc4a53d3f7aebc4f1765580430275099763e79345474bd7007d9 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15820.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15820.npy new file mode 100644 index 0000000000000000000000000000000000000000..42f48a4fe7676bc8f89c88b2aedfca4e80b6d402 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15820.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd6023f2f42ce61d644d560a8a8880f6064f5efdb9c7055dd3537ffed1b1b854 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15830.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15830.npy new file mode 100644 index 0000000000000000000000000000000000000000..40564ea7d3ebf6c3e4193b94460f49fba9e38252 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15830.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4321ce70f0fa09c25c159afd5092a7e98f1f5bf8457152f9ddf61cbbd4fa3bf +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15840.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15840.npy new file mode 100644 index 0000000000000000000000000000000000000000..76c02fa281e5bb36ee138c5ab88da74e1b7a07d7 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15840.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e0e5b77aa07bd550eee1f4832d4e9377f63208a826a8a4c603d25cc04558871 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15850.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15850.npy new file mode 100644 index 0000000000000000000000000000000000000000..9eddae589c066faca918da06696b00751b3a950a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15850.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4efeda580072776b5e9bfdf080e474b62785f353abd5c3e5e2de879f1c9c1b2f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15860.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15860.npy new file mode 100644 index 0000000000000000000000000000000000000000..b37f22188f2fb78b64bfbd0b8f48458809b591bd --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15860.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af004cae1516ad4751df2205f92c74717630c8dcc6b51d54b36ff0df1966b5c2 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15870.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15870.npy new file mode 100644 index 0000000000000000000000000000000000000000..35f37ee48691979fbef982b07c02c770d3c55687 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15870.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9897a94b55d196c306d460d7fa73685965f7de9dca45c628c713d03d20dbc37a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15880.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15880.npy new file mode 100644 index 0000000000000000000000000000000000000000..9e565082917603f99525e96b013976316c6786d9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15880.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a3d729bbc050cfbf0c17bdd58dfae5c3a97d7b999899bcb09be1de0a48d22aa +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15890.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15890.npy new file mode 100644 index 0000000000000000000000000000000000000000..43f534d5cfbf94bf64cfdb53657e93a775082350 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15890.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af800a582e577b50aa25651368c8552f1d22644c09296bb730bf9f2efccb8e2f +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15900.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15900.npy new file mode 100644 index 0000000000000000000000000000000000000000..d8bae3b27493c92d03aa8e239dd1a3e9e2462cbb --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15900.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cce129a468947ff4da385f42ff6e9a3cce835a7d948c0d38178b4735e306244 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15910.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15910.npy new file mode 100644 index 0000000000000000000000000000000000000000..d379248179ee5178e0ab8d32b987740ea221e444 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15910.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2597c8b6ec1fa6e15e2ba16e096a8680478e4bd5b1078689333426a694e73cef +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15920.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15920.npy new file mode 100644 index 0000000000000000000000000000000000000000..e7c191c02628bb5117e9708c8c5ba4226142694a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15920.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a5c0f453708979110b8afaf405cb94d20c4e4d8c9327ef2724a38590e5d37ae +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15930.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15930.npy new file mode 100644 index 0000000000000000000000000000000000000000..3c3ce7fd88ae97abbde45288e7829d33a7e512b1 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15930.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddf86058c74751ba83e9719473239f9af7d59ab02c0f66b4aeb9b0da9516b96b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15940.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15940.npy new file mode 100644 index 0000000000000000000000000000000000000000..611a50320d381ebd6185c22af731cfebe61e52b5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15940.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1479f59696d14d515765603e2d9bf48356a7b7dd9510b0ac7bd96815481868a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15950.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15950.npy new file mode 100644 index 0000000000000000000000000000000000000000..a7550e293209d53f4777a37fc5ba8b7dd3ab2980 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15950.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:107c094b52a96dcc1f97a6c288eea2649e03c53f0b9525a7c2ce51ac92e91bec +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15960.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15960.npy new file mode 100644 index 0000000000000000000000000000000000000000..fe96a556376e2e209f815a00c8a0ea45d09b136f --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15960.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8eea8dbaf6c1ca217fa5a690e69ce3a38575d16f18eef4ae30c4c2a7a40db509 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15970.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15970.npy new file mode 100644 index 0000000000000000000000000000000000000000..58c0d6f5a64a76302ca832f556b86b2f0b0db76d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15970.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0eab4c1fe11a80cb5b196a9e310bab9b8466af94ca51e0be513eccbdea83c9bf +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15980.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15980.npy new file mode 100644 index 0000000000000000000000000000000000000000..acdf52a3b3536eea6bdb9897733ec0c244e372e6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15980.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41ec2d254d84a799aca49d6ae5de99c7633ba59575049e3db3fd8dde7a59989b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15990.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15990.npy new file mode 100644 index 0000000000000000000000000000000000000000..f14ed1f3d07012cc3782ce4e298d95c08bffd54b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_15990.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22db0c0212edc24d699f7a4c5eb0c63042ef13d1ed86d2bf26a03031c3133b66 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16000.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16000.npy new file mode 100644 index 0000000000000000000000000000000000000000..c85318acf3fb1144ec0371aa77fe1de3015edaf6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16000.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5882355c14ffe779bbaa4f0753421a2d55d6105eafecc1a9008552cb9372cd5b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16010.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16010.npy new file mode 100644 index 0000000000000000000000000000000000000000..1f3c8980a2b937e51566bc5079e2fd5831116c4a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16010.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:618213bb61fdd0c30cc39f478e13fa9ace1438897a1663ef60072668e5ab2d96 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16020.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16020.npy new file mode 100644 index 0000000000000000000000000000000000000000..2cbcf80b719b5124ac53409dd335668817322a35 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16020.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dbfb4c64b59f59524e1aac7a75e78ddad8a3f377fdaa42cd45691ba28378bc8 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16030.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16030.npy new file mode 100644 index 0000000000000000000000000000000000000000..a5e7a31f5369bbc6bb7a6aebacfbab78b5ca7125 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16030.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0023f7c39ed857b680f849ea4825295b059abd6cb337fb0bea60e6d2ad022b07 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16040.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16040.npy new file mode 100644 index 0000000000000000000000000000000000000000..12dc2605856f1ca4b9120a1c6b35c143ad379ca8 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16040.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b60169a6c11ed96c85dccc45f3768b3bc3ff4735291c4e71032d8986ed7536f0 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16050.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16050.npy new file mode 100644 index 0000000000000000000000000000000000000000..5c245b43ba30249331f67626765f4afc80cc172a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16050.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e850d2f75846940f4543d6be062fe071a2fd57f1ac444180a93bb0c038296c12 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16060.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16060.npy new file mode 100644 index 0000000000000000000000000000000000000000..b8034113aa8543b62328c2c45e4238a2047e9506 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16060.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe3eb8c79481e88749ed96a64bdc20a6025e8e15a308a81c058258f8fc3e6549 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16070.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16070.npy new file mode 100644 index 0000000000000000000000000000000000000000..d50c33d224ad0a7f46b47889264dc51600a99783 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16070.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59d0caaf3fe6b6d64d9c4d4a3462e731b7815deda65b90c6ad1ff4e5cfb315ac +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16080.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16080.npy new file mode 100644 index 0000000000000000000000000000000000000000..c306685d4f6b85ba32a1c1bf447aa83fed1d45b5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16080.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1801eb1caba913a622cc53d3f0ff52276955c6e8379e9793deb4ec8eab31255b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16090.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16090.npy new file mode 100644 index 0000000000000000000000000000000000000000..0cdb6775625703989fb6fd684735cd1f9c3c3ad6 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16090.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01a1023251780ea518cd84f1e1207500e830fc37eea6da5acae2d2c250d9dd44 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16100.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16100.npy new file mode 100644 index 0000000000000000000000000000000000000000..853379daddbf0d7091b78a027478dbab4a49b74b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16100.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c800bfa048960d0275a6a788ec056e69a55c6c28d65473784d3a739f3251468 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16110.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16110.npy new file mode 100644 index 0000000000000000000000000000000000000000..f02aa711cf743f99faa8c54a7f7723a93404184a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16110.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93acfdd136ebe3174ebc9922ea257b005e6e9260cbdbf9ef157725c93d2fecfe +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16120.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16120.npy new file mode 100644 index 0000000000000000000000000000000000000000..7a6301ac6aa1d7c077fdaa319d24a82bb104af41 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16120.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeecc597827bdb67a86924ecf16816a03ce40ecbdfb08f9ddcbcdffb836724aa +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16130.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16130.npy new file mode 100644 index 0000000000000000000000000000000000000000..a4485875767d11d16570a4404b67a7e9152238f2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16130.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6ff8358605248b93945d5c05c0cffb81c2ca110131417941cfc37e96796a84e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16140.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16140.npy new file mode 100644 index 0000000000000000000000000000000000000000..78204bdcd2dc7d5e1680118bac3c61071554889a --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16140.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4cc5116489b4fe46020e50477b63535b068734f532ba78642ecd47807467b37 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16150.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16150.npy new file mode 100644 index 0000000000000000000000000000000000000000..113f349b1ad15dd456beb0c9201e27b0778c47e3 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16150.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efbf4db3ccb3daa31835ccb872e7d0a4ad8f863faca844c3a0a0e66f58b3c1d4 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16160.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16160.npy new file mode 100644 index 0000000000000000000000000000000000000000..d55915f789d382631a7033ef8404edcfdbc1fbf2 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16160.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a549dc7654c99d0a22507b320e468535e0650d19a2d552033d5ca280f9b57342 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16170.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16170.npy new file mode 100644 index 0000000000000000000000000000000000000000..2f20f1f60958af87258ffbd620bb266b055f303d --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16170.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5fe2b099021661f77f754c166befdaa9ec3561a20a6defe3745c1d6de5f9e31 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16180.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16180.npy new file mode 100644 index 0000000000000000000000000000000000000000..67ee6d68fc7be75eb2605deec2b75c28e5f0dcf5 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16180.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0582f2fb920cb46867cf6038c1a9a14b91d0e807bb1e591ccba696bcdd1ceeeb +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16190.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16190.npy new file mode 100644 index 0000000000000000000000000000000000000000..0a0742a8a711d8c8c399162747739e35530bf127 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16190.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bd2f79d677479703c81f18d7e4c2073e965a32c1e67b848fecdfd1e65ed8c15 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16200.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16200.npy new file mode 100644 index 0000000000000000000000000000000000000000..dbdc5d2dd84ffd7bcefea288f37f06f4251b2544 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16200.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1622b9e64b46b6d71742f8a25e68944add09d94e49378d6baab6ea8450f238e +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16210.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16210.npy new file mode 100644 index 0000000000000000000000000000000000000000..1eda908eacb3fd3446ebbc5a7c2e9d88f5296d6c --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16210.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:387ed6a479dedddc5b4e984830dbb1cd7e7c7fc93b809d30c3f814b2306b443a +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16220.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16220.npy new file mode 100644 index 0000000000000000000000000000000000000000..5a3c8f42c4f22f4efcb242191927539d08c190ed --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16220.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58008f0e934fec397e01576752ed4607fae5f3cc9f1cb8477e83d915e3345dcd +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16230.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16230.npy new file mode 100644 index 0000000000000000000000000000000000000000..a99d334de6df417284e36bd4830be20a92e2873b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16230.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:291df090e24eb4f314a96cb9fc6c55e07631d596991b0fe7c201b2058f7e9655 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16240.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16240.npy new file mode 100644 index 0000000000000000000000000000000000000000..e551881e07aafb63cc895937134c0018ecf7d75b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16240.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de315c61a59e2c58b862d3a83ce47617d9e2dcc8affe31abca3b220ba9852c8b +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16250.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16250.npy new file mode 100644 index 0000000000000000000000000000000000000000..a289ef048d2115ed7a1d47b48d6afb1431f3bfe9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16250.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f766e0e0a53219f0037ddaee4daf0d31ddededf4e2e770006ed4ae9c2864622 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16260.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16260.npy new file mode 100644 index 0000000000000000000000000000000000000000..02b51dc67e39b468ea074f84c8ba1c0381bace99 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16260.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc7ca38b90a5b59c43f74494a2c15d3bad45d7ce05e7b408bc689650a320fe46 +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16270.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16270.npy new file mode 100644 index 0000000000000000000000000000000000000000..8dc764aaae0b17c9249c48c5e502277478f1473e --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/rng_keys/rng_16270.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cfa63acf8209871d9a92727ede2abef544105535ef8f02644505169a89b90be +size 136 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/setup.json b/control_al_0.6_g_0.98_id_94_seed_9806094/setup.json new file mode 100644 index 0000000000000000000000000000000000000000..1e4c6f8f93dc8ea5032ff6d530d1b9919ead7cae --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/setup.json @@ -0,0 +1,96 @@ +{ + "config": { + "rl_action": "train", + "model_type": "impala", + "lr": 5e-05, + "discount_rate": 0.98, + "num_rollout_steps": 64, + "grad_acc_per_chunk": 5, + "num_rollout_chunks": 1, + "cheese_loc": "any", + "env_layout": "open", + "alpha": 0.6, + "env_size": 13, + "num_levels": 9600, + "compile": true, + "use_prev_action": false, + "weight_restrictions": null, + "weight_restrictions_invert": false, + "use_bf16": false, + "use_wandb": true, + "no_tqdm": true, + "seed": 9806094, + "mask_type": "first_episode", + "ckpt_dir": "jaxgmg2_antennaban2", + "vis_average_state": false, + "trim_episodes": false, + "num_total_env_steps": 9999974400, + "eval_every": 1, + "eff_horizon": null, + "optim": "adam", + "env_rule": "ban:c[10,11], m[11,:]; c[11,10], m[:,11]", + "env_rule_mixture": null, + "hf_user": "davidquarel", + "hf_collection": "davidquarel/jaxgmg", + "use_hf": true, + "num_hf_uploads": 1, + "use_log": true, + "log_optimizer_state": true, + "resume": null, + "resume_id": null, + "resume_optim": false, + "checkpoint": "control_al_0.6_g_0.98_id_94_seed_9806094", + "wandb_project": "jaxgmg2_antennaban", + "eval_schedule": "0:1,250:2,500:5,2000:10", + "render_sixel": false, + "sixel_idx": 60, + "live_monitor": false, + "run_id": 94, + "seed_formula": "", + "deterministic": true, + "penalize_time": false, + "f_str_ckpt": "control_al_0.6_g_0.98_id_94_seed_9806094", + "duplication_factor": -1, + "smoke": false, + "ntfy": "david_jaxgmg", + "num_chains": 6, + "num_draws": 3000, + "num_steps_bw_draws": 1, + "on_policy": true, + "llc_nbeta": 3000, + "localization": 10, + "exact_solver_each_draw": false, + "llc_optimizer": "sgld", + "iw_clip_eps": null, + "rmsprop_burnin_steps": 20, + "llc_data_file": "llc_scan_open_reinforce.pkl", + "llc_checkpoint_index": null, + "llc_checkpoint_number": null, + "sink": null, + "repo_id": "davidquarel/jaxgmg_ckpt_zip", + "use_shuffled_checkpoints": false, + "force_re_download": false, + "off_distribution_data": false, + "evaluate_every_position": false, + "num_prev_actions": 1, + "eff_acc_steps": 5, + "chunk_size": 9600, + "env_steps_per_microbatch": 122880, + "ckpt_path": "jaxgmg2_antennaban2/control_al_0.6_g_0.98_id_94_seed_9806094", + "env_steps_per_loop": 614400, + "total_loops": 16276 + }, + "setup": { + "start_time_utc": "2026-03-20T17:23:11.450095Z", + "seed": 9806094, + "device": "cuda", + "python_version": "3.11.11", + "torch_version": "2.10.0+cu128", + "jax_version": "0.6.2", + "hostname": "097744e31d87", + "platform": "Linux-5.15.0-151-generic-x86_64-with-glibc2.39", + "git_sha": null, + "git_branch": null, + "use_wandb": true + } +} \ No newline at end of file diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/setup.txt b/control_al_0.6_g_0.98_id_94_seed_9806094/setup.txt new file mode 100644 index 0000000000000000000000000000000000000000..f40c8a2f57990ee1267c6b49b6c3c77a39ef35fa --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/setup.txt @@ -0,0 +1,8 @@ +Start: 2026-03-20T17:23:11.450095Z +Seed: 9806094 +Device: cuda +Python: 3.11.11 | Torch: 2.10.0+cu128 | JAX: 0.6.2 +Host: 097744e31d87 +Platform: Linux-5.15.0-151-generic-x86_64-with-glibc2.39 +Git: branch=None sha=None +use_wandb: True diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/state_counts.npy b/control_al_0.6_g_0.98_id_94_seed_9806094/state_counts.npy new file mode 100644 index 0000000000000000000000000000000000000000..4e186fea6df0e3b1a199ce9b4af6612d95eaa191 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/state_counts.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e30255982111f767f8ec869bde0b6f46b4f4eb95087c780cffa71aff3a2769b2 +size 116288 diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/train.jsonl b/control_al_0.6_g_0.98_id_94_seed_9806094/train.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..e414d8467c43823a472124202296965f789456f9 --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/train.jsonl @@ -0,0 +1,16276 @@ +{"ts": "2026-03-20T17:23:27.626587Z", "loop": 0, "env_steps": 614399, "loss": 0.01937226392328739, "avg_return": 0.11593631654977798, "regret": 0.7276439070701599, "entropy": 1.3857959508895874, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:23:28.517920Z", "loop": 1, "env_steps": 1228799, "loss": 0.017364148050546646, "avg_return": 0.1124524474143982, "regret": 0.727080225944519, "entropy": 1.3857648372650146, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:23:29.404331Z", "loop": 2, "env_steps": 1843199, "loss": 0.018173426389694214, "avg_return": 0.11006200313568115, "regret": 0.7265304327011108, "entropy": 1.3857320547103882, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:23:30.291546Z", "loop": 3, "env_steps": 2457599, "loss": 0.018151238560676575, "avg_return": 0.11300523579120636, "regret": 0.7259957194328308, "entropy": 1.385696530342102, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:23:31.180488Z", "loop": 4, "env_steps": 3071999, "loss": 0.016920575872063637, "avg_return": 0.11334971338510513, "regret": 0.7254628539085388, "entropy": 1.3856582641601562, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:23:32.068871Z", "loop": 5, "env_steps": 3686399, "loss": 0.016722997650504112, "avg_return": 0.11137927323579788, "regret": 0.7249383926391602, "entropy": 1.3856176137924194, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:23:32.955846Z", "loop": 6, "env_steps": 4300799, "loss": 0.017156606540083885, "avg_return": 0.11231684684753418, "regret": 0.7244095802307129, "entropy": 1.3855749368667603, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:23:33.845196Z", "loop": 7, "env_steps": 4915199, "loss": 0.01644783467054367, "avg_return": 0.11016221344470978, "regret": 0.723878026008606, "entropy": 1.3855293989181519, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:23:34.732901Z", "loop": 8, "env_steps": 5529599, "loss": 0.018101736903190613, "avg_return": 0.11635874956846237, "regret": 0.7233380079269409, "entropy": 1.385481595993042, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:23:35.621460Z", "loop": 9, "env_steps": 6143999, "loss": 0.017096471041440964, "avg_return": 0.11385396867990494, "regret": 0.7227873802185059, "entropy": 1.3854310512542725, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:23:36.510049Z", "loop": 10, "env_steps": 6758399, "loss": 0.019253334030508995, "avg_return": 0.11424744874238968, "regret": 0.7222282886505127, "entropy": 1.385375738143921, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:23:37.398845Z", "loop": 11, "env_steps": 7372799, "loss": 0.020161908119916916, "avg_return": 0.11332514882087708, "regret": 0.721655011177063, "entropy": 1.3853169679641724, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:23:38.287643Z", "loop": 12, "env_steps": 7987199, "loss": 0.017972571775317192, "avg_return": 0.11277817189693451, "regret": 0.7210655808448792, "entropy": 1.3852546215057373, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:23:39.176036Z", "loop": 13, "env_steps": 8601599, "loss": 0.019450275227427483, "avg_return": 0.11559293419122696, "regret": 0.72046959400177, "entropy": 1.385188341140747, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:23:40.063489Z", "loop": 14, "env_steps": 9215999, "loss": 0.01965285837650299, "avg_return": 0.11969970911741257, "regret": 0.7198554873466492, "entropy": 1.3851178884506226, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:23:40.950764Z", "loop": 15, "env_steps": 9830399, "loss": 0.019630441442131996, "avg_return": 0.11339477449655533, "regret": 0.7192196846008301, "entropy": 1.3850409984588623, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:23:41.837303Z", "loop": 16, "env_steps": 10444799, "loss": 0.01909831166267395, "avg_return": 0.11388589441776276, "regret": 0.7185696363449097, "entropy": 1.3849620819091797, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:23:42.724295Z", "loop": 17, "env_steps": 11059199, "loss": 0.018986206501722336, "avg_return": 0.11620472371578217, "regret": 0.7179030179977417, "entropy": 1.3848774433135986, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:23:43.612533Z", "loop": 18, "env_steps": 11673599, "loss": 0.019452910870313644, "avg_return": 0.11744865775108337, "regret": 0.71721351146698, "entropy": 1.3847874402999878, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:23:44.501202Z", "loop": 19, "env_steps": 12287999, "loss": 0.01964222453534603, "avg_return": 0.12045451253652573, "regret": 0.7164968252182007, "entropy": 1.384687066078186, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:23:45.390104Z", "loop": 20, "env_steps": 12902399, "loss": 0.017370307818055153, "avg_return": 0.11660555750131607, "regret": 0.7157477736473083, "entropy": 1.3845810890197754, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:23:46.277416Z", "loop": 21, "env_steps": 13516799, "loss": 0.018003225326538086, "avg_return": 0.11872586607933044, "regret": 0.7149729132652283, "entropy": 1.384467363357544, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:23:47.165962Z", "loop": 22, "env_steps": 14131199, "loss": 0.019335100427269936, "avg_return": 0.11725745350122452, "regret": 0.7141591906547546, "entropy": 1.3843427896499634, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:23:48.053597Z", "loop": 23, "env_steps": 14745599, "loss": 0.019705863669514656, "avg_return": 0.11799541860818863, "regret": 0.7133169174194336, "entropy": 1.3842098712921143, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:23:48.938829Z", "loop": 24, "env_steps": 15359999, "loss": 0.019230928272008896, "avg_return": 0.12307103723287582, "regret": 0.7124371528625488, "entropy": 1.3840667009353638, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:23:49.825429Z", "loop": 25, "env_steps": 15974399, "loss": 0.019763533025979996, "avg_return": 0.1231197640299797, "regret": 0.7115187644958496, "entropy": 1.3839147090911865, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:23:50.712568Z", "loop": 26, "env_steps": 16588799, "loss": 0.020789360627532005, "avg_return": 0.12185409665107727, "regret": 0.7105549573898315, "entropy": 1.3837465047836304, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:23:51.599971Z", "loop": 27, "env_steps": 17203199, "loss": 0.018169282004237175, "avg_return": 0.12018725275993347, "regret": 0.7095398306846619, "entropy": 1.3835694789886475, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:23:52.486679Z", "loop": 28, "env_steps": 17817599, "loss": 0.02054664120078087, "avg_return": 0.1187095195055008, "regret": 0.7084729075431824, "entropy": 1.3833733797073364, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:23:53.376503Z", "loop": 29, "env_steps": 18431999, "loss": 0.020627014338970184, "avg_return": 0.12398849427700043, "regret": 0.7073507308959961, "entropy": 1.3831640481948853, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:23:54.266010Z", "loop": 30, "env_steps": 19046399, "loss": 0.019449368119239807, "avg_return": 0.12210312485694885, "regret": 0.7061783671379089, "entropy": 1.3829350471496582, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:23:55.152447Z", "loop": 31, "env_steps": 19660799, "loss": 0.018739013001322746, "avg_return": 0.12665905058383942, "regret": 0.7049717903137207, "entropy": 1.3826879262924194, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:23:56.040570Z", "loop": 32, "env_steps": 20275199, "loss": 0.02194952592253685, "avg_return": 0.12700322270393372, "regret": 0.7037246227264404, "entropy": 1.38242769241333, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:23:56.928063Z", "loop": 33, "env_steps": 20889599, "loss": 0.019829224795103073, "avg_return": 0.12861596047878265, "regret": 0.702427864074707, "entropy": 1.38214910030365, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:23:57.816253Z", "loop": 34, "env_steps": 21503999, "loss": 0.022078629583120346, "avg_return": 0.13136348128318787, "regret": 0.7010676860809326, "entropy": 1.381843090057373, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:23:58.704379Z", "loop": 35, "env_steps": 22118399, "loss": 0.02278306894004345, "avg_return": 0.1329803764820099, "regret": 0.6996268033981323, "entropy": 1.3815100193023682, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:23:59.590608Z", "loop": 36, "env_steps": 22732799, "loss": 0.02322952076792717, "avg_return": 0.13009081780910492, "regret": 0.6980999708175659, "entropy": 1.381144404411316, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:00.478046Z", "loop": 37, "env_steps": 23347199, "loss": 0.026162786409258842, "avg_return": 0.1346873790025711, "regret": 0.6964724659919739, "entropy": 1.380732774734497, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:01.365593Z", "loop": 38, "env_steps": 23961599, "loss": 0.02281523495912552, "avg_return": 0.13335591554641724, "regret": 0.6947395205497742, "entropy": 1.380287528038025, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:02.252643Z", "loop": 39, "env_steps": 24575999, "loss": 0.02374960109591484, "avg_return": 0.13634246587753296, "regret": 0.6929006576538086, "entropy": 1.37980055809021, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:03.141061Z", "loop": 40, "env_steps": 25190399, "loss": 0.024043550714850426, "avg_return": 0.14246489107608795, "regret": 0.6909111738204956, "entropy": 1.3792625665664673, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:04.029913Z", "loop": 41, "env_steps": 25804799, "loss": 0.02463710494339466, "avg_return": 0.13928401470184326, "regret": 0.6887668371200562, "entropy": 1.3786500692367554, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:04.920260Z", "loop": 42, "env_steps": 26419199, "loss": 0.023908168077468872, "avg_return": 0.1465514898300171, "regret": 0.6864665746688843, "entropy": 1.377968668937683, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:05.810037Z", "loop": 43, "env_steps": 27033599, "loss": 0.024791477248072624, "avg_return": 0.14449086785316467, "regret": 0.6839956045150757, "entropy": 1.3772237300872803, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:06.699066Z", "loop": 44, "env_steps": 27647999, "loss": 0.02405267208814621, "avg_return": 0.14396876096725464, "regret": 0.6813649535179138, "entropy": 1.3763760328292847, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:07.586555Z", "loop": 45, "env_steps": 28262399, "loss": 0.027106797322630882, "avg_return": 0.14628112316131592, "regret": 0.6785760521888733, "entropy": 1.3754245042800903, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:08.471700Z", "loop": 46, "env_steps": 28876799, "loss": 0.026690397411584854, "avg_return": 0.1463630348443985, "regret": 0.6756293773651123, "entropy": 1.374372124671936, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:09.358029Z", "loop": 47, "env_steps": 29491199, "loss": 0.027933260425925255, "avg_return": 0.14773871004581451, "regret": 0.6724659204483032, "entropy": 1.3731932640075684, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:10.246985Z", "loop": 48, "env_steps": 30105599, "loss": 0.030044278129935265, "avg_return": 0.15906311571598053, "regret": 0.6691091060638428, "entropy": 1.3718857765197754, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:11.135079Z", "loop": 49, "env_steps": 30719999, "loss": 0.02962050400674343, "avg_return": 0.16393685340881348, "regret": 0.6655429005622864, "entropy": 1.3704242706298828, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:12.021826Z", "loop": 50, "env_steps": 31334399, "loss": 0.02990891970694065, "avg_return": 0.16673646867275238, "regret": 0.6617880463600159, "entropy": 1.3687859773635864, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:12.908636Z", "loop": 51, "env_steps": 31948799, "loss": 0.03257168084383011, "avg_return": 0.17005030810832977, "regret": 0.6578020453453064, "entropy": 1.366943120956421, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:13.797219Z", "loop": 52, "env_steps": 32563199, "loss": 0.031998928636312485, "avg_return": 0.1702243834733963, "regret": 0.6535850763320923, "entropy": 1.3648653030395508, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:14.685367Z", "loop": 53, "env_steps": 33177599, "loss": 0.03254716098308563, "avg_return": 0.17836062610149384, "regret": 0.6491236686706543, "entropy": 1.3625202178955078, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:15.573986Z", "loop": 54, "env_steps": 33791999, "loss": 0.035467762500047684, "avg_return": 0.18107262253761292, "regret": 0.6443910598754883, "entropy": 1.3598262071609497, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:16.462484Z", "loop": 55, "env_steps": 34406399, "loss": 0.037711627781391144, "avg_return": 0.19295638799667358, "regret": 0.6393849849700928, "entropy": 1.3567590713500977, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:17.350620Z", "loop": 56, "env_steps": 35020799, "loss": 0.03653372451663017, "avg_return": 0.1999022215604782, "regret": 0.6340872049331665, "entropy": 1.3532421588897705, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:18.239139Z", "loop": 57, "env_steps": 35635199, "loss": 0.03624889254570007, "avg_return": 0.2052881121635437, "regret": 0.6284319758415222, "entropy": 1.3491463661193848, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:19.127440Z", "loop": 58, "env_steps": 36249599, "loss": 0.04239571839570999, "avg_return": 0.20679724216461182, "regret": 0.6225104928016663, "entropy": 1.3444374799728394, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:20.015691Z", "loop": 59, "env_steps": 36863999, "loss": 0.043513935059309006, "avg_return": 0.2213541716337204, "regret": 0.6164152026176453, "entropy": 1.3390346765518188, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:20.907965Z", "loop": 60, "env_steps": 37478399, "loss": 0.04541726037859917, "avg_return": 0.2236790508031845, "regret": 0.6101868152618408, "entropy": 1.3328460454940796, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:21.796270Z", "loop": 61, "env_steps": 38092799, "loss": 0.048673804849386215, "avg_return": 0.23715850710868835, "regret": 0.6039192080497742, "entropy": 1.325911283493042, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:22.683262Z", "loop": 62, "env_steps": 38707199, "loss": 0.0469028614461422, "avg_return": 0.2476489245891571, "regret": 0.597540020942688, "entropy": 1.3179609775543213, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:23.573771Z", "loop": 63, "env_steps": 39321599, "loss": 0.05132311210036278, "avg_return": 0.2523403465747833, "regret": 0.5911638140678406, "entropy": 1.308799386024475, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:24.463604Z", "loop": 64, "env_steps": 39935999, "loss": 0.048707377165555954, "avg_return": 0.26650020480155945, "regret": 0.5847834348678589, "entropy": 1.2982966899871826, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:25.352650Z", "loop": 65, "env_steps": 40550399, "loss": 0.05294239521026611, "avg_return": 0.2790299355983734, "regret": 0.5784423351287842, "entropy": 1.2864819765090942, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:26.241963Z", "loop": 66, "env_steps": 41164799, "loss": 0.05118795856833458, "avg_return": 0.2818242311477661, "regret": 0.5722086429595947, "entropy": 1.2728571891784668, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:27.132527Z", "loop": 67, "env_steps": 41779199, "loss": 0.0493541955947876, "avg_return": 0.2914206087589264, "regret": 0.5661715865135193, "entropy": 1.2574915885925293, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:28.022141Z", "loop": 68, "env_steps": 42393599, "loss": 0.04889364168047905, "avg_return": 0.29972371459007263, "regret": 0.5604146718978882, "entropy": 1.2402639389038086, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:28.913632Z", "loop": 69, "env_steps": 43007999, "loss": 0.04745237156748772, "avg_return": 0.3019006848335266, "regret": 0.5550167560577393, "entropy": 1.221328854560852, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:29.801917Z", "loop": 70, "env_steps": 43622399, "loss": 0.048491548746824265, "avg_return": 0.3117305040359497, "regret": 0.5500278472900391, "entropy": 1.200870394706726, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:30.692127Z", "loop": 71, "env_steps": 44236799, "loss": 0.04505644366145134, "avg_return": 0.3197784125804901, "regret": 0.545448899269104, "entropy": 1.1789047718048096, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:31.580445Z", "loop": 72, "env_steps": 44851199, "loss": 0.043447114527225494, "avg_return": 0.32448074221611023, "regret": 0.5412774682044983, "entropy": 1.1550689935684204, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:32.468537Z", "loop": 73, "env_steps": 45465599, "loss": 0.03944622725248337, "avg_return": 0.32395437359809875, "regret": 0.5375351309776306, "entropy": 1.1307510137557983, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:33.358691Z", "loop": 74, "env_steps": 46079999, "loss": 0.03748545050621033, "avg_return": 0.3233223557472229, "regret": 0.5341624617576599, "entropy": 1.1051785945892334, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:34.246760Z", "loop": 75, "env_steps": 46694399, "loss": 0.033687565475702286, "avg_return": 0.33011195063591003, "regret": 0.5311853885650635, "entropy": 1.0789350271224976, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:35.133774Z", "loop": 76, "env_steps": 47308799, "loss": 0.03417358919978142, "avg_return": 0.3352445960044861, "regret": 0.5286113619804382, "entropy": 1.0533654689788818, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:36.020010Z", "loop": 77, "env_steps": 47923199, "loss": 0.03331177681684494, "avg_return": 0.33665931224823, "regret": 0.5263728499412537, "entropy": 1.0279372930526733, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:36.908589Z", "loop": 78, "env_steps": 48537599, "loss": 0.03064003586769104, "avg_return": 0.336945503950119, "regret": 0.5243892669677734, "entropy": 1.0028369426727295, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:37.797245Z", "loop": 79, "env_steps": 49151999, "loss": 0.02972005307674408, "avg_return": 0.33767974376678467, "regret": 0.5226885080337524, "entropy": 0.9786912798881531, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:38.688375Z", "loop": 80, "env_steps": 49766399, "loss": 0.028087953105568886, "avg_return": 0.3419453203678131, "regret": 0.521244466304779, "entropy": 0.9560983777046204, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:39.584181Z", "loop": 81, "env_steps": 50380799, "loss": 0.027060801163315773, "avg_return": 0.3415635824203491, "regret": 0.5199745297431946, "entropy": 0.9343104362487793, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:40.472495Z", "loop": 82, "env_steps": 50995199, "loss": 0.024722199887037277, "avg_return": 0.34262019395828247, "regret": 0.5188973546028137, "entropy": 0.9133353233337402, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:41.362330Z", "loop": 83, "env_steps": 51609599, "loss": 0.02669546566903591, "avg_return": 0.35662004351615906, "regret": 0.5179716348648071, "entropy": 0.8944272994995117, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:42.252016Z", "loop": 84, "env_steps": 52223999, "loss": 0.023662786930799484, "avg_return": 0.3466155529022217, "regret": 0.5172165036201477, "entropy": 0.877555251121521, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:43.139905Z", "loop": 85, "env_steps": 52838399, "loss": 0.02338862419128418, "avg_return": 0.34633076190948486, "regret": 0.5165948271751404, "entropy": 0.8626680374145508, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:44.027851Z", "loop": 86, "env_steps": 53452799, "loss": 0.022722478955984116, "avg_return": 0.3473552167415619, "regret": 0.5160857439041138, "entropy": 0.8493990898132324, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:44.917452Z", "loop": 87, "env_steps": 54067199, "loss": 0.022089200094342232, "avg_return": 0.34256497025489807, "regret": 0.5156726837158203, "entropy": 0.8372157216072083, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:45.804916Z", "loop": 88, "env_steps": 54681599, "loss": 0.023113546893000603, "avg_return": 0.34994930028915405, "regret": 0.5153006315231323, "entropy": 0.8254571557044983, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:46.693830Z", "loop": 89, "env_steps": 55295999, "loss": 0.02234588749706745, "avg_return": 0.35129332542419434, "regret": 0.5149537920951843, "entropy": 0.8137052059173584, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:47.583277Z", "loop": 90, "env_steps": 55910399, "loss": 0.023678777739405632, "avg_return": 0.35691148042678833, "regret": 0.5146382451057434, "entropy": 0.8032655715942383, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:48.471579Z", "loop": 91, "env_steps": 56524799, "loss": 0.02018400840461254, "avg_return": 0.3466859459877014, "regret": 0.514358639717102, "entropy": 0.7931099534034729, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:49.361670Z", "loop": 92, "env_steps": 57139199, "loss": 0.020495358854532242, "avg_return": 0.3502548336982727, "regret": 0.5141009092330933, "entropy": 0.7844841480255127, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:50.248492Z", "loop": 93, "env_steps": 57753599, "loss": 0.020022232085466385, "avg_return": 0.35061976313591003, "regret": 0.5138829946517944, "entropy": 0.7766648530960083, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:51.136480Z", "loop": 94, "env_steps": 58367999, "loss": 0.020050490275025368, "avg_return": 0.3487510681152344, "regret": 0.5137166976928711, "entropy": 0.7699579000473022, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:52.023749Z", "loop": 95, "env_steps": 58982399, "loss": 0.019980989396572113, "avg_return": 0.3563315272331238, "regret": 0.5135800242424011, "entropy": 0.763385534286499, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:52.911741Z", "loop": 96, "env_steps": 59596799, "loss": 0.020175768062472343, "avg_return": 0.3444529175758362, "regret": 0.5134780406951904, "entropy": 0.7574812769889832, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:53.799441Z", "loop": 97, "env_steps": 60211199, "loss": 0.019122352823615074, "avg_return": 0.3448775112628937, "regret": 0.5134029984474182, "entropy": 0.7530434131622314, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:54.688012Z", "loop": 98, "env_steps": 60825599, "loss": 0.019885998219251633, "avg_return": 0.3481252193450928, "regret": 0.5133510828018188, "entropy": 0.7488886713981628, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:55.578581Z", "loop": 99, "env_steps": 61439999, "loss": 0.02036912553012371, "avg_return": 0.3438563942909241, "regret": 0.5132818222045898, "entropy": 0.7453981041908264, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:56.468764Z", "loop": 100, "env_steps": 62054399, "loss": 0.01990712806582451, "avg_return": 0.35800182819366455, "regret": 0.5132235884666443, "entropy": 0.7425435781478882, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:57.357931Z", "loop": 101, "env_steps": 62668799, "loss": 0.019268760457634926, "avg_return": 0.35558202862739563, "regret": 0.5131600499153137, "entropy": 0.7397336959838867, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:58.248684Z", "loop": 102, "env_steps": 63283199, "loss": 0.018501712009310722, "avg_return": 0.351590096950531, "regret": 0.5131210684776306, "entropy": 0.7372937202453613, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:24:59.136738Z", "loop": 103, "env_steps": 63897599, "loss": 0.019931631162762642, "avg_return": 0.3534824848175049, "regret": 0.5130870342254639, "entropy": 0.7354739308357239, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:00.026406Z", "loop": 104, "env_steps": 64511999, "loss": 0.018472224473953247, "avg_return": 0.3522745966911316, "regret": 0.5130718350410461, "entropy": 0.7337290644645691, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:00.915420Z", "loop": 105, "env_steps": 65126399, "loss": 0.019154762849211693, "avg_return": 0.3453616797924042, "regret": 0.5130408406257629, "entropy": 0.7320155501365662, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:01.806534Z", "loop": 106, "env_steps": 65740799, "loss": 0.018932489678263664, "avg_return": 0.3544054329395294, "regret": 0.5130175948143005, "entropy": 0.7302302718162537, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:02.695636Z", "loop": 107, "env_steps": 66355199, "loss": 0.018569858744740486, "avg_return": 0.34992510080337524, "regret": 0.5129864811897278, "entropy": 0.7284107804298401, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:03.582169Z", "loop": 108, "env_steps": 66969599, "loss": 0.018785636872053146, "avg_return": 0.3495255410671234, "regret": 0.5129672884941101, "entropy": 0.7265750169754028, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:04.470981Z", "loop": 109, "env_steps": 67583999, "loss": 0.01830311305820942, "avg_return": 0.3522360920906067, "regret": 0.5129544138908386, "entropy": 0.7249603867530823, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:05.359280Z", "loop": 110, "env_steps": 68198399, "loss": 0.018595976755023003, "avg_return": 0.3460272252559662, "regret": 0.5129362344741821, "entropy": 0.7235130667686462, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:06.247766Z", "loop": 111, "env_steps": 68812799, "loss": 0.018971091136336327, "avg_return": 0.3535904884338379, "regret": 0.5129225254058838, "entropy": 0.722253680229187, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:07.135338Z", "loop": 112, "env_steps": 69427199, "loss": 0.017322300001978874, "avg_return": 0.3491896688938141, "regret": 0.5129281282424927, "entropy": 0.7212444543838501, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:08.023767Z", "loop": 113, "env_steps": 70041599, "loss": 0.017500972375273705, "avg_return": 0.3498333692550659, "regret": 0.5129319429397583, "entropy": 0.720591127872467, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:08.912580Z", "loop": 114, "env_steps": 70655999, "loss": 0.018669409677386284, "avg_return": 0.3522169589996338, "regret": 0.5129121541976929, "entropy": 0.7199392318725586, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:09.801781Z", "loop": 115, "env_steps": 71270399, "loss": 0.01678054966032505, "avg_return": 0.3399449288845062, "regret": 0.5129128694534302, "entropy": 0.719253420829773, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:10.689704Z", "loop": 116, "env_steps": 71884799, "loss": 0.017646510154008865, "avg_return": 0.3444911241531372, "regret": 0.5129207968711853, "entropy": 0.7186660766601562, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:11.578542Z", "loop": 117, "env_steps": 72499199, "loss": 0.019677860662341118, "avg_return": 0.3553086221218109, "regret": 0.5129355192184448, "entropy": 0.7179279923439026, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:12.466020Z", "loop": 118, "env_steps": 73113599, "loss": 0.018068568781018257, "avg_return": 0.3497895896434784, "regret": 0.5129767656326294, "entropy": 0.7172523736953735, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:13.353864Z", "loop": 119, "env_steps": 73727999, "loss": 0.01918908953666687, "avg_return": 0.3536539673805237, "regret": 0.5130689740180969, "entropy": 0.7163987755775452, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:14.243073Z", "loop": 120, "env_steps": 74342399, "loss": 0.01833864115178585, "avg_return": 0.3525674641132355, "regret": 0.513258695602417, "entropy": 0.7153072953224182, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:15.136644Z", "loop": 121, "env_steps": 74956799, "loss": 0.019218740984797478, "avg_return": 0.3516887128353119, "regret": 0.513312041759491, "entropy": 0.7145999073982239, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:16.024313Z", "loop": 122, "env_steps": 75571199, "loss": 0.020277122035622597, "avg_return": 0.35045915842056274, "regret": 0.5132583975791931, "entropy": 0.7146167755126953, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:16.914446Z", "loop": 123, "env_steps": 76185599, "loss": 0.01717555709183216, "avg_return": 0.345203697681427, "regret": 0.5132092237472534, "entropy": 0.7147836685180664, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:17.804044Z", "loop": 124, "env_steps": 76799999, "loss": 0.019354242831468582, "avg_return": 0.35346877574920654, "regret": 0.513077974319458, "entropy": 0.7155529856681824, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:18.693007Z", "loop": 125, "env_steps": 77414399, "loss": 0.018605660647153854, "avg_return": 0.35166504979133606, "regret": 0.5129843354225159, "entropy": 0.7158445119857788, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:19.581567Z", "loop": 126, "env_steps": 78028799, "loss": 0.0188466664403677, "avg_return": 0.35338959097862244, "regret": 0.5129307508468628, "entropy": 0.7160441279411316, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:20.469898Z", "loop": 127, "env_steps": 78643199, "loss": 0.017971044406294823, "avg_return": 0.35039493441581726, "regret": 0.5128630995750427, "entropy": 0.7163947820663452, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:21.359535Z", "loop": 128, "env_steps": 79257599, "loss": 0.019329918548464775, "avg_return": 0.3498496115207672, "regret": 0.5128347873687744, "entropy": 0.7163768410682678, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:22.248562Z", "loop": 129, "env_steps": 79871999, "loss": 0.01940995268523693, "avg_return": 0.34878504276275635, "regret": 0.5128700733184814, "entropy": 0.7161017060279846, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:23.137688Z", "loop": 130, "env_steps": 80486399, "loss": 0.01826034113764763, "avg_return": 0.34820953011512756, "regret": 0.5128934979438782, "entropy": 0.7158514857292175, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:24.026916Z", "loop": 131, "env_steps": 81100799, "loss": 0.018164126202464104, "avg_return": 0.3550913631916046, "regret": 0.5128890872001648, "entropy": 0.7157962918281555, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:24.917097Z", "loop": 132, "env_steps": 81715199, "loss": 0.018692942336201668, "avg_return": 0.34567534923553467, "regret": 0.5128679275512695, "entropy": 0.7156095504760742, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:25.805484Z", "loop": 133, "env_steps": 82329599, "loss": 0.01781795732676983, "avg_return": 0.3489183187484741, "regret": 0.5129081010818481, "entropy": 0.7152828574180603, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:26.693284Z", "loop": 134, "env_steps": 82943999, "loss": 0.018728800117969513, "avg_return": 0.35843321681022644, "regret": 0.5129151344299316, "entropy": 0.7151260375976562, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:27.581162Z", "loop": 135, "env_steps": 83558399, "loss": 0.017784863710403442, "avg_return": 0.3472082018852234, "regret": 0.5129461288452148, "entropy": 0.7148640751838684, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:28.469200Z", "loop": 136, "env_steps": 84172799, "loss": 0.01891365461051464, "avg_return": 0.35154062509536743, "regret": 0.5129635334014893, "entropy": 0.714665412902832, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:29.358598Z", "loop": 137, "env_steps": 84787199, "loss": 0.020165693014860153, "avg_return": 0.35179445147514343, "regret": 0.5129703283309937, "entropy": 0.714598536491394, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:30.245781Z", "loop": 138, "env_steps": 85401599, "loss": 0.01689884439110756, "avg_return": 0.3488099277019501, "regret": 0.512958288192749, "entropy": 0.7144991755485535, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:31.134722Z", "loop": 139, "env_steps": 86015999, "loss": 0.018838584423065186, "avg_return": 0.35503247380256653, "regret": 0.5129362940788269, "entropy": 0.7144017815589905, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:32.022866Z", "loop": 140, "env_steps": 86630399, "loss": 0.018558336421847343, "avg_return": 0.34775662422180176, "regret": 0.5129416584968567, "entropy": 0.7143542766571045, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:32.911938Z", "loop": 141, "env_steps": 87244799, "loss": 0.01869601011276245, "avg_return": 0.35416609048843384, "regret": 0.512967050075531, "entropy": 0.7142629623413086, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:33.800827Z", "loop": 142, "env_steps": 87859199, "loss": 0.01926545239984989, "avg_return": 0.35615870356559753, "regret": 0.5129696130752563, "entropy": 0.7141084671020508, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:34.690191Z", "loop": 143, "env_steps": 88473599, "loss": 0.01767871342599392, "avg_return": 0.3487609922885895, "regret": 0.5129467844963074, "entropy": 0.7140544056892395, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:35.579137Z", "loop": 144, "env_steps": 89087999, "loss": 0.018503906205296516, "avg_return": 0.3558211624622345, "regret": 0.5129339694976807, "entropy": 0.7140542268753052, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:36.468499Z", "loop": 145, "env_steps": 89702399, "loss": 0.017807265743613243, "avg_return": 0.3518277704715729, "regret": 0.5128926634788513, "entropy": 0.7144565582275391, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:37.358759Z", "loop": 146, "env_steps": 90316799, "loss": 0.017897453159093857, "avg_return": 0.35182058811187744, "regret": 0.5128586888313293, "entropy": 0.7146661281585693, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:38.248947Z", "loop": 147, "env_steps": 90931199, "loss": 0.01786617748439312, "avg_return": 0.3493693470954895, "regret": 0.5128267407417297, "entropy": 0.7148391008377075, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:39.138295Z", "loop": 148, "env_steps": 91545599, "loss": 0.018337329849600792, "avg_return": 0.3529125452041626, "regret": 0.5128209590911865, "entropy": 0.7149159908294678, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:40.029941Z", "loop": 149, "env_steps": 92159999, "loss": 0.02017226628959179, "avg_return": 0.3505668044090271, "regret": 0.5128278732299805, "entropy": 0.7149839401245117, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:40.919993Z", "loop": 150, "env_steps": 92774399, "loss": 0.01811078004539013, "avg_return": 0.35057586431503296, "regret": 0.5128654837608337, "entropy": 0.7148264646530151, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:41.808999Z", "loop": 151, "env_steps": 93388799, "loss": 0.01803915947675705, "avg_return": 0.349242240190506, "regret": 0.5128929018974304, "entropy": 0.714706540107727, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:42.697827Z", "loop": 152, "env_steps": 94003199, "loss": 0.018820295110344887, "avg_return": 0.3522154688835144, "regret": 0.5128962397575378, "entropy": 0.7146788239479065, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:43.587306Z", "loop": 153, "env_steps": 94617599, "loss": 0.018495997413992882, "avg_return": 0.3501024842262268, "regret": 0.5128888487815857, "entropy": 0.7145424485206604, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:44.477778Z", "loop": 154, "env_steps": 95231999, "loss": 0.018805203959345818, "avg_return": 0.34692519903182983, "regret": 0.5128651261329651, "entropy": 0.7144748568534851, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:45.367708Z", "loop": 155, "env_steps": 95846399, "loss": 0.019422482699155807, "avg_return": 0.3511107861995697, "regret": 0.5128397345542908, "entropy": 0.7145557999610901, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:46.258230Z", "loop": 156, "env_steps": 96460799, "loss": 0.017376769334077835, "avg_return": 0.3462445139884949, "regret": 0.5128157734870911, "entropy": 0.714640200138092, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:47.147816Z", "loop": 157, "env_steps": 97075199, "loss": 0.018141118809580803, "avg_return": 0.34390878677368164, "regret": 0.5128160119056702, "entropy": 0.7147057056427002, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:48.036613Z", "loop": 158, "env_steps": 97689599, "loss": 0.019469914957880974, "avg_return": 0.3482625484466553, "regret": 0.5128070116043091, "entropy": 0.7146662473678589, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:48.925430Z", "loop": 159, "env_steps": 98303999, "loss": 0.019024183973670006, "avg_return": 0.34414759278297424, "regret": 0.5128213763237, "entropy": 0.7146164178848267, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:49.814410Z", "loop": 160, "env_steps": 98918399, "loss": 0.01935381442308426, "avg_return": 0.3549707531929016, "regret": 0.5128698945045471, "entropy": 0.7144343256950378, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:50.703657Z", "loop": 161, "env_steps": 99532799, "loss": 0.017614638432860374, "avg_return": 0.3458849787712097, "regret": 0.5129169821739197, "entropy": 0.7142133712768555, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:51.593859Z", "loop": 162, "env_steps": 100147199, "loss": 0.017613377422094345, "avg_return": 0.34582948684692383, "regret": 0.512980043888092, "entropy": 0.7138789296150208, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:52.482755Z", "loop": 163, "env_steps": 100761599, "loss": 0.01866600289940834, "avg_return": 0.3446526527404785, "regret": 0.5130450129508972, "entropy": 0.7134354710578918, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:53.369972Z", "loop": 164, "env_steps": 101375999, "loss": 0.019943200051784515, "avg_return": 0.3596237301826477, "regret": 0.5131037831306458, "entropy": 0.7129546403884888, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:54.257266Z", "loop": 165, "env_steps": 101990399, "loss": 0.017527379095554352, "avg_return": 0.3552802503108978, "regret": 0.5130941867828369, "entropy": 0.7128864526748657, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:55.146105Z", "loop": 166, "env_steps": 102604799, "loss": 0.01859942637383938, "avg_return": 0.35231271386146545, "regret": 0.5130377411842346, "entropy": 0.7129597663879395, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:56.034343Z", "loop": 167, "env_steps": 103219199, "loss": 0.01810285821557045, "avg_return": 0.3461328446865082, "regret": 0.5129909515380859, "entropy": 0.713068425655365, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:56.926032Z", "loop": 168, "env_steps": 103833599, "loss": 0.01857476681470871, "avg_return": 0.35110902786254883, "regret": 0.5129185914993286, "entropy": 0.7133957147598267, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:57.816025Z", "loop": 169, "env_steps": 104447999, "loss": 0.018800033256411552, "avg_return": 0.356173574924469, "regret": 0.5128616690635681, "entropy": 0.7135363817214966, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:58.705316Z", "loop": 170, "env_steps": 105062399, "loss": 0.018960172310471535, "avg_return": 0.3588964343070984, "regret": 0.5128425359725952, "entropy": 0.7136123776435852, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:25:59.594413Z", "loop": 171, "env_steps": 105676799, "loss": 0.018140194937586784, "avg_return": 0.3482091724872589, "regret": 0.5128198266029358, "entropy": 0.7135186791419983, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:00.484033Z", "loop": 172, "env_steps": 106291199, "loss": 0.018525632098317146, "avg_return": 0.3525306284427643, "regret": 0.5127953886985779, "entropy": 0.7136370539665222, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:01.374356Z", "loop": 173, "env_steps": 106905599, "loss": 0.018804531544446945, "avg_return": 0.35063010454177856, "regret": 0.5128238201141357, "entropy": 0.7132709622383118, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:02.263703Z", "loop": 174, "env_steps": 107519999, "loss": 0.019224122166633606, "avg_return": 0.35437995195388794, "regret": 0.5129044651985168, "entropy": 0.7128826379776001, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:03.152859Z", "loop": 175, "env_steps": 108134399, "loss": 0.018610423430800438, "avg_return": 0.3495315611362457, "regret": 0.5131059885025024, "entropy": 0.7119396328926086, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:04.041933Z", "loop": 176, "env_steps": 108748799, "loss": 0.018462836742401123, "avg_return": 0.351683109998703, "regret": 0.513425350189209, "entropy": 0.7103264331817627, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:04.933470Z", "loop": 177, "env_steps": 109363199, "loss": 0.01747211627662182, "avg_return": 0.34429919719696045, "regret": 0.5139376521110535, "entropy": 0.7077831625938416, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:05.824615Z", "loop": 178, "env_steps": 109977599, "loss": 0.01775042526423931, "avg_return": 0.34505656361579895, "regret": 0.5142697095870972, "entropy": 0.7061415910720825, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:06.714780Z", "loop": 179, "env_steps": 110591999, "loss": 0.01862778514623642, "avg_return": 0.3534124195575714, "regret": 0.5144733786582947, "entropy": 0.705134391784668, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:07.607952Z", "loop": 180, "env_steps": 111206399, "loss": 0.017912311479449272, "avg_return": 0.3531480133533478, "regret": 0.5145213007926941, "entropy": 0.7047964930534363, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:08.498648Z", "loop": 181, "env_steps": 111820799, "loss": 0.018681615591049194, "avg_return": 0.3533490300178528, "regret": 0.514577329158783, "entropy": 0.7046023011207581, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:09.388136Z", "loop": 182, "env_steps": 112435199, "loss": 0.02016321010887623, "avg_return": 0.3516940772533417, "regret": 0.5142523646354675, "entropy": 0.7058866024017334, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:10.278173Z", "loop": 183, "env_steps": 113049599, "loss": 0.01926627941429615, "avg_return": 0.3496428430080414, "regret": 0.5136942267417908, "entropy": 0.7084659337997437, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:11.169501Z", "loop": 184, "env_steps": 113663999, "loss": 0.017541082575917244, "avg_return": 0.35043469071388245, "regret": 0.5132307410240173, "entropy": 0.710675060749054, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:12.058256Z", "loop": 185, "env_steps": 114278399, "loss": 0.017797859385609627, "avg_return": 0.34902045130729675, "regret": 0.5129244327545166, "entropy": 0.7120862603187561, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:12.946624Z", "loop": 186, "env_steps": 114892799, "loss": 0.01752343215048313, "avg_return": 0.344348669052124, "regret": 0.5127936601638794, "entropy": 0.7127642631530762, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:13.836855Z", "loop": 187, "env_steps": 115507199, "loss": 0.018723180517554283, "avg_return": 0.34929201006889343, "regret": 0.5128002762794495, "entropy": 0.7129013538360596, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:14.728319Z", "loop": 188, "env_steps": 116121599, "loss": 0.018260670825839043, "avg_return": 0.3485771417617798, "regret": 0.5128700733184814, "entropy": 0.7127645015716553, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:15.617412Z", "loop": 189, "env_steps": 116735999, "loss": 0.018506566062569618, "avg_return": 0.3502156138420105, "regret": 0.5130154490470886, "entropy": 0.7123001217842102, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:16.505644Z", "loop": 190, "env_steps": 117350399, "loss": 0.018573392182588577, "avg_return": 0.35442978143692017, "regret": 0.5131962299346924, "entropy": 0.7115942239761353, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:17.394046Z", "loop": 191, "env_steps": 117964799, "loss": 0.0184535663574934, "avg_return": 0.34065473079681396, "regret": 0.5133067965507507, "entropy": 0.7109053134918213, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:18.282825Z", "loop": 192, "env_steps": 118579199, "loss": 0.01811465620994568, "avg_return": 0.34816762804985046, "regret": 0.5132901668548584, "entropy": 0.7106212377548218, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:19.173118Z", "loop": 193, "env_steps": 119193599, "loss": 0.018743013963103294, "avg_return": 0.34951895475387573, "regret": 0.5132372975349426, "entropy": 0.7104984521865845, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:20.064047Z", "loop": 194, "env_steps": 119807999, "loss": 0.018559206277132034, "avg_return": 0.35173046588897705, "regret": 0.5131163597106934, "entropy": 0.710572361946106, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:20.953983Z", "loop": 195, "env_steps": 120422399, "loss": 0.018098441883921623, "avg_return": 0.3465231657028198, "regret": 0.5129297971725464, "entropy": 0.7110008597373962, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:21.844495Z", "loop": 196, "env_steps": 121036799, "loss": 0.01914217136800289, "avg_return": 0.3509174585342407, "regret": 0.5127841830253601, "entropy": 0.7110666036605835, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:22.734639Z", "loop": 197, "env_steps": 121651199, "loss": 0.019051967188715935, "avg_return": 0.3511980473995209, "regret": 0.5127900242805481, "entropy": 0.7105777859687805, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:23.626128Z", "loop": 198, "env_steps": 122265599, "loss": 0.018059149384498596, "avg_return": 0.35176408290863037, "regret": 0.5129111409187317, "entropy": 0.7095614671707153, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:24.514972Z", "loop": 199, "env_steps": 122879999, "loss": 0.01799042895436287, "avg_return": 0.34983059763908386, "regret": 0.5130895376205444, "entropy": 0.7082664966583252, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:25.403830Z", "loop": 200, "env_steps": 123494399, "loss": 0.018485311418771744, "avg_return": 0.347423791885376, "regret": 0.5132717490196228, "entropy": 0.7070776224136353, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:26.292285Z", "loop": 201, "env_steps": 124108799, "loss": 0.01752462051808834, "avg_return": 0.35006701946258545, "regret": 0.513485312461853, "entropy": 0.7056131362915039, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:27.180480Z", "loop": 202, "env_steps": 124723199, "loss": 0.017103007063269615, "avg_return": 0.3425567150115967, "regret": 0.513579785823822, "entropy": 0.7047898173332214, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:28.071732Z", "loop": 203, "env_steps": 125337599, "loss": 0.01813775859773159, "avg_return": 0.35434597730636597, "regret": 0.513733446598053, "entropy": 0.7037763595581055, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:28.962164Z", "loop": 204, "env_steps": 125951999, "loss": 0.01789562590420246, "avg_return": 0.3568470776081085, "regret": 0.5137550234794617, "entropy": 0.7033935189247131, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:29.851532Z", "loop": 205, "env_steps": 126566399, "loss": 0.017195425927639008, "avg_return": 0.3435366451740265, "regret": 0.5136501789093018, "entropy": 0.7035608291625977, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:30.742372Z", "loop": 206, "env_steps": 127180799, "loss": 0.01747470535337925, "avg_return": 0.3520057797431946, "regret": 0.5135208964347839, "entropy": 0.7036370038986206, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:31.632172Z", "loop": 207, "env_steps": 127795199, "loss": 0.018396925181150436, "avg_return": 0.35239431262016296, "regret": 0.5132533311843872, "entropy": 0.7043917179107666, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:32.521817Z", "loop": 208, "env_steps": 128409599, "loss": 0.017431823536753654, "avg_return": 0.3481437861919403, "regret": 0.5129973292350769, "entropy": 0.705215334892273, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:33.412062Z", "loop": 209, "env_steps": 129023999, "loss": 0.019011646509170532, "avg_return": 0.34990522265434265, "regret": 0.5128361582756042, "entropy": 0.705756425857544, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:34.299323Z", "loop": 210, "env_steps": 129638399, "loss": 0.019231583923101425, "avg_return": 0.35880449414253235, "regret": 0.5127427577972412, "entropy": 0.7060204744338989, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:35.188478Z", "loop": 211, "env_steps": 130252799, "loss": 0.018016375601291656, "avg_return": 0.3477306365966797, "regret": 0.5127264261245728, "entropy": 0.7060034871101379, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:36.078943Z", "loop": 212, "env_steps": 130867199, "loss": 0.015547185204923153, "avg_return": 0.3421918451786041, "regret": 0.5127375721931458, "entropy": 0.7058336138725281, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:36.970592Z", "loop": 213, "env_steps": 131481599, "loss": 0.01755089871585369, "avg_return": 0.352202445268631, "regret": 0.512760579586029, "entropy": 0.7055414915084839, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:37.862202Z", "loop": 214, "env_steps": 132095999, "loss": 0.017706573009490967, "avg_return": 0.3472369611263275, "regret": 0.5127844214439392, "entropy": 0.7051841616630554, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:38.753097Z", "loop": 215, "env_steps": 132710399, "loss": 0.018481982871890068, "avg_return": 0.34809279441833496, "regret": 0.5127996206283569, "entropy": 0.7050014138221741, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:39.643152Z", "loop": 216, "env_steps": 133324799, "loss": 0.01760954223573208, "avg_return": 0.3451727628707886, "regret": 0.5127748847007751, "entropy": 0.7048507928848267, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:40.532673Z", "loop": 217, "env_steps": 133939199, "loss": 0.018082505092024803, "avg_return": 0.3565617799758911, "regret": 0.5127663016319275, "entropy": 0.7045654654502869, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:41.422209Z", "loop": 218, "env_steps": 134553599, "loss": 0.017437662929296494, "avg_return": 0.34687840938568115, "regret": 0.5127400159835815, "entropy": 0.7044671773910522, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:42.310662Z", "loop": 219, "env_steps": 135167999, "loss": 0.018830742686986923, "avg_return": 0.35555267333984375, "regret": 0.5127394795417786, "entropy": 0.7043225169181824, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:43.200642Z", "loop": 220, "env_steps": 135782399, "loss": 0.01927373558282852, "avg_return": 0.3509915769100189, "regret": 0.5127639770507812, "entropy": 0.7042219638824463, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:44.090973Z", "loop": 221, "env_steps": 136396799, "loss": 0.01831991970539093, "avg_return": 0.3406390845775604, "regret": 0.5127519369125366, "entropy": 0.7043184041976929, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:44.979079Z", "loop": 222, "env_steps": 137011199, "loss": 0.01739087514579296, "avg_return": 0.3500351905822754, "regret": 0.5127264261245728, "entropy": 0.7044309377670288, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:45.867639Z", "loop": 223, "env_steps": 137625599, "loss": 0.018120644614100456, "avg_return": 0.35317495465278625, "regret": 0.5127277374267578, "entropy": 0.7043906450271606, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:46.755959Z", "loop": 224, "env_steps": 138239999, "loss": 0.01806478016078472, "avg_return": 0.34575873613357544, "regret": 0.5127415060997009, "entropy": 0.7044169306755066, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:47.644788Z", "loop": 225, "env_steps": 138854399, "loss": 0.017841558903455734, "avg_return": 0.35405248403549194, "regret": 0.5127477645874023, "entropy": 0.7044380307197571, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:48.533256Z", "loop": 226, "env_steps": 139468799, "loss": 0.018653782084584236, "avg_return": 0.3474331200122833, "regret": 0.5127391219139099, "entropy": 0.7044899463653564, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:49.422824Z", "loop": 227, "env_steps": 140083199, "loss": 0.016722505912184715, "avg_return": 0.35083261132240295, "regret": 0.5127092599868774, "entropy": 0.7045024037361145, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:50.310853Z", "loop": 228, "env_steps": 140697599, "loss": 0.0181967131793499, "avg_return": 0.35143715143203735, "regret": 0.5127192139625549, "entropy": 0.7043749094009399, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:51.199974Z", "loop": 229, "env_steps": 141311999, "loss": 0.016572091728448868, "avg_return": 0.3524230718612671, "regret": 0.5127586722373962, "entropy": 0.7041357755661011, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:52.088886Z", "loop": 230, "env_steps": 141926399, "loss": 0.018420439213514328, "avg_return": 0.3555123805999756, "regret": 0.5128515958786011, "entropy": 0.7035895586013794, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:52.978735Z", "loop": 231, "env_steps": 142540799, "loss": 0.018795978277921677, "avg_return": 0.3505331575870514, "regret": 0.5129570960998535, "entropy": 0.7028900384902954, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:53.868621Z", "loop": 232, "env_steps": 143155199, "loss": 0.019238749518990517, "avg_return": 0.3576417863368988, "regret": 0.5129441618919373, "entropy": 0.7027708888053894, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:54.760717Z", "loop": 233, "env_steps": 143769599, "loss": 0.017715435475111008, "avg_return": 0.3524487018585205, "regret": 0.5128841996192932, "entropy": 0.7029045224189758, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:55.650425Z", "loop": 234, "env_steps": 144383999, "loss": 0.017712144181132317, "avg_return": 0.346036434173584, "regret": 0.5128592252731323, "entropy": 0.7029123306274414, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:56.540262Z", "loop": 235, "env_steps": 144998399, "loss": 0.016710421070456505, "avg_return": 0.3525913655757904, "regret": 0.5127760767936707, "entropy": 0.7031111717224121, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:57.430278Z", "loop": 236, "env_steps": 145612799, "loss": 0.018469631671905518, "avg_return": 0.34979447722435, "regret": 0.5127471685409546, "entropy": 0.7030750513076782, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:58.321910Z", "loop": 237, "env_steps": 146227199, "loss": 0.017466353252530098, "avg_return": 0.349901020526886, "regret": 0.5127232670783997, "entropy": 0.702979326248169, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:26:59.211386Z", "loop": 238, "env_steps": 146841599, "loss": 0.017696376889944077, "avg_return": 0.346204936504364, "regret": 0.5127320289611816, "entropy": 0.7026918530464172, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:00.100745Z", "loop": 239, "env_steps": 147455999, "loss": 0.01683252863585949, "avg_return": 0.35240527987480164, "regret": 0.512712836265564, "entropy": 0.7027069330215454, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:00.991910Z", "loop": 240, "env_steps": 148070399, "loss": 0.018026208505034447, "avg_return": 0.3489556312561035, "regret": 0.5126962661743164, "entropy": 0.7027252316474915, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:01.882316Z", "loop": 241, "env_steps": 148684799, "loss": 0.016531124711036682, "avg_return": 0.34668904542922974, "regret": 0.5126935243606567, "entropy": 0.7029010057449341, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:02.771285Z", "loop": 242, "env_steps": 149299199, "loss": 0.017917482182383537, "avg_return": 0.34938931465148926, "regret": 0.5126911401748657, "entropy": 0.7029417753219604, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:03.659663Z", "loop": 243, "env_steps": 149913599, "loss": 0.016611238941550255, "avg_return": 0.35097795724868774, "regret": 0.5126964449882507, "entropy": 0.7030694484710693, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:04.551606Z", "loop": 244, "env_steps": 150527999, "loss": 0.018996940925717354, "avg_return": 0.35169461369514465, "regret": 0.5126925706863403, "entropy": 0.7031387090682983, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:05.443049Z", "loop": 245, "env_steps": 151142399, "loss": 0.018240686506032944, "avg_return": 0.3483550548553467, "regret": 0.5126955509185791, "entropy": 0.703092634677887, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:06.334110Z", "loop": 246, "env_steps": 151756799, "loss": 0.017100496217608452, "avg_return": 0.3490617871284485, "regret": 0.5126999020576477, "entropy": 0.7030346393585205, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:07.221949Z", "loop": 247, "env_steps": 152371199, "loss": 0.018320031464099884, "avg_return": 0.3531700074672699, "regret": 0.5127160549163818, "entropy": 0.7029148936271667, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:08.110362Z", "loop": 248, "env_steps": 152985599, "loss": 0.018253309652209282, "avg_return": 0.34887126088142395, "regret": 0.5127172470092773, "entropy": 0.7027207016944885, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:08.998353Z", "loop": 249, "env_steps": 153599999, "loss": 0.0175851508975029, "avg_return": 0.3552040755748749, "regret": 0.5127449035644531, "entropy": 0.7024556398391724, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:09.888062Z", "loop": 250, "env_steps": 154214399, "loss": 0.018215490505099297, "avg_return": 0.3511425852775574, "regret": 0.5127901434898376, "entropy": 0.7020448446273804, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:10.740819Z", "loop": 251, "env_steps": 154828799, "loss": 0.018390515819191933, "avg_return": 0.35357147455215454, "regret": 0.5127901434898376, "entropy": 0.7017092704772949, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:11.631174Z", "loop": 252, "env_steps": 155443199, "loss": 0.01911069080233574, "avg_return": 0.35754072666168213, "regret": 0.5128698945045471, "entropy": 0.7013934254646301, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:12.482574Z", "loop": 253, "env_steps": 156057599, "loss": 0.018667161464691162, "avg_return": 0.3535471558570862, "regret": 0.5128698945045471, "entropy": 0.7012378573417664, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:13.370894Z", "loop": 254, "env_steps": 156671999, "loss": 0.01817755028605461, "avg_return": 0.35141995549201965, "regret": 0.5128339529037476, "entropy": 0.7012525796890259, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:14.223225Z", "loop": 255, "env_steps": 157286399, "loss": 0.019356880336999893, "avg_return": 0.35734823346138, "regret": 0.5128339529037476, "entropy": 0.7012327909469604, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:15.113412Z", "loop": 256, "env_steps": 157900799, "loss": 0.01831614039838314, "avg_return": 0.3560276925563812, "regret": 0.5128161907196045, "entropy": 0.7011609673500061, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:15.965858Z", "loop": 257, "env_steps": 158515199, "loss": 0.017976386472582817, "avg_return": 0.34593480825424194, "regret": 0.5128161907196045, "entropy": 0.7010537981987, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:16.854083Z", "loop": 258, "env_steps": 159129599, "loss": 0.017764292657375336, "avg_return": 0.3449685275554657, "regret": 0.5127987265586853, "entropy": 0.7009932398796082, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:17.707747Z", "loop": 259, "env_steps": 159743999, "loss": 0.01798328571021557, "avg_return": 0.3586914539337158, "regret": 0.5127987265586853, "entropy": 0.7012511491775513, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:18.599536Z", "loop": 260, "env_steps": 160358399, "loss": 0.017151398584246635, "avg_return": 0.34835776686668396, "regret": 0.5126745700836182, "entropy": 0.7011908292770386, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:19.452995Z", "loop": 261, "env_steps": 160972799, "loss": 0.018223905935883522, "avg_return": 0.3536687195301056, "regret": 0.5126745700836182, "entropy": 0.7010611295700073, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:20.342253Z", "loop": 262, "env_steps": 161587199, "loss": 0.018620016053318977, "avg_return": 0.3547903597354889, "regret": 0.5126904845237732, "entropy": 0.7007755637168884, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:21.195378Z", "loop": 263, "env_steps": 162201599, "loss": 0.01879427582025528, "avg_return": 0.3546532690525055, "regret": 0.5126904845237732, "entropy": 0.7003045678138733, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:22.085560Z", "loop": 264, "env_steps": 162815999, "loss": 0.017338579520583153, "avg_return": 0.3496689200401306, "regret": 0.5127934217453003, "entropy": 0.6999189853668213, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:22.939271Z", "loop": 265, "env_steps": 163430399, "loss": 0.016719792038202286, "avg_return": 0.34186020493507385, "regret": 0.5127934217453003, "entropy": 0.6992842555046082, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:23.828668Z", "loop": 266, "env_steps": 164044799, "loss": 0.01839713379740715, "avg_return": 0.3490295112133026, "regret": 0.5129918456077576, "entropy": 0.6988093256950378, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:24.682053Z", "loop": 267, "env_steps": 164659199, "loss": 0.017582854256033897, "avg_return": 0.350717157125473, "regret": 0.5129918456077576, "entropy": 0.698839545249939, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:25.571786Z", "loop": 268, "env_steps": 165273599, "loss": 0.018276194110512733, "avg_return": 0.3538205921649933, "regret": 0.5128825902938843, "entropy": 0.6989618539810181, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:26.423999Z", "loop": 269, "env_steps": 165887999, "loss": 0.01819235272705555, "avg_return": 0.34876948595046997, "regret": 0.5128825902938843, "entropy": 0.6992036700248718, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:27.314388Z", "loop": 270, "env_steps": 166502399, "loss": 0.01858578436076641, "avg_return": 0.3576955199241638, "regret": 0.5127881169319153, "entropy": 0.6992279291152954, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:28.167229Z", "loop": 271, "env_steps": 167116799, "loss": 0.018581341952085495, "avg_return": 0.3597191572189331, "regret": 0.5127881169319153, "entropy": 0.6994991898536682, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:29.056901Z", "loop": 272, "env_steps": 167731199, "loss": 0.018785536289215088, "avg_return": 0.350119024515152, "regret": 0.512671172618866, "entropy": 0.6995875239372253, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:29.908377Z", "loop": 273, "env_steps": 168345599, "loss": 0.018643338233232498, "avg_return": 0.34852564334869385, "regret": 0.512671172618866, "entropy": 0.6996245980262756, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:30.799223Z", "loop": 274, "env_steps": 168959999, "loss": 0.01814812235534191, "avg_return": 0.35284942388534546, "regret": 0.5126729607582092, "entropy": 0.6995329260826111, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:31.652447Z", "loop": 275, "env_steps": 169574399, "loss": 0.018126413226127625, "avg_return": 0.35084566473960876, "regret": 0.5126729607582092, "entropy": 0.6993923187255859, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:32.541038Z", "loop": 276, "env_steps": 170188799, "loss": 0.01887020282447338, "avg_return": 0.35810035467147827, "regret": 0.5127233862876892, "entropy": 0.6994001269340515, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:33.392182Z", "loop": 277, "env_steps": 170803199, "loss": 0.017253125086426735, "avg_return": 0.3542199730873108, "regret": 0.5127233862876892, "entropy": 0.6994158625602722, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:34.281217Z", "loop": 278, "env_steps": 171417599, "loss": 0.017694706097245216, "avg_return": 0.35187041759490967, "regret": 0.5127296447753906, "entropy": 0.6995029449462891, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:35.134016Z", "loop": 279, "env_steps": 172031999, "loss": 0.017446866258978844, "avg_return": 0.3485527038574219, "regret": 0.5127296447753906, "entropy": 0.6997196674346924, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:36.022667Z", "loop": 280, "env_steps": 172646399, "loss": 0.018177123740315437, "avg_return": 0.3547246754169464, "regret": 0.5126578211784363, "entropy": 0.6998457908630371, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:36.874803Z", "loop": 281, "env_steps": 173260799, "loss": 0.017682349309325218, "avg_return": 0.3483320474624634, "regret": 0.5126578211784363, "entropy": 0.6995509266853333, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:37.762261Z", "loop": 282, "env_steps": 173875199, "loss": 0.01746685616672039, "avg_return": 0.3435761034488678, "regret": 0.5127801299095154, "entropy": 0.6992276906967163, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:38.614241Z", "loop": 283, "env_steps": 174489599, "loss": 0.01745872013270855, "avg_return": 0.3496270775794983, "regret": 0.5127801299095154, "entropy": 0.6987879872322083, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:39.505421Z", "loop": 284, "env_steps": 175103999, "loss": 0.017515456303954124, "avg_return": 0.34792497754096985, "regret": 0.5129051208496094, "entropy": 0.6986079812049866, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:40.358664Z", "loop": 285, "env_steps": 175718399, "loss": 0.01906869187951088, "avg_return": 0.34844157099723816, "regret": 0.5129051208496094, "entropy": 0.6987001299858093, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:41.249499Z", "loop": 286, "env_steps": 176332799, "loss": 0.01704317331314087, "avg_return": 0.346894234418869, "regret": 0.5127633810043335, "entropy": 0.6991416215896606, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:42.101326Z", "loop": 287, "env_steps": 176947199, "loss": 0.018438799306750298, "avg_return": 0.3512480556964874, "regret": 0.5127633810043335, "entropy": 0.6995489001274109, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:42.992065Z", "loop": 288, "env_steps": 177561599, "loss": 0.01838829182088375, "avg_return": 0.3524389863014221, "regret": 0.5126505494117737, "entropy": 0.6996307969093323, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:43.846138Z", "loop": 289, "env_steps": 178175999, "loss": 0.01794544607400894, "avg_return": 0.35477733612060547, "regret": 0.5126505494117737, "entropy": 0.6995257139205933, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:44.736044Z", "loop": 290, "env_steps": 178790399, "loss": 0.017724191769957542, "avg_return": 0.3509984016418457, "regret": 0.5127519369125366, "entropy": 0.6992377042770386, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:45.588394Z", "loop": 291, "env_steps": 179404799, "loss": 0.017326992005109787, "avg_return": 0.3491760492324829, "regret": 0.5127519369125366, "entropy": 0.6986677050590515, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:46.478685Z", "loop": 292, "env_steps": 180019199, "loss": 0.017370736226439476, "avg_return": 0.3474883735179901, "regret": 0.513092041015625, "entropy": 0.6979190111160278, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:47.332025Z", "loop": 293, "env_steps": 180633599, "loss": 0.017436934635043144, "avg_return": 0.34472647309303284, "regret": 0.513092041015625, "entropy": 0.6970246434211731, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:48.221157Z", "loop": 294, "env_steps": 181247999, "loss": 0.019236495718359947, "avg_return": 0.34910115599632263, "regret": 0.5132839679718018, "entropy": 0.6972257494926453, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:49.074617Z", "loop": 295, "env_steps": 181862399, "loss": 0.016981635242700577, "avg_return": 0.3479247987270355, "regret": 0.5132839679718018, "entropy": 0.6979606747627258, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:49.963390Z", "loop": 296, "env_steps": 182476799, "loss": 0.017414823174476624, "avg_return": 0.3547024726867676, "regret": 0.5128750801086426, "entropy": 0.6988757252693176, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:50.816842Z", "loop": 297, "env_steps": 183091199, "loss": 0.016988614574074745, "avg_return": 0.34279248118400574, "regret": 0.5128750801086426, "entropy": 0.6994602084159851, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:51.706593Z", "loop": 298, "env_steps": 183705599, "loss": 0.018824296072125435, "avg_return": 0.35107192397117615, "regret": 0.5126532912254333, "entropy": 0.6997907161712646, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:52.558836Z", "loop": 299, "env_steps": 184319999, "loss": 0.018422286957502365, "avg_return": 0.3522472679615021, "regret": 0.5126532912254333, "entropy": 0.6997211575508118, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:53.446595Z", "loop": 300, "env_steps": 184934399, "loss": 0.017953453585505486, "avg_return": 0.3509374260902405, "regret": 0.5127352476119995, "entropy": 0.6995270252227783, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:54.298572Z", "loop": 301, "env_steps": 185548799, "loss": 0.017969515174627304, "avg_return": 0.35238251090049744, "regret": 0.5127352476119995, "entropy": 0.6990683674812317, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:55.187519Z", "loop": 302, "env_steps": 186163199, "loss": 0.01821594499051571, "avg_return": 0.34696510434150696, "regret": 0.5129497051239014, "entropy": 0.6985907554626465, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:56.039585Z", "loop": 303, "env_steps": 186777599, "loss": 0.017689315602183342, "avg_return": 0.35099050402641296, "regret": 0.5129497051239014, "entropy": 0.6982320547103882, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:56.928482Z", "loop": 304, "env_steps": 187391999, "loss": 0.018292656168341637, "avg_return": 0.34997451305389404, "regret": 0.5130992531776428, "entropy": 0.6981316804885864, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:57.781830Z", "loop": 305, "env_steps": 188006399, "loss": 0.01847362332046032, "avg_return": 0.35252082347869873, "regret": 0.5130992531776428, "entropy": 0.6984567642211914, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:58.670704Z", "loop": 306, "env_steps": 188620799, "loss": 0.017765820026397705, "avg_return": 0.3531962037086487, "regret": 0.5129666924476624, "entropy": 0.6988940238952637, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:27:59.523028Z", "loop": 307, "env_steps": 189235199, "loss": 0.019970513880252838, "avg_return": 0.35564708709716797, "regret": 0.5129666924476624, "entropy": 0.699585497379303, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:00.412795Z", "loop": 308, "env_steps": 189849599, "loss": 0.018033644184470177, "avg_return": 0.3474450409412384, "regret": 0.5126968026161194, "entropy": 0.7004817724227905, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:01.266118Z", "loop": 309, "env_steps": 190463999, "loss": 0.017695516347885132, "avg_return": 0.349656343460083, "regret": 0.5126968026161194, "entropy": 0.7009274959564209, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:02.157920Z", "loop": 310, "env_steps": 191078399, "loss": 0.01740548014640808, "avg_return": 0.34129998087882996, "regret": 0.5127193927764893, "entropy": 0.7009083032608032, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:03.010791Z", "loop": 311, "env_steps": 191692799, "loss": 0.017359798774123192, "avg_return": 0.34989696741104126, "regret": 0.5127193927764893, "entropy": 0.7005828022956848, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:03.900774Z", "loop": 312, "env_steps": 192307199, "loss": 0.018903300166130066, "avg_return": 0.35478001832962036, "regret": 0.5131204128265381, "entropy": 0.699642539024353, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:04.754449Z", "loop": 313, "env_steps": 192921599, "loss": 0.017693087458610535, "avg_return": 0.3473493754863739, "regret": 0.5131204128265381, "entropy": 0.6986056566238403, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:05.646035Z", "loop": 314, "env_steps": 193535999, "loss": 0.01784696988761425, "avg_return": 0.35389015078544617, "regret": 0.513642430305481, "entropy": 0.6977814435958862, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:06.498338Z", "loop": 315, "env_steps": 194150399, "loss": 0.017835525795817375, "avg_return": 0.3533935546875, "regret": 0.513642430305481, "entropy": 0.6981781125068665, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:07.389024Z", "loop": 316, "env_steps": 194764799, "loss": 0.01754867285490036, "avg_return": 0.34557828307151794, "regret": 0.5132278800010681, "entropy": 0.6996574997901917, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:08.243071Z", "loop": 317, "env_steps": 195379199, "loss": 0.018091095611453056, "avg_return": 0.3544726073741913, "regret": 0.5132278800010681, "entropy": 0.700514018535614, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:09.132124Z", "loop": 318, "env_steps": 195993599, "loss": 0.018147258087992668, "avg_return": 0.3520253002643585, "regret": 0.5128302574157715, "entropy": 0.7013285756111145, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:09.985263Z", "loop": 319, "env_steps": 196607999, "loss": 0.01793055422604084, "avg_return": 0.3461557626724243, "regret": 0.5128302574157715, "entropy": 0.7017301321029663, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:10.875457Z", "loop": 320, "env_steps": 197222399, "loss": 0.01652119867503643, "avg_return": 0.3487193286418915, "regret": 0.5126587152481079, "entropy": 0.7018741965293884, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:11.727516Z", "loop": 321, "env_steps": 197836799, "loss": 0.018552152439951897, "avg_return": 0.34792307019233704, "regret": 0.5126587152481079, "entropy": 0.7017967700958252, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:12.618627Z", "loop": 322, "env_steps": 198451199, "loss": 0.017400186508893967, "avg_return": 0.34657564759254456, "regret": 0.5127565860748291, "entropy": 0.701324999332428, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:13.471600Z", "loop": 323, "env_steps": 199065599, "loss": 0.017173349857330322, "avg_return": 0.35853034257888794, "regret": 0.5127565860748291, "entropy": 0.7007911801338196, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:14.362166Z", "loop": 324, "env_steps": 199679999, "loss": 0.01828635297715664, "avg_return": 0.3494870960712433, "regret": 0.512996256351471, "entropy": 0.7004644274711609, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:15.214701Z", "loop": 325, "env_steps": 200294399, "loss": 0.018902486190199852, "avg_return": 0.355563223361969, "regret": 0.512996256351471, "entropy": 0.6999086737632751, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:16.104721Z", "loop": 326, "env_steps": 200908799, "loss": 0.018713803961873055, "avg_return": 0.3453253209590912, "regret": 0.513430655002594, "entropy": 0.6985607743263245, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:16.957635Z", "loop": 327, "env_steps": 201523199, "loss": 0.017670342698693275, "avg_return": 0.3518974781036377, "regret": 0.513430655002594, "entropy": 0.6966795921325684, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:17.849430Z", "loop": 328, "env_steps": 202137599, "loss": 0.018354525789618492, "avg_return": 0.35383665561676025, "regret": 0.514041006565094, "entropy": 0.6960711479187012, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:18.701759Z", "loop": 329, "env_steps": 202751999, "loss": 0.016812272369861603, "avg_return": 0.3423457443714142, "regret": 0.514041006565094, "entropy": 0.6965813040733337, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:19.592388Z", "loop": 330, "env_steps": 203366399, "loss": 0.018805978819727898, "avg_return": 0.3508265018463135, "regret": 0.5137016773223877, "entropy": 0.6979838609695435, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:20.444434Z", "loop": 331, "env_steps": 203980799, "loss": 0.01876877062022686, "avg_return": 0.34963899850845337, "regret": 0.5137016773223877, "entropy": 0.6996200680732727, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:21.336166Z", "loop": 332, "env_steps": 204595199, "loss": 0.018839020282030106, "avg_return": 0.35532984137535095, "regret": 0.5130192637443542, "entropy": 0.7013076543807983, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:22.189386Z", "loop": 333, "env_steps": 205209599, "loss": 0.017492836341261864, "avg_return": 0.34905996918678284, "regret": 0.5130192637443542, "entropy": 0.702558159828186, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:23.081624Z", "loop": 334, "env_steps": 205823999, "loss": 0.017895761877298355, "avg_return": 0.3541102409362793, "regret": 0.5126739740371704, "entropy": 0.7034718990325928, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:23.934610Z", "loop": 335, "env_steps": 206438399, "loss": 0.018420066684484482, "avg_return": 0.3534805476665497, "regret": 0.5126739740371704, "entropy": 0.703872799873352, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:24.824197Z", "loop": 336, "env_steps": 207052799, "loss": 0.017718343064188957, "avg_return": 0.3493604063987732, "regret": 0.5128306746482849, "entropy": 0.7034839391708374, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:25.677698Z", "loop": 337, "env_steps": 207667199, "loss": 0.018893292173743248, "avg_return": 0.3535144627094269, "regret": 0.5128306746482849, "entropy": 0.7028833031654358, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:26.568042Z", "loop": 338, "env_steps": 208281599, "loss": 0.018361840397119522, "avg_return": 0.3477195203304291, "regret": 0.5132719874382019, "entropy": 0.7021066546440125, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:27.419894Z", "loop": 339, "env_steps": 208895999, "loss": 0.017509497702121735, "avg_return": 0.34848344326019287, "regret": 0.5132719874382019, "entropy": 0.7017979025840759, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:28.308507Z", "loop": 340, "env_steps": 209510399, "loss": 0.018642611801624298, "avg_return": 0.3536449372768402, "regret": 0.5134556293487549, "entropy": 0.7018665671348572, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:29.161265Z", "loop": 341, "env_steps": 210124799, "loss": 0.018727021291851997, "avg_return": 0.3569774329662323, "regret": 0.5134556293487549, "entropy": 0.702097475528717, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:30.051509Z", "loop": 342, "env_steps": 210739199, "loss": 0.019622420892119408, "avg_return": 0.3495523929595947, "regret": 0.5133606195449829, "entropy": 0.7027246356010437, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:30.904638Z", "loop": 343, "env_steps": 211353599, "loss": 0.020419424399733543, "avg_return": 0.36498770117759705, "regret": 0.5133606195449829, "entropy": 0.7036454677581787, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:31.792873Z", "loop": 344, "env_steps": 211967999, "loss": 0.0180958341807127, "avg_return": 0.35189419984817505, "regret": 0.5130723118782043, "entropy": 0.7044547200202942, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:32.644717Z", "loop": 345, "env_steps": 212582399, "loss": 0.019378717988729477, "avg_return": 0.347743958234787, "regret": 0.5130723118782043, "entropy": 0.7056565880775452, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:33.533498Z", "loop": 346, "env_steps": 213196799, "loss": 0.017001084983348846, "avg_return": 0.3480371832847595, "regret": 0.5128381848335266, "entropy": 0.7063063383102417, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:34.386016Z", "loop": 347, "env_steps": 213811199, "loss": 0.018549149855971336, "avg_return": 0.34857067465782166, "regret": 0.5128381848335266, "entropy": 0.7069732546806335, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:35.275147Z", "loop": 348, "env_steps": 214425599, "loss": 0.01737719587981701, "avg_return": 0.3420707881450653, "regret": 0.5127524733543396, "entropy": 0.7072809934616089, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:36.128458Z", "loop": 349, "env_steps": 215039999, "loss": 0.018862660974264145, "avg_return": 0.3547591269016266, "regret": 0.5127524733543396, "entropy": 0.7075512409210205, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:37.018369Z", "loop": 350, "env_steps": 215654399, "loss": 0.017667580395936966, "avg_return": 0.3511103689670563, "regret": 0.5126882195472717, "entropy": 0.7077760696411133, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:37.870726Z", "loop": 351, "env_steps": 216268799, "loss": 0.016994668170809746, "avg_return": 0.35206884145736694, "regret": 0.5126882195472717, "entropy": 0.7078042030334473, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:38.761101Z", "loop": 352, "env_steps": 216883199, "loss": 0.016933215782046318, "avg_return": 0.3542732298374176, "regret": 0.5127459764480591, "entropy": 0.7077385783195496, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:39.614571Z", "loop": 353, "env_steps": 217497599, "loss": 0.01772572658956051, "avg_return": 0.35450103878974915, "regret": 0.5127459764480591, "entropy": 0.7077338695526123, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:40.504307Z", "loop": 354, "env_steps": 218111999, "loss": 0.019041234627366066, "avg_return": 0.35187676548957825, "regret": 0.5128176808357239, "entropy": 0.707706868648529, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:41.356978Z", "loop": 355, "env_steps": 218726399, "loss": 0.018533756956458092, "avg_return": 0.346007764339447, "regret": 0.5128176808357239, "entropy": 0.7080084681510925, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:42.247879Z", "loop": 356, "env_steps": 219340799, "loss": 0.019016271457076073, "avg_return": 0.3527894616127014, "regret": 0.5127897262573242, "entropy": 0.7082211375236511, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:43.100488Z", "loop": 357, "env_steps": 219955199, "loss": 0.01855338364839554, "avg_return": 0.35109710693359375, "regret": 0.5127897262573242, "entropy": 0.7081916928291321, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:43.991793Z", "loop": 358, "env_steps": 220569599, "loss": 0.01889716647565365, "avg_return": 0.34853461384773254, "regret": 0.5128248929977417, "entropy": 0.7081443071365356, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:44.843977Z", "loop": 359, "env_steps": 221183999, "loss": 0.019555943086743355, "avg_return": 0.3565887212753296, "regret": 0.5128248929977417, "entropy": 0.7081810235977173, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:45.734871Z", "loop": 360, "env_steps": 221798399, "loss": 0.017779633402824402, "avg_return": 0.3486703038215637, "regret": 0.5128125548362732, "entropy": 0.7081382870674133, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:46.587763Z", "loop": 361, "env_steps": 222412799, "loss": 0.01925971731543541, "avg_return": 0.35303473472595215, "regret": 0.5128125548362732, "entropy": 0.7082361578941345, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:47.478992Z", "loop": 362, "env_steps": 223027199, "loss": 0.019805124029517174, "avg_return": 0.3542325496673584, "regret": 0.5127491354942322, "entropy": 0.7083555459976196, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:48.331445Z", "loop": 363, "env_steps": 223641599, "loss": 0.019191469997167587, "avg_return": 0.3560856282711029, "regret": 0.5127491354942322, "entropy": 0.7081677317619324, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:49.221033Z", "loop": 364, "env_steps": 224255999, "loss": 0.016712548211216927, "avg_return": 0.34846416115760803, "regret": 0.5127143263816833, "entropy": 0.7080646753311157, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:50.073551Z", "loop": 365, "env_steps": 224870399, "loss": 0.01829991303384304, "avg_return": 0.34994223713874817, "regret": 0.5127143263816833, "entropy": 0.7079643607139587, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:50.963205Z", "loop": 366, "env_steps": 225484799, "loss": 0.018467409536242485, "avg_return": 0.35440611839294434, "regret": 0.5126748085021973, "entropy": 0.7076539993286133, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:51.816578Z", "loop": 367, "env_steps": 226099199, "loss": 0.01897554285824299, "avg_return": 0.34609493613243103, "regret": 0.5126748085021973, "entropy": 0.7073646783828735, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:52.707183Z", "loop": 368, "env_steps": 226713599, "loss": 0.0178892333060503, "avg_return": 0.35095101594924927, "regret": 0.5127798318862915, "entropy": 0.7070592641830444, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:53.565833Z", "loop": 369, "env_steps": 227327999, "loss": 0.018721697852015495, "avg_return": 0.34827905893325806, "regret": 0.5127798318862915, "entropy": 0.7066630125045776, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:54.455279Z", "loop": 370, "env_steps": 227942399, "loss": 0.018897034227848053, "avg_return": 0.3500558137893677, "regret": 0.5129871368408203, "entropy": 0.7061975598335266, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:55.307734Z", "loop": 371, "env_steps": 228556799, "loss": 0.01841769926249981, "avg_return": 0.3463306128978729, "regret": 0.5129871368408203, "entropy": 0.7055889368057251, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:56.196697Z", "loop": 372, "env_steps": 229171199, "loss": 0.01763852871954441, "avg_return": 0.3514188230037689, "regret": 0.5132150053977966, "entropy": 0.7050014138221741, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:57.049449Z", "loop": 373, "env_steps": 229785599, "loss": 0.018444228917360306, "avg_return": 0.3494913578033447, "regret": 0.5132150053977966, "entropy": 0.7046700119972229, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:57.938741Z", "loop": 374, "env_steps": 230399999, "loss": 0.018344847485423088, "avg_return": 0.35247108340263367, "regret": 0.5131200551986694, "entropy": 0.7052277326583862, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:58.792510Z", "loop": 375, "env_steps": 231014399, "loss": 0.01770043559372425, "avg_return": 0.3459669351577759, "regret": 0.5131200551986694, "entropy": 0.7056362628936768, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:28:59.684813Z", "loop": 376, "env_steps": 231628799, "loss": 0.01716468669474125, "avg_return": 0.3415253162384033, "regret": 0.5129241943359375, "entropy": 0.706011950969696, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:00.538981Z", "loop": 377, "env_steps": 232243199, "loss": 0.01889127492904663, "avg_return": 0.34669607877731323, "regret": 0.5129241943359375, "entropy": 0.7067049741744995, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:01.427871Z", "loop": 378, "env_steps": 232857599, "loss": 0.01903984695672989, "avg_return": 0.3512558937072754, "regret": 0.5127127766609192, "entropy": 0.7071824669837952, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:02.280760Z", "loop": 379, "env_steps": 233471999, "loss": 0.01827164739370346, "avg_return": 0.35654643177986145, "regret": 0.5127127766609192, "entropy": 0.7072999477386475, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:03.172429Z", "loop": 380, "env_steps": 234086399, "loss": 0.01907317340373993, "avg_return": 0.35231471061706543, "regret": 0.5126786231994629, "entropy": 0.7072863578796387, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:04.025075Z", "loop": 381, "env_steps": 234700799, "loss": 0.017390184104442596, "avg_return": 0.3472091555595398, "regret": 0.5126786231994629, "entropy": 0.7068386077880859, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:04.914957Z", "loop": 382, "env_steps": 235315199, "loss": 0.018782690167427063, "avg_return": 0.35431596636772156, "regret": 0.5128225088119507, "entropy": 0.7064108848571777, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:05.768379Z", "loop": 383, "env_steps": 235929599, "loss": 0.01810251548886299, "avg_return": 0.35115155577659607, "regret": 0.5128225088119507, "entropy": 0.7056707143783569, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:06.660269Z", "loop": 384, "env_steps": 236543999, "loss": 0.017632562667131424, "avg_return": 0.3473162055015564, "regret": 0.5130500197410583, "entropy": 0.7051792740821838, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:07.513232Z", "loop": 385, "env_steps": 237158399, "loss": 0.017603309825062752, "avg_return": 0.3419678807258606, "regret": 0.5130500197410583, "entropy": 0.7050585746765137, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:08.403919Z", "loop": 386, "env_steps": 237772799, "loss": 0.0176148172467947, "avg_return": 0.3516307771205902, "regret": 0.5130889415740967, "entropy": 0.7050102353096008, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:09.256060Z", "loop": 387, "env_steps": 238387199, "loss": 0.01851222850382328, "avg_return": 0.35153549909591675, "regret": 0.5130889415740967, "entropy": 0.7052980065345764, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:10.145149Z", "loop": 388, "env_steps": 239001599, "loss": 0.01904933713376522, "avg_return": 0.3521885871887207, "regret": 0.5129352807998657, "entropy": 0.7056909799575806, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:10.997522Z", "loop": 389, "env_steps": 239615999, "loss": 0.018446115776896477, "avg_return": 0.35344329476356506, "regret": 0.5129352807998657, "entropy": 0.7061353921890259, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:11.887383Z", "loop": 390, "env_steps": 240230399, "loss": 0.01826610416173935, "avg_return": 0.35488754510879517, "regret": 0.5127413868904114, "entropy": 0.7065556049346924, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:12.740405Z", "loop": 391, "env_steps": 240844799, "loss": 0.017408376559615135, "avg_return": 0.34166473150253296, "regret": 0.5127413868904114, "entropy": 0.7065503597259521, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:13.630806Z", "loop": 392, "env_steps": 241459199, "loss": 0.020516952499747276, "avg_return": 0.3559933304786682, "regret": 0.5127033591270447, "entropy": 0.7067023515701294, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:14.482588Z", "loop": 393, "env_steps": 242073599, "loss": 0.018865851685404778, "avg_return": 0.35955291986465454, "regret": 0.5127033591270447, "entropy": 0.7070903778076172, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:15.372431Z", "loop": 394, "env_steps": 242687999, "loss": 0.018088694661855698, "avg_return": 0.35130739212036133, "regret": 0.5126626491546631, "entropy": 0.707390308380127, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:16.226300Z", "loop": 395, "env_steps": 243302399, "loss": 0.016947893425822258, "avg_return": 0.3478650152683258, "regret": 0.5126626491546631, "entropy": 0.7074272632598877, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:17.118157Z", "loop": 396, "env_steps": 243916799, "loss": 0.018331915140151978, "avg_return": 0.3398250937461853, "regret": 0.5126609206199646, "entropy": 0.7074369192123413, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:17.970224Z", "loop": 397, "env_steps": 244531199, "loss": 0.01838541403412819, "avg_return": 0.35175183415412903, "regret": 0.5126609206199646, "entropy": 0.7074369192123413, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:18.857967Z", "loop": 398, "env_steps": 245145599, "loss": 0.019191022962331772, "avg_return": 0.35112741589546204, "regret": 0.51265949010849, "entropy": 0.7073283195495605, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:19.709978Z", "loop": 399, "env_steps": 245759999, "loss": 0.01985192857682705, "avg_return": 0.3500145971775055, "regret": 0.51265949010849, "entropy": 0.707139253616333, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:20.599443Z", "loop": 400, "env_steps": 246374399, "loss": 0.019068097695708275, "avg_return": 0.3545844554901123, "regret": 0.5127082467079163, "entropy": 0.7067136764526367, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:21.452153Z", "loop": 401, "env_steps": 246988799, "loss": 0.01691867969930172, "avg_return": 0.34921351075172424, "regret": 0.5127082467079163, "entropy": 0.7059781551361084, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:22.341587Z", "loop": 402, "env_steps": 247603199, "loss": 0.019214484840631485, "avg_return": 0.3504292964935303, "regret": 0.5130369067192078, "entropy": 0.7051138281822205, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:23.193643Z", "loop": 403, "env_steps": 248217599, "loss": 0.01969577744603157, "avg_return": 0.3528713881969452, "regret": 0.5130369067192078, "entropy": 0.7044337391853333, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:24.083435Z", "loop": 404, "env_steps": 248831999, "loss": 0.018420768901705742, "avg_return": 0.35004064440727234, "regret": 0.513208270072937, "entropy": 0.7045189738273621, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:24.935113Z", "loop": 405, "env_steps": 249446399, "loss": 0.01874898560345173, "avg_return": 0.354239284992218, "regret": 0.513208270072937, "entropy": 0.7049880027770996, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:25.826506Z", "loop": 406, "env_steps": 250060799, "loss": 0.018074074760079384, "avg_return": 0.3564465045928955, "regret": 0.512930691242218, "entropy": 0.7058449983596802, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:26.678901Z", "loop": 407, "env_steps": 250675199, "loss": 0.01876223459839821, "avg_return": 0.34591811895370483, "regret": 0.512930691242218, "entropy": 0.7064307332038879, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:27.568393Z", "loop": 408, "env_steps": 251289599, "loss": 0.019151825457811356, "avg_return": 0.3485923409461975, "regret": 0.5126717686653137, "entropy": 0.7067617774009705, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:28.420395Z", "loop": 409, "env_steps": 251903999, "loss": 0.017401350662112236, "avg_return": 0.3485584557056427, "regret": 0.5126717686653137, "entropy": 0.7069271206855774, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:29.310028Z", "loop": 410, "env_steps": 252518399, "loss": 0.01692344807088375, "avg_return": 0.34574419260025024, "regret": 0.5126864314079285, "entropy": 0.7068542242050171, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:30.162472Z", "loop": 411, "env_steps": 253132799, "loss": 0.019815538078546524, "avg_return": 0.35270991921424866, "regret": 0.5126864314079285, "entropy": 0.7065340876579285, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:31.050228Z", "loop": 412, "env_steps": 253747199, "loss": 0.016446849331259727, "avg_return": 0.3427278995513916, "regret": 0.5129019618034363, "entropy": 0.7060933709144592, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:31.902268Z", "loop": 413, "env_steps": 254361599, "loss": 0.01742006652057171, "avg_return": 0.34517788887023926, "regret": 0.5129019618034363, "entropy": 0.7058001160621643, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:32.792793Z", "loop": 414, "env_steps": 254975999, "loss": 0.017794515937566757, "avg_return": 0.3433983027935028, "regret": 0.5130219459533691, "entropy": 0.7057620286941528, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:33.645472Z", "loop": 415, "env_steps": 255590399, "loss": 0.018819084390997887, "avg_return": 0.3530289828777313, "regret": 0.5130219459533691, "entropy": 0.7059735059738159, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:34.533438Z", "loop": 416, "env_steps": 256204799, "loss": 0.01917450688779354, "avg_return": 0.3497319221496582, "regret": 0.5129076838493347, "entropy": 0.7061048150062561, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:35.384811Z", "loop": 417, "env_steps": 256819199, "loss": 0.01872859336435795, "avg_return": 0.35480210185050964, "regret": 0.5129076838493347, "entropy": 0.7061811089515686, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:36.274224Z", "loop": 418, "env_steps": 257433599, "loss": 0.018486516550183296, "avg_return": 0.35206812620162964, "regret": 0.5127711892127991, "entropy": 0.7064960598945618, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:37.126963Z", "loop": 419, "env_steps": 258047999, "loss": 0.018542487174272537, "avg_return": 0.3510917127132416, "regret": 0.5127711892127991, "entropy": 0.7066702842712402, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:38.015240Z", "loop": 420, "env_steps": 258662399, "loss": 0.018586238846182823, "avg_return": 0.3449386954307556, "regret": 0.5127048492431641, "entropy": 0.7068677544593811, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:38.867526Z", "loop": 421, "env_steps": 259276799, "loss": 0.019252754747867584, "avg_return": 0.3541848361492157, "regret": 0.5127048492431641, "entropy": 0.7068886160850525, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:39.757460Z", "loop": 422, "env_steps": 259891199, "loss": 0.016936827450990677, "avg_return": 0.35118532180786133, "regret": 0.5126802921295166, "entropy": 0.7066711783409119, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:40.611014Z", "loop": 423, "env_steps": 260505599, "loss": 0.01900111325085163, "avg_return": 0.3528546094894409, "regret": 0.5126802921295166, "entropy": 0.7066675424575806, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:41.501678Z", "loop": 424, "env_steps": 261119999, "loss": 0.01936301402747631, "avg_return": 0.3540896773338318, "regret": 0.5126890540122986, "entropy": 0.7065253257751465, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:42.354762Z", "loop": 425, "env_steps": 261734399, "loss": 0.01849447935819626, "avg_return": 0.359910786151886, "regret": 0.5126890540122986, "entropy": 0.7062926888465881, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:43.243313Z", "loop": 426, "env_steps": 262348799, "loss": 0.018875032663345337, "avg_return": 0.3459586501121521, "regret": 0.5126710534095764, "entropy": 0.7062693238258362, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:44.095115Z", "loop": 427, "env_steps": 262963199, "loss": 0.019064782187342644, "avg_return": 0.35193198919296265, "regret": 0.5126710534095764, "entropy": 0.7063567042350769, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:44.984515Z", "loop": 428, "env_steps": 263577599, "loss": 0.01821269281208515, "avg_return": 0.35961708426475525, "regret": 0.5126475095748901, "entropy": 0.7065845727920532, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:45.837702Z", "loop": 429, "env_steps": 264191999, "loss": 0.01853235810995102, "avg_return": 0.34869834780693054, "regret": 0.5126475095748901, "entropy": 0.7067552208900452, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:46.728315Z", "loop": 430, "env_steps": 264806399, "loss": 0.020353205502033234, "avg_return": 0.35897010564804077, "regret": 0.5126386880874634, "entropy": 0.707016110420227, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:47.580834Z", "loop": 431, "env_steps": 265420799, "loss": 0.018657123669981956, "avg_return": 0.3438586890697479, "regret": 0.5126386880874634, "entropy": 0.7071500420570374, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:48.471981Z", "loop": 432, "env_steps": 266035199, "loss": 0.018447287380695343, "avg_return": 0.35185134410858154, "regret": 0.5126568675041199, "entropy": 0.707273542881012, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:49.325512Z", "loop": 433, "env_steps": 266649599, "loss": 0.01790594309568405, "avg_return": 0.3481752872467041, "regret": 0.5126568675041199, "entropy": 0.7073426842689514, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:50.217460Z", "loop": 434, "env_steps": 267263999, "loss": 0.01752580888569355, "avg_return": 0.3527163863182068, "regret": 0.5127108693122864, "entropy": 0.7074577808380127, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:51.069567Z", "loop": 435, "env_steps": 267878399, "loss": 0.01771499589085579, "avg_return": 0.3469332754611969, "regret": 0.5127108693122864, "entropy": 0.7074732780456543, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:51.961474Z", "loop": 436, "env_steps": 268492799, "loss": 0.018701346591114998, "avg_return": 0.34879517555236816, "regret": 0.5127233862876892, "entropy": 0.7076582908630371, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:52.814840Z", "loop": 437, "env_steps": 269107199, "loss": 0.01862032525241375, "avg_return": 0.3453701436519623, "regret": 0.5127233862876892, "entropy": 0.7078487873077393, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:53.705162Z", "loop": 438, "env_steps": 269721599, "loss": 0.019015900790691376, "avg_return": 0.3563801944255829, "regret": 0.5126805305480957, "entropy": 0.708001971244812, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:54.558443Z", "loop": 439, "env_steps": 270335999, "loss": 0.019470075145363808, "avg_return": 0.35645753145217896, "regret": 0.5126805305480957, "entropy": 0.7078042030334473, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:55.447696Z", "loop": 440, "env_steps": 270950399, "loss": 0.018801970407366753, "avg_return": 0.35459402203559875, "regret": 0.5126807689666748, "entropy": 0.7077762484550476, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:56.300142Z", "loop": 441, "env_steps": 271564799, "loss": 0.018531374633312225, "avg_return": 0.34823960065841675, "regret": 0.5126807689666748, "entropy": 0.7077162861824036, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:57.191112Z", "loop": 442, "env_steps": 272179199, "loss": 0.01895185373723507, "avg_return": 0.3510659337043762, "regret": 0.5127202868461609, "entropy": 0.7076412439346313, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:58.046387Z", "loop": 443, "env_steps": 272793599, "loss": 0.019920768216252327, "avg_return": 0.35330164432525635, "regret": 0.5127202868461609, "entropy": 0.7074191570281982, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:58.936151Z", "loop": 444, "env_steps": 273407999, "loss": 0.01835109107196331, "avg_return": 0.35297122597694397, "regret": 0.512799859046936, "entropy": 0.7070830464363098, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:29:59.789833Z", "loop": 445, "env_steps": 274022399, "loss": 0.018588483333587646, "avg_return": 0.3505983054637909, "regret": 0.512799859046936, "entropy": 0.7068439722061157, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:00.679662Z", "loop": 446, "env_steps": 274636799, "loss": 0.018285682424902916, "avg_return": 0.34881603717803955, "regret": 0.5128772258758545, "entropy": 0.7067313194274902, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:01.533990Z", "loop": 447, "env_steps": 275251199, "loss": 0.019066883251070976, "avg_return": 0.35172146558761597, "regret": 0.5128772258758545, "entropy": 0.7065483331680298, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:02.428313Z", "loop": 448, "env_steps": 275865599, "loss": 0.01864129863679409, "avg_return": 0.348743200302124, "regret": 0.5128258466720581, "entropy": 0.7066625356674194, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:03.283646Z", "loop": 449, "env_steps": 276479999, "loss": 0.017571182921528816, "avg_return": 0.35077738761901855, "regret": 0.5128258466720581, "entropy": 0.7068001627922058, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:04.173074Z", "loop": 450, "env_steps": 277094399, "loss": 0.017818478867411613, "avg_return": 0.35327595472335815, "regret": 0.5126813650131226, "entropy": 0.7068790793418884, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:05.025263Z", "loop": 451, "env_steps": 277708799, "loss": 0.018403541296720505, "avg_return": 0.35090014338493347, "regret": 0.5126813650131226, "entropy": 0.7067130208015442, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:05.914959Z", "loop": 452, "env_steps": 278323199, "loss": 0.017903873696923256, "avg_return": 0.3503233790397644, "regret": 0.5126195549964905, "entropy": 0.7066066265106201, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:06.767086Z", "loop": 453, "env_steps": 278937599, "loss": 0.01724611409008503, "avg_return": 0.3508773446083069, "regret": 0.5126195549964905, "entropy": 0.7064929008483887, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:07.657695Z", "loop": 454, "env_steps": 279551999, "loss": 0.01787872612476349, "avg_return": 0.3526360094547272, "regret": 0.512642502784729, "entropy": 0.706268846988678, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:08.510384Z", "loop": 455, "env_steps": 280166399, "loss": 0.017854776233434677, "avg_return": 0.3492324948310852, "regret": 0.512642502784729, "entropy": 0.7061851620674133, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:09.401224Z", "loop": 456, "env_steps": 280780799, "loss": 0.018863409757614136, "avg_return": 0.3530484139919281, "regret": 0.5126692056655884, "entropy": 0.7062569260597229, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:10.254395Z", "loop": 457, "env_steps": 281395199, "loss": 0.019100872799754143, "avg_return": 0.35788342356681824, "regret": 0.5126692056655884, "entropy": 0.7064269185066223, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:11.144648Z", "loop": 458, "env_steps": 282009599, "loss": 0.017821598798036575, "avg_return": 0.35377249121665955, "regret": 0.5126297473907471, "entropy": 0.7070322036743164, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:11.997623Z", "loop": 459, "env_steps": 282623999, "loss": 0.017976513132452965, "avg_return": 0.35496458411216736, "regret": 0.5126297473907471, "entropy": 0.7072908282279968, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:12.888133Z", "loop": 460, "env_steps": 283238399, "loss": 0.018064171075820923, "avg_return": 0.3444446921348572, "regret": 0.5126190185546875, "entropy": 0.7076942324638367, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:13.742299Z", "loop": 461, "env_steps": 283852799, "loss": 0.01830351911485195, "avg_return": 0.35992467403411865, "regret": 0.5126190185546875, "entropy": 0.7079188823699951, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:14.631370Z", "loop": 462, "env_steps": 284467199, "loss": 0.018440186977386475, "avg_return": 0.3486473858356476, "regret": 0.5126335024833679, "entropy": 0.7081379294395447, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:15.484268Z", "loop": 463, "env_steps": 285081599, "loss": 0.017565831542015076, "avg_return": 0.3454337418079376, "regret": 0.5126335024833679, "entropy": 0.7081999778747559, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:16.374159Z", "loop": 464, "env_steps": 285695999, "loss": 0.018832040950655937, "avg_return": 0.34874236583709717, "regret": 0.512648344039917, "entropy": 0.7083559036254883, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:17.227047Z", "loop": 465, "env_steps": 286310399, "loss": 0.017490727826952934, "avg_return": 0.34853067994117737, "regret": 0.512648344039917, "entropy": 0.7083595395088196, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:18.116825Z", "loop": 466, "env_steps": 286924799, "loss": 0.019149592146277428, "avg_return": 0.34929022192955017, "regret": 0.5126782655715942, "entropy": 0.7084711194038391, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:18.970075Z", "loop": 467, "env_steps": 287539199, "loss": 0.017336271703243256, "avg_return": 0.34679409861564636, "regret": 0.5126782655715942, "entropy": 0.7086083889007568, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:19.861349Z", "loop": 468, "env_steps": 288153599, "loss": 0.018504520878195763, "avg_return": 0.3516867756843567, "regret": 0.5126633048057556, "entropy": 0.7087243795394897, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:20.714242Z", "loop": 469, "env_steps": 288767999, "loss": 0.018414074555039406, "avg_return": 0.35221990942955017, "regret": 0.5126633048057556, "entropy": 0.7090715169906616, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:21.605905Z", "loop": 470, "env_steps": 289382399, "loss": 0.018367616459727287, "avg_return": 0.3509135842323303, "regret": 0.5126552581787109, "entropy": 0.7092264294624329, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:22.459277Z", "loop": 471, "env_steps": 289996799, "loss": 0.01755981706082821, "avg_return": 0.35253363847732544, "regret": 0.5126552581787109, "entropy": 0.7093204259872437, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:23.350263Z", "loop": 472, "env_steps": 290611199, "loss": 0.018447065725922585, "avg_return": 0.3508886396884918, "regret": 0.5126684904098511, "entropy": 0.7094302177429199, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:24.202799Z", "loop": 473, "env_steps": 291225599, "loss": 0.01793586276471615, "avg_return": 0.3521818220615387, "regret": 0.5126684904098511, "entropy": 0.7097488641738892, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:25.091429Z", "loop": 474, "env_steps": 291839999, "loss": 0.018969973549246788, "avg_return": 0.3549535870552063, "regret": 0.5126591324806213, "entropy": 0.7099464535713196, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:25.943661Z", "loop": 475, "env_steps": 292454399, "loss": 0.018272152170538902, "avg_return": 0.348611056804657, "regret": 0.5126591324806213, "entropy": 0.7101262807846069, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:26.834731Z", "loop": 476, "env_steps": 293068799, "loss": 0.018535267561674118, "avg_return": 0.34888210892677307, "regret": 0.5127079486846924, "entropy": 0.71002596616745, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:27.686943Z", "loop": 477, "env_steps": 293683199, "loss": 0.01794494315981865, "avg_return": 0.34508347511291504, "regret": 0.5127079486846924, "entropy": 0.7098585963249207, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:28.580208Z", "loop": 478, "env_steps": 294297599, "loss": 0.018238333985209465, "avg_return": 0.35090959072113037, "regret": 0.5128442049026489, "entropy": 0.7093977332115173, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:29.432137Z", "loop": 479, "env_steps": 294911999, "loss": 0.017999723553657532, "avg_return": 0.34972482919692993, "regret": 0.5128442049026489, "entropy": 0.7090843319892883, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:30.321029Z", "loop": 480, "env_steps": 295526399, "loss": 0.020079025998711586, "avg_return": 0.3506256341934204, "regret": 0.512872576713562, "entropy": 0.7090662717819214, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:31.173536Z", "loop": 481, "env_steps": 296140799, "loss": 0.01864614151418209, "avg_return": 0.3499601185321808, "regret": 0.512872576713562, "entropy": 0.7094380259513855, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:32.063898Z", "loop": 482, "env_steps": 296755199, "loss": 0.01932806894183159, "avg_return": 0.34804201126098633, "regret": 0.5126765966415405, "entropy": 0.709925651550293, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:32.916896Z", "loop": 483, "env_steps": 297369599, "loss": 0.0179909598082304, "avg_return": 0.34862497448921204, "regret": 0.5126765966415405, "entropy": 0.7099934220314026, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:33.806488Z", "loop": 484, "env_steps": 297983999, "loss": 0.018390530720353127, "avg_return": 0.3603723645210266, "regret": 0.5126327872276306, "entropy": 0.7100853323936462, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:34.658574Z", "loop": 485, "env_steps": 298598399, "loss": 0.018032636493444443, "avg_return": 0.3501474857330322, "regret": 0.5126327872276306, "entropy": 0.7097042202949524, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:35.549166Z", "loop": 486, "env_steps": 299212799, "loss": 0.017445607110857964, "avg_return": 0.34656527638435364, "regret": 0.5126614570617676, "entropy": 0.7093097567558289, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:36.402407Z", "loop": 487, "env_steps": 299827199, "loss": 0.019446320831775665, "avg_return": 0.3532877564430237, "regret": 0.5126614570617676, "entropy": 0.7088910341262817, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:37.292207Z", "loop": 488, "env_steps": 300441599, "loss": 0.0182526633143425, "avg_return": 0.3528625965118408, "regret": 0.5126286745071411, "entropy": 0.7082093954086304, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:38.144661Z", "loop": 489, "env_steps": 301055999, "loss": 0.01868419162929058, "avg_return": 0.3519919514656067, "regret": 0.5126286745071411, "entropy": 0.7075770497322083, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:39.034889Z", "loop": 490, "env_steps": 301670399, "loss": 0.018320491537451744, "avg_return": 0.34939080476760864, "regret": 0.5126092433929443, "entropy": 0.7070576548576355, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:39.888985Z", "loop": 491, "env_steps": 302284799, "loss": 0.01861397922039032, "avg_return": 0.35179537534713745, "regret": 0.5126092433929443, "entropy": 0.7066941857337952, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:40.778974Z", "loop": 492, "env_steps": 302899199, "loss": 0.018446968868374825, "avg_return": 0.34695684909820557, "regret": 0.5126002430915833, "entropy": 0.7064934372901917, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:41.631964Z", "loop": 493, "env_steps": 303513599, "loss": 0.018513627350330353, "avg_return": 0.35036706924438477, "regret": 0.5126002430915833, "entropy": 0.7062602043151855, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:42.522917Z", "loop": 494, "env_steps": 304127999, "loss": 0.01599186472594738, "avg_return": 0.33748796582221985, "regret": 0.5125910043716431, "entropy": 0.7059834599494934, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:43.375945Z", "loop": 495, "env_steps": 304742399, "loss": 0.018596751615405083, "avg_return": 0.34929367899894714, "regret": 0.5125910043716431, "entropy": 0.7056273221969604, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:44.265356Z", "loop": 496, "env_steps": 305356799, "loss": 0.01917995885014534, "avg_return": 0.35076215863227844, "regret": 0.5125856399536133, "entropy": 0.7052838802337646, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:45.118545Z", "loop": 497, "env_steps": 305971199, "loss": 0.017584269866347313, "avg_return": 0.34744104743003845, "regret": 0.5125856399536133, "entropy": 0.7050731778144836, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:46.008478Z", "loop": 498, "env_steps": 306585599, "loss": 0.01894734986126423, "avg_return": 0.35204365849494934, "regret": 0.5126051902770996, "entropy": 0.7048338651657104, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:46.862279Z", "loop": 499, "env_steps": 307199999, "loss": 0.01840927079319954, "avg_return": 0.3534334897994995, "regret": 0.5126051902770996, "entropy": 0.7045645713806152, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:47.752033Z", "loop": 500, "env_steps": 307814399, "loss": 0.01768948696553707, "avg_return": 0.3517141342163086, "regret": 0.5125819444656372, "entropy": 0.7046917080879211, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:48.604604Z", "loop": 501, "env_steps": 308428799, "loss": 0.018646446987986565, "avg_return": 0.35305115580558777, "regret": 0.5125819444656372, "entropy": 0.704727828502655, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:49.457723Z", "loop": 502, "env_steps": 309043199, "loss": 0.01760927028954029, "avg_return": 0.345912367105484, "regret": 0.5125819444656372, "entropy": 0.7046079635620117, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:50.310744Z", "loop": 503, "env_steps": 309657599, "loss": 0.017697645351290703, "avg_return": 0.3496890962123871, "regret": 0.5125819444656372, "entropy": 0.7042758464813232, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:51.162917Z", "loop": 504, "env_steps": 310271999, "loss": 0.01828104443848133, "avg_return": 0.3485323190689087, "regret": 0.5125819444656372, "entropy": 0.7040008902549744, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:52.053395Z", "loop": 505, "env_steps": 310886399, "loss": 0.018194537609815598, "avg_return": 0.35074561834335327, "regret": 0.5126175880432129, "entropy": 0.703709065914154, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:52.906011Z", "loop": 506, "env_steps": 311500799, "loss": 0.01720617339015007, "avg_return": 0.3454933166503906, "regret": 0.5126175880432129, "entropy": 0.7034635543823242, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:53.758652Z", "loop": 507, "env_steps": 312115199, "loss": 0.01821027882397175, "avg_return": 0.3579851984977722, "regret": 0.5126175880432129, "entropy": 0.703363835811615, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:54.611735Z", "loop": 508, "env_steps": 312729599, "loss": 0.016977986320853233, "avg_return": 0.34871119260787964, "regret": 0.5126175880432129, "entropy": 0.7035428881645203, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:55.465977Z", "loop": 509, "env_steps": 313343999, "loss": 0.018769733607769012, "avg_return": 0.34623923897743225, "regret": 0.5126175880432129, "entropy": 0.7035024166107178, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:56.357188Z", "loop": 510, "env_steps": 313958399, "loss": 0.01722952350974083, "avg_return": 0.3469493091106415, "regret": 0.5126013159751892, "entropy": 0.7037540674209595, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:57.210088Z", "loop": 511, "env_steps": 314572799, "loss": 0.019226642325520515, "avg_return": 0.3566069006919861, "regret": 0.5126013159751892, "entropy": 0.7040863633155823, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:58.063253Z", "loop": 512, "env_steps": 315187199, "loss": 0.018697822466492653, "avg_return": 0.3537737727165222, "regret": 0.5126013159751892, "entropy": 0.7042055130004883, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:58.916100Z", "loop": 513, "env_steps": 315801599, "loss": 0.017745191231369972, "avg_return": 0.3451133966445923, "regret": 0.5126013159751892, "entropy": 0.7042325735092163, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:30:59.769180Z", "loop": 514, "env_steps": 316415999, "loss": 0.01808617077767849, "avg_return": 0.35317161679267883, "regret": 0.5126013159751892, "entropy": 0.7042438983917236, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:00.657244Z", "loop": 515, "env_steps": 317030399, "loss": 0.01792152412235737, "avg_return": 0.3497197926044464, "regret": 0.5126126408576965, "entropy": 0.7043352127075195, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:01.508629Z", "loop": 516, "env_steps": 317644799, "loss": 0.019105831161141396, "avg_return": 0.35380980372428894, "regret": 0.5126126408576965, "entropy": 0.7042719721794128, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:02.360010Z", "loop": 517, "env_steps": 318259199, "loss": 0.018079282715916634, "avg_return": 0.3505353331565857, "regret": 0.5126126408576965, "entropy": 0.7043769359588623, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:03.213239Z", "loop": 518, "env_steps": 318873599, "loss": 0.018818145617842674, "avg_return": 0.3535306453704834, "regret": 0.5126126408576965, "entropy": 0.7042505741119385, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:04.065530Z", "loop": 519, "env_steps": 319487999, "loss": 0.017970552667975426, "avg_return": 0.3488805592060089, "regret": 0.5126126408576965, "entropy": 0.7041966915130615, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:04.954566Z", "loop": 520, "env_steps": 320102399, "loss": 0.017476435750722885, "avg_return": 0.3495722711086273, "regret": 0.5125692486763, "entropy": 0.7043008804321289, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:05.807885Z", "loop": 521, "env_steps": 320716799, "loss": 0.018452467396855354, "avg_return": 0.3439847528934479, "regret": 0.5125692486763, "entropy": 0.704211413860321, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:06.661477Z", "loop": 522, "env_steps": 321331199, "loss": 0.01756451278924942, "avg_return": 0.35097798705101013, "regret": 0.5125692486763, "entropy": 0.7040572762489319, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:07.513905Z", "loop": 523, "env_steps": 321945599, "loss": 0.018552804365754128, "avg_return": 0.3509056568145752, "regret": 0.5125692486763, "entropy": 0.7040033340454102, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:08.367040Z", "loop": 524, "env_steps": 322559999, "loss": 0.01912405900657177, "avg_return": 0.36057737469673157, "regret": 0.5125692486763, "entropy": 0.7039597034454346, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:09.254843Z", "loop": 525, "env_steps": 323174399, "loss": 0.017367541790008545, "avg_return": 0.3482758700847626, "regret": 0.5125594139099121, "entropy": 0.7038282155990601, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:10.108571Z", "loop": 526, "env_steps": 323788799, "loss": 0.019748542457818985, "avg_return": 0.3564129173755646, "regret": 0.5125594139099121, "entropy": 0.7038015127182007, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:10.960797Z", "loop": 527, "env_steps": 324403199, "loss": 0.018546728417277336, "avg_return": 0.35647323727607727, "regret": 0.5125594139099121, "entropy": 0.7036449909210205, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:11.812899Z", "loop": 528, "env_steps": 325017599, "loss": 0.018181324005126953, "avg_return": 0.35023385286331177, "regret": 0.5125594139099121, "entropy": 0.7034599781036377, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:12.665614Z", "loop": 529, "env_steps": 325631999, "loss": 0.01855621300637722, "avg_return": 0.34788185358047485, "regret": 0.5125594139099121, "entropy": 0.7032387256622314, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:13.556162Z", "loop": 530, "env_steps": 326246399, "loss": 0.01860262267291546, "avg_return": 0.35329583287239075, "regret": 0.5125851631164551, "entropy": 0.7033650279045105, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:14.408446Z", "loop": 531, "env_steps": 326860799, "loss": 0.017486486583948135, "avg_return": 0.35381942987442017, "regret": 0.5125851631164551, "entropy": 0.703520655632019, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:15.261487Z", "loop": 532, "env_steps": 327475199, "loss": 0.01974235102534294, "avg_return": 0.35809722542762756, "regret": 0.5125851631164551, "entropy": 0.7036784291267395, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:16.114123Z", "loop": 533, "env_steps": 328089599, "loss": 0.01764542981982231, "avg_return": 0.34940868616104126, "regret": 0.5125851631164551, "entropy": 0.7034762501716614, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:16.967214Z", "loop": 534, "env_steps": 328703999, "loss": 0.01888035051524639, "avg_return": 0.3576383590698242, "regret": 0.5125851631164551, "entropy": 0.7031354904174805, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:17.857781Z", "loop": 535, "env_steps": 329318399, "loss": 0.02007048949599266, "avg_return": 0.3526793122291565, "regret": 0.5127565264701843, "entropy": 0.7026777267456055, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:18.710811Z", "loop": 536, "env_steps": 329932799, "loss": 0.018866049125790596, "avg_return": 0.34958207607269287, "regret": 0.5127565264701843, "entropy": 0.702143132686615, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:19.563080Z", "loop": 537, "env_steps": 330547199, "loss": 0.018084215000271797, "avg_return": 0.3511715829372406, "regret": 0.5127565264701843, "entropy": 0.7018125057220459, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:20.415544Z", "loop": 538, "env_steps": 331161599, "loss": 0.01716039516031742, "avg_return": 0.3438175916671753, "regret": 0.5127565264701843, "entropy": 0.7018331289291382, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:21.268728Z", "loop": 539, "env_steps": 331775999, "loss": 0.018341001123189926, "avg_return": 0.3481980860233307, "regret": 0.5127565264701843, "entropy": 0.701887309551239, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:22.160326Z", "loop": 540, "env_steps": 332390399, "loss": 0.01770947128534317, "avg_return": 0.3430126905441284, "regret": 0.512845516204834, "entropy": 0.7022810578346252, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:23.012766Z", "loop": 541, "env_steps": 333004799, "loss": 0.01814877614378929, "avg_return": 0.34648463129997253, "regret": 0.512845516204834, "entropy": 0.7026979923248291, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:23.865660Z", "loop": 542, "env_steps": 333619199, "loss": 0.017290327697992325, "avg_return": 0.3483671545982361, "regret": 0.512845516204834, "entropy": 0.7027883529663086, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:24.718138Z", "loop": 543, "env_steps": 334233599, "loss": 0.018040135502815247, "avg_return": 0.3516729772090912, "regret": 0.512845516204834, "entropy": 0.7029063701629639, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:25.570892Z", "loop": 544, "env_steps": 334847999, "loss": 0.017534811049699783, "avg_return": 0.34853658080101013, "regret": 0.512845516204834, "entropy": 0.7028713822364807, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:26.460740Z", "loop": 545, "env_steps": 335462399, "loss": 0.01727159507572651, "avg_return": 0.34888359904289246, "regret": 0.5125856995582581, "entropy": 0.7027926445007324, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:27.314038Z", "loop": 546, "env_steps": 336076799, "loss": 0.01761777512729168, "avg_return": 0.35878002643585205, "regret": 0.5125856995582581, "entropy": 0.702868640422821, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:28.166433Z", "loop": 547, "env_steps": 336691199, "loss": 0.018676241859793663, "avg_return": 0.3549649119377136, "regret": 0.5125856995582581, "entropy": 0.7029471397399902, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:29.018310Z", "loop": 548, "env_steps": 337305599, "loss": 0.017245855182409286, "avg_return": 0.3482707738876343, "regret": 0.5125856995582581, "entropy": 0.7027503252029419, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:29.870144Z", "loop": 549, "env_steps": 337919999, "loss": 0.01767064817249775, "avg_return": 0.3505416512489319, "regret": 0.5125856995582581, "entropy": 0.7028614282608032, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:30.761774Z", "loop": 550, "env_steps": 338534399, "loss": 0.017539596185088158, "avg_return": 0.34750041365623474, "regret": 0.5127305388450623, "entropy": 0.7029284238815308, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:31.615620Z", "loop": 551, "env_steps": 339148799, "loss": 0.01819685846567154, "avg_return": 0.3470161557197571, "regret": 0.5127305388450623, "entropy": 0.7031942009925842, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:32.469192Z", "loop": 552, "env_steps": 339763199, "loss": 0.017380964010953903, "avg_return": 0.3479452431201935, "regret": 0.5127305388450623, "entropy": 0.7033559679985046, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:33.321890Z", "loop": 553, "env_steps": 340377599, "loss": 0.017782293260097504, "avg_return": 0.3472617566585541, "regret": 0.5127305388450623, "entropy": 0.7032007575035095, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:34.173704Z", "loop": 554, "env_steps": 340991999, "loss": 0.018345413729548454, "avg_return": 0.3453744947910309, "regret": 0.5127305388450623, "entropy": 0.7030016779899597, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:35.063923Z", "loop": 555, "env_steps": 341606399, "loss": 0.016668666154146194, "avg_return": 0.34965914487838745, "regret": 0.5126241445541382, "entropy": 0.7031131982803345, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:35.916390Z", "loop": 556, "env_steps": 342220799, "loss": 0.017189210280776024, "avg_return": 0.35168784856796265, "regret": 0.5126241445541382, "entropy": 0.7032164335250854, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:36.767594Z", "loop": 557, "env_steps": 342835199, "loss": 0.018575113266706467, "avg_return": 0.351938396692276, "regret": 0.5126241445541382, "entropy": 0.7032769322395325, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:37.618875Z", "loop": 558, "env_steps": 343449599, "loss": 0.017833931371569633, "avg_return": 0.3548174202442169, "regret": 0.5126241445541382, "entropy": 0.7032837271690369, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:38.471745Z", "loop": 559, "env_steps": 344063999, "loss": 0.018283704295754433, "avg_return": 0.3568178415298462, "regret": 0.5126241445541382, "entropy": 0.703303873538971, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:39.362165Z", "loop": 560, "env_steps": 344678399, "loss": 0.01842360384762287, "avg_return": 0.34734705090522766, "regret": 0.5125124454498291, "entropy": 0.7033677697181702, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:40.214810Z", "loop": 561, "env_steps": 345292799, "loss": 0.018066031858325005, "avg_return": 0.3464968800544739, "regret": 0.5125124454498291, "entropy": 0.7034581899642944, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:41.067383Z", "loop": 562, "env_steps": 345907199, "loss": 0.018351664766669273, "avg_return": 0.3482171893119812, "regret": 0.5125124454498291, "entropy": 0.703607439994812, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:41.919252Z", "loop": 563, "env_steps": 346521599, "loss": 0.01773856021463871, "avg_return": 0.3495471775531769, "regret": 0.5125124454498291, "entropy": 0.7036312222480774, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:42.771492Z", "loop": 564, "env_steps": 347135999, "loss": 0.019567685201764107, "avg_return": 0.3518182039260864, "regret": 0.5125124454498291, "entropy": 0.7037214040756226, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:43.662019Z", "loop": 565, "env_steps": 347750399, "loss": 0.01802089624106884, "avg_return": 0.3539069592952728, "regret": 0.5125352144241333, "entropy": 0.7037802338600159, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:44.513444Z", "loop": 566, "env_steps": 348364799, "loss": 0.01821998693048954, "avg_return": 0.34903454780578613, "regret": 0.5125352144241333, "entropy": 0.7037655115127563, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:45.366098Z", "loop": 567, "env_steps": 348979199, "loss": 0.017753688618540764, "avg_return": 0.34810540080070496, "regret": 0.5125352144241333, "entropy": 0.7039029598236084, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:46.218596Z", "loop": 568, "env_steps": 349593599, "loss": 0.018731437623500824, "avg_return": 0.35250502824783325, "regret": 0.5125352144241333, "entropy": 0.7042549252510071, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:47.071519Z", "loop": 569, "env_steps": 350207999, "loss": 0.01902846246957779, "avg_return": 0.3486423194408417, "regret": 0.5125352144241333, "entropy": 0.7046164274215698, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:47.960108Z", "loop": 570, "env_steps": 350822399, "loss": 0.019528783857822418, "avg_return": 0.35315099358558655, "regret": 0.512680172920227, "entropy": 0.7046754956245422, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:48.812188Z", "loop": 571, "env_steps": 351436799, "loss": 0.01795567385852337, "avg_return": 0.34849512577056885, "regret": 0.512680172920227, "entropy": 0.7049446702003479, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:49.664082Z", "loop": 572, "env_steps": 352051199, "loss": 0.01885327883064747, "avg_return": 0.3535443842411041, "regret": 0.512680172920227, "entropy": 0.7052466869354248, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:50.517057Z", "loop": 573, "env_steps": 352665599, "loss": 0.017117979004979134, "avg_return": 0.34957829117774963, "regret": 0.512680172920227, "entropy": 0.7054066061973572, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:51.369358Z", "loop": 574, "env_steps": 353279999, "loss": 0.016916753724217415, "avg_return": 0.3509501814842224, "regret": 0.512680172920227, "entropy": 0.7054405808448792, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:52.261386Z", "loop": 575, "env_steps": 353894399, "loss": 0.01803738810122013, "avg_return": 0.35423070192337036, "regret": 0.5125138163566589, "entropy": 0.7051971554756165, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:53.114326Z", "loop": 576, "env_steps": 354508799, "loss": 0.018309984356164932, "avg_return": 0.34822550415992737, "regret": 0.5125138163566589, "entropy": 0.7047441601753235, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:53.967488Z", "loop": 577, "env_steps": 355123199, "loss": 0.019063839688897133, "avg_return": 0.3463131785392761, "regret": 0.5125138163566589, "entropy": 0.7039828896522522, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:54.820148Z", "loop": 578, "env_steps": 355737599, "loss": 0.01861410029232502, "avg_return": 0.3542117774486542, "regret": 0.5125138163566589, "entropy": 0.703589141368866, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:55.673269Z", "loop": 579, "env_steps": 356351999, "loss": 0.01805409975349903, "avg_return": 0.3544217050075531, "regret": 0.5125138163566589, "entropy": 0.7030137181282043, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:56.563215Z", "loop": 580, "env_steps": 356966399, "loss": 0.017664192244410515, "avg_return": 0.3545263707637787, "regret": 0.51307213306427, "entropy": 0.7025362849235535, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:57.415852Z", "loop": 581, "env_steps": 357580799, "loss": 0.018758011981844902, "avg_return": 0.3504517376422882, "regret": 0.51307213306427, "entropy": 0.7026227116584778, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:58.268253Z", "loop": 582, "env_steps": 358195199, "loss": 0.01792827807366848, "avg_return": 0.34363463521003723, "regret": 0.51307213306427, "entropy": 0.7029702663421631, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:59.120691Z", "loop": 583, "env_steps": 358809599, "loss": 0.01895807310938835, "avg_return": 0.34927424788475037, "regret": 0.51307213306427, "entropy": 0.7037644982337952, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:31:59.972803Z", "loop": 584, "env_steps": 359423999, "loss": 0.018645716831088066, "avg_return": 0.35617780685424805, "regret": 0.51307213306427, "entropy": 0.7046254277229309, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:00.864321Z", "loop": 585, "env_steps": 360038399, "loss": 0.017837179824709892, "avg_return": 0.3459550440311432, "regret": 0.5125150680541992, "entropy": 0.7052314877510071, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:01.717364Z", "loop": 586, "env_steps": 360652799, "loss": 0.01689358614385128, "avg_return": 0.34858134388923645, "regret": 0.5125150680541992, "entropy": 0.7052772641181946, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:02.571062Z", "loop": 587, "env_steps": 361267199, "loss": 0.018181173130869865, "avg_return": 0.35027623176574707, "regret": 0.5125150680541992, "entropy": 0.705405592918396, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:03.423953Z", "loop": 588, "env_steps": 361881599, "loss": 0.019097452983260155, "avg_return": 0.3588017225265503, "regret": 0.5125150680541992, "entropy": 0.7055723071098328, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:04.276037Z", "loop": 589, "env_steps": 362495999, "loss": 0.01856566034257412, "avg_return": 0.3492693305015564, "regret": 0.5125150680541992, "entropy": 0.7059341669082642, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:05.166508Z", "loop": 590, "env_steps": 363110399, "loss": 0.01818639598786831, "avg_return": 0.3496807813644409, "regret": 0.512519121170044, "entropy": 0.7059158086776733, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:06.019574Z", "loop": 591, "env_steps": 363724799, "loss": 0.019468363374471664, "avg_return": 0.3600427806377411, "regret": 0.512519121170044, "entropy": 0.7060145139694214, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:06.872794Z", "loop": 592, "env_steps": 364339199, "loss": 0.018736885860562325, "avg_return": 0.35915157198905945, "regret": 0.512519121170044, "entropy": 0.7062658071517944, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:07.724733Z", "loop": 593, "env_steps": 364953599, "loss": 0.01892956905066967, "avg_return": 0.35592129826545715, "regret": 0.512519121170044, "entropy": 0.7064945697784424, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:08.576923Z", "loop": 594, "env_steps": 365567999, "loss": 0.01863800175487995, "avg_return": 0.35136958956718445, "regret": 0.512519121170044, "entropy": 0.7068724632263184, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:09.470139Z", "loop": 595, "env_steps": 366182399, "loss": 0.018180998042225838, "avg_return": 0.3522392511367798, "regret": 0.5125568509101868, "entropy": 0.707208514213562, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:10.323323Z", "loop": 596, "env_steps": 366796799, "loss": 0.01912214420735836, "avg_return": 0.3453507721424103, "regret": 0.5125568509101868, "entropy": 0.7075014114379883, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:11.175544Z", "loop": 597, "env_steps": 367411199, "loss": 0.017802607268095016, "avg_return": 0.3423779308795929, "regret": 0.5125568509101868, "entropy": 0.7078778743743896, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:12.027692Z", "loop": 598, "env_steps": 368025599, "loss": 0.01745072565972805, "avg_return": 0.3479527235031128, "regret": 0.5125568509101868, "entropy": 0.7081625461578369, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:12.879932Z", "loop": 599, "env_steps": 368639999, "loss": 0.017968272790312767, "avg_return": 0.34713074564933777, "regret": 0.5125568509101868, "entropy": 0.7082902789115906, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:13.771162Z", "loop": 600, "env_steps": 369254399, "loss": 0.017794497311115265, "avg_return": 0.35166096687316895, "regret": 0.5125216245651245, "entropy": 0.7081938982009888, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:14.623391Z", "loop": 601, "env_steps": 369868799, "loss": 0.018185609951615334, "avg_return": 0.3446502387523651, "regret": 0.5125216245651245, "entropy": 0.7078753113746643, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:15.475929Z", "loop": 602, "env_steps": 370483199, "loss": 0.018559781834483147, "avg_return": 0.35743725299835205, "regret": 0.5125216245651245, "entropy": 0.707239031791687, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:16.328017Z", "loop": 603, "env_steps": 371097599, "loss": 0.018913883715867996, "avg_return": 0.35336750745773315, "regret": 0.5125216245651245, "entropy": 0.7066828608512878, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:17.180301Z", "loop": 604, "env_steps": 371711999, "loss": 0.019110342487692833, "avg_return": 0.352781742811203, "regret": 0.5125216245651245, "entropy": 0.7063686847686768, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:18.070999Z", "loop": 605, "env_steps": 372326399, "loss": 0.017599022015929222, "avg_return": 0.3502242863178253, "regret": 0.5130741596221924, "entropy": 0.7062346339225769, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:18.923414Z", "loop": 606, "env_steps": 372940799, "loss": 0.017182888463139534, "avg_return": 0.3518596887588501, "regret": 0.5130741596221924, "entropy": 0.7062027454376221, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:19.777073Z", "loop": 607, "env_steps": 373555199, "loss": 0.020236166194081306, "avg_return": 0.35049229860305786, "regret": 0.5130741596221924, "entropy": 0.7064312100410461, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:20.629603Z", "loop": 608, "env_steps": 374169599, "loss": 0.018215766176581383, "avg_return": 0.34472131729125977, "regret": 0.5130741596221924, "entropy": 0.7064346671104431, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:21.482541Z", "loop": 609, "env_steps": 374783999, "loss": 0.018471071496605873, "avg_return": 0.3543490171432495, "regret": 0.5130741596221924, "entropy": 0.7071987390518188, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:22.373645Z", "loop": 610, "env_steps": 375398399, "loss": 0.017501747235655785, "avg_return": 0.34893307089805603, "regret": 0.5130165815353394, "entropy": 0.707870364189148, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:23.227719Z", "loop": 611, "env_steps": 376012799, "loss": 0.017654916271567345, "avg_return": 0.3507680892944336, "regret": 0.5130165815353394, "entropy": 0.7086858749389648, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:24.079678Z", "loop": 612, "env_steps": 376627199, "loss": 0.01890583522617817, "avg_return": 0.3545064330101013, "regret": 0.5130165815353394, "entropy": 0.7096505165100098, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:24.931411Z", "loop": 613, "env_steps": 377241599, "loss": 0.017453541979193687, "avg_return": 0.34808745980262756, "regret": 0.5130165815353394, "entropy": 0.7103195786476135, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:25.784097Z", "loop": 614, "env_steps": 377855999, "loss": 0.018485844135284424, "avg_return": 0.35813456773757935, "regret": 0.5130165815353394, "entropy": 0.7106887698173523, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:26.677154Z", "loop": 615, "env_steps": 378470399, "loss": 0.018061557784676552, "avg_return": 0.35050371289253235, "regret": 0.5125102996826172, "entropy": 0.711123526096344, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:27.529644Z", "loop": 616, "env_steps": 379084799, "loss": 0.019759660586714745, "avg_return": 0.35561174154281616, "regret": 0.5125102996826172, "entropy": 0.7112313508987427, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:28.383217Z", "loop": 617, "env_steps": 379699199, "loss": 0.017506709322333336, "avg_return": 0.3454723060131073, "regret": 0.5125102996826172, "entropy": 0.7110082507133484, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:29.236880Z", "loop": 618, "env_steps": 380313599, "loss": 0.01839577965438366, "avg_return": 0.351760596036911, "regret": 0.5125102996826172, "entropy": 0.7103464007377625, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:30.089834Z", "loop": 619, "env_steps": 380927999, "loss": 0.018415581434965134, "avg_return": 0.34633001685142517, "regret": 0.5125102996826172, "entropy": 0.7095634937286377, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:30.984357Z", "loop": 620, "env_steps": 381542399, "loss": 0.019377997145056725, "avg_return": 0.3496273159980774, "regret": 0.5129102468490601, "entropy": 0.7090533971786499, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:31.837555Z", "loop": 621, "env_steps": 382156799, "loss": 0.019810982048511505, "avg_return": 0.3471331298351288, "regret": 0.5129102468490601, "entropy": 0.7091127038002014, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:32.690402Z", "loop": 622, "env_steps": 382771199, "loss": 0.018858561292290688, "avg_return": 0.34653010964393616, "regret": 0.5129102468490601, "entropy": 0.7095564603805542, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:33.542421Z", "loop": 623, "env_steps": 383385599, "loss": 0.017500977963209152, "avg_return": 0.35159748792648315, "regret": 0.5129102468490601, "entropy": 0.7103455066680908, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:34.395747Z", "loop": 624, "env_steps": 383999999, "loss": 0.018066879361867905, "avg_return": 0.3508555591106415, "regret": 0.5129102468490601, "entropy": 0.7107412815093994, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:35.289271Z", "loop": 625, "env_steps": 384614399, "loss": 0.017369890585541725, "avg_return": 0.349549263715744, "regret": 0.5125111937522888, "entropy": 0.711168110370636, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:36.141263Z", "loop": 626, "env_steps": 385228799, "loss": 0.018827218562364578, "avg_return": 0.35564228892326355, "regret": 0.5125111937522888, "entropy": 0.7111273407936096, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:36.994087Z", "loop": 627, "env_steps": 385843199, "loss": 0.017688749358057976, "avg_return": 0.34780290722846985, "regret": 0.5125111937522888, "entropy": 0.7109882831573486, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:37.848019Z", "loop": 628, "env_steps": 386457599, "loss": 0.016848888248205185, "avg_return": 0.34763389825820923, "regret": 0.5125111937522888, "entropy": 0.7104367017745972, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:38.700563Z", "loop": 629, "env_steps": 387071999, "loss": 0.017927132546901703, "avg_return": 0.3537791669368744, "regret": 0.5125111937522888, "entropy": 0.709869921207428, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:39.590822Z", "loop": 630, "env_steps": 387686399, "loss": 0.018879493698477745, "avg_return": 0.35124921798706055, "regret": 0.5125912427902222, "entropy": 0.7092907428741455, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:40.443086Z", "loop": 631, "env_steps": 388300799, "loss": 0.0178881473839283, "avg_return": 0.3534490168094635, "regret": 0.5125912427902222, "entropy": 0.7085512280464172, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:41.296238Z", "loop": 632, "env_steps": 388915199, "loss": 0.018079154193401337, "avg_return": 0.3474047780036926, "regret": 0.5125912427902222, "entropy": 0.7082381844520569, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:42.149180Z", "loop": 633, "env_steps": 389529599, "loss": 0.01900183968245983, "avg_return": 0.3536601960659027, "regret": 0.5125912427902222, "entropy": 0.707898736000061, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:43.002495Z", "loop": 634, "env_steps": 390143999, "loss": 0.01812533102929592, "avg_return": 0.35227856040000916, "regret": 0.5125912427902222, "entropy": 0.7072380185127258, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:43.895032Z", "loop": 635, "env_steps": 390758399, "loss": 0.018272412940859795, "avg_return": 0.35197436809539795, "regret": 0.512636125087738, "entropy": 0.7066510319709778, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:44.747790Z", "loop": 636, "env_steps": 391372799, "loss": 0.018625741824507713, "avg_return": 0.3523313105106354, "regret": 0.512636125087738, "entropy": 0.7061107754707336, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:45.600865Z", "loop": 637, "env_steps": 391987199, "loss": 0.018290529027581215, "avg_return": 0.35420745611190796, "regret": 0.512636125087738, "entropy": 0.7059756517410278, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:46.453813Z", "loop": 638, "env_steps": 392601599, "loss": 0.01792500726878643, "avg_return": 0.3531895875930786, "regret": 0.512636125087738, "entropy": 0.7062482833862305, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:47.306257Z", "loop": 639, "env_steps": 393215999, "loss": 0.016966508701443672, "avg_return": 0.3455142676830292, "regret": 0.512636125087738, "entropy": 0.7064465284347534, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:48.199785Z", "loop": 640, "env_steps": 393830399, "loss": 0.018244007602334023, "avg_return": 0.3571148216724396, "regret": 0.512481153011322, "entropy": 0.7066344022750854, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:49.053046Z", "loop": 641, "env_steps": 394444799, "loss": 0.01949373260140419, "avg_return": 0.3480423390865326, "regret": 0.512481153011322, "entropy": 0.7069368362426758, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:49.906170Z", "loop": 642, "env_steps": 395059199, "loss": 0.01904950849711895, "avg_return": 0.3580741584300995, "regret": 0.512481153011322, "entropy": 0.7070651650428772, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:50.759375Z", "loop": 643, "env_steps": 395673599, "loss": 0.01871452108025551, "avg_return": 0.34749460220336914, "regret": 0.512481153011322, "entropy": 0.7073217034339905, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:51.612343Z", "loop": 644, "env_steps": 396287999, "loss": 0.017982469871640205, "avg_return": 0.34661296010017395, "regret": 0.512481153011322, "entropy": 0.7076106667518616, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:52.505382Z", "loop": 645, "env_steps": 396902399, "loss": 0.018029360100626945, "avg_return": 0.35075536370277405, "regret": 0.5124635696411133, "entropy": 0.7079174518585205, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:53.358911Z", "loop": 646, "env_steps": 397516799, "loss": 0.018104851245880127, "avg_return": 0.3496769368648529, "regret": 0.5124635696411133, "entropy": 0.707924485206604, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:54.211254Z", "loop": 647, "env_steps": 398131199, "loss": 0.018493352457880974, "avg_return": 0.35379427671432495, "regret": 0.5124635696411133, "entropy": 0.7082679867744446, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:55.063608Z", "loop": 648, "env_steps": 398745599, "loss": 0.017982088029384613, "avg_return": 0.34881383180618286, "regret": 0.5124635696411133, "entropy": 0.7086271643638611, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:55.915615Z", "loop": 649, "env_steps": 399359999, "loss": 0.019863642752170563, "avg_return": 0.349624902009964, "regret": 0.5124635696411133, "entropy": 0.7087947726249695, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:56.809503Z", "loop": 650, "env_steps": 399974399, "loss": 0.018551969900727272, "avg_return": 0.35091644525527954, "regret": 0.5125108361244202, "entropy": 0.7087382078170776, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:57.663189Z", "loop": 651, "env_steps": 400588799, "loss": 0.018009964376688004, "avg_return": 0.35390782356262207, "regret": 0.5125108361244202, "entropy": 0.7086604237556458, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:58.516507Z", "loop": 652, "env_steps": 401203199, "loss": 0.018016716465353966, "avg_return": 0.3500252068042755, "regret": 0.5125108361244202, "entropy": 0.7085601687431335, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:32:59.367908Z", "loop": 653, "env_steps": 401817599, "loss": 0.018781164661049843, "avg_return": 0.3498516380786896, "regret": 0.5125108361244202, "entropy": 0.7083524465560913, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:00.219599Z", "loop": 654, "env_steps": 402431999, "loss": 0.019066978245973587, "avg_return": 0.3530347943305969, "regret": 0.5125108361244202, "entropy": 0.7079158425331116, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:01.113682Z", "loop": 655, "env_steps": 403046399, "loss": 0.01812972128391266, "avg_return": 0.3530706465244293, "regret": 0.5124467611312866, "entropy": 0.7073251605033875, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:01.966551Z", "loop": 656, "env_steps": 403660799, "loss": 0.0187087245285511, "avg_return": 0.3542254865169525, "regret": 0.5124467611312866, "entropy": 0.7069306969642639, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:02.818415Z", "loop": 657, "env_steps": 404275199, "loss": 0.016806429252028465, "avg_return": 0.3540555536746979, "regret": 0.5124467611312866, "entropy": 0.7067245841026306, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:03.669771Z", "loop": 658, "env_steps": 404889599, "loss": 0.01780267246067524, "avg_return": 0.3527659475803375, "regret": 0.5124467611312866, "entropy": 0.7068315148353577, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:04.521203Z", "loop": 659, "env_steps": 405503999, "loss": 0.018142996355891228, "avg_return": 0.3474198877811432, "regret": 0.5124467611312866, "entropy": 0.7068069577217102, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:05.412806Z", "loop": 660, "env_steps": 406118399, "loss": 0.017278866842389107, "avg_return": 0.3515058755874634, "regret": 0.5123846530914307, "entropy": 0.7067033648490906, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:06.264545Z", "loop": 661, "env_steps": 406732799, "loss": 0.018026597797870636, "avg_return": 0.3574567437171936, "regret": 0.5123846530914307, "entropy": 0.7065423727035522, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:07.116520Z", "loop": 662, "env_steps": 407347199, "loss": 0.018403807654976845, "avg_return": 0.355800986289978, "regret": 0.5123846530914307, "entropy": 0.7062270045280457, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:07.968325Z", "loop": 663, "env_steps": 407961599, "loss": 0.018415171653032303, "avg_return": 0.3522094488143921, "regret": 0.5123846530914307, "entropy": 0.7057657241821289, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:08.821206Z", "loop": 664, "env_steps": 408575999, "loss": 0.017048634588718414, "avg_return": 0.34873855113983154, "regret": 0.5123846530914307, "entropy": 0.7055967450141907, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:09.713418Z", "loop": 665, "env_steps": 409190399, "loss": 0.01845281571149826, "avg_return": 0.3497104346752167, "regret": 0.5123764872550964, "entropy": 0.705697238445282, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:10.566244Z", "loop": 666, "env_steps": 409804799, "loss": 0.0185313131660223, "avg_return": 0.3520897626876831, "regret": 0.5123764872550964, "entropy": 0.7055671811103821, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:11.419854Z", "loop": 667, "env_steps": 410419199, "loss": 0.01802278496325016, "avg_return": 0.3464173972606659, "regret": 0.5123764872550964, "entropy": 0.7052547335624695, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:12.274072Z", "loop": 668, "env_steps": 411033599, "loss": 0.01770150288939476, "avg_return": 0.34974217414855957, "regret": 0.5123764872550964, "entropy": 0.7048177719116211, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:13.128061Z", "loop": 669, "env_steps": 411647999, "loss": 0.018551206216216087, "avg_return": 0.34970611333847046, "regret": 0.5123764872550964, "entropy": 0.7041682004928589, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:14.018357Z", "loop": 670, "env_steps": 412262399, "loss": 0.016665447503328323, "avg_return": 0.3535045385360718, "regret": 0.5128862261772156, "entropy": 0.7032830715179443, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:14.871322Z", "loop": 671, "env_steps": 412876799, "loss": 0.017858212813735008, "avg_return": 0.3509026765823364, "regret": 0.5128862261772156, "entropy": 0.701895534992218, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:15.723936Z", "loop": 672, "env_steps": 413491199, "loss": 0.01872841827571392, "avg_return": 0.3590363562107086, "regret": 0.5128862261772156, "entropy": 0.7010499835014343, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:16.577155Z", "loop": 673, "env_steps": 414105599, "loss": 0.01910494454205036, "avg_return": 0.3498899042606354, "regret": 0.5128862261772156, "entropy": 0.7015634775161743, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:17.429798Z", "loop": 674, "env_steps": 414719999, "loss": 0.016812879592180252, "avg_return": 0.3512313961982727, "regret": 0.5128862261772156, "entropy": 0.7019774317741394, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:18.319639Z", "loop": 675, "env_steps": 415334399, "loss": 0.017838403582572937, "avg_return": 0.34966740012168884, "regret": 0.5129321217536926, "entropy": 0.7031577229499817, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:19.171537Z", "loop": 676, "env_steps": 415948799, "loss": 0.017666948959231377, "avg_return": 0.35339683294296265, "regret": 0.5129321217536926, "entropy": 0.7046459317207336, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:20.023330Z", "loop": 677, "env_steps": 416563199, "loss": 0.018320357427001, "avg_return": 0.3537434935569763, "regret": 0.5129321217536926, "entropy": 0.7055628895759583, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:20.875760Z", "loop": 678, "env_steps": 417177599, "loss": 0.01889551617205143, "avg_return": 0.3480015993118286, "regret": 0.5129321217536926, "entropy": 0.7051219940185547, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:21.728201Z", "loop": 679, "env_steps": 417791999, "loss": 0.01825493946671486, "avg_return": 0.34944790601730347, "regret": 0.5129321217536926, "entropy": 0.7038894295692444, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:22.618839Z", "loop": 680, "env_steps": 418406399, "loss": 0.01789354905486107, "avg_return": 0.3482842743396759, "regret": 0.5128900408744812, "entropy": 0.7026569247245789, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:23.471941Z", "loop": 681, "env_steps": 419020799, "loss": 0.018948819488286972, "avg_return": 0.3509068489074707, "regret": 0.5128900408744812, "entropy": 0.7016341686248779, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:24.323904Z", "loop": 682, "env_steps": 419635199, "loss": 0.018159743398427963, "avg_return": 0.3481800854206085, "regret": 0.5128900408744812, "entropy": 0.7005043625831604, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:25.176261Z", "loop": 683, "env_steps": 420249599, "loss": 0.01998879574239254, "avg_return": 0.3552987277507782, "regret": 0.5128900408744812, "entropy": 0.7002025842666626, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:26.029294Z", "loop": 684, "env_steps": 420863999, "loss": 0.018382025882601738, "avg_return": 0.3514893054962158, "regret": 0.5128900408744812, "entropy": 0.7004653811454773, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:26.919305Z", "loop": 685, "env_steps": 421478399, "loss": 0.01700466312468052, "avg_return": 0.3485814929008484, "regret": 0.5131286978721619, "entropy": 0.7004095911979675, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:27.771532Z", "loop": 686, "env_steps": 422092799, "loss": 0.01892920583486557, "avg_return": 0.3504345715045929, "regret": 0.5131286978721619, "entropy": 0.7001663446426392, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:28.623735Z", "loop": 687, "env_steps": 422707199, "loss": 0.01900937221944332, "avg_return": 0.3535602390766144, "regret": 0.5131286978721619, "entropy": 0.7000421285629272, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:29.476365Z", "loop": 688, "env_steps": 423321599, "loss": 0.017968090251088142, "avg_return": 0.3477928042411804, "regret": 0.5131286978721619, "entropy": 0.7004380822181702, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:30.329939Z", "loop": 689, "env_steps": 423935999, "loss": 0.01781008578836918, "avg_return": 0.3507942855358124, "regret": 0.5131286978721619, "entropy": 0.7006308436393738, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:31.220945Z", "loop": 690, "env_steps": 424550399, "loss": 0.019628701731562614, "avg_return": 0.3542464077472687, "regret": 0.5126379132270813, "entropy": 0.7010910511016846, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:32.074075Z", "loop": 691, "env_steps": 425164799, "loss": 0.019132347777485847, "avg_return": 0.3548375964164734, "regret": 0.5126379132270813, "entropy": 0.7016217708587646, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:32.927025Z", "loop": 692, "env_steps": 425779199, "loss": 0.019467610865831375, "avg_return": 0.35829564929008484, "regret": 0.5126379132270813, "entropy": 0.7015564441680908, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:33.779876Z", "loop": 693, "env_steps": 426393599, "loss": 0.017275596037507057, "avg_return": 0.3461950719356537, "regret": 0.5126379132270813, "entropy": 0.7017025351524353, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:34.632438Z", "loop": 694, "env_steps": 427007999, "loss": 0.017500778660178185, "avg_return": 0.3533201217651367, "regret": 0.5126379132270813, "entropy": 0.7021229267120361, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:35.524350Z", "loop": 695, "env_steps": 427622399, "loss": 0.018333828076720238, "avg_return": 0.35932138562202454, "regret": 0.5122776627540588, "entropy": 0.7024303674697876, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:36.377218Z", "loop": 696, "env_steps": 428236799, "loss": 0.017680790275335312, "avg_return": 0.3505549132823944, "regret": 0.5122776627540588, "entropy": 0.7022628784179688, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:37.230185Z", "loop": 697, "env_steps": 428851199, "loss": 0.01828223280608654, "avg_return": 0.35407981276512146, "regret": 0.5122776627540588, "entropy": 0.7017911672592163, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:38.083803Z", "loop": 698, "env_steps": 429465599, "loss": 0.018254457041621208, "avg_return": 0.3491218388080597, "regret": 0.5122776627540588, "entropy": 0.7011557817459106, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:38.936161Z", "loop": 699, "env_steps": 430079999, "loss": 0.01692442037165165, "avg_return": 0.3507101535797119, "regret": 0.5122776627540588, "entropy": 0.700721025466919, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:39.828381Z", "loop": 700, "env_steps": 430694399, "loss": 0.01746763475239277, "avg_return": 0.34980282187461853, "regret": 0.5127448439598083, "entropy": 0.7003808617591858, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:40.681810Z", "loop": 701, "env_steps": 431308799, "loss": 0.01678149402141571, "avg_return": 0.3462403416633606, "regret": 0.5127448439598083, "entropy": 0.7010286450386047, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:41.536441Z", "loop": 702, "env_steps": 431923199, "loss": 0.019229985773563385, "avg_return": 0.3470083475112915, "regret": 0.5127448439598083, "entropy": 0.7014473080635071, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:42.391313Z", "loop": 703, "env_steps": 432537599, "loss": 0.017639799043536186, "avg_return": 0.3528112471103668, "regret": 0.5127448439598083, "entropy": 0.7018272280693054, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:43.244295Z", "loop": 704, "env_steps": 433151999, "loss": 0.017725298181176186, "avg_return": 0.3522641360759735, "regret": 0.5127448439598083, "entropy": 0.7025617361068726, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:44.135621Z", "loop": 705, "env_steps": 433766399, "loss": 0.018721560016274452, "avg_return": 0.35314875841140747, "regret": 0.5122878551483154, "entropy": 0.7030379772186279, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:44.988657Z", "loop": 706, "env_steps": 434380799, "loss": 0.016502009704709053, "avg_return": 0.3481990098953247, "regret": 0.5122878551483154, "entropy": 0.7036439180374146, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:45.842089Z", "loop": 707, "env_steps": 434995199, "loss": 0.018143758177757263, "avg_return": 0.35667863488197327, "regret": 0.5122878551483154, "entropy": 0.7042089700698853, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:46.694735Z", "loop": 708, "env_steps": 435609599, "loss": 0.018761441111564636, "avg_return": 0.3463398814201355, "regret": 0.5122878551483154, "entropy": 0.7048727869987488, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:47.546876Z", "loop": 709, "env_steps": 436223999, "loss": 0.01817432977259159, "avg_return": 0.34479472041130066, "regret": 0.5122878551483154, "entropy": 0.7055715322494507, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:48.441690Z", "loop": 710, "env_steps": 436838399, "loss": 0.018092641606926918, "avg_return": 0.3610191345214844, "regret": 0.5122737288475037, "entropy": 0.7065169811248779, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:49.295487Z", "loop": 711, "env_steps": 437452799, "loss": 0.017704762518405914, "avg_return": 0.35264989733695984, "regret": 0.5122737288475037, "entropy": 0.7071620225906372, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:50.148885Z", "loop": 712, "env_steps": 438067199, "loss": 0.017358554527163506, "avg_return": 0.3574628531932831, "regret": 0.5122737288475037, "entropy": 0.7074979543685913, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:51.001888Z", "loop": 713, "env_steps": 438681599, "loss": 0.01821138709783554, "avg_return": 0.3510882258415222, "regret": 0.5122737288475037, "entropy": 0.7077842950820923, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:51.855636Z", "loop": 714, "env_steps": 439295999, "loss": 0.01797313243150711, "avg_return": 0.35336682200431824, "regret": 0.5122737288475037, "entropy": 0.7080265283584595, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:52.749924Z", "loop": 715, "env_steps": 439910399, "loss": 0.01725449413061142, "avg_return": 0.35385197401046753, "regret": 0.5122745037078857, "entropy": 0.7085071802139282, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:53.603362Z", "loop": 716, "env_steps": 440524799, "loss": 0.01757972501218319, "avg_return": 0.35153064131736755, "regret": 0.5122745037078857, "entropy": 0.7088342308998108, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:54.455965Z", "loop": 717, "env_steps": 441139199, "loss": 0.017286119982600212, "avg_return": 0.34684011340141296, "regret": 0.5122745037078857, "entropy": 0.70928955078125, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:55.309899Z", "loop": 718, "env_steps": 441753599, "loss": 0.018378471955657005, "avg_return": 0.3586379885673523, "regret": 0.5122745037078857, "entropy": 0.7090875506401062, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:56.163150Z", "loop": 719, "env_steps": 442367999, "loss": 0.018675943836569786, "avg_return": 0.35270392894744873, "regret": 0.5122745037078857, "entropy": 0.7087944149971008, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:57.056322Z", "loop": 720, "env_steps": 442982399, "loss": 0.019816473126411438, "avg_return": 0.3501421809196472, "regret": 0.5124967098236084, "entropy": 0.7082012295722961, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:57.909624Z", "loop": 721, "env_steps": 443596799, "loss": 0.018497204408049583, "avg_return": 0.3556656241416931, "regret": 0.5124967098236084, "entropy": 0.7075895071029663, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:58.763114Z", "loop": 722, "env_steps": 444211199, "loss": 0.01939876563847065, "avg_return": 0.35873520374298096, "regret": 0.5124967098236084, "entropy": 0.707126796245575, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:33:59.616581Z", "loop": 723, "env_steps": 444825599, "loss": 0.018998561426997185, "avg_return": 0.35162681341171265, "regret": 0.5124967098236084, "entropy": 0.7072932124137878, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:00.469687Z", "loop": 724, "env_steps": 445439999, "loss": 0.018481604754924774, "avg_return": 0.35002464056015015, "regret": 0.5124967098236084, "entropy": 0.7072745561599731, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:01.361014Z", "loop": 725, "env_steps": 446054399, "loss": 0.01770598255097866, "avg_return": 0.3485623598098755, "regret": 0.5126628279685974, "entropy": 0.7074853777885437, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:02.214124Z", "loop": 726, "env_steps": 446668799, "loss": 0.016611438244581223, "avg_return": 0.34248626232147217, "regret": 0.5126628279685974, "entropy": 0.7076454758644104, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:03.066289Z", "loop": 727, "env_steps": 447283199, "loss": 0.018019719049334526, "avg_return": 0.3451544940471649, "regret": 0.5126628279685974, "entropy": 0.7078793048858643, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:03.919583Z", "loop": 728, "env_steps": 447897599, "loss": 0.019062627106904984, "avg_return": 0.3504711091518402, "regret": 0.5126628279685974, "entropy": 0.7083126902580261, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:04.772064Z", "loop": 729, "env_steps": 448511999, "loss": 0.01761937327682972, "avg_return": 0.3464581072330475, "regret": 0.5126628279685974, "entropy": 0.7089495658874512, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:05.664384Z", "loop": 730, "env_steps": 449126399, "loss": 0.018404290080070496, "avg_return": 0.3448283076286316, "regret": 0.512273371219635, "entropy": 0.7099204063415527, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:06.517477Z", "loop": 731, "env_steps": 449740799, "loss": 0.019919447600841522, "avg_return": 0.3518725037574768, "regret": 0.512273371219635, "entropy": 0.7103767395019531, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:07.369400Z", "loop": 732, "env_steps": 450355199, "loss": 0.018302783370018005, "avg_return": 0.3497009873390198, "regret": 0.512273371219635, "entropy": 0.7104856371879578, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:08.221505Z", "loop": 733, "env_steps": 450969599, "loss": 0.017554927617311478, "avg_return": 0.35788199305534363, "regret": 0.512273371219635, "entropy": 0.7104775905609131, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:09.074915Z", "loop": 734, "env_steps": 451583999, "loss": 0.01890275999903679, "avg_return": 0.3501213788986206, "regret": 0.512273371219635, "entropy": 0.710318386554718, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:09.968208Z", "loop": 735, "env_steps": 452198399, "loss": 0.018427519127726555, "avg_return": 0.35069525241851807, "regret": 0.5122317671775818, "entropy": 0.7099058032035828, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:10.820221Z", "loop": 736, "env_steps": 452812799, "loss": 0.019165758043527603, "avg_return": 0.3559238910675049, "regret": 0.5122317671775818, "entropy": 0.7095993161201477, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:11.673461Z", "loop": 737, "env_steps": 453427199, "loss": 0.017518747597932816, "avg_return": 0.3454243540763855, "regret": 0.5122317671775818, "entropy": 0.7091634273529053, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:12.526877Z", "loop": 738, "env_steps": 454041599, "loss": 0.01874570921063423, "avg_return": 0.3610506057739258, "regret": 0.5122317671775818, "entropy": 0.7089802026748657, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:13.380019Z", "loop": 739, "env_steps": 454655999, "loss": 0.019304325804114342, "avg_return": 0.3479497730731964, "regret": 0.5122317671775818, "entropy": 0.7085919976234436, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:14.272562Z", "loop": 740, "env_steps": 455270399, "loss": 0.016909679397940636, "avg_return": 0.34391653537750244, "regret": 0.5121810436248779, "entropy": 0.7081634998321533, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:15.125417Z", "loop": 741, "env_steps": 455884799, "loss": 0.01694234274327755, "avg_return": 0.3490124046802521, "regret": 0.5121810436248779, "entropy": 0.7074234485626221, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:15.979059Z", "loop": 742, "env_steps": 456499199, "loss": 0.018436677753925323, "avg_return": 0.3558017611503601, "regret": 0.5121810436248779, "entropy": 0.7068498730659485, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:16.832747Z", "loop": 743, "env_steps": 457113599, "loss": 0.019528377801179886, "avg_return": 0.34875693917274475, "regret": 0.5121810436248779, "entropy": 0.7067890763282776, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:17.685616Z", "loop": 744, "env_steps": 457727999, "loss": 0.017899783328175545, "avg_return": 0.35527902841567993, "regret": 0.5121810436248779, "entropy": 0.7068094611167908, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:18.575782Z", "loop": 745, "env_steps": 458342399, "loss": 0.01742725633084774, "avg_return": 0.3493230640888214, "regret": 0.5123487114906311, "entropy": 0.7068663239479065, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:19.429148Z", "loop": 746, "env_steps": 458956799, "loss": 0.019380662590265274, "avg_return": 0.35697177052497864, "regret": 0.5123487114906311, "entropy": 0.7064114212989807, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:20.282860Z", "loop": 747, "env_steps": 459571199, "loss": 0.01822119951248169, "avg_return": 0.34657976031303406, "regret": 0.5123487114906311, "entropy": 0.7060127854347229, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:21.136870Z", "loop": 748, "env_steps": 460185599, "loss": 0.01784726232290268, "avg_return": 0.34453925490379333, "regret": 0.5123487114906311, "entropy": 0.7052031755447388, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:21.989773Z", "loop": 749, "env_steps": 460799999, "loss": 0.018245050683617592, "avg_return": 0.3382152020931244, "regret": 0.5123487114906311, "entropy": 0.7048275470733643, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:22.882662Z", "loop": 750, "env_steps": 461414399, "loss": 0.01896953396499157, "avg_return": 0.35766735672950745, "regret": 0.5129504203796387, "entropy": 0.7047501802444458, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:23.735564Z", "loop": 751, "env_steps": 462028799, "loss": 0.017807092517614365, "avg_return": 0.3466580808162689, "regret": 0.5129504203796387, "entropy": 0.7048659324645996, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:24.588757Z", "loop": 752, "env_steps": 462643199, "loss": 0.01833510212600231, "avg_return": 0.3459184765815735, "regret": 0.5129504203796387, "entropy": 0.7055594325065613, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:25.441029Z", "loop": 753, "env_steps": 463257599, "loss": 0.017617329955101013, "avg_return": 0.34939709305763245, "regret": 0.5129504203796387, "entropy": 0.7061335444450378, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:26.294043Z", "loop": 754, "env_steps": 463871999, "loss": 0.01764155738055706, "avg_return": 0.35040175914764404, "regret": 0.5129504203796387, "entropy": 0.7069768905639648, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:27.185101Z", "loop": 755, "env_steps": 464486399, "loss": 0.019904566928744316, "avg_return": 0.3515154719352722, "regret": 0.5125420093536377, "entropy": 0.7080031633377075, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:28.038042Z", "loop": 756, "env_steps": 465100799, "loss": 0.017636580392718315, "avg_return": 0.3536120057106018, "regret": 0.5125420093536377, "entropy": 0.7088512778282166, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:28.891267Z", "loop": 757, "env_steps": 465715199, "loss": 0.016415001824498177, "avg_return": 0.3446730375289917, "regret": 0.5125420093536377, "entropy": 0.7103801369667053, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:29.744602Z", "loop": 758, "env_steps": 466329599, "loss": 0.018383925780653954, "avg_return": 0.3493177890777588, "regret": 0.5125420093536377, "entropy": 0.7113210558891296, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:30.597046Z", "loop": 759, "env_steps": 466943999, "loss": 0.017938610166311264, "avg_return": 0.35374218225479126, "regret": 0.5125420093536377, "entropy": 0.7117778062820435, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:31.488237Z", "loop": 760, "env_steps": 467558399, "loss": 0.01843913644552231, "avg_return": 0.3506624102592468, "regret": 0.5122485756874084, "entropy": 0.7119035720825195, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:32.341213Z", "loop": 761, "env_steps": 468172799, "loss": 0.018330996856093407, "avg_return": 0.35324981808662415, "regret": 0.5122485756874084, "entropy": 0.7117779850959778, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:33.195399Z", "loop": 762, "env_steps": 468787199, "loss": 0.018368268385529518, "avg_return": 0.34277909994125366, "regret": 0.5122485756874084, "entropy": 0.7115045785903931, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:34.046845Z", "loop": 763, "env_steps": 469401599, "loss": 0.01939236931502819, "avg_return": 0.3579363226890564, "regret": 0.5122485756874084, "entropy": 0.7110575437545776, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:34.898253Z", "loop": 764, "env_steps": 470015999, "loss": 0.01919681951403618, "avg_return": 0.34971871972084045, "regret": 0.5122485756874084, "entropy": 0.7111824750900269, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:35.789571Z", "loop": 765, "env_steps": 470630399, "loss": 0.018775809556245804, "avg_return": 0.34901997447013855, "regret": 0.5128725171089172, "entropy": 0.7119700908660889, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:36.643453Z", "loop": 766, "env_steps": 471244799, "loss": 0.0181626845151186, "avg_return": 0.3522607088088989, "regret": 0.5128725171089172, "entropy": 0.712287425994873, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:37.496349Z", "loop": 767, "env_steps": 471859199, "loss": 0.016372842714190483, "avg_return": 0.3555926978588104, "regret": 0.5128725171089172, "entropy": 0.7131343483924866, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:38.347966Z", "loop": 768, "env_steps": 472473599, "loss": 0.018946584314107895, "avg_return": 0.35493284463882446, "regret": 0.5128725171089172, "entropy": 0.7138126492500305, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:39.200447Z", "loop": 769, "env_steps": 473087999, "loss": 0.017331037670373917, "avg_return": 0.3527062237262726, "regret": 0.5128725171089172, "entropy": 0.7141686677932739, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:40.092608Z", "loop": 770, "env_steps": 473702399, "loss": 0.01827259175479412, "avg_return": 0.3518701195716858, "regret": 0.5121025443077087, "entropy": 0.7143214344978333, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:40.945175Z", "loop": 771, "env_steps": 474316799, "loss": 0.018826093524694443, "avg_return": 0.3551589846611023, "regret": 0.5121025443077087, "entropy": 0.7143549919128418, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:41.797895Z", "loop": 772, "env_steps": 474931199, "loss": 0.01823475770652294, "avg_return": 0.351972371339798, "regret": 0.5121025443077087, "entropy": 0.7143140435218811, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:42.650824Z", "loop": 773, "env_steps": 475545599, "loss": 0.01955040916800499, "avg_return": 0.3436223864555359, "regret": 0.5121025443077087, "entropy": 0.7139332890510559, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:43.504066Z", "loop": 774, "env_steps": 476159999, "loss": 0.01702713407576084, "avg_return": 0.3447265625, "regret": 0.5121025443077087, "entropy": 0.7130894064903259, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:44.397481Z", "loop": 775, "env_steps": 476774399, "loss": 0.01828688383102417, "avg_return": 0.35490697622299194, "regret": 0.512739896774292, "entropy": 0.712374746799469, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:45.250207Z", "loop": 776, "env_steps": 477388799, "loss": 0.018053455278277397, "avg_return": 0.3498196601867676, "regret": 0.512739896774292, "entropy": 0.7125240564346313, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:46.103047Z", "loop": 777, "env_steps": 478003199, "loss": 0.018863528966903687, "avg_return": 0.3502159118652344, "regret": 0.512739896774292, "entropy": 0.7131854891777039, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:46.956219Z", "loop": 778, "env_steps": 478617599, "loss": 0.01802671328186989, "avg_return": 0.3508880138397217, "regret": 0.512739896774292, "entropy": 0.713649570941925, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:47.809311Z", "loop": 779, "env_steps": 479231999, "loss": 0.01885087601840496, "avg_return": 0.3509422540664673, "regret": 0.512739896774292, "entropy": 0.7143682241439819, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:48.701402Z", "loop": 780, "env_steps": 479846399, "loss": 0.01815471239387989, "avg_return": 0.34667256474494934, "regret": 0.5120849013328552, "entropy": 0.7146225571632385, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:49.553878Z", "loop": 781, "env_steps": 480460799, "loss": 0.01795465312898159, "avg_return": 0.35722872614860535, "regret": 0.5120849013328552, "entropy": 0.715094268321991, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:50.407402Z", "loop": 782, "env_steps": 481075199, "loss": 0.018254825845360756, "avg_return": 0.35037437081336975, "regret": 0.5120849013328552, "entropy": 0.7151312828063965, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:51.259644Z", "loop": 783, "env_steps": 481689599, "loss": 0.018445657566189766, "avg_return": 0.35423630475997925, "regret": 0.5120849013328552, "entropy": 0.7141212821006775, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:52.112143Z", "loop": 784, "env_steps": 482303999, "loss": 0.019480058923363686, "avg_return": 0.35467255115509033, "regret": 0.5120849013328552, "entropy": 0.7127079963684082, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:53.000917Z", "loop": 785, "env_steps": 482918399, "loss": 0.018472755327820778, "avg_return": 0.3519727289676666, "regret": 0.5125954747200012, "entropy": 0.7116659879684448, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:53.852840Z", "loop": 786, "env_steps": 483532799, "loss": 0.018918156623840332, "avg_return": 0.34869584441185, "regret": 0.5125954747200012, "entropy": 0.7112141251564026, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:54.705096Z", "loop": 787, "env_steps": 484147199, "loss": 0.018036941066384315, "avg_return": 0.35569891333580017, "regret": 0.5125954747200012, "entropy": 0.7110984921455383, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:55.557508Z", "loop": 788, "env_steps": 484761599, "loss": 0.018173186108469963, "avg_return": 0.3534092307090759, "regret": 0.5125954747200012, "entropy": 0.7107872366905212, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:56.409879Z", "loop": 789, "env_steps": 485375999, "loss": 0.017480667680501938, "avg_return": 0.35175636410713196, "regret": 0.5125954747200012, "entropy": 0.7106455564498901, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:57.303418Z", "loop": 790, "env_steps": 485990399, "loss": 0.017719760537147522, "avg_return": 0.35071107745170593, "regret": 0.5124228000640869, "entropy": 0.711225152015686, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:58.155824Z", "loop": 791, "env_steps": 486604799, "loss": 0.01804991252720356, "avg_return": 0.3510066270828247, "regret": 0.5124228000640869, "entropy": 0.7118544578552246, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:59.008221Z", "loop": 792, "env_steps": 487219199, "loss": 0.01870065927505493, "avg_return": 0.35599127411842346, "regret": 0.5124228000640869, "entropy": 0.712299108505249, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:34:59.860842Z", "loop": 793, "env_steps": 487833599, "loss": 0.018858956173062325, "avg_return": 0.35144099593162537, "regret": 0.5124228000640869, "entropy": 0.712696373462677, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:00.714657Z", "loop": 794, "env_steps": 488447999, "loss": 0.01861429400742054, "avg_return": 0.35490676760673523, "regret": 0.5124228000640869, "entropy": 0.7128378748893738, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:01.608495Z", "loop": 795, "env_steps": 489062399, "loss": 0.01789717935025692, "avg_return": 0.3500444293022156, "regret": 0.5119655132293701, "entropy": 0.7125168442726135, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:02.461748Z", "loop": 796, "env_steps": 489676799, "loss": 0.019847337156534195, "avg_return": 0.36465173959732056, "regret": 0.5119655132293701, "entropy": 0.7114977836608887, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:03.314049Z", "loop": 797, "env_steps": 490291199, "loss": 0.018206341192126274, "avg_return": 0.3495486080646515, "regret": 0.5119655132293701, "entropy": 0.710260808467865, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:04.167480Z", "loop": 798, "env_steps": 490905599, "loss": 0.017705067992210388, "avg_return": 0.3495565354824066, "regret": 0.5119655132293701, "entropy": 0.7088266611099243, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:05.019739Z", "loop": 799, "env_steps": 491519999, "loss": 0.019334083423018456, "avg_return": 0.35949164628982544, "regret": 0.5119655132293701, "entropy": 0.7077001333236694, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:05.909888Z", "loop": 800, "env_steps": 492134399, "loss": 0.017106907442212105, "avg_return": 0.34594595432281494, "regret": 0.5126690864562988, "entropy": 0.7072396874427795, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:06.762704Z", "loop": 801, "env_steps": 492748799, "loss": 0.01798088476061821, "avg_return": 0.3506923019886017, "regret": 0.5126690864562988, "entropy": 0.7067208886146545, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:07.616360Z", "loop": 802, "env_steps": 493363199, "loss": 0.018875686451792717, "avg_return": 0.34967565536499023, "regret": 0.5126690864562988, "entropy": 0.7060999870300293, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:08.469845Z", "loop": 803, "env_steps": 493977599, "loss": 0.019726155325770378, "avg_return": 0.35225993394851685, "regret": 0.5126690864562988, "entropy": 0.7051966786384583, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:09.321919Z", "loop": 804, "env_steps": 494591999, "loss": 0.018867824226617813, "avg_return": 0.34720084071159363, "regret": 0.5126690864562988, "entropy": 0.7053039073944092, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:10.213258Z", "loop": 805, "env_steps": 495206399, "loss": 0.019092967733740807, "avg_return": 0.349705308675766, "regret": 0.5125462412834167, "entropy": 0.7061706781387329, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:11.067079Z", "loop": 806, "env_steps": 495820799, "loss": 0.018315648660063744, "avg_return": 0.35243019461631775, "regret": 0.5125462412834167, "entropy": 0.7082537412643433, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:11.919501Z", "loop": 807, "env_steps": 496435199, "loss": 0.017320415005087852, "avg_return": 0.35306358337402344, "regret": 0.5125462412834167, "entropy": 0.7096464037895203, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:12.771907Z", "loop": 808, "env_steps": 497049599, "loss": 0.01774829812347889, "avg_return": 0.3483981788158417, "regret": 0.5125462412834167, "entropy": 0.7096845507621765, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:13.623684Z", "loop": 809, "env_steps": 497663999, "loss": 0.017969226464629173, "avg_return": 0.3469887375831604, "regret": 0.5125462412834167, "entropy": 0.7091711759567261, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:14.513266Z", "loop": 810, "env_steps": 498278399, "loss": 0.01709291897714138, "avg_return": 0.34732672572135925, "regret": 0.5123572945594788, "entropy": 0.7078913450241089, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:15.367184Z", "loop": 811, "env_steps": 498892799, "loss": 0.01744004525244236, "avg_return": 0.34201687574386597, "regret": 0.5123572945594788, "entropy": 0.7070319056510925, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:16.219398Z", "loop": 812, "env_steps": 499507199, "loss": 0.01978202536702156, "avg_return": 0.3509388267993927, "regret": 0.5123572945594788, "entropy": 0.7061827778816223, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:17.072131Z", "loop": 813, "env_steps": 500121599, "loss": 0.01722104288637638, "avg_return": 0.34534958004951477, "regret": 0.5123572945594788, "entropy": 0.7057872414588928, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:17.925295Z", "loop": 814, "env_steps": 500735999, "loss": 0.018129369243979454, "avg_return": 0.35209891200065613, "regret": 0.5123572945594788, "entropy": 0.7060083150863647, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:18.818201Z", "loop": 815, "env_steps": 501350399, "loss": 0.017151474952697754, "avg_return": 0.3563229441642761, "regret": 0.5129494667053223, "entropy": 0.7068447470664978, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:19.671650Z", "loop": 816, "env_steps": 501964799, "loss": 0.019763220101594925, "avg_return": 0.3589912950992584, "regret": 0.5129494667053223, "entropy": 0.7085233330726624, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:20.525359Z", "loop": 817, "env_steps": 502579199, "loss": 0.01850643754005432, "avg_return": 0.34977808594703674, "regret": 0.5129494667053223, "entropy": 0.7113667726516724, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:21.378004Z", "loop": 818, "env_steps": 503193599, "loss": 0.0182988028973341, "avg_return": 0.3495054244995117, "regret": 0.5129494667053223, "entropy": 0.7133041620254517, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:22.230277Z", "loop": 819, "env_steps": 503807999, "loss": 0.018926069140434265, "avg_return": 0.35701876878738403, "regret": 0.5129494667053223, "entropy": 0.7138293981552124, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:23.121985Z", "loop": 820, "env_steps": 504422399, "loss": 0.018851948902010918, "avg_return": 0.3516971170902252, "regret": 0.5121099352836609, "entropy": 0.712870717048645, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:23.975907Z", "loop": 821, "env_steps": 505036799, "loss": 0.01845807395875454, "avg_return": 0.35181647539138794, "regret": 0.5121099352836609, "entropy": 0.711988091468811, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:24.828905Z", "loop": 822, "env_steps": 505651199, "loss": 0.01838267594575882, "avg_return": 0.35060635209083557, "regret": 0.5121099352836609, "entropy": 0.7115468978881836, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:25.682439Z", "loop": 823, "env_steps": 506265599, "loss": 0.019306739792227745, "avg_return": 0.3520580232143402, "regret": 0.5121099352836609, "entropy": 0.7110855579376221, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:26.535218Z", "loop": 824, "env_steps": 506879999, "loss": 0.01709013432264328, "avg_return": 0.347827672958374, "regret": 0.5121099352836609, "entropy": 0.7107619047164917, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:27.429259Z", "loop": 825, "env_steps": 507494399, "loss": 0.01910381391644478, "avg_return": 0.3432982861995697, "regret": 0.5128639340400696, "entropy": 0.7111375331878662, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:28.282497Z", "loop": 826, "env_steps": 508108799, "loss": 0.018711427226662636, "avg_return": 0.35387879610061646, "regret": 0.5128639340400696, "entropy": 0.7120376825332642, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:29.136216Z", "loop": 827, "env_steps": 508723199, "loss": 0.019586186856031418, "avg_return": 0.3518528342247009, "regret": 0.5128639340400696, "entropy": 0.7125833630561829, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:29.990039Z", "loop": 828, "env_steps": 509337599, "loss": 0.02021373063325882, "avg_return": 0.3570842444896698, "regret": 0.5128639340400696, "entropy": 0.7131003141403198, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:30.843011Z", "loop": 829, "env_steps": 509951999, "loss": 0.018605610355734825, "avg_return": 0.3486442267894745, "regret": 0.5128639340400696, "entropy": 0.7133257985115051, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:31.737025Z", "loop": 830, "env_steps": 510566399, "loss": 0.017657315358519554, "avg_return": 0.35177314281463623, "regret": 0.5121025443077087, "entropy": 0.7131183743476868, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:32.590757Z", "loop": 831, "env_steps": 511180799, "loss": 0.017095429822802544, "avg_return": 0.34833189845085144, "regret": 0.5121025443077087, "entropy": 0.7131664752960205, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:33.442964Z", "loop": 832, "env_steps": 511795199, "loss": 0.018358541652560234, "avg_return": 0.3549458384513855, "regret": 0.5121025443077087, "entropy": 0.7134300470352173, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:34.295003Z", "loop": 833, "env_steps": 512409599, "loss": 0.01848617009818554, "avg_return": 0.35185328125953674, "regret": 0.5121025443077087, "entropy": 0.7133797407150269, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:35.148510Z", "loop": 834, "env_steps": 513023999, "loss": 0.019230997189879417, "avg_return": 0.3511069416999817, "regret": 0.5121025443077087, "entropy": 0.7132965922355652, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:36.040781Z", "loop": 835, "env_steps": 513638399, "loss": 0.019243273884058, "avg_return": 0.3553563952445984, "regret": 0.5117250084877014, "entropy": 0.7134625911712646, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:36.894881Z", "loop": 836, "env_steps": 514252799, "loss": 0.017284784466028214, "avg_return": 0.3498019576072693, "regret": 0.5117250084877014, "entropy": 0.7134596109390259, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:37.748300Z", "loop": 837, "env_steps": 514867199, "loss": 0.018981067463755608, "avg_return": 0.35615453124046326, "regret": 0.5117250084877014, "entropy": 0.7130119800567627, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:38.601636Z", "loop": 838, "env_steps": 515481599, "loss": 0.018051473423838615, "avg_return": 0.35395851731300354, "regret": 0.5117250084877014, "entropy": 0.7128394246101379, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:39.454253Z", "loop": 839, "env_steps": 516095999, "loss": 0.019732441753149033, "avg_return": 0.35267946124076843, "regret": 0.5117250084877014, "entropy": 0.7130085229873657, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:40.344326Z", "loop": 840, "env_steps": 516710399, "loss": 0.01797131448984146, "avg_return": 0.3501896262168884, "regret": 0.5117120742797852, "entropy": 0.712867796421051, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:41.197373Z", "loop": 841, "env_steps": 517324799, "loss": 0.017026260495185852, "avg_return": 0.3511474132537842, "regret": 0.5117120742797852, "entropy": 0.7125998735427856, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:42.050541Z", "loop": 842, "env_steps": 517939199, "loss": 0.019346607849001884, "avg_return": 0.3510332405567169, "regret": 0.5117120742797852, "entropy": 0.7124797105789185, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:42.904316Z", "loop": 843, "env_steps": 518553599, "loss": 0.01830238662660122, "avg_return": 0.3513093888759613, "regret": 0.5117120742797852, "entropy": 0.7127809524536133, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:43.756896Z", "loop": 844, "env_steps": 519167999, "loss": 0.017641035839915276, "avg_return": 0.3506764769554138, "regret": 0.5117120742797852, "entropy": 0.7129068374633789, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:44.648537Z", "loop": 845, "env_steps": 519782399, "loss": 0.017645450308918953, "avg_return": 0.3555366098880768, "regret": 0.5116201639175415, "entropy": 0.7131989002227783, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:45.500835Z", "loop": 846, "env_steps": 520396799, "loss": 0.017678944393992424, "avg_return": 0.3457483649253845, "regret": 0.5116201639175415, "entropy": 0.713376522064209, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:46.353876Z", "loop": 847, "env_steps": 521011199, "loss": 0.018979091197252274, "avg_return": 0.34590426087379456, "regret": 0.5116201639175415, "entropy": 0.713089644908905, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:47.206984Z", "loop": 848, "env_steps": 521625599, "loss": 0.017000075429677963, "avg_return": 0.3519866466522217, "regret": 0.5116201639175415, "entropy": 0.712570071220398, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:48.060615Z", "loop": 849, "env_steps": 522239999, "loss": 0.018185582011938095, "avg_return": 0.3495546579360962, "regret": 0.5116201639175415, "entropy": 0.71258145570755, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:48.953420Z", "loop": 850, "env_steps": 522854399, "loss": 0.018300974741578102, "avg_return": 0.35462525486946106, "regret": 0.5116921067237854, "entropy": 0.712673008441925, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:49.806127Z", "loop": 851, "env_steps": 523468799, "loss": 0.017177913337945938, "avg_return": 0.355668842792511, "regret": 0.5116921067237854, "entropy": 0.712593138217926, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:50.660185Z", "loop": 852, "env_steps": 524083199, "loss": 0.018418721854686737, "avg_return": 0.35233286023139954, "regret": 0.5116921067237854, "entropy": 0.7122565507888794, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:51.514260Z", "loop": 853, "env_steps": 524697599, "loss": 0.017986057326197624, "avg_return": 0.35143235325813293, "regret": 0.5116921067237854, "entropy": 0.7120504975318909, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:52.367334Z", "loop": 854, "env_steps": 525311999, "loss": 0.01801704242825508, "avg_return": 0.35314875841140747, "regret": 0.5116921067237854, "entropy": 0.7115638852119446, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:53.261086Z", "loop": 855, "env_steps": 525926399, "loss": 0.019397297874093056, "avg_return": 0.34990617632865906, "regret": 0.5114870667457581, "entropy": 0.710931658744812, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:54.114670Z", "loop": 856, "env_steps": 526540799, "loss": 0.018595756962895393, "avg_return": 0.3486284911632538, "regret": 0.5114870667457581, "entropy": 0.7099482417106628, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:54.968551Z", "loop": 857, "env_steps": 527155199, "loss": 0.017461339011788368, "avg_return": 0.3518927991390228, "regret": 0.5114870667457581, "entropy": 0.7090185880661011, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:55.822348Z", "loop": 858, "env_steps": 527769599, "loss": 0.017774883657693863, "avg_return": 0.3525540232658386, "regret": 0.5114870667457581, "entropy": 0.7083571553230286, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:56.675212Z", "loop": 859, "env_steps": 528383999, "loss": 0.01784682646393776, "avg_return": 0.3488951623439789, "regret": 0.5114870667457581, "entropy": 0.7079399228096008, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:57.569719Z", "loop": 860, "env_steps": 528998399, "loss": 0.01788429729640484, "avg_return": 0.34688466787338257, "regret": 0.5114539265632629, "entropy": 0.7071542739868164, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:58.423335Z", "loop": 861, "env_steps": 529612799, "loss": 0.018379194661974907, "avg_return": 0.3535345494747162, "regret": 0.5114539265632629, "entropy": 0.7064453363418579, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:35:59.275894Z", "loop": 862, "env_steps": 530227199, "loss": 0.019089696928858757, "avg_return": 0.3538362979888916, "regret": 0.5114539265632629, "entropy": 0.7059128284454346, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:00.127933Z", "loop": 863, "env_steps": 530841599, "loss": 0.01822691224515438, "avg_return": 0.35011282563209534, "regret": 0.5114539265632629, "entropy": 0.7055380344390869, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:00.979613Z", "loop": 864, "env_steps": 531455999, "loss": 0.017838649451732635, "avg_return": 0.35300713777542114, "regret": 0.5114539265632629, "entropy": 0.7049704194068909, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:01.872854Z", "loop": 865, "env_steps": 532070399, "loss": 0.019335420802235603, "avg_return": 0.3555968403816223, "regret": 0.5118497014045715, "entropy": 0.7037262320518494, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:02.725456Z", "loop": 866, "env_steps": 532684799, "loss": 0.018685638904571533, "avg_return": 0.3497752845287323, "regret": 0.5118497014045715, "entropy": 0.7027934789657593, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:03.578213Z", "loop": 867, "env_steps": 533299199, "loss": 0.017142483964562416, "avg_return": 0.3500577509403229, "regret": 0.5118497014045715, "entropy": 0.7028952836990356, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:04.430589Z", "loop": 868, "env_steps": 533913599, "loss": 0.018028274178504944, "avg_return": 0.3526901304721832, "regret": 0.5118497014045715, "entropy": 0.7037404775619507, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:05.283414Z", "loop": 869, "env_steps": 534527999, "loss": 0.01772858202457428, "avg_return": 0.3509373962879181, "regret": 0.5118497014045715, "entropy": 0.7049811482429504, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:06.177439Z", "loop": 870, "env_steps": 535142399, "loss": 0.017030132934451103, "avg_return": 0.3468494415283203, "regret": 0.5112327933311462, "entropy": 0.7058702707290649, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:07.030828Z", "loop": 871, "env_steps": 535756799, "loss": 0.018005777150392532, "avg_return": 0.35180702805519104, "regret": 0.5112327933311462, "entropy": 0.705922544002533, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:07.884071Z", "loop": 872, "env_steps": 536371199, "loss": 0.01801300421357155, "avg_return": 0.3467366099357605, "regret": 0.5112327933311462, "entropy": 0.7057824730873108, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:08.737308Z", "loop": 873, "env_steps": 536985599, "loss": 0.019053669646382332, "avg_return": 0.35155579447746277, "regret": 0.5112327933311462, "entropy": 0.7053905129432678, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:09.589673Z", "loop": 874, "env_steps": 537599999, "loss": 0.017216265201568604, "avg_return": 0.3513578772544861, "regret": 0.5112327933311462, "entropy": 0.7052100896835327, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:10.483781Z", "loop": 875, "env_steps": 538214399, "loss": 0.017908407375216484, "avg_return": 0.35277876257896423, "regret": 0.5111501812934875, "entropy": 0.705064058303833, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:11.336850Z", "loop": 876, "env_steps": 538828799, "loss": 0.01659485138952732, "avg_return": 0.3417081832885742, "regret": 0.5111501812934875, "entropy": 0.7050423622131348, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:12.189381Z", "loop": 877, "env_steps": 539443199, "loss": 0.01820458471775055, "avg_return": 0.34984755516052246, "regret": 0.5111501812934875, "entropy": 0.7047520875930786, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:13.040957Z", "loop": 878, "env_steps": 540057599, "loss": 0.01787710003554821, "avg_return": 0.356673926115036, "regret": 0.5111501812934875, "entropy": 0.7044366598129272, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:13.893472Z", "loop": 879, "env_steps": 540671999, "loss": 0.01806643232703209, "avg_return": 0.3499053120613098, "regret": 0.5111501812934875, "entropy": 0.7036765813827515, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:14.786932Z", "loop": 880, "env_steps": 541286399, "loss": 0.018077438697218895, "avg_return": 0.34943151473999023, "regret": 0.5113006234169006, "entropy": 0.7028642296791077, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:15.640489Z", "loop": 881, "env_steps": 541900799, "loss": 0.018933739513158798, "avg_return": 0.35080093145370483, "regret": 0.5113006234169006, "entropy": 0.7017847895622253, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:16.494121Z", "loop": 882, "env_steps": 542515199, "loss": 0.016624078154563904, "avg_return": 0.3561113178730011, "regret": 0.5113006234169006, "entropy": 0.7011911273002625, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:17.347194Z", "loop": 883, "env_steps": 543129599, "loss": 0.018378324806690216, "avg_return": 0.3469582200050354, "regret": 0.5113006234169006, "entropy": 0.7004032135009766, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:18.200087Z", "loop": 884, "env_steps": 543743999, "loss": 0.018170474097132683, "avg_return": 0.34798499941825867, "regret": 0.5113006234169006, "entropy": 0.7004280686378479, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:19.092337Z", "loop": 885, "env_steps": 544358399, "loss": 0.018560921773314476, "avg_return": 0.3496894836425781, "regret": 0.5112848877906799, "entropy": 0.7015417814254761, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:19.944471Z", "loop": 886, "env_steps": 544972799, "loss": 0.017024865373969078, "avg_return": 0.3484475314617157, "regret": 0.5112848877906799, "entropy": 0.7027285695075989, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:20.796051Z", "loop": 887, "env_steps": 545587199, "loss": 0.01834968663752079, "avg_return": 0.3500920236110687, "regret": 0.5112848877906799, "entropy": 0.7030235528945923, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:21.649414Z", "loop": 888, "env_steps": 546201599, "loss": 0.018034612759947777, "avg_return": 0.3516930043697357, "regret": 0.5112848877906799, "entropy": 0.7031782865524292, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:22.502328Z", "loop": 889, "env_steps": 546815999, "loss": 0.018807286396622658, "avg_return": 0.35533156991004944, "regret": 0.5112848877906799, "entropy": 0.7025612592697144, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:23.393295Z", "loop": 890, "env_steps": 547430399, "loss": 0.018221385776996613, "avg_return": 0.35458284616470337, "regret": 0.511391818523407, "entropy": 0.7014791369438171, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:24.245023Z", "loop": 891, "env_steps": 548044799, "loss": 0.01789521984755993, "avg_return": 0.35066652297973633, "regret": 0.511391818523407, "entropy": 0.7000765204429626, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:25.099102Z", "loop": 892, "env_steps": 548659199, "loss": 0.01846117340028286, "avg_return": 0.35881438851356506, "regret": 0.511391818523407, "entropy": 0.6989081501960754, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:25.952380Z", "loop": 893, "env_steps": 549273599, "loss": 0.017787067219614983, "avg_return": 0.3484487533569336, "regret": 0.511391818523407, "entropy": 0.6996779441833496, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:26.804967Z", "loop": 894, "env_steps": 549887999, "loss": 0.017249567434191704, "avg_return": 0.3466995656490326, "regret": 0.511391818523407, "entropy": 0.700515866279602, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:27.694675Z", "loop": 895, "env_steps": 550502399, "loss": 0.018287431448698044, "avg_return": 0.35556739568710327, "regret": 0.5112015008926392, "entropy": 0.7015185952186584, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:28.546124Z", "loop": 896, "env_steps": 551116799, "loss": 0.01834755204617977, "avg_return": 0.3478837013244629, "regret": 0.5112015008926392, "entropy": 0.7028384208679199, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:29.398648Z", "loop": 897, "env_steps": 551731199, "loss": 0.016689840704202652, "avg_return": 0.3514312207698822, "regret": 0.5112015008926392, "entropy": 0.7031028866767883, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:30.250713Z", "loop": 898, "env_steps": 552345599, "loss": 0.018221616744995117, "avg_return": 0.3518153727054596, "regret": 0.5112015008926392, "entropy": 0.7026318311691284, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:31.103267Z", "loop": 899, "env_steps": 552959999, "loss": 0.018011555075645447, "avg_return": 0.3503352403640747, "regret": 0.5112015008926392, "entropy": 0.7013580203056335, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:31.996047Z", "loop": 900, "env_steps": 553574399, "loss": 0.018434224650263786, "avg_return": 0.35728296637535095, "regret": 0.5110328793525696, "entropy": 0.7005246877670288, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:32.848620Z", "loop": 901, "env_steps": 554188799, "loss": 0.01786017045378685, "avg_return": 0.35162580013275146, "regret": 0.5110328793525696, "entropy": 0.7002732157707214, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:33.701156Z", "loop": 902, "env_steps": 554803199, "loss": 0.01881667785346508, "avg_return": 0.35289642214775085, "regret": 0.5110328793525696, "entropy": 0.7005882263183594, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:34.553450Z", "loop": 903, "env_steps": 555417599, "loss": 0.017123907804489136, "avg_return": 0.3530077338218689, "regret": 0.5110328793525696, "entropy": 0.701179563999176, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:35.406249Z", "loop": 904, "env_steps": 556031999, "loss": 0.01732945814728737, "avg_return": 0.3508654832839966, "regret": 0.5110328793525696, "entropy": 0.7019410729408264, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:36.297504Z", "loop": 905, "env_steps": 556646399, "loss": 0.017182061448693275, "avg_return": 0.35084784030914307, "regret": 0.5104760527610779, "entropy": 0.7026475667953491, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:37.149169Z", "loop": 906, "env_steps": 557260799, "loss": 0.017412913963198662, "avg_return": 0.35268551111221313, "regret": 0.5104760527610779, "entropy": 0.7029491662979126, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:38.001456Z", "loop": 907, "env_steps": 557875199, "loss": 0.01850990764796734, "avg_return": 0.3553401231765747, "regret": 0.5104760527610779, "entropy": 0.702464759349823, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:38.854375Z", "loop": 908, "env_steps": 558489599, "loss": 0.01886584796011448, "avg_return": 0.3536573350429535, "regret": 0.5104760527610779, "entropy": 0.7009764909744263, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:39.707686Z", "loop": 909, "env_steps": 559103999, "loss": 0.017717299982905388, "avg_return": 0.35223260521888733, "regret": 0.5104760527610779, "entropy": 0.6981439590454102, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:40.595770Z", "loop": 910, "env_steps": 559718399, "loss": 0.017616553232073784, "avg_return": 0.348143994808197, "regret": 0.5118618011474609, "entropy": 0.6964136958122253, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:41.448410Z", "loop": 911, "env_steps": 560332799, "loss": 0.016905328258872032, "avg_return": 0.3474842309951782, "regret": 0.5118618011474609, "entropy": 0.6964318752288818, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:42.301699Z", "loop": 912, "env_steps": 560947199, "loss": 0.01933826319873333, "avg_return": 0.3556920289993286, "regret": 0.5118618011474609, "entropy": 0.6971944570541382, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:43.154963Z", "loop": 913, "env_steps": 561561599, "loss": 0.017732540145516396, "avg_return": 0.3471238613128662, "regret": 0.5118618011474609, "entropy": 0.6992607712745667, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:44.007703Z", "loop": 914, "env_steps": 562175999, "loss": 0.017036253586411476, "avg_return": 0.3464434742927551, "regret": 0.5118618011474609, "entropy": 0.7012441754341125, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:44.901104Z", "loop": 915, "env_steps": 562790399, "loss": 0.0164520051330328, "avg_return": 0.34580835700035095, "regret": 0.5102206468582153, "entropy": 0.7021457552909851, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:45.754329Z", "loop": 916, "env_steps": 563404799, "loss": 0.017805231735110283, "avg_return": 0.35460469126701355, "regret": 0.5102206468582153, "entropy": 0.7023805379867554, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:46.608521Z", "loop": 917, "env_steps": 564019199, "loss": 0.017066430300474167, "avg_return": 0.3454417586326599, "regret": 0.5102206468582153, "entropy": 0.7020865678787231, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:47.463146Z", "loop": 918, "env_steps": 564633599, "loss": 0.016874240711331367, "avg_return": 0.3501212000846863, "regret": 0.5102206468582153, "entropy": 0.7014267444610596, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:48.315914Z", "loop": 919, "env_steps": 565247999, "loss": 0.01745545119047165, "avg_return": 0.3525875508785248, "regret": 0.5102206468582153, "entropy": 0.7015154361724854, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:49.208460Z", "loop": 920, "env_steps": 565862399, "loss": 0.017372976988554, "avg_return": 0.3502766191959381, "regret": 0.5104870200157166, "entropy": 0.7014011740684509, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:50.062246Z", "loop": 921, "env_steps": 566476799, "loss": 0.01824815571308136, "avg_return": 0.35772472620010376, "regret": 0.5104870200157166, "entropy": 0.7018023729324341, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:50.915120Z", "loop": 922, "env_steps": 567091199, "loss": 0.018147660419344902, "avg_return": 0.35706034302711487, "regret": 0.5104870200157166, "entropy": 0.7022417783737183, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:51.767394Z", "loop": 923, "env_steps": 567705599, "loss": 0.016928015276789665, "avg_return": 0.3519669771194458, "regret": 0.5104870200157166, "entropy": 0.7027544975280762, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:52.620979Z", "loop": 924, "env_steps": 568319999, "loss": 0.017856420949101448, "avg_return": 0.3570573627948761, "regret": 0.5104870200157166, "entropy": 0.7030774354934692, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:53.516395Z", "loop": 925, "env_steps": 568934399, "loss": 0.01756501942873001, "avg_return": 0.3495550751686096, "regret": 0.5100512504577637, "entropy": 0.7025353312492371, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:54.370316Z", "loop": 926, "env_steps": 569548799, "loss": 0.019010838121175766, "avg_return": 0.3536754846572876, "regret": 0.5100512504577637, "entropy": 0.700697660446167, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:55.222911Z", "loop": 927, "env_steps": 570163199, "loss": 0.017585517838597298, "avg_return": 0.35496360063552856, "regret": 0.5100512504577637, "entropy": 0.6992757320404053, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:56.074335Z", "loop": 928, "env_steps": 570777599, "loss": 0.01607571355998516, "avg_return": 0.3487762212753296, "regret": 0.5100512504577637, "entropy": 0.6982203722000122, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:56.926506Z", "loop": 929, "env_steps": 571391999, "loss": 0.01600818522274494, "avg_return": 0.345665842294693, "regret": 0.5100512504577637, "entropy": 0.6982167959213257, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:57.820980Z", "loop": 930, "env_steps": 572006399, "loss": 0.017814232036471367, "avg_return": 0.35949641466140747, "regret": 0.5105313658714294, "entropy": 0.6990330219268799, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:58.674653Z", "loop": 931, "env_steps": 572620799, "loss": 0.01697765849530697, "avg_return": 0.3489204943180084, "regret": 0.5105313658714294, "entropy": 0.7003492116928101, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:36:59.527742Z", "loop": 932, "env_steps": 573235199, "loss": 0.017626795917749405, "avg_return": 0.35386282205581665, "regret": 0.5105313658714294, "entropy": 0.7014128565788269, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:00.380938Z", "loop": 933, "env_steps": 573849599, "loss": 0.01821155659854412, "avg_return": 0.3553202450275421, "regret": 0.5105313658714294, "entropy": 0.7021293640136719, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:01.235470Z", "loop": 934, "env_steps": 574463999, "loss": 0.01785231940448284, "avg_return": 0.3560042083263397, "regret": 0.5105313658714294, "entropy": 0.7023138999938965, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:02.131637Z", "loop": 935, "env_steps": 575078399, "loss": 0.016643105074763298, "avg_return": 0.35079076886177063, "regret": 0.5094947218894958, "entropy": 0.7019272446632385, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:02.984532Z", "loop": 936, "env_steps": 575692799, "loss": 0.018453791737556458, "avg_return": 0.35644400119781494, "regret": 0.5094947218894958, "entropy": 0.7012165188789368, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:03.836959Z", "loop": 937, "env_steps": 576307199, "loss": 0.016828013584017754, "avg_return": 0.3557276129722595, "regret": 0.5094947218894958, "entropy": 0.7002315521240234, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:04.691374Z", "loop": 938, "env_steps": 576921599, "loss": 0.017607171088457108, "avg_return": 0.3551371991634369, "regret": 0.5094947218894958, "entropy": 0.6997359395027161, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:05.544009Z", "loop": 939, "env_steps": 577535999, "loss": 0.017852455377578735, "avg_return": 0.3577147126197815, "regret": 0.5094947218894958, "entropy": 0.700175404548645, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:06.436581Z", "loop": 940, "env_steps": 578150399, "loss": 0.01807945966720581, "avg_return": 0.35320621728897095, "regret": 0.5091478228569031, "entropy": 0.7004433274269104, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:07.289690Z", "loop": 941, "env_steps": 578764799, "loss": 0.018658727407455444, "avg_return": 0.3616119921207428, "regret": 0.5091478228569031, "entropy": 0.7002478241920471, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:08.142850Z", "loop": 942, "env_steps": 579379199, "loss": 0.016640378162264824, "avg_return": 0.3494138717651367, "regret": 0.5091478228569031, "entropy": 0.6999383568763733, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:08.995941Z", "loop": 943, "env_steps": 579993599, "loss": 0.016537195071578026, "avg_return": 0.3560623228549957, "regret": 0.5091478228569031, "entropy": 0.6997206211090088, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:09.849786Z", "loop": 944, "env_steps": 580607999, "loss": 0.01746535114943981, "avg_return": 0.36446836590766907, "regret": 0.5091478228569031, "entropy": 0.6995511651039124, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:10.742552Z", "loop": 945, "env_steps": 581222399, "loss": 0.018183065578341484, "avg_return": 0.35749852657318115, "regret": 0.5088525414466858, "entropy": 0.6990755200386047, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:11.595211Z", "loop": 946, "env_steps": 581836799, "loss": 0.016352305188775063, "avg_return": 0.3549303710460663, "regret": 0.5088525414466858, "entropy": 0.6987926363945007, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:12.448678Z", "loop": 947, "env_steps": 582451199, "loss": 0.01862410455942154, "avg_return": 0.35382670164108276, "regret": 0.5088525414466858, "entropy": 0.6978564262390137, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:13.301153Z", "loop": 948, "env_steps": 583065599, "loss": 0.01764490082859993, "avg_return": 0.35522353649139404, "regret": 0.5088525414466858, "entropy": 0.6975093483924866, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:14.153862Z", "loop": 949, "env_steps": 583679999, "loss": 0.01701689325273037, "avg_return": 0.35624268651008606, "regret": 0.5088525414466858, "entropy": 0.6977493166923523, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:15.044318Z", "loop": 950, "env_steps": 584294399, "loss": 0.0175643227994442, "avg_return": 0.3584247827529907, "regret": 0.5088942646980286, "entropy": 0.697181761264801, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:15.896964Z", "loop": 951, "env_steps": 584908799, "loss": 0.017485998570919037, "avg_return": 0.3633517622947693, "regret": 0.5088942646980286, "entropy": 0.698263943195343, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:16.749096Z", "loop": 952, "env_steps": 585523199, "loss": 0.01794412173330784, "avg_return": 0.36169111728668213, "regret": 0.5088942646980286, "entropy": 0.6992729306221008, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:17.601724Z", "loop": 953, "env_steps": 586137599, "loss": 0.018399830907583237, "avg_return": 0.35742971301078796, "regret": 0.5088942646980286, "entropy": 0.6992233991622925, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:18.454536Z", "loop": 954, "env_steps": 586751999, "loss": 0.017139621078968048, "avg_return": 0.3534686267375946, "regret": 0.5088942646980286, "entropy": 0.6980709433555603, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:19.348467Z", "loop": 955, "env_steps": 587366399, "loss": 0.017459170892834663, "avg_return": 0.35906335711479187, "regret": 0.5084913969039917, "entropy": 0.6976916193962097, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:20.200459Z", "loop": 956, "env_steps": 587980799, "loss": 0.017532065510749817, "avg_return": 0.36282411217689514, "regret": 0.5084913969039917, "entropy": 0.6983601450920105, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:21.052996Z", "loop": 957, "env_steps": 588595199, "loss": 0.017416594550013542, "avg_return": 0.35011982917785645, "regret": 0.5084913969039917, "entropy": 0.6994233131408691, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:21.905590Z", "loop": 958, "env_steps": 589209599, "loss": 0.01796410046517849, "avg_return": 0.35625824332237244, "regret": 0.5084913969039917, "entropy": 0.6998673677444458, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:22.759709Z", "loop": 959, "env_steps": 589823999, "loss": 0.01798824779689312, "avg_return": 0.3575461506843567, "regret": 0.5084913969039917, "entropy": 0.6997924447059631, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:23.651746Z", "loop": 960, "env_steps": 590438399, "loss": 0.01887350343167782, "avg_return": 0.3592281639575958, "regret": 0.5075749158859253, "entropy": 0.6998787522315979, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:24.504526Z", "loop": 961, "env_steps": 591052799, "loss": 0.01605733297765255, "avg_return": 0.3522360324859619, "regret": 0.5075749158859253, "entropy": 0.6999342441558838, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:25.357615Z", "loop": 962, "env_steps": 591667199, "loss": 0.01641201786696911, "avg_return": 0.3502081632614136, "regret": 0.5075749158859253, "entropy": 0.6996985673904419, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:26.211053Z", "loop": 963, "env_steps": 592281599, "loss": 0.017948346212506294, "avg_return": 0.35590940713882446, "regret": 0.5075749158859253, "entropy": 0.6990497708320618, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:27.063793Z", "loop": 964, "env_steps": 592895999, "loss": 0.016687190160155296, "avg_return": 0.35742348432540894, "regret": 0.5075749158859253, "entropy": 0.6987112164497375, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:27.956474Z", "loop": 965, "env_steps": 593510399, "loss": 0.01749359630048275, "avg_return": 0.36348626017570496, "regret": 0.5072514414787292, "entropy": 0.6983067393302917, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:28.809913Z", "loop": 966, "env_steps": 594124799, "loss": 0.017205841839313507, "avg_return": 0.3534620404243469, "regret": 0.5072514414787292, "entropy": 0.6984360218048096, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:29.662559Z", "loop": 967, "env_steps": 594739199, "loss": 0.01760113798081875, "avg_return": 0.36023789644241333, "regret": 0.5072514414787292, "entropy": 0.6979689598083496, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:30.515240Z", "loop": 968, "env_steps": 595353599, "loss": 0.017296725884079933, "avg_return": 0.35801586508750916, "regret": 0.5072514414787292, "entropy": 0.6973711252212524, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:31.367177Z", "loop": 969, "env_steps": 595967999, "loss": 0.016744788736104965, "avg_return": 0.35309308767318726, "regret": 0.5072514414787292, "entropy": 0.6969033479690552, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:32.259771Z", "loop": 970, "env_steps": 596582399, "loss": 0.01599722169339657, "avg_return": 0.3531853258609772, "regret": 0.5064992308616638, "entropy": 0.6971877813339233, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:33.113015Z", "loop": 971, "env_steps": 597196799, "loss": 0.016880374401807785, "avg_return": 0.3517434895038605, "regret": 0.5064992308616638, "entropy": 0.6966670155525208, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:33.965478Z", "loop": 972, "env_steps": 597811199, "loss": 0.017612794414162636, "avg_return": 0.3567957282066345, "regret": 0.5064992308616638, "entropy": 0.6962816119194031, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:34.818967Z", "loop": 973, "env_steps": 598425599, "loss": 0.01833724044263363, "avg_return": 0.3566008508205414, "regret": 0.5064992308616638, "entropy": 0.695488691329956, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:35.671456Z", "loop": 974, "env_steps": 599039999, "loss": 0.01628006063401699, "avg_return": 0.3514558970928192, "regret": 0.5064992308616638, "entropy": 0.6953073143959045, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:36.562322Z", "loop": 975, "env_steps": 599654399, "loss": 0.018515577539801598, "avg_return": 0.3633981943130493, "regret": 0.5057995319366455, "entropy": 0.6947903633117676, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:37.414316Z", "loop": 976, "env_steps": 600268799, "loss": 0.01845507137477398, "avg_return": 0.36129507422447205, "regret": 0.5057995319366455, "entropy": 0.6934416890144348, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:38.266556Z", "loop": 977, "env_steps": 600883199, "loss": 0.01725739799439907, "avg_return": 0.359347403049469, "regret": 0.5057995319366455, "entropy": 0.6932395100593567, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:39.120175Z", "loop": 978, "env_steps": 601497599, "loss": 0.016441022977232933, "avg_return": 0.35486623644828796, "regret": 0.5057995319366455, "entropy": 0.6931617856025696, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:39.973205Z", "loop": 979, "env_steps": 602111999, "loss": 0.016763858497142792, "avg_return": 0.36124640703201294, "regret": 0.5057995319366455, "entropy": 0.692650556564331, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:40.866115Z", "loop": 980, "env_steps": 602726399, "loss": 0.01796196959912777, "avg_return": 0.3662988543510437, "regret": 0.5051319599151611, "entropy": 0.6909759640693665, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:41.719148Z", "loop": 981, "env_steps": 603340799, "loss": 0.01610703580081463, "avg_return": 0.35468026995658875, "regret": 0.5051319599151611, "entropy": 0.687095046043396, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:42.572758Z", "loop": 982, "env_steps": 603955199, "loss": 0.017064617946743965, "avg_return": 0.35826733708381653, "regret": 0.5051319599151611, "entropy": 0.6856383085250854, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:43.425187Z", "loop": 983, "env_steps": 604569599, "loss": 0.01709589920938015, "avg_return": 0.3569366931915283, "regret": 0.5051319599151611, "entropy": 0.6866351366043091, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:44.277189Z", "loop": 984, "env_steps": 605183999, "loss": 0.017010973766446114, "avg_return": 0.3569943308830261, "regret": 0.5051319599151611, "entropy": 0.6895303726196289, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:45.167990Z", "loop": 985, "env_steps": 605798399, "loss": 0.01705167628824711, "avg_return": 0.36150437593460083, "regret": 0.5042682886123657, "entropy": 0.6896640062332153, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:46.021508Z", "loop": 986, "env_steps": 606412799, "loss": 0.016444142907857895, "avg_return": 0.3552936911582947, "regret": 0.5042682886123657, "entropy": 0.6860654354095459, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:46.874203Z", "loop": 987, "env_steps": 607027199, "loss": 0.01642579399049282, "avg_return": 0.36755701899528503, "regret": 0.5042682886123657, "entropy": 0.6826940178871155, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:47.726662Z", "loop": 988, "env_steps": 607641599, "loss": 0.016213780269026756, "avg_return": 0.36411458253860474, "regret": 0.5042682886123657, "entropy": 0.6873866319656372, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:48.579053Z", "loop": 989, "env_steps": 608255999, "loss": 0.016260867938399315, "avg_return": 0.3630494475364685, "regret": 0.5042682886123657, "entropy": 0.6883563995361328, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:49.471216Z", "loop": 990, "env_steps": 608870399, "loss": 0.015458389185369015, "avg_return": 0.3535952568054199, "regret": 0.5031899809837341, "entropy": 0.6879298686981201, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:50.323675Z", "loop": 991, "env_steps": 609484799, "loss": 0.016681870445609093, "avg_return": 0.36924824118614197, "regret": 0.5031899809837341, "entropy": 0.6870207786560059, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:51.174975Z", "loop": 992, "env_steps": 610099199, "loss": 0.017970412969589233, "avg_return": 0.36473119258880615, "regret": 0.5031899809837341, "entropy": 0.6853584051132202, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:52.028351Z", "loop": 993, "env_steps": 610713599, "loss": 0.01693565584719181, "avg_return": 0.3600883185863495, "regret": 0.5031899809837341, "entropy": 0.6809946894645691, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:52.881194Z", "loop": 994, "env_steps": 611327999, "loss": 0.016409438103437424, "avg_return": 0.35938960313796997, "regret": 0.5031899809837341, "entropy": 0.674820601940155, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:53.771473Z", "loop": 995, "env_steps": 611942399, "loss": 0.01698841154575348, "avg_return": 0.35677415132522583, "regret": 0.5054590106010437, "entropy": 0.6685225367546082, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:54.623581Z", "loop": 996, "env_steps": 612556799, "loss": 0.016951031982898712, "avg_return": 0.35964637994766235, "regret": 0.5054590106010437, "entropy": 0.673444926738739, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:55.475924Z", "loop": 997, "env_steps": 613171199, "loss": 0.017007602378726006, "avg_return": 0.36571648716926575, "regret": 0.5054590106010437, "entropy": 0.6829627752304077, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:56.328917Z", "loop": 998, "env_steps": 613785599, "loss": 0.01640012301504612, "avg_return": 0.3562757074832916, "regret": 0.5054590106010437, "entropy": 0.6825180649757385, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:57.182220Z", "loop": 999, "env_steps": 614399999, "loss": 0.017260491847991943, "avg_return": 0.3619072735309601, "regret": 0.5054590106010437, "entropy": 0.673505425453186, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:58.073149Z", "loop": 1000, "env_steps": 615014399, "loss": 0.0183632243424654, "avg_return": 0.3634655475616455, "regret": 0.5049983859062195, "entropy": 0.6726162433624268, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:58.926259Z", "loop": 1001, "env_steps": 615628799, "loss": 0.016898732632398605, "avg_return": 0.364667683839798, "regret": 0.5049983859062195, "entropy": 0.67670738697052, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:37:59.778918Z", "loop": 1002, "env_steps": 616243199, "loss": 0.016616228967905045, "avg_return": 0.37114569544792175, "regret": 0.5049983859062195, "entropy": 0.6822832226753235, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:00.632008Z", "loop": 1003, "env_steps": 616857599, "loss": 0.014600815251469612, "avg_return": 0.35954728722572327, "regret": 0.5049983859062195, "entropy": 0.6816559433937073, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:01.484041Z", "loop": 1004, "env_steps": 617471999, "loss": 0.016140002757310867, "avg_return": 0.3624531030654907, "regret": 0.5049983859062195, "entropy": 0.6790987849235535, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:02.374171Z", "loop": 1005, "env_steps": 618086399, "loss": 0.015139671973884106, "avg_return": 0.3640277087688446, "regret": 0.5002162456512451, "entropy": 0.6785905361175537, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:03.226080Z", "loop": 1006, "env_steps": 618700799, "loss": 0.015821510925889015, "avg_return": 0.358289510011673, "regret": 0.5002162456512451, "entropy": 0.6785452961921692, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:04.077952Z", "loop": 1007, "env_steps": 619315199, "loss": 0.016147146001458168, "avg_return": 0.3693385124206543, "regret": 0.5002162456512451, "entropy": 0.6797147989273071, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:04.931129Z", "loop": 1008, "env_steps": 619929599, "loss": 0.015706077218055725, "avg_return": 0.36359867453575134, "regret": 0.5002162456512451, "entropy": 0.6795026659965515, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:05.784267Z", "loop": 1009, "env_steps": 620543999, "loss": 0.015890924260020256, "avg_return": 0.3669131398200989, "regret": 0.5002162456512451, "entropy": 0.6781497001647949, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:06.677246Z", "loop": 1010, "env_steps": 621158399, "loss": 0.01551852561533451, "avg_return": 0.3622293770313263, "regret": 0.49925607442855835, "entropy": 0.6774807572364807, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:07.530884Z", "loop": 1011, "env_steps": 621772799, "loss": 0.015241238288581371, "avg_return": 0.36826905608177185, "regret": 0.49925607442855835, "entropy": 0.6749885678291321, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:08.384871Z", "loop": 1012, "env_steps": 622387199, "loss": 0.014242710545659065, "avg_return": 0.36255279183387756, "regret": 0.49925607442855835, "entropy": 0.674826443195343, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:09.237124Z", "loop": 1013, "env_steps": 623001599, "loss": 0.015581727027893066, "avg_return": 0.3678934872150421, "regret": 0.49925607442855835, "entropy": 0.6717272996902466, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:10.090514Z", "loop": 1014, "env_steps": 623615999, "loss": 0.01523455698043108, "avg_return": 0.3604423999786377, "regret": 0.49925607442855835, "entropy": 0.6720647811889648, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:10.982114Z", "loop": 1015, "env_steps": 624230399, "loss": 0.014179821126163006, "avg_return": 0.36804336309432983, "regret": 0.4975379705429077, "entropy": 0.672620952129364, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:11.834259Z", "loop": 1016, "env_steps": 624844799, "loss": 0.015554000623524189, "avg_return": 0.360601544380188, "regret": 0.4975379705429077, "entropy": 0.6713061332702637, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:12.687437Z", "loop": 1017, "env_steps": 625459199, "loss": 0.01486574299633503, "avg_return": 0.36474308371543884, "regret": 0.4975379705429077, "entropy": 0.6660656332969666, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:13.540577Z", "loop": 1018, "env_steps": 626073599, "loss": 0.016157515347003937, "avg_return": 0.36837300658226013, "regret": 0.4975379705429077, "entropy": 0.6590784192085266, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:14.393053Z", "loop": 1019, "env_steps": 626687999, "loss": 0.01532340981066227, "avg_return": 0.36313971877098083, "regret": 0.4975379705429077, "entropy": 0.6575074791908264, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:15.284478Z", "loop": 1020, "env_steps": 627302399, "loss": 0.01424507237970829, "avg_return": 0.36319246888160706, "regret": 0.49549487233161926, "entropy": 0.6614359617233276, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:16.136682Z", "loop": 1021, "env_steps": 627916799, "loss": 0.015716195106506348, "avg_return": 0.36935335397720337, "regret": 0.49549487233161926, "entropy": 0.663642942905426, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:16.990228Z", "loop": 1022, "env_steps": 628531199, "loss": 0.014065228402614594, "avg_return": 0.36999475955963135, "regret": 0.49549487233161926, "entropy": 0.664103627204895, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:17.843382Z", "loop": 1023, "env_steps": 629145599, "loss": 0.015510882250964642, "avg_return": 0.372039794921875, "regret": 0.49549487233161926, "entropy": 0.662582278251648, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:18.696423Z", "loop": 1024, "env_steps": 629759999, "loss": 0.015055129304528236, "avg_return": 0.3769158124923706, "regret": 0.49549487233161926, "entropy": 0.6580522060394287, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:19.588674Z", "loop": 1025, "env_steps": 630374399, "loss": 0.015040993690490723, "avg_return": 0.3673511743545532, "regret": 0.4948245882987976, "entropy": 0.6581062078475952, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:20.441911Z", "loop": 1026, "env_steps": 630988799, "loss": 0.014150666072964668, "avg_return": 0.3663557171821594, "regret": 0.4948245882987976, "entropy": 0.6577618718147278, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:21.296012Z", "loop": 1027, "env_steps": 631603199, "loss": 0.014545544981956482, "avg_return": 0.376686155796051, "regret": 0.4948245882987976, "entropy": 0.6536645889282227, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:22.149368Z", "loop": 1028, "env_steps": 632217599, "loss": 0.01499982364475727, "avg_return": 0.37055522203445435, "regret": 0.4948245882987976, "entropy": 0.6474540829658508, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:23.001100Z", "loop": 1029, "env_steps": 632831999, "loss": 0.014872622676193714, "avg_return": 0.3629431128501892, "regret": 0.4948245882987976, "entropy": 0.637179970741272, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:23.892070Z", "loop": 1030, "env_steps": 633446399, "loss": 0.014549687504768372, "avg_return": 0.37660446763038635, "regret": 0.49407219886779785, "entropy": 0.6224585771560669, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:24.745325Z", "loop": 1031, "env_steps": 634060799, "loss": 0.014799890108406544, "avg_return": 0.3665190041065216, "regret": 0.49407219886779785, "entropy": 0.6186227202415466, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:25.599795Z", "loop": 1032, "env_steps": 634675199, "loss": 0.014748099260032177, "avg_return": 0.36914685368537903, "regret": 0.49407219886779785, "entropy": 0.6242721676826477, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:26.452346Z", "loop": 1033, "env_steps": 635289599, "loss": 0.014006062410771847, "avg_return": 0.3747410476207733, "regret": 0.49407219886779785, "entropy": 0.6258049607276917, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:27.305799Z", "loop": 1034, "env_steps": 635903999, "loss": 0.01403716392815113, "avg_return": 0.37512287497520447, "regret": 0.49407219886779785, "entropy": 0.6288038492202759, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:28.199890Z", "loop": 1035, "env_steps": 636518399, "loss": 0.013356474228203297, "avg_return": 0.37311509251594543, "regret": 0.4888680875301361, "entropy": 0.6315444111824036, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:29.053275Z", "loop": 1036, "env_steps": 637132799, "loss": 0.014588828198611736, "avg_return": 0.37820935249328613, "regret": 0.4888680875301361, "entropy": 0.6270172595977783, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:29.905977Z", "loop": 1037, "env_steps": 637747199, "loss": 0.013132721185684204, "avg_return": 0.36080923676490784, "regret": 0.4888680875301361, "entropy": 0.6196199059486389, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:30.756958Z", "loop": 1038, "env_steps": 638361599, "loss": 0.013263093307614326, "avg_return": 0.3661994934082031, "regret": 0.4888680875301361, "entropy": 0.6137524843215942, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:31.607537Z", "loop": 1039, "env_steps": 638975999, "loss": 0.013231204822659492, "avg_return": 0.3647180199623108, "regret": 0.4888680875301361, "entropy": 0.6147720217704773, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:32.499999Z", "loop": 1040, "env_steps": 639590399, "loss": 0.014189191162586212, "avg_return": 0.38408714532852173, "regret": 0.4881541430950165, "entropy": 0.6140559315681458, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:33.353063Z", "loop": 1041, "env_steps": 640204799, "loss": 0.012842855416238308, "avg_return": 0.3772125542163849, "regret": 0.4881541430950165, "entropy": 0.6064924001693726, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:34.205204Z", "loop": 1042, "env_steps": 640819199, "loss": 0.01318624522536993, "avg_return": 0.3854476511478424, "regret": 0.4881541430950165, "entropy": 0.5891528725624084, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:35.056775Z", "loop": 1043, "env_steps": 641433599, "loss": 0.014251706190407276, "avg_return": 0.37191763520240784, "regret": 0.4881541430950165, "entropy": 0.5785074830055237, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:35.908395Z", "loop": 1044, "env_steps": 642047999, "loss": 0.013259208761155605, "avg_return": 0.383139967918396, "regret": 0.4881541430950165, "entropy": 0.5823245644569397, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:36.799716Z", "loop": 1045, "env_steps": 642662399, "loss": 0.01223671156913042, "avg_return": 0.3837070167064667, "regret": 0.4827159643173218, "entropy": 0.5882631540298462, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:37.652048Z", "loop": 1046, "env_steps": 643276799, "loss": 0.01248044054955244, "avg_return": 0.385965496301651, "regret": 0.4827159643173218, "entropy": 0.592889666557312, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:38.504755Z", "loop": 1047, "env_steps": 643891199, "loss": 0.011640596203505993, "avg_return": 0.3743545711040497, "regret": 0.4827159643173218, "entropy": 0.5914796590805054, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:39.356724Z", "loop": 1048, "env_steps": 644505599, "loss": 0.012644504196941853, "avg_return": 0.3901057541370392, "regret": 0.4827159643173218, "entropy": 0.5808870196342468, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:40.209074Z", "loop": 1049, "env_steps": 645119999, "loss": 0.012103237211704254, "avg_return": 0.3820822834968567, "regret": 0.4827159643173218, "entropy": 0.5727710127830505, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:41.101541Z", "loop": 1050, "env_steps": 645734399, "loss": 0.01372173149138689, "avg_return": 0.3873206079006195, "regret": 0.48082026839256287, "entropy": 0.5533917546272278, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:41.954213Z", "loop": 1051, "env_steps": 646348799, "loss": 0.013792941346764565, "avg_return": 0.38019055128097534, "regret": 0.48082026839256287, "entropy": 0.5282054543495178, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:42.806052Z", "loop": 1052, "env_steps": 646963199, "loss": 0.013667464256286621, "avg_return": 0.3802891969680786, "regret": 0.48082026839256287, "entropy": 0.5263552069664001, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:43.658171Z", "loop": 1053, "env_steps": 647577599, "loss": 0.013186666183173656, "avg_return": 0.3835252821445465, "regret": 0.48082026839256287, "entropy": 0.52329421043396, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:44.510922Z", "loop": 1054, "env_steps": 648191999, "loss": 0.012177767232060432, "avg_return": 0.38674917817115784, "regret": 0.48082026839256287, "entropy": 0.5346847176551819, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:45.402860Z", "loop": 1055, "env_steps": 648806399, "loss": 0.010648253373801708, "avg_return": 0.37898096442222595, "regret": 0.47760388255119324, "entropy": 0.5472986102104187, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:46.255339Z", "loop": 1056, "env_steps": 649420799, "loss": 0.011668902821838856, "avg_return": 0.3865141272544861, "regret": 0.47760388255119324, "entropy": 0.5530503988265991, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:47.107510Z", "loop": 1057, "env_steps": 650035199, "loss": 0.01114947535097599, "avg_return": 0.38785457611083984, "regret": 0.47760388255119324, "entropy": 0.5481155514717102, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:47.960274Z", "loop": 1058, "env_steps": 650649599, "loss": 0.011089101433753967, "avg_return": 0.38095560669898987, "regret": 0.47760388255119324, "entropy": 0.5419489145278931, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:48.812917Z", "loop": 1059, "env_steps": 651263999, "loss": 0.012136644683778286, "avg_return": 0.38763511180877686, "regret": 0.47760388255119324, "entropy": 0.5394458174705505, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:49.705567Z", "loop": 1060, "env_steps": 651878399, "loss": 0.011589924804866314, "avg_return": 0.3855380117893219, "regret": 0.48478469252586365, "entropy": 0.5428258180618286, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:50.558822Z", "loop": 1061, "env_steps": 652492799, "loss": 0.010090158320963383, "avg_return": 0.3756999671459198, "regret": 0.48478469252586365, "entropy": 0.538236141204834, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:51.410968Z", "loop": 1062, "env_steps": 653107199, "loss": 0.01012460794299841, "avg_return": 0.3855648338794708, "regret": 0.48478469252586365, "entropy": 0.526907205581665, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:52.264060Z", "loop": 1063, "env_steps": 653721599, "loss": 0.010547545738518238, "avg_return": 0.39135390520095825, "regret": 0.48478469252586365, "entropy": 0.5020862817764282, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:53.115988Z", "loop": 1064, "env_steps": 654335999, "loss": 0.01179580669850111, "avg_return": 0.3884134590625763, "regret": 0.48478469252586365, "entropy": 0.48343420028686523, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:54.008688Z", "loop": 1065, "env_steps": 654950399, "loss": 0.012587365694344044, "avg_return": 0.38707485795021057, "regret": 0.47513115406036377, "entropy": 0.46984243392944336, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:54.862224Z", "loop": 1066, "env_steps": 655564799, "loss": 0.011226058006286621, "avg_return": 0.39293181896209717, "regret": 0.47513115406036377, "entropy": 0.47229161858558655, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:55.715796Z", "loop": 1067, "env_steps": 656179199, "loss": 0.011412139050662518, "avg_return": 0.39164429903030396, "regret": 0.47513115406036377, "entropy": 0.47456175088882446, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:56.568120Z", "loop": 1068, "env_steps": 656793599, "loss": 0.010293792001903057, "avg_return": 0.3993261754512787, "regret": 0.47513115406036377, "entropy": 0.4902240037918091, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:57.420855Z", "loop": 1069, "env_steps": 657407999, "loss": 0.010638422332704067, "avg_return": 0.39650192856788635, "regret": 0.47513115406036377, "entropy": 0.4884916841983795, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:58.312587Z", "loop": 1070, "env_steps": 658022399, "loss": 0.010157874785363674, "avg_return": 0.3986068367958069, "regret": 0.4708334505558014, "entropy": 0.4853825569152832, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:38:59.165712Z", "loop": 1071, "env_steps": 658636799, "loss": 0.009601733647286892, "avg_return": 0.390071839094162, "regret": 0.4708334505558014, "entropy": 0.47751110792160034, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:00.018050Z", "loop": 1072, "env_steps": 659251199, "loss": 0.009444471448659897, "avg_return": 0.38969361782073975, "regret": 0.4708334505558014, "entropy": 0.48133283853530884, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:00.870785Z", "loop": 1073, "env_steps": 659865599, "loss": 0.009691434912383556, "avg_return": 0.3920455574989319, "regret": 0.4708334505558014, "entropy": 0.4765586853027344, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:01.722828Z", "loop": 1074, "env_steps": 660479999, "loss": 0.009503687731921673, "avg_return": 0.39042970538139343, "regret": 0.4708334505558014, "entropy": 0.46717676520347595, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:02.615443Z", "loop": 1075, "env_steps": 661094399, "loss": 0.009670918807387352, "avg_return": 0.3967854380607605, "regret": 0.46639469265937805, "entropy": 0.45991843938827515, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:03.468325Z", "loop": 1076, "env_steps": 661708799, "loss": 0.010309113189578056, "avg_return": 0.39887359738349915, "regret": 0.46639469265937805, "entropy": 0.45371851325035095, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:04.321463Z", "loop": 1077, "env_steps": 662323199, "loss": 0.010345046408474445, "avg_return": 0.3977292478084564, "regret": 0.46639469265937805, "entropy": 0.4329080283641815, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:05.173850Z", "loop": 1078, "env_steps": 662937599, "loss": 0.011280848644673824, "avg_return": 0.4022553563117981, "regret": 0.46639469265937805, "entropy": 0.43705856800079346, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:06.026858Z", "loop": 1079, "env_steps": 663551999, "loss": 0.009797775186598301, "avg_return": 0.39725813269615173, "regret": 0.46639469265937805, "entropy": 0.4393475651741028, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:06.918242Z", "loop": 1080, "env_steps": 664166399, "loss": 0.008955356664955616, "avg_return": 0.39664390683174133, "regret": 0.46331384778022766, "entropy": 0.4400632381439209, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:07.771200Z", "loop": 1081, "env_steps": 664780799, "loss": 0.009731515310704708, "avg_return": 0.3979526162147522, "regret": 0.46331384778022766, "entropy": 0.441382497549057, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:08.624232Z", "loop": 1082, "env_steps": 665395199, "loss": 0.010103496722877026, "avg_return": 0.3959759473800659, "regret": 0.46331384778022766, "entropy": 0.4361639618873596, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:09.477152Z", "loop": 1083, "env_steps": 666009599, "loss": 0.0093552740290761, "avg_return": 0.4045141637325287, "regret": 0.46331384778022766, "entropy": 0.42933332920074463, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:10.328729Z", "loop": 1084, "env_steps": 666623999, "loss": 0.010485885664820671, "avg_return": 0.41418540477752686, "regret": 0.46331384778022766, "entropy": 0.427592933177948, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:11.220813Z", "loop": 1085, "env_steps": 667238399, "loss": 0.009503597393631935, "avg_return": 0.39774850010871887, "regret": 0.4600282907485962, "entropy": 0.42907533049583435, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:12.073674Z", "loop": 1086, "env_steps": 667852799, "loss": 0.009181474335491657, "avg_return": 0.4105836749076843, "regret": 0.4600282907485962, "entropy": 0.4264257550239563, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:12.926827Z", "loop": 1087, "env_steps": 668467199, "loss": 0.00891843531280756, "avg_return": 0.3995125889778137, "regret": 0.4600282907485962, "entropy": 0.4299007058143616, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:13.779524Z", "loop": 1088, "env_steps": 669081599, "loss": 0.009115239605307579, "avg_return": 0.40469393134117126, "regret": 0.4600282907485962, "entropy": 0.4273195266723633, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:14.632244Z", "loop": 1089, "env_steps": 669695999, "loss": 0.00883086770772934, "avg_return": 0.40071314573287964, "regret": 0.4600282907485962, "entropy": 0.42583638429641724, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:15.525518Z", "loop": 1090, "env_steps": 670310399, "loss": 0.009234333410859108, "avg_return": 0.40635502338409424, "regret": 0.4580090045928955, "entropy": 0.4266248345375061, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:16.378677Z", "loop": 1091, "env_steps": 670924799, "loss": 0.009573572315275669, "avg_return": 0.4101931154727936, "regret": 0.4580090045928955, "entropy": 0.424441933631897, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:17.231325Z", "loop": 1092, "env_steps": 671539199, "loss": 0.009359156712889671, "avg_return": 0.4074054956436157, "regret": 0.4580090045928955, "entropy": 0.411915123462677, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:18.082697Z", "loop": 1093, "env_steps": 672153599, "loss": 0.0104295639321208, "avg_return": 0.41589751839637756, "regret": 0.4580090045928955, "entropy": 0.4126996695995331, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:18.934269Z", "loop": 1094, "env_steps": 672767999, "loss": 0.010346857830882072, "avg_return": 0.4032535254955292, "regret": 0.4580090045928955, "entropy": 0.40578439831733704, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:19.828030Z", "loop": 1095, "env_steps": 673382399, "loss": 0.010768280364573002, "avg_return": 0.40349289774894714, "regret": 0.45546093583106995, "entropy": 0.39946624636650085, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:20.681639Z", "loop": 1096, "env_steps": 673996799, "loss": 0.011556643061339855, "avg_return": 0.4107780158519745, "regret": 0.45546093583106995, "entropy": 0.41125279664993286, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:21.534032Z", "loop": 1097, "env_steps": 674611199, "loss": 0.009629135020077229, "avg_return": 0.4064271152019501, "regret": 0.45546093583106995, "entropy": 0.4274609684944153, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:22.386868Z", "loop": 1098, "env_steps": 675225599, "loss": 0.009225758723914623, "avg_return": 0.4112556278705597, "regret": 0.45546093583106995, "entropy": 0.44530990719795227, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:23.239671Z", "loop": 1099, "env_steps": 675839999, "loss": 0.008723277598619461, "avg_return": 0.4082348644733429, "regret": 0.45546093583106995, "entropy": 0.4590022563934326, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:24.132177Z", "loop": 1100, "env_steps": 676454399, "loss": 0.009408107958734035, "avg_return": 0.41445791721343994, "regret": 0.45774930715560913, "entropy": 0.4528162181377411, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:24.984556Z", "loop": 1101, "env_steps": 677068799, "loss": 0.009011692367494106, "avg_return": 0.4031035006046295, "regret": 0.45774930715560913, "entropy": 0.4421437084674835, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:25.837332Z", "loop": 1102, "env_steps": 677683199, "loss": 0.009514774195849895, "avg_return": 0.41514986753463745, "regret": 0.45774930715560913, "entropy": 0.41930004954338074, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:26.695264Z", "loop": 1103, "env_steps": 678297599, "loss": 0.010592175647616386, "avg_return": 0.4207513928413391, "regret": 0.45774930715560913, "entropy": 0.41109466552734375, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:27.548388Z", "loop": 1104, "env_steps": 678911999, "loss": 0.010865873657166958, "avg_return": 0.4141542315483093, "regret": 0.45774930715560913, "entropy": 0.40125879645347595, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:28.440785Z", "loop": 1105, "env_steps": 679526399, "loss": 0.011093945242464542, "avg_return": 0.41777345538139343, "regret": 0.4500609040260315, "entropy": 0.39438286423683167, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:29.293911Z", "loop": 1106, "env_steps": 680140799, "loss": 0.010208279825747013, "avg_return": 0.4073902368545532, "regret": 0.4500609040260315, "entropy": 0.3887607157230377, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:30.146720Z", "loop": 1107, "env_steps": 680755199, "loss": 0.009662712924182415, "avg_return": 0.4096696078777313, "regret": 0.4500609040260315, "entropy": 0.39595988392829895, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:30.999347Z", "loop": 1108, "env_steps": 681369599, "loss": 0.009920429438352585, "avg_return": 0.4233604967594147, "regret": 0.4500609040260315, "entropy": 0.3990973234176636, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:31.852254Z", "loop": 1109, "env_steps": 681983999, "loss": 0.01014978438615799, "avg_return": 0.41761744022369385, "regret": 0.4500609040260315, "entropy": 0.40872466564178467, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:32.743847Z", "loop": 1110, "env_steps": 682598399, "loss": 0.009209557436406612, "avg_return": 0.42537426948547363, "regret": 0.4436831772327423, "entropy": 0.41082701086997986, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:33.596987Z", "loop": 1111, "env_steps": 683212799, "loss": 0.00938620325177908, "avg_return": 0.41487494111061096, "regret": 0.4436831772327423, "entropy": 0.41427478194236755, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:34.449999Z", "loop": 1112, "env_steps": 683827199, "loss": 0.009075219742953777, "avg_return": 0.4194255471229553, "regret": 0.4436831772327423, "entropy": 0.4175014793872833, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:35.302527Z", "loop": 1113, "env_steps": 684441599, "loss": 0.010357587598264217, "avg_return": 0.43544507026672363, "regret": 0.4436831772327423, "entropy": 0.4088152050971985, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:36.155473Z", "loop": 1114, "env_steps": 685055999, "loss": 0.009493785910308361, "avg_return": 0.4229183793067932, "regret": 0.4436831772327423, "entropy": 0.38836076855659485, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:37.048736Z", "loop": 1115, "env_steps": 685670399, "loss": 0.010779832489788532, "avg_return": 0.42411479353904724, "regret": 0.4393584728240967, "entropy": 0.3895244300365448, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:37.900483Z", "loop": 1116, "env_steps": 686284799, "loss": 0.009791064076125622, "avg_return": 0.4285420775413513, "regret": 0.4393584728240967, "entropy": 0.39000940322875977, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:38.752001Z", "loop": 1117, "env_steps": 686899199, "loss": 0.010809198953211308, "avg_return": 0.43130606412887573, "regret": 0.4393584728240967, "entropy": 0.40015318989753723, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:39.604807Z", "loop": 1118, "env_steps": 687513599, "loss": 0.0097563611343503, "avg_return": 0.42380672693252563, "regret": 0.4393584728240967, "entropy": 0.40514159202575684, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:40.457301Z", "loop": 1119, "env_steps": 688127999, "loss": 0.008952489122748375, "avg_return": 0.418727308511734, "regret": 0.4393584728240967, "entropy": 0.42469725012779236, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:41.352329Z", "loop": 1120, "env_steps": 688742399, "loss": 0.009191783145070076, "avg_return": 0.42145535349845886, "regret": 0.4386187195777893, "entropy": 0.4170675575733185, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:42.204684Z", "loop": 1121, "env_steps": 689356799, "loss": 0.009052962996065617, "avg_return": 0.4198070466518402, "regret": 0.4386187195777893, "entropy": 0.40893715620040894, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:43.057208Z", "loop": 1122, "env_steps": 689971199, "loss": 0.00955438893288374, "avg_return": 0.4299964904785156, "regret": 0.4386187195777893, "entropy": 0.379006028175354, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:43.910595Z", "loop": 1123, "env_steps": 690585599, "loss": 0.009703320451080799, "avg_return": 0.42446696758270264, "regret": 0.4386187195777893, "entropy": 0.35527217388153076, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:44.764129Z", "loop": 1124, "env_steps": 691199999, "loss": 0.010097558610141277, "avg_return": 0.4273117184638977, "regret": 0.4386187195777893, "entropy": 0.353447288274765, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:45.657051Z", "loop": 1125, "env_steps": 691814399, "loss": 0.010081581771373749, "avg_return": 0.4391818344593048, "regret": 0.42973679304122925, "entropy": 0.3647194504737854, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:46.509265Z", "loop": 1126, "env_steps": 692428799, "loss": 0.009460601024329662, "avg_return": 0.42993977665901184, "regret": 0.42973679304122925, "entropy": 0.3846028745174408, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:47.361847Z", "loop": 1127, "env_steps": 693043199, "loss": 0.009998966008424759, "avg_return": 0.4377813935279846, "regret": 0.42973679304122925, "entropy": 0.37433937191963196, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:48.215834Z", "loop": 1128, "env_steps": 693657599, "loss": 0.009770077653229237, "avg_return": 0.4397094249725342, "regret": 0.42973679304122925, "entropy": 0.3683604896068573, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:49.069242Z", "loop": 1129, "env_steps": 694271999, "loss": 0.0100815799087286, "avg_return": 0.44333353638648987, "regret": 0.42973679304122925, "entropy": 0.35520032048225403, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:49.962496Z", "loop": 1130, "env_steps": 694886399, "loss": 0.009342615492641926, "avg_return": 0.4370708465576172, "regret": 0.4254923164844513, "entropy": 0.3501467704772949, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:50.814482Z", "loop": 1131, "env_steps": 695500799, "loss": 0.009560986422002316, "avg_return": 0.437661349773407, "regret": 0.4254923164844513, "entropy": 0.34064415097236633, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:51.667590Z", "loop": 1132, "env_steps": 696115199, "loss": 0.009219189174473286, "avg_return": 0.44387155771255493, "regret": 0.4254923164844513, "entropy": 0.3593732714653015, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:52.521260Z", "loop": 1133, "env_steps": 696729599, "loss": 0.008991651237010956, "avg_return": 0.4375058114528656, "regret": 0.4254923164844513, "entropy": 0.3833646774291992, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:53.373613Z", "loop": 1134, "env_steps": 697343999, "loss": 0.0084787392988801, "avg_return": 0.4351729452610016, "regret": 0.4254923164844513, "entropy": 0.3920826017856598, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:54.268473Z", "loop": 1135, "env_steps": 697958399, "loss": 0.008732540532946587, "avg_return": 0.4361194968223572, "regret": 0.4229501187801361, "entropy": 0.381973534822464, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:55.121435Z", "loop": 1136, "env_steps": 698572799, "loss": 0.00884561613202095, "avg_return": 0.4396389424800873, "regret": 0.4229501187801361, "entropy": 0.3516123592853546, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:55.974936Z", "loop": 1137, "env_steps": 699187199, "loss": 0.010665327310562134, "avg_return": 0.44535091519355774, "regret": 0.4229501187801361, "entropy": 0.3270145654678345, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:56.828463Z", "loop": 1138, "env_steps": 699801599, "loss": 0.009900946170091629, "avg_return": 0.4370708465576172, "regret": 0.4229501187801361, "entropy": 0.31192728877067566, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:57.680908Z", "loop": 1139, "env_steps": 700415999, "loss": 0.00963734369724989, "avg_return": 0.4375338852405548, "regret": 0.4229501187801361, "entropy": 0.3114202618598938, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:58.573624Z", "loop": 1140, "env_steps": 701030399, "loss": 0.009583658538758755, "avg_return": 0.44429129362106323, "regret": 0.41623055934906006, "entropy": 0.3298459053039551, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:39:59.427275Z", "loop": 1141, "env_steps": 701644799, "loss": 0.009838931262493134, "avg_return": 0.4466824531555176, "regret": 0.41623055934906006, "entropy": 0.3649939298629761, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:00.280865Z", "loop": 1142, "env_steps": 702259199, "loss": 0.008855458348989487, "avg_return": 0.43963679671287537, "regret": 0.41623055934906006, "entropy": 0.3910038471221924, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:01.134054Z", "loop": 1143, "env_steps": 702873599, "loss": 0.00881238654255867, "avg_return": 0.44116729497909546, "regret": 0.41623055934906006, "entropy": 0.40115439891815186, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:01.987733Z", "loop": 1144, "env_steps": 703487999, "loss": 0.009586814790964127, "avg_return": 0.45304229855537415, "regret": 0.41623055934906006, "entropy": 0.3879252076148987, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:02.883099Z", "loop": 1145, "env_steps": 704102399, "loss": 0.008934961631894112, "avg_return": 0.44896647334098816, "regret": 0.41084223985671997, "entropy": 0.34598198533058167, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:03.740589Z", "loop": 1146, "env_steps": 704716799, "loss": 0.008745701052248478, "avg_return": 0.4457910656929016, "regret": 0.41084223985671997, "entropy": 0.31219619512557983, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:04.593698Z", "loop": 1147, "env_steps": 705331199, "loss": 0.009237430989742279, "avg_return": 0.4411894977092743, "regret": 0.41084223985671997, "entropy": 0.29816609621047974, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:05.446171Z", "loop": 1148, "env_steps": 705945599, "loss": 0.009158345870673656, "avg_return": 0.45402878522872925, "regret": 0.41084223985671997, "entropy": 0.30364933609962463, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:06.300004Z", "loop": 1149, "env_steps": 706559999, "loss": 0.008245016448199749, "avg_return": 0.45907527208328247, "regret": 0.41084223985671997, "entropy": 0.33340007066726685, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:07.193478Z", "loop": 1150, "env_steps": 707174399, "loss": 0.008229202590882778, "avg_return": 0.4515092670917511, "regret": 0.40777888894081116, "entropy": 0.3473741412162781, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:08.046690Z", "loop": 1151, "env_steps": 707788799, "loss": 0.008053846657276154, "avg_return": 0.45238983631134033, "regret": 0.40777888894081116, "entropy": 0.3735615611076355, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:08.899454Z", "loop": 1152, "env_steps": 708403199, "loss": 0.008662370964884758, "avg_return": 0.449717253446579, "regret": 0.40777888894081116, "entropy": 0.37559080123901367, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:09.752525Z", "loop": 1153, "env_steps": 709017599, "loss": 0.008758931420743465, "avg_return": 0.45921590924263, "regret": 0.40777888894081116, "entropy": 0.3612743318080902, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:10.605131Z", "loop": 1154, "env_steps": 709631999, "loss": 0.008073493838310242, "avg_return": 0.4520386755466461, "regret": 0.40777888894081116, "entropy": 0.34560805559158325, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:11.497606Z", "loop": 1155, "env_steps": 710246399, "loss": 0.009023199789226055, "avg_return": 0.45794403553009033, "regret": 0.40404102206230164, "entropy": 0.3116147518157959, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:12.350639Z", "loop": 1156, "env_steps": 710860799, "loss": 0.008655700832605362, "avg_return": 0.4613073766231537, "regret": 0.40404102206230164, "entropy": 0.2832028269767761, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:13.205185Z", "loop": 1157, "env_steps": 711475199, "loss": 0.008081275038421154, "avg_return": 0.45284369587898254, "regret": 0.40404102206230164, "entropy": 0.2660839557647705, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:14.058730Z", "loop": 1158, "env_steps": 712089599, "loss": 0.008049708791077137, "avg_return": 0.4541417062282562, "regret": 0.40404102206230164, "entropy": 0.2741087079048157, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:14.912101Z", "loop": 1159, "env_steps": 712703999, "loss": 0.0076613533310592175, "avg_return": 0.4605569541454315, "regret": 0.40404102206230164, "entropy": 0.31639984250068665, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:15.808478Z", "loop": 1160, "env_steps": 713318399, "loss": 0.008030707016587257, "avg_return": 0.4618366062641144, "regret": 0.40524888038635254, "entropy": 0.3641955554485321, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:16.662275Z", "loop": 1161, "env_steps": 713932799, "loss": 0.008528697304427624, "avg_return": 0.4477144479751587, "regret": 0.40524888038635254, "entropy": 0.37960201501846313, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:17.514383Z", "loop": 1162, "env_steps": 714547199, "loss": 0.008595823310315609, "avg_return": 0.4455687701702118, "regret": 0.40524888038635254, "entropy": 0.3800099194049835, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:18.367138Z", "loop": 1163, "env_steps": 715161599, "loss": 0.008180154487490654, "avg_return": 0.4635160565376282, "regret": 0.40524888038635254, "entropy": 0.3718673884868622, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:19.220693Z", "loop": 1164, "env_steps": 715775999, "loss": 0.0081096813082695, "avg_return": 0.4653675854206085, "regret": 0.40524888038635254, "entropy": 0.3397902846336365, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:20.113929Z", "loop": 1165, "env_steps": 716390399, "loss": 0.00712154945358634, "avg_return": 0.4696977734565735, "regret": 0.3992868661880493, "entropy": 0.3034566342830658, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:20.966439Z", "loop": 1166, "env_steps": 717004799, "loss": 0.007372660096734762, "avg_return": 0.46332478523254395, "regret": 0.3992868661880493, "entropy": 0.2866576015949249, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:21.820269Z", "loop": 1167, "env_steps": 717619199, "loss": 0.006742515601217747, "avg_return": 0.4607235789299011, "regret": 0.3992868661880493, "entropy": 0.26743587851524353, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:22.673650Z", "loop": 1168, "env_steps": 718233599, "loss": 0.006744903512299061, "avg_return": 0.45801088213920593, "regret": 0.3992868661880493, "entropy": 0.25954997539520264, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:23.527159Z", "loop": 1169, "env_steps": 718847999, "loss": 0.006370119284838438, "avg_return": 0.4665374457836151, "regret": 0.3992868661880493, "entropy": 0.2518998384475708, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:24.420670Z", "loop": 1170, "env_steps": 719462399, "loss": 0.006962861865758896, "avg_return": 0.458069771528244, "regret": 0.403731107711792, "entropy": 0.2563161849975586, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:25.273725Z", "loop": 1171, "env_steps": 720076799, "loss": 0.00602644681930542, "avg_return": 0.46456167101860046, "regret": 0.403731107711792, "entropy": 0.26638010144233704, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:26.126631Z", "loop": 1172, "env_steps": 720691199, "loss": 0.006095115095376968, "avg_return": 0.4598180651664734, "regret": 0.403731107711792, "entropy": 0.2919958829879761, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:26.980205Z", "loop": 1173, "env_steps": 721305599, "loss": 0.0068253763020038605, "avg_return": 0.4644697308540344, "regret": 0.403731107711792, "entropy": 0.30387455224990845, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:27.834667Z", "loop": 1174, "env_steps": 721919999, "loss": 0.007656837347894907, "avg_return": 0.47183606028556824, "regret": 0.403731107711792, "entropy": 0.3158799409866333, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:28.728781Z", "loop": 1175, "env_steps": 722534399, "loss": 0.0072355614975094795, "avg_return": 0.4613913595676422, "regret": 0.39915135502815247, "entropy": 0.32571685314178467, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:29.581606Z", "loop": 1176, "env_steps": 723148799, "loss": 0.0071053155697882175, "avg_return": 0.4609479010105133, "regret": 0.39915135502815247, "entropy": 0.3188844323158264, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:30.434272Z", "loop": 1177, "env_steps": 723763199, "loss": 0.0072892168536782265, "avg_return": 0.46223965287208557, "regret": 0.39915135502815247, "entropy": 0.3160609006881714, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:31.287786Z", "loop": 1178, "env_steps": 724377599, "loss": 0.006917331367731094, "avg_return": 0.46167683601379395, "regret": 0.39915135502815247, "entropy": 0.3153221309185028, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:32.141639Z", "loop": 1179, "env_steps": 724991999, "loss": 0.007427931763231754, "avg_return": 0.4722660481929779, "regret": 0.39915135502815247, "entropy": 0.30970460176467896, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:33.035017Z", "loop": 1180, "env_steps": 725606399, "loss": 0.007592491339892149, "avg_return": 0.47368094325065613, "regret": 0.39368224143981934, "entropy": 0.30296340584754944, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:33.887773Z", "loop": 1181, "env_steps": 726220799, "loss": 0.00823468528687954, "avg_return": 0.47605276107788086, "regret": 0.39368224143981934, "entropy": 0.3107343912124634, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:34.740628Z", "loop": 1182, "env_steps": 726835199, "loss": 0.008119511418044567, "avg_return": 0.47237062454223633, "regret": 0.39368224143981934, "entropy": 0.306845486164093, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:35.593110Z", "loop": 1183, "env_steps": 727449599, "loss": 0.007386577315628529, "avg_return": 0.47494661808013916, "regret": 0.39368224143981934, "entropy": 0.3027478754520416, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:36.445676Z", "loop": 1184, "env_steps": 728063999, "loss": 0.007773937191814184, "avg_return": 0.47813427448272705, "regret": 0.39368224143981934, "entropy": 0.29978811740875244, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:37.336624Z", "loop": 1185, "env_steps": 728678399, "loss": 0.007391129620373249, "avg_return": 0.47591766715049744, "regret": 0.39135023951530457, "entropy": 0.29939010739326477, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:38.189658Z", "loop": 1186, "env_steps": 729292799, "loss": 0.007686827331781387, "avg_return": 0.4807673692703247, "regret": 0.39135023951530457, "entropy": 0.30223792791366577, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:39.043472Z", "loop": 1187, "env_steps": 729907199, "loss": 0.007176305633038282, "avg_return": 0.4712139964103699, "regret": 0.39135023951530457, "entropy": 0.29773062467575073, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:39.895444Z", "loop": 1188, "env_steps": 730521599, "loss": 0.006841942667961121, "avg_return": 0.46432816982269287, "regret": 0.39135023951530457, "entropy": 0.29016202688217163, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:40.747324Z", "loop": 1189, "env_steps": 731135999, "loss": 0.00698090298101306, "avg_return": 0.47019660472869873, "regret": 0.39135023951530457, "entropy": 0.2926667034626007, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:41.641207Z", "loop": 1190, "env_steps": 731750399, "loss": 0.0072835213504731655, "avg_return": 0.4786251485347748, "regret": 0.38858211040496826, "entropy": 0.2727316617965698, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:42.495185Z", "loop": 1191, "env_steps": 732364799, "loss": 0.005455506965517998, "avg_return": 0.47197461128234863, "regret": 0.38858211040496826, "entropy": 0.24578118324279785, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:43.347861Z", "loop": 1192, "env_steps": 732979199, "loss": 0.006105985026806593, "avg_return": 0.4732885956764221, "regret": 0.38858211040496826, "entropy": 0.23444433510303497, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:44.201457Z", "loop": 1193, "env_steps": 733593599, "loss": 0.006119995377957821, "avg_return": 0.4748898446559906, "regret": 0.38858211040496826, "entropy": 0.22223246097564697, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:45.055577Z", "loop": 1194, "env_steps": 734207999, "loss": 0.005692263599485159, "avg_return": 0.4714464545249939, "regret": 0.38858211040496826, "entropy": 0.20965787768363953, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:45.950023Z", "loop": 1195, "env_steps": 734822399, "loss": 0.006118502002209425, "avg_return": 0.4725889265537262, "regret": 0.3930617868900299, "entropy": 0.20450685918331146, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:46.803923Z", "loop": 1196, "env_steps": 735436799, "loss": 0.005157421343028545, "avg_return": 0.46558135747909546, "regret": 0.3930617868900299, "entropy": 0.20548997819423676, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:47.658176Z", "loop": 1197, "env_steps": 736051199, "loss": 0.005410430487245321, "avg_return": 0.4742579162120819, "regret": 0.3930617868900299, "entropy": 0.2171139121055603, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:48.511375Z", "loop": 1198, "env_steps": 736665599, "loss": 0.0054842098616063595, "avg_return": 0.4757401645183563, "regret": 0.3930617868900299, "entropy": 0.2220500111579895, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:49.363821Z", "loop": 1199, "env_steps": 737279999, "loss": 0.005841575097292662, "avg_return": 0.4793444871902466, "regret": 0.3930617868900299, "entropy": 0.23961418867111206, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:50.256071Z", "loop": 1200, "env_steps": 737894399, "loss": 0.006457076407968998, "avg_return": 0.4789602756500244, "regret": 0.38626784086227417, "entropy": 0.2615926265716553, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:51.109367Z", "loop": 1201, "env_steps": 738508799, "loss": 0.006834921892732382, "avg_return": 0.4742308259010315, "regret": 0.38626784086227417, "entropy": 0.28098440170288086, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:51.962601Z", "loop": 1202, "env_steps": 739123199, "loss": 0.007794998586177826, "avg_return": 0.47164490818977356, "regret": 0.38626784086227417, "entropy": 0.2908168435096741, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:52.814863Z", "loop": 1203, "env_steps": 739737599, "loss": 0.008247766643762589, "avg_return": 0.46347007155418396, "regret": 0.38626784086227417, "entropy": 0.29255613684654236, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:53.666691Z", "loop": 1204, "env_steps": 740351999, "loss": 0.007816294208168983, "avg_return": 0.472046822309494, "regret": 0.38626784086227417, "entropy": 0.28763052821159363, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:54.558605Z", "loop": 1205, "env_steps": 740966399, "loss": 0.007849768735468388, "avg_return": 0.4802449643611908, "regret": 0.38824957609176636, "entropy": 0.2815124988555908, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:55.410785Z", "loop": 1206, "env_steps": 741580799, "loss": 0.005979703273624182, "avg_return": 0.47055283188819885, "regret": 0.38824957609176636, "entropy": 0.2663567066192627, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:56.263605Z", "loop": 1207, "env_steps": 742195199, "loss": 0.0054208203218877316, "avg_return": 0.47310954332351685, "regret": 0.38824957609176636, "entropy": 0.24625496566295624, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:57.115713Z", "loop": 1208, "env_steps": 742809599, "loss": 0.005229797679930925, "avg_return": 0.477338582277298, "regret": 0.38824957609176636, "entropy": 0.22017048299312592, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:57.968246Z", "loop": 1209, "env_steps": 743423999, "loss": 0.00494077755138278, "avg_return": 0.4723421335220337, "regret": 0.38824957609176636, "entropy": 0.191825732588768, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:58.860754Z", "loop": 1210, "env_steps": 744038399, "loss": 0.004771627951413393, "avg_return": 0.4707144796848297, "regret": 0.39709237217903137, "entropy": 0.17625342309474945, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:40:59.713337Z", "loop": 1211, "env_steps": 744652799, "loss": 0.004572346340864897, "avg_return": 0.4589051306247711, "regret": 0.39709237217903137, "entropy": 0.17266535758972168, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:00.566372Z", "loop": 1212, "env_steps": 745267199, "loss": 0.004649372771382332, "avg_return": 0.4707774519920349, "regret": 0.39709237217903137, "entropy": 0.17504169046878815, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:01.420042Z", "loop": 1213, "env_steps": 745881599, "loss": 0.004011538811028004, "avg_return": 0.4723232090473175, "regret": 0.39709237217903137, "entropy": 0.18400490283966064, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:02.272765Z", "loop": 1214, "env_steps": 746495999, "loss": 0.004396740812808275, "avg_return": 0.468132883310318, "regret": 0.39709237217903137, "entropy": 0.19463281333446503, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:03.164941Z", "loop": 1215, "env_steps": 747110399, "loss": 0.004777411464601755, "avg_return": 0.4720633924007416, "regret": 0.389516144990921, "entropy": 0.20797672867774963, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:04.018707Z", "loop": 1216, "env_steps": 747724799, "loss": 0.005159629974514246, "avg_return": 0.4764828681945801, "regret": 0.389516144990921, "entropy": 0.22452005743980408, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:04.871261Z", "loop": 1217, "env_steps": 748339199, "loss": 0.004723344463855028, "avg_return": 0.46962666511535645, "regret": 0.389516144990921, "entropy": 0.23478630185127258, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:05.724090Z", "loop": 1218, "env_steps": 748953599, "loss": 0.006455071270465851, "avg_return": 0.4802733361721039, "regret": 0.389516144990921, "entropy": 0.23945869505405426, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:06.576424Z", "loop": 1219, "env_steps": 749567999, "loss": 0.007168927695602179, "avg_return": 0.48107779026031494, "regret": 0.389516144990921, "entropy": 0.2524782419204712, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:07.468364Z", "loop": 1220, "env_steps": 750182399, "loss": 0.006937120109796524, "avg_return": 0.4668430685997009, "regret": 0.3933347165584564, "entropy": 0.2591293752193451, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:08.321818Z", "loop": 1221, "env_steps": 750796799, "loss": 0.007785014342516661, "avg_return": 0.47848236560821533, "regret": 0.3933347165584564, "entropy": 0.2551223337650299, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:09.174247Z", "loop": 1222, "env_steps": 751411199, "loss": 0.0074531035497784615, "avg_return": 0.475372314453125, "regret": 0.3933347165584564, "entropy": 0.249524787068367, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:10.027206Z", "loop": 1223, "env_steps": 752025599, "loss": 0.006997867953032255, "avg_return": 0.476689875125885, "regret": 0.3933347165584564, "entropy": 0.24338284134864807, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:10.879391Z", "loop": 1224, "env_steps": 752639999, "loss": 0.005521786864846945, "avg_return": 0.48056215047836304, "regret": 0.3933347165584564, "entropy": 0.2235846370458603, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:11.772791Z", "loop": 1225, "env_steps": 753254399, "loss": 0.005412106402218342, "avg_return": 0.4789368808269501, "regret": 0.3832824230194092, "entropy": 0.22556979954242706, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:12.625434Z", "loop": 1226, "env_steps": 753868799, "loss": 0.0049630808643996716, "avg_return": 0.4791623651981354, "regret": 0.3832824230194092, "entropy": 0.217956081032753, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:13.478405Z", "loop": 1227, "env_steps": 754483199, "loss": 0.00445239432156086, "avg_return": 0.47606968879699707, "regret": 0.3832824230194092, "entropy": 0.21920348703861237, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:14.331529Z", "loop": 1228, "env_steps": 755097599, "loss": 0.0046615018509328365, "avg_return": 0.48314040899276733, "regret": 0.3832824230194092, "entropy": 0.20623163878917694, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:15.185008Z", "loop": 1229, "env_steps": 755711999, "loss": 0.0052192737348377705, "avg_return": 0.4875037372112274, "regret": 0.3832824230194092, "entropy": 0.20208390057086945, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:16.078055Z", "loop": 1230, "env_steps": 756326399, "loss": 0.005030788481235504, "avg_return": 0.47494158148765564, "regret": 0.38643044233322144, "entropy": 0.1898777037858963, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:16.930139Z", "loop": 1231, "env_steps": 756940799, "loss": 0.004881387576460838, "avg_return": 0.4815101623535156, "regret": 0.38643044233322144, "entropy": 0.1939609944820404, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:17.783344Z", "loop": 1232, "env_steps": 757555199, "loss": 0.004634425509721041, "avg_return": 0.477957159280777, "regret": 0.38643044233322144, "entropy": 0.18657736480236053, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:18.636350Z", "loop": 1233, "env_steps": 758169599, "loss": 0.005123270209878683, "avg_return": 0.47466233372688293, "regret": 0.38643044233322144, "entropy": 0.19533780217170715, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:19.489292Z", "loop": 1234, "env_steps": 758783999, "loss": 0.0045600286684930325, "avg_return": 0.4791962802410126, "regret": 0.38643044233322144, "entropy": 0.19876237213611603, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:20.383259Z", "loop": 1235, "env_steps": 759398399, "loss": 0.004582749214023352, "avg_return": 0.4808436632156372, "regret": 0.38303354382514954, "entropy": 0.1998593807220459, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:21.235862Z", "loop": 1236, "env_steps": 760012799, "loss": 0.0050184037536382675, "avg_return": 0.47796428203582764, "regret": 0.38303354382514954, "entropy": 0.20607499778270721, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:22.089153Z", "loop": 1237, "env_steps": 760627199, "loss": 0.005122655536979437, "avg_return": 0.48381146788597107, "regret": 0.38303354382514954, "entropy": 0.21278947591781616, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:22.942187Z", "loop": 1238, "env_steps": 761241599, "loss": 0.004889635369181633, "avg_return": 0.4720097482204437, "regret": 0.38303354382514954, "entropy": 0.20849253237247467, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:23.795569Z", "loop": 1239, "env_steps": 761855999, "loss": 0.00540542509406805, "avg_return": 0.4817396104335785, "regret": 0.38303354382514954, "entropy": 0.21223704516887665, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:24.688057Z", "loop": 1240, "env_steps": 762470399, "loss": 0.005575698334723711, "avg_return": 0.49063295125961304, "regret": 0.38255736231803894, "entropy": 0.2130187600851059, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:25.540595Z", "loop": 1241, "env_steps": 763084799, "loss": 0.005308590829372406, "avg_return": 0.4836757481098175, "regret": 0.38255736231803894, "entropy": 0.210561603307724, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:26.393961Z", "loop": 1242, "env_steps": 763699199, "loss": 0.005999391432851553, "avg_return": 0.48174989223480225, "regret": 0.38255736231803894, "entropy": 0.21859994530677795, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:27.248292Z", "loop": 1243, "env_steps": 764313599, "loss": 0.005463736597448587, "avg_return": 0.48034465312957764, "regret": 0.38255736231803894, "entropy": 0.22223159670829773, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:28.101948Z", "loop": 1244, "env_steps": 764927999, "loss": 0.005155749153345823, "avg_return": 0.474935919046402, "regret": 0.38255736231803894, "entropy": 0.2230108678340912, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:28.995335Z", "loop": 1245, "env_steps": 765542399, "loss": 0.005788199137896299, "avg_return": 0.48193636536598206, "regret": 0.3824418783187866, "entropy": 0.21413712203502655, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:29.848982Z", "loop": 1246, "env_steps": 766156799, "loss": 0.005257147829979658, "avg_return": 0.4789879024028778, "regret": 0.3824418783187866, "entropy": 0.20731256902217865, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:30.703647Z", "loop": 1247, "env_steps": 766771199, "loss": 0.005135965533554554, "avg_return": 0.4776308834552765, "regret": 0.3824418783187866, "entropy": 0.20253093540668488, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:31.558155Z", "loop": 1248, "env_steps": 767385599, "loss": 0.005227986257523298, "avg_return": 0.48237356543540955, "regret": 0.3824418783187866, "entropy": 0.2062012255191803, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:32.410877Z", "loop": 1249, "env_steps": 767999999, "loss": 0.005082666873931885, "avg_return": 0.4843096435070038, "regret": 0.3824418783187866, "entropy": 0.20397570729255676, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:33.305098Z", "loop": 1250, "env_steps": 768614399, "loss": 0.005080375820398331, "avg_return": 0.47960755228996277, "regret": 0.3817306458950043, "entropy": 0.20941099524497986, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:34.158450Z", "loop": 1251, "env_steps": 769228799, "loss": 0.005458665546029806, "avg_return": 0.4821276366710663, "regret": 0.3817306458950043, "entropy": 0.20905810594558716, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:35.012781Z", "loop": 1252, "env_steps": 769843199, "loss": 0.004855241160839796, "avg_return": 0.4808304011821747, "regret": 0.3817306458950043, "entropy": 0.20670440793037415, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:35.866085Z", "loop": 1253, "env_steps": 770457599, "loss": 0.005463670939207077, "avg_return": 0.4840179979801178, "regret": 0.3817306458950043, "entropy": 0.20052474737167358, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:36.719916Z", "loop": 1254, "env_steps": 771071999, "loss": 0.005065829958766699, "avg_return": 0.4803547263145447, "regret": 0.3817306458950043, "entropy": 0.20435801148414612, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:37.614645Z", "loop": 1255, "env_steps": 771686399, "loss": 0.005805095192044973, "avg_return": 0.4769650399684906, "regret": 0.3812258839607239, "entropy": 0.20418374240398407, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:38.469137Z", "loop": 1256, "env_steps": 772300799, "loss": 0.005630157422274351, "avg_return": 0.4807329475879669, "regret": 0.3812258839607239, "entropy": 0.20454397797584534, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:39.323221Z", "loop": 1257, "env_steps": 772915199, "loss": 0.005900826305150986, "avg_return": 0.4786587655544281, "regret": 0.3812258839607239, "entropy": 0.2041151523590088, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:40.176643Z", "loop": 1258, "env_steps": 773529599, "loss": 0.005721535068005323, "avg_return": 0.4720310568809509, "regret": 0.3812258839607239, "entropy": 0.21192555129528046, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:41.030144Z", "loop": 1259, "env_steps": 774143999, "loss": 0.005996258929371834, "avg_return": 0.47941428422927856, "regret": 0.3812258839607239, "entropy": 0.21159480512142181, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:41.923903Z", "loop": 1260, "env_steps": 774758399, "loss": 0.006056699436157942, "avg_return": 0.48209866881370544, "regret": 0.3856995105743408, "entropy": 0.20101429522037506, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:42.777334Z", "loop": 1261, "env_steps": 775372799, "loss": 0.005944824777543545, "avg_return": 0.4830654561519623, "regret": 0.3856995105743408, "entropy": 0.20149938762187958, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:43.631018Z", "loop": 1262, "env_steps": 775987199, "loss": 0.005435195751488209, "avg_return": 0.4759954810142517, "regret": 0.3856995105743408, "entropy": 0.1959477812051773, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:44.483107Z", "loop": 1263, "env_steps": 776601599, "loss": 0.005199320148676634, "avg_return": 0.4825139343738556, "regret": 0.3856995105743408, "entropy": 0.19549359381198883, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:45.336205Z", "loop": 1264, "env_steps": 777215999, "loss": 0.004485239740461111, "avg_return": 0.4896238446235657, "regret": 0.3856995105743408, "entropy": 0.18743064999580383, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:46.230735Z", "loop": 1265, "env_steps": 777830399, "loss": 0.00452447310090065, "avg_return": 0.4783736765384674, "regret": 0.3811752200126648, "entropy": 0.18104413151741028, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:47.083902Z", "loop": 1266, "env_steps": 778444799, "loss": 0.004499918781220913, "avg_return": 0.48574239015579224, "regret": 0.3811752200126648, "entropy": 0.18846659362316132, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:47.937735Z", "loop": 1267, "env_steps": 779059199, "loss": 0.004104036837816238, "avg_return": 0.4740442633628845, "regret": 0.3811752200126648, "entropy": 0.19772648811340332, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:48.790802Z", "loop": 1268, "env_steps": 779673599, "loss": 0.003728111507371068, "avg_return": 0.484445720911026, "regret": 0.3811752200126648, "entropy": 0.17726770043373108, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:49.644313Z", "loop": 1269, "env_steps": 780287999, "loss": 0.0035850652493536472, "avg_return": 0.4787925183773041, "regret": 0.3811752200126648, "entropy": 0.15545715391635895, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:50.538280Z", "loop": 1270, "env_steps": 780902399, "loss": 0.003740232437849045, "avg_return": 0.4709814190864563, "regret": 0.3934599459171295, "entropy": 0.14377622306346893, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:51.391624Z", "loop": 1271, "env_steps": 781516799, "loss": 0.0047453949227929115, "avg_return": 0.4634142220020294, "regret": 0.3934599459171295, "entropy": 0.15050199627876282, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:52.246879Z", "loop": 1272, "env_steps": 782131199, "loss": 0.004743177443742752, "avg_return": 0.45268887281417847, "regret": 0.3934599459171295, "entropy": 0.14802668988704681, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:53.100034Z", "loop": 1273, "env_steps": 782745599, "loss": 0.004566628020256758, "avg_return": 0.4764370918273926, "regret": 0.3934599459171295, "entropy": 0.14829090237617493, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:53.953597Z", "loop": 1274, "env_steps": 783359999, "loss": 0.0035664045717567205, "avg_return": 0.4797240197658539, "regret": 0.3934599459171295, "entropy": 0.15783868730068207, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:54.847413Z", "loop": 1275, "env_steps": 783974399, "loss": 0.003772556548938155, "avg_return": 0.4889652132987976, "regret": 0.38548311591148376, "entropy": 0.16909077763557434, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:55.701487Z", "loop": 1276, "env_steps": 784588799, "loss": 0.004040083382278681, "avg_return": 0.4768904745578766, "regret": 0.38548311591148376, "entropy": 0.1846839338541031, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:56.555221Z", "loop": 1277, "env_steps": 785203199, "loss": 0.004431435372680426, "avg_return": 0.48499158024787903, "regret": 0.38548311591148376, "entropy": 0.19257158041000366, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:57.408527Z", "loop": 1278, "env_steps": 785817599, "loss": 0.00460056122392416, "avg_return": 0.48408952355384827, "regret": 0.38548311591148376, "entropy": 0.18260015547275543, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:58.261805Z", "loop": 1279, "env_steps": 786431999, "loss": 0.004574974533170462, "avg_return": 0.4830906391143799, "regret": 0.38548311591148376, "entropy": 0.1841057538986206, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:41:59.156880Z", "loop": 1280, "env_steps": 787046399, "loss": 0.005400851368904114, "avg_return": 0.4787631332874298, "regret": 0.38136622309684753, "entropy": 0.19742019474506378, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:00.009013Z", "loop": 1281, "env_steps": 787660799, "loss": 0.005589015316218138, "avg_return": 0.4738476574420929, "regret": 0.38136622309684753, "entropy": 0.20637401938438416, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:00.861450Z", "loop": 1282, "env_steps": 788275199, "loss": 0.006617805454879999, "avg_return": 0.4732281565666199, "regret": 0.38136622309684753, "entropy": 0.20878353714942932, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:01.713938Z", "loop": 1283, "env_steps": 788889599, "loss": 0.00551932817324996, "avg_return": 0.4793265759944916, "regret": 0.38136622309684753, "entropy": 0.20872095227241516, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:02.568120Z", "loop": 1284, "env_steps": 789503999, "loss": 0.0051310076378285885, "avg_return": 0.4811078608036041, "regret": 0.38136622309684753, "entropy": 0.19967809319496155, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:03.462080Z", "loop": 1285, "env_steps": 790118399, "loss": 0.004959110636264086, "avg_return": 0.4854333698749542, "regret": 0.38084176182746887, "entropy": 0.19170227646827698, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:04.314927Z", "loop": 1286, "env_steps": 790732799, "loss": 0.0050730775110423565, "avg_return": 0.4793855845928192, "regret": 0.38084176182746887, "entropy": 0.1868358701467514, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:05.168153Z", "loop": 1287, "env_steps": 791347199, "loss": 0.004459872376173735, "avg_return": 0.4743126630783081, "regret": 0.38084176182746887, "entropy": 0.18107794225215912, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:06.023176Z", "loop": 1288, "env_steps": 791961599, "loss": 0.004603448323905468, "avg_return": 0.48738551139831543, "regret": 0.38084176182746887, "entropy": 0.1790253072977066, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:06.875901Z", "loop": 1289, "env_steps": 792575999, "loss": 0.0043753087520599365, "avg_return": 0.48854899406433105, "regret": 0.38084176182746887, "entropy": 0.17649652063846588, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:07.770573Z", "loop": 1290, "env_steps": 793190399, "loss": 0.00455308286473155, "avg_return": 0.49059122800827026, "regret": 0.3809702694416046, "entropy": 0.17959502339363098, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:08.624591Z", "loop": 1291, "env_steps": 793804799, "loss": 0.003998129162937403, "avg_return": 0.47926488518714905, "regret": 0.3809702694416046, "entropy": 0.18140430748462677, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:09.478962Z", "loop": 1292, "env_steps": 794419199, "loss": 0.0032123096752911806, "avg_return": 0.4832148253917694, "regret": 0.3809702694416046, "entropy": 0.1760120540857315, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:10.332806Z", "loop": 1293, "env_steps": 795033599, "loss": 0.0030051281210035086, "avg_return": 0.47523388266563416, "regret": 0.3809702694416046, "entropy": 0.1464419662952423, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:11.185267Z", "loop": 1294, "env_steps": 795647999, "loss": 0.0028830384835600853, "avg_return": 0.4692055284976959, "regret": 0.3809702694416046, "entropy": 0.14122645556926727, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:12.076541Z", "loop": 1295, "env_steps": 796262399, "loss": 0.00323740323074162, "avg_return": 0.4686950743198395, "regret": 0.3952326774597168, "entropy": 0.13127854466438293, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:12.930180Z", "loop": 1296, "env_steps": 796876799, "loss": 0.0031426716595888138, "avg_return": 0.4740706980228424, "regret": 0.3952326774597168, "entropy": 0.13228526711463928, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:13.783309Z", "loop": 1297, "env_steps": 797491199, "loss": 0.0032924364786595106, "avg_return": 0.4636746346950531, "regret": 0.3952326774597168, "entropy": 0.13490475714206696, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:14.637152Z", "loop": 1298, "env_steps": 798105599, "loss": 0.002856481820344925, "avg_return": 0.47698426246643066, "regret": 0.3952326774597168, "entropy": 0.14886336028575897, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:15.490455Z", "loop": 1299, "env_steps": 798719999, "loss": 0.002945367945358157, "avg_return": 0.47949808835983276, "regret": 0.3952326774597168, "entropy": 0.1640910804271698, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:16.386165Z", "loop": 1300, "env_steps": 799334399, "loss": 0.004059337545186281, "avg_return": 0.491117000579834, "regret": 0.3806513845920563, "entropy": 0.1701900213956833, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:17.239545Z", "loop": 1301, "env_steps": 799948799, "loss": 0.00421882001683116, "avg_return": 0.4900035858154297, "regret": 0.3806513845920563, "entropy": 0.1715516448020935, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:18.092565Z", "loop": 1302, "env_steps": 800563199, "loss": 0.004119178280234337, "avg_return": 0.4836878478527069, "regret": 0.3806513845920563, "entropy": 0.16097348928451538, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:18.946897Z", "loop": 1303, "env_steps": 801177599, "loss": 0.003760010004043579, "avg_return": 0.48415812849998474, "regret": 0.3806513845920563, "entropy": 0.15826483070850372, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:19.799486Z", "loop": 1304, "env_steps": 801791999, "loss": 0.004109680652618408, "avg_return": 0.48611029982566833, "regret": 0.3806513845920563, "entropy": 0.16373267769813538, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:20.694085Z", "loop": 1305, "env_steps": 802406399, "loss": 0.004007698502391577, "avg_return": 0.47786596417427063, "regret": 0.37916824221611023, "entropy": 0.1576215624809265, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:21.547715Z", "loop": 1306, "env_steps": 803020799, "loss": 0.0040724314749240875, "avg_return": 0.4846337139606476, "regret": 0.37916824221611023, "entropy": 0.16064053773880005, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:22.403063Z", "loop": 1307, "env_steps": 803635199, "loss": 0.003911243285983801, "avg_return": 0.4842101037502289, "regret": 0.37916824221611023, "entropy": 0.15730102360248566, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:23.256241Z", "loop": 1308, "env_steps": 804249599, "loss": 0.0037568199913948774, "avg_return": 0.4739683270454407, "regret": 0.37916824221611023, "entropy": 0.15945322811603546, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:24.109019Z", "loop": 1309, "env_steps": 804863999, "loss": 0.00400681933388114, "avg_return": 0.4847962558269501, "regret": 0.37916824221611023, "entropy": 0.15568691492080688, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:25.003892Z", "loop": 1310, "env_steps": 805478399, "loss": 0.0041524386033415794, "avg_return": 0.485283225774765, "regret": 0.3802296221256256, "entropy": 0.16020581126213074, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:25.858271Z", "loop": 1311, "env_steps": 806092799, "loss": 0.003848246531561017, "avg_return": 0.48568838834762573, "regret": 0.3802296221256256, "entropy": 0.1584738790988922, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:26.711535Z", "loop": 1312, "env_steps": 806707199, "loss": 0.0038663086015731096, "avg_return": 0.48075634241104126, "regret": 0.3802296221256256, "entropy": 0.1621367484331131, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:27.564265Z", "loop": 1313, "env_steps": 807321599, "loss": 0.0038942601531744003, "avg_return": 0.4833097457885742, "regret": 0.3802296221256256, "entropy": 0.15602245926856995, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:28.417902Z", "loop": 1314, "env_steps": 807935999, "loss": 0.0038061209488660097, "avg_return": 0.4885893762111664, "regret": 0.3802296221256256, "entropy": 0.1540171056985855, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:29.312793Z", "loop": 1315, "env_steps": 808550399, "loss": 0.003945988602936268, "avg_return": 0.48916351795196533, "regret": 0.3792753219604492, "entropy": 0.15916702151298523, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:30.166998Z", "loop": 1316, "env_steps": 809164799, "loss": 0.0039706239476799965, "avg_return": 0.49036917090415955, "regret": 0.3792753219604492, "entropy": 0.1519021838903427, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:31.020527Z", "loop": 1317, "env_steps": 809779199, "loss": 0.004190751817077398, "avg_return": 0.48288047313690186, "regret": 0.3792753219604492, "entropy": 0.16048991680145264, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:31.872642Z", "loop": 1318, "env_steps": 810393599, "loss": 0.0039596050046384335, "avg_return": 0.48443517088890076, "regret": 0.3792753219604492, "entropy": 0.15421751141548157, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:32.724948Z", "loop": 1319, "env_steps": 811007999, "loss": 0.004080814775079489, "avg_return": 0.48633623123168945, "regret": 0.3792753219604492, "entropy": 0.160004660487175, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:33.618976Z", "loop": 1320, "env_steps": 811622399, "loss": 0.004490026272833347, "avg_return": 0.48998501896858215, "regret": 0.3788190484046936, "entropy": 0.16085892915725708, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:34.471807Z", "loop": 1321, "env_steps": 812236799, "loss": 0.004479270428419113, "avg_return": 0.4824868440628052, "regret": 0.3788190484046936, "entropy": 0.15851055085659027, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:35.324818Z", "loop": 1322, "env_steps": 812851199, "loss": 0.004016593098640442, "avg_return": 0.48717865347862244, "regret": 0.3788190484046936, "entropy": 0.1679236888885498, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:36.176989Z", "loop": 1323, "env_steps": 813465599, "loss": 0.004292031284421682, "avg_return": 0.4730692207813263, "regret": 0.3788190484046936, "entropy": 0.16826707124710083, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:37.029782Z", "loop": 1324, "env_steps": 814079999, "loss": 0.005031174048781395, "avg_return": 0.48217102885246277, "regret": 0.3788190484046936, "entropy": 0.1755422204732895, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:37.922963Z", "loop": 1325, "env_steps": 814694399, "loss": 0.0053391847759485245, "avg_return": 0.4835704565048218, "regret": 0.3830309212207794, "entropy": 0.18304196000099182, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:38.776496Z", "loop": 1326, "env_steps": 815308799, "loss": 0.005510096438229084, "avg_return": 0.4749048948287964, "regret": 0.3830309212207794, "entropy": 0.1839134246110916, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:39.628316Z", "loop": 1327, "env_steps": 815923199, "loss": 0.005923568271100521, "avg_return": 0.4732441306114197, "regret": 0.3830309212207794, "entropy": 0.19093698263168335, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:40.480575Z", "loop": 1328, "env_steps": 816537599, "loss": 0.005384537391364574, "avg_return": 0.47422730922698975, "regret": 0.3830309212207794, "entropy": 0.1893325001001358, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:41.333822Z", "loop": 1329, "env_steps": 817151999, "loss": 0.005392929073423147, "avg_return": 0.479893296957016, "regret": 0.3830309212207794, "entropy": 0.18451325595378876, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:42.228840Z", "loop": 1330, "env_steps": 817766399, "loss": 0.0057089063338935375, "avg_return": 0.47524502873420715, "regret": 0.3830883800983429, "entropy": 0.18927901983261108, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:43.084046Z", "loop": 1331, "env_steps": 818380799, "loss": 0.00492975814267993, "avg_return": 0.47714701294898987, "regret": 0.3830883800983429, "entropy": 0.1774953156709671, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:43.938369Z", "loop": 1332, "env_steps": 818995199, "loss": 0.004831735044717789, "avg_return": 0.4902489483356476, "regret": 0.3830883800983429, "entropy": 0.1770419478416443, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:44.792148Z", "loop": 1333, "env_steps": 819609599, "loss": 0.004682408645749092, "avg_return": 0.4827450215816498, "regret": 0.3830883800983429, "entropy": 0.16618132591247559, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:45.646528Z", "loop": 1334, "env_steps": 820223999, "loss": 0.004051279276609421, "avg_return": 0.4851243197917938, "regret": 0.3830883800983429, "entropy": 0.16900022327899933, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:46.540974Z", "loop": 1335, "env_steps": 820838399, "loss": 0.0037016943097114563, "avg_return": 0.4794294238090515, "regret": 0.3787662088871002, "entropy": 0.1654108315706253, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:47.394450Z", "loop": 1336, "env_steps": 821452799, "loss": 0.003658339846879244, "avg_return": 0.4796585738658905, "regret": 0.3787662088871002, "entropy": 0.16363310813903809, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:48.248007Z", "loop": 1337, "env_steps": 822067199, "loss": 0.004158115945756435, "avg_return": 0.4826054573059082, "regret": 0.3787662088871002, "entropy": 0.1565226912498474, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:49.102650Z", "loop": 1338, "env_steps": 822681599, "loss": 0.003676062449812889, "avg_return": 0.47665682435035706, "regret": 0.3787662088871002, "entropy": 0.15672151744365692, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:49.957621Z", "loop": 1339, "env_steps": 823295999, "loss": 0.0037020945455878973, "avg_return": 0.4886864423751831, "regret": 0.3787662088871002, "entropy": 0.1569613218307495, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:50.853298Z", "loop": 1340, "env_steps": 823910399, "loss": 0.00391754787415266, "avg_return": 0.4845470190048218, "regret": 0.37890657782554626, "entropy": 0.15667709708213806, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:51.705453Z", "loop": 1341, "env_steps": 824524799, "loss": 0.0037540141493082047, "avg_return": 0.47885245084762573, "regret": 0.37890657782554626, "entropy": 0.1641036868095398, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:52.557246Z", "loop": 1342, "env_steps": 825139199, "loss": 0.003850352019071579, "avg_return": 0.4856049716472626, "regret": 0.37890657782554626, "entropy": 0.15688104927539825, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:53.410034Z", "loop": 1343, "env_steps": 825753599, "loss": 0.0037698582746088505, "avg_return": 0.4824536144733429, "regret": 0.37890657782554626, "entropy": 0.1547175794839859, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:54.262471Z", "loop": 1344, "env_steps": 826367999, "loss": 0.004117043223232031, "avg_return": 0.4841066002845764, "regret": 0.37890657782554626, "entropy": 0.15578773617744446, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:55.160299Z", "loop": 1345, "env_steps": 826982399, "loss": 0.0036858238745480776, "avg_return": 0.4857012927532196, "regret": 0.38060373067855835, "entropy": 0.15990610420703888, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:56.012478Z", "loop": 1346, "env_steps": 827596799, "loss": 0.00354548217728734, "avg_return": 0.4760802388191223, "regret": 0.38060373067855835, "entropy": 0.1728917807340622, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:56.865460Z", "loop": 1347, "env_steps": 828211199, "loss": 0.003469874383881688, "avg_return": 0.4789648950099945, "regret": 0.38060373067855835, "entropy": 0.17093579471111298, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:57.717710Z", "loop": 1348, "env_steps": 828825599, "loss": 0.0035432358272373676, "avg_return": 0.48085689544677734, "regret": 0.38060373067855835, "entropy": 0.17136146128177643, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:58.570452Z", "loop": 1349, "env_steps": 829439999, "loss": 0.003526780055835843, "avg_return": 0.4802379608154297, "regret": 0.38060373067855835, "entropy": 0.17760120332241058, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:42:59.462346Z", "loop": 1350, "env_steps": 830054399, "loss": 0.004050728864967823, "avg_return": 0.4810273349285126, "regret": 0.3809986412525177, "entropy": 0.1749984174966812, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:00.315646Z", "loop": 1351, "env_steps": 830668799, "loss": 0.0038490891456604004, "avg_return": 0.4845358431339264, "regret": 0.3809986412525177, "entropy": 0.1667371690273285, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:01.168301Z", "loop": 1352, "env_steps": 831283199, "loss": 0.003741033375263214, "avg_return": 0.4756976068019867, "regret": 0.3809986412525177, "entropy": 0.16676874458789825, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:02.021275Z", "loop": 1353, "env_steps": 831897599, "loss": 0.003629915416240692, "avg_return": 0.4830961227416992, "regret": 0.3809986412525177, "entropy": 0.17205801606178284, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:02.873891Z", "loop": 1354, "env_steps": 832511999, "loss": 0.004075018223375082, "avg_return": 0.48624542355537415, "regret": 0.3809986412525177, "entropy": 0.1708361804485321, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:03.766968Z", "loop": 1355, "env_steps": 833126399, "loss": 0.0039316401816904545, "avg_return": 0.4802018404006958, "regret": 0.37862229347229004, "entropy": 0.1650131344795227, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:04.618635Z", "loop": 1356, "env_steps": 833740799, "loss": 0.004306894261389971, "avg_return": 0.48419779539108276, "regret": 0.37862229347229004, "entropy": 0.1689474880695343, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:05.471491Z", "loop": 1357, "env_steps": 834355199, "loss": 0.0039832391776144505, "avg_return": 0.48432403802871704, "regret": 0.37862229347229004, "entropy": 0.16275040805339813, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:06.323614Z", "loop": 1358, "env_steps": 834969599, "loss": 0.0042482097633183, "avg_return": 0.4845339059829712, "regret": 0.37862229347229004, "entropy": 0.17104285955429077, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:07.176022Z", "loop": 1359, "env_steps": 835583999, "loss": 0.004548320081084967, "avg_return": 0.48966848850250244, "regret": 0.37862229347229004, "entropy": 0.17130237817764282, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:08.069552Z", "loop": 1360, "env_steps": 836198399, "loss": 0.0041610742919147015, "avg_return": 0.4830307066440582, "regret": 0.3778640031814575, "entropy": 0.1713872104883194, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:08.922935Z", "loop": 1361, "env_steps": 836812799, "loss": 0.0046838452108204365, "avg_return": 0.48978284001350403, "regret": 0.3778640031814575, "entropy": 0.17306961119174957, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:09.776079Z", "loop": 1362, "env_steps": 837427199, "loss": 0.004954320378601551, "avg_return": 0.48642346262931824, "regret": 0.3778640031814575, "entropy": 0.1771121770143509, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:10.629181Z", "loop": 1363, "env_steps": 838041599, "loss": 0.005061795935034752, "avg_return": 0.47971221804618835, "regret": 0.3778640031814575, "entropy": 0.18309207260608673, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:11.481953Z", "loop": 1364, "env_steps": 838655999, "loss": 0.004956440534442663, "avg_return": 0.48435497283935547, "regret": 0.3778640031814575, "entropy": 0.18610453605651855, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:12.375542Z", "loop": 1365, "env_steps": 839270399, "loss": 0.005013044457882643, "avg_return": 0.47912201285362244, "regret": 0.3799799382686615, "entropy": 0.1784982681274414, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:13.228156Z", "loop": 1366, "env_steps": 839884799, "loss": 0.004667788278311491, "avg_return": 0.48077306151390076, "regret": 0.3799799382686615, "entropy": 0.1843820959329605, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:14.081404Z", "loop": 1367, "env_steps": 840499199, "loss": 0.004855378996580839, "avg_return": 0.4826231896877289, "regret": 0.3799799382686615, "entropy": 0.17366556823253632, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:14.934757Z", "loop": 1368, "env_steps": 841113599, "loss": 0.004044631030410528, "avg_return": 0.4848807454109192, "regret": 0.3799799382686615, "entropy": 0.17560997605323792, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:15.788477Z", "loop": 1369, "env_steps": 841727999, "loss": 0.004212597385048866, "avg_return": 0.48441609740257263, "regret": 0.3799799382686615, "entropy": 0.16808049380779266, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:16.681672Z", "loop": 1370, "env_steps": 842342399, "loss": 0.003890270134434104, "avg_return": 0.485197514295578, "regret": 0.37745025753974915, "entropy": 0.1698685735464096, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:17.534332Z", "loop": 1371, "env_steps": 842956799, "loss": 0.0036785476841032505, "avg_return": 0.48552319407463074, "regret": 0.37745025753974915, "entropy": 0.16558510065078735, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:18.387983Z", "loop": 1372, "env_steps": 843571199, "loss": 0.004018529783934355, "avg_return": 0.4902153015136719, "regret": 0.37745025753974915, "entropy": 0.1663716733455658, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:19.240576Z", "loop": 1373, "env_steps": 844185599, "loss": 0.0037127987015992403, "avg_return": 0.4803389608860016, "regret": 0.37745025753974915, "entropy": 0.16708330810070038, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:20.092271Z", "loop": 1374, "env_steps": 844799999, "loss": 0.004302472807466984, "avg_return": 0.48239171504974365, "regret": 0.37745025753974915, "entropy": 0.16399578750133514, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:20.985883Z", "loop": 1375, "env_steps": 845414399, "loss": 0.004133138339966536, "avg_return": 0.48050686717033386, "regret": 0.378061980009079, "entropy": 0.1666640192270279, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:21.839581Z", "loop": 1376, "env_steps": 846028799, "loss": 0.004014404024928808, "avg_return": 0.48664119839668274, "regret": 0.378061980009079, "entropy": 0.17026272416114807, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:22.691623Z", "loop": 1377, "env_steps": 846643199, "loss": 0.0038486779667437077, "avg_return": 0.48377707600593567, "regret": 0.378061980009079, "entropy": 0.16627714037895203, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:23.543097Z", "loop": 1378, "env_steps": 847257599, "loss": 0.004258826375007629, "avg_return": 0.4893104135990143, "regret": 0.378061980009079, "entropy": 0.15678918361663818, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:24.395186Z", "loop": 1379, "env_steps": 847871999, "loss": 0.0038718711584806442, "avg_return": 0.4890509247779846, "regret": 0.378061980009079, "entropy": 0.16613687574863434, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:25.289913Z", "loop": 1380, "env_steps": 848486399, "loss": 0.0041633229702711105, "avg_return": 0.48414602875709534, "regret": 0.3784918189048767, "entropy": 0.15626181662082672, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:26.143198Z", "loop": 1381, "env_steps": 849100799, "loss": 0.0038739752490073442, "avg_return": 0.486122190952301, "regret": 0.3784918189048767, "entropy": 0.1626526564359665, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:26.995174Z", "loop": 1382, "env_steps": 849715199, "loss": 0.0033578951843082905, "avg_return": 0.48328420519828796, "regret": 0.3784918189048767, "entropy": 0.16504354774951935, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:27.848139Z", "loop": 1383, "env_steps": 850329599, "loss": 0.003717773826792836, "avg_return": 0.4892222285270691, "regret": 0.3784918189048767, "entropy": 0.16796378791332245, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:28.701745Z", "loop": 1384, "env_steps": 850943999, "loss": 0.0038375293370336294, "avg_return": 0.4827578365802765, "regret": 0.3784918189048767, "entropy": 0.16409340500831604, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:29.598889Z", "loop": 1385, "env_steps": 851558399, "loss": 0.0036507428158074617, "avg_return": 0.48125219345092773, "regret": 0.37843647599220276, "entropy": 0.16603927314281464, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:30.452046Z", "loop": 1386, "env_steps": 852172799, "loss": 0.004061808343976736, "avg_return": 0.4855026304721832, "regret": 0.37843647599220276, "entropy": 0.16052177548408508, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:31.305132Z", "loop": 1387, "env_steps": 852787199, "loss": 0.0040983478538692, "avg_return": 0.492525190114975, "regret": 0.37843647599220276, "entropy": 0.1580374836921692, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:32.158322Z", "loop": 1388, "env_steps": 853401599, "loss": 0.0038686946500092745, "avg_return": 0.4822729229927063, "regret": 0.37843647599220276, "entropy": 0.1540514975786209, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:33.012598Z", "loop": 1389, "env_steps": 854015999, "loss": 0.003407337237149477, "avg_return": 0.4800697863101959, "regret": 0.37843647599220276, "entropy": 0.15864020586013794, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:33.905950Z", "loop": 1390, "env_steps": 854630399, "loss": 0.004269707482308149, "avg_return": 0.4895226061344147, "regret": 0.37743085622787476, "entropy": 0.16083434224128723, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:34.758420Z", "loop": 1391, "env_steps": 855244799, "loss": 0.004427609499543905, "avg_return": 0.48170411586761475, "regret": 0.37743085622787476, "entropy": 0.17170490324497223, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:35.611630Z", "loop": 1392, "env_steps": 855859199, "loss": 0.0045595052652060986, "avg_return": 0.4864698350429535, "regret": 0.37743085622787476, "entropy": 0.1688203066587448, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:36.465061Z", "loop": 1393, "env_steps": 856473599, "loss": 0.0050881002098321915, "avg_return": 0.48368409276008606, "regret": 0.37743085622787476, "entropy": 0.1733441948890686, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:37.318370Z", "loop": 1394, "env_steps": 857087999, "loss": 0.0051842364482581615, "avg_return": 0.48270198702812195, "regret": 0.37743085622787476, "entropy": 0.18123960494995117, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:38.211946Z", "loop": 1395, "env_steps": 857702399, "loss": 0.005041954573243856, "avg_return": 0.4816770553588867, "regret": 0.3787730932235718, "entropy": 0.17530657351016998, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:39.064598Z", "loop": 1396, "env_steps": 858316799, "loss": 0.005238709971308708, "avg_return": 0.4850881099700928, "regret": 0.3787730932235718, "entropy": 0.18251492083072662, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:39.917158Z", "loop": 1397, "env_steps": 858931199, "loss": 0.006242499686777592, "avg_return": 0.48543620109558105, "regret": 0.3787730932235718, "entropy": 0.18419772386550903, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:40.770130Z", "loop": 1398, "env_steps": 859545599, "loss": 0.0063923257403075695, "avg_return": 0.4856865704059601, "regret": 0.3787730932235718, "entropy": 0.19617164134979248, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:41.622790Z", "loop": 1399, "env_steps": 860159999, "loss": 0.006480536889284849, "avg_return": 0.48147472739219666, "regret": 0.3787730932235718, "entropy": 0.19027765095233917, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:42.517281Z", "loop": 1400, "env_steps": 860774399, "loss": 0.006358334328979254, "avg_return": 0.4773994982242584, "regret": 0.38233113288879395, "entropy": 0.19705639779567719, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:43.368908Z", "loop": 1401, "env_steps": 861388799, "loss": 0.0067244479432702065, "avg_return": 0.4785182774066925, "regret": 0.38233113288879395, "entropy": 0.19146020710468292, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:44.221150Z", "loop": 1402, "env_steps": 862003199, "loss": 0.005974448285996914, "avg_return": 0.48075151443481445, "regret": 0.38233113288879395, "entropy": 0.1853792667388916, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:45.074033Z", "loop": 1403, "env_steps": 862617599, "loss": 0.005581281613558531, "avg_return": 0.4869459271430969, "regret": 0.38233113288879395, "entropy": 0.17811794579029083, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:45.927211Z", "loop": 1404, "env_steps": 863231999, "loss": 0.004886011127382517, "avg_return": 0.4855036437511444, "regret": 0.38233113288879395, "entropy": 0.17565833032131195, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:46.819217Z", "loop": 1405, "env_steps": 863846399, "loss": 0.004291946534067392, "avg_return": 0.4824013411998749, "regret": 0.377637654542923, "entropy": 0.170420303940773, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:47.671424Z", "loop": 1406, "env_steps": 864460799, "loss": 0.004254851955920458, "avg_return": 0.48191937804222107, "regret": 0.377637654542923, "entropy": 0.16386625170707703, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:48.523726Z", "loop": 1407, "env_steps": 865075199, "loss": 0.003937532659620047, "avg_return": 0.4896373748779297, "regret": 0.377637654542923, "entropy": 0.16128894686698914, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:49.376390Z", "loop": 1408, "env_steps": 865689599, "loss": 0.0038336997386068106, "avg_return": 0.48594701290130615, "regret": 0.377637654542923, "entropy": 0.1571444272994995, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:50.228849Z", "loop": 1409, "env_steps": 866303999, "loss": 0.003861773759126663, "avg_return": 0.48915982246398926, "regret": 0.377637654542923, "entropy": 0.1621582806110382, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:51.122022Z", "loop": 1410, "env_steps": 866918399, "loss": 0.00396614708006382, "avg_return": 0.48862844705581665, "regret": 0.37768539786338806, "entropy": 0.15986590087413788, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:51.975841Z", "loop": 1411, "env_steps": 867532799, "loss": 0.0035609423648566008, "avg_return": 0.4875987768173218, "regret": 0.37768539786338806, "entropy": 0.15253882110118866, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:52.829491Z", "loop": 1412, "env_steps": 868147199, "loss": 0.0032634481322020292, "avg_return": 0.48642081022262573, "regret": 0.37768539786338806, "entropy": 0.1530229151248932, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:53.683251Z", "loop": 1413, "env_steps": 868761599, "loss": 0.0032488007564097643, "avg_return": 0.487924724817276, "regret": 0.37768539786338806, "entropy": 0.1472100019454956, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:54.536150Z", "loop": 1414, "env_steps": 869375999, "loss": 0.0030731335282325745, "avg_return": 0.48053213953971863, "regret": 0.37768539786338806, "entropy": 0.1513518989086151, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:55.429912Z", "loop": 1415, "env_steps": 869990399, "loss": 0.00314987706951797, "avg_return": 0.48682525753974915, "regret": 0.37873759865760803, "entropy": 0.1511373072862625, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:56.283123Z", "loop": 1416, "env_steps": 870604799, "loss": 0.003260636469349265, "avg_return": 0.49010881781578064, "regret": 0.37873759865760803, "entropy": 0.14954979717731476, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:57.136246Z", "loop": 1417, "env_steps": 871219199, "loss": 0.0031316441018134356, "avg_return": 0.48918163776397705, "regret": 0.37873759865760803, "entropy": 0.14914052188396454, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:57.989655Z", "loop": 1418, "env_steps": 871833599, "loss": 0.003285088110715151, "avg_return": 0.48472994565963745, "regret": 0.37873759865760803, "entropy": 0.1416015625, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:58.843979Z", "loop": 1419, "env_steps": 872447999, "loss": 0.0034858607687056065, "avg_return": 0.48735469579696655, "regret": 0.37873759865760803, "entropy": 0.14248360693454742, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:43:59.736449Z", "loop": 1420, "env_steps": 873062399, "loss": 0.0036471595522016287, "avg_return": 0.48335665464401245, "regret": 0.37781527638435364, "entropy": 0.15097250044345856, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:00.589626Z", "loop": 1421, "env_steps": 873676799, "loss": 0.0035349223762750626, "avg_return": 0.4876633286476135, "regret": 0.37781527638435364, "entropy": 0.14988453686237335, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:01.442926Z", "loop": 1422, "env_steps": 874291199, "loss": 0.0029839121270924807, "avg_return": 0.4834043085575104, "regret": 0.37781527638435364, "entropy": 0.15172037482261658, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:02.296926Z", "loop": 1423, "env_steps": 874905599, "loss": 0.003681096015498042, "avg_return": 0.4845810532569885, "regret": 0.37781527638435364, "entropy": 0.1539609581232071, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:03.149807Z", "loop": 1424, "env_steps": 875519999, "loss": 0.0041452315635979176, "avg_return": 0.4823949337005615, "regret": 0.37781527638435364, "entropy": 0.16195866465568542, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:04.044821Z", "loop": 1425, "env_steps": 876134399, "loss": 0.004548342432826757, "avg_return": 0.48798951506614685, "regret": 0.37758156657218933, "entropy": 0.16290155053138733, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:04.899110Z", "loop": 1426, "env_steps": 876748799, "loss": 0.004544899333268404, "avg_return": 0.4902232587337494, "regret": 0.37758156657218933, "entropy": 0.1732500195503235, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:05.753497Z", "loop": 1427, "env_steps": 877363199, "loss": 0.004980909172445536, "avg_return": 0.48753491044044495, "regret": 0.37758156657218933, "entropy": 0.17999137938022614, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:06.606123Z", "loop": 1428, "env_steps": 877977599, "loss": 0.005911907181143761, "avg_return": 0.4783604145050049, "regret": 0.37758156657218933, "entropy": 0.180546835064888, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:07.459572Z", "loop": 1429, "env_steps": 878591999, "loss": 0.0056748162023723125, "avg_return": 0.4833686351776123, "regret": 0.37758156657218933, "entropy": 0.18118561804294586, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:08.354417Z", "loop": 1430, "env_steps": 879206399, "loss": 0.006201418582350016, "avg_return": 0.4829566478729248, "regret": 0.37949538230895996, "entropy": 0.18525627255439758, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:09.209174Z", "loop": 1431, "env_steps": 879820799, "loss": 0.005953311454504728, "avg_return": 0.4821801483631134, "regret": 0.37949538230895996, "entropy": 0.1863471418619156, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:10.062903Z", "loop": 1432, "env_steps": 880435199, "loss": 0.00660685682669282, "avg_return": 0.4883422553539276, "regret": 0.37949538230895996, "entropy": 0.18721967935562134, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:10.916311Z", "loop": 1433, "env_steps": 881049599, "loss": 0.005989990662783384, "avg_return": 0.4818120300769806, "regret": 0.37949538230895996, "entropy": 0.18020418286323547, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:11.770024Z", "loop": 1434, "env_steps": 881663999, "loss": 0.006085103843361139, "avg_return": 0.48390403389930725, "regret": 0.37949538230895996, "entropy": 0.18138375878334045, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:12.663324Z", "loop": 1435, "env_steps": 882278399, "loss": 0.006350153591483831, "avg_return": 0.4849707782268524, "regret": 0.37882739305496216, "entropy": 0.1855831891298294, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:13.516374Z", "loop": 1436, "env_steps": 882892799, "loss": 0.005598713178187609, "avg_return": 0.48093390464782715, "regret": 0.37882739305496216, "entropy": 0.18628200888633728, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:14.369813Z", "loop": 1437, "env_steps": 883507199, "loss": 0.004717182833701372, "avg_return": 0.48458340764045715, "regret": 0.37882739305496216, "entropy": 0.16461525857448578, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:15.223209Z", "loop": 1438, "env_steps": 884121599, "loss": 0.0037063260097056627, "avg_return": 0.4868485629558563, "regret": 0.37882739305496216, "entropy": 0.15859583020210266, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:16.076881Z", "loop": 1439, "env_steps": 884735999, "loss": 0.0039299000054597855, "avg_return": 0.4927411377429962, "regret": 0.37882739305496216, "entropy": 0.14727486670017242, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:16.968934Z", "loop": 1440, "env_steps": 885350399, "loss": 0.003288569627329707, "avg_return": 0.48754364252090454, "regret": 0.37683987617492676, "entropy": 0.1427733153104782, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:17.822290Z", "loop": 1441, "env_steps": 885964799, "loss": 0.003167165908962488, "avg_return": 0.4819341003894806, "regret": 0.37683987617492676, "entropy": 0.13499365746974945, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:18.674088Z", "loop": 1442, "env_steps": 886579199, "loss": 0.0031137510668486357, "avg_return": 0.4851096272468567, "regret": 0.37683987617492676, "entropy": 0.1337513029575348, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:19.526921Z", "loop": 1443, "env_steps": 887193599, "loss": 0.002915482735261321, "avg_return": 0.491473913192749, "regret": 0.37683987617492676, "entropy": 0.1365402340888977, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:20.379827Z", "loop": 1444, "env_steps": 887807999, "loss": 0.0033155709970742464, "avg_return": 0.4943464398384094, "regret": 0.37683987617492676, "entropy": 0.14424842596054077, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:21.273629Z", "loop": 1445, "env_steps": 888422399, "loss": 0.0031987447291612625, "avg_return": 0.4907441735267639, "regret": 0.3779336214065552, "entropy": 0.14443060755729675, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:22.126469Z", "loop": 1446, "env_steps": 889036799, "loss": 0.003281340003013611, "avg_return": 0.48666444420814514, "regret": 0.3779336214065552, "entropy": 0.15102237462997437, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:22.979144Z", "loop": 1447, "env_steps": 889651199, "loss": 0.0036103129386901855, "avg_return": 0.48277994990348816, "regret": 0.3779336214065552, "entropy": 0.14644737541675568, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:23.832372Z", "loop": 1448, "env_steps": 890265599, "loss": 0.003181690815836191, "avg_return": 0.4811214208602905, "regret": 0.3779336214065552, "entropy": 0.15085525810718536, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:24.685645Z", "loop": 1449, "env_steps": 890879999, "loss": 0.002736148191615939, "avg_return": 0.48167359828948975, "regret": 0.3779336214065552, "entropy": 0.13693825900554657, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:25.579806Z", "loop": 1450, "env_steps": 891494399, "loss": 0.0025912325363606215, "avg_return": 0.48400065302848816, "regret": 0.3820526897907257, "entropy": 0.1299719214439392, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:26.433705Z", "loop": 1451, "env_steps": 892108799, "loss": 0.002074501011520624, "avg_return": 0.4784368574619293, "regret": 0.3820526897907257, "entropy": 0.12557967007160187, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:27.287092Z", "loop": 1452, "env_steps": 892723199, "loss": 0.0022073767613619566, "avg_return": 0.4793991148471832, "regret": 0.3820526897907257, "entropy": 0.11791335791349411, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:28.141344Z", "loop": 1453, "env_steps": 893337599, "loss": 0.002202858915552497, "avg_return": 0.4738003611564636, "regret": 0.3820526897907257, "entropy": 0.12132776528596878, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:28.995503Z", "loop": 1454, "env_steps": 893951999, "loss": 0.002215687185525894, "avg_return": 0.48234161734580994, "regret": 0.3820526897907257, "entropy": 0.13140259683132172, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:29.889369Z", "loop": 1455, "env_steps": 894566399, "loss": 0.0027846437878906727, "avg_return": 0.4811975359916687, "regret": 0.379591166973114, "entropy": 0.14593830704689026, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:30.741526Z", "loop": 1456, "env_steps": 895180799, "loss": 0.0027547685895115137, "avg_return": 0.4795108735561371, "regret": 0.379591166973114, "entropy": 0.15338164567947388, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:31.593693Z", "loop": 1457, "env_steps": 895795199, "loss": 0.003777309088036418, "avg_return": 0.49067074060440063, "regret": 0.379591166973114, "entropy": 0.15428526699543, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:32.447736Z", "loop": 1458, "env_steps": 896409599, "loss": 0.003607050748541951, "avg_return": 0.48678672313690186, "regret": 0.379591166973114, "entropy": 0.15588605403900146, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:33.301072Z", "loop": 1459, "env_steps": 897023999, "loss": 0.003509954083710909, "avg_return": 0.4821070432662964, "regret": 0.379591166973114, "entropy": 0.15942911803722382, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:34.192673Z", "loop": 1460, "env_steps": 897638399, "loss": 0.0038050932344049215, "avg_return": 0.49015992879867554, "regret": 0.3761991560459137, "entropy": 0.14464472234249115, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:35.045330Z", "loop": 1461, "env_steps": 898252799, "loss": 0.0032668255735188723, "avg_return": 0.488657146692276, "regret": 0.3761991560459137, "entropy": 0.14505694806575775, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:35.898875Z", "loop": 1462, "env_steps": 898867199, "loss": 0.003399337874725461, "avg_return": 0.47833502292633057, "regret": 0.3761991560459137, "entropy": 0.1433446705341339, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:36.751582Z", "loop": 1463, "env_steps": 899481599, "loss": 0.0037696417421102524, "avg_return": 0.48839595913887024, "regret": 0.3761991560459137, "entropy": 0.14299601316452026, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:37.603719Z", "loop": 1464, "env_steps": 900095999, "loss": 0.0037251703906804323, "avg_return": 0.4886656701564789, "regret": 0.3761991560459137, "entropy": 0.14923325181007385, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:38.494507Z", "loop": 1465, "env_steps": 900710399, "loss": 0.003656931919977069, "avg_return": 0.48109158873558044, "regret": 0.37723538279533386, "entropy": 0.1532052457332611, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:39.348603Z", "loop": 1466, "env_steps": 901324799, "loss": 0.00447814678773284, "avg_return": 0.4841935336589813, "regret": 0.37723538279533386, "entropy": 0.16281987726688385, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:40.201404Z", "loop": 1467, "env_steps": 901939199, "loss": 0.004504496231675148, "avg_return": 0.4830497205257416, "regret": 0.37723538279533386, "entropy": 0.16939839720726013, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:41.055070Z", "loop": 1468, "env_steps": 902553599, "loss": 0.005204060114920139, "avg_return": 0.488002747297287, "regret": 0.37723538279533386, "entropy": 0.17630524933338165, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:41.906887Z", "loop": 1469, "env_steps": 903167999, "loss": 0.006169350352138281, "avg_return": 0.48338523507118225, "regret": 0.37723538279533386, "entropy": 0.18855850398540497, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:42.800502Z", "loop": 1470, "env_steps": 903782399, "loss": 0.0068261283449828625, "avg_return": 0.4852907359600067, "regret": 0.38127195835113525, "entropy": 0.18725867569446564, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:43.654023Z", "loop": 1471, "env_steps": 904396799, "loss": 0.00686312559992075, "avg_return": 0.47490814328193665, "regret": 0.38127195835113525, "entropy": 0.18078124523162842, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:44.506561Z", "loop": 1472, "env_steps": 905011199, "loss": 0.006371455732733011, "avg_return": 0.47116053104400635, "regret": 0.38127195835113525, "entropy": 0.17583033442497253, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:45.359315Z", "loop": 1473, "env_steps": 905625599, "loss": 0.006743574049323797, "avg_return": 0.48150596022605896, "regret": 0.38127195835113525, "entropy": 0.17681163549423218, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:46.212424Z", "loop": 1474, "env_steps": 906239999, "loss": 0.0064399815164506435, "avg_return": 0.4796733856201172, "regret": 0.38127195835113525, "entropy": 0.1677950769662857, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:47.105440Z", "loop": 1475, "env_steps": 906854399, "loss": 0.006454973015934229, "avg_return": 0.48066824674606323, "regret": 0.3819962441921234, "entropy": 0.17752282321453094, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:47.958845Z", "loop": 1476, "env_steps": 907468799, "loss": 0.006575570907443762, "avg_return": 0.4821559190750122, "regret": 0.3819962441921234, "entropy": 0.16600529849529266, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:48.811642Z", "loop": 1477, "env_steps": 908083199, "loss": 0.006369839888066053, "avg_return": 0.4835440218448639, "regret": 0.3819962441921234, "entropy": 0.17018374800682068, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:49.664848Z", "loop": 1478, "env_steps": 908697599, "loss": 0.005629958119243383, "avg_return": 0.4765236973762512, "regret": 0.3819962441921234, "entropy": 0.16354142129421234, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:50.518678Z", "loop": 1479, "env_steps": 909311999, "loss": 0.005906812380999327, "avg_return": 0.4817241430282593, "regret": 0.3819962441921234, "entropy": 0.1720084547996521, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:51.411127Z", "loop": 1480, "env_steps": 909926399, "loss": 0.005879815202206373, "avg_return": 0.48372742533683777, "regret": 0.3779563307762146, "entropy": 0.17378096282482147, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:52.263419Z", "loop": 1481, "env_steps": 910540799, "loss": 0.005420948378741741, "avg_return": 0.4910769760608673, "regret": 0.3779563307762146, "entropy": 0.16613255441188812, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:53.117587Z", "loop": 1482, "env_steps": 911155199, "loss": 0.004360831342637539, "avg_return": 0.4867444932460785, "regret": 0.3779563307762146, "entropy": 0.15936365723609924, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:53.970420Z", "loop": 1483, "env_steps": 911769599, "loss": 0.003610748564824462, "avg_return": 0.4827808737754822, "regret": 0.3779563307762146, "entropy": 0.15265600383281708, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:54.823348Z", "loop": 1484, "env_steps": 912383999, "loss": 0.0032868520356714725, "avg_return": 0.48117637634277344, "regret": 0.3779563307762146, "entropy": 0.15413245558738708, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:55.715844Z", "loop": 1485, "env_steps": 912998399, "loss": 0.0028305898886173964, "avg_return": 0.4793289303779602, "regret": 0.37788641452789307, "entropy": 0.15746773779392242, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:56.569468Z", "loop": 1486, "env_steps": 913612799, "loss": 0.0029727185610681772, "avg_return": 0.4881933629512787, "regret": 0.37788641452789307, "entropy": 0.14245125651359558, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:57.422418Z", "loop": 1487, "env_steps": 914227199, "loss": 0.0028092944994568825, "avg_return": 0.4843699336051941, "regret": 0.37788641452789307, "entropy": 0.1347855031490326, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:58.274454Z", "loop": 1488, "env_steps": 914841599, "loss": 0.0032724495977163315, "avg_return": 0.48656219244003296, "regret": 0.37788641452789307, "entropy": 0.14234106242656708, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:44:59.127211Z", "loop": 1489, "env_steps": 915455999, "loss": 0.003409832715988159, "avg_return": 0.48409464955329895, "regret": 0.37788641452789307, "entropy": 0.1537237912416458, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:00.020537Z", "loop": 1490, "env_steps": 916070399, "loss": 0.0033832737244665623, "avg_return": 0.4896904230117798, "regret": 0.3800027072429657, "entropy": 0.14727666974067688, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:00.872534Z", "loop": 1491, "env_steps": 916684799, "loss": 0.0032949228771030903, "avg_return": 0.4776443541049957, "regret": 0.3800027072429657, "entropy": 0.1540372222661972, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:01.726668Z", "loop": 1492, "env_steps": 917299199, "loss": 0.0037699842359870672, "avg_return": 0.48927420377731323, "regret": 0.3800027072429657, "entropy": 0.15276238322257996, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:02.581776Z", "loop": 1493, "env_steps": 917913599, "loss": 0.0033766229171305895, "avg_return": 0.4942089319229126, "regret": 0.3800027072429657, "entropy": 0.15116555988788605, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:03.435121Z", "loop": 1494, "env_steps": 918527999, "loss": 0.0033692873548716307, "avg_return": 0.4856071174144745, "regret": 0.3800027072429657, "entropy": 0.14945901930332184, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:04.329334Z", "loop": 1495, "env_steps": 919142399, "loss": 0.003368399804458022, "avg_return": 0.4903647005558014, "regret": 0.38088443875312805, "entropy": 0.1425367295742035, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:05.183225Z", "loop": 1496, "env_steps": 919756799, "loss": 0.0029331704135984182, "avg_return": 0.4919806122779846, "regret": 0.38088443875312805, "entropy": 0.14654716849327087, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:06.037693Z", "loop": 1497, "env_steps": 920371199, "loss": 0.002571169286966324, "avg_return": 0.48526453971862793, "regret": 0.38088443875312805, "entropy": 0.14121204614639282, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:06.890238Z", "loop": 1498, "env_steps": 920985599, "loss": 0.002271008212119341, "avg_return": 0.4832611083984375, "regret": 0.38088443875312805, "entropy": 0.12929470837116241, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:07.743952Z", "loop": 1499, "env_steps": 921599999, "loss": 0.002057149773463607, "avg_return": 0.4776547849178314, "regret": 0.38088443875312805, "entropy": 0.12682917714118958, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:08.636249Z", "loop": 1500, "env_steps": 922214399, "loss": 0.002213921630755067, "avg_return": 0.47819551825523376, "regret": 0.3809831142425537, "entropy": 0.1254788041114807, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:09.491582Z", "loop": 1501, "env_steps": 922828799, "loss": 0.0021480435971170664, "avg_return": 0.4811519384384155, "regret": 0.3809831142425537, "entropy": 0.12931537628173828, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:10.344194Z", "loop": 1502, "env_steps": 923443199, "loss": 0.0021879395935684443, "avg_return": 0.4865082800388336, "regret": 0.3809831142425537, "entropy": 0.12123484909534454, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:11.197063Z", "loop": 1503, "env_steps": 924057599, "loss": 0.002234711078926921, "avg_return": 0.47898849844932556, "regret": 0.3809831142425537, "entropy": 0.1219068095088005, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:12.050184Z", "loop": 1504, "env_steps": 924671999, "loss": 0.0021994775161147118, "avg_return": 0.4900946021080017, "regret": 0.3809831142425537, "entropy": 0.1164582222700119, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:12.942861Z", "loop": 1505, "env_steps": 925286399, "loss": 0.002522932132706046, "avg_return": 0.48806092143058777, "regret": 0.37867823243141174, "entropy": 0.11799955368041992, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:13.795613Z", "loop": 1506, "env_steps": 925900799, "loss": 0.002424837090075016, "avg_return": 0.48586827516555786, "regret": 0.37867823243141174, "entropy": 0.12546126544475555, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:14.648255Z", "loop": 1507, "env_steps": 926515199, "loss": 0.0027185676153749228, "avg_return": 0.48583680391311646, "regret": 0.37867823243141174, "entropy": 0.1316380351781845, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:15.502066Z", "loop": 1508, "env_steps": 927129599, "loss": 0.0026852029841393232, "avg_return": 0.4850159287452698, "regret": 0.37867823243141174, "entropy": 0.13178569078445435, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:16.355360Z", "loop": 1509, "env_steps": 927743999, "loss": 0.003054035594686866, "avg_return": 0.48767971992492676, "regret": 0.37867823243141174, "entropy": 0.13983674347400665, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:17.247475Z", "loop": 1510, "env_steps": 928358399, "loss": 0.0031286110170185566, "avg_return": 0.482330322265625, "regret": 0.37666380405426025, "entropy": 0.1403535157442093, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:18.099630Z", "loop": 1511, "env_steps": 928972799, "loss": 0.0031472542323172092, "avg_return": 0.48404014110565186, "regret": 0.37666380405426025, "entropy": 0.13860857486724854, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:18.952867Z", "loop": 1512, "env_steps": 929587199, "loss": 0.003478705184534192, "avg_return": 0.4906575679779053, "regret": 0.37666380405426025, "entropy": 0.14174899458885193, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:19.806104Z", "loop": 1513, "env_steps": 930201599, "loss": 0.0036288206465542316, "avg_return": 0.48914897441864014, "regret": 0.37666380405426025, "entropy": 0.14482371509075165, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:20.660115Z", "loop": 1514, "env_steps": 930815999, "loss": 0.0034601190127432346, "avg_return": 0.48736104369163513, "regret": 0.37666380405426025, "entropy": 0.14614726603031158, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:21.552174Z", "loop": 1515, "env_steps": 931430399, "loss": 0.0038628820329904556, "avg_return": 0.4939573407173157, "regret": 0.376552939414978, "entropy": 0.14611504971981049, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:22.405005Z", "loop": 1516, "env_steps": 932044799, "loss": 0.004167427774518728, "avg_return": 0.4847692847251892, "regret": 0.376552939414978, "entropy": 0.1478639394044876, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:23.259306Z", "loop": 1517, "env_steps": 932659199, "loss": 0.004036674275994301, "avg_return": 0.48242732882499695, "regret": 0.376552939414978, "entropy": 0.14693933725357056, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:24.113919Z", "loop": 1518, "env_steps": 933273599, "loss": 0.0043975841253995895, "avg_return": 0.48705074191093445, "regret": 0.376552939414978, "entropy": 0.14973199367523193, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:24.968363Z", "loop": 1519, "env_steps": 933887999, "loss": 0.003767595859244466, "avg_return": 0.48142802715301514, "regret": 0.376552939414978, "entropy": 0.1427592784166336, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:25.862323Z", "loop": 1520, "env_steps": 934502399, "loss": 0.0037060824688524008, "avg_return": 0.4826124310493469, "regret": 0.376880019903183, "entropy": 0.14291347563266754, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:26.715076Z", "loop": 1521, "env_steps": 935116799, "loss": 0.004273875616490841, "avg_return": 0.4844401180744171, "regret": 0.376880019903183, "entropy": 0.14866642653942108, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:27.567892Z", "loop": 1522, "env_steps": 935731199, "loss": 0.003839756129309535, "avg_return": 0.49228715896606445, "regret": 0.376880019903183, "entropy": 0.13766375184059143, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:28.420132Z", "loop": 1523, "env_steps": 936345599, "loss": 0.0033838474191725254, "avg_return": 0.4807344675064087, "regret": 0.376880019903183, "entropy": 0.1382562667131424, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:29.272986Z", "loop": 1524, "env_steps": 936959999, "loss": 0.00380551815032959, "avg_return": 0.489339143037796, "regret": 0.376880019903183, "entropy": 0.13732248544692993, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:30.164865Z", "loop": 1525, "env_steps": 937574399, "loss": 0.0032208424527198076, "avg_return": 0.4933062791824341, "regret": 0.3768860995769501, "entropy": 0.13149936497211456, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:31.019194Z", "loop": 1526, "env_steps": 938188799, "loss": 0.0034328631591051817, "avg_return": 0.4875062108039856, "regret": 0.3768860995769501, "entropy": 0.1235194057226181, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:31.873059Z", "loop": 1527, "env_steps": 938803199, "loss": 0.00375336199067533, "avg_return": 0.4907323718070984, "regret": 0.3768860995769501, "entropy": 0.13125865161418915, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:32.727079Z", "loop": 1528, "env_steps": 939417599, "loss": 0.0037421935703605413, "avg_return": 0.4837318956851959, "regret": 0.3768860995769501, "entropy": 0.12914912402629852, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:33.581287Z", "loop": 1529, "env_steps": 940031999, "loss": 0.003696595085784793, "avg_return": 0.48404669761657715, "regret": 0.3768860995769501, "entropy": 0.1328481137752533, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:34.474454Z", "loop": 1530, "env_steps": 940646399, "loss": 0.003818390192463994, "avg_return": 0.48481905460357666, "regret": 0.37729883193969727, "entropy": 0.13897378742694855, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:35.327648Z", "loop": 1531, "env_steps": 941260799, "loss": 0.0036468468606472015, "avg_return": 0.48313090205192566, "regret": 0.37729883193969727, "entropy": 0.13779228925704956, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:36.182726Z", "loop": 1532, "env_steps": 941875199, "loss": 0.003970317076891661, "avg_return": 0.48931804299354553, "regret": 0.37729883193969727, "entropy": 0.13950809836387634, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:37.036960Z", "loop": 1533, "env_steps": 942489599, "loss": 0.004087693523615599, "avg_return": 0.491176575422287, "regret": 0.37729883193969727, "entropy": 0.1467452198266983, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:37.889921Z", "loop": 1534, "env_steps": 943103999, "loss": 0.004369260277599096, "avg_return": 0.48780956864356995, "regret": 0.37729883193969727, "entropy": 0.14014454185962677, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:38.783708Z", "loop": 1535, "env_steps": 943718399, "loss": 0.00392684293910861, "avg_return": 0.4878447651863098, "regret": 0.37581920623779297, "entropy": 0.14054051041603088, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:39.638246Z", "loop": 1536, "env_steps": 944332799, "loss": 0.003751179203391075, "avg_return": 0.4826717674732208, "regret": 0.37581920623779297, "entropy": 0.14313241839408875, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:40.491881Z", "loop": 1537, "env_steps": 944947199, "loss": 0.0037931681144982576, "avg_return": 0.4782177805900574, "regret": 0.37581920623779297, "entropy": 0.1475982815027237, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:41.344175Z", "loop": 1538, "env_steps": 945561599, "loss": 0.004560398403555155, "avg_return": 0.4863497018814087, "regret": 0.37581920623779297, "entropy": 0.15248654782772064, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:42.197170Z", "loop": 1539, "env_steps": 946175999, "loss": 0.0051314570009708405, "avg_return": 0.4884064793586731, "regret": 0.37581920623779297, "entropy": 0.1640557050704956, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:43.090616Z", "loop": 1540, "env_steps": 946790399, "loss": 0.005588214378803968, "avg_return": 0.4937419891357422, "regret": 0.3763357102870941, "entropy": 0.1629641354084015, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:43.944408Z", "loop": 1541, "env_steps": 947404799, "loss": 0.00523395324125886, "avg_return": 0.4849902391433716, "regret": 0.3763357102870941, "entropy": 0.1680345982313156, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:44.797926Z", "loop": 1542, "env_steps": 948019199, "loss": 0.005740107037127018, "avg_return": 0.4822380542755127, "regret": 0.3763357102870941, "entropy": 0.16848282516002655, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:45.650849Z", "loop": 1543, "env_steps": 948633599, "loss": 0.004397324752062559, "avg_return": 0.48683640360832214, "regret": 0.3763357102870941, "entropy": 0.15685860812664032, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:46.504562Z", "loop": 1544, "env_steps": 949247999, "loss": 0.0047597275115549564, "avg_return": 0.48282620310783386, "regret": 0.3763357102870941, "entropy": 0.15748168528079987, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:47.397529Z", "loop": 1545, "env_steps": 949862399, "loss": 0.004603612702339888, "avg_return": 0.48442912101745605, "regret": 0.37628409266471863, "entropy": 0.15747633576393127, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:48.250267Z", "loop": 1546, "env_steps": 950476799, "loss": 0.004487146157771349, "avg_return": 0.4891887605190277, "regret": 0.37628409266471863, "entropy": 0.1524771749973297, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:49.102869Z", "loop": 1547, "env_steps": 951091199, "loss": 0.004494314081966877, "avg_return": 0.4902345538139343, "regret": 0.37628409266471863, "entropy": 0.1483154445886612, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:49.956093Z", "loop": 1548, "env_steps": 951705599, "loss": 0.0037979010958224535, "avg_return": 0.48624593019485474, "regret": 0.37628409266471863, "entropy": 0.13942375779151917, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:50.809207Z", "loop": 1549, "env_steps": 952319999, "loss": 0.0035485823173075914, "avg_return": 0.49162447452545166, "regret": 0.37628409266471863, "entropy": 0.13895463943481445, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:51.701715Z", "loop": 1550, "env_steps": 952934399, "loss": 0.0034089807886630297, "avg_return": 0.4864567220211029, "regret": 0.37622153759002686, "entropy": 0.1302117556333542, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:52.555075Z", "loop": 1551, "env_steps": 953548799, "loss": 0.0032375664450228214, "avg_return": 0.4909264147281647, "regret": 0.37622153759002686, "entropy": 0.12574422359466553, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:53.407780Z", "loop": 1552, "env_steps": 954163199, "loss": 0.003330538747832179, "avg_return": 0.4969801902770996, "regret": 0.37622153759002686, "entropy": 0.12487418949604034, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:54.260637Z", "loop": 1553, "env_steps": 954777599, "loss": 0.0030375926289707422, "avg_return": 0.4857589304447174, "regret": 0.37622153759002686, "entropy": 0.12605029344558716, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:55.113619Z", "loop": 1554, "env_steps": 955391999, "loss": 0.0026257026474922895, "avg_return": 0.48928600549697876, "regret": 0.37622153759002686, "entropy": 0.12559431791305542, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:56.004818Z", "loop": 1555, "env_steps": 956006399, "loss": 0.0026219969149678946, "avg_return": 0.4878639876842499, "regret": 0.37646567821502686, "entropy": 0.12642908096313477, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:56.857549Z", "loop": 1556, "env_steps": 956620799, "loss": 0.0027510884683579206, "avg_return": 0.4868547320365906, "regret": 0.37646567821502686, "entropy": 0.11996204406023026, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:57.709664Z", "loop": 1557, "env_steps": 957235199, "loss": 0.0027116634882986546, "avg_return": 0.4884989559650421, "regret": 0.37646567821502686, "entropy": 0.11732218414545059, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:58.562509Z", "loop": 1558, "env_steps": 957849599, "loss": 0.0025722174905240536, "avg_return": 0.49050793051719666, "regret": 0.37646567821502686, "entropy": 0.11976949870586395, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:45:59.415164Z", "loop": 1559, "env_steps": 958463999, "loss": 0.0028018129523843527, "avg_return": 0.47996899485588074, "regret": 0.37646567821502686, "entropy": 0.12125692516565323, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:00.307106Z", "loop": 1560, "env_steps": 959078399, "loss": 0.0029240301810204983, "avg_return": 0.4843250513076782, "regret": 0.37596404552459717, "entropy": 0.11824445426464081, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:01.159703Z", "loop": 1561, "env_steps": 959692799, "loss": 0.002852134872227907, "avg_return": 0.48368602991104126, "regret": 0.37596404552459717, "entropy": 0.12383922934532166, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:02.012022Z", "loop": 1562, "env_steps": 960307199, "loss": 0.003009147010743618, "avg_return": 0.48405590653419495, "regret": 0.37596404552459717, "entropy": 0.13056780397891998, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:02.865908Z", "loop": 1563, "env_steps": 960921599, "loss": 0.003346891375258565, "avg_return": 0.4907667636871338, "regret": 0.37596404552459717, "entropy": 0.13381199538707733, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:03.719321Z", "loop": 1564, "env_steps": 961535999, "loss": 0.003474115626886487, "avg_return": 0.4934312105178833, "regret": 0.37596404552459717, "entropy": 0.13645443320274353, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:04.610254Z", "loop": 1565, "env_steps": 962150399, "loss": 0.0036084551829844713, "avg_return": 0.48386746644973755, "regret": 0.3766312897205353, "entropy": 0.13211235404014587, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:05.462831Z", "loop": 1566, "env_steps": 962764799, "loss": 0.0029840886127203703, "avg_return": 0.49085068702697754, "regret": 0.3766312897205353, "entropy": 0.12566815316677094, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:06.316343Z", "loop": 1567, "env_steps": 963379199, "loss": 0.002610438037663698, "avg_return": 0.48811453580856323, "regret": 0.3766312897205353, "entropy": 0.12077084183692932, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:07.170539Z", "loop": 1568, "env_steps": 963993599, "loss": 0.0027674438897520304, "avg_return": 0.4883509576320648, "regret": 0.3766312897205353, "entropy": 0.12212233990430832, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:08.023032Z", "loop": 1569, "env_steps": 964607999, "loss": 0.002801289549097419, "avg_return": 0.4783959686756134, "regret": 0.3766312897205353, "entropy": 0.12291160225868225, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:08.914862Z", "loop": 1570, "env_steps": 965222399, "loss": 0.0027659123297780752, "avg_return": 0.48268067836761475, "regret": 0.3767748773097992, "entropy": 0.1219581887125969, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:09.769171Z", "loop": 1571, "env_steps": 965836799, "loss": 0.0027162351179867983, "avg_return": 0.4877248704433441, "regret": 0.3767748773097992, "entropy": 0.12294390052556992, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:10.622392Z", "loop": 1572, "env_steps": 966451199, "loss": 0.0025475460570305586, "avg_return": 0.4851890206336975, "regret": 0.3767748773097992, "entropy": 0.12231927365064621, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:11.475032Z", "loop": 1573, "env_steps": 967065599, "loss": 0.0023807210382074118, "avg_return": 0.4787788987159729, "regret": 0.3767748773097992, "entropy": 0.11888869106769562, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:12.327687Z", "loop": 1574, "env_steps": 967679999, "loss": 0.002437330549582839, "avg_return": 0.48802420496940613, "regret": 0.3767748773097992, "entropy": 0.12076324969530106, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:13.219835Z", "loop": 1575, "env_steps": 968294399, "loss": 0.0025752822402864695, "avg_return": 0.49187278747558594, "regret": 0.37774068117141724, "entropy": 0.11393202096223831, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:14.072651Z", "loop": 1576, "env_steps": 968908799, "loss": 0.0027674527373164892, "avg_return": 0.4904136657714844, "regret": 0.37774068117141724, "entropy": 0.1169632151722908, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:14.925369Z", "loop": 1577, "env_steps": 969523199, "loss": 0.0026621914003044367, "avg_return": 0.49229392409324646, "regret": 0.37774068117141724, "entropy": 0.11385229974985123, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:15.778614Z", "loop": 1578, "env_steps": 970137599, "loss": 0.002527465345337987, "avg_return": 0.4890739619731903, "regret": 0.37774068117141724, "entropy": 0.11962403357028961, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:16.632021Z", "loop": 1579, "env_steps": 970751999, "loss": 0.0025323154404759407, "avg_return": 0.4872133433818817, "regret": 0.37774068117141724, "entropy": 0.12479231506586075, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:17.526336Z", "loop": 1580, "env_steps": 971366399, "loss": 0.002668006345629692, "avg_return": 0.48716631531715393, "regret": 0.3766712546348572, "entropy": 0.12257412821054459, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:18.379259Z", "loop": 1581, "env_steps": 971980799, "loss": 0.0027423768769949675, "avg_return": 0.49470236897468567, "regret": 0.3766712546348572, "entropy": 0.12220103293657303, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:19.231389Z", "loop": 1582, "env_steps": 972595199, "loss": 0.002742880955338478, "avg_return": 0.48696768283843994, "regret": 0.3766712546348572, "entropy": 0.1294993758201599, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:20.085069Z", "loop": 1583, "env_steps": 973209599, "loss": 0.0029866392724215984, "avg_return": 0.49227508902549744, "regret": 0.3766712546348572, "entropy": 0.13087396323680878, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:20.936840Z", "loop": 1584, "env_steps": 973823999, "loss": 0.0029473030008375645, "avg_return": 0.48842835426330566, "regret": 0.3766712546348572, "entropy": 0.13083575665950775, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:21.829013Z", "loop": 1585, "env_steps": 974438399, "loss": 0.0033039667177945375, "avg_return": 0.48852550983428955, "regret": 0.37614309787750244, "entropy": 0.13923725485801697, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:22.682723Z", "loop": 1586, "env_steps": 975052799, "loss": 0.003047207137569785, "avg_return": 0.4812909960746765, "regret": 0.37614309787750244, "entropy": 0.13831833004951477, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:23.536497Z", "loop": 1587, "env_steps": 975667199, "loss": 0.0036673916038125753, "avg_return": 0.49390193819999695, "regret": 0.37614309787750244, "entropy": 0.14104841649532318, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:24.388907Z", "loop": 1588, "env_steps": 976281599, "loss": 0.003832746297121048, "avg_return": 0.4938051402568817, "regret": 0.37614309787750244, "entropy": 0.1335361897945404, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:25.242986Z", "loop": 1589, "env_steps": 976895999, "loss": 0.003679385408759117, "avg_return": 0.4899497628211975, "regret": 0.37614309787750244, "entropy": 0.1438969224691391, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:26.136524Z", "loop": 1590, "env_steps": 977510399, "loss": 0.00426110066473484, "avg_return": 0.4841611981391907, "regret": 0.37593594193458557, "entropy": 0.13494479656219482, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:26.990626Z", "loop": 1591, "env_steps": 978124799, "loss": 0.003880210919305682, "avg_return": 0.4962742328643799, "regret": 0.37593594193458557, "entropy": 0.13053707778453827, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:27.844132Z", "loop": 1592, "env_steps": 978739199, "loss": 0.003736014710739255, "avg_return": 0.4891059398651123, "regret": 0.37593594193458557, "entropy": 0.12429804354906082, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:28.696261Z", "loop": 1593, "env_steps": 979353599, "loss": 0.0033141360618174076, "avg_return": 0.4830809533596039, "regret": 0.37593594193458557, "entropy": 0.12347234040498734, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:29.549193Z", "loop": 1594, "env_steps": 979967999, "loss": 0.003500548889860511, "avg_return": 0.4868500828742981, "regret": 0.37593594193458557, "entropy": 0.1350506693124771, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:30.444060Z", "loop": 1595, "env_steps": 980582399, "loss": 0.0037486886139959097, "avg_return": 0.485487163066864, "regret": 0.3772038519382477, "entropy": 0.1354556530714035, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:31.297434Z", "loop": 1596, "env_steps": 981196799, "loss": 0.00419530039653182, "avg_return": 0.4877459704875946, "regret": 0.3772038519382477, "entropy": 0.13815513253211975, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:32.150359Z", "loop": 1597, "env_steps": 981811199, "loss": 0.004377918783575296, "avg_return": 0.48482152819633484, "regret": 0.3772038519382477, "entropy": 0.14182673394680023, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:33.003557Z", "loop": 1598, "env_steps": 982425599, "loss": 0.0043475013226270676, "avg_return": 0.4867047369480133, "regret": 0.3772038519382477, "entropy": 0.1400720477104187, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:33.857052Z", "loop": 1599, "env_steps": 983039999, "loss": 0.0045066112652421, "avg_return": 0.48072367906570435, "regret": 0.3772038519382477, "entropy": 0.14234469830989838, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:34.748856Z", "loop": 1600, "env_steps": 983654399, "loss": 0.004781268071383238, "avg_return": 0.49059733748435974, "regret": 0.37778440117836, "entropy": 0.1455586701631546, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:35.602989Z", "loop": 1601, "env_steps": 984268799, "loss": 0.004607060458511114, "avg_return": 0.48895174264907837, "regret": 0.37778440117836, "entropy": 0.14341047406196594, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:36.456255Z", "loop": 1602, "env_steps": 984883199, "loss": 0.004769425373524427, "avg_return": 0.49035122990608215, "regret": 0.37778440117836, "entropy": 0.14137469232082367, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:37.309511Z", "loop": 1603, "env_steps": 985497599, "loss": 0.004133382812142372, "avg_return": 0.4800495505332947, "regret": 0.37778440117836, "entropy": 0.14357809722423553, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:38.162448Z", "loop": 1604, "env_steps": 986111999, "loss": 0.004794844891875982, "avg_return": 0.48922958970069885, "regret": 0.37778440117836, "entropy": 0.1433759331703186, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:39.054903Z", "loop": 1605, "env_steps": 986726399, "loss": 0.0047662826254963875, "avg_return": 0.4853619635105133, "regret": 0.37691283226013184, "entropy": 0.14830078184604645, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:39.908403Z", "loop": 1606, "env_steps": 987340799, "loss": 0.004309545736759901, "avg_return": 0.48152956366539, "regret": 0.37691283226013184, "entropy": 0.14867939054965973, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:40.761167Z", "loop": 1607, "env_steps": 987955199, "loss": 0.00500040827319026, "avg_return": 0.4874116778373718, "regret": 0.37691283226013184, "entropy": 0.15098503232002258, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:41.613685Z", "loop": 1608, "env_steps": 988569599, "loss": 0.005332119297236204, "avg_return": 0.49371474981307983, "regret": 0.37691283226013184, "entropy": 0.15822194516658783, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:42.466526Z", "loop": 1609, "env_steps": 989183999, "loss": 0.005898651666939259, "avg_return": 0.48339948058128357, "regret": 0.37691283226013184, "entropy": 0.1551828682422638, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:43.359968Z", "loop": 1610, "env_steps": 989798399, "loss": 0.0056991721503436565, "avg_return": 0.48345428705215454, "regret": 0.377412885427475, "entropy": 0.15380850434303284, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:44.212630Z", "loop": 1611, "env_steps": 990412799, "loss": 0.004966266918927431, "avg_return": 0.47978833317756653, "regret": 0.377412885427475, "entropy": 0.15785373747348785, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:45.064493Z", "loop": 1612, "env_steps": 991027199, "loss": 0.005724448710680008, "avg_return": 0.4920032322406769, "regret": 0.377412885427475, "entropy": 0.15304242074489594, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:45.916836Z", "loop": 1613, "env_steps": 991641599, "loss": 0.005522018764168024, "avg_return": 0.4815545380115509, "regret": 0.377412885427475, "entropy": 0.15748409926891327, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:46.769863Z", "loop": 1614, "env_steps": 992255999, "loss": 0.005391236860305071, "avg_return": 0.4856278598308563, "regret": 0.377412885427475, "entropy": 0.15527155995368958, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:47.663652Z", "loop": 1615, "env_steps": 992870399, "loss": 0.0054135494865477085, "avg_return": 0.481171578168869, "regret": 0.3773811161518097, "entropy": 0.1562701314687729, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:48.515708Z", "loop": 1616, "env_steps": 993484799, "loss": 0.005523878149688244, "avg_return": 0.4765549898147583, "regret": 0.3773811161518097, "entropy": 0.15550492703914642, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:49.367859Z", "loop": 1617, "env_steps": 994099199, "loss": 0.005377871450036764, "avg_return": 0.4853629767894745, "regret": 0.3773811161518097, "entropy": 0.15801799297332764, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:50.221657Z", "loop": 1618, "env_steps": 994713599, "loss": 0.005581419449299574, "avg_return": 0.4836149215698242, "regret": 0.3773811161518097, "entropy": 0.15834492444992065, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:51.074717Z", "loop": 1619, "env_steps": 995327999, "loss": 0.00551833538338542, "avg_return": 0.4795992076396942, "regret": 0.3773811161518097, "entropy": 0.15277831256389618, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:51.966375Z", "loop": 1620, "env_steps": 995942399, "loss": 0.005435849539935589, "avg_return": 0.4860735833644867, "regret": 0.37909752130508423, "entropy": 0.1522674709558487, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:52.818139Z", "loop": 1621, "env_steps": 996556799, "loss": 0.0059285699389874935, "avg_return": 0.485983282327652, "regret": 0.37909752130508423, "entropy": 0.15943792462348938, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:53.670660Z", "loop": 1622, "env_steps": 997171199, "loss": 0.006067745387554169, "avg_return": 0.49199941754341125, "regret": 0.37909752130508423, "entropy": 0.15769332647323608, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:54.523596Z", "loop": 1623, "env_steps": 997785599, "loss": 0.006024960428476334, "avg_return": 0.4906872808933258, "regret": 0.37909752130508423, "entropy": 0.16181530058383942, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:55.377078Z", "loop": 1624, "env_steps": 998399999, "loss": 0.00518915755674243, "avg_return": 0.4855043590068817, "regret": 0.37909752130508423, "entropy": 0.1568273901939392, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:56.270278Z", "loop": 1625, "env_steps": 999014399, "loss": 0.004935537930577993, "avg_return": 0.48934200406074524, "regret": 0.37703973054885864, "entropy": 0.15567384660243988, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:57.124191Z", "loop": 1626, "env_steps": 999628799, "loss": 0.004459933843463659, "avg_return": 0.4869498908519745, "regret": 0.37703973054885864, "entropy": 0.15064440667629242, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:57.976903Z", "loop": 1627, "env_steps": 1000243199, "loss": 0.004392750561237335, "avg_return": 0.4850914776325226, "regret": 0.37703973054885864, "entropy": 0.15105143189430237, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:58.830787Z", "loop": 1628, "env_steps": 1000857599, "loss": 0.003900219453498721, "avg_return": 0.48142141103744507, "regret": 0.37703973054885864, "entropy": 0.1406969577074051, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:46:59.683405Z", "loop": 1629, "env_steps": 1001471999, "loss": 0.0043085599318146706, "avg_return": 0.49092134833335876, "regret": 0.37703973054885864, "entropy": 0.1373470425605774, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:00.575906Z", "loop": 1630, "env_steps": 1002086399, "loss": 0.003895805450156331, "avg_return": 0.4863224923610687, "regret": 0.37662452459335327, "entropy": 0.1416379064321518, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:01.429141Z", "loop": 1631, "env_steps": 1002700799, "loss": 0.004183572251349688, "avg_return": 0.4881151020526886, "regret": 0.37662452459335327, "entropy": 0.1350315809249878, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:02.282027Z", "loop": 1632, "env_steps": 1003315199, "loss": 0.003972706850618124, "avg_return": 0.4887031614780426, "regret": 0.37662452459335327, "entropy": 0.13850218057632446, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:03.135110Z", "loop": 1633, "env_steps": 1003929599, "loss": 0.003773709060624242, "avg_return": 0.4925358295440674, "regret": 0.37662452459335327, "entropy": 0.13765256106853485, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:03.988430Z", "loop": 1634, "env_steps": 1004543999, "loss": 0.0029919652733951807, "avg_return": 0.4841139316558838, "regret": 0.37662452459335327, "entropy": 0.12926167249679565, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:04.880799Z", "loop": 1635, "env_steps": 1005158399, "loss": 0.003123735310509801, "avg_return": 0.48800238966941833, "regret": 0.3761548101902008, "entropy": 0.13150463998317719, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:05.734219Z", "loop": 1636, "env_steps": 1005772799, "loss": 0.002854243153706193, "avg_return": 0.48832666873931885, "regret": 0.3761548101902008, "entropy": 0.13345707952976227, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:06.586906Z", "loop": 1637, "env_steps": 1006387199, "loss": 0.003045512828975916, "avg_return": 0.47677576541900635, "regret": 0.3761548101902008, "entropy": 0.12835347652435303, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:07.440548Z", "loop": 1638, "env_steps": 1007001599, "loss": 0.00331325875595212, "avg_return": 0.4890463352203369, "regret": 0.3761548101902008, "entropy": 0.13265787065029144, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:08.292671Z", "loop": 1639, "env_steps": 1007615999, "loss": 0.003550215158611536, "avg_return": 0.4908907115459442, "regret": 0.3761548101902008, "entropy": 0.13956281542778015, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:09.184156Z", "loop": 1640, "env_steps": 1008230399, "loss": 0.0035830133128911257, "avg_return": 0.4879080355167389, "regret": 0.37645992636680603, "entropy": 0.14365079998970032, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:10.036679Z", "loop": 1641, "env_steps": 1008844799, "loss": 0.003388086101040244, "avg_return": 0.4916376769542694, "regret": 0.37645992636680603, "entropy": 0.14702056348323822, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:10.890037Z", "loop": 1642, "env_steps": 1009459199, "loss": 0.0038367153611034155, "avg_return": 0.4871438145637512, "regret": 0.37645992636680603, "entropy": 0.14624394476413727, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:11.743158Z", "loop": 1643, "env_steps": 1010073599, "loss": 0.003467002185061574, "avg_return": 0.4859500825405121, "regret": 0.37645992636680603, "entropy": 0.1473025530576706, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:12.595336Z", "loop": 1644, "env_steps": 1010687999, "loss": 0.0039017987437546253, "avg_return": 0.4977703094482422, "regret": 0.37645992636680603, "entropy": 0.14705277979373932, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:13.487008Z", "loop": 1645, "env_steps": 1011302399, "loss": 0.0036065622698515654, "avg_return": 0.48762890696525574, "regret": 0.3760148882865906, "entropy": 0.14664921164512634, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:14.341717Z", "loop": 1646, "env_steps": 1011916799, "loss": 0.0035374255385249853, "avg_return": 0.4876711666584015, "regret": 0.3760148882865906, "entropy": 0.14293654263019562, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:15.194092Z", "loop": 1647, "env_steps": 1012531199, "loss": 0.003599159186705947, "avg_return": 0.47974538803100586, "regret": 0.3760148882865906, "entropy": 0.14942170679569244, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:16.046017Z", "loop": 1648, "env_steps": 1013145599, "loss": 0.0038007949478924274, "avg_return": 0.48464640974998474, "regret": 0.3760148882865906, "entropy": 0.14644691348075867, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:16.899024Z", "loop": 1649, "env_steps": 1013759999, "loss": 0.003390009282156825, "avg_return": 0.4869776964187622, "regret": 0.3760148882865906, "entropy": 0.14225633442401886, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:17.793001Z", "loop": 1650, "env_steps": 1014374399, "loss": 0.003920923452824354, "avg_return": 0.4920811653137207, "regret": 0.3757847249507904, "entropy": 0.14425122737884521, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:18.646413Z", "loop": 1651, "env_steps": 1014988799, "loss": 0.0034528838004916906, "avg_return": 0.4873043894767761, "regret": 0.3757847249507904, "entropy": 0.14543984830379486, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:19.499342Z", "loop": 1652, "env_steps": 1015603199, "loss": 0.003946080803871155, "avg_return": 0.4877679646015167, "regret": 0.3757847249507904, "entropy": 0.14427831768989563, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:20.351198Z", "loop": 1653, "env_steps": 1016217599, "loss": 0.003880436299368739, "avg_return": 0.48420441150665283, "regret": 0.3757847249507904, "entropy": 0.14130210876464844, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:21.203855Z", "loop": 1654, "env_steps": 1016831999, "loss": 0.003802485531195998, "avg_return": 0.48973533511161804, "regret": 0.3757847249507904, "entropy": 0.14511410892009735, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:22.094750Z", "loop": 1655, "env_steps": 1017446399, "loss": 0.0037707414012402296, "avg_return": 0.4923378527164459, "regret": 0.3758883774280548, "entropy": 0.14647112786769867, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:22.947953Z", "loop": 1656, "env_steps": 1018060799, "loss": 0.0034296244848519564, "avg_return": 0.4852593243122101, "regret": 0.3758883774280548, "entropy": 0.14325565099716187, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:23.800651Z", "loop": 1657, "env_steps": 1018675199, "loss": 0.003213200019672513, "avg_return": 0.48376619815826416, "regret": 0.3758883774280548, "entropy": 0.14084574580192566, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:24.654799Z", "loop": 1658, "env_steps": 1019289599, "loss": 0.0029066053684800863, "avg_return": 0.4793429672718048, "regret": 0.3758883774280548, "entropy": 0.14379139244556427, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:25.507482Z", "loop": 1659, "env_steps": 1019903999, "loss": 0.002601537387818098, "avg_return": 0.48435792326927185, "regret": 0.3758883774280548, "entropy": 0.12694251537322998, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:26.399649Z", "loop": 1660, "env_steps": 1020518399, "loss": 0.00283994828350842, "avg_return": 0.4868546724319458, "regret": 0.376727819442749, "entropy": 0.12712962925434113, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:27.252752Z", "loop": 1661, "env_steps": 1021132799, "loss": 0.0022076626773923635, "avg_return": 0.49224966764450073, "regret": 0.376727819442749, "entropy": 0.12356629967689514, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:28.105205Z", "loop": 1662, "env_steps": 1021747199, "loss": 0.0019131277222186327, "avg_return": 0.48147186636924744, "regret": 0.376727819442749, "entropy": 0.12185662984848022, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:28.957437Z", "loop": 1663, "env_steps": 1022361599, "loss": 0.0020169527269899845, "avg_return": 0.4850878119468689, "regret": 0.376727819442749, "entropy": 0.11712689697742462, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:29.811481Z", "loop": 1664, "env_steps": 1022975999, "loss": 0.002398737473413348, "avg_return": 0.4916006028652191, "regret": 0.376727819442749, "entropy": 0.11487138271331787, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:30.703917Z", "loop": 1665, "env_steps": 1023590399, "loss": 0.0022384379990398884, "avg_return": 0.4915478527545929, "regret": 0.3788492679595947, "entropy": 0.11903547495603561, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:31.558047Z", "loop": 1666, "env_steps": 1024204799, "loss": 0.0020343000069260597, "avg_return": 0.4864591956138611, "regret": 0.3788492679595947, "entropy": 0.12249452620744705, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:32.410640Z", "loop": 1667, "env_steps": 1024819199, "loss": 0.002208912279456854, "avg_return": 0.48898905515670776, "regret": 0.3788492679595947, "entropy": 0.11814983934164047, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:33.263551Z", "loop": 1668, "env_steps": 1025433599, "loss": 0.002375811105594039, "avg_return": 0.48882976174354553, "regret": 0.3788492679595947, "entropy": 0.12042147666215897, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:34.116890Z", "loop": 1669, "env_steps": 1026047999, "loss": 0.002594367368146777, "avg_return": 0.4859952926635742, "regret": 0.3788492679595947, "entropy": 0.13236112892627716, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:35.010704Z", "loop": 1670, "env_steps": 1026662399, "loss": 0.0035890338476747274, "avg_return": 0.49188151955604553, "regret": 0.3768536150455475, "entropy": 0.13641618192195892, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:35.863211Z", "loop": 1671, "env_steps": 1027276799, "loss": 0.003405928611755371, "avg_return": 0.48393404483795166, "regret": 0.3768536150455475, "entropy": 0.136758953332901, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:36.716376Z", "loop": 1672, "env_steps": 1027891199, "loss": 0.0042772600427269936, "avg_return": 0.49112173914909363, "regret": 0.3768536150455475, "entropy": 0.149505153298378, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:37.569734Z", "loop": 1673, "env_steps": 1028505599, "loss": 0.0040963501669466496, "avg_return": 0.4831709861755371, "regret": 0.3768536150455475, "entropy": 0.15289084613323212, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:38.423247Z", "loop": 1674, "env_steps": 1029119999, "loss": 0.00412985822185874, "avg_return": 0.4843815267086029, "regret": 0.3768536150455475, "entropy": 0.1534893810749054, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:39.316461Z", "loop": 1675, "env_steps": 1029734399, "loss": 0.0037713726051151752, "avg_return": 0.4821796715259552, "regret": 0.377065509557724, "entropy": 0.1506660282611847, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:40.168208Z", "loop": 1676, "env_steps": 1030348799, "loss": 0.004145070444792509, "avg_return": 0.4890376031398773, "regret": 0.377065509557724, "entropy": 0.1469690054655075, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:41.020926Z", "loop": 1677, "env_steps": 1030963199, "loss": 0.0037549424450844526, "avg_return": 0.485439658164978, "regret": 0.377065509557724, "entropy": 0.1477193534374237, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:41.875548Z", "loop": 1678, "env_steps": 1031577599, "loss": 0.003823963226750493, "avg_return": 0.49145975708961487, "regret": 0.377065509557724, "entropy": 0.13597941398620605, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:42.729912Z", "loop": 1679, "env_steps": 1032191999, "loss": 0.0037199785001575947, "avg_return": 0.48947352170944214, "regret": 0.377065509557724, "entropy": 0.14346125721931458, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:43.622581Z", "loop": 1680, "env_steps": 1032806399, "loss": 0.003689816687256098, "avg_return": 0.48993104696273804, "regret": 0.3765413165092468, "entropy": 0.14153851568698883, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:44.475320Z", "loop": 1681, "env_steps": 1033420799, "loss": 0.0034826842602342367, "avg_return": 0.48665478825569153, "regret": 0.3765413165092468, "entropy": 0.13907022774219513, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:45.328794Z", "loop": 1682, "env_steps": 1034035199, "loss": 0.0035965368151664734, "avg_return": 0.48580968379974365, "regret": 0.3765413165092468, "entropy": 0.13819068670272827, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:46.182413Z", "loop": 1683, "env_steps": 1034649599, "loss": 0.0035960383247584105, "avg_return": 0.48450812697410583, "regret": 0.3765413165092468, "entropy": 0.13716907799243927, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:47.035859Z", "loop": 1684, "env_steps": 1035263999, "loss": 0.0028156826738268137, "avg_return": 0.4844323992729187, "regret": 0.3765413165092468, "entropy": 0.13092559576034546, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:47.927779Z", "loop": 1685, "env_steps": 1035878399, "loss": 0.0022408992517739534, "avg_return": 0.4895476996898651, "regret": 0.37668800354003906, "entropy": 0.11446791142225266, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:48.780671Z", "loop": 1686, "env_steps": 1036492799, "loss": 0.0018148137023672462, "avg_return": 0.479998379945755, "regret": 0.37668800354003906, "entropy": 0.11093965172767639, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:49.633237Z", "loop": 1687, "env_steps": 1037107199, "loss": 0.0021116998977959156, "avg_return": 0.4876580536365509, "regret": 0.37668800354003906, "entropy": 0.10558965802192688, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:50.486513Z", "loop": 1688, "env_steps": 1037721599, "loss": 0.0022385295014828444, "avg_return": 0.49150386452674866, "regret": 0.37668800354003906, "entropy": 0.10908865928649902, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:51.339657Z", "loop": 1689, "env_steps": 1038335999, "loss": 0.0017843985697254539, "avg_return": 0.47834452986717224, "regret": 0.37668800354003906, "entropy": 0.10262969136238098, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:52.231821Z", "loop": 1690, "env_steps": 1038950399, "loss": 0.0020845173858106136, "avg_return": 0.4875299334526062, "regret": 0.38079941272735596, "entropy": 0.0962446928024292, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:53.085863Z", "loop": 1691, "env_steps": 1039564799, "loss": 0.0022203715052455664, "avg_return": 0.4856109619140625, "regret": 0.38079941272735596, "entropy": 0.10041719675064087, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:53.939556Z", "loop": 1692, "env_steps": 1040179199, "loss": 0.0016548525309190154, "avg_return": 0.4789433777332306, "regret": 0.38079941272735596, "entropy": 0.09959644079208374, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:54.793985Z", "loop": 1693, "env_steps": 1040793599, "loss": 0.0017226961208507419, "avg_return": 0.49110984802246094, "regret": 0.38079941272735596, "entropy": 0.10770413279533386, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:55.647216Z", "loop": 1694, "env_steps": 1041407999, "loss": 0.0019604444969445467, "avg_return": 0.4910339415073395, "regret": 0.38079941272735596, "entropy": 0.11449538171291351, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:56.540331Z", "loop": 1695, "env_steps": 1042022399, "loss": 0.002286798320710659, "avg_return": 0.4811488091945648, "regret": 0.3768427073955536, "entropy": 0.11652828752994537, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:57.393510Z", "loop": 1696, "env_steps": 1042636799, "loss": 0.002368255751207471, "avg_return": 0.48790889978408813, "regret": 0.3768427073955536, "entropy": 0.12322254478931427, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:58.246516Z", "loop": 1697, "env_steps": 1043251199, "loss": 0.002623052801936865, "avg_return": 0.4859808087348938, "regret": 0.3768427073955536, "entropy": 0.1257668286561966, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:59.099632Z", "loop": 1698, "env_steps": 1043865599, "loss": 0.0029040658846497536, "avg_return": 0.48663240671157837, "regret": 0.3768427073955536, "entropy": 0.12199455499649048, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:47:59.952431Z", "loop": 1699, "env_steps": 1044479999, "loss": 0.002742011798545718, "avg_return": 0.4856549799442291, "regret": 0.3768427073955536, "entropy": 0.1304505616426468, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:00.843717Z", "loop": 1700, "env_steps": 1045094399, "loss": 0.0029073525220155716, "avg_return": 0.48289287090301514, "regret": 0.3759302794933319, "entropy": 0.12918247282505035, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:01.696773Z", "loop": 1701, "env_steps": 1045708799, "loss": 0.003161650151014328, "avg_return": 0.4963097870349884, "regret": 0.3759302794933319, "entropy": 0.13233844935894012, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:02.550593Z", "loop": 1702, "env_steps": 1046323199, "loss": 0.0033054635860025883, "avg_return": 0.48276495933532715, "regret": 0.3759302794933319, "entropy": 0.1307036280632019, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:03.404621Z", "loop": 1703, "env_steps": 1046937599, "loss": 0.003899696981534362, "avg_return": 0.4929753839969635, "regret": 0.3759302794933319, "entropy": 0.12976603209972382, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:04.256742Z", "loop": 1704, "env_steps": 1047551999, "loss": 0.003304099664092064, "avg_return": 0.4845346212387085, "regret": 0.3759302794933319, "entropy": 0.1272333413362503, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:05.150863Z", "loop": 1705, "env_steps": 1048166399, "loss": 0.003163166344165802, "avg_return": 0.49467214941978455, "regret": 0.37550365924835205, "entropy": 0.12056539207696915, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:06.003920Z", "loop": 1706, "env_steps": 1048780799, "loss": 0.003604913828894496, "avg_return": 0.49813956022262573, "regret": 0.37550365924835205, "entropy": 0.11655784398317337, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:06.857557Z", "loop": 1707, "env_steps": 1049395199, "loss": 0.003118938999250531, "avg_return": 0.48948803544044495, "regret": 0.37550365924835205, "entropy": 0.12149177491664886, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:07.710506Z", "loop": 1708, "env_steps": 1050009599, "loss": 0.0033611382823437452, "avg_return": 0.4899899363517761, "regret": 0.37550365924835205, "entropy": 0.11519856750965118, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:08.563149Z", "loop": 1709, "env_steps": 1050623999, "loss": 0.003448605304583907, "avg_return": 0.48638755083084106, "regret": 0.37550365924835205, "entropy": 0.12289732694625854, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:09.455943Z", "loop": 1710, "env_steps": 1051238399, "loss": 0.0035100027453154325, "avg_return": 0.49433431029319763, "regret": 0.37548112869262695, "entropy": 0.12503252923488617, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:10.309329Z", "loop": 1711, "env_steps": 1051852799, "loss": 0.00325070065446198, "avg_return": 0.48205435276031494, "regret": 0.37548112869262695, "entropy": 0.13365060091018677, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:11.161769Z", "loop": 1712, "env_steps": 1052467199, "loss": 0.0034257371444255114, "avg_return": 0.4888547956943512, "regret": 0.37548112869262695, "entropy": 0.1253763884305954, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:12.015565Z", "loop": 1713, "env_steps": 1053081599, "loss": 0.0035698392894119024, "avg_return": 0.49210429191589355, "regret": 0.37548112869262695, "entropy": 0.12691336870193481, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:12.868701Z", "loop": 1714, "env_steps": 1053695999, "loss": 0.0035862084478139877, "avg_return": 0.4848760962486267, "regret": 0.37548112869262695, "entropy": 0.12320742011070251, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:13.762320Z", "loop": 1715, "env_steps": 1054310399, "loss": 0.003912709653377533, "avg_return": 0.500874936580658, "regret": 0.3755132555961609, "entropy": 0.13530324399471283, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:14.614872Z", "loop": 1716, "env_steps": 1054924799, "loss": 0.0036534189712256193, "avg_return": 0.48948416113853455, "regret": 0.3755132555961609, "entropy": 0.1305575966835022, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:15.466759Z", "loop": 1717, "env_steps": 1055539199, "loss": 0.003382547292858362, "avg_return": 0.48723304271698, "regret": 0.3755132555961609, "entropy": 0.134968563914299, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:16.319195Z", "loop": 1718, "env_steps": 1056153599, "loss": 0.0038783696945756674, "avg_return": 0.4922221004962921, "regret": 0.3755132555961609, "entropy": 0.13755634427070618, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:17.173583Z", "loop": 1719, "env_steps": 1056767999, "loss": 0.003482051892206073, "avg_return": 0.49039775133132935, "regret": 0.3755132555961609, "entropy": 0.1285586804151535, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:18.066747Z", "loop": 1720, "env_steps": 1057382399, "loss": 0.00347519782371819, "avg_return": 0.48961010575294495, "regret": 0.3755186200141907, "entropy": 0.12827643752098083, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:18.918818Z", "loop": 1721, "env_steps": 1057996799, "loss": 0.003573234425857663, "avg_return": 0.4907894432544708, "regret": 0.3755186200141907, "entropy": 0.12417915463447571, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:19.771447Z", "loop": 1722, "env_steps": 1058611199, "loss": 0.0031946972012519836, "avg_return": 0.49380001425743103, "regret": 0.3755186200141907, "entropy": 0.12008008360862732, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:20.625014Z", "loop": 1723, "env_steps": 1059225599, "loss": 0.0030274956952780485, "avg_return": 0.4832390546798706, "regret": 0.3755186200141907, "entropy": 0.11909652501344681, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:21.478756Z", "loop": 1724, "env_steps": 1059839999, "loss": 0.003224471351131797, "avg_return": 0.47618553042411804, "regret": 0.3755186200141907, "entropy": 0.11979632079601288, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:22.371253Z", "loop": 1725, "env_steps": 1060454399, "loss": 0.0035187338944524527, "avg_return": 0.4941229224205017, "regret": 0.37686529755592346, "entropy": 0.12579454481601715, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:23.223546Z", "loop": 1726, "env_steps": 1061068799, "loss": 0.004445431288331747, "avg_return": 0.4910059869289398, "regret": 0.37686529755592346, "entropy": 0.13586649298667908, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:24.079373Z", "loop": 1727, "env_steps": 1061683199, "loss": 0.004235555883497, "avg_return": 0.4852794408798218, "regret": 0.37686529755592346, "entropy": 0.13180558383464813, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:24.932114Z", "loop": 1728, "env_steps": 1062297599, "loss": 0.00459198746830225, "avg_return": 0.48380041122436523, "regret": 0.37686529755592346, "entropy": 0.13893945515155792, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:25.785187Z", "loop": 1729, "env_steps": 1062911999, "loss": 0.005046611651778221, "avg_return": 0.4815513789653778, "regret": 0.37686529755592346, "entropy": 0.14374884963035583, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:26.678913Z", "loop": 1730, "env_steps": 1063526399, "loss": 0.0051237368024885654, "avg_return": 0.488223671913147, "regret": 0.3784841001033783, "entropy": 0.139788419008255, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:27.531575Z", "loop": 1731, "env_steps": 1064140799, "loss": 0.005086177494376898, "avg_return": 0.47639140486717224, "regret": 0.3784841001033783, "entropy": 0.14490880072116852, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:28.384483Z", "loop": 1732, "env_steps": 1064755199, "loss": 0.004823335912078619, "avg_return": 0.4771710932254791, "regret": 0.3784841001033783, "entropy": 0.142803356051445, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:29.237675Z", "loop": 1733, "env_steps": 1065369599, "loss": 0.005470223259180784, "avg_return": 0.4925629794597626, "regret": 0.3784841001033783, "entropy": 0.14782853424549103, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:30.089563Z", "loop": 1734, "env_steps": 1065983999, "loss": 0.0041404166258871555, "avg_return": 0.4838014841079712, "regret": 0.3784841001033783, "entropy": 0.1381313055753708, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:30.982946Z", "loop": 1735, "env_steps": 1066598399, "loss": 0.00411060219630599, "avg_return": 0.47841691970825195, "regret": 0.3758056163787842, "entropy": 0.13104715943336487, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:31.835872Z", "loop": 1736, "env_steps": 1067212799, "loss": 0.003697047708556056, "avg_return": 0.4928620457649231, "regret": 0.3758056163787842, "entropy": 0.12595008313655853, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:32.689540Z", "loop": 1737, "env_steps": 1067827199, "loss": 0.0033287552651017904, "avg_return": 0.48649731278419495, "regret": 0.3758056163787842, "entropy": 0.12416389584541321, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:33.542265Z", "loop": 1738, "env_steps": 1068441599, "loss": 0.003143122186884284, "avg_return": 0.49094995856285095, "regret": 0.3758056163787842, "entropy": 0.11787394434213638, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:34.395465Z", "loop": 1739, "env_steps": 1069055999, "loss": 0.0032589107286185026, "avg_return": 0.4900391697883606, "regret": 0.3758056163787842, "entropy": 0.12411791831254959, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:35.285913Z", "loop": 1740, "env_steps": 1069670399, "loss": 0.0028869963716715574, "avg_return": 0.48808762431144714, "regret": 0.37569135427474976, "entropy": 0.12193041294813156, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:36.137857Z", "loop": 1741, "env_steps": 1070284799, "loss": 0.0031363540329039097, "avg_return": 0.48828786611557007, "regret": 0.37569135427474976, "entropy": 0.11935208737850189, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:36.991278Z", "loop": 1742, "env_steps": 1070899199, "loss": 0.0032798019237816334, "avg_return": 0.4895193576812744, "regret": 0.37569135427474976, "entropy": 0.11527063697576523, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:37.844640Z", "loop": 1743, "env_steps": 1071513599, "loss": 0.0030097763519734144, "avg_return": 0.4869215488433838, "regret": 0.37569135427474976, "entropy": 0.12252435088157654, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:38.697694Z", "loop": 1744, "env_steps": 1072127999, "loss": 0.003308394690975547, "avg_return": 0.48391202092170715, "regret": 0.37569135427474976, "entropy": 0.12209521234035492, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:39.591219Z", "loop": 1745, "env_steps": 1072742399, "loss": 0.003248796332627535, "avg_return": 0.4874390661716461, "regret": 0.375916063785553, "entropy": 0.12105497717857361, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:40.443683Z", "loop": 1746, "env_steps": 1073356799, "loss": 0.0033204895444214344, "avg_return": 0.48367026448249817, "regret": 0.375916063785553, "entropy": 0.1291896402835846, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:41.296922Z", "loop": 1747, "env_steps": 1073971199, "loss": 0.0036735504399985075, "avg_return": 0.48729392886161804, "regret": 0.375916063785553, "entropy": 0.12495647370815277, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:42.149374Z", "loop": 1748, "env_steps": 1074585599, "loss": 0.0034543131478130817, "avg_return": 0.49108633399009705, "regret": 0.375916063785553, "entropy": 0.12386608868837357, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:43.001638Z", "loop": 1749, "env_steps": 1075199999, "loss": 0.0038978990633040667, "avg_return": 0.4821261167526245, "regret": 0.375916063785553, "entropy": 0.13363945484161377, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:43.892490Z", "loop": 1750, "env_steps": 1075814399, "loss": 0.0042071896605193615, "avg_return": 0.4877775311470032, "regret": 0.3760536015033722, "entropy": 0.13435742259025574, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:44.746345Z", "loop": 1751, "env_steps": 1076428799, "loss": 0.004219331778585911, "avg_return": 0.4831047058105469, "regret": 0.3760536015033722, "entropy": 0.13665816187858582, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:45.599905Z", "loop": 1752, "env_steps": 1077043199, "loss": 0.004475593566894531, "avg_return": 0.4881294369697571, "regret": 0.3760536015033722, "entropy": 0.13611049950122833, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:46.452186Z", "loop": 1753, "env_steps": 1077657599, "loss": 0.005416095722466707, "avg_return": 0.4821759760379791, "regret": 0.3760536015033722, "entropy": 0.15016108751296997, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:47.304616Z", "loop": 1754, "env_steps": 1078271999, "loss": 0.004936364945024252, "avg_return": 0.4929538667201996, "regret": 0.3760536015033722, "entropy": 0.13082000613212585, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:48.199142Z", "loop": 1755, "env_steps": 1078886399, "loss": 0.004919093102216721, "avg_return": 0.48074325919151306, "regret": 0.377128541469574, "entropy": 0.13592256605625153, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:49.052181Z", "loop": 1756, "env_steps": 1079500799, "loss": 0.004452047403901815, "avg_return": 0.4928963780403137, "regret": 0.377128541469574, "entropy": 0.13018177449703217, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:49.905482Z", "loop": 1757, "env_steps": 1080115199, "loss": 0.004991726949810982, "avg_return": 0.4833311438560486, "regret": 0.377128541469574, "entropy": 0.13434746861457825, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:50.758210Z", "loop": 1758, "env_steps": 1080729599, "loss": 0.004929863847792149, "avg_return": 0.4847514033317566, "regret": 0.377128541469574, "entropy": 0.13142076134681702, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:51.611449Z", "loop": 1759, "env_steps": 1081343999, "loss": 0.004926749039441347, "avg_return": 0.4863021969795227, "regret": 0.377128541469574, "entropy": 0.13265009224414825, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:52.505109Z", "loop": 1760, "env_steps": 1081958399, "loss": 0.004914627410471439, "avg_return": 0.49562349915504456, "regret": 0.37667933106422424, "entropy": 0.13877587020397186, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:53.357643Z", "loop": 1761, "env_steps": 1082572799, "loss": 0.004126154351979494, "avg_return": 0.4815796911716461, "regret": 0.37667933106422424, "entropy": 0.12702682614326477, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:54.210591Z", "loop": 1762, "env_steps": 1083187199, "loss": 0.004227811004966497, "avg_return": 0.4848969578742981, "regret": 0.37667933106422424, "entropy": 0.12693199515342712, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:55.063813Z", "loop": 1763, "env_steps": 1083801599, "loss": 0.003936955239623785, "avg_return": 0.4879573583602905, "regret": 0.37667933106422424, "entropy": 0.11769378930330276, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:55.916320Z", "loop": 1764, "env_steps": 1084415999, "loss": 0.003961008042097092, "avg_return": 0.4820481538772583, "regret": 0.37667933106422424, "entropy": 0.10720450431108475, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:56.810597Z", "loop": 1765, "env_steps": 1085030399, "loss": 0.004138526972383261, "avg_return": 0.4744318723678589, "regret": 0.3806942403316498, "entropy": 0.10863868147134781, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:57.664797Z", "loop": 1766, "env_steps": 1085644799, "loss": 0.004499062430113554, "avg_return": 0.4867289960384369, "regret": 0.3806942403316498, "entropy": 0.1114652156829834, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:58.518533Z", "loop": 1767, "env_steps": 1086259199, "loss": 0.004511657170951366, "avg_return": 0.4848826825618744, "regret": 0.3806942403316498, "entropy": 0.10482250154018402, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:48:59.371448Z", "loop": 1768, "env_steps": 1086873599, "loss": 0.004186324775218964, "avg_return": 0.48723816871643066, "regret": 0.3806942403316498, "entropy": 0.10627061128616333, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:00.223822Z", "loop": 1769, "env_steps": 1087487999, "loss": 0.004309832584112883, "avg_return": 0.48057231307029724, "regret": 0.3806942403316498, "entropy": 0.10788124799728394, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:01.115312Z", "loop": 1770, "env_steps": 1088102399, "loss": 0.00412454130128026, "avg_return": 0.4796128571033478, "regret": 0.37886518239974976, "entropy": 0.10773128271102905, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:01.969471Z", "loop": 1771, "env_steps": 1088716799, "loss": 0.004559584427624941, "avg_return": 0.48704060912132263, "regret": 0.37886518239974976, "entropy": 0.11607015132904053, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:02.822837Z", "loop": 1772, "env_steps": 1089331199, "loss": 0.0037879582960158587, "avg_return": 0.48772135376930237, "regret": 0.37886518239974976, "entropy": 0.11682548373937607, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:03.674523Z", "loop": 1773, "env_steps": 1089945599, "loss": 0.004407075699418783, "avg_return": 0.478620320558548, "regret": 0.37886518239974976, "entropy": 0.1255398392677307, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:04.527313Z", "loop": 1774, "env_steps": 1090559999, "loss": 0.005030912812799215, "avg_return": 0.48308828473091125, "regret": 0.37886518239974976, "entropy": 0.14268024265766144, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:05.421427Z", "loop": 1775, "env_steps": 1091174399, "loss": 0.0050818645395338535, "avg_return": 0.489681601524353, "regret": 0.3755730092525482, "entropy": 0.15393073856830597, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:06.275693Z", "loop": 1776, "env_steps": 1091788799, "loss": 0.004317101556807756, "avg_return": 0.49121907353401184, "regret": 0.3755730092525482, "entropy": 0.13227859139442444, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:07.128669Z", "loop": 1777, "env_steps": 1092403199, "loss": 0.002961208578199148, "avg_return": 0.4903981685638428, "regret": 0.3755730092525482, "entropy": 0.12337435781955719, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:07.980838Z", "loop": 1778, "env_steps": 1093017599, "loss": 0.0025673217605799437, "avg_return": 0.48902130126953125, "regret": 0.3755730092525482, "entropy": 0.1118723601102829, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:08.833810Z", "loop": 1779, "env_steps": 1093631999, "loss": 0.0023612508084625006, "avg_return": 0.4859901964664459, "regret": 0.3755730092525482, "entropy": 0.10224848240613937, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:09.727011Z", "loop": 1780, "env_steps": 1094246399, "loss": 0.00230268738232553, "avg_return": 0.4864560663700104, "regret": 0.37551629543304443, "entropy": 0.09963460266590118, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:10.581197Z", "loop": 1781, "env_steps": 1094860799, "loss": 0.002241626149043441, "avg_return": 0.48137563467025757, "regret": 0.37551629543304443, "entropy": 0.0994003638625145, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:11.434071Z", "loop": 1782, "env_steps": 1095475199, "loss": 0.0025877105072140694, "avg_return": 0.48378708958625793, "regret": 0.37551629543304443, "entropy": 0.10306485742330551, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:12.288407Z", "loop": 1783, "env_steps": 1096089599, "loss": 0.002644201274961233, "avg_return": 0.4860052168369293, "regret": 0.37551629543304443, "entropy": 0.10468044131994247, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:13.142029Z", "loop": 1784, "env_steps": 1096703999, "loss": 0.0030400906689465046, "avg_return": 0.4838947653770447, "regret": 0.37551629543304443, "entropy": 0.11926086246967316, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:14.035832Z", "loop": 1785, "env_steps": 1097318399, "loss": 0.003082046052441001, "avg_return": 0.48525646328926086, "regret": 0.3776737153530121, "entropy": 0.12214421480894089, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:14.889580Z", "loop": 1786, "env_steps": 1097932799, "loss": 0.0025484105572104454, "avg_return": 0.48378226161003113, "regret": 0.3776737153530121, "entropy": 0.11671841144561768, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:15.742557Z", "loop": 1787, "env_steps": 1098547199, "loss": 0.002122565871104598, "avg_return": 0.4789204001426697, "regret": 0.3776737153530121, "entropy": 0.1076701357960701, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:16.594753Z", "loop": 1788, "env_steps": 1099161599, "loss": 0.0016465828521177173, "avg_return": 0.4800260663032532, "regret": 0.3776737153530121, "entropy": 0.09195352345705032, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:17.446746Z", "loop": 1789, "env_steps": 1099775999, "loss": 0.0018535902490839362, "avg_return": 0.48348501324653625, "regret": 0.3776737153530121, "entropy": 0.08865366131067276, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:18.340623Z", "loop": 1790, "env_steps": 1100390399, "loss": 0.0016624482814222574, "avg_return": 0.4815393090248108, "regret": 0.38181331753730774, "entropy": 0.08114828169345856, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:19.193900Z", "loop": 1791, "env_steps": 1101004799, "loss": 0.0014265322824940085, "avg_return": 0.47700390219688416, "regret": 0.38181331753730774, "entropy": 0.08534146100282669, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:20.046726Z", "loop": 1792, "env_steps": 1101619199, "loss": 0.001624180586077273, "avg_return": 0.47617876529693604, "regret": 0.38181331753730774, "entropy": 0.08514789491891861, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:20.899156Z", "loop": 1793, "env_steps": 1102233599, "loss": 0.0018071172526106238, "avg_return": 0.4807257056236267, "regret": 0.38181331753730774, "entropy": 0.0906103327870369, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:21.751859Z", "loop": 1794, "env_steps": 1102847999, "loss": 0.001642058603465557, "avg_return": 0.4880253076553345, "regret": 0.38181331753730774, "entropy": 0.09397284686565399, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:22.644013Z", "loop": 1795, "env_steps": 1103462399, "loss": 0.0018464945023879409, "avg_return": 0.4867629110813141, "regret": 0.3789200782775879, "entropy": 0.09300429373979568, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:23.498671Z", "loop": 1796, "env_steps": 1104076799, "loss": 0.0021424535661935806, "avg_return": 0.48801901936531067, "regret": 0.3789200782775879, "entropy": 0.09850487858057022, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:24.351528Z", "loop": 1797, "env_steps": 1104691199, "loss": 0.0020756253506988287, "avg_return": 0.48446401953697205, "regret": 0.3789200782775879, "entropy": 0.10307109355926514, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:25.205019Z", "loop": 1798, "env_steps": 1105305599, "loss": 0.0025363152381032705, "avg_return": 0.488447368144989, "regret": 0.3789200782775879, "entropy": 0.10456540435552597, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:26.057367Z", "loop": 1799, "env_steps": 1105919999, "loss": 0.002920261351391673, "avg_return": 0.48958441615104675, "regret": 0.3789200782775879, "entropy": 0.11518190801143646, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:26.950006Z", "loop": 1800, "env_steps": 1106534399, "loss": 0.002996874740347266, "avg_return": 0.4879966974258423, "regret": 0.37591975927352905, "entropy": 0.11301251500844955, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:27.803751Z", "loop": 1801, "env_steps": 1107148799, "loss": 0.0028871360700577497, "avg_return": 0.4897492527961731, "regret": 0.37591975927352905, "entropy": 0.12147999554872513, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:28.657835Z", "loop": 1802, "env_steps": 1107763199, "loss": 0.003549352055415511, "avg_return": 0.4927741587162018, "regret": 0.37591975927352905, "entropy": 0.12008263170719147, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:29.510958Z", "loop": 1803, "env_steps": 1108377599, "loss": 0.0030195298604667187, "avg_return": 0.4853842854499817, "regret": 0.37591975927352905, "entropy": 0.11527787148952484, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:30.364409Z", "loop": 1804, "env_steps": 1108991999, "loss": 0.003282331395894289, "avg_return": 0.4850651025772095, "regret": 0.37591975927352905, "entropy": 0.11627517640590668, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:31.257898Z", "loop": 1805, "env_steps": 1109606399, "loss": 0.0027052978985011578, "avg_return": 0.4849855601787567, "regret": 0.3754751980304718, "entropy": 0.10788649320602417, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:32.111826Z", "loop": 1806, "env_steps": 1110220799, "loss": 0.002093455521389842, "avg_return": 0.4860336482524872, "regret": 0.3754751980304718, "entropy": 0.1036112979054451, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:32.965513Z", "loop": 1807, "env_steps": 1110835199, "loss": 0.0026985022705048323, "avg_return": 0.4935900866985321, "regret": 0.3754751980304718, "entropy": 0.1012502908706665, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:33.819993Z", "loop": 1808, "env_steps": 1111449599, "loss": 0.002313941949978471, "avg_return": 0.4877581298351288, "regret": 0.3754751980304718, "entropy": 0.09137295931577682, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:34.673071Z", "loop": 1809, "env_steps": 1112063999, "loss": 0.00226747989654541, "avg_return": 0.48490703105926514, "regret": 0.3754751980304718, "entropy": 0.09932400286197662, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:35.567396Z", "loop": 1810, "env_steps": 1112678399, "loss": 0.0025852867402136326, "avg_return": 0.481458455324173, "regret": 0.37560930848121643, "entropy": 0.10376733541488647, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:36.420078Z", "loop": 1811, "env_steps": 1113292799, "loss": 0.002843029098585248, "avg_return": 0.49472758173942566, "regret": 0.37560930848121643, "entropy": 0.10360680520534515, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:37.273900Z", "loop": 1812, "env_steps": 1113907199, "loss": 0.0024514172691851854, "avg_return": 0.4956907331943512, "regret": 0.37560930848121643, "entropy": 0.11194534599781036, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:38.126410Z", "loop": 1813, "env_steps": 1114521599, "loss": 0.002909010974690318, "avg_return": 0.49073272943496704, "regret": 0.37560930848121643, "entropy": 0.10754679888486862, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:38.979473Z", "loop": 1814, "env_steps": 1115135999, "loss": 0.0031567213591188192, "avg_return": 0.48918184638023376, "regret": 0.37560930848121643, "entropy": 0.11640703678131104, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:39.875485Z", "loop": 1815, "env_steps": 1115750399, "loss": 0.0038749538362026215, "avg_return": 0.4920105040073395, "regret": 0.37604665756225586, "entropy": 0.12291470170021057, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:40.730070Z", "loop": 1816, "env_steps": 1116364799, "loss": 0.0035920296795666218, "avg_return": 0.4860731065273285, "regret": 0.37604665756225586, "entropy": 0.1286906749010086, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:41.584825Z", "loop": 1817, "env_steps": 1116979199, "loss": 0.004820431582629681, "avg_return": 0.486607164144516, "regret": 0.37604665756225586, "entropy": 0.13590897619724274, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:42.438563Z", "loop": 1818, "env_steps": 1117593599, "loss": 0.005110792815685272, "avg_return": 0.48492228984832764, "regret": 0.37604665756225586, "entropy": 0.14841347932815552, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:43.292221Z", "loop": 1819, "env_steps": 1118207999, "loss": 0.00560346245765686, "avg_return": 0.4944175183773041, "regret": 0.37604665756225586, "entropy": 0.15205660462379456, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:44.188431Z", "loop": 1820, "env_steps": 1118822399, "loss": 0.005529884248971939, "avg_return": 0.4855302572250366, "regret": 0.37730392813682556, "entropy": 0.14663726091384888, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:45.042347Z", "loop": 1821, "env_steps": 1119436799, "loss": 0.005432480946183205, "avg_return": 0.4792621433734894, "regret": 0.37730392813682556, "entropy": 0.14228929579257965, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:45.896561Z", "loop": 1822, "env_steps": 1120051199, "loss": 0.004749753046780825, "avg_return": 0.48379945755004883, "regret": 0.37730392813682556, "entropy": 0.12738820910453796, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:46.749386Z", "loop": 1823, "env_steps": 1120665599, "loss": 0.004462254699319601, "avg_return": 0.4833407700061798, "regret": 0.37730392813682556, "entropy": 0.12121005356311798, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:47.602676Z", "loop": 1824, "env_steps": 1121279999, "loss": 0.004131469409912825, "avg_return": 0.4824983477592468, "regret": 0.37730392813682556, "entropy": 0.11998537927865982, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:48.499102Z", "loop": 1825, "env_steps": 1121894399, "loss": 0.004291854333132505, "avg_return": 0.48592814803123474, "regret": 0.3786717355251312, "entropy": 0.11307434737682343, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:49.353829Z", "loop": 1826, "env_steps": 1122508799, "loss": 0.005442182999104261, "avg_return": 0.48089784383773804, "regret": 0.3786717355251312, "entropy": 0.11727042496204376, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:50.207536Z", "loop": 1827, "env_steps": 1123123199, "loss": 0.005052200052887201, "avg_return": 0.48153606057167053, "regret": 0.3786717355251312, "entropy": 0.11622865498065948, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:51.061625Z", "loop": 1828, "env_steps": 1123737599, "loss": 0.004369150381535292, "avg_return": 0.477735310792923, "regret": 0.3786717355251312, "entropy": 0.11004436016082764, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:51.915681Z", "loop": 1829, "env_steps": 1124351999, "loss": 0.0039023873396217823, "avg_return": 0.49002382159233093, "regret": 0.3786717355251312, "entropy": 0.10577251762151718, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:52.811272Z", "loop": 1830, "env_steps": 1124966399, "loss": 0.003966409247368574, "avg_return": 0.4887206256389618, "regret": 0.3769359886646271, "entropy": 0.10451406240463257, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:53.664280Z", "loop": 1831, "env_steps": 1125580799, "loss": 0.004146660678088665, "avg_return": 0.49070844054222107, "regret": 0.3769359886646271, "entropy": 0.10871747881174088, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:54.517007Z", "loop": 1832, "env_steps": 1126195199, "loss": 0.0035820230841636658, "avg_return": 0.4760953485965729, "regret": 0.3769359886646271, "entropy": 0.10685385018587112, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:55.369527Z", "loop": 1833, "env_steps": 1126809599, "loss": 0.0037609220016747713, "avg_return": 0.49286678433418274, "regret": 0.3769359886646271, "entropy": 0.11226838827133179, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:56.222712Z", "loop": 1834, "env_steps": 1127423999, "loss": 0.004115565679967403, "avg_return": 0.4896836578845978, "regret": 0.3769359886646271, "entropy": 0.11851298809051514, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:57.116233Z", "loop": 1835, "env_steps": 1128038399, "loss": 0.0044942437671124935, "avg_return": 0.4905432164669037, "regret": 0.37584105134010315, "entropy": 0.12821967899799347, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:57.969498Z", "loop": 1836, "env_steps": 1128652799, "loss": 0.005047261249274015, "avg_return": 0.4954230785369873, "regret": 0.37584105134010315, "entropy": 0.1404784470796585, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:58.822526Z", "loop": 1837, "env_steps": 1129267199, "loss": 0.004512298386543989, "avg_return": 0.48987728357315063, "regret": 0.37584105134010315, "entropy": 0.14474140107631683, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:49:59.675698Z", "loop": 1838, "env_steps": 1129881599, "loss": 0.0035456193145364523, "avg_return": 0.49499425292015076, "regret": 0.37584105134010315, "entropy": 0.12318610399961472, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:00.528698Z", "loop": 1839, "env_steps": 1130495999, "loss": 0.002843250287696719, "avg_return": 0.48405441641807556, "regret": 0.37584105134010315, "entropy": 0.12725213170051575, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:01.421307Z", "loop": 1840, "env_steps": 1131110399, "loss": 0.002415352500975132, "avg_return": 0.48380276560783386, "regret": 0.377286434173584, "entropy": 0.11361078172922134, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:02.275040Z", "loop": 1841, "env_steps": 1131724799, "loss": 0.002395560732111335, "avg_return": 0.482432097196579, "regret": 0.377286434173584, "entropy": 0.12234548479318619, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:03.129306Z", "loop": 1842, "env_steps": 1132339199, "loss": 0.0021411566995084286, "avg_return": 0.4918493628501892, "regret": 0.377286434173584, "entropy": 0.10722168534994125, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:03.981609Z", "loop": 1843, "env_steps": 1132953599, "loss": 0.0021210191771388054, "avg_return": 0.4842492938041687, "regret": 0.377286434173584, "entropy": 0.10382963716983795, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:04.834404Z", "loop": 1844, "env_steps": 1133567999, "loss": 0.0019424933707341552, "avg_return": 0.4797137677669525, "regret": 0.377286434173584, "entropy": 0.10937906801700592, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:05.726474Z", "loop": 1845, "env_steps": 1134182399, "loss": 0.0019224639981985092, "avg_return": 0.48296886682510376, "regret": 0.3785170912742615, "entropy": 0.09542252123355865, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:06.578682Z", "loop": 1846, "env_steps": 1134796799, "loss": 0.0021939927246421576, "avg_return": 0.4860343933105469, "regret": 0.3785170912742615, "entropy": 0.09440361708402634, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:07.431392Z", "loop": 1847, "env_steps": 1135411199, "loss": 0.0022109162528067827, "avg_return": 0.48287105560302734, "regret": 0.3785170912742615, "entropy": 0.09645106643438339, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:08.284683Z", "loop": 1848, "env_steps": 1136025599, "loss": 0.0021246299147605896, "avg_return": 0.4872879087924957, "regret": 0.3785170912742615, "entropy": 0.0988733321428299, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:09.138268Z", "loop": 1849, "env_steps": 1136639999, "loss": 0.002160504227504134, "avg_return": 0.4820033013820648, "regret": 0.3785170912742615, "entropy": 0.10230696201324463, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:10.030573Z", "loop": 1850, "env_steps": 1137254399, "loss": 0.0019525414099916816, "avg_return": 0.486507773399353, "regret": 0.3780919015407562, "entropy": 0.09831252694129944, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:10.884267Z", "loop": 1851, "env_steps": 1137868799, "loss": 0.002007198054343462, "avg_return": 0.48390188813209534, "regret": 0.3780919015407562, "entropy": 0.09304029494524002, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:11.737490Z", "loop": 1852, "env_steps": 1138483199, "loss": 0.0022924456279724836, "avg_return": 0.4835048019886017, "regret": 0.3780919015407562, "entropy": 0.10297290235757828, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:12.590104Z", "loop": 1853, "env_steps": 1139097599, "loss": 0.0024983608163893223, "avg_return": 0.4932304918766022, "regret": 0.3780919015407562, "entropy": 0.1040288433432579, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:13.443894Z", "loop": 1854, "env_steps": 1139711999, "loss": 0.0023604610469192266, "avg_return": 0.48644837737083435, "regret": 0.3780919015407562, "entropy": 0.10421939194202423, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:14.340205Z", "loop": 1855, "env_steps": 1140326399, "loss": 0.0024974453262984753, "avg_return": 0.4863660931587219, "regret": 0.3774338364601135, "entropy": 0.10788853466510773, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:15.194885Z", "loop": 1856, "env_steps": 1140940799, "loss": 0.0027243932709097862, "avg_return": 0.4865257441997528, "regret": 0.3774338364601135, "entropy": 0.11197991669178009, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:16.049571Z", "loop": 1857, "env_steps": 1141555199, "loss": 0.002806176198646426, "avg_return": 0.4934162497520447, "regret": 0.3774338364601135, "entropy": 0.12025971710681915, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:16.903674Z", "loop": 1858, "env_steps": 1142169599, "loss": 0.0028327901381999254, "avg_return": 0.47774821519851685, "regret": 0.3774338364601135, "entropy": 0.12143094092607498, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:17.756455Z", "loop": 1859, "env_steps": 1142783999, "loss": 0.003082361537963152, "avg_return": 0.49285706877708435, "regret": 0.3774338364601135, "entropy": 0.11576662957668304, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:18.649358Z", "loop": 1860, "env_steps": 1143398399, "loss": 0.0028836147394031286, "avg_return": 0.4863254427909851, "regret": 0.37736713886260986, "entropy": 0.12171180546283722, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:19.502981Z", "loop": 1861, "env_steps": 1144012799, "loss": 0.0027025288436561823, "avg_return": 0.48961925506591797, "regret": 0.37736713886260986, "entropy": 0.11890200525522232, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:20.356035Z", "loop": 1862, "env_steps": 1144627199, "loss": 0.0028181965462863445, "avg_return": 0.4849730432033539, "regret": 0.37736713886260986, "entropy": 0.12129053473472595, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:21.208685Z", "loop": 1863, "env_steps": 1145241599, "loss": 0.0031590627040714025, "avg_return": 0.49065396189689636, "regret": 0.37736713886260986, "entropy": 0.12120646238327026, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:22.062354Z", "loop": 1864, "env_steps": 1145855999, "loss": 0.0031776127871125937, "avg_return": 0.48717254400253296, "regret": 0.37736713886260986, "entropy": 0.11704667657613754, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:22.955249Z", "loop": 1865, "env_steps": 1146470399, "loss": 0.002950069261714816, "avg_return": 0.48767945170402527, "regret": 0.376236230134964, "entropy": 0.11680246889591217, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:23.807828Z", "loop": 1866, "env_steps": 1147084799, "loss": 0.00287120440043509, "avg_return": 0.49315470457077026, "regret": 0.376236230134964, "entropy": 0.12061500549316406, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:24.661822Z", "loop": 1867, "env_steps": 1147699199, "loss": 0.0029973473865538836, "avg_return": 0.48892727494239807, "regret": 0.376236230134964, "entropy": 0.1207435205578804, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:25.514607Z", "loop": 1868, "env_steps": 1148313599, "loss": 0.002977593569085002, "avg_return": 0.49177807569503784, "regret": 0.376236230134964, "entropy": 0.11656492948532104, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:26.367913Z", "loop": 1869, "env_steps": 1148927999, "loss": 0.0028937379829585552, "avg_return": 0.48464739322662354, "regret": 0.376236230134964, "entropy": 0.11456096172332764, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:27.260518Z", "loop": 1870, "env_steps": 1149542399, "loss": 0.002940848469734192, "avg_return": 0.4839937388896942, "regret": 0.3760276734828949, "entropy": 0.12283588200807571, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:28.113898Z", "loop": 1871, "env_steps": 1150156799, "loss": 0.0030960184521973133, "avg_return": 0.4894942343235016, "regret": 0.3760276734828949, "entropy": 0.11515022069215775, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:28.967836Z", "loop": 1872, "env_steps": 1150771199, "loss": 0.0031276654917746782, "avg_return": 0.4828002452850342, "regret": 0.3760276734828949, "entropy": 0.1277126967906952, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:29.821266Z", "loop": 1873, "env_steps": 1151385599, "loss": 0.0031279490794986486, "avg_return": 0.4863158166408539, "regret": 0.3760276734828949, "entropy": 0.11792545765638351, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:30.674397Z", "loop": 1874, "env_steps": 1151999999, "loss": 0.003151489421725273, "avg_return": 0.4914359748363495, "regret": 0.3760276734828949, "entropy": 0.11870763450860977, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:31.567298Z", "loop": 1875, "env_steps": 1152614399, "loss": 0.0027978485450148582, "avg_return": 0.49972912669181824, "regret": 0.3757561147212982, "entropy": 0.12168610841035843, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:32.420870Z", "loop": 1876, "env_steps": 1153228799, "loss": 0.003413926577195525, "avg_return": 0.4882146716117859, "regret": 0.3757561147212982, "entropy": 0.12374920397996902, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:33.273589Z", "loop": 1877, "env_steps": 1153843199, "loss": 0.002866799710318446, "avg_return": 0.4842975437641144, "regret": 0.3757561147212982, "entropy": 0.1135631799697876, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:34.126164Z", "loop": 1878, "env_steps": 1154457599, "loss": 0.0030664929654449224, "avg_return": 0.4885656237602234, "regret": 0.3757561147212982, "entropy": 0.11660806089639664, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:34.979432Z", "loop": 1879, "env_steps": 1155071999, "loss": 0.0026385514065623283, "avg_return": 0.48612356185913086, "regret": 0.3757561147212982, "entropy": 0.11006994545459747, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:35.874406Z", "loop": 1880, "env_steps": 1155686399, "loss": 0.0028903994243592024, "avg_return": 0.4891457259654999, "regret": 0.3757658302783966, "entropy": 0.11853431910276413, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:36.727250Z", "loop": 1881, "env_steps": 1156300799, "loss": 0.0028759946580976248, "avg_return": 0.4958871006965637, "regret": 0.3757658302783966, "entropy": 0.1099211648106575, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:37.579873Z", "loop": 1882, "env_steps": 1156915199, "loss": 0.0026676158886402845, "avg_return": 0.48791658878326416, "regret": 0.3757658302783966, "entropy": 0.10792183876037598, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:38.432683Z", "loop": 1883, "env_steps": 1157529599, "loss": 0.002555753802880645, "avg_return": 0.4889957904815674, "regret": 0.3757658302783966, "entropy": 0.10532473772764206, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:39.286246Z", "loop": 1884, "env_steps": 1158143999, "loss": 0.0022842197213321924, "avg_return": 0.4872298240661621, "regret": 0.3757658302783966, "entropy": 0.10396827757358551, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:40.179643Z", "loop": 1885, "env_steps": 1158758399, "loss": 0.0026469107251614332, "avg_return": 0.4907173812389374, "regret": 0.37614285945892334, "entropy": 0.0980483889579773, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:41.032613Z", "loop": 1886, "env_steps": 1159372799, "loss": 0.0023012261372059584, "avg_return": 0.49009695649147034, "regret": 0.37614285945892334, "entropy": 0.10022523254156113, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:41.885001Z", "loop": 1887, "env_steps": 1159987199, "loss": 0.0022597103379666805, "avg_return": 0.48428356647491455, "regret": 0.37614285945892334, "entropy": 0.0968569815158844, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:42.736812Z", "loop": 1888, "env_steps": 1160601599, "loss": 0.001989776035770774, "avg_return": 0.4796113073825836, "regret": 0.37614285945892334, "entropy": 0.10085820406675339, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:43.589741Z", "loop": 1889, "env_steps": 1161215999, "loss": 0.0019176293862983584, "avg_return": 0.47634217143058777, "regret": 0.37614285945892334, "entropy": 0.09769820421934128, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:44.482035Z", "loop": 1890, "env_steps": 1161830399, "loss": 0.00206571607850492, "avg_return": 0.4818883240222931, "regret": 0.37558233737945557, "entropy": 0.10186892002820969, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:45.335176Z", "loop": 1891, "env_steps": 1162444799, "loss": 0.0022083267103880644, "avg_return": 0.4857184886932373, "regret": 0.37558233737945557, "entropy": 0.10228350013494492, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:46.187746Z", "loop": 1892, "env_steps": 1163059199, "loss": 0.0019406055798754096, "avg_return": 0.4799078404903412, "regret": 0.37558233737945557, "entropy": 0.09764164686203003, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:47.041083Z", "loop": 1893, "env_steps": 1163673599, "loss": 0.0022283203434199095, "avg_return": 0.4798443615436554, "regret": 0.37558233737945557, "entropy": 0.10685710608959198, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:47.894996Z", "loop": 1894, "env_steps": 1164287999, "loss": 0.002659297315403819, "avg_return": 0.4905003011226654, "regret": 0.37558233737945557, "entropy": 0.10905908048152924, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:48.787426Z", "loop": 1895, "env_steps": 1164902399, "loss": 0.0026827005203813314, "avg_return": 0.48390650749206543, "regret": 0.3756813108921051, "entropy": 0.11346094310283661, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:49.640690Z", "loop": 1896, "env_steps": 1165516799, "loss": 0.002988673746585846, "avg_return": 0.4930388927459717, "regret": 0.3756813108921051, "entropy": 0.11786933243274689, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:50.494344Z", "loop": 1897, "env_steps": 1166131199, "loss": 0.0029909757431596518, "avg_return": 0.4936058819293976, "regret": 0.3756813108921051, "entropy": 0.11539556831121445, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:51.347966Z", "loop": 1898, "env_steps": 1166745599, "loss": 0.0031060597393661737, "avg_return": 0.48984232544898987, "regret": 0.3756813108921051, "entropy": 0.1200862005352974, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:52.202321Z", "loop": 1899, "env_steps": 1167359999, "loss": 0.0030993453692644835, "avg_return": 0.4877508282661438, "regret": 0.3756813108921051, "entropy": 0.11971113830804825, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:53.092801Z", "loop": 1900, "env_steps": 1167974399, "loss": 0.0027830004692077637, "avg_return": 0.49010834097862244, "regret": 0.3759327232837677, "entropy": 0.11673365533351898, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:53.945600Z", "loop": 1901, "env_steps": 1168588799, "loss": 0.0030805261339992285, "avg_return": 0.4915372431278229, "regret": 0.3759327232837677, "entropy": 0.1136462613940239, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:54.797577Z", "loop": 1902, "env_steps": 1169203199, "loss": 0.003137314459308982, "avg_return": 0.48788657784461975, "regret": 0.3759327232837677, "entropy": 0.12015959620475769, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:55.650867Z", "loop": 1903, "env_steps": 1169817599, "loss": 0.00311965961009264, "avg_return": 0.48870423436164856, "regret": 0.3759327232837677, "entropy": 0.11292023956775665, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:56.504681Z", "loop": 1904, "env_steps": 1170431999, "loss": 0.002812460996210575, "avg_return": 0.48420029878616333, "regret": 0.3759327232837677, "entropy": 0.11889403313398361, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:57.397967Z", "loop": 1905, "env_steps": 1171046399, "loss": 0.0029727478977292776, "avg_return": 0.48676297068595886, "regret": 0.3759830892086029, "entropy": 0.12042801082134247, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:58.251910Z", "loop": 1906, "env_steps": 1171660799, "loss": 0.0033794657792896032, "avg_return": 0.4921988546848297, "regret": 0.3759830892086029, "entropy": 0.11242959648370743, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:59.105826Z", "loop": 1907, "env_steps": 1172275199, "loss": 0.003276554634794593, "avg_return": 0.4894830584526062, "regret": 0.3759830892086029, "entropy": 0.10631723701953888, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:50:59.959295Z", "loop": 1908, "env_steps": 1172889599, "loss": 0.0024185667280107737, "avg_return": 0.49180421233177185, "regret": 0.3759830892086029, "entropy": 0.1028638631105423, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:00.813307Z", "loop": 1909, "env_steps": 1173503999, "loss": 0.0022939948830753565, "avg_return": 0.49517664313316345, "regret": 0.3759830892086029, "entropy": 0.1044633761048317, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:01.706642Z", "loop": 1910, "env_steps": 1174118399, "loss": 0.00233902083709836, "avg_return": 0.4842967987060547, "regret": 0.3762654662132263, "entropy": 0.10093632340431213, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:02.560189Z", "loop": 1911, "env_steps": 1174732799, "loss": 0.0023288654629141092, "avg_return": 0.48218223452568054, "regret": 0.3762654662132263, "entropy": 0.10169381648302078, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:03.413524Z", "loop": 1912, "env_steps": 1175347199, "loss": 0.002371914451941848, "avg_return": 0.49630412459373474, "regret": 0.3762654662132263, "entropy": 0.09548572450876236, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:04.267143Z", "loop": 1913, "env_steps": 1175961599, "loss": 0.002535790903493762, "avg_return": 0.49247726798057556, "regret": 0.3762654662132263, "entropy": 0.10203041136264801, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:05.119377Z", "loop": 1914, "env_steps": 1176575999, "loss": 0.0024264389649033546, "avg_return": 0.483646959066391, "regret": 0.3762654662132263, "entropy": 0.09852446615695953, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:06.011261Z", "loop": 1915, "env_steps": 1177190399, "loss": 0.00304395635612309, "avg_return": 0.4851991832256317, "regret": 0.37595877051353455, "entropy": 0.1037900298833847, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:06.865040Z", "loop": 1916, "env_steps": 1177804799, "loss": 0.002918461337685585, "avg_return": 0.49242106080055237, "regret": 0.37595877051353455, "entropy": 0.11268702149391174, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:07.718406Z", "loop": 1917, "env_steps": 1178419199, "loss": 0.0034674808848649263, "avg_return": 0.4926597774028778, "regret": 0.37595877051353455, "entropy": 0.11584725975990295, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:08.572385Z", "loop": 1918, "env_steps": 1179033599, "loss": 0.002979334443807602, "avg_return": 0.4873066246509552, "regret": 0.37595877051353455, "entropy": 0.11926055699586868, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:09.425624Z", "loop": 1919, "env_steps": 1179647999, "loss": 0.0031636212952435017, "avg_return": 0.48842135071754456, "regret": 0.37595877051353455, "entropy": 0.1214996725320816, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:10.319279Z", "loop": 1920, "env_steps": 1180262399, "loss": 0.0032179548870772123, "avg_return": 0.49153193831443787, "regret": 0.3754919171333313, "entropy": 0.11759103834629059, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:11.172792Z", "loop": 1921, "env_steps": 1180876799, "loss": 0.003146452596411109, "avg_return": 0.4798298180103302, "regret": 0.3754919171333313, "entropy": 0.12275402992963791, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:12.026884Z", "loop": 1922, "env_steps": 1181491199, "loss": 0.0031806721817702055, "avg_return": 0.4988380968570709, "regret": 0.3754919171333313, "entropy": 0.12017028778791428, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:12.879963Z", "loop": 1923, "env_steps": 1182105599, "loss": 0.003453675424680114, "avg_return": 0.4929577708244324, "regret": 0.3754919171333313, "entropy": 0.12324569374322891, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:13.733028Z", "loop": 1924, "env_steps": 1182719999, "loss": 0.0032959983218461275, "avg_return": 0.490444540977478, "regret": 0.3754919171333313, "entropy": 0.12754471600055695, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:14.628621Z", "loop": 1925, "env_steps": 1183334399, "loss": 0.002987793181091547, "avg_return": 0.4852183163166046, "regret": 0.3753826916217804, "entropy": 0.12194690108299255, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:15.482445Z", "loop": 1926, "env_steps": 1183948799, "loss": 0.003083507064729929, "avg_return": 0.4881882965564728, "regret": 0.3753826916217804, "entropy": 0.11917756497859955, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:16.335902Z", "loop": 1927, "env_steps": 1184563199, "loss": 0.002740290714427829, "avg_return": 0.4844701290130615, "regret": 0.3753826916217804, "entropy": 0.11750418692827225, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:17.189096Z", "loop": 1928, "env_steps": 1185177599, "loss": 0.0029135250952094793, "avg_return": 0.48768311738967896, "regret": 0.3753826916217804, "entropy": 0.12076850235462189, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:18.042514Z", "loop": 1929, "env_steps": 1185791999, "loss": 0.0030645106453448534, "avg_return": 0.4844146966934204, "regret": 0.3753826916217804, "entropy": 0.11842110753059387, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:18.933474Z", "loop": 1930, "env_steps": 1186406399, "loss": 0.00275989412330091, "avg_return": 0.49386435747146606, "regret": 0.3755004405975342, "entropy": 0.1196819543838501, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:19.786788Z", "loop": 1931, "env_steps": 1187020799, "loss": 0.0024656171444803476, "avg_return": 0.488338440656662, "regret": 0.3755004405975342, "entropy": 0.12127761542797089, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:20.640302Z", "loop": 1932, "env_steps": 1187635199, "loss": 0.0023874908220022917, "avg_return": 0.48930004239082336, "regret": 0.3755004405975342, "entropy": 0.11843355745077133, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:21.493623Z", "loop": 1933, "env_steps": 1188249599, "loss": 0.0022972472943365574, "avg_return": 0.48516255617141724, "regret": 0.3755004405975342, "entropy": 0.11879409104585648, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:22.345939Z", "loop": 1934, "env_steps": 1188863999, "loss": 0.002121205208823085, "avg_return": 0.4861909747123718, "regret": 0.3755004405975342, "entropy": 0.11755175143480301, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:23.241196Z", "loop": 1935, "env_steps": 1189478399, "loss": 0.0027358918450772762, "avg_return": 0.48539596796035767, "regret": 0.37563180923461914, "entropy": 0.11872885376214981, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:24.094995Z", "loop": 1936, "env_steps": 1190092799, "loss": 0.002520830137655139, "avg_return": 0.4917427599430084, "regret": 0.37563180923461914, "entropy": 0.12358684837818146, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:24.949079Z", "loop": 1937, "env_steps": 1190707199, "loss": 0.0031252261251211166, "avg_return": 0.49168968200683594, "regret": 0.37563180923461914, "entropy": 0.12067072093486786, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:25.802780Z", "loop": 1938, "env_steps": 1191321599, "loss": 0.0030969614163041115, "avg_return": 0.4877946972846985, "regret": 0.37563180923461914, "entropy": 0.13270817697048187, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:26.656814Z", "loop": 1939, "env_steps": 1191935999, "loss": 0.0036618404556065798, "avg_return": 0.4943617880344391, "regret": 0.37563180923461914, "entropy": 0.1393585205078125, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:27.551126Z", "loop": 1940, "env_steps": 1192550399, "loss": 0.0039041300769895315, "avg_return": 0.49066823720932007, "regret": 0.37553563714027405, "entropy": 0.14228668808937073, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:28.405966Z", "loop": 1941, "env_steps": 1193164799, "loss": 0.0037113968282938004, "avg_return": 0.4847719371318817, "regret": 0.37553563714027405, "entropy": 0.14583751559257507, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:29.259003Z", "loop": 1942, "env_steps": 1193779199, "loss": 0.003880020696669817, "avg_return": 0.49299079179763794, "regret": 0.37553563714027405, "entropy": 0.14007224142551422, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:30.112786Z", "loop": 1943, "env_steps": 1194393599, "loss": 0.0033822532277554274, "avg_return": 0.49700215458869934, "regret": 0.37553563714027405, "entropy": 0.138487309217453, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:30.966746Z", "loop": 1944, "env_steps": 1195007999, "loss": 0.003537094919010997, "avg_return": 0.49011602997779846, "regret": 0.37553563714027405, "entropy": 0.1333637237548828, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:31.860780Z", "loop": 1945, "env_steps": 1195622399, "loss": 0.0034393214154988527, "avg_return": 0.4871217608451843, "regret": 0.3755148947238922, "entropy": 0.12587356567382812, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:32.713680Z", "loop": 1946, "env_steps": 1196236799, "loss": 0.0030861678533256054, "avg_return": 0.48181256651878357, "regret": 0.3755148947238922, "entropy": 0.129736065864563, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:33.566116Z", "loop": 1947, "env_steps": 1196851199, "loss": 0.0028111254796385765, "avg_return": 0.4926392734050751, "regret": 0.3755148947238922, "entropy": 0.13513298332691193, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:34.418714Z", "loop": 1948, "env_steps": 1197465599, "loss": 0.0030415435321629047, "avg_return": 0.4812682569026947, "regret": 0.3755148947238922, "entropy": 0.1328568160533905, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:35.272494Z", "loop": 1949, "env_steps": 1198079999, "loss": 0.0033289939165115356, "avg_return": 0.48682335019111633, "regret": 0.3755148947238922, "entropy": 0.13568179309368134, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:36.164557Z", "loop": 1950, "env_steps": 1198694399, "loss": 0.0032640553545206785, "avg_return": 0.4898771345615387, "regret": 0.3755628764629364, "entropy": 0.13733825087547302, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:37.017574Z", "loop": 1951, "env_steps": 1199308799, "loss": 0.0035874799359589815, "avg_return": 0.4949009418487549, "regret": 0.3755628764629364, "entropy": 0.1382523775100708, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:37.870176Z", "loop": 1952, "env_steps": 1199923199, "loss": 0.004087046720087528, "avg_return": 0.4795290231704712, "regret": 0.3755628764629364, "entropy": 0.1425628364086151, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:38.723990Z", "loop": 1953, "env_steps": 1200537599, "loss": 0.0042145708575844765, "avg_return": 0.47798672318458557, "regret": 0.3755628764629364, "entropy": 0.1433098167181015, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:39.577545Z", "loop": 1954, "env_steps": 1201151999, "loss": 0.00405611377209425, "avg_return": 0.48643383383750916, "regret": 0.3755628764629364, "entropy": 0.1348402202129364, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:40.469867Z", "loop": 1955, "env_steps": 1201766399, "loss": 0.003934967797249556, "avg_return": 0.49643662571907043, "regret": 0.3755786716938019, "entropy": 0.1418730467557907, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:41.321377Z", "loop": 1956, "env_steps": 1202380799, "loss": 0.003754234407097101, "avg_return": 0.4839787781238556, "regret": 0.3755786716938019, "entropy": 0.13759379088878632, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:42.173439Z", "loop": 1957, "env_steps": 1202995199, "loss": 0.00397709384560585, "avg_return": 0.48342183232307434, "regret": 0.3755786716938019, "entropy": 0.1376863718032837, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:43.026524Z", "loop": 1958, "env_steps": 1203609599, "loss": 0.004393039271235466, "avg_return": 0.4913274347782135, "regret": 0.3755786716938019, "entropy": 0.1379687786102295, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:43.879343Z", "loop": 1959, "env_steps": 1204223999, "loss": 0.004153132438659668, "avg_return": 0.479619562625885, "regret": 0.3755786716938019, "entropy": 0.14433182775974274, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:44.771548Z", "loop": 1960, "env_steps": 1204838399, "loss": 0.0046221367083489895, "avg_return": 0.48596325516700745, "regret": 0.37560713291168213, "entropy": 0.13947966694831848, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:45.624881Z", "loop": 1961, "env_steps": 1205452799, "loss": 0.004307858645915985, "avg_return": 0.48722195625305176, "regret": 0.37560713291168213, "entropy": 0.14639542996883392, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:46.478251Z", "loop": 1962, "env_steps": 1206067199, "loss": 0.004186356905847788, "avg_return": 0.4860871434211731, "regret": 0.37560713291168213, "entropy": 0.1407873034477234, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:47.330606Z", "loop": 1963, "env_steps": 1206681599, "loss": 0.004053826909512281, "avg_return": 0.494123250246048, "regret": 0.37560713291168213, "entropy": 0.13856381177902222, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:48.183315Z", "loop": 1964, "env_steps": 1207295999, "loss": 0.0035903826355934143, "avg_return": 0.49198099970817566, "regret": 0.37560713291168213, "entropy": 0.135366290807724, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:49.074645Z", "loop": 1965, "env_steps": 1207910399, "loss": 0.0038185380399227142, "avg_return": 0.4863981604576111, "regret": 0.3754997253417969, "entropy": 0.1273578256368637, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:49.927633Z", "loop": 1966, "env_steps": 1208524799, "loss": 0.003159439889714122, "avg_return": 0.4873936176300049, "regret": 0.3754997253417969, "entropy": 0.13141684234142303, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:50.780464Z", "loop": 1967, "env_steps": 1209139199, "loss": 0.0034427561331540346, "avg_return": 0.48491913080215454, "regret": 0.3754997253417969, "entropy": 0.12651823461055756, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:51.633742Z", "loop": 1968, "env_steps": 1209753599, "loss": 0.003458932740613818, "avg_return": 0.4931914508342743, "regret": 0.3754997253417969, "entropy": 0.1226377785205841, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:52.487051Z", "loop": 1969, "env_steps": 1210367999, "loss": 0.0028569651767611504, "avg_return": 0.4889328181743622, "regret": 0.3754997253417969, "entropy": 0.12401314079761505, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:53.380284Z", "loop": 1970, "env_steps": 1210982399, "loss": 0.003102135146036744, "avg_return": 0.4865323007106781, "regret": 0.3754247725009918, "entropy": 0.12550438940525055, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:54.233069Z", "loop": 1971, "env_steps": 1211596799, "loss": 0.0029879449866712093, "avg_return": 0.4893626570701599, "regret": 0.3754247725009918, "entropy": 0.1287621110677719, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:55.086074Z", "loop": 1972, "env_steps": 1212211199, "loss": 0.0034781568683683872, "avg_return": 0.4832246005535126, "regret": 0.3754247725009918, "entropy": 0.12656879425048828, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:55.939836Z", "loop": 1973, "env_steps": 1212825599, "loss": 0.004228560719639063, "avg_return": 0.4921126365661621, "regret": 0.3754247725009918, "entropy": 0.14042732119560242, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:56.792185Z", "loop": 1974, "env_steps": 1213439999, "loss": 0.004649503622204065, "avg_return": 0.48668691515922546, "regret": 0.3754247725009918, "entropy": 0.1497305929660797, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:57.683757Z", "loop": 1975, "env_steps": 1214054399, "loss": 0.005145594011992216, "avg_return": 0.4905034005641937, "regret": 0.3755461275577545, "entropy": 0.15232910215854645, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:58.536744Z", "loop": 1976, "env_steps": 1214668799, "loss": 0.005339520983397961, "avg_return": 0.4843946397304535, "regret": 0.3755461275577545, "entropy": 0.14920474588871002, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:51:59.391099Z", "loop": 1977, "env_steps": 1215283199, "loss": 0.005823336075991392, "avg_return": 0.48892080783843994, "regret": 0.3755461275577545, "entropy": 0.14983460307121277, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:00.244560Z", "loop": 1978, "env_steps": 1215897599, "loss": 0.005120593123137951, "avg_return": 0.4808221161365509, "regret": 0.3755461275577545, "entropy": 0.1527796983718872, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:01.097143Z", "loop": 1979, "env_steps": 1216511999, "loss": 0.005235040560364723, "avg_return": 0.49355071783065796, "regret": 0.3755461275577545, "entropy": 0.1519950032234192, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:01.990546Z", "loop": 1980, "env_steps": 1217126399, "loss": 0.005342911463230848, "avg_return": 0.4937286376953125, "regret": 0.37566447257995605, "entropy": 0.14684230089187622, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:02.844839Z", "loop": 1981, "env_steps": 1217740799, "loss": 0.004746223799884319, "avg_return": 0.48558178544044495, "regret": 0.37566447257995605, "entropy": 0.1405988335609436, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:03.698328Z", "loop": 1982, "env_steps": 1218355199, "loss": 0.004930467810481787, "avg_return": 0.48310399055480957, "regret": 0.37566447257995605, "entropy": 0.12610867619514465, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:04.550537Z", "loop": 1983, "env_steps": 1218969599, "loss": 0.004593999590724707, "avg_return": 0.49292004108428955, "regret": 0.37566447257995605, "entropy": 0.11736798286437988, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:05.403661Z", "loop": 1984, "env_steps": 1219583999, "loss": 0.004251876380294561, "avg_return": 0.48579874634742737, "regret": 0.37566447257995605, "entropy": 0.11236683279275894, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:06.296926Z", "loop": 1985, "env_steps": 1220198399, "loss": 0.004619851242750883, "avg_return": 0.4867636263370514, "regret": 0.3776012659072876, "entropy": 0.11251244693994522, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:07.149953Z", "loop": 1986, "env_steps": 1220812799, "loss": 0.00395022239536047, "avg_return": 0.48540669679641724, "regret": 0.3776012659072876, "entropy": 0.11157680302858353, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:08.004355Z", "loop": 1987, "env_steps": 1221427199, "loss": 0.004406829830259085, "avg_return": 0.4978136420249939, "regret": 0.3776012659072876, "entropy": 0.1093340739607811, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:08.856721Z", "loop": 1988, "env_steps": 1222041599, "loss": 0.00449076434597373, "avg_return": 0.48502570390701294, "regret": 0.3776012659072876, "entropy": 0.10339014232158661, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:09.710716Z", "loop": 1989, "env_steps": 1222655999, "loss": 0.0045974417589604855, "avg_return": 0.48560187220573425, "regret": 0.3776012659072876, "entropy": 0.10981874167919159, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:10.604744Z", "loop": 1990, "env_steps": 1223270399, "loss": 0.0043966397643089294, "avg_return": 0.4868618845939636, "regret": 0.37888699769973755, "entropy": 0.10850874334573746, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:11.457960Z", "loop": 1991, "env_steps": 1223884799, "loss": 0.004342545755207539, "avg_return": 0.47762492299079895, "regret": 0.37888699769973755, "entropy": 0.10356592386960983, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:12.311531Z", "loop": 1992, "env_steps": 1224499199, "loss": 0.004625156056135893, "avg_return": 0.49052390456199646, "regret": 0.37888699769973755, "entropy": 0.10934283584356308, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:13.166185Z", "loop": 1993, "env_steps": 1225113599, "loss": 0.003983595408499241, "avg_return": 0.4870247542858124, "regret": 0.37888699769973755, "entropy": 0.10323582589626312, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:14.020349Z", "loop": 1994, "env_steps": 1225727999, "loss": 0.004502181429415941, "avg_return": 0.48887839913368225, "regret": 0.37888699769973755, "entropy": 0.10437650978565216, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:14.913774Z", "loop": 1995, "env_steps": 1226342399, "loss": 0.004173662047833204, "avg_return": 0.48486360907554626, "regret": 0.3771764636039734, "entropy": 0.10697726160287857, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:15.767106Z", "loop": 1996, "env_steps": 1226956799, "loss": 0.004042792599648237, "avg_return": 0.4820084273815155, "regret": 0.3771764636039734, "entropy": 0.10805178433656693, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:16.621738Z", "loop": 1997, "env_steps": 1227571199, "loss": 0.0043777767568826675, "avg_return": 0.48961660265922546, "regret": 0.3771764636039734, "entropy": 0.11054384708404541, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:17.475268Z", "loop": 1998, "env_steps": 1228185599, "loss": 0.0037984028458595276, "avg_return": 0.49070191383361816, "regret": 0.3771764636039734, "entropy": 0.10700293630361557, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:18.328932Z", "loop": 1999, "env_steps": 1228799999, "loss": 0.004092003684490919, "avg_return": 0.48617005348205566, "regret": 0.3771764636039734, "entropy": 0.11769226938486099, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:19.223271Z", "loop": 2000, "env_steps": 1229414399, "loss": 0.004068356938660145, "avg_return": 0.4900481700897217, "regret": 0.37601223587989807, "entropy": 0.1133590042591095, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:20.077667Z", "loop": 2001, "env_steps": 1230028799, "loss": 0.004052816424518824, "avg_return": 0.48910197615623474, "regret": 0.37601223587989807, "entropy": 0.12397196143865585, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:20.931617Z", "loop": 2002, "env_steps": 1230643199, "loss": 0.004051447845995426, "avg_return": 0.49707338213920593, "regret": 0.37601223587989807, "entropy": 0.12021734565496445, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:21.785956Z", "loop": 2003, "env_steps": 1231257599, "loss": 0.004196028225123882, "avg_return": 0.49266552925109863, "regret": 0.37601223587989807, "entropy": 0.12085699290037155, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:22.640946Z", "loop": 2004, "env_steps": 1231871999, "loss": 0.004505055490881205, "avg_return": 0.48801764845848083, "regret": 0.37601223587989807, "entropy": 0.12630780041217804, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:23.495586Z", "loop": 2005, "env_steps": 1232486399, "loss": 0.003871276741847396, "avg_return": 0.48301392793655396, "regret": 0.37601223587989807, "entropy": 0.12441329658031464, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:24.348426Z", "loop": 2006, "env_steps": 1233100799, "loss": 0.004992740228772163, "avg_return": 0.4920264184474945, "regret": 0.37601223587989807, "entropy": 0.13900668919086456, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:25.201278Z", "loop": 2007, "env_steps": 1233715199, "loss": 0.004545816220343113, "avg_return": 0.48574861884117126, "regret": 0.37601223587989807, "entropy": 0.1349344700574875, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:26.053991Z", "loop": 2008, "env_steps": 1234329599, "loss": 0.00403721584007144, "avg_return": 0.4859870970249176, "regret": 0.37601223587989807, "entropy": 0.14123354852199554, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:26.907205Z", "loop": 2009, "env_steps": 1234943999, "loss": 0.004135608207434416, "avg_return": 0.4874036908149719, "regret": 0.37601223587989807, "entropy": 0.13670210540294647, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:27.798767Z", "loop": 2010, "env_steps": 1235558399, "loss": 0.004157436545938253, "avg_return": 0.4893973469734192, "regret": 0.3753375709056854, "entropy": 0.13030262291431427, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:28.650349Z", "loop": 2011, "env_steps": 1236172799, "loss": 0.003931703045964241, "avg_return": 0.4937586486339569, "regret": 0.3753375709056854, "entropy": 0.12412042915821075, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:29.502359Z", "loop": 2012, "env_steps": 1236787199, "loss": 0.0037373527884483337, "avg_return": 0.48451951146125793, "regret": 0.3753375709056854, "entropy": 0.12844304740428925, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:30.355562Z", "loop": 2013, "env_steps": 1237401599, "loss": 0.003509676782414317, "avg_return": 0.47871461510658264, "regret": 0.3753375709056854, "entropy": 0.12664204835891724, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:31.209180Z", "loop": 2014, "env_steps": 1238015999, "loss": 0.003720892360433936, "avg_return": 0.47974976897239685, "regret": 0.3753375709056854, "entropy": 0.13041430711746216, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:32.061249Z", "loop": 2015, "env_steps": 1238630399, "loss": 0.0043265605345368385, "avg_return": 0.49310681223869324, "regret": 0.3753375709056854, "entropy": 0.13819807767868042, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:32.912848Z", "loop": 2016, "env_steps": 1239244799, "loss": 0.004487514961510897, "avg_return": 0.494184672832489, "regret": 0.3753375709056854, "entropy": 0.1354132443666458, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:33.765209Z", "loop": 2017, "env_steps": 1239859199, "loss": 0.004473231267184019, "avg_return": 0.49036088585853577, "regret": 0.3753375709056854, "entropy": 0.13293573260307312, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:34.619251Z", "loop": 2018, "env_steps": 1240473599, "loss": 0.004195674788206816, "avg_return": 0.4866091012954712, "regret": 0.3753375709056854, "entropy": 0.13450652360916138, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:35.472409Z", "loop": 2019, "env_steps": 1241087999, "loss": 0.004116343799978495, "avg_return": 0.4852884113788605, "regret": 0.3753375709056854, "entropy": 0.1297358125448227, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:36.364355Z", "loop": 2020, "env_steps": 1241702399, "loss": 0.004423670936375856, "avg_return": 0.48328086733818054, "regret": 0.37550216913223267, "entropy": 0.12951532006263733, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:37.217057Z", "loop": 2021, "env_steps": 1242316799, "loss": 0.004240734968334436, "avg_return": 0.4840970039367676, "regret": 0.37550216913223267, "entropy": 0.125987708568573, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:38.070177Z", "loop": 2022, "env_steps": 1242931199, "loss": 0.003971980419009924, "avg_return": 0.4901450574398041, "regret": 0.37550216913223267, "entropy": 0.12663857638835907, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:38.923563Z", "loop": 2023, "env_steps": 1243545599, "loss": 0.004709583707153797, "avg_return": 0.48665085434913635, "regret": 0.37550216913223267, "entropy": 0.12389606982469559, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:39.776186Z", "loop": 2024, "env_steps": 1244159999, "loss": 0.004428258165717125, "avg_return": 0.49598339200019836, "regret": 0.37550216913223267, "entropy": 0.12709669768810272, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:40.629366Z", "loop": 2025, "env_steps": 1244774399, "loss": 0.0038907011039555073, "avg_return": 0.4859859347343445, "regret": 0.37550216913223267, "entropy": 0.12151110172271729, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:41.482472Z", "loop": 2026, "env_steps": 1245388799, "loss": 0.003284784033894539, "avg_return": 0.4881376326084137, "regret": 0.37550216913223267, "entropy": 0.11786758899688721, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:42.335091Z", "loop": 2027, "env_steps": 1246003199, "loss": 0.0026451379526406527, "avg_return": 0.484326034784317, "regret": 0.37550216913223267, "entropy": 0.10543163865804672, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:43.187355Z", "loop": 2028, "env_steps": 1246617599, "loss": 0.0021327261347323656, "avg_return": 0.4847818613052368, "regret": 0.37550216913223267, "entropy": 0.09396448731422424, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:44.039011Z", "loop": 2029, "env_steps": 1247231999, "loss": 0.002162980381399393, "avg_return": 0.4927401840686798, "regret": 0.37550216913223267, "entropy": 0.08392105251550674, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:44.932428Z", "loop": 2030, "env_steps": 1247846399, "loss": 0.0018709193682298064, "avg_return": 0.4903780221939087, "regret": 0.37537121772766113, "entropy": 0.08414383977651596, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:45.786745Z", "loop": 2031, "env_steps": 1248460799, "loss": 0.0019320648862048984, "avg_return": 0.48603108525276184, "regret": 0.37537121772766113, "entropy": 0.0882728323340416, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:46.640656Z", "loop": 2032, "env_steps": 1249075199, "loss": 0.0018750783056020737, "avg_return": 0.48768383264541626, "regret": 0.37537121772766113, "entropy": 0.08946997672319412, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:47.493684Z", "loop": 2033, "env_steps": 1249689599, "loss": 0.0019170325249433517, "avg_return": 0.47948578000068665, "regret": 0.37537121772766113, "entropy": 0.0886213630437851, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:48.347723Z", "loop": 2034, "env_steps": 1250303999, "loss": 0.0017813442973420024, "avg_return": 0.48892849683761597, "regret": 0.37537121772766113, "entropy": 0.08962050080299377, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:49.201586Z", "loop": 2035, "env_steps": 1250918399, "loss": 0.0017219011206179857, "avg_return": 0.492919921875, "regret": 0.37537121772766113, "entropy": 0.08523356914520264, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:50.055409Z", "loop": 2036, "env_steps": 1251532799, "loss": 0.0019439574098214507, "avg_return": 0.4888816475868225, "regret": 0.37537121772766113, "entropy": 0.09152199327945709, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:50.908301Z", "loop": 2037, "env_steps": 1252147199, "loss": 0.0019161952659487724, "avg_return": 0.48826509714126587, "regret": 0.37537121772766113, "entropy": 0.08433298021554947, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:51.761613Z", "loop": 2038, "env_steps": 1252761599, "loss": 0.0018887085607275367, "avg_return": 0.48515838384628296, "regret": 0.37537121772766113, "entropy": 0.09120609611272812, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:52.614129Z", "loop": 2039, "env_steps": 1253375999, "loss": 0.0018071895465254784, "avg_return": 0.4847579002380371, "regret": 0.37537121772766113, "entropy": 0.0874948725104332, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:53.506107Z", "loop": 2040, "env_steps": 1253990399, "loss": 0.0016275061061605811, "avg_return": 0.48856064677238464, "regret": 0.37550997734069824, "entropy": 0.08715291321277618, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:54.359631Z", "loop": 2041, "env_steps": 1254604799, "loss": 0.0017023911932483315, "avg_return": 0.48822125792503357, "regret": 0.37550997734069824, "entropy": 0.09040851891040802, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:55.213851Z", "loop": 2042, "env_steps": 1255219199, "loss": 0.0016779740108177066, "avg_return": 0.48536941409111023, "regret": 0.37550997734069824, "entropy": 0.09038208425045013, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:56.067193Z", "loop": 2043, "env_steps": 1255833599, "loss": 0.0017534872749820352, "avg_return": 0.4910368323326111, "regret": 0.37550997734069824, "entropy": 0.09310198575258255, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:56.920830Z", "loop": 2044, "env_steps": 1256447999, "loss": 0.0018765826243907213, "avg_return": 0.4974939227104187, "regret": 0.37550997734069824, "entropy": 0.09148433059453964, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:57.775304Z", "loop": 2045, "env_steps": 1257062399, "loss": 0.0019990960136055946, "avg_return": 0.49544525146484375, "regret": 0.37550997734069824, "entropy": 0.09593162685632706, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:58.628494Z", "loop": 2046, "env_steps": 1257676799, "loss": 0.001961673842743039, "avg_return": 0.49104565382003784, "regret": 0.37550997734069824, "entropy": 0.09782758355140686, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:52:59.481039Z", "loop": 2047, "env_steps": 1258291199, "loss": 0.0019143415847793221, "avg_return": 0.4921506941318512, "regret": 0.37550997734069824, "entropy": 0.10007153451442719, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:00.333249Z", "loop": 2048, "env_steps": 1258905599, "loss": 0.0018759614322334528, "avg_return": 0.48618119955062866, "regret": 0.37550997734069824, "entropy": 0.09554114937782288, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:01.185844Z", "loop": 2049, "env_steps": 1259519999, "loss": 0.0024484938476234674, "avg_return": 0.49206966161727905, "regret": 0.37550997734069824, "entropy": 0.10078616440296173, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:02.077136Z", "loop": 2050, "env_steps": 1260134399, "loss": 0.0019333113450556993, "avg_return": 0.48236197233200073, "regret": 0.3756817579269409, "entropy": 0.0987514853477478, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:02.930973Z", "loop": 2051, "env_steps": 1260748799, "loss": 0.0019118670606985688, "avg_return": 0.4920736253261566, "regret": 0.3756817579269409, "entropy": 0.09711704403162003, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:03.784228Z", "loop": 2052, "env_steps": 1261363199, "loss": 0.0016530780121684074, "avg_return": 0.49120092391967773, "regret": 0.3756817579269409, "entropy": 0.09517133235931396, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:04.637626Z", "loop": 2053, "env_steps": 1261977599, "loss": 0.0017988743493333459, "avg_return": 0.48250144720077515, "regret": 0.3756817579269409, "entropy": 0.09370709210634232, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:05.491396Z", "loop": 2054, "env_steps": 1262591999, "loss": 0.00184111506678164, "avg_return": 0.49262142181396484, "regret": 0.3756817579269409, "entropy": 0.09372217208147049, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:06.344621Z", "loop": 2055, "env_steps": 1263206399, "loss": 0.0017399750649929047, "avg_return": 0.4848715364933014, "regret": 0.3756817579269409, "entropy": 0.09147133678197861, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:07.197259Z", "loop": 2056, "env_steps": 1263820799, "loss": 0.0016948927659541368, "avg_return": 0.49145713448524475, "regret": 0.3756817579269409, "entropy": 0.09167235344648361, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:08.049973Z", "loop": 2057, "env_steps": 1264435199, "loss": 0.001959008164703846, "avg_return": 0.48847320675849915, "regret": 0.3756817579269409, "entropy": 0.0921189934015274, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:08.903137Z", "loop": 2058, "env_steps": 1265049599, "loss": 0.0020270554814487696, "avg_return": 0.4785603880882263, "regret": 0.3756817579269409, "entropy": 0.09210723638534546, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:09.755837Z", "loop": 2059, "env_steps": 1265663999, "loss": 0.0018604880897328258, "avg_return": 0.4861542284488678, "regret": 0.3756817579269409, "entropy": 0.09070434421300888, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:10.647779Z", "loop": 2060, "env_steps": 1266278399, "loss": 0.0022082109935581684, "avg_return": 0.4896980822086334, "regret": 0.37591660022735596, "entropy": 0.095744788646698, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:11.501166Z", "loop": 2061, "env_steps": 1266892799, "loss": 0.0018857931718230247, "avg_return": 0.4827137291431427, "regret": 0.37591660022735596, "entropy": 0.08989410847425461, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:12.354541Z", "loop": 2062, "env_steps": 1267507199, "loss": 0.0019338298588991165, "avg_return": 0.4964911937713623, "regret": 0.37591660022735596, "entropy": 0.08954887092113495, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:13.207159Z", "loop": 2063, "env_steps": 1268121599, "loss": 0.0018896382534876466, "avg_return": 0.4801476001739502, "regret": 0.37591660022735596, "entropy": 0.09899771213531494, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:14.060703Z", "loop": 2064, "env_steps": 1268735999, "loss": 0.001847849111072719, "avg_return": 0.48836782574653625, "regret": 0.37591660022735596, "entropy": 0.09811002016067505, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:14.913090Z", "loop": 2065, "env_steps": 1269350399, "loss": 0.001924224547110498, "avg_return": 0.4940817356109619, "regret": 0.37591660022735596, "entropy": 0.1033247709274292, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:15.765876Z", "loop": 2066, "env_steps": 1269964799, "loss": 0.0020949316676706076, "avg_return": 0.4820527136325836, "regret": 0.37591660022735596, "entropy": 0.10159704089164734, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:16.619278Z", "loop": 2067, "env_steps": 1270579199, "loss": 0.0024862352292984724, "avg_return": 0.48086726665496826, "regret": 0.37591660022735596, "entropy": 0.10884695500135422, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:17.472750Z", "loop": 2068, "env_steps": 1271193599, "loss": 0.002379226963967085, "avg_return": 0.48049840331077576, "regret": 0.37591660022735596, "entropy": 0.11314087361097336, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:18.325105Z", "loop": 2069, "env_steps": 1271807999, "loss": 0.0026369399856776, "avg_return": 0.48593375086784363, "regret": 0.37591660022735596, "entropy": 0.111296646296978, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:19.216288Z", "loop": 2070, "env_steps": 1272422399, "loss": 0.0022612111642956734, "avg_return": 0.4893029034137726, "regret": 0.3754289150238037, "entropy": 0.11549965292215347, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:20.069003Z", "loop": 2071, "env_steps": 1273036799, "loss": 0.0021367052104324102, "avg_return": 0.4924132525920868, "regret": 0.3754289150238037, "entropy": 0.10488677769899368, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:20.923174Z", "loop": 2072, "env_steps": 1273651199, "loss": 0.002061155391857028, "avg_return": 0.48412343859672546, "regret": 0.3754289150238037, "entropy": 0.09934127330780029, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:21.775593Z", "loop": 2073, "env_steps": 1274265599, "loss": 0.0019123706733807921, "avg_return": 0.4891100227832794, "regret": 0.3754289150238037, "entropy": 0.10399830341339111, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:22.627742Z", "loop": 2074, "env_steps": 1274879999, "loss": 0.0019517441978678107, "avg_return": 0.4799494445323944, "regret": 0.3754289150238037, "entropy": 0.1043187752366066, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:23.480021Z", "loop": 2075, "env_steps": 1275494399, "loss": 0.0018347057048231363, "avg_return": 0.49035874009132385, "regret": 0.3754289150238037, "entropy": 0.10615761578083038, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:24.333808Z", "loop": 2076, "env_steps": 1276108799, "loss": 0.0019841815810650587, "avg_return": 0.4858354926109314, "regret": 0.3754289150238037, "entropy": 0.09539157897233963, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:25.186586Z", "loop": 2077, "env_steps": 1276723199, "loss": 0.0021546785719692707, "avg_return": 0.4912591576576233, "regret": 0.3754289150238037, "entropy": 0.10094981640577316, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:26.039517Z", "loop": 2078, "env_steps": 1277337599, "loss": 0.0019937478937208652, "avg_return": 0.48607513308525085, "regret": 0.3754289150238037, "entropy": 0.10096405446529388, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:26.892145Z", "loop": 2079, "env_steps": 1277951999, "loss": 0.0018383044516667724, "avg_return": 0.4884088337421417, "regret": 0.3754289150238037, "entropy": 0.1004856675863266, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:27.784674Z", "loop": 2080, "env_steps": 1278566399, "loss": 0.0014536724193021655, "avg_return": 0.49117422103881836, "regret": 0.37533700466156006, "entropy": 0.09289006143808365, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:28.638293Z", "loop": 2081, "env_steps": 1279180799, "loss": 0.0016440667677670717, "avg_return": 0.48196345567703247, "regret": 0.37533700466156006, "entropy": 0.09749557077884674, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:29.492209Z", "loop": 2082, "env_steps": 1279795199, "loss": 0.0017859945073723793, "avg_return": 0.48713040351867676, "regret": 0.37533700466156006, "entropy": 0.08627410978078842, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:30.344689Z", "loop": 2083, "env_steps": 1280409599, "loss": 0.001954339910298586, "avg_return": 0.49265238642692566, "regret": 0.37533700466156006, "entropy": 0.09309778362512589, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:31.198210Z", "loop": 2084, "env_steps": 1281023999, "loss": 0.0021920986473560333, "avg_return": 0.49038198590278625, "regret": 0.37533700466156006, "entropy": 0.09187674522399902, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:32.051997Z", "loop": 2085, "env_steps": 1281638399, "loss": 0.0022593678440898657, "avg_return": 0.49319586157798767, "regret": 0.37533700466156006, "entropy": 0.09062521159648895, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:32.905116Z", "loop": 2086, "env_steps": 1282252799, "loss": 0.002158314222469926, "avg_return": 0.48948875069618225, "regret": 0.37533700466156006, "entropy": 0.09045691043138504, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:33.758011Z", "loop": 2087, "env_steps": 1282867199, "loss": 0.002232090337201953, "avg_return": 0.4823901355266571, "regret": 0.37533700466156006, "entropy": 0.09675678610801697, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:34.611094Z", "loop": 2088, "env_steps": 1283481599, "loss": 0.002080939244478941, "avg_return": 0.48819032311439514, "regret": 0.37533700466156006, "entropy": 0.09321042150259018, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:35.463687Z", "loop": 2089, "env_steps": 1284095999, "loss": 0.002375515643507242, "avg_return": 0.4881117343902588, "regret": 0.37533700466156006, "entropy": 0.08689992874860764, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:36.356004Z", "loop": 2090, "env_steps": 1284710399, "loss": 0.0020026378333568573, "avg_return": 0.48458048701286316, "regret": 0.3753652572631836, "entropy": 0.08941236138343811, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:37.210193Z", "loop": 2091, "env_steps": 1285324799, "loss": 0.0018615004373714328, "avg_return": 0.47613242268562317, "regret": 0.3753652572631836, "entropy": 0.09316731989383698, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:38.063928Z", "loop": 2092, "env_steps": 1285939199, "loss": 0.0020241045858711004, "avg_return": 0.4865293502807617, "regret": 0.3753652572631836, "entropy": 0.09802057594060898, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:38.916740Z", "loop": 2093, "env_steps": 1286553599, "loss": 0.0019283642759546638, "avg_return": 0.48555848002433777, "regret": 0.3753652572631836, "entropy": 0.08753028512001038, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:39.770190Z", "loop": 2094, "env_steps": 1287167999, "loss": 0.0021142447367310524, "avg_return": 0.49544674158096313, "regret": 0.3753652572631836, "entropy": 0.08572244644165039, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:40.623932Z", "loop": 2095, "env_steps": 1287782399, "loss": 0.0016426362562924623, "avg_return": 0.49977773427963257, "regret": 0.3753652572631836, "entropy": 0.09042719006538391, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:41.478369Z", "loop": 2096, "env_steps": 1288396799, "loss": 0.001890396000817418, "avg_return": 0.4968115985393524, "regret": 0.3753652572631836, "entropy": 0.08692540228366852, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:42.331651Z", "loop": 2097, "env_steps": 1289011199, "loss": 0.002021374646574259, "avg_return": 0.4822912812232971, "regret": 0.3753652572631836, "entropy": 0.09878775477409363, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:43.185113Z", "loop": 2098, "env_steps": 1289625599, "loss": 0.0024685116950422525, "avg_return": 0.487857460975647, "regret": 0.3753652572631836, "entropy": 0.11035066843032837, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:44.038559Z", "loop": 2099, "env_steps": 1290239999, "loss": 0.0031134800519794226, "avg_return": 0.49530062079429626, "regret": 0.3753652572631836, "entropy": 0.12351328134536743, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:44.930237Z", "loop": 2100, "env_steps": 1290854399, "loss": 0.004037090577185154, "avg_return": 0.48918652534484863, "regret": 0.3754136562347412, "entropy": 0.1217288076877594, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:45.783884Z", "loop": 2101, "env_steps": 1291468799, "loss": 0.0050785131752491, "avg_return": 0.49262431263923645, "regret": 0.3754136562347412, "entropy": 0.1290765106678009, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:46.636946Z", "loop": 2102, "env_steps": 1292083199, "loss": 0.0037344282027333975, "avg_return": 0.4799322485923767, "regret": 0.3754136562347412, "entropy": 0.12175986915826797, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:47.491395Z", "loop": 2103, "env_steps": 1292697599, "loss": 0.0034551587887108326, "avg_return": 0.48718273639678955, "regret": 0.3754136562347412, "entropy": 0.10182610899209976, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:48.346252Z", "loop": 2104, "env_steps": 1293311999, "loss": 0.003119760425761342, "avg_return": 0.49156656861305237, "regret": 0.3754136562347412, "entropy": 0.09444881230592728, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:49.200439Z", "loop": 2105, "env_steps": 1293926399, "loss": 0.003014031797647476, "avg_return": 0.48830446600914, "regret": 0.3754136562347412, "entropy": 0.08692220598459244, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:50.055357Z", "loop": 2106, "env_steps": 1294540799, "loss": 0.0032286110799759626, "avg_return": 0.48715344071388245, "regret": 0.3754136562347412, "entropy": 0.08845637738704681, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:50.908279Z", "loop": 2107, "env_steps": 1295155199, "loss": 0.0036850478500127792, "avg_return": 0.48702189326286316, "regret": 0.3754136562347412, "entropy": 0.0891292467713356, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:51.761320Z", "loop": 2108, "env_steps": 1295769599, "loss": 0.003663996234536171, "avg_return": 0.4857410788536072, "regret": 0.3754136562347412, "entropy": 0.0954524427652359, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:52.614593Z", "loop": 2109, "env_steps": 1296383999, "loss": 0.0037627238780260086, "avg_return": 0.4885181784629822, "regret": 0.3754136562347412, "entropy": 0.09253892302513123, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:53.505772Z", "loop": 2110, "env_steps": 1296998399, "loss": 0.0038402259815484285, "avg_return": 0.486349493265152, "regret": 0.3793340027332306, "entropy": 0.0896330401301384, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:54.359247Z", "loop": 2111, "env_steps": 1297612799, "loss": 0.0032598841935396194, "avg_return": 0.48750022053718567, "regret": 0.3793340027332306, "entropy": 0.08677729219198227, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:55.212076Z", "loop": 2112, "env_steps": 1298227199, "loss": 0.003177393227815628, "avg_return": 0.48652389645576477, "regret": 0.3793340027332306, "entropy": 0.08906968683004379, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:56.065265Z", "loop": 2113, "env_steps": 1298841599, "loss": 0.003259292570874095, "avg_return": 0.4856160581111908, "regret": 0.3793340027332306, "entropy": 0.09652265161275864, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:56.918252Z", "loop": 2114, "env_steps": 1299455999, "loss": 0.0037269608583301306, "avg_return": 0.4890756905078888, "regret": 0.3793340027332306, "entropy": 0.1060565859079361, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:57.771492Z", "loop": 2115, "env_steps": 1300070399, "loss": 0.0038276698905974627, "avg_return": 0.4832482933998108, "regret": 0.3793340027332306, "entropy": 0.10017123818397522, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:58.625071Z", "loop": 2116, "env_steps": 1300684799, "loss": 0.0029234362300485373, "avg_return": 0.4875357747077942, "regret": 0.3793340027332306, "entropy": 0.09941718727350235, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:53:59.479191Z", "loop": 2117, "env_steps": 1301299199, "loss": 0.003410911886021495, "avg_return": 0.4821007251739502, "regret": 0.3793340027332306, "entropy": 0.10507074743509293, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:00.332990Z", "loop": 2118, "env_steps": 1301913599, "loss": 0.0033953560050576925, "avg_return": 0.4797685742378235, "regret": 0.3793340027332306, "entropy": 0.10294753313064575, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:01.185811Z", "loop": 2119, "env_steps": 1302527999, "loss": 0.0038414187729358673, "avg_return": 0.4981462359428406, "regret": 0.3793340027332306, "entropy": 0.10732045024633408, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:02.079743Z", "loop": 2120, "env_steps": 1303142399, "loss": 0.0038344867061823606, "avg_return": 0.48621806502342224, "regret": 0.37564539909362793, "entropy": 0.11129234731197357, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:02.934087Z", "loop": 2121, "env_steps": 1303756799, "loss": 0.0034641025122255087, "avg_return": 0.49171561002731323, "regret": 0.37564539909362793, "entropy": 0.10370437055826187, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:03.787089Z", "loop": 2122, "env_steps": 1304371199, "loss": 0.0037728857714682817, "avg_return": 0.4935555160045624, "regret": 0.37564539909362793, "entropy": 0.11209787428379059, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:04.640033Z", "loop": 2123, "env_steps": 1304985599, "loss": 0.0037231724709272385, "avg_return": 0.4919930100440979, "regret": 0.37564539909362793, "entropy": 0.1109728068113327, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:05.493862Z", "loop": 2124, "env_steps": 1305599999, "loss": 0.004033736418932676, "avg_return": 0.4847393333911896, "regret": 0.37564539909362793, "entropy": 0.11388339102268219, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:06.348005Z", "loop": 2125, "env_steps": 1306214399, "loss": 0.0037500408943742514, "avg_return": 0.48798656463623047, "regret": 0.37564539909362793, "entropy": 0.1169251799583435, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:07.202256Z", "loop": 2126, "env_steps": 1306828799, "loss": 0.0038347523659467697, "avg_return": 0.4921703338623047, "regret": 0.37564539909362793, "entropy": 0.11521919816732407, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:08.054786Z", "loop": 2127, "env_steps": 1307443199, "loss": 0.0032578192185610533, "avg_return": 0.4871942400932312, "regret": 0.37564539909362793, "entropy": 0.11238669604063034, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:08.907785Z", "loop": 2128, "env_steps": 1308057599, "loss": 0.003418639302253723, "avg_return": 0.48302140831947327, "regret": 0.37564539909362793, "entropy": 0.11216865479946136, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:09.761860Z", "loop": 2129, "env_steps": 1308671999, "loss": 0.003590516746044159, "avg_return": 0.48603343963623047, "regret": 0.37564539909362793, "entropy": 0.11395193636417389, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:10.657315Z", "loop": 2130, "env_steps": 1309286399, "loss": 0.003217672696337104, "avg_return": 0.4827072322368622, "regret": 0.37539151310920715, "entropy": 0.1146627813577652, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:11.510582Z", "loop": 2131, "env_steps": 1309900799, "loss": 0.003775622695684433, "avg_return": 0.4868280589580536, "regret": 0.37539151310920715, "entropy": 0.11155001074075699, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:12.364782Z", "loop": 2132, "env_steps": 1310515199, "loss": 0.0035929791629314423, "avg_return": 0.49051418900489807, "regret": 0.37539151310920715, "entropy": 0.11122732609510422, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:13.218625Z", "loop": 2133, "env_steps": 1311129599, "loss": 0.003682246897369623, "avg_return": 0.48345375061035156, "regret": 0.37539151310920715, "entropy": 0.11274474859237671, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:14.071525Z", "loop": 2134, "env_steps": 1311743999, "loss": 0.0033848800230771303, "avg_return": 0.4866228401660919, "regret": 0.37539151310920715, "entropy": 0.10482338815927505, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:14.923788Z", "loop": 2135, "env_steps": 1312358399, "loss": 0.003051833715289831, "avg_return": 0.48762792348861694, "regret": 0.37539151310920715, "entropy": 0.10482370108366013, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:15.776651Z", "loop": 2136, "env_steps": 1312972799, "loss": 0.0029802012722939253, "avg_return": 0.49196478724479675, "regret": 0.37539151310920715, "entropy": 0.09351973980665207, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:16.630397Z", "loop": 2137, "env_steps": 1313587199, "loss": 0.0024962746538221836, "avg_return": 0.49065837264060974, "regret": 0.37539151310920715, "entropy": 0.08371938765048981, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:17.483439Z", "loop": 2138, "env_steps": 1314201599, "loss": 0.0028433219995349646, "avg_return": 0.48089540004730225, "regret": 0.37539151310920715, "entropy": 0.08613641560077667, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:18.336859Z", "loop": 2139, "env_steps": 1314815999, "loss": 0.003108802018687129, "avg_return": 0.4936716854572296, "regret": 0.37539151310920715, "entropy": 0.082461416721344, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:19.230286Z", "loop": 2140, "env_steps": 1315430399, "loss": 0.0032748859375715256, "avg_return": 0.4835066795349121, "regret": 0.3775567412376404, "entropy": 0.08451688289642334, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:20.084831Z", "loop": 2141, "env_steps": 1316044799, "loss": 0.003542860271409154, "avg_return": 0.48350343108177185, "regret": 0.3775567412376404, "entropy": 0.08552772551774979, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:20.938729Z", "loop": 2142, "env_steps": 1316659199, "loss": 0.003508365945890546, "avg_return": 0.4866541624069214, "regret": 0.3775567412376404, "entropy": 0.08839588612318039, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:21.791711Z", "loop": 2143, "env_steps": 1317273599, "loss": 0.003945255186408758, "avg_return": 0.4804598093032837, "regret": 0.3775567412376404, "entropy": 0.0841149091720581, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:22.645587Z", "loop": 2144, "env_steps": 1317887999, "loss": 0.0036208254750818014, "avg_return": 0.48007732629776, "regret": 0.3775567412376404, "entropy": 0.08726099133491516, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:23.499404Z", "loop": 2145, "env_steps": 1318502399, "loss": 0.0033126752823591232, "avg_return": 0.48293712735176086, "regret": 0.3775567412376404, "entropy": 0.08614162355661392, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:24.354655Z", "loop": 2146, "env_steps": 1319116799, "loss": 0.0029534122440963984, "avg_return": 0.4925665855407715, "regret": 0.3775567412376404, "entropy": 0.08210740238428116, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:25.207578Z", "loop": 2147, "env_steps": 1319731199, "loss": 0.0027284969110041857, "avg_return": 0.48607322573661804, "regret": 0.3775567412376404, "entropy": 0.08203624188899994, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:26.060204Z", "loop": 2148, "env_steps": 1320345599, "loss": 0.002715751528739929, "avg_return": 0.49108195304870605, "regret": 0.3775567412376404, "entropy": 0.08520552515983582, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:26.913941Z", "loop": 2149, "env_steps": 1320959999, "loss": 0.0032417529728263617, "avg_return": 0.48857203125953674, "regret": 0.3775567412376404, "entropy": 0.09223072230815887, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:27.807120Z", "loop": 2150, "env_steps": 1321574399, "loss": 0.003199853701516986, "avg_return": 0.4859705865383148, "regret": 0.37558773159980774, "entropy": 0.0970190092921257, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:28.660639Z", "loop": 2151, "env_steps": 1322188799, "loss": 0.0029851188883185387, "avg_return": 0.48285990953445435, "regret": 0.37558773159980774, "entropy": 0.10283508896827698, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:29.514485Z", "loop": 2152, "env_steps": 1322803199, "loss": 0.003531665075570345, "avg_return": 0.49269217252731323, "regret": 0.37558773159980774, "entropy": 0.10115119069814682, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:30.368486Z", "loop": 2153, "env_steps": 1323417599, "loss": 0.003279089694842696, "avg_return": 0.4918290376663208, "regret": 0.37558773159980774, "entropy": 0.11054986715316772, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:31.222587Z", "loop": 2154, "env_steps": 1324031999, "loss": 0.003362280549481511, "avg_return": 0.48752209544181824, "regret": 0.37558773159980774, "entropy": 0.10733535140752792, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:32.074830Z", "loop": 2155, "env_steps": 1324646399, "loss": 0.00333397276699543, "avg_return": 0.48691579699516296, "regret": 0.37558773159980774, "entropy": 0.10717259347438812, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:32.926796Z", "loop": 2156, "env_steps": 1325260799, "loss": 0.003224574029445648, "avg_return": 0.48799586296081543, "regret": 0.37558773159980774, "entropy": 0.10686220973730087, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:33.779650Z", "loop": 2157, "env_steps": 1325875199, "loss": 0.0026614784728735685, "avg_return": 0.4823675751686096, "regret": 0.37558773159980774, "entropy": 0.0907549187541008, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:34.633198Z", "loop": 2158, "env_steps": 1326489599, "loss": 0.0023985987063497305, "avg_return": 0.48234909772872925, "regret": 0.37558773159980774, "entropy": 0.08374087512493134, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:35.486646Z", "loop": 2159, "env_steps": 1327103999, "loss": 0.002596907550469041, "avg_return": 0.48417267203330994, "regret": 0.37558773159980774, "entropy": 0.08105561882257462, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:36.379050Z", "loop": 2160, "env_steps": 1327718399, "loss": 0.002941124839708209, "avg_return": 0.49040549993515015, "regret": 0.3761840760707855, "entropy": 0.07732551544904709, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:37.232912Z", "loop": 2161, "env_steps": 1328332799, "loss": 0.0036766522098332644, "avg_return": 0.4904281795024872, "regret": 0.3761840760707855, "entropy": 0.08350169658660889, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:38.087881Z", "loop": 2162, "env_steps": 1328947199, "loss": 0.0034152783919125795, "avg_return": 0.4880192279815674, "regret": 0.3761840760707855, "entropy": 0.08479562401771545, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:38.942102Z", "loop": 2163, "env_steps": 1329561599, "loss": 0.003115819999948144, "avg_return": 0.48741284012794495, "regret": 0.3761840760707855, "entropy": 0.0773351788520813, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:39.796044Z", "loop": 2164, "env_steps": 1330175999, "loss": 0.003432644996792078, "avg_return": 0.4860575497150421, "regret": 0.3761840760707855, "entropy": 0.08522921055555344, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:40.649666Z", "loop": 2165, "env_steps": 1330790399, "loss": 0.0034746613819152117, "avg_return": 0.49676790833473206, "regret": 0.3761840760707855, "entropy": 0.08225899934768677, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:41.504288Z", "loop": 2166, "env_steps": 1331404799, "loss": 0.004080490209162235, "avg_return": 0.49122047424316406, "regret": 0.3761840760707855, "entropy": 0.0874166339635849, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:42.358594Z", "loop": 2167, "env_steps": 1332019199, "loss": 0.003754861420020461, "avg_return": 0.48743298649787903, "regret": 0.3761840760707855, "entropy": 0.08296709507703781, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:43.212333Z", "loop": 2168, "env_steps": 1332633599, "loss": 0.003944107796996832, "avg_return": 0.48420900106430054, "regret": 0.3761840760707855, "entropy": 0.08768358826637268, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:44.067619Z", "loop": 2169, "env_steps": 1333247999, "loss": 0.003691940801218152, "avg_return": 0.48065415024757385, "regret": 0.3761840760707855, "entropy": 0.0839575007557869, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:44.960676Z", "loop": 2170, "env_steps": 1333862399, "loss": 0.004037334118038416, "avg_return": 0.486604779958725, "regret": 0.3772386312484741, "entropy": 0.08853936940431595, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:45.814885Z", "loop": 2171, "env_steps": 1334476799, "loss": 0.0036468624603003263, "avg_return": 0.4873480796813965, "regret": 0.3772386312484741, "entropy": 0.08593921363353729, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:46.669312Z", "loop": 2172, "env_steps": 1335091199, "loss": 0.0039397915825247765, "avg_return": 0.48791393637657166, "regret": 0.3772386312484741, "entropy": 0.09006572514772415, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:47.524041Z", "loop": 2173, "env_steps": 1335705599, "loss": 0.003288719803094864, "avg_return": 0.4916411340236664, "regret": 0.3772386312484741, "entropy": 0.08488120138645172, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:48.379132Z", "loop": 2174, "env_steps": 1336319999, "loss": 0.0026278679724782705, "avg_return": 0.4905960261821747, "regret": 0.3772386312484741, "entropy": 0.08136409521102905, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:49.232457Z", "loop": 2175, "env_steps": 1336934399, "loss": 0.0026116620283573866, "avg_return": 0.4929819405078888, "regret": 0.3772386312484741, "entropy": 0.0941072627902031, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:50.086103Z", "loop": 2176, "env_steps": 1337548799, "loss": 0.00342241651378572, "avg_return": 0.48682212829589844, "regret": 0.3772386312484741, "entropy": 0.10450605303049088, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:50.939083Z", "loop": 2177, "env_steps": 1338163199, "loss": 0.0032242138404399157, "avg_return": 0.48872116208076477, "regret": 0.3772386312484741, "entropy": 0.10742560029029846, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:51.792546Z", "loop": 2178, "env_steps": 1338777599, "loss": 0.0035066341515630484, "avg_return": 0.4857870042324066, "regret": 0.3772386312484741, "entropy": 0.11367154121398926, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:52.645797Z", "loop": 2179, "env_steps": 1339391999, "loss": 0.003880254225805402, "avg_return": 0.4915243685245514, "regret": 0.3772386312484741, "entropy": 0.11736821383237839, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:53.539087Z", "loop": 2180, "env_steps": 1340006399, "loss": 0.004020506050437689, "avg_return": 0.48340582847595215, "regret": 0.37533798813819885, "entropy": 0.12777243554592133, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:54.392138Z", "loop": 2181, "env_steps": 1340620799, "loss": 0.004338169004768133, "avg_return": 0.49008047580718994, "regret": 0.37533798813819885, "entropy": 0.13135024905204773, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:55.244738Z", "loop": 2182, "env_steps": 1341235199, "loss": 0.004003213252872229, "avg_return": 0.4856470823287964, "regret": 0.37533798813819885, "entropy": 0.1241382583975792, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:56.097599Z", "loop": 2183, "env_steps": 1341849599, "loss": 0.0030957264825701714, "avg_return": 0.4954662621021271, "regret": 0.37533798813819885, "entropy": 0.11608941107988358, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:56.951829Z", "loop": 2184, "env_steps": 1342463999, "loss": 0.003192306263372302, "avg_return": 0.4832271337509155, "regret": 0.37533798813819885, "entropy": 0.11621109396219254, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:57.806144Z", "loop": 2185, "env_steps": 1343078399, "loss": 0.002769497688859701, "avg_return": 0.4894314706325531, "regret": 0.37533798813819885, "entropy": 0.09843587875366211, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:58.659387Z", "loop": 2186, "env_steps": 1343692799, "loss": 0.0020604755263775587, "avg_return": 0.5013470649719238, "regret": 0.37533798813819885, "entropy": 0.08963042497634888, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:54:59.511503Z", "loop": 2187, "env_steps": 1344307199, "loss": 0.0019884579814970493, "avg_return": 0.49026408791542053, "regret": 0.37533798813819885, "entropy": 0.08871810138225555, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:00.364282Z", "loop": 2188, "env_steps": 1344921599, "loss": 0.001829985179938376, "avg_return": 0.4853866696357727, "regret": 0.37533798813819885, "entropy": 0.085352823138237, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:01.218838Z", "loop": 2189, "env_steps": 1345535999, "loss": 0.0016041024355217814, "avg_return": 0.4856685400009155, "regret": 0.37533798813819885, "entropy": 0.08660457283258438, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:02.116614Z", "loop": 2190, "env_steps": 1346150399, "loss": 0.0016652088379487395, "avg_return": 0.4873931109905243, "regret": 0.3754088282585144, "entropy": 0.08606944233179092, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:02.970961Z", "loop": 2191, "env_steps": 1346764799, "loss": 0.0018003551522269845, "avg_return": 0.4823215901851654, "regret": 0.3754088282585144, "entropy": 0.0863691046833992, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:03.824063Z", "loop": 2192, "env_steps": 1347379199, "loss": 0.0015726098790764809, "avg_return": 0.4837783873081207, "regret": 0.3754088282585144, "entropy": 0.08345062285661697, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:04.677673Z", "loop": 2193, "env_steps": 1347993599, "loss": 0.001589650521054864, "avg_return": 0.48516368865966797, "regret": 0.3754088282585144, "entropy": 0.08584234118461609, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:05.531444Z", "loop": 2194, "env_steps": 1348607999, "loss": 0.0015934959519654512, "avg_return": 0.4877714216709137, "regret": 0.3754088282585144, "entropy": 0.08083992451429367, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:06.384330Z", "loop": 2195, "env_steps": 1349222399, "loss": 0.0016097475308924913, "avg_return": 0.49901631474494934, "regret": 0.3754088282585144, "entropy": 0.08483909070491791, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:07.237273Z", "loop": 2196, "env_steps": 1349836799, "loss": 0.0018513360992074013, "avg_return": 0.48300182819366455, "regret": 0.3754088282585144, "entropy": 0.09130077809095383, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:08.090268Z", "loop": 2197, "env_steps": 1350451199, "loss": 0.0022559294011443853, "avg_return": 0.4953167736530304, "regret": 0.3754088282585144, "entropy": 0.09841111302375793, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:08.944109Z", "loop": 2198, "env_steps": 1351065599, "loss": 0.0020356227178126574, "avg_return": 0.491690993309021, "regret": 0.3754088282585144, "entropy": 0.09829901903867722, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:09.797159Z", "loop": 2199, "env_steps": 1351679999, "loss": 0.0020130565389990807, "avg_return": 0.4863767623901367, "regret": 0.3754088282585144, "entropy": 0.09778042882680893, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:10.689692Z", "loop": 2200, "env_steps": 1352294399, "loss": 0.0018397081876173615, "avg_return": 0.487796425819397, "regret": 0.3759942352771759, "entropy": 0.09633197635412216, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:11.544347Z", "loop": 2201, "env_steps": 1352908799, "loss": 0.0019035350997000933, "avg_return": 0.4944098889827728, "regret": 0.3759942352771759, "entropy": 0.1030743420124054, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:12.398668Z", "loop": 2202, "env_steps": 1353523199, "loss": 0.0023523166310042143, "avg_return": 0.4921219050884247, "regret": 0.3759942352771759, "entropy": 0.10808335244655609, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:13.251391Z", "loop": 2203, "env_steps": 1354137599, "loss": 0.002621532417833805, "avg_return": 0.48655253648757935, "regret": 0.3759942352771759, "entropy": 0.10841411352157593, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:14.104744Z", "loop": 2204, "env_steps": 1354751999, "loss": 0.002799917943775654, "avg_return": 0.4952518939971924, "regret": 0.3759942352771759, "entropy": 0.10654347389936447, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:14.957618Z", "loop": 2205, "env_steps": 1355366399, "loss": 0.0027019649278372526, "avg_return": 0.49000102281570435, "regret": 0.3759942352771759, "entropy": 0.11623283475637436, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:15.811727Z", "loop": 2206, "env_steps": 1355980799, "loss": 0.0026826963294297457, "avg_return": 0.482832133769989, "regret": 0.3759942352771759, "entropy": 0.11218550056219101, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:16.665409Z", "loop": 2207, "env_steps": 1356595199, "loss": 0.0028235260397195816, "avg_return": 0.4839457869529724, "regret": 0.3759942352771759, "entropy": 0.11322937160730362, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:17.519097Z", "loop": 2208, "env_steps": 1357209599, "loss": 0.0025920250918716192, "avg_return": 0.48545676469802856, "regret": 0.3759942352771759, "entropy": 0.11164005845785141, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:18.371217Z", "loop": 2209, "env_steps": 1357823999, "loss": 0.002729670377448201, "avg_return": 0.4822938144207001, "regret": 0.3759942352771759, "entropy": 0.11344579607248306, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:19.263279Z", "loop": 2210, "env_steps": 1358438399, "loss": 0.0029071110766381025, "avg_return": 0.4800947308540344, "regret": 0.3770121932029724, "entropy": 0.11085813492536545, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:20.117036Z", "loop": 2211, "env_steps": 1359052799, "loss": 0.0029743933118879795, "avg_return": 0.48228439688682556, "regret": 0.3770121932029724, "entropy": 0.1143428310751915, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:20.970648Z", "loop": 2212, "env_steps": 1359667199, "loss": 0.003025660291314125, "avg_return": 0.4907558262348175, "regret": 0.3770121932029724, "entropy": 0.11221472173929214, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:21.824438Z", "loop": 2213, "env_steps": 1360281599, "loss": 0.002967799548059702, "avg_return": 0.4847806990146637, "regret": 0.3770121932029724, "entropy": 0.10968434810638428, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:22.678478Z", "loop": 2214, "env_steps": 1360895999, "loss": 0.002920393366366625, "avg_return": 0.4862181842327118, "regret": 0.3770121932029724, "entropy": 0.1090383529663086, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:23.530622Z", "loop": 2215, "env_steps": 1361510399, "loss": 0.0025117865297943354, "avg_return": 0.4880920648574829, "regret": 0.3770121932029724, "entropy": 0.10936638712882996, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:24.384117Z", "loop": 2216, "env_steps": 1362124799, "loss": 0.002296799561008811, "avg_return": 0.48572662472724915, "regret": 0.3770121932029724, "entropy": 0.10409464687108994, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:25.237384Z", "loop": 2217, "env_steps": 1362739199, "loss": 0.0024061454460024834, "avg_return": 0.4853558838367462, "regret": 0.3770121932029724, "entropy": 0.10036259144544601, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:26.090756Z", "loop": 2218, "env_steps": 1363353599, "loss": 0.0023415666073560715, "avg_return": 0.4836403429508209, "regret": 0.3770121932029724, "entropy": 0.10255222767591476, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:26.943434Z", "loop": 2219, "env_steps": 1363967999, "loss": 0.002688947832211852, "avg_return": 0.49101758003234863, "regret": 0.3770121932029724, "entropy": 0.09666638821363449, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:27.834937Z", "loop": 2220, "env_steps": 1364582399, "loss": 0.002838506828993559, "avg_return": 0.48384904861450195, "regret": 0.3773123025894165, "entropy": 0.10899434983730316, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:28.689147Z", "loop": 2221, "env_steps": 1365196799, "loss": 0.002878734841942787, "avg_return": 0.4859292805194855, "regret": 0.3773123025894165, "entropy": 0.10517533868551254, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:29.542845Z", "loop": 2222, "env_steps": 1365811199, "loss": 0.002747342688962817, "avg_return": 0.4860450327396393, "regret": 0.3773123025894165, "entropy": 0.10744382441043854, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:30.395854Z", "loop": 2223, "env_steps": 1366425599, "loss": 0.002541671274229884, "avg_return": 0.48173660039901733, "regret": 0.3773123025894165, "entropy": 0.11070024967193604, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:31.247815Z", "loop": 2224, "env_steps": 1367039999, "loss": 0.0027016077656298876, "avg_return": 0.49092236161231995, "regret": 0.3773123025894165, "entropy": 0.10803720355033875, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:32.100716Z", "loop": 2225, "env_steps": 1367654399, "loss": 0.002395128831267357, "avg_return": 0.4985473155975342, "regret": 0.3773123025894165, "entropy": 0.11042088270187378, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:32.953638Z", "loop": 2226, "env_steps": 1368268799, "loss": 0.0020422262605279684, "avg_return": 0.4856724739074707, "regret": 0.3773123025894165, "entropy": 0.10959215462207794, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:33.808068Z", "loop": 2227, "env_steps": 1368883199, "loss": 0.0019027668749913573, "avg_return": 0.49602144956588745, "regret": 0.3773123025894165, "entropy": 0.0974767878651619, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:34.661642Z", "loop": 2228, "env_steps": 1369497599, "loss": 0.00193163868971169, "avg_return": 0.48777374625205994, "regret": 0.3773123025894165, "entropy": 0.09692312031984329, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:35.514681Z", "loop": 2229, "env_steps": 1370111999, "loss": 0.0018279607174918056, "avg_return": 0.4773542284965515, "regret": 0.3773123025894165, "entropy": 0.10310828685760498, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:36.409282Z", "loop": 2230, "env_steps": 1370726399, "loss": 0.0018923921743407845, "avg_return": 0.49110037088394165, "regret": 0.3755081295967102, "entropy": 0.10202781856060028, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:37.263438Z", "loop": 2231, "env_steps": 1371340799, "loss": 0.001644840114749968, "avg_return": 0.4898099899291992, "regret": 0.3755081295967102, "entropy": 0.09610388427972794, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:38.115639Z", "loop": 2232, "env_steps": 1371955199, "loss": 0.0018616389716044068, "avg_return": 0.4825291633605957, "regret": 0.3755081295967102, "entropy": 0.09022002667188644, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:38.968480Z", "loop": 2233, "env_steps": 1372569599, "loss": 0.0020335589069873095, "avg_return": 0.48346009850502014, "regret": 0.3755081295967102, "entropy": 0.0942111387848854, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:39.822255Z", "loop": 2234, "env_steps": 1373183999, "loss": 0.0021825693547725677, "avg_return": 0.4873572885990143, "regret": 0.3755081295967102, "entropy": 0.09561906009912491, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:40.675996Z", "loop": 2235, "env_steps": 1373798399, "loss": 0.0021605934016406536, "avg_return": 0.4866624176502228, "regret": 0.3755081295967102, "entropy": 0.0943240076303482, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:41.529201Z", "loop": 2236, "env_steps": 1374412799, "loss": 0.0019404012709856033, "avg_return": 0.48478373885154724, "regret": 0.3755081295967102, "entropy": 0.0952223464846611, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:42.382135Z", "loop": 2237, "env_steps": 1375027199, "loss": 0.001698254025541246, "avg_return": 0.4884960949420929, "regret": 0.3755081295967102, "entropy": 0.0918021947145462, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:43.236565Z", "loop": 2238, "env_steps": 1375641599, "loss": 0.001713407109491527, "avg_return": 0.4834039807319641, "regret": 0.3755081295967102, "entropy": 0.09190332144498825, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:44.090440Z", "loop": 2239, "env_steps": 1376255999, "loss": 0.0017720088362693787, "avg_return": 0.48313766717910767, "regret": 0.3755081295967102, "entropy": 0.09266427904367447, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:44.983051Z", "loop": 2240, "env_steps": 1376870399, "loss": 0.0016976604238152504, "avg_return": 0.4922722578048706, "regret": 0.3751991391181946, "entropy": 0.09806698560714722, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:45.835473Z", "loop": 2241, "env_steps": 1377484799, "loss": 0.0016665796283632517, "avg_return": 0.48859432339668274, "regret": 0.3751991391181946, "entropy": 0.09541143476963043, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:46.687861Z", "loop": 2242, "env_steps": 1378099199, "loss": 0.001965792616829276, "avg_return": 0.47825706005096436, "regret": 0.3751991391181946, "entropy": 0.09938964992761612, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:47.542886Z", "loop": 2243, "env_steps": 1378713599, "loss": 0.0019850742537528276, "avg_return": 0.49587932229042053, "regret": 0.3751991391181946, "entropy": 0.09779827296733856, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:48.396579Z", "loop": 2244, "env_steps": 1379327999, "loss": 0.0016874371794983745, "avg_return": 0.4824765622615814, "regret": 0.3751991391181946, "entropy": 0.09407469630241394, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:49.249456Z", "loop": 2245, "env_steps": 1379942399, "loss": 0.0017849818104878068, "avg_return": 0.48946234583854675, "regret": 0.3751991391181946, "entropy": 0.09421507269144058, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:50.102329Z", "loop": 2246, "env_steps": 1380556799, "loss": 0.0019329263595864177, "avg_return": 0.48827534914016724, "regret": 0.3751991391181946, "entropy": 0.09993130713701248, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:50.955795Z", "loop": 2247, "env_steps": 1381171199, "loss": 0.0019135473994538188, "avg_return": 0.4829941987991333, "regret": 0.3751991391181946, "entropy": 0.10167993605136871, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:51.809738Z", "loop": 2248, "env_steps": 1381785599, "loss": 0.001824217732064426, "avg_return": 0.4885638952255249, "regret": 0.3751991391181946, "entropy": 0.1041586697101593, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:52.662843Z", "loop": 2249, "env_steps": 1382399999, "loss": 0.001791587332263589, "avg_return": 0.4828200936317444, "regret": 0.3751991391181946, "entropy": 0.09815587848424911, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:53.553248Z", "loop": 2250, "env_steps": 1383014399, "loss": 0.001909836195409298, "avg_return": 0.4844372272491455, "regret": 0.37541133165359497, "entropy": 0.10831020772457123, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:54.408187Z", "loop": 2251, "env_steps": 1383628799, "loss": 0.0021328635048121214, "avg_return": 0.4925610423088074, "regret": 0.37541133165359497, "entropy": 0.1097167581319809, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:55.262779Z", "loop": 2252, "env_steps": 1384243199, "loss": 0.0020232379902154207, "avg_return": 0.4792904257774353, "regret": 0.37541133165359497, "entropy": 0.11019710451364517, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:56.118112Z", "loop": 2253, "env_steps": 1384857599, "loss": 0.002409484703093767, "avg_return": 0.4890574812889099, "regret": 0.37541133165359497, "entropy": 0.10644721984863281, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:56.972933Z", "loop": 2254, "env_steps": 1385471999, "loss": 0.002154463669285178, "avg_return": 0.4834936559200287, "regret": 0.37541133165359497, "entropy": 0.1069655641913414, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:57.828166Z", "loop": 2255, "env_steps": 1386086399, "loss": 0.0021978921722620726, "avg_return": 0.490405797958374, "regret": 0.37541133165359497, "entropy": 0.1075080931186676, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:58.683450Z", "loop": 2256, "env_steps": 1386700799, "loss": 0.0022912104614079, "avg_return": 0.4956032931804657, "regret": 0.37541133165359497, "entropy": 0.10504966974258423, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:55:59.536207Z", "loop": 2257, "env_steps": 1387315199, "loss": 0.0020294408313930035, "avg_return": 0.4871135652065277, "regret": 0.37541133165359497, "entropy": 0.10674583911895752, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:00.390243Z", "loop": 2258, "env_steps": 1387929599, "loss": 0.0020679000299423933, "avg_return": 0.4861437678337097, "regret": 0.37541133165359497, "entropy": 0.11181248724460602, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:01.243759Z", "loop": 2259, "env_steps": 1388543999, "loss": 0.0021709834691137075, "avg_return": 0.4867810308933258, "regret": 0.37541133165359497, "entropy": 0.10506951808929443, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:02.137852Z", "loop": 2260, "env_steps": 1389158399, "loss": 0.0018392617348581553, "avg_return": 0.4792141914367676, "regret": 0.37557870149612427, "entropy": 0.10589234530925751, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:02.992351Z", "loop": 2261, "env_steps": 1389772799, "loss": 0.002148944651708007, "avg_return": 0.4927367866039276, "regret": 0.37557870149612427, "entropy": 0.10941128432750702, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:03.847464Z", "loop": 2262, "env_steps": 1390387199, "loss": 0.0021104624029248953, "avg_return": 0.4937421679496765, "regret": 0.37557870149612427, "entropy": 0.11075828224420547, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:04.703081Z", "loop": 2263, "env_steps": 1391001599, "loss": 0.002072636503726244, "avg_return": 0.48679351806640625, "regret": 0.37557870149612427, "entropy": 0.11530021578073502, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:05.556226Z", "loop": 2264, "env_steps": 1391615999, "loss": 0.0016950247809290886, "avg_return": 0.4879363477230072, "regret": 0.37557870149612427, "entropy": 0.1075204610824585, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:06.408934Z", "loop": 2265, "env_steps": 1392230399, "loss": 0.002222576644271612, "avg_return": 0.49025431275367737, "regret": 0.37557870149612427, "entropy": 0.10491304099559784, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:07.262712Z", "loop": 2266, "env_steps": 1392844799, "loss": 0.001944112591445446, "avg_return": 0.48041000962257385, "regret": 0.37557870149612427, "entropy": 0.10895565897226334, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:08.116350Z", "loop": 2267, "env_steps": 1393459199, "loss": 0.001835409551858902, "avg_return": 0.49537843465805054, "regret": 0.37557870149612427, "entropy": 0.10979429632425308, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:08.968802Z", "loop": 2268, "env_steps": 1394073599, "loss": 0.0022815668489784002, "avg_return": 0.490898460149765, "regret": 0.37557870149612427, "entropy": 0.11257113516330719, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:09.821147Z", "loop": 2269, "env_steps": 1394687999, "loss": 0.0018851927015930414, "avg_return": 0.4885557293891907, "regret": 0.37557870149612427, "entropy": 0.1149614080786705, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:10.712804Z", "loop": 2270, "env_steps": 1395302399, "loss": 0.001971971709281206, "avg_return": 0.49089428782463074, "regret": 0.3757758140563965, "entropy": 0.11521504819393158, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:11.566835Z", "loop": 2271, "env_steps": 1395916799, "loss": 0.0018964570481330156, "avg_return": 0.47755423188209534, "regret": 0.3757758140563965, "entropy": 0.11801152676343918, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:12.420275Z", "loop": 2272, "env_steps": 1396531199, "loss": 0.0019553157035261393, "avg_return": 0.479322612285614, "regret": 0.3757758140563965, "entropy": 0.11877372115850449, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:13.273407Z", "loop": 2273, "env_steps": 1397145599, "loss": 0.002023403998464346, "avg_return": 0.4829624593257904, "regret": 0.3757758140563965, "entropy": 0.11856485903263092, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:14.126657Z", "loop": 2274, "env_steps": 1397759999, "loss": 0.002001840155571699, "avg_return": 0.48756134510040283, "regret": 0.3757758140563965, "entropy": 0.11516885459423065, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:14.981281Z", "loop": 2275, "env_steps": 1398374399, "loss": 0.0019437380833551288, "avg_return": 0.4929685592651367, "regret": 0.3757758140563965, "entropy": 0.10516002774238586, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:15.834831Z", "loop": 2276, "env_steps": 1398988799, "loss": 0.002048598136752844, "avg_return": 0.4886934459209442, "regret": 0.3757758140563965, "entropy": 0.11142975836992264, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:16.687831Z", "loop": 2277, "env_steps": 1399603199, "loss": 0.0021192010026425123, "avg_return": 0.4886472821235657, "regret": 0.3757758140563965, "entropy": 0.10664158314466476, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:17.541083Z", "loop": 2278, "env_steps": 1400217599, "loss": 0.0018819887191057205, "avg_return": 0.4807639718055725, "regret": 0.3757758140563965, "entropy": 0.10895565152168274, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:18.395169Z", "loop": 2279, "env_steps": 1400831999, "loss": 0.00205773813650012, "avg_return": 0.47986745834350586, "regret": 0.3757758140563965, "entropy": 0.11202715337276459, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:19.288585Z", "loop": 2280, "env_steps": 1401446399, "loss": 0.002110037487000227, "avg_return": 0.48338645696640015, "regret": 0.37591835856437683, "entropy": 0.1103844866156578, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:20.141597Z", "loop": 2281, "env_steps": 1402060799, "loss": 0.0022196739446371794, "avg_return": 0.4869280159473419, "regret": 0.37591835856437683, "entropy": 0.1074659675359726, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:20.994704Z", "loop": 2282, "env_steps": 1402675199, "loss": 0.0022369096986949444, "avg_return": 0.4945433735847473, "regret": 0.37591835856437683, "entropy": 0.11107300221920013, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:21.848445Z", "loop": 2283, "env_steps": 1403289599, "loss": 0.0021597249433398247, "avg_return": 0.48566803336143494, "regret": 0.37591835856437683, "entropy": 0.11017095297574997, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:22.701747Z", "loop": 2284, "env_steps": 1403903999, "loss": 0.0021420905832201242, "avg_return": 0.4890323579311371, "regret": 0.37591835856437683, "entropy": 0.10611531138420105, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:23.554809Z", "loop": 2285, "env_steps": 1404518399, "loss": 0.0022173889447003603, "avg_return": 0.4906390607357025, "regret": 0.37591835856437683, "entropy": 0.1065785363316536, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:24.407493Z", "loop": 2286, "env_steps": 1405132799, "loss": 0.002214693231508136, "avg_return": 0.4846266210079193, "regret": 0.37591835856437683, "entropy": 0.11100481450557709, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:25.261200Z", "loop": 2287, "env_steps": 1405747199, "loss": 0.0019624801352620125, "avg_return": 0.4883197247982025, "regret": 0.37591835856437683, "entropy": 0.1108287125825882, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:26.115454Z", "loop": 2288, "env_steps": 1406361599, "loss": 0.0021696286275982857, "avg_return": 0.4752785265445709, "regret": 0.37591835856437683, "entropy": 0.10969718545675278, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:26.970166Z", "loop": 2289, "env_steps": 1406975999, "loss": 0.0018532207468524575, "avg_return": 0.48650309443473816, "regret": 0.37591835856437683, "entropy": 0.10810666531324387, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:27.861747Z", "loop": 2290, "env_steps": 1407590399, "loss": 0.002254720777273178, "avg_return": 0.487723708152771, "regret": 0.37596628069877625, "entropy": 0.10375548154115677, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:28.716174Z", "loop": 2291, "env_steps": 1408204799, "loss": 0.002239346271380782, "avg_return": 0.49137452244758606, "regret": 0.37596628069877625, "entropy": 0.11516008526086807, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:29.569680Z", "loop": 2292, "env_steps": 1408819199, "loss": 0.0021156915463507175, "avg_return": 0.48815929889678955, "regret": 0.37596628069877625, "entropy": 0.11049558967351913, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:30.423539Z", "loop": 2293, "env_steps": 1409433599, "loss": 0.0021366022992879152, "avg_return": 0.4829128086566925, "regret": 0.37596628069877625, "entropy": 0.10800155252218246, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:31.277088Z", "loop": 2294, "env_steps": 1410047999, "loss": 0.002157346112653613, "avg_return": 0.48914480209350586, "regret": 0.37596628069877625, "entropy": 0.106538325548172, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:32.130347Z", "loop": 2295, "env_steps": 1410662399, "loss": 0.0026168699841946363, "avg_return": 0.4865093231201172, "regret": 0.37596628069877625, "entropy": 0.10682057589292526, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:32.983713Z", "loop": 2296, "env_steps": 1411276799, "loss": 0.002336014760658145, "avg_return": 0.4935072362422943, "regret": 0.37596628069877625, "entropy": 0.10872741043567657, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:33.836958Z", "loop": 2297, "env_steps": 1411891199, "loss": 0.0019223534036427736, "avg_return": 0.48154929280281067, "regret": 0.37596628069877625, "entropy": 0.10925870388746262, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:34.690387Z", "loop": 2298, "env_steps": 1412505599, "loss": 0.0020526039879769087, "avg_return": 0.48682159185409546, "regret": 0.37596628069877625, "entropy": 0.11105342209339142, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:35.543562Z", "loop": 2299, "env_steps": 1413119999, "loss": 0.0021196070592850447, "avg_return": 0.49055492877960205, "regret": 0.37596628069877625, "entropy": 0.10668063163757324, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:36.437741Z", "loop": 2300, "env_steps": 1413734399, "loss": 0.002091307658702135, "avg_return": 0.49070537090301514, "regret": 0.37592557072639465, "entropy": 0.10793834179639816, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:37.290216Z", "loop": 2301, "env_steps": 1414348799, "loss": 0.0018752031028270721, "avg_return": 0.4882071912288666, "regret": 0.37592557072639465, "entropy": 0.10892383754253387, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:38.144226Z", "loop": 2302, "env_steps": 1414963199, "loss": 0.002007835078984499, "avg_return": 0.48611584305763245, "regret": 0.37592557072639465, "entropy": 0.10516644269227982, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:38.998060Z", "loop": 2303, "env_steps": 1415577599, "loss": 0.0020921386312693357, "avg_return": 0.4844074547290802, "regret": 0.37592557072639465, "entropy": 0.11539070308208466, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:39.852423Z", "loop": 2304, "env_steps": 1416191999, "loss": 0.002442567842081189, "avg_return": 0.4800146222114563, "regret": 0.37592557072639465, "entropy": 0.12061254680156708, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:40.706306Z", "loop": 2305, "env_steps": 1416806399, "loss": 0.002446406986564398, "avg_return": 0.4827877879142761, "regret": 0.37592557072639465, "entropy": 0.12202811986207962, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:41.559899Z", "loop": 2306, "env_steps": 1417420799, "loss": 0.002179080853238702, "avg_return": 0.4802069664001465, "regret": 0.37592557072639465, "entropy": 0.11909091472625732, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:42.414593Z", "loop": 2307, "env_steps": 1418035199, "loss": 0.0024421222042292356, "avg_return": 0.49215540289878845, "regret": 0.37592557072639465, "entropy": 0.11373098939657211, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:43.268609Z", "loop": 2308, "env_steps": 1418649599, "loss": 0.002223548013716936, "avg_return": 0.4768475592136383, "regret": 0.37592557072639465, "entropy": 0.1191461980342865, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:44.122094Z", "loop": 2309, "env_steps": 1419263999, "loss": 0.0019164517289027572, "avg_return": 0.4861091673374176, "regret": 0.37592557072639465, "entropy": 0.11471479386091232, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:45.016221Z", "loop": 2310, "env_steps": 1419878399, "loss": 0.002118036849424243, "avg_return": 0.48522624373435974, "regret": 0.37667641043663025, "entropy": 0.11897487938404083, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:45.869869Z", "loop": 2311, "env_steps": 1420492799, "loss": 0.002083051484078169, "avg_return": 0.48855602741241455, "regret": 0.37667641043663025, "entropy": 0.11309780180454254, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:46.724321Z", "loop": 2312, "env_steps": 1421107199, "loss": 0.0018222343642264605, "avg_return": 0.49513378739356995, "regret": 0.37667641043663025, "entropy": 0.11109047383069992, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:47.578886Z", "loop": 2313, "env_steps": 1421721599, "loss": 0.001726816757582128, "avg_return": 0.48660382628440857, "regret": 0.37667641043663025, "entropy": 0.10279012471437454, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:48.432939Z", "loop": 2314, "env_steps": 1422335999, "loss": 0.0016185106942430139, "avg_return": 0.4942808747291565, "regret": 0.37667641043663025, "entropy": 0.09870589524507523, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:49.286949Z", "loop": 2315, "env_steps": 1422950399, "loss": 0.0016611366299912333, "avg_return": 0.4850352108478546, "regret": 0.37667641043663025, "entropy": 0.10014539211988449, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:50.141688Z", "loop": 2316, "env_steps": 1423564799, "loss": 0.0016897611785680056, "avg_return": 0.49553433060646057, "regret": 0.37667641043663025, "entropy": 0.10040566325187683, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:50.996744Z", "loop": 2317, "env_steps": 1424179199, "loss": 0.001665086834691465, "avg_return": 0.49394160509109497, "regret": 0.37667641043663025, "entropy": 0.10460758209228516, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:51.849571Z", "loop": 2318, "env_steps": 1424793599, "loss": 0.0015573621494695544, "avg_return": 0.48794251680374146, "regret": 0.37667641043663025, "entropy": 0.10206376016139984, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:52.702970Z", "loop": 2319, "env_steps": 1425407999, "loss": 0.0018092141253873706, "avg_return": 0.47944286465644836, "regret": 0.37667641043663025, "entropy": 0.10020880401134491, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:53.598237Z", "loop": 2320, "env_steps": 1426022399, "loss": 0.001664155744947493, "avg_return": 0.4889693260192871, "regret": 0.37569916248321533, "entropy": 0.09676522761583328, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:54.452114Z", "loop": 2321, "env_steps": 1426636799, "loss": 0.0016612218460068107, "avg_return": 0.49306783080101013, "regret": 0.37569916248321533, "entropy": 0.0997568815946579, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:55.305610Z", "loop": 2322, "env_steps": 1427251199, "loss": 0.0018482416635379195, "avg_return": 0.4850163757801056, "regret": 0.37569916248321533, "entropy": 0.09618992358446121, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:56.158682Z", "loop": 2323, "env_steps": 1427865599, "loss": 0.0018032323569059372, "avg_return": 0.4866332709789276, "regret": 0.37569916248321533, "entropy": 0.10564225912094116, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:57.013024Z", "loop": 2324, "env_steps": 1428479999, "loss": 0.001681622350588441, "avg_return": 0.4877994954586029, "regret": 0.37569916248321533, "entropy": 0.10164082050323486, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:57.866194Z", "loop": 2325, "env_steps": 1429094399, "loss": 0.001964100869372487, "avg_return": 0.48784029483795166, "regret": 0.37569916248321533, "entropy": 0.10858522355556488, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:58.719785Z", "loop": 2326, "env_steps": 1429708799, "loss": 0.0021426777821034193, "avg_return": 0.4881627559661865, "regret": 0.37569916248321533, "entropy": 0.1107943132519722, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:56:59.573490Z", "loop": 2327, "env_steps": 1430323199, "loss": 0.002731089713051915, "avg_return": 0.4872570037841797, "regret": 0.37569916248321533, "entropy": 0.1102989912033081, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:00.426799Z", "loop": 2328, "env_steps": 1430937599, "loss": 0.002776186680421233, "avg_return": 0.48405131697654724, "regret": 0.37569916248321533, "entropy": 0.11122052371501923, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:01.279825Z", "loop": 2329, "env_steps": 1431551999, "loss": 0.002651045098900795, "avg_return": 0.48961061239242554, "regret": 0.37569916248321533, "entropy": 0.10290186107158661, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:02.173470Z", "loop": 2330, "env_steps": 1432166399, "loss": 0.002284039044752717, "avg_return": 0.48669418692588806, "regret": 0.3787369132041931, "entropy": 0.09455540031194687, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:03.026756Z", "loop": 2331, "env_steps": 1432780799, "loss": 0.0016159549122676253, "avg_return": 0.4837263226509094, "regret": 0.3787369132041931, "entropy": 0.0777548998594284, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:03.881165Z", "loop": 2332, "env_steps": 1433395199, "loss": 0.0014371073339134455, "avg_return": 0.4807523787021637, "regret": 0.3787369132041931, "entropy": 0.06319039314985275, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:04.734812Z", "loop": 2333, "env_steps": 1434009599, "loss": 0.0012197605101391673, "avg_return": 0.4868294298648834, "regret": 0.3787369132041931, "entropy": 0.0627741888165474, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:05.588111Z", "loop": 2334, "env_steps": 1434623999, "loss": 0.001194930518977344, "avg_return": 0.4826551377773285, "regret": 0.3787369132041931, "entropy": 0.061168886721134186, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:06.441288Z", "loop": 2335, "env_steps": 1435238399, "loss": 0.0009720021043904126, "avg_return": 0.4707355797290802, "regret": 0.3787369132041931, "entropy": 0.05477089434862137, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:07.295940Z", "loop": 2336, "env_steps": 1435852799, "loss": 0.0008692179690115154, "avg_return": 0.4749685823917389, "regret": 0.3787369132041931, "entropy": 0.05547739565372467, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:08.149233Z", "loop": 2337, "env_steps": 1436467199, "loss": 0.0009114656713791192, "avg_return": 0.47391754388809204, "regret": 0.3787369132041931, "entropy": 0.05397200211882591, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:09.002637Z", "loop": 2338, "env_steps": 1437081599, "loss": 0.0011422717943787575, "avg_return": 0.4707067608833313, "regret": 0.3787369132041931, "entropy": 0.05332651361823082, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:09.855884Z", "loop": 2339, "env_steps": 1437695999, "loss": 0.0011699082097038627, "avg_return": 0.4822203814983368, "regret": 0.3787369132041931, "entropy": 0.0540902204811573, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:10.749880Z", "loop": 2340, "env_steps": 1438310399, "loss": 0.0011094002984464169, "avg_return": 0.48547857999801636, "regret": 0.3793071508407593, "entropy": 0.06036999076604843, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:11.603623Z", "loop": 2341, "env_steps": 1438924799, "loss": 0.0011811236618086696, "avg_return": 0.478411465883255, "regret": 0.3793071508407593, "entropy": 0.07157950848340988, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:12.456772Z", "loop": 2342, "env_steps": 1439539199, "loss": 0.0015031796647235751, "avg_return": 0.49585413932800293, "regret": 0.3793071508407593, "entropy": 0.06768648326396942, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:13.309883Z", "loop": 2343, "env_steps": 1440153599, "loss": 0.0015039932914078236, "avg_return": 0.4886207580566406, "regret": 0.3793071508407593, "entropy": 0.07109425961971283, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:14.164185Z", "loop": 2344, "env_steps": 1440767999, "loss": 0.0015589363174512982, "avg_return": 0.4856753647327423, "regret": 0.3793071508407593, "entropy": 0.07552812993526459, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:15.016867Z", "loop": 2345, "env_steps": 1441382399, "loss": 0.001915079541504383, "avg_return": 0.490136057138443, "regret": 0.3793071508407593, "entropy": 0.08209841698408127, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:15.869938Z", "loop": 2346, "env_steps": 1441996799, "loss": 0.0019110037246719003, "avg_return": 0.48556244373321533, "regret": 0.3793071508407593, "entropy": 0.08426574617624283, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:16.722994Z", "loop": 2347, "env_steps": 1442611199, "loss": 0.0019100302597507834, "avg_return": 0.49392345547676086, "regret": 0.3793071508407593, "entropy": 0.08509837090969086, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:17.576247Z", "loop": 2348, "env_steps": 1443225599, "loss": 0.002290167845785618, "avg_return": 0.4903533160686493, "regret": 0.3793071508407593, "entropy": 0.09250590950250626, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:18.429175Z", "loop": 2349, "env_steps": 1443839999, "loss": 0.002443083794787526, "avg_return": 0.4874304234981537, "regret": 0.3793071508407593, "entropy": 0.10464120656251907, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:19.320750Z", "loop": 2350, "env_steps": 1444454399, "loss": 0.0028267339803278446, "avg_return": 0.48299723863601685, "regret": 0.3760842978954315, "entropy": 0.11563318967819214, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:20.174936Z", "loop": 2351, "env_steps": 1445068799, "loss": 0.002920589642599225, "avg_return": 0.4948664605617523, "regret": 0.3760842978954315, "entropy": 0.11061878502368927, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:21.029415Z", "loop": 2352, "env_steps": 1445683199, "loss": 0.0032315750140696764, "avg_return": 0.4959714412689209, "regret": 0.3760842978954315, "entropy": 0.10837029665708542, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:21.883728Z", "loop": 2353, "env_steps": 1446297599, "loss": 0.002630397444590926, "avg_return": 0.4874591827392578, "regret": 0.3760842978954315, "entropy": 0.10535290092229843, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:22.735666Z", "loop": 2354, "env_steps": 1446911999, "loss": 0.0025972879957407713, "avg_return": 0.4944041073322296, "regret": 0.3760842978954315, "entropy": 0.09436218440532684, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:23.587156Z", "loop": 2355, "env_steps": 1447526399, "loss": 0.0018841868732124567, "avg_return": 0.4906386435031891, "regret": 0.3760842978954315, "entropy": 0.09714288264513016, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:24.440132Z", "loop": 2356, "env_steps": 1448140799, "loss": 0.002071735914796591, "avg_return": 0.4875076413154602, "regret": 0.3760842978954315, "entropy": 0.09519423544406891, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:25.293082Z", "loop": 2357, "env_steps": 1448755199, "loss": 0.002062309766188264, "avg_return": 0.4863756000995636, "regret": 0.3760842978954315, "entropy": 0.09376685321331024, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:26.146512Z", "loop": 2358, "env_steps": 1449369599, "loss": 0.0023521704133599997, "avg_return": 0.48885127902030945, "regret": 0.3760842978954315, "entropy": 0.09086006879806519, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:27.000008Z", "loop": 2359, "env_steps": 1449983999, "loss": 0.002317660255357623, "avg_return": 0.48669201135635376, "regret": 0.3760842978954315, "entropy": 0.08747300505638123, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:27.894445Z", "loop": 2360, "env_steps": 1450598399, "loss": 0.001650965423323214, "avg_return": 0.48576346039772034, "regret": 0.37561944127082825, "entropy": 0.08145599067211151, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:28.748670Z", "loop": 2361, "env_steps": 1451212799, "loss": 0.0015373185742646456, "avg_return": 0.4924428462982178, "regret": 0.37561944127082825, "entropy": 0.07214073091745377, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:29.602065Z", "loop": 2362, "env_steps": 1451827199, "loss": 0.0012799461837857962, "avg_return": 0.4884440302848816, "regret": 0.37561944127082825, "entropy": 0.07781106978654861, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:30.454777Z", "loop": 2363, "env_steps": 1452441599, "loss": 0.0017719271127134562, "avg_return": 0.48935776948928833, "regret": 0.37561944127082825, "entropy": 0.0859748125076294, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:31.306958Z", "loop": 2364, "env_steps": 1453055999, "loss": 0.002041740110144019, "avg_return": 0.49089163541793823, "regret": 0.37561944127082825, "entropy": 0.09016694128513336, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:32.159621Z", "loop": 2365, "env_steps": 1453670399, "loss": 0.0023461468517780304, "avg_return": 0.48483288288116455, "regret": 0.37561944127082825, "entropy": 0.09572309255599976, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:33.012842Z", "loop": 2366, "env_steps": 1454284799, "loss": 0.002602871274575591, "avg_return": 0.48649120330810547, "regret": 0.37561944127082825, "entropy": 0.10190439969301224, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:33.865906Z", "loop": 2367, "env_steps": 1454899199, "loss": 0.0036444987636059523, "avg_return": 0.48701509833335876, "regret": 0.37561944127082825, "entropy": 0.11344784498214722, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:34.718708Z", "loop": 2368, "env_steps": 1455513599, "loss": 0.0039305416867136955, "avg_return": 0.49087730050086975, "regret": 0.37561944127082825, "entropy": 0.11834615468978882, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:35.571540Z", "loop": 2369, "env_steps": 1456127999, "loss": 0.003986877854913473, "avg_return": 0.48469462990760803, "regret": 0.37561944127082825, "entropy": 0.12069550901651382, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:36.463732Z", "loop": 2370, "env_steps": 1456742399, "loss": 0.004102635663002729, "avg_return": 0.48996806144714355, "regret": 0.3754647672176361, "entropy": 0.12525466084480286, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:37.318117Z", "loop": 2371, "env_steps": 1457356799, "loss": 0.004293822683393955, "avg_return": 0.48386627435684204, "regret": 0.3754647672176361, "entropy": 0.12168678641319275, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:38.170768Z", "loop": 2372, "env_steps": 1457971199, "loss": 0.0038578163366764784, "avg_return": 0.47685059905052185, "regret": 0.3754647672176361, "entropy": 0.1212347224354744, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:39.023945Z", "loop": 2373, "env_steps": 1458585599, "loss": 0.004225918557494879, "avg_return": 0.48951807618141174, "regret": 0.3754647672176361, "entropy": 0.12247966229915619, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:39.877072Z", "loop": 2374, "env_steps": 1459199999, "loss": 0.00450908811762929, "avg_return": 0.4868775010108948, "regret": 0.3754647672176361, "entropy": 0.12296465784311295, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:40.731183Z", "loop": 2375, "env_steps": 1459814399, "loss": 0.004123212303966284, "avg_return": 0.4893173277378082, "regret": 0.3754647672176361, "entropy": 0.1181066483259201, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:41.584310Z", "loop": 2376, "env_steps": 1460428799, "loss": 0.0040713120251894, "avg_return": 0.48187655210494995, "regret": 0.3754647672176361, "entropy": 0.11900846660137177, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:42.438508Z", "loop": 2377, "env_steps": 1461043199, "loss": 0.004510289058089256, "avg_return": 0.4913054406642914, "regret": 0.3754647672176361, "entropy": 0.12218737602233887, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:43.291776Z", "loop": 2378, "env_steps": 1461657599, "loss": 0.004529214929789305, "avg_return": 0.4849694073200226, "regret": 0.3754647672176361, "entropy": 0.11303539574146271, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:44.145229Z", "loop": 2379, "env_steps": 1462271999, "loss": 0.00431802636012435, "avg_return": 0.486125648021698, "regret": 0.3754647672176361, "entropy": 0.11831117421388626, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:45.039491Z", "loop": 2380, "env_steps": 1462886399, "loss": 0.004253283143043518, "avg_return": 0.48853546380996704, "regret": 0.3755623996257782, "entropy": 0.11890729516744614, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:45.892703Z", "loop": 2381, "env_steps": 1463500799, "loss": 0.00360536458902061, "avg_return": 0.48867738246917725, "regret": 0.3755623996257782, "entropy": 0.10879036784172058, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:46.745770Z", "loop": 2382, "env_steps": 1464115199, "loss": 0.0035068669822067022, "avg_return": 0.4916195869445801, "regret": 0.3755623996257782, "entropy": 0.09972541779279709, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:47.599965Z", "loop": 2383, "env_steps": 1464729599, "loss": 0.0027639807667583227, "avg_return": 0.47988882660865784, "regret": 0.3755623996257782, "entropy": 0.08622997999191284, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:48.453993Z", "loop": 2384, "env_steps": 1465343999, "loss": 0.0022114445455372334, "avg_return": 0.4926286041736603, "regret": 0.3755623996257782, "entropy": 0.07943404465913773, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:49.307955Z", "loop": 2385, "env_steps": 1465958399, "loss": 0.002029339550063014, "avg_return": 0.48967444896698, "regret": 0.3755623996257782, "entropy": 0.06929143518209457, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:50.160003Z", "loop": 2386, "env_steps": 1466572799, "loss": 0.0021016241516917944, "avg_return": 0.48761314153671265, "regret": 0.3755623996257782, "entropy": 0.07303261011838913, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:51.012681Z", "loop": 2387, "env_steps": 1467187199, "loss": 0.0023066771682351828, "avg_return": 0.4886219799518585, "regret": 0.3755623996257782, "entropy": 0.07008752971887589, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:51.866288Z", "loop": 2388, "env_steps": 1467801599, "loss": 0.002296831225976348, "avg_return": 0.491639107465744, "regret": 0.3755623996257782, "entropy": 0.06810112297534943, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:52.720211Z", "loop": 2389, "env_steps": 1468415999, "loss": 0.0029032209422439337, "avg_return": 0.48851585388183594, "regret": 0.3755623996257782, "entropy": 0.07587727904319763, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:53.612663Z", "loop": 2390, "env_steps": 1469030399, "loss": 0.0037486478686332703, "avg_return": 0.48831045627593994, "regret": 0.3802334666252136, "entropy": 0.08516177535057068, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:54.465658Z", "loop": 2391, "env_steps": 1469644799, "loss": 0.004260353744029999, "avg_return": 0.48270294070243835, "regret": 0.3802334666252136, "entropy": 0.09279022365808487, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:55.319323Z", "loop": 2392, "env_steps": 1470259199, "loss": 0.004059780854731798, "avg_return": 0.47914329171180725, "regret": 0.3802334666252136, "entropy": 0.08990687876939774, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:56.173850Z", "loop": 2393, "env_steps": 1470873599, "loss": 0.0033756240736693144, "avg_return": 0.4810161590576172, "regret": 0.3802334666252136, "entropy": 0.08066115528345108, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:57.026835Z", "loop": 2394, "env_steps": 1471487999, "loss": 0.0032157101668417454, "avg_return": 0.48178625106811523, "regret": 0.3802334666252136, "entropy": 0.0743219256401062, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:57.880264Z", "loop": 2395, "env_steps": 1472102399, "loss": 0.002645244589075446, "avg_return": 0.4902219772338867, "regret": 0.3802334666252136, "entropy": 0.07089600712060928, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:58.733313Z", "loop": 2396, "env_steps": 1472716799, "loss": 0.0023846991825848818, "avg_return": 0.48147696256637573, "regret": 0.3802334666252136, "entropy": 0.06579843908548355, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:57:59.587269Z", "loop": 2397, "env_steps": 1473331199, "loss": 0.0024527553468942642, "avg_return": 0.48601919412612915, "regret": 0.3802334666252136, "entropy": 0.06455983221530914, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:00.440447Z", "loop": 2398, "env_steps": 1473945599, "loss": 0.0021965045016258955, "avg_return": 0.4891960918903351, "regret": 0.3802334666252136, "entropy": 0.06583001464605331, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:01.292518Z", "loop": 2399, "env_steps": 1474559999, "loss": 0.00208101118914783, "avg_return": 0.49253618717193604, "regret": 0.3802334666252136, "entropy": 0.06555651873350143, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:02.184123Z", "loop": 2400, "env_steps": 1475174399, "loss": 0.001867556944489479, "avg_return": 0.4910835325717926, "regret": 0.3759237825870514, "entropy": 0.06632561981678009, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:03.038238Z", "loop": 2401, "env_steps": 1475788799, "loss": 0.0021896788384765387, "avg_return": 0.4889205992221832, "regret": 0.3759237825870514, "entropy": 0.07073496282100677, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:03.892309Z", "loop": 2402, "env_steps": 1476403199, "loss": 0.001940447837114334, "avg_return": 0.48006582260131836, "regret": 0.3759237825870514, "entropy": 0.06863266229629517, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:04.745622Z", "loop": 2403, "env_steps": 1477017599, "loss": 0.0020931954495608807, "avg_return": 0.49874940514564514, "regret": 0.3759237825870514, "entropy": 0.07002038508653641, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:05.598886Z", "loop": 2404, "env_steps": 1477631999, "loss": 0.0016750562936067581, "avg_return": 0.48719656467437744, "regret": 0.3759237825870514, "entropy": 0.06907251477241516, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:06.453041Z", "loop": 2405, "env_steps": 1478246399, "loss": 0.0022395027335733175, "avg_return": 0.4848478436470032, "regret": 0.3759237825870514, "entropy": 0.0747818797826767, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:07.306937Z", "loop": 2406, "env_steps": 1478860799, "loss": 0.0020559828262776136, "avg_return": 0.4862523376941681, "regret": 0.3759237825870514, "entropy": 0.07739592343568802, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:08.160170Z", "loop": 2407, "env_steps": 1479475199, "loss": 0.00258258986286819, "avg_return": 0.4889540672302246, "regret": 0.3759237825870514, "entropy": 0.08148107677698135, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:09.012846Z", "loop": 2408, "env_steps": 1480089599, "loss": 0.0028543767984956503, "avg_return": 0.4935322105884552, "regret": 0.3759237825870514, "entropy": 0.08163662999868393, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:09.866436Z", "loop": 2409, "env_steps": 1480703999, "loss": 0.0030530423391610384, "avg_return": 0.4874589145183563, "regret": 0.3759237825870514, "entropy": 0.08899768441915512, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:10.759606Z", "loop": 2410, "env_steps": 1481318399, "loss": 0.003012746572494507, "avg_return": 0.4915793836116791, "regret": 0.3754781186580658, "entropy": 0.08801773935556412, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:11.614511Z", "loop": 2411, "env_steps": 1481932799, "loss": 0.0029239230789244175, "avg_return": 0.49019116163253784, "regret": 0.3754781186580658, "entropy": 0.08866200596094131, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:12.467700Z", "loop": 2412, "env_steps": 1482547199, "loss": 0.0025763220619410276, "avg_return": 0.4883858263492584, "regret": 0.3754781186580658, "entropy": 0.09129933267831802, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:13.320807Z", "loop": 2413, "env_steps": 1483161599, "loss": 0.0028442400507628918, "avg_return": 0.4878804683685303, "regret": 0.3754781186580658, "entropy": 0.09039274603128433, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:14.173563Z", "loop": 2414, "env_steps": 1483775999, "loss": 0.00316587439738214, "avg_return": 0.49331411719322205, "regret": 0.3754781186580658, "entropy": 0.09353679418563843, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:15.027031Z", "loop": 2415, "env_steps": 1484390399, "loss": 0.002851050114259124, "avg_return": 0.4792005121707916, "regret": 0.3754781186580658, "entropy": 0.09293432533740997, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:15.880346Z", "loop": 2416, "env_steps": 1485004799, "loss": 0.0025554790627211332, "avg_return": 0.4862869381904602, "regret": 0.3754781186580658, "entropy": 0.08648684620857239, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:16.733253Z", "loop": 2417, "env_steps": 1485619199, "loss": 0.0025302309077233076, "avg_return": 0.4849828779697418, "regret": 0.3754781186580658, "entropy": 0.08892647176980972, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:17.590282Z", "loop": 2418, "env_steps": 1486233599, "loss": 0.002688660519197583, "avg_return": 0.4932538866996765, "regret": 0.3754781186580658, "entropy": 0.08582290261983871, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:18.443174Z", "loop": 2419, "env_steps": 1486847999, "loss": 0.0024791776668280363, "avg_return": 0.48534780740737915, "regret": 0.3754781186580658, "entropy": 0.08778662234544754, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:19.335269Z", "loop": 2420, "env_steps": 1487462399, "loss": 0.00210389937274158, "avg_return": 0.488802969455719, "regret": 0.37553098797798157, "entropy": 0.0789884403347969, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:20.188767Z", "loop": 2421, "env_steps": 1488076799, "loss": 0.0019587099086493254, "avg_return": 0.4921468198299408, "regret": 0.37553098797798157, "entropy": 0.06869770586490631, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:21.041095Z", "loop": 2422, "env_steps": 1488691199, "loss": 0.002063550055027008, "avg_return": 0.4914521276950836, "regret": 0.37553098797798157, "entropy": 0.06791462749242783, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:21.893646Z", "loop": 2423, "env_steps": 1489305599, "loss": 0.0019562633242458105, "avg_return": 0.4841315746307373, "regret": 0.37553098797798157, "entropy": 0.06507163494825363, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:22.746274Z", "loop": 2424, "env_steps": 1489919999, "loss": 0.002120614517480135, "avg_return": 0.485677033662796, "regret": 0.37553098797798157, "entropy": 0.0681794062256813, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:23.600600Z", "loop": 2425, "env_steps": 1490534399, "loss": 0.002019343664869666, "avg_return": 0.4920428693294525, "regret": 0.37553098797798157, "entropy": 0.06346423923969269, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:24.453641Z", "loop": 2426, "env_steps": 1491148799, "loss": 0.002014698227867484, "avg_return": 0.4867645502090454, "regret": 0.37553098797798157, "entropy": 0.06926721334457397, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:25.306661Z", "loop": 2427, "env_steps": 1491763199, "loss": 0.001979221124202013, "avg_return": 0.48607635498046875, "regret": 0.37553098797798157, "entropy": 0.06911785900592804, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:26.162284Z", "loop": 2428, "env_steps": 1492377599, "loss": 0.002007473027333617, "avg_return": 0.4895303547382355, "regret": 0.37553098797798157, "entropy": 0.07407983392477036, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:27.016817Z", "loop": 2429, "env_steps": 1492991999, "loss": 0.002197947120293975, "avg_return": 0.47949907183647156, "regret": 0.37553098797798157, "entropy": 0.07327695190906525, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:27.911500Z", "loop": 2430, "env_steps": 1493606399, "loss": 0.002603784203529358, "avg_return": 0.4898853600025177, "regret": 0.3753671944141388, "entropy": 0.0817202776670456, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:28.763720Z", "loop": 2431, "env_steps": 1494220799, "loss": 0.002445746446028352, "avg_return": 0.4956156015396118, "regret": 0.3753671944141388, "entropy": 0.08292846381664276, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:29.616753Z", "loop": 2432, "env_steps": 1494835199, "loss": 0.0025890551041811705, "avg_return": 0.4905604124069214, "regret": 0.3753671944141388, "entropy": 0.0867549479007721, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:30.471158Z", "loop": 2433, "env_steps": 1495449599, "loss": 0.0024146081414073706, "avg_return": 0.4907407760620117, "regret": 0.3753671944141388, "entropy": 0.08046294003725052, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:31.325367Z", "loop": 2434, "env_steps": 1496063999, "loss": 0.0023292398545891047, "avg_return": 0.4904469847679138, "regret": 0.3753671944141388, "entropy": 0.07866392284631729, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:32.179401Z", "loop": 2435, "env_steps": 1496678399, "loss": 0.002032351912930608, "avg_return": 0.4860736131668091, "regret": 0.3753671944141388, "entropy": 0.07788567990064621, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:33.032489Z", "loop": 2436, "env_steps": 1497292799, "loss": 0.0019707861356437206, "avg_return": 0.481577068567276, "regret": 0.3753671944141388, "entropy": 0.07057522237300873, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:33.885652Z", "loop": 2437, "env_steps": 1497907199, "loss": 0.00162319780793041, "avg_return": 0.48910418152809143, "regret": 0.3753671944141388, "entropy": 0.0707770362496376, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:34.740085Z", "loop": 2438, "env_steps": 1498521599, "loss": 0.0019861345645040274, "avg_return": 0.49110114574432373, "regret": 0.3753671944141388, "entropy": 0.06530889868736267, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:35.592415Z", "loop": 2439, "env_steps": 1499135999, "loss": 0.0022518073674291372, "avg_return": 0.48564961552619934, "regret": 0.3753671944141388, "entropy": 0.0699501633644104, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:36.482800Z", "loop": 2440, "env_steps": 1499750399, "loss": 0.002154968213289976, "avg_return": 0.4905838668346405, "regret": 0.3757161498069763, "entropy": 0.06555134803056717, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:37.335756Z", "loop": 2441, "env_steps": 1500364799, "loss": 0.002190002938732505, "avg_return": 0.4813341498374939, "regret": 0.3757161498069763, "entropy": 0.06966311484575272, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:38.190188Z", "loop": 2442, "env_steps": 1500979199, "loss": 0.0022554751485586166, "avg_return": 0.4881201684474945, "regret": 0.3757161498069763, "entropy": 0.07042839378118515, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:39.044009Z", "loop": 2443, "env_steps": 1501593599, "loss": 0.002402674639597535, "avg_return": 0.48513898253440857, "regret": 0.3757161498069763, "entropy": 0.07011037319898605, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:39.897348Z", "loop": 2444, "env_steps": 1502207999, "loss": 0.002198429312556982, "avg_return": 0.4901551902294159, "regret": 0.3757161498069763, "entropy": 0.06792087852954865, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:40.750803Z", "loop": 2445, "env_steps": 1502822399, "loss": 0.001832623383961618, "avg_return": 0.4943569004535675, "regret": 0.3757161498069763, "entropy": 0.06398145854473114, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:41.605758Z", "loop": 2446, "env_steps": 1503436799, "loss": 0.0017428705468773842, "avg_return": 0.4963228404521942, "regret": 0.3757161498069763, "entropy": 0.062442656606435776, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:42.460163Z", "loop": 2447, "env_steps": 1504051199, "loss": 0.0016330814687535167, "avg_return": 0.47858449816703796, "regret": 0.3757161498069763, "entropy": 0.06627997010946274, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:43.314791Z", "loop": 2448, "env_steps": 1504665599, "loss": 0.0017656257841736078, "avg_return": 0.4860076904296875, "regret": 0.3757161498069763, "entropy": 0.06611362099647522, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:44.168067Z", "loop": 2449, "env_steps": 1505279999, "loss": 0.001818557269871235, "avg_return": 0.48283815383911133, "regret": 0.3757161498069763, "entropy": 0.06650689244270325, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:45.062326Z", "loop": 2450, "env_steps": 1505894399, "loss": 0.0017750615952536464, "avg_return": 0.48509976267814636, "regret": 0.3753548264503479, "entropy": 0.07418354600667953, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:45.916310Z", "loop": 2451, "env_steps": 1506508799, "loss": 0.0022698238026350737, "avg_return": 0.4929397702217102, "regret": 0.3753548264503479, "entropy": 0.07762785255908966, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:46.769608Z", "loop": 2452, "env_steps": 1507123199, "loss": 0.0024854252114892006, "avg_return": 0.4885494112968445, "regret": 0.3753548264503479, "entropy": 0.08395145833492279, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:47.623738Z", "loop": 2453, "env_steps": 1507737599, "loss": 0.0027648552786558867, "avg_return": 0.4869929254055023, "regret": 0.3753548264503479, "entropy": 0.09078141301870346, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:48.478797Z", "loop": 2454, "env_steps": 1508351999, "loss": 0.0029191330540925264, "avg_return": 0.4897857904434204, "regret": 0.3753548264503479, "entropy": 0.09526405483484268, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:49.333585Z", "loop": 2455, "env_steps": 1508966399, "loss": 0.003158391686156392, "avg_return": 0.49007514119148254, "regret": 0.3753548264503479, "entropy": 0.10185684263706207, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:50.187901Z", "loop": 2456, "env_steps": 1509580799, "loss": 0.0029388507828116417, "avg_return": 0.4828914403915405, "regret": 0.3753548264503479, "entropy": 0.10165052860975266, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:51.042611Z", "loop": 2457, "env_steps": 1510195199, "loss": 0.0033933052327483892, "avg_return": 0.49101513624191284, "regret": 0.3753548264503479, "entropy": 0.1042444109916687, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:51.896409Z", "loop": 2458, "env_steps": 1510809599, "loss": 0.0032477714121341705, "avg_return": 0.4898708760738373, "regret": 0.3753548264503479, "entropy": 0.1037033349275589, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:52.750557Z", "loop": 2459, "env_steps": 1511423999, "loss": 0.0028899263124912977, "avg_return": 0.4888721704483032, "regret": 0.3753548264503479, "entropy": 0.10402753949165344, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:53.644296Z", "loop": 2460, "env_steps": 1512038399, "loss": 0.003035404020920396, "avg_return": 0.4912983179092407, "regret": 0.37518173456192017, "entropy": 0.09693265706300735, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:54.498511Z", "loop": 2461, "env_steps": 1512652799, "loss": 0.0027456977404654026, "avg_return": 0.48469218611717224, "regret": 0.37518173456192017, "entropy": 0.09573876857757568, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:55.353811Z", "loop": 2462, "env_steps": 1513267199, "loss": 0.0026896430645138025, "avg_return": 0.48707062005996704, "regret": 0.37518173456192017, "entropy": 0.09281640499830246, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:56.208213Z", "loop": 2463, "env_steps": 1513881599, "loss": 0.0025822892785072327, "avg_return": 0.4813731908798218, "regret": 0.37518173456192017, "entropy": 0.08904850482940674, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:57.061389Z", "loop": 2464, "env_steps": 1514495999, "loss": 0.002282748930156231, "avg_return": 0.487845778465271, "regret": 0.37518173456192017, "entropy": 0.08105858415365219, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:57.914929Z", "loop": 2465, "env_steps": 1515110399, "loss": 0.002127197105437517, "avg_return": 0.4848252534866333, "regret": 0.37518173456192017, "entropy": 0.07715955376625061, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:58.769863Z", "loop": 2466, "env_steps": 1515724799, "loss": 0.0016226016450673342, "avg_return": 0.48273712396621704, "regret": 0.37518173456192017, "entropy": 0.07156526297330856, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:58:59.625378Z", "loop": 2467, "env_steps": 1516339199, "loss": 0.0015398007817566395, "avg_return": 0.4799254834651947, "regret": 0.37518173456192017, "entropy": 0.06321033835411072, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:00.478172Z", "loop": 2468, "env_steps": 1516953599, "loss": 0.0015641663921996951, "avg_return": 0.48514842987060547, "regret": 0.37518173456192017, "entropy": 0.05693801864981651, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:01.331600Z", "loop": 2469, "env_steps": 1517567999, "loss": 0.001996587496250868, "avg_return": 0.4821333885192871, "regret": 0.37518173456192017, "entropy": 0.061462465673685074, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:02.224949Z", "loop": 2470, "env_steps": 1518182399, "loss": 0.0023580461274832487, "avg_return": 0.48187097907066345, "regret": 0.3767843544483185, "entropy": 0.06391709297895432, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:03.079078Z", "loop": 2471, "env_steps": 1518796799, "loss": 0.0027062592562288046, "avg_return": 0.49178650975227356, "regret": 0.3767843544483185, "entropy": 0.06646911799907684, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:03.931235Z", "loop": 2472, "env_steps": 1519411199, "loss": 0.0026733020786195993, "avg_return": 0.4817712604999542, "regret": 0.3767843544483185, "entropy": 0.06571751832962036, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:04.783303Z", "loop": 2473, "env_steps": 1520025599, "loss": 0.002778991824015975, "avg_return": 0.48775503039360046, "regret": 0.3767843544483185, "entropy": 0.06750509142875671, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:05.637362Z", "loop": 2474, "env_steps": 1520639999, "loss": 0.002575622173026204, "avg_return": 0.4784931540489197, "regret": 0.3767843544483185, "entropy": 0.06620445102453232, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:06.492032Z", "loop": 2475, "env_steps": 1521254399, "loss": 0.0027617579326033592, "avg_return": 0.4847193658351898, "regret": 0.3767843544483185, "entropy": 0.06950367987155914, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:07.344285Z", "loop": 2476, "env_steps": 1521868799, "loss": 0.0029873698949813843, "avg_return": 0.48585888743400574, "regret": 0.3767843544483185, "entropy": 0.07217321544885635, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:08.196447Z", "loop": 2477, "env_steps": 1522483199, "loss": 0.0036822704132646322, "avg_return": 0.4909852147102356, "regret": 0.3767843544483185, "entropy": 0.07909033447504044, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:09.050989Z", "loop": 2478, "env_steps": 1523097599, "loss": 0.00428215553984046, "avg_return": 0.4824669361114502, "regret": 0.3767843544483185, "entropy": 0.0864516943693161, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:09.904868Z", "loop": 2479, "env_steps": 1523711999, "loss": 0.0034584004897624254, "avg_return": 0.48724207282066345, "regret": 0.3767843544483185, "entropy": 0.08021263033151627, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:10.797763Z", "loop": 2480, "env_steps": 1524326399, "loss": 0.003015987342223525, "avg_return": 0.4846371114253998, "regret": 0.3762257993221283, "entropy": 0.07539002597332001, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:11.650257Z", "loop": 2481, "env_steps": 1524940799, "loss": 0.0032790531404316425, "avg_return": 0.48184826970100403, "regret": 0.3762257993221283, "entropy": 0.07730945199728012, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:12.503227Z", "loop": 2482, "env_steps": 1525555199, "loss": 0.0037516006268560886, "avg_return": 0.4868616759777069, "regret": 0.3762257993221283, "entropy": 0.07878553122282028, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:13.357022Z", "loop": 2483, "env_steps": 1526169599, "loss": 0.0033225484658032656, "avg_return": 0.49101054668426514, "regret": 0.3762257993221283, "entropy": 0.07922787219285965, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:14.210762Z", "loop": 2484, "env_steps": 1526783999, "loss": 0.0034205098636448383, "avg_return": 0.4833123981952667, "regret": 0.3762257993221283, "entropy": 0.078587606549263, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:15.063176Z", "loop": 2485, "env_steps": 1527398399, "loss": 0.00391811691224575, "avg_return": 0.4752390682697296, "regret": 0.3762257993221283, "entropy": 0.08362231403589249, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:15.915691Z", "loop": 2486, "env_steps": 1528012799, "loss": 0.003868140745908022, "avg_return": 0.4877394735813141, "regret": 0.3762257993221283, "entropy": 0.08183500915765762, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:16.769535Z", "loop": 2487, "env_steps": 1528627199, "loss": 0.003606304293498397, "avg_return": 0.488028883934021, "regret": 0.3762257993221283, "entropy": 0.07887361943721771, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:17.622828Z", "loop": 2488, "env_steps": 1529241599, "loss": 0.0034746446181088686, "avg_return": 0.48747518658638, "regret": 0.3762257993221283, "entropy": 0.08254951238632202, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:18.476232Z", "loop": 2489, "env_steps": 1529855999, "loss": 0.0038847592659294605, "avg_return": 0.48421305418014526, "regret": 0.3762257993221283, "entropy": 0.08129718154668808, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:19.366872Z", "loop": 2490, "env_steps": 1530470399, "loss": 0.0035432539880275726, "avg_return": 0.4817889630794525, "regret": 0.3802829384803772, "entropy": 0.08079712092876434, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:20.221145Z", "loop": 2491, "env_steps": 1531084799, "loss": 0.0037389774806797504, "avg_return": 0.4758065938949585, "regret": 0.3802829384803772, "entropy": 0.08207789063453674, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:21.075098Z", "loop": 2492, "env_steps": 1531699199, "loss": 0.0037968007382005453, "avg_return": 0.4803900122642517, "regret": 0.3802829384803772, "entropy": 0.08072464168071747, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:21.929416Z", "loop": 2493, "env_steps": 1532313599, "loss": 0.004189038183540106, "avg_return": 0.4822494685649872, "regret": 0.3802829384803772, "entropy": 0.08334294706583023, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:22.781778Z", "loop": 2494, "env_steps": 1532927999, "loss": 0.0038019195199012756, "avg_return": 0.4821147918701172, "regret": 0.3802829384803772, "entropy": 0.08200997114181519, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:23.634639Z", "loop": 2495, "env_steps": 1533542399, "loss": 0.003602266311645508, "avg_return": 0.4838029742240906, "regret": 0.3802829384803772, "entropy": 0.07842313498258591, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:24.487299Z", "loop": 2496, "env_steps": 1534156799, "loss": 0.0033853717613965273, "avg_return": 0.4848591089248657, "regret": 0.3802829384803772, "entropy": 0.0826292410492897, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:25.340865Z", "loop": 2497, "env_steps": 1534771199, "loss": 0.0034800120629370213, "avg_return": 0.4862562119960785, "regret": 0.3802829384803772, "entropy": 0.07753593474626541, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:26.194156Z", "loop": 2498, "env_steps": 1535385599, "loss": 0.0037886376958340406, "avg_return": 0.489168256521225, "regret": 0.3802829384803772, "entropy": 0.0803767517209053, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:27.047467Z", "loop": 2499, "env_steps": 1535999999, "loss": 0.003413175465539098, "avg_return": 0.48042675852775574, "regret": 0.3802829384803772, "entropy": 0.07524055987596512, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:27.938584Z", "loop": 2500, "env_steps": 1536614399, "loss": 0.0031597695779055357, "avg_return": 0.4856078326702118, "regret": 0.37700843811035156, "entropy": 0.06960166990756989, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:28.791977Z", "loop": 2501, "env_steps": 1537228799, "loss": 0.002857849933207035, "avg_return": 0.48676371574401855, "regret": 0.37700843811035156, "entropy": 0.06454791128635406, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:29.645453Z", "loop": 2502, "env_steps": 1537843199, "loss": 0.0029394233133643866, "avg_return": 0.48169592022895813, "regret": 0.37700843811035156, "entropy": 0.06530310958623886, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:30.498597Z", "loop": 2503, "env_steps": 1538457599, "loss": 0.0031067703384906054, "avg_return": 0.48047441244125366, "regret": 0.37700843811035156, "entropy": 0.06766163557767868, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:31.351389Z", "loop": 2504, "env_steps": 1539071999, "loss": 0.002807230455800891, "avg_return": 0.4861599802970886, "regret": 0.37700843811035156, "entropy": 0.0652359202504158, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:32.205248Z", "loop": 2505, "env_steps": 1539686399, "loss": 0.0025246453005820513, "avg_return": 0.49484071135520935, "regret": 0.37700843811035156, "entropy": 0.05988897755742073, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:33.059053Z", "loop": 2506, "env_steps": 1540300799, "loss": 0.0024388881865888834, "avg_return": 0.47836533188819885, "regret": 0.37700843811035156, "entropy": 0.05988330394029617, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:33.912574Z", "loop": 2507, "env_steps": 1540915199, "loss": 0.002957097953185439, "avg_return": 0.48706260323524475, "regret": 0.37700843811035156, "entropy": 0.06652704626321793, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:34.764709Z", "loop": 2508, "env_steps": 1541529599, "loss": 0.0035261143930256367, "avg_return": 0.4860028624534607, "regret": 0.37700843811035156, "entropy": 0.08020757883787155, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:35.617058Z", "loop": 2509, "env_steps": 1542143999, "loss": 0.003522477811202407, "avg_return": 0.4889305830001831, "regret": 0.37700843811035156, "entropy": 0.0826699361205101, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:36.508969Z", "loop": 2510, "env_steps": 1542758399, "loss": 0.002308994298800826, "avg_return": 0.48108312487602234, "regret": 0.3752761781215668, "entropy": 0.07437844574451447, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:37.362752Z", "loop": 2511, "env_steps": 1543372799, "loss": 0.0018382802372798324, "avg_return": 0.485321968793869, "regret": 0.3752761781215668, "entropy": 0.0679231584072113, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:38.215688Z", "loop": 2512, "env_steps": 1543987199, "loss": 0.0014590242644771934, "avg_return": 0.4841707944869995, "regret": 0.3752761781215668, "entropy": 0.06383095681667328, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:39.069226Z", "loop": 2513, "env_steps": 1544601599, "loss": 0.001752170966938138, "avg_return": 0.4868028461933136, "regret": 0.3752761781215668, "entropy": 0.07345163077116013, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:39.922997Z", "loop": 2514, "env_steps": 1545215999, "loss": 0.001983798108994961, "avg_return": 0.4874679744243622, "regret": 0.3752761781215668, "entropy": 0.08263173699378967, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:40.777315Z", "loop": 2515, "env_steps": 1545830399, "loss": 0.002483644289895892, "avg_return": 0.4849534332752228, "regret": 0.3752761781215668, "entropy": 0.09348352998495102, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:41.630418Z", "loop": 2516, "env_steps": 1546444799, "loss": 0.003000787226483226, "avg_return": 0.4831364154815674, "regret": 0.3752761781215668, "entropy": 0.11219638586044312, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:42.482604Z", "loop": 2517, "env_steps": 1547059199, "loss": 0.0038371800910681486, "avg_return": 0.49713635444641113, "regret": 0.3752761781215668, "entropy": 0.11194831877946854, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:43.335894Z", "loop": 2518, "env_steps": 1547673599, "loss": 0.0033039734698832035, "avg_return": 0.4806593060493469, "regret": 0.3752761781215668, "entropy": 0.10971478372812271, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:44.189963Z", "loop": 2519, "env_steps": 1548287999, "loss": 0.002798141445964575, "avg_return": 0.4855097532272339, "regret": 0.3752761781215668, "entropy": 0.09981706738471985, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:45.082802Z", "loop": 2520, "env_steps": 1548902399, "loss": 0.002443591132760048, "avg_return": 0.49439185857772827, "regret": 0.37522751092910767, "entropy": 0.0824081152677536, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:45.936607Z", "loop": 2521, "env_steps": 1549516799, "loss": 0.002307228045538068, "avg_return": 0.49324676394462585, "regret": 0.37522751092910767, "entropy": 0.0792604461312294, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:46.790441Z", "loop": 2522, "env_steps": 1550131199, "loss": 0.001815533614717424, "avg_return": 0.4940638244152069, "regret": 0.37522751092910767, "entropy": 0.0800393596291542, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:47.645356Z", "loop": 2523, "env_steps": 1550745599, "loss": 0.0015234791208058596, "avg_return": 0.4875156879425049, "regret": 0.37522751092910767, "entropy": 0.07502815872430801, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:48.499300Z", "loop": 2524, "env_steps": 1551359999, "loss": 0.001348035759292543, "avg_return": 0.49144694209098816, "regret": 0.37522751092910767, "entropy": 0.07236473262310028, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:49.351599Z", "loop": 2525, "env_steps": 1551974399, "loss": 0.0013897862518206239, "avg_return": 0.4861280024051666, "regret": 0.37522751092910767, "entropy": 0.06843668967485428, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:50.203098Z", "loop": 2526, "env_steps": 1552588799, "loss": 0.0015250657452270389, "avg_return": 0.4861193895339966, "regret": 0.37522751092910767, "entropy": 0.0703563466668129, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:51.055528Z", "loop": 2527, "env_steps": 1553203199, "loss": 0.0015246792463585734, "avg_return": 0.48229146003723145, "regret": 0.37522751092910767, "entropy": 0.07595249265432358, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:51.909055Z", "loop": 2528, "env_steps": 1553817599, "loss": 0.0012416350655257702, "avg_return": 0.4888041317462921, "regret": 0.37522751092910767, "entropy": 0.07131385803222656, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:52.764861Z", "loop": 2529, "env_steps": 1554431999, "loss": 0.0011447792639955878, "avg_return": 0.49558085203170776, "regret": 0.37522751092910767, "entropy": 0.07203958928585052, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:53.659987Z", "loop": 2530, "env_steps": 1555046399, "loss": 0.0016776787815615535, "avg_return": 0.48687317967414856, "regret": 0.3758385479450226, "entropy": 0.07150913029909134, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:54.513686Z", "loop": 2531, "env_steps": 1555660799, "loss": 0.001945137046277523, "avg_return": 0.47780925035476685, "regret": 0.3758385479450226, "entropy": 0.07395478338003159, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:55.368513Z", "loop": 2532, "env_steps": 1556275199, "loss": 0.0019598561339080334, "avg_return": 0.48706549406051636, "regret": 0.3758385479450226, "entropy": 0.07923705875873566, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:56.222853Z", "loop": 2533, "env_steps": 1556889599, "loss": 0.0018241556826978922, "avg_return": 0.49255701899528503, "regret": 0.3758385479450226, "entropy": 0.06688437610864639, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:57.077405Z", "loop": 2534, "env_steps": 1557503999, "loss": 0.0017426429549232125, "avg_return": 0.4937933385372162, "regret": 0.3758385479450226, "entropy": 0.06355341523885727, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:57.931774Z", "loop": 2535, "env_steps": 1558118399, "loss": 0.0017305685905739665, "avg_return": 0.47893714904785156, "regret": 0.3758385479450226, "entropy": 0.06600978225469589, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:58.786117Z", "loop": 2536, "env_steps": 1558732799, "loss": 0.0015508289216086268, "avg_return": 0.47967052459716797, "regret": 0.3758385479450226, "entropy": 0.061967670917510986, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T17:59:59.639766Z", "loop": 2537, "env_steps": 1559347199, "loss": 0.001735371770337224, "avg_return": 0.48562130331993103, "regret": 0.3758385479450226, "entropy": 0.06565061211585999, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:00.494031Z", "loop": 2538, "env_steps": 1559961599, "loss": 0.0016637202352285385, "avg_return": 0.48319464921951294, "regret": 0.3758385479450226, "entropy": 0.06690723448991776, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:01.347466Z", "loop": 2539, "env_steps": 1560575999, "loss": 0.0017754985019564629, "avg_return": 0.4868311583995819, "regret": 0.3758385479450226, "entropy": 0.07203587144613266, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:02.243409Z", "loop": 2540, "env_steps": 1561190399, "loss": 0.0016731031937524676, "avg_return": 0.48359835147857666, "regret": 0.3770817518234253, "entropy": 0.06746432185173035, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:03.097689Z", "loop": 2541, "env_steps": 1561804799, "loss": 0.0018324647098779678, "avg_return": 0.48360463976860046, "regret": 0.3770817518234253, "entropy": 0.06783358752727509, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:03.953491Z", "loop": 2542, "env_steps": 1562419199, "loss": 0.001923962845467031, "avg_return": 0.48641109466552734, "regret": 0.3770817518234253, "entropy": 0.07016786187887192, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:04.809810Z", "loop": 2543, "env_steps": 1563033599, "loss": 0.0020154037047177553, "avg_return": 0.4870617687702179, "regret": 0.3770817518234253, "entropy": 0.07721935212612152, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:05.664361Z", "loop": 2544, "env_steps": 1563647999, "loss": 0.002027330920100212, "avg_return": 0.4879849851131439, "regret": 0.3770817518234253, "entropy": 0.07804681360721588, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:06.519082Z", "loop": 2545, "env_steps": 1564262399, "loss": 0.001874958979897201, "avg_return": 0.47946494817733765, "regret": 0.3770817518234253, "entropy": 0.0755092203617096, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:07.373850Z", "loop": 2546, "env_steps": 1564876799, "loss": 0.002173015847802162, "avg_return": 0.4881272614002228, "regret": 0.3770817518234253, "entropy": 0.07828595489263535, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:08.228350Z", "loop": 2547, "env_steps": 1565491199, "loss": 0.002143980236724019, "avg_return": 0.4954364597797394, "regret": 0.3770817518234253, "entropy": 0.07883427292108536, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:09.082670Z", "loop": 2548, "env_steps": 1566105599, "loss": 0.001708932570181787, "avg_return": 0.489515483379364, "regret": 0.3770817518234253, "entropy": 0.0723344013094902, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:09.937121Z", "loop": 2549, "env_steps": 1566719999, "loss": 0.001160301617346704, "avg_return": 0.477081298828125, "regret": 0.3770817518234253, "entropy": 0.05719279125332832, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:10.831462Z", "loop": 2550, "env_steps": 1567334399, "loss": 0.0011367005063220859, "avg_return": 0.4931408762931824, "regret": 0.37839871644973755, "entropy": 0.052236124873161316, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:11.685349Z", "loop": 2551, "env_steps": 1567948799, "loss": 0.0009348763269372284, "avg_return": 0.4908992648124695, "regret": 0.37839871644973755, "entropy": 0.04822475463151932, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:12.539356Z", "loop": 2552, "env_steps": 1568563199, "loss": 0.0011134528322145343, "avg_return": 0.4834305942058563, "regret": 0.37839871644973755, "entropy": 0.0454116053879261, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:13.393070Z", "loop": 2553, "env_steps": 1569177599, "loss": 0.0009411014034412801, "avg_return": 0.4729158580303192, "regret": 0.37839871644973755, "entropy": 0.04458794742822647, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:14.246504Z", "loop": 2554, "env_steps": 1569791999, "loss": 0.0007515608449466527, "avg_return": 0.47626450657844543, "regret": 0.37839871644973755, "entropy": 0.047750744968652725, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:15.100829Z", "loop": 2555, "env_steps": 1570406399, "loss": 0.0011239879531785846, "avg_return": 0.48413780331611633, "regret": 0.37839871644973755, "entropy": 0.04782146215438843, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:15.954591Z", "loop": 2556, "env_steps": 1571020799, "loss": 0.0008983556181192398, "avg_return": 0.4909197688102722, "regret": 0.37839871644973755, "entropy": 0.046842385083436966, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:16.807115Z", "loop": 2557, "env_steps": 1571635199, "loss": 0.0010033732978627086, "avg_return": 0.4794459044933319, "regret": 0.37839871644973755, "entropy": 0.0480157732963562, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:17.660652Z", "loop": 2558, "env_steps": 1572249599, "loss": 0.0009440277935937047, "avg_return": 0.4824758470058441, "regret": 0.37839871644973755, "entropy": 0.05604657903313637, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:18.514755Z", "loop": 2559, "env_steps": 1572863999, "loss": 0.001436389866285026, "avg_return": 0.49037685990333557, "regret": 0.37839871644973755, "entropy": 0.06591934710741043, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:19.408457Z", "loop": 2560, "env_steps": 1573478399, "loss": 0.00211005168966949, "avg_return": 0.4887634515762329, "regret": 0.3760198652744293, "entropy": 0.0786372721195221, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:20.261323Z", "loop": 2561, "env_steps": 1574092799, "loss": 0.002479699207469821, "avg_return": 0.48115262389183044, "regret": 0.3760198652744293, "entropy": 0.09092327207326889, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:21.114277Z", "loop": 2562, "env_steps": 1574707199, "loss": 0.003170473501086235, "avg_return": 0.49019119143486023, "regret": 0.3760198652744293, "entropy": 0.09917708486318588, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:21.968210Z", "loop": 2563, "env_steps": 1575321599, "loss": 0.002536154817789793, "avg_return": 0.48449352383613586, "regret": 0.3760198652744293, "entropy": 0.09993673861026764, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:22.824416Z", "loop": 2564, "env_steps": 1575935999, "loss": 0.0025854110717773438, "avg_return": 0.4992656707763672, "regret": 0.3760198652744293, "entropy": 0.09417614340782166, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:23.677729Z", "loop": 2565, "env_steps": 1576550399, "loss": 0.002274757018312812, "avg_return": 0.48491373658180237, "regret": 0.3760198652744293, "entropy": 0.09252885729074478, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:24.531380Z", "loop": 2566, "env_steps": 1577164799, "loss": 0.002609787043184042, "avg_return": 0.4861699640750885, "regret": 0.3760198652744293, "entropy": 0.08965560793876648, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:25.386859Z", "loop": 2567, "env_steps": 1577779199, "loss": 0.0024069820065051317, "avg_return": 0.4824058711528778, "regret": 0.3760198652744293, "entropy": 0.0905519351363182, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:26.240131Z", "loop": 2568, "env_steps": 1578393599, "loss": 0.0022655173670500517, "avg_return": 0.47961151599884033, "regret": 0.3760198652744293, "entropy": 0.09446699917316437, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:27.092970Z", "loop": 2569, "env_steps": 1579007999, "loss": 0.0023064520210027695, "avg_return": 0.4894079566001892, "regret": 0.3760198652744293, "entropy": 0.08710766583681107, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:27.987742Z", "loop": 2570, "env_steps": 1579622399, "loss": 0.002183392411097884, "avg_return": 0.4879530966281891, "regret": 0.3765028417110443, "entropy": 0.08589115738868713, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:28.841682Z", "loop": 2571, "env_steps": 1580236799, "loss": 0.0025069674011319876, "avg_return": 0.4891674816608429, "regret": 0.3765028417110443, "entropy": 0.09336450695991516, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:29.696765Z", "loop": 2572, "env_steps": 1580851199, "loss": 0.002512117847800255, "avg_return": 0.486682653427124, "regret": 0.3765028417110443, "entropy": 0.09320437908172607, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:30.550141Z", "loop": 2573, "env_steps": 1581465599, "loss": 0.0022618742659687996, "avg_return": 0.49213460087776184, "regret": 0.3765028417110443, "entropy": 0.0920255184173584, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:31.403405Z", "loop": 2574, "env_steps": 1582079999, "loss": 0.002568765077739954, "avg_return": 0.48608526587486267, "regret": 0.3765028417110443, "entropy": 0.09425695240497589, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:32.256051Z", "loop": 2575, "env_steps": 1582694399, "loss": 0.0023916575592011213, "avg_return": 0.4836650788784027, "regret": 0.3765028417110443, "entropy": 0.09358353912830353, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:33.108690Z", "loop": 2576, "env_steps": 1583308799, "loss": 0.0027167117223143578, "avg_return": 0.4908851087093353, "regret": 0.3765028417110443, "entropy": 0.099603570997715, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:33.962745Z", "loop": 2577, "env_steps": 1583923199, "loss": 0.0025669282767921686, "avg_return": 0.4809812605381012, "regret": 0.3765028417110443, "entropy": 0.09440615028142929, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:34.816401Z", "loop": 2578, "env_steps": 1584537599, "loss": 0.002709653228521347, "avg_return": 0.48713552951812744, "regret": 0.3765028417110443, "entropy": 0.09677661210298538, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:35.670634Z", "loop": 2579, "env_steps": 1585151999, "loss": 0.002822682959958911, "avg_return": 0.4954221248626709, "regret": 0.3765028417110443, "entropy": 0.09924596548080444, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:36.564120Z", "loop": 2580, "env_steps": 1585766399, "loss": 0.0025704558938741684, "avg_return": 0.4785008430480957, "regret": 0.3764563798904419, "entropy": 0.09553413838148117, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:37.418114Z", "loop": 2581, "env_steps": 1586380799, "loss": 0.002643166808411479, "avg_return": 0.4777607321739197, "regret": 0.3764563798904419, "entropy": 0.09224974364042282, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:38.272665Z", "loop": 2582, "env_steps": 1586995199, "loss": 0.0025740289129316807, "avg_return": 0.4799633324146271, "regret": 0.3764563798904419, "entropy": 0.09520415216684341, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:39.127389Z", "loop": 2583, "env_steps": 1587609599, "loss": 0.002319600898772478, "avg_return": 0.490475058555603, "regret": 0.3764563798904419, "entropy": 0.08887579292058945, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:39.981546Z", "loop": 2584, "env_steps": 1588223999, "loss": 0.0022225636057555676, "avg_return": 0.4889836609363556, "regret": 0.3764563798904419, "entropy": 0.0796741172671318, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:40.834980Z", "loop": 2585, "env_steps": 1588838399, "loss": 0.001731487805955112, "avg_return": 0.48500946164131165, "regret": 0.3764563798904419, "entropy": 0.07361309230327606, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:41.689011Z", "loop": 2586, "env_steps": 1589452799, "loss": 0.0013485669624060392, "avg_return": 0.4845685362815857, "regret": 0.3764563798904419, "entropy": 0.06710302829742432, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:42.543499Z", "loop": 2587, "env_steps": 1590067199, "loss": 0.0014499097596853971, "avg_return": 0.48498302698135376, "regret": 0.3764563798904419, "entropy": 0.06500940769910812, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:43.398613Z", "loop": 2588, "env_steps": 1590681599, "loss": 0.0013689713086932898, "avg_return": 0.48603734374046326, "regret": 0.3764563798904419, "entropy": 0.06564616411924362, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:44.251894Z", "loop": 2589, "env_steps": 1591295999, "loss": 0.0012590523110702634, "avg_return": 0.4921834468841553, "regret": 0.3764563798904419, "entropy": 0.06208892539143562, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:45.144391Z", "loop": 2590, "env_steps": 1591910399, "loss": 0.0011479620588943362, "avg_return": 0.4918312728404999, "regret": 0.37604764103889465, "entropy": 0.06197081878781319, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:45.997364Z", "loop": 2591, "env_steps": 1592524799, "loss": 0.0011138144182041287, "avg_return": 0.4896255135536194, "regret": 0.37604764103889465, "entropy": 0.0625607967376709, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:46.851813Z", "loop": 2592, "env_steps": 1593139199, "loss": 0.0010518789058551192, "avg_return": 0.48363444209098816, "regret": 0.37604764103889465, "entropy": 0.06266715377569199, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:47.704988Z", "loop": 2593, "env_steps": 1593753599, "loss": 0.0010770903900265694, "avg_return": 0.49031850695610046, "regret": 0.37604764103889465, "entropy": 0.05393049120903015, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:48.557430Z", "loop": 2594, "env_steps": 1594367999, "loss": 0.0009540161117911339, "avg_return": 0.4847696125507355, "regret": 0.37604764103889465, "entropy": 0.05561436340212822, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:49.410288Z", "loop": 2595, "env_steps": 1594982399, "loss": 0.001138585153967142, "avg_return": 0.4950212836265564, "regret": 0.37604764103889465, "entropy": 0.05485157296061516, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:50.264297Z", "loop": 2596, "env_steps": 1595596799, "loss": 0.0009313205373473465, "avg_return": 0.4905884861946106, "regret": 0.37604764103889465, "entropy": 0.055392853915691376, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:51.118225Z", "loop": 2597, "env_steps": 1596211199, "loss": 0.0008632920798845589, "avg_return": 0.48455810546875, "regret": 0.37604764103889465, "entropy": 0.05156983062624931, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:51.970932Z", "loop": 2598, "env_steps": 1596825599, "loss": 0.0010115772020071745, "avg_return": 0.48216766119003296, "regret": 0.37604764103889465, "entropy": 0.05229390785098076, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:52.823735Z", "loop": 2599, "env_steps": 1597439999, "loss": 0.0010411707917228341, "avg_return": 0.4891584515571594, "regret": 0.37604764103889465, "entropy": 0.05588548630475998, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:53.716417Z", "loop": 2600, "env_steps": 1598054399, "loss": 0.0008388307760469615, "avg_return": 0.48333796858787537, "regret": 0.3772338628768921, "entropy": 0.04977581277489662, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:54.570925Z", "loop": 2601, "env_steps": 1598668799, "loss": 0.0008902333793230355, "avg_return": 0.48612621426582336, "regret": 0.3772338628768921, "entropy": 0.04711328446865082, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:55.424891Z", "loop": 2602, "env_steps": 1599283199, "loss": 0.0009328589076176286, "avg_return": 0.4842842221260071, "regret": 0.3772338628768921, "entropy": 0.046039845794439316, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:56.278134Z", "loop": 2603, "env_steps": 1599897599, "loss": 0.0009163687936961651, "avg_return": 0.48693397641181946, "regret": 0.3772338628768921, "entropy": 0.04753899574279785, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:57.131700Z", "loop": 2604, "env_steps": 1600511999, "loss": 0.0008483837591484189, "avg_return": 0.48960059881210327, "regret": 0.3772338628768921, "entropy": 0.048771027475595474, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:57.985614Z", "loop": 2605, "env_steps": 1601126399, "loss": 0.0008920356049202383, "avg_return": 0.4773901104927063, "regret": 0.3772338628768921, "entropy": 0.0494719035923481, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:58.838927Z", "loop": 2606, "env_steps": 1601740799, "loss": 0.0007926944526843727, "avg_return": 0.4795204699039459, "regret": 0.3772338628768921, "entropy": 0.04665076360106468, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:00:59.691976Z", "loop": 2607, "env_steps": 1602355199, "loss": 0.0009670960134826601, "avg_return": 0.4906054735183716, "regret": 0.3772338628768921, "entropy": 0.049234069883823395, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:00.545640Z", "loop": 2608, "env_steps": 1602969599, "loss": 0.0009705728734843433, "avg_return": 0.4922652244567871, "regret": 0.3772338628768921, "entropy": 0.053948406130075455, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:01.400300Z", "loop": 2609, "env_steps": 1603583999, "loss": 0.0011586830951273441, "avg_return": 0.49819082021713257, "regret": 0.3772338628768921, "entropy": 0.04934835806488991, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:02.294771Z", "loop": 2610, "env_steps": 1604198399, "loss": 0.0010278084082528949, "avg_return": 0.4890686273574829, "regret": 0.3764960765838623, "entropy": 0.05692407116293907, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:03.148480Z", "loop": 2611, "env_steps": 1604812799, "loss": 0.0010008029639720917, "avg_return": 0.49260610342025757, "regret": 0.3764960765838623, "entropy": 0.05136683210730553, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:04.003098Z", "loop": 2612, "env_steps": 1605427199, "loss": 0.0010500906500965357, "avg_return": 0.493193119764328, "regret": 0.3764960765838623, "entropy": 0.05175457149744034, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:04.855796Z", "loop": 2613, "env_steps": 1606041599, "loss": 0.0009960356401279569, "avg_return": 0.4842488765716553, "regret": 0.3764960765838623, "entropy": 0.0517013743519783, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:05.709511Z", "loop": 2614, "env_steps": 1606655999, "loss": 0.0010605074930936098, "avg_return": 0.489729106426239, "regret": 0.3764960765838623, "entropy": 0.0552574023604393, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:06.562561Z", "loop": 2615, "env_steps": 1607270399, "loss": 0.0008725773659534752, "avg_return": 0.48677897453308105, "regret": 0.3764960765838623, "entropy": 0.05490553006529808, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:07.416231Z", "loop": 2616, "env_steps": 1607884799, "loss": 0.000900391663890332, "avg_return": 0.47976475954055786, "regret": 0.3764960765838623, "entropy": 0.0563705638051033, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:08.269661Z", "loop": 2617, "env_steps": 1608499199, "loss": 0.0010618007509037852, "avg_return": 0.48272705078125, "regret": 0.3764960765838623, "entropy": 0.06210005283355713, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:09.122807Z", "loop": 2618, "env_steps": 1609113599, "loss": 0.0012182830832898617, "avg_return": 0.4933561384677887, "regret": 0.3764960765838623, "entropy": 0.06591673940420151, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:09.975595Z", "loop": 2619, "env_steps": 1609727999, "loss": 0.0011535008670762181, "avg_return": 0.4806487560272217, "regret": 0.3764960765838623, "entropy": 0.07063650339841843, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:10.868006Z", "loop": 2620, "env_steps": 1610342399, "loss": 0.0016287071630358696, "avg_return": 0.48797109723091125, "regret": 0.37588074803352356, "entropy": 0.07551199942827225, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:11.721639Z", "loop": 2621, "env_steps": 1610956799, "loss": 0.001709918724372983, "avg_return": 0.4897717535495758, "regret": 0.37588074803352356, "entropy": 0.079689159989357, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:12.575276Z", "loop": 2622, "env_steps": 1611571199, "loss": 0.001937422901391983, "avg_return": 0.4823637008666992, "regret": 0.37588074803352356, "entropy": 0.08373335748910904, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:13.429715Z", "loop": 2623, "env_steps": 1612185599, "loss": 0.001797729404643178, "avg_return": 0.4840460419654846, "regret": 0.37588074803352356, "entropy": 0.08658672124147415, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:14.282966Z", "loop": 2624, "env_steps": 1612799999, "loss": 0.0020494593773037195, "avg_return": 0.48287975788116455, "regret": 0.37588074803352356, "entropy": 0.08008287847042084, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:15.137216Z", "loop": 2625, "env_steps": 1613414399, "loss": 0.001767544075846672, "avg_return": 0.4876311719417572, "regret": 0.37588074803352356, "entropy": 0.08222094178199768, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:15.990628Z", "loop": 2626, "env_steps": 1614028799, "loss": 0.001426787581294775, "avg_return": 0.4861859679222107, "regret": 0.37588074803352356, "entropy": 0.07963278889656067, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:16.844553Z", "loop": 2627, "env_steps": 1614643199, "loss": 0.0015463792951777577, "avg_return": 0.4917597472667694, "regret": 0.37588074803352356, "entropy": 0.06982125341892242, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:17.697798Z", "loop": 2628, "env_steps": 1615257599, "loss": 0.0012226852122694254, "avg_return": 0.47938787937164307, "regret": 0.37588074803352356, "entropy": 0.06705251336097717, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:18.550464Z", "loop": 2629, "env_steps": 1615871999, "loss": 0.0011928065214306116, "avg_return": 0.48741739988327026, "regret": 0.37588074803352356, "entropy": 0.061462581157684326, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:19.444418Z", "loop": 2630, "env_steps": 1616486399, "loss": 0.0013705509481951594, "avg_return": 0.48865577578544617, "regret": 0.3759355843067169, "entropy": 0.06308237463235855, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:20.298501Z", "loop": 2631, "env_steps": 1617100799, "loss": 0.0009435297106392682, "avg_return": 0.4945152997970581, "regret": 0.3759355843067169, "entropy": 0.05077548697590828, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:21.152775Z", "loop": 2632, "env_steps": 1617715199, "loss": 0.0008323228103108704, "avg_return": 0.4949595630168915, "regret": 0.3759355843067169, "entropy": 0.05111215263605118, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:22.005784Z", "loop": 2633, "env_steps": 1618329599, "loss": 0.0006788772298023105, "avg_return": 0.4919242560863495, "regret": 0.3759355843067169, "entropy": 0.041137974709272385, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:22.858770Z", "loop": 2634, "env_steps": 1618943999, "loss": 0.0004448566760402173, "avg_return": 0.48061275482177734, "regret": 0.3759355843067169, "entropy": 0.040526486933231354, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:23.711800Z", "loop": 2635, "env_steps": 1619558399, "loss": 0.0005656510475091636, "avg_return": 0.4849061667919159, "regret": 0.3759355843067169, "entropy": 0.04169666767120361, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:24.565911Z", "loop": 2636, "env_steps": 1620172799, "loss": 0.0006118196179158986, "avg_return": 0.4807869493961334, "regret": 0.3759355843067169, "entropy": 0.04034283384680748, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:25.419138Z", "loop": 2637, "env_steps": 1620787199, "loss": 0.0005966167082078755, "avg_return": 0.48327434062957764, "regret": 0.3759355843067169, "entropy": 0.039218705147504807, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:26.272635Z", "loop": 2638, "env_steps": 1621401599, "loss": 0.0005130538484081626, "avg_return": 0.4843803942203522, "regret": 0.3759355843067169, "entropy": 0.035377372056245804, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:27.124783Z", "loop": 2639, "env_steps": 1622015999, "loss": 0.0006362685235217214, "avg_return": 0.4825318455696106, "regret": 0.3759355843067169, "entropy": 0.03940796107053757, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:28.016777Z", "loop": 2640, "env_steps": 1622630399, "loss": 0.0004652857023756951, "avg_return": 0.4793737828731537, "regret": 0.37768468260765076, "entropy": 0.04395996034145355, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:28.870981Z", "loop": 2641, "env_steps": 1623244799, "loss": 0.0007252792711369693, "avg_return": 0.49347901344299316, "regret": 0.37768468260765076, "entropy": 0.043197546154260635, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:29.724814Z", "loop": 2642, "env_steps": 1623859199, "loss": 0.000606822082772851, "avg_return": 0.4817497432231903, "regret": 0.37768468260765076, "entropy": 0.04801933839917183, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:30.579122Z", "loop": 2643, "env_steps": 1624473599, "loss": 0.0009316623327322304, "avg_return": 0.4873410165309906, "regret": 0.37768468260765076, "entropy": 0.05751752108335495, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:31.432254Z", "loop": 2644, "env_steps": 1625087999, "loss": 0.0009640275384299457, "avg_return": 0.49119365215301514, "regret": 0.37768468260765076, "entropy": 0.06324326992034912, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:32.286500Z", "loop": 2645, "env_steps": 1625702399, "loss": 0.0013221375411376357, "avg_return": 0.4875164031982422, "regret": 0.37768468260765076, "entropy": 0.06633873283863068, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:33.141238Z", "loop": 2646, "env_steps": 1626316799, "loss": 0.0013762395828962326, "avg_return": 0.4887607991695404, "regret": 0.37768468260765076, "entropy": 0.072085440158844, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:33.995733Z", "loop": 2647, "env_steps": 1626931199, "loss": 0.00155509018804878, "avg_return": 0.49018657207489014, "regret": 0.37768468260765076, "entropy": 0.07841751724481583, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:34.848222Z", "loop": 2648, "env_steps": 1627545599, "loss": 0.0014221008168533444, "avg_return": 0.4807267487049103, "regret": 0.37768468260765076, "entropy": 0.07693894952535629, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:35.701626Z", "loop": 2649, "env_steps": 1628159999, "loss": 0.0015403947327286005, "avg_return": 0.48826172947883606, "regret": 0.37768468260765076, "entropy": 0.08398447930812836, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:36.595284Z", "loop": 2650, "env_steps": 1628774399, "loss": 0.001834484632126987, "avg_return": 0.49327215552330017, "regret": 0.37568673491477966, "entropy": 0.08525341749191284, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:37.449816Z", "loop": 2651, "env_steps": 1629388799, "loss": 0.0018716097110882401, "avg_return": 0.49163177609443665, "regret": 0.37568673491477966, "entropy": 0.08815864473581314, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:38.304209Z", "loop": 2652, "env_steps": 1630003199, "loss": 0.002057021716609597, "avg_return": 0.4886746406555176, "regret": 0.37568673491477966, "entropy": 0.08407261222600937, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:39.159541Z", "loop": 2653, "env_steps": 1630617599, "loss": 0.0021053485106676817, "avg_return": 0.4859668016433716, "regret": 0.37568673491477966, "entropy": 0.08576078712940216, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:40.015173Z", "loop": 2654, "env_steps": 1631231999, "loss": 0.002036206191405654, "avg_return": 0.4836346507072449, "regret": 0.37568673491477966, "entropy": 0.08709633350372314, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:40.869719Z", "loop": 2655, "env_steps": 1631846399, "loss": 0.0023675020784139633, "avg_return": 0.4881988763809204, "regret": 0.37568673491477966, "entropy": 0.09396537393331528, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:41.724163Z", "loop": 2656, "env_steps": 1632460799, "loss": 0.0025651485193520784, "avg_return": 0.4868520200252533, "regret": 0.37568673491477966, "entropy": 0.09511811286211014, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:42.578546Z", "loop": 2657, "env_steps": 1633075199, "loss": 0.002622728468850255, "avg_return": 0.4781668186187744, "regret": 0.37568673491477966, "entropy": 0.09330575168132782, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:43.431232Z", "loop": 2658, "env_steps": 1633689599, "loss": 0.002936613280326128, "avg_return": 0.49020203948020935, "regret": 0.37568673491477966, "entropy": 0.09445628523826599, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:44.284290Z", "loop": 2659, "env_steps": 1634303999, "loss": 0.0019141383236274123, "avg_return": 0.4827079474925995, "regret": 0.37568673491477966, "entropy": 0.08100684732198715, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:45.176973Z", "loop": 2660, "env_steps": 1634918399, "loss": 0.0018114174017682672, "avg_return": 0.4882275462150574, "regret": 0.3774794936180115, "entropy": 0.07087409496307373, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:46.031372Z", "loop": 2661, "env_steps": 1635532799, "loss": 0.002049405127763748, "avg_return": 0.4926246106624603, "regret": 0.3774794936180115, "entropy": 0.07321237027645111, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:46.884106Z", "loop": 2662, "env_steps": 1636147199, "loss": 0.002020985120907426, "avg_return": 0.4858143627643585, "regret": 0.3774794936180115, "entropy": 0.07350082695484161, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:47.737039Z", "loop": 2663, "env_steps": 1636761599, "loss": 0.00207515642978251, "avg_return": 0.48671215772628784, "regret": 0.3774794936180115, "entropy": 0.07163478434085846, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:48.590071Z", "loop": 2664, "env_steps": 1637375999, "loss": 0.0018760794773697853, "avg_return": 0.4814901351928711, "regret": 0.3774794936180115, "entropy": 0.08051542937755585, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:49.444377Z", "loop": 2665, "env_steps": 1637990399, "loss": 0.0016092521836981177, "avg_return": 0.4955490231513977, "regret": 0.3774794936180115, "entropy": 0.07113298028707504, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:50.297746Z", "loop": 2666, "env_steps": 1638604799, "loss": 0.0015944995684549212, "avg_return": 0.49572423100471497, "regret": 0.3774794936180115, "entropy": 0.07442231476306915, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:51.150305Z", "loop": 2667, "env_steps": 1639219199, "loss": 0.0017170058563351631, "avg_return": 0.4891773462295532, "regret": 0.3774794936180115, "entropy": 0.07179290801286697, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:52.004018Z", "loop": 2668, "env_steps": 1639833599, "loss": 0.001679203356616199, "avg_return": 0.4868839681148529, "regret": 0.3774794936180115, "entropy": 0.06719950586557388, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:52.859227Z", "loop": 2669, "env_steps": 1640447999, "loss": 0.001654617371968925, "avg_return": 0.4850670397281647, "regret": 0.3774794936180115, "entropy": 0.06949309259653091, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:53.752307Z", "loop": 2670, "env_steps": 1641062399, "loss": 0.0014696648577228189, "avg_return": 0.48392102122306824, "regret": 0.3752421438694, "entropy": 0.06835682690143585, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:54.605469Z", "loop": 2671, "env_steps": 1641676799, "loss": 0.001523951068520546, "avg_return": 0.49123963713645935, "regret": 0.3752421438694, "entropy": 0.07353638112545013, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:55.459023Z", "loop": 2672, "env_steps": 1642291199, "loss": 0.0014644913608208299, "avg_return": 0.4904206097126007, "regret": 0.3752421438694, "entropy": 0.06936363130807877, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:56.314643Z", "loop": 2673, "env_steps": 1642905599, "loss": 0.0015858877450227737, "avg_return": 0.4894939363002777, "regret": 0.3752421438694, "entropy": 0.06875520944595337, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:57.169018Z", "loop": 2674, "env_steps": 1643519999, "loss": 0.001455688732676208, "avg_return": 0.49564749002456665, "regret": 0.3752421438694, "entropy": 0.06717664003372192, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:58.021628Z", "loop": 2675, "env_steps": 1644134399, "loss": 0.0014473608462139964, "avg_return": 0.4868449568748474, "regret": 0.3752421438694, "entropy": 0.07295297086238861, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:58.873932Z", "loop": 2676, "env_steps": 1644748799, "loss": 0.001595309586264193, "avg_return": 0.4884641766548157, "regret": 0.3752421438694, "entropy": 0.07103964686393738, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:01:59.727925Z", "loop": 2677, "env_steps": 1645363199, "loss": 0.0015300282975658774, "avg_return": 0.4887743294239044, "regret": 0.3752421438694, "entropy": 0.06743313372135162, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:00.582364Z", "loop": 2678, "env_steps": 1645977599, "loss": 0.0015051470836624503, "avg_return": 0.48618438839912415, "regret": 0.3752421438694, "entropy": 0.07534108310937881, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:01.435626Z", "loop": 2679, "env_steps": 1646591999, "loss": 0.0014751659473404288, "avg_return": 0.49044790863990784, "regret": 0.3752421438694, "entropy": 0.06958846002817154, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:02.327338Z", "loop": 2680, "env_steps": 1647206399, "loss": 0.001744388835504651, "avg_return": 0.4928548336029053, "regret": 0.37504157423973083, "entropy": 0.0677890032529831, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:03.181565Z", "loop": 2681, "env_steps": 1647820799, "loss": 0.0017756711458787322, "avg_return": 0.48966407775878906, "regret": 0.37504157423973083, "entropy": 0.07213564217090607, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:04.035970Z", "loop": 2682, "env_steps": 1648435199, "loss": 0.001815920346416533, "avg_return": 0.49710267782211304, "regret": 0.37504157423973083, "entropy": 0.07679613679647446, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:04.889825Z", "loop": 2683, "env_steps": 1649049599, "loss": 0.0021641517523676157, "avg_return": 0.48642608523368835, "regret": 0.37504157423973083, "entropy": 0.07660519331693649, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:05.742724Z", "loop": 2684, "env_steps": 1649663999, "loss": 0.0021075629629194736, "avg_return": 0.4825243651866913, "regret": 0.37504157423973083, "entropy": 0.07867899537086487, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:06.596682Z", "loop": 2685, "env_steps": 1650278399, "loss": 0.0017915405333042145, "avg_return": 0.4878557324409485, "regret": 0.37504157423973083, "entropy": 0.08055289834737778, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:07.450445Z", "loop": 2686, "env_steps": 1650892799, "loss": 0.0020496330689638853, "avg_return": 0.4873630404472351, "regret": 0.37504157423973083, "entropy": 0.08498546481132507, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:08.304683Z", "loop": 2687, "env_steps": 1651507199, "loss": 0.0018089620862156153, "avg_return": 0.489246129989624, "regret": 0.37504157423973083, "entropy": 0.08373995125293732, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:09.158117Z", "loop": 2688, "env_steps": 1652121599, "loss": 0.001461642561480403, "avg_return": 0.4863247871398926, "regret": 0.37504157423973083, "entropy": 0.0859355553984642, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:10.010784Z", "loop": 2689, "env_steps": 1652735999, "loss": 0.001578397350385785, "avg_return": 0.49285924434661865, "regret": 0.37504157423973083, "entropy": 0.0750780701637268, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:10.902620Z", "loop": 2690, "env_steps": 1653350399, "loss": 0.0017807245021685958, "avg_return": 0.4929826557636261, "regret": 0.37503671646118164, "entropy": 0.0818418562412262, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:11.756692Z", "loop": 2691, "env_steps": 1653964799, "loss": 0.001605471596121788, "avg_return": 0.49154120683670044, "regret": 0.37503671646118164, "entropy": 0.09074588119983673, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:12.610304Z", "loop": 2692, "env_steps": 1654579199, "loss": 0.001461590058170259, "avg_return": 0.4875295162200928, "regret": 0.37503671646118164, "entropy": 0.07578318566083908, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:13.462939Z", "loop": 2693, "env_steps": 1655193599, "loss": 0.0018616029992699623, "avg_return": 0.4850536286830902, "regret": 0.37503671646118164, "entropy": 0.08400709182024002, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:14.316760Z", "loop": 2694, "env_steps": 1655807999, "loss": 0.0017047321889549494, "avg_return": 0.48616304993629456, "regret": 0.37503671646118164, "entropy": 0.08159293979406357, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:15.170378Z", "loop": 2695, "env_steps": 1656422399, "loss": 0.0016689536860212684, "avg_return": 0.490609347820282, "regret": 0.37503671646118164, "entropy": 0.08381476253271103, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:16.024775Z", "loop": 2696, "env_steps": 1657036799, "loss": 0.0015045114560052752, "avg_return": 0.48919567465782166, "regret": 0.37503671646118164, "entropy": 0.08361751586198807, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:16.878635Z", "loop": 2697, "env_steps": 1657651199, "loss": 0.0018418310210108757, "avg_return": 0.4952937960624695, "regret": 0.37503671646118164, "entropy": 0.07925038784742355, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:17.733052Z", "loop": 2698, "env_steps": 1658265599, "loss": 0.001815931755118072, "avg_return": 0.4972867965698242, "regret": 0.37503671646118164, "entropy": 0.08118626475334167, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:18.586018Z", "loop": 2699, "env_steps": 1658879999, "loss": 0.0018615294247865677, "avg_return": 0.48734214901924133, "regret": 0.37503671646118164, "entropy": 0.08622743934392929, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:19.478897Z", "loop": 2700, "env_steps": 1659494399, "loss": 0.002554589882493019, "avg_return": 0.4975931942462921, "regret": 0.3751847445964813, "entropy": 0.09140040725469589, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:20.331383Z", "loop": 2701, "env_steps": 1660108799, "loss": 0.002925112610682845, "avg_return": 0.48532676696777344, "regret": 0.3751847445964813, "entropy": 0.10023290663957596, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:21.185299Z", "loop": 2702, "env_steps": 1660723199, "loss": 0.0035761233884841204, "avg_return": 0.4907027781009674, "regret": 0.3751847445964813, "entropy": 0.10574320703744888, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:22.038399Z", "loop": 2703, "env_steps": 1661337599, "loss": 0.00388222630135715, "avg_return": 0.49164730310440063, "regret": 0.3751847445964813, "entropy": 0.11136464029550552, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:22.892116Z", "loop": 2704, "env_steps": 1661951999, "loss": 0.003883878467604518, "avg_return": 0.4833129048347473, "regret": 0.3751847445964813, "entropy": 0.11600582301616669, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:23.746515Z", "loop": 2705, "env_steps": 1662566399, "loss": 0.004481854848563671, "avg_return": 0.4837622046470642, "regret": 0.3751847445964813, "entropy": 0.12153518199920654, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:24.601529Z", "loop": 2706, "env_steps": 1663180799, "loss": 0.004750824999064207, "avg_return": 0.4912183880805969, "regret": 0.3751847445964813, "entropy": 0.12673453986644745, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:25.454492Z", "loop": 2707, "env_steps": 1663795199, "loss": 0.004458941984921694, "avg_return": 0.4890633821487427, "regret": 0.3751847445964813, "entropy": 0.11772528290748596, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:26.307327Z", "loop": 2708, "env_steps": 1664409599, "loss": 0.003862568410113454, "avg_return": 0.49155929684638977, "regret": 0.3751847445964813, "entropy": 0.10748898983001709, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:27.161719Z", "loop": 2709, "env_steps": 1665023999, "loss": 0.004037469159811735, "avg_return": 0.49111729860305786, "regret": 0.3751847445964813, "entropy": 0.10656315088272095, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:28.056135Z", "loop": 2710, "env_steps": 1665638399, "loss": 0.0035382534842938185, "avg_return": 0.4816517233848572, "regret": 0.3758806586265564, "entropy": 0.1034889742732048, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:28.909603Z", "loop": 2711, "env_steps": 1666252799, "loss": 0.0035631475038826466, "avg_return": 0.49030426144599915, "regret": 0.3758806586265564, "entropy": 0.1011914312839508, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:29.764866Z", "loop": 2712, "env_steps": 1666867199, "loss": 0.0039003323763608932, "avg_return": 0.4914267957210541, "regret": 0.3758806586265564, "entropy": 0.09808022528886795, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:30.619112Z", "loop": 2713, "env_steps": 1667481599, "loss": 0.003579916199669242, "avg_return": 0.47989341616630554, "regret": 0.3758806586265564, "entropy": 0.10096302628517151, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:31.473762Z", "loop": 2714, "env_steps": 1668095999, "loss": 0.0033238844480365515, "avg_return": 0.48471519351005554, "regret": 0.3758806586265564, "entropy": 0.08966309577226639, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:32.328656Z", "loop": 2715, "env_steps": 1668710399, "loss": 0.0032649561762809753, "avg_return": 0.48642295598983765, "regret": 0.3758806586265564, "entropy": 0.0856296494603157, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:33.182396Z", "loop": 2716, "env_steps": 1669324799, "loss": 0.0028417324647307396, "avg_return": 0.48077088594436646, "regret": 0.3758806586265564, "entropy": 0.07530944049358368, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:34.036205Z", "loop": 2717, "env_steps": 1669939199, "loss": 0.0026044005062431097, "avg_return": 0.482536643743515, "regret": 0.3758806586265564, "entropy": 0.07236298173666, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:34.891012Z", "loop": 2718, "env_steps": 1670553599, "loss": 0.0025569843128323555, "avg_return": 0.4937359690666199, "regret": 0.3758806586265564, "entropy": 0.06473052501678467, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:35.745044Z", "loop": 2719, "env_steps": 1671167999, "loss": 0.0021443048026412725, "avg_return": 0.4775114953517914, "regret": 0.3758806586265564, "entropy": 0.06301142275333405, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:36.639659Z", "loop": 2720, "env_steps": 1671782399, "loss": 0.0027287728153169155, "avg_return": 0.49060192704200745, "regret": 0.37902283668518066, "entropy": 0.06661222130060196, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:37.493724Z", "loop": 2721, "env_steps": 1672396799, "loss": 0.003020302625373006, "avg_return": 0.4772343933582306, "regret": 0.37902283668518066, "entropy": 0.07335425168275833, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:38.348838Z", "loop": 2722, "env_steps": 1673011199, "loss": 0.002848175587132573, "avg_return": 0.48670193552970886, "regret": 0.37902283668518066, "entropy": 0.06863398849964142, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:39.202793Z", "loop": 2723, "env_steps": 1673625599, "loss": 0.0024979044683277607, "avg_return": 0.4909810423851013, "regret": 0.37902283668518066, "entropy": 0.0660138726234436, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:40.056878Z", "loop": 2724, "env_steps": 1674239999, "loss": 0.0025771670043468475, "avg_return": 0.4759262204170227, "regret": 0.37902283668518066, "entropy": 0.06708630174398422, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:40.909536Z", "loop": 2725, "env_steps": 1674854399, "loss": 0.0022089711856096983, "avg_return": 0.4772917926311493, "regret": 0.37902283668518066, "entropy": 0.06255557388067245, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:41.762367Z", "loop": 2726, "env_steps": 1675468799, "loss": 0.001914865686558187, "avg_return": 0.4804077744483948, "regret": 0.37902283668518066, "entropy": 0.05907304584980011, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:42.616397Z", "loop": 2727, "env_steps": 1676083199, "loss": 0.0019521957729011774, "avg_return": 0.4913557469844818, "regret": 0.37902283668518066, "entropy": 0.05915014073252678, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:43.469705Z", "loop": 2728, "env_steps": 1676697599, "loss": 0.002008370589464903, "avg_return": 0.48157599568367004, "regret": 0.37902283668518066, "entropy": 0.05947878211736679, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:44.322734Z", "loop": 2729, "env_steps": 1677311999, "loss": 0.002279408974573016, "avg_return": 0.48294511437416077, "regret": 0.37902283668518066, "entropy": 0.06303031742572784, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:45.217868Z", "loop": 2730, "env_steps": 1677926399, "loss": 0.002314685145393014, "avg_return": 0.4887388348579407, "regret": 0.3770388662815094, "entropy": 0.062272049486637115, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:46.072365Z", "loop": 2731, "env_steps": 1678540799, "loss": 0.002310284413397312, "avg_return": 0.4865415692329407, "regret": 0.3770388662815094, "entropy": 0.06697794795036316, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:46.926185Z", "loop": 2732, "env_steps": 1679155199, "loss": 0.001967803342267871, "avg_return": 0.48506811261177063, "regret": 0.3770388662815094, "entropy": 0.06693381071090698, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:47.779636Z", "loop": 2733, "env_steps": 1679769599, "loss": 0.002518695779144764, "avg_return": 0.48642873764038086, "regret": 0.3770388662815094, "entropy": 0.0654006153345108, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:48.631959Z", "loop": 2734, "env_steps": 1680383999, "loss": 0.0020268354564905167, "avg_return": 0.4801332652568817, "regret": 0.3770388662815094, "entropy": 0.05868861451745033, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:49.484865Z", "loop": 2735, "env_steps": 1680998399, "loss": 0.0020038047805428505, "avg_return": 0.4989769756793976, "regret": 0.3770388662815094, "entropy": 0.05674051493406296, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:50.339099Z", "loop": 2736, "env_steps": 1681612799, "loss": 0.0018088164506480098, "avg_return": 0.4885613024234772, "regret": 0.3770388662815094, "entropy": 0.058616284281015396, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:51.193158Z", "loop": 2737, "env_steps": 1682227199, "loss": 0.001760885352268815, "avg_return": 0.4838368892669678, "regret": 0.3770388662815094, "entropy": 0.05810117721557617, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:52.046905Z", "loop": 2738, "env_steps": 1682841599, "loss": 0.001709807082079351, "avg_return": 0.48350292444229126, "regret": 0.3770388662815094, "entropy": 0.058711230754852295, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:52.901143Z", "loop": 2739, "env_steps": 1683455999, "loss": 0.0017710566753521562, "avg_return": 0.4859224557876587, "regret": 0.3770388662815094, "entropy": 0.05837300047278404, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:53.792343Z", "loop": 2740, "env_steps": 1684070399, "loss": 0.0015963561600074172, "avg_return": 0.481036901473999, "regret": 0.37568148970603943, "entropy": 0.05932226777076721, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:54.646813Z", "loop": 2741, "env_steps": 1684684799, "loss": 0.0016414368292316794, "avg_return": 0.48419222235679626, "regret": 0.37568148970603943, "entropy": 0.05920881778001785, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:55.500444Z", "loop": 2742, "env_steps": 1685299199, "loss": 0.0016931727295741439, "avg_return": 0.48299917578697205, "regret": 0.37568148970603943, "entropy": 0.05500062555074692, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:56.353815Z", "loop": 2743, "env_steps": 1685913599, "loss": 0.0016319284914061427, "avg_return": 0.493276983499527, "regret": 0.37568148970603943, "entropy": 0.05830760300159454, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:57.207442Z", "loop": 2744, "env_steps": 1686527999, "loss": 0.002080322476103902, "avg_return": 0.4947796165943146, "regret": 0.37568148970603943, "entropy": 0.06342895328998566, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:58.061768Z", "loop": 2745, "env_steps": 1687142399, "loss": 0.002198512200266123, "avg_return": 0.4876113533973694, "regret": 0.37568148970603943, "entropy": 0.067498579621315, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:58.916083Z", "loop": 2746, "env_steps": 1687756799, "loss": 0.0023651057854294777, "avg_return": 0.4917384386062622, "regret": 0.37568148970603943, "entropy": 0.07284829020500183, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:02:59.770720Z", "loop": 2747, "env_steps": 1688371199, "loss": 0.0025380016304552555, "avg_return": 0.4862063229084015, "regret": 0.37568148970603943, "entropy": 0.07173103094100952, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:00.624514Z", "loop": 2748, "env_steps": 1688985599, "loss": 0.0029880786314606667, "avg_return": 0.49013322591781616, "regret": 0.37568148970603943, "entropy": 0.08587872982025146, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:01.478108Z", "loop": 2749, "env_steps": 1689599999, "loss": 0.003381111193448305, "avg_return": 0.489876925945282, "regret": 0.37568148970603943, "entropy": 0.08822227269411087, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:02.368992Z", "loop": 2750, "env_steps": 1690214399, "loss": 0.0033108603674918413, "avg_return": 0.49853548407554626, "regret": 0.37529298663139343, "entropy": 0.08980873227119446, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:03.223511Z", "loop": 2751, "env_steps": 1690828799, "loss": 0.0028974669985473156, "avg_return": 0.48985201120376587, "regret": 0.37529298663139343, "entropy": 0.08880456537008286, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:04.076946Z", "loop": 2752, "env_steps": 1691443199, "loss": 0.002987135201692581, "avg_return": 0.4875231087207794, "regret": 0.37529298663139343, "entropy": 0.08703955262899399, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:04.928729Z", "loop": 2753, "env_steps": 1692057599, "loss": 0.003228765446692705, "avg_return": 0.49145591259002686, "regret": 0.37529298663139343, "entropy": 0.09135804325342178, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:05.782233Z", "loop": 2754, "env_steps": 1692671999, "loss": 0.003019017865881324, "avg_return": 0.49650678038597107, "regret": 0.37529298663139343, "entropy": 0.09271641075611115, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:06.635331Z", "loop": 2755, "env_steps": 1693286399, "loss": 0.003551489906385541, "avg_return": 0.4899181127548218, "regret": 0.37529298663139343, "entropy": 0.08969409763813019, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:07.488414Z", "loop": 2756, "env_steps": 1693900799, "loss": 0.0030970610678195953, "avg_return": 0.4948340058326721, "regret": 0.37529298663139343, "entropy": 0.08763161301612854, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:08.341134Z", "loop": 2757, "env_steps": 1694515199, "loss": 0.0026613909285515547, "avg_return": 0.48643648624420166, "regret": 0.37529298663139343, "entropy": 0.08697453141212463, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:09.195457Z", "loop": 2758, "env_steps": 1695129599, "loss": 0.002575451275333762, "avg_return": 0.4922315180301666, "regret": 0.37529298663139343, "entropy": 0.07521992176771164, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:10.049557Z", "loop": 2759, "env_steps": 1695743999, "loss": 0.0018216774333268404, "avg_return": 0.4891764521598816, "regret": 0.37529298663139343, "entropy": 0.06286980956792831, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:10.940525Z", "loop": 2760, "env_steps": 1696358399, "loss": 0.0015790114412084222, "avg_return": 0.4875725507736206, "regret": 0.37552914023399353, "entropy": 0.055647123605012894, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:11.793654Z", "loop": 2761, "env_steps": 1696972799, "loss": 0.0019251880003139377, "avg_return": 0.48178011178970337, "regret": 0.37552914023399353, "entropy": 0.059349287301301956, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:12.645610Z", "loop": 2762, "env_steps": 1697587199, "loss": 0.003233023453503847, "avg_return": 0.48490333557128906, "regret": 0.37552914023399353, "entropy": 0.07144598662853241, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:13.499919Z", "loop": 2763, "env_steps": 1698201599, "loss": 0.003924591466784477, "avg_return": 0.488803505897522, "regret": 0.37552914023399353, "entropy": 0.07896645367145538, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:14.353014Z", "loop": 2764, "env_steps": 1698815999, "loss": 0.003334578825160861, "avg_return": 0.48352158069610596, "regret": 0.37552914023399353, "entropy": 0.06857466697692871, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:15.206251Z", "loop": 2765, "env_steps": 1699430399, "loss": 0.002743771066889167, "avg_return": 0.4834347665309906, "regret": 0.37552914023399353, "entropy": 0.061354268342256546, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:16.059119Z", "loop": 2766, "env_steps": 1700044799, "loss": 0.0022823100443929434, "avg_return": 0.48604315519332886, "regret": 0.37552914023399353, "entropy": 0.05568379536271095, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:16.913155Z", "loop": 2767, "env_steps": 1700659199, "loss": 0.002314107259735465, "avg_return": 0.4827007055282593, "regret": 0.37552914023399353, "entropy": 0.05188218876719475, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:17.766369Z", "loop": 2768, "env_steps": 1701273599, "loss": 0.0023649337235838175, "avg_return": 0.4894142746925354, "regret": 0.37552914023399353, "entropy": 0.05506639927625656, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:18.620200Z", "loop": 2769, "env_steps": 1701887999, "loss": 0.002755951602011919, "avg_return": 0.48452016711235046, "regret": 0.37552914023399353, "entropy": 0.06181466579437256, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:19.510155Z", "loop": 2770, "env_steps": 1702502399, "loss": 0.0027537872083485126, "avg_return": 0.47868987917900085, "regret": 0.3771875500679016, "entropy": 0.06345351785421371, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:20.363776Z", "loop": 2771, "env_steps": 1703116799, "loss": 0.003599003655835986, "avg_return": 0.4876702129840851, "regret": 0.3771875500679016, "entropy": 0.07509610801935196, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:21.216802Z", "loop": 2772, "env_steps": 1703731199, "loss": 0.00369890034198761, "avg_return": 0.48905712366104126, "regret": 0.3771875500679016, "entropy": 0.07696188986301422, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:22.069802Z", "loop": 2773, "env_steps": 1704345599, "loss": 0.003366876160725951, "avg_return": 0.4876575767993927, "regret": 0.3771875500679016, "entropy": 0.07846079766750336, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:22.923755Z", "loop": 2774, "env_steps": 1704959999, "loss": 0.0027249183040112257, "avg_return": 0.4827076196670532, "regret": 0.3771875500679016, "entropy": 0.06957975029945374, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:23.777415Z", "loop": 2775, "env_steps": 1705574399, "loss": 0.002150977961719036, "avg_return": 0.4896567761898041, "regret": 0.3771875500679016, "entropy": 0.06395313888788223, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:24.630881Z", "loop": 2776, "env_steps": 1706188799, "loss": 0.001656357548199594, "avg_return": 0.491082102060318, "regret": 0.3771875500679016, "entropy": 0.059900760650634766, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:25.483145Z", "loop": 2777, "env_steps": 1706803199, "loss": 0.0019354202086105943, "avg_return": 0.48891204595565796, "regret": 0.3771875500679016, "entropy": 0.06477394700050354, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:26.336583Z", "loop": 2778, "env_steps": 1707417599, "loss": 0.0022887212689965963, "avg_return": 0.49030813574790955, "regret": 0.3771875500679016, "entropy": 0.07658272236585617, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:27.190021Z", "loop": 2779, "env_steps": 1708031999, "loss": 0.00236885785125196, "avg_return": 0.48244696855545044, "regret": 0.3771875500679016, "entropy": 0.08534163236618042, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:28.080235Z", "loop": 2780, "env_steps": 1708646399, "loss": 0.002376117277890444, "avg_return": 0.4873497188091278, "regret": 0.3752165138721466, "entropy": 0.09110534191131592, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:28.933444Z", "loop": 2781, "env_steps": 1709260799, "loss": 0.003534112125635147, "avg_return": 0.48014864325523376, "regret": 0.3752165138721466, "entropy": 0.09993792325258255, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:29.787536Z", "loop": 2782, "env_steps": 1709875199, "loss": 0.004421033896505833, "avg_return": 0.49667441844940186, "regret": 0.3752165138721466, "entropy": 0.11424898356199265, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:30.641276Z", "loop": 2783, "env_steps": 1710489599, "loss": 0.003968274220824242, "avg_return": 0.4849627912044525, "regret": 0.3752165138721466, "entropy": 0.1090884581208229, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:31.495064Z", "loop": 2784, "env_steps": 1711103999, "loss": 0.0030262235086411238, "avg_return": 0.48488616943359375, "regret": 0.3752165138721466, "entropy": 0.09816974401473999, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:32.349375Z", "loop": 2785, "env_steps": 1711718399, "loss": 0.0025502280332148075, "avg_return": 0.48691296577453613, "regret": 0.3752165138721466, "entropy": 0.09044018387794495, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:33.202024Z", "loop": 2786, "env_steps": 1712332799, "loss": 0.0019976214971393347, "avg_return": 0.4897839426994324, "regret": 0.3752165138721466, "entropy": 0.08532111346721649, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:34.055677Z", "loop": 2787, "env_steps": 1712947199, "loss": 0.0016299467533826828, "avg_return": 0.49157437682151794, "regret": 0.3752165138721466, "entropy": 0.0782759040594101, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:34.908464Z", "loop": 2788, "env_steps": 1713561599, "loss": 0.001541240606456995, "avg_return": 0.4942939281463623, "regret": 0.3752165138721466, "entropy": 0.0752171203494072, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:35.760821Z", "loop": 2789, "env_steps": 1714175999, "loss": 0.0010982271051034331, "avg_return": 0.4897722005844116, "regret": 0.3752165138721466, "entropy": 0.06928884983062744, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:36.652749Z", "loop": 2790, "env_steps": 1714790399, "loss": 0.0012215080205351114, "avg_return": 0.4829881489276886, "regret": 0.3753000497817993, "entropy": 0.061334457248449326, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:37.505734Z", "loop": 2791, "env_steps": 1715404799, "loss": 0.001092657446861267, "avg_return": 0.4835256040096283, "regret": 0.3753000497817993, "entropy": 0.06302956491708755, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:38.359158Z", "loop": 2792, "env_steps": 1716019199, "loss": 0.0014379055937752128, "avg_return": 0.4863099753856659, "regret": 0.3753000497817993, "entropy": 0.06006762012839317, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:39.212391Z", "loop": 2793, "env_steps": 1716633599, "loss": 0.0015317155048251152, "avg_return": 0.48677298426628113, "regret": 0.3753000497817993, "entropy": 0.06653927266597748, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:40.065271Z", "loop": 2794, "env_steps": 1717247999, "loss": 0.0012800226686522365, "avg_return": 0.483052134513855, "regret": 0.3753000497817993, "entropy": 0.06716032326221466, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:40.917942Z", "loop": 2795, "env_steps": 1717862399, "loss": 0.0015551036922261119, "avg_return": 0.48741358518600464, "regret": 0.3753000497817993, "entropy": 0.06896272301673889, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:41.772804Z", "loop": 2796, "env_steps": 1718476799, "loss": 0.0019026462687179446, "avg_return": 0.49592602252960205, "regret": 0.3753000497817993, "entropy": 0.06745227426290512, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:42.625903Z", "loop": 2797, "env_steps": 1719091199, "loss": 0.0018086209893226624, "avg_return": 0.4830460846424103, "regret": 0.3753000497817993, "entropy": 0.07382151484489441, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:43.478558Z", "loop": 2798, "env_steps": 1719705599, "loss": 0.0016694639343768358, "avg_return": 0.4997672736644745, "regret": 0.3753000497817993, "entropy": 0.0720331072807312, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:44.332326Z", "loop": 2799, "env_steps": 1720319999, "loss": 0.0016505552921444178, "avg_return": 0.4884243905544281, "regret": 0.3753000497817993, "entropy": 0.07359310239553452, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:45.225389Z", "loop": 2800, "env_steps": 1720934399, "loss": 0.0014459568774327636, "avg_return": 0.4902995824813843, "regret": 0.37715664505958557, "entropy": 0.06926481425762177, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:46.080060Z", "loop": 2801, "env_steps": 1721548799, "loss": 0.0014006083365529776, "avg_return": 0.4848054051399231, "regret": 0.37715664505958557, "entropy": 0.06973452866077423, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:46.933383Z", "loop": 2802, "env_steps": 1722163199, "loss": 0.0015610357513651252, "avg_return": 0.4863244891166687, "regret": 0.37715664505958557, "entropy": 0.07456578314304352, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:47.786905Z", "loop": 2803, "env_steps": 1722777599, "loss": 0.0013934612507000566, "avg_return": 0.4810923933982849, "regret": 0.37715664505958557, "entropy": 0.07608076184988022, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:48.641527Z", "loop": 2804, "env_steps": 1723391999, "loss": 0.0016683264402672648, "avg_return": 0.4844248592853546, "regret": 0.37715664505958557, "entropy": 0.07489381730556488, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:49.494932Z", "loop": 2805, "env_steps": 1724006399, "loss": 0.0022035050205886364, "avg_return": 0.4864198863506317, "regret": 0.37715664505958557, "entropy": 0.0882381945848465, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:50.347777Z", "loop": 2806, "env_steps": 1724620799, "loss": 0.002422597026452422, "avg_return": 0.48525410890579224, "regret": 0.37715664505958557, "entropy": 0.09556155651807785, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:51.201235Z", "loop": 2807, "env_steps": 1725235199, "loss": 0.0024787208531051874, "avg_return": 0.4884626865386963, "regret": 0.37715664505958557, "entropy": 0.10017222166061401, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:52.056199Z", "loop": 2808, "env_steps": 1725849599, "loss": 0.0022181901149451733, "avg_return": 0.4835969805717468, "regret": 0.37715664505958557, "entropy": 0.10051435232162476, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:52.909601Z", "loop": 2809, "env_steps": 1726463999, "loss": 0.00236847554333508, "avg_return": 0.4814649522304535, "regret": 0.37715664505958557, "entropy": 0.10270471125841141, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:53.800564Z", "loop": 2810, "env_steps": 1727078399, "loss": 0.002357844728976488, "avg_return": 0.4837040305137634, "regret": 0.38046935200691223, "entropy": 0.09304472804069519, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:54.654542Z", "loop": 2811, "env_steps": 1727692799, "loss": 0.002091652015224099, "avg_return": 0.4832371175289154, "regret": 0.38046935200691223, "entropy": 0.0921897441148758, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:55.508724Z", "loop": 2812, "env_steps": 1728307199, "loss": 0.00187137711327523, "avg_return": 0.4861874580383301, "regret": 0.38046935200691223, "entropy": 0.08593662828207016, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:56.361712Z", "loop": 2813, "env_steps": 1728921599, "loss": 0.0019155590562149882, "avg_return": 0.48774150013923645, "regret": 0.38046935200691223, "entropy": 0.09007001668214798, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:57.214233Z", "loop": 2814, "env_steps": 1729535999, "loss": 0.0019425398204475641, "avg_return": 0.4820520281791687, "regret": 0.38046935200691223, "entropy": 0.08782973885536194, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:58.066962Z", "loop": 2815, "env_steps": 1730150399, "loss": 0.0018815388903021812, "avg_return": 0.481231689453125, "regret": 0.38046935200691223, "entropy": 0.09180691093206406, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:58.920933Z", "loop": 2816, "env_steps": 1730764799, "loss": 0.0022118405904620886, "avg_return": 0.4885653257369995, "regret": 0.38046935200691223, "entropy": 0.09380023181438446, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:03:59.774483Z", "loop": 2817, "env_steps": 1731379199, "loss": 0.002166312886402011, "avg_return": 0.48137402534484863, "regret": 0.38046935200691223, "entropy": 0.10530460625886917, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:00.627145Z", "loop": 2818, "env_steps": 1731993599, "loss": 0.0023244526237249374, "avg_return": 0.4947488605976105, "regret": 0.38046935200691223, "entropy": 0.09701964259147644, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:01.479279Z", "loop": 2819, "env_steps": 1732607999, "loss": 0.002469570143148303, "avg_return": 0.48899272084236145, "regret": 0.38046935200691223, "entropy": 0.09954133629798889, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:02.370931Z", "loop": 2820, "env_steps": 1733222399, "loss": 0.002306167734786868, "avg_return": 0.49617159366607666, "regret": 0.3772473931312561, "entropy": 0.10074419528245926, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:03.224446Z", "loop": 2821, "env_steps": 1733836799, "loss": 0.0019548393320292234, "avg_return": 0.48715364933013916, "regret": 0.3772473931312561, "entropy": 0.09260212630033493, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:04.077491Z", "loop": 2822, "env_steps": 1734451199, "loss": 0.0016419788589701056, "avg_return": 0.4897044599056244, "regret": 0.3772473931312561, "entropy": 0.08907955884933472, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:04.930665Z", "loop": 2823, "env_steps": 1735065599, "loss": 0.001681459485553205, "avg_return": 0.4866108298301697, "regret": 0.3772473931312561, "entropy": 0.08059865981340408, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:05.784278Z", "loop": 2824, "env_steps": 1735679999, "loss": 0.0012369187315925956, "avg_return": 0.48307567834854126, "regret": 0.3772473931312561, "entropy": 0.07636632025241852, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:06.638030Z", "loop": 2825, "env_steps": 1736294399, "loss": 0.0010796035639941692, "avg_return": 0.48701682686805725, "regret": 0.3772473931312561, "entropy": 0.06415943801403046, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:07.491369Z", "loop": 2826, "env_steps": 1736908799, "loss": 0.0009789124596863985, "avg_return": 0.482257604598999, "regret": 0.3772473931312561, "entropy": 0.05676072835922241, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:08.344099Z", "loop": 2827, "env_steps": 1737523199, "loss": 0.0007569679291918874, "avg_return": 0.48515239357948303, "regret": 0.3772473931312561, "entropy": 0.05650508031249046, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:09.197191Z", "loop": 2828, "env_steps": 1738137599, "loss": 0.0008113089133985341, "avg_return": 0.48256632685661316, "regret": 0.3772473931312561, "entropy": 0.049996014684438705, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:10.050052Z", "loop": 2829, "env_steps": 1738751999, "loss": 0.0007413716521114111, "avg_return": 0.4851453900337219, "regret": 0.3772473931312561, "entropy": 0.05197054147720337, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:10.941174Z", "loop": 2830, "env_steps": 1739366399, "loss": 0.0007144467672333121, "avg_return": 0.4771258533000946, "regret": 0.37749582529067993, "entropy": 0.05119962617754936, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:11.795958Z", "loop": 2831, "env_steps": 1739980799, "loss": 0.0007391266990453005, "avg_return": 0.48376843333244324, "regret": 0.37749582529067993, "entropy": 0.045242879539728165, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:12.650558Z", "loop": 2832, "env_steps": 1740595199, "loss": 0.0010293055092915893, "avg_return": 0.486516535282135, "regret": 0.37749582529067993, "entropy": 0.05694611743092537, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:13.505037Z", "loop": 2833, "env_steps": 1741209599, "loss": 0.0008453751215711236, "avg_return": 0.48509421944618225, "regret": 0.37749582529067993, "entropy": 0.0563674233853817, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:14.359270Z", "loop": 2834, "env_steps": 1741823999, "loss": 0.001214312156662345, "avg_return": 0.49218785762786865, "regret": 0.37749582529067993, "entropy": 0.06153108552098274, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:15.212928Z", "loop": 2835, "env_steps": 1742438399, "loss": 0.0009855572134256363, "avg_return": 0.49069005250930786, "regret": 0.37749582529067993, "entropy": 0.06636785715818405, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:16.066235Z", "loop": 2836, "env_steps": 1743052799, "loss": 0.0012208819389343262, "avg_return": 0.48393821716308594, "regret": 0.37749582529067993, "entropy": 0.06815849244594574, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:16.919465Z", "loop": 2837, "env_steps": 1743667199, "loss": 0.0012400471605360508, "avg_return": 0.48641929030418396, "regret": 0.37749582529067993, "entropy": 0.07166653126478195, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:17.774212Z", "loop": 2838, "env_steps": 1744281599, "loss": 0.0016181471291929483, "avg_return": 0.48779815435409546, "regret": 0.37749582529067993, "entropy": 0.07652042806148529, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:18.628196Z", "loop": 2839, "env_steps": 1744895999, "loss": 0.0015405858866870403, "avg_return": 0.4868171811103821, "regret": 0.37749582529067993, "entropy": 0.08267698436975479, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:19.518856Z", "loop": 2840, "env_steps": 1745510399, "loss": 0.002071281662210822, "avg_return": 0.48776328563690186, "regret": 0.3757089078426361, "entropy": 0.08611657470464706, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:20.371339Z", "loop": 2841, "env_steps": 1746124799, "loss": 0.0020997037645429373, "avg_return": 0.4899599254131317, "regret": 0.3757089078426361, "entropy": 0.09107571095228195, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:21.224174Z", "loop": 2842, "env_steps": 1746739199, "loss": 0.002407098887488246, "avg_return": 0.4977816939353943, "regret": 0.3757089078426361, "entropy": 0.09032170474529266, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:22.079201Z", "loop": 2843, "env_steps": 1747353599, "loss": 0.0022958703339099884, "avg_return": 0.48212891817092896, "regret": 0.3757089078426361, "entropy": 0.09516225010156631, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:22.933127Z", "loop": 2844, "env_steps": 1747967999, "loss": 0.0029229624196887016, "avg_return": 0.4924059808254242, "regret": 0.3757089078426361, "entropy": 0.09358782321214676, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:23.785697Z", "loop": 2845, "env_steps": 1748582399, "loss": 0.0025201740209013224, "avg_return": 0.4846431016921997, "regret": 0.3757089078426361, "entropy": 0.09300179779529572, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:24.638763Z", "loop": 2846, "env_steps": 1749196799, "loss": 0.001923236413858831, "avg_return": 0.48750102519989014, "regret": 0.3757089078426361, "entropy": 0.08430501818656921, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:25.491589Z", "loop": 2847, "env_steps": 1749811199, "loss": 0.001918093883432448, "avg_return": 0.49397945404052734, "regret": 0.3757089078426361, "entropy": 0.08273395895957947, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:26.346081Z", "loop": 2848, "env_steps": 1750425599, "loss": 0.001856382004916668, "avg_return": 0.4831097424030304, "regret": 0.3757089078426361, "entropy": 0.08039737492799759, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:27.199738Z", "loop": 2849, "env_steps": 1751039999, "loss": 0.0022402051836252213, "avg_return": 0.48956403136253357, "regret": 0.3757089078426361, "entropy": 0.07913330942392349, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:28.090314Z", "loop": 2850, "env_steps": 1751654399, "loss": 0.0018917607376351953, "avg_return": 0.4907718002796173, "regret": 0.3750354051589966, "entropy": 0.07766719162464142, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:28.944360Z", "loop": 2851, "env_steps": 1752268799, "loss": 0.0018109929515048862, "avg_return": 0.4882635474205017, "regret": 0.3750354051589966, "entropy": 0.07304290682077408, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:29.799875Z", "loop": 2852, "env_steps": 1752883199, "loss": 0.001636141911149025, "avg_return": 0.4899451434612274, "regret": 0.3750354051589966, "entropy": 0.061038196086883545, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:30.654614Z", "loop": 2853, "env_steps": 1753497599, "loss": 0.0012783329002559185, "avg_return": 0.4939829707145691, "regret": 0.3750354051589966, "entropy": 0.05763915553689003, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:31.507373Z", "loop": 2854, "env_steps": 1754111999, "loss": 0.0011252117110416293, "avg_return": 0.494463711977005, "regret": 0.3750354051589966, "entropy": 0.0540817454457283, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:32.360834Z", "loop": 2855, "env_steps": 1754726399, "loss": 0.0012249340070411563, "avg_return": 0.4918935298919678, "regret": 0.3750354051589966, "entropy": 0.06007575988769531, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:33.215179Z", "loop": 2856, "env_steps": 1755340799, "loss": 0.0011211811797693372, "avg_return": 0.4860747754573822, "regret": 0.3750354051589966, "entropy": 0.056276835501194, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:34.068718Z", "loop": 2857, "env_steps": 1755955199, "loss": 0.0012033380335196853, "avg_return": 0.48464712500572205, "regret": 0.3750354051589966, "entropy": 0.06434483826160431, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:34.922552Z", "loop": 2858, "env_steps": 1756569599, "loss": 0.0012068640207871795, "avg_return": 0.4889313876628876, "regret": 0.3750354051589966, "entropy": 0.06663401424884796, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:35.774634Z", "loop": 2859, "env_steps": 1757183999, "loss": 0.0011954739456996322, "avg_return": 0.49031898379325867, "regret": 0.3750354051589966, "entropy": 0.06975122541189194, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:36.664999Z", "loop": 2860, "env_steps": 1757798399, "loss": 0.0011891331523656845, "avg_return": 0.49220511317253113, "regret": 0.37498679757118225, "entropy": 0.06770355254411697, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:37.519072Z", "loop": 2861, "env_steps": 1758412799, "loss": 0.0012576061999425292, "avg_return": 0.48794057965278625, "regret": 0.37498679757118225, "entropy": 0.0616263672709465, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:38.373536Z", "loop": 2862, "env_steps": 1759027199, "loss": 0.0011821116786450148, "avg_return": 0.487833172082901, "regret": 0.37498679757118225, "entropy": 0.06790654361248016, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:39.228327Z", "loop": 2863, "env_steps": 1759641599, "loss": 0.0012766104191541672, "avg_return": 0.4981500804424286, "regret": 0.37498679757118225, "entropy": 0.06360165029764175, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:40.082804Z", "loop": 2864, "env_steps": 1760255999, "loss": 0.001334397355094552, "avg_return": 0.49197128415107727, "regret": 0.37498679757118225, "entropy": 0.06739393621683121, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:40.937570Z", "loop": 2865, "env_steps": 1760870399, "loss": 0.0014014028711244464, "avg_return": 0.49003276228904724, "regret": 0.37498679757118225, "entropy": 0.0706162378191948, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:41.790902Z", "loop": 2866, "env_steps": 1761484799, "loss": 0.0012872318038716912, "avg_return": 0.485561728477478, "regret": 0.37498679757118225, "entropy": 0.07256940007209778, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:42.643676Z", "loop": 2867, "env_steps": 1762099199, "loss": 0.0011175646213814616, "avg_return": 0.4869879186153412, "regret": 0.37498679757118225, "entropy": 0.07721180468797684, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:43.496465Z", "loop": 2868, "env_steps": 1762713599, "loss": 0.0013160668313503265, "avg_return": 0.4891132116317749, "regret": 0.37498679757118225, "entropy": 0.07141704857349396, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:44.349232Z", "loop": 2869, "env_steps": 1763327999, "loss": 0.0014277672162279487, "avg_return": 0.48696449398994446, "regret": 0.37498679757118225, "entropy": 0.06730321794748306, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:45.243741Z", "loop": 2870, "env_steps": 1763942399, "loss": 0.0013314448297023773, "avg_return": 0.4947044551372528, "regret": 0.3749757409095764, "entropy": 0.07369710505008698, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:46.097430Z", "loop": 2871, "env_steps": 1764556799, "loss": 0.0012194908922538161, "avg_return": 0.49123790860176086, "regret": 0.3749757409095764, "entropy": 0.06558211892843246, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:46.951920Z", "loop": 2872, "env_steps": 1765171199, "loss": 0.0010336455889046192, "avg_return": 0.47753602266311646, "regret": 0.3749757409095764, "entropy": 0.06750612705945969, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:47.806326Z", "loop": 2873, "env_steps": 1765785599, "loss": 0.0012576953740790486, "avg_return": 0.48641958832740784, "regret": 0.3749757409095764, "entropy": 0.07725868374109268, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:48.661081Z", "loop": 2874, "env_steps": 1766399999, "loss": 0.0009098355076275766, "avg_return": 0.4796176254749298, "regret": 0.3749757409095764, "entropy": 0.07231901586055756, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:49.515125Z", "loop": 2875, "env_steps": 1767014399, "loss": 0.0013043172657489777, "avg_return": 0.49449536204338074, "regret": 0.3749757409095764, "entropy": 0.07427985966205597, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:50.368787Z", "loop": 2876, "env_steps": 1767628799, "loss": 0.0013742910232394934, "avg_return": 0.4904690682888031, "regret": 0.3749757409095764, "entropy": 0.07296964526176453, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:51.221928Z", "loop": 2877, "env_steps": 1768243199, "loss": 0.0012072789249941707, "avg_return": 0.48993977904319763, "regret": 0.3749757409095764, "entropy": 0.07434239983558655, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:52.075421Z", "loop": 2878, "env_steps": 1768857599, "loss": 0.0012147952802479267, "avg_return": 0.49582886695861816, "regret": 0.3749757409095764, "entropy": 0.07051147520542145, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:52.928551Z", "loop": 2879, "env_steps": 1769471999, "loss": 0.0013152111787348986, "avg_return": 0.4818248748779297, "regret": 0.3749757409095764, "entropy": 0.07754399627447128, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:53.819707Z", "loop": 2880, "env_steps": 1770086399, "loss": 0.001292307861149311, "avg_return": 0.490090548992157, "regret": 0.3749777376651764, "entropy": 0.07459646463394165, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:54.673775Z", "loop": 2881, "env_steps": 1770700799, "loss": 0.0014065190916880965, "avg_return": 0.48511576652526855, "regret": 0.3749777376651764, "entropy": 0.08402825146913528, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:55.527266Z", "loop": 2882, "env_steps": 1771315199, "loss": 0.0013338056160137057, "avg_return": 0.4940851926803589, "regret": 0.3749777376651764, "entropy": 0.0777379497885704, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:56.380829Z", "loop": 2883, "env_steps": 1771929599, "loss": 0.0012425859458744526, "avg_return": 0.4901403486728668, "regret": 0.3749777376651764, "entropy": 0.07278870791196823, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:57.233872Z", "loop": 2884, "env_steps": 1772543999, "loss": 0.0012572465930134058, "avg_return": 0.4923992455005646, "regret": 0.3749777376651764, "entropy": 0.08200127631425858, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:58.088267Z", "loop": 2885, "env_steps": 1773158399, "loss": 0.001375804073177278, "avg_return": 0.49085739254951477, "regret": 0.3749777376651764, "entropy": 0.07550851255655289, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:58.939939Z", "loop": 2886, "env_steps": 1773772799, "loss": 0.001332983491010964, "avg_return": 0.495181679725647, "regret": 0.3749777376651764, "entropy": 0.07354727387428284, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:04:59.792294Z", "loop": 2887, "env_steps": 1774387199, "loss": 0.001708006369881332, "avg_return": 0.48975372314453125, "regret": 0.3749777376651764, "entropy": 0.07776865363121033, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:00.645884Z", "loop": 2888, "env_steps": 1775001599, "loss": 0.0013227396411821246, "avg_return": 0.49124675989151, "regret": 0.3749777376651764, "entropy": 0.07757128775119781, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:01.499713Z", "loop": 2889, "env_steps": 1775615999, "loss": 0.001492779701948166, "avg_return": 0.49402132630348206, "regret": 0.3749777376651764, "entropy": 0.07538186013698578, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:02.391541Z", "loop": 2890, "env_steps": 1776230399, "loss": 0.0014344964874908328, "avg_return": 0.48629486560821533, "regret": 0.3749862015247345, "entropy": 0.07678955793380737, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:03.244329Z", "loop": 2891, "env_steps": 1776844799, "loss": 0.001144407200627029, "avg_return": 0.4833905100822449, "regret": 0.3749862015247345, "entropy": 0.07879002392292023, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:04.098817Z", "loop": 2892, "env_steps": 1777459199, "loss": 0.001481905928812921, "avg_return": 0.4918733239173889, "regret": 0.3749862015247345, "entropy": 0.07145374268293381, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:04.952657Z", "loop": 2893, "env_steps": 1778073599, "loss": 0.0011614825343713164, "avg_return": 0.48564842343330383, "regret": 0.3749862015247345, "entropy": 0.06993530690670013, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:05.806546Z", "loop": 2894, "env_steps": 1778687999, "loss": 0.001355355721898377, "avg_return": 0.48719412088394165, "regret": 0.3749862015247345, "entropy": 0.07030580937862396, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:06.659309Z", "loop": 2895, "env_steps": 1779302399, "loss": 0.0015137747395783663, "avg_return": 0.48343995213508606, "regret": 0.3749862015247345, "entropy": 0.07244665175676346, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:07.511914Z", "loop": 2896, "env_steps": 1779916799, "loss": 0.00199510483071208, "avg_return": 0.4917542636394501, "regret": 0.3749862015247345, "entropy": 0.07509059458971024, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:08.366807Z", "loop": 2897, "env_steps": 1780531199, "loss": 0.0022016342263668776, "avg_return": 0.48887020349502563, "regret": 0.3749862015247345, "entropy": 0.07927810400724411, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:09.220046Z", "loop": 2898, "env_steps": 1781145599, "loss": 0.002190698403865099, "avg_return": 0.488169401884079, "regret": 0.3749862015247345, "entropy": 0.0813949927687645, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:10.072800Z", "loop": 2899, "env_steps": 1781759999, "loss": 0.0022678340319544077, "avg_return": 0.4874231517314911, "regret": 0.3749862015247345, "entropy": 0.08248297870159149, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:10.963353Z", "loop": 2900, "env_steps": 1782374399, "loss": 0.0019344011088833213, "avg_return": 0.48586946725845337, "regret": 0.3750781714916229, "entropy": 0.07575078308582306, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:11.817269Z", "loop": 2901, "env_steps": 1782988799, "loss": 0.0020355090964585543, "avg_return": 0.49432286620140076, "regret": 0.3750781714916229, "entropy": 0.08016020059585571, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:12.671230Z", "loop": 2902, "env_steps": 1783603199, "loss": 0.0015598118770867586, "avg_return": 0.48671144247055054, "regret": 0.3750781714916229, "entropy": 0.08368141204118729, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:13.524277Z", "loop": 2903, "env_steps": 1784217599, "loss": 0.0020106849260628223, "avg_return": 0.49120423197746277, "regret": 0.3750781714916229, "entropy": 0.07509176433086395, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:14.376499Z", "loop": 2904, "env_steps": 1784831999, "loss": 0.0016227755695581436, "avg_return": 0.47662264108657837, "regret": 0.3750781714916229, "entropy": 0.08320071548223495, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:15.229524Z", "loop": 2905, "env_steps": 1785446399, "loss": 0.0016336760018020868, "avg_return": 0.4929594099521637, "regret": 0.3750781714916229, "entropy": 0.08330382406711578, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:16.083251Z", "loop": 2906, "env_steps": 1786060799, "loss": 0.0020431585144251585, "avg_return": 0.4895476996898651, "regret": 0.3750781714916229, "entropy": 0.08138809353113174, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:16.937286Z", "loop": 2907, "env_steps": 1786675199, "loss": 0.001932427636347711, "avg_return": 0.4872298836708069, "regret": 0.3750781714916229, "entropy": 0.08637012541294098, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:17.791011Z", "loop": 2908, "env_steps": 1787289599, "loss": 0.0018518184078857303, "avg_return": 0.4885832965373993, "regret": 0.3750781714916229, "entropy": 0.07941675931215286, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:18.645161Z", "loop": 2909, "env_steps": 1787903999, "loss": 0.0018974567065015435, "avg_return": 0.48753756284713745, "regret": 0.3750781714916229, "entropy": 0.08349516242742538, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:19.536979Z", "loop": 2910, "env_steps": 1788518399, "loss": 0.0018083675531670451, "avg_return": 0.48960840702056885, "regret": 0.3751947283744812, "entropy": 0.09128136187791824, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:20.389884Z", "loop": 2911, "env_steps": 1789132799, "loss": 0.0018933555111289024, "avg_return": 0.48022422194480896, "regret": 0.3751947283744812, "entropy": 0.08864308148622513, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:21.242874Z", "loop": 2912, "env_steps": 1789747199, "loss": 0.001951595419086516, "avg_return": 0.4824921190738678, "regret": 0.3751947283744812, "entropy": 0.09260206669569016, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:22.095957Z", "loop": 2913, "env_steps": 1790361599, "loss": 0.002358611673116684, "avg_return": 0.48930999636650085, "regret": 0.3751947283744812, "entropy": 0.09543198347091675, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:22.950200Z", "loop": 2914, "env_steps": 1790975999, "loss": 0.0024253916926681995, "avg_return": 0.48906779289245605, "regret": 0.3751947283744812, "entropy": 0.096927210688591, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:23.804166Z", "loop": 2915, "env_steps": 1791590399, "loss": 0.0023441037628799677, "avg_return": 0.48365458846092224, "regret": 0.3751947283744812, "entropy": 0.09853701293468475, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:24.658433Z", "loop": 2916, "env_steps": 1792204799, "loss": 0.002712917746976018, "avg_return": 0.49409008026123047, "regret": 0.3751947283744812, "entropy": 0.10092800110578537, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:25.511760Z", "loop": 2917, "env_steps": 1792819199, "loss": 0.0025204538833349943, "avg_return": 0.4906995892524719, "regret": 0.3751947283744812, "entropy": 0.09383674710988998, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:26.365277Z", "loop": 2918, "env_steps": 1793433599, "loss": 0.0024810682516545057, "avg_return": 0.48366889357566833, "regret": 0.3751947283744812, "entropy": 0.09978599101305008, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:27.219114Z", "loop": 2919, "env_steps": 1794047999, "loss": 0.00259664305485785, "avg_return": 0.48887351155281067, "regret": 0.3751947283744812, "entropy": 0.10598008334636688, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:28.110933Z", "loop": 2920, "env_steps": 1794662399, "loss": 0.002730745356529951, "avg_return": 0.48972225189208984, "regret": 0.3756042420864105, "entropy": 0.10963704437017441, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:28.964458Z", "loop": 2921, "env_steps": 1795276799, "loss": 0.002801604336127639, "avg_return": 0.48789775371551514, "regret": 0.3756042420864105, "entropy": 0.1132039874792099, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:29.817804Z", "loop": 2922, "env_steps": 1795891199, "loss": 0.002635581186041236, "avg_return": 0.4910295605659485, "regret": 0.3756042420864105, "entropy": 0.10870333015918732, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:30.670736Z", "loop": 2923, "env_steps": 1796505599, "loss": 0.00276032998226583, "avg_return": 0.48636922240257263, "regret": 0.3756042420864105, "entropy": 0.10113073140382767, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:31.523603Z", "loop": 2924, "env_steps": 1797119999, "loss": 0.002286202274262905, "avg_return": 0.48848095536231995, "regret": 0.3756042420864105, "entropy": 0.0989508405327797, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:32.377103Z", "loop": 2925, "env_steps": 1797734399, "loss": 0.00218711094930768, "avg_return": 0.4871845543384552, "regret": 0.3756042420864105, "entropy": 0.09555860608816147, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:33.231055Z", "loop": 2926, "env_steps": 1798348799, "loss": 0.00197827210649848, "avg_return": 0.4845365583896637, "regret": 0.3756042420864105, "entropy": 0.09294098615646362, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:34.084863Z", "loop": 2927, "env_steps": 1798963199, "loss": 0.0019244138384237885, "avg_return": 0.48390716314315796, "regret": 0.3756042420864105, "entropy": 0.09979741275310516, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:34.938052Z", "loop": 2928, "env_steps": 1799577599, "loss": 0.0020790304988622665, "avg_return": 0.48044851422309875, "regret": 0.3756042420864105, "entropy": 0.10269756615161896, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:35.790694Z", "loop": 2929, "env_steps": 1800191999, "loss": 0.0025706584565341473, "avg_return": 0.4889417588710785, "regret": 0.3756042420864105, "entropy": 0.10680146515369415, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:36.685626Z", "loop": 2930, "env_steps": 1800806399, "loss": 0.002899633953347802, "avg_return": 0.4943445920944214, "regret": 0.3758831322193146, "entropy": 0.11297763884067535, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:37.539151Z", "loop": 2931, "env_steps": 1801420799, "loss": 0.002675360534340143, "avg_return": 0.48223429918289185, "regret": 0.3758831322193146, "entropy": 0.10883908718824387, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:38.393789Z", "loop": 2932, "env_steps": 1802035199, "loss": 0.0028015372809022665, "avg_return": 0.4805401861667633, "regret": 0.3758831322193146, "entropy": 0.11032630503177643, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:39.247590Z", "loop": 2933, "env_steps": 1802649599, "loss": 0.0025323370937258005, "avg_return": 0.4771648645401001, "regret": 0.3758831322193146, "entropy": 0.11578119546175003, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:40.101960Z", "loop": 2934, "env_steps": 1803263999, "loss": 0.002847769297659397, "avg_return": 0.4924232065677643, "regret": 0.3758831322193146, "entropy": 0.10849212110042572, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:40.956317Z", "loop": 2935, "env_steps": 1803878399, "loss": 0.002580934204161167, "avg_return": 0.48038768768310547, "regret": 0.3758831322193146, "entropy": 0.10223838686943054, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:41.809930Z", "loop": 2936, "env_steps": 1804492799, "loss": 0.0023975525982677937, "avg_return": 0.4867083728313446, "regret": 0.3758831322193146, "entropy": 0.10459835082292557, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:42.662686Z", "loop": 2937, "env_steps": 1805107199, "loss": 0.0028913922142237425, "avg_return": 0.4858546555042267, "regret": 0.3758831322193146, "entropy": 0.10861720889806747, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:43.516717Z", "loop": 2938, "env_steps": 1805721599, "loss": 0.002797461813315749, "avg_return": 0.4822250008583069, "regret": 0.3758831322193146, "entropy": 0.1080821231007576, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:44.370920Z", "loop": 2939, "env_steps": 1806335999, "loss": 0.0025916032027453184, "avg_return": 0.4854445457458496, "regret": 0.3758831322193146, "entropy": 0.10351796448230743, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:45.262253Z", "loop": 2940, "env_steps": 1806950399, "loss": 0.0027065854519605637, "avg_return": 0.4870530366897583, "regret": 0.37521252036094666, "entropy": 0.10528568923473358, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:46.115254Z", "loop": 2941, "env_steps": 1807564799, "loss": 0.0027755743358284235, "avg_return": 0.48142310976982117, "regret": 0.37521252036094666, "entropy": 0.11341408640146255, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:46.969881Z", "loop": 2942, "env_steps": 1808179199, "loss": 0.0031690113246440887, "avg_return": 0.4874638617038727, "regret": 0.37521252036094666, "entropy": 0.11228395998477936, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:47.823796Z", "loop": 2943, "env_steps": 1808793599, "loss": 0.0030211310368031263, "avg_return": 0.4825590252876282, "regret": 0.37521252036094666, "entropy": 0.12237091362476349, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:48.676927Z", "loop": 2944, "env_steps": 1809407999, "loss": 0.0030594018753618, "avg_return": 0.4890298545360565, "regret": 0.37521252036094666, "entropy": 0.12198673188686371, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:49.531200Z", "loop": 2945, "env_steps": 1810022399, "loss": 0.003380898153409362, "avg_return": 0.49574336409568787, "regret": 0.37521252036094666, "entropy": 0.12355398386716843, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:50.386497Z", "loop": 2946, "env_steps": 1810636799, "loss": 0.0031679016537964344, "avg_return": 0.48779597878456116, "regret": 0.37521252036094666, "entropy": 0.12929974496364594, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:51.239673Z", "loop": 2947, "env_steps": 1811251199, "loss": 0.0031446751672774553, "avg_return": 0.4891320466995239, "regret": 0.37521252036094666, "entropy": 0.1240893080830574, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:52.092556Z", "loop": 2948, "env_steps": 1811865599, "loss": 0.003055793698877096, "avg_return": 0.49095654487609863, "regret": 0.37521252036094666, "entropy": 0.12881970405578613, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:52.945114Z", "loop": 2949, "env_steps": 1812479999, "loss": 0.0032937328796833754, "avg_return": 0.49516215920448303, "regret": 0.37521252036094666, "entropy": 0.13416926562786102, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:53.838614Z", "loop": 2950, "env_steps": 1813094399, "loss": 0.0030740785878151655, "avg_return": 0.48721131682395935, "regret": 0.37532490491867065, "entropy": 0.1360061764717102, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:54.692347Z", "loop": 2951, "env_steps": 1813708799, "loss": 0.0032038812059909105, "avg_return": 0.4885087311267853, "regret": 0.37532490491867065, "entropy": 0.12802930176258087, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:55.546215Z", "loop": 2952, "env_steps": 1814323199, "loss": 0.0031030948739498854, "avg_return": 0.492504745721817, "regret": 0.37532490491867065, "entropy": 0.12036265432834625, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:56.399140Z", "loop": 2953, "env_steps": 1814937599, "loss": 0.0032519882079213858, "avg_return": 0.48668718338012695, "regret": 0.37532490491867065, "entropy": 0.12323778867721558, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:57.252565Z", "loop": 2954, "env_steps": 1815551999, "loss": 0.003004255471751094, "avg_return": 0.4913676977157593, "regret": 0.37532490491867065, "entropy": 0.11919767409563065, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:58.105867Z", "loop": 2955, "env_steps": 1816166399, "loss": 0.0028270212933421135, "avg_return": 0.49285849928855896, "regret": 0.37532490491867065, "entropy": 0.11249794065952301, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:58.959042Z", "loop": 2956, "env_steps": 1816780799, "loss": 0.0029897333588451147, "avg_return": 0.49817901849746704, "regret": 0.37532490491867065, "entropy": 0.11375073343515396, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:05:59.812126Z", "loop": 2957, "env_steps": 1817395199, "loss": 0.0028492447454482317, "avg_return": 0.49093762040138245, "regret": 0.37532490491867065, "entropy": 0.11679840832948685, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:00.666388Z", "loop": 2958, "env_steps": 1818009599, "loss": 0.0027406648732721806, "avg_return": 0.4838995039463043, "regret": 0.37532490491867065, "entropy": 0.12226056307554245, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:01.519040Z", "loop": 2959, "env_steps": 1818623999, "loss": 0.0027321649249643087, "avg_return": 0.48502716422080994, "regret": 0.37532490491867065, "entropy": 0.10911034792661667, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:02.409661Z", "loop": 2960, "env_steps": 1819238399, "loss": 0.0029238881543278694, "avg_return": 0.4925321936607361, "regret": 0.37486985325813293, "entropy": 0.11222946643829346, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:03.263491Z", "loop": 2961, "env_steps": 1819852799, "loss": 0.0027510845102369785, "avg_return": 0.4911077916622162, "regret": 0.37486985325813293, "entropy": 0.10942479223012924, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:04.117790Z", "loop": 2962, "env_steps": 1820467199, "loss": 0.0027251034043729305, "avg_return": 0.48451006412506104, "regret": 0.37486985325813293, "entropy": 0.11404112726449966, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:04.970335Z", "loop": 2963, "env_steps": 1821081599, "loss": 0.0033939566928893328, "avg_return": 0.49619579315185547, "regret": 0.37486985325813293, "entropy": 0.11766376346349716, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:05.823413Z", "loop": 2964, "env_steps": 1821695999, "loss": 0.0032343552447855473, "avg_return": 0.4907682538032532, "regret": 0.37486985325813293, "entropy": 0.12139905989170074, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:06.676586Z", "loop": 2965, "env_steps": 1822310399, "loss": 0.0031818801071494818, "avg_return": 0.48566803336143494, "regret": 0.37486985325813293, "entropy": 0.12382189184427261, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:07.530822Z", "loop": 2966, "env_steps": 1822924799, "loss": 0.00318903592415154, "avg_return": 0.48824241757392883, "regret": 0.37486985325813293, "entropy": 0.12721651792526245, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:08.382949Z", "loop": 2967, "env_steps": 1823539199, "loss": 0.003244385588914156, "avg_return": 0.4815688729286194, "regret": 0.37486985325813293, "entropy": 0.12609365582466125, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:09.235251Z", "loop": 2968, "env_steps": 1824153599, "loss": 0.0032354071736335754, "avg_return": 0.48446035385131836, "regret": 0.37486985325813293, "entropy": 0.11953343451023102, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:10.088299Z", "loop": 2969, "env_steps": 1824767999, "loss": 0.0027728844434022903, "avg_return": 0.4897577166557312, "regret": 0.37486985325813293, "entropy": 0.1230933666229248, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:10.979899Z", "loop": 2970, "env_steps": 1825382399, "loss": 0.0032673075329512358, "avg_return": 0.48178529739379883, "regret": 0.3748888373374939, "entropy": 0.12452369928359985, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:11.833268Z", "loop": 2971, "env_steps": 1825996799, "loss": 0.0027436616364866495, "avg_return": 0.49288493394851685, "regret": 0.3748888373374939, "entropy": 0.12825945019721985, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:12.686761Z", "loop": 2972, "env_steps": 1826611199, "loss": 0.00334809347987175, "avg_return": 0.4890357553958893, "regret": 0.3748888373374939, "entropy": 0.12604235112667084, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:13.539885Z", "loop": 2973, "env_steps": 1827225599, "loss": 0.003124520182609558, "avg_return": 0.4833822250366211, "regret": 0.3748888373374939, "entropy": 0.13004694879055023, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:14.393340Z", "loop": 2974, "env_steps": 1827839999, "loss": 0.002984910272061825, "avg_return": 0.49423423409461975, "regret": 0.3748888373374939, "entropy": 0.13480934500694275, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:15.246273Z", "loop": 2975, "env_steps": 1828454399, "loss": 0.0032179777044802904, "avg_return": 0.4831264317035675, "regret": 0.3748888373374939, "entropy": 0.12429007887840271, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:16.099329Z", "loop": 2976, "env_steps": 1829068799, "loss": 0.0033995856065303087, "avg_return": 0.4892161786556244, "regret": 0.3748888373374939, "entropy": 0.13436970114707947, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:16.951853Z", "loop": 2977, "env_steps": 1829683199, "loss": 0.0033466459717601538, "avg_return": 0.48522061109542847, "regret": 0.3748888373374939, "entropy": 0.13372738659381866, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:17.805192Z", "loop": 2978, "env_steps": 1830297599, "loss": 0.003139713779091835, "avg_return": 0.4921031892299652, "regret": 0.3748888373374939, "entropy": 0.13195127248764038, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:18.658413Z", "loop": 2979, "env_steps": 1830911999, "loss": 0.003330114996060729, "avg_return": 0.48467549681663513, "regret": 0.3748888373374939, "entropy": 0.13322696089744568, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:19.548885Z", "loop": 2980, "env_steps": 1831526399, "loss": 0.0032879491336643696, "avg_return": 0.4960804879665375, "regret": 0.3750556707382202, "entropy": 0.13240966200828552, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:20.402253Z", "loop": 2981, "env_steps": 1832140799, "loss": 0.002930582733824849, "avg_return": 0.48660609126091003, "regret": 0.3750556707382202, "entropy": 0.1268993467092514, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:21.256664Z", "loop": 2982, "env_steps": 1832755199, "loss": 0.002553012454882264, "avg_return": 0.4880252182483673, "regret": 0.3750556707382202, "entropy": 0.11643839627504349, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:22.110489Z", "loop": 2983, "env_steps": 1833369599, "loss": 0.002297155326232314, "avg_return": 0.4903092086315155, "regret": 0.3750556707382202, "entropy": 0.10527265816926956, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:22.963175Z", "loop": 2984, "env_steps": 1833983999, "loss": 0.0016966763650998473, "avg_return": 0.4885513484477997, "regret": 0.3750556707382202, "entropy": 0.1016344428062439, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:23.815698Z", "loop": 2985, "env_steps": 1834598399, "loss": 0.001766317873261869, "avg_return": 0.4821614623069763, "regret": 0.3750556707382202, "entropy": 0.10584279894828796, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:24.669395Z", "loop": 2986, "env_steps": 1835212799, "loss": 0.0019464982906356454, "avg_return": 0.49137911200523376, "regret": 0.3750556707382202, "entropy": 0.10228302329778671, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:25.522981Z", "loop": 2987, "env_steps": 1835827199, "loss": 0.001517891651019454, "avg_return": 0.4954953193664551, "regret": 0.3750556707382202, "entropy": 0.10214640945196152, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:26.376749Z", "loop": 2988, "env_steps": 1836441599, "loss": 0.0018514238763600588, "avg_return": 0.4856295883655548, "regret": 0.3750556707382202, "entropy": 0.10240045189857483, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:27.229680Z", "loop": 2989, "env_steps": 1837055999, "loss": 0.001847643405199051, "avg_return": 0.4825460910797119, "regret": 0.3750556707382202, "entropy": 0.10981694608926773, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:28.122876Z", "loop": 2990, "env_steps": 1837670399, "loss": 0.002470562234520912, "avg_return": 0.48727208375930786, "regret": 0.3744643032550812, "entropy": 0.11531680822372437, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:28.976338Z", "loop": 2991, "env_steps": 1838284799, "loss": 0.002195767592638731, "avg_return": 0.49172231554985046, "regret": 0.3744643032550812, "entropy": 0.11746634542942047, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:29.831681Z", "loop": 2992, "env_steps": 1838899199, "loss": 0.0025903023779392242, "avg_return": 0.48628175258636475, "regret": 0.3744643032550812, "entropy": 0.12086229771375656, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:30.684600Z", "loop": 2993, "env_steps": 1839513599, "loss": 0.002804757095873356, "avg_return": 0.4917948544025421, "regret": 0.3744643032550812, "entropy": 0.12925434112548828, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:31.537500Z", "loop": 2994, "env_steps": 1840127999, "loss": 0.0027190465480089188, "avg_return": 0.48965689539909363, "regret": 0.3744643032550812, "entropy": 0.1469069868326187, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:32.391369Z", "loop": 2995, "env_steps": 1840742399, "loss": 0.002856273902580142, "avg_return": 0.4898727536201477, "regret": 0.3744643032550812, "entropy": 0.14008331298828125, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:33.245985Z", "loop": 2996, "env_steps": 1841356799, "loss": 0.003390547586604953, "avg_return": 0.4886099398136139, "regret": 0.3744643032550812, "entropy": 0.1506921797990799, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:34.099073Z", "loop": 2997, "env_steps": 1841971199, "loss": 0.003405369119718671, "avg_return": 0.4880715012550354, "regret": 0.3744643032550812, "entropy": 0.17386691272258759, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:34.951572Z", "loop": 2998, "env_steps": 1842585599, "loss": 0.003897278103977442, "avg_return": 0.487770140171051, "regret": 0.3744643032550812, "entropy": 0.17637059092521667, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:35.804379Z", "loop": 2999, "env_steps": 1843199999, "loss": 0.004385681822896004, "avg_return": 0.4931918978691101, "regret": 0.3744643032550812, "entropy": 0.1877203732728958, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:36.698971Z", "loop": 3000, "env_steps": 1843814399, "loss": 0.004473875276744366, "avg_return": 0.49731823801994324, "regret": 0.37260526418685913, "entropy": 0.18958963453769684, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:37.552698Z", "loop": 3001, "env_steps": 1844428799, "loss": 0.004521422553807497, "avg_return": 0.4823870062828064, "regret": 0.37260526418685913, "entropy": 0.2131718397140503, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:38.407091Z", "loop": 3002, "env_steps": 1845043199, "loss": 0.0049935136921703815, "avg_return": 0.493194580078125, "regret": 0.37260526418685913, "entropy": 0.22965723276138306, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:39.259923Z", "loop": 3003, "env_steps": 1845657599, "loss": 0.005977916996926069, "avg_return": 0.4956640601158142, "regret": 0.37260526418685913, "entropy": 0.2365906834602356, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:40.112907Z", "loop": 3004, "env_steps": 1846271999, "loss": 0.006005072966217995, "avg_return": 0.49139273166656494, "regret": 0.37260526418685913, "entropy": 0.24896998703479767, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:40.966128Z", "loop": 3005, "env_steps": 1846886399, "loss": 0.0065177977085113525, "avg_return": 0.5026348829269409, "regret": 0.37260526418685913, "entropy": 0.26656800508499146, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:41.819497Z", "loop": 3006, "env_steps": 1847500799, "loss": 0.006938247475773096, "avg_return": 0.49531057476997375, "regret": 0.37260526418685913, "entropy": 0.2852749824523926, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:42.672245Z", "loop": 3007, "env_steps": 1848115199, "loss": 0.007397837936878204, "avg_return": 0.4972265660762787, "regret": 0.37260526418685913, "entropy": 0.2924303710460663, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:43.525557Z", "loop": 3008, "env_steps": 1848729599, "loss": 0.007737928535789251, "avg_return": 0.49840688705444336, "regret": 0.37260526418685913, "entropy": 0.3167824149131775, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:44.378084Z", "loop": 3009, "env_steps": 1849343999, "loss": 0.008532202802598476, "avg_return": 0.5013124942779541, "regret": 0.37260526418685913, "entropy": 0.3356744647026062, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:45.272354Z", "loop": 3010, "env_steps": 1849958399, "loss": 0.009240231476724148, "avg_return": 0.4945710003376007, "regret": 0.3669842779636383, "entropy": 0.3564234673976898, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:46.126548Z", "loop": 3011, "env_steps": 1850572799, "loss": 0.010517849586904049, "avg_return": 0.4958198070526123, "regret": 0.3669842779636383, "entropy": 0.37737226486206055, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:46.981310Z", "loop": 3012, "env_steps": 1851187199, "loss": 0.011569215916097164, "avg_return": 0.49790239334106445, "regret": 0.3669842779636383, "entropy": 0.39664390683174133, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:47.835604Z", "loop": 3013, "env_steps": 1851801599, "loss": 0.01398328598588705, "avg_return": 0.4983704686164856, "regret": 0.3669842779636383, "entropy": 0.4255445599555969, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:48.689325Z", "loop": 3014, "env_steps": 1852415999, "loss": 0.01395475585013628, "avg_return": 0.5033897757530212, "regret": 0.3669842779636383, "entropy": 0.44912397861480713, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:49.542864Z", "loop": 3015, "env_steps": 1853030399, "loss": 0.015729408711194992, "avg_return": 0.49430522322654724, "regret": 0.3669842779636383, "entropy": 0.4612875282764435, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:50.395724Z", "loop": 3016, "env_steps": 1853644799, "loss": 0.01672789826989174, "avg_return": 0.4993395209312439, "regret": 0.3669842779636383, "entropy": 0.4814026355743408, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:51.248158Z", "loop": 3017, "env_steps": 1854259199, "loss": 0.017416315153241158, "avg_return": 0.5024248361587524, "regret": 0.3669842779636383, "entropy": 0.48588570952415466, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:52.101050Z", "loop": 3018, "env_steps": 1854873599, "loss": 0.01762850396335125, "avg_return": 0.4950295686721802, "regret": 0.3669842779636383, "entropy": 0.4859766960144043, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:52.954961Z", "loop": 3019, "env_steps": 1855487999, "loss": 0.01765470579266548, "avg_return": 0.49874401092529297, "regret": 0.3669842779636383, "entropy": 0.46921229362487793, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:53.851040Z", "loop": 3020, "env_steps": 1856102399, "loss": 0.015279300510883331, "avg_return": 0.4980384409427643, "regret": 0.3636021912097931, "entropy": 0.46840232610702515, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:54.705433Z", "loop": 3021, "env_steps": 1856716799, "loss": 0.01660611666738987, "avg_return": 0.5060888528823853, "regret": 0.3636021912097931, "entropy": 0.465541809797287, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:55.559071Z", "loop": 3022, "env_steps": 1857331199, "loss": 0.016301823779940605, "avg_return": 0.5005050301551819, "regret": 0.3636021912097931, "entropy": 0.44988852739334106, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:56.412408Z", "loop": 3023, "env_steps": 1857945599, "loss": 0.01590019091963768, "avg_return": 0.4940822422504425, "regret": 0.3636021912097931, "entropy": 0.4530218243598938, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:57.265448Z", "loop": 3024, "env_steps": 1858559999, "loss": 0.016479616984725, "avg_return": 0.5046001076698303, "regret": 0.3636021912097931, "entropy": 0.4499228298664093, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:58.118909Z", "loop": 3025, "env_steps": 1859174399, "loss": 0.01701849140226841, "avg_return": 0.5064842104911804, "regret": 0.3636021912097931, "entropy": 0.44715240597724915, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:58.971139Z", "loop": 3026, "env_steps": 1859788799, "loss": 0.01696287840604782, "avg_return": 0.5070845484733582, "regret": 0.3636021912097931, "entropy": 0.4441428780555725, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:06:59.823776Z", "loop": 3027, "env_steps": 1860403199, "loss": 0.01593047007918358, "avg_return": 0.5032626986503601, "regret": 0.3636021912097931, "entropy": 0.45037680864334106, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:00.676999Z", "loop": 3028, "env_steps": 1861017599, "loss": 0.015553966164588928, "avg_return": 0.5050553679466248, "regret": 0.3636021912097931, "entropy": 0.4440508186817169, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:01.530645Z", "loop": 3029, "env_steps": 1861631999, "loss": 0.015685120597481728, "avg_return": 0.5040861368179321, "regret": 0.3636021912097931, "entropy": 0.4492565095424652, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:02.425162Z", "loop": 3030, "env_steps": 1862246399, "loss": 0.015484854578971863, "avg_return": 0.5055813193321228, "regret": 0.35968247056007385, "entropy": 0.4559651017189026, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:03.280467Z", "loop": 3031, "env_steps": 1862860799, "loss": 0.018485065549612045, "avg_return": 0.501407265663147, "regret": 0.35968247056007385, "entropy": 0.4612079858779907, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:04.140053Z", "loop": 3032, "env_steps": 1863475199, "loss": 0.017661379650235176, "avg_return": 0.4966237545013428, "regret": 0.35968247056007385, "entropy": 0.46588823199272156, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:05.000538Z", "loop": 3033, "env_steps": 1864089599, "loss": 0.018231354653835297, "avg_return": 0.5037143230438232, "regret": 0.35968247056007385, "entropy": 0.4735696017742157, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:05.853985Z", "loop": 3034, "env_steps": 1864703999, "loss": 0.020135795697569847, "avg_return": 0.5052735805511475, "regret": 0.35968247056007385, "entropy": 0.47964879870414734, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:06.707049Z", "loop": 3035, "env_steps": 1865318399, "loss": 0.01906058005988598, "avg_return": 0.5053337812423706, "regret": 0.35968247056007385, "entropy": 0.4787922501564026, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:07.560297Z", "loop": 3036, "env_steps": 1865932799, "loss": 0.01913529448211193, "avg_return": 0.5066341161727905, "regret": 0.35968247056007385, "entropy": 0.4842744469642639, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:08.413729Z", "loop": 3037, "env_steps": 1866547199, "loss": 0.018958237022161484, "avg_return": 0.5068605542182922, "regret": 0.35968247056007385, "entropy": 0.4716789722442627, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:09.266416Z", "loop": 3038, "env_steps": 1867161599, "loss": 0.019047267735004425, "avg_return": 0.5102127194404602, "regret": 0.35968247056007385, "entropy": 0.479511559009552, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:10.119181Z", "loop": 3039, "env_steps": 1867775999, "loss": 0.018855607137084007, "avg_return": 0.5106071829795837, "regret": 0.35968247056007385, "entropy": 0.46318957209587097, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:11.015366Z", "loop": 3040, "env_steps": 1868390399, "loss": 0.018406718969345093, "avg_return": 0.5022559762001038, "regret": 0.3572852611541748, "entropy": 0.4592542350292206, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:11.868803Z", "loop": 3041, "env_steps": 1869004799, "loss": 0.018343158066272736, "avg_return": 0.5098713040351868, "regret": 0.3572852611541748, "entropy": 0.45512655377388, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:12.722272Z", "loop": 3042, "env_steps": 1869619199, "loss": 0.01924899034202099, "avg_return": 0.5061081647872925, "regret": 0.3572852611541748, "entropy": 0.46761614084243774, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:13.576224Z", "loop": 3043, "env_steps": 1870233599, "loss": 0.019108805805444717, "avg_return": 0.5039154291152954, "regret": 0.3572852611541748, "entropy": 0.46527647972106934, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:14.429443Z", "loop": 3044, "env_steps": 1870847999, "loss": 0.01880486123263836, "avg_return": 0.5065844058990479, "regret": 0.3572852611541748, "entropy": 0.45418521761894226, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:15.282644Z", "loop": 3045, "env_steps": 1871462399, "loss": 0.01880861632525921, "avg_return": 0.5065488815307617, "regret": 0.3572852611541748, "entropy": 0.46046820282936096, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:16.136496Z", "loop": 3046, "env_steps": 1872076799, "loss": 0.02004293166100979, "avg_return": 0.5057232975959778, "regret": 0.3572852611541748, "entropy": 0.4616834819316864, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:16.989638Z", "loop": 3047, "env_steps": 1872691199, "loss": 0.01869417540729046, "avg_return": 0.4965755343437195, "regret": 0.3572852611541748, "entropy": 0.45403438806533813, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:17.842649Z", "loop": 3048, "env_steps": 1873305599, "loss": 0.01956505887210369, "avg_return": 0.5100862979888916, "regret": 0.3572852611541748, "entropy": 0.4647260904312134, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:18.696716Z", "loop": 3049, "env_steps": 1873919999, "loss": 0.019461095333099365, "avg_return": 0.5050565004348755, "regret": 0.3572852611541748, "entropy": 0.4624421000480652, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:19.592420Z", "loop": 3050, "env_steps": 1874534399, "loss": 0.018332788720726967, "avg_return": 0.5085864663124084, "regret": 0.355563759803772, "entropy": 0.44844740629196167, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:20.445716Z", "loop": 3051, "env_steps": 1875148799, "loss": 0.017194246873259544, "avg_return": 0.5079473853111267, "regret": 0.355563759803772, "entropy": 0.44445252418518066, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:21.299923Z", "loop": 3052, "env_steps": 1875763199, "loss": 0.016440505161881447, "avg_return": 0.4965131878852844, "regret": 0.355563759803772, "entropy": 0.42447981238365173, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:22.152919Z", "loop": 3053, "env_steps": 1876377599, "loss": 0.018838638439774513, "avg_return": 0.5112661719322205, "regret": 0.355563759803772, "entropy": 0.4214014410972595, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:23.007331Z", "loop": 3054, "env_steps": 1876991999, "loss": 0.017449798062443733, "avg_return": 0.5088673233985901, "regret": 0.355563759803772, "entropy": 0.42324593663215637, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:23.861125Z", "loop": 3055, "env_steps": 1877606399, "loss": 0.01880650781095028, "avg_return": 0.5083444118499756, "regret": 0.355563759803772, "entropy": 0.4171619117259979, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:24.714354Z", "loop": 3056, "env_steps": 1878220799, "loss": 0.017163321375846863, "avg_return": 0.5101726651191711, "regret": 0.355563759803772, "entropy": 0.4124179184436798, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:25.567590Z", "loop": 3057, "env_steps": 1878835199, "loss": 0.01808912307024002, "avg_return": 0.5037650465965271, "regret": 0.355563759803772, "entropy": 0.42087703943252563, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:26.420027Z", "loop": 3058, "env_steps": 1879449599, "loss": 0.0198363084346056, "avg_return": 0.5093203783035278, "regret": 0.355563759803772, "entropy": 0.4102526605129242, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:27.274749Z", "loop": 3059, "env_steps": 1880063999, "loss": 0.018276408314704895, "avg_return": 0.5069745182991028, "regret": 0.355563759803772, "entropy": 0.41237396001815796, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:28.171907Z", "loop": 3060, "env_steps": 1880678399, "loss": 0.016993636265397072, "avg_return": 0.50653475522995, "regret": 0.3544592261314392, "entropy": 0.3995490074157715, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:29.034711Z", "loop": 3061, "env_steps": 1881292799, "loss": 0.01693475805222988, "avg_return": 0.5105090737342834, "regret": 0.3544592261314392, "entropy": 0.39712247252464294, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:29.886977Z", "loop": 3062, "env_steps": 1881907199, "loss": 0.01637917198240757, "avg_return": 0.5117309093475342, "regret": 0.3544592261314392, "entropy": 0.389168381690979, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:30.739391Z", "loop": 3063, "env_steps": 1882521599, "loss": 0.01537815947085619, "avg_return": 0.5078397393226624, "regret": 0.3544592261314392, "entropy": 0.3889399468898773, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:31.593957Z", "loop": 3064, "env_steps": 1883135999, "loss": 0.015677092596888542, "avg_return": 0.5149133205413818, "regret": 0.3544592261314392, "entropy": 0.3784019947052002, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:32.448699Z", "loop": 3065, "env_steps": 1883750399, "loss": 0.016452563926577568, "avg_return": 0.5060308575630188, "regret": 0.3544592261314392, "entropy": 0.3862980008125305, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:33.302339Z", "loop": 3066, "env_steps": 1884364799, "loss": 0.01731366477906704, "avg_return": 0.5036306977272034, "regret": 0.3544592261314392, "entropy": 0.41152453422546387, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:34.155187Z", "loop": 3067, "env_steps": 1884979199, "loss": 0.018756316974759102, "avg_return": 0.501055896282196, "regret": 0.3544592261314392, "entropy": 0.4394848048686981, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:35.009154Z", "loop": 3068, "env_steps": 1885593599, "loss": 0.018291501328349113, "avg_return": 0.500307559967041, "regret": 0.3544592261314392, "entropy": 0.4384450614452362, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:35.863731Z", "loop": 3069, "env_steps": 1886207999, "loss": 0.016786355525255203, "avg_return": 0.5095497965812683, "regret": 0.3544592261314392, "entropy": 0.4190070927143097, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:36.759958Z", "loop": 3070, "env_steps": 1886822399, "loss": 0.01685374230146408, "avg_return": 0.5080452561378479, "regret": 0.3493233323097229, "entropy": 0.4048748016357422, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:37.612654Z", "loop": 3071, "env_steps": 1887436799, "loss": 0.017350122332572937, "avg_return": 0.5159609913825989, "regret": 0.3493233323097229, "entropy": 0.4131801426410675, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:38.466045Z", "loop": 3072, "env_steps": 1888051199, "loss": 0.01598743535578251, "avg_return": 0.5143953561782837, "regret": 0.3493233323097229, "entropy": 0.4249911904335022, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:39.319450Z", "loop": 3073, "env_steps": 1888665599, "loss": 0.018737666308879852, "avg_return": 0.5132932662963867, "regret": 0.3493233323097229, "entropy": 0.43245261907577515, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:40.173083Z", "loop": 3074, "env_steps": 1889279999, "loss": 0.01874842680990696, "avg_return": 0.5091689825057983, "regret": 0.3493233323097229, "entropy": 0.43620723485946655, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:41.026614Z", "loop": 3075, "env_steps": 1889894399, "loss": 0.018564878031611443, "avg_return": 0.5175086855888367, "regret": 0.3493233323097229, "entropy": 0.4387466013431549, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:41.880648Z", "loop": 3076, "env_steps": 1890508799, "loss": 0.02065202221274376, "avg_return": 0.5209718942642212, "regret": 0.3493233323097229, "entropy": 0.439529150724411, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:42.733819Z", "loop": 3077, "env_steps": 1891123199, "loss": 0.018987532705068588, "avg_return": 0.513796329498291, "regret": 0.3493233323097229, "entropy": 0.4408780336380005, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:43.587467Z", "loop": 3078, "env_steps": 1891737599, "loss": 0.01869937777519226, "avg_return": 0.5182704925537109, "regret": 0.3493233323097229, "entropy": 0.4446708858013153, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:44.442381Z", "loop": 3079, "env_steps": 1892351999, "loss": 0.0198273416608572, "avg_return": 0.5115999579429626, "regret": 0.3493233323097229, "entropy": 0.44654425978660583, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:45.339818Z", "loop": 3080, "env_steps": 1892966399, "loss": 0.020002396777272224, "avg_return": 0.5150102972984314, "regret": 0.3492283821105957, "entropy": 0.449362576007843, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:46.192371Z", "loop": 3081, "env_steps": 1893580799, "loss": 0.018775632604956627, "avg_return": 0.51288902759552, "regret": 0.3492283821105957, "entropy": 0.43191632628440857, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:47.045783Z", "loop": 3082, "env_steps": 1894195199, "loss": 0.018946880474686623, "avg_return": 0.5113205909729004, "regret": 0.3492283821105957, "entropy": 0.4396441876888275, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:47.900230Z", "loop": 3083, "env_steps": 1894809599, "loss": 0.017183946445584297, "avg_return": 0.5119378566741943, "regret": 0.3492283821105957, "entropy": 0.43387994170188904, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:48.754776Z", "loop": 3084, "env_steps": 1895423999, "loss": 0.01600353978574276, "avg_return": 0.5178066492080688, "regret": 0.3492283821105957, "entropy": 0.4260517954826355, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:49.606476Z", "loop": 3085, "env_steps": 1896038399, "loss": 0.017272653058171272, "avg_return": 0.5114468336105347, "regret": 0.3492283821105957, "entropy": 0.42026010155677795, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:50.458926Z", "loop": 3086, "env_steps": 1896652799, "loss": 0.01785569079220295, "avg_return": 0.5157312154769897, "regret": 0.3492283821105957, "entropy": 0.42634689807891846, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:51.312821Z", "loop": 3087, "env_steps": 1897267199, "loss": 0.0183901134878397, "avg_return": 0.5234783291816711, "regret": 0.3492283821105957, "entropy": 0.4218303859233856, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:52.167021Z", "loop": 3088, "env_steps": 1897881599, "loss": 0.017368754372000694, "avg_return": 0.5164204835891724, "regret": 0.3492283821105957, "entropy": 0.4229525029659271, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:53.019871Z", "loop": 3089, "env_steps": 1898495999, "loss": 0.017463475465774536, "avg_return": 0.519499659538269, "regret": 0.3492283821105957, "entropy": 0.41846907138824463, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:53.912642Z", "loop": 3090, "env_steps": 1899110399, "loss": 0.015923183411359787, "avg_return": 0.5191368460655212, "regret": 0.3437019884586334, "entropy": 0.396176815032959, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:54.767203Z", "loop": 3091, "env_steps": 1899724799, "loss": 0.015149821527302265, "avg_return": 0.5204300880432129, "regret": 0.3437019884586334, "entropy": 0.3789691627025604, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:55.620904Z", "loop": 3092, "env_steps": 1900339199, "loss": 0.013650110922753811, "avg_return": 0.5162167549133301, "regret": 0.3437019884586334, "entropy": 0.36412641406059265, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:56.473561Z", "loop": 3093, "env_steps": 1900953599, "loss": 0.013770005665719509, "avg_return": 0.5122769474983215, "regret": 0.3437019884586334, "entropy": 0.3682839870452881, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:57.325834Z", "loop": 3094, "env_steps": 1901567999, "loss": 0.013160981237888336, "avg_return": 0.5142630338668823, "regret": 0.3437019884586334, "entropy": 0.37390920519828796, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:58.179558Z", "loop": 3095, "env_steps": 1902182399, "loss": 0.014883126132190228, "avg_return": 0.5211732387542725, "regret": 0.3437019884586334, "entropy": 0.3707004189491272, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:59.033372Z", "loop": 3096, "env_steps": 1902796799, "loss": 0.01507676113396883, "avg_return": 0.5180785059928894, "regret": 0.3437019884586334, "entropy": 0.38793718814849854, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:07:59.886168Z", "loop": 3097, "env_steps": 1903411199, "loss": 0.017147114500403404, "avg_return": 0.530461311340332, "regret": 0.3437019884586334, "entropy": 0.3809789717197418, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:00.737836Z", "loop": 3098, "env_steps": 1904025599, "loss": 0.016731705516576767, "avg_return": 0.5249823331832886, "regret": 0.3437019884586334, "entropy": 0.3876597285270691, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:01.590385Z", "loop": 3099, "env_steps": 1904639999, "loss": 0.018156347796320915, "avg_return": 0.523516833782196, "regret": 0.3437019884586334, "entropy": 0.39546504616737366, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:02.486012Z", "loop": 3100, "env_steps": 1905254399, "loss": 0.017951523885130882, "avg_return": 0.5234370827674866, "regret": 0.3377440869808197, "entropy": 0.39961716532707214, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:03.339169Z", "loop": 3101, "env_steps": 1905868799, "loss": 0.0182199664413929, "avg_return": 0.528247594833374, "regret": 0.3377440869808197, "entropy": 0.39580634236335754, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:04.192192Z", "loop": 3102, "env_steps": 1906483199, "loss": 0.01813875325024128, "avg_return": 0.528613805770874, "regret": 0.3377440869808197, "entropy": 0.39045655727386475, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:05.045494Z", "loop": 3103, "env_steps": 1907097599, "loss": 0.017450382933020592, "avg_return": 0.521542489528656, "regret": 0.3377440869808197, "entropy": 0.38865187764167786, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:05.898670Z", "loop": 3104, "env_steps": 1907711999, "loss": 0.01688237302005291, "avg_return": 0.5214871168136597, "regret": 0.3377440869808197, "entropy": 0.3874976933002472, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:06.752304Z", "loop": 3105, "env_steps": 1908326399, "loss": 0.01731954514980316, "avg_return": 0.5326558351516724, "regret": 0.3377440869808197, "entropy": 0.3780462145805359, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:07.605263Z", "loop": 3106, "env_steps": 1908940799, "loss": 0.017247535288333893, "avg_return": 0.5286176204681396, "regret": 0.3377440869808197, "entropy": 0.3765738010406494, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:08.458451Z", "loop": 3107, "env_steps": 1909555199, "loss": 0.016284501180052757, "avg_return": 0.5252233147621155, "regret": 0.3377440869808197, "entropy": 0.38647037744522095, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:09.310383Z", "loop": 3108, "env_steps": 1910169599, "loss": 0.01763051562011242, "avg_return": 0.5254791378974915, "regret": 0.3377440869808197, "entropy": 0.40055206418037415, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:10.163177Z", "loop": 3109, "env_steps": 1910783999, "loss": 0.016785873100161552, "avg_return": 0.5309983491897583, "regret": 0.3377440869808197, "entropy": 0.39982765913009644, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:11.058331Z", "loop": 3110, "env_steps": 1911398399, "loss": 0.019411537796258926, "avg_return": 0.5262391567230225, "regret": 0.3335627317428589, "entropy": 0.42255181074142456, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:11.911849Z", "loop": 3111, "env_steps": 1912012799, "loss": 0.018400510773062706, "avg_return": 0.5311126112937927, "regret": 0.3335627317428589, "entropy": 0.4424344003200531, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:12.764801Z", "loop": 3112, "env_steps": 1912627199, "loss": 0.021151665598154068, "avg_return": 0.5298792719841003, "regret": 0.3335627317428589, "entropy": 0.4451586604118347, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:13.618668Z", "loop": 3113, "env_steps": 1913241599, "loss": 0.020650174468755722, "avg_return": 0.5337169170379639, "regret": 0.3335627317428589, "entropy": 0.4457298517227173, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:14.472484Z", "loop": 3114, "env_steps": 1913855999, "loss": 0.022420663386583328, "avg_return": 0.5366241335868835, "regret": 0.3335627317428589, "entropy": 0.45736950635910034, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:15.326401Z", "loop": 3115, "env_steps": 1914470399, "loss": 0.022370539605617523, "avg_return": 0.5356857180595398, "regret": 0.3335627317428589, "entropy": 0.44797220826148987, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:16.179937Z", "loop": 3116, "env_steps": 1915084799, "loss": 0.022732017561793327, "avg_return": 0.5481662154197693, "regret": 0.3335627317428589, "entropy": 0.4474829137325287, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:17.033620Z", "loop": 3117, "env_steps": 1915699199, "loss": 0.023836730048060417, "avg_return": 0.5472086071968079, "regret": 0.3335627317428589, "entropy": 0.44853442907333374, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:17.887987Z", "loop": 3118, "env_steps": 1916313599, "loss": 0.02252458967268467, "avg_return": 0.5513601303100586, "regret": 0.3335627317428589, "entropy": 0.4525960087776184, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:18.742876Z", "loop": 3119, "env_steps": 1916927999, "loss": 0.026455799117684364, "avg_return": 0.5497796535491943, "regret": 0.3335627317428589, "entropy": 0.46759530901908875, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:19.639871Z", "loop": 3120, "env_steps": 1917542399, "loss": 0.025294912979006767, "avg_return": 0.5559788942337036, "regret": 0.3035111725330353, "entropy": 0.47953853011131287, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:20.493346Z", "loop": 3121, "env_steps": 1918156799, "loss": 0.02833278477191925, "avg_return": 0.5559290647506714, "regret": 0.3035111725330353, "entropy": 0.5055172443389893, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:21.346616Z", "loop": 3122, "env_steps": 1918771199, "loss": 0.027071908116340637, "avg_return": 0.5620132684707642, "regret": 0.3035111725330353, "entropy": 0.5005630850791931, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:22.201687Z", "loop": 3123, "env_steps": 1919385599, "loss": 0.030653048306703568, "avg_return": 0.5626871585845947, "regret": 0.3035111725330353, "entropy": 0.5164066553115845, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:23.055823Z", "loop": 3124, "env_steps": 1919999999, "loss": 0.03119928017258644, "avg_return": 0.5721167922019958, "regret": 0.3035111725330353, "entropy": 0.5306132435798645, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:23.909871Z", "loop": 3125, "env_steps": 1920614399, "loss": 0.032032087445259094, "avg_return": 0.5772383809089661, "regret": 0.3035111725330353, "entropy": 0.5235322713851929, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:24.763134Z", "loop": 3126, "env_steps": 1921228799, "loss": 0.03031635656952858, "avg_return": 0.5770302414894104, "regret": 0.3035111725330353, "entropy": 0.5256657004356384, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:25.618269Z", "loop": 3127, "env_steps": 1921843199, "loss": 0.03372793272137642, "avg_return": 0.5778169631958008, "regret": 0.3035111725330353, "entropy": 0.5274527668952942, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:26.472469Z", "loop": 3128, "env_steps": 1922457599, "loss": 0.03516858071088791, "avg_return": 0.5851526260375977, "regret": 0.3035111725330353, "entropy": 0.529774010181427, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:27.325320Z", "loop": 3129, "env_steps": 1923071999, "loss": 0.03696223720908165, "avg_return": 0.5901117324829102, "regret": 0.3035111725330353, "entropy": 0.5416335463523865, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:28.218580Z", "loop": 3130, "env_steps": 1923686399, "loss": 0.03533210977911949, "avg_return": 0.5821343064308167, "regret": 0.2744087278842926, "entropy": 0.5301241278648376, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:29.071057Z", "loop": 3131, "env_steps": 1924300799, "loss": 0.036365266889333725, "avg_return": 0.5805765390396118, "regret": 0.2744087278842926, "entropy": 0.5232537388801575, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:29.924599Z", "loop": 3132, "env_steps": 1924915199, "loss": 0.03768765181303024, "avg_return": 0.5944225788116455, "regret": 0.2744087278842926, "entropy": 0.538004457950592, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:30.777495Z", "loop": 3133, "env_steps": 1925529599, "loss": 0.03855885937809944, "avg_return": 0.5931130051612854, "regret": 0.2744087278842926, "entropy": 0.5634229183197021, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:31.631535Z", "loop": 3134, "env_steps": 1926143999, "loss": 0.04189285263419151, "avg_return": 0.5901610255241394, "regret": 0.2744087278842926, "entropy": 0.5892615914344788, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:32.486508Z", "loop": 3135, "env_steps": 1926758399, "loss": 0.04555104672908783, "avg_return": 0.5975247621536255, "regret": 0.2744087278842926, "entropy": 0.6044469475746155, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:33.340233Z", "loop": 3136, "env_steps": 1927372799, "loss": 0.03944653645157814, "avg_return": 0.5954353213310242, "regret": 0.2744087278842926, "entropy": 0.6087360978126526, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:34.193311Z", "loop": 3137, "env_steps": 1927987199, "loss": 0.04416303709149361, "avg_return": 0.6017299294471741, "regret": 0.2744087278842926, "entropy": 0.5972774624824524, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:35.046737Z", "loop": 3138, "env_steps": 1928601599, "loss": 0.04542763531208038, "avg_return": 0.6093378663063049, "regret": 0.2744087278842926, "entropy": 0.5846944451332092, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:35.899295Z", "loop": 3139, "env_steps": 1929215999, "loss": 0.0435355044901371, "avg_return": 0.6107084155082703, "regret": 0.2744087278842926, "entropy": 0.5864599943161011, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:36.798013Z", "loop": 3140, "env_steps": 1929830399, "loss": 0.04104330763220787, "avg_return": 0.6074124574661255, "regret": 0.24994875490665436, "entropy": 0.5739572048187256, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:37.650541Z", "loop": 3141, "env_steps": 1930444799, "loss": 0.04257618635892868, "avg_return": 0.6179320812225342, "regret": 0.24994875490665436, "entropy": 0.5646430850028992, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:38.504010Z", "loop": 3142, "env_steps": 1931059199, "loss": 0.04225283861160278, "avg_return": 0.6092321276664734, "regret": 0.24994875490665436, "entropy": 0.5807692408561707, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:39.358034Z", "loop": 3143, "env_steps": 1931673599, "loss": 0.04977521300315857, "avg_return": 0.6175359487533569, "regret": 0.24994875490665436, "entropy": 0.5852063894271851, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:40.211227Z", "loop": 3144, "env_steps": 1932287999, "loss": 0.047490183264017105, "avg_return": 0.6141034364700317, "regret": 0.24994875490665436, "entropy": 0.6039953827857971, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:41.065387Z", "loop": 3145, "env_steps": 1932902399, "loss": 0.0508916862308979, "avg_return": 0.6147791743278503, "regret": 0.24994875490665436, "entropy": 0.6108776330947876, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:41.919734Z", "loop": 3146, "env_steps": 1933516799, "loss": 0.046261247247457504, "avg_return": 0.6178872585296631, "regret": 0.24994875490665436, "entropy": 0.5835779905319214, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:42.774140Z", "loop": 3147, "env_steps": 1934131199, "loss": 0.045364316552877426, "avg_return": 0.6206681728363037, "regret": 0.24994875490665436, "entropy": 0.5684276819229126, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:43.627732Z", "loop": 3148, "env_steps": 1934745599, "loss": 0.0443408377468586, "avg_return": 0.6224997043609619, "regret": 0.24994875490665436, "entropy": 0.5752304196357727, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:44.481246Z", "loop": 3149, "env_steps": 1935359999, "loss": 0.04013853520154953, "avg_return": 0.6169549226760864, "regret": 0.24994875490665436, "entropy": 0.5805515646934509, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:45.380876Z", "loop": 3150, "env_steps": 1935974399, "loss": 0.04536869749426842, "avg_return": 0.624062180519104, "regret": 0.23769527673721313, "entropy": 0.5883499383926392, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:46.234714Z", "loop": 3151, "env_steps": 1936588799, "loss": 0.045269254595041275, "avg_return": 0.6271916031837463, "regret": 0.23769527673721313, "entropy": 0.607502281665802, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:47.086821Z", "loop": 3152, "env_steps": 1937203199, "loss": 0.047518301755189896, "avg_return": 0.6304816007614136, "regret": 0.23769527673721313, "entropy": 0.6192440986633301, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:47.939722Z", "loop": 3153, "env_steps": 1937817599, "loss": 0.052262354642152786, "avg_return": 0.6303216218948364, "regret": 0.23769527673721313, "entropy": 0.6198019981384277, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:48.793088Z", "loop": 3154, "env_steps": 1938431999, "loss": 0.05060424283146858, "avg_return": 0.6317786574363708, "regret": 0.23769527673721313, "entropy": 0.598011314868927, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:49.645741Z", "loop": 3155, "env_steps": 1939046399, "loss": 0.052522849291563034, "avg_return": 0.6341837644577026, "regret": 0.23769527673721313, "entropy": 0.586443305015564, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:50.499393Z", "loop": 3156, "env_steps": 1939660799, "loss": 0.051527608186006546, "avg_return": 0.6305868625640869, "regret": 0.23769527673721313, "entropy": 0.5609619617462158, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:51.351719Z", "loop": 3157, "env_steps": 1940275199, "loss": 0.05062186345458031, "avg_return": 0.6363515257835388, "regret": 0.23769527673721313, "entropy": 0.5481378436088562, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:52.204782Z", "loop": 3158, "env_steps": 1940889599, "loss": 0.05145755037665367, "avg_return": 0.6323757171630859, "regret": 0.23769527673721313, "entropy": 0.5477855801582336, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:53.058172Z", "loop": 3159, "env_steps": 1941503999, "loss": 0.054667603224515915, "avg_return": 0.6461964845657349, "regret": 0.23769527673721313, "entropy": 0.5596821904182434, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:53.953766Z", "loop": 3160, "env_steps": 1942118399, "loss": 0.052809227257966995, "avg_return": 0.6465722322463989, "regret": 0.21334728598594666, "entropy": 0.5882894396781921, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:54.807232Z", "loop": 3161, "env_steps": 1942732799, "loss": 0.05633502081036568, "avg_return": 0.6510212421417236, "regret": 0.21334728598594666, "entropy": 0.6010110974311829, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:55.660499Z", "loop": 3162, "env_steps": 1943347199, "loss": 0.05809152126312256, "avg_return": 0.655147910118103, "regret": 0.21334728598594666, "entropy": 0.6072523593902588, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:56.514391Z", "loop": 3163, "env_steps": 1943961599, "loss": 0.054316289722919464, "avg_return": 0.6495693325996399, "regret": 0.21334728598594666, "entropy": 0.5995621681213379, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:57.368321Z", "loop": 3164, "env_steps": 1944575999, "loss": 0.056937266141176224, "avg_return": 0.6572830080986023, "regret": 0.21334728598594666, "entropy": 0.5963135361671448, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:58.222648Z", "loop": 3165, "env_steps": 1945190399, "loss": 0.05882294848561287, "avg_return": 0.6556857228279114, "regret": 0.21334728598594666, "entropy": 0.5803263783454895, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:59.075873Z", "loop": 3166, "env_steps": 1945804799, "loss": 0.06455615907907486, "avg_return": 0.6554893255233765, "regret": 0.21334728598594666, "entropy": 0.562745213508606, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:08:59.928204Z", "loop": 3167, "env_steps": 1946419199, "loss": 0.06386753916740417, "avg_return": 0.6535778045654297, "regret": 0.21334728598594666, "entropy": 0.5685917735099792, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:00.781395Z", "loop": 3168, "env_steps": 1947033599, "loss": 0.06433679908514023, "avg_return": 0.667018473148346, "regret": 0.21334728598594666, "entropy": 0.5646640062332153, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:01.635702Z", "loop": 3169, "env_steps": 1947647999, "loss": 0.05968176946043968, "avg_return": 0.6591863036155701, "regret": 0.21334728598594666, "entropy": 0.5692296624183655, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:02.532491Z", "loop": 3170, "env_steps": 1948262399, "loss": 0.05794588848948479, "avg_return": 0.6657442450523376, "regret": 0.19437719881534576, "entropy": 0.5827928185462952, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:03.384590Z", "loop": 3171, "env_steps": 1948876799, "loss": 0.054118674248456955, "avg_return": 0.6623006463050842, "regret": 0.19437719881534576, "entropy": 0.5725066661834717, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:04.238456Z", "loop": 3172, "env_steps": 1949491199, "loss": 0.06344684958457947, "avg_return": 0.6731670498847961, "regret": 0.19437719881534576, "entropy": 0.5748589038848877, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:05.092277Z", "loop": 3173, "env_steps": 1950105599, "loss": 0.061055656522512436, "avg_return": 0.6780117154121399, "regret": 0.19437719881534576, "entropy": 0.5584317445755005, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:05.946155Z", "loop": 3174, "env_steps": 1950719999, "loss": 0.06611564755439758, "avg_return": 0.6724027395248413, "regret": 0.19437719881534576, "entropy": 0.5651944875717163, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:06.799529Z", "loop": 3175, "env_steps": 1951334399, "loss": 0.06103793531656265, "avg_return": 0.6776570081710815, "regret": 0.19437719881534576, "entropy": 0.5369777679443359, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:07.652184Z", "loop": 3176, "env_steps": 1951948799, "loss": 0.06184590607881546, "avg_return": 0.678302526473999, "regret": 0.19437719881534576, "entropy": 0.5366315245628357, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:08.506602Z", "loop": 3177, "env_steps": 1952563199, "loss": 0.06067389249801636, "avg_return": 0.6840647459030151, "regret": 0.19437719881534576, "entropy": 0.5447920560836792, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:09.360010Z", "loop": 3178, "env_steps": 1953177599, "loss": 0.06489644199609756, "avg_return": 0.6896520256996155, "regret": 0.19437719881534576, "entropy": 0.5456687808036804, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:10.213141Z", "loop": 3179, "env_steps": 1953791999, "loss": 0.0619848370552063, "avg_return": 0.6885571479797363, "regret": 0.19437719881534576, "entropy": 0.5618460178375244, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:11.109176Z", "loop": 3180, "env_steps": 1954406399, "loss": 0.0637531727552414, "avg_return": 0.6935389637947083, "regret": 0.16661450266838074, "entropy": 0.5562453866004944, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:11.962436Z", "loop": 3181, "env_steps": 1955020799, "loss": 0.06395677477121353, "avg_return": 0.6973913908004761, "regret": 0.16661450266838074, "entropy": 0.5317895412445068, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:12.816307Z", "loop": 3182, "env_steps": 1955635199, "loss": 0.0642169639468193, "avg_return": 0.6976784467697144, "regret": 0.16661450266838074, "entropy": 0.524634063243866, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:13.669264Z", "loop": 3183, "env_steps": 1956249599, "loss": 0.06208119913935661, "avg_return": 0.6996163725852966, "regret": 0.16661450266838074, "entropy": 0.5264570116996765, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:14.521048Z", "loop": 3184, "env_steps": 1956863999, "loss": 0.06682497262954712, "avg_return": 0.7076529264450073, "regret": 0.16661450266838074, "entropy": 0.527371346950531, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:15.373287Z", "loop": 3185, "env_steps": 1957478399, "loss": 0.06441106647253036, "avg_return": 0.7008089423179626, "regret": 0.16661450266838074, "entropy": 0.537323534488678, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:16.226517Z", "loop": 3186, "env_steps": 1958092799, "loss": 0.06931853294372559, "avg_return": 0.7062394618988037, "regret": 0.16661450266838074, "entropy": 0.539605975151062, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:17.079728Z", "loop": 3187, "env_steps": 1958707199, "loss": 0.06369953602552414, "avg_return": 0.7098150849342346, "regret": 0.16661450266838074, "entropy": 0.5151389837265015, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:17.932360Z", "loop": 3188, "env_steps": 1959321599, "loss": 0.06509369611740112, "avg_return": 0.7056079506874084, "regret": 0.16661450266838074, "entropy": 0.514699399471283, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:18.784614Z", "loop": 3189, "env_steps": 1959935999, "loss": 0.06291227787733078, "avg_return": 0.7076572179794312, "regret": 0.16661450266838074, "entropy": 0.5378550291061401, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:19.679710Z", "loop": 3190, "env_steps": 1960550399, "loss": 0.07095526903867722, "avg_return": 0.7139607071876526, "regret": 0.1456674188375473, "entropy": 0.5570432543754578, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:20.534079Z", "loop": 3191, "env_steps": 1961164799, "loss": 0.07320361584424973, "avg_return": 0.7134131789207458, "regret": 0.1456674188375473, "entropy": 0.542777955532074, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:21.387592Z", "loop": 3192, "env_steps": 1961779199, "loss": 0.0710483118891716, "avg_return": 0.7132987380027771, "regret": 0.1456674188375473, "entropy": 0.5393515825271606, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:22.240430Z", "loop": 3193, "env_steps": 1962393599, "loss": 0.07078352570533752, "avg_return": 0.7103458046913147, "regret": 0.1456674188375473, "entropy": 0.5237587690353394, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:23.093543Z", "loop": 3194, "env_steps": 1963007999, "loss": 0.0713091492652893, "avg_return": 0.7152189016342163, "regret": 0.1456674188375473, "entropy": 0.5195388197898865, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:23.945680Z", "loop": 3195, "env_steps": 1963622399, "loss": 0.06895088404417038, "avg_return": 0.7199723720550537, "regret": 0.1456674188375473, "entropy": 0.527523934841156, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:24.799216Z", "loop": 3196, "env_steps": 1964236799, "loss": 0.06749223917722702, "avg_return": 0.7168616056442261, "regret": 0.1456674188375473, "entropy": 0.5474793910980225, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:25.652886Z", "loop": 3197, "env_steps": 1964851199, "loss": 0.07245513051748276, "avg_return": 0.7211764454841614, "regret": 0.1456674188375473, "entropy": 0.5604814887046814, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:26.504808Z", "loop": 3198, "env_steps": 1965465599, "loss": 0.07320854812860489, "avg_return": 0.7231864333152771, "regret": 0.1456674188375473, "entropy": 0.5496507883071899, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:27.358172Z", "loop": 3199, "env_steps": 1966079999, "loss": 0.07434504479169846, "avg_return": 0.7274070382118225, "regret": 0.1456674188375473, "entropy": 0.5493749976158142, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:28.255736Z", "loop": 3200, "env_steps": 1966694399, "loss": 0.07591430097818375, "avg_return": 0.7252210378646851, "regret": 0.1318378746509552, "entropy": 0.5320500731468201, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:29.109117Z", "loop": 3201, "env_steps": 1967308799, "loss": 0.07370071858167648, "avg_return": 0.7202182412147522, "regret": 0.1318378746509552, "entropy": 0.5155840516090393, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:29.963501Z", "loop": 3202, "env_steps": 1967923199, "loss": 0.07312872260808945, "avg_return": 0.7273051142692566, "regret": 0.1318378746509552, "entropy": 0.5283856391906738, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:30.816499Z", "loop": 3203, "env_steps": 1968537599, "loss": 0.07892357558012009, "avg_return": 0.7376084923744202, "regret": 0.1318378746509552, "entropy": 0.5301789045333862, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:31.672153Z", "loop": 3204, "env_steps": 1969151999, "loss": 0.07595282047986984, "avg_return": 0.7320389747619629, "regret": 0.1318378746509552, "entropy": 0.5350006222724915, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:32.525456Z", "loop": 3205, "env_steps": 1969766399, "loss": 0.0729275494813919, "avg_return": 0.7295384407043457, "regret": 0.1318378746509552, "entropy": 0.5478280782699585, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:33.378576Z", "loop": 3206, "env_steps": 1970380799, "loss": 0.07433698326349258, "avg_return": 0.7379701137542725, "regret": 0.1318378746509552, "entropy": 0.524733304977417, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:34.232384Z", "loop": 3207, "env_steps": 1970995199, "loss": 0.06926983594894409, "avg_return": 0.7396535873413086, "regret": 0.1318378746509552, "entropy": 0.5023155212402344, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:35.086114Z", "loop": 3208, "env_steps": 1971609599, "loss": 0.07203692197799683, "avg_return": 0.7399945259094238, "regret": 0.1318378746509552, "entropy": 0.48981496691703796, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:35.940607Z", "loop": 3209, "env_steps": 1972223999, "loss": 0.06991780549287796, "avg_return": 0.7414477467536926, "regret": 0.1318378746509552, "entropy": 0.49361759424209595, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:36.838277Z", "loop": 3210, "env_steps": 1972838399, "loss": 0.07184094935655594, "avg_return": 0.7384420037269592, "regret": 0.12037254869937897, "entropy": 0.4918862283229828, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:37.691187Z", "loop": 3211, "env_steps": 1973452799, "loss": 0.06735260784626007, "avg_return": 0.7415847182273865, "regret": 0.12037254869937897, "entropy": 0.4906645119190216, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:38.547130Z", "loop": 3212, "env_steps": 1974067199, "loss": 0.06940441578626633, "avg_return": 0.7423874139785767, "regret": 0.12037254869937897, "entropy": 0.5020384192466736, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:39.401817Z", "loop": 3213, "env_steps": 1974681599, "loss": 0.06544890254735947, "avg_return": 0.7468275427818298, "regret": 0.12037254869937897, "entropy": 0.4855920672416687, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:40.255737Z", "loop": 3214, "env_steps": 1975295999, "loss": 0.06883314996957779, "avg_return": 0.7461901903152466, "regret": 0.12037254869937897, "entropy": 0.4774266183376312, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:41.109505Z", "loop": 3215, "env_steps": 1975910399, "loss": 0.06674818694591522, "avg_return": 0.7475939989089966, "regret": 0.12037254869937897, "entropy": 0.47797679901123047, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:41.963667Z", "loop": 3216, "env_steps": 1976524799, "loss": 0.06858041137456894, "avg_return": 0.745506227016449, "regret": 0.12037254869937897, "entropy": 0.4636225700378418, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:42.816816Z", "loop": 3217, "env_steps": 1977139199, "loss": 0.06884265691041946, "avg_return": 0.7549559473991394, "regret": 0.12037254869937897, "entropy": 0.4648149609565735, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:43.669942Z", "loop": 3218, "env_steps": 1977753599, "loss": 0.06974266469478607, "avg_return": 0.7476243376731873, "regret": 0.12037254869937897, "entropy": 0.46522459387779236, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:44.522918Z", "loop": 3219, "env_steps": 1978367999, "loss": 0.07046937942504883, "avg_return": 0.7565404772758484, "regret": 0.12037254869937897, "entropy": 0.4549919366836548, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:45.421814Z", "loop": 3220, "env_steps": 1978982399, "loss": 0.06638005375862122, "avg_return": 0.7580910325050354, "regret": 0.10468529164791107, "entropy": 0.45738485455513, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:46.274391Z", "loop": 3221, "env_steps": 1979596799, "loss": 0.06726982444524765, "avg_return": 0.7545482516288757, "regret": 0.10468529164791107, "entropy": 0.4385063052177429, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:47.127786Z", "loop": 3222, "env_steps": 1980211199, "loss": 0.07081983238458633, "avg_return": 0.7555983662605286, "regret": 0.10468529164791107, "entropy": 0.46612945199012756, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:47.981605Z", "loop": 3223, "env_steps": 1980825599, "loss": 0.07088064402341843, "avg_return": 0.7575892806053162, "regret": 0.10468529164791107, "entropy": 0.46569254994392395, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:48.836802Z", "loop": 3224, "env_steps": 1981439999, "loss": 0.07245482504367828, "avg_return": 0.7620912194252014, "regret": 0.10468529164791107, "entropy": 0.4643920063972473, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:49.690309Z", "loop": 3225, "env_steps": 1982054399, "loss": 0.06905214488506317, "avg_return": 0.757758378982544, "regret": 0.10468529164791107, "entropy": 0.4647234082221985, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:50.543590Z", "loop": 3226, "env_steps": 1982668799, "loss": 0.06903485208749771, "avg_return": 0.7632376551628113, "regret": 0.10468529164791107, "entropy": 0.46308138966560364, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:51.397669Z", "loop": 3227, "env_steps": 1983283199, "loss": 0.06711138784885406, "avg_return": 0.7589401602745056, "regret": 0.10468529164791107, "entropy": 0.4677848815917969, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:52.251315Z", "loop": 3228, "env_steps": 1983897599, "loss": 0.06416011601686478, "avg_return": 0.7575048208236694, "regret": 0.10468529164791107, "entropy": 0.46703094244003296, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:53.103726Z", "loop": 3229, "env_steps": 1984511999, "loss": 0.06764501333236694, "avg_return": 0.7600911855697632, "regret": 0.10468529164791107, "entropy": 0.46324124932289124, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:53.999328Z", "loop": 3230, "env_steps": 1985126399, "loss": 0.07220723479986191, "avg_return": 0.7628071308135986, "regret": 0.09787961840629578, "entropy": 0.46101856231689453, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:54.853877Z", "loop": 3231, "env_steps": 1985740799, "loss": 0.07174842804670334, "avg_return": 0.764414370059967, "regret": 0.09787961840629578, "entropy": 0.4547736942768097, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:55.707709Z", "loop": 3232, "env_steps": 1986355199, "loss": 0.07022544741630554, "avg_return": 0.7570574879646301, "regret": 0.09787961840629578, "entropy": 0.454650342464447, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:56.560879Z", "loop": 3233, "env_steps": 1986969599, "loss": 0.07086670398712158, "avg_return": 0.7580196261405945, "regret": 0.09787961840629578, "entropy": 0.4561109244823456, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:57.413313Z", "loop": 3234, "env_steps": 1987583999, "loss": 0.07047147303819656, "avg_return": 0.7612055540084839, "regret": 0.09787961840629578, "entropy": 0.4450051784515381, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:58.267447Z", "loop": 3235, "env_steps": 1988198399, "loss": 0.06736031174659729, "avg_return": 0.763462245464325, "regret": 0.09787961840629578, "entropy": 0.4448418617248535, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:59.121487Z", "loop": 3236, "env_steps": 1988812799, "loss": 0.06830582022666931, "avg_return": 0.7687771320343018, "regret": 0.09787961840629578, "entropy": 0.45372653007507324, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:09:59.974294Z", "loop": 3237, "env_steps": 1989427199, "loss": 0.06990264356136322, "avg_return": 0.7694600820541382, "regret": 0.09787961840629578, "entropy": 0.4480496942996979, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:00.827577Z", "loop": 3238, "env_steps": 1990041599, "loss": 0.07019736617803574, "avg_return": 0.7709825038909912, "regret": 0.09787961840629578, "entropy": 0.44178444147109985, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:01.680980Z", "loop": 3239, "env_steps": 1990655999, "loss": 0.0688232034444809, "avg_return": 0.7692504525184631, "regret": 0.09787961840629578, "entropy": 0.4394303560256958, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:02.578673Z", "loop": 3240, "env_steps": 1991270399, "loss": 0.07318427413702011, "avg_return": 0.7627133131027222, "regret": 0.09919213503599167, "entropy": 0.444323867559433, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:03.434206Z", "loop": 3241, "env_steps": 1991884799, "loss": 0.07486230134963989, "avg_return": 0.7515907287597656, "regret": 0.09919213503599167, "entropy": 0.46406611800193787, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:04.289349Z", "loop": 3242, "env_steps": 1992499199, "loss": 0.07248120754957199, "avg_return": 0.7605289220809937, "regret": 0.09919213503599167, "entropy": 0.46106958389282227, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:05.142635Z", "loop": 3243, "env_steps": 1993113599, "loss": 0.06704411655664444, "avg_return": 0.7604961395263672, "regret": 0.09919213503599167, "entropy": 0.43324193358421326, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:05.995301Z", "loop": 3244, "env_steps": 1993727999, "loss": 0.06938068568706512, "avg_return": 0.7634966373443604, "regret": 0.09919213503599167, "entropy": 0.4489264190196991, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:06.848565Z", "loop": 3245, "env_steps": 1994342399, "loss": 0.06629084050655365, "avg_return": 0.7612245678901672, "regret": 0.09919213503599167, "entropy": 0.4472852349281311, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:07.702693Z", "loop": 3246, "env_steps": 1994956799, "loss": 0.06515683233737946, "avg_return": 0.7675369381904602, "regret": 0.09919213503599167, "entropy": 0.4513983130455017, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:08.557447Z", "loop": 3247, "env_steps": 1995571199, "loss": 0.0698685422539711, "avg_return": 0.7741507291793823, "regret": 0.09919213503599167, "entropy": 0.44145962595939636, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:09.410798Z", "loop": 3248, "env_steps": 1996185599, "loss": 0.06353773176670074, "avg_return": 0.777187168598175, "regret": 0.09919213503599167, "entropy": 0.4125407934188843, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:10.265212Z", "loop": 3249, "env_steps": 1996799999, "loss": 0.06183987855911255, "avg_return": 0.7739744186401367, "regret": 0.09919213503599167, "entropy": 0.38939735293388367, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:11.161972Z", "loop": 3250, "env_steps": 1997414399, "loss": 0.06403765827417374, "avg_return": 0.7734814882278442, "regret": 0.08932209014892578, "entropy": 0.399431049823761, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:12.016155Z", "loop": 3251, "env_steps": 1998028799, "loss": 0.06498221307992935, "avg_return": 0.7750558257102966, "regret": 0.08932209014892578, "entropy": 0.4156738221645355, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:12.869404Z", "loop": 3252, "env_steps": 1998643199, "loss": 0.0677562952041626, "avg_return": 0.7621328234672546, "regret": 0.08932209014892578, "entropy": 0.43675023317337036, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:13.721735Z", "loop": 3253, "env_steps": 1999257599, "loss": 0.0685676783323288, "avg_return": 0.7653224468231201, "regret": 0.08932209014892578, "entropy": 0.4473823606967926, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:14.574736Z", "loop": 3254, "env_steps": 1999871999, "loss": 0.06307902187108994, "avg_return": 0.7770223021507263, "regret": 0.08932209014892578, "entropy": 0.4179806113243103, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:15.427739Z", "loop": 3255, "env_steps": 2000486399, "loss": 0.06589110195636749, "avg_return": 0.7773471474647522, "regret": 0.08932209014892578, "entropy": 0.4215409755706787, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:16.280590Z", "loop": 3256, "env_steps": 2001100799, "loss": 0.06683757901191711, "avg_return": 0.7765284180641174, "regret": 0.08932209014892578, "entropy": 0.41175246238708496, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:17.133106Z", "loop": 3257, "env_steps": 2001715199, "loss": 0.06283267587423325, "avg_return": 0.7814213037490845, "regret": 0.08932209014892578, "entropy": 0.40928423404693604, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:17.986001Z", "loop": 3258, "env_steps": 2002329599, "loss": 0.06648818403482437, "avg_return": 0.7766526341438293, "regret": 0.08932209014892578, "entropy": 0.4197063148021698, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:18.838669Z", "loop": 3259, "env_steps": 2002943999, "loss": 0.06669962406158447, "avg_return": 0.777549147605896, "regret": 0.08932209014892578, "entropy": 0.42401838302612305, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:19.734127Z", "loop": 3260, "env_steps": 2003558399, "loss": 0.0693211778998375, "avg_return": 0.7797166705131531, "regret": 0.08464816957712173, "entropy": 0.41641533374786377, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:20.587132Z", "loop": 3261, "env_steps": 2004172799, "loss": 0.06804011762142181, "avg_return": 0.781342089176178, "regret": 0.08464816957712173, "entropy": 0.4236959218978882, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:21.440415Z", "loop": 3262, "env_steps": 2004787199, "loss": 0.06826934218406677, "avg_return": 0.7763561010360718, "regret": 0.08464816957712173, "entropy": 0.4158979058265686, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:22.293592Z", "loop": 3263, "env_steps": 2005401599, "loss": 0.0665249153971672, "avg_return": 0.7773204445838928, "regret": 0.08464816957712173, "entropy": 0.413152813911438, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:23.147000Z", "loop": 3264, "env_steps": 2006015999, "loss": 0.06461837142705917, "avg_return": 0.7792428731918335, "regret": 0.08464816957712173, "entropy": 0.4132950007915497, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:23.999970Z", "loop": 3265, "env_steps": 2006630399, "loss": 0.06136750057339668, "avg_return": 0.7804272770881653, "regret": 0.08464816957712173, "entropy": 0.41105809807777405, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:24.853286Z", "loop": 3266, "env_steps": 2007244799, "loss": 0.05853891372680664, "avg_return": 0.7812161445617676, "regret": 0.08464816957712173, "entropy": 0.3953266441822052, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:25.705750Z", "loop": 3267, "env_steps": 2007859199, "loss": 0.056088872253894806, "avg_return": 0.778132438659668, "regret": 0.08464816957712173, "entropy": 0.3770604729652405, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:26.558794Z", "loop": 3268, "env_steps": 2008473599, "loss": 0.060430288314819336, "avg_return": 0.7826291918754578, "regret": 0.08464816957712173, "entropy": 0.39248940348625183, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:27.411353Z", "loop": 3269, "env_steps": 2009087999, "loss": 0.05764901638031006, "avg_return": 0.7810564637184143, "regret": 0.08464816957712173, "entropy": 0.3956620693206787, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:28.305956Z", "loop": 3270, "env_steps": 2009702399, "loss": 0.060345377773046494, "avg_return": 0.7803961038589478, "regret": 0.07885639369487762, "entropy": 0.3874431550502777, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:29.159296Z", "loop": 3271, "env_steps": 2010316799, "loss": 0.06046495586633682, "avg_return": 0.7835897207260132, "regret": 0.07885639369487762, "entropy": 0.3795068860054016, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:30.011952Z", "loop": 3272, "env_steps": 2010931199, "loss": 0.062287528067827225, "avg_return": 0.7781908512115479, "regret": 0.07885639369487762, "entropy": 0.38167405128479004, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:30.864984Z", "loop": 3273, "env_steps": 2011545599, "loss": 0.05944788455963135, "avg_return": 0.7786266207695007, "regret": 0.07885639369487762, "entropy": 0.3888428509235382, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:31.718826Z", "loop": 3274, "env_steps": 2012159999, "loss": 0.06078318879008293, "avg_return": 0.778541624546051, "regret": 0.07885639369487762, "entropy": 0.38885951042175293, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:32.571233Z", "loop": 3275, "env_steps": 2012774399, "loss": 0.06533399224281311, "avg_return": 0.776204526424408, "regret": 0.07885639369487762, "entropy": 0.4063621163368225, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:33.424154Z", "loop": 3276, "env_steps": 2013388799, "loss": 0.06322184205055237, "avg_return": 0.7833167910575867, "regret": 0.07885639369487762, "entropy": 0.41658130288124084, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:34.277014Z", "loop": 3277, "env_steps": 2014003199, "loss": 0.06536605954170227, "avg_return": 0.7843104004859924, "regret": 0.07885639369487762, "entropy": 0.4197598397731781, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:35.130697Z", "loop": 3278, "env_steps": 2014617599, "loss": 0.0643681064248085, "avg_return": 0.7867736220359802, "regret": 0.07885639369487762, "entropy": 0.4191388785839081, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:35.983324Z", "loop": 3279, "env_steps": 2015231999, "loss": 0.06685812026262283, "avg_return": 0.7898152470588684, "regret": 0.07885639369487762, "entropy": 0.40791961550712585, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:36.878202Z", "loop": 3280, "env_steps": 2015846399, "loss": 0.06268253177404404, "avg_return": 0.7926546335220337, "regret": 0.07059357315301895, "entropy": 0.39785802364349365, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:37.731732Z", "loop": 3281, "env_steps": 2016460799, "loss": 0.06814203411340714, "avg_return": 0.7927001714706421, "regret": 0.07059357315301895, "entropy": 0.3990558087825775, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:38.585604Z", "loop": 3282, "env_steps": 2017075199, "loss": 0.06795864552259445, "avg_return": 0.7858684062957764, "regret": 0.07059357315301895, "entropy": 0.4098181426525116, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:39.438987Z", "loop": 3283, "env_steps": 2017689599, "loss": 0.06636054813861847, "avg_return": 0.7856528162956238, "regret": 0.07059357315301895, "entropy": 0.4048300087451935, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:40.291963Z", "loop": 3284, "env_steps": 2018303999, "loss": 0.06617028266191483, "avg_return": 0.7929357290267944, "regret": 0.07059357315301895, "entropy": 0.40867316722869873, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:41.144362Z", "loop": 3285, "env_steps": 2018918399, "loss": 0.06320276111364365, "avg_return": 0.7878589630126953, "regret": 0.07059357315301895, "entropy": 0.382951021194458, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:41.998318Z", "loop": 3286, "env_steps": 2019532799, "loss": 0.06418605148792267, "avg_return": 0.7828236222267151, "regret": 0.07059357315301895, "entropy": 0.3939052224159241, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:42.851614Z", "loop": 3287, "env_steps": 2020147199, "loss": 0.062009017914533615, "avg_return": 0.7772839069366455, "regret": 0.07059357315301895, "entropy": 0.3956027328968048, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:43.704276Z", "loop": 3288, "env_steps": 2020761599, "loss": 0.060947299003601074, "avg_return": 0.7835828065872192, "regret": 0.07059357315301895, "entropy": 0.39402684569358826, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:44.557401Z", "loop": 3289, "env_steps": 2021375999, "loss": 0.06250598281621933, "avg_return": 0.7898809313774109, "regret": 0.07059357315301895, "entropy": 0.3888707458972931, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:45.454693Z", "loop": 3290, "env_steps": 2021990399, "loss": 0.060496985912323, "avg_return": 0.7937795519828796, "regret": 0.06676443666219711, "entropy": 0.3814636468887329, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:46.308558Z", "loop": 3291, "env_steps": 2022604799, "loss": 0.06107183173298836, "avg_return": 0.798563539981842, "regret": 0.06676443666219711, "entropy": 0.3548782169818878, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:47.162731Z", "loop": 3292, "env_steps": 2023219199, "loss": 0.061390478163957596, "avg_return": 0.7977680563926697, "regret": 0.06676443666219711, "entropy": 0.35687950253486633, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:48.015933Z", "loop": 3293, "env_steps": 2023833599, "loss": 0.06057722121477127, "avg_return": 0.7972753047943115, "regret": 0.06676443666219711, "entropy": 0.34794554114341736, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:48.869953Z", "loop": 3294, "env_steps": 2024447999, "loss": 0.06022268161177635, "avg_return": 0.7968069911003113, "regret": 0.06676443666219711, "entropy": 0.3522495627403259, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:49.725056Z", "loop": 3295, "env_steps": 2025062399, "loss": 0.060519516468048096, "avg_return": 0.79800945520401, "regret": 0.06676443666219711, "entropy": 0.36029404401779175, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:50.578902Z", "loop": 3296, "env_steps": 2025676799, "loss": 0.06074002385139465, "avg_return": 0.8001818060874939, "regret": 0.06676443666219711, "entropy": 0.3651290237903595, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:51.431884Z", "loop": 3297, "env_steps": 2026291199, "loss": 0.060826148837804794, "avg_return": 0.800018310546875, "regret": 0.06676443666219711, "entropy": 0.3690394461154938, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:52.286023Z", "loop": 3298, "env_steps": 2026905599, "loss": 0.05874994024634361, "avg_return": 0.799617350101471, "regret": 0.06676443666219711, "entropy": 0.3599233031272888, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:53.140570Z", "loop": 3299, "env_steps": 2027519999, "loss": 0.057182300835847855, "avg_return": 0.8030635118484497, "regret": 0.06676443666219711, "entropy": 0.3423687219619751, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:54.036870Z", "loop": 3300, "env_steps": 2028134399, "loss": 0.06248128041625023, "avg_return": 0.8008263111114502, "regret": 0.061738040298223495, "entropy": 0.36142197251319885, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:54.890619Z", "loop": 3301, "env_steps": 2028748799, "loss": 0.05752649903297424, "avg_return": 0.8005854487419128, "regret": 0.061738040298223495, "entropy": 0.34602078795433044, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:55.743430Z", "loop": 3302, "env_steps": 2029363199, "loss": 0.05907774716615677, "avg_return": 0.8005493879318237, "regret": 0.061738040298223495, "entropy": 0.3476268947124481, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:56.597325Z", "loop": 3303, "env_steps": 2029977599, "loss": 0.059863943606615067, "avg_return": 0.8014890551567078, "regret": 0.061738040298223495, "entropy": 0.3516296148300171, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:57.451550Z", "loop": 3304, "env_steps": 2030591999, "loss": 0.06344252079725266, "avg_return": 0.8001608848571777, "regret": 0.061738040298223495, "entropy": 0.368318647146225, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:58.305430Z", "loop": 3305, "env_steps": 2031206399, "loss": 0.05904802307486534, "avg_return": 0.7971299290657043, "regret": 0.061738040298223495, "entropy": 0.35894501209259033, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:10:59.159014Z", "loop": 3306, "env_steps": 2031820799, "loss": 0.05946960672736168, "avg_return": 0.802265465259552, "regret": 0.061738040298223495, "entropy": 0.35833004117012024, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:00.012329Z", "loop": 3307, "env_steps": 2032435199, "loss": 0.060195714235305786, "avg_return": 0.8046143651008606, "regret": 0.061738040298223495, "entropy": 0.3370282053947449, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:00.865298Z", "loop": 3308, "env_steps": 2033049599, "loss": 0.057251907885074615, "avg_return": 0.7983107566833496, "regret": 0.061738040298223495, "entropy": 0.34447118639945984, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:01.719608Z", "loop": 3309, "env_steps": 2033663999, "loss": 0.05946815013885498, "avg_return": 0.7992489337921143, "regret": 0.061738040298223495, "entropy": 0.3479611873626709, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:02.615726Z", "loop": 3310, "env_steps": 2034278399, "loss": 0.06045309454202652, "avg_return": 0.804906964302063, "regret": 0.056325674057006836, "entropy": 0.35751020908355713, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:03.468191Z", "loop": 3311, "env_steps": 2034892799, "loss": 0.06240445375442505, "avg_return": 0.8017501831054688, "regret": 0.056325674057006836, "entropy": 0.3792278468608856, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:04.320826Z", "loop": 3312, "env_steps": 2035507199, "loss": 0.05732575058937073, "avg_return": 0.7953794598579407, "regret": 0.056325674057006836, "entropy": 0.37858226895332336, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:05.175534Z", "loop": 3313, "env_steps": 2036121599, "loss": 0.06248752027750015, "avg_return": 0.8025894165039062, "regret": 0.056325674057006836, "entropy": 0.376253604888916, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:06.029248Z", "loop": 3314, "env_steps": 2036735999, "loss": 0.06438226252794266, "avg_return": 0.8106867671012878, "regret": 0.056325674057006836, "entropy": 0.36241233348846436, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:06.883428Z", "loop": 3315, "env_steps": 2037350399, "loss": 0.06180717423558235, "avg_return": 0.8061183094978333, "regret": 0.056325674057006836, "entropy": 0.3451829254627228, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:07.737948Z", "loop": 3316, "env_steps": 2037964799, "loss": 0.05987843498587608, "avg_return": 0.8043462038040161, "regret": 0.056325674057006836, "entropy": 0.3437541425228119, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:08.593575Z", "loop": 3317, "env_steps": 2038579199, "loss": 0.060028303414583206, "avg_return": 0.8052891492843628, "regret": 0.056325674057006836, "entropy": 0.3459015190601349, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:09.448120Z", "loop": 3318, "env_steps": 2039193599, "loss": 0.05974068120121956, "avg_return": 0.8015541434288025, "regret": 0.056325674057006836, "entropy": 0.34883564710617065, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:10.302121Z", "loop": 3319, "env_steps": 2039807999, "loss": 0.060813140124082565, "avg_return": 0.8012649416923523, "regret": 0.056325674057006836, "entropy": 0.3464290201663971, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:11.199426Z", "loop": 3320, "env_steps": 2040422399, "loss": 0.06014992669224739, "avg_return": 0.8078487515449524, "regret": 0.055211666971445084, "entropy": 0.35650634765625, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:12.053501Z", "loop": 3321, "env_steps": 2041036799, "loss": 0.05911881849169731, "avg_return": 0.8078755140304565, "regret": 0.055211666971445084, "entropy": 0.34995609521865845, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:12.907124Z", "loop": 3322, "env_steps": 2041651199, "loss": 0.05733697488903999, "avg_return": 0.8044518232345581, "regret": 0.055211666971445084, "entropy": 0.34848955273628235, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:13.760369Z", "loop": 3323, "env_steps": 2042265599, "loss": 0.0577213354408741, "avg_return": 0.8043394088745117, "regret": 0.055211666971445084, "entropy": 0.35641443729400635, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:14.613560Z", "loop": 3324, "env_steps": 2042879999, "loss": 0.05789307504892349, "avg_return": 0.7943342924118042, "regret": 0.055211666971445084, "entropy": 0.3634237051010132, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:15.466701Z", "loop": 3325, "env_steps": 2043494399, "loss": 0.056502629071474075, "avg_return": 0.8007057905197144, "regret": 0.055211666971445084, "entropy": 0.3517082929611206, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:16.319726Z", "loop": 3326, "env_steps": 2044108799, "loss": 0.058955248445272446, "avg_return": 0.8107576966285706, "regret": 0.055211666971445084, "entropy": 0.3514411747455597, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:17.172609Z", "loop": 3327, "env_steps": 2044723199, "loss": 0.05838499590754509, "avg_return": 0.8126640915870667, "regret": 0.055211666971445084, "entropy": 0.3393441140651703, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:18.025447Z", "loop": 3328, "env_steps": 2045337599, "loss": 0.06051882728934288, "avg_return": 0.8087937831878662, "regret": 0.055211666971445084, "entropy": 0.3406918942928314, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:18.879014Z", "loop": 3329, "env_steps": 2045951999, "loss": 0.05957130715250969, "avg_return": 0.8090834021568298, "regret": 0.055211666971445084, "entropy": 0.3408634066581726, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:19.774555Z", "loop": 3330, "env_steps": 2046566399, "loss": 0.05893056467175484, "avg_return": 0.8063643574714661, "regret": 0.055933915078639984, "entropy": 0.34241777658462524, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:20.628095Z", "loop": 3331, "env_steps": 2047180799, "loss": 0.06272458285093307, "avg_return": 0.8080704808235168, "regret": 0.055933915078639984, "entropy": 0.35406413674354553, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:21.483002Z", "loop": 3332, "env_steps": 2047795199, "loss": 0.06245309114456177, "avg_return": 0.8094714283943176, "regret": 0.055933915078639984, "entropy": 0.3560376763343811, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:22.336764Z", "loop": 3333, "env_steps": 2048409599, "loss": 0.06465475261211395, "avg_return": 0.8166024088859558, "regret": 0.055933915078639984, "entropy": 0.36365973949432373, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:23.189985Z", "loop": 3334, "env_steps": 2049023999, "loss": 0.06004749611020088, "avg_return": 0.8112720847129822, "regret": 0.055933915078639984, "entropy": 0.3560132086277008, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:24.044189Z", "loop": 3335, "env_steps": 2049638399, "loss": 0.06018267199397087, "avg_return": 0.8095841407775879, "regret": 0.055933915078639984, "entropy": 0.3654078245162964, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:24.900015Z", "loop": 3336, "env_steps": 2050252799, "loss": 0.058107949793338776, "avg_return": 0.808007538318634, "regret": 0.055933915078639984, "entropy": 0.35702306032180786, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:25.753664Z", "loop": 3337, "env_steps": 2050867199, "loss": 0.060184407979249954, "avg_return": 0.8089209198951721, "regret": 0.055933915078639984, "entropy": 0.3594943583011627, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:26.606722Z", "loop": 3338, "env_steps": 2051481599, "loss": 0.062431700527668, "avg_return": 0.8144049048423767, "regret": 0.055933915078639984, "entropy": 0.360295832157135, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:27.460474Z", "loop": 3339, "env_steps": 2052095999, "loss": 0.06334903836250305, "avg_return": 0.8171187043190002, "regret": 0.055933915078639984, "entropy": 0.3641582727432251, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:28.356767Z", "loop": 3340, "env_steps": 2052710399, "loss": 0.06320445984601974, "avg_return": 0.812428891658783, "regret": 0.049015697091817856, "entropy": 0.36071881651878357, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:29.209615Z", "loop": 3341, "env_steps": 2053324799, "loss": 0.06056791543960571, "avg_return": 0.8106650114059448, "regret": 0.049015697091817856, "entropy": 0.3508675992488861, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:30.062730Z", "loop": 3342, "env_steps": 2053939199, "loss": 0.061155226081609726, "avg_return": 0.8121509552001953, "regret": 0.049015697091817856, "entropy": 0.33790063858032227, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:30.916612Z", "loop": 3343, "env_steps": 2054553599, "loss": 0.05825546383857727, "avg_return": 0.8104482293128967, "regret": 0.049015697091817856, "entropy": 0.32545894384384155, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:31.770725Z", "loop": 3344, "env_steps": 2055167999, "loss": 0.05715779587626457, "avg_return": 0.8137530088424683, "regret": 0.049015697091817856, "entropy": 0.32086190581321716, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:32.623572Z", "loop": 3345, "env_steps": 2055782399, "loss": 0.05758677050471306, "avg_return": 0.8148196339607239, "regret": 0.049015697091817856, "entropy": 0.32604673504829407, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:33.476846Z", "loop": 3346, "env_steps": 2056396799, "loss": 0.05610555037856102, "avg_return": 0.8150651454925537, "regret": 0.049015697091817856, "entropy": 0.3286752998828888, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:34.329430Z", "loop": 3347, "env_steps": 2057011199, "loss": 0.05778467282652855, "avg_return": 0.8166802525520325, "regret": 0.049015697091817856, "entropy": 0.3402579724788666, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:35.183198Z", "loop": 3348, "env_steps": 2057625599, "loss": 0.05716270953416824, "avg_return": 0.8151560425758362, "regret": 0.049015697091817856, "entropy": 0.339630663394928, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:36.036104Z", "loop": 3349, "env_steps": 2058239999, "loss": 0.0559181347489357, "avg_return": 0.8169542551040649, "regret": 0.049015697091817856, "entropy": 0.32899507880210876, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:36.929796Z", "loop": 3350, "env_steps": 2058854399, "loss": 0.05714242532849312, "avg_return": 0.816849410533905, "regret": 0.04388173669576645, "entropy": 0.32528093457221985, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:37.782974Z", "loop": 3351, "env_steps": 2059468799, "loss": 0.053620900958776474, "avg_return": 0.8196136951446533, "regret": 0.04388173669576645, "entropy": 0.3156927525997162, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:38.637022Z", "loop": 3352, "env_steps": 2060083199, "loss": 0.055198926478624344, "avg_return": 0.8198087215423584, "regret": 0.04388173669576645, "entropy": 0.30847689509391785, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:39.491302Z", "loop": 3353, "env_steps": 2060697599, "loss": 0.057168882340192795, "avg_return": 0.8211957812309265, "regret": 0.04388173669576645, "entropy": 0.30974042415618896, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:40.346833Z", "loop": 3354, "env_steps": 2061311999, "loss": 0.05659906193614006, "avg_return": 0.8186088800430298, "regret": 0.04388173669576645, "entropy": 0.3162643313407898, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:41.202105Z", "loop": 3355, "env_steps": 2061926399, "loss": 0.052377182990312576, "avg_return": 0.8180372714996338, "regret": 0.04388173669576645, "entropy": 0.3054969310760498, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:42.055059Z", "loop": 3356, "env_steps": 2062540799, "loss": 0.05609351024031639, "avg_return": 0.8200947046279907, "regret": 0.04388173669576645, "entropy": 0.32375919818878174, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:42.907152Z", "loop": 3357, "env_steps": 2063155199, "loss": 0.05410673841834068, "avg_return": 0.8220908045768738, "regret": 0.04388173669576645, "entropy": 0.31020888686180115, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:43.760224Z", "loop": 3358, "env_steps": 2063769599, "loss": 0.05478004366159439, "avg_return": 0.8199198246002197, "regret": 0.04388173669576645, "entropy": 0.32478052377700806, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:44.614091Z", "loop": 3359, "env_steps": 2064383999, "loss": 0.058205317705869675, "avg_return": 0.8199114203453064, "regret": 0.04388173669576645, "entropy": 0.3259332478046417, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:45.510787Z", "loop": 3360, "env_steps": 2064998399, "loss": 0.05635688453912735, "avg_return": 0.8206072449684143, "regret": 0.04224422574043274, "entropy": 0.33169952034950256, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:46.363279Z", "loop": 3361, "env_steps": 2065612799, "loss": 0.05591951683163643, "avg_return": 0.8196257948875427, "regret": 0.04224422574043274, "entropy": 0.3115154802799225, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:47.216160Z", "loop": 3362, "env_steps": 2066227199, "loss": 0.05669662356376648, "avg_return": 0.8195620179176331, "regret": 0.04224422574043274, "entropy": 0.3217219114303589, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:48.070057Z", "loop": 3363, "env_steps": 2066841599, "loss": 0.05815892294049263, "avg_return": 0.8196243643760681, "regret": 0.04224422574043274, "entropy": 0.32974326610565186, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:48.923292Z", "loop": 3364, "env_steps": 2067455999, "loss": 0.057218100875616074, "avg_return": 0.8200668692588806, "regret": 0.04224422574043274, "entropy": 0.3300172984600067, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:49.775906Z", "loop": 3365, "env_steps": 2068070399, "loss": 0.05845223739743233, "avg_return": 0.8216573596000671, "regret": 0.04224422574043274, "entropy": 0.335383802652359, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:50.628772Z", "loop": 3366, "env_steps": 2068684799, "loss": 0.05694477632641792, "avg_return": 0.8226081728935242, "regret": 0.04224422574043274, "entropy": 0.3239302635192871, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:51.482541Z", "loop": 3367, "env_steps": 2069299199, "loss": 0.05644523724913597, "avg_return": 0.8214766383171082, "regret": 0.04224422574043274, "entropy": 0.32210829854011536, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:52.335742Z", "loop": 3368, "env_steps": 2069913599, "loss": 0.059154149144887924, "avg_return": 0.8212844133377075, "regret": 0.04224422574043274, "entropy": 0.3304794728755951, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:53.188342Z", "loop": 3369, "env_steps": 2070527999, "loss": 0.05963311716914177, "avg_return": 0.8195780515670776, "regret": 0.04224422574043274, "entropy": 0.3277243375778198, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:54.082415Z", "loop": 3370, "env_steps": 2071142399, "loss": 0.055717695504426956, "avg_return": 0.8222727179527283, "regret": 0.04128770902752876, "entropy": 0.31339317560195923, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:54.936459Z", "loop": 3371, "env_steps": 2071756799, "loss": 0.05675491690635681, "avg_return": 0.8230395913124084, "regret": 0.04128770902752876, "entropy": 0.3141418695449829, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:55.790456Z", "loop": 3372, "env_steps": 2072371199, "loss": 0.05628785118460655, "avg_return": 0.8241655826568604, "regret": 0.04128770902752876, "entropy": 0.32785576581954956, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:56.643641Z", "loop": 3373, "env_steps": 2072985599, "loss": 0.057999469339847565, "avg_return": 0.8235504627227783, "regret": 0.04128770902752876, "entropy": 0.33406391739845276, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:57.498102Z", "loop": 3374, "env_steps": 2073599999, "loss": 0.05386635661125183, "avg_return": 0.8203273415565491, "regret": 0.04128770902752876, "entropy": 0.3259604275226593, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:58.352112Z", "loop": 3375, "env_steps": 2074214399, "loss": 0.05719770863652229, "avg_return": 0.8192741870880127, "regret": 0.04128770902752876, "entropy": 0.33736294507980347, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:11:59.205645Z", "loop": 3376, "env_steps": 2074828799, "loss": 0.05375568941235542, "avg_return": 0.8213937878608704, "regret": 0.04128770902752876, "entropy": 0.3215709328651428, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:00.059270Z", "loop": 3377, "env_steps": 2075443199, "loss": 0.05292137339711189, "avg_return": 0.8269226551055908, "regret": 0.04128770902752876, "entropy": 0.30844441056251526, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:00.912978Z", "loop": 3378, "env_steps": 2076057599, "loss": 0.05256984755396843, "avg_return": 0.827777624130249, "regret": 0.04128770902752876, "entropy": 0.3003275990486145, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:01.767879Z", "loop": 3379, "env_steps": 2076671999, "loss": 0.05112912133336067, "avg_return": 0.8246867060661316, "regret": 0.04128770902752876, "entropy": 0.28820309042930603, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:02.663807Z", "loop": 3380, "env_steps": 2077286399, "loss": 0.05263699218630791, "avg_return": 0.8257759809494019, "regret": 0.03946429491043091, "entropy": 0.2927950322628021, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:03.518605Z", "loop": 3381, "env_steps": 2077900799, "loss": 0.05418376997113228, "avg_return": 0.8257978558540344, "regret": 0.03946429491043091, "entropy": 0.30839288234710693, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:04.373477Z", "loop": 3382, "env_steps": 2078515199, "loss": 0.05239881947636604, "avg_return": 0.8269017338752747, "regret": 0.03946429491043091, "entropy": 0.2952125668525696, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:05.227989Z", "loop": 3383, "env_steps": 2079129599, "loss": 0.05179641768336296, "avg_return": 0.824043869972229, "regret": 0.03946429491043091, "entropy": 0.30892959237098694, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:06.082071Z", "loop": 3384, "env_steps": 2079743999, "loss": 0.05220678448677063, "avg_return": 0.8240956664085388, "regret": 0.03946429491043091, "entropy": 0.3062584698200226, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:06.937201Z", "loop": 3385, "env_steps": 2080358399, "loss": 0.05356214568018913, "avg_return": 0.8223541378974915, "regret": 0.03946429491043091, "entropy": 0.30356866121292114, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:07.792338Z", "loop": 3386, "env_steps": 2080972799, "loss": 0.05203249678015709, "avg_return": 0.8231392502784729, "regret": 0.03946429491043091, "entropy": 0.30445483326911926, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:08.646345Z", "loop": 3387, "env_steps": 2081587199, "loss": 0.05330443009734154, "avg_return": 0.8269684314727783, "regret": 0.03946429491043091, "entropy": 0.30464300513267517, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:09.499527Z", "loop": 3388, "env_steps": 2082201599, "loss": 0.05273410677909851, "avg_return": 0.825630247592926, "regret": 0.03946429491043091, "entropy": 0.2987244427204132, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:10.352624Z", "loop": 3389, "env_steps": 2082815999, "loss": 0.05225960537791252, "avg_return": 0.8289556503295898, "regret": 0.03946429491043091, "entropy": 0.2968805134296417, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:11.249404Z", "loop": 3390, "env_steps": 2083430399, "loss": 0.05403422191739082, "avg_return": 0.8288857340812683, "regret": 0.036207977682352066, "entropy": 0.3086317181587219, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:12.103519Z", "loop": 3391, "env_steps": 2084044799, "loss": 0.0513414703309536, "avg_return": 0.8285407423973083, "regret": 0.036207977682352066, "entropy": 0.28763753175735474, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:12.957262Z", "loop": 3392, "env_steps": 2084659199, "loss": 0.054282136261463165, "avg_return": 0.8255172967910767, "regret": 0.036207977682352066, "entropy": 0.29803887009620667, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:13.810925Z", "loop": 3393, "env_steps": 2085273599, "loss": 0.05267822742462158, "avg_return": 0.8261680006980896, "regret": 0.036207977682352066, "entropy": 0.3005310893058777, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:14.664995Z", "loop": 3394, "env_steps": 2085887999, "loss": 0.05313372611999512, "avg_return": 0.8252389430999756, "regret": 0.036207977682352066, "entropy": 0.29783135652542114, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:15.519069Z", "loop": 3395, "env_steps": 2086502399, "loss": 0.05253801494836807, "avg_return": 0.8251939415931702, "regret": 0.036207977682352066, "entropy": 0.30909496545791626, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:16.372272Z", "loop": 3396, "env_steps": 2087116799, "loss": 0.05369991809129715, "avg_return": 0.8252997398376465, "regret": 0.036207977682352066, "entropy": 0.3043062388896942, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:17.224855Z", "loop": 3397, "env_steps": 2087731199, "loss": 0.05327460169792175, "avg_return": 0.8256494402885437, "regret": 0.036207977682352066, "entropy": 0.31246334314346313, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:18.077981Z", "loop": 3398, "env_steps": 2088345599, "loss": 0.05255066230893135, "avg_return": 0.828053891658783, "regret": 0.036207977682352066, "entropy": 0.3011057376861572, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:18.931913Z", "loop": 3399, "env_steps": 2088959999, "loss": 0.051412779837846756, "avg_return": 0.8270151019096375, "regret": 0.036207977682352066, "entropy": 0.28894728422164917, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:19.825969Z", "loop": 3400, "env_steps": 2089574399, "loss": 0.048465535044670105, "avg_return": 0.8239510655403137, "regret": 0.03902669623494148, "entropy": 0.28533974289894104, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:20.678847Z", "loop": 3401, "env_steps": 2090188799, "loss": 0.05298734828829765, "avg_return": 0.8253679871559143, "regret": 0.03902669623494148, "entropy": 0.2917807996273041, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:21.532572Z", "loop": 3402, "env_steps": 2090803199, "loss": 0.049560412764549255, "avg_return": 0.8295912742614746, "regret": 0.03902669623494148, "entropy": 0.2867690920829773, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:22.387516Z", "loop": 3403, "env_steps": 2091417599, "loss": 0.05657970905303955, "avg_return": 0.8272666335105896, "regret": 0.03902669623494148, "entropy": 0.3211533725261688, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:23.242747Z", "loop": 3404, "env_steps": 2092031999, "loss": 0.05284266546368599, "avg_return": 0.8253175020217896, "regret": 0.03902669623494148, "entropy": 0.30947867035865784, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:24.096728Z", "loop": 3405, "env_steps": 2092646399, "loss": 0.055112093687057495, "avg_return": 0.8289021253585815, "regret": 0.03902669623494148, "entropy": 0.31586140394210815, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:24.950501Z", "loop": 3406, "env_steps": 2093260799, "loss": 0.0551106221973896, "avg_return": 0.8293966054916382, "regret": 0.03902669623494148, "entropy": 0.30951178073883057, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:25.805067Z", "loop": 3407, "env_steps": 2093875199, "loss": 0.05195777490735054, "avg_return": 0.829656720161438, "regret": 0.03902669623494148, "entropy": 0.29636481404304504, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:26.660365Z", "loop": 3408, "env_steps": 2094489599, "loss": 0.05165693908929825, "avg_return": 0.8244165182113647, "regret": 0.03902669623494148, "entropy": 0.29184114933013916, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:27.513199Z", "loop": 3409, "env_steps": 2095103999, "loss": 0.0523797944188118, "avg_return": 0.8231894969940186, "regret": 0.03902669623494148, "entropy": 0.29452210664749146, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:28.407798Z", "loop": 3410, "env_steps": 2095718399, "loss": 0.05214967951178551, "avg_return": 0.8214990496635437, "regret": 0.03906489536166191, "entropy": 0.2973982095718384, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:29.261715Z", "loop": 3411, "env_steps": 2096332799, "loss": 0.05213524028658867, "avg_return": 0.826235294342041, "regret": 0.03906489536166191, "entropy": 0.29859501123428345, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:30.115833Z", "loop": 3412, "env_steps": 2096947199, "loss": 0.0512576662003994, "avg_return": 0.830182671546936, "regret": 0.03906489536166191, "entropy": 0.2916446924209595, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:30.969505Z", "loop": 3413, "env_steps": 2097561599, "loss": 0.05109001323580742, "avg_return": 0.8299022912979126, "regret": 0.03906489536166191, "entropy": 0.29680687189102173, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:31.824058Z", "loop": 3414, "env_steps": 2098175999, "loss": 0.05497347190976143, "avg_return": 0.8262484073638916, "regret": 0.03906489536166191, "entropy": 0.3021980822086334, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:32.677609Z", "loop": 3415, "env_steps": 2098790399, "loss": 0.05392978712916374, "avg_return": 0.8216538429260254, "regret": 0.03906489536166191, "entropy": 0.31120866537094116, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:33.530720Z", "loop": 3416, "env_steps": 2099404799, "loss": 0.0543086938560009, "avg_return": 0.8166594505310059, "regret": 0.03906489536166191, "entropy": 0.30432483553886414, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:34.385412Z", "loop": 3417, "env_steps": 2100019199, "loss": 0.05431770905852318, "avg_return": 0.8188347816467285, "regret": 0.03906489536166191, "entropy": 0.295439213514328, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:35.240284Z", "loop": 3418, "env_steps": 2100633599, "loss": 0.05453045293688774, "avg_return": 0.8268581628799438, "regret": 0.03906489536166191, "entropy": 0.2996772229671478, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:36.094220Z", "loop": 3419, "env_steps": 2101247999, "loss": 0.053406793624162674, "avg_return": 0.8303072452545166, "regret": 0.03906489536166191, "entropy": 0.29346251487731934, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:36.988358Z", "loop": 3420, "env_steps": 2101862399, "loss": 0.04945210739970207, "avg_return": 0.8314879536628723, "regret": 0.03099149279296398, "entropy": 0.2813356816768646, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:37.843161Z", "loop": 3421, "env_steps": 2102476799, "loss": 0.048829372972249985, "avg_return": 0.8276616930961609, "regret": 0.03099149279296398, "entropy": 0.27905794978141785, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:38.697570Z", "loop": 3422, "env_steps": 2103091199, "loss": 0.05293257161974907, "avg_return": 0.8177160024642944, "regret": 0.03099149279296398, "entropy": 0.3006410300731659, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:39.552515Z", "loop": 3423, "env_steps": 2103705599, "loss": 0.05034829303622246, "avg_return": 0.8149027824401855, "regret": 0.03099149279296398, "entropy": 0.29556789994239807, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:40.406271Z", "loop": 3424, "env_steps": 2104319999, "loss": 0.049705784767866135, "avg_return": 0.8199324011802673, "regret": 0.03099149279296398, "entropy": 0.2831506133079529, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:41.259914Z", "loop": 3425, "env_steps": 2104934399, "loss": 0.05021841451525688, "avg_return": 0.8288239240646362, "regret": 0.03099149279296398, "entropy": 0.28981873393058777, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:42.114699Z", "loop": 3426, "env_steps": 2105548799, "loss": 0.050824571400880814, "avg_return": 0.8341823220252991, "regret": 0.03099149279296398, "entropy": 0.28836652636528015, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:42.968435Z", "loop": 3427, "env_steps": 2106163199, "loss": 0.05193847045302391, "avg_return": 0.8335365056991577, "regret": 0.03099149279296398, "entropy": 0.2909791171550751, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:43.822814Z", "loop": 3428, "env_steps": 2106777599, "loss": 0.05167558789253235, "avg_return": 0.8327139616012573, "regret": 0.03099149279296398, "entropy": 0.27701812982559204, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:44.677023Z", "loop": 3429, "env_steps": 2107391999, "loss": 0.05228383466601372, "avg_return": 0.8281243443489075, "regret": 0.03099149279296398, "entropy": 0.2816736698150635, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:45.573454Z", "loop": 3430, "env_steps": 2108006399, "loss": 0.05041422322392464, "avg_return": 0.8265763521194458, "regret": 0.0372297540307045, "entropy": 0.2753523588180542, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:46.427278Z", "loop": 3431, "env_steps": 2108620799, "loss": 0.04897706210613251, "avg_return": 0.8243962526321411, "regret": 0.0372297540307045, "entropy": 0.2823825776576996, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:47.281745Z", "loop": 3432, "env_steps": 2109235199, "loss": 0.05045662075281143, "avg_return": 0.8286694884300232, "regret": 0.0372297540307045, "entropy": 0.2780790328979492, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:48.134407Z", "loop": 3433, "env_steps": 2109849599, "loss": 0.051932673901319504, "avg_return": 0.8313002586364746, "regret": 0.0372297540307045, "entropy": 0.2884347438812256, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:48.987717Z", "loop": 3434, "env_steps": 2110463999, "loss": 0.04987424239516258, "avg_return": 0.8320589065551758, "regret": 0.0372297540307045, "entropy": 0.2787419557571411, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:49.841141Z", "loop": 3435, "env_steps": 2111078399, "loss": 0.050523169338703156, "avg_return": 0.834403395652771, "regret": 0.0372297540307045, "entropy": 0.2819826900959015, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:50.694846Z", "loop": 3436, "env_steps": 2111692799, "loss": 0.05019122362136841, "avg_return": 0.8328104615211487, "regret": 0.0372297540307045, "entropy": 0.289760559797287, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:51.549412Z", "loop": 3437, "env_steps": 2112307199, "loss": 0.05057940632104874, "avg_return": 0.8318473100662231, "regret": 0.0372297540307045, "entropy": 0.28374144434928894, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:52.403937Z", "loop": 3438, "env_steps": 2112921599, "loss": 0.050788670778274536, "avg_return": 0.8342774510383606, "regret": 0.0372297540307045, "entropy": 0.2881792485713959, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:53.259709Z", "loop": 3439, "env_steps": 2113535999, "loss": 0.05029008910059929, "avg_return": 0.8351758122444153, "regret": 0.0372297540307045, "entropy": 0.27777037024497986, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:54.158507Z", "loop": 3440, "env_steps": 2114150399, "loss": 0.049279868602752686, "avg_return": 0.835550844669342, "regret": 0.02639492228627205, "entropy": 0.2809433341026306, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:55.013020Z", "loop": 3441, "env_steps": 2114764799, "loss": 0.048165082931518555, "avg_return": 0.8381442427635193, "regret": 0.02639492228627205, "entropy": 0.2708258330821991, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:55.867335Z", "loop": 3442, "env_steps": 2115379199, "loss": 0.04729285463690758, "avg_return": 0.8312676548957825, "regret": 0.02639492228627205, "entropy": 0.269305944442749, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:56.721846Z", "loop": 3443, "env_steps": 2115993599, "loss": 0.04804202541708946, "avg_return": 0.8296700119972229, "regret": 0.02639492228627205, "entropy": 0.2675288915634155, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:57.575224Z", "loop": 3444, "env_steps": 2116607999, "loss": 0.04670074209570885, "avg_return": 0.8366548418998718, "regret": 0.02639492228627205, "entropy": 0.266137033700943, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:58.429172Z", "loop": 3445, "env_steps": 2117222399, "loss": 0.04755564033985138, "avg_return": 0.8365949988365173, "regret": 0.02639492228627205, "entropy": 0.26638472080230713, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:12:59.282754Z", "loop": 3446, "env_steps": 2117836799, "loss": 0.043727993965148926, "avg_return": 0.8357935547828674, "regret": 0.02639492228627205, "entropy": 0.2623986303806305, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:00.135602Z", "loop": 3447, "env_steps": 2118451199, "loss": 0.047822292894124985, "avg_return": 0.8364755511283875, "regret": 0.02639492228627205, "entropy": 0.2722419202327728, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:00.988297Z", "loop": 3448, "env_steps": 2119065599, "loss": 0.0471344068646431, "avg_return": 0.8328166007995605, "regret": 0.02639492228627205, "entropy": 0.2667279839515686, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:01.842369Z", "loop": 3449, "env_steps": 2119679999, "loss": 0.044523462653160095, "avg_return": 0.8345096111297607, "regret": 0.02639492228627205, "entropy": 0.2593608796596527, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:02.736951Z", "loop": 3450, "env_steps": 2120294399, "loss": 0.04636237397789955, "avg_return": 0.8366753458976746, "regret": 0.027813266962766647, "entropy": 0.26396065950393677, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:03.591456Z", "loop": 3451, "env_steps": 2120908799, "loss": 0.0467330701649189, "avg_return": 0.8355348110198975, "regret": 0.027813266962766647, "entropy": 0.2680360972881317, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:04.445383Z", "loop": 3452, "env_steps": 2121523199, "loss": 0.044543005526065826, "avg_return": 0.8364549279212952, "regret": 0.027813266962766647, "entropy": 0.2582709491252899, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:05.300712Z", "loop": 3453, "env_steps": 2122137599, "loss": 0.04800054803490639, "avg_return": 0.834684431552887, "regret": 0.027813266962766647, "entropy": 0.26838141679763794, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:06.155147Z", "loop": 3454, "env_steps": 2122751999, "loss": 0.04589332640171051, "avg_return": 0.835343062877655, "regret": 0.027813266962766647, "entropy": 0.26464933156967163, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:07.009153Z", "loop": 3455, "env_steps": 2123366399, "loss": 0.04871520400047302, "avg_return": 0.8367142677307129, "regret": 0.027813266962766647, "entropy": 0.27858301997184753, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:07.863367Z", "loop": 3456, "env_steps": 2123980799, "loss": 0.047194696962833405, "avg_return": 0.835281491279602, "regret": 0.027813266962766647, "entropy": 0.27153462171554565, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:08.718246Z", "loop": 3457, "env_steps": 2124595199, "loss": 0.04703345522284508, "avg_return": 0.8351995944976807, "regret": 0.027813266962766647, "entropy": 0.26676368713378906, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:09.572407Z", "loop": 3458, "env_steps": 2125209599, "loss": 0.04748442769050598, "avg_return": 0.8369125723838806, "regret": 0.027813266962766647, "entropy": 0.2753882110118866, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:10.427280Z", "loop": 3459, "env_steps": 2125823999, "loss": 0.04769020527601242, "avg_return": 0.8376350998878479, "regret": 0.027813266962766647, "entropy": 0.2688312530517578, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:11.323416Z", "loop": 3460, "env_steps": 2126438399, "loss": 0.045541416853666306, "avg_return": 0.838525652885437, "regret": 0.024744374677538872, "entropy": 0.2569986879825592, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:12.178081Z", "loop": 3461, "env_steps": 2127052799, "loss": 0.046529363840818405, "avg_return": 0.8382498025894165, "regret": 0.024744374677538872, "entropy": 0.253911554813385, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:13.032983Z", "loop": 3462, "env_steps": 2127667199, "loss": 0.04443180188536644, "avg_return": 0.8331453800201416, "regret": 0.024744374677538872, "entropy": 0.2492283284664154, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:13.886103Z", "loop": 3463, "env_steps": 2128281599, "loss": 0.046892598271369934, "avg_return": 0.8301447629928589, "regret": 0.024744374677538872, "entropy": 0.25649189949035645, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:14.739162Z", "loop": 3464, "env_steps": 2128895999, "loss": 0.0491609126329422, "avg_return": 0.8322908878326416, "regret": 0.024744374677538872, "entropy": 0.26229074597358704, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:15.592295Z", "loop": 3465, "env_steps": 2129510399, "loss": 0.04563004896044731, "avg_return": 0.837068498134613, "regret": 0.024744374677538872, "entropy": 0.25236761569976807, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:16.445281Z", "loop": 3466, "env_steps": 2130124799, "loss": 0.04570699855685234, "avg_return": 0.8384199142456055, "regret": 0.024744374677538872, "entropy": 0.2671700417995453, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:17.299299Z", "loop": 3467, "env_steps": 2130739199, "loss": 0.04679041728377342, "avg_return": 0.836032509803772, "regret": 0.024744374677538872, "entropy": 0.2674280107021332, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:18.153119Z", "loop": 3468, "env_steps": 2131353599, "loss": 0.04694516584277153, "avg_return": 0.8342083692550659, "regret": 0.024744374677538872, "entropy": 0.27667489647865295, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:19.006660Z", "loop": 3469, "env_steps": 2131967999, "loss": 0.050160665065050125, "avg_return": 0.8336784839630127, "regret": 0.024744374677538872, "entropy": 0.28302961587905884, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:19.901170Z", "loop": 3470, "env_steps": 2132582399, "loss": 0.046546753495931625, "avg_return": 0.8353561758995056, "regret": 0.02890879102051258, "entropy": 0.2736240327358246, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:20.755152Z", "loop": 3471, "env_steps": 2133196799, "loss": 0.048931755125522614, "avg_return": 0.8360350131988525, "regret": 0.02890879102051258, "entropy": 0.266591340303421, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:21.609210Z", "loop": 3472, "env_steps": 2133811199, "loss": 0.04381044581532478, "avg_return": 0.8358365893363953, "regret": 0.02890879102051258, "entropy": 0.24694155156612396, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:22.463201Z", "loop": 3473, "env_steps": 2134425599, "loss": 0.048466142266988754, "avg_return": 0.8358226418495178, "regret": 0.02890879102051258, "entropy": 0.25180837512016296, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:23.316236Z", "loop": 3474, "env_steps": 2135039999, "loss": 0.04583507403731346, "avg_return": 0.831972599029541, "regret": 0.02890879102051258, "entropy": 0.25738662481307983, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:24.169009Z", "loop": 3475, "env_steps": 2135654399, "loss": 0.04771770164370537, "avg_return": 0.8339515328407288, "regret": 0.02890879102051258, "entropy": 0.2583211660385132, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:25.023002Z", "loop": 3476, "env_steps": 2136268799, "loss": 0.045650701969861984, "avg_return": 0.8349947929382324, "regret": 0.02890879102051258, "entropy": 0.25797849893569946, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:25.876301Z", "loop": 3477, "env_steps": 2136883199, "loss": 0.04651238024234772, "avg_return": 0.8362984657287598, "regret": 0.02890879102051258, "entropy": 0.2697962820529938, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:26.728674Z", "loop": 3478, "env_steps": 2137497599, "loss": 0.04621944576501846, "avg_return": 0.8328838348388672, "regret": 0.02890879102051258, "entropy": 0.27226293087005615, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:27.582434Z", "loop": 3479, "env_steps": 2138111999, "loss": 0.04855235293507576, "avg_return": 0.8336872458457947, "regret": 0.02890879102051258, "entropy": 0.2783968150615692, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:28.476512Z", "loop": 3480, "env_steps": 2138726399, "loss": 0.04623400792479515, "avg_return": 0.837073564529419, "regret": 0.025628212839365005, "entropy": 0.2584725320339203, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:29.330141Z", "loop": 3481, "env_steps": 2139340799, "loss": 0.04482864961028099, "avg_return": 0.8395867347717285, "regret": 0.025628212839365005, "entropy": 0.2513442635536194, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:30.184326Z", "loop": 3482, "env_steps": 2139955199, "loss": 0.044389694929122925, "avg_return": 0.8378815650939941, "regret": 0.025628212839365005, "entropy": 0.23702216148376465, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:31.037871Z", "loop": 3483, "env_steps": 2140569599, "loss": 0.043912190943956375, "avg_return": 0.8339357972145081, "regret": 0.025628212839365005, "entropy": 0.23008301854133606, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:31.891185Z", "loop": 3484, "env_steps": 2141183999, "loss": 0.04352567717432976, "avg_return": 0.8302900791168213, "regret": 0.025628212839365005, "entropy": 0.23629212379455566, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:32.745322Z", "loop": 3485, "env_steps": 2141798399, "loss": 0.04674017056822777, "avg_return": 0.8338095545768738, "regret": 0.025628212839365005, "entropy": 0.23855841159820557, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:33.598834Z", "loop": 3486, "env_steps": 2142412799, "loss": 0.042799439281225204, "avg_return": 0.8397780060768127, "regret": 0.025628212839365005, "entropy": 0.23285304009914398, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:34.453149Z", "loop": 3487, "env_steps": 2143027199, "loss": 0.04330594092607498, "avg_return": 0.8416914939880371, "regret": 0.025628212839365005, "entropy": 0.2532213628292084, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:35.307480Z", "loop": 3488, "env_steps": 2143641599, "loss": 0.04637530818581581, "avg_return": 0.8395292162895203, "regret": 0.025628212839365005, "entropy": 0.26122865080833435, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:36.161707Z", "loop": 3489, "env_steps": 2144255999, "loss": 0.04646872729063034, "avg_return": 0.8335733413696289, "regret": 0.025628212839365005, "entropy": 0.27058330178260803, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:37.056626Z", "loop": 3490, "env_steps": 2144870399, "loss": 0.045588985085487366, "avg_return": 0.8348576426506042, "regret": 0.02790442667901516, "entropy": 0.26801931858062744, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:37.910285Z", "loop": 3491, "env_steps": 2145484799, "loss": 0.04662066325545311, "avg_return": 0.8405751585960388, "regret": 0.02790442667901516, "entropy": 0.2598642408847809, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:38.764229Z", "loop": 3492, "env_steps": 2146099199, "loss": 0.044567715376615524, "avg_return": 0.8398534059524536, "regret": 0.02790442667901516, "entropy": 0.2455742359161377, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:39.617095Z", "loop": 3493, "env_steps": 2146713599, "loss": 0.04676014930009842, "avg_return": 0.8363356590270996, "regret": 0.02790442667901516, "entropy": 0.24762298166751862, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:40.471230Z", "loop": 3494, "env_steps": 2147327999, "loss": 0.048267289996147156, "avg_return": 0.8333573341369629, "regret": 0.02790442667901516, "entropy": 0.24788333475589752, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:41.324571Z", "loop": 3495, "env_steps": 2147942399, "loss": 0.04697362333536148, "avg_return": 0.8308550715446472, "regret": 0.02790442667901516, "entropy": 0.24392856657505035, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:42.178562Z", "loop": 3496, "env_steps": 2148556799, "loss": 0.04497937858104706, "avg_return": 0.8330146074295044, "regret": 0.02790442667901516, "entropy": 0.24192392826080322, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:43.032364Z", "loop": 3497, "env_steps": 2149171199, "loss": 0.043021004647016525, "avg_return": 0.8340949416160583, "regret": 0.02790442667901516, "entropy": 0.2397291362285614, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:43.886501Z", "loop": 3498, "env_steps": 2149785599, "loss": 0.048123549669981, "avg_return": 0.8304073810577393, "regret": 0.02790442667901516, "entropy": 0.2739753723144531, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:44.739816Z", "loop": 3499, "env_steps": 2150399999, "loss": 0.047439612448215485, "avg_return": 0.8270857930183411, "regret": 0.02790442667901516, "entropy": 0.279986709356308, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:45.634529Z", "loop": 3500, "env_steps": 2151014399, "loss": 0.04795598238706589, "avg_return": 0.8316788673400879, "regret": 0.03052169643342495, "entropy": 0.2756478786468506, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:46.487256Z", "loop": 3501, "env_steps": 2151628799, "loss": 0.04627857729792595, "avg_return": 0.8360266089439392, "regret": 0.03052169643342495, "entropy": 0.272028386592865, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:47.340650Z", "loop": 3502, "env_steps": 2152243199, "loss": 0.045105453580617905, "avg_return": 0.8366438746452332, "regret": 0.03052169643342495, "entropy": 0.26029205322265625, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:48.194613Z", "loop": 3503, "env_steps": 2152857599, "loss": 0.04472641274333, "avg_return": 0.8356901407241821, "regret": 0.03052169643342495, "entropy": 0.25005337595939636, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:49.049196Z", "loop": 3504, "env_steps": 2153471999, "loss": 0.04670369625091553, "avg_return": 0.8333343863487244, "regret": 0.03052169643342495, "entropy": 0.25625985860824585, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:49.903599Z", "loop": 3505, "env_steps": 2154086399, "loss": 0.04580214247107506, "avg_return": 0.8308781981468201, "regret": 0.03052169643342495, "entropy": 0.25077056884765625, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:50.758115Z", "loop": 3506, "env_steps": 2154700799, "loss": 0.043785788118839264, "avg_return": 0.8267173171043396, "regret": 0.03052169643342495, "entropy": 0.24595104157924652, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:51.612244Z", "loop": 3507, "env_steps": 2155315199, "loss": 0.046700116246938705, "avg_return": 0.8292503952980042, "regret": 0.03052169643342495, "entropy": 0.25531941652297974, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:52.466457Z", "loop": 3508, "env_steps": 2155929599, "loss": 0.04486364498734474, "avg_return": 0.8338842391967773, "regret": 0.03052169643342495, "entropy": 0.25356754660606384, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:53.319704Z", "loop": 3509, "env_steps": 2156543999, "loss": 0.04517299681901932, "avg_return": 0.8368740677833557, "regret": 0.03052169643342495, "entropy": 0.25575295090675354, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:54.211888Z", "loop": 3510, "env_steps": 2157158399, "loss": 0.04580323398113251, "avg_return": 0.8405659794807434, "regret": 0.022930508479475975, "entropy": 0.25706762075424194, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:55.064917Z", "loop": 3511, "env_steps": 2157772799, "loss": 0.04720192030072212, "avg_return": 0.8413389325141907, "regret": 0.022930508479475975, "entropy": 0.2625751495361328, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:55.918358Z", "loop": 3512, "env_steps": 2158387199, "loss": 0.04558486491441727, "avg_return": 0.840355634689331, "regret": 0.022930508479475975, "entropy": 0.2560868263244629, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:56.772692Z", "loop": 3513, "env_steps": 2159001599, "loss": 0.04856635257601738, "avg_return": 0.8382019400596619, "regret": 0.022930508479475975, "entropy": 0.2646685838699341, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:57.626798Z", "loop": 3514, "env_steps": 2159615999, "loss": 0.04899788275361061, "avg_return": 0.8340381979942322, "regret": 0.022930508479475975, "entropy": 0.2734958827495575, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:58.479316Z", "loop": 3515, "env_steps": 2160230399, "loss": 0.04974409565329552, "avg_return": 0.8327600359916687, "regret": 0.022930508479475975, "entropy": 0.27374106645584106, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:13:59.331967Z", "loop": 3516, "env_steps": 2160844799, "loss": 0.048240404576063156, "avg_return": 0.8315931558609009, "regret": 0.022930508479475975, "entropy": 0.273807168006897, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:00.184692Z", "loop": 3517, "env_steps": 2161459199, "loss": 0.046685975044965744, "avg_return": 0.8333924412727356, "regret": 0.022930508479475975, "entropy": 0.2618979513645172, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:01.038714Z", "loop": 3518, "env_steps": 2162073599, "loss": 0.045247480273246765, "avg_return": 0.8381149172782898, "regret": 0.022930508479475975, "entropy": 0.24784162640571594, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:01.892463Z", "loop": 3519, "env_steps": 2162687999, "loss": 0.046635594218969345, "avg_return": 0.8406448364257812, "regret": 0.022930508479475975, "entropy": 0.25601351261138916, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:02.787476Z", "loop": 3520, "env_steps": 2163302399, "loss": 0.04535175487399101, "avg_return": 0.8420832753181458, "regret": 0.021641336381435394, "entropy": 0.24673429131507874, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:03.641226Z", "loop": 3521, "env_steps": 2163916799, "loss": 0.0414808988571167, "avg_return": 0.8418115377426147, "regret": 0.021641336381435394, "entropy": 0.23347137868404388, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:04.496162Z", "loop": 3522, "env_steps": 2164531199, "loss": 0.04418770596385002, "avg_return": 0.8434203863143921, "regret": 0.021641336381435394, "entropy": 0.24653151631355286, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:05.350365Z", "loop": 3523, "env_steps": 2165145599, "loss": 0.045502979308366776, "avg_return": 0.8422887325286865, "regret": 0.021641336381435394, "entropy": 0.2453635334968567, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:06.203393Z", "loop": 3524, "env_steps": 2165759999, "loss": 0.04326110705733299, "avg_return": 0.8443199992179871, "regret": 0.021641336381435394, "entropy": 0.2371945083141327, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:07.056784Z", "loop": 3525, "env_steps": 2166374399, "loss": 0.04430580884218216, "avg_return": 0.8440266847610474, "regret": 0.021641336381435394, "entropy": 0.24769826233386993, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:07.910929Z", "loop": 3526, "env_steps": 2166988799, "loss": 0.04048820957541466, "avg_return": 0.8439359664916992, "regret": 0.021641336381435394, "entropy": 0.23124875128269196, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:08.765017Z", "loop": 3527, "env_steps": 2167603199, "loss": 0.0428374744951725, "avg_return": 0.8438274264335632, "regret": 0.021641336381435394, "entropy": 0.23674587905406952, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:09.617686Z", "loop": 3528, "env_steps": 2168217599, "loss": 0.03809058293700218, "avg_return": 0.8443257808685303, "regret": 0.021641336381435394, "entropy": 0.22289957106113434, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:10.471019Z", "loop": 3529, "env_steps": 2168831999, "loss": 0.042443107813596725, "avg_return": 0.8436328172683716, "regret": 0.021641336381435394, "entropy": 0.23716463148593903, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:11.366318Z", "loop": 3530, "env_steps": 2169446399, "loss": 0.040639232844114304, "avg_return": 0.8439775705337524, "regret": 0.020010054111480713, "entropy": 0.2338026463985443, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:12.220342Z", "loop": 3531, "env_steps": 2170060799, "loss": 0.03962279483675957, "avg_return": 0.8419659733772278, "regret": 0.020010054111480713, "entropy": 0.2301785945892334, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:13.074729Z", "loop": 3532, "env_steps": 2170675199, "loss": 0.03952551633119583, "avg_return": 0.8400713205337524, "regret": 0.020010054111480713, "entropy": 0.23322661221027374, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:13.928854Z", "loop": 3533, "env_steps": 2171289599, "loss": 0.038686636835336685, "avg_return": 0.8421033620834351, "regret": 0.020010054111480713, "entropy": 0.22943708300590515, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:14.782991Z", "loop": 3534, "env_steps": 2171903999, "loss": 0.03981111943721771, "avg_return": 0.8406687378883362, "regret": 0.020010054111480713, "entropy": 0.2354569286108017, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:15.636979Z", "loop": 3535, "env_steps": 2172518399, "loss": 0.041568707674741745, "avg_return": 0.8418817520141602, "regret": 0.020010054111480713, "entropy": 0.23404929041862488, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:16.489955Z", "loop": 3536, "env_steps": 2173132799, "loss": 0.04053379222750664, "avg_return": 0.8425288200378418, "regret": 0.020010054111480713, "entropy": 0.2339985966682434, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:17.343256Z", "loop": 3537, "env_steps": 2173747199, "loss": 0.03999760374426842, "avg_return": 0.8413609266281128, "regret": 0.020010054111480713, "entropy": 0.23014095425605774, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:18.194990Z", "loop": 3538, "env_steps": 2174361599, "loss": 0.040421172976493835, "avg_return": 0.8403837084770203, "regret": 0.020010054111480713, "entropy": 0.22938410937786102, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:19.048023Z", "loop": 3539, "env_steps": 2174975999, "loss": 0.043668974190950394, "avg_return": 0.8415270447731018, "regret": 0.020010054111480713, "entropy": 0.23669879138469696, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:19.942901Z", "loop": 3540, "env_steps": 2175590399, "loss": 0.042721912264823914, "avg_return": 0.8405576348304749, "regret": 0.02166878618299961, "entropy": 0.2320244163274765, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:20.796342Z", "loop": 3541, "env_steps": 2176204799, "loss": 0.04313306137919426, "avg_return": 0.8431174755096436, "regret": 0.02166878618299961, "entropy": 0.2386513650417328, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:21.648837Z", "loop": 3542, "env_steps": 2176819199, "loss": 0.04553694650530815, "avg_return": 0.844989538192749, "regret": 0.02166878618299961, "entropy": 0.2463308721780777, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:22.502380Z", "loop": 3543, "env_steps": 2177433599, "loss": 0.0454646460711956, "avg_return": 0.8447340130805969, "regret": 0.02166878618299961, "entropy": 0.2481401562690735, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:23.355762Z", "loop": 3544, "env_steps": 2178047999, "loss": 0.04406718537211418, "avg_return": 0.8455050587654114, "regret": 0.02166878618299961, "entropy": 0.25474774837493896, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:24.209367Z", "loop": 3545, "env_steps": 2178662399, "loss": 0.04617580398917198, "avg_return": 0.8451639413833618, "regret": 0.02166878618299961, "entropy": 0.26162734627723694, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:25.062533Z", "loop": 3546, "env_steps": 2179276799, "loss": 0.04517987370491028, "avg_return": 0.8439164161682129, "regret": 0.02166878618299961, "entropy": 0.26089614629745483, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:25.915921Z", "loop": 3547, "env_steps": 2179891199, "loss": 0.046480484306812286, "avg_return": 0.8448142409324646, "regret": 0.02166878618299961, "entropy": 0.26637184619903564, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:26.768970Z", "loop": 3548, "env_steps": 2180505599, "loss": 0.04753006622195244, "avg_return": 0.843842089176178, "regret": 0.02166878618299961, "entropy": 0.2628888189792633, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:27.622930Z", "loop": 3549, "env_steps": 2181119999, "loss": 0.049037814140319824, "avg_return": 0.8424206972122192, "regret": 0.02166878618299961, "entropy": 0.27006709575653076, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:28.516725Z", "loop": 3550, "env_steps": 2181734399, "loss": 0.048091500997543335, "avg_return": 0.8407533168792725, "regret": 0.021574389189481735, "entropy": 0.2721349895000458, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:29.370349Z", "loop": 3551, "env_steps": 2182348799, "loss": 0.048651233315467834, "avg_return": 0.8394405245780945, "regret": 0.021574389189481735, "entropy": 0.26989275217056274, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:30.224216Z", "loop": 3552, "env_steps": 2182963199, "loss": 0.04680629447102547, "avg_return": 0.8410231471061707, "regret": 0.021574389189481735, "entropy": 0.2604216933250427, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:31.078657Z", "loop": 3553, "env_steps": 2183577599, "loss": 0.04735714569687843, "avg_return": 0.8403724431991577, "regret": 0.021574389189481735, "entropy": 0.2623916268348694, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:31.931784Z", "loop": 3554, "env_steps": 2184191999, "loss": 0.04346676170825958, "avg_return": 0.842430830001831, "regret": 0.021574389189481735, "entropy": 0.2385689914226532, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:32.785862Z", "loop": 3555, "env_steps": 2184806399, "loss": 0.04394451901316643, "avg_return": 0.8421640992164612, "regret": 0.021574389189481735, "entropy": 0.24200256168842316, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:33.639934Z", "loop": 3556, "env_steps": 2185420799, "loss": 0.04126068577170372, "avg_return": 0.8451555371284485, "regret": 0.021574389189481735, "entropy": 0.23219667375087738, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:34.494825Z", "loop": 3557, "env_steps": 2186035199, "loss": 0.03984612971544266, "avg_return": 0.8454691767692566, "regret": 0.021574389189481735, "entropy": 0.22534087300300598, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:35.349390Z", "loop": 3558, "env_steps": 2186649599, "loss": 0.039375897496938705, "avg_return": 0.8455104827880859, "regret": 0.021574389189481735, "entropy": 0.22442635893821716, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:36.203496Z", "loop": 3559, "env_steps": 2187263999, "loss": 0.03946110978722572, "avg_return": 0.847135603427887, "regret": 0.021574389189481735, "entropy": 0.21961016952991486, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:37.100525Z", "loop": 3560, "env_steps": 2187878399, "loss": 0.041962191462516785, "avg_return": 0.8432595729827881, "regret": 0.02052290551364422, "entropy": 0.23723536729812622, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:37.953097Z", "loop": 3561, "env_steps": 2188492799, "loss": 0.039362940937280655, "avg_return": 0.8422331213951111, "regret": 0.02052290551364422, "entropy": 0.23268085718154907, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:38.806608Z", "loop": 3562, "env_steps": 2189107199, "loss": 0.04110287129878998, "avg_return": 0.8404091596603394, "regret": 0.02052290551364422, "entropy": 0.23336443305015564, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:39.660745Z", "loop": 3563, "env_steps": 2189721599, "loss": 0.03977743908762932, "avg_return": 0.8413559198379517, "regret": 0.02052290551364422, "entropy": 0.2325064092874527, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:40.515155Z", "loop": 3564, "env_steps": 2190335999, "loss": 0.03778843209147453, "avg_return": 0.8425804376602173, "regret": 0.02052290551364422, "entropy": 0.21229678392410278, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:41.368201Z", "loop": 3565, "env_steps": 2190950399, "loss": 0.037837859243154526, "avg_return": 0.845329999923706, "regret": 0.02052290551364422, "entropy": 0.21518833935260773, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:42.221438Z", "loop": 3566, "env_steps": 2191564799, "loss": 0.036696918308734894, "avg_return": 0.8455424308776855, "regret": 0.02052290551364422, "entropy": 0.20962795615196228, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:43.074233Z", "loop": 3567, "env_steps": 2192179199, "loss": 0.037196166813373566, "avg_return": 0.8469890356063843, "regret": 0.02052290551364422, "entropy": 0.21617084741592407, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:43.926942Z", "loop": 3568, "env_steps": 2192793599, "loss": 0.039115242660045624, "avg_return": 0.8456858396530151, "regret": 0.02052290551364422, "entropy": 0.21775978803634644, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:44.779402Z", "loop": 3569, "env_steps": 2193407999, "loss": 0.039685968309640884, "avg_return": 0.8453289270401001, "regret": 0.02052290551364422, "entropy": 0.22574423253536224, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:45.673909Z", "loop": 3570, "env_steps": 2194022399, "loss": 0.03846065700054169, "avg_return": 0.8467323184013367, "regret": 0.017747322097420692, "entropy": 0.22551245987415314, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:46.526828Z", "loop": 3571, "env_steps": 2194636799, "loss": 0.03865433856844902, "avg_return": 0.8478280901908875, "regret": 0.017747322097420692, "entropy": 0.22919996082782745, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:47.381248Z", "loop": 3572, "env_steps": 2195251199, "loss": 0.04101727530360222, "avg_return": 0.847770631313324, "regret": 0.017747322097420692, "entropy": 0.23324358463287354, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:48.234544Z", "loop": 3573, "env_steps": 2195865599, "loss": 0.03977454453706741, "avg_return": 0.8470094203948975, "regret": 0.017747322097420692, "entropy": 0.23084202408790588, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:49.088849Z", "loop": 3574, "env_steps": 2196479999, "loss": 0.04119870439171791, "avg_return": 0.8462427854537964, "regret": 0.017747322097420692, "entropy": 0.24014341831207275, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:49.942436Z", "loop": 3575, "env_steps": 2197094399, "loss": 0.042881712317466736, "avg_return": 0.8430997729301453, "regret": 0.017747322097420692, "entropy": 0.24149826169013977, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:50.796001Z", "loop": 3576, "env_steps": 2197708799, "loss": 0.042316775768995285, "avg_return": 0.8456836938858032, "regret": 0.017747322097420692, "entropy": 0.23956868052482605, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:51.649134Z", "loop": 3577, "env_steps": 2198323199, "loss": 0.04135027155280113, "avg_return": 0.84710294008255, "regret": 0.017747322097420692, "entropy": 0.2302275151014328, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:52.501955Z", "loop": 3578, "env_steps": 2198937599, "loss": 0.03944477066397667, "avg_return": 0.8478782773017883, "regret": 0.017747322097420692, "entropy": 0.2203107327222824, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:53.354654Z", "loop": 3579, "env_steps": 2199551999, "loss": 0.039176277816295624, "avg_return": 0.8470192551612854, "regret": 0.017747322097420692, "entropy": 0.22932088375091553, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:54.249150Z", "loop": 3580, "env_steps": 2200166399, "loss": 0.039342958480119705, "avg_return": 0.8462364673614502, "regret": 0.015724914148449898, "entropy": 0.22625049948692322, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:55.101700Z", "loop": 3581, "env_steps": 2200780799, "loss": 0.03866565227508545, "avg_return": 0.8473579287528992, "regret": 0.015724914148449898, "entropy": 0.22520259022712708, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:55.955846Z", "loop": 3582, "env_steps": 2201395199, "loss": 0.040404774248600006, "avg_return": 0.8478536605834961, "regret": 0.015724914148449898, "entropy": 0.22480487823486328, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:56.809199Z", "loop": 3583, "env_steps": 2202009599, "loss": 0.038877181708812714, "avg_return": 0.843694269657135, "regret": 0.015724914148449898, "entropy": 0.2299129217863083, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:57.663532Z", "loop": 3584, "env_steps": 2202623999, "loss": 0.04198335483670235, "avg_return": 0.8440864086151123, "regret": 0.015724914148449898, "entropy": 0.23290807008743286, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:58.517957Z", "loop": 3585, "env_steps": 2203238399, "loss": 0.04211467131972313, "avg_return": 0.8434107899665833, "regret": 0.015724914148449898, "entropy": 0.22617016732692719, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:14:59.371738Z", "loop": 3586, "env_steps": 2203852799, "loss": 0.042523887008428574, "avg_return": 0.843988299369812, "regret": 0.015724914148449898, "entropy": 0.23650793731212616, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:00.223458Z", "loop": 3587, "env_steps": 2204467199, "loss": 0.04091189429163933, "avg_return": 0.8455977439880371, "regret": 0.015724914148449898, "entropy": 0.22962453961372375, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:01.075454Z", "loop": 3588, "env_steps": 2205081599, "loss": 0.0404842346906662, "avg_return": 0.8480824828147888, "regret": 0.015724914148449898, "entropy": 0.23134590685367584, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:01.929824Z", "loop": 3589, "env_steps": 2205695999, "loss": 0.040781885385513306, "avg_return": 0.8475818037986755, "regret": 0.015724914148449898, "entropy": 0.2327297031879425, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:02.825838Z", "loop": 3590, "env_steps": 2206310399, "loss": 0.040553051978349686, "avg_return": 0.8443799018859863, "regret": 0.017085669562220573, "entropy": 0.22853407263755798, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:03.678672Z", "loop": 3591, "env_steps": 2206924799, "loss": 0.040173400193452835, "avg_return": 0.8439133167266846, "regret": 0.017085669562220573, "entropy": 0.22853057086467743, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:04.531963Z", "loop": 3592, "env_steps": 2207539199, "loss": 0.041216619312763214, "avg_return": 0.8421356678009033, "regret": 0.017085669562220573, "entropy": 0.22728481888771057, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:05.384843Z", "loop": 3593, "env_steps": 2208153599, "loss": 0.039522770792245865, "avg_return": 0.844886302947998, "regret": 0.017085669562220573, "entropy": 0.2229873090982437, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:06.238645Z", "loop": 3594, "env_steps": 2208767999, "loss": 0.04036705940961838, "avg_return": 0.8451299667358398, "regret": 0.017085669562220573, "entropy": 0.2292473167181015, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:07.091530Z", "loop": 3595, "env_steps": 2209382399, "loss": 0.03939713537693024, "avg_return": 0.8463063836097717, "regret": 0.017085669562220573, "entropy": 0.22534599900245667, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:07.943906Z", "loop": 3596, "env_steps": 2209996799, "loss": 0.04140089079737663, "avg_return": 0.8465862274169922, "regret": 0.017085669562220573, "entropy": 0.23549436032772064, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:08.796193Z", "loop": 3597, "env_steps": 2210611199, "loss": 0.03888402134180069, "avg_return": 0.8484563827514648, "regret": 0.017085669562220573, "entropy": 0.2261795550584793, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:09.649554Z", "loop": 3598, "env_steps": 2211225599, "loss": 0.039278727024793625, "avg_return": 0.8487423658370972, "regret": 0.017085669562220573, "entropy": 0.22492678463459015, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:10.502159Z", "loop": 3599, "env_steps": 2211839999, "loss": 0.03822338581085205, "avg_return": 0.8492212295532227, "regret": 0.017085669562220573, "entropy": 0.22195258736610413, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:11.396651Z", "loop": 3600, "env_steps": 2212454399, "loss": 0.03701196610927582, "avg_return": 0.8479967713356018, "regret": 0.014969583600759506, "entropy": 0.21387295424938202, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:12.251897Z", "loop": 3601, "env_steps": 2213068799, "loss": 0.04106758162379265, "avg_return": 0.84600430727005, "regret": 0.014969583600759506, "entropy": 0.22890356183052063, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:13.105453Z", "loop": 3602, "env_steps": 2213683199, "loss": 0.04049354046583176, "avg_return": 0.8439063429832458, "regret": 0.014969583600759506, "entropy": 0.22289970517158508, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:13.958465Z", "loop": 3603, "env_steps": 2214297599, "loss": 0.041771408170461655, "avg_return": 0.8460716009140015, "regret": 0.014969583600759506, "entropy": 0.22615687549114227, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:14.813080Z", "loop": 3604, "env_steps": 2214911999, "loss": 0.039198245853185654, "avg_return": 0.8460643887519836, "regret": 0.014969583600759506, "entropy": 0.22241535782814026, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:15.667407Z", "loop": 3605, "env_steps": 2215526399, "loss": 0.03887266665697098, "avg_return": 0.8485457301139832, "regret": 0.014969583600759506, "entropy": 0.22215287387371063, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:16.521272Z", "loop": 3606, "env_steps": 2216140799, "loss": 0.039449479430913925, "avg_return": 0.847690999507904, "regret": 0.014969583600759506, "entropy": 0.22560325264930725, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:17.375165Z", "loop": 3607, "env_steps": 2216755199, "loss": 0.04089057818055153, "avg_return": 0.848333477973938, "regret": 0.014969583600759506, "entropy": 0.23053959012031555, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:18.229550Z", "loop": 3608, "env_steps": 2217369599, "loss": 0.04270804300904274, "avg_return": 0.8437314033508301, "regret": 0.014969583600759506, "entropy": 0.2320653349161148, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:19.083795Z", "loop": 3609, "env_steps": 2217983999, "loss": 0.038926370441913605, "avg_return": 0.8473482728004456, "regret": 0.014969583600759506, "entropy": 0.22525975108146667, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:19.978726Z", "loop": 3610, "env_steps": 2218598399, "loss": 0.0390658937394619, "avg_return": 0.8497894406318665, "regret": 0.014398603700101376, "entropy": 0.2245360165834427, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:20.831558Z", "loop": 3611, "env_steps": 2219212799, "loss": 0.038649167865514755, "avg_return": 0.8479180335998535, "regret": 0.014398603700101376, "entropy": 0.2164011001586914, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:21.685361Z", "loop": 3612, "env_steps": 2219827199, "loss": 0.03938062861561775, "avg_return": 0.8494016528129578, "regret": 0.014398603700101376, "entropy": 0.214039608836174, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:22.540007Z", "loop": 3613, "env_steps": 2220441599, "loss": 0.03755740448832512, "avg_return": 0.8492064476013184, "regret": 0.014398603700101376, "entropy": 0.2126806080341339, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:23.392725Z", "loop": 3614, "env_steps": 2221055999, "loss": 0.03751952946186066, "avg_return": 0.8494658470153809, "regret": 0.014398603700101376, "entropy": 0.21119974553585052, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:24.246037Z", "loop": 3615, "env_steps": 2221670399, "loss": 0.039749715477228165, "avg_return": 0.8501576781272888, "regret": 0.014398603700101376, "entropy": 0.21613706648349762, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:25.099978Z", "loop": 3616, "env_steps": 2222284799, "loss": 0.03631649911403656, "avg_return": 0.8487991690635681, "regret": 0.014398603700101376, "entropy": 0.20434655249118805, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:25.954996Z", "loop": 3617, "env_steps": 2222899199, "loss": 0.041050270199775696, "avg_return": 0.8489380478858948, "regret": 0.014398603700101376, "entropy": 0.2154635190963745, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:26.808838Z", "loop": 3618, "env_steps": 2223513599, "loss": 0.03775620087981224, "avg_return": 0.8476846814155579, "regret": 0.014398603700101376, "entropy": 0.20837387442588806, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:27.662260Z", "loop": 3619, "env_steps": 2224127999, "loss": 0.038063716143369675, "avg_return": 0.8491413593292236, "regret": 0.014398603700101376, "entropy": 0.2043210119009018, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:28.557246Z", "loop": 3620, "env_steps": 2224742399, "loss": 0.03590963035821915, "avg_return": 0.8479637503623962, "regret": 0.014910592697560787, "entropy": 0.2012280821800232, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:29.411996Z", "loop": 3621, "env_steps": 2225356799, "loss": 0.037164609879255295, "avg_return": 0.8482202291488647, "regret": 0.014910592697560787, "entropy": 0.20829154551029205, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:30.265675Z", "loop": 3622, "env_steps": 2225971199, "loss": 0.03793508559465408, "avg_return": 0.849252462387085, "regret": 0.014910592697560787, "entropy": 0.21511824429035187, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:31.119653Z", "loop": 3623, "env_steps": 2226585599, "loss": 0.0371205173432827, "avg_return": 0.8488743901252747, "regret": 0.014910592697560787, "entropy": 0.21682536602020264, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:31.973448Z", "loop": 3624, "env_steps": 2227199999, "loss": 0.03744758293032646, "avg_return": 0.8486814498901367, "regret": 0.014910592697560787, "entropy": 0.21317772567272186, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:32.827258Z", "loop": 3625, "env_steps": 2227814399, "loss": 0.037708692252635956, "avg_return": 0.851332426071167, "regret": 0.014910592697560787, "entropy": 0.2103051394224167, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:33.681003Z", "loop": 3626, "env_steps": 2228428799, "loss": 0.03689330816268921, "avg_return": 0.8499621748924255, "regret": 0.014910592697560787, "entropy": 0.19869239628314972, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:34.534182Z", "loop": 3627, "env_steps": 2229043199, "loss": 0.03503664210438728, "avg_return": 0.8493627309799194, "regret": 0.014910592697560787, "entropy": 0.2093251347541809, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:35.386181Z", "loop": 3628, "env_steps": 2229657599, "loss": 0.03741015866398811, "avg_return": 0.8500216603279114, "regret": 0.014910592697560787, "entropy": 0.20403538644313812, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:36.238836Z", "loop": 3629, "env_steps": 2230271999, "loss": 0.035173457115888596, "avg_return": 0.8495954871177673, "regret": 0.014910592697560787, "entropy": 0.1988345831632614, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:37.132931Z", "loop": 3630, "env_steps": 2230886399, "loss": 0.03706355392932892, "avg_return": 0.8489168882369995, "regret": 0.0147707499563694, "entropy": 0.20394276082515717, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:37.985959Z", "loop": 3631, "env_steps": 2231500799, "loss": 0.03799251466989517, "avg_return": 0.8510224223136902, "regret": 0.0147707499563694, "entropy": 0.21057192981243134, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:38.838879Z", "loop": 3632, "env_steps": 2232115199, "loss": 0.035065907984972, "avg_return": 0.8511092066764832, "regret": 0.0147707499563694, "entropy": 0.19794566929340363, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:39.692086Z", "loop": 3633, "env_steps": 2232729599, "loss": 0.036879491060972214, "avg_return": 0.8494341969490051, "regret": 0.0147707499563694, "entropy": 0.20182625949382782, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:40.544722Z", "loop": 3634, "env_steps": 2233343999, "loss": 0.03495326265692711, "avg_return": 0.8503530025482178, "regret": 0.0147707499563694, "entropy": 0.19709895551204681, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:41.398578Z", "loop": 3635, "env_steps": 2233958399, "loss": 0.036635544151067734, "avg_return": 0.8504105806350708, "regret": 0.0147707499563694, "entropy": 0.20494920015335083, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:42.252702Z", "loop": 3636, "env_steps": 2234572799, "loss": 0.03491302207112312, "avg_return": 0.8516075015068054, "regret": 0.0147707499563694, "entropy": 0.1945836842060089, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:43.106649Z", "loop": 3637, "env_steps": 2235187199, "loss": 0.035239871591329575, "avg_return": 0.8528640270233154, "regret": 0.0147707499563694, "entropy": 0.19707678258419037, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:43.961626Z", "loop": 3638, "env_steps": 2235801599, "loss": 0.03492472693324089, "avg_return": 0.8507921695709229, "regret": 0.0147707499563694, "entropy": 0.20206235349178314, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:44.815542Z", "loop": 3639, "env_steps": 2236415999, "loss": 0.03439893200993538, "avg_return": 0.851585328578949, "regret": 0.0147707499563694, "entropy": 0.19319015741348267, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:45.714043Z", "loop": 3640, "env_steps": 2237030399, "loss": 0.035029418766498566, "avg_return": 0.8517089486122131, "regret": 0.012562040239572525, "entropy": 0.19611334800720215, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:46.568141Z", "loop": 3641, "env_steps": 2237644799, "loss": 0.03621915355324745, "avg_return": 0.8501442074775696, "regret": 0.012562040239572525, "entropy": 0.19607284665107727, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:47.422274Z", "loop": 3642, "env_steps": 2238259199, "loss": 0.03620731458067894, "avg_return": 0.851061999797821, "regret": 0.012562040239572525, "entropy": 0.20890958607196808, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:48.275931Z", "loop": 3643, "env_steps": 2238873599, "loss": 0.03457457944750786, "avg_return": 0.8505561351776123, "regret": 0.012562040239572525, "entropy": 0.2031676471233368, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:49.129984Z", "loop": 3644, "env_steps": 2239487999, "loss": 0.03599311411380768, "avg_return": 0.8501681685447693, "regret": 0.012562040239572525, "entropy": 0.2069532871246338, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:49.984095Z", "loop": 3645, "env_steps": 2240102399, "loss": 0.0356748066842556, "avg_return": 0.851518452167511, "regret": 0.012562040239572525, "entropy": 0.2030218094587326, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:50.837035Z", "loop": 3646, "env_steps": 2240716799, "loss": 0.03828681632876396, "avg_return": 0.8515061736106873, "regret": 0.012562040239572525, "entropy": 0.21371231973171234, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:51.690307Z", "loop": 3647, "env_steps": 2241331199, "loss": 0.038626644760370255, "avg_return": 0.850268542766571, "regret": 0.012562040239572525, "entropy": 0.21690762042999268, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:52.543982Z", "loop": 3648, "env_steps": 2241945599, "loss": 0.03871966898441315, "avg_return": 0.848747193813324, "regret": 0.012562040239572525, "entropy": 0.21656900644302368, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:53.398380Z", "loop": 3649, "env_steps": 2242559999, "loss": 0.039414625614881516, "avg_return": 0.8490118384361267, "regret": 0.012562040239572525, "entropy": 0.21678707003593445, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:54.293043Z", "loop": 3650, "env_steps": 2243174399, "loss": 0.03881017491221428, "avg_return": 0.8488312363624573, "regret": 0.014772135764360428, "entropy": 0.21985198557376862, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:55.146349Z", "loop": 3651, "env_steps": 2243788799, "loss": 0.03806848078966141, "avg_return": 0.8486698865890503, "regret": 0.014772135764360428, "entropy": 0.20842161774635315, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:56.000739Z", "loop": 3652, "env_steps": 2244403199, "loss": 0.03784939646720886, "avg_return": 0.8492307066917419, "regret": 0.014772135764360428, "entropy": 0.2129426747560501, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:56.855837Z", "loop": 3653, "env_steps": 2245017599, "loss": 0.03688138350844383, "avg_return": 0.8477540612220764, "regret": 0.014772135764360428, "entropy": 0.20558589696884155, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:57.709353Z", "loop": 3654, "env_steps": 2245631999, "loss": 0.038026873022317886, "avg_return": 0.8463684320449829, "regret": 0.014772135764360428, "entropy": 0.21135365962982178, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:58.561980Z", "loop": 3655, "env_steps": 2246246399, "loss": 0.039561059325933456, "avg_return": 0.847069501876831, "regret": 0.014772135764360428, "entropy": 0.21371708810329437, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:15:59.414772Z", "loop": 3656, "env_steps": 2246860799, "loss": 0.03774546831846237, "avg_return": 0.845650851726532, "regret": 0.014772135764360428, "entropy": 0.21733832359313965, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:00.268768Z", "loop": 3657, "env_steps": 2247475199, "loss": 0.034938789904117584, "avg_return": 0.8480798602104187, "regret": 0.014772135764360428, "entropy": 0.1956971138715744, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:01.121797Z", "loop": 3658, "env_steps": 2248089599, "loss": 0.03810298442840576, "avg_return": 0.8511521816253662, "regret": 0.014772135764360428, "entropy": 0.20740863680839539, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:01.974629Z", "loop": 3659, "env_steps": 2248703999, "loss": 0.03494654595851898, "avg_return": 0.8495004773139954, "regret": 0.014772135764360428, "entropy": 0.2056361734867096, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:02.870936Z", "loop": 3660, "env_steps": 2249318399, "loss": 0.03453122451901436, "avg_return": 0.8521748781204224, "regret": 0.012597563676536083, "entropy": 0.19828060269355774, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:03.724579Z", "loop": 3661, "env_steps": 2249932799, "loss": 0.035013020038604736, "avg_return": 0.8518603444099426, "regret": 0.012597563676536083, "entropy": 0.19568949937820435, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:04.579455Z", "loop": 3662, "env_steps": 2250547199, "loss": 0.03342180699110031, "avg_return": 0.8530962467193604, "regret": 0.012597563676536083, "entropy": 0.19376921653747559, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:05.433127Z", "loop": 3663, "env_steps": 2251161599, "loss": 0.03390774875879288, "avg_return": 0.8506757616996765, "regret": 0.012597563676536083, "entropy": 0.1923857480287552, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:06.286344Z", "loop": 3664, "env_steps": 2251775999, "loss": 0.03352911025285721, "avg_return": 0.8507441282272339, "regret": 0.012597563676536083, "entropy": 0.1917329728603363, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:07.140395Z", "loop": 3665, "env_steps": 2252390399, "loss": 0.035417668521404266, "avg_return": 0.851632297039032, "regret": 0.012597563676536083, "entropy": 0.197895348072052, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:07.995047Z", "loop": 3666, "env_steps": 2253004799, "loss": 0.03311335667967796, "avg_return": 0.8491616249084473, "regret": 0.012597563676536083, "entropy": 0.18742507696151733, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:08.849051Z", "loop": 3667, "env_steps": 2253619199, "loss": 0.033118702471256256, "avg_return": 0.8490417003631592, "regret": 0.012597563676536083, "entropy": 0.19194994866847992, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:09.702465Z", "loop": 3668, "env_steps": 2254233599, "loss": 0.03314108029007912, "avg_return": 0.8501636385917664, "regret": 0.012597563676536083, "entropy": 0.18727554380893707, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:10.557462Z", "loop": 3669, "env_steps": 2254847999, "loss": 0.034923113882541656, "avg_return": 0.8507522940635681, "regret": 0.012597563676536083, "entropy": 0.18910114467144012, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:11.450986Z", "loop": 3670, "env_steps": 2255462399, "loss": 0.03288329020142555, "avg_return": 0.8520553708076477, "regret": 0.011667675338685513, "entropy": 0.18893004953861237, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:12.305607Z", "loop": 3671, "env_steps": 2256076799, "loss": 0.0327969565987587, "avg_return": 0.8539319038391113, "regret": 0.011667675338685513, "entropy": 0.1835002303123474, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:13.160286Z", "loop": 3672, "env_steps": 2256691199, "loss": 0.036651838570833206, "avg_return": 0.8518208265304565, "regret": 0.011667675338685513, "entropy": 0.1979115903377533, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:14.014133Z", "loop": 3673, "env_steps": 2257305599, "loss": 0.03393520414829254, "avg_return": 0.849083662033081, "regret": 0.011667675338685513, "entropy": 0.19116701185703278, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:14.868098Z", "loop": 3674, "env_steps": 2257919999, "loss": 0.03490414470434189, "avg_return": 0.8484176397323608, "regret": 0.011667675338685513, "entropy": 0.19777578115463257, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:15.721928Z", "loop": 3675, "env_steps": 2258534399, "loss": 0.038080401718616486, "avg_return": 0.846874475479126, "regret": 0.011667675338685513, "entropy": 0.20852325856685638, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:16.575629Z", "loop": 3676, "env_steps": 2259148799, "loss": 0.03681875392794609, "avg_return": 0.8450780510902405, "regret": 0.011667675338685513, "entropy": 0.21027453243732452, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:17.430341Z", "loop": 3677, "env_steps": 2259763199, "loss": 0.03642366826534271, "avg_return": 0.8447462320327759, "regret": 0.011667675338685513, "entropy": 0.2018970549106598, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:18.283690Z", "loop": 3678, "env_steps": 2260377599, "loss": 0.03569084033370018, "avg_return": 0.8456935286521912, "regret": 0.011667675338685513, "entropy": 0.19958281517028809, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:19.138003Z", "loop": 3679, "env_steps": 2260991999, "loss": 0.03561803326010704, "avg_return": 0.8496591448783875, "regret": 0.011667675338685513, "entropy": 0.19447721540927887, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:20.031065Z", "loop": 3680, "env_steps": 2261606399, "loss": 0.03363243490457535, "avg_return": 0.8527238368988037, "regret": 0.011798067949712276, "entropy": 0.1889655888080597, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:20.885168Z", "loop": 3681, "env_steps": 2262220799, "loss": 0.033427562564611435, "avg_return": 0.8531642556190491, "regret": 0.011798067949712276, "entropy": 0.1933368742465973, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:21.738021Z", "loop": 3682, "env_steps": 2262835199, "loss": 0.033518753945827484, "avg_return": 0.8507145643234253, "regret": 0.011798067949712276, "entropy": 0.19383695721626282, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:22.591146Z", "loop": 3683, "env_steps": 2263449599, "loss": 0.03816070407629013, "avg_return": 0.8463834524154663, "regret": 0.011798067949712276, "entropy": 0.20713689923286438, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:23.445493Z", "loop": 3684, "env_steps": 2264063999, "loss": 0.03768278658390045, "avg_return": 0.8468356728553772, "regret": 0.011798067949712276, "entropy": 0.21647858619689941, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:24.298812Z", "loop": 3685, "env_steps": 2264678399, "loss": 0.03440612927079201, "avg_return": 0.8484115600585938, "regret": 0.011798067949712276, "entropy": 0.20004712045192719, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:25.151582Z", "loop": 3686, "env_steps": 2265292799, "loss": 0.03386547043919563, "avg_return": 0.8525350689888, "regret": 0.011798067949712276, "entropy": 0.19253744184970856, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:26.005008Z", "loop": 3687, "env_steps": 2265907199, "loss": 0.034968819469213486, "avg_return": 0.8523306250572205, "regret": 0.011798067949712276, "entropy": 0.19872501492500305, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:26.858472Z", "loop": 3688, "env_steps": 2266521599, "loss": 0.03360217809677124, "avg_return": 0.8527154922485352, "regret": 0.011798067949712276, "entropy": 0.19088618457317352, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:27.712039Z", "loop": 3689, "env_steps": 2267135999, "loss": 0.03421090170741081, "avg_return": 0.8512325286865234, "regret": 0.011798067949712276, "entropy": 0.189663365483284, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:28.605717Z", "loop": 3690, "env_steps": 2267750399, "loss": 0.032789405435323715, "avg_return": 0.8513900637626648, "regret": 0.011992995627224445, "entropy": 0.1876385509967804, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:29.457691Z", "loop": 3691, "env_steps": 2268364799, "loss": 0.03339818865060806, "avg_return": 0.8518183827400208, "regret": 0.011992995627224445, "entropy": 0.19497548043727875, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:30.309881Z", "loop": 3692, "env_steps": 2268979199, "loss": 0.03604186326265335, "avg_return": 0.8523977994918823, "regret": 0.011992995627224445, "entropy": 0.19759146869182587, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:31.163692Z", "loop": 3693, "env_steps": 2269593599, "loss": 0.03414171561598778, "avg_return": 0.8533055782318115, "regret": 0.011992995627224445, "entropy": 0.19437016546726227, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:32.017481Z", "loop": 3694, "env_steps": 2270207999, "loss": 0.035343416035175323, "avg_return": 0.8540758490562439, "regret": 0.011992995627224445, "entropy": 0.19699996709823608, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:32.871130Z", "loop": 3695, "env_steps": 2270822399, "loss": 0.03551340475678444, "avg_return": 0.8521600365638733, "regret": 0.011992995627224445, "entropy": 0.20122624933719635, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:33.724951Z", "loop": 3696, "env_steps": 2271436799, "loss": 0.039354342967271805, "avg_return": 0.8489150404930115, "regret": 0.011992995627224445, "entropy": 0.2188873142004013, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:34.579472Z", "loop": 3697, "env_steps": 2272051199, "loss": 0.03703472390770912, "avg_return": 0.8495819568634033, "regret": 0.011992995627224445, "entropy": 0.20643381774425507, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:35.433289Z", "loop": 3698, "env_steps": 2272665599, "loss": 0.03656549006700516, "avg_return": 0.8527575135231018, "regret": 0.011992995627224445, "entropy": 0.20110434293746948, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:36.287689Z", "loop": 3699, "env_steps": 2273279999, "loss": 0.034699879586696625, "avg_return": 0.853013813495636, "regret": 0.011992995627224445, "entropy": 0.19661390781402588, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:37.181209Z", "loop": 3700, "env_steps": 2273894399, "loss": 0.032159846276044846, "avg_return": 0.8527488112449646, "regret": 0.010069583542644978, "entropy": 0.18693377077579498, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:38.034703Z", "loop": 3701, "env_steps": 2274508799, "loss": 0.0328616127371788, "avg_return": 0.8515392541885376, "regret": 0.010069583542644978, "entropy": 0.1827748715877533, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:38.888411Z", "loop": 3702, "env_steps": 2275123199, "loss": 0.03235549479722977, "avg_return": 0.8492136597633362, "regret": 0.010069583542644978, "entropy": 0.1784147024154663, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:39.742996Z", "loop": 3703, "env_steps": 2275737599, "loss": 0.032395653426647186, "avg_return": 0.8486408591270447, "regret": 0.010069583542644978, "entropy": 0.18078476190567017, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:40.597241Z", "loop": 3704, "env_steps": 2276351999, "loss": 0.0336453914642334, "avg_return": 0.8524585366249084, "regret": 0.010069583542644978, "entropy": 0.18092121183872223, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:41.450502Z", "loop": 3705, "env_steps": 2276966399, "loss": 0.031899914145469666, "avg_return": 0.853999674320221, "regret": 0.010069583542644978, "entropy": 0.18378503620624542, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:42.303761Z", "loop": 3706, "env_steps": 2277580799, "loss": 0.034026484936475754, "avg_return": 0.8534278273582458, "regret": 0.010069583542644978, "entropy": 0.1998099386692047, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:43.156921Z", "loop": 3707, "env_steps": 2278195199, "loss": 0.03514428064227104, "avg_return": 0.8476670384407043, "regret": 0.010069583542644978, "entropy": 0.20106729865074158, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:44.010761Z", "loop": 3708, "env_steps": 2278809599, "loss": 0.034032948315143585, "avg_return": 0.852161169052124, "regret": 0.010069583542644978, "entropy": 0.19174841046333313, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:44.863491Z", "loop": 3709, "env_steps": 2279423999, "loss": 0.03369879350066185, "avg_return": 0.85392826795578, "regret": 0.010069583542644978, "entropy": 0.19124625623226166, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:45.756160Z", "loop": 3710, "env_steps": 2280038399, "loss": 0.03267373889684677, "avg_return": 0.8533071875572205, "regret": 0.011364289559423923, "entropy": 0.18536795675754547, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:46.609923Z", "loop": 3711, "env_steps": 2280652799, "loss": 0.03287668526172638, "avg_return": 0.8491160869598389, "regret": 0.011364289559423923, "entropy": 0.18335597217082977, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:47.464420Z", "loop": 3712, "env_steps": 2281267199, "loss": 0.03332475945353508, "avg_return": 0.850240170955658, "regret": 0.011364289559423923, "entropy": 0.18334978818893433, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:48.318753Z", "loop": 3713, "env_steps": 2281881599, "loss": 0.03213782235980034, "avg_return": 0.8523759841918945, "regret": 0.011364289559423923, "entropy": 0.1761704534292221, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:49.171711Z", "loop": 3714, "env_steps": 2282495999, "loss": 0.031380996108055115, "avg_return": 0.8528998494148254, "regret": 0.011364289559423923, "entropy": 0.17933669686317444, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:50.024713Z", "loop": 3715, "env_steps": 2283110399, "loss": 0.03177720680832863, "avg_return": 0.8537260293960571, "regret": 0.011364289559423923, "entropy": 0.18689264357089996, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:50.878635Z", "loop": 3716, "env_steps": 2283724799, "loss": 0.03293352574110031, "avg_return": 0.8549273610115051, "regret": 0.011364289559423923, "entropy": 0.18876169621944427, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:51.732677Z", "loop": 3717, "env_steps": 2284339199, "loss": 0.034494586288928986, "avg_return": 0.8534175753593445, "regret": 0.011364289559423923, "entropy": 0.19886593520641327, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:52.586117Z", "loop": 3718, "env_steps": 2284953599, "loss": 0.03536873683333397, "avg_return": 0.8534462451934814, "regret": 0.011364289559423923, "entropy": 0.19800765812397003, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:53.439263Z", "loop": 3719, "env_steps": 2285567999, "loss": 0.03484335169196129, "avg_return": 0.8536220788955688, "regret": 0.011364289559423923, "entropy": 0.19745352864265442, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:54.335680Z", "loop": 3720, "env_steps": 2286182399, "loss": 0.03427702188491821, "avg_return": 0.8527418375015259, "regret": 0.010609538294374943, "entropy": 0.19650734961032867, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:55.188892Z", "loop": 3721, "env_steps": 2286796799, "loss": 0.03612271323800087, "avg_return": 0.8534175753593445, "regret": 0.010609538294374943, "entropy": 0.20079077780246735, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:56.041613Z", "loop": 3722, "env_steps": 2287411199, "loss": 0.03436846658587456, "avg_return": 0.8535220623016357, "regret": 0.010609538294374943, "entropy": 0.19827890396118164, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:56.895186Z", "loop": 3723, "env_steps": 2288025599, "loss": 0.03161170706152916, "avg_return": 0.8532137274742126, "regret": 0.010609538294374943, "entropy": 0.18945233523845673, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:57.749444Z", "loop": 3724, "env_steps": 2288639999, "loss": 0.03200444206595421, "avg_return": 0.8516690731048584, "regret": 0.010609538294374943, "entropy": 0.18592260777950287, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:58.603195Z", "loop": 3725, "env_steps": 2289254399, "loss": 0.030824635177850723, "avg_return": 0.8531576991081238, "regret": 0.010609538294374943, "entropy": 0.18189550936222076, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:16:59.456707Z", "loop": 3726, "env_steps": 2289868799, "loss": 0.030443985015153885, "avg_return": 0.8523736000061035, "regret": 0.010609538294374943, "entropy": 0.17455779016017914, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:00.309511Z", "loop": 3727, "env_steps": 2290483199, "loss": 0.03223093971610069, "avg_return": 0.8549562692642212, "regret": 0.010609538294374943, "entropy": 0.1858537197113037, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:01.163339Z", "loop": 3728, "env_steps": 2291097599, "loss": 0.02909247949719429, "avg_return": 0.8524919152259827, "regret": 0.010609538294374943, "entropy": 0.16499146819114685, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:02.016545Z", "loop": 3729, "env_steps": 2291711999, "loss": 0.031217599287629128, "avg_return": 0.8545196652412415, "regret": 0.010609538294374943, "entropy": 0.17655213177204132, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:02.909854Z", "loop": 3730, "env_steps": 2292326399, "loss": 0.0311909019947052, "avg_return": 0.8546265959739685, "regret": 0.010005306452512741, "entropy": 0.17844058573246002, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:03.763491Z", "loop": 3731, "env_steps": 2292940799, "loss": 0.030684946104884148, "avg_return": 0.8529666066169739, "regret": 0.010005306452512741, "entropy": 0.17757007479667664, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:04.617277Z", "loop": 3732, "env_steps": 2293555199, "loss": 0.0331556461751461, "avg_return": 0.8515729904174805, "regret": 0.010005306452512741, "entropy": 0.1864224523305893, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:05.471008Z", "loop": 3733, "env_steps": 2294169599, "loss": 0.03285921737551689, "avg_return": 0.8511627316474915, "regret": 0.010005306452512741, "entropy": 0.18682949244976044, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:06.324280Z", "loop": 3734, "env_steps": 2294783999, "loss": 0.03399495407938957, "avg_return": 0.8511808514595032, "regret": 0.010005306452512741, "entropy": 0.18506528437137604, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:07.177258Z", "loop": 3735, "env_steps": 2295398399, "loss": 0.031749945133924484, "avg_return": 0.8532254695892334, "regret": 0.010005306452512741, "entropy": 0.18118047714233398, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:08.030393Z", "loop": 3736, "env_steps": 2296012799, "loss": 0.030503317713737488, "avg_return": 0.8543644547462463, "regret": 0.010005306452512741, "entropy": 0.17749297618865967, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:08.883297Z", "loop": 3737, "env_steps": 2296627199, "loss": 0.031810641288757324, "avg_return": 0.8545079827308655, "regret": 0.010005306452512741, "entropy": 0.17751921713352203, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:09.737331Z", "loop": 3738, "env_steps": 2297241599, "loss": 0.029602257534861565, "avg_return": 0.8526423573493958, "regret": 0.010005306452512741, "entropy": 0.17355795204639435, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:10.592323Z", "loop": 3739, "env_steps": 2297855999, "loss": 0.030841803178191185, "avg_return": 0.852746307849884, "regret": 0.010005306452512741, "entropy": 0.17400281131267548, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:11.488803Z", "loop": 3740, "env_steps": 2298470399, "loss": 0.032147157937288284, "avg_return": 0.8537840247154236, "regret": 0.011007453314960003, "entropy": 0.17953956127166748, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:12.341288Z", "loop": 3741, "env_steps": 2299084799, "loss": 0.03192625567317009, "avg_return": 0.8523022532463074, "regret": 0.011007453314960003, "entropy": 0.18135786056518555, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:13.193770Z", "loop": 3742, "env_steps": 2299699199, "loss": 0.03251514956355095, "avg_return": 0.8519970178604126, "regret": 0.011007453314960003, "entropy": 0.17766979336738586, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:14.047368Z", "loop": 3743, "env_steps": 2300313599, "loss": 0.032671499997377396, "avg_return": 0.8522647023200989, "regret": 0.011007453314960003, "entropy": 0.17908962070941925, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:14.900962Z", "loop": 3744, "env_steps": 2300927999, "loss": 0.03234827145934105, "avg_return": 0.8511089086532593, "regret": 0.011007453314960003, "entropy": 0.17469282448291779, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:15.753933Z", "loop": 3745, "env_steps": 2301542399, "loss": 0.03176100179553032, "avg_return": 0.8526583313941956, "regret": 0.011007453314960003, "entropy": 0.18528692424297333, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:16.606639Z", "loop": 3746, "env_steps": 2302156799, "loss": 0.030374428257346153, "avg_return": 0.8516090512275696, "regret": 0.011007453314960003, "entropy": 0.17599987983703613, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:17.459933Z", "loop": 3747, "env_steps": 2302771199, "loss": 0.032616984099149704, "avg_return": 0.8513246178627014, "regret": 0.011007453314960003, "entropy": 0.18809548020362854, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:18.313823Z", "loop": 3748, "env_steps": 2303385599, "loss": 0.0333825945854187, "avg_return": 0.8491999506950378, "regret": 0.011007453314960003, "entropy": 0.19056765735149384, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:19.166722Z", "loop": 3749, "env_steps": 2303999999, "loss": 0.03381631523370743, "avg_return": 0.8485949039459229, "regret": 0.011007453314960003, "entropy": 0.1899750828742981, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:20.060513Z", "loop": 3750, "env_steps": 2304614399, "loss": 0.036435317248106, "avg_return": 0.8467959761619568, "regret": 0.015423067845404148, "entropy": 0.19414514303207397, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:20.913634Z", "loop": 3751, "env_steps": 2305228799, "loss": 0.03297490254044533, "avg_return": 0.8502148389816284, "regret": 0.015423067845404148, "entropy": 0.1928001344203949, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:21.768991Z", "loop": 3752, "env_steps": 2305843199, "loss": 0.03279251977801323, "avg_return": 0.8514174222946167, "regret": 0.015423067845404148, "entropy": 0.1853279322385788, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:22.622757Z", "loop": 3753, "env_steps": 2306457599, "loss": 0.03067193739116192, "avg_return": 0.8529781103134155, "regret": 0.015423067845404148, "entropy": 0.17786948382854462, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:23.475806Z", "loop": 3754, "env_steps": 2307071999, "loss": 0.030580846592783928, "avg_return": 0.8534444570541382, "regret": 0.015423067845404148, "entropy": 0.17632165551185608, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:24.328870Z", "loop": 3755, "env_steps": 2307686399, "loss": 0.031124351546168327, "avg_return": 0.8512928485870361, "regret": 0.015423067845404148, "entropy": 0.16892705857753754, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:25.182774Z", "loop": 3756, "env_steps": 2308300799, "loss": 0.030088577419519424, "avg_return": 0.8516008853912354, "regret": 0.015423067845404148, "entropy": 0.16176967322826385, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:26.036167Z", "loop": 3757, "env_steps": 2308915199, "loss": 0.030473848804831505, "avg_return": 0.8460866212844849, "regret": 0.015423067845404148, "entropy": 0.16908647119998932, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:26.888852Z", "loop": 3758, "env_steps": 2309529599, "loss": 0.031419966369867325, "avg_return": 0.8452130556106567, "regret": 0.015423067845404148, "entropy": 0.17928673326969147, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:27.741303Z", "loop": 3759, "env_steps": 2310143999, "loss": 0.03215653821825981, "avg_return": 0.8468737602233887, "regret": 0.015423067845404148, "entropy": 0.18108905851840973, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:28.636676Z", "loop": 3760, "env_steps": 2310758399, "loss": 0.03322555124759674, "avg_return": 0.8494112491607666, "regret": 0.014233613386750221, "entropy": 0.19219249486923218, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:29.491170Z", "loop": 3761, "env_steps": 2311372799, "loss": 0.034849654883146286, "avg_return": 0.8465399146080017, "regret": 0.014233613386750221, "entropy": 0.20217148959636688, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:30.345785Z", "loop": 3762, "env_steps": 2311987199, "loss": 0.03661469742655754, "avg_return": 0.8429419994354248, "regret": 0.014233613386750221, "entropy": 0.21045947074890137, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:31.199045Z", "loop": 3763, "env_steps": 2312601599, "loss": 0.034140657633543015, "avg_return": 0.8488512635231018, "regret": 0.014233613386750221, "entropy": 0.1969446986913681, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:32.053427Z", "loop": 3764, "env_steps": 2313215999, "loss": 0.03165000304579735, "avg_return": 0.8545565009117126, "regret": 0.014233613386750221, "entropy": 0.1807565689086914, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:32.908059Z", "loop": 3765, "env_steps": 2313830399, "loss": 0.031413864344358444, "avg_return": 0.8560546040534973, "regret": 0.014233613386750221, "entropy": 0.17304997146129608, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:33.760888Z", "loop": 3766, "env_steps": 2314444799, "loss": 0.030622536316514015, "avg_return": 0.8551478385925293, "regret": 0.014233613386750221, "entropy": 0.1735949069261551, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:34.613974Z", "loop": 3767, "env_steps": 2315059199, "loss": 0.032987963408231735, "avg_return": 0.851949155330658, "regret": 0.014233613386750221, "entropy": 0.17982204258441925, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:35.467072Z", "loop": 3768, "env_steps": 2315673599, "loss": 0.031669650226831436, "avg_return": 0.8491036295890808, "regret": 0.014233613386750221, "entropy": 0.18722976744174957, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:36.320324Z", "loop": 3769, "env_steps": 2316287999, "loss": 0.03306945785880089, "avg_return": 0.850064218044281, "regret": 0.014233613386750221, "entropy": 0.18545737862586975, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:37.213828Z", "loop": 3770, "env_steps": 2316902399, "loss": 0.03204301744699478, "avg_return": 0.8514617681503296, "regret": 0.013395257294178009, "entropy": 0.1787920743227005, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:38.068328Z", "loop": 3771, "env_steps": 2317516799, "loss": 0.03220859169960022, "avg_return": 0.8499293923377991, "regret": 0.013395257294178009, "entropy": 0.18020467460155487, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:38.923412Z", "loop": 3772, "env_steps": 2318131199, "loss": 0.03329463675618172, "avg_return": 0.8498156666755676, "regret": 0.013395257294178009, "entropy": 0.1826833188533783, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:39.778239Z", "loop": 3773, "env_steps": 2318745599, "loss": 0.03237208351492882, "avg_return": 0.8509131073951721, "regret": 0.013395257294178009, "entropy": 0.18015554547309875, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:40.632562Z", "loop": 3774, "env_steps": 2319359999, "loss": 0.03191693127155304, "avg_return": 0.8536577820777893, "regret": 0.013395257294178009, "entropy": 0.17736676335334778, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:41.485953Z", "loop": 3775, "env_steps": 2319974399, "loss": 0.029424969106912613, "avg_return": 0.8547393083572388, "regret": 0.013395257294178009, "entropy": 0.1711799055337906, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:42.339409Z", "loop": 3776, "env_steps": 2320588799, "loss": 0.030502429232001305, "avg_return": 0.8539205193519592, "regret": 0.013395257294178009, "entropy": 0.17067328095436096, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:43.192082Z", "loop": 3777, "env_steps": 2321203199, "loss": 0.030674433335661888, "avg_return": 0.8549644947052002, "regret": 0.013395257294178009, "entropy": 0.17609085142612457, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:44.044587Z", "loop": 3778, "env_steps": 2321817599, "loss": 0.030395878478884697, "avg_return": 0.8543905019760132, "regret": 0.013395257294178009, "entropy": 0.17849624156951904, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:44.898812Z", "loop": 3779, "env_steps": 2322431999, "loss": 0.030818117782473564, "avg_return": 0.8532881140708923, "regret": 0.013395257294178009, "entropy": 0.17768919467926025, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:45.792879Z", "loop": 3780, "env_steps": 2323046399, "loss": 0.03139747679233551, "avg_return": 0.851262629032135, "regret": 0.011636516079306602, "entropy": 0.1806582361459732, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:46.647462Z", "loop": 3781, "env_steps": 2323660799, "loss": 0.03132055327296257, "avg_return": 0.8506302237510681, "regret": 0.011636516079306602, "entropy": 0.18189822137355804, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:47.500992Z", "loop": 3782, "env_steps": 2324275199, "loss": 0.033120784908533096, "avg_return": 0.8509663939476013, "regret": 0.011636516079306602, "entropy": 0.18640857934951782, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:48.355342Z", "loop": 3783, "env_steps": 2324889599, "loss": 0.032847143709659576, "avg_return": 0.8504253625869751, "regret": 0.011636516079306602, "entropy": 0.1789909154176712, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:49.208902Z", "loop": 3784, "env_steps": 2325503999, "loss": 0.03128167986869812, "avg_return": 0.852975070476532, "regret": 0.011636516079306602, "entropy": 0.18159890174865723, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:50.061814Z", "loop": 3785, "env_steps": 2326118399, "loss": 0.031199147924780846, "avg_return": 0.8530621528625488, "regret": 0.011636516079306602, "entropy": 0.18691763281822205, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:50.915160Z", "loop": 3786, "env_steps": 2326732799, "loss": 0.030792782083153725, "avg_return": 0.8531666994094849, "regret": 0.011636516079306602, "entropy": 0.18501435220241547, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:51.769596Z", "loop": 3787, "env_steps": 2327347199, "loss": 0.033519815653562546, "avg_return": 0.8511096239089966, "regret": 0.011636516079306602, "entropy": 0.1910553127527237, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:52.624515Z", "loop": 3788, "env_steps": 2327961599, "loss": 0.032072488218545914, "avg_return": 0.8531836867332458, "regret": 0.011636516079306602, "entropy": 0.17895276844501495, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:53.478245Z", "loop": 3789, "env_steps": 2328575999, "loss": 0.031408753246068954, "avg_return": 0.8527677655220032, "regret": 0.011636516079306602, "entropy": 0.18427635729312897, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:54.371305Z", "loop": 3790, "env_steps": 2329190399, "loss": 0.030767962336540222, "avg_return": 0.8551157116889954, "regret": 0.00899612344801426, "entropy": 0.1775892972946167, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:55.225704Z", "loop": 3791, "env_steps": 2329804799, "loss": 0.030426347628235817, "avg_return": 0.8547906875610352, "regret": 0.00899612344801426, "entropy": 0.17340418696403503, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:56.079885Z", "loop": 3792, "env_steps": 2330419199, "loss": 0.02843332104384899, "avg_return": 0.8542641401290894, "regret": 0.00899612344801426, "entropy": 0.1697133481502533, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:56.933510Z", "loop": 3793, "env_steps": 2331033599, "loss": 0.029910007491707802, "avg_return": 0.8537946939468384, "regret": 0.00899612344801426, "entropy": 0.16676579415798187, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:57.786922Z", "loop": 3794, "env_steps": 2331647999, "loss": 0.03173868730664253, "avg_return": 0.8522002100944519, "regret": 0.00899612344801426, "entropy": 0.17163001000881195, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:58.640897Z", "loop": 3795, "env_steps": 2332262399, "loss": 0.029261166229844093, "avg_return": 0.852666974067688, "regret": 0.00899612344801426, "entropy": 0.1686185598373413, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:17:59.494254Z", "loop": 3796, "env_steps": 2332876799, "loss": 0.02899337187409401, "avg_return": 0.8539780974388123, "regret": 0.00899612344801426, "entropy": 0.16361494362354279, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:00.348303Z", "loop": 3797, "env_steps": 2333491199, "loss": 0.02918856404721737, "avg_return": 0.8547328114509583, "regret": 0.00899612344801426, "entropy": 0.1610098034143448, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:01.201384Z", "loop": 3798, "env_steps": 2334105599, "loss": 0.027440747246146202, "avg_return": 0.8560144305229187, "regret": 0.00899612344801426, "entropy": 0.1605873554944992, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:02.055320Z", "loop": 3799, "env_steps": 2334719999, "loss": 0.02856854908168316, "avg_return": 0.8562577366828918, "regret": 0.00899612344801426, "entropy": 0.1738234907388687, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:02.949147Z", "loop": 3800, "env_steps": 2335334399, "loss": 0.03065088763833046, "avg_return": 0.855148434638977, "regret": 0.008479529060423374, "entropy": 0.17478381097316742, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:03.803416Z", "loop": 3801, "env_steps": 2335948799, "loss": 0.03242642804980278, "avg_return": 0.8555855751037598, "regret": 0.008479529060423374, "entropy": 0.17936699092388153, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:04.657907Z", "loop": 3802, "env_steps": 2336563199, "loss": 0.0307941772043705, "avg_return": 0.8554905652999878, "regret": 0.008479529060423374, "entropy": 0.17071019113063812, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:05.512848Z", "loop": 3803, "env_steps": 2337177599, "loss": 0.029530305415391922, "avg_return": 0.8552138209342957, "regret": 0.008479529060423374, "entropy": 0.1683250516653061, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:06.365234Z", "loop": 3804, "env_steps": 2337791999, "loss": 0.029378367587924004, "avg_return": 0.8546457290649414, "regret": 0.008479529060423374, "entropy": 0.16662220656871796, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:07.217742Z", "loop": 3805, "env_steps": 2338406399, "loss": 0.02889006771147251, "avg_return": 0.8564929366111755, "regret": 0.008479529060423374, "entropy": 0.1599254310131073, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:08.071099Z", "loop": 3806, "env_steps": 2339020799, "loss": 0.02827705256640911, "avg_return": 0.8567277193069458, "regret": 0.008479529060423374, "entropy": 0.16218681633472443, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:08.925489Z", "loop": 3807, "env_steps": 2339635199, "loss": 0.029675260186195374, "avg_return": 0.8555942177772522, "regret": 0.008479529060423374, "entropy": 0.1680753231048584, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:09.778653Z", "loop": 3808, "env_steps": 2340249599, "loss": 0.029151618480682373, "avg_return": 0.8550696969032288, "regret": 0.008479529060423374, "entropy": 0.16610927879810333, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:10.631321Z", "loop": 3809, "env_steps": 2340863999, "loss": 0.026720548048615456, "avg_return": 0.8561021089553833, "regret": 0.008479529060423374, "entropy": 0.1572689712047577, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:11.524653Z", "loop": 3810, "env_steps": 2341478399, "loss": 0.028586197644472122, "avg_return": 0.8559499382972717, "regret": 0.0073806787841022015, "entropy": 0.1579202264547348, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:12.379101Z", "loop": 3811, "env_steps": 2342092799, "loss": 0.026857206597924232, "avg_return": 0.8554376363754272, "regret": 0.0073806787841022015, "entropy": 0.1593741476535797, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:13.233989Z", "loop": 3812, "env_steps": 2342707199, "loss": 0.029123580083251, "avg_return": 0.8552746772766113, "regret": 0.0073806787841022015, "entropy": 0.15863437950611115, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:14.086899Z", "loop": 3813, "env_steps": 2343321599, "loss": 0.025913476943969727, "avg_return": 0.8553459048271179, "regret": 0.0073806787841022015, "entropy": 0.15119799971580505, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:14.940131Z", "loop": 3814, "env_steps": 2343935999, "loss": 0.027976742014288902, "avg_return": 0.8532810211181641, "regret": 0.0073806787841022015, "entropy": 0.1564454883337021, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:15.794478Z", "loop": 3815, "env_steps": 2344550399, "loss": 0.026884540915489197, "avg_return": 0.8535128235816956, "regret": 0.0073806787841022015, "entropy": 0.14895814657211304, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:16.647751Z", "loop": 3816, "env_steps": 2345164799, "loss": 0.02838638797402382, "avg_return": 0.853729784488678, "regret": 0.0073806787841022015, "entropy": 0.15483583509922028, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:17.501036Z", "loop": 3817, "env_steps": 2345779199, "loss": 0.028131598606705666, "avg_return": 0.8536847233772278, "regret": 0.0073806787841022015, "entropy": 0.1591467261314392, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:18.353598Z", "loop": 3818, "env_steps": 2346393599, "loss": 0.03003021515905857, "avg_return": 0.8505438566207886, "regret": 0.0073806787841022015, "entropy": 0.16303078830242157, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:19.207170Z", "loop": 3819, "env_steps": 2347007999, "loss": 0.029021045193076134, "avg_return": 0.8509462475776672, "regret": 0.0073806787841022015, "entropy": 0.1643979251384735, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:20.100312Z", "loop": 3820, "env_steps": 2347622399, "loss": 0.027781857177615166, "avg_return": 0.8528445363044739, "regret": 0.011303535662591457, "entropy": 0.16432614624500275, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:20.953669Z", "loop": 3821, "env_steps": 2348236799, "loss": 0.030690519139170647, "avg_return": 0.8536009192466736, "regret": 0.011303535662591457, "entropy": 0.17045652866363525, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:21.806078Z", "loop": 3822, "env_steps": 2348851199, "loss": 0.028639307245612144, "avg_return": 0.854114830493927, "regret": 0.011303535662591457, "entropy": 0.16206756234169006, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:22.659702Z", "loop": 3823, "env_steps": 2349465599, "loss": 0.028145236894488335, "avg_return": 0.8551808595657349, "regret": 0.011303535662591457, "entropy": 0.16368621587753296, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:23.513229Z", "loop": 3824, "env_steps": 2350079999, "loss": 0.029544537886977196, "avg_return": 0.8531410098075867, "regret": 0.011303535662591457, "entropy": 0.1646890789270401, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:24.366937Z", "loop": 3825, "env_steps": 2350694399, "loss": 0.02771752141416073, "avg_return": 0.8566988110542297, "regret": 0.011303535662591457, "entropy": 0.1583596020936966, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:25.220767Z", "loop": 3826, "env_steps": 2351308799, "loss": 0.027301330119371414, "avg_return": 0.855118453502655, "regret": 0.011303535662591457, "entropy": 0.15593387186527252, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:26.075130Z", "loop": 3827, "env_steps": 2351923199, "loss": 0.025608718395233154, "avg_return": 0.8557137250900269, "regret": 0.011303535662591457, "entropy": 0.15554867684841156, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:26.928878Z", "loop": 3828, "env_steps": 2352537599, "loss": 0.028601765632629395, "avg_return": 0.8562454581260681, "regret": 0.011303535662591457, "entropy": 0.16465628147125244, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:27.782441Z", "loop": 3829, "env_steps": 2353151999, "loss": 0.027439409866929054, "avg_return": 0.8554563522338867, "regret": 0.011303535662591457, "entropy": 0.16120311617851257, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:28.674769Z", "loop": 3830, "env_steps": 2353766399, "loss": 0.029739851132035255, "avg_return": 0.8535032272338867, "regret": 0.010815467685461044, "entropy": 0.17065460979938507, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:29.528153Z", "loop": 3831, "env_steps": 2354380799, "loss": 0.030431708320975304, "avg_return": 0.8510407209396362, "regret": 0.010815467685461044, "entropy": 0.17425718903541565, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:30.381577Z", "loop": 3832, "env_steps": 2354995199, "loss": 0.03131621703505516, "avg_return": 0.850916862487793, "regret": 0.010815467685461044, "entropy": 0.1790391504764557, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:31.234755Z", "loop": 3833, "env_steps": 2355609599, "loss": 0.034773170948028564, "avg_return": 0.847717821598053, "regret": 0.010815467685461044, "entropy": 0.18807213008403778, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:32.088363Z", "loop": 3834, "env_steps": 2356223999, "loss": 0.03200417757034302, "avg_return": 0.8498660326004028, "regret": 0.010815467685461044, "entropy": 0.1754998117685318, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:32.942611Z", "loop": 3835, "env_steps": 2356838399, "loss": 0.03045273758471012, "avg_return": 0.8532503247261047, "regret": 0.010815467685461044, "entropy": 0.17375636100769043, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:33.796733Z", "loop": 3836, "env_steps": 2357452799, "loss": 0.029997995123267174, "avg_return": 0.8556751608848572, "regret": 0.010815467685461044, "entropy": 0.170273095369339, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:34.650092Z", "loop": 3837, "env_steps": 2358067199, "loss": 0.028557507321238518, "avg_return": 0.8557707071304321, "regret": 0.010815467685461044, "entropy": 0.1627599447965622, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:35.503846Z", "loop": 3838, "env_steps": 2358681599, "loss": 0.029126901179552078, "avg_return": 0.8545522093772888, "regret": 0.010815467685461044, "entropy": 0.1764041930437088, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:36.357263Z", "loop": 3839, "env_steps": 2359295999, "loss": 0.03296219930052757, "avg_return": 0.8529193997383118, "regret": 0.010815467685461044, "entropy": 0.189407616853714, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:37.253990Z", "loop": 3840, "env_steps": 2359910399, "loss": 0.03182632103562355, "avg_return": 0.8532259464263916, "regret": 0.010269916616380215, "entropy": 0.18359389901161194, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:38.106698Z", "loop": 3841, "env_steps": 2360524799, "loss": 0.03180857002735138, "avg_return": 0.852725625038147, "regret": 0.010269916616380215, "entropy": 0.17825153470039368, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:38.961039Z", "loop": 3842, "env_steps": 2361139199, "loss": 0.031452689319849014, "avg_return": 0.8532596826553345, "regret": 0.010269916616380215, "entropy": 0.18230260908603668, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:39.815692Z", "loop": 3843, "env_steps": 2361753599, "loss": 0.02989562228322029, "avg_return": 0.8528128266334534, "regret": 0.010269916616380215, "entropy": 0.17924946546554565, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:40.668854Z", "loop": 3844, "env_steps": 2362367999, "loss": 0.032104115933179855, "avg_return": 0.8522501587867737, "regret": 0.010269916616380215, "entropy": 0.1843157708644867, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:41.521771Z", "loop": 3845, "env_steps": 2362982399, "loss": 0.031095415353775024, "avg_return": 0.8509389162063599, "regret": 0.010269916616380215, "entropy": 0.1787978559732437, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:42.375430Z", "loop": 3846, "env_steps": 2363596799, "loss": 0.030654162168502808, "avg_return": 0.8536199927330017, "regret": 0.010269916616380215, "entropy": 0.1793113648891449, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:43.229193Z", "loop": 3847, "env_steps": 2364211199, "loss": 0.029328688979148865, "avg_return": 0.8556925654411316, "regret": 0.010269916616380215, "entropy": 0.16811688244342804, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:44.083267Z", "loop": 3848, "env_steps": 2364825599, "loss": 0.028728056699037552, "avg_return": 0.8549672365188599, "regret": 0.010269916616380215, "entropy": 0.16395783424377441, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:44.935346Z", "loop": 3849, "env_steps": 2365439999, "loss": 0.028439436107873917, "avg_return": 0.8549909591674805, "regret": 0.010269916616380215, "entropy": 0.1644551008939743, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:45.828313Z", "loop": 3850, "env_steps": 2366054399, "loss": 0.028937799856066704, "avg_return": 0.8549627661705017, "regret": 0.007993057370185852, "entropy": 0.16604001820087433, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:46.681583Z", "loop": 3851, "env_steps": 2366668799, "loss": 0.028969382867217064, "avg_return": 0.8558911085128784, "regret": 0.007993057370185852, "entropy": 0.16272753477096558, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:47.535188Z", "loop": 3852, "env_steps": 2367283199, "loss": 0.027059538289904594, "avg_return": 0.8558002710342407, "regret": 0.007993057370185852, "entropy": 0.15611805021762848, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:48.388644Z", "loop": 3853, "env_steps": 2367897599, "loss": 0.028663793578743935, "avg_return": 0.8564300537109375, "regret": 0.007993057370185852, "entropy": 0.1648859679698944, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:49.242278Z", "loop": 3854, "env_steps": 2368511999, "loss": 0.029351655393838882, "avg_return": 0.8556410670280457, "regret": 0.007993057370185852, "entropy": 0.1623883992433548, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:50.095648Z", "loop": 3855, "env_steps": 2369126399, "loss": 0.028447842225432396, "avg_return": 0.8549171090126038, "regret": 0.007993057370185852, "entropy": 0.15736043453216553, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:50.949331Z", "loop": 3856, "env_steps": 2369740799, "loss": 0.0281288530677557, "avg_return": 0.8567798137664795, "regret": 0.007993057370185852, "entropy": 0.1596178263425827, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:51.802519Z", "loop": 3857, "env_steps": 2370355199, "loss": 0.02712785080075264, "avg_return": 0.8561788201332092, "regret": 0.007993057370185852, "entropy": 0.15856610238552094, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:52.656065Z", "loop": 3858, "env_steps": 2370969599, "loss": 0.028900420293211937, "avg_return": 0.8558844327926636, "regret": 0.007993057370185852, "entropy": 0.15647326409816742, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:53.508621Z", "loop": 3859, "env_steps": 2371583999, "loss": 0.02930879034101963, "avg_return": 0.8558424115180969, "regret": 0.007993057370185852, "entropy": 0.16070792078971863, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:54.402395Z", "loop": 3860, "env_steps": 2372198399, "loss": 0.03031753934919834, "avg_return": 0.8551865816116333, "regret": 0.007772418670356274, "entropy": 0.1701679527759552, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:55.257444Z", "loop": 3861, "env_steps": 2372812799, "loss": 0.028954943642020226, "avg_return": 0.8549613356590271, "regret": 0.007772418670356274, "entropy": 0.16475602984428406, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:56.111753Z", "loop": 3862, "env_steps": 2373427199, "loss": 0.02917356789112091, "avg_return": 0.8567237257957458, "regret": 0.007772418670356274, "entropy": 0.1660747230052948, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:56.965160Z", "loop": 3863, "env_steps": 2374041599, "loss": 0.02828526869416237, "avg_return": 0.8540198802947998, "regret": 0.007772418670356274, "entropy": 0.16792218387126923, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:57.818843Z", "loop": 3864, "env_steps": 2374655999, "loss": 0.030214084312319756, "avg_return": 0.852465808391571, "regret": 0.007772418670356274, "entropy": 0.17133980989456177, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:58.672314Z", "loop": 3865, "env_steps": 2375270399, "loss": 0.03068421594798565, "avg_return": 0.8549609780311584, "regret": 0.007772418670356274, "entropy": 0.16863197088241577, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:18:59.526540Z", "loop": 3866, "env_steps": 2375884799, "loss": 0.029946057125926018, "avg_return": 0.8568263053894043, "regret": 0.007772418670356274, "entropy": 0.17369772493839264, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:00.379861Z", "loop": 3867, "env_steps": 2376499199, "loss": 0.029686568304896355, "avg_return": 0.8549261689186096, "regret": 0.007772418670356274, "entropy": 0.17313306033611298, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:01.232528Z", "loop": 3868, "env_steps": 2377113599, "loss": 0.02878345549106598, "avg_return": 0.855044960975647, "regret": 0.007772418670356274, "entropy": 0.17433381080627441, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:02.085939Z", "loop": 3869, "env_steps": 2377727999, "loss": 0.030546290799975395, "avg_return": 0.8547888398170471, "regret": 0.007772418670356274, "entropy": 0.1765308529138565, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:02.980697Z", "loop": 3870, "env_steps": 2378342399, "loss": 0.030165472999215126, "avg_return": 0.8529490232467651, "regret": 0.010184070095419884, "entropy": 0.1754654049873352, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:03.834534Z", "loop": 3871, "env_steps": 2378956799, "loss": 0.03097633458673954, "avg_return": 0.8519704937934875, "regret": 0.010184070095419884, "entropy": 0.17687617242336273, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:04.686300Z", "loop": 3872, "env_steps": 2379571199, "loss": 0.03133218362927437, "avg_return": 0.8496882915496826, "regret": 0.010184070095419884, "entropy": 0.17344462871551514, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:05.538602Z", "loop": 3873, "env_steps": 2380185599, "loss": 0.03329108655452728, "avg_return": 0.850949227809906, "regret": 0.010184070095419884, "entropy": 0.18088676035404205, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:06.392193Z", "loop": 3874, "env_steps": 2380799999, "loss": 0.03381733223795891, "avg_return": 0.8510831594467163, "regret": 0.010184070095419884, "entropy": 0.17782872915267944, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:07.246308Z", "loop": 3875, "env_steps": 2381414399, "loss": 0.033282484859228134, "avg_return": 0.8522130250930786, "regret": 0.010184070095419884, "entropy": 0.1809314489364624, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:08.099144Z", "loop": 3876, "env_steps": 2382028799, "loss": 0.031536493450403214, "avg_return": 0.853456437587738, "regret": 0.010184070095419884, "entropy": 0.17613796889781952, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:08.951423Z", "loop": 3877, "env_steps": 2382643199, "loss": 0.03130055591464043, "avg_return": 0.8549376726150513, "regret": 0.010184070095419884, "entropy": 0.1736256331205368, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:09.804396Z", "loop": 3878, "env_steps": 2383257599, "loss": 0.03167223557829857, "avg_return": 0.8545701503753662, "regret": 0.010184070095419884, "entropy": 0.1809197962284088, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:10.658259Z", "loop": 3879, "env_steps": 2383871999, "loss": 0.030937811359763145, "avg_return": 0.8537299633026123, "regret": 0.010184070095419884, "entropy": 0.17705988883972168, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:11.552365Z", "loop": 3880, "env_steps": 2384486399, "loss": 0.03344572335481644, "avg_return": 0.8529945015907288, "regret": 0.010826684534549713, "entropy": 0.18071800470352173, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:12.405121Z", "loop": 3881, "env_steps": 2385100799, "loss": 0.02890240214765072, "avg_return": 0.8543113470077515, "regret": 0.010826684534549713, "entropy": 0.16730506718158722, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:13.257725Z", "loop": 3882, "env_steps": 2385715199, "loss": 0.029031921178102493, "avg_return": 0.8573317527770996, "regret": 0.010826684534549713, "entropy": 0.16186262667179108, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:14.110926Z", "loop": 3883, "env_steps": 2386329599, "loss": 0.026753315702080727, "avg_return": 0.8575145602226257, "regret": 0.010826684534549713, "entropy": 0.1542881727218628, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:14.964926Z", "loop": 3884, "env_steps": 2386943999, "loss": 0.02847418002784252, "avg_return": 0.8548608422279358, "regret": 0.010826684534549713, "entropy": 0.16516762971878052, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:15.818246Z", "loop": 3885, "env_steps": 2387558399, "loss": 0.030765509232878685, "avg_return": 0.8506411910057068, "regret": 0.010826684534549713, "entropy": 0.16638974845409393, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:16.671573Z", "loop": 3886, "env_steps": 2388172799, "loss": 0.030128149315714836, "avg_return": 0.8501675724983215, "regret": 0.010826684534549713, "entropy": 0.1633777618408203, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:17.524667Z", "loop": 3887, "env_steps": 2388787199, "loss": 0.0305353794246912, "avg_return": 0.8505992889404297, "regret": 0.010826684534549713, "entropy": 0.1615210622549057, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:18.378262Z", "loop": 3888, "env_steps": 2389401599, "loss": 0.03172215074300766, "avg_return": 0.8507891893386841, "regret": 0.010826684534549713, "entropy": 0.166848823428154, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:19.231630Z", "loop": 3889, "env_steps": 2390015999, "loss": 0.02827703021466732, "avg_return": 0.8553776144981384, "regret": 0.010826684534549713, "entropy": 0.15629130601882935, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:20.125214Z", "loop": 3890, "env_steps": 2390630399, "loss": 0.029002878814935684, "avg_return": 0.856401264667511, "regret": 0.007747779134660959, "entropy": 0.16062292456626892, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:20.979986Z", "loop": 3891, "env_steps": 2391244799, "loss": 0.029673879966139793, "avg_return": 0.8548570871353149, "regret": 0.007747779134660959, "entropy": 0.167793869972229, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:21.834099Z", "loop": 3892, "env_steps": 2391859199, "loss": 0.030184730887413025, "avg_return": 0.8549450635910034, "regret": 0.007747779134660959, "entropy": 0.1751043051481247, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:22.688237Z", "loop": 3893, "env_steps": 2392473599, "loss": 0.03391942009329796, "avg_return": 0.853805661201477, "regret": 0.007747779134660959, "entropy": 0.18743127584457397, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:23.540951Z", "loop": 3894, "env_steps": 2393087999, "loss": 0.03218202292919159, "avg_return": 0.8544397950172424, "regret": 0.007747779134660959, "entropy": 0.1776532232761383, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:24.395670Z", "loop": 3895, "env_steps": 2393702399, "loss": 0.02976739965379238, "avg_return": 0.8553974628448486, "regret": 0.007747779134660959, "entropy": 0.16556623578071594, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:25.249199Z", "loop": 3896, "env_steps": 2394316799, "loss": 0.029652372002601624, "avg_return": 0.8571817278862, "regret": 0.007747779134660959, "entropy": 0.16635075211524963, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:26.102986Z", "loop": 3897, "env_steps": 2394931199, "loss": 0.028227312490344048, "avg_return": 0.8569151163101196, "regret": 0.007747779134660959, "entropy": 0.15781106054782867, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:26.956274Z", "loop": 3898, "env_steps": 2395545599, "loss": 0.02762795053422451, "avg_return": 0.8567736744880676, "regret": 0.007747779134660959, "entropy": 0.15387780964374542, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:27.809268Z", "loop": 3899, "env_steps": 2396159999, "loss": 0.025763127952814102, "avg_return": 0.8562055826187134, "regret": 0.007747779134660959, "entropy": 0.15146984159946442, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:28.703760Z", "loop": 3900, "env_steps": 2396774399, "loss": 0.02578836679458618, "avg_return": 0.8549036979675293, "regret": 0.006786183454096317, "entropy": 0.1450672447681427, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:29.557185Z", "loop": 3901, "env_steps": 2397388799, "loss": 0.02538173273205757, "avg_return": 0.8553674817085266, "regret": 0.006786183454096317, "entropy": 0.14067958295345306, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:30.410374Z", "loop": 3902, "env_steps": 2398003199, "loss": 0.02571873739361763, "avg_return": 0.8563403487205505, "regret": 0.006786183454096317, "entropy": 0.14713360369205475, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:31.263210Z", "loop": 3903, "env_steps": 2398617599, "loss": 0.026464609429240227, "avg_return": 0.8554056286811829, "regret": 0.006786183454096317, "entropy": 0.14686743915081024, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:32.117809Z", "loop": 3904, "env_steps": 2399231999, "loss": 0.025272933766245842, "avg_return": 0.8537459373474121, "regret": 0.006786183454096317, "entropy": 0.14325283467769623, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:32.971901Z", "loop": 3905, "env_steps": 2399846399, "loss": 0.027315635234117508, "avg_return": 0.8568152785301208, "regret": 0.006786183454096317, "entropy": 0.15215930342674255, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:33.825763Z", "loop": 3906, "env_steps": 2400460799, "loss": 0.028448471799492836, "avg_return": 0.8544806241989136, "regret": 0.006786183454096317, "entropy": 0.15666945278644562, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:34.678637Z", "loop": 3907, "env_steps": 2401075199, "loss": 0.02730047143995762, "avg_return": 0.8526341319084167, "regret": 0.006786183454096317, "entropy": 0.15381205081939697, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:35.533117Z", "loop": 3908, "env_steps": 2401689599, "loss": 0.029423106461763382, "avg_return": 0.8501039147377014, "regret": 0.006786183454096317, "entropy": 0.16036386787891388, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:36.386466Z", "loop": 3909, "env_steps": 2402303999, "loss": 0.030915027484297752, "avg_return": 0.8504520058631897, "regret": 0.006786183454096317, "entropy": 0.16611923277378082, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:37.280499Z", "loop": 3910, "env_steps": 2402918399, "loss": 0.030744442716240883, "avg_return": 0.8489975929260254, "regret": 0.013517476618289948, "entropy": 0.16279956698417664, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:38.134161Z", "loop": 3911, "env_steps": 2403532799, "loss": 0.03081049583852291, "avg_return": 0.8510611057281494, "regret": 0.013517476618289948, "entropy": 0.16493655741214752, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:38.988444Z", "loop": 3912, "env_steps": 2404147199, "loss": 0.02810218743979931, "avg_return": 0.8530334234237671, "regret": 0.013517476618289948, "entropy": 0.15344487130641937, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:39.841720Z", "loop": 3913, "env_steps": 2404761599, "loss": 0.028332803398370743, "avg_return": 0.8554321527481079, "regret": 0.013517476618289948, "entropy": 0.15606658160686493, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:40.694857Z", "loop": 3914, "env_steps": 2405375999, "loss": 0.026759082451462746, "avg_return": 0.8563043475151062, "regret": 0.013517476618289948, "entropy": 0.1529785543680191, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:41.548087Z", "loop": 3915, "env_steps": 2405990399, "loss": 0.026386281475424767, "avg_return": 0.8567143082618713, "regret": 0.013517476618289948, "entropy": 0.15048274397850037, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:42.402242Z", "loop": 3916, "env_steps": 2406604799, "loss": 0.027546003460884094, "avg_return": 0.8561004996299744, "regret": 0.013517476618289948, "entropy": 0.152530238032341, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:43.254538Z", "loop": 3917, "env_steps": 2407219199, "loss": 0.02689882554113865, "avg_return": 0.8558956980705261, "regret": 0.013517476618289948, "entropy": 0.15595528483390808, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:44.106893Z", "loop": 3918, "env_steps": 2407833599, "loss": 0.027844129130244255, "avg_return": 0.8541945815086365, "regret": 0.013517476618289948, "entropy": 0.15820518136024475, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:44.960471Z", "loop": 3919, "env_steps": 2408447999, "loss": 0.02896873652935028, "avg_return": 0.8520887494087219, "regret": 0.013517476618289948, "entropy": 0.16536016762256622, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:45.854609Z", "loop": 3920, "env_steps": 2409062399, "loss": 0.02939889207482338, "avg_return": 0.8497220277786255, "regret": 0.013277238234877586, "entropy": 0.16594254970550537, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:46.708576Z", "loop": 3921, "env_steps": 2409676799, "loss": 0.031081486493349075, "avg_return": 0.8510225415229797, "regret": 0.013277238234877586, "entropy": 0.17300082743167877, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:47.562866Z", "loop": 3922, "env_steps": 2410291199, "loss": 0.027867106720805168, "avg_return": 0.8537294864654541, "regret": 0.013277238234877586, "entropy": 0.15934856235980988, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:48.417309Z", "loop": 3923, "env_steps": 2410905599, "loss": 0.027751151472330093, "avg_return": 0.8545365333557129, "regret": 0.013277238234877586, "entropy": 0.15470770001411438, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:49.271049Z", "loop": 3924, "env_steps": 2411519999, "loss": 0.02750116027891636, "avg_return": 0.8568999171257019, "regret": 0.013277238234877586, "entropy": 0.1503189355134964, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:50.125303Z", "loop": 3925, "env_steps": 2412134399, "loss": 0.02719459868967533, "avg_return": 0.8560517430305481, "regret": 0.013277238234877586, "entropy": 0.14826127886772156, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:50.978846Z", "loop": 3926, "env_steps": 2412748799, "loss": 0.027714146301150322, "avg_return": 0.8550592064857483, "regret": 0.013277238234877586, "entropy": 0.15299715101718903, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:51.832983Z", "loop": 3927, "env_steps": 2413363199, "loss": 0.031054913997650146, "avg_return": 0.8536714911460876, "regret": 0.013277238234877586, "entropy": 0.1617586463689804, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:52.686722Z", "loop": 3928, "env_steps": 2413977599, "loss": 0.029999399557709694, "avg_return": 0.8526947498321533, "regret": 0.013277238234877586, "entropy": 0.16784964501857758, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:53.540100Z", "loop": 3929, "env_steps": 2414591999, "loss": 0.03022177331149578, "avg_return": 0.8490385413169861, "regret": 0.013277238234877586, "entropy": 0.16328196227550507, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:54.434691Z", "loop": 3930, "env_steps": 2415206399, "loss": 0.03472740203142166, "avg_return": 0.8469255566596985, "regret": 0.015523656271398067, "entropy": 0.1767345517873764, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:55.288047Z", "loop": 3931, "env_steps": 2415820799, "loss": 0.03434574976563454, "avg_return": 0.8480938076972961, "regret": 0.015523656271398067, "entropy": 0.18318748474121094, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:56.142353Z", "loop": 3932, "env_steps": 2416435199, "loss": 0.03256722912192345, "avg_return": 0.8490107655525208, "regret": 0.015523656271398067, "entropy": 0.17588219046592712, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:56.995767Z", "loop": 3933, "env_steps": 2417049599, "loss": 0.0318436473608017, "avg_return": 0.8516560196876526, "regret": 0.015523656271398067, "entropy": 0.1680786907672882, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:57.849120Z", "loop": 3934, "env_steps": 2417663999, "loss": 0.028859486803412437, "avg_return": 0.8534926772117615, "regret": 0.015523656271398067, "entropy": 0.16353556513786316, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:58.703057Z", "loop": 3935, "env_steps": 2418278399, "loss": 0.02894926443696022, "avg_return": 0.8549563884735107, "regret": 0.015523656271398067, "entropy": 0.1609719842672348, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:19:59.557068Z", "loop": 3936, "env_steps": 2418892799, "loss": 0.028590697795152664, "avg_return": 0.8563029170036316, "regret": 0.015523656271398067, "entropy": 0.15875089168548584, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:00.410870Z", "loop": 3937, "env_steps": 2419507199, "loss": 0.028804926201701164, "avg_return": 0.8547692894935608, "regret": 0.015523656271398067, "entropy": 0.16107191145420074, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:01.264140Z", "loop": 3938, "env_steps": 2420121599, "loss": 0.027222050353884697, "avg_return": 0.8571569919586182, "regret": 0.015523656271398067, "entropy": 0.15525241196155548, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:02.117752Z", "loop": 3939, "env_steps": 2420735999, "loss": 0.024330787360668182, "avg_return": 0.857693076133728, "regret": 0.015523656271398067, "entropy": 0.14513471722602844, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:03.014399Z", "loop": 3940, "env_steps": 2421350399, "loss": 0.026478826999664307, "avg_return": 0.8573482632637024, "regret": 0.006461809854954481, "entropy": 0.15119369328022003, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:03.870362Z", "loop": 3941, "env_steps": 2421964799, "loss": 0.027242425829172134, "avg_return": 0.855427086353302, "regret": 0.006461809854954481, "entropy": 0.15383268892765045, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:04.724750Z", "loop": 3942, "env_steps": 2422579199, "loss": 0.025507209822535515, "avg_return": 0.8562520742416382, "regret": 0.006461809854954481, "entropy": 0.15036240220069885, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:05.579654Z", "loop": 3943, "env_steps": 2423193599, "loss": 0.026716500520706177, "avg_return": 0.8572242259979248, "regret": 0.006461809854954481, "entropy": 0.15032008290290833, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:06.433883Z", "loop": 3944, "env_steps": 2423807999, "loss": 0.02602287009358406, "avg_return": 0.8579000234603882, "regret": 0.006461809854954481, "entropy": 0.1468992978334427, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:07.289032Z", "loop": 3945, "env_steps": 2424422399, "loss": 0.02448229491710663, "avg_return": 0.8578770160675049, "regret": 0.006461809854954481, "entropy": 0.1434500366449356, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:08.144097Z", "loop": 3946, "env_steps": 2425036799, "loss": 0.02516232244670391, "avg_return": 0.8586304187774658, "regret": 0.006461809854954481, "entropy": 0.14390859007835388, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:08.997808Z", "loop": 3947, "env_steps": 2425651199, "loss": 0.026819854974746704, "avg_return": 0.8573766350746155, "regret": 0.006461809854954481, "entropy": 0.15117569267749786, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:09.850487Z", "loop": 3948, "env_steps": 2426265599, "loss": 0.02717452682554722, "avg_return": 0.8550315499305725, "regret": 0.006461809854954481, "entropy": 0.1586793065071106, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:10.704245Z", "loop": 3949, "env_steps": 2426879999, "loss": 0.028512105345726013, "avg_return": 0.8538812398910522, "regret": 0.006461809854954481, "entropy": 0.16025839745998383, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:11.599861Z", "loop": 3950, "env_steps": 2427494399, "loss": 0.029545500874519348, "avg_return": 0.8534495234489441, "regret": 0.00991387851536274, "entropy": 0.16223523020744324, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:12.453862Z", "loop": 3951, "env_steps": 2428108799, "loss": 0.026836315169930458, "avg_return": 0.8553065061569214, "regret": 0.00991387851536274, "entropy": 0.16025115549564362, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:13.308413Z", "loop": 3952, "env_steps": 2428723199, "loss": 0.02864319086074829, "avg_return": 0.8559308052062988, "regret": 0.00991387851536274, "entropy": 0.159556046128273, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:14.162097Z", "loop": 3953, "env_steps": 2429337599, "loss": 0.026403134688735008, "avg_return": 0.856968104839325, "regret": 0.00991387851536274, "entropy": 0.1537083089351654, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:15.016198Z", "loop": 3954, "env_steps": 2429951999, "loss": 0.024922287091612816, "avg_return": 0.8573874235153198, "regret": 0.00991387851536274, "entropy": 0.14533944427967072, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:15.869749Z", "loop": 3955, "env_steps": 2430566399, "loss": 0.025012046098709106, "avg_return": 0.8585212230682373, "regret": 0.00991387851536274, "entropy": 0.1476803719997406, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:16.724430Z", "loop": 3956, "env_steps": 2431180799, "loss": 0.026344729587435722, "avg_return": 0.8562093377113342, "regret": 0.00991387851536274, "entropy": 0.14603666961193085, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:17.578489Z", "loop": 3957, "env_steps": 2431795199, "loss": 0.025220921263098717, "avg_return": 0.8578304052352905, "regret": 0.00991387851536274, "entropy": 0.14631323516368866, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:18.431607Z", "loop": 3958, "env_steps": 2432409599, "loss": 0.02619357965886593, "avg_return": 0.8569640517234802, "regret": 0.00991387851536274, "entropy": 0.14686593413352966, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:19.286148Z", "loop": 3959, "env_steps": 2433023999, "loss": 0.02617192640900612, "avg_return": 0.8561477065086365, "regret": 0.00991387851536274, "entropy": 0.14741770923137665, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:20.179299Z", "loop": 3960, "env_steps": 2433638399, "loss": 0.025396889075636864, "avg_return": 0.8545992970466614, "regret": 0.00728584174066782, "entropy": 0.1451423019170761, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:21.033525Z", "loop": 3961, "env_steps": 2434252799, "loss": 0.02748827077448368, "avg_return": 0.8549169898033142, "regret": 0.00728584174066782, "entropy": 0.15034383535385132, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:21.886310Z", "loop": 3962, "env_steps": 2434867199, "loss": 0.027253711596131325, "avg_return": 0.8549292087554932, "regret": 0.00728584174066782, "entropy": 0.1547054946422577, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:22.738409Z", "loop": 3963, "env_steps": 2435481599, "loss": 0.026703989133238792, "avg_return": 0.8568229079246521, "regret": 0.00728584174066782, "entropy": 0.15319012105464935, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:23.592864Z", "loop": 3964, "env_steps": 2436095999, "loss": 0.02768765762448311, "avg_return": 0.8576287031173706, "regret": 0.00728584174066782, "entropy": 0.1569536328315735, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:24.447608Z", "loop": 3965, "env_steps": 2436710399, "loss": 0.025523532181978226, "avg_return": 0.8552484512329102, "regret": 0.00728584174066782, "entropy": 0.1516627073287964, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:25.300773Z", "loop": 3966, "env_steps": 2437324799, "loss": 0.026621311902999878, "avg_return": 0.8546942472457886, "regret": 0.00728584174066782, "entropy": 0.1579338163137436, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:26.153447Z", "loop": 3967, "env_steps": 2437939199, "loss": 0.027944928035140038, "avg_return": 0.857147753238678, "regret": 0.00728584174066782, "entropy": 0.15956050157546997, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:27.006131Z", "loop": 3968, "env_steps": 2438553599, "loss": 0.0251260157674551, "avg_return": 0.8588001728057861, "regret": 0.00728584174066782, "entropy": 0.14900487661361694, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:27.860664Z", "loop": 3969, "env_steps": 2439167999, "loss": 0.02739371731877327, "avg_return": 0.8584983348846436, "regret": 0.00728584174066782, "entropy": 0.15670202672481537, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:28.755550Z", "loop": 3970, "env_steps": 2439782399, "loss": 0.026044650003314018, "avg_return": 0.857550859451294, "regret": 0.006907148286700249, "entropy": 0.1468881368637085, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:29.608852Z", "loop": 3971, "env_steps": 2440396799, "loss": 0.026733169332146645, "avg_return": 0.8553142547607422, "regret": 0.006907148286700249, "entropy": 0.14920786023139954, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:30.462953Z", "loop": 3972, "env_steps": 2441011199, "loss": 0.026606252416968346, "avg_return": 0.8549931049346924, "regret": 0.006907148286700249, "entropy": 0.14297330379486084, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:31.317188Z", "loop": 3973, "env_steps": 2441625599, "loss": 0.026973852887749672, "avg_return": 0.8542081713676453, "regret": 0.006907148286700249, "entropy": 0.1536174714565277, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:32.172377Z", "loop": 3974, "env_steps": 2442239999, "loss": 0.027117827907204628, "avg_return": 0.8542516231536865, "regret": 0.006907148286700249, "entropy": 0.149509459733963, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:33.027391Z", "loop": 3975, "env_steps": 2442854399, "loss": 0.029010165482759476, "avg_return": 0.8545658588409424, "regret": 0.006907148286700249, "entropy": 0.15352271497249603, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:33.880789Z", "loop": 3976, "env_steps": 2443468799, "loss": 0.026563316583633423, "avg_return": 0.854631781578064, "regret": 0.006907148286700249, "entropy": 0.14468461275100708, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:34.735415Z", "loop": 3977, "env_steps": 2444083199, "loss": 0.026480412110686302, "avg_return": 0.8551058173179626, "regret": 0.006907148286700249, "entropy": 0.1467563658952713, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:35.590740Z", "loop": 3978, "env_steps": 2444697599, "loss": 0.026568589732050896, "avg_return": 0.8562666773796082, "regret": 0.006907148286700249, "entropy": 0.15373024344444275, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:36.446996Z", "loop": 3979, "env_steps": 2445311999, "loss": 0.027697263285517693, "avg_return": 0.8555169701576233, "regret": 0.006907148286700249, "entropy": 0.15695607662200928, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:37.343173Z", "loop": 3980, "env_steps": 2445926399, "loss": 0.030093351379036903, "avg_return": 0.8546565771102905, "regret": 0.0088888481259346, "entropy": 0.17018014192581177, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:38.198537Z", "loop": 3981, "env_steps": 2446540799, "loss": 0.030641591176390648, "avg_return": 0.8497458100318909, "regret": 0.0088888481259346, "entropy": 0.17283830046653748, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:39.053623Z", "loop": 3982, "env_steps": 2447155199, "loss": 0.03116295300424099, "avg_return": 0.8467046618461609, "regret": 0.0088888481259346, "entropy": 0.1772950291633606, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:39.908468Z", "loop": 3983, "env_steps": 2447769599, "loss": 0.02843189612030983, "avg_return": 0.8502670526504517, "regret": 0.0088888481259346, "entropy": 0.1652228832244873, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:40.763960Z", "loop": 3984, "env_steps": 2448383999, "loss": 0.027008358389139175, "avg_return": 0.8541017770767212, "regret": 0.0088888481259346, "entropy": 0.15851083397865295, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:41.618343Z", "loop": 3985, "env_steps": 2448998399, "loss": 0.024999693036079407, "avg_return": 0.8556797504425049, "regret": 0.0088888481259346, "entropy": 0.14267905056476593, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:42.472151Z", "loop": 3986, "env_steps": 2449612799, "loss": 0.026070982217788696, "avg_return": 0.8575289845466614, "regret": 0.0088888481259346, "entropy": 0.14096607267856598, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:43.325940Z", "loop": 3987, "env_steps": 2450227199, "loss": 0.025452006608247757, "avg_return": 0.8554308414459229, "regret": 0.0088888481259346, "entropy": 0.14160442352294922, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:44.179231Z", "loop": 3988, "env_steps": 2450841599, "loss": 0.02470066398382187, "avg_return": 0.8552893400192261, "regret": 0.0088888481259346, "entropy": 0.1398824006319046, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:45.032944Z", "loop": 3989, "env_steps": 2451455999, "loss": 0.02470812015235424, "avg_return": 0.8565872311592102, "regret": 0.0088888481259346, "entropy": 0.13720659911632538, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:45.926672Z", "loop": 3990, "env_steps": 2452070399, "loss": 0.02667829766869545, "avg_return": 0.855891764163971, "regret": 0.007640533614903688, "entropy": 0.14308065176010132, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:46.781162Z", "loop": 3991, "env_steps": 2452684799, "loss": 0.02823459543287754, "avg_return": 0.855379045009613, "regret": 0.007640533614903688, "entropy": 0.15250864624977112, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:47.635746Z", "loop": 3992, "env_steps": 2453299199, "loss": 0.029359763488173485, "avg_return": 0.8530807495117188, "regret": 0.007640533614903688, "entropy": 0.1616414487361908, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:48.490985Z", "loop": 3993, "env_steps": 2453913599, "loss": 0.03063277341425419, "avg_return": 0.8501225113868713, "regret": 0.007640533614903688, "entropy": 0.17071515321731567, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:49.344652Z", "loop": 3994, "env_steps": 2454527999, "loss": 0.03337645158171654, "avg_return": 0.8462147116661072, "regret": 0.007640533614903688, "entropy": 0.1749313324689865, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:50.198686Z", "loop": 3995, "env_steps": 2455142399, "loss": 0.03196047991514206, "avg_return": 0.8447708487510681, "regret": 0.007640533614903688, "entropy": 0.1768355667591095, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:51.052961Z", "loop": 3996, "env_steps": 2455756799, "loss": 0.03385087102651596, "avg_return": 0.8449021577835083, "regret": 0.007640533614903688, "entropy": 0.18614891171455383, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:51.906937Z", "loop": 3997, "env_steps": 2456371199, "loss": 0.030412977561354637, "avg_return": 0.8460641503334045, "regret": 0.007640533614903688, "entropy": 0.17255479097366333, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:52.760517Z", "loop": 3998, "env_steps": 2456985599, "loss": 0.03063097596168518, "avg_return": 0.8491483926773071, "regret": 0.007640533614903688, "entropy": 0.167024627327919, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:53.614792Z", "loop": 3999, "env_steps": 2457599999, "loss": 0.03058394230902195, "avg_return": 0.8491423726081848, "regret": 0.007640533614903688, "entropy": 0.17002452909946442, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:54.507514Z", "loop": 4000, "env_steps": 2458214399, "loss": 0.030070126056671143, "avg_return": 0.8532488346099854, "regret": 0.011301921680569649, "entropy": 0.16315019130706787, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:55.362652Z", "loop": 4001, "env_steps": 2458828799, "loss": 0.028991570696234703, "avg_return": 0.8534138202667236, "regret": 0.011301921680569649, "entropy": 0.15594621002674103, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:56.216251Z", "loop": 4002, "env_steps": 2459443199, "loss": 0.029191065579652786, "avg_return": 0.8557239770889282, "regret": 0.011301921680569649, "entropy": 0.16530996561050415, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:57.069431Z", "loop": 4003, "env_steps": 2460057599, "loss": 0.026219753548502922, "avg_return": 0.8556209802627563, "regret": 0.011301921680569649, "entropy": 0.15028074383735657, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:57.922016Z", "loop": 4004, "env_steps": 2460671999, "loss": 0.027110302820801735, "avg_return": 0.8565077781677246, "regret": 0.011301921680569649, "entropy": 0.15036652982234955, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:58.776576Z", "loop": 4005, "env_steps": 2461286399, "loss": 0.024856140837073326, "avg_return": 0.8580433130264282, "regret": 0.011301921680569649, "entropy": 0.14209234714508057, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:20:59.629217Z", "loop": 4006, "env_steps": 2461900799, "loss": 0.02414763905107975, "avg_return": 0.8583201169967651, "regret": 0.011301921680569649, "entropy": 0.1398872435092926, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:00.482535Z", "loop": 4007, "env_steps": 2462515199, "loss": 0.02489355020225048, "avg_return": 0.857903242111206, "regret": 0.011301921680569649, "entropy": 0.13965672254562378, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:01.336433Z", "loop": 4008, "env_steps": 2463129599, "loss": 0.0250331312417984, "avg_return": 0.8572192788124084, "regret": 0.011301921680569649, "entropy": 0.14999163150787354, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:02.190159Z", "loop": 4009, "env_steps": 2463743999, "loss": 0.026143062859773636, "avg_return": 0.8566862344741821, "regret": 0.011301921680569649, "entropy": 0.14887304604053497, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:03.083429Z", "loop": 4010, "env_steps": 2464358399, "loss": 0.027532368898391724, "avg_return": 0.8546842932701111, "regret": 0.009615748189389706, "entropy": 0.1563243567943573, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:03.938062Z", "loop": 4011, "env_steps": 2464972799, "loss": 0.029982570558786392, "avg_return": 0.852893054485321, "regret": 0.009615748189389706, "entropy": 0.16348102688789368, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:04.790926Z", "loop": 4012, "env_steps": 2465587199, "loss": 0.02686837688088417, "avg_return": 0.8551949262619019, "regret": 0.009615748189389706, "entropy": 0.15192455053329468, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:05.644516Z", "loop": 4013, "env_steps": 2466201599, "loss": 0.025102445855736732, "avg_return": 0.85587078332901, "regret": 0.009615748189389706, "entropy": 0.14162133634090424, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:06.498805Z", "loop": 4014, "env_steps": 2466815999, "loss": 0.024973303079605103, "avg_return": 0.8575049042701721, "regret": 0.009615748189389706, "entropy": 0.13969796895980835, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:07.352696Z", "loop": 4015, "env_steps": 2467430399, "loss": 0.02480260282754898, "avg_return": 0.8597915768623352, "regret": 0.009615748189389706, "entropy": 0.13909165561199188, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:08.206758Z", "loop": 4016, "env_steps": 2468044799, "loss": 0.0228074062615633, "avg_return": 0.8581855297088623, "regret": 0.009615748189389706, "entropy": 0.13560903072357178, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:09.060707Z", "loop": 4017, "env_steps": 2468659199, "loss": 0.02412378415465355, "avg_return": 0.8586761951446533, "regret": 0.009615748189389706, "entropy": 0.13713231682777405, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:09.915510Z", "loop": 4018, "env_steps": 2469273599, "loss": 0.024701569229364395, "avg_return": 0.8576326966285706, "regret": 0.009615748189389706, "entropy": 0.1374487578868866, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:10.768831Z", "loop": 4019, "env_steps": 2469887999, "loss": 0.023620130494236946, "avg_return": 0.8582637906074524, "regret": 0.009615748189389706, "entropy": 0.13182668387889862, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:11.661610Z", "loop": 4020, "env_steps": 2470502399, "loss": 0.024275805801153183, "avg_return": 0.8577736616134644, "regret": 0.006321164313703775, "entropy": 0.13820074498653412, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:12.513882Z", "loop": 4021, "env_steps": 2471116799, "loss": 0.024595987051725388, "avg_return": 0.8591007590293884, "regret": 0.006321164313703775, "entropy": 0.14161448180675507, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:13.367478Z", "loop": 4022, "env_steps": 2471731199, "loss": 0.02386905811727047, "avg_return": 0.8593408465385437, "regret": 0.006321164313703775, "entropy": 0.13949957489967346, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:14.221698Z", "loop": 4023, "env_steps": 2472345599, "loss": 0.024610331282019615, "avg_return": 0.856990396976471, "regret": 0.006321164313703775, "entropy": 0.14107924699783325, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:15.075580Z", "loop": 4024, "env_steps": 2472959999, "loss": 0.026780668646097183, "avg_return": 0.8546480536460876, "regret": 0.006321164313703775, "entropy": 0.14266520738601685, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:15.928997Z", "loop": 4025, "env_steps": 2473574399, "loss": 0.02488439530134201, "avg_return": 0.8588035106658936, "regret": 0.006321164313703775, "entropy": 0.1410728543996811, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:16.784054Z", "loop": 4026, "env_steps": 2474188799, "loss": 0.02634882926940918, "avg_return": 0.8571527600288391, "regret": 0.006321164313703775, "entropy": 0.14510734379291534, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:17.638135Z", "loop": 4027, "env_steps": 2474803199, "loss": 0.024270402267575264, "avg_return": 0.8577572107315063, "regret": 0.006321164313703775, "entropy": 0.1376606673002243, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:18.491715Z", "loop": 4028, "env_steps": 2475417599, "loss": 0.024208003655076027, "avg_return": 0.8570458292961121, "regret": 0.006321164313703775, "entropy": 0.14045898616313934, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:19.345670Z", "loop": 4029, "env_steps": 2476031999, "loss": 0.02544442191720009, "avg_return": 0.8564421534538269, "regret": 0.006321164313703775, "entropy": 0.14481812715530396, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:20.239521Z", "loop": 4030, "env_steps": 2476646399, "loss": 0.025746280327439308, "avg_return": 0.8564988374710083, "regret": 0.0075896321795880795, "entropy": 0.14166370034217834, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:21.092789Z", "loop": 4031, "env_steps": 2477260799, "loss": 0.027273235842585564, "avg_return": 0.8561230897903442, "regret": 0.0075896321795880795, "entropy": 0.15099738538265228, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:21.945535Z", "loop": 4032, "env_steps": 2477875199, "loss": 0.02766437828540802, "avg_return": 0.8565022945404053, "regret": 0.0075896321795880795, "entropy": 0.15240219235420227, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:22.799249Z", "loop": 4033, "env_steps": 2478489599, "loss": 0.02644590102136135, "avg_return": 0.8573349118232727, "regret": 0.0075896321795880795, "entropy": 0.14956115186214447, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:23.654033Z", "loop": 4034, "env_steps": 2479103999, "loss": 0.02664257027208805, "avg_return": 0.8568234443664551, "regret": 0.0075896321795880795, "entropy": 0.1508459746837616, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:24.507757Z", "loop": 4035, "env_steps": 2479718399, "loss": 0.0243623536080122, "avg_return": 0.8579167127609253, "regret": 0.0075896321795880795, "entropy": 0.14455048739910126, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:25.361074Z", "loop": 4036, "env_steps": 2480332799, "loss": 0.025941843166947365, "avg_return": 0.8576140403747559, "regret": 0.0075896321795880795, "entropy": 0.14554987847805023, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:26.215374Z", "loop": 4037, "env_steps": 2480947199, "loss": 0.02564282715320587, "avg_return": 0.8581066131591797, "regret": 0.0075896321795880795, "entropy": 0.1456935703754425, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:27.070548Z", "loop": 4038, "env_steps": 2481561599, "loss": 0.025041332468390465, "avg_return": 0.856679379940033, "regret": 0.0075896321795880795, "entropy": 0.14318129420280457, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:27.924383Z", "loop": 4039, "env_steps": 2482175999, "loss": 0.024171676486730576, "avg_return": 0.8577412962913513, "regret": 0.0075896321795880795, "entropy": 0.13814115524291992, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:28.817775Z", "loop": 4040, "env_steps": 2482790399, "loss": 0.0234052836894989, "avg_return": 0.8584190011024475, "regret": 0.005415340419858694, "entropy": 0.12943679094314575, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:29.672553Z", "loop": 4041, "env_steps": 2483404799, "loss": 0.023408113047480583, "avg_return": 0.8571299314498901, "regret": 0.005415340419858694, "entropy": 0.1349993348121643, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:30.527715Z", "loop": 4042, "env_steps": 2484019199, "loss": 0.023622626438736916, "avg_return": 0.8566265106201172, "regret": 0.005415340419858694, "entropy": 0.13418631255626678, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:31.382335Z", "loop": 4043, "env_steps": 2484633599, "loss": 0.025556480512022972, "avg_return": 0.8556691408157349, "regret": 0.005415340419858694, "entropy": 0.1372821182012558, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:32.235094Z", "loop": 4044, "env_steps": 2485247999, "loss": 0.024219907820224762, "avg_return": 0.85545414686203, "regret": 0.005415340419858694, "entropy": 0.13300983607769012, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:33.088226Z", "loop": 4045, "env_steps": 2485862399, "loss": 0.024564774706959724, "avg_return": 0.8576174378395081, "regret": 0.005415340419858694, "entropy": 0.1344684213399887, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:33.941876Z", "loop": 4046, "env_steps": 2486476799, "loss": 0.022373074665665627, "avg_return": 0.8567872047424316, "regret": 0.005415340419858694, "entropy": 0.1282597780227661, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:34.796429Z", "loop": 4047, "env_steps": 2487091199, "loss": 0.023121042177081108, "avg_return": 0.8568463325500488, "regret": 0.005415340419858694, "entropy": 0.12927202880382538, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:35.650135Z", "loop": 4048, "env_steps": 2487705599, "loss": 0.02234896831214428, "avg_return": 0.8562896847724915, "regret": 0.005415340419858694, "entropy": 0.12917201220989227, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:36.503520Z", "loop": 4049, "env_steps": 2488319999, "loss": 0.023849379271268845, "avg_return": 0.8575522899627686, "regret": 0.005415340419858694, "entropy": 0.13185706734657288, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:37.399318Z", "loop": 4050, "env_steps": 2488934399, "loss": 0.022788483649492264, "avg_return": 0.8570147752761841, "regret": 0.006367759313434362, "entropy": 0.12843918800354004, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:38.253353Z", "loop": 4051, "env_steps": 2489548799, "loss": 0.023491034284234047, "avg_return": 0.8585599064826965, "regret": 0.006367759313434362, "entropy": 0.13036102056503296, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:39.107113Z", "loop": 4052, "env_steps": 2490163199, "loss": 0.023040495812892914, "avg_return": 0.8580306172370911, "regret": 0.006367759313434362, "entropy": 0.12869882583618164, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:39.961611Z", "loop": 4053, "env_steps": 2490777599, "loss": 0.023734400048851967, "avg_return": 0.8588173389434814, "regret": 0.006367759313434362, "entropy": 0.1328589916229248, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:40.815243Z", "loop": 4054, "env_steps": 2491391999, "loss": 0.02281297743320465, "avg_return": 0.8593722581863403, "regret": 0.006367759313434362, "entropy": 0.13070960342884064, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:41.670025Z", "loop": 4055, "env_steps": 2492006399, "loss": 0.022625146433711052, "avg_return": 0.8582308292388916, "regret": 0.006367759313434362, "entropy": 0.13379158079624176, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:42.524103Z", "loop": 4056, "env_steps": 2492620799, "loss": 0.02216460555791855, "avg_return": 0.8582596778869629, "regret": 0.006367759313434362, "entropy": 0.1314622312784195, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:43.376926Z", "loop": 4057, "env_steps": 2493235199, "loss": 0.02312563732266426, "avg_return": 0.8578908443450928, "regret": 0.006367759313434362, "entropy": 0.12934136390686035, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:44.229591Z", "loop": 4058, "env_steps": 2493849599, "loss": 0.022598978132009506, "avg_return": 0.8576726317405701, "regret": 0.006367759313434362, "entropy": 0.12717433273792267, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:45.083572Z", "loop": 4059, "env_steps": 2494463999, "loss": 0.024368291720747948, "avg_return": 0.8580822944641113, "regret": 0.006367759313434362, "entropy": 0.13333474099636078, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:45.977782Z", "loop": 4060, "env_steps": 2495078399, "loss": 0.024246854707598686, "avg_return": 0.8581240177154541, "regret": 0.005500332918018103, "entropy": 0.1359945833683014, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:46.831498Z", "loop": 4061, "env_steps": 2495692799, "loss": 0.024891426786780357, "avg_return": 0.857441246509552, "regret": 0.005500332918018103, "entropy": 0.13688868284225464, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:47.684599Z", "loop": 4062, "env_steps": 2496307199, "loss": 0.02350553683936596, "avg_return": 0.8587899208068848, "regret": 0.005500332918018103, "entropy": 0.13077332079410553, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:48.537707Z", "loop": 4063, "env_steps": 2496921599, "loss": 0.023295653983950615, "avg_return": 0.8578072190284729, "regret": 0.005500332918018103, "entropy": 0.13195346295833588, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:49.392075Z", "loop": 4064, "env_steps": 2497535999, "loss": 0.02424824796617031, "avg_return": 0.8575328588485718, "regret": 0.005500332918018103, "entropy": 0.13389191031455994, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:50.246466Z", "loop": 4065, "env_steps": 2498150399, "loss": 0.025020763278007507, "avg_return": 0.8585945963859558, "regret": 0.005500332918018103, "entropy": 0.13858067989349365, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:51.100519Z", "loop": 4066, "env_steps": 2498764799, "loss": 0.022702544927597046, "avg_return": 0.8578171133995056, "regret": 0.005500332918018103, "entropy": 0.13246384263038635, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:51.953491Z", "loop": 4067, "env_steps": 2499379199, "loss": 0.02333529107272625, "avg_return": 0.8575423359870911, "regret": 0.005500332918018103, "entropy": 0.1359812468290329, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:52.807424Z", "loop": 4068, "env_steps": 2499993599, "loss": 0.022953249514102936, "avg_return": 0.85981285572052, "regret": 0.005500332918018103, "entropy": 0.13237951695919037, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:53.661197Z", "loop": 4069, "env_steps": 2500607999, "loss": 0.02318383939564228, "avg_return": 0.8576593399047852, "regret": 0.005500332918018103, "entropy": 0.13200075924396515, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:54.554232Z", "loop": 4070, "env_steps": 2501222399, "loss": 0.023253384977579117, "avg_return": 0.8577536940574646, "regret": 0.004959840793162584, "entropy": 0.13105693459510803, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:55.406875Z", "loop": 4071, "env_steps": 2501836799, "loss": 0.022843068465590477, "avg_return": 0.8569425940513611, "regret": 0.004959840793162584, "entropy": 0.12967002391815186, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:56.259807Z", "loop": 4072, "env_steps": 2502451199, "loss": 0.02325497940182686, "avg_return": 0.8565041422843933, "regret": 0.004959840793162584, "entropy": 0.13328546285629272, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:57.114776Z", "loop": 4073, "env_steps": 2503065599, "loss": 0.023636579513549805, "avg_return": 0.8558111786842346, "regret": 0.004959840793162584, "entropy": 0.1346118450164795, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:57.968001Z", "loop": 4074, "env_steps": 2503679999, "loss": 0.025587618350982666, "avg_return": 0.8553940057754517, "regret": 0.004959840793162584, "entropy": 0.14248543977737427, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:58.822433Z", "loop": 4075, "env_steps": 2504294399, "loss": 0.02479734644293785, "avg_return": 0.8549870848655701, "regret": 0.004959840793162584, "entropy": 0.14177951216697693, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:21:59.676050Z", "loop": 4076, "env_steps": 2504908799, "loss": 0.02503584884107113, "avg_return": 0.8552741408348083, "regret": 0.004959840793162584, "entropy": 0.1437782496213913, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:00.530704Z", "loop": 4077, "env_steps": 2505523199, "loss": 0.026196664199233055, "avg_return": 0.8545587658882141, "regret": 0.004959840793162584, "entropy": 0.1459703892469406, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:01.385441Z", "loop": 4078, "env_steps": 2506137599, "loss": 0.0230543352663517, "avg_return": 0.8573163151741028, "regret": 0.004959840793162584, "entropy": 0.13695554435253143, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:02.240037Z", "loop": 4079, "env_steps": 2506751999, "loss": 0.025200968608260155, "avg_return": 0.8555318117141724, "regret": 0.004959840793162584, "entropy": 0.1418522298336029, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:03.134195Z", "loop": 4080, "env_steps": 2507366399, "loss": 0.023444144055247307, "avg_return": 0.8590836524963379, "regret": 0.005681028589606285, "entropy": 0.1378626823425293, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:03.988320Z", "loop": 4081, "env_steps": 2507980799, "loss": 0.023842385038733482, "avg_return": 0.8590407371520996, "regret": 0.005681028589606285, "entropy": 0.13793155550956726, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:04.842950Z", "loop": 4082, "env_steps": 2508595199, "loss": 0.024365892633795738, "avg_return": 0.859085202217102, "regret": 0.005681028589606285, "entropy": 0.14272606372833252, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:05.697054Z", "loop": 4083, "env_steps": 2509209599, "loss": 0.023942142724990845, "avg_return": 0.8587659001350403, "regret": 0.005681028589606285, "entropy": 0.1350187361240387, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:06.550672Z", "loop": 4084, "env_steps": 2509823999, "loss": 0.02591313235461712, "avg_return": 0.8568618893623352, "regret": 0.005681028589606285, "entropy": 0.14735381305217743, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:07.405011Z", "loop": 4085, "env_steps": 2510438399, "loss": 0.02671147882938385, "avg_return": 0.8548157215118408, "regret": 0.005681028589606285, "entropy": 0.14392869174480438, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:08.258949Z", "loop": 4086, "env_steps": 2511052799, "loss": 0.028828833252191544, "avg_return": 0.8539799451828003, "regret": 0.005681028589606285, "entropy": 0.15143996477127075, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:09.112613Z", "loop": 4087, "env_steps": 2511667199, "loss": 0.02620006538927555, "avg_return": 0.8536282777786255, "regret": 0.005681028589606285, "entropy": 0.14943315088748932, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:09.965901Z", "loop": 4088, "env_steps": 2512281599, "loss": 0.027182413265109062, "avg_return": 0.854089081287384, "regret": 0.005681028589606285, "entropy": 0.14567649364471436, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:10.819380Z", "loop": 4089, "env_steps": 2512895999, "loss": 0.026940980926156044, "avg_return": 0.8560464978218079, "regret": 0.005681028589606285, "entropy": 0.14895233511924744, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:11.712277Z", "loop": 4090, "env_steps": 2513510399, "loss": 0.02790537290275097, "avg_return": 0.8548900485038757, "regret": 0.007245856337249279, "entropy": 0.16087347269058228, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:12.566592Z", "loop": 4091, "env_steps": 2514124799, "loss": 0.03295917809009552, "avg_return": 0.8533864617347717, "regret": 0.007245856337249279, "entropy": 0.188717782497406, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:13.422324Z", "loop": 4092, "env_steps": 2514739199, "loss": 0.03365882486104965, "avg_return": 0.8518925905227661, "regret": 0.007245856337249279, "entropy": 0.19334428012371063, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:14.278569Z", "loop": 4093, "env_steps": 2515353599, "loss": 0.03221750259399414, "avg_return": 0.8512120842933655, "regret": 0.007245856337249279, "entropy": 0.18475092947483063, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:15.132190Z", "loop": 4094, "env_steps": 2515967999, "loss": 0.03105228580534458, "avg_return": 0.8533602356910706, "regret": 0.007245856337249279, "entropy": 0.17222906649112701, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:15.986502Z", "loop": 4095, "env_steps": 2516582399, "loss": 0.026850569993257523, "avg_return": 0.8549433350563049, "regret": 0.007245856337249279, "entropy": 0.15331539511680603, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:16.839867Z", "loop": 4096, "env_steps": 2517196799, "loss": 0.028217514976859093, "avg_return": 0.8555477261543274, "regret": 0.007245856337249279, "entropy": 0.1551613211631775, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:17.695417Z", "loop": 4097, "env_steps": 2517811199, "loss": 0.028262365609407425, "avg_return": 0.8534221649169922, "regret": 0.007245856337249279, "entropy": 0.1495121419429779, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:18.549271Z", "loop": 4098, "env_steps": 2518425599, "loss": 0.028153596445918083, "avg_return": 0.8520508408546448, "regret": 0.007245856337249279, "entropy": 0.14685186743736267, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:19.402168Z", "loop": 4099, "env_steps": 2519039999, "loss": 0.02835889160633087, "avg_return": 0.8503051400184631, "regret": 0.007245856337249279, "entropy": 0.14665056765079498, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:20.295120Z", "loop": 4100, "env_steps": 2519654399, "loss": 0.02965736761689186, "avg_return": 0.8491397500038147, "regret": 0.013627282343804836, "entropy": 0.14989882707595825, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:21.150686Z", "loop": 4101, "env_steps": 2520268799, "loss": 0.026310225948691368, "avg_return": 0.8523321747779846, "regret": 0.013627282343804836, "entropy": 0.14333359897136688, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:22.005089Z", "loop": 4102, "env_steps": 2520883199, "loss": 0.024939557537436485, "avg_return": 0.8541167378425598, "regret": 0.013627282343804836, "entropy": 0.1308542788028717, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:22.858435Z", "loop": 4103, "env_steps": 2521497599, "loss": 0.02242639660835266, "avg_return": 0.8548507690429688, "regret": 0.013627282343804836, "entropy": 0.1280142366886139, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:23.711195Z", "loop": 4104, "env_steps": 2522111999, "loss": 0.023153631016612053, "avg_return": 0.8564778566360474, "regret": 0.013627282343804836, "entropy": 0.12591513991355896, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:24.565327Z", "loop": 4105, "env_steps": 2522726399, "loss": 0.02239326201379299, "avg_return": 0.8567982316017151, "regret": 0.013627282343804836, "entropy": 0.12419091165065765, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:25.418951Z", "loop": 4106, "env_steps": 2523340799, "loss": 0.0216644499450922, "avg_return": 0.8586930632591248, "regret": 0.013627282343804836, "entropy": 0.12463810294866562, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:26.271729Z", "loop": 4107, "env_steps": 2523955199, "loss": 0.021380329504609108, "avg_return": 0.8562793135643005, "regret": 0.013627282343804836, "entropy": 0.12330009043216705, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:27.124352Z", "loop": 4108, "env_steps": 2524569599, "loss": 0.025353623554110527, "avg_return": 0.8583580851554871, "regret": 0.013627282343804836, "entropy": 0.14261718094348907, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:27.977949Z", "loop": 4109, "env_steps": 2525183999, "loss": 0.024003498256206512, "avg_return": 0.8561276197433472, "regret": 0.013627282343804836, "entropy": 0.1366187334060669, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:28.872422Z", "loop": 4110, "env_steps": 2525798399, "loss": 0.026332486420869827, "avg_return": 0.8542149066925049, "regret": 0.009172439575195312, "entropy": 0.1432432383298874, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:29.726991Z", "loop": 4111, "env_steps": 2526412799, "loss": 0.02619258500635624, "avg_return": 0.854931652545929, "regret": 0.009172439575195312, "entropy": 0.14247214794158936, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:30.580561Z", "loop": 4112, "env_steps": 2527027199, "loss": 0.02477293834090233, "avg_return": 0.8547119498252869, "regret": 0.009172439575195312, "entropy": 0.13510726392269135, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:31.435212Z", "loop": 4113, "env_steps": 2527641599, "loss": 0.022148046642541885, "avg_return": 0.855969250202179, "regret": 0.009172439575195312, "entropy": 0.13267412781715393, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:32.288991Z", "loop": 4114, "env_steps": 2528255999, "loss": 0.0251438170671463, "avg_return": 0.8554071187973022, "regret": 0.009172439575195312, "entropy": 0.14110323786735535, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:33.143116Z", "loop": 4115, "env_steps": 2528870399, "loss": 0.026661211624741554, "avg_return": 0.8547760248184204, "regret": 0.009172439575195312, "entropy": 0.1376025676727295, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:33.996524Z", "loop": 4116, "env_steps": 2529484799, "loss": 0.027443213388323784, "avg_return": 0.8480870127677917, "regret": 0.009172439575195312, "entropy": 0.14613454043865204, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:34.850337Z", "loop": 4117, "env_steps": 2530099199, "loss": 0.027431076392531395, "avg_return": 0.8465484380722046, "regret": 0.009172439575195312, "entropy": 0.14769332110881805, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:35.703829Z", "loop": 4118, "env_steps": 2530713599, "loss": 0.02744363248348236, "avg_return": 0.8493861556053162, "regret": 0.009172439575195312, "entropy": 0.14271800220012665, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:36.557099Z", "loop": 4119, "env_steps": 2531327999, "loss": 0.026127291843295097, "avg_return": 0.8511393666267395, "regret": 0.009172439575195312, "entropy": 0.1398973912000656, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:37.452643Z", "loop": 4120, "env_steps": 2531942399, "loss": 0.025377321988344193, "avg_return": 0.8546958565711975, "regret": 0.008464737795293331, "entropy": 0.14066417515277863, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:38.307238Z", "loop": 4121, "env_steps": 2532556799, "loss": 0.024964764714241028, "avg_return": 0.8578248023986816, "regret": 0.008464737795293331, "entropy": 0.14029207825660706, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:39.161510Z", "loop": 4122, "env_steps": 2533171199, "loss": 0.02524070255458355, "avg_return": 0.8564440011978149, "regret": 0.008464737795293331, "entropy": 0.14457565546035767, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:40.016070Z", "loop": 4123, "env_steps": 2533785599, "loss": 0.02733158878982067, "avg_return": 0.8573011755943298, "regret": 0.008464737795293331, "entropy": 0.15654750168323517, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:40.869878Z", "loop": 4124, "env_steps": 2534399999, "loss": 0.028220251202583313, "avg_return": 0.8548489809036255, "regret": 0.008464737795293331, "entropy": 0.16829828917980194, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:41.723353Z", "loop": 4125, "env_steps": 2535014399, "loss": 0.031026089563965797, "avg_return": 0.8540295362472534, "regret": 0.008464737795293331, "entropy": 0.17852158844470978, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:42.576618Z", "loop": 4126, "env_steps": 2535628799, "loss": 0.02960796467959881, "avg_return": 0.8536883592605591, "regret": 0.008464737795293331, "entropy": 0.17333094775676727, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:43.430313Z", "loop": 4127, "env_steps": 2536243199, "loss": 0.027104347944259644, "avg_return": 0.8558716773986816, "regret": 0.008464737795293331, "entropy": 0.15775229036808014, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:44.284247Z", "loop": 4128, "env_steps": 2536857599, "loss": 0.026393461972475052, "avg_return": 0.8568305373191833, "regret": 0.008464737795293331, "entropy": 0.14595483243465424, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:45.138524Z", "loop": 4129, "env_steps": 2537471999, "loss": 0.024563897401094437, "avg_return": 0.8573628067970276, "regret": 0.008464737795293331, "entropy": 0.1364424228668213, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:46.030721Z", "loop": 4130, "env_steps": 2538086399, "loss": 0.02240808866918087, "avg_return": 0.8591123819351196, "regret": 0.004828667268157005, "entropy": 0.1309363692998886, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:46.885884Z", "loop": 4131, "env_steps": 2538700799, "loss": 0.021345140412449837, "avg_return": 0.859707772731781, "regret": 0.004828667268157005, "entropy": 0.12533597648143768, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:47.740786Z", "loop": 4132, "env_steps": 2539315199, "loss": 0.023655341938138008, "avg_return": 0.8598164319992065, "regret": 0.004828667268157005, "entropy": 0.13909243047237396, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:48.595099Z", "loop": 4133, "env_steps": 2539929599, "loss": 0.023696208372712135, "avg_return": 0.8592609763145447, "regret": 0.004828667268157005, "entropy": 0.1344274878501892, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:49.447371Z", "loop": 4134, "env_steps": 2540543999, "loss": 0.022914113476872444, "avg_return": 0.8577520847320557, "regret": 0.004828667268157005, "entropy": 0.13333769142627716, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:50.300218Z", "loop": 4135, "env_steps": 2541158399, "loss": 0.025596586987376213, "avg_return": 0.8550822138786316, "regret": 0.004828667268157005, "entropy": 0.1437874585390091, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:51.153995Z", "loop": 4136, "env_steps": 2541772799, "loss": 0.026068469509482384, "avg_return": 0.8533291816711426, "regret": 0.004828667268157005, "entropy": 0.1425953507423401, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:52.007968Z", "loop": 4137, "env_steps": 2542387199, "loss": 0.026434937492012978, "avg_return": 0.8552879095077515, "regret": 0.004828667268157005, "entropy": 0.14563027024269104, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:52.861145Z", "loop": 4138, "env_steps": 2543001599, "loss": 0.026877740398049355, "avg_return": 0.8564460277557373, "regret": 0.004828667268157005, "entropy": 0.15180261433124542, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:53.714406Z", "loop": 4139, "env_steps": 2543615999, "loss": 0.02643715776503086, "avg_return": 0.8562119007110596, "regret": 0.004828667268157005, "entropy": 0.14750197529792786, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:54.607949Z", "loop": 4140, "env_steps": 2544230399, "loss": 0.023963628336787224, "avg_return": 0.855553925037384, "regret": 0.006354824639856815, "entropy": 0.13646738231182098, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:55.462705Z", "loop": 4141, "env_steps": 2544844799, "loss": 0.02295473776757717, "avg_return": 0.8579409122467041, "regret": 0.006354824639856815, "entropy": 0.13604134321212769, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:56.317411Z", "loop": 4142, "env_steps": 2545459199, "loss": 0.024184031412005424, "avg_return": 0.8565529584884644, "regret": 0.006354824639856815, "entropy": 0.132790207862854, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:57.170401Z", "loop": 4143, "env_steps": 2546073599, "loss": 0.02331852726638317, "avg_return": 0.8556150794029236, "regret": 0.006354824639856815, "entropy": 0.13085518777370453, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:58.024329Z", "loop": 4144, "env_steps": 2546687999, "loss": 0.025767439976334572, "avg_return": 0.8552678823471069, "regret": 0.006354824639856815, "entropy": 0.13619737327098846, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:58.877100Z", "loop": 4145, "env_steps": 2547302399, "loss": 0.025281131267547607, "avg_return": 0.8544935584068298, "regret": 0.006354824639856815, "entropy": 0.13637371361255646, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:22:59.731173Z", "loop": 4146, "env_steps": 2547916799, "loss": 0.02468334138393402, "avg_return": 0.8553619384765625, "regret": 0.006354824639856815, "entropy": 0.13496987521648407, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:00.584636Z", "loop": 4147, "env_steps": 2548531199, "loss": 0.02437230944633484, "avg_return": 0.857081949710846, "regret": 0.006354824639856815, "entropy": 0.1342010349035263, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:01.437936Z", "loop": 4148, "env_steps": 2549145599, "loss": 0.02344883792102337, "avg_return": 0.8580861687660217, "regret": 0.006354824639856815, "entropy": 0.13092544674873352, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:02.291721Z", "loop": 4149, "env_steps": 2549759999, "loss": 0.023142240941524506, "avg_return": 0.8598032593727112, "regret": 0.006354824639856815, "entropy": 0.13121098279953003, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:03.186654Z", "loop": 4150, "env_steps": 2550374399, "loss": 0.0227830670773983, "avg_return": 0.8587136268615723, "regret": 0.004435883369296789, "entropy": 0.13135936856269836, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:04.041261Z", "loop": 4151, "env_steps": 2550988799, "loss": 0.024765536189079285, "avg_return": 0.8564750552177429, "regret": 0.004435883369296789, "entropy": 0.1447650045156479, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:04.896033Z", "loop": 4152, "env_steps": 2551603199, "loss": 0.025776682421565056, "avg_return": 0.8578088879585266, "regret": 0.004435883369296789, "entropy": 0.14705783128738403, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:05.749850Z", "loop": 4153, "env_steps": 2552217599, "loss": 0.026765961199998856, "avg_return": 0.8566217422485352, "regret": 0.004435883369296789, "entropy": 0.15375466644763947, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:06.604820Z", "loop": 4154, "env_steps": 2552831999, "loss": 0.029565760865807533, "avg_return": 0.8538762331008911, "regret": 0.004435883369296789, "entropy": 0.15881691873073578, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:07.459256Z", "loop": 4155, "env_steps": 2553446399, "loss": 0.030178217217326164, "avg_return": 0.8541477918624878, "regret": 0.004435883369296789, "entropy": 0.16678741574287415, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:08.314069Z", "loop": 4156, "env_steps": 2554060799, "loss": 0.027319852262735367, "avg_return": 0.853424072265625, "regret": 0.004435883369296789, "entropy": 0.15785740315914154, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:09.167832Z", "loop": 4157, "env_steps": 2554675199, "loss": 0.028150349855422974, "avg_return": 0.8564949631690979, "regret": 0.004435883369296789, "entropy": 0.15821127593517303, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:10.022113Z", "loop": 4158, "env_steps": 2555289599, "loss": 0.02755567990243435, "avg_return": 0.8580130338668823, "regret": 0.004435883369296789, "entropy": 0.15336090326309204, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:10.875501Z", "loop": 4159, "env_steps": 2555903999, "loss": 0.023621702566742897, "avg_return": 0.8577947020530701, "regret": 0.004435883369296789, "entropy": 0.13858267664909363, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:11.768497Z", "loop": 4160, "env_steps": 2556518399, "loss": 0.025267526507377625, "avg_return": 0.8578603267669678, "regret": 0.005100437439978123, "entropy": 0.15037550032138824, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:12.622415Z", "loop": 4161, "env_steps": 2557132799, "loss": 0.025086993351578712, "avg_return": 0.8587270379066467, "regret": 0.005100437439978123, "entropy": 0.14067815244197845, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:13.475481Z", "loop": 4162, "env_steps": 2557747199, "loss": 0.02434239350259304, "avg_return": 0.8576284050941467, "regret": 0.005100437439978123, "entropy": 0.14299720525741577, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:14.328848Z", "loop": 4163, "env_steps": 2558361599, "loss": 0.025720352306962013, "avg_return": 0.8566597700119019, "regret": 0.005100437439978123, "entropy": 0.14097516238689423, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:15.182416Z", "loop": 4164, "env_steps": 2558975999, "loss": 0.023440195247530937, "avg_return": 0.8548892140388489, "regret": 0.005100437439978123, "entropy": 0.12988784909248352, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:16.036523Z", "loop": 4165, "env_steps": 2559590399, "loss": 0.024055970832705498, "avg_return": 0.8566760420799255, "regret": 0.005100437439978123, "entropy": 0.13757732510566711, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:16.889890Z", "loop": 4166, "env_steps": 2560204799, "loss": 0.02592971734702587, "avg_return": 0.8561049699783325, "regret": 0.005100437439978123, "entropy": 0.14349804818630219, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:17.742927Z", "loop": 4167, "env_steps": 2560819199, "loss": 0.023588310927152634, "avg_return": 0.8571754097938538, "regret": 0.005100437439978123, "entropy": 0.13874101638793945, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:18.596627Z", "loop": 4168, "env_steps": 2561433599, "loss": 0.025011012330651283, "avg_return": 0.8573750853538513, "regret": 0.005100437439978123, "entropy": 0.14061979949474335, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:19.450433Z", "loop": 4169, "env_steps": 2562047999, "loss": 0.02396870218217373, "avg_return": 0.8564085364341736, "regret": 0.005100437439978123, "entropy": 0.14086803793907166, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:20.345351Z", "loop": 4170, "env_steps": 2562662399, "loss": 0.025800222530961037, "avg_return": 0.8589518666267395, "regret": 0.006217528134584427, "entropy": 0.1400006115436554, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:21.198634Z", "loop": 4171, "env_steps": 2563276799, "loss": 0.024696262553334236, "avg_return": 0.8576874732971191, "regret": 0.006217528134584427, "entropy": 0.14287282526493073, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:22.053219Z", "loop": 4172, "env_steps": 2563891199, "loss": 0.023189807310700417, "avg_return": 0.8569633364677429, "regret": 0.006217528134584427, "entropy": 0.1383771151304245, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:22.907934Z", "loop": 4173, "env_steps": 2564505599, "loss": 0.0257559921592474, "avg_return": 0.8579829931259155, "regret": 0.006217528134584427, "entropy": 0.14310221374034882, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:23.761559Z", "loop": 4174, "env_steps": 2565119999, "loss": 0.023642010986804962, "avg_return": 0.8569217324256897, "regret": 0.006217528134584427, "entropy": 0.1363404095172882, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:24.613757Z", "loop": 4175, "env_steps": 2565734399, "loss": 0.02544873021543026, "avg_return": 0.8565905690193176, "regret": 0.006217528134584427, "entropy": 0.13864274322986603, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:25.465507Z", "loop": 4176, "env_steps": 2566348799, "loss": 0.022834934294223785, "avg_return": 0.859494149684906, "regret": 0.006217528134584427, "entropy": 0.13466641306877136, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:26.320169Z", "loop": 4177, "env_steps": 2566963199, "loss": 0.024203650653362274, "avg_return": 0.8583890199661255, "regret": 0.006217528134584427, "entropy": 0.14127600193023682, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:27.173499Z", "loop": 4178, "env_steps": 2567577599, "loss": 0.023872703313827515, "avg_return": 0.8583117723464966, "regret": 0.006217528134584427, "entropy": 0.1402565985918045, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:28.026697Z", "loop": 4179, "env_steps": 2568191999, "loss": 0.024037836119532585, "avg_return": 0.8580746650695801, "regret": 0.006217528134584427, "entropy": 0.1323520392179489, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:28.918941Z", "loop": 4180, "env_steps": 2568806399, "loss": 0.023235494270920753, "avg_return": 0.8582503199577332, "regret": 0.005006518680602312, "entropy": 0.13296949863433838, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:29.773766Z", "loop": 4181, "env_steps": 2569420799, "loss": 0.025553418323397636, "avg_return": 0.859295666217804, "regret": 0.005006518680602312, "entropy": 0.13716360926628113, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:30.628169Z", "loop": 4182, "env_steps": 2570035199, "loss": 0.02436341904103756, "avg_return": 0.8590419888496399, "regret": 0.005006518680602312, "entropy": 0.13501915335655212, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:31.482265Z", "loop": 4183, "env_steps": 2570649599, "loss": 0.021831097081303596, "avg_return": 0.8584511280059814, "regret": 0.005006518680602312, "entropy": 0.12478989362716675, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:32.335847Z", "loop": 4184, "env_steps": 2571263999, "loss": 0.025403935462236404, "avg_return": 0.8585741519927979, "regret": 0.005006518680602312, "entropy": 0.13761571049690247, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:33.189886Z", "loop": 4185, "env_steps": 2571878399, "loss": 0.02479112520813942, "avg_return": 0.8577185273170471, "regret": 0.005006518680602312, "entropy": 0.13587990403175354, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:34.044158Z", "loop": 4186, "env_steps": 2572492799, "loss": 0.02316947840154171, "avg_return": 0.857273280620575, "regret": 0.005006518680602312, "entropy": 0.1372409164905548, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:34.898195Z", "loop": 4187, "env_steps": 2573107199, "loss": 0.023679157719016075, "avg_return": 0.8575767278671265, "regret": 0.005006518680602312, "entropy": 0.13541696965694427, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:35.751730Z", "loop": 4188, "env_steps": 2573721599, "loss": 0.02341489866375923, "avg_return": 0.8582730293273926, "regret": 0.005006518680602312, "entropy": 0.14282840490341187, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:36.606359Z", "loop": 4189, "env_steps": 2574335999, "loss": 0.02473234198987484, "avg_return": 0.8559814691543579, "regret": 0.005006518680602312, "entropy": 0.1399737447500229, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:37.499582Z", "loop": 4190, "env_steps": 2574950399, "loss": 0.02576122060418129, "avg_return": 0.8560530543327332, "regret": 0.008629005402326584, "entropy": 0.15205194056034088, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:38.353131Z", "loop": 4191, "env_steps": 2575564799, "loss": 0.027135733515024185, "avg_return": 0.8536497354507446, "regret": 0.008629005402326584, "entropy": 0.16191434860229492, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:39.207811Z", "loop": 4192, "env_steps": 2576179199, "loss": 0.027288764715194702, "avg_return": 0.8543704152107239, "regret": 0.008629005402326584, "entropy": 0.15448175370693207, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:40.061801Z", "loop": 4193, "env_steps": 2576793599, "loss": 0.026377787813544273, "avg_return": 0.854969322681427, "regret": 0.008629005402326584, "entropy": 0.15363584458827972, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:40.915194Z", "loop": 4194, "env_steps": 2577407999, "loss": 0.02562500536441803, "avg_return": 0.8568146824836731, "regret": 0.008629005402326584, "entropy": 0.14788658916950226, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:41.769289Z", "loop": 4195, "env_steps": 2578022399, "loss": 0.024187995120882988, "avg_return": 0.8572282195091248, "regret": 0.008629005402326584, "entropy": 0.1388884037733078, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:42.623645Z", "loop": 4196, "env_steps": 2578636799, "loss": 0.024495530873537064, "avg_return": 0.8560107350349426, "regret": 0.008629005402326584, "entropy": 0.14489050209522247, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:43.478206Z", "loop": 4197, "env_steps": 2579251199, "loss": 0.023352710530161858, "avg_return": 0.856520414352417, "regret": 0.008629005402326584, "entropy": 0.14076358079910278, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:44.332347Z", "loop": 4198, "env_steps": 2579865599, "loss": 0.02502683736383915, "avg_return": 0.8558522462844849, "regret": 0.008629005402326584, "entropy": 0.1443975269794464, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:45.186713Z", "loop": 4199, "env_steps": 2580479999, "loss": 0.026392612606287003, "avg_return": 0.856027364730835, "regret": 0.008629005402326584, "entropy": 0.15289625525474548, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:46.081872Z", "loop": 4200, "env_steps": 2581094399, "loss": 0.026342889294028282, "avg_return": 0.8570759296417236, "regret": 0.008204720914363861, "entropy": 0.1550104022026062, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:46.935570Z", "loop": 4201, "env_steps": 2581708799, "loss": 0.026988252997398376, "avg_return": 0.8560290932655334, "regret": 0.008204720914363861, "entropy": 0.1573142111301422, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:47.790167Z", "loop": 4202, "env_steps": 2582323199, "loss": 0.027826720848679543, "avg_return": 0.8550584316253662, "regret": 0.008204720914363861, "entropy": 0.16456449031829834, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:48.644878Z", "loop": 4203, "env_steps": 2582937599, "loss": 0.028264671564102173, "avg_return": 0.852628231048584, "regret": 0.008204720914363861, "entropy": 0.16734476387500763, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:49.500043Z", "loop": 4204, "env_steps": 2583551999, "loss": 0.028418174013495445, "avg_return": 0.8554943799972534, "regret": 0.008204720914363861, "entropy": 0.16577912867069244, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:50.355515Z", "loop": 4205, "env_steps": 2584166399, "loss": 0.02792150154709816, "avg_return": 0.8553188443183899, "regret": 0.008204720914363861, "entropy": 0.16535095870494843, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:51.210286Z", "loop": 4206, "env_steps": 2584780799, "loss": 0.026286542415618896, "avg_return": 0.8548262715339661, "regret": 0.008204720914363861, "entropy": 0.15508964657783508, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:52.065209Z", "loop": 4207, "env_steps": 2585395199, "loss": 0.026666471734642982, "avg_return": 0.8561424016952515, "regret": 0.008204720914363861, "entropy": 0.152568981051445, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:52.920986Z", "loop": 4208, "env_steps": 2586009599, "loss": 0.026203474029898643, "avg_return": 0.8566570281982422, "regret": 0.008204720914363861, "entropy": 0.15265651047229767, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:53.774921Z", "loop": 4209, "env_steps": 2586623999, "loss": 0.027224427089095116, "avg_return": 0.8541616797447205, "regret": 0.008204720914363861, "entropy": 0.15345008671283722, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:54.671676Z", "loop": 4210, "env_steps": 2587238399, "loss": 0.026442689821124077, "avg_return": 0.8551725745201111, "regret": 0.009326576255261898, "entropy": 0.14792554080486298, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:55.525553Z", "loop": 4211, "env_steps": 2587852799, "loss": 0.02638005092740059, "avg_return": 0.8533558249473572, "regret": 0.009326576255261898, "entropy": 0.14445169270038605, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:56.378448Z", "loop": 4212, "env_steps": 2588467199, "loss": 0.02614029310643673, "avg_return": 0.8544490933418274, "regret": 0.009326576255261898, "entropy": 0.14658772945404053, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:57.232213Z", "loop": 4213, "env_steps": 2589081599, "loss": 0.026695430278778076, "avg_return": 0.8547632098197937, "regret": 0.009326576255261898, "entropy": 0.1507992148399353, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:58.087920Z", "loop": 4214, "env_steps": 2589695999, "loss": 0.0262418482452631, "avg_return": 0.851534366607666, "regret": 0.009326576255261898, "entropy": 0.14805637300014496, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:58.942837Z", "loop": 4215, "env_steps": 2590310399, "loss": 0.02798851765692234, "avg_return": 0.8502865433692932, "regret": 0.009326576255261898, "entropy": 0.15401338040828705, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:23:59.796342Z", "loop": 4216, "env_steps": 2590924799, "loss": 0.02712877094745636, "avg_return": 0.8508263230323792, "regret": 0.009326576255261898, "entropy": 0.15351280570030212, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:00.650578Z", "loop": 4217, "env_steps": 2591539199, "loss": 0.024134745821356773, "avg_return": 0.85274738073349, "regret": 0.009326576255261898, "entropy": 0.1389852613210678, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:01.505193Z", "loop": 4218, "env_steps": 2592153599, "loss": 0.02298918552696705, "avg_return": 0.8559849262237549, "regret": 0.009326576255261898, "entropy": 0.13047465682029724, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:02.360236Z", "loop": 4219, "env_steps": 2592767999, "loss": 0.02362620271742344, "avg_return": 0.8568306565284729, "regret": 0.009326576255261898, "entropy": 0.1301209181547165, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:03.254506Z", "loop": 4220, "env_steps": 2593382399, "loss": 0.021790670230984688, "avg_return": 0.8570658564567566, "regret": 0.00497842114418745, "entropy": 0.1273183673620224, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:04.108347Z", "loop": 4221, "env_steps": 2593996799, "loss": 0.022693639621138573, "avg_return": 0.8580464720726013, "regret": 0.00497842114418745, "entropy": 0.1283462643623352, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:04.964461Z", "loop": 4222, "env_steps": 2594611199, "loss": 0.022369081154465675, "avg_return": 0.8594724535942078, "regret": 0.00497842114418745, "entropy": 0.12978923320770264, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:05.818780Z", "loop": 4223, "env_steps": 2595225599, "loss": 0.022494405508041382, "avg_return": 0.8602972626686096, "regret": 0.00497842114418745, "entropy": 0.1250843107700348, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:06.672860Z", "loop": 4224, "env_steps": 2595839999, "loss": 0.02270270138978958, "avg_return": 0.8606042861938477, "regret": 0.00497842114418745, "entropy": 0.12974484264850616, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:07.526443Z", "loop": 4225, "env_steps": 2596454399, "loss": 0.021823277696967125, "avg_return": 0.8597460389137268, "regret": 0.00497842114418745, "entropy": 0.1261795610189438, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:08.381520Z", "loop": 4226, "env_steps": 2597068799, "loss": 0.02344832755625248, "avg_return": 0.8587679266929626, "regret": 0.00497842114418745, "entropy": 0.1327688843011856, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:09.235553Z", "loop": 4227, "env_steps": 2597683199, "loss": 0.022983502596616745, "avg_return": 0.8602258563041687, "regret": 0.00497842114418745, "entropy": 0.12317948043346405, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:10.089491Z", "loop": 4228, "env_steps": 2598297599, "loss": 0.022996215149760246, "avg_return": 0.8597087860107422, "regret": 0.00497842114418745, "entropy": 0.12328656017780304, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:10.942836Z", "loop": 4229, "env_steps": 2598911999, "loss": 0.022432856261730194, "avg_return": 0.8583019375801086, "regret": 0.00497842114418745, "entropy": 0.12756703794002533, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:11.838467Z", "loop": 4230, "env_steps": 2599526399, "loss": 0.022510765120387077, "avg_return": 0.8599998354911804, "regret": 0.005062040872871876, "entropy": 0.12481797486543655, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:12.692342Z", "loop": 4231, "env_steps": 2600140799, "loss": 0.021357832476496696, "avg_return": 0.8567213416099548, "regret": 0.005062040872871876, "entropy": 0.12200213223695755, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:13.546356Z", "loop": 4232, "env_steps": 2600755199, "loss": 0.022090274840593338, "avg_return": 0.8583258390426636, "regret": 0.005062040872871876, "entropy": 0.12768907845020294, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:14.401098Z", "loop": 4233, "env_steps": 2601369599, "loss": 0.02282804809510708, "avg_return": 0.8592802286148071, "regret": 0.005062040872871876, "entropy": 0.12258077412843704, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:15.256084Z", "loop": 4234, "env_steps": 2601983999, "loss": 0.021457504481077194, "avg_return": 0.858547568321228, "regret": 0.005062040872871876, "entropy": 0.12158659845590591, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:16.112884Z", "loop": 4235, "env_steps": 2602598399, "loss": 0.02260749600827694, "avg_return": 0.857627809047699, "regret": 0.005062040872871876, "entropy": 0.12607017159461975, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:16.968030Z", "loop": 4236, "env_steps": 2603212799, "loss": 0.024160603061318398, "avg_return": 0.856299638748169, "regret": 0.005062040872871876, "entropy": 0.1350742131471634, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:17.821170Z", "loop": 4237, "env_steps": 2603827199, "loss": 0.02599777653813362, "avg_return": 0.854067325592041, "regret": 0.005062040872871876, "entropy": 0.13730719685554504, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:18.675327Z", "loop": 4238, "env_steps": 2604441599, "loss": 0.023874515667557716, "avg_return": 0.8550201654434204, "regret": 0.005062040872871876, "entropy": 0.1303769201040268, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:19.529253Z", "loop": 4239, "env_steps": 2605055999, "loss": 0.02360864356160164, "avg_return": 0.8576003313064575, "regret": 0.005062040872871876, "entropy": 0.12790030241012573, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:20.425676Z", "loop": 4240, "env_steps": 2605670399, "loss": 0.022345496341586113, "avg_return": 0.8575637936592102, "regret": 0.006235537119209766, "entropy": 0.12070387601852417, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:21.279903Z", "loop": 4241, "env_steps": 2606284799, "loss": 0.022329937666654587, "avg_return": 0.8559277653694153, "regret": 0.006235537119209766, "entropy": 0.12218166142702103, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:22.136320Z", "loop": 4242, "env_steps": 2606899199, "loss": 0.024321643635630608, "avg_return": 0.856512188911438, "regret": 0.006235537119209766, "entropy": 0.13057295978069305, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:22.991553Z", "loop": 4243, "env_steps": 2607513599, "loss": 0.024381067603826523, "avg_return": 0.8569365739822388, "regret": 0.006235537119209766, "entropy": 0.1326560527086258, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:23.845805Z", "loop": 4244, "env_steps": 2608127999, "loss": 0.02305532805621624, "avg_return": 0.85547935962677, "regret": 0.006235537119209766, "entropy": 0.12759020924568176, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:24.701040Z", "loop": 4245, "env_steps": 2608742399, "loss": 0.023800602182745934, "avg_return": 0.856552243232727, "regret": 0.006235537119209766, "entropy": 0.13071641325950623, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:25.555537Z", "loop": 4246, "env_steps": 2609356799, "loss": 0.022802820429205894, "avg_return": 0.858512818813324, "regret": 0.006235537119209766, "entropy": 0.12953387200832367, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:26.409184Z", "loop": 4247, "env_steps": 2609971199, "loss": 0.02140636369585991, "avg_return": 0.8586204051971436, "regret": 0.006235537119209766, "entropy": 0.12727053463459015, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:27.262380Z", "loop": 4248, "env_steps": 2610585599, "loss": 0.020934469997882843, "avg_return": 0.8580849170684814, "regret": 0.006235537119209766, "entropy": 0.12440693378448486, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:28.117341Z", "loop": 4249, "env_steps": 2611199999, "loss": 0.023231755942106247, "avg_return": 0.8576268553733826, "regret": 0.006235537119209766, "entropy": 0.1268264353275299, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:29.013886Z", "loop": 4250, "env_steps": 2611814399, "loss": 0.02304253540933132, "avg_return": 0.8579109907150269, "regret": 0.0059035890735685825, "entropy": 0.1292174607515335, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:29.867331Z", "loop": 4251, "env_steps": 2612428799, "loss": 0.02271166816353798, "avg_return": 0.8564294576644897, "regret": 0.0059035890735685825, "entropy": 0.12764127552509308, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:30.721988Z", "loop": 4252, "env_steps": 2613043199, "loss": 0.023068867623806, "avg_return": 0.857044517993927, "regret": 0.0059035890735685825, "entropy": 0.13366936147212982, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:31.576518Z", "loop": 4253, "env_steps": 2613657599, "loss": 0.022762181237339973, "avg_return": 0.8586047291755676, "regret": 0.0059035890735685825, "entropy": 0.12809190154075623, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:32.431996Z", "loop": 4254, "env_steps": 2614271999, "loss": 0.023675357922911644, "avg_return": 0.8591522574424744, "regret": 0.0059035890735685825, "entropy": 0.1339772343635559, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:33.287444Z", "loop": 4255, "env_steps": 2614886399, "loss": 0.022295039147138596, "avg_return": 0.8607030510902405, "regret": 0.0059035890735685825, "entropy": 0.13081829249858856, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:34.141578Z", "loop": 4256, "env_steps": 2615500799, "loss": 0.023884786292910576, "avg_return": 0.8597478270530701, "regret": 0.0059035890735685825, "entropy": 0.13372109830379486, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:34.996077Z", "loop": 4257, "env_steps": 2616115199, "loss": 0.023025060072541237, "avg_return": 0.8591803312301636, "regret": 0.0059035890735685825, "entropy": 0.12968097627162933, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:35.850626Z", "loop": 4258, "env_steps": 2616729599, "loss": 0.021540800109505653, "avg_return": 0.8580006957054138, "regret": 0.0059035890735685825, "entropy": 0.12543119490146637, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:36.707172Z", "loop": 4259, "env_steps": 2617343999, "loss": 0.02201542817056179, "avg_return": 0.858356773853302, "regret": 0.0059035890735685825, "entropy": 0.127579003572464, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:37.603714Z", "loop": 4260, "env_steps": 2617958399, "loss": 0.020979613065719604, "avg_return": 0.8584158420562744, "regret": 0.005406857468187809, "entropy": 0.12391892075538635, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:38.457763Z", "loop": 4261, "env_steps": 2618572799, "loss": 0.022453991696238518, "avg_return": 0.858405351638794, "regret": 0.005406857468187809, "entropy": 0.12682968378067017, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:39.312866Z", "loop": 4262, "env_steps": 2619187199, "loss": 0.023135870695114136, "avg_return": 0.8544732928276062, "regret": 0.005406857468187809, "entropy": 0.12691199779510498, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:40.167794Z", "loop": 4263, "env_steps": 2619801599, "loss": 0.02321125566959381, "avg_return": 0.8546149730682373, "regret": 0.005406857468187809, "entropy": 0.12727080285549164, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:41.022214Z", "loop": 4264, "env_steps": 2620415999, "loss": 0.023079950362443924, "avg_return": 0.8523786664009094, "regret": 0.005406857468187809, "entropy": 0.12161606550216675, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:41.875915Z", "loop": 4265, "env_steps": 2621030399, "loss": 0.023002970963716507, "avg_return": 0.8547040224075317, "regret": 0.005406857468187809, "entropy": 0.12382952123880386, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:42.729580Z", "loop": 4266, "env_steps": 2621644799, "loss": 0.02352471463382244, "avg_return": 0.8521183729171753, "regret": 0.005406857468187809, "entropy": 0.1262323558330536, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:43.583242Z", "loop": 4267, "env_steps": 2622259199, "loss": 0.021627653390169144, "avg_return": 0.8553712964057922, "regret": 0.005406857468187809, "entropy": 0.12492022663354874, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:44.436943Z", "loop": 4268, "env_steps": 2622873599, "loss": 0.021842243149876595, "avg_return": 0.8565137982368469, "regret": 0.005406857468187809, "entropy": 0.12189976871013641, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:45.291497Z", "loop": 4269, "env_steps": 2623487999, "loss": 0.0217145923525095, "avg_return": 0.8589033484458923, "regret": 0.005406857468187809, "entropy": 0.12177827209234238, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:46.184196Z", "loop": 4270, "env_steps": 2624102399, "loss": 0.021042199805378914, "avg_return": 0.8589520454406738, "regret": 0.00485654454678297, "entropy": 0.11877527832984924, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:47.038200Z", "loop": 4271, "env_steps": 2624716799, "loss": 0.0217612162232399, "avg_return": 0.8570782542228699, "regret": 0.00485654454678297, "entropy": 0.12489070743322372, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:47.892173Z", "loop": 4272, "env_steps": 2625331199, "loss": 0.022881504148244858, "avg_return": 0.8577231764793396, "regret": 0.00485654454678297, "entropy": 0.12541303038597107, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:48.746612Z", "loop": 4273, "env_steps": 2625945599, "loss": 0.02420283667743206, "avg_return": 0.8559008240699768, "regret": 0.00485654454678297, "entropy": 0.13529810309410095, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:49.601117Z", "loop": 4274, "env_steps": 2626559999, "loss": 0.025828076526522636, "avg_return": 0.8536421656608582, "regret": 0.00485654454678297, "entropy": 0.14095206558704376, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:50.454063Z", "loop": 4275, "env_steps": 2627174399, "loss": 0.024812547490000725, "avg_return": 0.8565260767936707, "regret": 0.00485654454678297, "entropy": 0.13346311450004578, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:51.307943Z", "loop": 4276, "env_steps": 2627788799, "loss": 0.023026984184980392, "avg_return": 0.8574700951576233, "regret": 0.00485654454678297, "entropy": 0.12599487602710724, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:52.162360Z", "loop": 4277, "env_steps": 2628403199, "loss": 0.021330539137125015, "avg_return": 0.8585520386695862, "regret": 0.00485654454678297, "entropy": 0.11986223608255386, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:53.016225Z", "loop": 4278, "env_steps": 2629017599, "loss": 0.019890759140253067, "avg_return": 0.8590705394744873, "regret": 0.00485654454678297, "entropy": 0.11646656692028046, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:53.869872Z", "loop": 4279, "env_steps": 2629631999, "loss": 0.021349329501390457, "avg_return": 0.8595180511474609, "regret": 0.00485654454678297, "entropy": 0.11601527780294418, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:54.765063Z", "loop": 4280, "env_steps": 2630246399, "loss": 0.020154306665062904, "avg_return": 0.8581585884094238, "regret": 0.004720434546470642, "entropy": 0.11678915470838547, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:55.619383Z", "loop": 4281, "env_steps": 2630860799, "loss": 0.021052509546279907, "avg_return": 0.8583873510360718, "regret": 0.004720434546470642, "entropy": 0.12117777019739151, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:56.473799Z", "loop": 4282, "env_steps": 2631475199, "loss": 0.020712127909064293, "avg_return": 0.8576314449310303, "regret": 0.004720434546470642, "entropy": 0.12285258620977402, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:57.327500Z", "loop": 4283, "env_steps": 2632089599, "loss": 0.02204751968383789, "avg_return": 0.8584653735160828, "regret": 0.004720434546470642, "entropy": 0.12156765908002853, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:58.181969Z", "loop": 4284, "env_steps": 2632703999, "loss": 0.02220950461924076, "avg_return": 0.8594157099723816, "regret": 0.004720434546470642, "entropy": 0.1287764310836792, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:59.035422Z", "loop": 4285, "env_steps": 2633318399, "loss": 0.02189941704273224, "avg_return": 0.8576908707618713, "regret": 0.004720434546470642, "entropy": 0.12523075938224792, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:24:59.889091Z", "loop": 4286, "env_steps": 2633932799, "loss": 0.024159830063581467, "avg_return": 0.8539110422134399, "regret": 0.004720434546470642, "entropy": 0.1368284672498703, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:00.743107Z", "loop": 4287, "env_steps": 2634547199, "loss": 0.02514171414077282, "avg_return": 0.853108286857605, "regret": 0.004720434546470642, "entropy": 0.1333872526884079, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:01.597669Z", "loop": 4288, "env_steps": 2635161599, "loss": 0.02552671730518341, "avg_return": 0.8566475510597229, "regret": 0.004720434546470642, "entropy": 0.13997136056423187, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:02.452035Z", "loop": 4289, "env_steps": 2635775999, "loss": 0.02272174507379532, "avg_return": 0.8588502407073975, "regret": 0.004720434546470642, "entropy": 0.12820231914520264, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:03.347501Z", "loop": 4290, "env_steps": 2636390399, "loss": 0.021792292594909668, "avg_return": 0.858888566493988, "regret": 0.0036592097021639347, "entropy": 0.1240307092666626, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:04.201925Z", "loop": 4291, "env_steps": 2637004799, "loss": 0.02124776877462864, "avg_return": 0.8601066470146179, "regret": 0.0036592097021639347, "entropy": 0.11766715347766876, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:05.055625Z", "loop": 4292, "env_steps": 2637619199, "loss": 0.02174893580377102, "avg_return": 0.858001708984375, "regret": 0.0036592097021639347, "entropy": 0.12152371555566788, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:05.909066Z", "loop": 4293, "env_steps": 2638233599, "loss": 0.023221677169203758, "avg_return": 0.8584077954292297, "regret": 0.0036592097021639347, "entropy": 0.12755730748176575, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:06.763786Z", "loop": 4294, "env_steps": 2638847999, "loss": 0.020639944821596146, "avg_return": 0.8559448719024658, "regret": 0.0036592097021639347, "entropy": 0.11631873995065689, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:07.619051Z", "loop": 4295, "env_steps": 2639462399, "loss": 0.021053651347756386, "avg_return": 0.8578734397888184, "regret": 0.0036592097021639347, "entropy": 0.12203318625688553, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:08.473286Z", "loop": 4296, "env_steps": 2640076799, "loss": 0.021272795274853706, "avg_return": 0.8589043617248535, "regret": 0.0036592097021639347, "entropy": 0.11692942678928375, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:09.327480Z", "loop": 4297, "env_steps": 2640691199, "loss": 0.01976930908858776, "avg_return": 0.8592106103897095, "regret": 0.0036592097021639347, "entropy": 0.11799079924821854, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:10.181338Z", "loop": 4298, "env_steps": 2641305599, "loss": 0.020974380895495415, "avg_return": 0.8612457513809204, "regret": 0.0036592097021639347, "entropy": 0.12085665762424469, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:11.036224Z", "loop": 4299, "env_steps": 2641919999, "loss": 0.02171335555613041, "avg_return": 0.8606679439544678, "regret": 0.0036592097021639347, "entropy": 0.12245691567659378, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:11.930090Z", "loop": 4300, "env_steps": 2642534399, "loss": 0.02176467888057232, "avg_return": 0.8605981469154358, "regret": 0.0037077313754707575, "entropy": 0.1217099279165268, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:12.785734Z", "loop": 4301, "env_steps": 2643148799, "loss": 0.021540777757763863, "avg_return": 0.8598154783248901, "regret": 0.0037077313754707575, "entropy": 0.12294987589120865, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:13.639804Z", "loop": 4302, "env_steps": 2643763199, "loss": 0.022824056446552277, "avg_return": 0.8592508435249329, "regret": 0.0037077313754707575, "entropy": 0.12797613441944122, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:14.494233Z", "loop": 4303, "env_steps": 2644377599, "loss": 0.024191176518797874, "avg_return": 0.8571669459342957, "regret": 0.0037077313754707575, "entropy": 0.13848337531089783, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:15.349458Z", "loop": 4304, "env_steps": 2644991999, "loss": 0.02494828961789608, "avg_return": 0.8571582436561584, "regret": 0.0037077313754707575, "entropy": 0.13648414611816406, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:16.203857Z", "loop": 4305, "env_steps": 2645606399, "loss": 0.02509402669966221, "avg_return": 0.8569560050964355, "regret": 0.0037077313754707575, "entropy": 0.13024234771728516, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:17.059055Z", "loop": 4306, "env_steps": 2646220799, "loss": 0.02288088947534561, "avg_return": 0.8587129712104797, "regret": 0.0037077313754707575, "entropy": 0.1265026032924652, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:17.913804Z", "loop": 4307, "env_steps": 2646835199, "loss": 0.02107778750360012, "avg_return": 0.8605833053588867, "regret": 0.0037077313754707575, "entropy": 0.11940043419599533, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:18.769066Z", "loop": 4308, "env_steps": 2647449599, "loss": 0.021398093551397324, "avg_return": 0.8602651357650757, "regret": 0.0037077313754707575, "entropy": 0.12100565433502197, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:19.623457Z", "loop": 4309, "env_steps": 2648063999, "loss": 0.018298618495464325, "avg_return": 0.8600378632545471, "regret": 0.0037077313754707575, "entropy": 0.11129473894834518, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:20.518328Z", "loop": 4310, "env_steps": 2648678399, "loss": 0.019335076212882996, "avg_return": 0.8601170182228088, "regret": 0.0036806077696383, "entropy": 0.11745728552341461, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:21.371353Z", "loop": 4311, "env_steps": 2649292799, "loss": 0.018699686974287033, "avg_return": 0.8594873547554016, "regret": 0.0036806077696383, "entropy": 0.1083502396941185, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:22.223750Z", "loop": 4312, "env_steps": 2649907199, "loss": 0.02073904685676098, "avg_return": 0.8590932488441467, "regret": 0.0036806077696383, "entropy": 0.11494289338588715, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:23.077891Z", "loop": 4313, "env_steps": 2650521599, "loss": 0.019903235137462616, "avg_return": 0.8593104481697083, "regret": 0.0036806077696383, "entropy": 0.11222557723522186, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:23.932206Z", "loop": 4314, "env_steps": 2651135999, "loss": 0.020310120657086372, "avg_return": 0.8599902391433716, "regret": 0.0036806077696383, "entropy": 0.11360019445419312, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:24.786332Z", "loop": 4315, "env_steps": 2651750399, "loss": 0.020413286983966827, "avg_return": 0.8595369458198547, "regret": 0.0036806077696383, "entropy": 0.1127743050456047, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:25.639710Z", "loop": 4316, "env_steps": 2652364799, "loss": 0.02106420136988163, "avg_return": 0.8601701855659485, "regret": 0.0036806077696383, "entropy": 0.11636332422494888, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:26.493488Z", "loop": 4317, "env_steps": 2652979199, "loss": 0.022452523931860924, "avg_return": 0.8595318794250488, "regret": 0.0036806077696383, "entropy": 0.1260649412870407, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:27.347569Z", "loop": 4318, "env_steps": 2653593599, "loss": 0.0203813798725605, "avg_return": 0.8602398633956909, "regret": 0.0036806077696383, "entropy": 0.12164299935102463, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:28.200880Z", "loop": 4319, "env_steps": 2654207999, "loss": 0.022017478942871094, "avg_return": 0.8597807288169861, "regret": 0.0036806077696383, "entropy": 0.12464166432619095, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:29.093963Z", "loop": 4320, "env_steps": 2654822399, "loss": 0.021973690018057823, "avg_return": 0.858035683631897, "regret": 0.004295762628316879, "entropy": 0.1325768679380417, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:29.947211Z", "loop": 4321, "env_steps": 2655436799, "loss": 0.023849064484238625, "avg_return": 0.856573224067688, "regret": 0.004295762628316879, "entropy": 0.13374078273773193, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:30.801961Z", "loop": 4322, "env_steps": 2656051199, "loss": 0.025065088644623756, "avg_return": 0.8563324213027954, "regret": 0.004295762628316879, "entropy": 0.1442725956439972, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:31.656614Z", "loop": 4323, "env_steps": 2656665599, "loss": 0.023494457826018333, "avg_return": 0.8567341566085815, "regret": 0.004295762628316879, "entropy": 0.13935516774654388, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:32.509856Z", "loop": 4324, "env_steps": 2657279999, "loss": 0.02329246886074543, "avg_return": 0.8598809838294983, "regret": 0.004295762628316879, "entropy": 0.13322490453720093, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:33.363754Z", "loop": 4325, "env_steps": 2657894399, "loss": 0.02266368642449379, "avg_return": 0.8591499924659729, "regret": 0.004295762628316879, "entropy": 0.12525972723960876, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:34.219692Z", "loop": 4326, "env_steps": 2658508799, "loss": 0.02177455648779869, "avg_return": 0.8601881265640259, "regret": 0.004295762628316879, "entropy": 0.12457754462957382, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:35.073567Z", "loop": 4327, "env_steps": 2659123199, "loss": 0.021191997453570366, "avg_return": 0.860317587852478, "regret": 0.004295762628316879, "entropy": 0.11454706639051437, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:35.927873Z", "loop": 4328, "env_steps": 2659737599, "loss": 0.021130777895450592, "avg_return": 0.8577657341957092, "regret": 0.004295762628316879, "entropy": 0.11957754194736481, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:36.782273Z", "loop": 4329, "env_steps": 2660351999, "loss": 0.02212040312588215, "avg_return": 0.8577011227607727, "regret": 0.004295762628316879, "entropy": 0.12412885576486588, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:37.677960Z", "loop": 4330, "env_steps": 2660966399, "loss": 0.020628927275538445, "avg_return": 0.8576464056968689, "regret": 0.006310394499450922, "entropy": 0.11596661061048508, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:38.532210Z", "loop": 4331, "env_steps": 2661580799, "loss": 0.023369988426566124, "avg_return": 0.8570196628570557, "regret": 0.006310394499450922, "entropy": 0.12590816617012024, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:39.388214Z", "loop": 4332, "env_steps": 2662195199, "loss": 0.020859986543655396, "avg_return": 0.8586814403533936, "regret": 0.006310394499450922, "entropy": 0.1129709780216217, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:40.242781Z", "loop": 4333, "env_steps": 2662809599, "loss": 0.02158699557185173, "avg_return": 0.8597931861877441, "regret": 0.006310394499450922, "entropy": 0.12254457920789719, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:41.097596Z", "loop": 4334, "env_steps": 2663423999, "loss": 0.018669644370675087, "avg_return": 0.8587275147438049, "regret": 0.006310394499450922, "entropy": 0.10815294831991196, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:41.951055Z", "loop": 4335, "env_steps": 2664038399, "loss": 0.019918227568268776, "avg_return": 0.8591213226318359, "regret": 0.006310394499450922, "entropy": 0.1134321317076683, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:42.804390Z", "loop": 4336, "env_steps": 2664652799, "loss": 0.020299948751926422, "avg_return": 0.8595966696739197, "regret": 0.006310394499450922, "entropy": 0.1166367456316948, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:43.657873Z", "loop": 4337, "env_steps": 2665267199, "loss": 0.019969098269939423, "avg_return": 0.8612895011901855, "regret": 0.006310394499450922, "entropy": 0.11637891083955765, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:44.511852Z", "loop": 4338, "env_steps": 2665881599, "loss": 0.023048091679811478, "avg_return": 0.8585242629051208, "regret": 0.006310394499450922, "entropy": 0.12180675566196442, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:45.365266Z", "loop": 4339, "env_steps": 2666495999, "loss": 0.021595889702439308, "avg_return": 0.8588646650314331, "regret": 0.006310394499450922, "entropy": 0.12263224273920059, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:46.259627Z", "loop": 4340, "env_steps": 2667110399, "loss": 0.02187761291861534, "avg_return": 0.8577722311019897, "regret": 0.005213856231421232, "entropy": 0.12408994883298874, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:47.113388Z", "loop": 4341, "env_steps": 2667724799, "loss": 0.02377295307815075, "avg_return": 0.8567917346954346, "regret": 0.005213856231421232, "entropy": 0.12729708850383759, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:47.967182Z", "loop": 4342, "env_steps": 2668339199, "loss": 0.022573618218302727, "avg_return": 0.8580255508422852, "regret": 0.005213856231421232, "entropy": 0.12305770814418793, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:48.820527Z", "loop": 4343, "env_steps": 2668953599, "loss": 0.02092067152261734, "avg_return": 0.8579312562942505, "regret": 0.005213856231421232, "entropy": 0.11766541004180908, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:49.675301Z", "loop": 4344, "env_steps": 2669567999, "loss": 0.019923126325011253, "avg_return": 0.8594933152198792, "regret": 0.005213856231421232, "entropy": 0.11607978492975235, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:50.528469Z", "loop": 4345, "env_steps": 2670182399, "loss": 0.020335661247372627, "avg_return": 0.8604282736778259, "regret": 0.005213856231421232, "entropy": 0.11306159198284149, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:51.382411Z", "loop": 4346, "env_steps": 2670796799, "loss": 0.020051153376698494, "avg_return": 0.8617959022521973, "regret": 0.005213856231421232, "entropy": 0.11849445104598999, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:52.236315Z", "loop": 4347, "env_steps": 2671411199, "loss": 0.020199840888381004, "avg_return": 0.8598366379737854, "regret": 0.005213856231421232, "entropy": 0.11443663388490677, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:53.090814Z", "loop": 4348, "env_steps": 2672025599, "loss": 0.020080408081412315, "avg_return": 0.8600398898124695, "regret": 0.005213856231421232, "entropy": 0.11587925255298615, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:53.944941Z", "loop": 4349, "env_steps": 2672639999, "loss": 0.02024025097489357, "avg_return": 0.8592476844787598, "regret": 0.005213856231421232, "entropy": 0.11273742467164993, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:54.843687Z", "loop": 4350, "env_steps": 2673254399, "loss": 0.020240044221282005, "avg_return": 0.8625473976135254, "regret": 0.003512241644784808, "entropy": 0.1208641529083252, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:55.697007Z", "loop": 4351, "env_steps": 2673868799, "loss": 0.020558757707476616, "avg_return": 0.8611693382263184, "regret": 0.003512241644784808, "entropy": 0.11945491284132004, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:56.551703Z", "loop": 4352, "env_steps": 2674483199, "loss": 0.02055959589779377, "avg_return": 0.8602824211120605, "regret": 0.003512241644784808, "entropy": 0.11497841030359268, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:57.405350Z", "loop": 4353, "env_steps": 2675097599, "loss": 0.019947422668337822, "avg_return": 0.8605096936225891, "regret": 0.003512241644784808, "entropy": 0.11228854209184647, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:58.260262Z", "loop": 4354, "env_steps": 2675711999, "loss": 0.02107485756278038, "avg_return": 0.8571202754974365, "regret": 0.003512241644784808, "entropy": 0.11656349897384644, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:59.114805Z", "loop": 4355, "env_steps": 2676326399, "loss": 0.021555785089731216, "avg_return": 0.8581205606460571, "regret": 0.003512241644784808, "entropy": 0.11960621178150177, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:25:59.968230Z", "loop": 4356, "env_steps": 2676940799, "loss": 0.021780522540211678, "avg_return": 0.8583321571350098, "regret": 0.003512241644784808, "entropy": 0.11601785570383072, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:00.822365Z", "loop": 4357, "env_steps": 2677555199, "loss": 0.021437818184494972, "avg_return": 0.8575364351272583, "regret": 0.003512241644784808, "entropy": 0.11646830290555954, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:01.676698Z", "loop": 4358, "env_steps": 2678169599, "loss": 0.021677246317267418, "avg_return": 0.8547375798225403, "regret": 0.003512241644784808, "entropy": 0.11925480514764786, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:02.530981Z", "loop": 4359, "env_steps": 2678783999, "loss": 0.022007878869771957, "avg_return": 0.8560404777526855, "regret": 0.003512241644784808, "entropy": 0.11604571342468262, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:03.426056Z", "loop": 4360, "env_steps": 2679398399, "loss": 0.021017463877797127, "avg_return": 0.8549160957336426, "regret": 0.008953085169196129, "entropy": 0.11599870771169662, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:04.279372Z", "loop": 4361, "env_steps": 2680012799, "loss": 0.020829780027270317, "avg_return": 0.8537126779556274, "regret": 0.008953085169196129, "entropy": 0.11558913439512253, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:05.133256Z", "loop": 4362, "env_steps": 2680627199, "loss": 0.020577447488904, "avg_return": 0.8533852100372314, "regret": 0.008953085169196129, "entropy": 0.11097364872694016, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:05.987409Z", "loop": 4363, "env_steps": 2681241599, "loss": 0.02120666764676571, "avg_return": 0.8519567847251892, "regret": 0.008953085169196129, "entropy": 0.11336006224155426, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:06.841748Z", "loop": 4364, "env_steps": 2681855999, "loss": 0.01921532116830349, "avg_return": 0.8541600704193115, "regret": 0.008953085169196129, "entropy": 0.11010614037513733, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:07.694899Z", "loop": 4365, "env_steps": 2682470399, "loss": 0.019534839317202568, "avg_return": 0.857581615447998, "regret": 0.008953085169196129, "entropy": 0.10659198462963104, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:08.547867Z", "loop": 4366, "env_steps": 2683084799, "loss": 0.01805661991238594, "avg_return": 0.8587509393692017, "regret": 0.008953085169196129, "entropy": 0.10337962955236435, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:09.401685Z", "loop": 4367, "env_steps": 2683699199, "loss": 0.021129656583070755, "avg_return": 0.8598861694335938, "regret": 0.008953085169196129, "entropy": 0.1147298589348793, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:10.257049Z", "loop": 4368, "env_steps": 2684313599, "loss": 0.020792139694094658, "avg_return": 0.8606467843055725, "regret": 0.008953085169196129, "entropy": 0.11393871903419495, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:11.110442Z", "loop": 4369, "env_steps": 2684927999, "loss": 0.02142983488738537, "avg_return": 0.8586812615394592, "regret": 0.008953085169196129, "entropy": 0.11775004863739014, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:12.003386Z", "loop": 4370, "env_steps": 2685542399, "loss": 0.02112237736582756, "avg_return": 0.8599146008491516, "regret": 0.005422535352408886, "entropy": 0.11588101834058762, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:12.856273Z", "loop": 4371, "env_steps": 2686156799, "loss": 0.022479496896266937, "avg_return": 0.8579895496368408, "regret": 0.005422535352408886, "entropy": 0.12242812663316727, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:13.711513Z", "loop": 4372, "env_steps": 2686771199, "loss": 0.02229534462094307, "avg_return": 0.858888566493988, "regret": 0.005422535352408886, "entropy": 0.12134295701980591, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:14.565383Z", "loop": 4373, "env_steps": 2687385599, "loss": 0.020638292655348778, "avg_return": 0.8600711226463318, "regret": 0.005422535352408886, "entropy": 0.11752425134181976, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:15.418702Z", "loop": 4374, "env_steps": 2687999999, "loss": 0.019613785669207573, "avg_return": 0.8594543933868408, "regret": 0.005422535352408886, "entropy": 0.11403398960828781, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:16.272796Z", "loop": 4375, "env_steps": 2688614399, "loss": 0.01932712458074093, "avg_return": 0.8591233491897583, "regret": 0.005422535352408886, "entropy": 0.1150524914264679, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:17.128305Z", "loop": 4376, "env_steps": 2689228799, "loss": 0.02097253128886223, "avg_return": 0.8588733077049255, "regret": 0.005422535352408886, "entropy": 0.11504509299993515, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:17.982524Z", "loop": 4377, "env_steps": 2689843199, "loss": 0.021232260391116142, "avg_return": 0.8598785400390625, "regret": 0.005422535352408886, "entropy": 0.11678320914506912, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:18.836507Z", "loop": 4378, "env_steps": 2690457599, "loss": 0.0201752707362175, "avg_return": 0.8593517541885376, "regret": 0.005422535352408886, "entropy": 0.1166377142071724, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:19.689417Z", "loop": 4379, "env_steps": 2691071999, "loss": 0.020868433639407158, "avg_return": 0.8597645163536072, "regret": 0.005422535352408886, "entropy": 0.11664990335702896, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:20.584634Z", "loop": 4380, "env_steps": 2691686399, "loss": 0.02110617235302925, "avg_return": 0.859268844127655, "regret": 0.004685087129473686, "entropy": 0.12323162704706192, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:21.438496Z", "loop": 4381, "env_steps": 2692300799, "loss": 0.021369967609643936, "avg_return": 0.8589093089103699, "regret": 0.004685087129473686, "entropy": 0.12122687697410583, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:22.293125Z", "loop": 4382, "env_steps": 2692915199, "loss": 0.022753791883587837, "avg_return": 0.8576822280883789, "regret": 0.004685087129473686, "entropy": 0.12662045657634735, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:23.147046Z", "loop": 4383, "env_steps": 2693529599, "loss": 0.022520845755934715, "avg_return": 0.8582180142402649, "regret": 0.004685087129473686, "entropy": 0.12482469528913498, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:24.001153Z", "loop": 4384, "env_steps": 2694143999, "loss": 0.022711945697665215, "avg_return": 0.8579785227775574, "regret": 0.004685087129473686, "entropy": 0.12446831166744232, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:24.855138Z", "loop": 4385, "env_steps": 2694758399, "loss": 0.023743748664855957, "avg_return": 0.8564116358757019, "regret": 0.004685087129473686, "entropy": 0.1277466118335724, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:25.709616Z", "loop": 4386, "env_steps": 2695372799, "loss": 0.023564733564853668, "avg_return": 0.8560541272163391, "regret": 0.004685087129473686, "entropy": 0.12884819507598877, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:26.565027Z", "loop": 4387, "env_steps": 2695987199, "loss": 0.02312624827027321, "avg_return": 0.8588282465934753, "regret": 0.004685087129473686, "entropy": 0.12915614247322083, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:27.417744Z", "loop": 4388, "env_steps": 2696601599, "loss": 0.022004904225468636, "avg_return": 0.8570038080215454, "regret": 0.004685087129473686, "entropy": 0.12177294492721558, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:28.271167Z", "loop": 4389, "env_steps": 2697215999, "loss": 0.0215581264346838, "avg_return": 0.8603371381759644, "regret": 0.004685087129473686, "entropy": 0.12245051562786102, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:29.166267Z", "loop": 4390, "env_steps": 2697830399, "loss": 0.020568562671542168, "avg_return": 0.8597983717918396, "regret": 0.00396878132596612, "entropy": 0.11916398257017136, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:30.020459Z", "loop": 4391, "env_steps": 2698444799, "loss": 0.020332278683781624, "avg_return": 0.8598309755325317, "regret": 0.00396878132596612, "entropy": 0.11793235689401627, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:30.874550Z", "loop": 4392, "env_steps": 2699059199, "loss": 0.020416563376784325, "avg_return": 0.8599628806114197, "regret": 0.00396878132596612, "entropy": 0.11176307499408722, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:31.729176Z", "loop": 4393, "env_steps": 2699673599, "loss": 0.021487688645720482, "avg_return": 0.8596609830856323, "regret": 0.00396878132596612, "entropy": 0.11701303720474243, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:32.583842Z", "loop": 4394, "env_steps": 2700287999, "loss": 0.02037952095270157, "avg_return": 0.8591105341911316, "regret": 0.00396878132596612, "entropy": 0.11423610150814056, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:33.438236Z", "loop": 4395, "env_steps": 2700902399, "loss": 0.02050747349858284, "avg_return": 0.8601540327072144, "regret": 0.00396878132596612, "entropy": 0.11528467386960983, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:34.291676Z", "loop": 4396, "env_steps": 2701516799, "loss": 0.022189170122146606, "avg_return": 0.8607527613639832, "regret": 0.00396878132596612, "entropy": 0.12110359221696854, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:35.145505Z", "loop": 4397, "env_steps": 2702131199, "loss": 0.021446188911795616, "avg_return": 0.859123170375824, "regret": 0.00396878132596612, "entropy": 0.11270859092473984, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:35.998846Z", "loop": 4398, "env_steps": 2702745599, "loss": 0.020888449624180794, "avg_return": 0.8603993058204651, "regret": 0.00396878132596612, "entropy": 0.11864820867776871, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:36.853042Z", "loop": 4399, "env_steps": 2703359999, "loss": 0.022721342742443085, "avg_return": 0.8597444891929626, "regret": 0.00396878132596612, "entropy": 0.1253846138715744, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:37.748913Z", "loop": 4400, "env_steps": 2703974399, "loss": 0.022080590948462486, "avg_return": 0.8568786978721619, "regret": 0.005411813501268625, "entropy": 0.11769253015518188, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:38.603131Z", "loop": 4401, "env_steps": 2704588799, "loss": 0.022804537788033485, "avg_return": 0.8563156127929688, "regret": 0.005411813501268625, "entropy": 0.12170162796974182, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:39.457665Z", "loop": 4402, "env_steps": 2705203199, "loss": 0.0221941526979208, "avg_return": 0.8563814759254456, "regret": 0.005411813501268625, "entropy": 0.12184474617242813, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:40.312571Z", "loop": 4403, "env_steps": 2705817599, "loss": 0.022742843255400658, "avg_return": 0.8576365113258362, "regret": 0.005411813501268625, "entropy": 0.12771692872047424, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:41.166824Z", "loop": 4404, "env_steps": 2706431999, "loss": 0.024077197536826134, "avg_return": 0.8598580956459045, "regret": 0.005411813501268625, "entropy": 0.13282081484794617, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:42.021370Z", "loop": 4405, "env_steps": 2707046399, "loss": 0.023095088079571724, "avg_return": 0.8580074310302734, "regret": 0.005411813501268625, "entropy": 0.134286031126976, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:42.875125Z", "loop": 4406, "env_steps": 2707660799, "loss": 0.024156682193279266, "avg_return": 0.8585246801376343, "regret": 0.005411813501268625, "entropy": 0.13661591708660126, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:43.729220Z", "loop": 4407, "env_steps": 2708275199, "loss": 0.024673115462064743, "avg_return": 0.8575264811515808, "regret": 0.005411813501268625, "entropy": 0.14142319560050964, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:44.584049Z", "loop": 4408, "env_steps": 2708889599, "loss": 0.023211725056171417, "avg_return": 0.8585749268531799, "regret": 0.005411813501268625, "entropy": 0.13708367943763733, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:45.438742Z", "loop": 4409, "env_steps": 2709503999, "loss": 0.02508951537311077, "avg_return": 0.8577625751495361, "regret": 0.005411813501268625, "entropy": 0.13979466259479523, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:46.334687Z", "loop": 4410, "env_steps": 2710118399, "loss": 0.025807535275816917, "avg_return": 0.8573046922683716, "regret": 0.005222289822995663, "entropy": 0.1395818144083023, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:47.188327Z", "loop": 4411, "env_steps": 2710732799, "loss": 0.025484789162874222, "avg_return": 0.8573780655860901, "regret": 0.005222289822995663, "entropy": 0.14247973263263702, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:48.042072Z", "loop": 4412, "env_steps": 2711347199, "loss": 0.023511815816164017, "avg_return": 0.8581341505050659, "regret": 0.005222289822995663, "entropy": 0.13630540668964386, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:48.896266Z", "loop": 4413, "env_steps": 2711961599, "loss": 0.02275683358311653, "avg_return": 0.857223629951477, "regret": 0.005222289822995663, "entropy": 0.12798821926116943, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:49.751413Z", "loop": 4414, "env_steps": 2712575999, "loss": 0.024741051718592644, "avg_return": 0.858896791934967, "regret": 0.005222289822995663, "entropy": 0.1338554173707962, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:50.604907Z", "loop": 4415, "env_steps": 2713190399, "loss": 0.021504830569028854, "avg_return": 0.859729528427124, "regret": 0.005222289822995663, "entropy": 0.12150648981332779, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:51.457565Z", "loop": 4416, "env_steps": 2713804799, "loss": 0.021050894632935524, "avg_return": 0.8609405755996704, "regret": 0.005222289822995663, "entropy": 0.12034224718809128, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:52.311122Z", "loop": 4417, "env_steps": 2714419199, "loss": 0.01940387301146984, "avg_return": 0.86137455701828, "regret": 0.005222289822995663, "entropy": 0.11472976207733154, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:53.166471Z", "loop": 4418, "env_steps": 2715033599, "loss": 0.0198665838688612, "avg_return": 0.8617294430732727, "regret": 0.005222289822995663, "entropy": 0.11259793490171432, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:54.021720Z", "loop": 4419, "env_steps": 2715647999, "loss": 0.01940298266708851, "avg_return": 0.8606355786323547, "regret": 0.005222289822995663, "entropy": 0.10927323251962662, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:54.915865Z", "loop": 4420, "env_steps": 2716262399, "loss": 0.01973649673163891, "avg_return": 0.8602643013000488, "regret": 0.003204712411388755, "entropy": 0.11135254800319672, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:55.770675Z", "loop": 4421, "env_steps": 2716876799, "loss": 0.020727869123220444, "avg_return": 0.8595656752586365, "regret": 0.003204712411388755, "entropy": 0.11490768194198608, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:56.625661Z", "loop": 4422, "env_steps": 2717491199, "loss": 0.020088648423552513, "avg_return": 0.8584699630737305, "regret": 0.003204712411388755, "entropy": 0.11109058558940887, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:57.479495Z", "loop": 4423, "env_steps": 2718105599, "loss": 0.018763763830065727, "avg_return": 0.857790470123291, "regret": 0.003204712411388755, "entropy": 0.10929408669471741, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:58.331775Z", "loop": 4424, "env_steps": 2718719999, "loss": 0.02125520072877407, "avg_return": 0.8564040064811707, "regret": 0.003204712411388755, "entropy": 0.11682700365781784, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:26:59.184462Z", "loop": 4425, "env_steps": 2719334399, "loss": 0.02140974812209606, "avg_return": 0.8564280271530151, "regret": 0.003204712411388755, "entropy": 0.11959075927734375, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:00.038513Z", "loop": 4426, "env_steps": 2719948799, "loss": 0.02243572287261486, "avg_return": 0.8571126461029053, "regret": 0.003204712411388755, "entropy": 0.11454612761735916, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:00.891645Z", "loop": 4427, "env_steps": 2720563199, "loss": 0.019923359155654907, "avg_return": 0.858461856842041, "regret": 0.003204712411388755, "entropy": 0.11319859325885773, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:01.744585Z", "loop": 4428, "env_steps": 2721177599, "loss": 0.02108732797205448, "avg_return": 0.858604371547699, "regret": 0.003204712411388755, "entropy": 0.11614220589399338, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:02.598727Z", "loop": 4429, "env_steps": 2721791999, "loss": 0.020965812727808952, "avg_return": 0.8585118055343628, "regret": 0.003204712411388755, "entropy": 0.11257234215736389, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:03.496490Z", "loop": 4430, "env_steps": 2722406399, "loss": 0.018104560673236847, "avg_return": 0.8594357371330261, "regret": 0.003947271499782801, "entropy": 0.10929770022630692, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:04.351527Z", "loop": 4431, "env_steps": 2723020799, "loss": 0.020240632817149162, "avg_return": 0.8600846529006958, "regret": 0.003947271499782801, "entropy": 0.1112341657280922, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:05.207328Z", "loop": 4432, "env_steps": 2723635199, "loss": 0.019101697951555252, "avg_return": 0.8588285446166992, "regret": 0.003947271499782801, "entropy": 0.11454204469919205, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:06.061150Z", "loop": 4433, "env_steps": 2724249599, "loss": 0.021700715646147728, "avg_return": 0.8575810194015503, "regret": 0.003947271499782801, "entropy": 0.11906728148460388, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:06.915889Z", "loop": 4434, "env_steps": 2724863999, "loss": 0.020648840814828873, "avg_return": 0.8589039444923401, "regret": 0.003947271499782801, "entropy": 0.11643756181001663, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:07.769758Z", "loop": 4435, "env_steps": 2725478399, "loss": 0.022594353184103966, "avg_return": 0.8557364344596863, "regret": 0.003947271499782801, "entropy": 0.1235092282295227, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:08.625078Z", "loop": 4436, "env_steps": 2726092799, "loss": 0.021976066753268242, "avg_return": 0.8576815128326416, "regret": 0.003947271499782801, "entropy": 0.12427166849374771, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:09.478936Z", "loop": 4437, "env_steps": 2726707199, "loss": 0.02221493422985077, "avg_return": 0.8575075268745422, "regret": 0.003947271499782801, "entropy": 0.12258386611938477, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:10.333685Z", "loop": 4438, "env_steps": 2727321599, "loss": 0.02153456024825573, "avg_return": 0.8576045036315918, "regret": 0.003947271499782801, "entropy": 0.12439345568418503, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:11.187596Z", "loop": 4439, "env_steps": 2727935999, "loss": 0.02151317149400711, "avg_return": 0.8568937182426453, "regret": 0.003947271499782801, "entropy": 0.12466801702976227, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:12.082830Z", "loop": 4440, "env_steps": 2728550399, "loss": 0.02283121831715107, "avg_return": 0.8588194847106934, "regret": 0.005241368897259235, "entropy": 0.12572593986988068, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:12.936622Z", "loop": 4441, "env_steps": 2729164799, "loss": 0.02017478086054325, "avg_return": 0.8585507273674011, "regret": 0.005241368897259235, "entropy": 0.11515171825885773, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:13.791949Z", "loop": 4442, "env_steps": 2729779199, "loss": 0.022385302931070328, "avg_return": 0.8583903312683105, "regret": 0.005241368897259235, "entropy": 0.1255292296409607, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:14.646520Z", "loop": 4443, "env_steps": 2730393599, "loss": 0.022506004199385643, "avg_return": 0.8588557243347168, "regret": 0.005241368897259235, "entropy": 0.1251843273639679, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:15.501562Z", "loop": 4444, "env_steps": 2731007999, "loss": 0.02050359919667244, "avg_return": 0.8583729267120361, "regret": 0.005241368897259235, "entropy": 0.11781371384859085, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:16.357677Z", "loop": 4445, "env_steps": 2731622399, "loss": 0.020891064777970314, "avg_return": 0.8586102724075317, "regret": 0.005241368897259235, "entropy": 0.11642687022686005, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:17.212911Z", "loop": 4446, "env_steps": 2732236799, "loss": 0.019644757732748985, "avg_return": 0.8611380457878113, "regret": 0.005241368897259235, "entropy": 0.11608929187059402, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:18.067197Z", "loop": 4447, "env_steps": 2732851199, "loss": 0.021725136786699295, "avg_return": 0.8586962819099426, "regret": 0.005241368897259235, "entropy": 0.12191805988550186, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:18.922286Z", "loop": 4448, "env_steps": 2733465599, "loss": 0.020047185942530632, "avg_return": 0.859178900718689, "regret": 0.005241368897259235, "entropy": 0.11998721957206726, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:19.777269Z", "loop": 4449, "env_steps": 2734079999, "loss": 0.022344013676047325, "avg_return": 0.8579174280166626, "regret": 0.005241368897259235, "entropy": 0.12802423536777496, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:20.674662Z", "loop": 4450, "env_steps": 2734694399, "loss": 0.02290298603475094, "avg_return": 0.8575893640518188, "regret": 0.007082275580614805, "entropy": 0.12949594855308533, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:21.529529Z", "loop": 4451, "env_steps": 2735308799, "loss": 0.021961115300655365, "avg_return": 0.8586730360984802, "regret": 0.007082275580614805, "entropy": 0.12456025183200836, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:22.384005Z", "loop": 4452, "env_steps": 2735923199, "loss": 0.02183130569756031, "avg_return": 0.861162543296814, "regret": 0.007082275580614805, "entropy": 0.12723949551582336, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:23.238921Z", "loop": 4453, "env_steps": 2736537599, "loss": 0.019933318719267845, "avg_return": 0.8571534156799316, "regret": 0.007082275580614805, "entropy": 0.11674807220697403, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:24.093483Z", "loop": 4454, "env_steps": 2737151999, "loss": 0.02087494730949402, "avg_return": 0.8586323261260986, "regret": 0.007082275580614805, "entropy": 0.11694800853729248, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:24.947458Z", "loop": 4455, "env_steps": 2737766399, "loss": 0.020700402557849884, "avg_return": 0.8577637076377869, "regret": 0.007082275580614805, "entropy": 0.11636800318956375, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:25.800728Z", "loop": 4456, "env_steps": 2738380799, "loss": 0.020299380645155907, "avg_return": 0.8573358654975891, "regret": 0.007082275580614805, "entropy": 0.11441724002361298, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:26.653817Z", "loop": 4457, "env_steps": 2738995199, "loss": 0.021280521526932716, "avg_return": 0.8588446378707886, "regret": 0.007082275580614805, "entropy": 0.11359747499227524, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:27.508289Z", "loop": 4458, "env_steps": 2739609599, "loss": 0.020003752782940865, "avg_return": 0.859157919883728, "regret": 0.007082275580614805, "entropy": 0.11318463832139969, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:28.361823Z", "loop": 4459, "env_steps": 2740223999, "loss": 0.01973055489361286, "avg_return": 0.8600378632545471, "regret": 0.007082275580614805, "entropy": 0.11309373378753662, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:29.256454Z", "loop": 4460, "env_steps": 2740838399, "loss": 0.020795881748199463, "avg_return": 0.8601502776145935, "regret": 0.0037217549979686737, "entropy": 0.11951367557048798, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:30.110684Z", "loop": 4461, "env_steps": 2741452799, "loss": 0.0191575326025486, "avg_return": 0.8608041405677795, "regret": 0.0037217549979686737, "entropy": 0.11557423323392868, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:30.965234Z", "loop": 4462, "env_steps": 2742067199, "loss": 0.02118316851556301, "avg_return": 0.8591099381446838, "regret": 0.0037217549979686737, "entropy": 0.11946363747119904, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:31.818794Z", "loop": 4463, "env_steps": 2742681599, "loss": 0.01969565823674202, "avg_return": 0.8583542108535767, "regret": 0.0037217549979686737, "entropy": 0.11678256094455719, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:32.672303Z", "loop": 4464, "env_steps": 2743295999, "loss": 0.020805684849619865, "avg_return": 0.8587395548820496, "regret": 0.0037217549979686737, "entropy": 0.11449947953224182, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:33.525580Z", "loop": 4465, "env_steps": 2743910399, "loss": 0.0220160111784935, "avg_return": 0.8607137203216553, "regret": 0.0037217549979686737, "entropy": 0.11816898733377457, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:34.379405Z", "loop": 4466, "env_steps": 2744524799, "loss": 0.01959688402712345, "avg_return": 0.8602471351623535, "regret": 0.0037217549979686737, "entropy": 0.1122385710477829, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:35.233273Z", "loop": 4467, "env_steps": 2745139199, "loss": 0.01948714256286621, "avg_return": 0.8598982691764832, "regret": 0.0037217549979686737, "entropy": 0.10876395553350449, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:36.087015Z", "loop": 4468, "env_steps": 2745753599, "loss": 0.018609603866934776, "avg_return": 0.8589750528335571, "regret": 0.0037217549979686737, "entropy": 0.11027925461530685, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:36.940735Z", "loop": 4469, "env_steps": 2746367999, "loss": 0.019524797797203064, "avg_return": 0.8591808080673218, "regret": 0.0037217549979686737, "entropy": 0.10973361879587173, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:37.835687Z", "loop": 4470, "env_steps": 2746982399, "loss": 0.020269742235541344, "avg_return": 0.860226035118103, "regret": 0.004076696000993252, "entropy": 0.10949268937110901, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:38.689334Z", "loop": 4471, "env_steps": 2747596799, "loss": 0.01944122649729252, "avg_return": 0.859802782535553, "regret": 0.004076696000993252, "entropy": 0.10928066819906235, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:39.543537Z", "loop": 4472, "env_steps": 2748211199, "loss": 0.020769719034433365, "avg_return": 0.859341025352478, "regret": 0.004076696000993252, "entropy": 0.1161293238401413, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:40.398107Z", "loop": 4473, "env_steps": 2748825599, "loss": 0.02197994850575924, "avg_return": 0.8583313226699829, "regret": 0.004076696000993252, "entropy": 0.11797382682561874, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:41.252047Z", "loop": 4474, "env_steps": 2749439999, "loss": 0.02044565975666046, "avg_return": 0.8571780323982239, "regret": 0.004076696000993252, "entropy": 0.11207881569862366, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:42.105760Z", "loop": 4475, "env_steps": 2750054399, "loss": 0.02243155986070633, "avg_return": 0.8569254875183105, "regret": 0.004076696000993252, "entropy": 0.12108708173036575, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:42.960278Z", "loop": 4476, "env_steps": 2750668799, "loss": 0.02179265022277832, "avg_return": 0.8583052754402161, "regret": 0.004076696000993252, "entropy": 0.12111297249794006, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:43.814386Z", "loop": 4477, "env_steps": 2751283199, "loss": 0.02085702493786812, "avg_return": 0.8574022650718689, "regret": 0.004076696000993252, "entropy": 0.11544917523860931, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:44.668480Z", "loop": 4478, "env_steps": 2751897599, "loss": 0.021990975365042686, "avg_return": 0.8571270704269409, "regret": 0.004076696000993252, "entropy": 0.11898022145032883, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:45.522383Z", "loop": 4479, "env_steps": 2752511999, "loss": 0.02175878919661045, "avg_return": 0.8582708835601807, "regret": 0.004076696000993252, "entropy": 0.11824657768011093, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:46.416718Z", "loop": 4480, "env_steps": 2753126399, "loss": 0.01968563161790371, "avg_return": 0.859218180179596, "regret": 0.004354051314294338, "entropy": 0.11654611676931381, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:47.270318Z", "loop": 4481, "env_steps": 2753740799, "loss": 0.020704125985503197, "avg_return": 0.859844982624054, "regret": 0.004354051314294338, "entropy": 0.11370401829481125, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:48.124975Z", "loop": 4482, "env_steps": 2754355199, "loss": 0.02199947088956833, "avg_return": 0.859315812587738, "regret": 0.004354051314294338, "entropy": 0.11909792572259903, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:48.978340Z", "loop": 4483, "env_steps": 2754969599, "loss": 0.01990174502134323, "avg_return": 0.8588707447052002, "regret": 0.004354051314294338, "entropy": 0.11271770298480988, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:49.832011Z", "loop": 4484, "env_steps": 2755583999, "loss": 0.022501805797219276, "avg_return": 0.8591607809066772, "regret": 0.004354051314294338, "entropy": 0.12199036031961441, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:50.685699Z", "loop": 4485, "env_steps": 2756198399, "loss": 0.021984469145536423, "avg_return": 0.8601700067520142, "regret": 0.004354051314294338, "entropy": 0.11826080083847046, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:51.539788Z", "loop": 4486, "env_steps": 2756812799, "loss": 0.021704185754060745, "avg_return": 0.860182523727417, "regret": 0.004354051314294338, "entropy": 0.12138324230909348, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:52.392692Z", "loop": 4487, "env_steps": 2757427199, "loss": 0.02220187894999981, "avg_return": 0.8577019572257996, "regret": 0.004354051314294338, "entropy": 0.12126904726028442, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:53.246501Z", "loop": 4488, "env_steps": 2758041599, "loss": 0.021157220005989075, "avg_return": 0.8583808541297913, "regret": 0.004354051314294338, "entropy": 0.12055843323469162, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:54.100194Z", "loop": 4489, "env_steps": 2758655999, "loss": 0.02141333743929863, "avg_return": 0.8595532178878784, "regret": 0.004354051314294338, "entropy": 0.11908160895109177, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:54.994547Z", "loop": 4490, "env_steps": 2759270399, "loss": 0.02096402458846569, "avg_return": 0.8600486516952515, "regret": 0.003600663272663951, "entropy": 0.11628700792789459, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:55.848840Z", "loop": 4491, "env_steps": 2759884799, "loss": 0.020073581486940384, "avg_return": 0.8599405884742737, "regret": 0.003600663272663951, "entropy": 0.11697221547365189, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:56.702344Z", "loop": 4492, "env_steps": 2760499199, "loss": 0.020048033446073532, "avg_return": 0.8601334095001221, "regret": 0.003600663272663951, "entropy": 0.11560742557048798, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:57.556276Z", "loop": 4493, "env_steps": 2761113599, "loss": 0.0200429055839777, "avg_return": 0.8619930148124695, "regret": 0.003600663272663951, "entropy": 0.11624754220247269, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:58.410513Z", "loop": 4494, "env_steps": 2761727999, "loss": 0.02088497020304203, "avg_return": 0.8603411912918091, "regret": 0.003600663272663951, "entropy": 0.118065744638443, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:27:59.264749Z", "loop": 4495, "env_steps": 2762342399, "loss": 0.020976228639483452, "avg_return": 0.8601353168487549, "regret": 0.003600663272663951, "entropy": 0.11677772551774979, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:00.117787Z", "loop": 4496, "env_steps": 2762956799, "loss": 0.022630929946899414, "avg_return": 0.860121488571167, "regret": 0.003600663272663951, "entropy": 0.12050499022006989, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:00.970877Z", "loop": 4497, "env_steps": 2763571199, "loss": 0.020772946998476982, "avg_return": 0.8599752187728882, "regret": 0.003600663272663951, "entropy": 0.11469481140375137, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:01.824560Z", "loop": 4498, "env_steps": 2764185599, "loss": 0.02036467008292675, "avg_return": 0.8599027991294861, "regret": 0.003600663272663951, "entropy": 0.11544468253850937, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:02.677973Z", "loop": 4499, "env_steps": 2764799999, "loss": 0.01789592020213604, "avg_return": 0.8615989089012146, "regret": 0.003600663272663951, "entropy": 0.10493877530097961, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:03.571086Z", "loop": 4500, "env_steps": 2765414399, "loss": 0.019339127466082573, "avg_return": 0.860557496547699, "regret": 0.002799247857183218, "entropy": 0.10487198084592819, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:04.424095Z", "loop": 4501, "env_steps": 2766028799, "loss": 0.019409647211432457, "avg_return": 0.8596177101135254, "regret": 0.002799247857183218, "entropy": 0.10717804729938507, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:05.278047Z", "loop": 4502, "env_steps": 2766643199, "loss": 0.017547739669680595, "avg_return": 0.8609899878501892, "regret": 0.002799247857183218, "entropy": 0.09932653605937958, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:06.133289Z", "loop": 4503, "env_steps": 2767257599, "loss": 0.019081376492977142, "avg_return": 0.8598948121070862, "regret": 0.002799247857183218, "entropy": 0.10803861916065216, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:06.988202Z", "loop": 4504, "env_steps": 2767871999, "loss": 0.01755375787615776, "avg_return": 0.861123263835907, "regret": 0.002799247857183218, "entropy": 0.10065897554159164, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:07.842140Z", "loop": 4505, "env_steps": 2768486399, "loss": 0.019168315455317497, "avg_return": 0.8604292869567871, "regret": 0.002799247857183218, "entropy": 0.10345430672168732, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:08.697103Z", "loop": 4506, "env_steps": 2769100799, "loss": 0.018879519775509834, "avg_return": 0.8612156510353088, "regret": 0.002799247857183218, "entropy": 0.1055704653263092, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:09.552174Z", "loop": 4507, "env_steps": 2769715199, "loss": 0.020102979615330696, "avg_return": 0.8597409129142761, "regret": 0.002799247857183218, "entropy": 0.10939773172140121, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:10.407127Z", "loop": 4508, "env_steps": 2770329599, "loss": 0.018037332221865654, "avg_return": 0.8604568839073181, "regret": 0.002799247857183218, "entropy": 0.10370007157325745, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:11.262557Z", "loop": 4509, "env_steps": 2770943999, "loss": 0.017797905951738358, "avg_return": 0.8603163957595825, "regret": 0.002799247857183218, "entropy": 0.10220011323690414, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:12.160539Z", "loop": 4510, "env_steps": 2771558399, "loss": 0.018280087038874626, "avg_return": 0.859839677810669, "regret": 0.003761074272915721, "entropy": 0.10466611385345459, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:13.013141Z", "loop": 4511, "env_steps": 2772172799, "loss": 0.01809031516313553, "avg_return": 0.861690878868103, "regret": 0.003761074272915721, "entropy": 0.10106359422206879, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:13.867380Z", "loop": 4512, "env_steps": 2772787199, "loss": 0.018287543207406998, "avg_return": 0.8615972995758057, "regret": 0.003761074272915721, "entropy": 0.0974474772810936, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:14.722448Z", "loop": 4513, "env_steps": 2773401599, "loss": 0.018219616264104843, "avg_return": 0.8612575531005859, "regret": 0.003761074272915721, "entropy": 0.10232274234294891, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:15.575894Z", "loop": 4514, "env_steps": 2774015999, "loss": 0.01811446063220501, "avg_return": 0.8628808856010437, "regret": 0.003761074272915721, "entropy": 0.10123272985219955, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:16.429117Z", "loop": 4515, "env_steps": 2774630399, "loss": 0.01932525634765625, "avg_return": 0.8617229461669922, "regret": 0.003761074272915721, "entropy": 0.10869631171226501, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:17.283082Z", "loop": 4516, "env_steps": 2775244799, "loss": 0.019757866859436035, "avg_return": 0.8596510887145996, "regret": 0.003761074272915721, "entropy": 0.1067647635936737, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:18.137157Z", "loop": 4517, "env_steps": 2775859199, "loss": 0.017533820122480392, "avg_return": 0.8594656586647034, "regret": 0.003761074272915721, "entropy": 0.10254359990358353, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:18.990836Z", "loop": 4518, "env_steps": 2776473599, "loss": 0.019292596727609634, "avg_return": 0.8606205582618713, "regret": 0.003761074272915721, "entropy": 0.11043985933065414, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:19.843397Z", "loop": 4519, "env_steps": 2777087999, "loss": 0.019328376278281212, "avg_return": 0.8609702587127686, "regret": 0.003761074272915721, "entropy": 0.10550513118505478, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:20.737096Z", "loop": 4520, "env_steps": 2777702399, "loss": 0.01858827844262123, "avg_return": 0.8610605001449585, "regret": 0.003057696158066392, "entropy": 0.1079583540558815, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:21.591847Z", "loop": 4521, "env_steps": 2778316799, "loss": 0.018177326768636703, "avg_return": 0.8593697547912598, "regret": 0.003057696158066392, "entropy": 0.1014123260974884, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:22.446063Z", "loop": 4522, "env_steps": 2778931199, "loss": 0.018735546618700027, "avg_return": 0.8588246703147888, "regret": 0.003057696158066392, "entropy": 0.10765793174505234, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:23.300492Z", "loop": 4523, "env_steps": 2779545599, "loss": 0.02001686953008175, "avg_return": 0.8582265377044678, "regret": 0.003057696158066392, "entropy": 0.10916109383106232, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:24.153166Z", "loop": 4524, "env_steps": 2780159999, "loss": 0.02001797780394554, "avg_return": 0.8565741181373596, "regret": 0.003057696158066392, "entropy": 0.10544008016586304, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:25.007120Z", "loop": 4525, "env_steps": 2780774399, "loss": 0.020101888105273247, "avg_return": 0.8539625406265259, "regret": 0.003057696158066392, "entropy": 0.10618220269680023, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:25.861763Z", "loop": 4526, "env_steps": 2781388799, "loss": 0.019736777991056442, "avg_return": 0.8539830446243286, "regret": 0.003057696158066392, "entropy": 0.10660936683416367, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:26.716356Z", "loop": 4527, "env_steps": 2782003199, "loss": 0.018974091857671738, "avg_return": 0.8574581146240234, "regret": 0.003057696158066392, "entropy": 0.1015106588602066, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:27.569275Z", "loop": 4528, "env_steps": 2782617599, "loss": 0.019443877041339874, "avg_return": 0.8588231801986694, "regret": 0.003057696158066392, "entropy": 0.10346508026123047, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:28.422787Z", "loop": 4529, "env_steps": 2783231999, "loss": 0.019926829263567924, "avg_return": 0.861740231513977, "regret": 0.003057696158066392, "entropy": 0.10417092591524124, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:29.317744Z", "loop": 4530, "env_steps": 2783846399, "loss": 0.0177451204508543, "avg_return": 0.8612885475158691, "regret": 0.0029870308935642242, "entropy": 0.09745218604803085, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:30.173201Z", "loop": 4531, "env_steps": 2784460799, "loss": 0.01717294566333294, "avg_return": 0.8600360155105591, "regret": 0.0029870308935642242, "entropy": 0.09751533716917038, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:31.026951Z", "loop": 4532, "env_steps": 2785075199, "loss": 0.01829858496785164, "avg_return": 0.8590830564498901, "regret": 0.0029870308935642242, "entropy": 0.10590821504592896, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:31.881129Z", "loop": 4533, "env_steps": 2785689599, "loss": 0.020306702703237534, "avg_return": 0.8576267957687378, "regret": 0.0029870308935642242, "entropy": 0.11128700524568558, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:32.735676Z", "loop": 4534, "env_steps": 2786303999, "loss": 0.01956188678741455, "avg_return": 0.8566257953643799, "regret": 0.0029870308935642242, "entropy": 0.11321316659450531, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:33.590197Z", "loop": 4535, "env_steps": 2786918399, "loss": 0.020885499194264412, "avg_return": 0.8584206104278564, "regret": 0.0029870308935642242, "entropy": 0.1117020845413208, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:34.443483Z", "loop": 4536, "env_steps": 2787532799, "loss": 0.019134800881147385, "avg_return": 0.8569696545600891, "regret": 0.0029870308935642242, "entropy": 0.10440655052661896, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:35.297889Z", "loop": 4537, "env_steps": 2788147199, "loss": 0.01983034238219261, "avg_return": 0.8574785590171814, "regret": 0.0029870308935642242, "entropy": 0.11245591938495636, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:36.151875Z", "loop": 4538, "env_steps": 2788761599, "loss": 0.021013198420405388, "avg_return": 0.858537495136261, "regret": 0.0029870308935642242, "entropy": 0.11028611660003662, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:37.007370Z", "loop": 4539, "env_steps": 2789375999, "loss": 0.01909947209060192, "avg_return": 0.8586328625679016, "regret": 0.0029870308935642242, "entropy": 0.10688074678182602, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:37.903658Z", "loop": 4540, "env_steps": 2789990399, "loss": 0.018356475979089737, "avg_return": 0.8597980737686157, "regret": 0.003951421007514, "entropy": 0.10549432784318924, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:38.758580Z", "loop": 4541, "env_steps": 2790604799, "loss": 0.019311336800456047, "avg_return": 0.8584591746330261, "regret": 0.003951421007514, "entropy": 0.1108444482088089, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:39.613461Z", "loop": 4542, "env_steps": 2791219199, "loss": 0.01900489814579487, "avg_return": 0.8593860268592834, "regret": 0.003951421007514, "entropy": 0.10736487805843353, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:40.466560Z", "loop": 4543, "env_steps": 2791833599, "loss": 0.020377187058329582, "avg_return": 0.8605963587760925, "regret": 0.003951421007514, "entropy": 0.11090271919965744, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:41.321218Z", "loop": 4544, "env_steps": 2792447999, "loss": 0.02005879394710064, "avg_return": 0.859315812587738, "regret": 0.003951421007514, "entropy": 0.11218826472759247, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:42.175525Z", "loop": 4545, "env_steps": 2793062399, "loss": 0.020800119265913963, "avg_return": 0.8579770922660828, "regret": 0.003951421007514, "entropy": 0.11371469497680664, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:43.030066Z", "loop": 4546, "env_steps": 2793676799, "loss": 0.020874543115496635, "avg_return": 0.8578538298606873, "regret": 0.003951421007514, "entropy": 0.1193641871213913, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:43.884656Z", "loop": 4547, "env_steps": 2794291199, "loss": 0.021120287477970123, "avg_return": 0.8578692674636841, "regret": 0.003951421007514, "entropy": 0.11675504595041275, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:44.739742Z", "loop": 4548, "env_steps": 2794905599, "loss": 0.02132466249167919, "avg_return": 0.8581434488296509, "regret": 0.003951421007514, "entropy": 0.11998360604047775, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:45.594816Z", "loop": 4549, "env_steps": 2795519999, "loss": 0.02143963985145092, "avg_return": 0.8582826852798462, "regret": 0.003951421007514, "entropy": 0.11950256675481796, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:46.492719Z", "loop": 4550, "env_steps": 2796134399, "loss": 0.020011989399790764, "avg_return": 0.8586334586143494, "regret": 0.004546512383967638, "entropy": 0.11099596321582794, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:47.346375Z", "loop": 4551, "env_steps": 2796748799, "loss": 0.01911945454776287, "avg_return": 0.8583221435546875, "regret": 0.004546512383967638, "entropy": 0.1071263998746872, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:48.199477Z", "loop": 4552, "env_steps": 2797363199, "loss": 0.0198268610984087, "avg_return": 0.8591026067733765, "regret": 0.004546512383967638, "entropy": 0.10809117555618286, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:49.054759Z", "loop": 4553, "env_steps": 2797977599, "loss": 0.02008097805082798, "avg_return": 0.8592551946640015, "regret": 0.004546512383967638, "entropy": 0.11443375796079636, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:49.909251Z", "loop": 4554, "env_steps": 2798591999, "loss": 0.01957971416413784, "avg_return": 0.8595314621925354, "regret": 0.004546512383967638, "entropy": 0.11271515488624573, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:50.762890Z", "loop": 4555, "env_steps": 2799206399, "loss": 0.018767019733786583, "avg_return": 0.8600800037384033, "regret": 0.004546512383967638, "entropy": 0.10786211490631104, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:51.616540Z", "loop": 4556, "env_steps": 2799820799, "loss": 0.018894260749220848, "avg_return": 0.8622658252716064, "regret": 0.004546512383967638, "entropy": 0.10948871076107025, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:52.470650Z", "loop": 4557, "env_steps": 2800435199, "loss": 0.018187349662184715, "avg_return": 0.8612304925918579, "regret": 0.004546512383967638, "entropy": 0.10833647102117538, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:53.324341Z", "loop": 4558, "env_steps": 2801049599, "loss": 0.019731199368834496, "avg_return": 0.8598408102989197, "regret": 0.004546512383967638, "entropy": 0.11086281388998032, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:54.178646Z", "loop": 4559, "env_steps": 2801663999, "loss": 0.02076660469174385, "avg_return": 0.8609303832054138, "regret": 0.004546512383967638, "entropy": 0.11741480976343155, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:55.075807Z", "loop": 4560, "env_steps": 2802278399, "loss": 0.02156030386686325, "avg_return": 0.8597310781478882, "regret": 0.002807616489008069, "entropy": 0.11861851066350937, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:55.929755Z", "loop": 4561, "env_steps": 2802892799, "loss": 0.02350335381925106, "avg_return": 0.8605710864067078, "regret": 0.002807616489008069, "entropy": 0.12443551421165466, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:56.783171Z", "loop": 4562, "env_steps": 2803507199, "loss": 0.02121639810502529, "avg_return": 0.8600319623947144, "regret": 0.002807616489008069, "entropy": 0.1206711083650589, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:57.636720Z", "loop": 4563, "env_steps": 2804121599, "loss": 0.02186819724738598, "avg_return": 0.8606355786323547, "regret": 0.002807616489008069, "entropy": 0.12388743460178375, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:58.490994Z", "loop": 4564, "env_steps": 2804735999, "loss": 0.02289963699877262, "avg_return": 0.8605667352676392, "regret": 0.002807616489008069, "entropy": 0.12433568388223648, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:28:59.345440Z", "loop": 4565, "env_steps": 2805350399, "loss": 0.02250988595187664, "avg_return": 0.8607950806617737, "regret": 0.002807616489008069, "entropy": 0.1268986016511917, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:00.199651Z", "loop": 4566, "env_steps": 2805964799, "loss": 0.023719344288110733, "avg_return": 0.8596905469894409, "regret": 0.002807616489008069, "entropy": 0.13378269970417023, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:01.055019Z", "loop": 4567, "env_steps": 2806579199, "loss": 0.023184334859251976, "avg_return": 0.8602079749107361, "regret": 0.002807616489008069, "entropy": 0.13155777752399445, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:01.910645Z", "loop": 4568, "env_steps": 2807193599, "loss": 0.02090621553361416, "avg_return": 0.8596270084381104, "regret": 0.002807616489008069, "entropy": 0.12278522551059723, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:02.764839Z", "loop": 4569, "env_steps": 2807807999, "loss": 0.021651118993759155, "avg_return": 0.8602850437164307, "regret": 0.002807616489008069, "entropy": 0.1176682785153389, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:03.660075Z", "loop": 4570, "env_steps": 2808422399, "loss": 0.02051045373082161, "avg_return": 0.859936535358429, "regret": 0.003368605626747012, "entropy": 0.12205270677804947, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:04.513982Z", "loop": 4571, "env_steps": 2809036799, "loss": 0.02087516151368618, "avg_return": 0.8588001728057861, "regret": 0.003368605626747012, "entropy": 0.11763817816972733, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:05.369011Z", "loop": 4572, "env_steps": 2809651199, "loss": 0.022378088906407356, "avg_return": 0.8586158156394958, "regret": 0.003368605626747012, "entropy": 0.1193404272198677, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:06.223748Z", "loop": 4573, "env_steps": 2810265599, "loss": 0.022828510031104088, "avg_return": 0.8587462306022644, "regret": 0.003368605626747012, "entropy": 0.12238696217536926, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:07.077375Z", "loop": 4574, "env_steps": 2810879999, "loss": 0.021263549104332924, "avg_return": 0.8548282980918884, "regret": 0.003368605626747012, "entropy": 0.11929218471050262, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:07.931410Z", "loop": 4575, "env_steps": 2811494399, "loss": 0.02209305390715599, "avg_return": 0.8581574559211731, "regret": 0.003368605626747012, "entropy": 0.12539201974868774, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:08.785331Z", "loop": 4576, "env_steps": 2812108799, "loss": 0.02056688256561756, "avg_return": 0.857342541217804, "regret": 0.003368605626747012, "entropy": 0.11802096664905548, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:09.639486Z", "loop": 4577, "env_steps": 2812723199, "loss": 0.020081045106053352, "avg_return": 0.8581358194351196, "regret": 0.003368605626747012, "entropy": 0.1084020659327507, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:10.494040Z", "loop": 4578, "env_steps": 2813337599, "loss": 0.021546512842178345, "avg_return": 0.8575626611709595, "regret": 0.003368605626747012, "entropy": 0.12109971791505814, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:11.347170Z", "loop": 4579, "env_steps": 2813951999, "loss": 0.021270420402288437, "avg_return": 0.8570836782455444, "regret": 0.003368605626747012, "entropy": 0.11582256108522415, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:12.241474Z", "loop": 4580, "env_steps": 2814566399, "loss": 0.021712230518460274, "avg_return": 0.8584427833557129, "regret": 0.0056944130919873714, "entropy": 0.11982923001050949, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:13.095289Z", "loop": 4581, "env_steps": 2815180799, "loss": 0.019818393513560295, "avg_return": 0.8600106239318848, "regret": 0.0056944130919873714, "entropy": 0.11357574909925461, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:13.949850Z", "loop": 4582, "env_steps": 2815795199, "loss": 0.02002074383199215, "avg_return": 0.859873354434967, "regret": 0.0056944130919873714, "entropy": 0.11116699874401093, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:14.803399Z", "loop": 4583, "env_steps": 2816409599, "loss": 0.020340068265795708, "avg_return": 0.8613156080245972, "regret": 0.0056944130919873714, "entropy": 0.11114519834518433, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:15.657394Z", "loop": 4584, "env_steps": 2817023999, "loss": 0.01782977394759655, "avg_return": 0.8603862524032593, "regret": 0.0056944130919873714, "entropy": 0.10346508771181107, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:16.512420Z", "loop": 4585, "env_steps": 2817638399, "loss": 0.018520532175898552, "avg_return": 0.8604118227958679, "regret": 0.0056944130919873714, "entropy": 0.10441681742668152, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:17.367712Z", "loop": 4586, "env_steps": 2818252799, "loss": 0.01953711174428463, "avg_return": 0.8616496920585632, "regret": 0.0056944130919873714, "entropy": 0.1060977354645729, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:18.221330Z", "loop": 4587, "env_steps": 2818867199, "loss": 0.01805611327290535, "avg_return": 0.8598120212554932, "regret": 0.0056944130919873714, "entropy": 0.10068803280591965, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:19.078560Z", "loop": 4588, "env_steps": 2819481599, "loss": 0.020100003108382225, "avg_return": 0.8610503077507019, "regret": 0.0056944130919873714, "entropy": 0.10866059362888336, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:19.934230Z", "loop": 4589, "env_steps": 2820095999, "loss": 0.01760895550251007, "avg_return": 0.8587858080863953, "regret": 0.0056944130919873714, "entropy": 0.10245255380868912, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:20.830230Z", "loop": 4590, "env_steps": 2820710399, "loss": 0.020338602364063263, "avg_return": 0.8605402708053589, "regret": 0.0038431789726018906, "entropy": 0.10999374836683273, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:21.684645Z", "loop": 4591, "env_steps": 2821324799, "loss": 0.01901143789291382, "avg_return": 0.8591345548629761, "regret": 0.0038431789726018906, "entropy": 0.1066322848200798, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:22.539513Z", "loop": 4592, "env_steps": 2821939199, "loss": 0.01928551495075226, "avg_return": 0.8600109815597534, "regret": 0.0038431789726018906, "entropy": 0.1112251952290535, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:23.394344Z", "loop": 4593, "env_steps": 2822553599, "loss": 0.02019507996737957, "avg_return": 0.861751914024353, "regret": 0.0038431789726018906, "entropy": 0.1094362884759903, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:24.248471Z", "loop": 4594, "env_steps": 2823167999, "loss": 0.020765164867043495, "avg_return": 0.8617565035820007, "regret": 0.0038431789726018906, "entropy": 0.11239500343799591, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:25.102653Z", "loop": 4595, "env_steps": 2823782399, "loss": 0.01986304670572281, "avg_return": 0.8611200451850891, "regret": 0.0038431789726018906, "entropy": 0.11007901281118393, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:25.956292Z", "loop": 4596, "env_steps": 2824396799, "loss": 0.017867568880319595, "avg_return": 0.8610736131668091, "regret": 0.0038431789726018906, "entropy": 0.10418922454118729, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:26.810020Z", "loop": 4597, "env_steps": 2825011199, "loss": 0.01970600336790085, "avg_return": 0.8617855310440063, "regret": 0.0038431789726018906, "entropy": 0.11253523081541061, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:27.665207Z", "loop": 4598, "env_steps": 2825625599, "loss": 0.020492054522037506, "avg_return": 0.8614408373832703, "regret": 0.0038431789726018906, "entropy": 0.11315669864416122, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:28.519476Z", "loop": 4599, "env_steps": 2826239999, "loss": 0.018949514254927635, "avg_return": 0.8607960343360901, "regret": 0.0038431789726018906, "entropy": 0.11189927160739899, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:29.414891Z", "loop": 4600, "env_steps": 2826854399, "loss": 0.02117936871945858, "avg_return": 0.8592973947525024, "regret": 0.004322801250964403, "entropy": 0.11774414777755737, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:30.268103Z", "loop": 4601, "env_steps": 2827468799, "loss": 0.021963944658637047, "avg_return": 0.8575555682182312, "regret": 0.004322801250964403, "entropy": 0.12149886041879654, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:31.121920Z", "loop": 4602, "env_steps": 2828083199, "loss": 0.02101193740963936, "avg_return": 0.8579177260398865, "regret": 0.004322801250964403, "entropy": 0.1177750751376152, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:31.976644Z", "loop": 4603, "env_steps": 2828697599, "loss": 0.018824711441993713, "avg_return": 0.8590037226676941, "regret": 0.004322801250964403, "entropy": 0.11189045011997223, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:32.831046Z", "loop": 4604, "env_steps": 2829311999, "loss": 0.022031931206583977, "avg_return": 0.8581916689872742, "regret": 0.004322801250964403, "entropy": 0.11913787573575974, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:33.684664Z", "loop": 4605, "env_steps": 2829926399, "loss": 0.018789710476994514, "avg_return": 0.8590523600578308, "regret": 0.004322801250964403, "entropy": 0.10868756473064423, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:34.539568Z", "loop": 4606, "env_steps": 2830540799, "loss": 0.01894323155283928, "avg_return": 0.8603053092956543, "regret": 0.004322801250964403, "entropy": 0.110903300344944, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:35.393404Z", "loop": 4607, "env_steps": 2831155199, "loss": 0.021288646385073662, "avg_return": 0.8590086102485657, "regret": 0.004322801250964403, "entropy": 0.11520817130804062, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:36.248281Z", "loop": 4608, "env_steps": 2831769599, "loss": 0.02029024064540863, "avg_return": 0.859079122543335, "regret": 0.004322801250964403, "entropy": 0.11112946271896362, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:37.103242Z", "loop": 4609, "env_steps": 2832383999, "loss": 0.018407737836241722, "avg_return": 0.8603416085243225, "regret": 0.004322801250964403, "entropy": 0.1086774542927742, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:37.997617Z", "loop": 4610, "env_steps": 2832998399, "loss": 0.018780214712023735, "avg_return": 0.8600438833236694, "regret": 0.003753281431272626, "entropy": 0.10571988672018051, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:38.850510Z", "loop": 4611, "env_steps": 2833612799, "loss": 0.019235266372561455, "avg_return": 0.8600011467933655, "regret": 0.003753281431272626, "entropy": 0.10515620559453964, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:39.706500Z", "loop": 4612, "env_steps": 2834227199, "loss": 0.018194546923041344, "avg_return": 0.861416220664978, "regret": 0.003753281431272626, "entropy": 0.10909995436668396, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:40.561228Z", "loop": 4613, "env_steps": 2834841599, "loss": 0.019572464749217033, "avg_return": 0.8608811497688293, "regret": 0.003753281431272626, "entropy": 0.10667899996042252, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:41.415825Z", "loop": 4614, "env_steps": 2835455999, "loss": 0.01728413812816143, "avg_return": 0.861157238483429, "regret": 0.003753281431272626, "entropy": 0.1025700643658638, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:42.270890Z", "loop": 4615, "env_steps": 2836070399, "loss": 0.019535085186362267, "avg_return": 0.8610315322875977, "regret": 0.003753281431272626, "entropy": 0.10263540595769882, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:43.126879Z", "loop": 4616, "env_steps": 2836684799, "loss": 0.01817977987229824, "avg_return": 0.8612691164016724, "regret": 0.003753281431272626, "entropy": 0.1052691861987114, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:43.982244Z", "loop": 4617, "env_steps": 2837299199, "loss": 0.01804206147789955, "avg_return": 0.8588606715202332, "regret": 0.003753281431272626, "entropy": 0.10189730674028397, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:44.836799Z", "loop": 4618, "env_steps": 2837913599, "loss": 0.01956918090581894, "avg_return": 0.8590080738067627, "regret": 0.003753281431272626, "entropy": 0.10862036794424057, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:45.690267Z", "loop": 4619, "env_steps": 2838527999, "loss": 0.0192630123347044, "avg_return": 0.8599936962127686, "regret": 0.003753281431272626, "entropy": 0.11193643510341644, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:46.582858Z", "loop": 4620, "env_steps": 2839142399, "loss": 0.018817493692040443, "avg_return": 0.8593964576721191, "regret": 0.004353711381554604, "entropy": 0.10245253890752792, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:47.435779Z", "loop": 4621, "env_steps": 2839756799, "loss": 0.018564460799098015, "avg_return": 0.8607357144355774, "regret": 0.004353711381554604, "entropy": 0.09965988993644714, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:48.290219Z", "loop": 4622, "env_steps": 2840371199, "loss": 0.01770193688571453, "avg_return": 0.8605217933654785, "regret": 0.004353711381554604, "entropy": 0.10319468379020691, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:49.144043Z", "loop": 4623, "env_steps": 2840985599, "loss": 0.01798984222114086, "avg_return": 0.8598789572715759, "regret": 0.004353711381554604, "entropy": 0.10066001117229462, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:49.998425Z", "loop": 4624, "env_steps": 2841599999, "loss": 0.018115194514393806, "avg_return": 0.859783947467804, "regret": 0.004353711381554604, "entropy": 0.10207844525575638, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:50.852689Z", "loop": 4625, "env_steps": 2842214399, "loss": 0.01898977719247341, "avg_return": 0.8600835204124451, "regret": 0.004353711381554604, "entropy": 0.10143407434225082, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:51.707256Z", "loop": 4626, "env_steps": 2842828799, "loss": 0.019768748432397842, "avg_return": 0.8605139255523682, "regret": 0.004353711381554604, "entropy": 0.10570614784955978, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:52.561939Z", "loop": 4627, "env_steps": 2843443199, "loss": 0.019159892573952675, "avg_return": 0.8614579439163208, "regret": 0.004353711381554604, "entropy": 0.10394567251205444, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:53.416239Z", "loop": 4628, "env_steps": 2844057599, "loss": 0.02043995074927807, "avg_return": 0.8600255250930786, "regret": 0.004353711381554604, "entropy": 0.10584107786417007, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:54.270882Z", "loop": 4629, "env_steps": 2844671999, "loss": 0.02066684328019619, "avg_return": 0.8571873307228088, "regret": 0.004353711381554604, "entropy": 0.11101079732179642, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:55.164858Z", "loop": 4630, "env_steps": 2845286399, "loss": 0.019785230979323387, "avg_return": 0.8572763204574585, "regret": 0.006353516131639481, "entropy": 0.11150971055030823, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:56.018306Z", "loop": 4631, "env_steps": 2845900799, "loss": 0.021840328350663185, "avg_return": 0.8573600649833679, "regret": 0.006353516131639481, "entropy": 0.11744096130132675, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:56.871588Z", "loop": 4632, "env_steps": 2846515199, "loss": 0.019742166623473167, "avg_return": 0.8582003712654114, "regret": 0.006353516131639481, "entropy": 0.10815491527318954, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:57.725477Z", "loop": 4633, "env_steps": 2847129599, "loss": 0.019248900935053825, "avg_return": 0.859207808971405, "regret": 0.006353516131639481, "entropy": 0.107630655169487, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:58.578248Z", "loop": 4634, "env_steps": 2847743999, "loss": 0.019833913072943687, "avg_return": 0.8611024022102356, "regret": 0.006353516131639481, "entropy": 0.10995405912399292, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:29:59.431858Z", "loop": 4635, "env_steps": 2848358399, "loss": 0.01776178553700447, "avg_return": 0.8608834147453308, "regret": 0.006353516131639481, "entropy": 0.10025012493133545, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:00.285771Z", "loop": 4636, "env_steps": 2848972799, "loss": 0.01805824786424637, "avg_return": 0.8595130443572998, "regret": 0.006353516131639481, "entropy": 0.09797672927379608, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:01.138652Z", "loop": 4637, "env_steps": 2849587199, "loss": 0.018108801916241646, "avg_return": 0.860505998134613, "regret": 0.006353516131639481, "entropy": 0.10630293190479279, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:01.992835Z", "loop": 4638, "env_steps": 2850201599, "loss": 0.020706145092844963, "avg_return": 0.8613743185997009, "regret": 0.006353516131639481, "entropy": 0.11074365675449371, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:02.848727Z", "loop": 4639, "env_steps": 2850815999, "loss": 0.02016550675034523, "avg_return": 0.8604761958122253, "regret": 0.006353516131639481, "entropy": 0.11249466240406036, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:03.743684Z", "loop": 4640, "env_steps": 2851430399, "loss": 0.021908996626734734, "avg_return": 0.8573979735374451, "regret": 0.004345542751252651, "entropy": 0.12100254744291306, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:04.596939Z", "loop": 4641, "env_steps": 2852044799, "loss": 0.020954934880137444, "avg_return": 0.8590707778930664, "regret": 0.004345542751252651, "entropy": 0.11653193086385727, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:05.450247Z", "loop": 4642, "env_steps": 2852659199, "loss": 0.02367108128964901, "avg_return": 0.8566133975982666, "regret": 0.004345542751252651, "entropy": 0.12977945804595947, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:06.304978Z", "loop": 4643, "env_steps": 2853273599, "loss": 0.02599913254380226, "avg_return": 0.8543824553489685, "regret": 0.004345542751252651, "entropy": 0.13775861263275146, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:07.160032Z", "loop": 4644, "env_steps": 2853887999, "loss": 0.023915886878967285, "avg_return": 0.8547483682632446, "regret": 0.004345542751252651, "entropy": 0.1317390501499176, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:08.015881Z", "loop": 4645, "env_steps": 2854502399, "loss": 0.024629956111311913, "avg_return": 0.8568581342697144, "regret": 0.004345542751252651, "entropy": 0.1312614530324936, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:08.870933Z", "loop": 4646, "env_steps": 2855116799, "loss": 0.021980104967951775, "avg_return": 0.8585152626037598, "regret": 0.004345542751252651, "entropy": 0.12359974533319473, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:09.726136Z", "loop": 4647, "env_steps": 2855731199, "loss": 0.022522564977407455, "avg_return": 0.858161449432373, "regret": 0.004345542751252651, "entropy": 0.12621164321899414, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:10.580066Z", "loop": 4648, "env_steps": 2856345599, "loss": 0.02040575072169304, "avg_return": 0.860235333442688, "regret": 0.004345542751252651, "entropy": 0.11539711803197861, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:11.433829Z", "loop": 4649, "env_steps": 2856959999, "loss": 0.02049139514565468, "avg_return": 0.8601311445236206, "regret": 0.004345542751252651, "entropy": 0.11564701050519943, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:12.327772Z", "loop": 4650, "env_steps": 2857574399, "loss": 0.02029874175786972, "avg_return": 0.8592421412467957, "regret": 0.003623431548476219, "entropy": 0.11185061186552048, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:13.180253Z", "loop": 4651, "env_steps": 2858188799, "loss": 0.020789721980690956, "avg_return": 0.8586246967315674, "regret": 0.003623431548476219, "entropy": 0.11241161078214645, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:14.034382Z", "loop": 4652, "env_steps": 2858803199, "loss": 0.021432509645819664, "avg_return": 0.8552922606468201, "regret": 0.003623431548476219, "entropy": 0.1196693629026413, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:14.889697Z", "loop": 4653, "env_steps": 2859417599, "loss": 0.020546041429042816, "avg_return": 0.8534929752349854, "regret": 0.003623431548476219, "entropy": 0.10823321342468262, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:15.745515Z", "loop": 4654, "env_steps": 2860031999, "loss": 0.022125843912363052, "avg_return": 0.8539948463439941, "regret": 0.003623431548476219, "entropy": 0.1155635416507721, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:16.600273Z", "loop": 4655, "env_steps": 2860646399, "loss": 0.022051392123103142, "avg_return": 0.8584588766098022, "regret": 0.003623431548476219, "entropy": 0.11654046922922134, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:17.454610Z", "loop": 4656, "env_steps": 2861260799, "loss": 0.02038002200424671, "avg_return": 0.859065592288971, "regret": 0.003623431548476219, "entropy": 0.10991130769252777, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:18.310940Z", "loop": 4657, "env_steps": 2861875199, "loss": 0.02029527723789215, "avg_return": 0.8603643774986267, "regret": 0.003623431548476219, "entropy": 0.11241351813077927, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:19.166555Z", "loop": 4658, "env_steps": 2862489599, "loss": 0.020028002560138702, "avg_return": 0.860733687877655, "regret": 0.003623431548476219, "entropy": 0.10722806304693222, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:20.021932Z", "loop": 4659, "env_steps": 2863103999, "loss": 0.01900557614862919, "avg_return": 0.8616812229156494, "regret": 0.003623431548476219, "entropy": 0.10392847657203674, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:20.915598Z", "loop": 4660, "env_steps": 2863718399, "loss": 0.02019999362528324, "avg_return": 0.8611224293708801, "regret": 0.003138457890599966, "entropy": 0.11360228061676025, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:21.769456Z", "loop": 4661, "env_steps": 2864332799, "loss": 0.02080201916396618, "avg_return": 0.8587115406990051, "regret": 0.003138457890599966, "entropy": 0.11245419830083847, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:22.624378Z", "loop": 4662, "env_steps": 2864947199, "loss": 0.019590599462389946, "avg_return": 0.85898357629776, "regret": 0.003138457890599966, "entropy": 0.11325345933437347, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:23.478170Z", "loop": 4663, "env_steps": 2865561599, "loss": 0.021085234358906746, "avg_return": 0.8586609363555908, "regret": 0.003138457890599966, "entropy": 0.11858010292053223, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:24.331909Z", "loop": 4664, "env_steps": 2866175999, "loss": 0.022023025900125504, "avg_return": 0.8585032224655151, "regret": 0.003138457890599966, "entropy": 0.12204550951719284, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:25.185931Z", "loop": 4665, "env_steps": 2866790399, "loss": 0.022555004805326462, "avg_return": 0.858866810798645, "regret": 0.003138457890599966, "entropy": 0.11843334138393402, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:26.039665Z", "loop": 4666, "env_steps": 2867404799, "loss": 0.020976554602384567, "avg_return": 0.8591852188110352, "regret": 0.003138457890599966, "entropy": 0.11954265832901001, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:26.894142Z", "loop": 4667, "env_steps": 2868019199, "loss": 0.020754816010594368, "avg_return": 0.860325038433075, "regret": 0.003138457890599966, "entropy": 0.11575797945261002, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:27.747670Z", "loop": 4668, "env_steps": 2868633599, "loss": 0.019001422449946404, "avg_return": 0.8615087866783142, "regret": 0.003138457890599966, "entropy": 0.10906203836202621, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:28.601364Z", "loop": 4669, "env_steps": 2869247999, "loss": 0.017461959272623062, "avg_return": 0.8609968423843384, "regret": 0.003138457890599966, "entropy": 0.10389447957277298, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:29.496179Z", "loop": 4670, "env_steps": 2869862399, "loss": 0.019216129556298256, "avg_return": 0.8609182834625244, "regret": 0.002037063241004944, "entropy": 0.11022684723138809, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:30.351323Z", "loop": 4671, "env_steps": 2870476799, "loss": 0.019549615681171417, "avg_return": 0.8618633151054382, "regret": 0.002037063241004944, "entropy": 0.10936693847179413, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:31.206670Z", "loop": 4672, "env_steps": 2871091199, "loss": 0.020207971334457397, "avg_return": 0.8623605370521545, "regret": 0.002037063241004944, "entropy": 0.10978133231401443, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:32.061617Z", "loop": 4673, "env_steps": 2871705599, "loss": 0.018697237595915794, "avg_return": 0.8619264960289001, "regret": 0.002037063241004944, "entropy": 0.10746803879737854, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:32.915288Z", "loop": 4674, "env_steps": 2872319999, "loss": 0.018778828904032707, "avg_return": 0.8618937134742737, "regret": 0.002037063241004944, "entropy": 0.10494070500135422, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:33.769374Z", "loop": 4675, "env_steps": 2872934399, "loss": 0.020186830312013626, "avg_return": 0.8596134781837463, "regret": 0.002037063241004944, "entropy": 0.11050903797149658, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:34.623012Z", "loop": 4676, "env_steps": 2873548799, "loss": 0.019529487937688828, "avg_return": 0.8616479635238647, "regret": 0.002037063241004944, "entropy": 0.10746800899505615, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:35.476693Z", "loop": 4677, "env_steps": 2874163199, "loss": 0.019016552716493607, "avg_return": 0.8596811890602112, "regret": 0.002037063241004944, "entropy": 0.10856495797634125, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:36.329441Z", "loop": 4678, "env_steps": 2874777599, "loss": 0.02039608359336853, "avg_return": 0.8625751733779907, "regret": 0.002037063241004944, "entropy": 0.11727961152791977, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:37.182852Z", "loop": 4679, "env_steps": 2875391999, "loss": 0.020784374326467514, "avg_return": 0.8602877855300903, "regret": 0.002037063241004944, "entropy": 0.11610103398561478, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:38.077531Z", "loop": 4680, "env_steps": 2876006399, "loss": 0.02253890223801136, "avg_return": 0.8608304858207703, "regret": 0.00364122586324811, "entropy": 0.12346924841403961, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:38.931574Z", "loop": 4681, "env_steps": 2876620799, "loss": 0.022245321422815323, "avg_return": 0.8558787107467651, "regret": 0.00364122586324811, "entropy": 0.12908534705638885, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:39.786231Z", "loop": 4682, "env_steps": 2877235199, "loss": 0.024413006380200386, "avg_return": 0.8543860912322998, "regret": 0.00364122586324811, "entropy": 0.13803161680698395, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:40.641126Z", "loop": 4683, "env_steps": 2877849599, "loss": 0.02240033820271492, "avg_return": 0.8575653433799744, "regret": 0.00364122586324811, "entropy": 0.12850573658943176, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:41.496351Z", "loop": 4684, "env_steps": 2878463999, "loss": 0.022015690803527832, "avg_return": 0.8591505885124207, "regret": 0.00364122586324811, "entropy": 0.12387286126613617, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:42.351471Z", "loop": 4685, "env_steps": 2879078399, "loss": 0.023013262078166008, "avg_return": 0.8600714206695557, "regret": 0.00364122586324811, "entropy": 0.12678402662277222, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:43.206013Z", "loop": 4686, "env_steps": 2879692799, "loss": 0.022506942972540855, "avg_return": 0.8613958954811096, "regret": 0.00364122586324811, "entropy": 0.12463773787021637, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:44.058997Z", "loop": 4687, "env_steps": 2880307199, "loss": 0.02054642140865326, "avg_return": 0.8586936593055725, "regret": 0.00364122586324811, "entropy": 0.12221357971429825, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:44.911973Z", "loop": 4688, "env_steps": 2880921599, "loss": 0.02194902114570141, "avg_return": 0.8589619994163513, "regret": 0.00364122586324811, "entropy": 0.12214759737253189, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:45.766291Z", "loop": 4689, "env_steps": 2881535999, "loss": 0.0217824038118124, "avg_return": 0.8603338599205017, "regret": 0.00364122586324811, "entropy": 0.1175668016076088, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:46.660625Z", "loop": 4690, "env_steps": 2882150399, "loss": 0.02077506110072136, "avg_return": 0.8611392378807068, "regret": 0.003082453506067395, "entropy": 0.11452793329954147, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:47.514631Z", "loop": 4691, "env_steps": 2882764799, "loss": 0.01777893863618374, "avg_return": 0.8603253364562988, "regret": 0.003082453506067395, "entropy": 0.10734202712774277, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:48.369557Z", "loop": 4692, "env_steps": 2883379199, "loss": 0.020531965419650078, "avg_return": 0.8603631854057312, "regret": 0.003082453506067395, "entropy": 0.11623241752386093, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:49.225262Z", "loop": 4693, "env_steps": 2883993599, "loss": 0.020603995770215988, "avg_return": 0.861900269985199, "regret": 0.003082453506067395, "entropy": 0.11065395921468735, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:50.079714Z", "loop": 4694, "env_steps": 2884607999, "loss": 0.018545670434832573, "avg_return": 0.8608185052871704, "regret": 0.003082453506067395, "entropy": 0.10704947263002396, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:50.934179Z", "loop": 4695, "env_steps": 2885222399, "loss": 0.0209478922188282, "avg_return": 0.8605580925941467, "regret": 0.003082453506067395, "entropy": 0.11162975430488586, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:51.787755Z", "loop": 4696, "env_steps": 2885836799, "loss": 0.021591218188405037, "avg_return": 0.857418417930603, "regret": 0.003082453506067395, "entropy": 0.12153127044439316, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:52.641852Z", "loop": 4697, "env_steps": 2886451199, "loss": 0.02402626723051071, "avg_return": 0.8577748537063599, "regret": 0.003082453506067395, "entropy": 0.13289959728717804, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:53.496936Z", "loop": 4698, "env_steps": 2887065599, "loss": 0.019690727815032005, "avg_return": 0.8600640296936035, "regret": 0.003082453506067395, "entropy": 0.1171049028635025, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:54.352242Z", "loop": 4699, "env_steps": 2887679999, "loss": 0.01964523084461689, "avg_return": 0.861214816570282, "regret": 0.003082453506067395, "entropy": 0.11196545511484146, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:55.248357Z", "loop": 4700, "env_steps": 2888294399, "loss": 0.021051442250609398, "avg_return": 0.862296462059021, "regret": 0.0023935141507536173, "entropy": 0.1141391322016716, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:56.102587Z", "loop": 4701, "env_steps": 2888908799, "loss": 0.021246666088700294, "avg_return": 0.859329879283905, "regret": 0.0023935141507536173, "entropy": 0.11221428215503693, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:56.957378Z", "loop": 4702, "env_steps": 2889523199, "loss": 0.02291330136358738, "avg_return": 0.8583952188491821, "regret": 0.0023935141507536173, "entropy": 0.12237004190683365, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:57.812452Z", "loop": 4703, "env_steps": 2890137599, "loss": 0.02394172176718712, "avg_return": 0.8542237281799316, "regret": 0.0023935141507536173, "entropy": 0.12129482626914978, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:58.667040Z", "loop": 4704, "env_steps": 2890751999, "loss": 0.02358689159154892, "avg_return": 0.8533212542533875, "regret": 0.0023935141507536173, "entropy": 0.1269618421792984, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:30:59.521624Z", "loop": 4705, "env_steps": 2891366399, "loss": 0.023933308199048042, "avg_return": 0.8522921204566956, "regret": 0.0023935141507536173, "entropy": 0.1268373280763626, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:00.375655Z", "loop": 4706, "env_steps": 2891980799, "loss": 0.023961303755640984, "avg_return": 0.8583880662918091, "regret": 0.0023935141507536173, "entropy": 0.13130760192871094, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:01.229561Z", "loop": 4707, "env_steps": 2892595199, "loss": 0.022029129788279533, "avg_return": 0.8582831025123596, "regret": 0.0023935141507536173, "entropy": 0.12298314273357391, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:02.083198Z", "loop": 4708, "env_steps": 2893209599, "loss": 0.021507857367396355, "avg_return": 0.860377311706543, "regret": 0.0023935141507536173, "entropy": 0.12288575619459152, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:02.936876Z", "loop": 4709, "env_steps": 2893823999, "loss": 0.02134488895535469, "avg_return": 0.8606380224227905, "regret": 0.0023935141507536173, "entropy": 0.12154077738523483, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:03.832676Z", "loop": 4710, "env_steps": 2894438399, "loss": 0.024015938863158226, "avg_return": 0.8606252074241638, "regret": 0.004460064694285393, "entropy": 0.13544973731040955, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:04.686925Z", "loop": 4711, "env_steps": 2895052799, "loss": 0.023645058274269104, "avg_return": 0.85862135887146, "regret": 0.004460064694285393, "entropy": 0.1354099065065384, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:05.542300Z", "loop": 4712, "env_steps": 2895667199, "loss": 0.022796938195824623, "avg_return": 0.8586870431900024, "regret": 0.004460064694285393, "entropy": 0.13289128243923187, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:06.397155Z", "loop": 4713, "env_steps": 2896281599, "loss": 0.02454441413283348, "avg_return": 0.8586408495903015, "regret": 0.004460064694285393, "entropy": 0.13710784912109375, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:07.251995Z", "loop": 4714, "env_steps": 2896895999, "loss": 0.025246698409318924, "avg_return": 0.858497142791748, "regret": 0.004460064694285393, "entropy": 0.13542449474334717, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:08.106121Z", "loop": 4715, "env_steps": 2897510399, "loss": 0.02309505082666874, "avg_return": 0.8595478534698486, "regret": 0.004460064694285393, "entropy": 0.1307125687599182, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:08.960962Z", "loop": 4716, "env_steps": 2898124799, "loss": 0.022442586719989777, "avg_return": 0.8598844408988953, "regret": 0.004460064694285393, "entropy": 0.12875047326087952, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:09.816227Z", "loop": 4717, "env_steps": 2898739199, "loss": 0.021978145465254784, "avg_return": 0.8600612878799438, "regret": 0.004460064694285393, "entropy": 0.1277068704366684, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:10.671361Z", "loop": 4718, "env_steps": 2899353599, "loss": 0.02113932929933071, "avg_return": 0.8603551387786865, "regret": 0.004460064694285393, "entropy": 0.12535011768341064, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:11.525298Z", "loop": 4719, "env_steps": 2899967999, "loss": 0.021902596578001976, "avg_return": 0.8592816591262817, "regret": 0.004460064694285393, "entropy": 0.1282685399055481, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:12.420691Z", "loop": 4720, "env_steps": 2900582399, "loss": 0.021638475358486176, "avg_return": 0.8598474264144897, "regret": 0.00476592592895031, "entropy": 0.12460539489984512, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:13.275442Z", "loop": 4721, "env_steps": 2901196799, "loss": 0.02341475524008274, "avg_return": 0.8590903878211975, "regret": 0.00476592592895031, "entropy": 0.13113096356391907, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:14.130670Z", "loop": 4722, "env_steps": 2901811199, "loss": 0.022242125123739243, "avg_return": 0.8593562841415405, "regret": 0.00476592592895031, "entropy": 0.1278340071439743, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:14.984269Z", "loop": 4723, "env_steps": 2902425599, "loss": 0.020824095234274864, "avg_return": 0.8591640591621399, "regret": 0.00476592592895031, "entropy": 0.12247532606124878, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:15.838136Z", "loop": 4724, "env_steps": 2903039999, "loss": 0.02305355668067932, "avg_return": 0.8590720891952515, "regret": 0.00476592592895031, "entropy": 0.12991875410079956, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:16.692662Z", "loop": 4725, "env_steps": 2903654399, "loss": 0.02036682516336441, "avg_return": 0.8606480360031128, "regret": 0.00476592592895031, "entropy": 0.11889968812465668, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:17.547131Z", "loop": 4726, "env_steps": 2904268799, "loss": 0.02130800299346447, "avg_return": 0.8591246604919434, "regret": 0.00476592592895031, "entropy": 0.11692246049642563, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:18.401478Z", "loop": 4727, "env_steps": 2904883199, "loss": 0.020831463858485222, "avg_return": 0.8604148626327515, "regret": 0.00476592592895031, "entropy": 0.11565269529819489, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:19.254915Z", "loop": 4728, "env_steps": 2905497599, "loss": 0.019660739228129387, "avg_return": 0.8620805144309998, "regret": 0.00476592592895031, "entropy": 0.11473109573125839, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:20.108314Z", "loop": 4729, "env_steps": 2906111999, "loss": 0.019520962610840797, "avg_return": 0.8606367111206055, "regret": 0.00476592592895031, "entropy": 0.11053097993135452, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:21.004192Z", "loop": 4730, "env_steps": 2906726399, "loss": 0.01944468356668949, "avg_return": 0.8615663051605225, "regret": 0.0022211840841919184, "entropy": 0.11294039338827133, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:21.858249Z", "loop": 4731, "env_steps": 2907340799, "loss": 0.020198527723550797, "avg_return": 0.861365795135498, "regret": 0.0022211840841919184, "entropy": 0.11392652988433838, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:22.712276Z", "loop": 4732, "env_steps": 2907955199, "loss": 0.02141611836850643, "avg_return": 0.8601562976837158, "regret": 0.0022211840841919184, "entropy": 0.11574486643075943, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:23.566763Z", "loop": 4733, "env_steps": 2908569599, "loss": 0.019625216722488403, "avg_return": 0.8612403273582458, "regret": 0.0022211840841919184, "entropy": 0.11579889059066772, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:24.421541Z", "loop": 4734, "env_steps": 2909183999, "loss": 0.020396647974848747, "avg_return": 0.8608861565589905, "regret": 0.0022211840841919184, "entropy": 0.11148707568645477, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:25.275843Z", "loop": 4735, "env_steps": 2909798399, "loss": 0.02046985924243927, "avg_return": 0.8611255288124084, "regret": 0.0022211840841919184, "entropy": 0.11552000045776367, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:26.130663Z", "loop": 4736, "env_steps": 2910412799, "loss": 0.020750368013978004, "avg_return": 0.8576527833938599, "regret": 0.0022211840841919184, "entropy": 0.115608349442482, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:26.983589Z", "loop": 4737, "env_steps": 2911027199, "loss": 0.02158695086836815, "avg_return": 0.857933759689331, "regret": 0.0022211840841919184, "entropy": 0.1196620836853981, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:27.836233Z", "loop": 4738, "env_steps": 2911641599, "loss": 0.02217511087656021, "avg_return": 0.8575734496116638, "regret": 0.0022211840841919184, "entropy": 0.12235767394304276, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:28.690376Z", "loop": 4739, "env_steps": 2912255999, "loss": 0.020451566204428673, "avg_return": 0.8578253388404846, "regret": 0.0022211840841919184, "entropy": 0.11610423028469086, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:29.583653Z", "loop": 4740, "env_steps": 2912870399, "loss": 0.021722882986068726, "avg_return": 0.8573614954948425, "regret": 0.005846476182341576, "entropy": 0.12198475748300552, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:30.437354Z", "loop": 4741, "env_steps": 2913484799, "loss": 0.02130895107984543, "avg_return": 0.8593485951423645, "regret": 0.005846476182341576, "entropy": 0.12312056869268417, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:31.291461Z", "loop": 4742, "env_steps": 2914099199, "loss": 0.02173689194023609, "avg_return": 0.8585302829742432, "regret": 0.005846476182341576, "entropy": 0.11991088092327118, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:32.146565Z", "loop": 4743, "env_steps": 2914713599, "loss": 0.02272467315196991, "avg_return": 0.8602626919746399, "regret": 0.005846476182341576, "entropy": 0.12487592548131943, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:33.000411Z", "loop": 4744, "env_steps": 2915327999, "loss": 0.021185338497161865, "avg_return": 0.8607937693595886, "regret": 0.005846476182341576, "entropy": 0.12178415060043335, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:33.854816Z", "loop": 4745, "env_steps": 2915942399, "loss": 0.02047836408019066, "avg_return": 0.8598478436470032, "regret": 0.005846476182341576, "entropy": 0.12243818491697311, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:34.708695Z", "loop": 4746, "env_steps": 2916556799, "loss": 0.021034633740782738, "avg_return": 0.8610303997993469, "regret": 0.005846476182341576, "entropy": 0.1221088320016861, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:35.563842Z", "loop": 4747, "env_steps": 2917171199, "loss": 0.01967778243124485, "avg_return": 0.8610777258872986, "regret": 0.005846476182341576, "entropy": 0.11475718021392822, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:36.417920Z", "loop": 4748, "env_steps": 2917785599, "loss": 0.021158067509531975, "avg_return": 0.8615067601203918, "regret": 0.005846476182341576, "entropy": 0.12067040801048279, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:37.272004Z", "loop": 4749, "env_steps": 2918399999, "loss": 0.019613904878497124, "avg_return": 0.8623302578926086, "regret": 0.005846476182341576, "entropy": 0.1103653684258461, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:38.169299Z", "loop": 4750, "env_steps": 2919014399, "loss": 0.020582152530550957, "avg_return": 0.8612685203552246, "regret": 0.0019092480652034283, "entropy": 0.11417960375547409, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:39.022801Z", "loop": 4751, "env_steps": 2919628799, "loss": 0.019605210050940514, "avg_return": 0.8627607226371765, "regret": 0.0019092480652034283, "entropy": 0.10925710201263428, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:39.878959Z", "loop": 4752, "env_steps": 2920243199, "loss": 0.018681110814213753, "avg_return": 0.8628131151199341, "regret": 0.0019092480652034283, "entropy": 0.10874728113412857, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:40.735356Z", "loop": 4753, "env_steps": 2920857599, "loss": 0.01865062676370144, "avg_return": 0.8610815405845642, "regret": 0.0019092480652034283, "entropy": 0.10474713146686554, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:41.591811Z", "loop": 4754, "env_steps": 2921471999, "loss": 0.019796831533312798, "avg_return": 0.861581027507782, "regret": 0.0019092480652034283, "entropy": 0.11015881597995758, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:42.448044Z", "loop": 4755, "env_steps": 2922086399, "loss": 0.020071953535079956, "avg_return": 0.8612958192825317, "regret": 0.0019092480652034283, "entropy": 0.1127820611000061, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:43.303488Z", "loop": 4756, "env_steps": 2922700799, "loss": 0.01869153417646885, "avg_return": 0.8596059083938599, "regret": 0.0019092480652034283, "entropy": 0.10860301554203033, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:44.159383Z", "loop": 4757, "env_steps": 2923315199, "loss": 0.019699901342391968, "avg_return": 0.8602243065834045, "regret": 0.0019092480652034283, "entropy": 0.1111614853143692, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:45.015025Z", "loop": 4758, "env_steps": 2923929599, "loss": 0.0199130829423666, "avg_return": 0.8604995012283325, "regret": 0.0019092480652034283, "entropy": 0.11170052736997604, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:45.871076Z", "loop": 4759, "env_steps": 2924543999, "loss": 0.020329177379608154, "avg_return": 0.8584715127944946, "regret": 0.0019092480652034283, "entropy": 0.11105047166347504, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:46.768594Z", "loop": 4760, "env_steps": 2925158399, "loss": 0.019370686262845993, "avg_return": 0.8596968054771423, "regret": 0.003401351161301136, "entropy": 0.11071350425481796, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:47.623265Z", "loop": 4761, "env_steps": 2925772799, "loss": 0.019802337512373924, "avg_return": 0.861187756061554, "regret": 0.003401351161301136, "entropy": 0.1095685139298439, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:48.477942Z", "loop": 4762, "env_steps": 2926387199, "loss": 0.020136121660470963, "avg_return": 0.8609400391578674, "regret": 0.003401351161301136, "entropy": 0.1119132786989212, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:49.331566Z", "loop": 4763, "env_steps": 2927001599, "loss": 0.019551871344447136, "avg_return": 0.8605303168296814, "regret": 0.003401351161301136, "entropy": 0.10939595103263855, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:50.185162Z", "loop": 4764, "env_steps": 2927615999, "loss": 0.019684920087456703, "avg_return": 0.8609517812728882, "regret": 0.003401351161301136, "entropy": 0.11452434211969376, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:51.038762Z", "loop": 4765, "env_steps": 2928230399, "loss": 0.020106660202145576, "avg_return": 0.861098051071167, "regret": 0.003401351161301136, "entropy": 0.11398749053478241, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:51.892128Z", "loop": 4766, "env_steps": 2928844799, "loss": 0.020931098610162735, "avg_return": 0.8613544702529907, "regret": 0.003401351161301136, "entropy": 0.11817055195569992, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:52.745587Z", "loop": 4767, "env_steps": 2929459199, "loss": 0.019710799679160118, "avg_return": 0.8617820143699646, "regret": 0.003401351161301136, "entropy": 0.11363320797681808, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:53.599202Z", "loop": 4768, "env_steps": 2930073599, "loss": 0.019888373091816902, "avg_return": 0.8602253198623657, "regret": 0.003401351161301136, "entropy": 0.11271040886640549, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:54.452512Z", "loop": 4769, "env_steps": 2930687999, "loss": 0.021158939227461815, "avg_return": 0.8591355681419373, "regret": 0.003401351161301136, "entropy": 0.11868954449892044, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:55.346532Z", "loop": 4770, "env_steps": 2931302399, "loss": 0.02096775732934475, "avg_return": 0.859933614730835, "regret": 0.0032149124890565872, "entropy": 0.11792147159576416, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:56.200423Z", "loop": 4771, "env_steps": 2931916799, "loss": 0.020010298117995262, "avg_return": 0.8603220582008362, "regret": 0.0032149124890565872, "entropy": 0.11839228123426437, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:57.054258Z", "loop": 4772, "env_steps": 2932531199, "loss": 0.021181154996156693, "avg_return": 0.86009281873703, "regret": 0.0032149124890565872, "entropy": 0.12197396159172058, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:57.907991Z", "loop": 4773, "env_steps": 2933145599, "loss": 0.020857559517025948, "avg_return": 0.8576968312263489, "regret": 0.0032149124890565872, "entropy": 0.11763592809438705, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:58.762171Z", "loop": 4774, "env_steps": 2933759999, "loss": 0.02129671536386013, "avg_return": 0.8588142991065979, "regret": 0.0032149124890565872, "entropy": 0.12688973546028137, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:31:59.617091Z", "loop": 4775, "env_steps": 2934374399, "loss": 0.021865300834178925, "avg_return": 0.8569765686988831, "regret": 0.0032149124890565872, "entropy": 0.12735778093338013, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:00.471413Z", "loop": 4776, "env_steps": 2934988799, "loss": 0.02246280014514923, "avg_return": 0.8574021458625793, "regret": 0.0032149124890565872, "entropy": 0.1240968257188797, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:01.325106Z", "loop": 4777, "env_steps": 2935603199, "loss": 0.0228403452783823, "avg_return": 0.8596621751785278, "regret": 0.0032149124890565872, "entropy": 0.12893016636371613, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:02.178187Z", "loop": 4778, "env_steps": 2936217599, "loss": 0.021071208640933037, "avg_return": 0.8597784638404846, "regret": 0.0032149124890565872, "entropy": 0.1216265931725502, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:03.031837Z", "loop": 4779, "env_steps": 2936831999, "loss": 0.020973725244402885, "avg_return": 0.8610584735870361, "regret": 0.0032149124890565872, "entropy": 0.1209774985909462, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:03.927689Z", "loop": 4780, "env_steps": 2937446399, "loss": 0.020528137683868408, "avg_return": 0.8604368567466736, "regret": 0.002901734784245491, "entropy": 0.11455436795949936, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:04.781034Z", "loop": 4781, "env_steps": 2938060799, "loss": 0.02002028375864029, "avg_return": 0.8599225282669067, "regret": 0.002901734784245491, "entropy": 0.11455778777599335, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:05.634257Z", "loop": 4782, "env_steps": 2938675199, "loss": 0.01902027055621147, "avg_return": 0.8612412810325623, "regret": 0.002901734784245491, "entropy": 0.10819362848997116, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:06.488067Z", "loop": 4783, "env_steps": 2939289599, "loss": 0.020636020228266716, "avg_return": 0.8601462841033936, "regret": 0.002901734784245491, "entropy": 0.11642903089523315, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:07.342472Z", "loop": 4784, "env_steps": 2939903999, "loss": 0.021075356751680374, "avg_return": 0.8597440719604492, "regret": 0.002901734784245491, "entropy": 0.11768466979265213, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:08.197419Z", "loop": 4785, "env_steps": 2940518399, "loss": 0.02010931819677353, "avg_return": 0.859843373298645, "regret": 0.002901734784245491, "entropy": 0.11789891868829727, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:09.050992Z", "loop": 4786, "env_steps": 2941132799, "loss": 0.020493466407060623, "avg_return": 0.8591951727867126, "regret": 0.002901734784245491, "entropy": 0.11836035549640656, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:09.903755Z", "loop": 4787, "env_steps": 2941747199, "loss": 0.021266289055347443, "avg_return": 0.8594970703125, "regret": 0.002901734784245491, "entropy": 0.11638858914375305, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:10.757484Z", "loop": 4788, "env_steps": 2942361599, "loss": 0.018668975681066513, "avg_return": 0.8607098460197449, "regret": 0.002901734784245491, "entropy": 0.1060216873884201, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:11.612015Z", "loop": 4789, "env_steps": 2942975999, "loss": 0.019035503268241882, "avg_return": 0.8609802722930908, "regret": 0.002901734784245491, "entropy": 0.10709346830844879, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:12.506129Z", "loop": 4790, "env_steps": 2943590399, "loss": 0.01897856965661049, "avg_return": 0.8614890575408936, "regret": 0.0023467042483389378, "entropy": 0.10685636848211288, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:13.359602Z", "loop": 4791, "env_steps": 2944204799, "loss": 0.017230693250894547, "avg_return": 0.8618762493133545, "regret": 0.0023467042483389378, "entropy": 0.10000204294919968, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:14.213491Z", "loop": 4792, "env_steps": 2944819199, "loss": 0.019615234807133675, "avg_return": 0.8628387451171875, "regret": 0.0023467042483389378, "entropy": 0.10639385133981705, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:15.067614Z", "loop": 4793, "env_steps": 2945433599, "loss": 0.01937050186097622, "avg_return": 0.8606173992156982, "regret": 0.0023467042483389378, "entropy": 0.10734158009290695, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:15.920997Z", "loop": 4794, "env_steps": 2946047999, "loss": 0.019630463793873787, "avg_return": 0.8618725538253784, "regret": 0.0023467042483389378, "entropy": 0.1066974475979805, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:16.774814Z", "loop": 4795, "env_steps": 2946662399, "loss": 0.018014168366789818, "avg_return": 0.8607236742973328, "regret": 0.0023467042483389378, "entropy": 0.10472644865512848, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:17.628085Z", "loop": 4796, "env_steps": 2947276799, "loss": 0.01799730397760868, "avg_return": 0.8594952821731567, "regret": 0.0023467042483389378, "entropy": 0.1026477962732315, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:18.481283Z", "loop": 4797, "env_steps": 2947891199, "loss": 0.02104061469435692, "avg_return": 0.8600561618804932, "regret": 0.0023467042483389378, "entropy": 0.11321647465229034, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:19.335312Z", "loop": 4798, "env_steps": 2948505599, "loss": 0.01947944052517414, "avg_return": 0.8592881560325623, "regret": 0.0023467042483389378, "entropy": 0.11268193274736404, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:20.188769Z", "loop": 4799, "env_steps": 2949119999, "loss": 0.02009354718029499, "avg_return": 0.8597967624664307, "regret": 0.0023467042483389378, "entropy": 0.10970436036586761, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:21.084041Z", "loop": 4800, "env_steps": 2949734399, "loss": 0.021033210679888725, "avg_return": 0.858570396900177, "regret": 0.005192701704800129, "entropy": 0.11632492393255234, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:21.938428Z", "loop": 4801, "env_steps": 2950348799, "loss": 0.02040058746933937, "avg_return": 0.8587625622749329, "regret": 0.005192701704800129, "entropy": 0.11600420624017715, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:22.794388Z", "loop": 4802, "env_steps": 2950963199, "loss": 0.021798018366098404, "avg_return": 0.8574549555778503, "regret": 0.005192701704800129, "entropy": 0.12122631818056107, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:23.648992Z", "loop": 4803, "env_steps": 2951577599, "loss": 0.02086646482348442, "avg_return": 0.8600841760635376, "regret": 0.005192701704800129, "entropy": 0.11562951654195786, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:24.504978Z", "loop": 4804, "env_steps": 2952191999, "loss": 0.02015208639204502, "avg_return": 0.8584374189376831, "regret": 0.005192701704800129, "entropy": 0.11379142105579376, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:25.359506Z", "loop": 4805, "env_steps": 2952806399, "loss": 0.019081518054008484, "avg_return": 0.8585841059684753, "regret": 0.005192701704800129, "entropy": 0.10950007289648056, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:26.215820Z", "loop": 4806, "env_steps": 2953420799, "loss": 0.02034672535955906, "avg_return": 0.8605301976203918, "regret": 0.005192701704800129, "entropy": 0.11280780285596848, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:27.072314Z", "loop": 4807, "env_steps": 2954035199, "loss": 0.020058676600456238, "avg_return": 0.8606811761856079, "regret": 0.005192701704800129, "entropy": 0.10884112119674683, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:27.928491Z", "loop": 4808, "env_steps": 2954649599, "loss": 0.01888212002813816, "avg_return": 0.8600203394889832, "regret": 0.005192701704800129, "entropy": 0.10282297432422638, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:28.783856Z", "loop": 4809, "env_steps": 2955263999, "loss": 0.01868549920618534, "avg_return": 0.8591489791870117, "regret": 0.005192701704800129, "entropy": 0.10612279921770096, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:29.679455Z", "loop": 4810, "env_steps": 2955878399, "loss": 0.01937675289809704, "avg_return": 0.8606844544410706, "regret": 0.003778348211199045, "entropy": 0.1077767089009285, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:30.533501Z", "loop": 4811, "env_steps": 2956492799, "loss": 0.018597474321722984, "avg_return": 0.8601676821708679, "regret": 0.003778348211199045, "entropy": 0.10651308298110962, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:31.388047Z", "loop": 4812, "env_steps": 2957107199, "loss": 0.02058626152575016, "avg_return": 0.8604501485824585, "regret": 0.003778348211199045, "entropy": 0.11137782037258148, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:32.241865Z", "loop": 4813, "env_steps": 2957721599, "loss": 0.01928083226084709, "avg_return": 0.861056923866272, "regret": 0.003778348211199045, "entropy": 0.10252383351325989, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:33.095305Z", "loop": 4814, "env_steps": 2958335999, "loss": 0.019067665562033653, "avg_return": 0.8597497940063477, "regret": 0.003778348211199045, "entropy": 0.10462573170661926, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:33.949141Z", "loop": 4815, "env_steps": 2958950399, "loss": 0.019496498629450798, "avg_return": 0.8613325953483582, "regret": 0.003778348211199045, "entropy": 0.10520593822002411, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:34.803379Z", "loop": 4816, "env_steps": 2959564799, "loss": 0.017283974215388298, "avg_return": 0.8622526526451111, "regret": 0.003778348211199045, "entropy": 0.09733659029006958, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:35.658033Z", "loop": 4817, "env_steps": 2960179199, "loss": 0.016386857256293297, "avg_return": 0.8624392151832581, "regret": 0.003778348211199045, "entropy": 0.0968782976269722, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:36.511438Z", "loop": 4818, "env_steps": 2960793599, "loss": 0.016296349465847015, "avg_return": 0.8623266816139221, "regret": 0.003778348211199045, "entropy": 0.0955854132771492, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:37.365451Z", "loop": 4819, "env_steps": 2961407999, "loss": 0.018096258863806725, "avg_return": 0.8612074851989746, "regret": 0.003778348211199045, "entropy": 0.10096274316310883, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:38.260255Z", "loop": 4820, "env_steps": 2962022399, "loss": 0.017968833446502686, "avg_return": 0.8609771728515625, "regret": 0.0017242622561752796, "entropy": 0.10276515036821365, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:39.115016Z", "loop": 4821, "env_steps": 2962636799, "loss": 0.01966623030602932, "avg_return": 0.8615168333053589, "regret": 0.0017242622561752796, "entropy": 0.11221013963222504, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:39.970791Z", "loop": 4822, "env_steps": 2963251199, "loss": 0.019991977140307426, "avg_return": 0.8608297109603882, "regret": 0.0017242622561752796, "entropy": 0.1102725937962532, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:40.825096Z", "loop": 4823, "env_steps": 2963865599, "loss": 0.021477054804563522, "avg_return": 0.8621071577072144, "regret": 0.0017242622561752796, "entropy": 0.11979277431964874, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:41.679572Z", "loop": 4824, "env_steps": 2964479999, "loss": 0.02212958037853241, "avg_return": 0.8613446354866028, "regret": 0.0017242622561752796, "entropy": 0.12351258099079132, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:42.534328Z", "loop": 4825, "env_steps": 2965094399, "loss": 0.022747118026018143, "avg_return": 0.8606609106063843, "regret": 0.0017242622561752796, "entropy": 0.12711435556411743, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:43.389752Z", "loop": 4826, "env_steps": 2965708799, "loss": 0.02203369326889515, "avg_return": 0.8596006631851196, "regret": 0.0017242622561752796, "entropy": 0.1217540055513382, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:44.244302Z", "loop": 4827, "env_steps": 2966323199, "loss": 0.023003704845905304, "avg_return": 0.8604105114936829, "regret": 0.0017242622561752796, "entropy": 0.12411607801914215, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:45.097915Z", "loop": 4828, "env_steps": 2966937599, "loss": 0.022044120356440544, "avg_return": 0.860927164554596, "regret": 0.0017242622561752796, "entropy": 0.1233406811952591, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:45.952202Z", "loop": 4829, "env_steps": 2967551999, "loss": 0.021221082657575607, "avg_return": 0.8599913716316223, "regret": 0.0017242622561752796, "entropy": 0.12536902725696564, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:46.847260Z", "loop": 4830, "env_steps": 2968166399, "loss": 0.02028464898467064, "avg_return": 0.8601458668708801, "regret": 0.002753977198153734, "entropy": 0.11579518765211105, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:47.702177Z", "loop": 4831, "env_steps": 2968780799, "loss": 0.02119397185742855, "avg_return": 0.8602864742279053, "regret": 0.002753977198153734, "entropy": 0.1163654699921608, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:48.556515Z", "loop": 4832, "env_steps": 2969395199, "loss": 0.019528616219758987, "avg_return": 0.8607204556465149, "regret": 0.002753977198153734, "entropy": 0.11231173574924469, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:49.410606Z", "loop": 4833, "env_steps": 2970009599, "loss": 0.020079785957932472, "avg_return": 0.8602026700973511, "regret": 0.002753977198153734, "entropy": 0.1113637238740921, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:50.265980Z", "loop": 4834, "env_steps": 2970623999, "loss": 0.02008729986846447, "avg_return": 0.861626923084259, "regret": 0.002753977198153734, "entropy": 0.11496346443891525, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:51.121847Z", "loop": 4835, "env_steps": 2971238399, "loss": 0.019212696701288223, "avg_return": 0.8592197895050049, "regret": 0.002753977198153734, "entropy": 0.10636945068836212, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:51.975899Z", "loop": 4836, "env_steps": 2971852799, "loss": 0.02018650621175766, "avg_return": 0.8597460985183716, "regret": 0.002753977198153734, "entropy": 0.11329980194568634, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:52.829011Z", "loop": 4837, "env_steps": 2972467199, "loss": 0.020356521010398865, "avg_return": 0.8602479100227356, "regret": 0.002753977198153734, "entropy": 0.10967834293842316, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:53.682422Z", "loop": 4838, "env_steps": 2973081599, "loss": 0.01961386203765869, "avg_return": 0.8605886101722717, "regret": 0.002753977198153734, "entropy": 0.10965938121080399, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:54.536553Z", "loop": 4839, "env_steps": 2973695999, "loss": 0.02012881264090538, "avg_return": 0.8606225848197937, "regret": 0.002753977198153734, "entropy": 0.11423086374998093, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:55.430900Z", "loop": 4840, "env_steps": 2974310399, "loss": 0.019317997619509697, "avg_return": 0.8599410057067871, "regret": 0.0035057293716818094, "entropy": 0.10904809087514877, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:56.283987Z", "loop": 4841, "env_steps": 2974924799, "loss": 0.019107595086097717, "avg_return": 0.8597089052200317, "regret": 0.0035057293716818094, "entropy": 0.10907991975545883, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:57.136814Z", "loop": 4842, "env_steps": 2975539199, "loss": 0.020904820412397385, "avg_return": 0.8600847721099854, "regret": 0.0035057293716818094, "entropy": 0.11567424237728119, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:57.991106Z", "loop": 4843, "env_steps": 2976153599, "loss": 0.019617442041635513, "avg_return": 0.8599280714988708, "regret": 0.0035057293716818094, "entropy": 0.11161961406469345, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:58.846029Z", "loop": 4844, "env_steps": 2976767999, "loss": 0.018938153982162476, "avg_return": 0.8602310419082642, "regret": 0.0035057293716818094, "entropy": 0.11016132682561874, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:32:59.699570Z", "loop": 4845, "env_steps": 2977382399, "loss": 0.01986795663833618, "avg_return": 0.8597355484962463, "regret": 0.0035057293716818094, "entropy": 0.1093793660402298, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:00.552349Z", "loop": 4846, "env_steps": 2977996799, "loss": 0.02025020681321621, "avg_return": 0.861778974533081, "regret": 0.0035057293716818094, "entropy": 0.115335613489151, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:01.406195Z", "loop": 4847, "env_steps": 2978611199, "loss": 0.01918632909655571, "avg_return": 0.8610972166061401, "regret": 0.0035057293716818094, "entropy": 0.10722311586141586, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:02.261026Z", "loop": 4848, "env_steps": 2979225599, "loss": 0.018671629950404167, "avg_return": 0.8626978993415833, "regret": 0.0035057293716818094, "entropy": 0.10626162588596344, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:03.115044Z", "loop": 4849, "env_steps": 2979839999, "loss": 0.01950112171471119, "avg_return": 0.8611443042755127, "regret": 0.0035057293716818094, "entropy": 0.11279593408107758, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:04.007653Z", "loop": 4850, "env_steps": 2980454399, "loss": 0.01862838864326477, "avg_return": 0.8616925477981567, "regret": 0.0022495018783956766, "entropy": 0.10910563915967941, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:04.862562Z", "loop": 4851, "env_steps": 2981068799, "loss": 0.018444491550326347, "avg_return": 0.8615257143974304, "regret": 0.0022495018783956766, "entropy": 0.10772135853767395, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:05.717969Z", "loop": 4852, "env_steps": 2981683199, "loss": 0.020569439977407455, "avg_return": 0.8611579537391663, "regret": 0.0022495018783956766, "entropy": 0.11353222280740738, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:06.572946Z", "loop": 4853, "env_steps": 2982297599, "loss": 0.020508188754320145, "avg_return": 0.860032856464386, "regret": 0.0022495018783956766, "entropy": 0.11506953835487366, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:07.427273Z", "loop": 4854, "env_steps": 2982911999, "loss": 0.01922200433909893, "avg_return": 0.8616833686828613, "regret": 0.0022495018783956766, "entropy": 0.10979116708040237, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:08.282171Z", "loop": 4855, "env_steps": 2983526399, "loss": 0.019915174692869186, "avg_return": 0.8607301115989685, "regret": 0.0022495018783956766, "entropy": 0.11165904253721237, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:09.136401Z", "loop": 4856, "env_steps": 2984140799, "loss": 0.01915767975151539, "avg_return": 0.8612483739852905, "regret": 0.0022495018783956766, "entropy": 0.10558164119720459, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:09.990131Z", "loop": 4857, "env_steps": 2984755199, "loss": 0.02093368209898472, "avg_return": 0.8600398898124695, "regret": 0.0022495018783956766, "entropy": 0.11565140634775162, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:10.844246Z", "loop": 4858, "env_steps": 2985369599, "loss": 0.020211800932884216, "avg_return": 0.862532377243042, "regret": 0.0022495018783956766, "entropy": 0.11464833468198776, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:11.699545Z", "loop": 4859, "env_steps": 2985983999, "loss": 0.019648320972919464, "avg_return": 0.8615759611129761, "regret": 0.0022495018783956766, "entropy": 0.11225629597902298, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:12.596175Z", "loop": 4860, "env_steps": 2986598399, "loss": 0.019384117797017097, "avg_return": 0.8598936200141907, "regret": 0.002626220928505063, "entropy": 0.11090385168790817, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:13.451548Z", "loop": 4861, "env_steps": 2987212799, "loss": 0.01964140497148037, "avg_return": 0.8611294031143188, "regret": 0.002626220928505063, "entropy": 0.1155223399400711, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:14.306147Z", "loop": 4862, "env_steps": 2987827199, "loss": 0.020682308822870255, "avg_return": 0.86105877161026, "regret": 0.002626220928505063, "entropy": 0.1132422611117363, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:15.161308Z", "loop": 4863, "env_steps": 2988441599, "loss": 0.019539806991815567, "avg_return": 0.8612979054450989, "regret": 0.002626220928505063, "entropy": 0.11123360693454742, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:16.014900Z", "loop": 4864, "env_steps": 2989055999, "loss": 0.019163930788636208, "avg_return": 0.8607316017150879, "regret": 0.002626220928505063, "entropy": 0.10900464653968811, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:16.868849Z", "loop": 4865, "env_steps": 2989670399, "loss": 0.01915801875293255, "avg_return": 0.8619223237037659, "regret": 0.002626220928505063, "entropy": 0.10662099719047546, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:17.723322Z", "loop": 4866, "env_steps": 2990284799, "loss": 0.01849920116364956, "avg_return": 0.8631783127784729, "regret": 0.002626220928505063, "entropy": 0.10136967897415161, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:18.578510Z", "loop": 4867, "env_steps": 2990899199, "loss": 0.019956281408667564, "avg_return": 0.8608399629592896, "regret": 0.002626220928505063, "entropy": 0.11038544028997421, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:19.432039Z", "loop": 4868, "env_steps": 2991513599, "loss": 0.02044064737856388, "avg_return": 0.8601037859916687, "regret": 0.002626220928505063, "entropy": 0.10656362771987915, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:20.286478Z", "loop": 4869, "env_steps": 2992127999, "loss": 0.020446114242076874, "avg_return": 0.8606857657432556, "regret": 0.002626220928505063, "entropy": 0.11295350641012192, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:21.181984Z", "loop": 4870, "env_steps": 2992742399, "loss": 0.018062656745314598, "avg_return": 0.8585177063941956, "regret": 0.0045899758115410805, "entropy": 0.0987035259604454, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:22.036044Z", "loop": 4871, "env_steps": 2993356799, "loss": 0.01908029243350029, "avg_return": 0.8586464524269104, "regret": 0.0045899758115410805, "entropy": 0.10413505882024765, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:22.891098Z", "loop": 4872, "env_steps": 2993971199, "loss": 0.019754616543650627, "avg_return": 0.8587836027145386, "regret": 0.0045899758115410805, "entropy": 0.1079719141125679, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:23.744568Z", "loop": 4873, "env_steps": 2994585599, "loss": 0.020008018240332603, "avg_return": 0.858913779258728, "regret": 0.0045899758115410805, "entropy": 0.10499750077724457, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:24.598104Z", "loop": 4874, "env_steps": 2995199999, "loss": 0.02139968052506447, "avg_return": 0.8601973652839661, "regret": 0.0045899758115410805, "entropy": 0.1132914125919342, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:25.453416Z", "loop": 4875, "env_steps": 2995814399, "loss": 0.019524388015270233, "avg_return": 0.8605301976203918, "regret": 0.0045899758115410805, "entropy": 0.10446327924728394, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:26.308323Z", "loop": 4876, "env_steps": 2996428799, "loss": 0.020097464323043823, "avg_return": 0.8605881929397583, "regret": 0.0045899758115410805, "entropy": 0.11166779696941376, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:27.162222Z", "loop": 4877, "env_steps": 2997043199, "loss": 0.020191598683595657, "avg_return": 0.8605135083198547, "regret": 0.0045899758115410805, "entropy": 0.11057718843221664, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:28.016978Z", "loop": 4878, "env_steps": 2997657599, "loss": 0.01970207318663597, "avg_return": 0.8616836667060852, "regret": 0.0045899758115410805, "entropy": 0.11255922168493271, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:28.872479Z", "loop": 4879, "env_steps": 2998271999, "loss": 0.01810825988650322, "avg_return": 0.8609694838523865, "regret": 0.0045899758115410805, "entropy": 0.10445483028888702, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:29.769309Z", "loop": 4880, "env_steps": 2998886399, "loss": 0.021535424515604973, "avg_return": 0.861589789390564, "regret": 0.002418571151793003, "entropy": 0.11906231939792633, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:30.624525Z", "loop": 4881, "env_steps": 2999500799, "loss": 0.020551027730107307, "avg_return": 0.8610184788703918, "regret": 0.002418571151793003, "entropy": 0.1221303716301918, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:31.479087Z", "loop": 4882, "env_steps": 3000115199, "loss": 0.022409936413168907, "avg_return": 0.8582348823547363, "regret": 0.002418571151793003, "entropy": 0.1252414882183075, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:32.334258Z", "loop": 4883, "env_steps": 3000729599, "loss": 0.023676250129938126, "avg_return": 0.8570074439048767, "regret": 0.002418571151793003, "entropy": 0.13640227913856506, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:33.189813Z", "loop": 4884, "env_steps": 3001343999, "loss": 0.024578599259257317, "avg_return": 0.8543906807899475, "regret": 0.002418571151793003, "entropy": 0.13922633230686188, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:34.045560Z", "loop": 4885, "env_steps": 3001958399, "loss": 0.023134863004088402, "avg_return": 0.8556689620018005, "regret": 0.002418571151793003, "entropy": 0.1376645267009735, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:34.900170Z", "loop": 4886, "env_steps": 3002572799, "loss": 0.02275748923420906, "avg_return": 0.8586772084236145, "regret": 0.002418571151793003, "entropy": 0.13282908499240875, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:35.755244Z", "loop": 4887, "env_steps": 3003187199, "loss": 0.02111349254846573, "avg_return": 0.8606869578361511, "regret": 0.002418571151793003, "entropy": 0.1219853088259697, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:36.611561Z", "loop": 4888, "env_steps": 3003801599, "loss": 0.020203134045004845, "avg_return": 0.861720621585846, "regret": 0.002418571151793003, "entropy": 0.1141069084405899, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:37.466525Z", "loop": 4889, "env_steps": 3004415999, "loss": 0.01968858577311039, "avg_return": 0.8618699312210083, "regret": 0.002418571151793003, "entropy": 0.10690563917160034, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:38.361786Z", "loop": 4890, "env_steps": 3005030399, "loss": 0.0197050329297781, "avg_return": 0.86219322681427, "regret": 0.001645460957661271, "entropy": 0.10874038189649582, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:39.215810Z", "loop": 4891, "env_steps": 3005644799, "loss": 0.017951615154743195, "avg_return": 0.8609030246734619, "regret": 0.001645460957661271, "entropy": 0.10270664095878601, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:40.069399Z", "loop": 4892, "env_steps": 3006259199, "loss": 0.019033372402191162, "avg_return": 0.8623008131980896, "regret": 0.001645460957661271, "entropy": 0.10842777043581009, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:40.924332Z", "loop": 4893, "env_steps": 3006873599, "loss": 0.018357068300247192, "avg_return": 0.8625735640525818, "regret": 0.001645460957661271, "entropy": 0.10736662149429321, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:41.779763Z", "loop": 4894, "env_steps": 3007487999, "loss": 0.02042279578745365, "avg_return": 0.8603515028953552, "regret": 0.001645460957661271, "entropy": 0.10835912078619003, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:42.636121Z", "loop": 4895, "env_steps": 3008102399, "loss": 0.01821826957166195, "avg_return": 0.8617222309112549, "regret": 0.001645460957661271, "entropy": 0.10616004467010498, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:43.489232Z", "loop": 4896, "env_steps": 3008716799, "loss": 0.018366781994700432, "avg_return": 0.8604441285133362, "regret": 0.001645460957661271, "entropy": 0.10679468512535095, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:44.342798Z", "loop": 4897, "env_steps": 3009331199, "loss": 0.01760636270046234, "avg_return": 0.8609522581100464, "regret": 0.001645460957661271, "entropy": 0.10354642570018768, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:45.198469Z", "loop": 4898, "env_steps": 3009945599, "loss": 0.019572628661990166, "avg_return": 0.861584484577179, "regret": 0.001645460957661271, "entropy": 0.10987463593482971, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:46.052024Z", "loop": 4899, "env_steps": 3010559999, "loss": 0.017926959320902824, "avg_return": 0.8619006276130676, "regret": 0.001645460957661271, "entropy": 0.1019725352525711, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:46.945637Z", "loop": 4900, "env_steps": 3011174399, "loss": 0.019244076684117317, "avg_return": 0.860042154788971, "regret": 0.0021999317687004805, "entropy": 0.10645777732133865, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:47.799429Z", "loop": 4901, "env_steps": 3011788799, "loss": 0.01928780786693096, "avg_return": 0.861578106880188, "regret": 0.0021999317687004805, "entropy": 0.10368091613054276, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:48.655171Z", "loop": 4902, "env_steps": 3012403199, "loss": 0.018515361472964287, "avg_return": 0.8608382344245911, "regret": 0.0021999317687004805, "entropy": 0.10509640723466873, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:49.510641Z", "loop": 4903, "env_steps": 3013017599, "loss": 0.01824137382209301, "avg_return": 0.8610803484916687, "regret": 0.0021999317687004805, "entropy": 0.10622718185186386, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:50.364549Z", "loop": 4904, "env_steps": 3013631999, "loss": 0.019072677940130234, "avg_return": 0.8604675531387329, "regret": 0.0021999317687004805, "entropy": 0.10813184082508087, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:51.217129Z", "loop": 4905, "env_steps": 3014246399, "loss": 0.018647056072950363, "avg_return": 0.8604779243469238, "regret": 0.0021999317687004805, "entropy": 0.09922070801258087, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:52.070685Z", "loop": 4906, "env_steps": 3014860799, "loss": 0.019145919010043144, "avg_return": 0.8603056073188782, "regret": 0.0021999317687004805, "entropy": 0.10631067305803299, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:52.926346Z", "loop": 4907, "env_steps": 3015475199, "loss": 0.019364185631275177, "avg_return": 0.8591451048851013, "regret": 0.0021999317687004805, "entropy": 0.10743217915296555, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:53.780353Z", "loop": 4908, "env_steps": 3016089599, "loss": 0.019370829686522484, "avg_return": 0.8599202632904053, "regret": 0.0021999317687004805, "entropy": 0.10462120175361633, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:54.633363Z", "loop": 4909, "env_steps": 3016703999, "loss": 0.018293648958206177, "avg_return": 0.8596636056900024, "regret": 0.0021999317687004805, "entropy": 0.10274787992238998, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:55.529767Z", "loop": 4910, "env_steps": 3017318399, "loss": 0.019349146634340286, "avg_return": 0.8598892688751221, "regret": 0.0036769320722669363, "entropy": 0.10800501704216003, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:56.383831Z", "loop": 4911, "env_steps": 3017932799, "loss": 0.019202498719096184, "avg_return": 0.8591489791870117, "regret": 0.0036769320722669363, "entropy": 0.11182525753974915, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:57.236813Z", "loop": 4912, "env_steps": 3018547199, "loss": 0.018266160041093826, "avg_return": 0.8604022264480591, "regret": 0.0036769320722669363, "entropy": 0.10442885011434555, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:58.090208Z", "loop": 4913, "env_steps": 3019161599, "loss": 0.019451318308711052, "avg_return": 0.861445963382721, "regret": 0.0036769320722669363, "entropy": 0.1109905019402504, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:58.944660Z", "loop": 4914, "env_steps": 3019775999, "loss": 0.018032699823379517, "avg_return": 0.8593166470527649, "regret": 0.0036769320722669363, "entropy": 0.10255347192287445, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:33:59.798079Z", "loop": 4915, "env_steps": 3020390399, "loss": 0.02041269838809967, "avg_return": 0.8622361421585083, "regret": 0.0036769320722669363, "entropy": 0.10812263935804367, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:00.651578Z", "loop": 4916, "env_steps": 3021004799, "loss": 0.01711377315223217, "avg_return": 0.8609643578529358, "regret": 0.0036769320722669363, "entropy": 0.10012975335121155, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:01.504473Z", "loop": 4917, "env_steps": 3021619199, "loss": 0.01855504885315895, "avg_return": 0.8617590665817261, "regret": 0.0036769320722669363, "entropy": 0.10363369435071945, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:02.358795Z", "loop": 4918, "env_steps": 3022233599, "loss": 0.0182344913482666, "avg_return": 0.8597664833068848, "regret": 0.0036769320722669363, "entropy": 0.10277446359395981, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:03.213428Z", "loop": 4919, "env_steps": 3022847999, "loss": 0.017986824735999107, "avg_return": 0.8614680171012878, "regret": 0.0036769320722669363, "entropy": 0.10318285971879959, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:04.108012Z", "loop": 4920, "env_steps": 3023462399, "loss": 0.017634889110922813, "avg_return": 0.8615906834602356, "regret": 0.002598026068881154, "entropy": 0.10141997039318085, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:04.961463Z", "loop": 4921, "env_steps": 3024076799, "loss": 0.016700295731425285, "avg_return": 0.8589810132980347, "regret": 0.002598026068881154, "entropy": 0.09653550386428833, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:05.815588Z", "loop": 4922, "env_steps": 3024691199, "loss": 0.017845075577497482, "avg_return": 0.8605511784553528, "regret": 0.002598026068881154, "entropy": 0.09847895056009293, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:06.668464Z", "loop": 4923, "env_steps": 3025305599, "loss": 0.018849557265639305, "avg_return": 0.8604366183280945, "regret": 0.002598026068881154, "entropy": 0.10575401782989502, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:07.521307Z", "loop": 4924, "env_steps": 3025919999, "loss": 0.019094014540314674, "avg_return": 0.8614229559898376, "regret": 0.002598026068881154, "entropy": 0.10569531470537186, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:08.375633Z", "loop": 4925, "env_steps": 3026534399, "loss": 0.019579794257879257, "avg_return": 0.8592907786369324, "regret": 0.002598026068881154, "entropy": 0.10499031096696854, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:09.230118Z", "loop": 4926, "env_steps": 3027148799, "loss": 0.018956145271658897, "avg_return": 0.859767496585846, "regret": 0.002598026068881154, "entropy": 0.10803349316120148, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:10.084278Z", "loop": 4927, "env_steps": 3027763199, "loss": 0.019919125363230705, "avg_return": 0.8596522212028503, "regret": 0.002598026068881154, "entropy": 0.10824930667877197, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:10.938582Z", "loop": 4928, "env_steps": 3028377599, "loss": 0.01758885197341442, "avg_return": 0.8588157296180725, "regret": 0.002598026068881154, "entropy": 0.10358483344316483, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:11.793646Z", "loop": 4929, "env_steps": 3028991999, "loss": 0.019404811784625053, "avg_return": 0.8594246506690979, "regret": 0.002598026068881154, "entropy": 0.10723192244768143, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:12.689514Z", "loop": 4930, "env_steps": 3029606399, "loss": 0.018902411684393883, "avg_return": 0.8599847555160522, "regret": 0.003581627272069454, "entropy": 0.10724706947803497, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:13.543846Z", "loop": 4931, "env_steps": 3030220799, "loss": 0.020209401845932007, "avg_return": 0.861621618270874, "regret": 0.003581627272069454, "entropy": 0.10859677195549011, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:14.397814Z", "loop": 4932, "env_steps": 3030835199, "loss": 0.019066348671913147, "avg_return": 0.8605460524559021, "regret": 0.003581627272069454, "entropy": 0.10711958259344101, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:15.252577Z", "loop": 4933, "env_steps": 3031449599, "loss": 0.019584184512495995, "avg_return": 0.8618159294128418, "regret": 0.003581627272069454, "entropy": 0.10684149712324142, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:16.107572Z", "loop": 4934, "env_steps": 3032063999, "loss": 0.01717495545744896, "avg_return": 0.8605683445930481, "regret": 0.003581627272069454, "entropy": 0.0984501913189888, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:16.964114Z", "loop": 4935, "env_steps": 3032678399, "loss": 0.018267549574375153, "avg_return": 0.8608841896057129, "regret": 0.003581627272069454, "entropy": 0.10173571109771729, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:17.819105Z", "loop": 4936, "env_steps": 3033292799, "loss": 0.01762409694492817, "avg_return": 0.8622336983680725, "regret": 0.003581627272069454, "entropy": 0.10182134062051773, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:18.674469Z", "loop": 4937, "env_steps": 3033907199, "loss": 0.019431566819548607, "avg_return": 0.861490786075592, "regret": 0.003581627272069454, "entropy": 0.10487240552902222, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:19.529063Z", "loop": 4938, "env_steps": 3034521599, "loss": 0.018339360132813454, "avg_return": 0.8602774143218994, "regret": 0.003581627272069454, "entropy": 0.10019609332084656, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:20.384117Z", "loop": 4939, "env_steps": 3035135999, "loss": 0.017294494435191154, "avg_return": 0.8618127703666687, "regret": 0.003581627272069454, "entropy": 0.0998920202255249, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:21.278472Z", "loop": 4940, "env_steps": 3035750399, "loss": 0.01818961463868618, "avg_return": 0.8605202436447144, "regret": 0.002556955674663186, "entropy": 0.1020074114203453, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:22.131339Z", "loop": 4941, "env_steps": 3036364799, "loss": 0.01975945755839348, "avg_return": 0.8605732321739197, "regret": 0.002556955674663186, "entropy": 0.10488276928663254, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:22.987120Z", "loop": 4942, "env_steps": 3036979199, "loss": 0.017226381227374077, "avg_return": 0.859419047832489, "regret": 0.002556955674663186, "entropy": 0.09739960730075836, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:23.841391Z", "loop": 4943, "env_steps": 3037593599, "loss": 0.01890552043914795, "avg_return": 0.859520673751831, "regret": 0.002556955674663186, "entropy": 0.10504120588302612, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:24.695088Z", "loop": 4944, "env_steps": 3038207999, "loss": 0.01819831132888794, "avg_return": 0.8598201870918274, "regret": 0.002556955674663186, "entropy": 0.10677366703748703, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:25.548723Z", "loop": 4945, "env_steps": 3038822399, "loss": 0.019135339185595512, "avg_return": 0.8604724407196045, "regret": 0.002556955674663186, "entropy": 0.11098725348711014, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:26.402107Z", "loop": 4946, "env_steps": 3039436799, "loss": 0.020059410482645035, "avg_return": 0.8596208095550537, "regret": 0.002556955674663186, "entropy": 0.11163979768753052, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:27.255956Z", "loop": 4947, "env_steps": 3040051199, "loss": 0.017972851172089577, "avg_return": 0.8600382804870605, "regret": 0.002556955674663186, "entropy": 0.10499398410320282, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:28.109617Z", "loop": 4948, "env_steps": 3040665599, "loss": 0.019987178966403008, "avg_return": 0.8602490425109863, "regret": 0.002556955674663186, "entropy": 0.11188437789678574, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:28.964589Z", "loop": 4949, "env_steps": 3041279999, "loss": 0.018964480608701706, "avg_return": 0.8596900701522827, "regret": 0.002556955674663186, "entropy": 0.10829342901706696, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:29.861430Z", "loop": 4950, "env_steps": 3041894399, "loss": 0.01914464682340622, "avg_return": 0.8591002821922302, "regret": 0.004873879719525576, "entropy": 0.10759640485048294, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:30.715118Z", "loop": 4951, "env_steps": 3042508799, "loss": 0.021175725385546684, "avg_return": 0.8581971526145935, "regret": 0.004873879719525576, "entropy": 0.1136089339852333, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:31.569456Z", "loop": 4952, "env_steps": 3043123199, "loss": 0.019798707216978073, "avg_return": 0.8573493361473083, "regret": 0.004873879719525576, "entropy": 0.11014693975448608, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:32.423822Z", "loop": 4953, "env_steps": 3043737599, "loss": 0.01944700814783573, "avg_return": 0.8596265912055969, "regret": 0.004873879719525576, "entropy": 0.10592726618051529, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:33.278164Z", "loop": 4954, "env_steps": 3044351999, "loss": 0.019849680364131927, "avg_return": 0.8595213890075684, "regret": 0.004873879719525576, "entropy": 0.11082401871681213, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:34.132021Z", "loop": 4955, "env_steps": 3044966399, "loss": 0.0186742153018713, "avg_return": 0.8610062599182129, "regret": 0.004873879719525576, "entropy": 0.10295441001653671, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:34.987049Z", "loop": 4956, "env_steps": 3045580799, "loss": 0.019466685131192207, "avg_return": 0.8598642945289612, "regret": 0.004873879719525576, "entropy": 0.1079530119895935, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:35.842119Z", "loop": 4957, "env_steps": 3046195199, "loss": 0.01975437067449093, "avg_return": 0.8602926731109619, "regret": 0.004873879719525576, "entropy": 0.11117910593748093, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:36.697036Z", "loop": 4958, "env_steps": 3046809599, "loss": 0.01943315379321575, "avg_return": 0.8590234518051147, "regret": 0.004873879719525576, "entropy": 0.11399104446172714, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:37.550763Z", "loop": 4959, "env_steps": 3047423999, "loss": 0.018913429230451584, "avg_return": 0.8606682419776917, "regret": 0.004873879719525576, "entropy": 0.107399582862854, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:38.445729Z", "loop": 4960, "env_steps": 3048038399, "loss": 0.01889035850763321, "avg_return": 0.8598177433013916, "regret": 0.0035982737317681313, "entropy": 0.10987930744886398, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:39.300093Z", "loop": 4961, "env_steps": 3048652799, "loss": 0.021230628713965416, "avg_return": 0.8594521284103394, "regret": 0.0035982737317681313, "entropy": 0.11992859840393066, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:40.155230Z", "loop": 4962, "env_steps": 3049267199, "loss": 0.02155652455985546, "avg_return": 0.8598140478134155, "regret": 0.0035982737317681313, "entropy": 0.11600035429000854, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:41.009107Z", "loop": 4963, "env_steps": 3049881599, "loss": 0.021050963550806046, "avg_return": 0.8608899116516113, "regret": 0.0035982737317681313, "entropy": 0.11464493721723557, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:41.862288Z", "loop": 4964, "env_steps": 3050495999, "loss": 0.020710118114948273, "avg_return": 0.8596840500831604, "regret": 0.0035982737317681313, "entropy": 0.1182514876127243, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:42.715973Z", "loop": 4965, "env_steps": 3051110399, "loss": 0.020968038588762283, "avg_return": 0.8608622550964355, "regret": 0.0035982737317681313, "entropy": 0.11316186189651489, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:43.571240Z", "loop": 4966, "env_steps": 3051724799, "loss": 0.0213329941034317, "avg_return": 0.8612464666366577, "regret": 0.0035982737317681313, "entropy": 0.11763008683919907, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:44.425379Z", "loop": 4967, "env_steps": 3052339199, "loss": 0.02101714164018631, "avg_return": 0.8619614839553833, "regret": 0.0035982737317681313, "entropy": 0.11493265628814697, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:45.279095Z", "loop": 4968, "env_steps": 3052953599, "loss": 0.02046731486916542, "avg_return": 0.8626115918159485, "regret": 0.0035982737317681313, "entropy": 0.10958652943372726, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:46.133122Z", "loop": 4969, "env_steps": 3053567999, "loss": 0.020019935443997383, "avg_return": 0.8606165051460266, "regret": 0.0035982737317681313, "entropy": 0.10678795725107193, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:47.028764Z", "loop": 4970, "env_steps": 3054182399, "loss": 0.019015386700630188, "avg_return": 0.8624866008758545, "regret": 0.0020339747425168753, "entropy": 0.10708156228065491, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:47.883342Z", "loop": 4971, "env_steps": 3054796799, "loss": 0.018277626484632492, "avg_return": 0.8614308834075928, "regret": 0.0020339747425168753, "entropy": 0.10523992776870728, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:48.737547Z", "loop": 4972, "env_steps": 3055411199, "loss": 0.0202134158462286, "avg_return": 0.8604189157485962, "regret": 0.0020339747425168753, "entropy": 0.10576111823320389, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:49.591609Z", "loop": 4973, "env_steps": 3056025599, "loss": 0.020082030445337296, "avg_return": 0.8609452247619629, "regret": 0.0020339747425168753, "entropy": 0.1103348508477211, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:50.445754Z", "loop": 4974, "env_steps": 3056639999, "loss": 0.01799429953098297, "avg_return": 0.8599012494087219, "regret": 0.0020339747425168753, "entropy": 0.1000877320766449, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:51.300632Z", "loop": 4975, "env_steps": 3057254399, "loss": 0.01843414269387722, "avg_return": 0.8593958020210266, "regret": 0.0020339747425168753, "entropy": 0.10418915003538132, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:52.155469Z", "loop": 4976, "env_steps": 3057868799, "loss": 0.017352042719721794, "avg_return": 0.8585747480392456, "regret": 0.0020339747425168753, "entropy": 0.10121328383684158, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:53.009978Z", "loop": 4977, "env_steps": 3058483199, "loss": 0.01769723743200302, "avg_return": 0.8617057204246521, "regret": 0.0020339747425168753, "entropy": 0.09930245578289032, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:53.864032Z", "loop": 4978, "env_steps": 3059097599, "loss": 0.019077587872743607, "avg_return": 0.8620033860206604, "regret": 0.0020339747425168753, "entropy": 0.10386915504932404, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:54.718483Z", "loop": 4979, "env_steps": 3059711999, "loss": 0.01692197285592556, "avg_return": 0.8621813058853149, "regret": 0.0020339747425168753, "entropy": 0.09505685418844223, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:55.612826Z", "loop": 4980, "env_steps": 3060326399, "loss": 0.01780334673821926, "avg_return": 0.8614213466644287, "regret": 0.0020962567068636417, "entropy": 0.0962350070476532, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:56.467503Z", "loop": 4981, "env_steps": 3060940799, "loss": 0.017920996993780136, "avg_return": 0.8614248037338257, "regret": 0.0020962567068636417, "entropy": 0.10088472813367844, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:57.320951Z", "loop": 4982, "env_steps": 3061555199, "loss": 0.017389951273798943, "avg_return": 0.8626587390899658, "regret": 0.0020962567068636417, "entropy": 0.09877409785985947, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:58.174881Z", "loop": 4983, "env_steps": 3062169599, "loss": 0.018328219652175903, "avg_return": 0.8619266152381897, "regret": 0.0020962567068636417, "entropy": 0.09931918978691101, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:59.028361Z", "loop": 4984, "env_steps": 3062783999, "loss": 0.017465880140662193, "avg_return": 0.8622965812683105, "regret": 0.0020962567068636417, "entropy": 0.09961888194084167, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:34:59.883446Z", "loop": 4985, "env_steps": 3063398399, "loss": 0.01835576817393303, "avg_return": 0.8622194528579712, "regret": 0.0020962567068636417, "entropy": 0.10106173157691956, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:00.737765Z", "loop": 4986, "env_steps": 3064012799, "loss": 0.017640452831983566, "avg_return": 0.8601576685905457, "regret": 0.0020962567068636417, "entropy": 0.10066692531108856, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:01.593983Z", "loop": 4987, "env_steps": 3064627199, "loss": 0.017721081152558327, "avg_return": 0.8600071668624878, "regret": 0.0020962567068636417, "entropy": 0.10064531862735748, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:02.448156Z", "loop": 4988, "env_steps": 3065241599, "loss": 0.018821028992533684, "avg_return": 0.8621834516525269, "regret": 0.0020962567068636417, "entropy": 0.10436887294054031, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:03.303635Z", "loop": 4989, "env_steps": 3065855999, "loss": 0.018413422629237175, "avg_return": 0.8601920008659363, "regret": 0.0020962567068636417, "entropy": 0.10225630551576614, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:04.198451Z", "loop": 4990, "env_steps": 3066470399, "loss": 0.0193480234593153, "avg_return": 0.8613462448120117, "regret": 0.0031276410445570946, "entropy": 0.10203784704208374, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:05.051835Z", "loop": 4991, "env_steps": 3067084799, "loss": 0.019106179475784302, "avg_return": 0.8610430955886841, "regret": 0.0031276410445570946, "entropy": 0.10415279865264893, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:05.905122Z", "loop": 4992, "env_steps": 3067699199, "loss": 0.01977596804499626, "avg_return": 0.8589485883712769, "regret": 0.0031276410445570946, "entropy": 0.10715556144714355, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:06.760267Z", "loop": 4993, "env_steps": 3068313599, "loss": 0.02022130973637104, "avg_return": 0.8589355945587158, "regret": 0.0031276410445570946, "entropy": 0.11655822396278381, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:07.614769Z", "loop": 4994, "env_steps": 3068927999, "loss": 0.019978519529104233, "avg_return": 0.8592987060546875, "regret": 0.0031276410445570946, "entropy": 0.1127399206161499, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:08.468160Z", "loop": 4995, "env_steps": 3069542399, "loss": 0.021000977605581284, "avg_return": 0.8586304783821106, "regret": 0.0031276410445570946, "entropy": 0.11588774621486664, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:09.323464Z", "loop": 4996, "env_steps": 3070156799, "loss": 0.02100026234984398, "avg_return": 0.856887936592102, "regret": 0.0031276410445570946, "entropy": 0.11167827248573303, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:10.179314Z", "loop": 4997, "env_steps": 3070771199, "loss": 0.02076081559062004, "avg_return": 0.8573018312454224, "regret": 0.0031276410445570946, "entropy": 0.11705446988344193, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:11.034189Z", "loop": 4998, "env_steps": 3071385599, "loss": 0.02147398516535759, "avg_return": 0.8577885031700134, "regret": 0.0031276410445570946, "entropy": 0.1156127005815506, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:11.889428Z", "loop": 4999, "env_steps": 3071999999, "loss": 0.01925116963684559, "avg_return": 0.858736515045166, "regret": 0.0031276410445570946, "entropy": 0.11006517708301544, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:12.787194Z", "loop": 5000, "env_steps": 3072614399, "loss": 0.019933925941586494, "avg_return": 0.858466386795044, "regret": 0.004287195857614279, "entropy": 0.10873015224933624, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:13.642159Z", "loop": 5001, "env_steps": 3073228799, "loss": 0.01993260346353054, "avg_return": 0.8599821329116821, "regret": 0.004287195857614279, "entropy": 0.11016648262739182, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:14.496500Z", "loop": 5002, "env_steps": 3073843199, "loss": 0.01983361504971981, "avg_return": 0.8606705665588379, "regret": 0.004287195857614279, "entropy": 0.11510385572910309, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:15.351495Z", "loop": 5003, "env_steps": 3074457599, "loss": 0.021330637857317924, "avg_return": 0.8599090576171875, "regret": 0.004287195857614279, "entropy": 0.11475162953138351, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:16.206208Z", "loop": 5004, "env_steps": 3075071999, "loss": 0.020933134481310844, "avg_return": 0.8600494861602783, "regret": 0.004287195857614279, "entropy": 0.11678707599639893, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:17.061355Z", "loop": 5005, "env_steps": 3075686399, "loss": 0.021264873445034027, "avg_return": 0.8587597608566284, "regret": 0.004287195857614279, "entropy": 0.1178915873169899, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:17.916553Z", "loop": 5006, "env_steps": 3076300799, "loss": 0.023035570979118347, "avg_return": 0.8582471013069153, "regret": 0.004287195857614279, "entropy": 0.12669630348682404, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:18.771517Z", "loop": 5007, "env_steps": 3076915199, "loss": 0.022853946313261986, "avg_return": 0.858873724937439, "regret": 0.004287195857614279, "entropy": 0.12698809802532196, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:19.626996Z", "loop": 5008, "env_steps": 3077529599, "loss": 0.023535026237368584, "avg_return": 0.8576756119728088, "regret": 0.004287195857614279, "entropy": 0.12590806186199188, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:20.481191Z", "loop": 5009, "env_steps": 3078143999, "loss": 0.024271830916404724, "avg_return": 0.8573010563850403, "regret": 0.004287195857614279, "entropy": 0.13258571922779083, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:21.374324Z", "loop": 5010, "env_steps": 3078758399, "loss": 0.024750811979174614, "avg_return": 0.8574729561805725, "regret": 0.006057970225811005, "entropy": 0.1323998123407364, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:22.227674Z", "loop": 5011, "env_steps": 3079372799, "loss": 0.02364303730428219, "avg_return": 0.8580006957054138, "regret": 0.006057970225811005, "entropy": 0.1327645182609558, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:23.082261Z", "loop": 5012, "env_steps": 3079987199, "loss": 0.023238571360707283, "avg_return": 0.8595564961433411, "regret": 0.006057970225811005, "entropy": 0.13505636155605316, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:23.936578Z", "loop": 5013, "env_steps": 3080601599, "loss": 0.02501768246293068, "avg_return": 0.8594165444374084, "regret": 0.006057970225811005, "entropy": 0.14394399523735046, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:24.789882Z", "loop": 5014, "env_steps": 3081215999, "loss": 0.02512642741203308, "avg_return": 0.8586245179176331, "regret": 0.006057970225811005, "entropy": 0.14168787002563477, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:25.643554Z", "loop": 5015, "env_steps": 3081830399, "loss": 0.028037061914801598, "avg_return": 0.8547429442405701, "regret": 0.006057970225811005, "entropy": 0.16123011708259583, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:26.499973Z", "loop": 5016, "env_steps": 3082444799, "loss": 0.031059300526976585, "avg_return": 0.8512045741081238, "regret": 0.006057970225811005, "entropy": 0.17119623720645905, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:27.354221Z", "loop": 5017, "env_steps": 3083059199, "loss": 0.030903667211532593, "avg_return": 0.8506606221199036, "regret": 0.006057970225811005, "entropy": 0.17311377823352814, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:28.207548Z", "loop": 5018, "env_steps": 3083673599, "loss": 0.030741611495614052, "avg_return": 0.8538810610771179, "regret": 0.006057970225811005, "entropy": 0.17097540199756622, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:29.060725Z", "loop": 5019, "env_steps": 3084287999, "loss": 0.02903716079890728, "avg_return": 0.857996940612793, "regret": 0.006057970225811005, "entropy": 0.1572863757610321, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:29.955358Z", "loop": 5020, "env_steps": 3084902399, "loss": 0.024944037199020386, "avg_return": 0.8575012683868408, "regret": 0.004331971984356642, "entropy": 0.1411392092704773, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:30.809426Z", "loop": 5021, "env_steps": 3085516799, "loss": 0.023351358249783516, "avg_return": 0.8595839738845825, "regret": 0.004331971984356642, "entropy": 0.1318502426147461, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:31.662920Z", "loop": 5022, "env_steps": 3086131199, "loss": 0.02348906919360161, "avg_return": 0.8604960441589355, "regret": 0.004331971984356642, "entropy": 0.1235489770770073, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:32.516287Z", "loop": 5023, "env_steps": 3086745599, "loss": 0.02182837389409542, "avg_return": 0.8618178367614746, "regret": 0.004331971984356642, "entropy": 0.12153996527194977, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:33.369826Z", "loop": 5024, "env_steps": 3087359999, "loss": 0.020773332566022873, "avg_return": 0.8611018061637878, "regret": 0.004331971984356642, "entropy": 0.1139686182141304, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:34.224295Z", "loop": 5025, "env_steps": 3087974399, "loss": 0.01958019845187664, "avg_return": 0.8629967570304871, "regret": 0.004331971984356642, "entropy": 0.10285346955060959, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:35.078052Z", "loop": 5026, "env_steps": 3088588799, "loss": 0.018718859180808067, "avg_return": 0.8623415231704712, "regret": 0.004331971984356642, "entropy": 0.10341576486825943, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:35.931363Z", "loop": 5027, "env_steps": 3089203199, "loss": 0.01918507181107998, "avg_return": 0.86136794090271, "regret": 0.004331971984356642, "entropy": 0.10432275384664536, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:36.786089Z", "loop": 5028, "env_steps": 3089817599, "loss": 0.018860427662730217, "avg_return": 0.8617161512374878, "regret": 0.004331971984356642, "entropy": 0.09809093177318573, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:37.640692Z", "loop": 5029, "env_steps": 3090431999, "loss": 0.01824093982577324, "avg_return": 0.8603106141090393, "regret": 0.004331971984356642, "entropy": 0.10331646353006363, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:38.536415Z", "loop": 5030, "env_steps": 3091046399, "loss": 0.017209915444254875, "avg_return": 0.8610915541648865, "regret": 0.002085944404825568, "entropy": 0.09962620586156845, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:39.390885Z", "loop": 5031, "env_steps": 3091660799, "loss": 0.017110582441091537, "avg_return": 0.8623111248016357, "regret": 0.002085944404825568, "entropy": 0.09818439930677414, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:40.245279Z", "loop": 5032, "env_steps": 3092275199, "loss": 0.017833620309829712, "avg_return": 0.8617120385169983, "regret": 0.002085944404825568, "entropy": 0.09820584207773209, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:41.100014Z", "loop": 5033, "env_steps": 3092889599, "loss": 0.019320426508784294, "avg_return": 0.8608970046043396, "regret": 0.002085944404825568, "entropy": 0.1058313250541687, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:41.954764Z", "loop": 5034, "env_steps": 3093503999, "loss": 0.019585920497775078, "avg_return": 0.8602870106697083, "regret": 0.002085944404825568, "entropy": 0.10898245871067047, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:42.809322Z", "loop": 5035, "env_steps": 3094118399, "loss": 0.02083502523601055, "avg_return": 0.8581279516220093, "regret": 0.002085944404825568, "entropy": 0.11448150128126144, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:43.664046Z", "loop": 5036, "env_steps": 3094732799, "loss": 0.020360058173537254, "avg_return": 0.8580369353294373, "regret": 0.002085944404825568, "entropy": 0.10939204692840576, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:44.519010Z", "loop": 5037, "env_steps": 3095347199, "loss": 0.020548611879348755, "avg_return": 0.857018232345581, "regret": 0.002085944404825568, "entropy": 0.11042223870754242, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:45.374059Z", "loop": 5038, "env_steps": 3095961599, "loss": 0.018771274015307426, "avg_return": 0.8606165051460266, "regret": 0.002085944404825568, "entropy": 0.10815609246492386, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:46.227719Z", "loop": 5039, "env_steps": 3096575999, "loss": 0.0182478129863739, "avg_return": 0.8609509468078613, "regret": 0.002085944404825568, "entropy": 0.10144536197185516, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:47.120730Z", "loop": 5040, "env_steps": 3097190399, "loss": 0.0172889307141304, "avg_return": 0.8616812229156494, "regret": 0.002238800283521414, "entropy": 0.10031413286924362, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:47.974239Z", "loop": 5041, "env_steps": 3097804799, "loss": 0.018171897158026695, "avg_return": 0.8593735694885254, "regret": 0.002238800283521414, "entropy": 0.10239370167255402, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:48.827714Z", "loop": 5042, "env_steps": 3098419199, "loss": 0.018502775579690933, "avg_return": 0.8596735000610352, "regret": 0.002238800283521414, "entropy": 0.1000899150967598, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:49.682535Z", "loop": 5043, "env_steps": 3099033599, "loss": 0.018794385716319084, "avg_return": 0.8597806096076965, "regret": 0.002238800283521414, "entropy": 0.10417863726615906, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:50.537914Z", "loop": 5044, "env_steps": 3099647999, "loss": 0.02055002562701702, "avg_return": 0.8583447337150574, "regret": 0.002238800283521414, "entropy": 0.1124875396490097, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:51.392703Z", "loop": 5045, "env_steps": 3100262399, "loss": 0.02079099416732788, "avg_return": 0.8554201722145081, "regret": 0.002238800283521414, "entropy": 0.10926011949777603, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:52.246309Z", "loop": 5046, "env_steps": 3100876799, "loss": 0.020043661817908287, "avg_return": 0.8558436036109924, "regret": 0.002238800283521414, "entropy": 0.10899226367473602, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:53.100849Z", "loop": 5047, "env_steps": 3101491199, "loss": 0.02016664296388626, "avg_return": 0.8586026430130005, "regret": 0.002238800283521414, "entropy": 0.1079687550663948, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:53.955661Z", "loop": 5048, "env_steps": 3102105599, "loss": 0.01920301653444767, "avg_return": 0.8587151169776917, "regret": 0.002238800283521414, "entropy": 0.10465754568576813, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:54.809807Z", "loop": 5049, "env_steps": 3102719999, "loss": 0.01929296739399433, "avg_return": 0.8609090447425842, "regret": 0.002238800283521414, "entropy": 0.1068912222981453, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:55.705780Z", "loop": 5050, "env_steps": 3103334399, "loss": 0.020221158862113953, "avg_return": 0.8601351380348206, "regret": 0.0032070777378976345, "entropy": 0.11073601245880127, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:56.558638Z", "loop": 5051, "env_steps": 3103948799, "loss": 0.019825052469968796, "avg_return": 0.8609960079193115, "regret": 0.0032070777378976345, "entropy": 0.11069998890161514, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:57.412983Z", "loop": 5052, "env_steps": 3104563199, "loss": 0.019271038472652435, "avg_return": 0.8606830835342407, "regret": 0.0032070777378976345, "entropy": 0.10933390259742737, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:58.267135Z", "loop": 5053, "env_steps": 3105177599, "loss": 0.01982784830033779, "avg_return": 0.8597530126571655, "regret": 0.0032070777378976345, "entropy": 0.11098368465900421, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:59.121525Z", "loop": 5054, "env_steps": 3105791999, "loss": 0.018951455131173134, "avg_return": 0.8606616258621216, "regret": 0.0032070777378976345, "entropy": 0.10737217962741852, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:35:59.976291Z", "loop": 5055, "env_steps": 3106406399, "loss": 0.020297683775424957, "avg_return": 0.8619517087936401, "regret": 0.0032070777378976345, "entropy": 0.11370716243982315, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:00.832004Z", "loop": 5056, "env_steps": 3107020799, "loss": 0.020439548417925835, "avg_return": 0.8602904677391052, "regret": 0.0032070777378976345, "entropy": 0.11326728761196136, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:01.686100Z", "loop": 5057, "env_steps": 3107635199, "loss": 0.020321588963270187, "avg_return": 0.862464427947998, "regret": 0.0032070777378976345, "entropy": 0.11222951859235764, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:02.540833Z", "loop": 5058, "env_steps": 3108249599, "loss": 0.020189857110381126, "avg_return": 0.8611890077590942, "regret": 0.0032070777378976345, "entropy": 0.11368346214294434, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:03.394795Z", "loop": 5059, "env_steps": 3108863999, "loss": 0.02039911411702633, "avg_return": 0.8604639768600464, "regret": 0.0032070777378976345, "entropy": 0.11235189437866211, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:04.287956Z", "loop": 5060, "env_steps": 3109478399, "loss": 0.019986096769571304, "avg_return": 0.8623053431510925, "regret": 0.002452491084113717, "entropy": 0.1113353818655014, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:05.141618Z", "loop": 5061, "env_steps": 3110092799, "loss": 0.01827072538435459, "avg_return": 0.8606404662132263, "regret": 0.002452491084113717, "entropy": 0.10846155136823654, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:05.997056Z", "loop": 5062, "env_steps": 3110707199, "loss": 0.019791362807154655, "avg_return": 0.8619358539581299, "regret": 0.002452491084113717, "entropy": 0.11625697463750839, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:06.852333Z", "loop": 5063, "env_steps": 3111321599, "loss": 0.020110998302698135, "avg_return": 0.8616738319396973, "regret": 0.002452491084113717, "entropy": 0.11110229790210724, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:07.707461Z", "loop": 5064, "env_steps": 3111935999, "loss": 0.01847757212817669, "avg_return": 0.8614304065704346, "regret": 0.002452491084113717, "entropy": 0.10632248967885971, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:08.563776Z", "loop": 5065, "env_steps": 3112550399, "loss": 0.018550969660282135, "avg_return": 0.8614685535430908, "regret": 0.002452491084113717, "entropy": 0.10519753396511078, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:09.419057Z", "loop": 5066, "env_steps": 3113164799, "loss": 0.020109616219997406, "avg_return": 0.8621022701263428, "regret": 0.002452491084113717, "entropy": 0.1132727861404419, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:10.275193Z", "loop": 5067, "env_steps": 3113779199, "loss": 0.019519444555044174, "avg_return": 0.8624379634857178, "regret": 0.002452491084113717, "entropy": 0.10811404883861542, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:11.129374Z", "loop": 5068, "env_steps": 3114393599, "loss": 0.020011644810438156, "avg_return": 0.8617358803749084, "regret": 0.002452491084113717, "entropy": 0.10982801765203476, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:11.983132Z", "loop": 5069, "env_steps": 3115007999, "loss": 0.020261995494365692, "avg_return": 0.8615615963935852, "regret": 0.002452491084113717, "entropy": 0.11278234422206879, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:12.878036Z", "loop": 5070, "env_steps": 3115622399, "loss": 0.02017182670533657, "avg_return": 0.861833930015564, "regret": 0.002405276522040367, "entropy": 0.11061018705368042, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:13.732858Z", "loop": 5071, "env_steps": 3116236799, "loss": 0.018782811239361763, "avg_return": 0.8616666793823242, "regret": 0.002405276522040367, "entropy": 0.10737262666225433, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:14.586398Z", "loop": 5072, "env_steps": 3116851199, "loss": 0.020566390827298164, "avg_return": 0.8599607348442078, "regret": 0.002405276522040367, "entropy": 0.10965938121080399, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:15.439227Z", "loop": 5073, "env_steps": 3117465599, "loss": 0.019715558737516403, "avg_return": 0.8612325191497803, "regret": 0.002405276522040367, "entropy": 0.1091829165816307, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:16.292241Z", "loop": 5074, "env_steps": 3118079999, "loss": 0.019853565841913223, "avg_return": 0.8620347380638123, "regret": 0.002405276522040367, "entropy": 0.10695110261440277, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:17.147172Z", "loop": 5075, "env_steps": 3118694399, "loss": 0.018874764442443848, "avg_return": 0.8597082495689392, "regret": 0.002405276522040367, "entropy": 0.10754187405109406, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:18.001218Z", "loop": 5076, "env_steps": 3119308799, "loss": 0.020228026434779167, "avg_return": 0.8627617359161377, "regret": 0.002405276522040367, "entropy": 0.11003553122282028, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:18.854360Z", "loop": 5077, "env_steps": 3119923199, "loss": 0.01961681619286537, "avg_return": 0.8616748452186584, "regret": 0.002405276522040367, "entropy": 0.10997433215379715, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:19.707684Z", "loop": 5078, "env_steps": 3120537599, "loss": 0.021316103637218475, "avg_return": 0.8593601584434509, "regret": 0.002405276522040367, "entropy": 0.11342710256576538, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:20.561683Z", "loop": 5079, "env_steps": 3121151999, "loss": 0.020016981288790703, "avg_return": 0.8616281151771545, "regret": 0.002405276522040367, "entropy": 0.1082664281129837, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:21.456223Z", "loop": 5080, "env_steps": 3121766399, "loss": 0.020175885409116745, "avg_return": 0.858995795249939, "regret": 0.0044103660620749, "entropy": 0.10693089663982391, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:22.308963Z", "loop": 5081, "env_steps": 3122380799, "loss": 0.022756334394216537, "avg_return": 0.8600954413414001, "regret": 0.0044103660620749, "entropy": 0.11746955662965775, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:23.161100Z", "loop": 5082, "env_steps": 3122995199, "loss": 0.01945752464234829, "avg_return": 0.85953289270401, "regret": 0.0044103660620749, "entropy": 0.11200250685214996, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:24.013808Z", "loop": 5083, "env_steps": 3123609599, "loss": 0.018994025886058807, "avg_return": 0.8605290055274963, "regret": 0.0044103660620749, "entropy": 0.1098865270614624, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:24.867507Z", "loop": 5084, "env_steps": 3124223999, "loss": 0.018767789006233215, "avg_return": 0.8620351552963257, "regret": 0.0044103660620749, "entropy": 0.11089201271533966, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:25.720840Z", "loop": 5085, "env_steps": 3124838399, "loss": 0.02077874355018139, "avg_return": 0.8617612719535828, "regret": 0.0044103660620749, "entropy": 0.11867028474807739, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:26.574180Z", "loop": 5086, "env_steps": 3125452799, "loss": 0.01981632597744465, "avg_return": 0.8605553507804871, "regret": 0.0044103660620749, "entropy": 0.1176355630159378, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:27.429478Z", "loop": 5087, "env_steps": 3126067199, "loss": 0.02401164546608925, "avg_return": 0.8599117398262024, "regret": 0.0044103660620749, "entropy": 0.12935954332351685, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:28.282998Z", "loop": 5088, "env_steps": 3126681599, "loss": 0.022808482870459557, "avg_return": 0.8598480224609375, "regret": 0.0044103660620749, "entropy": 0.13023871183395386, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:29.137042Z", "loop": 5089, "env_steps": 3127295999, "loss": 0.023712491616606712, "avg_return": 0.8570103049278259, "regret": 0.0044103660620749, "entropy": 0.1327236443758011, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:30.030623Z", "loop": 5090, "env_steps": 3127910399, "loss": 0.023694854229688644, "avg_return": 0.8576195240020752, "regret": 0.007341325748711824, "entropy": 0.1357414275407791, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:30.883727Z", "loop": 5091, "env_steps": 3128524799, "loss": 0.022824421525001526, "avg_return": 0.8586298823356628, "regret": 0.007341325748711824, "entropy": 0.1322251260280609, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:31.737513Z", "loop": 5092, "env_steps": 3129139199, "loss": 0.024103617295622826, "avg_return": 0.8601917624473572, "regret": 0.007341325748711824, "entropy": 0.1323731243610382, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:32.591359Z", "loop": 5093, "env_steps": 3129753599, "loss": 0.022955110296607018, "avg_return": 0.8601181507110596, "regret": 0.007341325748711824, "entropy": 0.129050612449646, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:33.445604Z", "loop": 5094, "env_steps": 3130367999, "loss": 0.02102363109588623, "avg_return": 0.8609178066253662, "regret": 0.007341325748711824, "entropy": 0.12337559461593628, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:34.298833Z", "loop": 5095, "env_steps": 3130982399, "loss": 0.020019887015223503, "avg_return": 0.861487865447998, "regret": 0.007341325748711824, "entropy": 0.11367694288492203, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:35.151450Z", "loop": 5096, "env_steps": 3131596799, "loss": 0.020509444177150726, "avg_return": 0.8598828315734863, "regret": 0.007341325748711824, "entropy": 0.11646996438503265, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:36.005227Z", "loop": 5097, "env_steps": 3132211199, "loss": 0.01958465948700905, "avg_return": 0.8591544032096863, "regret": 0.007341325748711824, "entropy": 0.11114728450775146, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:36.859345Z", "loop": 5098, "env_steps": 3132825599, "loss": 0.02051214873790741, "avg_return": 0.8593218922615051, "regret": 0.007341325748711824, "entropy": 0.11041247099637985, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:37.713394Z", "loop": 5099, "env_steps": 3133439999, "loss": 0.022033384069800377, "avg_return": 0.8593040108680725, "regret": 0.007341325748711824, "entropy": 0.1132267490029335, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:38.605987Z", "loop": 5100, "env_steps": 3134054399, "loss": 0.0193472933024168, "avg_return": 0.8603577613830566, "regret": 0.003957265056669712, "entropy": 0.10856974869966507, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:39.458796Z", "loop": 5101, "env_steps": 3134668799, "loss": 0.019889352843165398, "avg_return": 0.859012246131897, "regret": 0.003957265056669712, "entropy": 0.11006961017847061, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:40.315194Z", "loop": 5102, "env_steps": 3135283199, "loss": 0.019184477627277374, "avg_return": 0.8613969087600708, "regret": 0.003957265056669712, "entropy": 0.10372848808765411, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:41.169498Z", "loop": 5103, "env_steps": 3135897599, "loss": 0.018284453079104424, "avg_return": 0.8600319623947144, "regret": 0.003957265056669712, "entropy": 0.10226010531187057, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:42.024390Z", "loop": 5104, "env_steps": 3136511999, "loss": 0.02000335231423378, "avg_return": 0.8607694506645203, "regret": 0.003957265056669712, "entropy": 0.10810733586549759, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:42.879518Z", "loop": 5105, "env_steps": 3137126399, "loss": 0.020015612244606018, "avg_return": 0.8607825040817261, "regret": 0.003957265056669712, "entropy": 0.11005406826734543, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:43.734640Z", "loop": 5106, "env_steps": 3137740799, "loss": 0.019475309178233147, "avg_return": 0.8614147901535034, "regret": 0.003957265056669712, "entropy": 0.10598992556333542, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:44.588603Z", "loop": 5107, "env_steps": 3138355199, "loss": 0.017522694543004036, "avg_return": 0.8620102405548096, "regret": 0.003957265056669712, "entropy": 0.1032576933503151, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:45.442845Z", "loop": 5108, "env_steps": 3138969599, "loss": 0.020636852830648422, "avg_return": 0.860353946685791, "regret": 0.003957265056669712, "entropy": 0.10993080586194992, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:46.297638Z", "loop": 5109, "env_steps": 3139583999, "loss": 0.019916314631700516, "avg_return": 0.8590186834335327, "regret": 0.003957265056669712, "entropy": 0.11177823692560196, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:47.193397Z", "loop": 5110, "env_steps": 3140198399, "loss": 0.02071632817387581, "avg_return": 0.8578241467475891, "regret": 0.005764493253082037, "entropy": 0.11429653316736221, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:48.048491Z", "loop": 5111, "env_steps": 3140812799, "loss": 0.022925294935703278, "avg_return": 0.8533707857131958, "regret": 0.005764493253082037, "entropy": 0.12430457770824432, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:48.903640Z", "loop": 5112, "env_steps": 3141427199, "loss": 0.022733524441719055, "avg_return": 0.8536696434020996, "regret": 0.005764493253082037, "entropy": 0.12207982689142227, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:49.758729Z", "loop": 5113, "env_steps": 3142041599, "loss": 0.022474313154816628, "avg_return": 0.8567495942115784, "regret": 0.005764493253082037, "entropy": 0.12106892466545105, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:50.614685Z", "loop": 5114, "env_steps": 3142655999, "loss": 0.018691839650273323, "avg_return": 0.859955370426178, "regret": 0.005764493253082037, "entropy": 0.11300555616617203, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:51.470155Z", "loop": 5115, "env_steps": 3143270399, "loss": 0.019649170339107513, "avg_return": 0.8609471917152405, "regret": 0.005764493253082037, "entropy": 0.1125413328409195, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:52.324944Z", "loop": 5116, "env_steps": 3143884799, "loss": 0.01817113347351551, "avg_return": 0.8619760274887085, "regret": 0.005764493253082037, "entropy": 0.10332798957824707, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:53.179498Z", "loop": 5117, "env_steps": 3144499199, "loss": 0.019372394308447838, "avg_return": 0.8607686758041382, "regret": 0.005764493253082037, "entropy": 0.1020449548959732, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:54.035115Z", "loop": 5118, "env_steps": 3145113599, "loss": 0.017735041677951813, "avg_return": 0.8618801236152649, "regret": 0.005764493253082037, "entropy": 0.09812161326408386, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:54.888631Z", "loop": 5119, "env_steps": 3145727999, "loss": 0.018641537055373192, "avg_return": 0.8618280291557312, "regret": 0.005764493253082037, "entropy": 0.10842696577310562, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:55.782521Z", "loop": 5120, "env_steps": 3146342399, "loss": 0.019250376150012016, "avg_return": 0.8609684705734253, "regret": 0.001891855150461197, "entropy": 0.10310761630535126, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:56.636262Z", "loop": 5121, "env_steps": 3146956799, "loss": 0.01815955899655819, "avg_return": 0.8601152896881104, "regret": 0.001891855150461197, "entropy": 0.10633262246847153, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:57.491425Z", "loop": 5122, "env_steps": 3147571199, "loss": 0.018614545464515686, "avg_return": 0.8611999750137329, "regret": 0.001891855150461197, "entropy": 0.10661276429891586, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:58.345044Z", "loop": 5123, "env_steps": 3148185599, "loss": 0.01995885744690895, "avg_return": 0.86174076795578, "regret": 0.001891855150461197, "entropy": 0.10714682191610336, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:36:59.199669Z", "loop": 5124, "env_steps": 3148799999, "loss": 0.017848536372184753, "avg_return": 0.8618378043174744, "regret": 0.001891855150461197, "entropy": 0.10439720749855042, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:00.053921Z", "loop": 5125, "env_steps": 3149414399, "loss": 0.019915947690606117, "avg_return": 0.8622257709503174, "regret": 0.001891855150461197, "entropy": 0.10641062259674072, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:00.908712Z", "loop": 5126, "env_steps": 3150028799, "loss": 0.018460337072610855, "avg_return": 0.8618309497833252, "regret": 0.001891855150461197, "entropy": 0.10100121796131134, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:01.761532Z", "loop": 5127, "env_steps": 3150643199, "loss": 0.019866475835442543, "avg_return": 0.8616066575050354, "regret": 0.001891855150461197, "entropy": 0.1070479080080986, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:02.615315Z", "loop": 5128, "env_steps": 3151257599, "loss": 0.020614339038729668, "avg_return": 0.8615739345550537, "regret": 0.001891855150461197, "entropy": 0.11103123426437378, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:03.469892Z", "loop": 5129, "env_steps": 3151871999, "loss": 0.019087834283709526, "avg_return": 0.8614910840988159, "regret": 0.001891855150461197, "entropy": 0.10824549943208694, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:04.365277Z", "loop": 5130, "env_steps": 3152486399, "loss": 0.019958246499300003, "avg_return": 0.8613401651382446, "regret": 0.0024222631473094225, "entropy": 0.10863477736711502, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:05.219252Z", "loop": 5131, "env_steps": 3153100799, "loss": 0.02051650919020176, "avg_return": 0.8594399094581604, "regret": 0.0024222631473094225, "entropy": 0.10754884034395218, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:06.072979Z", "loop": 5132, "env_steps": 3153715199, "loss": 0.02110864967107773, "avg_return": 0.8595179319381714, "regret": 0.0024222631473094225, "entropy": 0.11385120451450348, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:06.927057Z", "loop": 5133, "env_steps": 3154329599, "loss": 0.020840266719460487, "avg_return": 0.8610266447067261, "regret": 0.0024222631473094225, "entropy": 0.11091482639312744, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:07.781739Z", "loop": 5134, "env_steps": 3154943999, "loss": 0.01962059549987316, "avg_return": 0.8598580956459045, "regret": 0.0024222631473094225, "entropy": 0.11493019014596939, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:08.637022Z", "loop": 5135, "env_steps": 3155558399, "loss": 0.0204202588647604, "avg_return": 0.8612706661224365, "regret": 0.0024222631473094225, "entropy": 0.11417502164840698, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:09.490838Z", "loop": 5136, "env_steps": 3156172799, "loss": 0.02080150507390499, "avg_return": 0.8611765503883362, "regret": 0.0024222631473094225, "entropy": 0.11065573245286942, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:10.344256Z", "loop": 5137, "env_steps": 3156787199, "loss": 0.01863170973956585, "avg_return": 0.8603755831718445, "regret": 0.0024222631473094225, "entropy": 0.10300958156585693, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:11.198738Z", "loop": 5138, "env_steps": 3157401599, "loss": 0.019891615957021713, "avg_return": 0.860777735710144, "regret": 0.0024222631473094225, "entropy": 0.11154939234256744, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:12.052948Z", "loop": 5139, "env_steps": 3158015999, "loss": 0.020793896168470383, "avg_return": 0.8613069653511047, "regret": 0.0024222631473094225, "entropy": 0.11451447010040283, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:12.948141Z", "loop": 5140, "env_steps": 3158630399, "loss": 0.020829500630497932, "avg_return": 0.8605835437774658, "regret": 0.002406761283054948, "entropy": 0.11380987614393234, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:13.801882Z", "loop": 5141, "env_steps": 3159244799, "loss": 0.019084451720118523, "avg_return": 0.8612469434738159, "regret": 0.002406761283054948, "entropy": 0.10910746455192566, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:14.656275Z", "loop": 5142, "env_steps": 3159859199, "loss": 0.01974339596927166, "avg_return": 0.8619911074638367, "regret": 0.002406761283054948, "entropy": 0.11124254763126373, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:15.511354Z", "loop": 5143, "env_steps": 3160473599, "loss": 0.020270980894565582, "avg_return": 0.8596998453140259, "regret": 0.002406761283054948, "entropy": 0.1093367263674736, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:16.364927Z", "loop": 5144, "env_steps": 3161087999, "loss": 0.019592411816120148, "avg_return": 0.8615424036979675, "regret": 0.002406761283054948, "entropy": 0.10882224887609482, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:17.218931Z", "loop": 5145, "env_steps": 3161702399, "loss": 0.018735142424702644, "avg_return": 0.8625181317329407, "regret": 0.002406761283054948, "entropy": 0.11092611402273178, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:18.072407Z", "loop": 5146, "env_steps": 3162316799, "loss": 0.02075691521167755, "avg_return": 0.8622305393218994, "regret": 0.002406761283054948, "entropy": 0.11405142396688461, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:18.925482Z", "loop": 5147, "env_steps": 3162931199, "loss": 0.017917843535542488, "avg_return": 0.8630946278572083, "regret": 0.002406761283054948, "entropy": 0.1046907976269722, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:19.779426Z", "loop": 5148, "env_steps": 3163545599, "loss": 0.019041363149881363, "avg_return": 0.8617822527885437, "regret": 0.002406761283054948, "entropy": 0.10760217905044556, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:20.633148Z", "loop": 5149, "env_steps": 3164159999, "loss": 0.018539050593972206, "avg_return": 0.861442506313324, "regret": 0.002406761283054948, "entropy": 0.10572846978902817, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:21.526512Z", "loop": 5150, "env_steps": 3164774399, "loss": 0.018940282985568047, "avg_return": 0.8620580434799194, "regret": 0.0014903424307703972, "entropy": 0.11088783293962479, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:22.381868Z", "loop": 5151, "env_steps": 3165388799, "loss": 0.02055962197482586, "avg_return": 0.8632168769836426, "regret": 0.0014903424307703972, "entropy": 0.10751203447580338, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:23.236030Z", "loop": 5152, "env_steps": 3166003199, "loss": 0.019795319065451622, "avg_return": 0.8609097599983215, "regret": 0.0014903424307703972, "entropy": 0.10960393399000168, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:24.091655Z", "loop": 5153, "env_steps": 3166617599, "loss": 0.019828272983431816, "avg_return": 0.8613629341125488, "regret": 0.0014903424307703972, "entropy": 0.11303798854351044, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:24.945316Z", "loop": 5154, "env_steps": 3167231999, "loss": 0.02176782302558422, "avg_return": 0.8621479272842407, "regret": 0.0014903424307703972, "entropy": 0.1205424815416336, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:25.798362Z", "loop": 5155, "env_steps": 3167846399, "loss": 0.021325288340449333, "avg_return": 0.8607692718505859, "regret": 0.0014903424307703972, "entropy": 0.11766643822193146, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:26.651607Z", "loop": 5156, "env_steps": 3168460799, "loss": 0.022803014144301414, "avg_return": 0.8614146113395691, "regret": 0.0014903424307703972, "entropy": 0.12941974401474, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:27.506456Z", "loop": 5157, "env_steps": 3169075199, "loss": 0.02348637394607067, "avg_return": 0.8597998023033142, "regret": 0.0014903424307703972, "entropy": 0.13652189075946808, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:28.360768Z", "loop": 5158, "env_steps": 3169689599, "loss": 0.026919817551970482, "avg_return": 0.8579999804496765, "regret": 0.0014903424307703972, "entropy": 0.14625711739063263, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:29.213775Z", "loop": 5159, "env_steps": 3170303999, "loss": 0.027240360155701637, "avg_return": 0.8573958277702332, "regret": 0.0014903424307703972, "entropy": 0.14905501902103424, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:30.108195Z", "loop": 5160, "env_steps": 3170918399, "loss": 0.025181306526064873, "avg_return": 0.8557659983634949, "regret": 0.006804260425269604, "entropy": 0.14327377080917358, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:30.963349Z", "loop": 5161, "env_steps": 3171532799, "loss": 0.025196025148034096, "avg_return": 0.8568640351295471, "regret": 0.006804260425269604, "entropy": 0.14508403837680817, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:31.816239Z", "loop": 5162, "env_steps": 3172147199, "loss": 0.02293284423649311, "avg_return": 0.8599090576171875, "regret": 0.006804260425269604, "entropy": 0.13317309319972992, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:32.669593Z", "loop": 5163, "env_steps": 3172761599, "loss": 0.02413990907371044, "avg_return": 0.8604547381401062, "regret": 0.006804260425269604, "entropy": 0.12760776281356812, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:33.523751Z", "loop": 5164, "env_steps": 3173375999, "loss": 0.022045886144042015, "avg_return": 0.8614882826805115, "regret": 0.006804260425269604, "entropy": 0.12430223822593689, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:34.378310Z", "loop": 5165, "env_steps": 3173990399, "loss": 0.020027397200465202, "avg_return": 0.8605107665061951, "regret": 0.006804260425269604, "entropy": 0.11728242039680481, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:35.232448Z", "loop": 5166, "env_steps": 3174604799, "loss": 0.019934460520744324, "avg_return": 0.8621509075164795, "regret": 0.006804260425269604, "entropy": 0.10925442725419998, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:36.086673Z", "loop": 5167, "env_steps": 3175219199, "loss": 0.020007025450468063, "avg_return": 0.8605139255523682, "regret": 0.006804260425269604, "entropy": 0.10865908861160278, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:36.941556Z", "loop": 5168, "env_steps": 3175833599, "loss": 0.018690530210733414, "avg_return": 0.861426830291748, "regret": 0.006804260425269604, "entropy": 0.10496991872787476, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:37.795555Z", "loop": 5169, "env_steps": 3176447999, "loss": 0.01967177353799343, "avg_return": 0.8617439866065979, "regret": 0.006804260425269604, "entropy": 0.10501431673765182, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:38.690013Z", "loop": 5170, "env_steps": 3177062399, "loss": 0.017671940848231316, "avg_return": 0.8619493842124939, "regret": 0.001630099955946207, "entropy": 0.10024155676364899, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:39.544046Z", "loop": 5171, "env_steps": 3177676799, "loss": 0.019259870052337646, "avg_return": 0.8617130517959595, "regret": 0.001630099955946207, "entropy": 0.10627587139606476, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:40.398774Z", "loop": 5172, "env_steps": 3178291199, "loss": 0.018917066976428032, "avg_return": 0.8628559708595276, "regret": 0.001630099955946207, "entropy": 0.10328175872564316, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:41.253066Z", "loop": 5173, "env_steps": 3178905599, "loss": 0.01766619272530079, "avg_return": 0.8616899847984314, "regret": 0.001630099955946207, "entropy": 0.10147830843925476, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:42.107880Z", "loop": 5174, "env_steps": 3179519999, "loss": 0.01790647767484188, "avg_return": 0.862189769744873, "regret": 0.001630099955946207, "entropy": 0.0991259515285492, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:42.961743Z", "loop": 5175, "env_steps": 3180134399, "loss": 0.01924235001206398, "avg_return": 0.8601922988891602, "regret": 0.001630099955946207, "entropy": 0.10696911066770554, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:43.816302Z", "loop": 5176, "env_steps": 3180748799, "loss": 0.020230742171406746, "avg_return": 0.8605320453643799, "regret": 0.001630099955946207, "entropy": 0.11177491396665573, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:44.668781Z", "loop": 5177, "env_steps": 3181363199, "loss": 0.018560856580734253, "avg_return": 0.8603910803794861, "regret": 0.001630099955946207, "entropy": 0.10310328006744385, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:45.522173Z", "loop": 5178, "env_steps": 3181977599, "loss": 0.01963319070637226, "avg_return": 0.8603911399841309, "regret": 0.001630099955946207, "entropy": 0.11085536330938339, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:46.376388Z", "loop": 5179, "env_steps": 3182591999, "loss": 0.019622093066573143, "avg_return": 0.8603123426437378, "regret": 0.001630099955946207, "entropy": 0.10955625027418137, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:47.270375Z", "loop": 5180, "env_steps": 3183206399, "loss": 0.018798623234033585, "avg_return": 0.8594319820404053, "regret": 0.003066436154767871, "entropy": 0.10666072368621826, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:48.123235Z", "loop": 5181, "env_steps": 3183820799, "loss": 0.019139114767313004, "avg_return": 0.8595402240753174, "regret": 0.003066436154767871, "entropy": 0.10459538549184799, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:48.976795Z", "loop": 5182, "env_steps": 3184435199, "loss": 0.020084455609321594, "avg_return": 0.8604642152786255, "regret": 0.003066436154767871, "entropy": 0.11200422048568726, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:49.830769Z", "loop": 5183, "env_steps": 3185049599, "loss": 0.019067926332354546, "avg_return": 0.8596340417861938, "regret": 0.003066436154767871, "entropy": 0.10903425514698029, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:50.684920Z", "loop": 5184, "env_steps": 3185663999, "loss": 0.018276408314704895, "avg_return": 0.8597113490104675, "regret": 0.003066436154767871, "entropy": 0.10511239618062973, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:51.538702Z", "loop": 5185, "env_steps": 3186278399, "loss": 0.01933555118739605, "avg_return": 0.8598827123641968, "regret": 0.003066436154767871, "entropy": 0.10458386689424515, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:52.391422Z", "loop": 5186, "env_steps": 3186892799, "loss": 0.01707419753074646, "avg_return": 0.8601369261741638, "regret": 0.003066436154767871, "entropy": 0.10206390172243118, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:53.244446Z", "loop": 5187, "env_steps": 3187507199, "loss": 0.01890355534851551, "avg_return": 0.859539806842804, "regret": 0.003066436154767871, "entropy": 0.09779062867164612, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:54.098292Z", "loop": 5188, "env_steps": 3188121599, "loss": 0.020893355831503868, "avg_return": 0.8594396114349365, "regret": 0.003066436154767871, "entropy": 0.10940690338611603, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:54.951945Z", "loop": 5189, "env_steps": 3188735999, "loss": 0.0175153948366642, "avg_return": 0.8601635694503784, "regret": 0.003066436154767871, "entropy": 0.10114362090826035, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:55.845438Z", "loop": 5190, "env_steps": 3189350399, "loss": 0.0183863565325737, "avg_return": 0.8616888523101807, "regret": 0.0022921781055629253, "entropy": 0.10597093403339386, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:56.699450Z", "loop": 5191, "env_steps": 3189964799, "loss": 0.018551845103502274, "avg_return": 0.8616000413894653, "regret": 0.0022921781055629253, "entropy": 0.10482431203126907, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:57.553929Z", "loop": 5192, "env_steps": 3190579199, "loss": 0.017988592386245728, "avg_return": 0.8626180291175842, "regret": 0.0022921781055629253, "entropy": 0.10267447680234909, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:58.407868Z", "loop": 5193, "env_steps": 3191193599, "loss": 0.01855914480984211, "avg_return": 0.8623350262641907, "regret": 0.0022921781055629253, "entropy": 0.10833438485860825, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:37:59.261874Z", "loop": 5194, "env_steps": 3191807999, "loss": 0.01847233437001705, "avg_return": 0.8614192008972168, "regret": 0.0022921781055629253, "entropy": 0.10053759068250656, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:00.115601Z", "loop": 5195, "env_steps": 3192422399, "loss": 0.0173138789832592, "avg_return": 0.8615800142288208, "regret": 0.0022921781055629253, "entropy": 0.09968139976263046, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:00.968465Z", "loop": 5196, "env_steps": 3193036799, "loss": 0.018222438171505928, "avg_return": 0.8604720234870911, "regret": 0.0022921781055629253, "entropy": 0.1030196100473404, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:01.821767Z", "loop": 5197, "env_steps": 3193651199, "loss": 0.017373407259583473, "avg_return": 0.8625439405441284, "regret": 0.0022921781055629253, "entropy": 0.09990055859088898, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:02.674948Z", "loop": 5198, "env_steps": 3194265599, "loss": 0.020215874537825584, "avg_return": 0.8632269501686096, "regret": 0.0022921781055629253, "entropy": 0.10768329352140427, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:03.529459Z", "loop": 5199, "env_steps": 3194879999, "loss": 0.02007458172738552, "avg_return": 0.8611410856246948, "regret": 0.0022921781055629253, "entropy": 0.10862608253955841, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:04.423781Z", "loop": 5200, "env_steps": 3195494399, "loss": 0.018674839287996292, "avg_return": 0.8628876209259033, "regret": 0.0018134238198399544, "entropy": 0.1060657873749733, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:05.278331Z", "loop": 5201, "env_steps": 3196108799, "loss": 0.01834341138601303, "avg_return": 0.860942006111145, "regret": 0.0018134238198399544, "entropy": 0.10320989787578583, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:06.133766Z", "loop": 5202, "env_steps": 3196723199, "loss": 0.019730282947421074, "avg_return": 0.8628561496734619, "regret": 0.0018134238198399544, "entropy": 0.1062779501080513, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:06.990253Z", "loop": 5203, "env_steps": 3197337599, "loss": 0.01855040155351162, "avg_return": 0.8604583144187927, "regret": 0.0018134238198399544, "entropy": 0.10467508435249329, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:07.849303Z", "loop": 5204, "env_steps": 3197951999, "loss": 0.01886865124106407, "avg_return": 0.860462486743927, "regret": 0.0018134238198399544, "entropy": 0.10197605192661285, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:08.703226Z", "loop": 5205, "env_steps": 3198566399, "loss": 0.02048635110259056, "avg_return": 0.861186146736145, "regret": 0.0018134238198399544, "entropy": 0.11367376148700714, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:09.557670Z", "loop": 5206, "env_steps": 3199180799, "loss": 0.02207619696855545, "avg_return": 0.8583698868751526, "regret": 0.0018134238198399544, "entropy": 0.1141081228852272, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:10.411253Z", "loop": 5207, "env_steps": 3199795199, "loss": 0.0226209107786417, "avg_return": 0.8591508269309998, "regret": 0.0018134238198399544, "entropy": 0.12121491879224777, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:11.265884Z", "loop": 5208, "env_steps": 3200409599, "loss": 0.021670332178473473, "avg_return": 0.8595314621925354, "regret": 0.0018134238198399544, "entropy": 0.11856063455343246, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:12.120903Z", "loop": 5209, "env_steps": 3201023999, "loss": 0.021400755271315575, "avg_return": 0.8579728603363037, "regret": 0.0018134238198399544, "entropy": 0.11809690296649933, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:13.016917Z", "loop": 5210, "env_steps": 3201638399, "loss": 0.020477497950196266, "avg_return": 0.8607388734817505, "regret": 0.0027456101961433887, "entropy": 0.11172027885913849, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:13.872402Z", "loop": 5211, "env_steps": 3202252799, "loss": 0.01874764822423458, "avg_return": 0.8613142967224121, "regret": 0.0027456101961433887, "entropy": 0.10411244630813599, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:14.726447Z", "loop": 5212, "env_steps": 3202867199, "loss": 0.01855911873281002, "avg_return": 0.8618143796920776, "regret": 0.0027456101961433887, "entropy": 0.10442807525396347, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:15.579825Z", "loop": 5213, "env_steps": 3203481599, "loss": 0.01879836991429329, "avg_return": 0.8618482947349548, "regret": 0.0027456101961433887, "entropy": 0.10406116396188736, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:16.433572Z", "loop": 5214, "env_steps": 3204095999, "loss": 0.0189875066280365, "avg_return": 0.8633068799972534, "regret": 0.0027456101961433887, "entropy": 0.10741852968931198, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:17.287901Z", "loop": 5215, "env_steps": 3204710399, "loss": 0.019225573167204857, "avg_return": 0.862204909324646, "regret": 0.0027456101961433887, "entropy": 0.10633453726768494, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:18.142195Z", "loop": 5216, "env_steps": 3205324799, "loss": 0.019633179530501366, "avg_return": 0.8610891103744507, "regret": 0.0027456101961433887, "entropy": 0.11297404021024704, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:18.998691Z", "loop": 5217, "env_steps": 3205939199, "loss": 0.019127007573843002, "avg_return": 0.8620175123214722, "regret": 0.0027456101961433887, "entropy": 0.10867731273174286, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:19.852181Z", "loop": 5218, "env_steps": 3206553599, "loss": 0.020559515804052353, "avg_return": 0.8627569675445557, "regret": 0.0027456101961433887, "entropy": 0.11078829318284988, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:20.706393Z", "loop": 5219, "env_steps": 3207167999, "loss": 0.019644077867269516, "avg_return": 0.8624613881111145, "regret": 0.0027456101961433887, "entropy": 0.11195076256990433, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:21.601443Z", "loop": 5220, "env_steps": 3207782399, "loss": 0.017878388985991478, "avg_return": 0.8623260855674744, "regret": 0.0018682758091017604, "entropy": 0.10594475269317627, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:22.456751Z", "loop": 5221, "env_steps": 3208396799, "loss": 0.018745822831988335, "avg_return": 0.8622967004776001, "regret": 0.0018682758091017604, "entropy": 0.10397019982337952, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:23.310695Z", "loop": 5222, "env_steps": 3209011199, "loss": 0.018257832154631615, "avg_return": 0.8627081513404846, "regret": 0.0018682758091017604, "entropy": 0.10372110456228256, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:24.165303Z", "loop": 5223, "env_steps": 3209625599, "loss": 0.018173184245824814, "avg_return": 0.8609310984611511, "regret": 0.0018682758091017604, "entropy": 0.10142284631729126, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:25.019179Z", "loop": 5224, "env_steps": 3210239999, "loss": 0.01951364241540432, "avg_return": 0.8619457483291626, "regret": 0.0018682758091017604, "entropy": 0.1062719076871872, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:25.873937Z", "loop": 5225, "env_steps": 3210854399, "loss": 0.01805781200528145, "avg_return": 0.8602790236473083, "regret": 0.0018682758091017604, "entropy": 0.10112334042787552, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:26.727747Z", "loop": 5226, "env_steps": 3211468799, "loss": 0.01822449080646038, "avg_return": 0.8593747019767761, "regret": 0.0018682758091017604, "entropy": 0.10478991270065308, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:27.583460Z", "loop": 5227, "env_steps": 3212083199, "loss": 0.019906198605895042, "avg_return": 0.8582829833030701, "regret": 0.0018682758091017604, "entropy": 0.10433946549892426, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:28.438049Z", "loop": 5228, "env_steps": 3212697599, "loss": 0.020469849929213524, "avg_return": 0.8592461347579956, "regret": 0.0018682758091017604, "entropy": 0.10533538460731506, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:29.291569Z", "loop": 5229, "env_steps": 3213311999, "loss": 0.02063717506825924, "avg_return": 0.8606423139572144, "regret": 0.0018682758091017604, "entropy": 0.10691481828689575, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:30.186465Z", "loop": 5230, "env_steps": 3213926399, "loss": 0.01999223791062832, "avg_return": 0.8599796891212463, "regret": 0.0034004838671535254, "entropy": 0.11226683855056763, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:31.041022Z", "loop": 5231, "env_steps": 3214540799, "loss": 0.017785344272851944, "avg_return": 0.8602355122566223, "regret": 0.0034004838671535254, "entropy": 0.10105594247579575, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:31.894594Z", "loop": 5232, "env_steps": 3215155199, "loss": 0.020404769107699394, "avg_return": 0.8614634275436401, "regret": 0.0034004838671535254, "entropy": 0.10681602358818054, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:32.748070Z", "loop": 5233, "env_steps": 3215769599, "loss": 0.017847692593932152, "avg_return": 0.8614650964736938, "regret": 0.0034004838671535254, "entropy": 0.09984520822763443, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:33.602224Z", "loop": 5234, "env_steps": 3216383999, "loss": 0.01832450181245804, "avg_return": 0.8625486493110657, "regret": 0.0034004838671535254, "entropy": 0.10109838098287582, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:34.457114Z", "loop": 5235, "env_steps": 3216998399, "loss": 0.01851041615009308, "avg_return": 0.8613792061805725, "regret": 0.0034004838671535254, "entropy": 0.10429592430591583, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:35.310545Z", "loop": 5236, "env_steps": 3217612799, "loss": 0.017412366345524788, "avg_return": 0.8622223138809204, "regret": 0.0034004838671535254, "entropy": 0.10048442333936691, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:36.164157Z", "loop": 5237, "env_steps": 3218227199, "loss": 0.019179558381438255, "avg_return": 0.8617470264434814, "regret": 0.0034004838671535254, "entropy": 0.10490899533033371, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:37.018571Z", "loop": 5238, "env_steps": 3218841599, "loss": 0.020002800971269608, "avg_return": 0.8609403967857361, "regret": 0.0034004838671535254, "entropy": 0.1101946160197258, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:37.873539Z", "loop": 5239, "env_steps": 3219455999, "loss": 0.019005415961146355, "avg_return": 0.8605839014053345, "regret": 0.0034004838671535254, "entropy": 0.11120488494634628, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:38.767703Z", "loop": 5240, "env_steps": 3220070399, "loss": 0.020724022760987282, "avg_return": 0.8598194718360901, "regret": 0.003449707292020321, "entropy": 0.11750651150941849, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:39.621325Z", "loop": 5241, "env_steps": 3220684799, "loss": 0.02224121056497097, "avg_return": 0.8583003878593445, "regret": 0.003449707292020321, "entropy": 0.12274906039237976, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:40.475745Z", "loop": 5242, "env_steps": 3221299199, "loss": 0.023782646283507347, "avg_return": 0.859846830368042, "regret": 0.003449707292020321, "entropy": 0.12786085903644562, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:41.330846Z", "loop": 5243, "env_steps": 3221913599, "loss": 0.021654848009347916, "avg_return": 0.8591249585151672, "regret": 0.003449707292020321, "entropy": 0.12068747729063034, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:42.185474Z", "loop": 5244, "env_steps": 3222527999, "loss": 0.021055996417999268, "avg_return": 0.8604183197021484, "regret": 0.003449707292020321, "entropy": 0.11845982074737549, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:43.039448Z", "loop": 5245, "env_steps": 3223142399, "loss": 0.020050009712576866, "avg_return": 0.8605849146842957, "regret": 0.003449707292020321, "entropy": 0.11146916449069977, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:43.893176Z", "loop": 5246, "env_steps": 3223756799, "loss": 0.01889677159488201, "avg_return": 0.8611003756523132, "regret": 0.003449707292020321, "entropy": 0.10879649966955185, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:44.748161Z", "loop": 5247, "env_steps": 3224371199, "loss": 0.019892826676368713, "avg_return": 0.8623508810997009, "regret": 0.003449707292020321, "entropy": 0.1109432652592659, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:45.601044Z", "loop": 5248, "env_steps": 3224985599, "loss": 0.01879662089049816, "avg_return": 0.8614134788513184, "regret": 0.003449707292020321, "entropy": 0.10728492587804794, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:46.453876Z", "loop": 5249, "env_steps": 3225599999, "loss": 0.01863420382142067, "avg_return": 0.8617648482322693, "regret": 0.003449707292020321, "entropy": 0.10708124190568924, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:47.348268Z", "loop": 5250, "env_steps": 3226214399, "loss": 0.021143009886145592, "avg_return": 0.8607986569404602, "regret": 0.00223292363807559, "entropy": 0.11467821151018143, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:48.204112Z", "loop": 5251, "env_steps": 3226828799, "loss": 0.020445263013243675, "avg_return": 0.8618732690811157, "regret": 0.00223292363807559, "entropy": 0.11392036825418472, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:49.058354Z", "loop": 5252, "env_steps": 3227443199, "loss": 0.019780876114964485, "avg_return": 0.8614389300346375, "regret": 0.00223292363807559, "entropy": 0.1124282106757164, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:49.913034Z", "loop": 5253, "env_steps": 3228057599, "loss": 0.021113727241754532, "avg_return": 0.8598534464836121, "regret": 0.00223292363807559, "entropy": 0.11572475731372833, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:50.766401Z", "loop": 5254, "env_steps": 3228671999, "loss": 0.019875548779964447, "avg_return": 0.8614727258682251, "regret": 0.00223292363807559, "entropy": 0.1105961725115776, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:51.619776Z", "loop": 5255, "env_steps": 3229286399, "loss": 0.019907115027308464, "avg_return": 0.8597696423530579, "regret": 0.00223292363807559, "entropy": 0.11205948889255524, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:52.474569Z", "loop": 5256, "env_steps": 3229900799, "loss": 0.021778279915452003, "avg_return": 0.8577755689620972, "regret": 0.00223292363807559, "entropy": 0.11555532366037369, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:53.328476Z", "loop": 5257, "env_steps": 3230515199, "loss": 0.023061899468302727, "avg_return": 0.8583776950836182, "regret": 0.00223292363807559, "entropy": 0.1217031329870224, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:54.182149Z", "loop": 5258, "env_steps": 3231129599, "loss": 0.020891277119517326, "avg_return": 0.8579776287078857, "regret": 0.00223292363807559, "entropy": 0.11799144744873047, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:55.036010Z", "loop": 5259, "env_steps": 3231743999, "loss": 0.020182626321911812, "avg_return": 0.8589013814926147, "regret": 0.00223292363807559, "entropy": 0.11103972047567368, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:55.931277Z", "loop": 5260, "env_steps": 3232358399, "loss": 0.020136822015047073, "avg_return": 0.8613371253013611, "regret": 0.003672068240121007, "entropy": 0.11243624240159988, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:56.785402Z", "loop": 5261, "env_steps": 3232972799, "loss": 0.019442467018961906, "avg_return": 0.8610934615135193, "regret": 0.003672068240121007, "entropy": 0.10875385254621506, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:57.639498Z", "loop": 5262, "env_steps": 3233587199, "loss": 0.018800726160407066, "avg_return": 0.8617345094680786, "regret": 0.003672068240121007, "entropy": 0.10666772723197937, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:58.492602Z", "loop": 5263, "env_steps": 3234201599, "loss": 0.018456965684890747, "avg_return": 0.8607199192047119, "regret": 0.003672068240121007, "entropy": 0.10312120616436005, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:38:59.345725Z", "loop": 5264, "env_steps": 3234815999, "loss": 0.018603188917040825, "avg_return": 0.8614501357078552, "regret": 0.003672068240121007, "entropy": 0.10444337874650955, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:00.200441Z", "loop": 5265, "env_steps": 3235430399, "loss": 0.017079446464776993, "avg_return": 0.8625325560569763, "regret": 0.003672068240121007, "entropy": 0.09861303865909576, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:01.055263Z", "loop": 5266, "env_steps": 3236044799, "loss": 0.018292319029569626, "avg_return": 0.8622733950614929, "regret": 0.003672068240121007, "entropy": 0.09970789402723312, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:01.908827Z", "loop": 5267, "env_steps": 3236659199, "loss": 0.01819385215640068, "avg_return": 0.861676037311554, "regret": 0.003672068240121007, "entropy": 0.10335828363895416, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:02.763136Z", "loop": 5268, "env_steps": 3237273599, "loss": 0.01944553107023239, "avg_return": 0.8608280420303345, "regret": 0.003672068240121007, "entropy": 0.10833228379487991, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:03.617329Z", "loop": 5269, "env_steps": 3237887999, "loss": 0.020573869347572327, "avg_return": 0.8604831099510193, "regret": 0.003672068240121007, "entropy": 0.11489655077457428, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:04.512809Z", "loop": 5270, "env_steps": 3238502399, "loss": 0.022018471732735634, "avg_return": 0.8594464063644409, "regret": 0.0040197125636041164, "entropy": 0.12098316848278046, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:05.366857Z", "loop": 5271, "env_steps": 3239116799, "loss": 0.02135927975177765, "avg_return": 0.8578904271125793, "regret": 0.0040197125636041164, "entropy": 0.11230475455522537, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:06.219462Z", "loop": 5272, "env_steps": 3239731199, "loss": 0.02060323767364025, "avg_return": 0.8596585392951965, "regret": 0.0040197125636041164, "entropy": 0.11141636222600937, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:07.072362Z", "loop": 5273, "env_steps": 3240345599, "loss": 0.019879398867487907, "avg_return": 0.8613682389259338, "regret": 0.0040197125636041164, "entropy": 0.10872823745012283, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:07.927166Z", "loop": 5274, "env_steps": 3240959999, "loss": 0.017884813249111176, "avg_return": 0.8599886298179626, "regret": 0.0040197125636041164, "entropy": 0.10296405851840973, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:08.781434Z", "loop": 5275, "env_steps": 3241574399, "loss": 0.01831202022731304, "avg_return": 0.8615952730178833, "regret": 0.0040197125636041164, "entropy": 0.10201519727706909, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:09.635363Z", "loop": 5276, "env_steps": 3242188799, "loss": 0.018974926322698593, "avg_return": 0.8608924746513367, "regret": 0.0040197125636041164, "entropy": 0.10136587917804718, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:10.488949Z", "loop": 5277, "env_steps": 3242803199, "loss": 0.017757991328835487, "avg_return": 0.8616697192192078, "regret": 0.0040197125636041164, "entropy": 0.10376409441232681, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:11.343543Z", "loop": 5278, "env_steps": 3243417599, "loss": 0.01918933354318142, "avg_return": 0.8608019351959229, "regret": 0.0040197125636041164, "entropy": 0.10812091827392578, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:12.197103Z", "loop": 5279, "env_steps": 3244031999, "loss": 0.017090601846575737, "avg_return": 0.86106938123703, "regret": 0.0040197125636041164, "entropy": 0.10239119082689285, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:13.089941Z", "loop": 5280, "env_steps": 3244646399, "loss": 0.016575952991843224, "avg_return": 0.860856831073761, "regret": 0.0024545739870518446, "entropy": 0.0983818769454956, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:13.944202Z", "loop": 5281, "env_steps": 3245260799, "loss": 0.018377987667918205, "avg_return": 0.8617860078811646, "regret": 0.0024545739870518446, "entropy": 0.10034852474927902, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:14.798757Z", "loop": 5282, "env_steps": 3245875199, "loss": 0.018028173595666885, "avg_return": 0.8619413375854492, "regret": 0.0024545739870518446, "entropy": 0.0993974432349205, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:15.653438Z", "loop": 5283, "env_steps": 3246489599, "loss": 0.01794063299894333, "avg_return": 0.8614276051521301, "regret": 0.0024545739870518446, "entropy": 0.09811922162771225, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:16.508443Z", "loop": 5284, "env_steps": 3247103999, "loss": 0.017786405980587006, "avg_return": 0.8623016476631165, "regret": 0.0024545739870518446, "entropy": 0.0988326445221901, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:17.363668Z", "loop": 5285, "env_steps": 3247718399, "loss": 0.017830925062298775, "avg_return": 0.8620573282241821, "regret": 0.0024545739870518446, "entropy": 0.09814492613077164, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:18.218894Z", "loop": 5286, "env_steps": 3248332799, "loss": 0.01839171163737774, "avg_return": 0.8633762001991272, "regret": 0.0024545739870518446, "entropy": 0.10348717123270035, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:19.073508Z", "loop": 5287, "env_steps": 3248947199, "loss": 0.017683280631899834, "avg_return": 0.8618518114089966, "regret": 0.0024545739870518446, "entropy": 0.09995230287313461, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:19.927869Z", "loop": 5288, "env_steps": 3249561599, "loss": 0.01808648370206356, "avg_return": 0.8615007996559143, "regret": 0.0024545739870518446, "entropy": 0.10010133683681488, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:20.781843Z", "loop": 5289, "env_steps": 3250175999, "loss": 0.019887087866663933, "avg_return": 0.8621283173561096, "regret": 0.0024545739870518446, "entropy": 0.10660017281770706, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:21.675617Z", "loop": 5290, "env_steps": 3250790399, "loss": 0.01865394413471222, "avg_return": 0.8631331324577332, "regret": 0.0014439040096476674, "entropy": 0.10427433252334595, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:22.530511Z", "loop": 5291, "env_steps": 3251404799, "loss": 0.018834099173545837, "avg_return": 0.8623431324958801, "regret": 0.0014439040096476674, "entropy": 0.10037165135145187, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:23.385234Z", "loop": 5292, "env_steps": 3252019199, "loss": 0.018727248534560204, "avg_return": 0.862162709236145, "regret": 0.0014439040096476674, "entropy": 0.10326972603797913, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:24.239249Z", "loop": 5293, "env_steps": 3252633599, "loss": 0.017805183306336403, "avg_return": 0.8614313006401062, "regret": 0.0014439040096476674, "entropy": 0.1046985387802124, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:25.093073Z", "loop": 5294, "env_steps": 3253247999, "loss": 0.01978965848684311, "avg_return": 0.8624247312545776, "regret": 0.0014439040096476674, "entropy": 0.10884267091751099, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:25.947144Z", "loop": 5295, "env_steps": 3253862399, "loss": 0.019766803830862045, "avg_return": 0.8611720204353333, "regret": 0.0014439040096476674, "entropy": 0.1098102480173111, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:26.802431Z", "loop": 5296, "env_steps": 3254476799, "loss": 0.02023920975625515, "avg_return": 0.861345648765564, "regret": 0.0014439040096476674, "entropy": 0.11312208324670792, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:27.656900Z", "loop": 5297, "env_steps": 3255091199, "loss": 0.02111162059009075, "avg_return": 0.8611516356468201, "regret": 0.0014439040096476674, "entropy": 0.11500783264636993, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:28.511563Z", "loop": 5298, "env_steps": 3255705599, "loss": 0.021565912291407585, "avg_return": 0.8602427244186401, "regret": 0.0014439040096476674, "entropy": 0.11786673218011856, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:29.365050Z", "loop": 5299, "env_steps": 3256319999, "loss": 0.02200665883719921, "avg_return": 0.862433910369873, "regret": 0.0014439040096476674, "entropy": 0.12045849859714508, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:30.258190Z", "loop": 5300, "env_steps": 3256934399, "loss": 0.019252600148320198, "avg_return": 0.860419750213623, "regret": 0.0030860155820846558, "entropy": 0.11542992293834686, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:31.112010Z", "loop": 5301, "env_steps": 3257548799, "loss": 0.021191928535699844, "avg_return": 0.860541820526123, "regret": 0.0030860155820846558, "entropy": 0.11781424283981323, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:31.966770Z", "loop": 5302, "env_steps": 3258163199, "loss": 0.020888743922114372, "avg_return": 0.8606918454170227, "regret": 0.0030860155820846558, "entropy": 0.1170671209692955, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:32.820493Z", "loop": 5303, "env_steps": 3258777599, "loss": 0.02008446864783764, "avg_return": 0.8583503365516663, "regret": 0.0030860155820846558, "entropy": 0.11651187390089035, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:33.673192Z", "loop": 5304, "env_steps": 3259391999, "loss": 0.020577413961291313, "avg_return": 0.8592812418937683, "regret": 0.0030860155820846558, "entropy": 0.11565656960010529, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:34.526146Z", "loop": 5305, "env_steps": 3260006399, "loss": 0.020019656047225, "avg_return": 0.8584578633308411, "regret": 0.0030860155820846558, "entropy": 0.11499109119176865, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:35.380665Z", "loop": 5306, "env_steps": 3260620799, "loss": 0.02004033327102661, "avg_return": 0.8600049018859863, "regret": 0.0030860155820846558, "entropy": 0.11479354649782181, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:36.235872Z", "loop": 5307, "env_steps": 3261235199, "loss": 0.018296774476766586, "avg_return": 0.8617358803749084, "regret": 0.0030860155820846558, "entropy": 0.1058356836438179, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:37.088702Z", "loop": 5308, "env_steps": 3261849599, "loss": 0.02008260227739811, "avg_return": 0.8605849146842957, "regret": 0.0030860155820846558, "entropy": 0.10917694866657257, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:37.941915Z", "loop": 5309, "env_steps": 3262463999, "loss": 0.017855552956461906, "avg_return": 0.8623566031455994, "regret": 0.0030860155820846558, "entropy": 0.10306088626384735, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:38.837743Z", "loop": 5310, "env_steps": 3263078399, "loss": 0.018859857693314552, "avg_return": 0.861301600933075, "regret": 0.0016002972843125463, "entropy": 0.1045633852481842, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:39.691547Z", "loop": 5311, "env_steps": 3263692799, "loss": 0.0180860236287117, "avg_return": 0.8623120188713074, "regret": 0.0016002972843125463, "entropy": 0.10254987329244614, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:40.545502Z", "loop": 5312, "env_steps": 3264307199, "loss": 0.01843590848147869, "avg_return": 0.8626514673233032, "regret": 0.0016002972843125463, "entropy": 0.09659117460250854, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:41.399191Z", "loop": 5313, "env_steps": 3264921599, "loss": 0.016417212784290314, "avg_return": 0.8619597554206848, "regret": 0.0016002972843125463, "entropy": 0.09724769741296768, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:42.252834Z", "loop": 5314, "env_steps": 3265535999, "loss": 0.017335625365376472, "avg_return": 0.8614649772644043, "regret": 0.0016002972843125463, "entropy": 0.09686625003814697, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:43.107127Z", "loop": 5315, "env_steps": 3266150399, "loss": 0.01960071362555027, "avg_return": 0.8602726459503174, "regret": 0.0016002972843125463, "entropy": 0.10917981714010239, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:43.961553Z", "loop": 5316, "env_steps": 3266764799, "loss": 0.020368190482258797, "avg_return": 0.8562705516815186, "regret": 0.0016002972843125463, "entropy": 0.10980302095413208, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:44.816104Z", "loop": 5317, "env_steps": 3267379199, "loss": 0.02255258336663246, "avg_return": 0.8539683222770691, "regret": 0.0016002972843125463, "entropy": 0.11498560756444931, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:45.669490Z", "loop": 5318, "env_steps": 3267993599, "loss": 0.024772709235548973, "avg_return": 0.8505666255950928, "regret": 0.0016002972843125463, "entropy": 0.12707087397575378, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:46.523158Z", "loop": 5319, "env_steps": 3268607999, "loss": 0.023189526051282883, "avg_return": 0.8516631126403809, "regret": 0.0016002972843125463, "entropy": 0.12392689287662506, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:47.417758Z", "loop": 5320, "env_steps": 3269222399, "loss": 0.02255837433040142, "avg_return": 0.8545758128166199, "regret": 0.009379337541759014, "entropy": 0.11797235161066055, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:48.272244Z", "loop": 5321, "env_steps": 3269836799, "loss": 0.021114816889166832, "avg_return": 0.8554966449737549, "regret": 0.009379337541759014, "entropy": 0.11077229678630829, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:49.126135Z", "loop": 5322, "env_steps": 3270451199, "loss": 0.020200306549668312, "avg_return": 0.8591998219490051, "regret": 0.009379337541759014, "entropy": 0.10457587987184525, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:49.979028Z", "loop": 5323, "env_steps": 3271065599, "loss": 0.018215792253613472, "avg_return": 0.8610170483589172, "regret": 0.009379337541759014, "entropy": 0.09950356185436249, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:50.832833Z", "loop": 5324, "env_steps": 3271679999, "loss": 0.017196049913764, "avg_return": 0.8617615103721619, "regret": 0.009379337541759014, "entropy": 0.09584920108318329, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:51.686861Z", "loop": 5325, "env_steps": 3272294399, "loss": 0.018010573461651802, "avg_return": 0.8626692891120911, "regret": 0.009379337541759014, "entropy": 0.09865788370370865, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:52.540051Z", "loop": 5326, "env_steps": 3272908799, "loss": 0.018768299371004105, "avg_return": 0.8616607785224915, "regret": 0.009379337541759014, "entropy": 0.10155194252729416, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:53.393512Z", "loop": 5327, "env_steps": 3273523199, "loss": 0.01901175267994404, "avg_return": 0.8596351146697998, "regret": 0.009379337541759014, "entropy": 0.10583829879760742, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:54.247223Z", "loop": 5328, "env_steps": 3274137599, "loss": 0.019922485575079918, "avg_return": 0.8588266968727112, "regret": 0.009379337541759014, "entropy": 0.10960878431797028, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:55.103180Z", "loop": 5329, "env_steps": 3274751999, "loss": 0.01959613524377346, "avg_return": 0.8576147556304932, "regret": 0.009379337541759014, "entropy": 0.11689246445894241, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:55.999894Z", "loop": 5330, "env_steps": 3275366399, "loss": 0.02095135860145092, "avg_return": 0.8568711280822754, "regret": 0.006003732793033123, "entropy": 0.11506443470716476, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:56.853340Z", "loop": 5331, "env_steps": 3275980799, "loss": 0.020169323310256004, "avg_return": 0.8570852875709534, "regret": 0.006003732793033123, "entropy": 0.11700988560914993, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:57.706817Z", "loop": 5332, "env_steps": 3276595199, "loss": 0.020432360470294952, "avg_return": 0.8582916259765625, "regret": 0.006003732793033123, "entropy": 0.11485087871551514, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:58.561243Z", "loop": 5333, "env_steps": 3277209599, "loss": 0.021286634728312492, "avg_return": 0.8592466711997986, "regret": 0.006003732793033123, "entropy": 0.11896911263465881, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:39:59.415459Z", "loop": 5334, "env_steps": 3277823999, "loss": 0.02059362828731537, "avg_return": 0.8583571314811707, "regret": 0.006003732793033123, "entropy": 0.1138281375169754, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:00.269353Z", "loop": 5335, "env_steps": 3278438399, "loss": 0.019436543807387352, "avg_return": 0.858169674873352, "regret": 0.006003732793033123, "entropy": 0.11092139780521393, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:01.123430Z", "loop": 5336, "env_steps": 3279052799, "loss": 0.020880332216620445, "avg_return": 0.8578851819038391, "regret": 0.006003732793033123, "entropy": 0.11012835800647736, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:01.977865Z", "loop": 5337, "env_steps": 3279667199, "loss": 0.02154158614575863, "avg_return": 0.8553227782249451, "regret": 0.006003732793033123, "entropy": 0.11318924278020859, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:02.832513Z", "loop": 5338, "env_steps": 3280281599, "loss": 0.01997806318104267, "avg_return": 0.8569933176040649, "regret": 0.006003732793033123, "entropy": 0.10963194072246552, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:03.687667Z", "loop": 5339, "env_steps": 3280895999, "loss": 0.020679496228694916, "avg_return": 0.8601914644241333, "regret": 0.006003732793033123, "entropy": 0.11098714917898178, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:04.582574Z", "loop": 5340, "env_steps": 3281510399, "loss": 0.018267150968313217, "avg_return": 0.8605763912200928, "regret": 0.003237081691622734, "entropy": 0.1052972599864006, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:05.437037Z", "loop": 5341, "env_steps": 3282124799, "loss": 0.018755653873085976, "avg_return": 0.8622662425041199, "regret": 0.003237081691622734, "entropy": 0.10703623294830322, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:06.292272Z", "loop": 5342, "env_steps": 3282739199, "loss": 0.018957054242491722, "avg_return": 0.8612107634544373, "regret": 0.003237081691622734, "entropy": 0.1030094251036644, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:07.146229Z", "loop": 5343, "env_steps": 3283353599, "loss": 0.019857434555888176, "avg_return": 0.8602900505065918, "regret": 0.003237081691622734, "entropy": 0.10985837131738663, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:08.000136Z", "loop": 5344, "env_steps": 3283967999, "loss": 0.018960466608405113, "avg_return": 0.8620669841766357, "regret": 0.003237081691622734, "entropy": 0.10895983874797821, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:08.854972Z", "loop": 5345, "env_steps": 3284582399, "loss": 0.019907774403691292, "avg_return": 0.8615594506263733, "regret": 0.003237081691622734, "entropy": 0.1105649545788765, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:09.709896Z", "loop": 5346, "env_steps": 3285196799, "loss": 0.019219303503632545, "avg_return": 0.8604297041893005, "regret": 0.003237081691622734, "entropy": 0.1122099906206131, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:10.564404Z", "loop": 5347, "env_steps": 3285811199, "loss": 0.018338650465011597, "avg_return": 0.8633966445922852, "regret": 0.003237081691622734, "entropy": 0.10799702256917953, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:11.420323Z", "loop": 5348, "env_steps": 3286425599, "loss": 0.019646165892481804, "avg_return": 0.8612860441207886, "regret": 0.003237081691622734, "entropy": 0.11337815225124359, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:12.273922Z", "loop": 5349, "env_steps": 3287039999, "loss": 0.019784944131970406, "avg_return": 0.8622825145721436, "regret": 0.003237081691622734, "entropy": 0.11504078656435013, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:13.170270Z", "loop": 5350, "env_steps": 3287654399, "loss": 0.020053934305906296, "avg_return": 0.8609535694122314, "regret": 0.002437824849039316, "entropy": 0.11508394032716751, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:14.024993Z", "loop": 5351, "env_steps": 3288268799, "loss": 0.01916288398206234, "avg_return": 0.8617230653762817, "regret": 0.002437824849039316, "entropy": 0.1125810295343399, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:14.881012Z", "loop": 5352, "env_steps": 3288883199, "loss": 0.020767182111740112, "avg_return": 0.8618725538253784, "regret": 0.002437824849039316, "entropy": 0.1122751533985138, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:15.736239Z", "loop": 5353, "env_steps": 3289497599, "loss": 0.02058866061270237, "avg_return": 0.8606091737747192, "regret": 0.002437824849039316, "entropy": 0.11497466266155243, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:16.591282Z", "loop": 5354, "env_steps": 3290111999, "loss": 0.01986190862953663, "avg_return": 0.8606225848197937, "regret": 0.002437824849039316, "entropy": 0.1125151664018631, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:17.446046Z", "loop": 5355, "env_steps": 3290726399, "loss": 0.01992078684270382, "avg_return": 0.8609352707862854, "regret": 0.002437824849039316, "entropy": 0.11344271153211594, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:18.299892Z", "loop": 5356, "env_steps": 3291340799, "loss": 0.02134852670133114, "avg_return": 0.8617885708808899, "regret": 0.002437824849039316, "entropy": 0.11519956588745117, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:19.154548Z", "loop": 5357, "env_steps": 3291955199, "loss": 0.020384198054671288, "avg_return": 0.8604242205619812, "regret": 0.002437824849039316, "entropy": 0.11072432994842529, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:20.008207Z", "loop": 5358, "env_steps": 3292569599, "loss": 0.01973026432096958, "avg_return": 0.8616836667060852, "regret": 0.002437824849039316, "entropy": 0.10797826945781708, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:20.861577Z", "loop": 5359, "env_steps": 3293183999, "loss": 0.02006644196808338, "avg_return": 0.8609525561332703, "regret": 0.002437824849039316, "entropy": 0.1089853048324585, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:21.757752Z", "loop": 5360, "env_steps": 3293798399, "loss": 0.018523063510656357, "avg_return": 0.8616027235984802, "regret": 0.0018665038514882326, "entropy": 0.09919175505638123, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:22.612378Z", "loop": 5361, "env_steps": 3294412799, "loss": 0.019515128806233406, "avg_return": 0.8608357906341553, "regret": 0.0018665038514882326, "entropy": 0.10983803123235703, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:23.466756Z", "loop": 5362, "env_steps": 3295027199, "loss": 0.01989774964749813, "avg_return": 0.8603363037109375, "regret": 0.0018665038514882326, "entropy": 0.1123514175415039, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:24.321670Z", "loop": 5363, "env_steps": 3295641599, "loss": 0.018856829032301903, "avg_return": 0.8594415783882141, "regret": 0.0018665038514882326, "entropy": 0.10605452954769135, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:25.176394Z", "loop": 5364, "env_steps": 3296255999, "loss": 0.019929710775613785, "avg_return": 0.8603631854057312, "regret": 0.0018665038514882326, "entropy": 0.11125050485134125, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:26.032731Z", "loop": 5365, "env_steps": 3296870399, "loss": 0.018694458529353142, "avg_return": 0.8592521548271179, "regret": 0.0018665038514882326, "entropy": 0.11251949518918991, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:26.888050Z", "loop": 5366, "env_steps": 3297484799, "loss": 0.020908018574118614, "avg_return": 0.8592236638069153, "regret": 0.0018665038514882326, "entropy": 0.1142943724989891, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:27.743530Z", "loop": 5367, "env_steps": 3298099199, "loss": 0.022004518657922745, "avg_return": 0.8597609400749207, "regret": 0.0018665038514882326, "entropy": 0.11995287239551544, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:28.597551Z", "loop": 5368, "env_steps": 3298713599, "loss": 0.01897372119128704, "avg_return": 0.8581525087356567, "regret": 0.0018665038514882326, "entropy": 0.1113920658826828, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:29.452800Z", "loop": 5369, "env_steps": 3299327999, "loss": 0.021225985139608383, "avg_return": 0.8588141202926636, "regret": 0.0018665038514882326, "entropy": 0.11852839589118958, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:30.348287Z", "loop": 5370, "env_steps": 3299942399, "loss": 0.01986958645284176, "avg_return": 0.8598030805587769, "regret": 0.003953846637159586, "entropy": 0.11135918647050858, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:31.201194Z", "loop": 5371, "env_steps": 3300556799, "loss": 0.020169824361801147, "avg_return": 0.8602467775344849, "regret": 0.003953846637159586, "entropy": 0.11475648730993271, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:32.053966Z", "loop": 5372, "env_steps": 3301171199, "loss": 0.02174367569386959, "avg_return": 0.8594394326210022, "regret": 0.003953846637159586, "entropy": 0.11496201157569885, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:32.907840Z", "loop": 5373, "env_steps": 3301785599, "loss": 0.0206648837774992, "avg_return": 0.8612443208694458, "regret": 0.003953846637159586, "entropy": 0.11733466386795044, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:33.762484Z", "loop": 5374, "env_steps": 3302399999, "loss": 0.01847279630601406, "avg_return": 0.8601691126823425, "regret": 0.003953846637159586, "entropy": 0.10621470957994461, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:34.616936Z", "loop": 5375, "env_steps": 3303014399, "loss": 0.018113326281309128, "avg_return": 0.8621740937232971, "regret": 0.003953846637159586, "entropy": 0.10320242494344711, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:35.470076Z", "loop": 5376, "env_steps": 3303628799, "loss": 0.018528282642364502, "avg_return": 0.8618972897529602, "regret": 0.003953846637159586, "entropy": 0.1014835312962532, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:36.323995Z", "loop": 5377, "env_steps": 3304243199, "loss": 0.017848152667284012, "avg_return": 0.8615991473197937, "regret": 0.003953846637159586, "entropy": 0.09857838600873947, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:37.177994Z", "loop": 5378, "env_steps": 3304857599, "loss": 0.018756845965981483, "avg_return": 0.8611419796943665, "regret": 0.003953846637159586, "entropy": 0.10306382924318314, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:38.032474Z", "loop": 5379, "env_steps": 3305471999, "loss": 0.017929712310433388, "avg_return": 0.8625168800354004, "regret": 0.003953846637159586, "entropy": 0.09775545448064804, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:38.925608Z", "loop": 5380, "env_steps": 3306086399, "loss": 0.018064631149172783, "avg_return": 0.8618274331092834, "regret": 0.0014865288976579905, "entropy": 0.09933564811944962, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:39.778584Z", "loop": 5381, "env_steps": 3306700799, "loss": 0.018997838720679283, "avg_return": 0.8615767359733582, "regret": 0.0014865288976579905, "entropy": 0.10016874223947525, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:40.632282Z", "loop": 5382, "env_steps": 3307315199, "loss": 0.017695965245366096, "avg_return": 0.863727867603302, "regret": 0.0014865288976579905, "entropy": 0.1000732034444809, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:41.486256Z", "loop": 5383, "env_steps": 3307929599, "loss": 0.01682162471115589, "avg_return": 0.8625435829162598, "regret": 0.0014865288976579905, "entropy": 0.10073169320821762, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:42.340195Z", "loop": 5384, "env_steps": 3308543999, "loss": 0.017529550939798355, "avg_return": 0.8623292446136475, "regret": 0.0014865288976579905, "entropy": 0.10521996021270752, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:43.193518Z", "loop": 5385, "env_steps": 3309158399, "loss": 0.016823194921016693, "avg_return": 0.8614658713340759, "regret": 0.0014865288976579905, "entropy": 0.09353316575288773, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:44.046862Z", "loop": 5386, "env_steps": 3309772799, "loss": 0.017773974686861038, "avg_return": 0.8624602556228638, "regret": 0.0014865288976579905, "entropy": 0.10169993340969086, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:44.900268Z", "loop": 5387, "env_steps": 3310387199, "loss": 0.018260834738612175, "avg_return": 0.8641654849052429, "regret": 0.0014865288976579905, "entropy": 0.09733069688081741, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:45.753834Z", "loop": 5388, "env_steps": 3311001599, "loss": 0.01679142750799656, "avg_return": 0.862143874168396, "regret": 0.0014865288976579905, "entropy": 0.09702486544847488, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:46.607906Z", "loop": 5389, "env_steps": 3311615999, "loss": 0.017645390704274178, "avg_return": 0.8638120889663696, "regret": 0.0014865288976579905, "entropy": 0.09618053585290909, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:47.502165Z", "loop": 5390, "env_steps": 3312230399, "loss": 0.017773063853383064, "avg_return": 0.8612234592437744, "regret": 0.0012003593146800995, "entropy": 0.09650016576051712, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:48.355286Z", "loop": 5391, "env_steps": 3312844799, "loss": 0.01824093423783779, "avg_return": 0.8618559241294861, "regret": 0.0012003593146800995, "entropy": 0.09859603643417358, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:49.209464Z", "loop": 5392, "env_steps": 3313459199, "loss": 0.01839078776538372, "avg_return": 0.8620551824569702, "regret": 0.0012003593146800995, "entropy": 0.10161913931369781, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:50.063940Z", "loop": 5393, "env_steps": 3314073599, "loss": 0.01708589307963848, "avg_return": 0.8614239692687988, "regret": 0.0012003593146800995, "entropy": 0.09577402472496033, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:50.918689Z", "loop": 5394, "env_steps": 3314687999, "loss": 0.018200790509581566, "avg_return": 0.8621126413345337, "regret": 0.0012003593146800995, "entropy": 0.10087524354457855, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:51.772680Z", "loop": 5395, "env_steps": 3315302399, "loss": 0.01891198568046093, "avg_return": 0.8610590696334839, "regret": 0.0012003593146800995, "entropy": 0.10448484867811203, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:52.626860Z", "loop": 5396, "env_steps": 3315916799, "loss": 0.01860971748828888, "avg_return": 0.8620529174804688, "regret": 0.0012003593146800995, "entropy": 0.1040235385298729, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:53.481283Z", "loop": 5397, "env_steps": 3316531199, "loss": 0.018458040431141853, "avg_return": 0.8629463911056519, "regret": 0.0012003593146800995, "entropy": 0.10069574415683746, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:54.334885Z", "loop": 5398, "env_steps": 3317145599, "loss": 0.018321238458156586, "avg_return": 0.8628113269805908, "regret": 0.0012003593146800995, "entropy": 0.10047402232885361, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:55.188112Z", "loop": 5399, "env_steps": 3317759999, "loss": 0.018280355259776115, "avg_return": 0.8606697916984558, "regret": 0.0012003593146800995, "entropy": 0.10665397346019745, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:56.082858Z", "loop": 5400, "env_steps": 3318374399, "loss": 0.019094813615083694, "avg_return": 0.861240565776825, "regret": 0.001637913752347231, "entropy": 0.10684352368116379, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:56.937698Z", "loop": 5401, "env_steps": 3318988799, "loss": 0.017815129831433296, "avg_return": 0.8617945313453674, "regret": 0.001637913752347231, "entropy": 0.10157649219036102, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:57.791979Z", "loop": 5402, "env_steps": 3319603199, "loss": 0.019074851647019386, "avg_return": 0.8621160984039307, "regret": 0.001637913752347231, "entropy": 0.10810290277004242, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:58.646781Z", "loop": 5403, "env_steps": 3320217599, "loss": 0.02086648903787136, "avg_return": 0.8620039820671082, "regret": 0.001637913752347231, "entropy": 0.11150909960269928, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:40:59.501665Z", "loop": 5404, "env_steps": 3320831999, "loss": 0.01918726973235607, "avg_return": 0.8610135316848755, "regret": 0.001637913752347231, "entropy": 0.10552079230546951, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:00.355888Z", "loop": 5405, "env_steps": 3321446399, "loss": 0.018980370834469795, "avg_return": 0.8612278699874878, "regret": 0.001637913752347231, "entropy": 0.10682855546474457, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:01.208833Z", "loop": 5406, "env_steps": 3322060799, "loss": 0.019317662343382835, "avg_return": 0.8622092604637146, "regret": 0.001637913752347231, "entropy": 0.10752851516008377, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:02.062054Z", "loop": 5407, "env_steps": 3322675199, "loss": 0.019583968445658684, "avg_return": 0.862850546836853, "regret": 0.001637913752347231, "entropy": 0.10916408151388168, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:02.915880Z", "loop": 5408, "env_steps": 3323289599, "loss": 0.019640540704131126, "avg_return": 0.8622450232505798, "regret": 0.001637913752347231, "entropy": 0.1086399182677269, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:03.770073Z", "loop": 5409, "env_steps": 3323903999, "loss": 0.01806741952896118, "avg_return": 0.8626229166984558, "regret": 0.001637913752347231, "entropy": 0.10322042554616928, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:04.664621Z", "loop": 5410, "env_steps": 3324518399, "loss": 0.017907360568642616, "avg_return": 0.8617753386497498, "regret": 0.0018775201169773936, "entropy": 0.10304243117570877, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:05.519545Z", "loop": 5411, "env_steps": 3325132799, "loss": 0.01987845078110695, "avg_return": 0.8613397479057312, "regret": 0.0018775201169773936, "entropy": 0.10775355994701385, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:06.374511Z", "loop": 5412, "env_steps": 3325747199, "loss": 0.019102158024907112, "avg_return": 0.860511302947998, "regret": 0.0018775201169773936, "entropy": 0.10606139153242111, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:07.230240Z", "loop": 5413, "env_steps": 3326361599, "loss": 0.01894538290798664, "avg_return": 0.8620589375495911, "regret": 0.0018775201169773936, "entropy": 0.10820158571004868, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:08.086079Z", "loop": 5414, "env_steps": 3326975999, "loss": 0.01858982816338539, "avg_return": 0.8614317178726196, "regret": 0.0018775201169773936, "entropy": 0.10422025620937347, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:08.941487Z", "loop": 5415, "env_steps": 3327590399, "loss": 0.0183344017714262, "avg_return": 0.8613544702529907, "regret": 0.0018775201169773936, "entropy": 0.1034429594874382, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:09.796283Z", "loop": 5416, "env_steps": 3328204799, "loss": 0.019534997642040253, "avg_return": 0.8610543012619019, "regret": 0.0018775201169773936, "entropy": 0.10914427787065506, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:10.650225Z", "loop": 5417, "env_steps": 3328819199, "loss": 0.01892082765698433, "avg_return": 0.8612713813781738, "regret": 0.0018775201169773936, "entropy": 0.1041598990559578, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:11.504559Z", "loop": 5418, "env_steps": 3329433599, "loss": 0.020653171464800835, "avg_return": 0.8580297827720642, "regret": 0.0018775201169773936, "entropy": 0.11399269104003906, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:12.359149Z", "loop": 5419, "env_steps": 3330047999, "loss": 0.020742809399962425, "avg_return": 0.8580436110496521, "regret": 0.0018775201169773936, "entropy": 0.11401129513978958, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:13.254058Z", "loop": 5420, "env_steps": 3330662399, "loss": 0.022384196519851685, "avg_return": 0.856445848941803, "regret": 0.006841940339654684, "entropy": 0.12366126477718353, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:14.108703Z", "loop": 5421, "env_steps": 3331276799, "loss": 0.022573349997401237, "avg_return": 0.8546922206878662, "regret": 0.006841940339654684, "entropy": 0.12295016646385193, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:14.962916Z", "loop": 5422, "env_steps": 3331891199, "loss": 0.024252820760011673, "avg_return": 0.8551743030548096, "regret": 0.006841940339654684, "entropy": 0.13039588928222656, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:15.816836Z", "loop": 5423, "env_steps": 3332505599, "loss": 0.024016885086894035, "avg_return": 0.855943500995636, "regret": 0.006841940339654684, "entropy": 0.12807311117649078, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:16.673250Z", "loop": 5424, "env_steps": 3333119999, "loss": 0.021697787567973137, "avg_return": 0.8553162813186646, "regret": 0.006841940339654684, "entropy": 0.11986957490444183, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:17.528685Z", "loop": 5425, "env_steps": 3333734399, "loss": 0.022896580398082733, "avg_return": 0.8563448190689087, "regret": 0.006841940339654684, "entropy": 0.12240025401115417, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:18.381815Z", "loop": 5426, "env_steps": 3334348799, "loss": 0.023088430985808372, "avg_return": 0.8562095165252686, "regret": 0.006841940339654684, "entropy": 0.12303977459669113, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:19.234989Z", "loop": 5427, "env_steps": 3334963199, "loss": 0.022100483998656273, "avg_return": 0.8575030565261841, "regret": 0.006841940339654684, "entropy": 0.12251797318458557, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:20.089624Z", "loop": 5428, "env_steps": 3335577599, "loss": 0.020118582993745804, "avg_return": 0.8584070205688477, "regret": 0.006841940339654684, "entropy": 0.11613491922616959, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:20.944281Z", "loop": 5429, "env_steps": 3336191999, "loss": 0.02044704742729664, "avg_return": 0.8583676218986511, "regret": 0.006841940339654684, "entropy": 0.11490526795387268, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:21.837792Z", "loop": 5430, "env_steps": 3336806399, "loss": 0.0194851066917181, "avg_return": 0.8607229590415955, "regret": 0.00363095011562109, "entropy": 0.10780646651983261, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:22.690971Z", "loop": 5431, "env_steps": 3337420799, "loss": 0.018612166866660118, "avg_return": 0.8615204095840454, "regret": 0.00363095011562109, "entropy": 0.10657746344804764, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:23.544315Z", "loop": 5432, "env_steps": 3338035199, "loss": 0.01873420923948288, "avg_return": 0.8613523840904236, "regret": 0.00363095011562109, "entropy": 0.1023215502500534, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:24.398547Z", "loop": 5433, "env_steps": 3338649599, "loss": 0.017666364088654518, "avg_return": 0.8621832728385925, "regret": 0.00363095011562109, "entropy": 0.10300911217927933, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:25.252023Z", "loop": 5434, "env_steps": 3339263999, "loss": 0.018373725935816765, "avg_return": 0.8608996868133545, "regret": 0.00363095011562109, "entropy": 0.10243125259876251, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:26.105761Z", "loop": 5435, "env_steps": 3339878399, "loss": 0.01819985918700695, "avg_return": 0.8610813617706299, "regret": 0.00363095011562109, "entropy": 0.10154037922620773, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:26.959685Z", "loop": 5436, "env_steps": 3340492799, "loss": 0.018201714381575584, "avg_return": 0.8628243207931519, "regret": 0.00363095011562109, "entropy": 0.10176894068717957, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:27.813011Z", "loop": 5437, "env_steps": 3341107199, "loss": 0.017110977321863174, "avg_return": 0.8629030585289001, "regret": 0.00363095011562109, "entropy": 0.0975588709115982, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:28.667620Z", "loop": 5438, "env_steps": 3341721599, "loss": 0.018050236627459526, "avg_return": 0.8618574142456055, "regret": 0.00363095011562109, "entropy": 0.09916117042303085, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:29.521482Z", "loop": 5439, "env_steps": 3342335999, "loss": 0.018688146024942398, "avg_return": 0.8625283241271973, "regret": 0.00363095011562109, "entropy": 0.10373875498771667, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:30.415943Z", "loop": 5440, "env_steps": 3342950399, "loss": 0.017100458964705467, "avg_return": 0.862316906452179, "regret": 0.0014324872754514217, "entropy": 0.09630605578422546, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:31.269761Z", "loop": 5441, "env_steps": 3343564799, "loss": 0.019626330584287643, "avg_return": 0.8623082637786865, "regret": 0.0014324872754514217, "entropy": 0.10510905832052231, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:32.123968Z", "loop": 5442, "env_steps": 3344179199, "loss": 0.01780540496110916, "avg_return": 0.8626046180725098, "regret": 0.0014324872754514217, "entropy": 0.10043403506278992, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:32.978315Z", "loop": 5443, "env_steps": 3344793599, "loss": 0.017624234780669212, "avg_return": 0.8622176051139832, "regret": 0.0014324872754514217, "entropy": 0.10239659994840622, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:33.831719Z", "loop": 5444, "env_steps": 3345407999, "loss": 0.018208898603916168, "avg_return": 0.8608083128929138, "regret": 0.0014324872754514217, "entropy": 0.10314981639385223, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:34.685529Z", "loop": 5445, "env_steps": 3346022399, "loss": 0.0172648336738348, "avg_return": 0.8623982667922974, "regret": 0.0014324872754514217, "entropy": 0.10077739506959915, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:35.540168Z", "loop": 5446, "env_steps": 3346636799, "loss": 0.01870747096836567, "avg_return": 0.8630924820899963, "regret": 0.0014324872754514217, "entropy": 0.10331027209758759, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:36.394488Z", "loop": 5447, "env_steps": 3347251199, "loss": 0.018989039584994316, "avg_return": 0.8628420233726501, "regret": 0.0014324872754514217, "entropy": 0.1076992079615593, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:37.248770Z", "loop": 5448, "env_steps": 3347865599, "loss": 0.017630036920309067, "avg_return": 0.8606804609298706, "regret": 0.0014324872754514217, "entropy": 0.1005217507481575, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:38.102275Z", "loop": 5449, "env_steps": 3348479999, "loss": 0.017796559259295464, "avg_return": 0.8607833981513977, "regret": 0.0014324872754514217, "entropy": 0.1002516970038414, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:38.996099Z", "loop": 5450, "env_steps": 3349094399, "loss": 0.0194180216640234, "avg_return": 0.8615342378616333, "regret": 0.001968464581295848, "entropy": 0.10435792803764343, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:39.850828Z", "loop": 5451, "env_steps": 3349708799, "loss": 0.017602859064936638, "avg_return": 0.8599935173988342, "regret": 0.001968464581295848, "entropy": 0.09656239300966263, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:40.704877Z", "loop": 5452, "env_steps": 3350323199, "loss": 0.01823771931231022, "avg_return": 0.861584484577179, "regret": 0.001968464581295848, "entropy": 0.10175744444131851, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:41.561265Z", "loop": 5453, "env_steps": 3350937599, "loss": 0.019107772037386894, "avg_return": 0.8608335852622986, "regret": 0.001968464581295848, "entropy": 0.10471559315919876, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:42.414297Z", "loop": 5454, "env_steps": 3351551999, "loss": 0.01887814700603485, "avg_return": 0.8602018356323242, "regret": 0.001968464581295848, "entropy": 0.10296355187892914, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:43.267714Z", "loop": 5455, "env_steps": 3352166399, "loss": 0.01868678443133831, "avg_return": 0.8597238659858704, "regret": 0.001968464581295848, "entropy": 0.10649745911359787, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:44.122223Z", "loop": 5456, "env_steps": 3352780799, "loss": 0.019068842753767967, "avg_return": 0.8616178631782532, "regret": 0.001968464581295848, "entropy": 0.10757159441709518, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:44.976184Z", "loop": 5457, "env_steps": 3353395199, "loss": 0.018594415858387947, "avg_return": 0.8610333204269409, "regret": 0.001968464581295848, "entropy": 0.10582222789525986, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:45.829508Z", "loop": 5458, "env_steps": 3354009599, "loss": 0.020240411162376404, "avg_return": 0.8625079393386841, "regret": 0.001968464581295848, "entropy": 0.11317705363035202, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:46.682390Z", "loop": 5459, "env_steps": 3354623999, "loss": 0.02073991484940052, "avg_return": 0.8599644303321838, "regret": 0.001968464581295848, "entropy": 0.11637232452630997, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:47.578002Z", "loop": 5460, "env_steps": 3355238399, "loss": 0.01974552869796753, "avg_return": 0.8597939014434814, "regret": 0.003993379883468151, "entropy": 0.1143592894077301, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:48.432639Z", "loop": 5461, "env_steps": 3355852799, "loss": 0.020882323384284973, "avg_return": 0.8608274459838867, "regret": 0.003993379883468151, "entropy": 0.123525470495224, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:49.287074Z", "loop": 5462, "env_steps": 3356467199, "loss": 0.021806588396430016, "avg_return": 0.8594714403152466, "regret": 0.003993379883468151, "entropy": 0.12352616339921951, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:50.141074Z", "loop": 5463, "env_steps": 3357081599, "loss": 0.021480074152350426, "avg_return": 0.8594464063644409, "regret": 0.003993379883468151, "entropy": 0.12185298651456833, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:50.996125Z", "loop": 5464, "env_steps": 3357695999, "loss": 0.022376909852027893, "avg_return": 0.8604514002799988, "regret": 0.003993379883468151, "entropy": 0.1258266568183899, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:51.850456Z", "loop": 5465, "env_steps": 3358310399, "loss": 0.02035772241652012, "avg_return": 0.8601118326187134, "regret": 0.003993379883468151, "entropy": 0.11798958480358124, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:52.704964Z", "loop": 5466, "env_steps": 3358924799, "loss": 0.020348306745290756, "avg_return": 0.8603768944740295, "regret": 0.003993379883468151, "entropy": 0.11575343459844589, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:53.559122Z", "loop": 5467, "env_steps": 3359539199, "loss": 0.02044369839131832, "avg_return": 0.8622128367424011, "regret": 0.003993379883468151, "entropy": 0.11410017311573029, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:54.413518Z", "loop": 5468, "env_steps": 3360153599, "loss": 0.019560961052775383, "avg_return": 0.8618068695068359, "regret": 0.003993379883468151, "entropy": 0.10762172192335129, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:55.267413Z", "loop": 5469, "env_steps": 3360767999, "loss": 0.01955207996070385, "avg_return": 0.8626402020454407, "regret": 0.003993379883468151, "entropy": 0.11085297167301178, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:56.161070Z", "loop": 5470, "env_steps": 3361382399, "loss": 0.018807588145136833, "avg_return": 0.86050945520401, "regret": 0.002642399398609996, "entropy": 0.11140911281108856, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:57.015562Z", "loop": 5471, "env_steps": 3361996799, "loss": 0.018697230145335197, "avg_return": 0.8600659370422363, "regret": 0.002642399398609996, "entropy": 0.1109200045466423, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:57.869494Z", "loop": 5472, "env_steps": 3362611199, "loss": 0.019775984808802605, "avg_return": 0.860505998134613, "regret": 0.002642399398609996, "entropy": 0.10911329835653305, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:58.724386Z", "loop": 5473, "env_steps": 3363225599, "loss": 0.01897299475967884, "avg_return": 0.8612860441207886, "regret": 0.002642399398609996, "entropy": 0.10886503010988235, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:41:59.578357Z", "loop": 5474, "env_steps": 3363839999, "loss": 0.01970306783914566, "avg_return": 0.8606634736061096, "regret": 0.002642399398609996, "entropy": 0.11088045686483383, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:00.432236Z", "loop": 5475, "env_steps": 3364454399, "loss": 0.021525241434574127, "avg_return": 0.8604809641838074, "regret": 0.002642399398609996, "entropy": 0.11356867849826813, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:01.285082Z", "loop": 5476, "env_steps": 3365068799, "loss": 0.018287573009729385, "avg_return": 0.8616070747375488, "regret": 0.002642399398609996, "entropy": 0.10554350912570953, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:02.138379Z", "loop": 5477, "env_steps": 3365683199, "loss": 0.01893453858792782, "avg_return": 0.861060380935669, "regret": 0.002642399398609996, "entropy": 0.10482491552829742, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:02.992128Z", "loop": 5478, "env_steps": 3366297599, "loss": 0.018856503069400787, "avg_return": 0.8627688884735107, "regret": 0.002642399398609996, "entropy": 0.10730666667222977, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:03.846521Z", "loop": 5479, "env_steps": 3366911999, "loss": 0.018884947523474693, "avg_return": 0.8610024452209473, "regret": 0.002642399398609996, "entropy": 0.10342952609062195, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:04.742222Z", "loop": 5480, "env_steps": 3367526399, "loss": 0.016943108290433884, "avg_return": 0.8631874918937683, "regret": 0.0016265354352071881, "entropy": 0.09979553520679474, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:05.596463Z", "loop": 5481, "env_steps": 3368140799, "loss": 0.01658104732632637, "avg_return": 0.8630599975585938, "regret": 0.0016265354352071881, "entropy": 0.09934300929307938, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:06.451401Z", "loop": 5482, "env_steps": 3368755199, "loss": 0.018589837476611137, "avg_return": 0.8616610765457153, "regret": 0.0016265354352071881, "entropy": 0.10397558659315109, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:07.307456Z", "loop": 5483, "env_steps": 3369369599, "loss": 0.01918855868279934, "avg_return": 0.8609122037887573, "regret": 0.0016265354352071881, "entropy": 0.1057608351111412, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:08.161923Z", "loop": 5484, "env_steps": 3369983999, "loss": 0.018135419115424156, "avg_return": 0.8609902262687683, "regret": 0.0016265354352071881, "entropy": 0.10779538005590439, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:09.015758Z", "loop": 5485, "env_steps": 3370598399, "loss": 0.01985015720129013, "avg_return": 0.8613088130950928, "regret": 0.0016265354352071881, "entropy": 0.11228587478399277, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:09.868884Z", "loop": 5486, "env_steps": 3371212799, "loss": 0.020126456394791603, "avg_return": 0.8614140152931213, "regret": 0.0016265354352071881, "entropy": 0.11688698828220367, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:10.723064Z", "loop": 5487, "env_steps": 3371827199, "loss": 0.021088948473334312, "avg_return": 0.8608555197715759, "regret": 0.0016265354352071881, "entropy": 0.11878275126218796, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:11.577070Z", "loop": 5488, "env_steps": 3372441599, "loss": 0.019791221246123314, "avg_return": 0.8609663844108582, "regret": 0.0016265354352071881, "entropy": 0.11890046298503876, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:12.430485Z", "loop": 5489, "env_steps": 3373055999, "loss": 0.020716063678264618, "avg_return": 0.8595542311668396, "regret": 0.0016265354352071881, "entropy": 0.12081540375947952, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:13.325266Z", "loop": 5490, "env_steps": 3373670399, "loss": 0.022075120359659195, "avg_return": 0.8604777455329895, "regret": 0.0036306295078247786, "entropy": 0.12392836064100266, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:14.179482Z", "loop": 5491, "env_steps": 3374284799, "loss": 0.020850850269198418, "avg_return": 0.8604611158370972, "regret": 0.0036306295078247786, "entropy": 0.11556554585695267, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:15.034229Z", "loop": 5492, "env_steps": 3374899199, "loss": 0.021037399768829346, "avg_return": 0.8608254194259644, "regret": 0.0036306295078247786, "entropy": 0.11711472272872925, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:15.889870Z", "loop": 5493, "env_steps": 3375513599, "loss": 0.02053155191242695, "avg_return": 0.8612761497497559, "regret": 0.0036306295078247786, "entropy": 0.11350397020578384, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:16.742369Z", "loop": 5494, "env_steps": 3376127999, "loss": 0.020351234823465347, "avg_return": 0.8610787987709045, "regret": 0.0036306295078247786, "entropy": 0.11498679965734482, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:17.596107Z", "loop": 5495, "env_steps": 3376742399, "loss": 0.019859764724969864, "avg_return": 0.8611858487129211, "regret": 0.0036306295078247786, "entropy": 0.11206136643886566, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:18.450542Z", "loop": 5496, "env_steps": 3377356799, "loss": 0.01767829991877079, "avg_return": 0.8611698746681213, "regret": 0.0036306295078247786, "entropy": 0.10561332106590271, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:19.305904Z", "loop": 5497, "env_steps": 3377971199, "loss": 0.02076781913638115, "avg_return": 0.861781656742096, "regret": 0.0036306295078247786, "entropy": 0.11207543313503265, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:20.159816Z", "loop": 5498, "env_steps": 3378585599, "loss": 0.020701779052615166, "avg_return": 0.8618649244308472, "regret": 0.0036306295078247786, "entropy": 0.11491873115301132, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:21.014153Z", "loop": 5499, "env_steps": 3379199999, "loss": 0.020456010475754738, "avg_return": 0.8614895939826965, "regret": 0.0036306295078247786, "entropy": 0.109935462474823, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:21.908893Z", "loop": 5500, "env_steps": 3379814399, "loss": 0.01930149458348751, "avg_return": 0.8613988161087036, "regret": 0.001825380721129477, "entropy": 0.11118827760219574, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:22.762966Z", "loop": 5501, "env_steps": 3380428799, "loss": 0.018075665459036827, "avg_return": 0.8610492944717407, "regret": 0.001825380721129477, "entropy": 0.10066384077072144, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:23.616783Z", "loop": 5502, "env_steps": 3381043199, "loss": 0.017995482310652733, "avg_return": 0.8628571033477783, "regret": 0.001825380721129477, "entropy": 0.10244851559400558, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:24.470823Z", "loop": 5503, "env_steps": 3381657599, "loss": 0.01823819987475872, "avg_return": 0.8620078563690186, "regret": 0.001825380721129477, "entropy": 0.10200104117393494, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:25.323957Z", "loop": 5504, "env_steps": 3382271999, "loss": 0.019183436408638954, "avg_return": 0.8624973893165588, "regret": 0.001825380721129477, "entropy": 0.10588260740041733, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:26.177408Z", "loop": 5505, "env_steps": 3382886399, "loss": 0.01811867579817772, "avg_return": 0.8620569109916687, "regret": 0.001825380721129477, "entropy": 0.10009971261024475, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:27.031479Z", "loop": 5506, "env_steps": 3383500799, "loss": 0.017193395644426346, "avg_return": 0.8620626926422119, "regret": 0.001825380721129477, "entropy": 0.09964043647050858, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:27.886804Z", "loop": 5507, "env_steps": 3384115199, "loss": 0.01752873696386814, "avg_return": 0.862863302230835, "regret": 0.001825380721129477, "entropy": 0.0991288498044014, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:28.740151Z", "loop": 5508, "env_steps": 3384729599, "loss": 0.018029097467660904, "avg_return": 0.8615412712097168, "regret": 0.001825380721129477, "entropy": 0.09881847351789474, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:29.593522Z", "loop": 5509, "env_steps": 3385343999, "loss": 0.017347950488328934, "avg_return": 0.8608009219169617, "regret": 0.001825380721129477, "entropy": 0.10413675755262375, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:30.487465Z", "loop": 5510, "env_steps": 3385958399, "loss": 0.019019007682800293, "avg_return": 0.8619557619094849, "regret": 0.0021397899836301804, "entropy": 0.10629185289144516, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:31.341762Z", "loop": 5511, "env_steps": 3386572799, "loss": 0.01902739331126213, "avg_return": 0.8608852624893188, "regret": 0.0021397899836301804, "entropy": 0.10782783478498459, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:32.195757Z", "loop": 5512, "env_steps": 3387187199, "loss": 0.019010750576853752, "avg_return": 0.8608834147453308, "regret": 0.0021397899836301804, "entropy": 0.10866384953260422, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:33.049517Z", "loop": 5513, "env_steps": 3387801599, "loss": 0.01869014836847782, "avg_return": 0.8625532388687134, "regret": 0.0021397899836301804, "entropy": 0.10426521301269531, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:33.904047Z", "loop": 5514, "env_steps": 3388415999, "loss": 0.02046000026166439, "avg_return": 0.8615313172340393, "regret": 0.0021397899836301804, "entropy": 0.1113099455833435, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:34.758545Z", "loop": 5515, "env_steps": 3389030399, "loss": 0.020173348486423492, "avg_return": 0.862399697303772, "regret": 0.0021397899836301804, "entropy": 0.11470133066177368, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:35.612060Z", "loop": 5516, "env_steps": 3389644799, "loss": 0.021229660138487816, "avg_return": 0.8593050241470337, "regret": 0.0021397899836301804, "entropy": 0.11612572520971298, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:36.465538Z", "loop": 5517, "env_steps": 3390259199, "loss": 0.019692160189151764, "avg_return": 0.8589009642601013, "regret": 0.0021397899836301804, "entropy": 0.11113463342189789, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:37.319770Z", "loop": 5518, "env_steps": 3390873599, "loss": 0.021256981417536736, "avg_return": 0.8597506880760193, "regret": 0.0021397899836301804, "entropy": 0.11497543007135391, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:38.173775Z", "loop": 5519, "env_steps": 3391487999, "loss": 0.01949390023946762, "avg_return": 0.8601084351539612, "regret": 0.0021397899836301804, "entropy": 0.115989089012146, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:39.066935Z", "loop": 5520, "env_steps": 3392102399, "loss": 0.01834285445511341, "avg_return": 0.8598472476005554, "regret": 0.0028587656561285257, "entropy": 0.10771264135837555, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:39.921199Z", "loop": 5521, "env_steps": 3392716799, "loss": 0.018984563648700714, "avg_return": 0.8624087572097778, "regret": 0.0028587656561285257, "entropy": 0.10572020709514618, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:40.776092Z", "loop": 5522, "env_steps": 3393331199, "loss": 0.01713930442929268, "avg_return": 0.8613157272338867, "regret": 0.0028587656561285257, "entropy": 0.09669572860002518, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:41.630326Z", "loop": 5523, "env_steps": 3393945599, "loss": 0.017819620668888092, "avg_return": 0.8613388538360596, "regret": 0.0028587656561285257, "entropy": 0.09940943866968155, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:42.484085Z", "loop": 5524, "env_steps": 3394559999, "loss": 0.01779871992766857, "avg_return": 0.8607997894287109, "regret": 0.0028587656561285257, "entropy": 0.09921348094940186, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:43.337508Z", "loop": 5525, "env_steps": 3395174399, "loss": 0.018111184239387512, "avg_return": 0.8611117005348206, "regret": 0.0028587656561285257, "entropy": 0.10116596519947052, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:44.191794Z", "loop": 5526, "env_steps": 3395788799, "loss": 0.019747430458664894, "avg_return": 0.860809326171875, "regret": 0.0028587656561285257, "entropy": 0.10495996475219727, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:45.046160Z", "loop": 5527, "env_steps": 3396403199, "loss": 0.019239554181694984, "avg_return": 0.8600206971168518, "regret": 0.0028587656561285257, "entropy": 0.10737592726945877, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:45.900111Z", "loop": 5528, "env_steps": 3397017599, "loss": 0.020175935700535774, "avg_return": 0.8596974611282349, "regret": 0.0028587656561285257, "entropy": 0.10629235208034515, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:46.754727Z", "loop": 5529, "env_steps": 3397631999, "loss": 0.019184080883860588, "avg_return": 0.8599348068237305, "regret": 0.0028587656561285257, "entropy": 0.10768605768680573, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:47.650409Z", "loop": 5530, "env_steps": 3398246399, "loss": 0.018669908866286278, "avg_return": 0.8599969744682312, "regret": 0.003621070645749569, "entropy": 0.10534968227148056, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:48.504061Z", "loop": 5531, "env_steps": 3398860799, "loss": 0.01852702908217907, "avg_return": 0.8599233031272888, "regret": 0.003621070645749569, "entropy": 0.10424800962209702, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:49.358198Z", "loop": 5532, "env_steps": 3399475199, "loss": 0.018563728779554367, "avg_return": 0.8597702980041504, "regret": 0.003621070645749569, "entropy": 0.1042635515332222, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:50.212554Z", "loop": 5533, "env_steps": 3400089599, "loss": 0.01756995916366577, "avg_return": 0.8597678542137146, "regret": 0.003621070645749569, "entropy": 0.09886335581541061, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:51.066957Z", "loop": 5534, "env_steps": 3400703999, "loss": 0.017808636650443077, "avg_return": 0.8618727922439575, "regret": 0.003621070645749569, "entropy": 0.10005784034729004, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:51.919360Z", "loop": 5535, "env_steps": 3401318399, "loss": 0.016720805317163467, "avg_return": 0.8623067140579224, "regret": 0.003621070645749569, "entropy": 0.09380636364221573, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:52.771999Z", "loop": 5536, "env_steps": 3401932799, "loss": 0.01776946522295475, "avg_return": 0.8615655899047852, "regret": 0.003621070645749569, "entropy": 0.09478621929883957, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:53.626054Z", "loop": 5537, "env_steps": 3402547199, "loss": 0.01833302341401577, "avg_return": 0.8607370257377625, "regret": 0.003621070645749569, "entropy": 0.09936103969812393, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:54.479328Z", "loop": 5538, "env_steps": 3403161599, "loss": 0.018199807032942772, "avg_return": 0.8625015616416931, "regret": 0.003621070645749569, "entropy": 0.10133136063814163, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:55.331994Z", "loop": 5539, "env_steps": 3403775999, "loss": 0.017481300979852676, "avg_return": 0.8620609641075134, "regret": 0.003621070645749569, "entropy": 0.09901808947324753, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:56.225976Z", "loop": 5540, "env_steps": 3404390399, "loss": 0.01728563942015171, "avg_return": 0.8626235127449036, "regret": 0.001134598278440535, "entropy": 0.09602758288383484, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:57.079727Z", "loop": 5541, "env_steps": 3405004799, "loss": 0.015913022682070732, "avg_return": 0.8606870770454407, "regret": 0.001134598278440535, "entropy": 0.09222027659416199, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:57.933395Z", "loop": 5542, "env_steps": 3405619199, "loss": 0.017143212258815765, "avg_return": 0.863234281539917, "regret": 0.001134598278440535, "entropy": 0.0951296016573906, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:58.787681Z", "loop": 5543, "env_steps": 3406233599, "loss": 0.018251044675707817, "avg_return": 0.8622443675994873, "regret": 0.001134598278440535, "entropy": 0.09864512085914612, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:42:59.640171Z", "loop": 5544, "env_steps": 3406847999, "loss": 0.01738280989229679, "avg_return": 0.8624264001846313, "regret": 0.001134598278440535, "entropy": 0.0991324931383133, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:00.493004Z", "loop": 5545, "env_steps": 3407462399, "loss": 0.01786571368575096, "avg_return": 0.8596457839012146, "regret": 0.001134598278440535, "entropy": 0.10307654738426208, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:01.347567Z", "loop": 5546, "env_steps": 3408076799, "loss": 0.01852375641465187, "avg_return": 0.8606553077697754, "regret": 0.001134598278440535, "entropy": 0.10245195031166077, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:02.203401Z", "loop": 5547, "env_steps": 3408691199, "loss": 0.02016489952802658, "avg_return": 0.861954391002655, "regret": 0.001134598278440535, "entropy": 0.10838741064071655, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:03.057557Z", "loop": 5548, "env_steps": 3409305599, "loss": 0.017814336344599724, "avg_return": 0.8604558706283569, "regret": 0.001134598278440535, "entropy": 0.09984701871871948, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:03.911238Z", "loop": 5549, "env_steps": 3409919999, "loss": 0.019102221354842186, "avg_return": 0.8612139821052551, "regret": 0.001134598278440535, "entropy": 0.10602175444364548, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:04.807280Z", "loop": 5550, "env_steps": 3410534399, "loss": 0.019774915650486946, "avg_return": 0.8598777651786804, "regret": 0.0019201295217499137, "entropy": 0.10756171494722366, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:05.661285Z", "loop": 5551, "env_steps": 3411148799, "loss": 0.018948359414935112, "avg_return": 0.8611272573471069, "regret": 0.0019201295217499137, "entropy": 0.10754115134477615, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:06.515902Z", "loop": 5552, "env_steps": 3411763199, "loss": 0.018693042919039726, "avg_return": 0.8630005121231079, "regret": 0.0019201295217499137, "entropy": 0.10859588533639908, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:07.369177Z", "loop": 5553, "env_steps": 3412377599, "loss": 0.01797989197075367, "avg_return": 0.8615812659263611, "regret": 0.0019201295217499137, "entropy": 0.10456958413124084, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:08.225108Z", "loop": 5554, "env_steps": 3412991999, "loss": 0.02059701830148697, "avg_return": 0.8604967594146729, "regret": 0.0019201295217499137, "entropy": 0.11115389317274094, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:09.079816Z", "loop": 5555, "env_steps": 3413606399, "loss": 0.01812874525785446, "avg_return": 0.8605120182037354, "regret": 0.0019201295217499137, "entropy": 0.10766423493623734, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:09.933770Z", "loop": 5556, "env_steps": 3414220799, "loss": 0.018707439303398132, "avg_return": 0.8608811497688293, "regret": 0.0019201295217499137, "entropy": 0.10333286225795746, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:10.787755Z", "loop": 5557, "env_steps": 3414835199, "loss": 0.020122256129980087, "avg_return": 0.8616658449172974, "regret": 0.0019201295217499137, "entropy": 0.11101680248975754, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:11.643770Z", "loop": 5558, "env_steps": 3415449599, "loss": 0.018398242071270943, "avg_return": 0.8608622550964355, "regret": 0.0019201295217499137, "entropy": 0.10426715016365051, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:12.498998Z", "loop": 5559, "env_steps": 3416063999, "loss": 0.020276809111237526, "avg_return": 0.8611444234848022, "regret": 0.0019201295217499137, "entropy": 0.10841525346040726, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:13.396374Z", "loop": 5560, "env_steps": 3416678399, "loss": 0.018568791449069977, "avg_return": 0.8607458472251892, "regret": 0.00186470418702811, "entropy": 0.10393384844064713, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:14.250576Z", "loop": 5561, "env_steps": 3417292799, "loss": 0.018966466188430786, "avg_return": 0.8619828224182129, "regret": 0.00186470418702811, "entropy": 0.10714983940124512, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:15.104920Z", "loop": 5562, "env_steps": 3417907199, "loss": 0.019100625067949295, "avg_return": 0.8619940280914307, "regret": 0.00186470418702811, "entropy": 0.10717764496803284, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:15.958357Z", "loop": 5563, "env_steps": 3418521599, "loss": 0.017733870074152946, "avg_return": 0.8618209958076477, "regret": 0.00186470418702811, "entropy": 0.09925302118062973, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:16.811685Z", "loop": 5564, "env_steps": 3419135999, "loss": 0.018310902640223503, "avg_return": 0.863051176071167, "regret": 0.00186470418702811, "entropy": 0.10180369764566422, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:17.665306Z", "loop": 5565, "env_steps": 3419750399, "loss": 0.01701020821928978, "avg_return": 0.8610947728157043, "regret": 0.00186470418702811, "entropy": 0.09698960930109024, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:18.519860Z", "loop": 5566, "env_steps": 3420364799, "loss": 0.017220471054315567, "avg_return": 0.8623006343841553, "regret": 0.00186470418702811, "entropy": 0.09742565453052521, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:19.373943Z", "loop": 5567, "env_steps": 3420979199, "loss": 0.01754583977162838, "avg_return": 0.8612522482872009, "regret": 0.00186470418702811, "entropy": 0.09835387021303177, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:20.227037Z", "loop": 5568, "env_steps": 3421593599, "loss": 0.016802005469799042, "avg_return": 0.8622020483016968, "regret": 0.00186470418702811, "entropy": 0.09726658463478088, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:21.080551Z", "loop": 5569, "env_steps": 3422207999, "loss": 0.017710810527205467, "avg_return": 0.8612697720527649, "regret": 0.00186470418702811, "entropy": 0.09812051057815552, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:21.976333Z", "loop": 5570, "env_steps": 3422822399, "loss": 0.018773922696709633, "avg_return": 0.8621153235435486, "regret": 0.0019858814775943756, "entropy": 0.10296975076198578, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:22.830041Z", "loop": 5571, "env_steps": 3423436799, "loss": 0.019891859963536263, "avg_return": 0.8615968823432922, "regret": 0.0019858814775943756, "entropy": 0.10637170821428299, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:23.683445Z", "loop": 5572, "env_steps": 3424051199, "loss": 0.01736542396247387, "avg_return": 0.861250638961792, "regret": 0.0019858814775943756, "entropy": 0.09990447014570236, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:24.537561Z", "loop": 5573, "env_steps": 3424665599, "loss": 0.01753937639296055, "avg_return": 0.8611220717430115, "regret": 0.0019858814775943756, "entropy": 0.09509878605604172, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:25.392494Z", "loop": 5574, "env_steps": 3425279999, "loss": 0.018052486702799797, "avg_return": 0.8626039624214172, "regret": 0.0019858814775943756, "entropy": 0.10172490030527115, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:26.246087Z", "loop": 5575, "env_steps": 3425894399, "loss": 0.017602046951651573, "avg_return": 0.8616974353790283, "regret": 0.0019858814775943756, "entropy": 0.10216273367404938, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:27.099797Z", "loop": 5576, "env_steps": 3426508799, "loss": 0.017099576070904732, "avg_return": 0.8613244891166687, "regret": 0.0019858814775943756, "entropy": 0.10183747857809067, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:27.953350Z", "loop": 5577, "env_steps": 3427123199, "loss": 0.019576622173190117, "avg_return": 0.8614792227745056, "regret": 0.0019858814775943756, "entropy": 0.10757188498973846, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:28.808017Z", "loop": 5578, "env_steps": 3427737599, "loss": 0.02141619846224785, "avg_return": 0.858514130115509, "regret": 0.0019858814775943756, "entropy": 0.11812150478363037, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:29.662007Z", "loop": 5579, "env_steps": 3428351999, "loss": 0.02499617263674736, "avg_return": 0.85383141040802, "regret": 0.0019858814775943756, "entropy": 0.13256104290485382, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:30.555594Z", "loop": 5580, "env_steps": 3428966399, "loss": 0.027541279792785645, "avg_return": 0.8495863080024719, "regret": 0.014889146201312542, "entropy": 0.145392045378685, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:31.409724Z", "loop": 5581, "env_steps": 3429580799, "loss": 0.022847888991236687, "avg_return": 0.855728805065155, "regret": 0.014889146201312542, "entropy": 0.12714144587516785, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:32.265487Z", "loop": 5582, "env_steps": 3430195199, "loss": 0.019766082987189293, "avg_return": 0.8619958758354187, "regret": 0.014889146201312542, "entropy": 0.11323250085115433, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:33.119851Z", "loop": 5583, "env_steps": 3430809599, "loss": 0.016623124480247498, "avg_return": 0.8623590469360352, "regret": 0.014889146201312542, "entropy": 0.10116519033908844, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:33.973521Z", "loop": 5584, "env_steps": 3431423999, "loss": 0.017480432987213135, "avg_return": 0.8623449802398682, "regret": 0.014889146201312542, "entropy": 0.10042938590049744, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:34.827405Z", "loop": 5585, "env_steps": 3432038399, "loss": 0.017710139974951744, "avg_return": 0.8630838990211487, "regret": 0.014889146201312542, "entropy": 0.1010626032948494, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:35.682452Z", "loop": 5586, "env_steps": 3432652799, "loss": 0.019169753417372704, "avg_return": 0.8624117970466614, "regret": 0.014889146201312542, "entropy": 0.10775486379861832, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:36.537675Z", "loop": 5587, "env_steps": 3433267199, "loss": 0.019434886053204536, "avg_return": 0.8619198799133301, "regret": 0.014889146201312542, "entropy": 0.10953345894813538, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:37.392040Z", "loop": 5588, "env_steps": 3433881599, "loss": 0.02044627070426941, "avg_return": 0.8587049841880798, "regret": 0.014889146201312542, "entropy": 0.11216570436954498, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:38.246445Z", "loop": 5589, "env_steps": 3434495999, "loss": 0.021936263889074326, "avg_return": 0.8588141798973083, "regret": 0.014889146201312542, "entropy": 0.11305860430002213, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:39.141818Z", "loop": 5590, "env_steps": 3435110399, "loss": 0.022688589990139008, "avg_return": 0.8559073805809021, "regret": 0.007671944331377745, "entropy": 0.12039898335933685, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:39.998141Z", "loop": 5591, "env_steps": 3435724799, "loss": 0.021970661357045174, "avg_return": 0.8556334376335144, "regret": 0.007671944331377745, "entropy": 0.11729520559310913, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:40.851870Z", "loop": 5592, "env_steps": 3436339199, "loss": 0.020513353869318962, "avg_return": 0.8547079563140869, "regret": 0.007671944331377745, "entropy": 0.111793652176857, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:41.705311Z", "loop": 5593, "env_steps": 3436953599, "loss": 0.02136257104575634, "avg_return": 0.8568362593650818, "regret": 0.007671944331377745, "entropy": 0.11885540187358856, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:42.559144Z", "loop": 5594, "env_steps": 3437567999, "loss": 0.020965157076716423, "avg_return": 0.8590224385261536, "regret": 0.007671944331377745, "entropy": 0.11913597583770752, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:43.412063Z", "loop": 5595, "env_steps": 3438182399, "loss": 0.021136796101927757, "avg_return": 0.8607151508331299, "regret": 0.007671944331377745, "entropy": 0.11797308176755905, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:44.267246Z", "loop": 5596, "env_steps": 3438796799, "loss": 0.02180343121290207, "avg_return": 0.8605920672416687, "regret": 0.007671944331377745, "entropy": 0.12399028241634369, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:45.120961Z", "loop": 5597, "env_steps": 3439411199, "loss": 0.02037574164569378, "avg_return": 0.8618247509002686, "regret": 0.007671944331377745, "entropy": 0.11730043590068817, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:45.974159Z", "loop": 5598, "env_steps": 3440025599, "loss": 0.020251141861081123, "avg_return": 0.862067461013794, "regret": 0.007671944331377745, "entropy": 0.1159888505935669, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:46.827602Z", "loop": 5599, "env_steps": 3440639999, "loss": 0.021965930238366127, "avg_return": 0.8598877191543579, "regret": 0.007671944331377745, "entropy": 0.12498599290847778, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:47.721067Z", "loop": 5600, "env_steps": 3441254399, "loss": 0.0208993349224329, "avg_return": 0.8611345887184143, "regret": 0.0032441921066492796, "entropy": 0.12025297433137894, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:48.574680Z", "loop": 5601, "env_steps": 3441868799, "loss": 0.022654814645648003, "avg_return": 0.8600106835365295, "regret": 0.0032441921066492796, "entropy": 0.12064383924007416, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:49.429631Z", "loop": 5602, "env_steps": 3442483199, "loss": 0.021844256669282913, "avg_return": 0.8596041202545166, "regret": 0.0032441921066492796, "entropy": 0.12164965271949768, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:50.283102Z", "loop": 5603, "env_steps": 3443097599, "loss": 0.02162943221628666, "avg_return": 0.8608851432800293, "regret": 0.0032441921066492796, "entropy": 0.12212410569190979, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:51.136400Z", "loop": 5604, "env_steps": 3443711999, "loss": 0.019734671339392662, "avg_return": 0.8596833348274231, "regret": 0.0032441921066492796, "entropy": 0.11458044499158859, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:51.989941Z", "loop": 5605, "env_steps": 3444326399, "loss": 0.02149079740047455, "avg_return": 0.8615819215774536, "regret": 0.0032441921066492796, "entropy": 0.12300737202167511, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:52.843247Z", "loop": 5606, "env_steps": 3444940799, "loss": 0.02115664817392826, "avg_return": 0.8596808314323425, "regret": 0.0032441921066492796, "entropy": 0.12130896002054214, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:53.696874Z", "loop": 5607, "env_steps": 3445555199, "loss": 0.022318892180919647, "avg_return": 0.8596954345703125, "regret": 0.0032441921066492796, "entropy": 0.12592656910419464, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:54.551581Z", "loop": 5608, "env_steps": 3446169599, "loss": 0.021948492154479027, "avg_return": 0.86099773645401, "regret": 0.0032441921066492796, "entropy": 0.12583716213703156, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:55.405424Z", "loop": 5609, "env_steps": 3446783999, "loss": 0.02210903726518154, "avg_return": 0.8604221940040588, "regret": 0.0032441921066492796, "entropy": 0.12416758388280869, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:56.299941Z", "loop": 5610, "env_steps": 3447398399, "loss": 0.02270779386162758, "avg_return": 0.8597384095191956, "regret": 0.004244896117597818, "entropy": 0.1283043920993805, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:57.154007Z", "loop": 5611, "env_steps": 3448012799, "loss": 0.022752659395337105, "avg_return": 0.8589133024215698, "regret": 0.004244896117597818, "entropy": 0.13278822600841522, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:58.008179Z", "loop": 5612, "env_steps": 3448627199, "loss": 0.02280094474554062, "avg_return": 0.8573819398880005, "regret": 0.004244896117597818, "entropy": 0.13328835368156433, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:58.863308Z", "loop": 5613, "env_steps": 3449241599, "loss": 0.023721780627965927, "avg_return": 0.858308732509613, "regret": 0.004244896117597818, "entropy": 0.1360941380262375, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:43:59.719098Z", "loop": 5614, "env_steps": 3449855999, "loss": 0.02187908999621868, "avg_return": 0.8583644032478333, "regret": 0.004244896117597818, "entropy": 0.12782219052314758, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:00.574878Z", "loop": 5615, "env_steps": 3450470399, "loss": 0.021314231678843498, "avg_return": 0.8592734932899475, "regret": 0.004244896117597818, "entropy": 0.12355370819568634, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:01.430629Z", "loop": 5616, "env_steps": 3451084799, "loss": 0.022065386176109314, "avg_return": 0.8597898483276367, "regret": 0.004244896117597818, "entropy": 0.11992624402046204, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:02.287058Z", "loop": 5617, "env_steps": 3451699199, "loss": 0.020766304805874825, "avg_return": 0.86136394739151, "regret": 0.004244896117597818, "entropy": 0.11767783015966415, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:03.143002Z", "loop": 5618, "env_steps": 3452313599, "loss": 0.020884640514850616, "avg_return": 0.8618996143341064, "regret": 0.004244896117597818, "entropy": 0.11829493194818497, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:03.998398Z", "loop": 5619, "env_steps": 3452927999, "loss": 0.018434561789035797, "avg_return": 0.8620102405548096, "regret": 0.004244896117597818, "entropy": 0.10479346662759781, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:04.894052Z", "loop": 5620, "env_steps": 3453542399, "loss": 0.020123407244682312, "avg_return": 0.8615800142288208, "regret": 0.0019337573321536183, "entropy": 0.11004962772130966, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:05.746969Z", "loop": 5621, "env_steps": 3454156799, "loss": 0.019240915775299072, "avg_return": 0.8600358366966248, "regret": 0.0019337573321536183, "entropy": 0.10984913259744644, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:06.599826Z", "loop": 5622, "env_steps": 3454771199, "loss": 0.020838988944888115, "avg_return": 0.8606848120689392, "regret": 0.0019337573321536183, "entropy": 0.11027979105710983, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:07.454214Z", "loop": 5623, "env_steps": 3455385599, "loss": 0.02122766152024269, "avg_return": 0.8606199622154236, "regret": 0.0019337573321536183, "entropy": 0.11799696832895279, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:08.308627Z", "loop": 5624, "env_steps": 3455999999, "loss": 0.019295668229460716, "avg_return": 0.8610532879829407, "regret": 0.0019337573321536183, "entropy": 0.11140089482069016, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:09.163344Z", "loop": 5625, "env_steps": 3456614399, "loss": 0.02166745439171791, "avg_return": 0.8610295653343201, "regret": 0.0019337573321536183, "entropy": 0.11999290436506271, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:10.016886Z", "loop": 5626, "env_steps": 3457228799, "loss": 0.02111893892288208, "avg_return": 0.8612944483757019, "regret": 0.0019337573321536183, "entropy": 0.11220411211252213, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:10.871045Z", "loop": 5627, "env_steps": 3457843199, "loss": 0.020907102152705193, "avg_return": 0.8609405755996704, "regret": 0.0019337573321536183, "entropy": 0.11567656695842743, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:11.725834Z", "loop": 5628, "env_steps": 3458457599, "loss": 0.02156410738825798, "avg_return": 0.8595272302627563, "regret": 0.0019337573321536183, "entropy": 0.12083190679550171, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:12.580323Z", "loop": 5629, "env_steps": 3459071999, "loss": 0.02098146267235279, "avg_return": 0.86149662733078, "regret": 0.0019337573321536183, "entropy": 0.11796458065509796, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:13.474763Z", "loop": 5630, "env_steps": 3459686399, "loss": 0.020486215129494667, "avg_return": 0.8614272475242615, "regret": 0.0026264020707458258, "entropy": 0.11525838077068329, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:14.328682Z", "loop": 5631, "env_steps": 3460300799, "loss": 0.02106408402323723, "avg_return": 0.8610519766807556, "regret": 0.0026264020707458258, "entropy": 0.11851698905229568, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:15.183387Z", "loop": 5632, "env_steps": 3460915199, "loss": 0.01967705972492695, "avg_return": 0.8615549206733704, "regret": 0.0026264020707458258, "entropy": 0.10862748324871063, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:16.038409Z", "loop": 5633, "env_steps": 3461529599, "loss": 0.020194275304675102, "avg_return": 0.8623008131980896, "regret": 0.0026264020707458258, "entropy": 0.1106075793504715, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:16.892494Z", "loop": 5634, "env_steps": 3462143999, "loss": 0.018547601997852325, "avg_return": 0.8604950308799744, "regret": 0.0026264020707458258, "entropy": 0.10962376743555069, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:17.746292Z", "loop": 5635, "env_steps": 3462758399, "loss": 0.018854552879929543, "avg_return": 0.8622348308563232, "regret": 0.0026264020707458258, "entropy": 0.1082896888256073, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:18.600904Z", "loop": 5636, "env_steps": 3463372799, "loss": 0.01842634193599224, "avg_return": 0.8619210124015808, "regret": 0.0026264020707458258, "entropy": 0.10830464959144592, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:19.455799Z", "loop": 5637, "env_steps": 3463987199, "loss": 0.01973581686615944, "avg_return": 0.8635626435279846, "regret": 0.0026264020707458258, "entropy": 0.10839660465717316, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:20.310223Z", "loop": 5638, "env_steps": 3464601599, "loss": 0.018956029787659645, "avg_return": 0.8615432977676392, "regret": 0.0026264020707458258, "entropy": 0.10080724209547043, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:21.163306Z", "loop": 5639, "env_steps": 3465215999, "loss": 0.019214970991015434, "avg_return": 0.8612778186798096, "regret": 0.0026264020707458258, "entropy": 0.10666535794734955, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:22.057656Z", "loop": 5640, "env_steps": 3465830399, "loss": 0.019256478175520897, "avg_return": 0.8629390597343445, "regret": 0.001704927533864975, "entropy": 0.10977640748023987, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:22.911954Z", "loop": 5641, "env_steps": 3466444799, "loss": 0.019691167399287224, "avg_return": 0.8603355288505554, "regret": 0.001704927533864975, "entropy": 0.10954498499631882, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:23.765971Z", "loop": 5642, "env_steps": 3467059199, "loss": 0.01924034021794796, "avg_return": 0.8626821041107178, "regret": 0.001704927533864975, "entropy": 0.10728930681943893, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:24.619876Z", "loop": 5643, "env_steps": 3467673599, "loss": 0.019608011469244957, "avg_return": 0.8616069555282593, "regret": 0.001704927533864975, "entropy": 0.10918056964874268, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:25.473911Z", "loop": 5644, "env_steps": 3468287999, "loss": 0.01999976672232151, "avg_return": 0.8612803220748901, "regret": 0.001704927533864975, "entropy": 0.11361877620220184, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:26.328316Z", "loop": 5645, "env_steps": 3468902399, "loss": 0.017864422872662544, "avg_return": 0.8600172400474548, "regret": 0.001704927533864975, "entropy": 0.1048586294054985, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:27.182977Z", "loop": 5646, "env_steps": 3469516799, "loss": 0.01828792132437229, "avg_return": 0.8622170090675354, "regret": 0.001704927533864975, "entropy": 0.10550589859485626, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:28.037027Z", "loop": 5647, "env_steps": 3470131199, "loss": 0.018987400457262993, "avg_return": 0.8620368838310242, "regret": 0.001704927533864975, "entropy": 0.10651542991399765, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:28.891116Z", "loop": 5648, "env_steps": 3470745599, "loss": 0.01708807609975338, "avg_return": 0.8630713820457458, "regret": 0.001704927533864975, "entropy": 0.10104959458112717, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:29.744614Z", "loop": 5649, "env_steps": 3471359999, "loss": 0.016614949330687523, "avg_return": 0.8617786765098572, "regret": 0.001704927533864975, "entropy": 0.09316762536764145, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:30.639287Z", "loop": 5650, "env_steps": 3471974399, "loss": 0.016722187399864197, "avg_return": 0.8622967600822449, "regret": 0.0012505293125286698, "entropy": 0.09094160050153732, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:31.494944Z", "loop": 5651, "env_steps": 3472588799, "loss": 0.01622183434665203, "avg_return": 0.8626088500022888, "regret": 0.0012505293125286698, "entropy": 0.09027351438999176, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:32.349687Z", "loop": 5652, "env_steps": 3473203199, "loss": 0.016409857198596, "avg_return": 0.8611041307449341, "regret": 0.0012505293125286698, "entropy": 0.0920560285449028, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:33.203504Z", "loop": 5653, "env_steps": 3473817599, "loss": 0.016212573274970055, "avg_return": 0.8617323040962219, "regret": 0.0012505293125286698, "entropy": 0.09218836575746536, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:34.056938Z", "loop": 5654, "env_steps": 3474431999, "loss": 0.01652608811855316, "avg_return": 0.8627099990844727, "regret": 0.0012505293125286698, "entropy": 0.0905359759926796, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:34.913755Z", "loop": 5655, "env_steps": 3475046399, "loss": 0.016527382656931877, "avg_return": 0.862105131149292, "regret": 0.0012505293125286698, "entropy": 0.09352938085794449, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:35.767869Z", "loop": 5656, "env_steps": 3475660799, "loss": 0.016684850677847862, "avg_return": 0.8625357151031494, "regret": 0.0012505293125286698, "entropy": 0.09311719983816147, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:36.622306Z", "loop": 5657, "env_steps": 3476275199, "loss": 0.016696413978934288, "avg_return": 0.8627716302871704, "regret": 0.0012505293125286698, "entropy": 0.09134651720523834, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:37.476564Z", "loop": 5658, "env_steps": 3476889599, "loss": 0.01628098450601101, "avg_return": 0.8624929785728455, "regret": 0.0012505293125286698, "entropy": 0.09301989525556564, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:38.331782Z", "loop": 5659, "env_steps": 3477503999, "loss": 0.016390360891819, "avg_return": 0.8631266355514526, "regret": 0.0012505293125286698, "entropy": 0.09164044260978699, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:39.226616Z", "loop": 5660, "env_steps": 3478118399, "loss": 0.017001068219542503, "avg_return": 0.8633061051368713, "regret": 0.001291970256716013, "entropy": 0.09556092321872711, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:40.081337Z", "loop": 5661, "env_steps": 3478732799, "loss": 0.01701572723686695, "avg_return": 0.8610632419586182, "regret": 0.001291970256716013, "entropy": 0.09131833910942078, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:40.933776Z", "loop": 5662, "env_steps": 3479347199, "loss": 0.017772076651453972, "avg_return": 0.8622571229934692, "regret": 0.001291970256716013, "entropy": 0.09713566303253174, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:41.786791Z", "loop": 5663, "env_steps": 3479961599, "loss": 0.0174977108836174, "avg_return": 0.8618184328079224, "regret": 0.001291970256716013, "entropy": 0.09507428854703903, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:42.641562Z", "loop": 5664, "env_steps": 3480575999, "loss": 0.0175973828881979, "avg_return": 0.8628520965576172, "regret": 0.001291970256716013, "entropy": 0.09500983357429504, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:43.495427Z", "loop": 5665, "env_steps": 3481190399, "loss": 0.016249217092990875, "avg_return": 0.8611210584640503, "regret": 0.001291970256716013, "entropy": 0.09393667429685593, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:44.348975Z", "loop": 5666, "env_steps": 3481804799, "loss": 0.016862990334630013, "avg_return": 0.8625626564025879, "regret": 0.001291970256716013, "entropy": 0.0943450853228569, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:45.203117Z", "loop": 5667, "env_steps": 3482419199, "loss": 0.016787230968475342, "avg_return": 0.8628631830215454, "regret": 0.001291970256716013, "entropy": 0.09171244502067566, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:46.056994Z", "loop": 5668, "env_steps": 3483033599, "loss": 0.017542093992233276, "avg_return": 0.8641131520271301, "regret": 0.001291970256716013, "entropy": 0.09501945227384567, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:46.910982Z", "loop": 5669, "env_steps": 3483647999, "loss": 0.018142033368349075, "avg_return": 0.8643426895141602, "regret": 0.001291970256716013, "entropy": 0.09722646325826645, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:47.804710Z", "loop": 5670, "env_steps": 3484262399, "loss": 0.01715988479554653, "avg_return": 0.862550675868988, "regret": 0.0010613540653139353, "entropy": 0.09472846984863281, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:48.659353Z", "loop": 5671, "env_steps": 3484876799, "loss": 0.017635375261306763, "avg_return": 0.8614501953125, "regret": 0.0010613540653139353, "entropy": 0.09867268055677414, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:49.514775Z", "loop": 5672, "env_steps": 3485491199, "loss": 0.016830312088131905, "avg_return": 0.8638277649879456, "regret": 0.0010613540653139353, "entropy": 0.09457900375127792, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:50.369354Z", "loop": 5673, "env_steps": 3486105599, "loss": 0.01683398149907589, "avg_return": 0.8631929755210876, "regret": 0.0010613540653139353, "entropy": 0.09498047083616257, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:51.224811Z", "loop": 5674, "env_steps": 3486719999, "loss": 0.01728791929781437, "avg_return": 0.8623603582382202, "regret": 0.0010613540653139353, "entropy": 0.10036226361989975, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:52.080722Z", "loop": 5675, "env_steps": 3487334399, "loss": 0.017416689544916153, "avg_return": 0.8632391691207886, "regret": 0.0010613540653139353, "entropy": 0.09862041473388672, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:52.934819Z", "loop": 5676, "env_steps": 3487948799, "loss": 0.017859678715467453, "avg_return": 0.8632014989852905, "regret": 0.0010613540653139353, "entropy": 0.1001397967338562, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:53.789158Z", "loop": 5677, "env_steps": 3488563199, "loss": 0.01669463887810707, "avg_return": 0.8628818988800049, "regret": 0.0010613540653139353, "entropy": 0.09969880431890488, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:54.644760Z", "loop": 5678, "env_steps": 3489177599, "loss": 0.018223484978079796, "avg_return": 0.862605631351471, "regret": 0.0010613540653139353, "entropy": 0.10213296115398407, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:55.500077Z", "loop": 5679, "env_steps": 3489791999, "loss": 0.01748652569949627, "avg_return": 0.8628368377685547, "regret": 0.0010613540653139353, "entropy": 0.09816783666610718, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:56.393956Z", "loop": 5680, "env_steps": 3490406399, "loss": 0.0171778853982687, "avg_return": 0.8631834387779236, "regret": 0.0014817510964348912, "entropy": 0.10038240998983383, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:57.247252Z", "loop": 5681, "env_steps": 3491020799, "loss": 0.02018403820693493, "avg_return": 0.8616154193878174, "regret": 0.0014817510964348912, "entropy": 0.11264456808567047, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:58.102356Z", "loop": 5682, "env_steps": 3491635199, "loss": 0.019490277394652367, "avg_return": 0.8603102564811707, "regret": 0.0014817510964348912, "entropy": 0.11039955914020538, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:58.958399Z", "loop": 5683, "env_steps": 3492249599, "loss": 0.018920352682471275, "avg_return": 0.8618568181991577, "regret": 0.0014817510964348912, "entropy": 0.11144644767045975, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:44:59.814188Z", "loop": 5684, "env_steps": 3492863999, "loss": 0.02015703171491623, "avg_return": 0.8605322241783142, "regret": 0.0014817510964348912, "entropy": 0.11246237903833389, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:00.668865Z", "loop": 5685, "env_steps": 3493478399, "loss": 0.018623588606715202, "avg_return": 0.8611694574356079, "regret": 0.0014817510964348912, "entropy": 0.10905437171459198, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:01.524713Z", "loop": 5686, "env_steps": 3494092799, "loss": 0.019243082031607628, "avg_return": 0.8603925704956055, "regret": 0.0014817510964348912, "entropy": 0.1134871318936348, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:02.382406Z", "loop": 5687, "env_steps": 3494707199, "loss": 0.020004263147711754, "avg_return": 0.8615778088569641, "regret": 0.0014817510964348912, "entropy": 0.11502812057733536, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:03.238720Z", "loop": 5688, "env_steps": 3495321599, "loss": 0.018985316157341003, "avg_return": 0.8610689640045166, "regret": 0.0014817510964348912, "entropy": 0.10870035737752914, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:04.093649Z", "loop": 5689, "env_steps": 3495935999, "loss": 0.01934475265443325, "avg_return": 0.8602274656295776, "regret": 0.0014817510964348912, "entropy": 0.11064482480287552, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:04.990110Z", "loop": 5690, "env_steps": 3496550399, "loss": 0.019268082454800606, "avg_return": 0.8612914085388184, "regret": 0.002769401064142585, "entropy": 0.10730333626270294, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:05.844506Z", "loop": 5691, "env_steps": 3497164799, "loss": 0.019695302471518517, "avg_return": 0.8616155982017517, "regret": 0.002769401064142585, "entropy": 0.11266856640577316, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:06.699393Z", "loop": 5692, "env_steps": 3497779199, "loss": 0.019001418724656105, "avg_return": 0.86174076795578, "regret": 0.002769401064142585, "entropy": 0.11330372840166092, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:07.554212Z", "loop": 5693, "env_steps": 3498393599, "loss": 0.020274167880415916, "avg_return": 0.8606436252593994, "regret": 0.002769401064142585, "entropy": 0.11160960793495178, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:08.408727Z", "loop": 5694, "env_steps": 3499007999, "loss": 0.01844976097345352, "avg_return": 0.8602848649024963, "regret": 0.002769401064142585, "entropy": 0.10734744369983673, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:09.263389Z", "loop": 5695, "env_steps": 3499622399, "loss": 0.01847515068948269, "avg_return": 0.8614729046821594, "regret": 0.002769401064142585, "entropy": 0.10423148423433304, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:10.117897Z", "loop": 5696, "env_steps": 3500236799, "loss": 0.017432672902941704, "avg_return": 0.8625909686088562, "regret": 0.002769401064142585, "entropy": 0.10022059082984924, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:10.971943Z", "loop": 5697, "env_steps": 3500851199, "loss": 0.019286254420876503, "avg_return": 0.8619470596313477, "regret": 0.002769401064142585, "entropy": 0.10592070966959, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:11.825230Z", "loop": 5698, "env_steps": 3501465599, "loss": 0.017993411049246788, "avg_return": 0.8625246286392212, "regret": 0.002769401064142585, "entropy": 0.09943881630897522, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:12.681228Z", "loop": 5699, "env_steps": 3502079999, "loss": 0.017961999401450157, "avg_return": 0.8626804947853088, "regret": 0.002769401064142585, "entropy": 0.09796284884214401, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:13.579056Z", "loop": 5700, "env_steps": 3502694399, "loss": 0.017192378640174866, "avg_return": 0.8635535836219788, "regret": 0.0009907418861985207, "entropy": 0.09769314527511597, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:14.433796Z", "loop": 5701, "env_steps": 3503308799, "loss": 0.018064355477690697, "avg_return": 0.8626230955123901, "regret": 0.0009907418861985207, "entropy": 0.10064227133989334, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:15.289246Z", "loop": 5702, "env_steps": 3503923199, "loss": 0.01684465818107128, "avg_return": 0.8623701930046082, "regret": 0.0009907418861985207, "entropy": 0.09540685266256332, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:16.143851Z", "loop": 5703, "env_steps": 3504537599, "loss": 0.017269281670451164, "avg_return": 0.8622244596481323, "regret": 0.0009907418861985207, "entropy": 0.0948617160320282, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:16.997756Z", "loop": 5704, "env_steps": 3505151999, "loss": 0.01670006476342678, "avg_return": 0.86329185962677, "regret": 0.0009907418861985207, "entropy": 0.0927780419588089, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:17.852492Z", "loop": 5705, "env_steps": 3505766399, "loss": 0.016356831416487694, "avg_return": 0.8612583875656128, "regret": 0.0009907418861985207, "entropy": 0.09107906371355057, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:18.707028Z", "loop": 5706, "env_steps": 3506380799, "loss": 0.01694558933377266, "avg_return": 0.8630102872848511, "regret": 0.0009907418861985207, "entropy": 0.09387495368719101, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:19.561727Z", "loop": 5707, "env_steps": 3506995199, "loss": 0.018404019996523857, "avg_return": 0.8612172603607178, "regret": 0.0009907418861985207, "entropy": 0.09921926259994507, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:20.416285Z", "loop": 5708, "env_steps": 3507609599, "loss": 0.016967585310339928, "avg_return": 0.860940158367157, "regret": 0.0009907418861985207, "entropy": 0.09830883890390396, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:21.270583Z", "loop": 5709, "env_steps": 3508223999, "loss": 0.018726404756307602, "avg_return": 0.8596386909484863, "regret": 0.0009907418861985207, "entropy": 0.10555871576070786, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:22.164819Z", "loop": 5710, "env_steps": 3508838399, "loss": 0.02031216025352478, "avg_return": 0.8604941964149475, "regret": 0.004180485848337412, "entropy": 0.10934097319841385, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:23.018966Z", "loop": 5711, "env_steps": 3509452799, "loss": 0.01960131712257862, "avg_return": 0.8578773140907288, "regret": 0.004180485848337412, "entropy": 0.11005734652280807, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:23.871575Z", "loop": 5712, "env_steps": 3510067199, "loss": 0.01977703534066677, "avg_return": 0.8582919239997864, "regret": 0.004180485848337412, "entropy": 0.10887020081281662, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:24.724838Z", "loop": 5713, "env_steps": 3510681599, "loss": 0.02053377404808998, "avg_return": 0.8582104444503784, "regret": 0.004180485848337412, "entropy": 0.11243488639593124, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:25.579113Z", "loop": 5714, "env_steps": 3511295999, "loss": 0.01821490190923214, "avg_return": 0.8606459498405457, "regret": 0.004180485848337412, "entropy": 0.10536879301071167, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:26.434062Z", "loop": 5715, "env_steps": 3511910399, "loss": 0.018913155421614647, "avg_return": 0.8608193397521973, "regret": 0.004180485848337412, "entropy": 0.10600005835294724, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:27.288235Z", "loop": 5716, "env_steps": 3512524799, "loss": 0.016804421320557594, "avg_return": 0.8620176315307617, "regret": 0.004180485848337412, "entropy": 0.09517396986484528, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:28.142248Z", "loop": 5717, "env_steps": 3513139199, "loss": 0.015752652660012245, "avg_return": 0.8611204028129578, "regret": 0.004180485848337412, "entropy": 0.08884283155202866, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:28.996407Z", "loop": 5718, "env_steps": 3513753599, "loss": 0.017361043021082878, "avg_return": 0.862069308757782, "regret": 0.004180485848337412, "entropy": 0.09617207199335098, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:29.850061Z", "loop": 5719, "env_steps": 3514367999, "loss": 0.016577942296862602, "avg_return": 0.862300455570221, "regret": 0.004180485848337412, "entropy": 0.09308341145515442, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:30.744645Z", "loop": 5720, "env_steps": 3514982399, "loss": 0.01653888076543808, "avg_return": 0.8617759346961975, "regret": 0.0021704910323023796, "entropy": 0.0926625207066536, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:31.597513Z", "loop": 5721, "env_steps": 3515596799, "loss": 0.01664707437157631, "avg_return": 0.8623185157775879, "regret": 0.0021704910323023796, "entropy": 0.09415514022111893, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:32.450933Z", "loop": 5722, "env_steps": 3516211199, "loss": 0.018144650384783745, "avg_return": 0.8601289987564087, "regret": 0.0021704910323023796, "entropy": 0.09859920293092728, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:33.305635Z", "loop": 5723, "env_steps": 3516825599, "loss": 0.016862429678440094, "avg_return": 0.8608748316764832, "regret": 0.0021704910323023796, "entropy": 0.0918319821357727, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:34.160534Z", "loop": 5724, "env_steps": 3517439999, "loss": 0.01834443397819996, "avg_return": 0.8604826927185059, "regret": 0.0021704910323023796, "entropy": 0.09899979084730148, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:35.014174Z", "loop": 5725, "env_steps": 3518054399, "loss": 0.016838258132338524, "avg_return": 0.8610554337501526, "regret": 0.0021704910323023796, "entropy": 0.09558891505002975, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:35.868838Z", "loop": 5726, "env_steps": 3518668799, "loss": 0.017485318705439568, "avg_return": 0.8620251417160034, "regret": 0.0021704910323023796, "entropy": 0.09592142701148987, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:36.723680Z", "loop": 5727, "env_steps": 3519283199, "loss": 0.01692379079759121, "avg_return": 0.8612784743309021, "regret": 0.0021704910323023796, "entropy": 0.09310853481292725, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:37.578585Z", "loop": 5728, "env_steps": 3519897599, "loss": 0.015870267525315285, "avg_return": 0.8606424927711487, "regret": 0.0021704910323023796, "entropy": 0.09000033140182495, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:38.433080Z", "loop": 5729, "env_steps": 3520511999, "loss": 0.018025211989879608, "avg_return": 0.8619509339332581, "regret": 0.0021704910323023796, "entropy": 0.09617719799280167, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:39.326430Z", "loop": 5730, "env_steps": 3521126399, "loss": 0.020206226035952568, "avg_return": 0.861238956451416, "regret": 0.0022403416223824024, "entropy": 0.1021755114197731, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:40.189043Z", "loop": 5731, "env_steps": 3521740799, "loss": 0.019301269203424454, "avg_return": 0.861224889755249, "regret": 0.0022403416223824024, "entropy": 0.10702201724052429, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:41.043380Z", "loop": 5732, "env_steps": 3522355199, "loss": 0.017983408644795418, "avg_return": 0.8599031567573547, "regret": 0.0022403416223824024, "entropy": 0.09734348207712173, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:41.898530Z", "loop": 5733, "env_steps": 3522969599, "loss": 0.017302105203270912, "avg_return": 0.8614001870155334, "regret": 0.0022403416223824024, "entropy": 0.09439479559659958, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:42.751981Z", "loop": 5734, "env_steps": 3523583999, "loss": 0.016932474449276924, "avg_return": 0.8615291714668274, "regret": 0.0022403416223824024, "entropy": 0.097466379404068, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:43.605974Z", "loop": 5735, "env_steps": 3524198399, "loss": 0.018419256433844566, "avg_return": 0.8625630140304565, "regret": 0.0022403416223824024, "entropy": 0.10055212676525116, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:44.459923Z", "loop": 5736, "env_steps": 3524812799, "loss": 0.018688371405005455, "avg_return": 0.8619957566261292, "regret": 0.0022403416223824024, "entropy": 0.09928975254297256, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:45.313656Z", "loop": 5737, "env_steps": 3525427199, "loss": 0.017393963411450386, "avg_return": 0.8595483899116516, "regret": 0.0022403416223824024, "entropy": 0.10190259665250778, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:46.167323Z", "loop": 5738, "env_steps": 3526041599, "loss": 0.018290508538484573, "avg_return": 0.8601595163345337, "regret": 0.0022403416223824024, "entropy": 0.10386934876441956, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:47.021282Z", "loop": 5739, "env_steps": 3526655999, "loss": 0.018822191283106804, "avg_return": 0.8602384924888611, "regret": 0.0022403416223824024, "entropy": 0.10606939345598221, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:47.915379Z", "loop": 5740, "env_steps": 3527270399, "loss": 0.018566077575087547, "avg_return": 0.8606311082839966, "regret": 0.0025702016428112984, "entropy": 0.1070115715265274, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:48.769179Z", "loop": 5741, "env_steps": 3527884799, "loss": 0.019538307562470436, "avg_return": 0.8602607250213623, "regret": 0.0025702016428112984, "entropy": 0.10611861944198608, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:49.622703Z", "loop": 5742, "env_steps": 3528499199, "loss": 0.019392793998122215, "avg_return": 0.8611059784889221, "regret": 0.0025702016428112984, "entropy": 0.10781991481781006, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:50.477739Z", "loop": 5743, "env_steps": 3529113599, "loss": 0.018239231780171394, "avg_return": 0.8603019118309021, "regret": 0.0025702016428112984, "entropy": 0.10522714257240295, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:51.330955Z", "loop": 5744, "env_steps": 3529727999, "loss": 0.018496094271540642, "avg_return": 0.8608061671257019, "regret": 0.0025702016428112984, "entropy": 0.10330081731081009, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:52.183887Z", "loop": 5745, "env_steps": 3530342399, "loss": 0.01828690618276596, "avg_return": 0.8616155982017517, "regret": 0.0025702016428112984, "entropy": 0.10740971565246582, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:53.038087Z", "loop": 5746, "env_steps": 3530956799, "loss": 0.01783568039536476, "avg_return": 0.8620687127113342, "regret": 0.0025702016428112984, "entropy": 0.10283543169498444, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:53.893357Z", "loop": 5747, "env_steps": 3531571199, "loss": 0.01838010735809803, "avg_return": 0.8614287376403809, "regret": 0.0025702016428112984, "entropy": 0.10338255763053894, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:54.747333Z", "loop": 5748, "env_steps": 3532185599, "loss": 0.01821197383105755, "avg_return": 0.8622230291366577, "regret": 0.0025702016428112984, "entropy": 0.10153628140687943, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:55.600365Z", "loop": 5749, "env_steps": 3532799999, "loss": 0.018092971295118332, "avg_return": 0.8611482977867126, "regret": 0.0025702016428112984, "entropy": 0.09937301278114319, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:56.493957Z", "loop": 5750, "env_steps": 3533414399, "loss": 0.01701926626265049, "avg_return": 0.8629091382026672, "regret": 0.0016199704259634018, "entropy": 0.09899190813302994, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:57.347753Z", "loop": 5751, "env_steps": 3534028799, "loss": 0.01818968541920185, "avg_return": 0.8610135316848755, "regret": 0.0016199704259634018, "entropy": 0.09960860759019852, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:58.201723Z", "loop": 5752, "env_steps": 3534643199, "loss": 0.01741849072277546, "avg_return": 0.8630748987197876, "regret": 0.0016199704259634018, "entropy": 0.09624598175287247, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:59.055055Z", "loop": 5753, "env_steps": 3535257599, "loss": 0.019792944192886353, "avg_return": 0.8619776368141174, "regret": 0.0016199704259634018, "entropy": 0.1039390042424202, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:45:59.909000Z", "loop": 5754, "env_steps": 3535871999, "loss": 0.01778021827340126, "avg_return": 0.8623736500740051, "regret": 0.0016199704259634018, "entropy": 0.09661021828651428, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:00.763536Z", "loop": 5755, "env_steps": 3536486399, "loss": 0.017452025786042213, "avg_return": 0.8637823462486267, "regret": 0.0016199704259634018, "entropy": 0.1010647565126419, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:01.617992Z", "loop": 5756, "env_steps": 3537100799, "loss": 0.018216613680124283, "avg_return": 0.8626919984817505, "regret": 0.0016199704259634018, "entropy": 0.10212820023298264, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:02.470533Z", "loop": 5757, "env_steps": 3537715199, "loss": 0.018461620435118675, "avg_return": 0.862348735332489, "regret": 0.0016199704259634018, "entropy": 0.10284049808979034, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:03.325036Z", "loop": 5758, "env_steps": 3538329599, "loss": 0.017143091186881065, "avg_return": 0.8632845282554626, "regret": 0.0016199704259634018, "entropy": 0.10074369609355927, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:04.179051Z", "loop": 5759, "env_steps": 3538943999, "loss": 0.020881667733192444, "avg_return": 0.8621162176132202, "regret": 0.0016199704259634018, "entropy": 0.11316071450710297, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:05.075539Z", "loop": 5760, "env_steps": 3539558399, "loss": 0.019997594878077507, "avg_return": 0.8602690100669861, "regret": 0.0018654927844181657, "entropy": 0.11406217515468597, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:05.930070Z", "loop": 5761, "env_steps": 3540172799, "loss": 0.022961098700761795, "avg_return": 0.8618221282958984, "regret": 0.0018654927844181657, "entropy": 0.12553411722183228, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:06.784730Z", "loop": 5762, "env_steps": 3540787199, "loss": 0.022301942110061646, "avg_return": 0.8606942892074585, "regret": 0.0018654927844181657, "entropy": 0.12846435606479645, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:07.638623Z", "loop": 5763, "env_steps": 3541401599, "loss": 0.022672457620501518, "avg_return": 0.8579109907150269, "regret": 0.0018654927844181657, "entropy": 0.13220742344856262, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:08.492996Z", "loop": 5764, "env_steps": 3542015999, "loss": 0.022807253524661064, "avg_return": 0.8595882654190063, "regret": 0.0018654927844181657, "entropy": 0.1327807456254959, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:09.348141Z", "loop": 5765, "env_steps": 3542630399, "loss": 0.021832076832652092, "avg_return": 0.8586423993110657, "regret": 0.0018654927844181657, "entropy": 0.1224760040640831, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:10.202946Z", "loop": 5766, "env_steps": 3543244799, "loss": 0.02123609185218811, "avg_return": 0.8602264523506165, "regret": 0.0018654927844181657, "entropy": 0.1254226416349411, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:11.057833Z", "loop": 5767, "env_steps": 3543859199, "loss": 0.02001889795064926, "avg_return": 0.8605489134788513, "regret": 0.0018654927844181657, "entropy": 0.11347401142120361, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:11.912029Z", "loop": 5768, "env_steps": 3544473599, "loss": 0.020155703648924828, "avg_return": 0.8625956177711487, "regret": 0.0018654927844181657, "entropy": 0.11602301895618439, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:12.767318Z", "loop": 5769, "env_steps": 3545087999, "loss": 0.018157830461859703, "avg_return": 0.8616754412651062, "regret": 0.0018654927844181657, "entropy": 0.1078915148973465, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:13.663498Z", "loop": 5770, "env_steps": 3545702399, "loss": 0.019222106784582138, "avg_return": 0.8631398677825928, "regret": 0.001249197288416326, "entropy": 0.10885414481163025, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:14.517775Z", "loop": 5771, "env_steps": 3546316799, "loss": 0.01891256682574749, "avg_return": 0.8618401288986206, "regret": 0.001249197288416326, "entropy": 0.10604646056890488, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:15.372913Z", "loop": 5772, "env_steps": 3546931199, "loss": 0.018266884610056877, "avg_return": 0.8608801364898682, "regret": 0.001249197288416326, "entropy": 0.10552355647087097, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:16.228702Z", "loop": 5773, "env_steps": 3547545599, "loss": 0.019313519820570946, "avg_return": 0.8625540137290955, "regret": 0.001249197288416326, "entropy": 0.10844805836677551, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:17.084098Z", "loop": 5774, "env_steps": 3548159999, "loss": 0.018866602331399918, "avg_return": 0.8629046678543091, "regret": 0.001249197288416326, "entropy": 0.10805869847536087, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:17.938298Z", "loop": 5775, "env_steps": 3548774399, "loss": 0.020030958577990532, "avg_return": 0.8630993962287903, "regret": 0.001249197288416326, "entropy": 0.1110382154583931, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:18.792493Z", "loop": 5776, "env_steps": 3549388799, "loss": 0.019309738650918007, "avg_return": 0.8621183633804321, "regret": 0.001249197288416326, "entropy": 0.1094685047864914, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:19.647397Z", "loop": 5777, "env_steps": 3550003199, "loss": 0.01900382898747921, "avg_return": 0.8625595569610596, "regret": 0.001249197288416326, "entropy": 0.10976634174585342, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:20.502212Z", "loop": 5778, "env_steps": 3550617599, "loss": 0.019416678696870804, "avg_return": 0.8625530004501343, "regret": 0.001249197288416326, "entropy": 0.11024882644414902, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:21.356457Z", "loop": 5779, "env_steps": 3551231999, "loss": 0.022760821506381035, "avg_return": 0.8624966740608215, "regret": 0.001249197288416326, "entropy": 0.11933283507823944, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:22.250698Z", "loop": 5780, "env_steps": 3551846399, "loss": 0.02085955999791622, "avg_return": 0.8614984154701233, "regret": 0.002039457904174924, "entropy": 0.11860569566488266, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:23.103992Z", "loop": 5781, "env_steps": 3552460799, "loss": 0.021416660398244858, "avg_return": 0.8613799214363098, "regret": 0.002039457904174924, "entropy": 0.11694445461034775, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:23.958052Z", "loop": 5782, "env_steps": 3553075199, "loss": 0.0232172142714262, "avg_return": 0.8580491542816162, "regret": 0.002039457904174924, "entropy": 0.12573492527008057, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:24.812473Z", "loop": 5783, "env_steps": 3553689599, "loss": 0.02511662058532238, "avg_return": 0.8585395216941833, "regret": 0.002039457904174924, "entropy": 0.1320810317993164, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:25.666493Z", "loop": 5784, "env_steps": 3554303999, "loss": 0.023374592885375023, "avg_return": 0.8553221821784973, "regret": 0.002039457904174924, "entropy": 0.12789073586463928, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:26.520295Z", "loop": 5785, "env_steps": 3554918399, "loss": 0.02575700916349888, "avg_return": 0.8545098900794983, "regret": 0.002039457904174924, "entropy": 0.1297329068183899, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:27.375377Z", "loop": 5786, "env_steps": 3555532799, "loss": 0.02534639649093151, "avg_return": 0.8553975820541382, "regret": 0.002039457904174924, "entropy": 0.13167054951190948, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:28.230769Z", "loop": 5787, "env_steps": 3556147199, "loss": 0.024286044761538506, "avg_return": 0.8569720387458801, "regret": 0.002039457904174924, "entropy": 0.1374286413192749, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:29.086089Z", "loop": 5788, "env_steps": 3556761599, "loss": 0.02331421710550785, "avg_return": 0.859520673751831, "regret": 0.002039457904174924, "entropy": 0.1271055042743683, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:29.940279Z", "loop": 5789, "env_steps": 3557375999, "loss": 0.023365575820207596, "avg_return": 0.858683705329895, "regret": 0.002039457904174924, "entropy": 0.13238412141799927, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:30.837429Z", "loop": 5790, "env_steps": 3557990399, "loss": 0.02432394213974476, "avg_return": 0.8601426482200623, "regret": 0.003433533012866974, "entropy": 0.1301480084657669, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:31.691423Z", "loop": 5791, "env_steps": 3558604799, "loss": 0.022266415879130363, "avg_return": 0.8605068922042847, "regret": 0.003433533012866974, "entropy": 0.12504324316978455, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:32.545722Z", "loop": 5792, "env_steps": 3559219199, "loss": 0.02223913185298443, "avg_return": 0.8608141541481018, "regret": 0.003433533012866974, "entropy": 0.12360332161188126, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:33.399674Z", "loop": 5793, "env_steps": 3559833599, "loss": 0.022018281742930412, "avg_return": 0.860530436038971, "regret": 0.003433533012866974, "entropy": 0.12224073708057404, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:34.254230Z", "loop": 5794, "env_steps": 3560447999, "loss": 0.021120978519320488, "avg_return": 0.8617634177207947, "regret": 0.003433533012866974, "entropy": 0.12114790827035904, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:35.108000Z", "loop": 5795, "env_steps": 3561062399, "loss": 0.021202512085437775, "avg_return": 0.8619633316993713, "regret": 0.003433533012866974, "entropy": 0.11645673960447311, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:35.962524Z", "loop": 5796, "env_steps": 3561676799, "loss": 0.019663140177726746, "avg_return": 0.8629604578018188, "regret": 0.003433533012866974, "entropy": 0.1117246001958847, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:36.818127Z", "loop": 5797, "env_steps": 3562291199, "loss": 0.019192541018128395, "avg_return": 0.8625736832618713, "regret": 0.003433533012866974, "entropy": 0.10871895402669907, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:37.672155Z", "loop": 5798, "env_steps": 3562905599, "loss": 0.01838253065943718, "avg_return": 0.862064003944397, "regret": 0.003433533012866974, "entropy": 0.10316742956638336, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:38.525732Z", "loop": 5799, "env_steps": 3563519999, "loss": 0.020083419978618622, "avg_return": 0.8617088794708252, "regret": 0.003433533012866974, "entropy": 0.11116765439510345, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:39.420161Z", "loop": 5800, "env_steps": 3564134399, "loss": 0.019375545904040337, "avg_return": 0.8619217276573181, "regret": 0.0010165367275476456, "entropy": 0.1061631515622139, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:40.275092Z", "loop": 5801, "env_steps": 3564748799, "loss": 0.019283173605799675, "avg_return": 0.8631457686424255, "regret": 0.0010165367275476456, "entropy": 0.10544293373823166, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:41.129239Z", "loop": 5802, "env_steps": 3565363199, "loss": 0.018820980563759804, "avg_return": 0.8619074821472168, "regret": 0.0010165367275476456, "entropy": 0.10189424455165863, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:41.981453Z", "loop": 5803, "env_steps": 3565977599, "loss": 0.017454126849770546, "avg_return": 0.8617757558822632, "regret": 0.0010165367275476456, "entropy": 0.09957811236381531, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:42.834135Z", "loop": 5804, "env_steps": 3566591999, "loss": 0.01798226684331894, "avg_return": 0.8627093434333801, "regret": 0.0010165367275476456, "entropy": 0.09786761552095413, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:43.689152Z", "loop": 5805, "env_steps": 3567206399, "loss": 0.019016293808817863, "avg_return": 0.86130291223526, "regret": 0.0010165367275476456, "entropy": 0.10578694194555283, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:44.542994Z", "loop": 5806, "env_steps": 3567820799, "loss": 0.017962224781513214, "avg_return": 0.8621159195899963, "regret": 0.0010165367275476456, "entropy": 0.10187333822250366, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:45.396118Z", "loop": 5807, "env_steps": 3568435199, "loss": 0.018896909430623055, "avg_return": 0.8606606125831604, "regret": 0.0010165367275476456, "entropy": 0.10121505707502365, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:46.249543Z", "loop": 5808, "env_steps": 3569049599, "loss": 0.016254978254437447, "avg_return": 0.8614770770072937, "regret": 0.0010165367275476456, "entropy": 0.08973052352666855, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:47.104063Z", "loop": 5809, "env_steps": 3569663999, "loss": 0.01717790775001049, "avg_return": 0.863008975982666, "regret": 0.0010165367275476456, "entropy": 0.09630752354860306, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:47.998986Z", "loop": 5810, "env_steps": 3570278399, "loss": 0.01774921640753746, "avg_return": 0.8620955348014832, "regret": 0.0009887154446914792, "entropy": 0.09609117358922958, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:48.853541Z", "loop": 5811, "env_steps": 3570892799, "loss": 0.016459856182336807, "avg_return": 0.8630955219268799, "regret": 0.0009887154446914792, "entropy": 0.09166555851697922, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:49.707555Z", "loop": 5812, "env_steps": 3571507199, "loss": 0.017097406089305878, "avg_return": 0.8618803024291992, "regret": 0.0009887154446914792, "entropy": 0.09610260277986526, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:50.562505Z", "loop": 5813, "env_steps": 3572121599, "loss": 0.01560803223401308, "avg_return": 0.8624411225318909, "regret": 0.0009887154446914792, "entropy": 0.09345372021198273, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:51.417305Z", "loop": 5814, "env_steps": 3572735999, "loss": 0.017725644633173943, "avg_return": 0.8610832095146179, "regret": 0.0009887154446914792, "entropy": 0.10066114366054535, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:52.271451Z", "loop": 5815, "env_steps": 3573350399, "loss": 0.019221974536776543, "avg_return": 0.8609448671340942, "regret": 0.0009887154446914792, "entropy": 0.10490509867668152, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:53.125521Z", "loop": 5816, "env_steps": 3573964799, "loss": 0.01828424446284771, "avg_return": 0.8613688349723816, "regret": 0.0009887154446914792, "entropy": 0.10286962985992432, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:53.980555Z", "loop": 5817, "env_steps": 3574579199, "loss": 0.019807374104857445, "avg_return": 0.8584287762641907, "regret": 0.0009887154446914792, "entropy": 0.11029959470033646, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:54.835631Z", "loop": 5818, "env_steps": 3575193599, "loss": 0.021263843402266502, "avg_return": 0.8578521013259888, "regret": 0.0009887154446914792, "entropy": 0.11348230391740799, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:55.691028Z", "loop": 5819, "env_steps": 3575807999, "loss": 0.021014951169490814, "avg_return": 0.8561770915985107, "regret": 0.0009887154446914792, "entropy": 0.11247149854898453, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:56.586555Z", "loop": 5820, "env_steps": 3576422399, "loss": 0.021835675463080406, "avg_return": 0.8564737439155579, "regret": 0.006172605324536562, "entropy": 0.11336375027894974, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:57.440017Z", "loop": 5821, "env_steps": 3577036799, "loss": 0.019466271623969078, "avg_return": 0.8589203357696533, "regret": 0.006172605324536562, "entropy": 0.10749501734972, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:58.292926Z", "loop": 5822, "env_steps": 3577651199, "loss": 0.020421547815203667, "avg_return": 0.8590912222862244, "regret": 0.006172605324536562, "entropy": 0.10873502492904663, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:46:59.147374Z", "loop": 5823, "env_steps": 3578265599, "loss": 0.019412819296121597, "avg_return": 0.8612799048423767, "regret": 0.006172605324536562, "entropy": 0.10318762063980103, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:00.001737Z", "loop": 5824, "env_steps": 3578879999, "loss": 0.017328230664134026, "avg_return": 0.8611885905265808, "regret": 0.006172605324536562, "entropy": 0.09768373519182205, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:00.855544Z", "loop": 5825, "env_steps": 3579494399, "loss": 0.0171828456223011, "avg_return": 0.8597685098648071, "regret": 0.006172605324536562, "entropy": 0.09532333165407181, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:01.709491Z", "loop": 5826, "env_steps": 3580108799, "loss": 0.017492758110165596, "avg_return": 0.862215518951416, "regret": 0.006172605324536562, "entropy": 0.09749239683151245, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:02.564113Z", "loop": 5827, "env_steps": 3580723199, "loss": 0.017424769699573517, "avg_return": 0.8636675477027893, "regret": 0.006172605324536562, "entropy": 0.09450965374708176, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:03.418761Z", "loop": 5828, "env_steps": 3581337599, "loss": 0.016129901632666588, "avg_return": 0.8616982102394104, "regret": 0.006172605324536562, "entropy": 0.0904908999800682, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:04.273106Z", "loop": 5829, "env_steps": 3581951999, "loss": 0.018129227682948112, "avg_return": 0.8628954291343689, "regret": 0.006172605324536562, "entropy": 0.09783604741096497, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:05.166307Z", "loop": 5830, "env_steps": 3582566399, "loss": 0.017353234812617302, "avg_return": 0.8620445132255554, "regret": 0.001029269304126501, "entropy": 0.0962979793548584, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:06.019916Z", "loop": 5831, "env_steps": 3583180799, "loss": 0.017440274357795715, "avg_return": 0.8617286086082458, "regret": 0.001029269304126501, "entropy": 0.09530185908079147, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:06.874648Z", "loop": 5832, "env_steps": 3583795199, "loss": 0.017035534605383873, "avg_return": 0.8628525137901306, "regret": 0.001029269304126501, "entropy": 0.09633157402276993, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:07.730777Z", "loop": 5833, "env_steps": 3584409599, "loss": 0.016674969345331192, "avg_return": 0.8615342378616333, "regret": 0.001029269304126501, "entropy": 0.09687831252813339, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:08.585778Z", "loop": 5834, "env_steps": 3585023999, "loss": 0.018870361149311066, "avg_return": 0.8615387082099915, "regret": 0.001029269304126501, "entropy": 0.1014794111251831, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:09.440781Z", "loop": 5835, "env_steps": 3585638399, "loss": 0.017545675858855247, "avg_return": 0.8616925477981567, "regret": 0.001029269304126501, "entropy": 0.09965130686759949, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:10.296610Z", "loop": 5836, "env_steps": 3586252799, "loss": 0.018455376848578453, "avg_return": 0.8601504564285278, "regret": 0.001029269304126501, "entropy": 0.10413892567157745, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:11.151821Z", "loop": 5837, "env_steps": 3586867199, "loss": 0.017852917313575745, "avg_return": 0.8613051772117615, "regret": 0.001029269304126501, "entropy": 0.10032036155462265, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:12.008074Z", "loop": 5838, "env_steps": 3587481599, "loss": 0.017936449497938156, "avg_return": 0.8618723750114441, "regret": 0.001029269304126501, "entropy": 0.09982367604970932, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:12.863132Z", "loop": 5839, "env_steps": 3588095999, "loss": 0.01843901537358761, "avg_return": 0.8602072596549988, "regret": 0.001029269304126501, "entropy": 0.10576560348272324, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:13.758204Z", "loop": 5840, "env_steps": 3588710399, "loss": 0.01809275895357132, "avg_return": 0.8602176308631897, "regret": 0.002030751435086131, "entropy": 0.1002998948097229, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:14.615455Z", "loop": 5841, "env_steps": 3589324799, "loss": 0.01841246709227562, "avg_return": 0.8627556562423706, "regret": 0.002030751435086131, "entropy": 0.10425037145614624, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:15.472187Z", "loop": 5842, "env_steps": 3589939199, "loss": 0.01686595380306244, "avg_return": 0.861221969127655, "regret": 0.002030751435086131, "entropy": 0.09598448127508163, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:16.327386Z", "loop": 5843, "env_steps": 3590553599, "loss": 0.01725979708135128, "avg_return": 0.8611487746238708, "regret": 0.002030751435086131, "entropy": 0.09167907387018204, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:17.183626Z", "loop": 5844, "env_steps": 3591167999, "loss": 0.016013532876968384, "avg_return": 0.8620194792747498, "regret": 0.002030751435086131, "entropy": 0.09226405620574951, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:18.039515Z", "loop": 5845, "env_steps": 3591782399, "loss": 0.016753943637013435, "avg_return": 0.8620855808258057, "regret": 0.002030751435086131, "entropy": 0.09336204826831818, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:18.895555Z", "loop": 5846, "env_steps": 3592396799, "loss": 0.01878710463643074, "avg_return": 0.8620815277099609, "regret": 0.002030751435086131, "entropy": 0.09734905511140823, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:19.751174Z", "loop": 5847, "env_steps": 3593011199, "loss": 0.017405468970537186, "avg_return": 0.8627842664718628, "regret": 0.002030751435086131, "entropy": 0.0977972075343132, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:20.605890Z", "loop": 5848, "env_steps": 3593625599, "loss": 0.017218416556715965, "avg_return": 0.8601718544960022, "regret": 0.002030751435086131, "entropy": 0.09518148750066757, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:21.460748Z", "loop": 5849, "env_steps": 3594239999, "loss": 0.0171805527061224, "avg_return": 0.8607698678970337, "regret": 0.002030751435086131, "entropy": 0.09527430683374405, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:22.356888Z", "loop": 5850, "env_steps": 3594854399, "loss": 0.017855657264590263, "avg_return": 0.8612338304519653, "regret": 0.0026065753772854805, "entropy": 0.09699688106775284, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:23.212102Z", "loop": 5851, "env_steps": 3595468799, "loss": 0.016652021557092667, "avg_return": 0.8612497448921204, "regret": 0.0026065753772854805, "entropy": 0.09329037368297577, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:24.069244Z", "loop": 5852, "env_steps": 3596083199, "loss": 0.016629455611109734, "avg_return": 0.860694408416748, "regret": 0.0026065753772854805, "entropy": 0.09421596676111221, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:24.925769Z", "loop": 5853, "env_steps": 3596697599, "loss": 0.017958341166377068, "avg_return": 0.858507513999939, "regret": 0.0026065753772854805, "entropy": 0.09893448650836945, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:25.782301Z", "loop": 5854, "env_steps": 3597311999, "loss": 0.0180441252887249, "avg_return": 0.860927939414978, "regret": 0.0026065753772854805, "entropy": 0.10246593505144119, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:26.639477Z", "loop": 5855, "env_steps": 3597926399, "loss": 0.015908144414424896, "avg_return": 0.8609090447425842, "regret": 0.0026065753772854805, "entropy": 0.08829334378242493, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:27.497032Z", "loop": 5856, "env_steps": 3598540799, "loss": 0.016991956159472466, "avg_return": 0.8618682026863098, "regret": 0.0026065753772854805, "entropy": 0.09698490053415298, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:28.355461Z", "loop": 5857, "env_steps": 3599155199, "loss": 0.016642093658447266, "avg_return": 0.8618851900100708, "regret": 0.0026065753772854805, "entropy": 0.0937982127070427, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:29.211270Z", "loop": 5858, "env_steps": 3599769599, "loss": 0.015996035188436508, "avg_return": 0.8617779016494751, "regret": 0.0026065753772854805, "entropy": 0.09106171876192093, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:30.068008Z", "loop": 5859, "env_steps": 3600383999, "loss": 0.015680130571126938, "avg_return": 0.8603865504264832, "regret": 0.0026065753772854805, "entropy": 0.0900118350982666, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:30.966500Z", "loop": 5860, "env_steps": 3600998399, "loss": 0.0155014768242836, "avg_return": 0.8621888160705566, "regret": 0.0019062322098761797, "entropy": 0.09107153117656708, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:31.823796Z", "loop": 5861, "env_steps": 3601612799, "loss": 0.01596498116850853, "avg_return": 0.8608431220054626, "regret": 0.0019062322098761797, "entropy": 0.08808271586894989, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:32.679415Z", "loop": 5862, "env_steps": 3602227199, "loss": 0.01700720563530922, "avg_return": 0.8611618280410767, "regret": 0.0019062322098761797, "entropy": 0.09307205677032471, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:33.535167Z", "loop": 5863, "env_steps": 3602841599, "loss": 0.016329271718859673, "avg_return": 0.8611543774604797, "regret": 0.0019062322098761797, "entropy": 0.0928569957613945, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:34.391363Z", "loop": 5864, "env_steps": 3603455999, "loss": 0.01626683585345745, "avg_return": 0.8623465895652771, "regret": 0.0019062322098761797, "entropy": 0.09078042209148407, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:35.246515Z", "loop": 5865, "env_steps": 3604070399, "loss": 0.01675632782280445, "avg_return": 0.8620405197143555, "regret": 0.0019062322098761797, "entropy": 0.08853664249181747, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:36.102479Z", "loop": 5866, "env_steps": 3604684799, "loss": 0.015977129340171814, "avg_return": 0.8632051944732666, "regret": 0.0019062322098761797, "entropy": 0.08999475091695786, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:36.957731Z", "loop": 5867, "env_steps": 3605299199, "loss": 0.017070896923542023, "avg_return": 0.8635040521621704, "regret": 0.0019062322098761797, "entropy": 0.09574346244335175, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:37.813134Z", "loop": 5868, "env_steps": 3605913599, "loss": 0.015360626392066479, "avg_return": 0.8642779588699341, "regret": 0.0019062322098761797, "entropy": 0.08759652078151703, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:38.668487Z", "loop": 5869, "env_steps": 3606527999, "loss": 0.015500135719776154, "avg_return": 0.8627311587333679, "regret": 0.0019062322098761797, "entropy": 0.0864025354385376, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:39.565055Z", "loop": 5870, "env_steps": 3607142399, "loss": 0.015071520581841469, "avg_return": 0.8628765344619751, "regret": 0.0008750498527660966, "entropy": 0.08645080029964447, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:40.420923Z", "loop": 5871, "env_steps": 3607756799, "loss": 0.01757149025797844, "avg_return": 0.863569438457489, "regret": 0.0008750498527660966, "entropy": 0.09653402119874954, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:41.276897Z", "loop": 5872, "env_steps": 3608371199, "loss": 0.016312824562191963, "avg_return": 0.8640000820159912, "regret": 0.0008750498527660966, "entropy": 0.08754230290651321, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:42.132666Z", "loop": 5873, "env_steps": 3608985599, "loss": 0.01598864048719406, "avg_return": 0.8628094792366028, "regret": 0.0008750498527660966, "entropy": 0.08795095980167389, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:42.988897Z", "loop": 5874, "env_steps": 3609599999, "loss": 0.016834385693073273, "avg_return": 0.8634788990020752, "regret": 0.0008750498527660966, "entropy": 0.09170404076576233, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:43.844848Z", "loop": 5875, "env_steps": 3610214399, "loss": 0.01634368859231472, "avg_return": 0.8625748157501221, "regret": 0.0008750498527660966, "entropy": 0.09136452525854111, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:44.700422Z", "loop": 5876, "env_steps": 3610828799, "loss": 0.01575198955833912, "avg_return": 0.8619928359985352, "regret": 0.0008750498527660966, "entropy": 0.0901002287864685, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:45.556272Z", "loop": 5877, "env_steps": 3611443199, "loss": 0.01718754880130291, "avg_return": 0.8611481785774231, "regret": 0.0008750498527660966, "entropy": 0.09390594810247421, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:46.412185Z", "loop": 5878, "env_steps": 3612057599, "loss": 0.01746111921966076, "avg_return": 0.8632116913795471, "regret": 0.0008750498527660966, "entropy": 0.09354409575462341, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:47.268678Z", "loop": 5879, "env_steps": 3612671999, "loss": 0.017794379964470863, "avg_return": 0.8623055219650269, "regret": 0.0008750498527660966, "entropy": 0.09524811804294586, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:48.164871Z", "loop": 5880, "env_steps": 3613286399, "loss": 0.01729585975408554, "avg_return": 0.8622831702232361, "regret": 0.001366536831483245, "entropy": 0.0944746881723404, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:49.020461Z", "loop": 5881, "env_steps": 3613900799, "loss": 0.016721708700060844, "avg_return": 0.8632823824882507, "regret": 0.001366536831483245, "entropy": 0.09367451816797256, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:49.875203Z", "loop": 5882, "env_steps": 3614515199, "loss": 0.017015470191836357, "avg_return": 0.8622289299964905, "regret": 0.001366536831483245, "entropy": 0.09498327970504761, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:50.731013Z", "loop": 5883, "env_steps": 3615129599, "loss": 0.015287655405700207, "avg_return": 0.8626243472099304, "regret": 0.001366536831483245, "entropy": 0.09295861423015594, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:51.585582Z", "loop": 5884, "env_steps": 3615743999, "loss": 0.01750335469841957, "avg_return": 0.8616567254066467, "regret": 0.001366536831483245, "entropy": 0.09547929465770721, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:52.440203Z", "loop": 5885, "env_steps": 3616358399, "loss": 0.016436832025647163, "avg_return": 0.8606979846954346, "regret": 0.001366536831483245, "entropy": 0.09175510704517365, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:53.296161Z", "loop": 5886, "env_steps": 3616972799, "loss": 0.01699591986835003, "avg_return": 0.8621155023574829, "regret": 0.001366536831483245, "entropy": 0.09545031189918518, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:54.151804Z", "loop": 5887, "env_steps": 3617587199, "loss": 0.017273670062422752, "avg_return": 0.8619710206985474, "regret": 0.001366536831483245, "entropy": 0.09477037191390991, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:55.007224Z", "loop": 5888, "env_steps": 3618201599, "loss": 0.016880445182323456, "avg_return": 0.8625495433807373, "regret": 0.001366536831483245, "entropy": 0.09230019897222519, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:55.862403Z", "loop": 5889, "env_steps": 3618815999, "loss": 0.0177502129226923, "avg_return": 0.8630843162536621, "regret": 0.001366536831483245, "entropy": 0.09402427822351456, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:56.757333Z", "loop": 5890, "env_steps": 3619430399, "loss": 0.017261095345020294, "avg_return": 0.8623979091644287, "regret": 0.001065114513039589, "entropy": 0.09430725127458572, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:57.613568Z", "loop": 5891, "env_steps": 3620044799, "loss": 0.017848599702119827, "avg_return": 0.8612712025642395, "regret": 0.001065114513039589, "entropy": 0.09709395468235016, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:58.469121Z", "loop": 5892, "env_steps": 3620659199, "loss": 0.01794671081006527, "avg_return": 0.8616413474082947, "regret": 0.001065114513039589, "entropy": 0.1000775694847107, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:47:59.324392Z", "loop": 5893, "env_steps": 3621273599, "loss": 0.018094127997756004, "avg_return": 0.8623321652412415, "regret": 0.001065114513039589, "entropy": 0.10226399451494217, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:00.178408Z", "loop": 5894, "env_steps": 3621887999, "loss": 0.01715293899178505, "avg_return": 0.8626944422721863, "regret": 0.001065114513039589, "entropy": 0.0975104346871376, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:01.033960Z", "loop": 5895, "env_steps": 3622502399, "loss": 0.018897591158747673, "avg_return": 0.8610207438468933, "regret": 0.001065114513039589, "entropy": 0.10499455779790878, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:01.889681Z", "loop": 5896, "env_steps": 3623116799, "loss": 0.017760971561074257, "avg_return": 0.8613190054893494, "regret": 0.001065114513039589, "entropy": 0.1021018922328949, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:02.744735Z", "loop": 5897, "env_steps": 3623731199, "loss": 0.01797792874276638, "avg_return": 0.8634459376335144, "regret": 0.001065114513039589, "entropy": 0.09881647676229477, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:03.599252Z", "loop": 5898, "env_steps": 3624345599, "loss": 0.016840314492583275, "avg_return": 0.8627293109893799, "regret": 0.001065114513039589, "entropy": 0.09549041837453842, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:04.454341Z", "loop": 5899, "env_steps": 3624959999, "loss": 0.017898499965667725, "avg_return": 0.8624135255813599, "regret": 0.001065114513039589, "entropy": 0.10010484606027603, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:05.351086Z", "loop": 5900, "env_steps": 3625574399, "loss": 0.01771819218993187, "avg_return": 0.8621382713317871, "regret": 0.0011702580377459526, "entropy": 0.09986221790313721, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:06.205733Z", "loop": 5901, "env_steps": 3626188799, "loss": 0.018046269193291664, "avg_return": 0.8629423975944519, "regret": 0.0011702580377459526, "entropy": 0.10044028609991074, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:07.061575Z", "loop": 5902, "env_steps": 3626803199, "loss": 0.01799999736249447, "avg_return": 0.8628499507904053, "regret": 0.0011702580377459526, "entropy": 0.09554493427276611, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:07.917308Z", "loop": 5903, "env_steps": 3627417599, "loss": 0.016743047162890434, "avg_return": 0.861116349697113, "regret": 0.0011702580377459526, "entropy": 0.09754783660173416, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:08.772481Z", "loop": 5904, "env_steps": 3628031999, "loss": 0.01737310364842415, "avg_return": 0.8623740673065186, "regret": 0.0011702580377459526, "entropy": 0.09891226142644882, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:09.627823Z", "loop": 5905, "env_steps": 3628646399, "loss": 0.017884446308016777, "avg_return": 0.8614310622215271, "regret": 0.0011702580377459526, "entropy": 0.099636510014534, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:10.483069Z", "loop": 5906, "env_steps": 3629260799, "loss": 0.017432725057005882, "avg_return": 0.8613705635070801, "regret": 0.0011702580377459526, "entropy": 0.10091105103492737, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:11.339261Z", "loop": 5907, "env_steps": 3629875199, "loss": 0.01968683861196041, "avg_return": 0.8603387475013733, "regret": 0.0011702580377459526, "entropy": 0.10699134320020676, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:12.194423Z", "loop": 5908, "env_steps": 3630489599, "loss": 0.019530609250068665, "avg_return": 0.8608109951019287, "regret": 0.0011702580377459526, "entropy": 0.10735606402158737, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:13.051504Z", "loop": 5909, "env_steps": 3631103999, "loss": 0.018195590004324913, "avg_return": 0.8615795969963074, "regret": 0.0011702580377459526, "entropy": 0.10245196521282196, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:13.948811Z", "loop": 5910, "env_steps": 3631718399, "loss": 0.0189978014677763, "avg_return": 0.8613678216934204, "regret": 0.0025958335027098656, "entropy": 0.10514684021472931, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:14.806173Z", "loop": 5911, "env_steps": 3632332799, "loss": 0.018328141421079636, "avg_return": 0.8602297306060791, "regret": 0.0025958335027098656, "entropy": 0.09925585240125656, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:15.661220Z", "loop": 5912, "env_steps": 3632947199, "loss": 0.01851336471736431, "avg_return": 0.8601619601249695, "regret": 0.0025958335027098656, "entropy": 0.10148181766271591, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:16.516045Z", "loop": 5913, "env_steps": 3633561599, "loss": 0.017851194366812706, "avg_return": 0.861107587814331, "regret": 0.0025958335027098656, "entropy": 0.09973640739917755, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:17.372216Z", "loop": 5914, "env_steps": 3634175999, "loss": 0.01805129460990429, "avg_return": 0.8611729145050049, "regret": 0.0025958335027098656, "entropy": 0.09989907592535019, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:18.229174Z", "loop": 5915, "env_steps": 3634790399, "loss": 0.017678748816251755, "avg_return": 0.8613866567611694, "regret": 0.0025958335027098656, "entropy": 0.10038697719573975, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:19.084055Z", "loop": 5916, "env_steps": 3635404799, "loss": 0.01937621645629406, "avg_return": 0.860758900642395, "regret": 0.0025958335027098656, "entropy": 0.10551650822162628, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:19.938879Z", "loop": 5917, "env_steps": 3636019199, "loss": 0.01779749058187008, "avg_return": 0.8602551221847534, "regret": 0.0025958335027098656, "entropy": 0.10332809388637543, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:20.794737Z", "loop": 5918, "env_steps": 3636633599, "loss": 0.019799066707491875, "avg_return": 0.8601025342941284, "regret": 0.0025958335027098656, "entropy": 0.10735944658517838, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:21.649114Z", "loop": 5919, "env_steps": 3637247999, "loss": 0.01828904077410698, "avg_return": 0.8603013157844543, "regret": 0.0025958335027098656, "entropy": 0.10187634080648422, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:22.546002Z", "loop": 5920, "env_steps": 3637862399, "loss": 0.018786506727337837, "avg_return": 0.8603243231773376, "regret": 0.002723107812926173, "entropy": 0.10612256079912186, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:23.400040Z", "loop": 5921, "env_steps": 3638476799, "loss": 0.01842646114528179, "avg_return": 0.8606101870536804, "regret": 0.002723107812926173, "entropy": 0.10633819550275803, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:24.255827Z", "loop": 5922, "env_steps": 3639091199, "loss": 0.018099037930369377, "avg_return": 0.8607901930809021, "regret": 0.002723107812926173, "entropy": 0.10354539006948471, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:25.112099Z", "loop": 5923, "env_steps": 3639705599, "loss": 0.018957896158099174, "avg_return": 0.8608408570289612, "regret": 0.002723107812926173, "entropy": 0.10439914464950562, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:25.968030Z", "loop": 5924, "env_steps": 3640319999, "loss": 0.017010539770126343, "avg_return": 0.8602424263954163, "regret": 0.002723107812926173, "entropy": 0.09607833623886108, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:26.825143Z", "loop": 5925, "env_steps": 3640934399, "loss": 0.018712645396590233, "avg_return": 0.8613942861557007, "regret": 0.002723107812926173, "entropy": 0.10567919909954071, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:27.681416Z", "loop": 5926, "env_steps": 3641548799, "loss": 0.019764121621847153, "avg_return": 0.8609381318092346, "regret": 0.002723107812926173, "entropy": 0.11203457415103912, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:28.537020Z", "loop": 5927, "env_steps": 3642163199, "loss": 0.018616510555148125, "avg_return": 0.8593336939811707, "regret": 0.002723107812926173, "entropy": 0.10661035031080246, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:29.393679Z", "loop": 5928, "env_steps": 3642777599, "loss": 0.01851636916399002, "avg_return": 0.8607407808303833, "regret": 0.002723107812926173, "entropy": 0.10637934505939484, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:30.250077Z", "loop": 5929, "env_steps": 3643391999, "loss": 0.018396947532892227, "avg_return": 0.8610942959785461, "regret": 0.002723107812926173, "entropy": 0.10480361431837082, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:31.151883Z", "loop": 5930, "env_steps": 3644006399, "loss": 0.018797749653458595, "avg_return": 0.8609302043914795, "regret": 0.002155706286430359, "entropy": 0.10471253842115402, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:32.006715Z", "loop": 5931, "env_steps": 3644620799, "loss": 0.018624134361743927, "avg_return": 0.8610430955886841, "regret": 0.002155706286430359, "entropy": 0.10464400053024292, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:32.863136Z", "loop": 5932, "env_steps": 3645235199, "loss": 0.019387824460864067, "avg_return": 0.8617119789123535, "regret": 0.002155706286430359, "entropy": 0.11120879650115967, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:33.719227Z", "loop": 5933, "env_steps": 3645849599, "loss": 0.018995031714439392, "avg_return": 0.8605967164039612, "regret": 0.002155706286430359, "entropy": 0.1080772802233696, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:34.575474Z", "loop": 5934, "env_steps": 3646463999, "loss": 0.017415033653378487, "avg_return": 0.8606600165367126, "regret": 0.002155706286430359, "entropy": 0.10475793480873108, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:35.429695Z", "loop": 5935, "env_steps": 3647078399, "loss": 0.019110238179564476, "avg_return": 0.860202968120575, "regret": 0.002155706286430359, "entropy": 0.11088231950998306, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:36.283842Z", "loop": 5936, "env_steps": 3647692799, "loss": 0.01920098438858986, "avg_return": 0.8622322678565979, "regret": 0.002155706286430359, "entropy": 0.10544518381357193, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:37.139090Z", "loop": 5937, "env_steps": 3648307199, "loss": 0.018729252740740776, "avg_return": 0.8617616891860962, "regret": 0.002155706286430359, "entropy": 0.10707023739814758, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:37.994694Z", "loop": 5938, "env_steps": 3648921599, "loss": 0.01815044693648815, "avg_return": 0.861186146736145, "regret": 0.002155706286430359, "entropy": 0.1042213961482048, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:38.850092Z", "loop": 5939, "env_steps": 3649535999, "loss": 0.018050389364361763, "avg_return": 0.860292911529541, "regret": 0.002155706286430359, "entropy": 0.1047222688794136, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:39.747598Z", "loop": 5940, "env_steps": 3650150399, "loss": 0.01933886669576168, "avg_return": 0.8617307543754578, "regret": 0.001707190414890647, "entropy": 0.11044175177812576, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:40.603827Z", "loop": 5941, "env_steps": 3650764799, "loss": 0.01777656562626362, "avg_return": 0.8621044158935547, "regret": 0.001707190414890647, "entropy": 0.10147286206483841, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:41.459234Z", "loop": 5942, "env_steps": 3651379199, "loss": 0.018733618780970573, "avg_return": 0.861476480960846, "regret": 0.001707190414890647, "entropy": 0.10570765286684036, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:42.315975Z", "loop": 5943, "env_steps": 3651993599, "loss": 0.017623160034418106, "avg_return": 0.8618704676628113, "regret": 0.001707190414890647, "entropy": 0.10119538009166718, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:43.171699Z", "loop": 5944, "env_steps": 3652607999, "loss": 0.018229318782687187, "avg_return": 0.8621518015861511, "regret": 0.001707190414890647, "entropy": 0.10713128745555878, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:44.027523Z", "loop": 5945, "env_steps": 3653222399, "loss": 0.017198476940393448, "avg_return": 0.8618534803390503, "regret": 0.001707190414890647, "entropy": 0.1016654521226883, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:44.883171Z", "loop": 5946, "env_steps": 3653836799, "loss": 0.017764871940016747, "avg_return": 0.8615413904190063, "regret": 0.001707190414890647, "entropy": 0.10411352664232254, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:45.738747Z", "loop": 5947, "env_steps": 3654451199, "loss": 0.01949932612478733, "avg_return": 0.8609438538551331, "regret": 0.001707190414890647, "entropy": 0.10647150874137878, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:46.593675Z", "loop": 5948, "env_steps": 3655065599, "loss": 0.01924886554479599, "avg_return": 0.8615021109580994, "regret": 0.001707190414890647, "entropy": 0.10330656915903091, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:47.449611Z", "loop": 5949, "env_steps": 3655679999, "loss": 0.01957721821963787, "avg_return": 0.8622500896453857, "regret": 0.001707190414890647, "entropy": 0.10558479279279709, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:48.344998Z", "loop": 5950, "env_steps": 3656294399, "loss": 0.01932545378804207, "avg_return": 0.8620550632476807, "regret": 0.0023540975525975227, "entropy": 0.10511210560798645, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:49.200547Z", "loop": 5951, "env_steps": 3656908799, "loss": 0.018093151971697807, "avg_return": 0.8606032729148865, "regret": 0.0023540975525975227, "entropy": 0.10180075466632843, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:50.057483Z", "loop": 5952, "env_steps": 3657523199, "loss": 0.018735647201538086, "avg_return": 0.8603684902191162, "regret": 0.0023540975525975227, "entropy": 0.10739447176456451, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:50.913316Z", "loop": 5953, "env_steps": 3658137599, "loss": 0.019434809684753418, "avg_return": 0.8623622059822083, "regret": 0.0023540975525975227, "entropy": 0.10572659224271774, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:51.769720Z", "loop": 5954, "env_steps": 3658751999, "loss": 0.018564313650131226, "avg_return": 0.8617825508117676, "regret": 0.0023540975525975227, "entropy": 0.10220622271299362, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:52.626324Z", "loop": 5955, "env_steps": 3659366399, "loss": 0.017258133739233017, "avg_return": 0.8622511029243469, "regret": 0.0023540975525975227, "entropy": 0.10079993307590485, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:53.483185Z", "loop": 5956, "env_steps": 3659980799, "loss": 0.017584985122084618, "avg_return": 0.8611264228820801, "regret": 0.0023540975525975227, "entropy": 0.10062556713819504, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:54.341336Z", "loop": 5957, "env_steps": 3660595199, "loss": 0.017987728118896484, "avg_return": 0.8622903823852539, "regret": 0.0023540975525975227, "entropy": 0.10336209833621979, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:55.197064Z", "loop": 5958, "env_steps": 3661209599, "loss": 0.02023971453309059, "avg_return": 0.8610751628875732, "regret": 0.0023540975525975227, "entropy": 0.11211269348859787, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:56.054114Z", "loop": 5959, "env_steps": 3661823999, "loss": 0.017848636955022812, "avg_return": 0.8623337745666504, "regret": 0.0023540975525975227, "entropy": 0.10251585394144058, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:56.952660Z", "loop": 5960, "env_steps": 3662438399, "loss": 0.017146358266472816, "avg_return": 0.861862301826477, "regret": 0.0016261739656329155, "entropy": 0.10111583769321442, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:57.807938Z", "loop": 5961, "env_steps": 3663052799, "loss": 0.018095554783940315, "avg_return": 0.8619933128356934, "regret": 0.0016261739656329155, "entropy": 0.10440214723348618, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:58.663188Z", "loop": 5962, "env_steps": 3663667199, "loss": 0.018458984792232513, "avg_return": 0.8606043457984924, "regret": 0.0016261739656329155, "entropy": 0.10363753885030746, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:48:59.518022Z", "loop": 5963, "env_steps": 3664281599, "loss": 0.016779636964201927, "avg_return": 0.862362265586853, "regret": 0.0016261739656329155, "entropy": 0.10495875775814056, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:00.375212Z", "loop": 5964, "env_steps": 3664895999, "loss": 0.017078954726457596, "avg_return": 0.861958920955658, "regret": 0.0016261739656329155, "entropy": 0.09986209869384766, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:01.231235Z", "loop": 5965, "env_steps": 3665510399, "loss": 0.017903340980410576, "avg_return": 0.862808346748352, "regret": 0.0016261739656329155, "entropy": 0.10421280562877655, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:02.086666Z", "loop": 5966, "env_steps": 3666124799, "loss": 0.017462797462940216, "avg_return": 0.8617134690284729, "regret": 0.0016261739656329155, "entropy": 0.10430070757865906, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:02.940911Z", "loop": 5967, "env_steps": 3666739199, "loss": 0.01847928576171398, "avg_return": 0.86279296875, "regret": 0.0016261739656329155, "entropy": 0.10552973300218582, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:03.795736Z", "loop": 5968, "env_steps": 3667353599, "loss": 0.01793925277888775, "avg_return": 0.8629626631736755, "regret": 0.0016261739656329155, "entropy": 0.10392016172409058, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:04.651261Z", "loop": 5969, "env_steps": 3667967999, "loss": 0.01753959432244301, "avg_return": 0.8619764447212219, "regret": 0.0016261739656329155, "entropy": 0.10031919926404953, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:05.547075Z", "loop": 5970, "env_steps": 3668582399, "loss": 0.016773518174886703, "avg_return": 0.8620121479034424, "regret": 0.0015342436963692307, "entropy": 0.10188225656747818, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:06.402634Z", "loop": 5971, "env_steps": 3669196799, "loss": 0.018128475174307823, "avg_return": 0.8618049025535583, "regret": 0.0015342436963692307, "entropy": 0.1033824160695076, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:07.258961Z", "loop": 5972, "env_steps": 3669811199, "loss": 0.017583711072802544, "avg_return": 0.8607977628707886, "regret": 0.0015342436963692307, "entropy": 0.10214018076658249, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:08.115313Z", "loop": 5973, "env_steps": 3670425599, "loss": 0.01722106523811817, "avg_return": 0.8634265065193176, "regret": 0.0015342436963692307, "entropy": 0.09932275861501694, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:08.970258Z", "loop": 5974, "env_steps": 3671039999, "loss": 0.017945749685168266, "avg_return": 0.8623443841934204, "regret": 0.0015342436963692307, "entropy": 0.10537313669919968, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:09.826285Z", "loop": 5975, "env_steps": 3671654399, "loss": 0.018199415877461433, "avg_return": 0.8609310388565063, "regret": 0.0015342436963692307, "entropy": 0.10381438583135605, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:10.682017Z", "loop": 5976, "env_steps": 3672268799, "loss": 0.019247740507125854, "avg_return": 0.862230658531189, "regret": 0.0015342436963692307, "entropy": 0.10808269679546356, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:11.536501Z", "loop": 5977, "env_steps": 3672883199, "loss": 0.01832290180027485, "avg_return": 0.8617279529571533, "regret": 0.0015342436963692307, "entropy": 0.10322815179824829, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:12.391564Z", "loop": 5978, "env_steps": 3673497599, "loss": 0.017753634601831436, "avg_return": 0.8602797389030457, "regret": 0.0015342436963692307, "entropy": 0.10676707327365875, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:13.246756Z", "loop": 5979, "env_steps": 3674111999, "loss": 0.019275957718491554, "avg_return": 0.8608394861221313, "regret": 0.0015342436963692307, "entropy": 0.11106161773204803, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:14.143250Z", "loop": 5980, "env_steps": 3674726399, "loss": 0.021621115505695343, "avg_return": 0.857631266117096, "regret": 0.004568994045257568, "entropy": 0.1188366636633873, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:14.998291Z", "loop": 5981, "env_steps": 3675340799, "loss": 0.022178059443831444, "avg_return": 0.8576615452766418, "regret": 0.004568994045257568, "entropy": 0.12369334697723389, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:15.853039Z", "loop": 5982, "env_steps": 3675955199, "loss": 0.023661505430936813, "avg_return": 0.8550265431404114, "regret": 0.004568994045257568, "entropy": 0.12652114033699036, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:16.708934Z", "loop": 5983, "env_steps": 3676569599, "loss": 0.02152072638273239, "avg_return": 0.8555150628089905, "regret": 0.004568994045257568, "entropy": 0.11983940750360489, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:17.566398Z", "loop": 5984, "env_steps": 3677183999, "loss": 0.022166725248098373, "avg_return": 0.8568732738494873, "regret": 0.004568994045257568, "entropy": 0.12437951564788818, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:18.421762Z", "loop": 5985, "env_steps": 3677798399, "loss": 0.019189557060599327, "avg_return": 0.8589622974395752, "regret": 0.004568994045257568, "entropy": 0.1096087321639061, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:19.276826Z", "loop": 5986, "env_steps": 3678412799, "loss": 0.01998571865260601, "avg_return": 0.8601812720298767, "regret": 0.004568994045257568, "entropy": 0.11166223138570786, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:20.132543Z", "loop": 5987, "env_steps": 3679027199, "loss": 0.01891150511801243, "avg_return": 0.8602771162986755, "regret": 0.004568994045257568, "entropy": 0.10716872662305832, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:20.989368Z", "loop": 5988, "env_steps": 3679641599, "loss": 0.01845407858490944, "avg_return": 0.8595969676971436, "regret": 0.004568994045257568, "entropy": 0.10480738431215286, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:21.844614Z", "loop": 5989, "env_steps": 3680255999, "loss": 0.018652688711881638, "avg_return": 0.8601566553115845, "regret": 0.004568994045257568, "entropy": 0.10670052468776703, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:22.738740Z", "loop": 5990, "env_steps": 3680870399, "loss": 0.018796907737851143, "avg_return": 0.8600589036941528, "regret": 0.0035943351686000824, "entropy": 0.09955042600631714, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:23.593239Z", "loop": 5991, "env_steps": 3681484799, "loss": 0.018108822405338287, "avg_return": 0.8597433567047119, "regret": 0.0035943351686000824, "entropy": 0.09832455962896347, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:24.448623Z", "loop": 5992, "env_steps": 3682099199, "loss": 0.018919508904218674, "avg_return": 0.8610360026359558, "regret": 0.0035943351686000824, "entropy": 0.10829905420541763, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:25.303354Z", "loop": 5993, "env_steps": 3682713599, "loss": 0.018729163333773613, "avg_return": 0.8598853945732117, "regret": 0.0035943351686000824, "entropy": 0.1037599965929985, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:26.157386Z", "loop": 5994, "env_steps": 3683327999, "loss": 0.01817396841943264, "avg_return": 0.8615834712982178, "regret": 0.0035943351686000824, "entropy": 0.10214587301015854, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:27.012472Z", "loop": 5995, "env_steps": 3683942399, "loss": 0.01699567399919033, "avg_return": 0.8622086644172668, "regret": 0.0035943351686000824, "entropy": 0.09337597340345383, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:27.868641Z", "loop": 5996, "env_steps": 3684556799, "loss": 0.016579849645495415, "avg_return": 0.861233651638031, "regret": 0.0035943351686000824, "entropy": 0.09531404823064804, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:28.724212Z", "loop": 5997, "env_steps": 3685171199, "loss": 0.017500169575214386, "avg_return": 0.8621259927749634, "regret": 0.0035943351686000824, "entropy": 0.0972038134932518, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:29.579181Z", "loop": 5998, "env_steps": 3685785599, "loss": 0.016469966620206833, "avg_return": 0.8620384931564331, "regret": 0.0035943351686000824, "entropy": 0.09368345141410828, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:30.433477Z", "loop": 5999, "env_steps": 3686399999, "loss": 0.01791752688586712, "avg_return": 0.8624963760375977, "regret": 0.0035943351686000824, "entropy": 0.09858310967683792, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:31.328114Z", "loop": 6000, "env_steps": 3687014399, "loss": 0.017338190227746964, "avg_return": 0.8618459105491638, "regret": 0.0014141907449811697, "entropy": 0.09709382802248001, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:32.184699Z", "loop": 6001, "env_steps": 3687628799, "loss": 0.01799498312175274, "avg_return": 0.8619165420532227, "regret": 0.0014141907449811697, "entropy": 0.10567467659711838, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:33.040372Z", "loop": 6002, "env_steps": 3688243199, "loss": 0.018136074766516685, "avg_return": 0.8618769645690918, "regret": 0.0014141907449811697, "entropy": 0.1029936671257019, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:33.897311Z", "loop": 6003, "env_steps": 3688857599, "loss": 0.016623860225081444, "avg_return": 0.8618968725204468, "regret": 0.0014141907449811697, "entropy": 0.09584549814462662, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:34.754696Z", "loop": 6004, "env_steps": 3689471999, "loss": 0.01863926090300083, "avg_return": 0.862028956413269, "regret": 0.0014141907449811697, "entropy": 0.10626766085624695, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:35.610589Z", "loop": 6005, "env_steps": 3690086399, "loss": 0.01792176067829132, "avg_return": 0.8602700233459473, "regret": 0.0014141907449811697, "entropy": 0.09990131855010986, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:36.466628Z", "loop": 6006, "env_steps": 3690700799, "loss": 0.01884954608976841, "avg_return": 0.8599817156791687, "regret": 0.0014141907449811697, "entropy": 0.10211338847875595, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:37.322505Z", "loop": 6007, "env_steps": 3691315199, "loss": 0.01932613179087639, "avg_return": 0.859358012676239, "regret": 0.0014141907449811697, "entropy": 0.10276706516742706, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:38.178291Z", "loop": 6008, "env_steps": 3691929599, "loss": 0.0204404816031456, "avg_return": 0.8591339588165283, "regret": 0.0014141907449811697, "entropy": 0.1093304455280304, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:39.033873Z", "loop": 6009, "env_steps": 3692543999, "loss": 0.01714765839278698, "avg_return": 0.8600842356681824, "regret": 0.0014141907449811697, "entropy": 0.10054665803909302, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:39.931572Z", "loop": 6010, "env_steps": 3693158399, "loss": 0.01800021342933178, "avg_return": 0.8596140742301941, "regret": 0.0034748127218335867, "entropy": 0.1011333167552948, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:40.787800Z", "loop": 6011, "env_steps": 3693772799, "loss": 0.01759479194879532, "avg_return": 0.859378457069397, "regret": 0.0034748127218335867, "entropy": 0.10022492706775665, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:41.643894Z", "loop": 6012, "env_steps": 3694387199, "loss": 0.01670103333890438, "avg_return": 0.8605731129646301, "regret": 0.0034748127218335867, "entropy": 0.09567062556743622, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:42.500513Z", "loop": 6013, "env_steps": 3695001599, "loss": 0.017069965600967407, "avg_return": 0.8590174317359924, "regret": 0.0034748127218335867, "entropy": 0.09877356141805649, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:43.356929Z", "loop": 6014, "env_steps": 3695615999, "loss": 0.016869349405169487, "avg_return": 0.8598065376281738, "regret": 0.0034748127218335867, "entropy": 0.09812295436859131, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:44.212677Z", "loop": 6015, "env_steps": 3696230399, "loss": 0.018101461231708527, "avg_return": 0.8597728610038757, "regret": 0.0034748127218335867, "entropy": 0.09801687300205231, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:45.069201Z", "loop": 6016, "env_steps": 3696844799, "loss": 0.019933845847845078, "avg_return": 0.8592203259468079, "regret": 0.0034748127218335867, "entropy": 0.10515664517879486, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:45.925076Z", "loop": 6017, "env_steps": 3697459199, "loss": 0.01886632852256298, "avg_return": 0.860719621181488, "regret": 0.0034748127218335867, "entropy": 0.10148824751377106, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:46.781179Z", "loop": 6018, "env_steps": 3698073599, "loss": 0.017562614753842354, "avg_return": 0.8623985052108765, "regret": 0.0034748127218335867, "entropy": 0.09704937040805817, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:47.637655Z", "loop": 6019, "env_steps": 3698687999, "loss": 0.018445100635290146, "avg_return": 0.8615878224372864, "regret": 0.0034748127218335867, "entropy": 0.09494610130786896, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:48.535549Z", "loop": 6020, "env_steps": 3699302399, "loss": 0.0168988686054945, "avg_return": 0.8629667162895203, "regret": 0.0012509297812357545, "entropy": 0.09211680293083191, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:49.390991Z", "loop": 6021, "env_steps": 3699916799, "loss": 0.017106778919696808, "avg_return": 0.8637121915817261, "regret": 0.0012509297812357545, "entropy": 0.0917426124215126, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:50.245707Z", "loop": 6022, "env_steps": 3700531199, "loss": 0.01609966717660427, "avg_return": 0.8630020618438721, "regret": 0.0012509297812357545, "entropy": 0.09032788872718811, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:51.100295Z", "loop": 6023, "env_steps": 3701145599, "loss": 0.016057496890425682, "avg_return": 0.8624287843704224, "regret": 0.0012509297812357545, "entropy": 0.08993016183376312, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:51.955668Z", "loop": 6024, "env_steps": 3701759999, "loss": 0.01845686510205269, "avg_return": 0.8626880049705505, "regret": 0.0012509297812357545, "entropy": 0.0960441306233406, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:52.810691Z", "loop": 6025, "env_steps": 3702374399, "loss": 0.015683937817811966, "avg_return": 0.8613321185112, "regret": 0.0012509297812357545, "entropy": 0.08971396088600159, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:53.665107Z", "loop": 6026, "env_steps": 3702988799, "loss": 0.01769111305475235, "avg_return": 0.86060631275177, "regret": 0.0012509297812357545, "entropy": 0.09764672070741653, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:54.519009Z", "loop": 6027, "env_steps": 3703603199, "loss": 0.018631456419825554, "avg_return": 0.8612335324287415, "regret": 0.0012509297812357545, "entropy": 0.10090513527393341, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:55.374127Z", "loop": 6028, "env_steps": 3704217599, "loss": 0.017923152074217796, "avg_return": 0.8596607446670532, "regret": 0.0012509297812357545, "entropy": 0.10201574862003326, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:56.229405Z", "loop": 6029, "env_steps": 3704831999, "loss": 0.01837843842804432, "avg_return": 0.8594040870666504, "regret": 0.0012509297812357545, "entropy": 0.10277187079191208, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:57.123523Z", "loop": 6030, "env_steps": 3705446399, "loss": 0.018076634034514427, "avg_return": 0.8589868545532227, "regret": 0.0036431539338082075, "entropy": 0.09950853139162064, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:57.977604Z", "loop": 6031, "env_steps": 3706060799, "loss": 0.018337303772568703, "avg_return": 0.8606430292129517, "regret": 0.0036431539338082075, "entropy": 0.0995650589466095, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:58.832945Z", "loop": 6032, "env_steps": 3706675199, "loss": 0.01763427071273327, "avg_return": 0.859424889087677, "regret": 0.0036431539338082075, "entropy": 0.09656383842229843, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:49:59.688221Z", "loop": 6033, "env_steps": 3707289599, "loss": 0.016858624294400215, "avg_return": 0.8604298830032349, "regret": 0.0036431539338082075, "entropy": 0.097697913646698, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:00.542918Z", "loop": 6034, "env_steps": 3707903999, "loss": 0.017790796235203743, "avg_return": 0.862338662147522, "regret": 0.0036431539338082075, "entropy": 0.0956171378493309, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:01.399538Z", "loop": 6035, "env_steps": 3708518399, "loss": 0.017871294170618057, "avg_return": 0.8595805168151855, "regret": 0.0036431539338082075, "entropy": 0.09782228618860245, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:02.256728Z", "loop": 6036, "env_steps": 3709132799, "loss": 0.01844167523086071, "avg_return": 0.8621330857276917, "regret": 0.0036431539338082075, "entropy": 0.10044391453266144, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:03.113993Z", "loop": 6037, "env_steps": 3709747199, "loss": 0.01766452006995678, "avg_return": 0.8615595698356628, "regret": 0.0036431539338082075, "entropy": 0.0974736288189888, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:03.974695Z", "loop": 6038, "env_steps": 3710361599, "loss": 0.018080180510878563, "avg_return": 0.8593835830688477, "regret": 0.0036431539338082075, "entropy": 0.0974312350153923, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:04.832650Z", "loop": 6039, "env_steps": 3710975999, "loss": 0.018931513652205467, "avg_return": 0.8594116568565369, "regret": 0.0036431539338082075, "entropy": 0.1009688451886177, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:05.728437Z", "loop": 6040, "env_steps": 3711590399, "loss": 0.01978200674057007, "avg_return": 0.8607245087623596, "regret": 0.004335147328674793, "entropy": 0.1043606847524643, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:06.583341Z", "loop": 6041, "env_steps": 3712204799, "loss": 0.01919456012547016, "avg_return": 0.8579239845275879, "regret": 0.004335147328674793, "entropy": 0.10330593585968018, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:07.439137Z", "loop": 6042, "env_steps": 3712819199, "loss": 0.020347310230135918, "avg_return": 0.8581706881523132, "regret": 0.004335147328674793, "entropy": 0.1085173711180687, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:08.293907Z", "loop": 6043, "env_steps": 3713433599, "loss": 0.01942918263375759, "avg_return": 0.8597338795661926, "regret": 0.004335147328674793, "entropy": 0.10114564001560211, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:09.149090Z", "loop": 6044, "env_steps": 3714047999, "loss": 0.019053542986512184, "avg_return": 0.8609086275100708, "regret": 0.004335147328674793, "entropy": 0.10324028879404068, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:10.003914Z", "loop": 6045, "env_steps": 3714662399, "loss": 0.017511658370494843, "avg_return": 0.8617388010025024, "regret": 0.004335147328674793, "entropy": 0.09711606055498123, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:10.858868Z", "loop": 6046, "env_steps": 3715276799, "loss": 0.016117392107844353, "avg_return": 0.8612536787986755, "regret": 0.004335147328674793, "entropy": 0.09026632457971573, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:11.714812Z", "loop": 6047, "env_steps": 3715891199, "loss": 0.016914617270231247, "avg_return": 0.861102819442749, "regret": 0.004335147328674793, "entropy": 0.0914098471403122, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:12.570399Z", "loop": 6048, "env_steps": 3716505599, "loss": 0.01753016747534275, "avg_return": 0.861822247505188, "regret": 0.004335147328674793, "entropy": 0.09568686783313751, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:13.424992Z", "loop": 6049, "env_steps": 3717119999, "loss": 0.01763538084924221, "avg_return": 0.8614029884338379, "regret": 0.004335147328674793, "entropy": 0.09402233362197876, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:14.320656Z", "loop": 6050, "env_steps": 3717734399, "loss": 0.015880458056926727, "avg_return": 0.8623884320259094, "regret": 0.0013464940711855888, "entropy": 0.08796873688697815, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:15.175844Z", "loop": 6051, "env_steps": 3718348799, "loss": 0.015539395622909069, "avg_return": 0.8624916672706604, "regret": 0.0013464940711855888, "entropy": 0.08828328549861908, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:16.032343Z", "loop": 6052, "env_steps": 3718963199, "loss": 0.01670920103788376, "avg_return": 0.8627516627311707, "regret": 0.0013464940711855888, "entropy": 0.09250438213348389, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:16.887949Z", "loop": 6053, "env_steps": 3719577599, "loss": 0.015869734808802605, "avg_return": 0.8624805808067322, "regret": 0.0013464940711855888, "entropy": 0.0899311825633049, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:17.743128Z", "loop": 6054, "env_steps": 3720191999, "loss": 0.016731204465031624, "avg_return": 0.8629964590072632, "regret": 0.0013464940711855888, "entropy": 0.09198427200317383, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:18.598782Z", "loop": 6055, "env_steps": 3720806399, "loss": 0.0171450637280941, "avg_return": 0.863681435585022, "regret": 0.0013464940711855888, "entropy": 0.09364178031682968, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:19.454761Z", "loop": 6056, "env_steps": 3721420799, "loss": 0.01556032057851553, "avg_return": 0.8618581295013428, "regret": 0.0013464940711855888, "entropy": 0.09025440365076065, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:20.310701Z", "loop": 6057, "env_steps": 3722035199, "loss": 0.015971889719367027, "avg_return": 0.861819863319397, "regret": 0.0013464940711855888, "entropy": 0.09005172550678253, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:21.166066Z", "loop": 6058, "env_steps": 3722649599, "loss": 0.01637076400220394, "avg_return": 0.8626731634140015, "regret": 0.0013464940711855888, "entropy": 0.09060240536928177, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:22.021256Z", "loop": 6059, "env_steps": 3723263999, "loss": 0.017546530812978745, "avg_return": 0.8616605997085571, "regret": 0.0013464940711855888, "entropy": 0.09687762707471848, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:22.917574Z", "loop": 6060, "env_steps": 3723878399, "loss": 0.015966197475790977, "avg_return": 0.8616095185279846, "regret": 0.001944087096489966, "entropy": 0.0896398052573204, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:23.773577Z", "loop": 6061, "env_steps": 3724492799, "loss": 0.01766914501786232, "avg_return": 0.8626154065132141, "regret": 0.001944087096489966, "entropy": 0.09812092781066895, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:24.629159Z", "loop": 6062, "env_steps": 3725107199, "loss": 0.017288092523813248, "avg_return": 0.861114501953125, "regret": 0.001944087096489966, "entropy": 0.0966658890247345, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:25.485305Z", "loop": 6063, "env_steps": 3725721599, "loss": 0.016204427927732468, "avg_return": 0.8610753417015076, "regret": 0.001944087096489966, "entropy": 0.09132374078035355, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:26.344760Z", "loop": 6064, "env_steps": 3726335999, "loss": 0.01666434295475483, "avg_return": 0.8604989051818848, "regret": 0.001944087096489966, "entropy": 0.09637463092803955, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:27.200188Z", "loop": 6065, "env_steps": 3726950399, "loss": 0.018332934007048607, "avg_return": 0.8617359399795532, "regret": 0.001944087096489966, "entropy": 0.09919807314872742, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:28.055308Z", "loop": 6066, "env_steps": 3727564799, "loss": 0.017368828877806664, "avg_return": 0.8624323606491089, "regret": 0.001944087096489966, "entropy": 0.09617627412080765, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:28.912450Z", "loop": 6067, "env_steps": 3728179199, "loss": 0.016703234985470772, "avg_return": 0.861268937587738, "regret": 0.001944087096489966, "entropy": 0.09330151230096817, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:29.768187Z", "loop": 6068, "env_steps": 3728793599, "loss": 0.01599831134080887, "avg_return": 0.8613967895507812, "regret": 0.001944087096489966, "entropy": 0.09251466393470764, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:30.623307Z", "loop": 6069, "env_steps": 3729407999, "loss": 0.015695778653025627, "avg_return": 0.8618571162223816, "regret": 0.001944087096489966, "entropy": 0.0883527547121048, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:31.519313Z", "loop": 6070, "env_steps": 3730022399, "loss": 0.01716299168765545, "avg_return": 0.8629065155982971, "regret": 0.0011657745344564319, "entropy": 0.0931270644068718, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:32.374374Z", "loop": 6071, "env_steps": 3730636799, "loss": 0.017546415328979492, "avg_return": 0.8629079461097717, "regret": 0.0011657745344564319, "entropy": 0.0923091322183609, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:33.229005Z", "loop": 6072, "env_steps": 3731251199, "loss": 0.01557460892945528, "avg_return": 0.8622904419898987, "regret": 0.0011657745344564319, "entropy": 0.08992128074169159, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:34.084110Z", "loop": 6073, "env_steps": 3731865599, "loss": 0.01574430800974369, "avg_return": 0.8633325695991516, "regret": 0.0011657745344564319, "entropy": 0.08994556218385696, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:34.939960Z", "loop": 6074, "env_steps": 3732479999, "loss": 0.01694362238049507, "avg_return": 0.8626719117164612, "regret": 0.0011657745344564319, "entropy": 0.08921772986650467, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:35.795504Z", "loop": 6075, "env_steps": 3733094399, "loss": 0.016251329332590103, "avg_return": 0.862174391746521, "regret": 0.0011657745344564319, "entropy": 0.09456345438957214, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:36.649589Z", "loop": 6076, "env_steps": 3733708799, "loss": 0.017602551728487015, "avg_return": 0.8630537986755371, "regret": 0.0011657745344564319, "entropy": 0.09418942779302597, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:37.504534Z", "loop": 6077, "env_steps": 3734323199, "loss": 0.017860181629657745, "avg_return": 0.862728476524353, "regret": 0.0011657745344564319, "entropy": 0.09216591715812683, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:38.359757Z", "loop": 6078, "env_steps": 3734937599, "loss": 0.01707799918949604, "avg_return": 0.8630818724632263, "regret": 0.0011657745344564319, "entropy": 0.09503064304590225, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:39.215864Z", "loop": 6079, "env_steps": 3735551999, "loss": 0.01591496728360653, "avg_return": 0.8620255589485168, "regret": 0.0011657745344564319, "entropy": 0.09089577198028564, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:40.113104Z", "loop": 6080, "env_steps": 3736166399, "loss": 0.016676058992743492, "avg_return": 0.8631758689880371, "regret": 0.0010376694845035672, "entropy": 0.09172940999269485, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:40.967952Z", "loop": 6081, "env_steps": 3736780799, "loss": 0.01711883395910263, "avg_return": 0.8630580902099609, "regret": 0.0010376694845035672, "entropy": 0.09256062656641006, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:41.823714Z", "loop": 6082, "env_steps": 3737395199, "loss": 0.01621297188103199, "avg_return": 0.862934410572052, "regret": 0.0010376694845035672, "entropy": 0.08927316218614578, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:42.680931Z", "loop": 6083, "env_steps": 3738009599, "loss": 0.01699555478990078, "avg_return": 0.8621853590011597, "regret": 0.0010376694845035672, "entropy": 0.09464555233716965, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:43.537026Z", "loop": 6084, "env_steps": 3738623999, "loss": 0.016140302643179893, "avg_return": 0.8622194528579712, "regret": 0.0010376694845035672, "entropy": 0.094769686460495, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:44.392748Z", "loop": 6085, "env_steps": 3739238399, "loss": 0.016128143295645714, "avg_return": 0.8613787293434143, "regret": 0.0010376694845035672, "entropy": 0.09094779193401337, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:45.248900Z", "loop": 6086, "env_steps": 3739852799, "loss": 0.01773929037153721, "avg_return": 0.862118124961853, "regret": 0.0010376694845035672, "entropy": 0.09815807640552521, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:46.104435Z", "loop": 6087, "env_steps": 3740467199, "loss": 0.016331171616911888, "avg_return": 0.8603214621543884, "regret": 0.0010376694845035672, "entropy": 0.09261967986822128, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:46.960186Z", "loop": 6088, "env_steps": 3741081599, "loss": 0.017485227435827255, "avg_return": 0.8621786832809448, "regret": 0.0010376694845035672, "entropy": 0.09725764393806458, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:47.815519Z", "loop": 6089, "env_steps": 3741695999, "loss": 0.016203686594963074, "avg_return": 0.8615729212760925, "regret": 0.0010376694845035672, "entropy": 0.09422662109136581, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:48.710278Z", "loop": 6090, "env_steps": 3742310399, "loss": 0.01628880202770233, "avg_return": 0.8629599213600159, "regret": 0.001492989482358098, "entropy": 0.08807120472192764, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:49.565537Z", "loop": 6091, "env_steps": 3742924799, "loss": 0.017714357003569603, "avg_return": 0.8603958487510681, "regret": 0.001492989482358098, "entropy": 0.09804796427488327, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:50.422872Z", "loop": 6092, "env_steps": 3743539199, "loss": 0.017530657351017, "avg_return": 0.862932026386261, "regret": 0.001492989482358098, "entropy": 0.09864683449268341, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:51.280307Z", "loop": 6093, "env_steps": 3744153599, "loss": 0.01668163202702999, "avg_return": 0.8622052073478699, "regret": 0.001492989482358098, "entropy": 0.09470272064208984, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:52.138305Z", "loop": 6094, "env_steps": 3744767999, "loss": 0.01661062240600586, "avg_return": 0.8620553016662598, "regret": 0.001492989482358098, "entropy": 0.0943652018904686, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:52.994360Z", "loop": 6095, "env_steps": 3745382399, "loss": 0.016393858939409256, "avg_return": 0.8628444671630859, "regret": 0.001492989482358098, "entropy": 0.0933925062417984, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:53.850990Z", "loop": 6096, "env_steps": 3745996799, "loss": 0.017467759549617767, "avg_return": 0.862527072429657, "regret": 0.001492989482358098, "entropy": 0.09521618485450745, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:54.707203Z", "loop": 6097, "env_steps": 3746611199, "loss": 0.017503175884485245, "avg_return": 0.8616009950637817, "regret": 0.001492989482358098, "entropy": 0.09603337198495865, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:55.563843Z", "loop": 6098, "env_steps": 3747225599, "loss": 0.01571579836308956, "avg_return": 0.8632187843322754, "regret": 0.001492989482358098, "entropy": 0.09062352031469345, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:56.420467Z", "loop": 6099, "env_steps": 3747839999, "loss": 0.017066478729248047, "avg_return": 0.8605597019195557, "regret": 0.001492989482358098, "entropy": 0.09591749310493469, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:57.316261Z", "loop": 6100, "env_steps": 3748454399, "loss": 0.0165009256452322, "avg_return": 0.8595216870307922, "regret": 0.0025670435279607773, "entropy": 0.09120337665081024, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:58.172626Z", "loop": 6101, "env_steps": 3749068799, "loss": 0.01719518005847931, "avg_return": 0.8586788177490234, "regret": 0.0025670435279607773, "entropy": 0.09263266623020172, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:59.029363Z", "loop": 6102, "env_steps": 3749683199, "loss": 0.017354831099510193, "avg_return": 0.8617569208145142, "regret": 0.0025670435279607773, "entropy": 0.09754585474729538, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:50:59.884192Z", "loop": 6103, "env_steps": 3750297599, "loss": 0.015955787152051926, "avg_return": 0.8609627485275269, "regret": 0.0025670435279607773, "entropy": 0.08892279118299484, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:00.738934Z", "loop": 6104, "env_steps": 3750911999, "loss": 0.016402628272771835, "avg_return": 0.8607358932495117, "regret": 0.0025670435279607773, "entropy": 0.09188868850469589, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:01.593698Z", "loop": 6105, "env_steps": 3751526399, "loss": 0.016012774780392647, "avg_return": 0.8619263172149658, "regret": 0.0025670435279607773, "entropy": 0.09436395019292831, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:02.449947Z", "loop": 6106, "env_steps": 3752140799, "loss": 0.017833610996603966, "avg_return": 0.8608868718147278, "regret": 0.0025670435279607773, "entropy": 0.09880999475717545, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:03.305327Z", "loop": 6107, "env_steps": 3752755199, "loss": 0.017048273235559464, "avg_return": 0.8599979877471924, "regret": 0.0025670435279607773, "entropy": 0.0973517894744873, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:04.160033Z", "loop": 6108, "env_steps": 3753369599, "loss": 0.017392054200172424, "avg_return": 0.8610832095146179, "regret": 0.0025670435279607773, "entropy": 0.09632330387830734, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:05.013966Z", "loop": 6109, "env_steps": 3753983999, "loss": 0.01827836222946644, "avg_return": 0.8605629801750183, "regret": 0.0025670435279607773, "entropy": 0.09875953942537308, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:05.910276Z", "loop": 6110, "env_steps": 3754598399, "loss": 0.01778576336801052, "avg_return": 0.8587545156478882, "regret": 0.0026723279152065516, "entropy": 0.0982641726732254, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:06.765879Z", "loop": 6111, "env_steps": 3755212799, "loss": 0.018232380971312523, "avg_return": 0.8607399463653564, "regret": 0.0026723279152065516, "entropy": 0.10012413561344147, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:07.620995Z", "loop": 6112, "env_steps": 3755827199, "loss": 0.01754535362124443, "avg_return": 0.8611580729484558, "regret": 0.0026723279152065516, "entropy": 0.09420595318078995, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:08.475837Z", "loop": 6113, "env_steps": 3756441599, "loss": 0.016216199845075607, "avg_return": 0.8610381484031677, "regret": 0.0026723279152065516, "entropy": 0.09370650351047516, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:09.330964Z", "loop": 6114, "env_steps": 3757055999, "loss": 0.016482586041092873, "avg_return": 0.8609984517097473, "regret": 0.0026723279152065516, "entropy": 0.09415771812200546, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:10.186921Z", "loop": 6115, "env_steps": 3757670399, "loss": 0.01810973323881626, "avg_return": 0.8608679175376892, "regret": 0.0026723279152065516, "entropy": 0.10061007738113403, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:11.043138Z", "loop": 6116, "env_steps": 3758284799, "loss": 0.017725957557559013, "avg_return": 0.8610146045684814, "regret": 0.0026723279152065516, "entropy": 0.09956812113523483, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:11.898349Z", "loop": 6117, "env_steps": 3758899199, "loss": 0.017360569909214973, "avg_return": 0.8599481582641602, "regret": 0.0026723279152065516, "entropy": 0.09687285870313644, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:12.754173Z", "loop": 6118, "env_steps": 3759513599, "loss": 0.01694812811911106, "avg_return": 0.8631473779678345, "regret": 0.0026723279152065516, "entropy": 0.09620627015829086, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:13.609705Z", "loop": 6119, "env_steps": 3760127999, "loss": 0.01618742011487484, "avg_return": 0.8618031740188599, "regret": 0.0026723279152065516, "entropy": 0.0918632373213768, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:14.505072Z", "loop": 6120, "env_steps": 3760742399, "loss": 0.015393991954624653, "avg_return": 0.8622955679893494, "regret": 0.0014092504279688, "entropy": 0.08664999157190323, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:15.361396Z", "loop": 6121, "env_steps": 3761356799, "loss": 0.01650865562260151, "avg_return": 0.8636684417724609, "regret": 0.0014092504279688, "entropy": 0.0921868309378624, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:16.216553Z", "loop": 6122, "env_steps": 3761971199, "loss": 0.016484195366501808, "avg_return": 0.8626132607460022, "regret": 0.0014092504279688, "entropy": 0.09151002764701843, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:17.071288Z", "loop": 6123, "env_steps": 3762585599, "loss": 0.01655801199376583, "avg_return": 0.8632277846336365, "regret": 0.0014092504279688, "entropy": 0.09206737577915192, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:17.927424Z", "loop": 6124, "env_steps": 3763199999, "loss": 0.016982343047857285, "avg_return": 0.8630960583686829, "regret": 0.0014092504279688, "entropy": 0.09729527682065964, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:18.782077Z", "loop": 6125, "env_steps": 3763814399, "loss": 0.016198890283703804, "avg_return": 0.8628208637237549, "regret": 0.0014092504279688, "entropy": 0.09396743774414062, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:19.637760Z", "loop": 6126, "env_steps": 3764428799, "loss": 0.016847319900989532, "avg_return": 0.8633681535720825, "regret": 0.0014092504279688, "entropy": 0.09365159273147583, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:20.493928Z", "loop": 6127, "env_steps": 3765043199, "loss": 0.01722940243780613, "avg_return": 0.8625379800796509, "regret": 0.0014092504279688, "entropy": 0.09304437041282654, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:21.349377Z", "loop": 6128, "env_steps": 3765657599, "loss": 0.017702624201774597, "avg_return": 0.8616375923156738, "regret": 0.0014092504279688, "entropy": 0.09899861365556717, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:22.203905Z", "loop": 6129, "env_steps": 3766271999, "loss": 0.017353177070617676, "avg_return": 0.8622291088104248, "regret": 0.0014092504279688, "entropy": 0.09661214053630829, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:23.098940Z", "loop": 6130, "env_steps": 3766886399, "loss": 0.018309196457266808, "avg_return": 0.8621206879615784, "regret": 0.0011961903655901551, "entropy": 0.09846633672714233, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:23.954143Z", "loop": 6131, "env_steps": 3767500799, "loss": 0.017159992828965187, "avg_return": 0.8630344867706299, "regret": 0.0011961903655901551, "entropy": 0.09665080904960632, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:24.808962Z", "loop": 6132, "env_steps": 3768115199, "loss": 0.01698394864797592, "avg_return": 0.8631685376167297, "regret": 0.0011961903655901551, "entropy": 0.09665040671825409, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:25.664816Z", "loop": 6133, "env_steps": 3768729599, "loss": 0.01692199520766735, "avg_return": 0.8635739088058472, "regret": 0.0011961903655901551, "entropy": 0.09559940546751022, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:26.520889Z", "loop": 6134, "env_steps": 3769343999, "loss": 0.017083870247006416, "avg_return": 0.8635032176971436, "regret": 0.0011961903655901551, "entropy": 0.09540755301713943, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:27.375587Z", "loop": 6135, "env_steps": 3769958399, "loss": 0.01650981977581978, "avg_return": 0.8621781468391418, "regret": 0.0011961903655901551, "entropy": 0.0968097597360611, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:28.230540Z", "loop": 6136, "env_steps": 3770572799, "loss": 0.017756644636392593, "avg_return": 0.863000214099884, "regret": 0.0011961903655901551, "entropy": 0.0955321192741394, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:29.085815Z", "loop": 6137, "env_steps": 3771187199, "loss": 0.016703473404049873, "avg_return": 0.8620426654815674, "regret": 0.0011961903655901551, "entropy": 0.09690406918525696, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:29.941210Z", "loop": 6138, "env_steps": 3771801599, "loss": 0.017991837114095688, "avg_return": 0.8620477318763733, "regret": 0.0011961903655901551, "entropy": 0.09938711673021317, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:30.797048Z", "loop": 6139, "env_steps": 3772415999, "loss": 0.016936728730797768, "avg_return": 0.8624621629714966, "regret": 0.0011961903655901551, "entropy": 0.09619280695915222, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:31.692621Z", "loop": 6140, "env_steps": 3773030399, "loss": 0.01763251982629299, "avg_return": 0.8619582056999207, "regret": 0.0014894771156832576, "entropy": 0.10124369710683823, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:32.549064Z", "loop": 6141, "env_steps": 3773644799, "loss": 0.01778181456029415, "avg_return": 0.8612511157989502, "regret": 0.0014894771156832576, "entropy": 0.1022832915186882, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:33.404421Z", "loop": 6142, "env_steps": 3774259199, "loss": 0.018898701295256615, "avg_return": 0.8622112274169922, "regret": 0.0014894771156832576, "entropy": 0.10855045169591904, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:34.259957Z", "loop": 6143, "env_steps": 3774873599, "loss": 0.01899331994354725, "avg_return": 0.8584790229797363, "regret": 0.0014894771156832576, "entropy": 0.10783262550830841, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:35.115760Z", "loop": 6144, "env_steps": 3775487999, "loss": 0.020413069054484367, "avg_return": 0.8595518469810486, "regret": 0.0014894771156832576, "entropy": 0.1163487359881401, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:35.972289Z", "loop": 6145, "env_steps": 3776102399, "loss": 0.020156828686594963, "avg_return": 0.8609975576400757, "regret": 0.0014894771156832576, "entropy": 0.11619501560926437, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:36.828664Z", "loop": 6146, "env_steps": 3776716799, "loss": 0.0205660592764616, "avg_return": 0.8590853214263916, "regret": 0.0014894771156832576, "entropy": 0.11503077298402786, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:37.684962Z", "loop": 6147, "env_steps": 3777331199, "loss": 0.021936848759651184, "avg_return": 0.8594987392425537, "regret": 0.0014894771156832576, "entropy": 0.12353384494781494, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:38.540663Z", "loop": 6148, "env_steps": 3777945599, "loss": 0.023027775809168816, "avg_return": 0.8585337400436401, "regret": 0.0014894771156832576, "entropy": 0.12973015010356903, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:39.396475Z", "loop": 6149, "env_steps": 3778559999, "loss": 0.02370677888393402, "avg_return": 0.8580151796340942, "regret": 0.0014894771156832576, "entropy": 0.13165323436260223, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:40.291679Z", "loop": 6150, "env_steps": 3779174399, "loss": 0.02257678471505642, "avg_return": 0.8593202829360962, "regret": 0.004754469729959965, "entropy": 0.13183389604091644, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:41.146674Z", "loop": 6151, "env_steps": 3779788799, "loss": 0.022335385903716087, "avg_return": 0.8593778610229492, "regret": 0.004754469729959965, "entropy": 0.12736447155475616, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:42.002528Z", "loop": 6152, "env_steps": 3780403199, "loss": 0.023736998438835144, "avg_return": 0.8580526113510132, "regret": 0.004754469729959965, "entropy": 0.13051003217697144, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:42.858251Z", "loop": 6153, "env_steps": 3781017599, "loss": 0.02348455786705017, "avg_return": 0.8583459854125977, "regret": 0.004754469729959965, "entropy": 0.128243088722229, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:43.712022Z", "loop": 6154, "env_steps": 3781631999, "loss": 0.023240260779857635, "avg_return": 0.8566761612892151, "regret": 0.004754469729959965, "entropy": 0.12870608270168304, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:44.566625Z", "loop": 6155, "env_steps": 3782246399, "loss": 0.025299951434135437, "avg_return": 0.8576874732971191, "regret": 0.004754469729959965, "entropy": 0.13350263237953186, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:45.422285Z", "loop": 6156, "env_steps": 3782860799, "loss": 0.023900730535387993, "avg_return": 0.8567413687705994, "regret": 0.004754469729959965, "entropy": 0.13210079073905945, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:46.277125Z", "loop": 6157, "env_steps": 3783475199, "loss": 0.0250575989484787, "avg_return": 0.8560845255851746, "regret": 0.004754469729959965, "entropy": 0.12772691249847412, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:47.132474Z", "loop": 6158, "env_steps": 3784089599, "loss": 0.023923464119434357, "avg_return": 0.8556059002876282, "regret": 0.004754469729959965, "entropy": 0.12887509167194366, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:47.988293Z", "loop": 6159, "env_steps": 3784703999, "loss": 0.025415895506739616, "avg_return": 0.856913685798645, "regret": 0.004754469729959965, "entropy": 0.1352667510509491, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:48.886595Z", "loop": 6160, "env_steps": 3785318399, "loss": 0.02648870460689068, "avg_return": 0.854066789150238, "regret": 0.007683805655688047, "entropy": 0.13281045854091644, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:49.742278Z", "loop": 6161, "env_steps": 3785932799, "loss": 0.025844797492027283, "avg_return": 0.8556872606277466, "regret": 0.007683805655688047, "entropy": 0.13822703063488007, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:50.597026Z", "loop": 6162, "env_steps": 3786547199, "loss": 0.026981735602021217, "avg_return": 0.8575896620750427, "regret": 0.007683805655688047, "entropy": 0.1391889601945877, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:51.451127Z", "loop": 6163, "env_steps": 3787161599, "loss": 0.027259722352027893, "avg_return": 0.8573827147483826, "regret": 0.007683805655688047, "entropy": 0.1438155472278595, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:52.306352Z", "loop": 6164, "env_steps": 3787775999, "loss": 0.026992827653884888, "avg_return": 0.8580609560012817, "regret": 0.007683805655688047, "entropy": 0.14643892645835876, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:53.161362Z", "loop": 6165, "env_steps": 3788390399, "loss": 0.02919396199285984, "avg_return": 0.8584402799606323, "regret": 0.007683805655688047, "entropy": 0.15115776658058167, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:54.015443Z", "loop": 6166, "env_steps": 3789004799, "loss": 0.02844315767288208, "avg_return": 0.8577211499214172, "regret": 0.007683805655688047, "entropy": 0.15259282290935516, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:54.869904Z", "loop": 6167, "env_steps": 3789619199, "loss": 0.029262730851769447, "avg_return": 0.8597375750541687, "regret": 0.007683805655688047, "entropy": 0.14897119998931885, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:55.725399Z", "loop": 6168, "env_steps": 3790233599, "loss": 0.028715891763567924, "avg_return": 0.8590027093887329, "regret": 0.007683805655688047, "entropy": 0.15082652866840363, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:56.581331Z", "loop": 6169, "env_steps": 3790847999, "loss": 0.025980019941926003, "avg_return": 0.860682487487793, "regret": 0.007683805655688047, "entropy": 0.1385667622089386, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:57.478796Z", "loop": 6170, "env_steps": 3791462399, "loss": 0.024329664185643196, "avg_return": 0.8620864152908325, "regret": 0.0023884137626737356, "entropy": 0.1303407996892929, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:58.333855Z", "loop": 6171, "env_steps": 3792076799, "loss": 0.023180630058050156, "avg_return": 0.8622855544090271, "regret": 0.0023884137626737356, "entropy": 0.12386374920606613, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:51:59.189183Z", "loop": 6172, "env_steps": 3792691199, "loss": 0.020066438242793083, "avg_return": 0.861710250377655, "regret": 0.0023884137626737356, "entropy": 0.11302302032709122, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:00.044396Z", "loop": 6173, "env_steps": 3793305599, "loss": 0.021565860137343407, "avg_return": 0.8619418740272522, "regret": 0.0023884137626737356, "entropy": 0.1151101365685463, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:00.899094Z", "loop": 6174, "env_steps": 3793919999, "loss": 0.019936366006731987, "avg_return": 0.8619482517242432, "regret": 0.0023884137626737356, "entropy": 0.11588752269744873, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:01.754246Z", "loop": 6175, "env_steps": 3794534399, "loss": 0.020321303978562355, "avg_return": 0.8618815541267395, "regret": 0.0023884137626737356, "entropy": 0.11670678853988647, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:02.609638Z", "loop": 6176, "env_steps": 3795148799, "loss": 0.021773405373096466, "avg_return": 0.8618174195289612, "regret": 0.0023884137626737356, "entropy": 0.11863936483860016, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:03.463756Z", "loop": 6177, "env_steps": 3795763199, "loss": 0.0210589449852705, "avg_return": 0.8630107045173645, "regret": 0.0023884137626737356, "entropy": 0.11522185802459717, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:04.318916Z", "loop": 6178, "env_steps": 3796377599, "loss": 0.020379114896059036, "avg_return": 0.8616154193878174, "regret": 0.0023884137626737356, "entropy": 0.11037475615739822, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:05.174391Z", "loop": 6179, "env_steps": 3796991999, "loss": 0.021324722096323967, "avg_return": 0.8603355288505554, "regret": 0.0023884137626737356, "entropy": 0.11576632410287857, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:06.070767Z", "loop": 6180, "env_steps": 3797606399, "loss": 0.02185988239943981, "avg_return": 0.8610286712646484, "regret": 0.002213904168456793, "entropy": 0.1206418126821518, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:06.925431Z", "loop": 6181, "env_steps": 3798220799, "loss": 0.02064933441579342, "avg_return": 0.8622286319732666, "regret": 0.002213904168456793, "entropy": 0.11176645755767822, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:07.780294Z", "loop": 6182, "env_steps": 3798835199, "loss": 0.018795093521475792, "avg_return": 0.8620241284370422, "regret": 0.002213904168456793, "entropy": 0.11183366924524307, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:08.637277Z", "loop": 6183, "env_steps": 3799449599, "loss": 0.017998557537794113, "avg_return": 0.8610988855361938, "regret": 0.002213904168456793, "entropy": 0.10159356147050858, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:09.494377Z", "loop": 6184, "env_steps": 3800063999, "loss": 0.018416745588183403, "avg_return": 0.8632904291152954, "regret": 0.002213904168456793, "entropy": 0.10114564001560211, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:10.349507Z", "loop": 6185, "env_steps": 3800678399, "loss": 0.018571408465504646, "avg_return": 0.861564576625824, "regret": 0.002213904168456793, "entropy": 0.09821260720491409, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:11.204265Z", "loop": 6186, "env_steps": 3801292799, "loss": 0.017279593273997307, "avg_return": 0.861686646938324, "regret": 0.002213904168456793, "entropy": 0.09580796957015991, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:12.060381Z", "loop": 6187, "env_steps": 3801907199, "loss": 0.01666613668203354, "avg_return": 0.8624895215034485, "regret": 0.002213904168456793, "entropy": 0.09202452003955841, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:12.915605Z", "loop": 6188, "env_steps": 3802521599, "loss": 0.01854001358151436, "avg_return": 0.8633024096488953, "regret": 0.002213904168456793, "entropy": 0.10045439749956131, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:13.770602Z", "loop": 6189, "env_steps": 3803135999, "loss": 0.017597708851099014, "avg_return": 0.8622199892997742, "regret": 0.002213904168456793, "entropy": 0.09270701557397842, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:14.666116Z", "loop": 6190, "env_steps": 3803750399, "loss": 0.014941036701202393, "avg_return": 0.8629842400550842, "regret": 0.0010667274473235011, "entropy": 0.08594641834497452, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:15.522191Z", "loop": 6191, "env_steps": 3804364799, "loss": 0.015433810651302338, "avg_return": 0.8634909391403198, "regret": 0.0010667274473235011, "entropy": 0.0869130864739418, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:16.377371Z", "loop": 6192, "env_steps": 3804979199, "loss": 0.014974516816437244, "avg_return": 0.8633435368537903, "regret": 0.0010667274473235011, "entropy": 0.08579394221305847, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:17.232801Z", "loop": 6193, "env_steps": 3805593599, "loss": 0.015190339647233486, "avg_return": 0.8614428639411926, "regret": 0.0010667274473235011, "entropy": 0.08923433721065521, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:18.087536Z", "loop": 6194, "env_steps": 3806207999, "loss": 0.016286753118038177, "avg_return": 0.8633723258972168, "regret": 0.0010667274473235011, "entropy": 0.08977404236793518, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:18.943050Z", "loop": 6195, "env_steps": 3806822399, "loss": 0.015886573120951653, "avg_return": 0.8598157167434692, "regret": 0.0010667274473235011, "entropy": 0.08936599642038345, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:19.798613Z", "loop": 6196, "env_steps": 3807436799, "loss": 0.0160750150680542, "avg_return": 0.8613641858100891, "regret": 0.0010667274473235011, "entropy": 0.08802910894155502, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:20.654303Z", "loop": 6197, "env_steps": 3808051199, "loss": 0.017108237370848656, "avg_return": 0.8605912327766418, "regret": 0.0010667274473235011, "entropy": 0.09303918480873108, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:21.509463Z", "loop": 6198, "env_steps": 3808665599, "loss": 0.015692157670855522, "avg_return": 0.8618466258049011, "regret": 0.0010667274473235011, "entropy": 0.0919308215379715, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:22.365551Z", "loop": 6199, "env_steps": 3809279999, "loss": 0.01750100776553154, "avg_return": 0.8620213270187378, "regret": 0.0010667274473235011, "entropy": 0.09639164805412292, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:23.263194Z", "loop": 6200, "env_steps": 3809894399, "loss": 0.017397133633494377, "avg_return": 0.8611000776290894, "regret": 0.0024652599822729826, "entropy": 0.09491810947656631, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:24.119758Z", "loop": 6201, "env_steps": 3810508799, "loss": 0.016423841938376427, "avg_return": 0.8612517714500427, "regret": 0.0024652599822729826, "entropy": 0.09073711186647415, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:24.974878Z", "loop": 6202, "env_steps": 3811123199, "loss": 0.016845770180225372, "avg_return": 0.8606764078140259, "regret": 0.0024652599822729826, "entropy": 0.09042131900787354, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:25.830589Z", "loop": 6203, "env_steps": 3811737599, "loss": 0.01578139327466488, "avg_return": 0.8615731000900269, "regret": 0.0024652599822729826, "entropy": 0.08683206886053085, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:26.685015Z", "loop": 6204, "env_steps": 3812351999, "loss": 0.01726343110203743, "avg_return": 0.8624946475028992, "regret": 0.0024652599822729826, "entropy": 0.0907931849360466, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:27.539863Z", "loop": 6205, "env_steps": 3812966399, "loss": 0.016400758177042007, "avg_return": 0.8621987104415894, "regret": 0.0024652599822729826, "entropy": 0.08773773163557053, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:28.394817Z", "loop": 6206, "env_steps": 3813580799, "loss": 0.016131171956658363, "avg_return": 0.8631662130355835, "regret": 0.0024652599822729826, "entropy": 0.09237643331289291, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:29.250090Z", "loop": 6207, "env_steps": 3814195199, "loss": 0.015742260962724686, "avg_return": 0.8611488938331604, "regret": 0.0024652599822729826, "entropy": 0.0894191786646843, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:30.105590Z", "loop": 6208, "env_steps": 3814809599, "loss": 0.015335343778133392, "avg_return": 0.8613458275794983, "regret": 0.0024652599822729826, "entropy": 0.08813686668872833, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:30.961735Z", "loop": 6209, "env_steps": 3815423999, "loss": 0.01525921281427145, "avg_return": 0.8617959022521973, "regret": 0.0024652599822729826, "entropy": 0.08831475675106049, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:31.857930Z", "loop": 6210, "env_steps": 3816038399, "loss": 0.01630043238401413, "avg_return": 0.861358642578125, "regret": 0.0020221599843353033, "entropy": 0.08980847150087357, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:32.714188Z", "loop": 6211, "env_steps": 3816652799, "loss": 0.015681788325309753, "avg_return": 0.8614801168441772, "regret": 0.0020221599843353033, "entropy": 0.08752012997865677, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:33.570076Z", "loop": 6212, "env_steps": 3817267199, "loss": 0.017101973295211792, "avg_return": 0.859903872013092, "regret": 0.0020221599843353033, "entropy": 0.09628593921661377, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:34.425758Z", "loop": 6213, "env_steps": 3817881599, "loss": 0.01792251132428646, "avg_return": 0.8606715202331543, "regret": 0.0020221599843353033, "entropy": 0.10193661600351334, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:35.282577Z", "loop": 6214, "env_steps": 3818495999, "loss": 0.018338380381464958, "avg_return": 0.8583313226699829, "regret": 0.0020221599843353033, "entropy": 0.09646862745285034, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:36.139527Z", "loop": 6215, "env_steps": 3819110399, "loss": 0.01705101691186428, "avg_return": 0.8586794137954712, "regret": 0.0020221599843353033, "entropy": 0.0947520062327385, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:36.995215Z", "loop": 6216, "env_steps": 3819724799, "loss": 0.017595576122403145, "avg_return": 0.856981098651886, "regret": 0.0020221599843353033, "entropy": 0.09643996506929398, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:37.850230Z", "loop": 6217, "env_steps": 3820339199, "loss": 0.017684277147054672, "avg_return": 0.8592332005500793, "regret": 0.0020221599843353033, "entropy": 0.0972619280219078, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:38.705493Z", "loop": 6218, "env_steps": 3820953599, "loss": 0.017918597906827927, "avg_return": 0.8618023991584778, "regret": 0.0020221599843353033, "entropy": 0.09976495802402496, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:39.561676Z", "loop": 6219, "env_steps": 3821567999, "loss": 0.016120174899697304, "avg_return": 0.8616585731506348, "regret": 0.0020221599843353033, "entropy": 0.09144378453493118, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:40.456325Z", "loop": 6220, "env_steps": 3822182399, "loss": 0.01540599949657917, "avg_return": 0.8625099062919617, "regret": 0.002170477993786335, "entropy": 0.08709350228309631, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:41.312473Z", "loop": 6221, "env_steps": 3822796799, "loss": 0.014826630242168903, "avg_return": 0.8624204993247986, "regret": 0.002170477993786335, "entropy": 0.08410616219043732, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:42.166884Z", "loop": 6222, "env_steps": 3823411199, "loss": 0.013921177946031094, "avg_return": 0.8624661564826965, "regret": 0.002170477993786335, "entropy": 0.08128026872873306, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:43.021973Z", "loop": 6223, "env_steps": 3824025599, "loss": 0.01518203318119049, "avg_return": 0.8625956177711487, "regret": 0.002170477993786335, "entropy": 0.08795290440320969, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:43.877439Z", "loop": 6224, "env_steps": 3824639999, "loss": 0.015507319942116737, "avg_return": 0.8622716665267944, "regret": 0.002170477993786335, "entropy": 0.08698458969593048, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:44.732608Z", "loop": 6225, "env_steps": 3825254399, "loss": 0.01735970564186573, "avg_return": 0.8616990447044373, "regret": 0.002170477993786335, "entropy": 0.08989766985177994, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:45.587930Z", "loop": 6226, "env_steps": 3825868799, "loss": 0.016053376719355583, "avg_return": 0.8619018793106079, "regret": 0.002170477993786335, "entropy": 0.08780291676521301, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:46.443925Z", "loop": 6227, "env_steps": 3826483199, "loss": 0.016559602692723274, "avg_return": 0.8621771335601807, "regret": 0.002170477993786335, "entropy": 0.08809739351272583, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:47.299618Z", "loop": 6228, "env_steps": 3827097599, "loss": 0.01700766012072563, "avg_return": 0.8610413074493408, "regret": 0.002170477993786335, "entropy": 0.0960926041007042, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:48.155672Z", "loop": 6229, "env_steps": 3827711999, "loss": 0.017581066116690636, "avg_return": 0.8589974045753479, "regret": 0.002170477993786335, "entropy": 0.09923169761896133, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:49.051916Z", "loop": 6230, "env_steps": 3828326399, "loss": 0.01778581365942955, "avg_return": 0.8578131198883057, "regret": 0.004888871684670448, "entropy": 0.09449376165866852, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:49.907979Z", "loop": 6231, "env_steps": 3828940799, "loss": 0.01785186119377613, "avg_return": 0.8577612638473511, "regret": 0.004888871684670448, "entropy": 0.09834980219602585, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:50.763440Z", "loop": 6232, "env_steps": 3829555199, "loss": 0.017931221053004265, "avg_return": 0.8570829629898071, "regret": 0.004888871684670448, "entropy": 0.10302538424730301, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:51.619748Z", "loop": 6233, "env_steps": 3830169599, "loss": 0.018922489136457443, "avg_return": 0.8583136200904846, "regret": 0.004888871684670448, "entropy": 0.10490667819976807, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:52.476066Z", "loop": 6234, "env_steps": 3830783999, "loss": 0.01820201240479946, "avg_return": 0.8584873676300049, "regret": 0.004888871684670448, "entropy": 0.098171167075634, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:53.331405Z", "loop": 6235, "env_steps": 3831398399, "loss": 0.01734667830169201, "avg_return": 0.8591839671134949, "regret": 0.004888871684670448, "entropy": 0.0967818945646286, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:54.185335Z", "loop": 6236, "env_steps": 3832012799, "loss": 0.018075788393616676, "avg_return": 0.8600038886070251, "regret": 0.004888871684670448, "entropy": 0.0979643166065216, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:55.039237Z", "loop": 6237, "env_steps": 3832627199, "loss": 0.0165863074362278, "avg_return": 0.8617173433303833, "regret": 0.004888871684670448, "entropy": 0.09241149574518204, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:55.895392Z", "loop": 6238, "env_steps": 3833241599, "loss": 0.016390779986977577, "avg_return": 0.8619053363800049, "regret": 0.004888871684670448, "entropy": 0.09155472368001938, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:56.751006Z", "loop": 6239, "env_steps": 3833855999, "loss": 0.015882370993494987, "avg_return": 0.861815333366394, "regret": 0.004888871684670448, "entropy": 0.0892384871840477, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:57.646167Z", "loop": 6240, "env_steps": 3834470399, "loss": 0.016098320484161377, "avg_return": 0.8626774549484253, "regret": 0.0011628266656771302, "entropy": 0.08557089418172836, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:58.501353Z", "loop": 6241, "env_steps": 3835084799, "loss": 0.016572190448641777, "avg_return": 0.8624006509780884, "regret": 0.0011628266656771302, "entropy": 0.08621916174888611, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:52:59.357207Z", "loop": 6242, "env_steps": 3835699199, "loss": 0.016770081594586372, "avg_return": 0.863124430179596, "regret": 0.0011628266656771302, "entropy": 0.08882491290569305, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:00.213161Z", "loop": 6243, "env_steps": 3836313599, "loss": 0.016753515228629112, "avg_return": 0.8626353144645691, "regret": 0.0011628266656771302, "entropy": 0.0904284194111824, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:01.068797Z", "loop": 6244, "env_steps": 3836927999, "loss": 0.016607746481895447, "avg_return": 0.8623393774032593, "regret": 0.0011628266656771302, "entropy": 0.09314772486686707, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:01.923838Z", "loop": 6245, "env_steps": 3837542399, "loss": 0.017170865088701248, "avg_return": 0.8596901893615723, "regret": 0.0011628266656771302, "entropy": 0.09512742608785629, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:02.779458Z", "loop": 6246, "env_steps": 3838156799, "loss": 0.01831095479428768, "avg_return": 0.8596692085266113, "regret": 0.0011628266656771302, "entropy": 0.10296724736690521, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:03.635053Z", "loop": 6247, "env_steps": 3838771199, "loss": 0.01769060268998146, "avg_return": 0.8594484925270081, "regret": 0.0011628266656771302, "entropy": 0.10237990319728851, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:04.489656Z", "loop": 6248, "env_steps": 3839385599, "loss": 0.022396070882678032, "avg_return": 0.8587157130241394, "regret": 0.0011628266656771302, "entropy": 0.1175541952252388, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:05.343844Z", "loop": 6249, "env_steps": 3839999999, "loss": 0.020268471911549568, "avg_return": 0.8570383191108704, "regret": 0.0011628266656771302, "entropy": 0.11117459088563919, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:06.241112Z", "loop": 6250, "env_steps": 3840614399, "loss": 0.022149914875626564, "avg_return": 0.8542320728302002, "regret": 0.009102300740778446, "entropy": 0.11746618896722794, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:07.095286Z", "loop": 6251, "env_steps": 3841228799, "loss": 0.022527454420924187, "avg_return": 0.8499313592910767, "regret": 0.009102300740778446, "entropy": 0.11721924692392349, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:07.950256Z", "loop": 6252, "env_steps": 3841843199, "loss": 0.023476257920265198, "avg_return": 0.8470850586891174, "regret": 0.009102300740778446, "entropy": 0.12333936989307404, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:08.805664Z", "loop": 6253, "env_steps": 3842457599, "loss": 0.023872684687376022, "avg_return": 0.850898027420044, "regret": 0.009102300740778446, "entropy": 0.12332528829574585, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:09.660277Z", "loop": 6254, "env_steps": 3843071999, "loss": 0.02567620575428009, "avg_return": 0.8513223528862, "regret": 0.009102300740778446, "entropy": 0.13611933588981628, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:10.514519Z", "loop": 6255, "env_steps": 3843686399, "loss": 0.02464744821190834, "avg_return": 0.8542388081550598, "regret": 0.009102300740778446, "entropy": 0.13599924743175507, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:11.369082Z", "loop": 6256, "env_steps": 3844300799, "loss": 0.026615215465426445, "avg_return": 0.8530673980712891, "regret": 0.009102300740778446, "entropy": 0.14252272248268127, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:12.224323Z", "loop": 6257, "env_steps": 3844915199, "loss": 0.027913272380828857, "avg_return": 0.8525490164756775, "regret": 0.009102300740778446, "entropy": 0.14933985471725464, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:13.079625Z", "loop": 6258, "env_steps": 3845529599, "loss": 0.027144504711031914, "avg_return": 0.8502118587493896, "regret": 0.009102300740778446, "entropy": 0.1465158313512802, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:13.934904Z", "loop": 6259, "env_steps": 3846143999, "loss": 0.02960258722305298, "avg_return": 0.8500983119010925, "regret": 0.009102300740778446, "entropy": 0.16050632297992706, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:14.833183Z", "loop": 6260, "env_steps": 3846758399, "loss": 0.02905312180519104, "avg_return": 0.851630687713623, "regret": 0.012691349722445011, "entropy": 0.15803951025009155, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:15.688806Z", "loop": 6261, "env_steps": 3847372799, "loss": 0.027785737067461014, "avg_return": 0.8521113395690918, "regret": 0.012691349722445011, "entropy": 0.1560322493314743, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:16.545080Z", "loop": 6262, "env_steps": 3847987199, "loss": 0.027072248980402946, "avg_return": 0.8547208905220032, "regret": 0.012691349722445011, "entropy": 0.1466391682624817, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:17.400756Z", "loop": 6263, "env_steps": 3848601599, "loss": 0.02459009550511837, "avg_return": 0.8565895557403564, "regret": 0.012691349722445011, "entropy": 0.13869160413742065, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:18.255156Z", "loop": 6264, "env_steps": 3849215999, "loss": 0.02389100380241871, "avg_return": 0.85642009973526, "regret": 0.012691349722445011, "entropy": 0.12964627146720886, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:19.109812Z", "loop": 6265, "env_steps": 3849830399, "loss": 0.023584768176078796, "avg_return": 0.85648113489151, "regret": 0.012691349722445011, "entropy": 0.1268729567527771, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:19.964812Z", "loop": 6266, "env_steps": 3850444799, "loss": 0.023966109380126, "avg_return": 0.8597235083580017, "regret": 0.012691349722445011, "entropy": 0.12478111684322357, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:20.820579Z", "loop": 6267, "env_steps": 3851059199, "loss": 0.02286721207201481, "avg_return": 0.8600621819496155, "regret": 0.012691349722445011, "entropy": 0.12249255925416946, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:21.675580Z", "loop": 6268, "env_steps": 3851673599, "loss": 0.022815024480223656, "avg_return": 0.86085045337677, "regret": 0.012691349722445011, "entropy": 0.1217200979590416, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:22.530824Z", "loop": 6269, "env_steps": 3852287999, "loss": 0.021468453109264374, "avg_return": 0.8614528775215149, "regret": 0.012691349722445011, "entropy": 0.11287172138690948, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:23.427878Z", "loop": 6270, "env_steps": 3852902399, "loss": 0.020555702969431877, "avg_return": 0.8626723289489746, "regret": 0.00208448339253664, "entropy": 0.11261015385389328, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:24.283455Z", "loop": 6271, "env_steps": 3853516799, "loss": 0.02017655037343502, "avg_return": 0.8630657196044922, "regret": 0.00208448339253664, "entropy": 0.10513739287853241, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:25.137738Z", "loop": 6272, "env_steps": 3854131199, "loss": 0.018047083169221878, "avg_return": 0.8625345826148987, "regret": 0.00208448339253664, "entropy": 0.09860149025917053, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:25.993448Z", "loop": 6273, "env_steps": 3854745599, "loss": 0.01860962249338627, "avg_return": 0.8630875945091248, "regret": 0.00208448339253664, "entropy": 0.0998096615076065, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:26.849388Z", "loop": 6274, "env_steps": 3855359999, "loss": 0.018744880333542824, "avg_return": 0.8619750142097473, "regret": 0.00208448339253664, "entropy": 0.0998491644859314, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:27.704341Z", "loop": 6275, "env_steps": 3855974399, "loss": 0.018529808148741722, "avg_return": 0.8620629906654358, "regret": 0.00208448339253664, "entropy": 0.10149435698986053, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:28.559353Z", "loop": 6276, "env_steps": 3856588799, "loss": 0.0184706449508667, "avg_return": 0.8617082834243774, "regret": 0.00208448339253664, "entropy": 0.09946871548891068, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:29.414343Z", "loop": 6277, "env_steps": 3857203199, "loss": 0.018107708543539047, "avg_return": 0.8620477318763733, "regret": 0.00208448339253664, "entropy": 0.10155889391899109, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:30.270543Z", "loop": 6278, "env_steps": 3857817599, "loss": 0.01797436736524105, "avg_return": 0.8620151877403259, "regret": 0.00208448339253664, "entropy": 0.0996747687458992, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:31.126538Z", "loop": 6279, "env_steps": 3858431999, "loss": 0.01712157018482685, "avg_return": 0.8603556752204895, "regret": 0.00208448339253664, "entropy": 0.09802639484405518, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:32.021847Z", "loop": 6280, "env_steps": 3859046399, "loss": 0.016305027529597282, "avg_return": 0.8606502413749695, "regret": 0.002454218454658985, "entropy": 0.09400591254234314, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:32.877559Z", "loop": 6281, "env_steps": 3859660799, "loss": 0.0163207296282053, "avg_return": 0.8626446723937988, "regret": 0.002454218454658985, "entropy": 0.09046807885169983, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:33.732845Z", "loop": 6282, "env_steps": 3860275199, "loss": 0.01723431423306465, "avg_return": 0.8624888062477112, "regret": 0.002454218454658985, "entropy": 0.09269893169403076, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:34.588082Z", "loop": 6283, "env_steps": 3860889599, "loss": 0.017830785363912582, "avg_return": 0.8617491126060486, "regret": 0.002454218454658985, "entropy": 0.09363984316587448, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:35.444240Z", "loop": 6284, "env_steps": 3861503999, "loss": 0.016094772145152092, "avg_return": 0.8624415397644043, "regret": 0.002454218454658985, "entropy": 0.08703923970460892, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:36.299532Z", "loop": 6285, "env_steps": 3862118399, "loss": 0.01549075823277235, "avg_return": 0.8633020520210266, "regret": 0.002454218454658985, "entropy": 0.08764658868312836, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:37.154468Z", "loop": 6286, "env_steps": 3862732799, "loss": 0.016201892867684364, "avg_return": 0.8624457716941833, "regret": 0.002454218454658985, "entropy": 0.08551744371652603, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:38.009807Z", "loop": 6287, "env_steps": 3863347199, "loss": 0.014522927813231945, "avg_return": 0.8624750971794128, "regret": 0.002454218454658985, "entropy": 0.08385015279054642, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:38.864441Z", "loop": 6288, "env_steps": 3863961599, "loss": 0.014461240731179714, "avg_return": 0.8617554903030396, "regret": 0.002454218454658985, "entropy": 0.07950762659311295, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:39.719361Z", "loop": 6289, "env_steps": 3864575999, "loss": 0.015630044043064117, "avg_return": 0.8627653121948242, "regret": 0.002454218454658985, "entropy": 0.08417955785989761, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:40.615213Z", "loop": 6290, "env_steps": 3865190399, "loss": 0.015290207229554653, "avg_return": 0.8618477582931519, "regret": 0.002026390051469207, "entropy": 0.08277197927236557, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:41.469667Z", "loop": 6291, "env_steps": 3865804799, "loss": 0.015072225593030453, "avg_return": 0.8614817261695862, "regret": 0.002026390051469207, "entropy": 0.08890251070261002, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:42.324352Z", "loop": 6292, "env_steps": 3866419199, "loss": 0.017213119193911552, "avg_return": 0.8597656488418579, "regret": 0.002026390051469207, "entropy": 0.09184856712818146, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:43.180882Z", "loop": 6293, "env_steps": 3867033599, "loss": 0.01664961315691471, "avg_return": 0.8594643473625183, "regret": 0.002026390051469207, "entropy": 0.08881323039531708, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:44.036394Z", "loop": 6294, "env_steps": 3867647999, "loss": 0.017565244808793068, "avg_return": 0.8579831123352051, "regret": 0.002026390051469207, "entropy": 0.09612619876861572, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:44.891027Z", "loop": 6295, "env_steps": 3868262399, "loss": 0.017424819990992546, "avg_return": 0.8576158881187439, "regret": 0.002026390051469207, "entropy": 0.0967075526714325, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:45.745776Z", "loop": 6296, "env_steps": 3868876799, "loss": 0.01599310152232647, "avg_return": 0.8577883243560791, "regret": 0.002026390051469207, "entropy": 0.08735490590333939, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:46.601591Z", "loop": 6297, "env_steps": 3869491199, "loss": 0.018405377864837646, "avg_return": 0.8596281409263611, "regret": 0.002026390051469207, "entropy": 0.09646864235401154, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:47.456558Z", "loop": 6298, "env_steps": 3870105599, "loss": 0.018113410100340843, "avg_return": 0.8599912524223328, "regret": 0.002026390051469207, "entropy": 0.09768474847078323, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:48.311654Z", "loop": 6299, "env_steps": 3870719999, "loss": 0.015525603666901588, "avg_return": 0.86081862449646, "regret": 0.002026390051469207, "entropy": 0.09190063923597336, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:49.205872Z", "loop": 6300, "env_steps": 3871334399, "loss": 0.017679570242762566, "avg_return": 0.8602553606033325, "regret": 0.0034600156359374523, "entropy": 0.09259594976902008, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:50.061320Z", "loop": 6301, "env_steps": 3871948799, "loss": 0.01759573258459568, "avg_return": 0.8593524098396301, "regret": 0.0034600156359374523, "entropy": 0.09538467973470688, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:50.918032Z", "loop": 6302, "env_steps": 3872563199, "loss": 0.018461354076862335, "avg_return": 0.8617292642593384, "regret": 0.0034600156359374523, "entropy": 0.09483282268047333, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:51.773352Z", "loop": 6303, "env_steps": 3873177599, "loss": 0.018025709316134453, "avg_return": 0.8609071969985962, "regret": 0.0034600156359374523, "entropy": 0.09789133816957474, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:52.629116Z", "loop": 6304, "env_steps": 3873791999, "loss": 0.016615603119134903, "avg_return": 0.8623098134994507, "regret": 0.0034600156359374523, "entropy": 0.08886216580867767, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:53.485224Z", "loop": 6305, "env_steps": 3874406399, "loss": 0.016001280397176743, "avg_return": 0.8609598278999329, "regret": 0.0034600156359374523, "entropy": 0.08621737360954285, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:54.341734Z", "loop": 6306, "env_steps": 3875020799, "loss": 0.016591636463999748, "avg_return": 0.8614504337310791, "regret": 0.0034600156359374523, "entropy": 0.08937151730060577, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:55.198632Z", "loop": 6307, "env_steps": 3875635199, "loss": 0.015396391041576862, "avg_return": 0.8624877333641052, "regret": 0.0034600156359374523, "entropy": 0.0893220603466034, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:56.054882Z", "loop": 6308, "env_steps": 3876249599, "loss": 0.016680901870131493, "avg_return": 0.861548900604248, "regret": 0.0034600156359374523, "entropy": 0.0905536338686943, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:56.910579Z", "loop": 6309, "env_steps": 3876863999, "loss": 0.017110921442508698, "avg_return": 0.86326003074646, "regret": 0.0034600156359374523, "entropy": 0.09395765513181686, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:57.807633Z", "loop": 6310, "env_steps": 3877478399, "loss": 0.017004044726490974, "avg_return": 0.8612061738967896, "regret": 0.001989486627280712, "entropy": 0.09486988931894302, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:58.663305Z", "loop": 6311, "env_steps": 3878092799, "loss": 0.01592222973704338, "avg_return": 0.8616361618041992, "regret": 0.001989486627280712, "entropy": 0.09075023978948593, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:53:59.518210Z", "loop": 6312, "env_steps": 3878707199, "loss": 0.01719602569937706, "avg_return": 0.860282838344574, "regret": 0.001989486627280712, "entropy": 0.0968279093503952, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:00.374035Z", "loop": 6313, "env_steps": 3879321599, "loss": 0.016251077875494957, "avg_return": 0.8600876331329346, "regret": 0.001989486627280712, "entropy": 0.09318824112415314, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:01.229317Z", "loop": 6314, "env_steps": 3879935999, "loss": 0.017031336203217506, "avg_return": 0.8609885573387146, "regret": 0.001989486627280712, "entropy": 0.09437011927366257, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:02.086058Z", "loop": 6315, "env_steps": 3880550399, "loss": 0.016129586845636368, "avg_return": 0.8615003824234009, "regret": 0.001989486627280712, "entropy": 0.09267760068178177, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:02.942339Z", "loop": 6316, "env_steps": 3881164799, "loss": 0.01676773652434349, "avg_return": 0.8613627552986145, "regret": 0.001989486627280712, "entropy": 0.09628771990537643, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:03.797579Z", "loop": 6317, "env_steps": 3881779199, "loss": 0.01690298691391945, "avg_return": 0.860668957233429, "regret": 0.001989486627280712, "entropy": 0.09973203390836716, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:04.652270Z", "loop": 6318, "env_steps": 3882393599, "loss": 0.017133604735136032, "avg_return": 0.8607392311096191, "regret": 0.001989486627280712, "entropy": 0.10019871592521667, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:05.506702Z", "loop": 6319, "env_steps": 3883007999, "loss": 0.018405409529805183, "avg_return": 0.8582177758216858, "regret": 0.001989486627280712, "entropy": 0.10728906840085983, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:06.403583Z", "loop": 6320, "env_steps": 3883622399, "loss": 0.01883039064705372, "avg_return": 0.8583618402481079, "regret": 0.004495156463235617, "entropy": 0.10432201623916626, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:07.259140Z", "loop": 6321, "env_steps": 3884236799, "loss": 0.0190005823969841, "avg_return": 0.8595823645591736, "regret": 0.004495156463235617, "entropy": 0.1081337183713913, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:08.114243Z", "loop": 6322, "env_steps": 3884851199, "loss": 0.01772216707468033, "avg_return": 0.8595139980316162, "regret": 0.004495156463235617, "entropy": 0.10345040261745453, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:08.968892Z", "loop": 6323, "env_steps": 3885465599, "loss": 0.01735331118106842, "avg_return": 0.859856367111206, "regret": 0.004495156463235617, "entropy": 0.09981860220432281, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:09.824767Z", "loop": 6324, "env_steps": 3886079999, "loss": 0.018366605043411255, "avg_return": 0.8595911860466003, "regret": 0.004495156463235617, "entropy": 0.107011578977108, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:10.679332Z", "loop": 6325, "env_steps": 3886694399, "loss": 0.01750940829515457, "avg_return": 0.8617305755615234, "regret": 0.004495156463235617, "entropy": 0.09833917766809464, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:11.534349Z", "loop": 6326, "env_steps": 3887308799, "loss": 0.01891346648335457, "avg_return": 0.8604154586791992, "regret": 0.004495156463235617, "entropy": 0.10536998510360718, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:12.389279Z", "loop": 6327, "env_steps": 3887923199, "loss": 0.016102997586131096, "avg_return": 0.8607344627380371, "regret": 0.004495156463235617, "entropy": 0.0979740172624588, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:13.244697Z", "loop": 6328, "env_steps": 3888537599, "loss": 0.017539797350764275, "avg_return": 0.8625008463859558, "regret": 0.004495156463235617, "entropy": 0.10127371549606323, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:14.099422Z", "loop": 6329, "env_steps": 3889151999, "loss": 0.018512656912207603, "avg_return": 0.8622851967811584, "regret": 0.004495156463235617, "entropy": 0.10210108011960983, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:14.993694Z", "loop": 6330, "env_steps": 3889766399, "loss": 0.01785298064351082, "avg_return": 0.8597210645675659, "regret": 0.0018822082784026861, "entropy": 0.09924142062664032, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:15.848686Z", "loop": 6331, "env_steps": 3890380799, "loss": 0.016424814239144325, "avg_return": 0.8623512983322144, "regret": 0.0018822082784026861, "entropy": 0.0990247130393982, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:16.704480Z", "loop": 6332, "env_steps": 3890995199, "loss": 0.017816899344325066, "avg_return": 0.8615803122520447, "regret": 0.0018822082784026861, "entropy": 0.10411833226680756, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:17.560335Z", "loop": 6333, "env_steps": 3891609599, "loss": 0.018394656479358673, "avg_return": 0.8617055416107178, "regret": 0.0018822082784026861, "entropy": 0.09970158338546753, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:18.415503Z", "loop": 6334, "env_steps": 3892223999, "loss": 0.017833223566412926, "avg_return": 0.8613905906677246, "regret": 0.0018822082784026861, "entropy": 0.10299080610275269, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:19.270699Z", "loop": 6335, "env_steps": 3892838399, "loss": 0.018915673717856407, "avg_return": 0.861065685749054, "regret": 0.0018822082784026861, "entropy": 0.1012798547744751, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:20.126251Z", "loop": 6336, "env_steps": 3893452799, "loss": 0.01764032058417797, "avg_return": 0.8616465330123901, "regret": 0.0018822082784026861, "entropy": 0.09930668026208878, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:20.981020Z", "loop": 6337, "env_steps": 3894067199, "loss": 0.01786009594798088, "avg_return": 0.8632580041885376, "regret": 0.0018822082784026861, "entropy": 0.10069078207015991, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:21.837502Z", "loop": 6338, "env_steps": 3894681599, "loss": 0.019224364310503006, "avg_return": 0.8619980812072754, "regret": 0.0018822082784026861, "entropy": 0.10366912186145782, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:22.693716Z", "loop": 6339, "env_steps": 3895295999, "loss": 0.019939038902521133, "avg_return": 0.861507773399353, "regret": 0.0018822082784026861, "entropy": 0.10936293005943298, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:23.588776Z", "loop": 6340, "env_steps": 3895910399, "loss": 0.01783524826169014, "avg_return": 0.8625807762145996, "regret": 0.0022842336911708117, "entropy": 0.10318692773580551, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:24.443632Z", "loop": 6341, "env_steps": 3896524799, "loss": 0.0186578668653965, "avg_return": 0.8602663278579712, "regret": 0.0022842336911708117, "entropy": 0.10574835538864136, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:25.298765Z", "loop": 6342, "env_steps": 3897139199, "loss": 0.018698131665587425, "avg_return": 0.8603327870368958, "regret": 0.0022842336911708117, "entropy": 0.10324022173881531, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:26.155069Z", "loop": 6343, "env_steps": 3897753599, "loss": 0.017528042197227478, "avg_return": 0.8610818982124329, "regret": 0.0022842336911708117, "entropy": 0.1012110784649849, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:27.012895Z", "loop": 6344, "env_steps": 3898367999, "loss": 0.018734579905867577, "avg_return": 0.8617331981658936, "regret": 0.0022842336911708117, "entropy": 0.10622400045394897, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:27.867751Z", "loop": 6345, "env_steps": 3898982399, "loss": 0.018147259950637817, "avg_return": 0.8612555265426636, "regret": 0.0022842336911708117, "entropy": 0.10543765127658844, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:28.722503Z", "loop": 6346, "env_steps": 3899596799, "loss": 0.019528059288859367, "avg_return": 0.8609421849250793, "regret": 0.0022842336911708117, "entropy": 0.10718077421188354, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:29.578504Z", "loop": 6347, "env_steps": 3900211199, "loss": 0.018963409587740898, "avg_return": 0.8629089593887329, "regret": 0.0022842336911708117, "entropy": 0.10272133350372314, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:30.435226Z", "loop": 6348, "env_steps": 3900825599, "loss": 0.019220886752009392, "avg_return": 0.8615437150001526, "regret": 0.0022842336911708117, "entropy": 0.1045573428273201, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:31.289393Z", "loop": 6349, "env_steps": 3901439999, "loss": 0.01839536987245083, "avg_return": 0.8603811860084534, "regret": 0.0022842336911708117, "entropy": 0.10097197443246841, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:32.184059Z", "loop": 6350, "env_steps": 3902054399, "loss": 0.017889758571982384, "avg_return": 0.8612350821495056, "regret": 0.001996844308450818, "entropy": 0.1014273464679718, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:33.039569Z", "loop": 6351, "env_steps": 3902668799, "loss": 0.01698484644293785, "avg_return": 0.8619918823242188, "regret": 0.001996844308450818, "entropy": 0.10303892940282822, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:33.895266Z", "loop": 6352, "env_steps": 3903283199, "loss": 0.018506405875086784, "avg_return": 0.8619728684425354, "regret": 0.001996844308450818, "entropy": 0.10379740595817566, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:34.750313Z", "loop": 6353, "env_steps": 3903897599, "loss": 0.01767684519290924, "avg_return": 0.8610695600509644, "regret": 0.001996844308450818, "entropy": 0.10394848138093948, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:35.605237Z", "loop": 6354, "env_steps": 3904511999, "loss": 0.01810399815440178, "avg_return": 0.8620888590812683, "regret": 0.001996844308450818, "entropy": 0.10714933276176453, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:36.460660Z", "loop": 6355, "env_steps": 3905126399, "loss": 0.01850929856300354, "avg_return": 0.8622509837150574, "regret": 0.001996844308450818, "entropy": 0.10509216785430908, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:37.317408Z", "loop": 6356, "env_steps": 3905740799, "loss": 0.017801303416490555, "avg_return": 0.8631632924079895, "regret": 0.001996844308450818, "entropy": 0.105072520673275, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:38.173243Z", "loop": 6357, "env_steps": 3906355199, "loss": 0.018033085390925407, "avg_return": 0.8613939881324768, "regret": 0.001996844308450818, "entropy": 0.10739796608686447, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:39.028135Z", "loop": 6358, "env_steps": 3906969599, "loss": 0.018785594031214714, "avg_return": 0.8603808879852295, "regret": 0.001996844308450818, "entropy": 0.10359149426221848, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:39.883123Z", "loop": 6359, "env_steps": 3907583999, "loss": 0.017859909683465958, "avg_return": 0.8609092235565186, "regret": 0.001996844308450818, "entropy": 0.10076373815536499, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:40.779667Z", "loop": 6360, "env_steps": 3908198399, "loss": 0.016682378947734833, "avg_return": 0.8626551628112793, "regret": 0.0017528727184981108, "entropy": 0.09942120313644409, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:41.636599Z", "loop": 6361, "env_steps": 3908812799, "loss": 0.01733493246138096, "avg_return": 0.8620760440826416, "regret": 0.0017528727184981108, "entropy": 0.1003371849656105, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:42.492296Z", "loop": 6362, "env_steps": 3909427199, "loss": 0.017558716237545013, "avg_return": 0.8603289723396301, "regret": 0.0017528727184981108, "entropy": 0.09606959670782089, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:43.347840Z", "loop": 6363, "env_steps": 3910041599, "loss": 0.017927266657352448, "avg_return": 0.861399233341217, "regret": 0.0017528727184981108, "entropy": 0.09908349066972733, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:44.203914Z", "loop": 6364, "env_steps": 3910655999, "loss": 0.018363459035754204, "avg_return": 0.8626919984817505, "regret": 0.0017528727184981108, "entropy": 0.09967780858278275, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:45.059203Z", "loop": 6365, "env_steps": 3911270399, "loss": 0.017133917659521103, "avg_return": 0.8629843592643738, "regret": 0.0017528727184981108, "entropy": 0.09592800587415695, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:45.914329Z", "loop": 6366, "env_steps": 3911884799, "loss": 0.015530243515968323, "avg_return": 0.8627487421035767, "regret": 0.0017528727184981108, "entropy": 0.08789095282554626, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:46.770144Z", "loop": 6367, "env_steps": 3912499199, "loss": 0.016208255663514137, "avg_return": 0.8624888062477112, "regret": 0.0017528727184981108, "entropy": 0.09139619022607803, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:47.625117Z", "loop": 6368, "env_steps": 3913113599, "loss": 0.01582719199359417, "avg_return": 0.8625896573066711, "regret": 0.0017528727184981108, "entropy": 0.08771862089633942, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:48.479733Z", "loop": 6369, "env_steps": 3913727999, "loss": 0.01734299026429653, "avg_return": 0.8645617961883545, "regret": 0.0017528727184981108, "entropy": 0.08858569711446762, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:49.375911Z", "loop": 6370, "env_steps": 3914342399, "loss": 0.014693312346935272, "avg_return": 0.8634928464889526, "regret": 0.0007906815153546631, "entropy": 0.08381275087594986, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:50.233331Z", "loop": 6371, "env_steps": 3914956799, "loss": 0.015804078429937363, "avg_return": 0.8623374700546265, "regret": 0.0007906815153546631, "entropy": 0.08803103119134903, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:51.089231Z", "loop": 6372, "env_steps": 3915571199, "loss": 0.013616873882710934, "avg_return": 0.8635064959526062, "regret": 0.0007906815153546631, "entropy": 0.07454846799373627, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:51.944716Z", "loop": 6373, "env_steps": 3916185599, "loss": 0.015079791657626629, "avg_return": 0.8618572354316711, "regret": 0.0007906815153546631, "entropy": 0.0837588682770729, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:52.800898Z", "loop": 6374, "env_steps": 3916799999, "loss": 0.014860162511467934, "avg_return": 0.8622790575027466, "regret": 0.0007906815153546631, "entropy": 0.08075393736362457, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:53.658010Z", "loop": 6375, "env_steps": 3917414399, "loss": 0.01515185832977295, "avg_return": 0.8640401363372803, "regret": 0.0007906815153546631, "entropy": 0.08254105597734451, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:54.514393Z", "loop": 6376, "env_steps": 3918028799, "loss": 0.014350175857543945, "avg_return": 0.8617346286773682, "regret": 0.0007906815153546631, "entropy": 0.08010336756706238, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:55.369201Z", "loop": 6377, "env_steps": 3918643199, "loss": 0.015352471731603146, "avg_return": 0.8607825040817261, "regret": 0.0007906815153546631, "entropy": 0.0833369791507721, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:56.224225Z", "loop": 6378, "env_steps": 3919257599, "loss": 0.015749318525195122, "avg_return": 0.8628507852554321, "regret": 0.0007906815153546631, "entropy": 0.08376318216323853, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:57.079852Z", "loop": 6379, "env_steps": 3919871999, "loss": 0.015087555162608624, "avg_return": 0.8631907105445862, "regret": 0.0007906815153546631, "entropy": 0.08554092049598694, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:57.976084Z", "loop": 6380, "env_steps": 3920486399, "loss": 0.015146243385970592, "avg_return": 0.8626046180725098, "regret": 0.0010161844547837973, "entropy": 0.08492778241634369, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:58.831498Z", "loop": 6381, "env_steps": 3921100799, "loss": 0.014759152196347713, "avg_return": 0.8626658320426941, "regret": 0.0010161844547837973, "entropy": 0.0839514434337616, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:54:59.685311Z", "loop": 6382, "env_steps": 3921715199, "loss": 0.015522307716310024, "avg_return": 0.8621439933776855, "regret": 0.0010161844547837973, "entropy": 0.08826510608196259, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:00.540611Z", "loop": 6383, "env_steps": 3922329599, "loss": 0.016021516174077988, "avg_return": 0.8606902360916138, "regret": 0.0010161844547837973, "entropy": 0.08638684451580048, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:01.397567Z", "loop": 6384, "env_steps": 3922943999, "loss": 0.015598843805491924, "avg_return": 0.8619306683540344, "regret": 0.0010161844547837973, "entropy": 0.08446997404098511, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:02.253479Z", "loop": 6385, "env_steps": 3923558399, "loss": 0.015528162010014057, "avg_return": 0.8617875576019287, "regret": 0.0010161844547837973, "entropy": 0.08690610527992249, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:03.109564Z", "loop": 6386, "env_steps": 3924172799, "loss": 0.014969542622566223, "avg_return": 0.8605192303657532, "regret": 0.0010161844547837973, "entropy": 0.08536651730537415, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:03.965129Z", "loop": 6387, "env_steps": 3924787199, "loss": 0.016601886600255966, "avg_return": 0.8585347533226013, "regret": 0.0010161844547837973, "entropy": 0.08803412318229675, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:04.819885Z", "loop": 6388, "env_steps": 3925401599, "loss": 0.016630493104457855, "avg_return": 0.8586289882659912, "regret": 0.0010161844547837973, "entropy": 0.0879126787185669, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:05.675418Z", "loop": 6389, "env_steps": 3926015999, "loss": 0.016027133911848068, "avg_return": 0.8594706654548645, "regret": 0.0010161844547837973, "entropy": 0.0856744796037674, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:06.570743Z", "loop": 6390, "env_steps": 3926630399, "loss": 0.01451216358691454, "avg_return": 0.8612769842147827, "regret": 0.0029666293412446976, "entropy": 0.08464087545871735, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:07.425690Z", "loop": 6391, "env_steps": 3927244799, "loss": 0.016227962449193, "avg_return": 0.8632991909980774, "regret": 0.0029666293412446976, "entropy": 0.08667728304862976, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:08.280745Z", "loop": 6392, "env_steps": 3927859199, "loss": 0.015054582618176937, "avg_return": 0.8638092279434204, "regret": 0.0029666293412446976, "entropy": 0.08593088388442993, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:09.136290Z", "loop": 6393, "env_steps": 3928473599, "loss": 0.016636667773127556, "avg_return": 0.8636824488639832, "regret": 0.0029666293412446976, "entropy": 0.08583570271730423, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:09.991947Z", "loop": 6394, "env_steps": 3929087999, "loss": 0.015290096402168274, "avg_return": 0.8619400262832642, "regret": 0.0029666293412446976, "entropy": 0.08559535443782806, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:10.847019Z", "loop": 6395, "env_steps": 3929702399, "loss": 0.01823458820581436, "avg_return": 0.8609293699264526, "regret": 0.0029666293412446976, "entropy": 0.09465623646974564, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:11.702182Z", "loop": 6396, "env_steps": 3930316799, "loss": 0.016808977350592613, "avg_return": 0.8600837588310242, "regret": 0.0029666293412446976, "entropy": 0.09380107372999191, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:12.558531Z", "loop": 6397, "env_steps": 3930931199, "loss": 0.018117619678378105, "avg_return": 0.8594065308570862, "regret": 0.0029666293412446976, "entropy": 0.0942462906241417, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:13.415150Z", "loop": 6398, "env_steps": 3931545599, "loss": 0.017478637397289276, "avg_return": 0.8595757484436035, "regret": 0.0029666293412446976, "entropy": 0.09761332720518112, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:14.271516Z", "loop": 6399, "env_steps": 3932159999, "loss": 0.016663169488310814, "avg_return": 0.8608850240707397, "regret": 0.0029666293412446976, "entropy": 0.09412320703268051, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:15.166243Z", "loop": 6400, "env_steps": 3932774399, "loss": 0.016844598576426506, "avg_return": 0.8609462976455688, "regret": 0.002175845205783844, "entropy": 0.09119206666946411, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:16.021784Z", "loop": 6401, "env_steps": 3933388799, "loss": 0.01649172231554985, "avg_return": 0.861955463886261, "regret": 0.002175845205783844, "entropy": 0.09021501988172531, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:16.877415Z", "loop": 6402, "env_steps": 3934003199, "loss": 0.015848860144615173, "avg_return": 0.8623753786087036, "regret": 0.002175845205783844, "entropy": 0.0885629653930664, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:17.733251Z", "loop": 6403, "env_steps": 3934617599, "loss": 0.016346776857972145, "avg_return": 0.8618882298469543, "regret": 0.002175845205783844, "entropy": 0.08824721723794937, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:18.588825Z", "loop": 6404, "env_steps": 3935231999, "loss": 0.014958634972572327, "avg_return": 0.8618350625038147, "regret": 0.002175845205783844, "entropy": 0.08169741928577423, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:19.444532Z", "loop": 6405, "env_steps": 3935846399, "loss": 0.014935046434402466, "avg_return": 0.8624122142791748, "regret": 0.002175845205783844, "entropy": 0.08255736529827118, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:20.300934Z", "loop": 6406, "env_steps": 3936460799, "loss": 0.014248109422624111, "avg_return": 0.8629136085510254, "regret": 0.002175845205783844, "entropy": 0.08065959811210632, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:21.156366Z", "loop": 6407, "env_steps": 3937075199, "loss": 0.015299580991268158, "avg_return": 0.8629781007766724, "regret": 0.002175845205783844, "entropy": 0.08455036580562592, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:22.011409Z", "loop": 6408, "env_steps": 3937689599, "loss": 0.0160610843449831, "avg_return": 0.8626027703285217, "regret": 0.002175845205783844, "entropy": 0.08645699173212051, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:22.866132Z", "loop": 6409, "env_steps": 3938303999, "loss": 0.014914813451468945, "avg_return": 0.8634241223335266, "regret": 0.002175845205783844, "entropy": 0.08208315819501877, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:23.761604Z", "loop": 6410, "env_steps": 3938918399, "loss": 0.015583706088364124, "avg_return": 0.8625862002372742, "regret": 0.0012575885048136115, "entropy": 0.08584833890199661, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:24.617035Z", "loop": 6411, "env_steps": 3939532799, "loss": 0.014779764227569103, "avg_return": 0.8618395328521729, "regret": 0.0012575885048136115, "entropy": 0.08298047631978989, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:25.472522Z", "loop": 6412, "env_steps": 3940147199, "loss": 0.015364857390522957, "avg_return": 0.8607783317565918, "regret": 0.0012575885048136115, "entropy": 0.08835455775260925, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:26.327668Z", "loop": 6413, "env_steps": 3940761599, "loss": 0.015091908164322376, "avg_return": 0.8620234131813049, "regret": 0.0012575885048136115, "entropy": 0.08561481535434723, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:27.183606Z", "loop": 6414, "env_steps": 3941375999, "loss": 0.017302166670560837, "avg_return": 0.8610439300537109, "regret": 0.0012575885048136115, "entropy": 0.08894860744476318, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:28.038979Z", "loop": 6415, "env_steps": 3941990399, "loss": 0.015748940408229828, "avg_return": 0.8596407175064087, "regret": 0.0012575885048136115, "entropy": 0.08877501636743546, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:28.894155Z", "loop": 6416, "env_steps": 3942604799, "loss": 0.016955023631453514, "avg_return": 0.8586623072624207, "regret": 0.0012575885048136115, "entropy": 0.08965934813022614, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:29.749627Z", "loop": 6417, "env_steps": 3943219199, "loss": 0.016115227714180946, "avg_return": 0.8595032095909119, "regret": 0.0012575885048136115, "entropy": 0.09232474118471146, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:30.604679Z", "loop": 6418, "env_steps": 3943833599, "loss": 0.016841623932123184, "avg_return": 0.8600943088531494, "regret": 0.0012575885048136115, "entropy": 0.09312321990728378, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:31.459536Z", "loop": 6419, "env_steps": 3944447999, "loss": 0.016636861488223076, "avg_return": 0.8599333763122559, "regret": 0.0012575885048136115, "entropy": 0.0923696905374527, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:32.354714Z", "loop": 6420, "env_steps": 3945062399, "loss": 0.01693740300834179, "avg_return": 0.8604120016098022, "regret": 0.003423811635002494, "entropy": 0.09323836863040924, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:33.210183Z", "loop": 6421, "env_steps": 3945676799, "loss": 0.016522839665412903, "avg_return": 0.8588722944259644, "regret": 0.003423811635002494, "entropy": 0.092296302318573, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:34.065781Z", "loop": 6422, "env_steps": 3946291199, "loss": 0.016985824331641197, "avg_return": 0.8597293496131897, "regret": 0.003423811635002494, "entropy": 0.0920497477054596, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:34.920760Z", "loop": 6423, "env_steps": 3946905599, "loss": 0.01678343117237091, "avg_return": 0.8589240908622742, "regret": 0.003423811635002494, "entropy": 0.09376271814107895, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:35.775508Z", "loop": 6424, "env_steps": 3947519999, "loss": 0.016133250668644905, "avg_return": 0.859984278678894, "regret": 0.003423811635002494, "entropy": 0.08816060423851013, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:36.632181Z", "loop": 6425, "env_steps": 3948134399, "loss": 0.015790902078151703, "avg_return": 0.8590850830078125, "regret": 0.003423811635002494, "entropy": 0.08864030241966248, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:37.488552Z", "loop": 6426, "env_steps": 3948748799, "loss": 0.015174135565757751, "avg_return": 0.8600027561187744, "regret": 0.003423811635002494, "entropy": 0.0864957720041275, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:38.342320Z", "loop": 6427, "env_steps": 3949363199, "loss": 0.016596248373389244, "avg_return": 0.8599855899810791, "regret": 0.003423811635002494, "entropy": 0.09014708548784256, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:39.196736Z", "loop": 6428, "env_steps": 3949977599, "loss": 0.016958849504590034, "avg_return": 0.8620412349700928, "regret": 0.003423811635002494, "entropy": 0.08799578994512558, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:40.053509Z", "loop": 6429, "env_steps": 3950591999, "loss": 0.01592438295483589, "avg_return": 0.8587883710861206, "regret": 0.003423811635002494, "entropy": 0.08463707566261292, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:40.951980Z", "loop": 6430, "env_steps": 3951206399, "loss": 0.015647171065211296, "avg_return": 0.8605756759643555, "regret": 0.002061894629150629, "entropy": 0.08452869951725006, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:41.808255Z", "loop": 6431, "env_steps": 3951820799, "loss": 0.01638493314385414, "avg_return": 0.8610584735870361, "regret": 0.002061894629150629, "entropy": 0.08841411769390106, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:42.663426Z", "loop": 6432, "env_steps": 3952435199, "loss": 0.015143620781600475, "avg_return": 0.8618715405464172, "regret": 0.002061894629150629, "entropy": 0.0882590040564537, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:43.519224Z", "loop": 6433, "env_steps": 3953049599, "loss": 0.015168395824730396, "avg_return": 0.8622702956199646, "regret": 0.002061894629150629, "entropy": 0.08343293517827988, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:44.375411Z", "loop": 6434, "env_steps": 3953663999, "loss": 0.014591069892048836, "avg_return": 0.86148601770401, "regret": 0.002061894629150629, "entropy": 0.08153247833251953, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:45.231683Z", "loop": 6435, "env_steps": 3954278399, "loss": 0.015826141461730003, "avg_return": 0.8628215789794922, "regret": 0.002061894629150629, "entropy": 0.08665916323661804, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:46.087067Z", "loop": 6436, "env_steps": 3954892799, "loss": 0.015315762721002102, "avg_return": 0.8624991774559021, "regret": 0.002061894629150629, "entropy": 0.08300971984863281, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:46.943769Z", "loop": 6437, "env_steps": 3955507199, "loss": 0.016336780041456223, "avg_return": 0.8627468347549438, "regret": 0.002061894629150629, "entropy": 0.08881296962499619, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:47.799548Z", "loop": 6438, "env_steps": 3956121599, "loss": 0.015329457819461823, "avg_return": 0.8633022308349609, "regret": 0.002061894629150629, "entropy": 0.08613848686218262, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:48.655784Z", "loop": 6439, "env_steps": 3956735999, "loss": 0.016175299882888794, "avg_return": 0.8614290356636047, "regret": 0.002061894629150629, "entropy": 0.09271692484617233, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:49.553065Z", "loop": 6440, "env_steps": 3957350399, "loss": 0.016502128913998604, "avg_return": 0.8626407980918884, "regret": 0.001921299728564918, "entropy": 0.08927401155233383, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:50.408753Z", "loop": 6441, "env_steps": 3957964799, "loss": 0.01647379621863365, "avg_return": 0.8606355786323547, "regret": 0.001921299728564918, "entropy": 0.09072230011224747, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:51.264526Z", "loop": 6442, "env_steps": 3958579199, "loss": 0.015415576286613941, "avg_return": 0.8596230149269104, "regret": 0.001921299728564918, "entropy": 0.08907366544008255, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:52.120032Z", "loop": 6443, "env_steps": 3959193599, "loss": 0.01644027791917324, "avg_return": 0.8605329394340515, "regret": 0.001921299728564918, "entropy": 0.09220190346240997, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:52.975782Z", "loop": 6444, "env_steps": 3959807999, "loss": 0.016905203461647034, "avg_return": 0.8598911762237549, "regret": 0.001921299728564918, "entropy": 0.09359437227249146, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:53.831778Z", "loop": 6445, "env_steps": 3960422399, "loss": 0.01689484901726246, "avg_return": 0.8608366250991821, "regret": 0.001921299728564918, "entropy": 0.09269130229949951, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:54.686748Z", "loop": 6446, "env_steps": 3961036799, "loss": 0.016358593478798866, "avg_return": 0.8610202074050903, "regret": 0.001921299728564918, "entropy": 0.09036919474601746, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:55.541295Z", "loop": 6447, "env_steps": 3961651199, "loss": 0.01631057821214199, "avg_return": 0.8605343699455261, "regret": 0.001921299728564918, "entropy": 0.09225137531757355, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:56.396660Z", "loop": 6448, "env_steps": 3962265599, "loss": 0.017878210172057152, "avg_return": 0.8592073917388916, "regret": 0.001921299728564918, "entropy": 0.09948257356882095, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:57.253050Z", "loop": 6449, "env_steps": 3962879999, "loss": 0.017879405990242958, "avg_return": 0.8601845502853394, "regret": 0.001921299728564918, "entropy": 0.0991608276963234, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:58.151089Z", "loop": 6450, "env_steps": 3963494399, "loss": 0.017870422452688217, "avg_return": 0.8613688349723816, "regret": 0.0027305246330797672, "entropy": 0.09699415415525436, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:59.005437Z", "loop": 6451, "env_steps": 3964108799, "loss": 0.017241550609469414, "avg_return": 0.8608976602554321, "regret": 0.0027305246330797672, "entropy": 0.09702445566654205, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:55:59.860237Z", "loop": 6452, "env_steps": 3964723199, "loss": 0.018309051170945168, "avg_return": 0.8610616326332092, "regret": 0.0027305246330797672, "entropy": 0.10092990100383759, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:00.716827Z", "loop": 6453, "env_steps": 3965337599, "loss": 0.018067732453346252, "avg_return": 0.8615451455116272, "regret": 0.0027305246330797672, "entropy": 0.09982888400554657, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:01.571818Z", "loop": 6454, "env_steps": 3965951999, "loss": 0.018039576709270477, "avg_return": 0.8611049652099609, "regret": 0.0027305246330797672, "entropy": 0.10044248402118683, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:02.426105Z", "loop": 6455, "env_steps": 3966566399, "loss": 0.020081736147403717, "avg_return": 0.8600301146507263, "regret": 0.0027305246330797672, "entropy": 0.11322791874408722, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:03.280940Z", "loop": 6456, "env_steps": 3967180799, "loss": 0.02072022669017315, "avg_return": 0.8597695231437683, "regret": 0.0027305246330797672, "entropy": 0.11703504621982574, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:04.137473Z", "loop": 6457, "env_steps": 3967795199, "loss": 0.021938052028417587, "avg_return": 0.8586493134498596, "regret": 0.0027305246330797672, "entropy": 0.12357893586158752, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:04.992559Z", "loop": 6458, "env_steps": 3968409599, "loss": 0.021839505061507225, "avg_return": 0.8530119061470032, "regret": 0.0027305246330797672, "entropy": 0.1264348179101944, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:05.848964Z", "loop": 6459, "env_steps": 3969023999, "loss": 0.023269837722182274, "avg_return": 0.8540231585502625, "regret": 0.0027305246330797672, "entropy": 0.13355787098407745, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:06.746956Z", "loop": 6460, "env_steps": 3969638399, "loss": 0.022564129903912544, "avg_return": 0.8553043007850647, "regret": 0.00828498974442482, "entropy": 0.12782154977321625, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:07.603748Z", "loop": 6461, "env_steps": 3970252799, "loss": 0.02246045134961605, "avg_return": 0.8585038185119629, "regret": 0.00828498974442482, "entropy": 0.127073273062706, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:08.459770Z", "loop": 6462, "env_steps": 3970867199, "loss": 0.02100643329322338, "avg_return": 0.8599882125854492, "regret": 0.00828498974442482, "entropy": 0.12528090178966522, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:09.315532Z", "loop": 6463, "env_steps": 3971481599, "loss": 0.021182028576731682, "avg_return": 0.8595831394195557, "regret": 0.00828498974442482, "entropy": 0.11989430338144302, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:10.171431Z", "loop": 6464, "env_steps": 3972095999, "loss": 0.020955616608262062, "avg_return": 0.8585570454597473, "regret": 0.00828498974442482, "entropy": 0.11622191220521927, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:11.027943Z", "loop": 6465, "env_steps": 3972710399, "loss": 0.020835544914007187, "avg_return": 0.8599838614463806, "regret": 0.00828498974442482, "entropy": 0.11130548268556595, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:11.883843Z", "loop": 6466, "env_steps": 3973324799, "loss": 0.01891268976032734, "avg_return": 0.8586620092391968, "regret": 0.00828498974442482, "entropy": 0.10720385611057281, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:12.738332Z", "loop": 6467, "env_steps": 3973939199, "loss": 0.02013053558766842, "avg_return": 0.8572522401809692, "regret": 0.00828498974442482, "entropy": 0.10759540647268295, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:13.593030Z", "loop": 6468, "env_steps": 3974553599, "loss": 0.018747692927718163, "avg_return": 0.8566400408744812, "regret": 0.00828498974442482, "entropy": 0.10259844362735748, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:14.449727Z", "loop": 6469, "env_steps": 3975167999, "loss": 0.02078753150999546, "avg_return": 0.8560354709625244, "regret": 0.00828498974442482, "entropy": 0.1110999658703804, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:15.345929Z", "loop": 6470, "env_steps": 3975782399, "loss": 0.021421212702989578, "avg_return": 0.8566163182258606, "regret": 0.007427152246236801, "entropy": 0.10822036117315292, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:16.200858Z", "loop": 6471, "env_steps": 3976396799, "loss": 0.020756656304001808, "avg_return": 0.8551391959190369, "regret": 0.007427152246236801, "entropy": 0.11174628883600235, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:17.056916Z", "loop": 6472, "env_steps": 3977011199, "loss": 0.020693790167570114, "avg_return": 0.8546273112297058, "regret": 0.007427152246236801, "entropy": 0.10884951800107956, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:17.911210Z", "loop": 6473, "env_steps": 3977625599, "loss": 0.021184802055358887, "avg_return": 0.8559167981147766, "regret": 0.007427152246236801, "entropy": 0.11028183996677399, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:18.765870Z", "loop": 6474, "env_steps": 3978239999, "loss": 0.021446431055665016, "avg_return": 0.8555927872657776, "regret": 0.007427152246236801, "entropy": 0.11153363436460495, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:19.620653Z", "loop": 6475, "env_steps": 3978854399, "loss": 0.022725438699126244, "avg_return": 0.857387900352478, "regret": 0.007427152246236801, "entropy": 0.11664295941591263, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:20.475658Z", "loop": 6476, "env_steps": 3979468799, "loss": 0.021779753267765045, "avg_return": 0.8575559854507446, "regret": 0.007427152246236801, "entropy": 0.11766219884157181, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:21.331028Z", "loop": 6477, "env_steps": 3980083199, "loss": 0.023018382489681244, "avg_return": 0.8595362305641174, "regret": 0.007427152246236801, "entropy": 0.11933410167694092, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:22.186383Z", "loop": 6478, "env_steps": 3980697599, "loss": 0.02274218387901783, "avg_return": 0.8592724800109863, "regret": 0.007427152246236801, "entropy": 0.12325697392225266, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:23.042507Z", "loop": 6479, "env_steps": 3981311999, "loss": 0.022390216588974, "avg_return": 0.86069256067276, "regret": 0.007427152246236801, "entropy": 0.11881547421216965, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:23.938238Z", "loop": 6480, "env_steps": 3981926399, "loss": 0.022358370944857597, "avg_return": 0.8602122068405151, "regret": 0.0032452635932713747, "entropy": 0.11955393850803375, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:24.794302Z", "loop": 6481, "env_steps": 3982540799, "loss": 0.02237607166171074, "avg_return": 0.8610376119613647, "regret": 0.0032452635932713747, "entropy": 0.1183566302061081, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:25.648581Z", "loop": 6482, "env_steps": 3983155199, "loss": 0.02157478779554367, "avg_return": 0.86149001121521, "regret": 0.0032452635932713747, "entropy": 0.11452144384384155, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:26.502379Z", "loop": 6483, "env_steps": 3983769599, "loss": 0.020562201738357544, "avg_return": 0.861592710018158, "regret": 0.0032452635932713747, "entropy": 0.11644476652145386, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:27.358005Z", "loop": 6484, "env_steps": 3984383999, "loss": 0.01937495358288288, "avg_return": 0.8624690771102905, "regret": 0.0032452635932713747, "entropy": 0.10760689526796341, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:28.213009Z", "loop": 6485, "env_steps": 3984998399, "loss": 0.018434135243296623, "avg_return": 0.8603699803352356, "regret": 0.0032452635932713747, "entropy": 0.10415644943714142, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:29.067727Z", "loop": 6486, "env_steps": 3985612799, "loss": 0.0188762154430151, "avg_return": 0.8624809980392456, "regret": 0.0032452635932713747, "entropy": 0.10481070727109909, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:29.922144Z", "loop": 6487, "env_steps": 3986227199, "loss": 0.02152128890156746, "avg_return": 0.8613160252571106, "regret": 0.0032452635932713747, "entropy": 0.11282330751419067, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:30.778635Z", "loop": 6488, "env_steps": 3986841599, "loss": 0.019345538690686226, "avg_return": 0.8616957664489746, "regret": 0.0032452635932713747, "entropy": 0.10558509826660156, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:31.634371Z", "loop": 6489, "env_steps": 3987455999, "loss": 0.01849249005317688, "avg_return": 0.8612339496612549, "regret": 0.0032452635932713747, "entropy": 0.1023760512471199, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:32.529608Z", "loop": 6490, "env_steps": 3988070399, "loss": 0.020225562155246735, "avg_return": 0.8611959218978882, "regret": 0.0023335341829806566, "entropy": 0.10963708162307739, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:33.384616Z", "loop": 6491, "env_steps": 3988684799, "loss": 0.020476505160331726, "avg_return": 0.8601682782173157, "regret": 0.0023335341829806566, "entropy": 0.11453627794981003, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:34.240526Z", "loop": 6492, "env_steps": 3989299199, "loss": 0.02114017866551876, "avg_return": 0.8601541519165039, "regret": 0.0023335341829806566, "entropy": 0.11740201711654663, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:35.096251Z", "loop": 6493, "env_steps": 3989913599, "loss": 0.02062404900789261, "avg_return": 0.8612269163131714, "regret": 0.0023335341829806566, "entropy": 0.1152159720659256, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:35.952321Z", "loop": 6494, "env_steps": 3990527999, "loss": 0.021485695615410805, "avg_return": 0.8616446256637573, "regret": 0.0023335341829806566, "entropy": 0.11580193042755127, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:36.807639Z", "loop": 6495, "env_steps": 3991142399, "loss": 0.019895626232028008, "avg_return": 0.8611859083175659, "regret": 0.0023335341829806566, "entropy": 0.10792561620473862, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:37.662761Z", "loop": 6496, "env_steps": 3991756799, "loss": 0.020383110269904137, "avg_return": 0.8613405823707581, "regret": 0.0023335341829806566, "entropy": 0.1079045906662941, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:38.518034Z", "loop": 6497, "env_steps": 3992371199, "loss": 0.018709959462285042, "avg_return": 0.8618699312210083, "regret": 0.0023335341829806566, "entropy": 0.10604094713926315, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:39.373836Z", "loop": 6498, "env_steps": 3992985599, "loss": 0.018283633515238762, "avg_return": 0.8629463911056519, "regret": 0.0023335341829806566, "entropy": 0.10110616683959961, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:40.230005Z", "loop": 6499, "env_steps": 3993599999, "loss": 0.017967555671930313, "avg_return": 0.8604339957237244, "regret": 0.0023335341829806566, "entropy": 0.09889916330575943, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:41.125692Z", "loop": 6500, "env_steps": 3994214399, "loss": 0.018231583759188652, "avg_return": 0.8600291013717651, "regret": 0.00235771294683218, "entropy": 0.09900113940238953, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:41.980862Z", "loop": 6501, "env_steps": 3994828799, "loss": 0.018638964742422104, "avg_return": 0.8603041768074036, "regret": 0.00235771294683218, "entropy": 0.10137521475553513, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:42.836767Z", "loop": 6502, "env_steps": 3995443199, "loss": 0.018896466121077538, "avg_return": 0.8598322868347168, "regret": 0.00235771294683218, "entropy": 0.10247000306844711, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:43.692568Z", "loop": 6503, "env_steps": 3996057599, "loss": 0.01771504245698452, "avg_return": 0.860907793045044, "regret": 0.00235771294683218, "entropy": 0.09715675562620163, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:44.547413Z", "loop": 6504, "env_steps": 3996671999, "loss": 0.018996810540556908, "avg_return": 0.8575183153152466, "regret": 0.00235771294683218, "entropy": 0.10055088251829147, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:45.402703Z", "loop": 6505, "env_steps": 3997286399, "loss": 0.017915483564138412, "avg_return": 0.8575606346130371, "regret": 0.00235771294683218, "entropy": 0.09831269830465317, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:46.257660Z", "loop": 6506, "env_steps": 3997900799, "loss": 0.018677271902561188, "avg_return": 0.8575671315193176, "regret": 0.00235771294683218, "entropy": 0.09621421992778778, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:47.113959Z", "loop": 6507, "env_steps": 3998515199, "loss": 0.019237220287322998, "avg_return": 0.8548250794410706, "regret": 0.00235771294683218, "entropy": 0.1015738770365715, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:47.969432Z", "loop": 6508, "env_steps": 3999129599, "loss": 0.018703019246459007, "avg_return": 0.8571441769599915, "regret": 0.00235771294683218, "entropy": 0.1009816825389862, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:48.825268Z", "loop": 6509, "env_steps": 3999743999, "loss": 0.018919125199317932, "avg_return": 0.8564058542251587, "regret": 0.00235771294683218, "entropy": 0.09879817813634872, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:49.721556Z", "loop": 6510, "env_steps": 4000358399, "loss": 0.018570145592093468, "avg_return": 0.8582270741462708, "regret": 0.005394178442656994, "entropy": 0.10166841745376587, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:50.576901Z", "loop": 6511, "env_steps": 4000972799, "loss": 0.017861895263195038, "avg_return": 0.8596956729888916, "regret": 0.005394178442656994, "entropy": 0.09651441872119904, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:51.432394Z", "loop": 6512, "env_steps": 4001587199, "loss": 0.017261847853660583, "avg_return": 0.8610435128211975, "regret": 0.005394178442656994, "entropy": 0.09470473974943161, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:52.288519Z", "loop": 6513, "env_steps": 4002201599, "loss": 0.016050493344664574, "avg_return": 0.8617055416107178, "regret": 0.005394178442656994, "entropy": 0.09086800366640091, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:53.142939Z", "loop": 6514, "env_steps": 4002815999, "loss": 0.016911718994379044, "avg_return": 0.8630989789962769, "regret": 0.005394178442656994, "entropy": 0.09133776277303696, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:53.998124Z", "loop": 6515, "env_steps": 4003430399, "loss": 0.01621856912970543, "avg_return": 0.8618001341819763, "regret": 0.005394178442656994, "entropy": 0.08844570070505142, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:54.854121Z", "loop": 6516, "env_steps": 4004044799, "loss": 0.014983353205025196, "avg_return": 0.8618080019950867, "regret": 0.005394178442656994, "entropy": 0.08569672703742981, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:55.708810Z", "loop": 6517, "env_steps": 4004659199, "loss": 0.01675630733370781, "avg_return": 0.8628528118133545, "regret": 0.005394178442656994, "entropy": 0.08914922177791595, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:56.563889Z", "loop": 6518, "env_steps": 4005273599, "loss": 0.016213929280638695, "avg_return": 0.8625602126121521, "regret": 0.005394178442656994, "entropy": 0.08928954601287842, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:57.420832Z", "loop": 6519, "env_steps": 4005887999, "loss": 0.01636662147939205, "avg_return": 0.8622925877571106, "regret": 0.005394178442656994, "entropy": 0.09193500131368637, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:58.316852Z", "loop": 6520, "env_steps": 4006502399, "loss": 0.018556950613856316, "avg_return": 0.8613194227218628, "regret": 0.0015837587416172028, "entropy": 0.09772130846977234, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:56:59.172368Z", "loop": 6521, "env_steps": 4007116799, "loss": 0.018475646153092384, "avg_return": 0.8604629635810852, "regret": 0.0015837587416172028, "entropy": 0.10198245942592621, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:00.028712Z", "loop": 6522, "env_steps": 4007731199, "loss": 0.01810310408473015, "avg_return": 0.8617454171180725, "regret": 0.0015837587416172028, "entropy": 0.10102617740631104, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:00.885123Z", "loop": 6523, "env_steps": 4008345599, "loss": 0.01999981887638569, "avg_return": 0.8627583980560303, "regret": 0.0015837587416172028, "entropy": 0.10759178549051285, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:01.740481Z", "loop": 6524, "env_steps": 4008959999, "loss": 0.018696393817663193, "avg_return": 0.861436665058136, "regret": 0.0015837587416172028, "entropy": 0.10046829283237457, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:02.596425Z", "loop": 6525, "env_steps": 4009574399, "loss": 0.019467143341898918, "avg_return": 0.8610879778862, "regret": 0.0015837587416172028, "entropy": 0.10609813034534454, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:03.452050Z", "loop": 6526, "env_steps": 4010188799, "loss": 0.019512372091412544, "avg_return": 0.8600813746452332, "regret": 0.0015837587416172028, "entropy": 0.10800113528966904, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:04.307538Z", "loop": 6527, "env_steps": 4010803199, "loss": 0.021135693415999413, "avg_return": 0.8602694869041443, "regret": 0.0015837587416172028, "entropy": 0.11934886127710342, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:05.162412Z", "loop": 6528, "env_steps": 4011417599, "loss": 0.021096831187605858, "avg_return": 0.8578985929489136, "regret": 0.0015837587416172028, "entropy": 0.11350718140602112, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:06.018640Z", "loop": 6529, "env_steps": 4012031999, "loss": 0.020579097792506218, "avg_return": 0.859076738357544, "regret": 0.0015837587416172028, "entropy": 0.11036258190870285, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:06.915915Z", "loop": 6530, "env_steps": 4012646399, "loss": 0.019366569817066193, "avg_return": 0.8609659075737, "regret": 0.0026443847455084324, "entropy": 0.1014140322804451, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:07.772874Z", "loop": 6531, "env_steps": 4013260799, "loss": 0.01763705536723137, "avg_return": 0.8612002730369568, "regret": 0.0026443847455084324, "entropy": 0.10199925303459167, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:08.627556Z", "loop": 6532, "env_steps": 4013875199, "loss": 0.018170258030295372, "avg_return": 0.8602336049079895, "regret": 0.0026443847455084324, "entropy": 0.10236101597547531, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:09.483023Z", "loop": 6533, "env_steps": 4014489599, "loss": 0.017133859917521477, "avg_return": 0.862042248249054, "regret": 0.0026443847455084324, "entropy": 0.09852442145347595, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:10.339819Z", "loop": 6534, "env_steps": 4015103999, "loss": 0.017560947686433792, "avg_return": 0.8608962297439575, "regret": 0.0026443847455084324, "entropy": 0.09430810809135437, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:11.197355Z", "loop": 6535, "env_steps": 4015718399, "loss": 0.01876613311469555, "avg_return": 0.8591477870941162, "regret": 0.0026443847455084324, "entropy": 0.1011316254734993, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:12.053496Z", "loop": 6536, "env_steps": 4016332799, "loss": 0.01970890909433365, "avg_return": 0.8598130345344543, "regret": 0.0026443847455084324, "entropy": 0.10633424669504166, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:12.908565Z", "loop": 6537, "env_steps": 4016947199, "loss": 0.020159419625997543, "avg_return": 0.8587723970413208, "regret": 0.0026443847455084324, "entropy": 0.10592375695705414, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:13.764254Z", "loop": 6538, "env_steps": 4017561599, "loss": 0.019938666373491287, "avg_return": 0.8604746460914612, "regret": 0.0026443847455084324, "entropy": 0.10573440045118332, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:14.620790Z", "loop": 6539, "env_steps": 4018175999, "loss": 0.01646772399544716, "avg_return": 0.860262393951416, "regret": 0.0026443847455084324, "entropy": 0.09323850274085999, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:15.517657Z", "loop": 6540, "env_steps": 4018790399, "loss": 0.016052836552262306, "avg_return": 0.8608484864234924, "regret": 0.002156337257474661, "entropy": 0.09161676466464996, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:16.373260Z", "loop": 6541, "env_steps": 4019404799, "loss": 0.017285943031311035, "avg_return": 0.8625404834747314, "regret": 0.002156337257474661, "entropy": 0.0949791669845581, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:17.229101Z", "loop": 6542, "env_steps": 4020019199, "loss": 0.015002160333096981, "avg_return": 0.8617987036705017, "regret": 0.002156337257474661, "entropy": 0.0863029733300209, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:18.085597Z", "loop": 6543, "env_steps": 4020633599, "loss": 0.015796808525919914, "avg_return": 0.8616299629211426, "regret": 0.002156337257474661, "entropy": 0.08968771994113922, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:18.941716Z", "loop": 6544, "env_steps": 4021247999, "loss": 0.014949366450309753, "avg_return": 0.861602783203125, "regret": 0.002156337257474661, "entropy": 0.08764933049678802, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:19.798582Z", "loop": 6545, "env_steps": 4021862399, "loss": 0.016426939517259598, "avg_return": 0.8630744814872742, "regret": 0.002156337257474661, "entropy": 0.09207519888877869, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:20.655199Z", "loop": 6546, "env_steps": 4022476799, "loss": 0.014597284607589245, "avg_return": 0.8625134229660034, "regret": 0.002156337257474661, "entropy": 0.08350596576929092, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:21.511264Z", "loop": 6547, "env_steps": 4023091199, "loss": 0.01512956153601408, "avg_return": 0.8628864884376526, "regret": 0.002156337257474661, "entropy": 0.08452683687210083, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:22.366831Z", "loop": 6548, "env_steps": 4023705599, "loss": 0.016564374789595604, "avg_return": 0.8618378639221191, "regret": 0.002156337257474661, "entropy": 0.0915827676653862, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:23.222354Z", "loop": 6549, "env_steps": 4024319999, "loss": 0.015729939565062523, "avg_return": 0.862088143825531, "regret": 0.002156337257474661, "entropy": 0.08845951408147812, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:24.123421Z", "loop": 6550, "env_steps": 4024934399, "loss": 0.01457523088902235, "avg_return": 0.8618070483207703, "regret": 0.0012526406208053231, "entropy": 0.08339405059814453, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:24.979065Z", "loop": 6551, "env_steps": 4025548799, "loss": 0.015976492315530777, "avg_return": 0.8612605929374695, "regret": 0.0012526406208053231, "entropy": 0.08870572596788406, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:25.834244Z", "loop": 6552, "env_steps": 4026163199, "loss": 0.016351494938135147, "avg_return": 0.8624123334884644, "regret": 0.0012526406208053231, "entropy": 0.09451194107532501, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:26.688834Z", "loop": 6553, "env_steps": 4026777599, "loss": 0.015671905130147934, "avg_return": 0.8623059391975403, "regret": 0.0012526406208053231, "entropy": 0.08856763690710068, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:27.544173Z", "loop": 6554, "env_steps": 4027391999, "loss": 0.015924528241157532, "avg_return": 0.8608870506286621, "regret": 0.0012526406208053231, "entropy": 0.09324312955141068, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:28.399113Z", "loop": 6555, "env_steps": 4028006399, "loss": 0.016834652051329613, "avg_return": 0.8619650602340698, "regret": 0.0012526406208053231, "entropy": 0.09748563915491104, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:29.253636Z", "loop": 6556, "env_steps": 4028620799, "loss": 0.018376056104898453, "avg_return": 0.8616273999214172, "regret": 0.0012526406208053231, "entropy": 0.09693730622529984, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:30.109001Z", "loop": 6557, "env_steps": 4029235199, "loss": 0.017220867797732353, "avg_return": 0.8634468913078308, "regret": 0.0012526406208053231, "entropy": 0.0969555452466011, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:30.964811Z", "loop": 6558, "env_steps": 4029849599, "loss": 0.0169901754707098, "avg_return": 0.8614023923873901, "regret": 0.0012526406208053231, "entropy": 0.09710728377103806, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:31.820546Z", "loop": 6559, "env_steps": 4030463999, "loss": 0.016982678323984146, "avg_return": 0.8619897961616516, "regret": 0.0012526406208053231, "entropy": 0.1006755530834198, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:32.716377Z", "loop": 6560, "env_steps": 4031078399, "loss": 0.018867697566747665, "avg_return": 0.8621822595596313, "regret": 0.0020452591124922037, "entropy": 0.10803680866956711, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:33.572096Z", "loop": 6561, "env_steps": 4031692799, "loss": 0.020358802750706673, "avg_return": 0.8624651432037354, "regret": 0.0020452591124922037, "entropy": 0.11434952169656754, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:34.430485Z", "loop": 6562, "env_steps": 4032307199, "loss": 0.01971675641834736, "avg_return": 0.8603473901748657, "regret": 0.0020452591124922037, "entropy": 0.11296950280666351, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:35.287893Z", "loop": 6563, "env_steps": 4032921599, "loss": 0.02135520987212658, "avg_return": 0.8600397706031799, "regret": 0.0020452591124922037, "entropy": 0.12104351073503494, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:36.143684Z", "loop": 6564, "env_steps": 4033535999, "loss": 0.023556744679808617, "avg_return": 0.8598530292510986, "regret": 0.0020452591124922037, "entropy": 0.13402505218982697, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:36.999269Z", "loop": 6565, "env_steps": 4034150399, "loss": 0.025555923581123352, "avg_return": 0.857708752155304, "regret": 0.0020452591124922037, "entropy": 0.1407681554555893, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:37.855866Z", "loop": 6566, "env_steps": 4034764799, "loss": 0.027918873354792595, "avg_return": 0.8566794991493225, "regret": 0.0020452591124922037, "entropy": 0.15203814208507538, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:38.711509Z", "loop": 6567, "env_steps": 4035379199, "loss": 0.030685896053910255, "avg_return": 0.8543243408203125, "regret": 0.0020452591124922037, "entropy": 0.1666502058506012, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:39.566620Z", "loop": 6568, "env_steps": 4035993599, "loss": 0.03182653710246086, "avg_return": 0.8532306551933289, "regret": 0.0020452591124922037, "entropy": 0.1737033873796463, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:40.421279Z", "loop": 6569, "env_steps": 4036607999, "loss": 0.030720701441168785, "avg_return": 0.8545948266983032, "regret": 0.0020452591124922037, "entropy": 0.16802434623241425, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:41.317950Z", "loop": 6570, "env_steps": 4037222399, "loss": 0.02894572727382183, "avg_return": 0.8558657169342041, "regret": 0.007569757290184498, "entropy": 0.15375599265098572, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:42.174220Z", "loop": 6571, "env_steps": 4037836799, "loss": 0.026409653946757317, "avg_return": 0.858040988445282, "regret": 0.007569757290184498, "entropy": 0.14268583059310913, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:43.031037Z", "loop": 6572, "env_steps": 4038451199, "loss": 0.024970289319753647, "avg_return": 0.8600432276725769, "regret": 0.007569757290184498, "entropy": 0.13152766227722168, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:43.886830Z", "loop": 6573, "env_steps": 4039065599, "loss": 0.02230493724346161, "avg_return": 0.8592487573623657, "regret": 0.007569757290184498, "entropy": 0.12096869200468063, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:44.742531Z", "loop": 6574, "env_steps": 4039679999, "loss": 0.02170199155807495, "avg_return": 0.8600832223892212, "regret": 0.007569757290184498, "entropy": 0.11512088775634766, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:45.597938Z", "loop": 6575, "env_steps": 4040294399, "loss": 0.019956698641180992, "avg_return": 0.8626620769500732, "regret": 0.007569757290184498, "entropy": 0.10949017107486725, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:46.453385Z", "loop": 6576, "env_steps": 4040908799, "loss": 0.01770537905395031, "avg_return": 0.8628643155097961, "regret": 0.007569757290184498, "entropy": 0.10146096348762512, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:47.309062Z", "loop": 6577, "env_steps": 4041523199, "loss": 0.017676714807748795, "avg_return": 0.8625921607017517, "regret": 0.007569757290184498, "entropy": 0.09872932732105255, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:48.164617Z", "loop": 6578, "env_steps": 4042137599, "loss": 0.015948312357068062, "avg_return": 0.8626007437705994, "regret": 0.007569757290184498, "entropy": 0.09220891445875168, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:49.019524Z", "loop": 6579, "env_steps": 4042751999, "loss": 0.015179373323917389, "avg_return": 0.8629952073097229, "regret": 0.007569757290184498, "entropy": 0.08407716453075409, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:49.915595Z", "loop": 6580, "env_steps": 4043366399, "loss": 0.014971372671425343, "avg_return": 0.8626551628112793, "regret": 0.001146102324128151, "entropy": 0.0834931880235672, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:50.770208Z", "loop": 6581, "env_steps": 4043980799, "loss": 0.015893232077360153, "avg_return": 0.8605497479438782, "regret": 0.001146102324128151, "entropy": 0.09013106673955917, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:51.627097Z", "loop": 6582, "env_steps": 4044595199, "loss": 0.014274947345256805, "avg_return": 0.861757218837738, "regret": 0.001146102324128151, "entropy": 0.0802345797419548, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:52.481988Z", "loop": 6583, "env_steps": 4045209599, "loss": 0.015939898788928986, "avg_return": 0.8626027703285217, "regret": 0.001146102324128151, "entropy": 0.0869922861456871, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:53.336949Z", "loop": 6584, "env_steps": 4045823999, "loss": 0.014765395782887936, "avg_return": 0.8617038130760193, "regret": 0.001146102324128151, "entropy": 0.08495423197746277, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:54.192238Z", "loop": 6585, "env_steps": 4046438399, "loss": 0.01656949892640114, "avg_return": 0.8609143495559692, "regret": 0.001146102324128151, "entropy": 0.08760599046945572, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:55.048820Z", "loop": 6586, "env_steps": 4047052799, "loss": 0.016272766515612602, "avg_return": 0.8601102828979492, "regret": 0.001146102324128151, "entropy": 0.0906413197517395, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:55.904150Z", "loop": 6587, "env_steps": 4047667199, "loss": 0.01600433699786663, "avg_return": 0.8619950413703918, "regret": 0.001146102324128151, "entropy": 0.08685243874788284, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:56.759362Z", "loop": 6588, "env_steps": 4048281599, "loss": 0.015979867428541183, "avg_return": 0.861206591129303, "regret": 0.001146102324128151, "entropy": 0.08459024876356125, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:57.614668Z", "loop": 6589, "env_steps": 4048895999, "loss": 0.016566045582294464, "avg_return": 0.8630946278572083, "regret": 0.001146102324128151, "entropy": 0.08640088140964508, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:58.512360Z", "loop": 6590, "env_steps": 4049510399, "loss": 0.015154855325818062, "avg_return": 0.8618668913841248, "regret": 0.0013541835360229015, "entropy": 0.0834590345621109, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:57:59.368129Z", "loop": 6591, "env_steps": 4050124799, "loss": 0.014689916744828224, "avg_return": 0.8617025017738342, "regret": 0.0013541835360229015, "entropy": 0.08191653341054916, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:00.223474Z", "loop": 6592, "env_steps": 4050739199, "loss": 0.015494833700358868, "avg_return": 0.8623608350753784, "regret": 0.0013541835360229015, "entropy": 0.08095654100179672, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:01.078915Z", "loop": 6593, "env_steps": 4051353599, "loss": 0.014555081725120544, "avg_return": 0.8625866174697876, "regret": 0.0013541835360229015, "entropy": 0.0811588317155838, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:01.934911Z", "loop": 6594, "env_steps": 4051967999, "loss": 0.013939037919044495, "avg_return": 0.8632859587669373, "regret": 0.0013541835360229015, "entropy": 0.07740471512079239, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:02.790326Z", "loop": 6595, "env_steps": 4052582399, "loss": 0.014225552789866924, "avg_return": 0.8622967600822449, "regret": 0.0013541835360229015, "entropy": 0.07806549221277237, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:03.644770Z", "loop": 6596, "env_steps": 4053196799, "loss": 0.015863696113228798, "avg_return": 0.8635037541389465, "regret": 0.0013541835360229015, "entropy": 0.08224110305309296, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:04.498899Z", "loop": 6597, "env_steps": 4053811199, "loss": 0.014573991298675537, "avg_return": 0.8633439540863037, "regret": 0.0013541835360229015, "entropy": 0.07923075556755066, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:05.354056Z", "loop": 6598, "env_steps": 4054425599, "loss": 0.01415340881794691, "avg_return": 0.862273097038269, "regret": 0.0013541835360229015, "entropy": 0.0821327269077301, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:06.209440Z", "loop": 6599, "env_steps": 4055039999, "loss": 0.015312391333281994, "avg_return": 0.8625403046607971, "regret": 0.0013541835360229015, "entropy": 0.08213251084089279, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:07.105796Z", "loop": 6600, "env_steps": 4055654399, "loss": 0.015835504978895187, "avg_return": 0.8627006411552429, "regret": 0.001584700308740139, "entropy": 0.08822730928659439, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:07.960740Z", "loop": 6601, "env_steps": 4056268799, "loss": 0.016458099707961082, "avg_return": 0.8627323508262634, "regret": 0.001584700308740139, "entropy": 0.09154502302408218, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:08.816710Z", "loop": 6602, "env_steps": 4056883199, "loss": 0.01643572747707367, "avg_return": 0.8613833785057068, "regret": 0.001584700308740139, "entropy": 0.0853932723402977, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:09.673367Z", "loop": 6603, "env_steps": 4057497599, "loss": 0.01574872061610222, "avg_return": 0.8624723553657532, "regret": 0.001584700308740139, "entropy": 0.09124822169542313, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:10.529067Z", "loop": 6604, "env_steps": 4058111999, "loss": 0.01583918370306492, "avg_return": 0.8614841103553772, "regret": 0.001584700308740139, "entropy": 0.08759218454360962, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:11.384531Z", "loop": 6605, "env_steps": 4058726399, "loss": 0.015980800613760948, "avg_return": 0.8614923357963562, "regret": 0.001584700308740139, "entropy": 0.09104055166244507, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:12.240198Z", "loop": 6606, "env_steps": 4059340799, "loss": 0.016380272805690765, "avg_return": 0.8624094128608704, "regret": 0.001584700308740139, "entropy": 0.08960191905498505, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:13.095974Z", "loop": 6607, "env_steps": 4059955199, "loss": 0.015830809250473976, "avg_return": 0.8617523312568665, "regret": 0.001584700308740139, "entropy": 0.09080736339092255, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:13.952153Z", "loop": 6608, "env_steps": 4060569599, "loss": 0.016181981191039085, "avg_return": 0.8616606593132019, "regret": 0.001584700308740139, "entropy": 0.09153112024068832, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:14.806924Z", "loop": 6609, "env_steps": 4061183999, "loss": 0.01738378405570984, "avg_return": 0.8607921600341797, "regret": 0.001584700308740139, "entropy": 0.09483294934034348, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:15.703566Z", "loop": 6610, "env_steps": 4061798399, "loss": 0.015375688672065735, "avg_return": 0.862525463104248, "regret": 0.0011370280990377069, "entropy": 0.08524803072214127, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:16.558832Z", "loop": 6611, "env_steps": 4062412799, "loss": 0.014834272675216198, "avg_return": 0.8629982471466064, "regret": 0.0011370280990377069, "entropy": 0.08559542149305344, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:17.414395Z", "loop": 6612, "env_steps": 4063027199, "loss": 0.01506826002150774, "avg_return": 0.8635233044624329, "regret": 0.0011370280990377069, "entropy": 0.0841113030910492, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:18.269770Z", "loop": 6613, "env_steps": 4063641599, "loss": 0.014620954170823097, "avg_return": 0.8629383444786072, "regret": 0.0011370280990377069, "entropy": 0.08166109025478363, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:19.125853Z", "loop": 6614, "env_steps": 4064255999, "loss": 0.016070852056145668, "avg_return": 0.8633382320404053, "regret": 0.0011370280990377069, "entropy": 0.08628059178590775, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:19.981202Z", "loop": 6615, "env_steps": 4064870399, "loss": 0.015407675877213478, "avg_return": 0.8628716468811035, "regret": 0.0011370280990377069, "entropy": 0.08237386494874954, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:20.836635Z", "loop": 6616, "env_steps": 4065484799, "loss": 0.013777717016637325, "avg_return": 0.8639706373214722, "regret": 0.0011370280990377069, "entropy": 0.08062025904655457, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:21.691331Z", "loop": 6617, "env_steps": 4066099199, "loss": 0.015503956936299801, "avg_return": 0.862338662147522, "regret": 0.0011370280990377069, "entropy": 0.08469276875257492, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:22.547302Z", "loop": 6618, "env_steps": 4066713599, "loss": 0.014831858687102795, "avg_return": 0.8624349236488342, "regret": 0.0011370280990377069, "entropy": 0.08358733355998993, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:23.401522Z", "loop": 6619, "env_steps": 4067327999, "loss": 0.016611402854323387, "avg_return": 0.8626620769500732, "regret": 0.0011370280990377069, "entropy": 0.08771494776010513, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:24.295997Z", "loop": 6620, "env_steps": 4067942399, "loss": 0.015056337229907513, "avg_return": 0.863396942615509, "regret": 0.0009726693970151246, "entropy": 0.08309871703386307, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:25.151634Z", "loop": 6621, "env_steps": 4068556799, "loss": 0.016482951119542122, "avg_return": 0.8619862198829651, "regret": 0.0009726693970151246, "entropy": 0.08872685581445694, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:26.007922Z", "loop": 6622, "env_steps": 4069171199, "loss": 0.014580677263438702, "avg_return": 0.8616440892219543, "regret": 0.0009726693970151246, "entropy": 0.0826151967048645, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:26.863454Z", "loop": 6623, "env_steps": 4069785599, "loss": 0.015831006690859795, "avg_return": 0.8621424436569214, "regret": 0.0009726693970151246, "entropy": 0.08398790657520294, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:27.718728Z", "loop": 6624, "env_steps": 4070399999, "loss": 0.014869824051856995, "avg_return": 0.8620805144309998, "regret": 0.0009726693970151246, "entropy": 0.08447752147912979, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:28.574091Z", "loop": 6625, "env_steps": 4071014399, "loss": 0.014195133931934834, "avg_return": 0.8631088733673096, "regret": 0.0009726693970151246, "entropy": 0.08068195730447769, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:29.430591Z", "loop": 6626, "env_steps": 4071628799, "loss": 0.015127223916351795, "avg_return": 0.8626684546470642, "regret": 0.0009726693970151246, "entropy": 0.08338168263435364, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:30.287174Z", "loop": 6627, "env_steps": 4072243199, "loss": 0.014355427585542202, "avg_return": 0.8612285852432251, "regret": 0.0009726693970151246, "entropy": 0.07958091795444489, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:31.143382Z", "loop": 6628, "env_steps": 4072857599, "loss": 0.015589368529617786, "avg_return": 0.8619838953018188, "regret": 0.0009726693970151246, "entropy": 0.08385022729635239, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:31.998821Z", "loop": 6629, "env_steps": 4073471999, "loss": 0.014856996014714241, "avg_return": 0.8612205982208252, "regret": 0.0009726693970151246, "entropy": 0.08390441536903381, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:32.897600Z", "loop": 6630, "env_steps": 4074086399, "loss": 0.015400032512843609, "avg_return": 0.8610953688621521, "regret": 0.002566874958574772, "entropy": 0.08516930043697357, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:33.753643Z", "loop": 6631, "env_steps": 4074700799, "loss": 0.0172010138630867, "avg_return": 0.8596850037574768, "regret": 0.002566874958574772, "entropy": 0.09164567291736603, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:34.609861Z", "loop": 6632, "env_steps": 4075315199, "loss": 0.018537798896431923, "avg_return": 0.8581153750419617, "regret": 0.002566874958574772, "entropy": 0.09687721729278564, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:35.464475Z", "loop": 6633, "env_steps": 4075929599, "loss": 0.02003050036728382, "avg_return": 0.8577349781990051, "regret": 0.002566874958574772, "entropy": 0.10177568346261978, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:36.319034Z", "loop": 6634, "env_steps": 4076543999, "loss": 0.018939675763249397, "avg_return": 0.8575074672698975, "regret": 0.002566874958574772, "entropy": 0.0983840599656105, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:37.175354Z", "loop": 6635, "env_steps": 4077158399, "loss": 0.018287768587470055, "avg_return": 0.8565961122512817, "regret": 0.002566874958574772, "entropy": 0.09414871782064438, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:38.032583Z", "loop": 6636, "env_steps": 4077772799, "loss": 0.019843675196170807, "avg_return": 0.8557891845703125, "regret": 0.002566874958574772, "entropy": 0.10045921802520752, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:38.887330Z", "loop": 6637, "env_steps": 4078387199, "loss": 0.018221640959382057, "avg_return": 0.8573350310325623, "regret": 0.002566874958574772, "entropy": 0.09538345783948898, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:39.743064Z", "loop": 6638, "env_steps": 4079001599, "loss": 0.018198996782302856, "avg_return": 0.8600647449493408, "regret": 0.002566874958574772, "entropy": 0.09687239676713943, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:40.598754Z", "loop": 6639, "env_steps": 4079615999, "loss": 0.016310805454850197, "avg_return": 0.8596482276916504, "regret": 0.002566874958574772, "entropy": 0.09259983897209167, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:41.496986Z", "loop": 6640, "env_steps": 4080230399, "loss": 0.0158084686845541, "avg_return": 0.8618760108947754, "regret": 0.0026261191815137863, "entropy": 0.08641122281551361, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:42.353369Z", "loop": 6641, "env_steps": 4080844799, "loss": 0.015171850100159645, "avg_return": 0.8615748286247253, "regret": 0.0026261191815137863, "entropy": 0.08602301776409149, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:43.208153Z", "loop": 6642, "env_steps": 4081459199, "loss": 0.014522137120366096, "avg_return": 0.862903892993927, "regret": 0.0026261191815137863, "entropy": 0.07792608439922333, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:44.062952Z", "loop": 6643, "env_steps": 4082073599, "loss": 0.014116229489445686, "avg_return": 0.8624991774559021, "regret": 0.0026261191815137863, "entropy": 0.07549626380205154, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:44.918408Z", "loop": 6644, "env_steps": 4082687999, "loss": 0.01334425713866949, "avg_return": 0.8627270460128784, "regret": 0.0026261191815137863, "entropy": 0.07476899027824402, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:45.773171Z", "loop": 6645, "env_steps": 4083302399, "loss": 0.014366802759468555, "avg_return": 0.8618087768554688, "regret": 0.0026261191815137863, "entropy": 0.07950418442487717, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:46.629435Z", "loop": 6646, "env_steps": 4083916799, "loss": 0.01581043004989624, "avg_return": 0.8615258932113647, "regret": 0.0026261191815137863, "entropy": 0.08277194201946259, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:47.485194Z", "loop": 6647, "env_steps": 4084531199, "loss": 0.013627816922962666, "avg_return": 0.8627287149429321, "regret": 0.0026261191815137863, "entropy": 0.07828930020332336, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:48.341333Z", "loop": 6648, "env_steps": 4085145599, "loss": 0.014504673890769482, "avg_return": 0.8629465103149414, "regret": 0.0026261191815137863, "entropy": 0.08103369176387787, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:49.198203Z", "loop": 6649, "env_steps": 4085759999, "loss": 0.014970703981816769, "avg_return": 0.8628723621368408, "regret": 0.0026261191815137863, "entropy": 0.08163727819919586, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:50.095468Z", "loop": 6650, "env_steps": 4086374399, "loss": 0.014943663962185383, "avg_return": 0.8621500730514526, "regret": 0.0009206765098497272, "entropy": 0.08478498458862305, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:50.952344Z", "loop": 6651, "env_steps": 4086988799, "loss": 0.015524327754974365, "avg_return": 0.8624710440635681, "regret": 0.0009206765098497272, "entropy": 0.08689384907484055, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:51.807925Z", "loop": 6652, "env_steps": 4087603199, "loss": 0.016990723088383675, "avg_return": 0.861426591873169, "regret": 0.0009206765098497272, "entropy": 0.09228218346834183, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:52.665692Z", "loop": 6653, "env_steps": 4088217599, "loss": 0.016857663169503212, "avg_return": 0.8621663451194763, "regret": 0.0009206765098497272, "entropy": 0.09249922633171082, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:53.521686Z", "loop": 6654, "env_steps": 4088831999, "loss": 0.01868666708469391, "avg_return": 0.8601726293563843, "regret": 0.0009206765098497272, "entropy": 0.10085663199424744, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:54.376582Z", "loop": 6655, "env_steps": 4089446399, "loss": 0.020113548263907433, "avg_return": 0.8574364185333252, "regret": 0.0009206765098497272, "entropy": 0.1056833267211914, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:55.231424Z", "loop": 6656, "env_steps": 4090060799, "loss": 0.018735306337475777, "avg_return": 0.8591053485870361, "regret": 0.0009206765098497272, "entropy": 0.10031509399414062, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:56.087101Z", "loop": 6657, "env_steps": 4090675199, "loss": 0.018822545185685158, "avg_return": 0.8610766530036926, "regret": 0.0009206765098497272, "entropy": 0.10004285722970963, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:56.942257Z", "loop": 6658, "env_steps": 4091289599, "loss": 0.01771167851984501, "avg_return": 0.8615956902503967, "regret": 0.0009206765098497272, "entropy": 0.09668794274330139, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:57.797489Z", "loop": 6659, "env_steps": 4091903999, "loss": 0.016164375469088554, "avg_return": 0.862250566482544, "regret": 0.0009206765098497272, "entropy": 0.0927019715309143, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:58.692329Z", "loop": 6660, "env_steps": 4092518399, "loss": 0.01684681884944439, "avg_return": 0.8623523116111755, "regret": 0.0008512299973517656, "entropy": 0.09391777217388153, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:58:59.548242Z", "loop": 6661, "env_steps": 4093132799, "loss": 0.016545383259654045, "avg_return": 0.8636676073074341, "regret": 0.0008512299973517656, "entropy": 0.08940202742815018, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:00.403917Z", "loop": 6662, "env_steps": 4093747199, "loss": 0.017360983416438103, "avg_return": 0.8620843887329102, "regret": 0.0008512299973517656, "entropy": 0.0946292132139206, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:01.260784Z", "loop": 6663, "env_steps": 4094361599, "loss": 0.015823697671294212, "avg_return": 0.8640956878662109, "regret": 0.0008512299973517656, "entropy": 0.09117697924375534, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:02.116377Z", "loop": 6664, "env_steps": 4094975999, "loss": 0.01705203764140606, "avg_return": 0.8621010780334473, "regret": 0.0008512299973517656, "entropy": 0.0913139209151268, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:02.973163Z", "loop": 6665, "env_steps": 4095590399, "loss": 0.01857195794582367, "avg_return": 0.8606745600700378, "regret": 0.0008512299973517656, "entropy": 0.09929078817367554, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:03.828734Z", "loop": 6666, "env_steps": 4096204799, "loss": 0.017094284296035767, "avg_return": 0.8615065813064575, "regret": 0.0008512299973517656, "entropy": 0.0922401174902916, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:04.684671Z", "loop": 6667, "env_steps": 4096819199, "loss": 0.019497765228152275, "avg_return": 0.8612192273139954, "regret": 0.0008512299973517656, "entropy": 0.09772831946611404, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:05.540539Z", "loop": 6668, "env_steps": 4097433599, "loss": 0.019483022391796112, "avg_return": 0.8589180707931519, "regret": 0.0008512299973517656, "entropy": 0.1029142290353775, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:06.396385Z", "loop": 6669, "env_steps": 4098047999, "loss": 0.019372878596186638, "avg_return": 0.8544982075691223, "regret": 0.0008512299973517656, "entropy": 0.10189015418291092, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:07.292876Z", "loop": 6670, "env_steps": 4098662399, "loss": 0.02046397142112255, "avg_return": 0.8550633192062378, "regret": 0.009230665862560272, "entropy": 0.10888775438070297, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:08.148629Z", "loop": 6671, "env_steps": 4099276799, "loss": 0.02255721390247345, "avg_return": 0.8557496070861816, "regret": 0.009230665862560272, "entropy": 0.1094382107257843, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:09.004915Z", "loop": 6672, "env_steps": 4099891199, "loss": 0.019255807623267174, "avg_return": 0.8567230701446533, "regret": 0.009230665862560272, "entropy": 0.10411711037158966, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:09.861272Z", "loop": 6673, "env_steps": 4100505599, "loss": 0.019068364053964615, "avg_return": 0.859136164188385, "regret": 0.009230665862560272, "entropy": 0.10106425732374191, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:10.716871Z", "loop": 6674, "env_steps": 4101119999, "loss": 0.018202444538474083, "avg_return": 0.8602170944213867, "regret": 0.009230665862560272, "entropy": 0.09522885084152222, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:11.574513Z", "loop": 6675, "env_steps": 4101734399, "loss": 0.01641235500574112, "avg_return": 0.8611265420913696, "regret": 0.009230665862560272, "entropy": 0.08952721208333969, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:12.432421Z", "loop": 6676, "env_steps": 4102348799, "loss": 0.015566825866699219, "avg_return": 0.8608585000038147, "regret": 0.009230665862560272, "entropy": 0.0860816240310669, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:13.288364Z", "loop": 6677, "env_steps": 4102963199, "loss": 0.016021933406591415, "avg_return": 0.8612809181213379, "regret": 0.009230665862560272, "entropy": 0.084096260368824, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:14.143346Z", "loop": 6678, "env_steps": 4103577599, "loss": 0.014779252000153065, "avg_return": 0.8620519042015076, "regret": 0.009230665862560272, "entropy": 0.08086871355772018, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:14.997710Z", "loop": 6679, "env_steps": 4104191999, "loss": 0.015535605140030384, "avg_return": 0.8634143471717834, "regret": 0.009230665862560272, "entropy": 0.08133852481842041, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:15.891984Z", "loop": 6680, "env_steps": 4104806399, "loss": 0.014241029508411884, "avg_return": 0.8612552285194397, "regret": 0.0015245582908391953, "entropy": 0.0791841372847557, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:16.748524Z", "loop": 6681, "env_steps": 4105420799, "loss": 0.013977176509797573, "avg_return": 0.8614300489425659, "regret": 0.0015245582908391953, "entropy": 0.07885919511318207, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:17.603764Z", "loop": 6682, "env_steps": 4106035199, "loss": 0.013539698906242847, "avg_return": 0.8620914816856384, "regret": 0.0015245582908391953, "entropy": 0.07915959507226944, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:18.458797Z", "loop": 6683, "env_steps": 4106649599, "loss": 0.014416073448956013, "avg_return": 0.8606178760528564, "regret": 0.0015245582908391953, "entropy": 0.08106155693531036, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:19.315092Z", "loop": 6684, "env_steps": 4107263999, "loss": 0.015448011457920074, "avg_return": 0.8607317209243774, "regret": 0.0015245582908391953, "entropy": 0.08141716569662094, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:20.170705Z", "loop": 6685, "env_steps": 4107878399, "loss": 0.015667207539081573, "avg_return": 0.861159086227417, "regret": 0.0015245582908391953, "entropy": 0.0819886177778244, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:21.025305Z", "loop": 6686, "env_steps": 4108492799, "loss": 0.01541358232498169, "avg_return": 0.86142498254776, "regret": 0.0015245582908391953, "entropy": 0.08336757123470306, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:21.880169Z", "loop": 6687, "env_steps": 4109107199, "loss": 0.014451627619564533, "avg_return": 0.8611756563186646, "regret": 0.0015245582908391953, "entropy": 0.0797148123383522, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:22.735914Z", "loop": 6688, "env_steps": 4109721599, "loss": 0.014584287069737911, "avg_return": 0.8613859415054321, "regret": 0.0015245582908391953, "entropy": 0.07771626114845276, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:23.593260Z", "loop": 6689, "env_steps": 4110335999, "loss": 0.013786745257675648, "avg_return": 0.8626790642738342, "regret": 0.0015245582908391953, "entropy": 0.07507535815238953, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:24.490585Z", "loop": 6690, "env_steps": 4110950399, "loss": 0.01481117494404316, "avg_return": 0.8630797266960144, "regret": 0.0013086559483781457, "entropy": 0.08191423863172531, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:25.346661Z", "loop": 6691, "env_steps": 4111564799, "loss": 0.01340631302446127, "avg_return": 0.8624888062477112, "regret": 0.0013086559483781457, "entropy": 0.07799827307462692, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:26.202186Z", "loop": 6692, "env_steps": 4112179199, "loss": 0.013964124023914337, "avg_return": 0.8623387813568115, "regret": 0.0013086559483781457, "entropy": 0.07809511572122574, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:27.057298Z", "loop": 6693, "env_steps": 4112793599, "loss": 0.014302804134786129, "avg_return": 0.8617334961891174, "regret": 0.0013086559483781457, "entropy": 0.07924464344978333, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:27.912825Z", "loop": 6694, "env_steps": 4113407999, "loss": 0.013533330522477627, "avg_return": 0.8624113202095032, "regret": 0.0013086559483781457, "entropy": 0.0758327841758728, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:28.768410Z", "loop": 6695, "env_steps": 4114022399, "loss": 0.015097217634320259, "avg_return": 0.861367404460907, "regret": 0.0013086559483781457, "entropy": 0.08360239863395691, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:29.624253Z", "loop": 6696, "env_steps": 4114636799, "loss": 0.015096954070031643, "avg_return": 0.8628731369972229, "regret": 0.0013086559483781457, "entropy": 0.08194025605916977, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:30.480180Z", "loop": 6697, "env_steps": 4115251199, "loss": 0.014307892881333828, "avg_return": 0.862001895904541, "regret": 0.0013086559483781457, "entropy": 0.07826055586338043, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:31.335468Z", "loop": 6698, "env_steps": 4115865599, "loss": 0.015370264649391174, "avg_return": 0.8627773523330688, "regret": 0.0013086559483781457, "entropy": 0.08469085395336151, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:32.190530Z", "loop": 6699, "env_steps": 4116479999, "loss": 0.015015832148492336, "avg_return": 0.8608379364013672, "regret": 0.0013086559483781457, "entropy": 0.08136565238237381, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:33.086018Z", "loop": 6700, "env_steps": 4117094399, "loss": 0.01491513755172491, "avg_return": 0.8614219427108765, "regret": 0.0013412418775260448, "entropy": 0.08019264787435532, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:33.939809Z", "loop": 6701, "env_steps": 4117708799, "loss": 0.014435318298637867, "avg_return": 0.8620312809944153, "regret": 0.0013412418775260448, "entropy": 0.08068736642599106, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:34.793573Z", "loop": 6702, "env_steps": 4118323199, "loss": 0.015018097124993801, "avg_return": 0.8620467185974121, "regret": 0.0013412418775260448, "entropy": 0.08289456367492676, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:35.648504Z", "loop": 6703, "env_steps": 4118937599, "loss": 0.01552841067314148, "avg_return": 0.8623113036155701, "regret": 0.0013412418775260448, "entropy": 0.08233726024627686, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:36.504564Z", "loop": 6704, "env_steps": 4119551999, "loss": 0.014649231918156147, "avg_return": 0.8625971674919128, "regret": 0.0013412418775260448, "entropy": 0.07867748290300369, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:37.360286Z", "loop": 6705, "env_steps": 4120166399, "loss": 0.014917138032615185, "avg_return": 0.8629504442214966, "regret": 0.0013412418775260448, "entropy": 0.08146030455827713, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:38.216262Z", "loop": 6706, "env_steps": 4120780799, "loss": 0.01443781889975071, "avg_return": 0.8625614643096924, "regret": 0.0013412418775260448, "entropy": 0.08222061395645142, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:39.071945Z", "loop": 6707, "env_steps": 4121395199, "loss": 0.014953135512769222, "avg_return": 0.8622540235519409, "regret": 0.0013412418775260448, "entropy": 0.08021751046180725, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:39.927414Z", "loop": 6708, "env_steps": 4122009599, "loss": 0.013951520435512066, "avg_return": 0.8615073561668396, "regret": 0.0013412418775260448, "entropy": 0.07773058116436005, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:40.782962Z", "loop": 6709, "env_steps": 4122623999, "loss": 0.013325675390660763, "avg_return": 0.8632210493087769, "regret": 0.0013412418775260448, "entropy": 0.07710953056812286, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:41.677377Z", "loop": 6710, "env_steps": 4123238399, "loss": 0.014354482293128967, "avg_return": 0.8624566793441772, "regret": 0.001456553814932704, "entropy": 0.08146936446428299, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:42.531529Z", "loop": 6711, "env_steps": 4123852799, "loss": 0.013716083951294422, "avg_return": 0.8614736199378967, "regret": 0.001456553814932704, "entropy": 0.07694422453641891, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:43.387241Z", "loop": 6712, "env_steps": 4124467199, "loss": 0.015627896413207054, "avg_return": 0.86029052734375, "regret": 0.001456553814932704, "entropy": 0.08225042372941971, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:44.243419Z", "loop": 6713, "env_steps": 4125081599, "loss": 0.014542484655976295, "avg_return": 0.8614369630813599, "regret": 0.001456553814932704, "entropy": 0.08015675842761993, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:45.098633Z", "loop": 6714, "env_steps": 4125695999, "loss": 0.01436854898929596, "avg_return": 0.8630855679512024, "regret": 0.001456553814932704, "entropy": 0.08389613032341003, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:45.953207Z", "loop": 6715, "env_steps": 4126310399, "loss": 0.016311487182974815, "avg_return": 0.8613554239273071, "regret": 0.001456553814932704, "entropy": 0.08509095758199692, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:46.808875Z", "loop": 6716, "env_steps": 4126924799, "loss": 0.0142742320895195, "avg_return": 0.8612948060035706, "regret": 0.001456553814932704, "entropy": 0.08102793246507645, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:47.664374Z", "loop": 6717, "env_steps": 4127539199, "loss": 0.014614291489124298, "avg_return": 0.8606659173965454, "regret": 0.001456553814932704, "entropy": 0.08367452770471573, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:48.519826Z", "loop": 6718, "env_steps": 4128153599, "loss": 0.014692503027617931, "avg_return": 0.8616148233413696, "regret": 0.001456553814932704, "entropy": 0.08014623820781708, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:49.375125Z", "loop": 6719, "env_steps": 4128767999, "loss": 0.014186403714120388, "avg_return": 0.8604947328567505, "regret": 0.001456553814932704, "entropy": 0.08141797035932541, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:50.270942Z", "loop": 6720, "env_steps": 4129382399, "loss": 0.014775047078728676, "avg_return": 0.8609473705291748, "regret": 0.0015758269000798464, "entropy": 0.08393619954586029, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:51.127876Z", "loop": 6721, "env_steps": 4129996799, "loss": 0.014193265698850155, "avg_return": 0.8625783324241638, "regret": 0.0015758269000798464, "entropy": 0.07834535092115402, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:51.983230Z", "loop": 6722, "env_steps": 4130611199, "loss": 0.014676189981400967, "avg_return": 0.8615399599075317, "regret": 0.0015758269000798464, "entropy": 0.08759232610464096, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:52.839350Z", "loop": 6723, "env_steps": 4131225599, "loss": 0.014691682532429695, "avg_return": 0.8623478412628174, "regret": 0.0015758269000798464, "entropy": 0.07898491621017456, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:53.695376Z", "loop": 6724, "env_steps": 4131839999, "loss": 0.015041167847812176, "avg_return": 0.8611792922019958, "regret": 0.0015758269000798464, "entropy": 0.0822700709104538, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:54.549891Z", "loop": 6725, "env_steps": 4132454399, "loss": 0.013613319955766201, "avg_return": 0.861748456954956, "regret": 0.0015758269000798464, "entropy": 0.07959666848182678, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:55.406824Z", "loop": 6726, "env_steps": 4133068799, "loss": 0.01566140167415142, "avg_return": 0.8626888394355774, "regret": 0.0015758269000798464, "entropy": 0.08150181919336319, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:56.263072Z", "loop": 6727, "env_steps": 4133683199, "loss": 0.01371718943119049, "avg_return": 0.8613846898078918, "regret": 0.0015758269000798464, "entropy": 0.0771356150507927, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:57.118120Z", "loop": 6728, "env_steps": 4134297599, "loss": 0.014822877943515778, "avg_return": 0.8623995184898376, "regret": 0.0015758269000798464, "entropy": 0.07913074642419815, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:57.973419Z", "loop": 6729, "env_steps": 4134911999, "loss": 0.014900474809110165, "avg_return": 0.8634839057922363, "regret": 0.0015758269000798464, "entropy": 0.08038143813610077, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:58.871279Z", "loop": 6730, "env_steps": 4135526399, "loss": 0.013474334962666035, "avg_return": 0.8617612719535828, "regret": 0.0011851724702864885, "entropy": 0.07636559754610062, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T18:59:59.726511Z", "loop": 6731, "env_steps": 4136140799, "loss": 0.015267685055732727, "avg_return": 0.8626164197921753, "regret": 0.0011851724702864885, "entropy": 0.0817485824227333, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:00.583135Z", "loop": 6732, "env_steps": 4136755199, "loss": 0.0147282425314188, "avg_return": 0.8636692762374878, "regret": 0.0011851724702864885, "entropy": 0.082114078104496, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:01.436293Z", "loop": 6733, "env_steps": 4137369599, "loss": 0.015108631923794746, "avg_return": 0.8621739149093628, "regret": 0.0011851724702864885, "entropy": 0.0812399759888649, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:02.291970Z", "loop": 6734, "env_steps": 4137983999, "loss": 0.015193215571343899, "avg_return": 0.8632233738899231, "regret": 0.0011851724702864885, "entropy": 0.08377256989479065, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:03.148425Z", "loop": 6735, "env_steps": 4138598399, "loss": 0.016358714550733566, "avg_return": 0.8621639013290405, "regret": 0.0011851724702864885, "entropy": 0.08395712077617645, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:04.004153Z", "loop": 6736, "env_steps": 4139212799, "loss": 0.015517458319664001, "avg_return": 0.8630303144454956, "regret": 0.0011851724702864885, "entropy": 0.08039600402116776, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:04.859809Z", "loop": 6737, "env_steps": 4139827199, "loss": 0.013914729468524456, "avg_return": 0.8632979393005371, "regret": 0.0011851724702864885, "entropy": 0.0795566514134407, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:05.715115Z", "loop": 6738, "env_steps": 4140441599, "loss": 0.015399816446006298, "avg_return": 0.863209068775177, "regret": 0.0011851724702864885, "entropy": 0.0827454924583435, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:06.570409Z", "loop": 6739, "env_steps": 4141055999, "loss": 0.014947197400033474, "avg_return": 0.8629012107849121, "regret": 0.0011851724702864885, "entropy": 0.08037158101797104, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:07.466753Z", "loop": 6740, "env_steps": 4141670399, "loss": 0.015581214800477028, "avg_return": 0.863483726978302, "regret": 0.0007991258171387017, "entropy": 0.08499655872583389, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:08.322680Z", "loop": 6741, "env_steps": 4142284799, "loss": 0.015242873691022396, "avg_return": 0.8625715374946594, "regret": 0.0007991258171387017, "entropy": 0.08697864413261414, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:09.177744Z", "loop": 6742, "env_steps": 4142899199, "loss": 0.014442640356719494, "avg_return": 0.8635094165802002, "regret": 0.0007991258171387017, "entropy": 0.07946992665529251, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:10.033246Z", "loop": 6743, "env_steps": 4143513599, "loss": 0.014891929924488068, "avg_return": 0.8634320497512817, "regret": 0.0007991258171387017, "entropy": 0.08025624603033066, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:10.889306Z", "loop": 6744, "env_steps": 4144127999, "loss": 0.015621042810380459, "avg_return": 0.8637776970863342, "regret": 0.0007991258171387017, "entropy": 0.08533359318971634, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:11.746335Z", "loop": 6745, "env_steps": 4144742399, "loss": 0.01541738398373127, "avg_return": 0.8635808229446411, "regret": 0.0007991258171387017, "entropy": 0.08193156123161316, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:12.602479Z", "loop": 6746, "env_steps": 4145356799, "loss": 0.015709729865193367, "avg_return": 0.8640706539154053, "regret": 0.0007991258171387017, "entropy": 0.08186014741659164, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:13.457176Z", "loop": 6747, "env_steps": 4145971199, "loss": 0.015327828004956245, "avg_return": 0.8626049160957336, "regret": 0.0007991258171387017, "entropy": 0.08446178585290909, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:14.313054Z", "loop": 6748, "env_steps": 4146585599, "loss": 0.015596071258187294, "avg_return": 0.8647257685661316, "regret": 0.0007991258171387017, "entropy": 0.08702106028795242, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:15.168818Z", "loop": 6749, "env_steps": 4147199999, "loss": 0.014719068072736263, "avg_return": 0.8623741865158081, "regret": 0.0007991258171387017, "entropy": 0.08162061870098114, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:16.064632Z", "loop": 6750, "env_steps": 4147814399, "loss": 0.01600245200097561, "avg_return": 0.8622500896453857, "regret": 0.0007947072735987604, "entropy": 0.08613719046115875, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:16.920503Z", "loop": 6751, "env_steps": 4148428799, "loss": 0.016152415424585342, "avg_return": 0.8621004223823547, "regret": 0.0007947072735987604, "entropy": 0.0864909365773201, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:17.777426Z", "loop": 6752, "env_steps": 4149043199, "loss": 0.016280800104141235, "avg_return": 0.8612635731697083, "regret": 0.0007947072735987604, "entropy": 0.09060055762529373, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:18.633363Z", "loop": 6753, "env_steps": 4149657599, "loss": 0.016835151240229607, "avg_return": 0.8624162077903748, "regret": 0.0007947072735987604, "entropy": 0.08973255753517151, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:19.489794Z", "loop": 6754, "env_steps": 4150271999, "loss": 0.017333639785647392, "avg_return": 0.8622963428497314, "regret": 0.0007947072735987604, "entropy": 0.09402969479560852, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:20.345411Z", "loop": 6755, "env_steps": 4150886399, "loss": 0.01645381562411785, "avg_return": 0.8618494868278503, "regret": 0.0007947072735987604, "entropy": 0.09371327608823776, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:21.201364Z", "loop": 6756, "env_steps": 4151500799, "loss": 0.016224315389990807, "avg_return": 0.8610419034957886, "regret": 0.0007947072735987604, "entropy": 0.09010395407676697, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:22.056822Z", "loop": 6757, "env_steps": 4152115199, "loss": 0.017217140644788742, "avg_return": 0.8618506789207458, "regret": 0.0007947072735987604, "entropy": 0.09670648723840714, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:22.913310Z", "loop": 6758, "env_steps": 4152729599, "loss": 0.018496941775083542, "avg_return": 0.8616564869880676, "regret": 0.0007947072735987604, "entropy": 0.09712262451648712, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:23.770776Z", "loop": 6759, "env_steps": 4153343999, "loss": 0.01596980169415474, "avg_return": 0.8607954978942871, "regret": 0.0007947072735987604, "entropy": 0.09298572689294815, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:24.667114Z", "loop": 6760, "env_steps": 4153958399, "loss": 0.01710728369653225, "avg_return": 0.8619882464408875, "regret": 0.0014962356071919203, "entropy": 0.09408577531576157, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:25.522567Z", "loop": 6761, "env_steps": 4154572799, "loss": 0.01787588931620121, "avg_return": 0.8615145087242126, "regret": 0.0014962356071919203, "entropy": 0.09472009539604187, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:26.377743Z", "loop": 6762, "env_steps": 4155187199, "loss": 0.015805428847670555, "avg_return": 0.8624094128608704, "regret": 0.0014962356071919203, "entropy": 0.08958233892917633, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:27.233568Z", "loop": 6763, "env_steps": 4155801599, "loss": 0.01682383008301258, "avg_return": 0.8606052994728088, "regret": 0.0014962356071919203, "entropy": 0.09384167939424515, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:28.090200Z", "loop": 6764, "env_steps": 4156415999, "loss": 0.015993289649486542, "avg_return": 0.8639464378356934, "regret": 0.0014962356071919203, "entropy": 0.08832570910453796, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:28.944809Z", "loop": 6765, "env_steps": 4157030399, "loss": 0.017945293337106705, "avg_return": 0.861513078212738, "regret": 0.0014962356071919203, "entropy": 0.09667092561721802, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:29.799464Z", "loop": 6766, "env_steps": 4157644799, "loss": 0.01860990561544895, "avg_return": 0.862932562828064, "regret": 0.0014962356071919203, "entropy": 0.10182937979698181, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:30.655285Z", "loop": 6767, "env_steps": 4158259199, "loss": 0.018420405685901642, "avg_return": 0.8629091382026672, "regret": 0.0014962356071919203, "entropy": 0.103176049888134, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:31.511978Z", "loop": 6768, "env_steps": 4158873599, "loss": 0.019212424755096436, "avg_return": 0.8618072867393494, "regret": 0.0014962356071919203, "entropy": 0.10625500231981277, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:32.367817Z", "loop": 6769, "env_steps": 4159487999, "loss": 0.02005360648036003, "avg_return": 0.8634220361709595, "regret": 0.0014962356071919203, "entropy": 0.10612227022647858, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:33.265822Z", "loop": 6770, "env_steps": 4160102399, "loss": 0.018558861687779427, "avg_return": 0.8616070747375488, "regret": 0.0013315618271008134, "entropy": 0.1014356017112732, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:34.121548Z", "loop": 6771, "env_steps": 4160716799, "loss": 0.01779770851135254, "avg_return": 0.860760509967804, "regret": 0.0013315618271008134, "entropy": 0.10116779804229736, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:34.977903Z", "loop": 6772, "env_steps": 4161331199, "loss": 0.01924416981637478, "avg_return": 0.8613072633743286, "regret": 0.0013315618271008134, "entropy": 0.10597629100084305, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:35.834936Z", "loop": 6773, "env_steps": 4161945599, "loss": 0.018460437655448914, "avg_return": 0.8620715737342834, "regret": 0.0013315618271008134, "entropy": 0.10220161080360413, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:36.690447Z", "loop": 6774, "env_steps": 4162559999, "loss": 0.018109137192368507, "avg_return": 0.8623937964439392, "regret": 0.0013315618271008134, "entropy": 0.10158681124448776, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:37.546078Z", "loop": 6775, "env_steps": 4163174399, "loss": 0.019084414467215538, "avg_return": 0.8623337149620056, "regret": 0.0013315618271008134, "entropy": 0.10162533819675446, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:38.401519Z", "loop": 6776, "env_steps": 4163788799, "loss": 0.016878999769687653, "avg_return": 0.8623083829879761, "regret": 0.0013315618271008134, "entropy": 0.09685054421424866, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:39.257637Z", "loop": 6777, "env_steps": 4164403199, "loss": 0.01811876706779003, "avg_return": 0.862466037273407, "regret": 0.0013315618271008134, "entropy": 0.09387540817260742, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:40.113575Z", "loop": 6778, "env_steps": 4165017599, "loss": 0.016624830663204193, "avg_return": 0.8618867993354797, "regret": 0.0013315618271008134, "entropy": 0.09471205621957779, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:40.969282Z", "loop": 6779, "env_steps": 4165631999, "loss": 0.017421279102563858, "avg_return": 0.8623236417770386, "regret": 0.0013315618271008134, "entropy": 0.09486658126115799, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:41.867310Z", "loop": 6780, "env_steps": 4166246399, "loss": 0.01566929928958416, "avg_return": 0.8609712719917297, "regret": 0.001642965362407267, "entropy": 0.0879727378487587, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:42.722291Z", "loop": 6781, "env_steps": 4166860799, "loss": 0.017123129218816757, "avg_return": 0.8643821477890015, "regret": 0.001642965362407267, "entropy": 0.09233590960502625, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:43.578726Z", "loop": 6782, "env_steps": 4167475199, "loss": 0.0162701066583395, "avg_return": 0.862144410610199, "regret": 0.001642965362407267, "entropy": 0.0930476114153862, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:44.434838Z", "loop": 6783, "env_steps": 4168089599, "loss": 0.016121817752718925, "avg_return": 0.8613933324813843, "regret": 0.001642965362407267, "entropy": 0.08778806030750275, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:45.289049Z", "loop": 6784, "env_steps": 4168703999, "loss": 0.015608372166752815, "avg_return": 0.8632497191429138, "regret": 0.001642965362407267, "entropy": 0.0887971892952919, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:46.143911Z", "loop": 6785, "env_steps": 4169318399, "loss": 0.01607022061944008, "avg_return": 0.8616558909416199, "regret": 0.001642965362407267, "entropy": 0.08799310028553009, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:47.000346Z", "loop": 6786, "env_steps": 4169932799, "loss": 0.015363039448857307, "avg_return": 0.8615812659263611, "regret": 0.001642965362407267, "entropy": 0.08800383657217026, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:47.855810Z", "loop": 6787, "env_steps": 4170547199, "loss": 0.01672949828207493, "avg_return": 0.8630701899528503, "regret": 0.001642965362407267, "entropy": 0.0925358235836029, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:48.710847Z", "loop": 6788, "env_steps": 4171161599, "loss": 0.017220990732312202, "avg_return": 0.862291693687439, "regret": 0.001642965362407267, "entropy": 0.0947900116443634, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:49.566208Z", "loop": 6789, "env_steps": 4171775999, "loss": 0.01531639602035284, "avg_return": 0.8634615540504456, "regret": 0.001642965362407267, "entropy": 0.08648517727851868, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:50.461989Z", "loop": 6790, "env_steps": 4172390399, "loss": 0.017322806641459465, "avg_return": 0.8618894815444946, "regret": 0.0016265774611383677, "entropy": 0.09386482834815979, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:51.317694Z", "loop": 6791, "env_steps": 4173004799, "loss": 0.01594632863998413, "avg_return": 0.8632668256759644, "regret": 0.0016265774611383677, "entropy": 0.08952591568231583, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:52.172317Z", "loop": 6792, "env_steps": 4173619199, "loss": 0.016793934628367424, "avg_return": 0.8608906269073486, "regret": 0.0016265774611383677, "entropy": 0.08908958733081818, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:53.026839Z", "loop": 6793, "env_steps": 4174233599, "loss": 0.016252057626843452, "avg_return": 0.8613954782485962, "regret": 0.0016265774611383677, "entropy": 0.09139341115951538, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:53.882143Z", "loop": 6794, "env_steps": 4174847999, "loss": 0.017032550647854805, "avg_return": 0.8604861497879028, "regret": 0.0016265774611383677, "entropy": 0.09471160918474197, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:54.738152Z", "loop": 6795, "env_steps": 4175462399, "loss": 0.0178848747164011, "avg_return": 0.8594990968704224, "regret": 0.0016265774611383677, "entropy": 0.09123127162456512, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:55.592953Z", "loop": 6796, "env_steps": 4176076799, "loss": 0.01773545891046524, "avg_return": 0.858665406703949, "regret": 0.0016265774611383677, "entropy": 0.09644729644060135, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:56.447538Z", "loop": 6797, "env_steps": 4176691199, "loss": 0.019782263785600662, "avg_return": 0.8587146997451782, "regret": 0.0016265774611383677, "entropy": 0.10569719225168228, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:57.302570Z", "loop": 6798, "env_steps": 4177305599, "loss": 0.020122036337852478, "avg_return": 0.8583107590675354, "regret": 0.0016265774611383677, "entropy": 0.10353381186723709, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:58.158028Z", "loop": 6799, "env_steps": 4177919999, "loss": 0.019789421930909157, "avg_return": 0.8581656813621521, "regret": 0.0016265774611383677, "entropy": 0.10507528483867645, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:59.053055Z", "loop": 6800, "env_steps": 4178534399, "loss": 0.01974431425333023, "avg_return": 0.8573609590530396, "regret": 0.005184374283999205, "entropy": 0.10824636369943619, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:00:59.908529Z", "loop": 6801, "env_steps": 4179148799, "loss": 0.01788993552327156, "avg_return": 0.8606252074241638, "regret": 0.005184374283999205, "entropy": 0.10173112899065018, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:00.763369Z", "loop": 6802, "env_steps": 4179763199, "loss": 0.01803923211991787, "avg_return": 0.859825849533081, "regret": 0.005184374283999205, "entropy": 0.10222195833921432, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:01.618926Z", "loop": 6803, "env_steps": 4180377599, "loss": 0.01922554522752762, "avg_return": 0.860194742679596, "regret": 0.005184374283999205, "entropy": 0.10631661862134933, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:02.473826Z", "loop": 6804, "env_steps": 4180991999, "loss": 0.01903454214334488, "avg_return": 0.8597497940063477, "regret": 0.005184374283999205, "entropy": 0.10365051031112671, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:03.329051Z", "loop": 6805, "env_steps": 4181606399, "loss": 0.018813474103808403, "avg_return": 0.8593096137046814, "regret": 0.005184374283999205, "entropy": 0.10827403515577316, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:04.184740Z", "loop": 6806, "env_steps": 4182220799, "loss": 0.01887093298137188, "avg_return": 0.8589691519737244, "regret": 0.005184374283999205, "entropy": 0.10633353888988495, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:05.040074Z", "loop": 6807, "env_steps": 4182835199, "loss": 0.020738326013088226, "avg_return": 0.8593758344650269, "regret": 0.005184374283999205, "entropy": 0.11374646425247192, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:05.896771Z", "loop": 6808, "env_steps": 4183449599, "loss": 0.022481434047222137, "avg_return": 0.8568739891052246, "regret": 0.005184374283999205, "entropy": 0.12337494641542435, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:06.752279Z", "loop": 6809, "env_steps": 4184063999, "loss": 0.02241886407136917, "avg_return": 0.856518566608429, "regret": 0.005184374283999205, "entropy": 0.12596233189105988, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:07.647753Z", "loop": 6810, "env_steps": 4184678399, "loss": 0.02269146591424942, "avg_return": 0.8565564155578613, "regret": 0.007084470242261887, "entropy": 0.1244945377111435, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:08.502115Z", "loop": 6811, "env_steps": 4185292799, "loss": 0.02268935553729534, "avg_return": 0.8559057712554932, "regret": 0.007084470242261887, "entropy": 0.12360376119613647, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:09.357690Z", "loop": 6812, "env_steps": 4185907199, "loss": 0.02292669005692005, "avg_return": 0.8565155267715454, "regret": 0.007084470242261887, "entropy": 0.12681567668914795, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:10.212651Z", "loop": 6813, "env_steps": 4186521599, "loss": 0.022578028962016106, "avg_return": 0.8570648431777954, "regret": 0.007084470242261887, "entropy": 0.12314031273126602, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:11.067831Z", "loop": 6814, "env_steps": 4187135999, "loss": 0.0219236072152853, "avg_return": 0.8566855192184448, "regret": 0.007084470242261887, "entropy": 0.1211816817522049, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:11.922758Z", "loop": 6815, "env_steps": 4187750399, "loss": 0.022442899644374847, "avg_return": 0.8548205494880676, "regret": 0.007084470242261887, "entropy": 0.12312798947095871, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:12.777118Z", "loop": 6816, "env_steps": 4188364799, "loss": 0.022582178935408592, "avg_return": 0.8545742034912109, "regret": 0.007084470242261887, "entropy": 0.11709944158792496, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:13.632306Z", "loop": 6817, "env_steps": 4188979199, "loss": 0.02105872705578804, "avg_return": 0.8512992262840271, "regret": 0.007084470242261887, "entropy": 0.11328508704900742, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:14.486980Z", "loop": 6818, "env_steps": 4189593599, "loss": 0.021694792434573174, "avg_return": 0.8497265577316284, "regret": 0.007084470242261887, "entropy": 0.11554928123950958, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:15.342280Z", "loop": 6819, "env_steps": 4190207999, "loss": 0.02254643477499485, "avg_return": 0.8521385788917542, "regret": 0.007084470242261887, "entropy": 0.1132686510682106, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:16.236664Z", "loop": 6820, "env_steps": 4190822399, "loss": 0.021327150985598564, "avg_return": 0.8516987562179565, "regret": 0.009948812425136566, "entropy": 0.11444807797670364, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:17.091891Z", "loop": 6821, "env_steps": 4191436799, "loss": 0.020725538954138756, "avg_return": 0.8560444116592407, "regret": 0.009948812425136566, "entropy": 0.11164748668670654, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:17.946833Z", "loop": 6822, "env_steps": 4192051199, "loss": 0.020829180255532265, "avg_return": 0.8567466139793396, "regret": 0.009948812425136566, "entropy": 0.112240731716156, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:18.802765Z", "loop": 6823, "env_steps": 4192665599, "loss": 0.020708514377474785, "avg_return": 0.8562203049659729, "regret": 0.009948812425136566, "entropy": 0.10828116536140442, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:19.658591Z", "loop": 6824, "env_steps": 4193279999, "loss": 0.019274191930890083, "avg_return": 0.8601645231246948, "regret": 0.009948812425136566, "entropy": 0.10228373855352402, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:20.513462Z", "loop": 6825, "env_steps": 4193894399, "loss": 0.018095748499035835, "avg_return": 0.8596504926681519, "regret": 0.009948812425136566, "entropy": 0.1036887988448143, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:21.368524Z", "loop": 6826, "env_steps": 4194508799, "loss": 0.018469011411070824, "avg_return": 0.8609595894813538, "regret": 0.009948812425136566, "entropy": 0.09948296844959259, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:22.224210Z", "loop": 6827, "env_steps": 4195123199, "loss": 0.018156137317419052, "avg_return": 0.8620322942733765, "regret": 0.009948812425136566, "entropy": 0.0931362584233284, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:23.079194Z", "loop": 6828, "env_steps": 4195737599, "loss": 0.015777401626110077, "avg_return": 0.8631747364997864, "regret": 0.009948812425136566, "entropy": 0.0921032503247261, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:23.933318Z", "loop": 6829, "env_steps": 4196351999, "loss": 0.016742944717407227, "avg_return": 0.8627297282218933, "regret": 0.009948812425136566, "entropy": 0.09106005728244781, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:24.828934Z", "loop": 6830, "env_steps": 4196966399, "loss": 0.017044033855199814, "avg_return": 0.863322377204895, "regret": 0.000788709323387593, "entropy": 0.09101226180791855, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:25.684903Z", "loop": 6831, "env_steps": 4197580799, "loss": 0.016468998044729233, "avg_return": 0.8614816665649414, "regret": 0.000788709323387593, "entropy": 0.09112047404050827, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:26.540039Z", "loop": 6832, "env_steps": 4198195199, "loss": 0.01767716184258461, "avg_return": 0.8606211543083191, "regret": 0.000788709323387593, "entropy": 0.0978054404258728, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:27.394261Z", "loop": 6833, "env_steps": 4198809599, "loss": 0.018028754740953445, "avg_return": 0.8583314418792725, "regret": 0.000788709323387593, "entropy": 0.09889115393161774, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:28.248674Z", "loop": 6834, "env_steps": 4199423999, "loss": 0.017004268243908882, "avg_return": 0.8607177734375, "regret": 0.000788709323387593, "entropy": 0.09190559387207031, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:29.103302Z", "loop": 6835, "env_steps": 4200038399, "loss": 0.015851151198148727, "avg_return": 0.8604036569595337, "regret": 0.000788709323387593, "entropy": 0.08712149411439896, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:29.958484Z", "loop": 6836, "env_steps": 4200652799, "loss": 0.01613648794591427, "avg_return": 0.8627093434333801, "regret": 0.000788709323387593, "entropy": 0.09060288220643997, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:30.813880Z", "loop": 6837, "env_steps": 4201267199, "loss": 0.014761342667043209, "avg_return": 0.8630041480064392, "regret": 0.000788709323387593, "entropy": 0.0844469889998436, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:31.669334Z", "loop": 6838, "env_steps": 4201881599, "loss": 0.016183968633413315, "avg_return": 0.8625029921531677, "regret": 0.000788709323387593, "entropy": 0.08532880246639252, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:32.524818Z", "loop": 6839, "env_steps": 4202495999, "loss": 0.015474190004169941, "avg_return": 0.863300085067749, "regret": 0.000788709323387593, "entropy": 0.08431850373744965, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:33.420442Z", "loop": 6840, "env_steps": 4203110399, "loss": 0.014915543608367443, "avg_return": 0.8615689277648926, "regret": 0.0007522840169258416, "entropy": 0.08408750593662262, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:34.276537Z", "loop": 6841, "env_steps": 4203724799, "loss": 0.015350270085036755, "avg_return": 0.8638096451759338, "regret": 0.0007522840169258416, "entropy": 0.08212337642908096, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:35.134064Z", "loop": 6842, "env_steps": 4204339199, "loss": 0.014778568409383297, "avg_return": 0.8627347946166992, "regret": 0.0007522840169258416, "entropy": 0.08291580528020859, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:35.990299Z", "loop": 6843, "env_steps": 4204953599, "loss": 0.014814293943345547, "avg_return": 0.8631860613822937, "regret": 0.0007522840169258416, "entropy": 0.0813574269413948, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:36.845674Z", "loop": 6844, "env_steps": 4205567999, "loss": 0.015973230823874474, "avg_return": 0.8618336915969849, "regret": 0.0007522840169258416, "entropy": 0.08593543618917465, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:37.701384Z", "loop": 6845, "env_steps": 4206182399, "loss": 0.014939404092729092, "avg_return": 0.861397922039032, "regret": 0.0007522840169258416, "entropy": 0.08567500859498978, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:38.556843Z", "loop": 6846, "env_steps": 4206796799, "loss": 0.01560928113758564, "avg_return": 0.862188458442688, "regret": 0.0007522840169258416, "entropy": 0.08913131058216095, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:39.411575Z", "loop": 6847, "env_steps": 4207411199, "loss": 0.015774449333548546, "avg_return": 0.8634146451950073, "regret": 0.0007522840169258416, "entropy": 0.08767953515052795, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:40.266189Z", "loop": 6848, "env_steps": 4208025599, "loss": 0.015027162618935108, "avg_return": 0.8626543283462524, "regret": 0.0007522840169258416, "entropy": 0.08270560204982758, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:41.121484Z", "loop": 6849, "env_steps": 4208639999, "loss": 0.016395775601267815, "avg_return": 0.8626251220703125, "regret": 0.0007522840169258416, "entropy": 0.09009568393230438, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:42.018320Z", "loop": 6850, "env_steps": 4209254399, "loss": 0.015016851015388966, "avg_return": 0.8640000820159912, "regret": 0.0009492130484431982, "entropy": 0.085030198097229, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:42.874221Z", "loop": 6851, "env_steps": 4209868799, "loss": 0.015449203550815582, "avg_return": 0.8621336221694946, "regret": 0.0009492130484431982, "entropy": 0.08601254224777222, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:43.731465Z", "loop": 6852, "env_steps": 4210483199, "loss": 0.01449092011898756, "avg_return": 0.8644800186157227, "regret": 0.0009492130484431982, "entropy": 0.08318363130092621, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:44.588308Z", "loop": 6853, "env_steps": 4211097599, "loss": 0.016254650428891182, "avg_return": 0.8635522723197937, "regret": 0.0009492130484431982, "entropy": 0.08904080092906952, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:45.445319Z", "loop": 6854, "env_steps": 4211711999, "loss": 0.014634045772254467, "avg_return": 0.8613686561584473, "regret": 0.0009492130484431982, "entropy": 0.08119521290063858, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:46.300854Z", "loop": 6855, "env_steps": 4212326399, "loss": 0.014121484942734241, "avg_return": 0.8635964393615723, "regret": 0.0009492130484431982, "entropy": 0.08024981617927551, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:47.155050Z", "loop": 6856, "env_steps": 4212940799, "loss": 0.01585446298122406, "avg_return": 0.8636443018913269, "regret": 0.0009492130484431982, "entropy": 0.084384985268116, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:48.009051Z", "loop": 6857, "env_steps": 4213555199, "loss": 0.014600614085793495, "avg_return": 0.863589882850647, "regret": 0.0009492130484431982, "entropy": 0.08227206021547318, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:48.865464Z", "loop": 6858, "env_steps": 4214169599, "loss": 0.015036146156489849, "avg_return": 0.8637466430664062, "regret": 0.0009492130484431982, "entropy": 0.08556897938251495, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:49.720851Z", "loop": 6859, "env_steps": 4214783999, "loss": 0.015964796766638756, "avg_return": 0.8618539571762085, "regret": 0.0009492130484431982, "entropy": 0.08563415706157684, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:50.615705Z", "loop": 6860, "env_steps": 4215398399, "loss": 0.015305349603295326, "avg_return": 0.8642287254333496, "regret": 0.0006519993185065687, "entropy": 0.08214063942432404, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:51.471422Z", "loop": 6861, "env_steps": 4216012799, "loss": 0.014853425323963165, "avg_return": 0.862720787525177, "regret": 0.0006519993185065687, "entropy": 0.08093483000993729, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:52.326374Z", "loop": 6862, "env_steps": 4216627199, "loss": 0.015017158351838589, "avg_return": 0.8627277612686157, "regret": 0.0006519993185065687, "entropy": 0.08353400975465775, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:53.180885Z", "loop": 6863, "env_steps": 4217241599, "loss": 0.015955902636051178, "avg_return": 0.8637374043464661, "regret": 0.0006519993185065687, "entropy": 0.08636931329965591, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:54.036480Z", "loop": 6864, "env_steps": 4217855999, "loss": 0.015225260518491268, "avg_return": 0.86265629529953, "regret": 0.0006519993185065687, "entropy": 0.08500214666128159, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:54.893613Z", "loop": 6865, "env_steps": 4218470399, "loss": 0.015477950684726238, "avg_return": 0.8624454736709595, "regret": 0.0006519993185065687, "entropy": 0.08789663761854172, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:55.749661Z", "loop": 6866, "env_steps": 4219084799, "loss": 0.015561006031930447, "avg_return": 0.8619440793991089, "regret": 0.0006519993185065687, "entropy": 0.08394663035869598, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:56.605327Z", "loop": 6867, "env_steps": 4219699199, "loss": 0.014292590320110321, "avg_return": 0.8634912371635437, "regret": 0.0006519993185065687, "entropy": 0.08171769231557846, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:57.460442Z", "loop": 6868, "env_steps": 4220313599, "loss": 0.015151343308389187, "avg_return": 0.8626684546470642, "regret": 0.0006519993185065687, "entropy": 0.08426663279533386, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:58.315486Z", "loop": 6869, "env_steps": 4220927999, "loss": 0.015734830871224403, "avg_return": 0.8627409338951111, "regret": 0.0006519993185065687, "entropy": 0.08917661756277084, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:01:59.212885Z", "loop": 6870, "env_steps": 4221542399, "loss": 0.015046332962810993, "avg_return": 0.8610918521881104, "regret": 0.001659441040828824, "entropy": 0.0837591364979744, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:00.067783Z", "loop": 6871, "env_steps": 4222156799, "loss": 0.016570571810007095, "avg_return": 0.8638039231300354, "regret": 0.001659441040828824, "entropy": 0.09073690325021744, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:00.923479Z", "loop": 6872, "env_steps": 4222771199, "loss": 0.016341708600521088, "avg_return": 0.8621273040771484, "regret": 0.001659441040828824, "entropy": 0.08827443420886993, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:01.779555Z", "loop": 6873, "env_steps": 4223385599, "loss": 0.016563696786761284, "avg_return": 0.8616235852241516, "regret": 0.001659441040828824, "entropy": 0.08936086297035217, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:02.634061Z", "loop": 6874, "env_steps": 4223999999, "loss": 0.015023562125861645, "avg_return": 0.862835705280304, "regret": 0.001659441040828824, "entropy": 0.0883878767490387, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:03.488492Z", "loop": 6875, "env_steps": 4224614399, "loss": 0.015026633627712727, "avg_return": 0.8644859194755554, "regret": 0.001659441040828824, "entropy": 0.08368562161922455, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:04.343924Z", "loop": 6876, "env_steps": 4225228799, "loss": 0.014638674445450306, "avg_return": 0.8618664741516113, "regret": 0.001659441040828824, "entropy": 0.08103114366531372, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:05.199883Z", "loop": 6877, "env_steps": 4225843199, "loss": 0.014834626577794552, "avg_return": 0.8623364567756653, "regret": 0.001659441040828824, "entropy": 0.0809660404920578, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:06.054806Z", "loop": 6878, "env_steps": 4226457599, "loss": 0.014706628397107124, "avg_return": 0.8613733053207397, "regret": 0.001659441040828824, "entropy": 0.08224746584892273, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:06.909815Z", "loop": 6879, "env_steps": 4227071999, "loss": 0.015776388347148895, "avg_return": 0.8612292408943176, "regret": 0.001659441040828824, "entropy": 0.08659902960062027, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:07.803715Z", "loop": 6880, "env_steps": 4227686399, "loss": 0.014580880291759968, "avg_return": 0.8628477454185486, "regret": 0.0008768411935307086, "entropy": 0.08099022507667542, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:08.661045Z", "loop": 6881, "env_steps": 4228300799, "loss": 0.014360377565026283, "avg_return": 0.861581027507782, "regret": 0.0008768411935307086, "entropy": 0.08064994215965271, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:09.517216Z", "loop": 6882, "env_steps": 4228915199, "loss": 0.01415362861007452, "avg_return": 0.8630478382110596, "regret": 0.0008768411935307086, "entropy": 0.0800764262676239, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:10.372363Z", "loop": 6883, "env_steps": 4229529599, "loss": 0.014567377977073193, "avg_return": 0.8633556365966797, "regret": 0.0008768411935307086, "entropy": 0.08003140985965729, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:11.228353Z", "loop": 6884, "env_steps": 4230143999, "loss": 0.014973118901252747, "avg_return": 0.8617792725563049, "regret": 0.0008768411935307086, "entropy": 0.08211404085159302, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:12.085734Z", "loop": 6885, "env_steps": 4230758399, "loss": 0.014941813424229622, "avg_return": 0.8618003726005554, "regret": 0.0008768411935307086, "entropy": 0.08269773423671722, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:12.943414Z", "loop": 6886, "env_steps": 4231372799, "loss": 0.015515456907451153, "avg_return": 0.862403392791748, "regret": 0.0008768411935307086, "entropy": 0.08484102040529251, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:13.799873Z", "loop": 6887, "env_steps": 4231987199, "loss": 0.01446333434432745, "avg_return": 0.8619252443313599, "regret": 0.0008768411935307086, "entropy": 0.08227617293596268, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:14.654809Z", "loop": 6888, "env_steps": 4232601599, "loss": 0.015078241936862469, "avg_return": 0.8624737858772278, "regret": 0.0008768411935307086, "entropy": 0.08149013668298721, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:15.511252Z", "loop": 6889, "env_steps": 4233215999, "loss": 0.01465130876749754, "avg_return": 0.8622409105300903, "regret": 0.0008768411935307086, "entropy": 0.08663603663444519, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:16.410459Z", "loop": 6890, "env_steps": 4233830399, "loss": 0.013698338530957699, "avg_return": 0.8626542091369629, "regret": 0.00090739008737728, "entropy": 0.07704073935747147, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:17.266528Z", "loop": 6891, "env_steps": 4234444799, "loss": 0.013367136009037495, "avg_return": 0.862320065498352, "regret": 0.00090739008737728, "entropy": 0.07720969617366791, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:18.122237Z", "loop": 6892, "env_steps": 4235059199, "loss": 0.014619654975831509, "avg_return": 0.8626590371131897, "regret": 0.00090739008737728, "entropy": 0.0817730650305748, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:18.978544Z", "loop": 6893, "env_steps": 4235673599, "loss": 0.015023802407085896, "avg_return": 0.8621614575386047, "regret": 0.00090739008737728, "entropy": 0.08216816931962967, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:19.835341Z", "loop": 6894, "env_steps": 4236287999, "loss": 0.014352576807141304, "avg_return": 0.8623514771461487, "regret": 0.00090739008737728, "entropy": 0.08092346787452698, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:20.691290Z", "loop": 6895, "env_steps": 4236902399, "loss": 0.014546682126820087, "avg_return": 0.8633618354797363, "regret": 0.00090739008737728, "entropy": 0.07793094962835312, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:21.546986Z", "loop": 6896, "env_steps": 4237516799, "loss": 0.015348166227340698, "avg_return": 0.8625068068504333, "regret": 0.00090739008737728, "entropy": 0.08503688871860504, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:22.403235Z", "loop": 6897, "env_steps": 4238131199, "loss": 0.014001351781189442, "avg_return": 0.8622565865516663, "regret": 0.00090739008737728, "entropy": 0.0820515975356102, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:23.258537Z", "loop": 6898, "env_steps": 4238745599, "loss": 0.014683005400002003, "avg_return": 0.8622782826423645, "regret": 0.00090739008737728, "entropy": 0.0806984156370163, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:24.113606Z", "loop": 6899, "env_steps": 4239359999, "loss": 0.014164215885102749, "avg_return": 0.8627137541770935, "regret": 0.00090739008737728, "entropy": 0.07952353358268738, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:25.010640Z", "loop": 6900, "env_steps": 4239974399, "loss": 0.01463236566632986, "avg_return": 0.8623199462890625, "regret": 0.0010107419220730662, "entropy": 0.08110109716653824, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:25.867058Z", "loop": 6901, "env_steps": 4240588799, "loss": 0.013916661031544209, "avg_return": 0.8627719283103943, "regret": 0.0010107419220730662, "entropy": 0.0805068090558052, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:26.721380Z", "loop": 6902, "env_steps": 4241203199, "loss": 0.01454561110585928, "avg_return": 0.8622118234634399, "regret": 0.0010107419220730662, "entropy": 0.07982693612575531, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:27.575722Z", "loop": 6903, "env_steps": 4241817599, "loss": 0.014056137762963772, "avg_return": 0.8627634644508362, "regret": 0.0010107419220730662, "entropy": 0.08055321872234344, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:28.431212Z", "loop": 6904, "env_steps": 4242431999, "loss": 0.014222580008208752, "avg_return": 0.8625063300132751, "regret": 0.0010107419220730662, "entropy": 0.07912278920412064, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:29.288264Z", "loop": 6905, "env_steps": 4243046399, "loss": 0.014812505804002285, "avg_return": 0.8628674745559692, "regret": 0.0010107419220730662, "entropy": 0.08080203086137772, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:30.143369Z", "loop": 6906, "env_steps": 4243660799, "loss": 0.014557860791683197, "avg_return": 0.8625822067260742, "regret": 0.0010107419220730662, "entropy": 0.0789325013756752, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:30.998586Z", "loop": 6907, "env_steps": 4244275199, "loss": 0.015876244753599167, "avg_return": 0.8631109595298767, "regret": 0.0010107419220730662, "entropy": 0.08602602034807205, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:31.853752Z", "loop": 6908, "env_steps": 4244889599, "loss": 0.014553490094840527, "avg_return": 0.8624916672706604, "regret": 0.0010107419220730662, "entropy": 0.07992825657129288, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:32.709311Z", "loop": 6909, "env_steps": 4245503999, "loss": 0.015009770169854164, "avg_return": 0.8617993593215942, "regret": 0.0010107419220730662, "entropy": 0.07959936559200287, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:33.604963Z", "loop": 6910, "env_steps": 4246118399, "loss": 0.01444205828011036, "avg_return": 0.8641384840011597, "regret": 0.0006701719830743968, "entropy": 0.07872361689805984, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:34.460175Z", "loop": 6911, "env_steps": 4246732799, "loss": 0.01396770030260086, "avg_return": 0.863216757774353, "regret": 0.0006701719830743968, "entropy": 0.08050750195980072, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:35.315322Z", "loop": 6912, "env_steps": 4247347199, "loss": 0.015062771737575531, "avg_return": 0.8636189103126526, "regret": 0.0006701719830743968, "entropy": 0.08341718465089798, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:36.171280Z", "loop": 6913, "env_steps": 4247961599, "loss": 0.01400744915008545, "avg_return": 0.8633648753166199, "regret": 0.0006701719830743968, "entropy": 0.07920322567224503, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:37.027107Z", "loop": 6914, "env_steps": 4248575999, "loss": 0.013663274236023426, "avg_return": 0.862659215927124, "regret": 0.0006701719830743968, "entropy": 0.07761379331350327, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:37.881536Z", "loop": 6915, "env_steps": 4249190399, "loss": 0.014062942937016487, "avg_return": 0.8627838492393494, "regret": 0.0006701719830743968, "entropy": 0.08002647012472153, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:38.736542Z", "loop": 6916, "env_steps": 4249804799, "loss": 0.014229695312678814, "avg_return": 0.8630216717720032, "regret": 0.0006701719830743968, "entropy": 0.0824018195271492, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:39.592028Z", "loop": 6917, "env_steps": 4250419199, "loss": 0.014634904451668262, "avg_return": 0.8631683588027954, "regret": 0.0006701719830743968, "entropy": 0.08101637661457062, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:40.447780Z", "loop": 6918, "env_steps": 4251033599, "loss": 0.0156706590205431, "avg_return": 0.862902045249939, "regret": 0.0006701719830743968, "entropy": 0.08447974920272827, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:41.303482Z", "loop": 6919, "env_steps": 4251647999, "loss": 0.01501410361379385, "avg_return": 0.8616991639137268, "regret": 0.0006701719830743968, "entropy": 0.08376993983983994, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:42.198341Z", "loop": 6920, "env_steps": 4252262399, "loss": 0.015978315845131874, "avg_return": 0.8623389005661011, "regret": 0.0007573440088890493, "entropy": 0.08463820070028305, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:43.053596Z", "loop": 6921, "env_steps": 4252876799, "loss": 0.01416922640055418, "avg_return": 0.861711323261261, "regret": 0.0007573440088890493, "entropy": 0.0819597914814949, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:43.909533Z", "loop": 6922, "env_steps": 4253491199, "loss": 0.014829225838184357, "avg_return": 0.8626701235771179, "regret": 0.0007573440088890493, "entropy": 0.08468688279390335, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:44.764498Z", "loop": 6923, "env_steps": 4254105599, "loss": 0.015012266114354134, "avg_return": 0.8614251017570496, "regret": 0.0007573440088890493, "entropy": 0.08744022250175476, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:45.619280Z", "loop": 6924, "env_steps": 4254719999, "loss": 0.01430665422230959, "avg_return": 0.862616777420044, "regret": 0.0007573440088890493, "entropy": 0.0802304819226265, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:46.475481Z", "loop": 6925, "env_steps": 4255334399, "loss": 0.015351816080510616, "avg_return": 0.861642062664032, "regret": 0.0007573440088890493, "entropy": 0.08666738122701645, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:47.331325Z", "loop": 6926, "env_steps": 4255948799, "loss": 0.015027515590190887, "avg_return": 0.8621639013290405, "regret": 0.0007573440088890493, "entropy": 0.0860779732465744, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:48.186927Z", "loop": 6927, "env_steps": 4256563199, "loss": 0.016074301674962044, "avg_return": 0.860365092754364, "regret": 0.0007573440088890493, "entropy": 0.08815894275903702, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:49.042798Z", "loop": 6928, "env_steps": 4257177599, "loss": 0.015912670642137527, "avg_return": 0.862715482711792, "regret": 0.0007573440088890493, "entropy": 0.08973342925310135, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:49.897578Z", "loop": 6929, "env_steps": 4257791999, "loss": 0.017284201458096504, "avg_return": 0.8610308766365051, "regret": 0.0007573440088890493, "entropy": 0.09068763256072998, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:50.792630Z", "loop": 6930, "env_steps": 4258406399, "loss": 0.015630176290869713, "avg_return": 0.8616144061088562, "regret": 0.0024118113797158003, "entropy": 0.08559121191501617, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:51.647745Z", "loop": 6931, "env_steps": 4259020799, "loss": 0.01692749373614788, "avg_return": 0.8612172603607178, "regret": 0.0024118113797158003, "entropy": 0.09386814385652542, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:52.503295Z", "loop": 6932, "env_steps": 4259635199, "loss": 0.015326986089348793, "avg_return": 0.8614367842674255, "regret": 0.0024118113797158003, "entropy": 0.08832701295614243, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:53.359266Z", "loop": 6933, "env_steps": 4260249599, "loss": 0.015629542991518974, "avg_return": 0.8622798919677734, "regret": 0.0024118113797158003, "entropy": 0.08867772668600082, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:54.214801Z", "loop": 6934, "env_steps": 4260863999, "loss": 0.01530738826841116, "avg_return": 0.8617130517959595, "regret": 0.0024118113797158003, "entropy": 0.08234048634767532, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:55.071218Z", "loop": 6935, "env_steps": 4261478399, "loss": 0.014167877845466137, "avg_return": 0.862301230430603, "regret": 0.0024118113797158003, "entropy": 0.07871868461370468, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:55.927574Z", "loop": 6936, "env_steps": 4262092799, "loss": 0.014957129955291748, "avg_return": 0.8622610569000244, "regret": 0.0024118113797158003, "entropy": 0.08191077411174774, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:56.784845Z", "loop": 6937, "env_steps": 4262707199, "loss": 0.015436914749443531, "avg_return": 0.8622986078262329, "regret": 0.0024118113797158003, "entropy": 0.0839625895023346, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:57.640158Z", "loop": 6938, "env_steps": 4263321599, "loss": 0.015909241512417793, "avg_return": 0.8615818619728088, "regret": 0.0024118113797158003, "entropy": 0.08436162024736404, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:58.495430Z", "loop": 6939, "env_steps": 4263935999, "loss": 0.01621720753610134, "avg_return": 0.8615779876708984, "regret": 0.0024118113797158003, "entropy": 0.08544258028268814, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:02:59.391347Z", "loop": 6940, "env_steps": 4264550399, "loss": 0.014992055483162403, "avg_return": 0.8626263737678528, "regret": 0.0019505827222019434, "entropy": 0.08526697009801865, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:00.248247Z", "loop": 6941, "env_steps": 4265164799, "loss": 0.014819378964602947, "avg_return": 0.8616151213645935, "regret": 0.0019505827222019434, "entropy": 0.08579730987548828, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:01.103873Z", "loop": 6942, "env_steps": 4265779199, "loss": 0.015402252785861492, "avg_return": 0.8615094423294067, "regret": 0.0019505827222019434, "entropy": 0.08554869145154953, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:01.959561Z", "loop": 6943, "env_steps": 4266393599, "loss": 0.01568857952952385, "avg_return": 0.8606750965118408, "regret": 0.0019505827222019434, "entropy": 0.08811178803443909, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:02.816043Z", "loop": 6944, "env_steps": 4267007999, "loss": 0.01708979718387127, "avg_return": 0.862294614315033, "regret": 0.0019505827222019434, "entropy": 0.0930732786655426, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:03.671399Z", "loop": 6945, "env_steps": 4267622399, "loss": 0.017618009820580482, "avg_return": 0.860008180141449, "regret": 0.0019505827222019434, "entropy": 0.09750814735889435, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:04.526630Z", "loop": 6946, "env_steps": 4268236799, "loss": 0.016683651134371758, "avg_return": 0.8595154285430908, "regret": 0.0019505827222019434, "entropy": 0.0972452387213707, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:05.381335Z", "loop": 6947, "env_steps": 4268851199, "loss": 0.018068214878439903, "avg_return": 0.8592588305473328, "regret": 0.0019505827222019434, "entropy": 0.09875034540891647, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:06.235959Z", "loop": 6948, "env_steps": 4269465599, "loss": 0.01734987460076809, "avg_return": 0.8607553243637085, "regret": 0.0019505827222019434, "entropy": 0.09575951099395752, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:07.091053Z", "loop": 6949, "env_steps": 4270079999, "loss": 0.016149355098605156, "avg_return": 0.8613589406013489, "regret": 0.0019505827222019434, "entropy": 0.09384885430335999, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:07.987959Z", "loop": 6950, "env_steps": 4270694399, "loss": 0.01679089106619358, "avg_return": 0.8626157641410828, "regret": 0.0017928022425621748, "entropy": 0.09152039885520935, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:08.842943Z", "loop": 6951, "env_steps": 4271308799, "loss": 0.016150278970599174, "avg_return": 0.8627323508262634, "regret": 0.0017928022425621748, "entropy": 0.09029586613178253, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:09.698620Z", "loop": 6952, "env_steps": 4271923199, "loss": 0.014877066016197205, "avg_return": 0.8628214001655579, "regret": 0.0017928022425621748, "entropy": 0.08691415935754776, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:10.554703Z", "loop": 6953, "env_steps": 4272537599, "loss": 0.01464243233203888, "avg_return": 0.862650990486145, "regret": 0.0017928022425621748, "entropy": 0.08094369620084763, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:11.410320Z", "loop": 6954, "env_steps": 4273151999, "loss": 0.015663469210267067, "avg_return": 0.8619705438613892, "regret": 0.0017928022425621748, "entropy": 0.08588986098766327, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:12.266556Z", "loop": 6955, "env_steps": 4273766399, "loss": 0.015529450960457325, "avg_return": 0.8608694672584534, "regret": 0.0017928022425621748, "entropy": 0.08694586902856827, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:13.123168Z", "loop": 6956, "env_steps": 4274380799, "loss": 0.014944112859666348, "avg_return": 0.8628100752830505, "regret": 0.0017928022425621748, "entropy": 0.08035863935947418, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:13.978571Z", "loop": 6957, "env_steps": 4274995199, "loss": 0.014622891321778297, "avg_return": 0.8633660078048706, "regret": 0.0017928022425621748, "entropy": 0.07953710854053497, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:14.835773Z", "loop": 6958, "env_steps": 4275609599, "loss": 0.014255634509027004, "avg_return": 0.8623160123825073, "regret": 0.0017928022425621748, "entropy": 0.08071261644363403, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:15.692204Z", "loop": 6959, "env_steps": 4276223999, "loss": 0.014856128953397274, "avg_return": 0.8609627485275269, "regret": 0.0017928022425621748, "entropy": 0.0820886492729187, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:16.588770Z", "loop": 6960, "env_steps": 4276838399, "loss": 0.014585347846150398, "avg_return": 0.8609446287155151, "regret": 0.0019409290980547667, "entropy": 0.08130396157503128, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:17.443255Z", "loop": 6961, "env_steps": 4277452799, "loss": 0.015504819341003895, "avg_return": 0.860697865486145, "regret": 0.0019409290980547667, "entropy": 0.08651517331600189, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:18.296997Z", "loop": 6962, "env_steps": 4278067199, "loss": 0.015661044046282768, "avg_return": 0.8604937791824341, "regret": 0.0019409290980547667, "entropy": 0.08664467185735703, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:19.153129Z", "loop": 6963, "env_steps": 4278681599, "loss": 0.016736319288611412, "avg_return": 0.8607707023620605, "regret": 0.0019409290980547667, "entropy": 0.09106425940990448, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:20.009627Z", "loop": 6964, "env_steps": 4279295999, "loss": 0.01623392663896084, "avg_return": 0.8601381778717041, "regret": 0.0019409290980547667, "entropy": 0.08927766978740692, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:20.865536Z", "loop": 6965, "env_steps": 4279910399, "loss": 0.015022031031548977, "avg_return": 0.8601583242416382, "regret": 0.0019409290980547667, "entropy": 0.0811227411031723, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:21.722346Z", "loop": 6966, "env_steps": 4280524799, "loss": 0.01475268043577671, "avg_return": 0.8609427809715271, "regret": 0.0019409290980547667, "entropy": 0.08370841294527054, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:22.577224Z", "loop": 6967, "env_steps": 4281139199, "loss": 0.015453352592885494, "avg_return": 0.8579778075218201, "regret": 0.0019409290980547667, "entropy": 0.08443273603916168, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:23.433248Z", "loop": 6968, "env_steps": 4281753599, "loss": 0.01601794920861721, "avg_return": 0.8619659543037415, "regret": 0.0019409290980547667, "entropy": 0.08571363240480423, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:24.288919Z", "loop": 6969, "env_steps": 4282367999, "loss": 0.013761147856712341, "avg_return": 0.8604292869567871, "regret": 0.0019409290980547667, "entropy": 0.07986265420913696, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:25.183940Z", "loop": 6970, "env_steps": 4282982399, "loss": 0.015879979357123375, "avg_return": 0.8608587980270386, "regret": 0.0026367383543401957, "entropy": 0.08498241752386093, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:26.039513Z", "loop": 6971, "env_steps": 4283596799, "loss": 0.014605732634663582, "avg_return": 0.8615765571594238, "regret": 0.0026367383543401957, "entropy": 0.07871673256158829, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:26.896029Z", "loop": 6972, "env_steps": 4284211199, "loss": 0.014427845366299152, "avg_return": 0.8605294227600098, "regret": 0.0026367383543401957, "entropy": 0.0792139396071434, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:27.752499Z", "loop": 6973, "env_steps": 4284825599, "loss": 0.013808073475956917, "avg_return": 0.8619328737258911, "regret": 0.0026367383543401957, "entropy": 0.07873300462961197, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:28.609300Z", "loop": 6974, "env_steps": 4285439999, "loss": 0.014774543233215809, "avg_return": 0.8623180389404297, "regret": 0.0026367383543401957, "entropy": 0.08183214068412781, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:29.466050Z", "loop": 6975, "env_steps": 4286054399, "loss": 0.015247995033860207, "avg_return": 0.8618543744087219, "regret": 0.0026367383543401957, "entropy": 0.08390460163354874, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:30.320755Z", "loop": 6976, "env_steps": 4286668799, "loss": 0.014330001547932625, "avg_return": 0.8628725409507751, "regret": 0.0026367383543401957, "entropy": 0.07962197065353394, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:31.176486Z", "loop": 6977, "env_steps": 4287283199, "loss": 0.014297428540885448, "avg_return": 0.8640848994255066, "regret": 0.0026367383543401957, "entropy": 0.08001869916915894, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:32.032134Z", "loop": 6978, "env_steps": 4287897599, "loss": 0.014654791913926601, "avg_return": 0.8623374700546265, "regret": 0.0026367383543401957, "entropy": 0.08069873601198196, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:32.887095Z", "loop": 6979, "env_steps": 4288511999, "loss": 0.013983477838337421, "avg_return": 0.8637192845344543, "regret": 0.0026367383543401957, "entropy": 0.0770258754491806, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:33.783651Z", "loop": 6980, "env_steps": 4289126399, "loss": 0.01545021217316389, "avg_return": 0.8619043231010437, "regret": 0.0005968853947706521, "entropy": 0.084012970328331, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:34.639197Z", "loop": 6981, "env_steps": 4289740799, "loss": 0.014104180037975311, "avg_return": 0.8636963963508606, "regret": 0.0005968853947706521, "entropy": 0.08233051747083664, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:35.495838Z", "loop": 6982, "env_steps": 4290355199, "loss": 0.01484112348407507, "avg_return": 0.8633848428726196, "regret": 0.0005968853947706521, "entropy": 0.08169057220220566, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:36.351392Z", "loop": 6983, "env_steps": 4290969599, "loss": 0.014472139067947865, "avg_return": 0.8636336326599121, "regret": 0.0005968853947706521, "entropy": 0.08193822205066681, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:37.206865Z", "loop": 6984, "env_steps": 4291583999, "loss": 0.015069297514855862, "avg_return": 0.8621267080307007, "regret": 0.0005968853947706521, "entropy": 0.08242019265890121, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:38.063443Z", "loop": 6985, "env_steps": 4292198399, "loss": 0.014857101254165173, "avg_return": 0.8615900874137878, "regret": 0.0005968853947706521, "entropy": 0.08427920937538147, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:38.919339Z", "loop": 6986, "env_steps": 4292812799, "loss": 0.014972602017223835, "avg_return": 0.8630978465080261, "regret": 0.0005968853947706521, "entropy": 0.08216143399477005, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:39.775101Z", "loop": 6987, "env_steps": 4293427199, "loss": 0.014880499802529812, "avg_return": 0.8621286153793335, "regret": 0.0005968853947706521, "entropy": 0.08139833062887192, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:40.630515Z", "loop": 6988, "env_steps": 4294041599, "loss": 0.014748635701835155, "avg_return": 0.8621654510498047, "regret": 0.0005968853947706521, "entropy": 0.08023007959127426, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:41.485761Z", "loop": 6989, "env_steps": 4294655999, "loss": 0.015249351039528847, "avg_return": 0.8620229363441467, "regret": 0.0005968853947706521, "entropy": 0.08335328847169876, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:42.383987Z", "loop": 6990, "env_steps": 4295270399, "loss": 0.013786518946290016, "avg_return": 0.8634529709815979, "regret": 0.0009643075172789395, "entropy": 0.0794672891497612, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:43.239337Z", "loop": 6991, "env_steps": 4295884799, "loss": 0.013647066429257393, "avg_return": 0.8619758486747742, "regret": 0.0009643075172789395, "entropy": 0.07807419449090958, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:44.095146Z", "loop": 6992, "env_steps": 4296499199, "loss": 0.014949117787182331, "avg_return": 0.8620806932449341, "regret": 0.0009643075172789395, "entropy": 0.08209190517663956, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:44.949937Z", "loop": 6993, "env_steps": 4297113599, "loss": 0.015466091223061085, "avg_return": 0.8633513450622559, "regret": 0.0009643075172789395, "entropy": 0.08810015022754669, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:45.805139Z", "loop": 6994, "env_steps": 4297727999, "loss": 0.01504876371473074, "avg_return": 0.8615399599075317, "regret": 0.0009643075172789395, "entropy": 0.08314000070095062, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:46.660896Z", "loop": 6995, "env_steps": 4298342399, "loss": 0.015340501442551613, "avg_return": 0.862585186958313, "regret": 0.0009643075172789395, "entropy": 0.08558762073516846, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:47.517081Z", "loop": 6996, "env_steps": 4298956799, "loss": 0.014535591006278992, "avg_return": 0.8635618090629578, "regret": 0.0009643075172789395, "entropy": 0.07833333313465118, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:48.372169Z", "loop": 6997, "env_steps": 4299571199, "loss": 0.014771565794944763, "avg_return": 0.8628101944923401, "regret": 0.0009643075172789395, "entropy": 0.0817936435341835, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:49.228490Z", "loop": 6998, "env_steps": 4300185599, "loss": 0.015355429612100124, "avg_return": 0.8623799681663513, "regret": 0.0009643075172789395, "entropy": 0.08472731709480286, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:50.084692Z", "loop": 6999, "env_steps": 4300799999, "loss": 0.01430441439151764, "avg_return": 0.8619372844696045, "regret": 0.0009643075172789395, "entropy": 0.07677943259477615, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:50.981614Z", "loop": 7000, "env_steps": 4301414399, "loss": 0.015087149105966091, "avg_return": 0.8612454533576965, "regret": 0.001473197597078979, "entropy": 0.08274468034505844, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:51.837841Z", "loop": 7001, "env_steps": 4302028799, "loss": 0.015093582682311535, "avg_return": 0.8627653121948242, "regret": 0.001473197597078979, "entropy": 0.08150883764028549, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:52.692773Z", "loop": 7002, "env_steps": 4302643199, "loss": 0.015285897068679333, "avg_return": 0.8627185225486755, "regret": 0.001473197597078979, "entropy": 0.08280298113822937, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:53.547735Z", "loop": 7003, "env_steps": 4303257599, "loss": 0.01570883020758629, "avg_return": 0.8628666400909424, "regret": 0.001473197597078979, "entropy": 0.08329398185014725, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:54.403270Z", "loop": 7004, "env_steps": 4303871999, "loss": 0.014279578812420368, "avg_return": 0.8635439276695251, "regret": 0.001473197597078979, "entropy": 0.07827731966972351, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:55.258355Z", "loop": 7005, "env_steps": 4304486399, "loss": 0.01498135644942522, "avg_return": 0.8618450164794922, "regret": 0.001473197597078979, "entropy": 0.08075825870037079, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:56.112919Z", "loop": 7006, "env_steps": 4305100799, "loss": 0.013390357606112957, "avg_return": 0.8608382344245911, "regret": 0.001473197597078979, "entropy": 0.07769208401441574, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:56.968413Z", "loop": 7007, "env_steps": 4305715199, "loss": 0.01370125263929367, "avg_return": 0.8624536395072937, "regret": 0.001473197597078979, "entropy": 0.07809608429670334, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:57.824613Z", "loop": 7008, "env_steps": 4306329599, "loss": 0.014630364254117012, "avg_return": 0.8607239127159119, "regret": 0.001473197597078979, "entropy": 0.08317989856004715, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:58.680202Z", "loop": 7009, "env_steps": 4306943999, "loss": 0.014386670663952827, "avg_return": 0.8629191517829895, "regret": 0.001473197597078979, "entropy": 0.07883963733911514, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:03:59.575650Z", "loop": 7010, "env_steps": 4307558399, "loss": 0.014592193067073822, "avg_return": 0.8614354729652405, "regret": 0.001229127636179328, "entropy": 0.07979278266429901, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:00.431120Z", "loop": 7011, "env_steps": 4308172799, "loss": 0.014223511330783367, "avg_return": 0.8625256419181824, "regret": 0.001229127636179328, "entropy": 0.07973042130470276, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:01.285775Z", "loop": 7012, "env_steps": 4308787199, "loss": 0.013865371234714985, "avg_return": 0.8613260388374329, "regret": 0.001229127636179328, "entropy": 0.07464122027158737, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:02.141202Z", "loop": 7013, "env_steps": 4309401599, "loss": 0.014338056556880474, "avg_return": 0.8622199892997742, "regret": 0.001229127636179328, "entropy": 0.07828909903764725, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:02.996887Z", "loop": 7014, "env_steps": 4310015999, "loss": 0.01436684187501669, "avg_return": 0.8614628314971924, "regret": 0.001229127636179328, "entropy": 0.08380286395549774, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:03.852069Z", "loop": 7015, "env_steps": 4310630399, "loss": 0.014974928461015224, "avg_return": 0.8635688424110413, "regret": 0.001229127636179328, "entropy": 0.08448831737041473, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:04.706479Z", "loop": 7016, "env_steps": 4311244799, "loss": 0.013988964259624481, "avg_return": 0.8629736304283142, "regret": 0.001229127636179328, "entropy": 0.08109598606824875, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:05.561261Z", "loop": 7017, "env_steps": 4311859199, "loss": 0.015077220275998116, "avg_return": 0.8626566529273987, "regret": 0.001229127636179328, "entropy": 0.08568041771650314, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:06.415660Z", "loop": 7018, "env_steps": 4312473599, "loss": 0.014822687022387981, "avg_return": 0.8634188175201416, "regret": 0.001229127636179328, "entropy": 0.08163374662399292, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:07.271417Z", "loop": 7019, "env_steps": 4313087999, "loss": 0.015151843428611755, "avg_return": 0.8615977168083191, "regret": 0.001229127636179328, "entropy": 0.08357658237218857, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:08.166751Z", "loop": 7020, "env_steps": 4313702399, "loss": 0.014720414765179157, "avg_return": 0.8618579506874084, "regret": 0.0013416860019788146, "entropy": 0.08181560784578323, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:09.022064Z", "loop": 7021, "env_steps": 4314316799, "loss": 0.015253886580467224, "avg_return": 0.8618548512458801, "regret": 0.0013416860019788146, "entropy": 0.08447258174419403, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:09.877439Z", "loop": 7022, "env_steps": 4314931199, "loss": 0.01586020737886429, "avg_return": 0.8621793985366821, "regret": 0.0013416860019788146, "entropy": 0.084435373544693, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:10.733665Z", "loop": 7023, "env_steps": 4315545599, "loss": 0.01525583304464817, "avg_return": 0.8621159791946411, "regret": 0.0013416860019788146, "entropy": 0.08575135469436646, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:11.589046Z", "loop": 7024, "env_steps": 4316159999, "loss": 0.015560354106128216, "avg_return": 0.8625879287719727, "regret": 0.0013416860019788146, "entropy": 0.08302989602088928, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:12.444080Z", "loop": 7025, "env_steps": 4316774399, "loss": 0.015047122724354267, "avg_return": 0.86175537109375, "regret": 0.0013416860019788146, "entropy": 0.08567553758621216, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:13.298834Z", "loop": 7026, "env_steps": 4317388799, "loss": 0.01606927439570427, "avg_return": 0.8622280359268188, "regret": 0.0013416860019788146, "entropy": 0.09219129383563995, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:14.155250Z", "loop": 7027, "env_steps": 4318003199, "loss": 0.0168480034917593, "avg_return": 0.8628348708152771, "regret": 0.0013416860019788146, "entropy": 0.09382657706737518, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:15.011712Z", "loop": 7028, "env_steps": 4318617599, "loss": 0.01706322282552719, "avg_return": 0.8610268235206604, "regret": 0.0013416860019788146, "entropy": 0.0959009900689125, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:15.866185Z", "loop": 7029, "env_steps": 4319231999, "loss": 0.01785510778427124, "avg_return": 0.8603782057762146, "regret": 0.0013416860019788146, "entropy": 0.09780826419591904, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:16.760800Z", "loop": 7030, "env_steps": 4319846399, "loss": 0.019214168190956116, "avg_return": 0.86081862449646, "regret": 0.00319743063300848, "entropy": 0.10574466735124588, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:17.616742Z", "loop": 7031, "env_steps": 4320460799, "loss": 0.018228702247142792, "avg_return": 0.8602549433708191, "regret": 0.00319743063300848, "entropy": 0.10614398866891861, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:18.472576Z", "loop": 7032, "env_steps": 4321075199, "loss": 0.01891455613076687, "avg_return": 0.8600529432296753, "regret": 0.00319743063300848, "entropy": 0.10727047920227051, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:19.328961Z", "loop": 7033, "env_steps": 4321689599, "loss": 0.017495905980467796, "avg_return": 0.8612319231033325, "regret": 0.00319743063300848, "entropy": 0.10264133661985397, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:20.183220Z", "loop": 7034, "env_steps": 4322303999, "loss": 0.01741177774965763, "avg_return": 0.8610333204269409, "regret": 0.00319743063300848, "entropy": 0.10097028315067291, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:21.038046Z", "loop": 7035, "env_steps": 4322918399, "loss": 0.017360389232635498, "avg_return": 0.8618576526641846, "regret": 0.00319743063300848, "entropy": 0.09939960390329361, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:21.893641Z", "loop": 7036, "env_steps": 4323532799, "loss": 0.015647342428565025, "avg_return": 0.8615111708641052, "regret": 0.00319743063300848, "entropy": 0.09211087971925735, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:22.748345Z", "loop": 7037, "env_steps": 4324147199, "loss": 0.016858462244272232, "avg_return": 0.8630983829498291, "regret": 0.00319743063300848, "entropy": 0.09141823649406433, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:23.603346Z", "loop": 7038, "env_steps": 4324761599, "loss": 0.016427984461188316, "avg_return": 0.8611633777618408, "regret": 0.00319743063300848, "entropy": 0.09601721912622452, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:24.460152Z", "loop": 7039, "env_steps": 4325375999, "loss": 0.01713954657316208, "avg_return": 0.8613991737365723, "regret": 0.00319743063300848, "entropy": 0.09324327856302261, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:25.355395Z", "loop": 7040, "env_steps": 4325990399, "loss": 0.018296530470252037, "avg_return": 0.8630822896957397, "regret": 0.0019236297812312841, "entropy": 0.09851033240556717, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:26.211377Z", "loop": 7041, "env_steps": 4326604799, "loss": 0.01645740121603012, "avg_return": 0.8614585399627686, "regret": 0.0019236297812312841, "entropy": 0.09000200033187866, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:27.068648Z", "loop": 7042, "env_steps": 4327219199, "loss": 0.016622690483927727, "avg_return": 0.8618971109390259, "regret": 0.0019236297812312841, "entropy": 0.0973479151725769, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:27.925266Z", "loop": 7043, "env_steps": 4327833599, "loss": 0.017205841839313507, "avg_return": 0.8609849214553833, "regret": 0.0019236297812312841, "entropy": 0.09496136009693146, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:28.781496Z", "loop": 7044, "env_steps": 4328447999, "loss": 0.016919709742069244, "avg_return": 0.8623409271240234, "regret": 0.0019236297812312841, "entropy": 0.09591050446033478, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:29.636454Z", "loop": 7045, "env_steps": 4329062399, "loss": 0.016724683344364166, "avg_return": 0.8610278367996216, "regret": 0.0019236297812312841, "entropy": 0.09314953535795212, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:30.491271Z", "loop": 7046, "env_steps": 4329676799, "loss": 0.015797972679138184, "avg_return": 0.8609188199043274, "regret": 0.0019236297812312841, "entropy": 0.09084150195121765, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:31.346967Z", "loop": 7047, "env_steps": 4330291199, "loss": 0.01600359007716179, "avg_return": 0.8629583716392517, "regret": 0.0019236297812312841, "entropy": 0.09104590862989426, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:32.202754Z", "loop": 7048, "env_steps": 4330905599, "loss": 0.015630168840289116, "avg_return": 0.8607391715049744, "regret": 0.0019236297812312841, "entropy": 0.09119421988725662, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:33.059693Z", "loop": 7049, "env_steps": 4331519999, "loss": 0.016960667446255684, "avg_return": 0.8620596528053284, "regret": 0.0019236297812312841, "entropy": 0.09601717442274094, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:33.956992Z", "loop": 7050, "env_steps": 4332134399, "loss": 0.017012523487210274, "avg_return": 0.8621719479560852, "regret": 0.0017670794622972608, "entropy": 0.09768427908420563, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:34.813437Z", "loop": 7051, "env_steps": 4332748799, "loss": 0.01613827794790268, "avg_return": 0.8625820279121399, "regret": 0.0017670794622972608, "entropy": 0.09192223846912384, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:35.668516Z", "loop": 7052, "env_steps": 4333363199, "loss": 0.017918212339282036, "avg_return": 0.8625460863113403, "regret": 0.0017670794622972608, "entropy": 0.0991152673959732, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:36.523209Z", "loop": 7053, "env_steps": 4333977599, "loss": 0.01764858327805996, "avg_return": 0.8617532849311829, "regret": 0.0017670794622972608, "entropy": 0.09413409233093262, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:37.378234Z", "loop": 7054, "env_steps": 4334591999, "loss": 0.01736028864979744, "avg_return": 0.8620076775550842, "regret": 0.0017670794622972608, "entropy": 0.09946542233228683, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:38.234594Z", "loop": 7055, "env_steps": 4335206399, "loss": 0.017876213416457176, "avg_return": 0.8609012961387634, "regret": 0.0017670794622972608, "entropy": 0.09130755066871643, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:39.088935Z", "loop": 7056, "env_steps": 4335820799, "loss": 0.0186531450599432, "avg_return": 0.8591803312301636, "regret": 0.0017670794622972608, "entropy": 0.09845496714115143, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:39.943512Z", "loop": 7057, "env_steps": 4336435199, "loss": 0.017880747094750404, "avg_return": 0.8593756556510925, "regret": 0.0017670794622972608, "entropy": 0.09455393999814987, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:40.798380Z", "loop": 7058, "env_steps": 4337049599, "loss": 0.01924438774585724, "avg_return": 0.8583032488822937, "regret": 0.0017670794622972608, "entropy": 0.1002364382147789, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:41.653972Z", "loop": 7059, "env_steps": 4337663999, "loss": 0.018636666238307953, "avg_return": 0.8590149879455566, "regret": 0.0017670794622972608, "entropy": 0.09974157810211182, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:42.549652Z", "loop": 7060, "env_steps": 4338278399, "loss": 0.01902065984904766, "avg_return": 0.8593394160270691, "regret": 0.005125252064317465, "entropy": 0.10097849369049072, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:43.404457Z", "loop": 7061, "env_steps": 4338892799, "loss": 0.017934827134013176, "avg_return": 0.8603424429893494, "regret": 0.005125252064317465, "entropy": 0.09666816890239716, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:44.258706Z", "loop": 7062, "env_steps": 4339507199, "loss": 0.016442155465483665, "avg_return": 0.8611023426055908, "regret": 0.005125252064317465, "entropy": 0.08682017773389816, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:45.114018Z", "loop": 7063, "env_steps": 4340121599, "loss": 0.015269515104591846, "avg_return": 0.862074613571167, "regret": 0.005125252064317465, "entropy": 0.08551588654518127, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:45.969961Z", "loop": 7064, "env_steps": 4340735999, "loss": 0.015564563684165478, "avg_return": 0.8616289496421814, "regret": 0.005125252064317465, "entropy": 0.08432430028915405, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:46.825718Z", "loop": 7065, "env_steps": 4341350399, "loss": 0.014652694575488567, "avg_return": 0.8633089661598206, "regret": 0.005125252064317465, "entropy": 0.07906261086463928, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:47.681938Z", "loop": 7066, "env_steps": 4341964799, "loss": 0.014457419514656067, "avg_return": 0.8619089722633362, "regret": 0.005125252064317465, "entropy": 0.08202613890171051, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:48.536998Z", "loop": 7067, "env_steps": 4342579199, "loss": 0.014614510349929333, "avg_return": 0.8617027997970581, "regret": 0.005125252064317465, "entropy": 0.08270613849163055, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:49.392776Z", "loop": 7068, "env_steps": 4343193599, "loss": 0.01466758456081152, "avg_return": 0.8622336983680725, "regret": 0.005125252064317465, "entropy": 0.08199530094861984, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:50.247922Z", "loop": 7069, "env_steps": 4343807999, "loss": 0.014304064214229584, "avg_return": 0.8629403114318848, "regret": 0.005125252064317465, "entropy": 0.07915014028549194, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:51.144451Z", "loop": 7070, "env_steps": 4344422399, "loss": 0.014503533020615578, "avg_return": 0.8630878925323486, "regret": 0.0012990370159968734, "entropy": 0.07941728085279465, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:52.000097Z", "loop": 7071, "env_steps": 4345036799, "loss": 0.014288472011685371, "avg_return": 0.8630393743515015, "regret": 0.0012990370159968734, "entropy": 0.07466572523117065, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:52.856115Z", "loop": 7072, "env_steps": 4345651199, "loss": 0.015365170314908028, "avg_return": 0.8607704639434814, "regret": 0.0012990370159968734, "entropy": 0.0831279456615448, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:53.712303Z", "loop": 7073, "env_steps": 4346265599, "loss": 0.01458131242543459, "avg_return": 0.8620734810829163, "regret": 0.0012990370159968734, "entropy": 0.07737457007169724, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:54.567612Z", "loop": 7074, "env_steps": 4346879999, "loss": 0.013813394121825695, "avg_return": 0.8636907935142517, "regret": 0.0012990370159968734, "entropy": 0.07549811154603958, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:55.422679Z", "loop": 7075, "env_steps": 4347494399, "loss": 0.014911132864654064, "avg_return": 0.862103283405304, "regret": 0.0012990370159968734, "entropy": 0.07796012610197067, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:56.277947Z", "loop": 7076, "env_steps": 4348108799, "loss": 0.013862043619155884, "avg_return": 0.8614646792411804, "regret": 0.0012990370159968734, "entropy": 0.07783880829811096, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:57.134566Z", "loop": 7077, "env_steps": 4348723199, "loss": 0.013367678038775921, "avg_return": 0.8624727725982666, "regret": 0.0012990370159968734, "entropy": 0.07807908207178116, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:57.991164Z", "loop": 7078, "env_steps": 4349337599, "loss": 0.015398462302982807, "avg_return": 0.8605905175209045, "regret": 0.0012990370159968734, "entropy": 0.08805546909570694, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:58.846732Z", "loop": 7079, "env_steps": 4349951999, "loss": 0.01466467883437872, "avg_return": 0.860787570476532, "regret": 0.0012990370159968734, "entropy": 0.08389516174793243, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:04:59.743403Z", "loop": 7080, "env_steps": 4350566399, "loss": 0.014552163891494274, "avg_return": 0.8627199530601501, "regret": 0.001984938746318221, "entropy": 0.08163448423147202, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:00.599747Z", "loop": 7081, "env_steps": 4351180799, "loss": 0.01410018838942051, "avg_return": 0.8618630170822144, "regret": 0.001984938746318221, "entropy": 0.08079015463590622, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:01.456220Z", "loop": 7082, "env_steps": 4351795199, "loss": 0.01431827712804079, "avg_return": 0.863176703453064, "regret": 0.001984938746318221, "entropy": 0.08038589358329773, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:02.313353Z", "loop": 7083, "env_steps": 4352409599, "loss": 0.014604776166379452, "avg_return": 0.8624818921089172, "regret": 0.001984938746318221, "entropy": 0.07519598305225372, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:03.167957Z", "loop": 7084, "env_steps": 4353023999, "loss": 0.014840777032077312, "avg_return": 0.8632017374038696, "regret": 0.001984938746318221, "entropy": 0.08237942308187485, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:04.022362Z", "loop": 7085, "env_steps": 4353638399, "loss": 0.013213961385190487, "avg_return": 0.862571120262146, "regret": 0.001984938746318221, "entropy": 0.07526784390211105, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:04.878520Z", "loop": 7086, "env_steps": 4354252799, "loss": 0.01378535758703947, "avg_return": 0.8634551167488098, "regret": 0.001984938746318221, "entropy": 0.07397489994764328, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:05.733666Z", "loop": 7087, "env_steps": 4354867199, "loss": 0.014465570449829102, "avg_return": 0.8625590205192566, "regret": 0.001984938746318221, "entropy": 0.07798672467470169, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:06.588619Z", "loop": 7088, "env_steps": 4355481599, "loss": 0.01322128064930439, "avg_return": 0.8624505996704102, "regret": 0.001984938746318221, "entropy": 0.07344948500394821, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:07.443247Z", "loop": 7089, "env_steps": 4356095999, "loss": 0.0153847336769104, "avg_return": 0.8625041842460632, "regret": 0.001984938746318221, "entropy": 0.0839785486459732, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:08.340637Z", "loop": 7090, "env_steps": 4356710399, "loss": 0.01428582239896059, "avg_return": 0.8627036809921265, "regret": 0.0008893622434698045, "entropy": 0.07982414960861206, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:09.197186Z", "loop": 7091, "env_steps": 4357324799, "loss": 0.013348882086575031, "avg_return": 0.8633131384849548, "regret": 0.0008893622434698045, "entropy": 0.07875123620033264, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:10.053883Z", "loop": 7092, "env_steps": 4357939199, "loss": 0.014721731655299664, "avg_return": 0.8625145554542542, "regret": 0.0008893622434698045, "entropy": 0.08061597496271133, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:10.909368Z", "loop": 7093, "env_steps": 4358553599, "loss": 0.014351573772728443, "avg_return": 0.8628199696540833, "regret": 0.0008893622434698045, "entropy": 0.07736268639564514, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:11.765044Z", "loop": 7094, "env_steps": 4359167999, "loss": 0.015133646316826344, "avg_return": 0.8623831272125244, "regret": 0.0008893622434698045, "entropy": 0.08235981315374374, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:12.620271Z", "loop": 7095, "env_steps": 4359782399, "loss": 0.014247344806790352, "avg_return": 0.8605029582977295, "regret": 0.0008893622434698045, "entropy": 0.07821956276893616, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:13.476617Z", "loop": 7096, "env_steps": 4360396799, "loss": 0.015791943296790123, "avg_return": 0.8625438809394836, "regret": 0.0008893622434698045, "entropy": 0.0858968123793602, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:14.333131Z", "loop": 7097, "env_steps": 4361011199, "loss": 0.0144767751917243, "avg_return": 0.8619688153266907, "regret": 0.0008893622434698045, "entropy": 0.0798301249742508, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:15.187866Z", "loop": 7098, "env_steps": 4361625599, "loss": 0.01390730869024992, "avg_return": 0.8631567358970642, "regret": 0.0008893622434698045, "entropy": 0.07992751151323318, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:16.043215Z", "loop": 7099, "env_steps": 4362239999, "loss": 0.01336160209029913, "avg_return": 0.8627312183380127, "regret": 0.0008893622434698045, "entropy": 0.07695408165454865, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:16.937891Z", "loop": 7100, "env_steps": 4362854399, "loss": 0.014121243730187416, "avg_return": 0.862044095993042, "regret": 0.000756132765673101, "entropy": 0.07728232443332672, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:17.793399Z", "loop": 7101, "env_steps": 4363468799, "loss": 0.014934194274246693, "avg_return": 0.8642324805259705, "regret": 0.000756132765673101, "entropy": 0.07934941351413727, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:18.649111Z", "loop": 7102, "env_steps": 4364083199, "loss": 0.0138121098279953, "avg_return": 0.8633697628974915, "regret": 0.000756132765673101, "entropy": 0.07772738486528397, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:19.505463Z", "loop": 7103, "env_steps": 4364697599, "loss": 0.014034152030944824, "avg_return": 0.8637031316757202, "regret": 0.000756132765673101, "entropy": 0.07745889574289322, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:20.361953Z", "loop": 7104, "env_steps": 4365311999, "loss": 0.013705424964427948, "avg_return": 0.8627091646194458, "regret": 0.000756132765673101, "entropy": 0.07701890170574188, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:21.218536Z", "loop": 7105, "env_steps": 4365926399, "loss": 0.014652899466454983, "avg_return": 0.8622165322303772, "regret": 0.000756132765673101, "entropy": 0.08457750827074051, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:22.074045Z", "loop": 7106, "env_steps": 4366540799, "loss": 0.015545378439128399, "avg_return": 0.8633747696876526, "regret": 0.000756132765673101, "entropy": 0.08441151678562164, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:22.930297Z", "loop": 7107, "env_steps": 4367155199, "loss": 0.013442707248032093, "avg_return": 0.8624739050865173, "regret": 0.000756132765673101, "entropy": 0.07793397456407547, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:23.786455Z", "loop": 7108, "env_steps": 4367769599, "loss": 0.01413717307150364, "avg_return": 0.8617556095123291, "regret": 0.000756132765673101, "entropy": 0.07625371962785721, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:24.642668Z", "loop": 7109, "env_steps": 4368383999, "loss": 0.01638372801244259, "avg_return": 0.8637162446975708, "regret": 0.000756132765673101, "entropy": 0.0883229598402977, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:25.542540Z", "loop": 7110, "env_steps": 4368998399, "loss": 0.015007329173386097, "avg_return": 0.8626649975776672, "regret": 0.0006584566435776651, "entropy": 0.08310547471046448, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:26.398222Z", "loop": 7111, "env_steps": 4369612799, "loss": 0.014436638914048672, "avg_return": 0.8623473048210144, "regret": 0.0006584566435776651, "entropy": 0.08135443180799484, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:27.254422Z", "loop": 7112, "env_steps": 4370227199, "loss": 0.014064348302781582, "avg_return": 0.8622256517410278, "regret": 0.0006584566435776651, "entropy": 0.07736124098300934, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:28.110652Z", "loop": 7113, "env_steps": 4370841599, "loss": 0.014230131171643734, "avg_return": 0.8628125190734863, "regret": 0.0006584566435776651, "entropy": 0.07997506856918335, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:28.967309Z", "loop": 7114, "env_steps": 4371455999, "loss": 0.014413055963814259, "avg_return": 0.8634487986564636, "regret": 0.0006584566435776651, "entropy": 0.08165764808654785, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:29.823971Z", "loop": 7115, "env_steps": 4372070399, "loss": 0.014249457977712154, "avg_return": 0.8635215163230896, "regret": 0.0006584566435776651, "entropy": 0.07890424877405167, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:30.680336Z", "loop": 7116, "env_steps": 4372684799, "loss": 0.013550165109336376, "avg_return": 0.8623171448707581, "regret": 0.0006584566435776651, "entropy": 0.0764341801404953, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:31.536597Z", "loop": 7117, "env_steps": 4373299199, "loss": 0.013917068019509315, "avg_return": 0.8627830147743225, "regret": 0.0006584566435776651, "entropy": 0.0782289057970047, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:32.394574Z", "loop": 7118, "env_steps": 4373913599, "loss": 0.013758115470409393, "avg_return": 0.8630473017692566, "regret": 0.0006584566435776651, "entropy": 0.07695881277322769, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:33.251024Z", "loop": 7119, "env_steps": 4374527999, "loss": 0.01432035118341446, "avg_return": 0.8622849583625793, "regret": 0.0006584566435776651, "entropy": 0.08204534649848938, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:34.149230Z", "loop": 7120, "env_steps": 4375142399, "loss": 0.01388497930020094, "avg_return": 0.8628177046775818, "regret": 0.0007303814054466784, "entropy": 0.07764212042093277, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:35.004388Z", "loop": 7121, "env_steps": 4375756799, "loss": 0.014298665337264538, "avg_return": 0.8628549575805664, "regret": 0.0007303814054466784, "entropy": 0.08141347765922546, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:35.860538Z", "loop": 7122, "env_steps": 4376371199, "loss": 0.014851212501525879, "avg_return": 0.864412248134613, "regret": 0.0007303814054466784, "entropy": 0.08156801760196686, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:36.715445Z", "loop": 7123, "env_steps": 4376985599, "loss": 0.014091593213379383, "avg_return": 0.8616949915885925, "regret": 0.0007303814054466784, "entropy": 0.07679634541273117, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:37.570764Z", "loop": 7124, "env_steps": 4377599999, "loss": 0.014521841891109943, "avg_return": 0.8635773658752441, "regret": 0.0007303814054466784, "entropy": 0.07842337340116501, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:38.425446Z", "loop": 7125, "env_steps": 4378214399, "loss": 0.01372317224740982, "avg_return": 0.8633098602294922, "regret": 0.0007303814054466784, "entropy": 0.07501517981290817, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:39.281906Z", "loop": 7126, "env_steps": 4378828799, "loss": 0.014357680454850197, "avg_return": 0.863121747970581, "regret": 0.0007303814054466784, "entropy": 0.07867452502250671, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:40.138577Z", "loop": 7127, "env_steps": 4379443199, "loss": 0.015164750628173351, "avg_return": 0.8638585805892944, "regret": 0.0007303814054466784, "entropy": 0.08417287468910217, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:40.995043Z", "loop": 7128, "env_steps": 4380057599, "loss": 0.014629614539444447, "avg_return": 0.8615770936012268, "regret": 0.0007303814054466784, "entropy": 0.08258063346147537, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:41.851112Z", "loop": 7129, "env_steps": 4380671999, "loss": 0.013857140205800533, "avg_return": 0.8625470399856567, "regret": 0.0007303814054466784, "entropy": 0.07771365344524384, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:42.747130Z", "loop": 7130, "env_steps": 4381286399, "loss": 0.014903168193995953, "avg_return": 0.8631744384765625, "regret": 0.0009190279524773359, "entropy": 0.08142465353012085, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:43.602675Z", "loop": 7131, "env_steps": 4381900799, "loss": 0.015170037746429443, "avg_return": 0.8633874654769897, "regret": 0.0009190279524773359, "entropy": 0.08387715369462967, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:44.458692Z", "loop": 7132, "env_steps": 4382515199, "loss": 0.015039028599858284, "avg_return": 0.8632668256759644, "regret": 0.0009190279524773359, "entropy": 0.08276408910751343, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:45.314458Z", "loop": 7133, "env_steps": 4383129599, "loss": 0.014537489973008633, "avg_return": 0.8638747334480286, "regret": 0.0009190279524773359, "entropy": 0.08076652139425278, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:46.169087Z", "loop": 7134, "env_steps": 4383743999, "loss": 0.015189476311206818, "avg_return": 0.8629547357559204, "regret": 0.0009190279524773359, "entropy": 0.07966198772192001, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:47.023737Z", "loop": 7135, "env_steps": 4384358399, "loss": 0.015212859027087688, "avg_return": 0.8644405603408813, "regret": 0.0009190279524773359, "entropy": 0.08485503494739532, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:47.879395Z", "loop": 7136, "env_steps": 4384972799, "loss": 0.014795340597629547, "avg_return": 0.8630253076553345, "regret": 0.0009190279524773359, "entropy": 0.08118046820163727, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:48.735277Z", "loop": 7137, "env_steps": 4385587199, "loss": 0.013584787026047707, "avg_return": 0.8627449870109558, "regret": 0.0009190279524773359, "entropy": 0.07678912580013275, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:49.590161Z", "loop": 7138, "env_steps": 4386201599, "loss": 0.014600159600377083, "avg_return": 0.863614022731781, "regret": 0.0009190279524773359, "entropy": 0.08113370090723038, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:50.445660Z", "loop": 7139, "env_steps": 4386815999, "loss": 0.015219061635434628, "avg_return": 0.8649030923843384, "regret": 0.0009190279524773359, "entropy": 0.0813642367720604, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:51.342287Z", "loop": 7140, "env_steps": 4387430399, "loss": 0.01572299748659134, "avg_return": 0.8631761074066162, "regret": 0.0008569954079575837, "entropy": 0.0861910879611969, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:52.198386Z", "loop": 7141, "env_steps": 4388044799, "loss": 0.015126898884773254, "avg_return": 0.861947774887085, "regret": 0.0008569954079575837, "entropy": 0.0838092714548111, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:53.054176Z", "loop": 7142, "env_steps": 4388659199, "loss": 0.015141951851546764, "avg_return": 0.8631606101989746, "regret": 0.0008569954079575837, "entropy": 0.08354280889034271, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:53.909531Z", "loop": 7143, "env_steps": 4389273599, "loss": 0.015125888399779797, "avg_return": 0.8620682954788208, "regret": 0.0008569954079575837, "entropy": 0.08617643266916275, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:54.765246Z", "loop": 7144, "env_steps": 4389887999, "loss": 0.016549518331885338, "avg_return": 0.8618532419204712, "regret": 0.0008569954079575837, "entropy": 0.08882876485586166, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:55.622228Z", "loop": 7145, "env_steps": 4390502399, "loss": 0.014956160448491573, "avg_return": 0.8609397411346436, "regret": 0.0008569954079575837, "entropy": 0.08517816662788391, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:56.477908Z", "loop": 7146, "env_steps": 4391116799, "loss": 0.017566094174981117, "avg_return": 0.8618066906929016, "regret": 0.0008569954079575837, "entropy": 0.09474077820777893, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:57.332876Z", "loop": 7147, "env_steps": 4391731199, "loss": 0.016963934525847435, "avg_return": 0.8595839738845825, "regret": 0.0008569954079575837, "entropy": 0.09498140215873718, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:58.187298Z", "loop": 7148, "env_steps": 4392345599, "loss": 0.01696254312992096, "avg_return": 0.8601141571998596, "regret": 0.0008569954079575837, "entropy": 0.09566571563482285, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:59.042527Z", "loop": 7149, "env_steps": 4392959999, "loss": 0.01798659935593605, "avg_return": 0.861401379108429, "regret": 0.0008569954079575837, "entropy": 0.0978478491306305, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:05:59.938740Z", "loop": 7150, "env_steps": 4393574399, "loss": 0.01639832742512226, "avg_return": 0.8612189888954163, "regret": 0.0023798777256160975, "entropy": 0.09154921770095825, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:00.794480Z", "loop": 7151, "env_steps": 4394188799, "loss": 0.016382446512579918, "avg_return": 0.8613939881324768, "regret": 0.0023798777256160975, "entropy": 0.08833998441696167, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:01.649019Z", "loop": 7152, "env_steps": 4394803199, "loss": 0.01405880507081747, "avg_return": 0.861355721950531, "regret": 0.0023798777256160975, "entropy": 0.08177244663238525, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:02.504968Z", "loop": 7153, "env_steps": 4395417599, "loss": 0.014958038926124573, "avg_return": 0.8628019690513611, "regret": 0.0023798777256160975, "entropy": 0.08494631201028824, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:03.360956Z", "loop": 7154, "env_steps": 4396031999, "loss": 0.012671969830989838, "avg_return": 0.8626084327697754, "regret": 0.0023798777256160975, "entropy": 0.07419178634881973, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:04.216291Z", "loop": 7155, "env_steps": 4396646399, "loss": 0.01438780128955841, "avg_return": 0.8619030117988586, "regret": 0.0023798777256160975, "entropy": 0.07808703184127808, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:05.073518Z", "loop": 7156, "env_steps": 4397260799, "loss": 0.013820916414260864, "avg_return": 0.8625597357749939, "regret": 0.0023798777256160975, "entropy": 0.07716931402683258, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:05.929207Z", "loop": 7157, "env_steps": 4397875199, "loss": 0.015145780518651009, "avg_return": 0.8625605702400208, "regret": 0.0023798777256160975, "entropy": 0.07973427325487137, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:06.785442Z", "loop": 7158, "env_steps": 4398489599, "loss": 0.013886255212128162, "avg_return": 0.8623167872428894, "regret": 0.0023798777256160975, "entropy": 0.07530107349157333, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:07.641767Z", "loop": 7159, "env_steps": 4399103999, "loss": 0.015743009746074677, "avg_return": 0.8625889420509338, "regret": 0.0023798777256160975, "entropy": 0.08469782769680023, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:08.538437Z", "loop": 7160, "env_steps": 4399718399, "loss": 0.015110701322555542, "avg_return": 0.8621110320091248, "regret": 0.001239969627931714, "entropy": 0.07889942079782486, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:09.394054Z", "loop": 7161, "env_steps": 4400332799, "loss": 0.014100384898483753, "avg_return": 0.8614481091499329, "regret": 0.001239969627931714, "entropy": 0.07992073893547058, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:10.248840Z", "loop": 7162, "env_steps": 4400947199, "loss": 0.015045898035168648, "avg_return": 0.8609093427658081, "regret": 0.001239969627931714, "entropy": 0.08304043114185333, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:11.104256Z", "loop": 7163, "env_steps": 4401561599, "loss": 0.016505779698491096, "avg_return": 0.8609934449195862, "regret": 0.001239969627931714, "entropy": 0.08658124506473541, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:11.959671Z", "loop": 7164, "env_steps": 4402175999, "loss": 0.01583288609981537, "avg_return": 0.8617011904716492, "regret": 0.001239969627931714, "entropy": 0.08612111955881119, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:12.815502Z", "loop": 7165, "env_steps": 4402790399, "loss": 0.015669142827391624, "avg_return": 0.8595778346061707, "regret": 0.001239969627931714, "entropy": 0.08742207288742065, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:13.670642Z", "loop": 7166, "env_steps": 4403404799, "loss": 0.014766553416848183, "avg_return": 0.8599678874015808, "regret": 0.001239969627931714, "entropy": 0.08170910179615021, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:14.526860Z", "loop": 7167, "env_steps": 4404019199, "loss": 0.014020726084709167, "avg_return": 0.8601320385932922, "regret": 0.001239969627931714, "entropy": 0.08008910715579987, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:15.381657Z", "loop": 7168, "env_steps": 4404633599, "loss": 0.015780769288539886, "avg_return": 0.8597000241279602, "regret": 0.001239969627931714, "entropy": 0.08281520754098892, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:16.237645Z", "loop": 7169, "env_steps": 4405247999, "loss": 0.014911419712007046, "avg_return": 0.8597832322120667, "regret": 0.001239969627931714, "entropy": 0.08709041774272919, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:17.132950Z", "loop": 7170, "env_steps": 4405862399, "loss": 0.01453514862805605, "avg_return": 0.8598688840866089, "regret": 0.0031697156373411417, "entropy": 0.08353082835674286, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:17.988020Z", "loop": 7171, "env_steps": 4406476799, "loss": 0.016339298337697983, "avg_return": 0.8616787791252136, "regret": 0.0031697156373411417, "entropy": 0.08859052509069443, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:18.844188Z", "loop": 7172, "env_steps": 4407091199, "loss": 0.016242487356066704, "avg_return": 0.8609417676925659, "regret": 0.0031697156373411417, "entropy": 0.09106073528528214, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:19.699804Z", "loop": 7173, "env_steps": 4407705599, "loss": 0.014285631477832794, "avg_return": 0.8605718016624451, "regret": 0.0031697156373411417, "entropy": 0.08371524512767792, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:20.555714Z", "loop": 7174, "env_steps": 4408319999, "loss": 0.015117816627025604, "avg_return": 0.8608391284942627, "regret": 0.0031697156373411417, "entropy": 0.08560828119516373, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:21.411530Z", "loop": 7175, "env_steps": 4408934399, "loss": 0.015084311366081238, "avg_return": 0.8621584177017212, "regret": 0.0031697156373411417, "entropy": 0.08084442466497421, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:22.267468Z", "loop": 7176, "env_steps": 4409548799, "loss": 0.014870178885757923, "avg_return": 0.8618379831314087, "regret": 0.0031697156373411417, "entropy": 0.07910583168268204, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:23.124156Z", "loop": 7177, "env_steps": 4410163199, "loss": 0.014220567420125008, "avg_return": 0.8619700074195862, "regret": 0.0031697156373411417, "entropy": 0.08530827611684799, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:23.981469Z", "loop": 7178, "env_steps": 4410777599, "loss": 0.014626668766140938, "avg_return": 0.8608549237251282, "regret": 0.0031697156373411417, "entropy": 0.07882200181484222, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:24.836922Z", "loop": 7179, "env_steps": 4411391999, "loss": 0.014886832796037197, "avg_return": 0.8599735498428345, "regret": 0.0031697156373411417, "entropy": 0.08178181201219559, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:25.731530Z", "loop": 7180, "env_steps": 4412006399, "loss": 0.01440597977489233, "avg_return": 0.8623390793800354, "regret": 0.0020065216813236475, "entropy": 0.07682010531425476, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:26.586906Z", "loop": 7181, "env_steps": 4412620799, "loss": 0.014345782808959484, "avg_return": 0.8614106178283691, "regret": 0.0020065216813236475, "entropy": 0.08107683062553406, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:27.443492Z", "loop": 7182, "env_steps": 4413235199, "loss": 0.014689132571220398, "avg_return": 0.862118124961853, "regret": 0.0020065216813236475, "entropy": 0.0807698518037796, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:28.298995Z", "loop": 7183, "env_steps": 4413849599, "loss": 0.015279932878911495, "avg_return": 0.8623469471931458, "regret": 0.0020065216813236475, "entropy": 0.08582444489002228, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:29.154261Z", "loop": 7184, "env_steps": 4414463999, "loss": 0.015971122309565544, "avg_return": 0.8614046573638916, "regret": 0.0020065216813236475, "entropy": 0.08490961790084839, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:30.010235Z", "loop": 7185, "env_steps": 4415078399, "loss": 0.015801681205630302, "avg_return": 0.8614391088485718, "regret": 0.0020065216813236475, "entropy": 0.09130112826824188, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:30.867463Z", "loop": 7186, "env_steps": 4415692799, "loss": 0.017444008961319923, "avg_return": 0.8589091300964355, "regret": 0.0020065216813236475, "entropy": 0.09467770904302597, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:31.722381Z", "loop": 7187, "env_steps": 4416307199, "loss": 0.020154163241386414, "avg_return": 0.8563488125801086, "regret": 0.0020065216813236475, "entropy": 0.10508548468351364, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:32.577975Z", "loop": 7188, "env_steps": 4416921599, "loss": 0.021548012271523476, "avg_return": 0.8529946804046631, "regret": 0.0020065216813236475, "entropy": 0.11392419040203094, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:33.432481Z", "loop": 7189, "env_steps": 4417535999, "loss": 0.022760938853025436, "avg_return": 0.8532410264015198, "regret": 0.0020065216813236475, "entropy": 0.11782737076282501, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:34.328312Z", "loop": 7190, "env_steps": 4418150399, "loss": 0.0201845895498991, "avg_return": 0.8560516834259033, "regret": 0.008897799998521805, "entropy": 0.10912498831748962, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:35.182632Z", "loop": 7191, "env_steps": 4418764799, "loss": 0.018584812059998512, "avg_return": 0.8572024703025818, "regret": 0.008897799998521805, "entropy": 0.10166288167238235, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:36.037865Z", "loop": 7192, "env_steps": 4419379199, "loss": 0.01739651709794998, "avg_return": 0.8609397411346436, "regret": 0.008897799998521805, "entropy": 0.09062379598617554, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:36.893009Z", "loop": 7193, "env_steps": 4419993599, "loss": 0.015564258210361004, "avg_return": 0.8611122965812683, "regret": 0.008897799998521805, "entropy": 0.08557817339897156, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:37.749764Z", "loop": 7194, "env_steps": 4420607999, "loss": 0.015682777389883995, "avg_return": 0.8619748950004578, "regret": 0.008897799998521805, "entropy": 0.0898740366101265, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:38.605367Z", "loop": 7195, "env_steps": 4421222399, "loss": 0.015329994261264801, "avg_return": 0.8634815812110901, "regret": 0.008897799998521805, "entropy": 0.08551400899887085, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:39.460384Z", "loop": 7196, "env_steps": 4421836799, "loss": 0.013299956917762756, "avg_return": 0.861865758895874, "regret": 0.008897799998521805, "entropy": 0.07869690656661987, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:40.315060Z", "loop": 7197, "env_steps": 4422451199, "loss": 0.01553625799715519, "avg_return": 0.8620592355728149, "regret": 0.008897799998521805, "entropy": 0.08411671221256256, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:41.170088Z", "loop": 7198, "env_steps": 4423065599, "loss": 0.014805625192821026, "avg_return": 0.861786425113678, "regret": 0.008897799998521805, "entropy": 0.08505847305059433, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:42.025281Z", "loop": 7199, "env_steps": 4423679999, "loss": 0.015790177509188652, "avg_return": 0.8633198142051697, "regret": 0.008897799998521805, "entropy": 0.08598797023296356, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:42.921159Z", "loop": 7200, "env_steps": 4424294399, "loss": 0.016542507335543633, "avg_return": 0.8625537157058716, "regret": 0.001220368780195713, "entropy": 0.08982162922620773, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:43.777161Z", "loop": 7201, "env_steps": 4424908799, "loss": 0.015253863297402859, "avg_return": 0.8617783784866333, "regret": 0.001220368780195713, "entropy": 0.08581788092851639, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:44.633731Z", "loop": 7202, "env_steps": 4425523199, "loss": 0.01506054401397705, "avg_return": 0.8615185022354126, "regret": 0.001220368780195713, "entropy": 0.08521099388599396, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:45.489080Z", "loop": 7203, "env_steps": 4426137599, "loss": 0.015352885238826275, "avg_return": 0.862954318523407, "regret": 0.001220368780195713, "entropy": 0.0862954705953598, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:46.344144Z", "loop": 7204, "env_steps": 4426751999, "loss": 0.016950225457549095, "avg_return": 0.863077700138092, "regret": 0.001220368780195713, "entropy": 0.09146085381507874, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:47.199749Z", "loop": 7205, "env_steps": 4427366399, "loss": 0.01608375832438469, "avg_return": 0.8616766333580017, "regret": 0.001220368780195713, "entropy": 0.08889653533697128, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:48.056061Z", "loop": 7206, "env_steps": 4427980799, "loss": 0.01694207452237606, "avg_return": 0.8615159392356873, "regret": 0.001220368780195713, "entropy": 0.09476297348737717, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:48.910791Z", "loop": 7207, "env_steps": 4428595199, "loss": 0.015586623921990395, "avg_return": 0.862358808517456, "regret": 0.001220368780195713, "entropy": 0.08480952680110931, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:49.764869Z", "loop": 7208, "env_steps": 4429209599, "loss": 0.016521474346518517, "avg_return": 0.8632902503013611, "regret": 0.001220368780195713, "entropy": 0.08821824193000793, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:50.621123Z", "loop": 7209, "env_steps": 4429823999, "loss": 0.015948910266160965, "avg_return": 0.8626123070716858, "regret": 0.001220368780195713, "entropy": 0.08685725927352905, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:51.516981Z", "loop": 7210, "env_steps": 4430438399, "loss": 0.014573662541806698, "avg_return": 0.8637683391571045, "regret": 0.0009365080040879548, "entropy": 0.08275004476308823, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:52.373259Z", "loop": 7211, "env_steps": 4431052799, "loss": 0.01606861501932144, "avg_return": 0.8616322875022888, "regret": 0.0009365080040879548, "entropy": 0.08905375748872757, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:53.228962Z", "loop": 7212, "env_steps": 4431667199, "loss": 0.014546521008014679, "avg_return": 0.8621496558189392, "regret": 0.0009365080040879548, "entropy": 0.0851927101612091, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:54.083861Z", "loop": 7213, "env_steps": 4432281599, "loss": 0.015174326486885548, "avg_return": 0.862541913986206, "regret": 0.0009365080040879548, "entropy": 0.08176889270544052, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:54.941482Z", "loop": 7214, "env_steps": 4432895999, "loss": 0.01564760133624077, "avg_return": 0.861835241317749, "regret": 0.0009365080040879548, "entropy": 0.08553925901651382, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:55.798301Z", "loop": 7215, "env_steps": 4433510399, "loss": 0.015872832387685776, "avg_return": 0.8606809973716736, "regret": 0.0009365080040879548, "entropy": 0.0853339210152626, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:56.653996Z", "loop": 7216, "env_steps": 4434124799, "loss": 0.0157452505081892, "avg_return": 0.8615189790725708, "regret": 0.0009365080040879548, "entropy": 0.08971750736236572, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:57.510797Z", "loop": 7217, "env_steps": 4434739199, "loss": 0.015783699229359627, "avg_return": 0.8612008690834045, "regret": 0.0009365080040879548, "entropy": 0.08628593385219574, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:58.368709Z", "loop": 7218, "env_steps": 4435353599, "loss": 0.015645591542124748, "avg_return": 0.8626310229301453, "regret": 0.0009365080040879548, "entropy": 0.08860655128955841, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:06:59.226116Z", "loop": 7219, "env_steps": 4435967999, "loss": 0.016267141327261925, "avg_return": 0.8612077236175537, "regret": 0.0009365080040879548, "entropy": 0.08575636148452759, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:00.123309Z", "loop": 7220, "env_steps": 4436582399, "loss": 0.015594683587551117, "avg_return": 0.8609398603439331, "regret": 0.002831648802384734, "entropy": 0.08720844984054565, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:00.979933Z", "loop": 7221, "env_steps": 4437196799, "loss": 0.015093077905476093, "avg_return": 0.861616313457489, "regret": 0.002831648802384734, "entropy": 0.08315468579530716, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:01.835214Z", "loop": 7222, "env_steps": 4437811199, "loss": 0.0150596396997571, "avg_return": 0.8618113398551941, "regret": 0.002831648802384734, "entropy": 0.08481216430664062, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:02.689931Z", "loop": 7223, "env_steps": 4438425599, "loss": 0.016122329980134964, "avg_return": 0.8619124293327332, "regret": 0.002831648802384734, "entropy": 0.08909556269645691, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:03.545022Z", "loop": 7224, "env_steps": 4439039999, "loss": 0.015577571466565132, "avg_return": 0.8615016937255859, "regret": 0.002831648802384734, "entropy": 0.08458635210990906, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:04.401153Z", "loop": 7225, "env_steps": 4439654399, "loss": 0.016045907512307167, "avg_return": 0.8619630932807922, "regret": 0.002831648802384734, "entropy": 0.09194207936525345, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:05.256415Z", "loop": 7226, "env_steps": 4440268799, "loss": 0.016189487650990486, "avg_return": 0.8589314818382263, "regret": 0.002831648802384734, "entropy": 0.09130948781967163, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:06.113019Z", "loop": 7227, "env_steps": 4440883199, "loss": 0.016191428527235985, "avg_return": 0.8591596484184265, "regret": 0.002831648802384734, "entropy": 0.08980609476566315, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:06.968447Z", "loop": 7228, "env_steps": 4441497599, "loss": 0.01680552028119564, "avg_return": 0.857979953289032, "regret": 0.002831648802384734, "entropy": 0.09162833541631699, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:07.825593Z", "loop": 7229, "env_steps": 4442111999, "loss": 0.01572977565228939, "avg_return": 0.856198251247406, "regret": 0.002831648802384734, "entropy": 0.09406986087560654, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:08.722250Z", "loop": 7230, "env_steps": 4442726399, "loss": 0.015746992081403732, "avg_return": 0.8574432730674744, "regret": 0.006371898576617241, "entropy": 0.09432514756917953, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:09.576952Z", "loop": 7231, "env_steps": 4443340799, "loss": 0.016305144876241684, "avg_return": 0.8575218915939331, "regret": 0.006371898576617241, "entropy": 0.09480912238359451, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:10.432742Z", "loop": 7232, "env_steps": 4443955199, "loss": 0.01550037320703268, "avg_return": 0.8591610193252563, "regret": 0.006371898576617241, "entropy": 0.08687358349561691, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:11.290169Z", "loop": 7233, "env_steps": 4444569599, "loss": 0.017223238945007324, "avg_return": 0.8594834804534912, "regret": 0.006371898576617241, "entropy": 0.09797210991382599, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:12.145116Z", "loop": 7234, "env_steps": 4445183999, "loss": 0.014828984625637531, "avg_return": 0.8622338175773621, "regret": 0.006371898576617241, "entropy": 0.08860182762145996, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:12.999679Z", "loop": 7235, "env_steps": 4445798399, "loss": 0.015575291588902473, "avg_return": 0.8617208003997803, "regret": 0.006371898576617241, "entropy": 0.08855754882097244, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:13.854224Z", "loop": 7236, "env_steps": 4446412799, "loss": 0.015369477681815624, "avg_return": 0.8629475831985474, "regret": 0.006371898576617241, "entropy": 0.09044785797595978, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:14.709534Z", "loop": 7237, "env_steps": 4447027199, "loss": 0.015561397187411785, "avg_return": 0.8607443571090698, "regret": 0.006371898576617241, "entropy": 0.087550587952137, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:15.565670Z", "loop": 7238, "env_steps": 4447641599, "loss": 0.016665896400809288, "avg_return": 0.862206220626831, "regret": 0.006371898576617241, "entropy": 0.09214083105325699, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:16.420281Z", "loop": 7239, "env_steps": 4448255999, "loss": 0.017009373754262924, "avg_return": 0.8622551560401917, "regret": 0.006371898576617241, "entropy": 0.09165346622467041, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:17.316269Z", "loop": 7240, "env_steps": 4448870399, "loss": 0.015510158613324165, "avg_return": 0.8625783324241638, "regret": 0.0012662045191973448, "entropy": 0.09173716604709625, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:18.172298Z", "loop": 7241, "env_steps": 4449484799, "loss": 0.015856288373470306, "avg_return": 0.8618143796920776, "regret": 0.0012662045191973448, "entropy": 0.0911431536078453, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:19.027613Z", "loop": 7242, "env_steps": 4450099199, "loss": 0.01601269282400608, "avg_return": 0.8630535006523132, "regret": 0.0012662045191973448, "entropy": 0.09317285567522049, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:19.882961Z", "loop": 7243, "env_steps": 4450713599, "loss": 0.016289209946990013, "avg_return": 0.861365795135498, "regret": 0.0012662045191973448, "entropy": 0.09404028952121735, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:20.738205Z", "loop": 7244, "env_steps": 4451327999, "loss": 0.01706112176179886, "avg_return": 0.8628550171852112, "regret": 0.0012662045191973448, "entropy": 0.09505140781402588, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:21.593142Z", "loop": 7245, "env_steps": 4451942399, "loss": 0.016702665016055107, "avg_return": 0.8627196550369263, "regret": 0.0012662045191973448, "entropy": 0.09354336559772491, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:22.448997Z", "loop": 7246, "env_steps": 4452556799, "loss": 0.01658131368458271, "avg_return": 0.8607500195503235, "regret": 0.0012662045191973448, "entropy": 0.09525234252214432, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:23.304404Z", "loop": 7247, "env_steps": 4453171199, "loss": 0.015494964085519314, "avg_return": 0.8624054193496704, "regret": 0.0012662045191973448, "entropy": 0.09102408587932587, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:24.159532Z", "loop": 7248, "env_steps": 4453785599, "loss": 0.016902079805731773, "avg_return": 0.8632731437683105, "regret": 0.0012662045191973448, "entropy": 0.09694509208202362, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:25.016486Z", "loop": 7249, "env_steps": 4454399999, "loss": 0.015172163024544716, "avg_return": 0.8614689111709595, "regret": 0.0012662045191973448, "entropy": 0.08693563938140869, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:25.912184Z", "loop": 7250, "env_steps": 4455014399, "loss": 0.014524956233799458, "avg_return": 0.862855851650238, "regret": 0.0008974011288955808, "entropy": 0.08657948672771454, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:26.767566Z", "loop": 7251, "env_steps": 4455628799, "loss": 0.01547266822308302, "avg_return": 0.8615401387214661, "regret": 0.0008974011288955808, "entropy": 0.08916649967432022, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:27.623206Z", "loop": 7252, "env_steps": 4456243199, "loss": 0.01480431854724884, "avg_return": 0.8617503046989441, "regret": 0.0008974011288955808, "entropy": 0.0856407880783081, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:28.477746Z", "loop": 7253, "env_steps": 4456857599, "loss": 0.014161116443574429, "avg_return": 0.8612695336341858, "regret": 0.0008974011288955808, "entropy": 0.08434577286243439, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:29.333326Z", "loop": 7254, "env_steps": 4457471999, "loss": 0.015328186564147472, "avg_return": 0.8642722964286804, "regret": 0.0008974011288955808, "entropy": 0.08490317314863205, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:30.189695Z", "loop": 7255, "env_steps": 4458086399, "loss": 0.015751227736473083, "avg_return": 0.8625446557998657, "regret": 0.0008974011288955808, "entropy": 0.09127646684646606, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:31.044382Z", "loop": 7256, "env_steps": 4458700799, "loss": 0.015130579471588135, "avg_return": 0.8629299998283386, "regret": 0.0008974011288955808, "entropy": 0.08709526807069778, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:31.899613Z", "loop": 7257, "env_steps": 4459315199, "loss": 0.014999744482338428, "avg_return": 0.8625155091285706, "regret": 0.0008974011288955808, "entropy": 0.08485386520624161, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:32.755833Z", "loop": 7258, "env_steps": 4459929599, "loss": 0.014566227793693542, "avg_return": 0.8633837103843689, "regret": 0.0008974011288955808, "entropy": 0.08395326137542725, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:33.611371Z", "loop": 7259, "env_steps": 4460543999, "loss": 0.015411782078444958, "avg_return": 0.8627598285675049, "regret": 0.0008974011288955808, "entropy": 0.08485201746225357, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:34.507546Z", "loop": 7260, "env_steps": 4461158399, "loss": 0.01588939130306244, "avg_return": 0.8623393177986145, "regret": 0.0011057308875024319, "entropy": 0.08447495847940445, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:35.362747Z", "loop": 7261, "env_steps": 4461772799, "loss": 0.014613203704357147, "avg_return": 0.8615044355392456, "regret": 0.0011057308875024319, "entropy": 0.081308513879776, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:36.217988Z", "loop": 7262, "env_steps": 4462387199, "loss": 0.014742513187229633, "avg_return": 0.8613830804824829, "regret": 0.0011057308875024319, "entropy": 0.08325625956058502, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:37.072910Z", "loop": 7263, "env_steps": 4463001599, "loss": 0.01609061099588871, "avg_return": 0.8639774918556213, "regret": 0.0011057308875024319, "entropy": 0.08818060159683228, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:37.928357Z", "loop": 7264, "env_steps": 4463615999, "loss": 0.014822258614003658, "avg_return": 0.8627734780311584, "regret": 0.0011057308875024319, "entropy": 0.07957271486520767, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:38.783826Z", "loop": 7265, "env_steps": 4464230399, "loss": 0.014854997396469116, "avg_return": 0.8637150526046753, "regret": 0.0011057308875024319, "entropy": 0.08329995721578598, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:39.639390Z", "loop": 7266, "env_steps": 4464844799, "loss": 0.014922628179192543, "avg_return": 0.863554835319519, "regret": 0.0011057308875024319, "entropy": 0.08104510605335236, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:40.494534Z", "loop": 7267, "env_steps": 4465459199, "loss": 0.014517116360366344, "avg_return": 0.8623453974723816, "regret": 0.0011057308875024319, "entropy": 0.08468768000602722, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:41.351471Z", "loop": 7268, "env_steps": 4466073599, "loss": 0.014248534105718136, "avg_return": 0.8628214597702026, "regret": 0.0011057308875024319, "entropy": 0.07909928262233734, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:42.208113Z", "loop": 7269, "env_steps": 4466687999, "loss": 0.014532259665429592, "avg_return": 0.8634124994277954, "regret": 0.0011057308875024319, "entropy": 0.08019015192985535, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:43.105021Z", "loop": 7270, "env_steps": 4467302399, "loss": 0.015172043815255165, "avg_return": 0.8622819185256958, "regret": 0.001062088878825307, "entropy": 0.0823536291718483, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:43.959661Z", "loop": 7271, "env_steps": 4467916799, "loss": 0.014027751050889492, "avg_return": 0.8625198602676392, "regret": 0.001062088878825307, "entropy": 0.0803118348121643, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:44.814435Z", "loop": 7272, "env_steps": 4468531199, "loss": 0.013926181010901928, "avg_return": 0.8625769019126892, "regret": 0.001062088878825307, "entropy": 0.07710210978984833, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:45.670844Z", "loop": 7273, "env_steps": 4469145599, "loss": 0.015671728178858757, "avg_return": 0.8624392747879028, "regret": 0.001062088878825307, "entropy": 0.08127237111330032, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:46.526962Z", "loop": 7274, "env_steps": 4469759999, "loss": 0.014779827557504177, "avg_return": 0.8625038862228394, "regret": 0.001062088878825307, "entropy": 0.07997509837150574, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:47.381533Z", "loop": 7275, "env_steps": 4470374399, "loss": 0.013400547206401825, "avg_return": 0.8626359105110168, "regret": 0.001062088878825307, "entropy": 0.07676780968904495, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:48.235526Z", "loop": 7276, "env_steps": 4470988799, "loss": 0.015430159866809845, "avg_return": 0.8632429242134094, "regret": 0.001062088878825307, "entropy": 0.08245773613452911, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:49.090678Z", "loop": 7277, "env_steps": 4471603199, "loss": 0.015569299459457397, "avg_return": 0.8607189059257507, "regret": 0.001062088878825307, "entropy": 0.08115334808826447, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:49.945942Z", "loop": 7278, "env_steps": 4472217599, "loss": 0.013751854188740253, "avg_return": 0.8631496429443359, "regret": 0.001062088878825307, "entropy": 0.07708068192005157, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:50.800971Z", "loop": 7279, "env_steps": 4472831999, "loss": 0.014804604463279247, "avg_return": 0.8622691035270691, "regret": 0.001062088878825307, "entropy": 0.08308745175600052, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:51.695947Z", "loop": 7280, "env_steps": 4473446399, "loss": 0.014366214163601398, "avg_return": 0.8620743155479431, "regret": 0.0013017556630074978, "entropy": 0.07892867922782898, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:52.552204Z", "loop": 7281, "env_steps": 4474060799, "loss": 0.013879521749913692, "avg_return": 0.8627573847770691, "regret": 0.0013017556630074978, "entropy": 0.07867209613323212, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:53.407214Z", "loop": 7282, "env_steps": 4474675199, "loss": 0.013890990987420082, "avg_return": 0.861365795135498, "regret": 0.0013017556630074978, "entropy": 0.07591314613819122, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:54.262962Z", "loop": 7283, "env_steps": 4475289599, "loss": 0.01284142304211855, "avg_return": 0.8620678782463074, "regret": 0.0013017556630074978, "entropy": 0.07514570653438568, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:55.118203Z", "loop": 7284, "env_steps": 4475903999, "loss": 0.01393828820437193, "avg_return": 0.8623096942901611, "regret": 0.0013017556630074978, "entropy": 0.0750848650932312, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:55.972607Z", "loop": 7285, "env_steps": 4476518399, "loss": 0.01536263432353735, "avg_return": 0.8619807958602905, "regret": 0.0013017556630074978, "entropy": 0.07982416450977325, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:56.827398Z", "loop": 7286, "env_steps": 4477132799, "loss": 0.014755013398826122, "avg_return": 0.8622941374778748, "regret": 0.0013017556630074978, "entropy": 0.08100297302007675, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:57.683662Z", "loop": 7287, "env_steps": 4477747199, "loss": 0.01490473747253418, "avg_return": 0.8622056245803833, "regret": 0.0013017556630074978, "entropy": 0.0797363668680191, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:58.539200Z", "loop": 7288, "env_steps": 4478361599, "loss": 0.01487374771386385, "avg_return": 0.8617671728134155, "regret": 0.0013017556630074978, "entropy": 0.08199126273393631, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:07:59.393699Z", "loop": 7289, "env_steps": 4478975999, "loss": 0.01479368843138218, "avg_return": 0.860274076461792, "regret": 0.0013017556630074978, "entropy": 0.08349563926458359, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:00.289980Z", "loop": 7290, "env_steps": 4479590399, "loss": 0.015223887749016285, "avg_return": 0.862023115158081, "regret": 0.0029329415410757065, "entropy": 0.08288662880659103, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:01.145778Z", "loop": 7291, "env_steps": 4480204799, "loss": 0.015133540146052837, "avg_return": 0.8593594431877136, "regret": 0.0029329415410757065, "entropy": 0.08395130187273026, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:02.002026Z", "loop": 7292, "env_steps": 4480819199, "loss": 0.015766432508826256, "avg_return": 0.8600237965583801, "regret": 0.0029329415410757065, "entropy": 0.08491288125514984, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:02.857548Z", "loop": 7293, "env_steps": 4481433599, "loss": 0.014615329913794994, "avg_return": 0.8590250611305237, "regret": 0.0029329415410757065, "entropy": 0.07804863154888153, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:03.711460Z", "loop": 7294, "env_steps": 4482047999, "loss": 0.0142796216532588, "avg_return": 0.8617390990257263, "regret": 0.0029329415410757065, "entropy": 0.08016294240951538, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:04.565406Z", "loop": 7295, "env_steps": 4482662399, "loss": 0.014413910917937756, "avg_return": 0.8610357642173767, "regret": 0.0029329415410757065, "entropy": 0.07793701440095901, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:05.421209Z", "loop": 7296, "env_steps": 4483276799, "loss": 0.01497959066182375, "avg_return": 0.8621498942375183, "regret": 0.0029329415410757065, "entropy": 0.08019120991230011, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:06.276519Z", "loop": 7297, "env_steps": 4483891199, "loss": 0.014349802397191525, "avg_return": 0.8607747554779053, "regret": 0.0029329415410757065, "entropy": 0.07727072387933731, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:07.131147Z", "loop": 7298, "env_steps": 4484505599, "loss": 0.014398462139070034, "avg_return": 0.8604599237442017, "regret": 0.0029329415410757065, "entropy": 0.08079718053340912, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:07.986423Z", "loop": 7299, "env_steps": 4485119999, "loss": 0.01482740230858326, "avg_return": 0.8607125878334045, "regret": 0.0029329415410757065, "entropy": 0.08039622753858566, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:08.880970Z", "loop": 7300, "env_steps": 4485734399, "loss": 0.016337109729647636, "avg_return": 0.8612797260284424, "regret": 0.0020330059342086315, "entropy": 0.08394715934991837, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:09.736622Z", "loop": 7301, "env_steps": 4486348799, "loss": 0.015100309625267982, "avg_return": 0.8607543110847473, "regret": 0.0020330059342086315, "entropy": 0.08247341215610504, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:10.592353Z", "loop": 7302, "env_steps": 4486963199, "loss": 0.014695778489112854, "avg_return": 0.8614806532859802, "regret": 0.0020330059342086315, "entropy": 0.08268184959888458, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:11.447528Z", "loop": 7303, "env_steps": 4487577599, "loss": 0.013817700557410717, "avg_return": 0.863188624382019, "regret": 0.0020330059342086315, "entropy": 0.07647033780813217, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:12.302724Z", "loop": 7304, "env_steps": 4488191999, "loss": 0.013763372786343098, "avg_return": 0.8634090423583984, "regret": 0.0020330059342086315, "entropy": 0.0743110254406929, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:13.158838Z", "loop": 7305, "env_steps": 4488806399, "loss": 0.014416299760341644, "avg_return": 0.8628131151199341, "regret": 0.0020330059342086315, "entropy": 0.07801097631454468, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:14.014434Z", "loop": 7306, "env_steps": 4489420799, "loss": 0.013152778148651123, "avg_return": 0.8637687563896179, "regret": 0.0020330059342086315, "entropy": 0.0746663510799408, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:14.869876Z", "loop": 7307, "env_steps": 4490035199, "loss": 0.013458050787448883, "avg_return": 0.8641030192375183, "regret": 0.0020330059342086315, "entropy": 0.0747961699962616, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:15.725503Z", "loop": 7308, "env_steps": 4490649599, "loss": 0.013834096491336823, "avg_return": 0.8612878918647766, "regret": 0.0020330059342086315, "entropy": 0.07402563840150833, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:16.580941Z", "loop": 7309, "env_steps": 4491263999, "loss": 0.014017514884471893, "avg_return": 0.86277836561203, "regret": 0.0020330059342086315, "entropy": 0.07836037874221802, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:17.476619Z", "loop": 7310, "env_steps": 4491878399, "loss": 0.01486437488347292, "avg_return": 0.8628849387168884, "regret": 0.0010750570800155401, "entropy": 0.08107177913188934, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:18.332854Z", "loop": 7311, "env_steps": 4492492799, "loss": 0.015020295977592468, "avg_return": 0.8608856201171875, "regret": 0.0010750570800155401, "entropy": 0.08016010373830795, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:19.188521Z", "loop": 7312, "env_steps": 4493107199, "loss": 0.016416771337389946, "avg_return": 0.8600009083747864, "regret": 0.0010750570800155401, "entropy": 0.08366240561008453, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:20.043762Z", "loop": 7313, "env_steps": 4493721599, "loss": 0.016092758625745773, "avg_return": 0.8568896651268005, "regret": 0.0010750570800155401, "entropy": 0.08232444524765015, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:20.898973Z", "loop": 7314, "env_steps": 4494335999, "loss": 0.015030592679977417, "avg_return": 0.8559489250183105, "regret": 0.0010750570800155401, "entropy": 0.08290436118841171, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:21.755405Z", "loop": 7315, "env_steps": 4494950399, "loss": 0.015845466405153275, "avg_return": 0.8559531569480896, "regret": 0.0010750570800155401, "entropy": 0.08614125847816467, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:22.610219Z", "loop": 7316, "env_steps": 4495564799, "loss": 0.015729384496808052, "avg_return": 0.856782853603363, "regret": 0.0010750570800155401, "entropy": 0.0801476389169693, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:23.465131Z", "loop": 7317, "env_steps": 4496179199, "loss": 0.0147956982254982, "avg_return": 0.8624998331069946, "regret": 0.0010750570800155401, "entropy": 0.07810965180397034, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:24.321163Z", "loop": 7318, "env_steps": 4496793599, "loss": 0.014329532161355019, "avg_return": 0.8614996671676636, "regret": 0.0010750570800155401, "entropy": 0.07913947850465775, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:25.177480Z", "loop": 7319, "env_steps": 4497407999, "loss": 0.013539952225983143, "avg_return": 0.86082524061203, "regret": 0.0010750570800155401, "entropy": 0.07783123105764389, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:26.073604Z", "loop": 7320, "env_steps": 4498022399, "loss": 0.013780205510556698, "avg_return": 0.8615391254425049, "regret": 0.0009448736673220992, "entropy": 0.07394126802682877, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:26.928095Z", "loop": 7321, "env_steps": 4498636799, "loss": 0.013968326151371002, "avg_return": 0.8623376488685608, "regret": 0.0009448736673220992, "entropy": 0.07580506056547165, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:27.782732Z", "loop": 7322, "env_steps": 4499251199, "loss": 0.013320534490048885, "avg_return": 0.8627429604530334, "regret": 0.0009448736673220992, "entropy": 0.07414272427558899, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:28.638188Z", "loop": 7323, "env_steps": 4499865599, "loss": 0.014192494563758373, "avg_return": 0.8640913963317871, "regret": 0.0009448736673220992, "entropy": 0.07648064196109772, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:29.494928Z", "loop": 7324, "env_steps": 4500479999, "loss": 0.013234900310635567, "avg_return": 0.863419234752655, "regret": 0.0009448736673220992, "entropy": 0.07206837832927704, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:30.350393Z", "loop": 7325, "env_steps": 4501094399, "loss": 0.013504213653504848, "avg_return": 0.8626973628997803, "regret": 0.0009448736673220992, "entropy": 0.07330455631017685, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:31.204795Z", "loop": 7326, "env_steps": 4501708799, "loss": 0.013595028780400753, "avg_return": 0.8637011647224426, "regret": 0.0009448736673220992, "entropy": 0.07404708117246628, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:32.060217Z", "loop": 7327, "env_steps": 4502323199, "loss": 0.014509816654026508, "avg_return": 0.86121666431427, "regret": 0.0009448736673220992, "entropy": 0.07726442068815231, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:32.915810Z", "loop": 7328, "env_steps": 4502937599, "loss": 0.014748445712029934, "avg_return": 0.8637619018554688, "regret": 0.0009448736673220992, "entropy": 0.08145599812269211, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:33.770774Z", "loop": 7329, "env_steps": 4503551999, "loss": 0.014270404353737831, "avg_return": 0.8622361421585083, "regret": 0.0009448736673220992, "entropy": 0.07891979813575745, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:34.666278Z", "loop": 7330, "env_steps": 4504166399, "loss": 0.01413563173264265, "avg_return": 0.8622792959213257, "regret": 0.0007758420542813838, "entropy": 0.08001407235860825, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:35.522755Z", "loop": 7331, "env_steps": 4504780799, "loss": 0.01565650664269924, "avg_return": 0.8630426526069641, "regret": 0.0007758420542813838, "entropy": 0.08320575207471848, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:36.379104Z", "loop": 7332, "env_steps": 4505395199, "loss": 0.014236114919185638, "avg_return": 0.8644620180130005, "regret": 0.0007758420542813838, "entropy": 0.08300145715475082, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:37.235337Z", "loop": 7333, "env_steps": 4506009599, "loss": 0.01454442273825407, "avg_return": 0.8622949719429016, "regret": 0.0007758420542813838, "entropy": 0.08343847095966339, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:38.090869Z", "loop": 7334, "env_steps": 4506623999, "loss": 0.01448533870279789, "avg_return": 0.8629406690597534, "regret": 0.0007758420542813838, "entropy": 0.08526007831096649, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:38.948255Z", "loop": 7335, "env_steps": 4507238399, "loss": 0.01339500118046999, "avg_return": 0.8637545108795166, "regret": 0.0007758420542813838, "entropy": 0.0798366591334343, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:39.804011Z", "loop": 7336, "env_steps": 4507852799, "loss": 0.015311515890061855, "avg_return": 0.8627360463142395, "regret": 0.0007758420542813838, "entropy": 0.08185175806283951, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:40.660627Z", "loop": 7337, "env_steps": 4508467199, "loss": 0.014692306518554688, "avg_return": 0.8622296452522278, "regret": 0.0007758420542813838, "entropy": 0.07801052927970886, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:41.516416Z", "loop": 7338, "env_steps": 4509081599, "loss": 0.014341925270855427, "avg_return": 0.8618080019950867, "regret": 0.0007758420542813838, "entropy": 0.07957115769386292, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:42.372387Z", "loop": 7339, "env_steps": 4509695999, "loss": 0.01362100150436163, "avg_return": 0.863512396812439, "regret": 0.0007758420542813838, "entropy": 0.07598885148763657, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:43.268829Z", "loop": 7340, "env_steps": 4510310399, "loss": 0.014708161354064941, "avg_return": 0.8632669448852539, "regret": 0.0005128552438691258, "entropy": 0.08201316744089127, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:44.123868Z", "loop": 7341, "env_steps": 4510924799, "loss": 0.014550645835697651, "avg_return": 0.8645502924919128, "regret": 0.0005128552438691258, "entropy": 0.07656911015510559, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:44.979959Z", "loop": 7342, "env_steps": 4511539199, "loss": 0.013520635664463043, "avg_return": 0.8626652956008911, "regret": 0.0005128552438691258, "entropy": 0.07444491982460022, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:45.836652Z", "loop": 7343, "env_steps": 4512153599, "loss": 0.014917760156095028, "avg_return": 0.8642455339431763, "regret": 0.0005128552438691258, "entropy": 0.080174520611763, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:46.691525Z", "loop": 7344, "env_steps": 4512767999, "loss": 0.014990853145718575, "avg_return": 0.8639557957649231, "regret": 0.0005128552438691258, "entropy": 0.08200427144765854, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:47.546872Z", "loop": 7345, "env_steps": 4513382399, "loss": 0.01503031887114048, "avg_return": 0.8627198338508606, "regret": 0.0005128552438691258, "entropy": 0.08122927695512772, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:48.402783Z", "loop": 7346, "env_steps": 4513996799, "loss": 0.014574152417480946, "avg_return": 0.8629415035247803, "regret": 0.0005128552438691258, "entropy": 0.08226723968982697, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:49.259084Z", "loop": 7347, "env_steps": 4514611199, "loss": 0.014709803275763988, "avg_return": 0.8629636764526367, "regret": 0.0005128552438691258, "entropy": 0.08164907246828079, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:50.114922Z", "loop": 7348, "env_steps": 4515225599, "loss": 0.015193303115665913, "avg_return": 0.8621342182159424, "regret": 0.0005128552438691258, "entropy": 0.08175870776176453, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:50.970033Z", "loop": 7349, "env_steps": 4515839999, "loss": 0.016362929716706276, "avg_return": 0.8620715737342834, "regret": 0.0005128552438691258, "entropy": 0.08721572160720825, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:51.864965Z", "loop": 7350, "env_steps": 4516454399, "loss": 0.01675635762512684, "avg_return": 0.861642062664032, "regret": 0.0013323582243174314, "entropy": 0.08659935742616653, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:52.721588Z", "loop": 7351, "env_steps": 4517068799, "loss": 0.01582665927708149, "avg_return": 0.8617895841598511, "regret": 0.0013323582243174314, "entropy": 0.08662725985050201, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:53.577398Z", "loop": 7352, "env_steps": 4517683199, "loss": 0.015333984978497028, "avg_return": 0.863195538520813, "regret": 0.0013323582243174314, "entropy": 0.08723714202642441, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:54.431965Z", "loop": 7353, "env_steps": 4518297599, "loss": 0.016343489289283752, "avg_return": 0.8629122376441956, "regret": 0.0013323582243174314, "entropy": 0.08554066717624664, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:55.287000Z", "loop": 7354, "env_steps": 4518911999, "loss": 0.015052206814289093, "avg_return": 0.8629236817359924, "regret": 0.0013323582243174314, "entropy": 0.08328163623809814, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:56.142266Z", "loop": 7355, "env_steps": 4519526399, "loss": 0.01520558726042509, "avg_return": 0.862869918346405, "regret": 0.0013323582243174314, "entropy": 0.08121484518051147, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:56.997581Z", "loop": 7356, "env_steps": 4520140799, "loss": 0.014160963706672192, "avg_return": 0.8613262176513672, "regret": 0.0013323582243174314, "entropy": 0.07758255302906036, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:57.853846Z", "loop": 7357, "env_steps": 4520755199, "loss": 0.013623381033539772, "avg_return": 0.8624956607818604, "regret": 0.0013323582243174314, "entropy": 0.07533682882785797, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:58.709258Z", "loop": 7358, "env_steps": 4521369599, "loss": 0.014622869901359081, "avg_return": 0.862605094909668, "regret": 0.0013323582243174314, "entropy": 0.07986702024936676, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:08:59.563849Z", "loop": 7359, "env_steps": 4521983999, "loss": 0.01400187611579895, "avg_return": 0.8622564077377319, "regret": 0.0013323582243174314, "entropy": 0.07759372144937515, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:00.459943Z", "loop": 7360, "env_steps": 4522598399, "loss": 0.01407683826982975, "avg_return": 0.8605591058731079, "regret": 0.0017774990992620587, "entropy": 0.0779072493314743, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:01.314693Z", "loop": 7361, "env_steps": 4523212799, "loss": 0.014547914266586304, "avg_return": 0.8610832095146179, "regret": 0.0017774990992620587, "entropy": 0.0794588252902031, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:02.170855Z", "loop": 7362, "env_steps": 4523827199, "loss": 0.013723566196858883, "avg_return": 0.8596012592315674, "regret": 0.0017774990992620587, "entropy": 0.07176773995161057, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:03.026130Z", "loop": 7363, "env_steps": 4524441599, "loss": 0.014445829205214977, "avg_return": 0.8595497608184814, "regret": 0.0017774990992620587, "entropy": 0.07795470952987671, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:03.880692Z", "loop": 7364, "env_steps": 4525055999, "loss": 0.01344359666109085, "avg_return": 0.8598894476890564, "regret": 0.0017774990992620587, "entropy": 0.07592006027698517, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:04.736164Z", "loop": 7365, "env_steps": 4525670399, "loss": 0.013861814513802528, "avg_return": 0.8610368967056274, "regret": 0.0017774990992620587, "entropy": 0.07628277689218521, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:05.591963Z", "loop": 7366, "env_steps": 4526284799, "loss": 0.013882571831345558, "avg_return": 0.8598142862319946, "regret": 0.0017774990992620587, "entropy": 0.07476893067359924, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:06.446320Z", "loop": 7367, "env_steps": 4526899199, "loss": 0.015182407572865486, "avg_return": 0.8626652359962463, "regret": 0.0017774990992620587, "entropy": 0.07827454805374146, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:07.302309Z", "loop": 7368, "env_steps": 4527513599, "loss": 0.01338648796081543, "avg_return": 0.8615697622299194, "regret": 0.0017774990992620587, "entropy": 0.07290277630090714, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:08.160244Z", "loop": 7369, "env_steps": 4528127999, "loss": 0.014010480605065823, "avg_return": 0.8626751899719238, "regret": 0.0017774990992620587, "entropy": 0.07254358381032944, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:09.057970Z", "loop": 7370, "env_steps": 4528742399, "loss": 0.013063326478004456, "avg_return": 0.8638119697570801, "regret": 0.0011993980733677745, "entropy": 0.07364111393690109, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:09.914469Z", "loop": 7371, "env_steps": 4529356799, "loss": 0.014057817868888378, "avg_return": 0.8607972264289856, "regret": 0.0011993980733677745, "entropy": 0.07760392874479294, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:10.770689Z", "loop": 7372, "env_steps": 4529971199, "loss": 0.013123552314937115, "avg_return": 0.8627815842628479, "regret": 0.0011993980733677745, "entropy": 0.07412222027778625, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:11.625875Z", "loop": 7373, "env_steps": 4530585599, "loss": 0.013311420567333698, "avg_return": 0.8620736002922058, "regret": 0.0011993980733677745, "entropy": 0.07109908014535904, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:12.481067Z", "loop": 7374, "env_steps": 4531199999, "loss": 0.013172022067010403, "avg_return": 0.8623147010803223, "regret": 0.0011993980733677745, "entropy": 0.0724608451128006, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:13.335768Z", "loop": 7375, "env_steps": 4531814399, "loss": 0.014198136515915394, "avg_return": 0.862843930721283, "regret": 0.0011993980733677745, "entropy": 0.07264652848243713, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:14.189967Z", "loop": 7376, "env_steps": 4532428799, "loss": 0.014044499956071377, "avg_return": 0.8622335195541382, "regret": 0.0011993980733677745, "entropy": 0.07300311326980591, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:15.044998Z", "loop": 7377, "env_steps": 4533043199, "loss": 0.01297647226601839, "avg_return": 0.8616676926612854, "regret": 0.0011993980733677745, "entropy": 0.07182396948337555, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:15.900925Z", "loop": 7378, "env_steps": 4533657599, "loss": 0.014061860740184784, "avg_return": 0.8636528849601746, "regret": 0.0011993980733677745, "entropy": 0.07275454699993134, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:16.756302Z", "loop": 7379, "env_steps": 4534271999, "loss": 0.012331776320934296, "avg_return": 0.8638153076171875, "regret": 0.0011993980733677745, "entropy": 0.06953136622905731, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:17.653458Z", "loop": 7380, "env_steps": 4534886399, "loss": 0.012681885622441769, "avg_return": 0.8619863986968994, "regret": 0.0008041007095016539, "entropy": 0.06768670678138733, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:18.508729Z", "loop": 7381, "env_steps": 4535500799, "loss": 0.013071894645690918, "avg_return": 0.8631974458694458, "regret": 0.0008041007095016539, "entropy": 0.07194147258996964, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:19.364756Z", "loop": 7382, "env_steps": 4536115199, "loss": 0.012910643592476845, "avg_return": 0.8638184666633606, "regret": 0.0008041007095016539, "entropy": 0.07102902978658676, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:20.219489Z", "loop": 7383, "env_steps": 4536729599, "loss": 0.013597053475677967, "avg_return": 0.8625556826591492, "regret": 0.0008041007095016539, "entropy": 0.07074800133705139, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:21.074774Z", "loop": 7384, "env_steps": 4537343999, "loss": 0.01359703578054905, "avg_return": 0.8627854585647583, "regret": 0.0008041007095016539, "entropy": 0.07295066863298416, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:21.929955Z", "loop": 7385, "env_steps": 4537958399, "loss": 0.012733697891235352, "avg_return": 0.8628723621368408, "regret": 0.0008041007095016539, "entropy": 0.0709264725446701, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:22.785551Z", "loop": 7386, "env_steps": 4538572799, "loss": 0.013714839704334736, "avg_return": 0.863707423210144, "regret": 0.0008041007095016539, "entropy": 0.0747603103518486, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:23.641035Z", "loop": 7387, "env_steps": 4539187199, "loss": 0.014109744690358639, "avg_return": 0.8625875115394592, "regret": 0.0008041007095016539, "entropy": 0.07705159485340118, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:24.495986Z", "loop": 7388, "env_steps": 4539801599, "loss": 0.01378385629504919, "avg_return": 0.8638327121734619, "regret": 0.0008041007095016539, "entropy": 0.07742547243833542, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:25.351299Z", "loop": 7389, "env_steps": 4540415999, "loss": 0.014593887142837048, "avg_return": 0.8630651831626892, "regret": 0.0008041007095016539, "entropy": 0.07942310720682144, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:26.247026Z", "loop": 7390, "env_steps": 4541030399, "loss": 0.014101703651249409, "avg_return": 0.8622317910194397, "regret": 0.0006785803707316518, "entropy": 0.08000506460666656, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:27.102813Z", "loop": 7391, "env_steps": 4541644799, "loss": 0.015741931274533272, "avg_return": 0.8637438416481018, "regret": 0.0006785803707316518, "entropy": 0.08564894646406174, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:27.958076Z", "loop": 7392, "env_steps": 4542259199, "loss": 0.014876484870910645, "avg_return": 0.8618713617324829, "regret": 0.0006785803707316518, "entropy": 0.08622319996356964, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:28.813926Z", "loop": 7393, "env_steps": 4542873599, "loss": 0.01643936149775982, "avg_return": 0.8617768287658691, "regret": 0.0006785803707316518, "entropy": 0.08738730847835541, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:29.669170Z", "loop": 7394, "env_steps": 4543487999, "loss": 0.01694674603641033, "avg_return": 0.862758219242096, "regret": 0.0006785803707316518, "entropy": 0.09433840960264206, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:30.523456Z", "loop": 7395, "env_steps": 4544102399, "loss": 0.01595829427242279, "avg_return": 0.8630949854850769, "regret": 0.0006785803707316518, "entropy": 0.09238240122795105, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:31.378924Z", "loop": 7396, "env_steps": 4544716799, "loss": 0.017891624942421913, "avg_return": 0.8608555197715759, "regret": 0.0006785803707316518, "entropy": 0.09495537728071213, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:32.235351Z", "loop": 7397, "env_steps": 4545331199, "loss": 0.01790097914636135, "avg_return": 0.8620875477790833, "regret": 0.0006785803707316518, "entropy": 0.09944971650838852, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:33.091324Z", "loop": 7398, "env_steps": 4545945599, "loss": 0.017039639875292778, "avg_return": 0.8618376851081848, "regret": 0.0006785803707316518, "entropy": 0.09398704767227173, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:33.946656Z", "loop": 7399, "env_steps": 4546559999, "loss": 0.016869843006134033, "avg_return": 0.8612597584724426, "regret": 0.0006785803707316518, "entropy": 0.09490547329187393, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:34.842140Z", "loop": 7400, "env_steps": 4547174399, "loss": 0.01746019534766674, "avg_return": 0.8605204224586487, "regret": 0.002014322206377983, "entropy": 0.09889340400695801, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:35.698230Z", "loop": 7401, "env_steps": 4547788799, "loss": 0.016446148976683617, "avg_return": 0.8617662787437439, "regret": 0.002014322206377983, "entropy": 0.09446346759796143, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:36.553740Z", "loop": 7402, "env_steps": 4548403199, "loss": 0.01699770800769329, "avg_return": 0.8619372844696045, "regret": 0.002014322206377983, "entropy": 0.09365725517272949, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:37.408612Z", "loop": 7403, "env_steps": 4549017599, "loss": 0.01612747833132744, "avg_return": 0.861568033695221, "regret": 0.002014322206377983, "entropy": 0.0932106152176857, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:38.262900Z", "loop": 7404, "env_steps": 4549631999, "loss": 0.015616758726537228, "avg_return": 0.8625577092170715, "regret": 0.002014322206377983, "entropy": 0.08985376358032227, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:39.118732Z", "loop": 7405, "env_steps": 4550246399, "loss": 0.015653176233172417, "avg_return": 0.8622564077377319, "regret": 0.002014322206377983, "entropy": 0.09082478284835815, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:39.975245Z", "loop": 7406, "env_steps": 4550860799, "loss": 0.015794893726706505, "avg_return": 0.8613371253013611, "regret": 0.002014322206377983, "entropy": 0.09057110548019409, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:40.830085Z", "loop": 7407, "env_steps": 4551475199, "loss": 0.015207584016025066, "avg_return": 0.8615726828575134, "regret": 0.002014322206377983, "entropy": 0.08529104292392731, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:41.685200Z", "loop": 7408, "env_steps": 4552089599, "loss": 0.01576516032218933, "avg_return": 0.8618238568305969, "regret": 0.002014322206377983, "entropy": 0.08707944303750992, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:42.541335Z", "loop": 7409, "env_steps": 4552703999, "loss": 0.018119540065526962, "avg_return": 0.8623592257499695, "regret": 0.002014322206377983, "entropy": 0.09905804693698883, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:43.437453Z", "loop": 7410, "env_steps": 4553318399, "loss": 0.01697373203933239, "avg_return": 0.8595580458641052, "regret": 0.002062385668978095, "entropy": 0.09051103889942169, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:44.292969Z", "loop": 7411, "env_steps": 4553932799, "loss": 0.01747160218656063, "avg_return": 0.8611664772033691, "regret": 0.002062385668978095, "entropy": 0.0965343490242958, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:45.147960Z", "loop": 7412, "env_steps": 4554547199, "loss": 0.01649124175310135, "avg_return": 0.8611621260643005, "regret": 0.002062385668978095, "entropy": 0.09055058658123016, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:46.003895Z", "loop": 7413, "env_steps": 4555161599, "loss": 0.016431106254458427, "avg_return": 0.8614463210105896, "regret": 0.002062385668978095, "entropy": 0.09073696285486221, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:46.859440Z", "loop": 7414, "env_steps": 4555775999, "loss": 0.016355538740754128, "avg_return": 0.8618596792221069, "regret": 0.002062385668978095, "entropy": 0.09254211187362671, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:47.714663Z", "loop": 7415, "env_steps": 4556390399, "loss": 0.01594121754169464, "avg_return": 0.8612380027770996, "regret": 0.002062385668978095, "entropy": 0.09048175066709518, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:48.569840Z", "loop": 7416, "env_steps": 4557004799, "loss": 0.015540099702775478, "avg_return": 0.8621887564659119, "regret": 0.002062385668978095, "entropy": 0.08724846690893173, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:49.424667Z", "loop": 7417, "env_steps": 4557619199, "loss": 0.014953087083995342, "avg_return": 0.8622491955757141, "regret": 0.002062385668978095, "entropy": 0.08654401451349258, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:50.279541Z", "loop": 7418, "env_steps": 4558233599, "loss": 0.015919722616672516, "avg_return": 0.8619924187660217, "regret": 0.002062385668978095, "entropy": 0.08707340806722641, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:51.135773Z", "loop": 7419, "env_steps": 4558847999, "loss": 0.016611149534583092, "avg_return": 0.8613413572311401, "regret": 0.002062385668978095, "entropy": 0.09222547709941864, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:52.032661Z", "loop": 7420, "env_steps": 4559462399, "loss": 0.01623285934329033, "avg_return": 0.8627392649650574, "regret": 0.0010439315810799599, "entropy": 0.08644811809062958, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:52.889083Z", "loop": 7421, "env_steps": 4560076799, "loss": 0.015939420089125633, "avg_return": 0.8624218106269836, "regret": 0.0010439315810799599, "entropy": 0.08486778289079666, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:53.744693Z", "loop": 7422, "env_steps": 4560691199, "loss": 0.015440486371517181, "avg_return": 0.8645033836364746, "regret": 0.0010439315810799599, "entropy": 0.08168338239192963, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:54.600463Z", "loop": 7423, "env_steps": 4561305599, "loss": 0.015465487726032734, "avg_return": 0.862147867679596, "regret": 0.0010439315810799599, "entropy": 0.08213825523853302, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:55.456133Z", "loop": 7424, "env_steps": 4561919999, "loss": 0.014905184507369995, "avg_return": 0.8631064295768738, "regret": 0.0010439315810799599, "entropy": 0.0797843337059021, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:56.311197Z", "loop": 7425, "env_steps": 4562534399, "loss": 0.014288666658103466, "avg_return": 0.8634771704673767, "regret": 0.0010439315810799599, "entropy": 0.0808347761631012, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:57.166267Z", "loop": 7426, "env_steps": 4563148799, "loss": 0.014866076409816742, "avg_return": 0.862886905670166, "regret": 0.0010439315810799599, "entropy": 0.08276446908712387, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:58.021949Z", "loop": 7427, "env_steps": 4563763199, "loss": 0.014852449297904968, "avg_return": 0.8615682125091553, "regret": 0.0010439315810799599, "entropy": 0.08188328891992569, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:58.878431Z", "loop": 7428, "env_steps": 4564377599, "loss": 0.015307853929698467, "avg_return": 0.8622117042541504, "regret": 0.0010439315810799599, "entropy": 0.0892099142074585, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:09:59.733518Z", "loop": 7429, "env_steps": 4564991999, "loss": 0.01603083498775959, "avg_return": 0.8624837398529053, "regret": 0.0010439315810799599, "entropy": 0.08617713302373886, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:00.630454Z", "loop": 7430, "env_steps": 4565606399, "loss": 0.015220442786812782, "avg_return": 0.8618585467338562, "regret": 0.001184138935059309, "entropy": 0.08506352454423904, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:01.485628Z", "loop": 7431, "env_steps": 4566220799, "loss": 0.015888234600424767, "avg_return": 0.8613530397415161, "regret": 0.001184138935059309, "entropy": 0.08615899085998535, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:02.344681Z", "loop": 7432, "env_steps": 4566835199, "loss": 0.01633591018617153, "avg_return": 0.8607519865036011, "regret": 0.001184138935059309, "entropy": 0.0916532352566719, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:03.200275Z", "loop": 7433, "env_steps": 4567449599, "loss": 0.016161635518074036, "avg_return": 0.8623965382575989, "regret": 0.001184138935059309, "entropy": 0.09159719944000244, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:04.056460Z", "loop": 7434, "env_steps": 4568063999, "loss": 0.015747468918561935, "avg_return": 0.8619211316108704, "regret": 0.001184138935059309, "entropy": 0.08894143998622894, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:04.912036Z", "loop": 7435, "env_steps": 4568678399, "loss": 0.015837423503398895, "avg_return": 0.8620935082435608, "regret": 0.001184138935059309, "entropy": 0.08863212913274765, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:05.768111Z", "loop": 7436, "env_steps": 4569292799, "loss": 0.01668846234679222, "avg_return": 0.8631064295768738, "regret": 0.001184138935059309, "entropy": 0.08429417014122009, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:06.623390Z", "loop": 7437, "env_steps": 4569907199, "loss": 0.015549366362392902, "avg_return": 0.8606470227241516, "regret": 0.001184138935059309, "entropy": 0.0855930894613266, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:07.480242Z", "loop": 7438, "env_steps": 4570521599, "loss": 0.014959548600018024, "avg_return": 0.8630776405334473, "regret": 0.001184138935059309, "entropy": 0.08051475137472153, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:08.335501Z", "loop": 7439, "env_steps": 4571135999, "loss": 0.013973004184663296, "avg_return": 0.8622447848320007, "regret": 0.001184138935059309, "entropy": 0.07937023043632507, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:09.233208Z", "loop": 7440, "env_steps": 4571750399, "loss": 0.0142847690731287, "avg_return": 0.8625285029411316, "regret": 0.0013048878172412515, "entropy": 0.08271265029907227, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:10.088305Z", "loop": 7441, "env_steps": 4572364799, "loss": 0.015318000689148903, "avg_return": 0.8632287979125977, "regret": 0.0013048878172412515, "entropy": 0.08263296633958817, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:10.943791Z", "loop": 7442, "env_steps": 4572979199, "loss": 0.014222423546016216, "avg_return": 0.8637502193450928, "regret": 0.0013048878172412515, "entropy": 0.07899730652570724, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:11.799881Z", "loop": 7443, "env_steps": 4573593599, "loss": 0.014558075927197933, "avg_return": 0.8625928163528442, "regret": 0.0013048878172412515, "entropy": 0.08412081748247147, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:12.656337Z", "loop": 7444, "env_steps": 4574207999, "loss": 0.014072388410568237, "avg_return": 0.8618834614753723, "regret": 0.0013048878172412515, "entropy": 0.07767470180988312, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:13.512275Z", "loop": 7445, "env_steps": 4574822399, "loss": 0.01617930643260479, "avg_return": 0.8614353537559509, "regret": 0.0013048878172412515, "entropy": 0.08946221321821213, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:14.368649Z", "loop": 7446, "env_steps": 4575436799, "loss": 0.015626853331923485, "avg_return": 0.8610416054725647, "regret": 0.0013048878172412515, "entropy": 0.09073927253484726, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:15.224948Z", "loop": 7447, "env_steps": 4576051199, "loss": 0.016358913853764534, "avg_return": 0.8623199462890625, "regret": 0.0013048878172412515, "entropy": 0.09091372787952423, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:16.082046Z", "loop": 7448, "env_steps": 4576665599, "loss": 0.016329331323504448, "avg_return": 0.8629396557807922, "regret": 0.0013048878172412515, "entropy": 0.09113070368766785, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:16.937694Z", "loop": 7449, "env_steps": 4577279999, "loss": 0.014297060668468475, "avg_return": 0.8623720407485962, "regret": 0.0013048878172412515, "entropy": 0.0801304504275322, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:17.833786Z", "loop": 7450, "env_steps": 4577894399, "loss": 0.015666905790567398, "avg_return": 0.8627488613128662, "regret": 0.0009601243655197322, "entropy": 0.08360335230827332, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:18.690647Z", "loop": 7451, "env_steps": 4578508799, "loss": 0.01524294912815094, "avg_return": 0.8627914786338806, "regret": 0.0009601243655197322, "entropy": 0.0825376957654953, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:19.546590Z", "loop": 7452, "env_steps": 4579123199, "loss": 0.015134482644498348, "avg_return": 0.8637831807136536, "regret": 0.0009601243655197322, "entropy": 0.08439266681671143, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:20.401330Z", "loop": 7453, "env_steps": 4579737599, "loss": 0.015121313743293285, "avg_return": 0.8616015911102295, "regret": 0.0009601243655197322, "entropy": 0.08578494191169739, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:21.256840Z", "loop": 7454, "env_steps": 4580351999, "loss": 0.01583431474864483, "avg_return": 0.8625177145004272, "regret": 0.0009601243655197322, "entropy": 0.08327484130859375, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:22.113961Z", "loop": 7455, "env_steps": 4580966399, "loss": 0.016043391078710556, "avg_return": 0.8609508275985718, "regret": 0.0009601243655197322, "entropy": 0.0878620371222496, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:22.970975Z", "loop": 7456, "env_steps": 4581580799, "loss": 0.016019511967897415, "avg_return": 0.8622052073478699, "regret": 0.0009601243655197322, "entropy": 0.09059686958789825, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:23.827408Z", "loop": 7457, "env_steps": 4582195199, "loss": 0.01646866463124752, "avg_return": 0.862444281578064, "regret": 0.0009601243655197322, "entropy": 0.08947798609733582, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:24.682710Z", "loop": 7458, "env_steps": 4582809599, "loss": 0.01545003242790699, "avg_return": 0.8627380728721619, "regret": 0.0009601243655197322, "entropy": 0.08289990574121475, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:25.538916Z", "loop": 7459, "env_steps": 4583423999, "loss": 0.0138096259906888, "avg_return": 0.8629912734031677, "regret": 0.0009601243655197322, "entropy": 0.0752558782696724, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:26.437045Z", "loop": 7460, "env_steps": 4584038399, "loss": 0.014310576021671295, "avg_return": 0.862501323223114, "regret": 0.0005609743529930711, "entropy": 0.07841512560844421, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:27.293076Z", "loop": 7461, "env_steps": 4584652799, "loss": 0.014313735067844391, "avg_return": 0.8622139692306519, "regret": 0.0005609743529930711, "entropy": 0.08210807293653488, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:28.148416Z", "loop": 7462, "env_steps": 4585267199, "loss": 0.01359716709703207, "avg_return": 0.8636354804039001, "regret": 0.0005609743529930711, "entropy": 0.07810265570878983, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:29.004138Z", "loop": 7463, "env_steps": 4585881599, "loss": 0.014583590440452099, "avg_return": 0.8628169894218445, "regret": 0.0005609743529930711, "entropy": 0.07883408665657043, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:29.861786Z", "loop": 7464, "env_steps": 4586495999, "loss": 0.01436928566545248, "avg_return": 0.8629014492034912, "regret": 0.0005609743529930711, "entropy": 0.07962120324373245, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:30.717370Z", "loop": 7465, "env_steps": 4587110399, "loss": 0.013406542129814625, "avg_return": 0.8623736500740051, "regret": 0.0005609743529930711, "entropy": 0.07706666737794876, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:31.574953Z", "loop": 7466, "env_steps": 4587724799, "loss": 0.013520057313144207, "avg_return": 0.862893283367157, "regret": 0.0005609743529930711, "entropy": 0.07671459019184113, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:32.430865Z", "loop": 7467, "env_steps": 4588339199, "loss": 0.015201172791421413, "avg_return": 0.8637227416038513, "regret": 0.0005609743529930711, "entropy": 0.0828106626868248, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:33.287225Z", "loop": 7468, "env_steps": 4588953599, "loss": 0.014611695893108845, "avg_return": 0.8617279529571533, "regret": 0.0005609743529930711, "entropy": 0.08341257274150848, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:34.142902Z", "loop": 7469, "env_steps": 4589567999, "loss": 0.014224131591618061, "avg_return": 0.8627616763114929, "regret": 0.0005609743529930711, "entropy": 0.0805014818906784, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:35.042074Z", "loop": 7470, "env_steps": 4590182399, "loss": 0.014902414754033089, "avg_return": 0.8635725975036621, "regret": 0.0008956589736044407, "entropy": 0.08087063580751419, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:35.897461Z", "loop": 7471, "env_steps": 4590796799, "loss": 0.014109189622104168, "avg_return": 0.8628008365631104, "regret": 0.0008956589736044407, "entropy": 0.07860589772462845, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:36.753487Z", "loop": 7472, "env_steps": 4591411199, "loss": 0.014140118844807148, "avg_return": 0.8626123070716858, "regret": 0.0008956589736044407, "entropy": 0.0778379812836647, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:37.609269Z", "loop": 7473, "env_steps": 4592025599, "loss": 0.013511908240616322, "avg_return": 0.8631191253662109, "regret": 0.0008956589736044407, "entropy": 0.07467222958803177, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:38.465687Z", "loop": 7474, "env_steps": 4592639999, "loss": 0.014341503381729126, "avg_return": 0.8613796234130859, "regret": 0.0008956589736044407, "entropy": 0.07841423898935318, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:39.321834Z", "loop": 7475, "env_steps": 4593254399, "loss": 0.013172045350074768, "avg_return": 0.8637691736221313, "regret": 0.0008956589736044407, "entropy": 0.07517168670892715, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:40.177580Z", "loop": 7476, "env_steps": 4593868799, "loss": 0.014255031943321228, "avg_return": 0.8626784682273865, "regret": 0.0008956589736044407, "entropy": 0.08070691674947739, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:41.032321Z", "loop": 7477, "env_steps": 4594483199, "loss": 0.013325025327503681, "avg_return": 0.8628381490707397, "regret": 0.0008956589736044407, "entropy": 0.07504471391439438, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:41.887911Z", "loop": 7478, "env_steps": 4595097599, "loss": 0.01450333185493946, "avg_return": 0.8626871109008789, "regret": 0.0008956589736044407, "entropy": 0.07977355271577835, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:42.743409Z", "loop": 7479, "env_steps": 4595711999, "loss": 0.015002814121544361, "avg_return": 0.8623998165130615, "regret": 0.0008956589736044407, "entropy": 0.08158461004495621, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:43.638211Z", "loop": 7480, "env_steps": 4596326399, "loss": 0.014745189808309078, "avg_return": 0.862773060798645, "regret": 0.000991066568531096, "entropy": 0.08011516183614731, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:44.493300Z", "loop": 7481, "env_steps": 4596940799, "loss": 0.015668800100684166, "avg_return": 0.8626242280006409, "regret": 0.000991066568531096, "entropy": 0.08861550688743591, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:45.348948Z", "loop": 7482, "env_steps": 4597555199, "loss": 0.015859724953770638, "avg_return": 0.8621002435684204, "regret": 0.000991066568531096, "entropy": 0.0881471037864685, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:46.205382Z", "loop": 7483, "env_steps": 4598169599, "loss": 0.016318518668413162, "avg_return": 0.8625739812850952, "regret": 0.000991066568531096, "entropy": 0.09124869108200073, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:47.062452Z", "loop": 7484, "env_steps": 4598783999, "loss": 0.018121642991900444, "avg_return": 0.8601531386375427, "regret": 0.000991066568531096, "entropy": 0.0971314087510109, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:47.918259Z", "loop": 7485, "env_steps": 4599398399, "loss": 0.01839735545217991, "avg_return": 0.8586223721504211, "regret": 0.000991066568531096, "entropy": 0.10217256844043732, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:48.772747Z", "loop": 7486, "env_steps": 4600012799, "loss": 0.01794571988284588, "avg_return": 0.8593699336051941, "regret": 0.000991066568531096, "entropy": 0.09817779809236526, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:49.628385Z", "loop": 7487, "env_steps": 4600627199, "loss": 0.016827084124088287, "avg_return": 0.8585217595100403, "regret": 0.000991066568531096, "entropy": 0.09656938910484314, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:50.484566Z", "loop": 7488, "env_steps": 4601241599, "loss": 0.017510754987597466, "avg_return": 0.8613510131835938, "regret": 0.000991066568531096, "entropy": 0.09950227290391922, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:51.339819Z", "loop": 7489, "env_steps": 4601855999, "loss": 0.014931455254554749, "avg_return": 0.8612630367279053, "regret": 0.000991066568531096, "entropy": 0.09108764678239822, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:52.234607Z", "loop": 7490, "env_steps": 4602470399, "loss": 0.01608826220035553, "avg_return": 0.861750602722168, "regret": 0.0019248828757554293, "entropy": 0.09294725954532623, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:53.091411Z", "loop": 7491, "env_steps": 4603084799, "loss": 0.014627598226070404, "avg_return": 0.8621290326118469, "regret": 0.0019248828757554293, "entropy": 0.08303789049386978, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:53.947515Z", "loop": 7492, "env_steps": 4603699199, "loss": 0.014658342115581036, "avg_return": 0.8622838258743286, "regret": 0.0019248828757554293, "entropy": 0.08405327796936035, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:54.802498Z", "loop": 7493, "env_steps": 4604313599, "loss": 0.014661477878689766, "avg_return": 0.8617541790008545, "regret": 0.0019248828757554293, "entropy": 0.08220544457435608, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:55.657812Z", "loop": 7494, "env_steps": 4604927999, "loss": 0.01498352736234665, "avg_return": 0.8613223433494568, "regret": 0.0019248828757554293, "entropy": 0.08511778712272644, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:56.513102Z", "loop": 7495, "env_steps": 4605542399, "loss": 0.015598651953041553, "avg_return": 0.8619095087051392, "regret": 0.0019248828757554293, "entropy": 0.08638979494571686, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:57.369121Z", "loop": 7496, "env_steps": 4606156799, "loss": 0.01574130356311798, "avg_return": 0.8621386885643005, "regret": 0.0019248828757554293, "entropy": 0.08669642359018326, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:58.224829Z", "loop": 7497, "env_steps": 4606771199, "loss": 0.015732811763882637, "avg_return": 0.8615981340408325, "regret": 0.0019248828757554293, "entropy": 0.08740127086639404, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:59.081429Z", "loop": 7498, "env_steps": 4607385599, "loss": 0.015969105064868927, "avg_return": 0.8610789179801941, "regret": 0.0019248828757554293, "entropy": 0.08995582908391953, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:10:59.937282Z", "loop": 7499, "env_steps": 4607999999, "loss": 0.015250131487846375, "avg_return": 0.8617333173751831, "regret": 0.0019248828757554293, "entropy": 0.08789237588644028, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:00.834375Z", "loop": 7500, "env_steps": 4608614399, "loss": 0.015837544575333595, "avg_return": 0.8636399507522583, "regret": 0.0015293469186872244, "entropy": 0.08679798990488052, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:01.691095Z", "loop": 7501, "env_steps": 4609228799, "loss": 0.016369743272662163, "avg_return": 0.8621205687522888, "regret": 0.0015293469186872244, "entropy": 0.08695896714925766, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:02.546840Z", "loop": 7502, "env_steps": 4609843199, "loss": 0.015977131202816963, "avg_return": 0.8608453869819641, "regret": 0.0015293469186872244, "entropy": 0.08985418826341629, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:03.403491Z", "loop": 7503, "env_steps": 4610457599, "loss": 0.015333673916757107, "avg_return": 0.8606303334236145, "regret": 0.0015293469186872244, "entropy": 0.08829890191555023, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:04.260185Z", "loop": 7504, "env_steps": 4611071999, "loss": 0.016139287501573563, "avg_return": 0.8610735535621643, "regret": 0.0015293469186872244, "entropy": 0.092821404337883, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:05.115371Z", "loop": 7505, "env_steps": 4611686399, "loss": 0.018991364166140556, "avg_return": 0.8601430654525757, "regret": 0.0015293469186872244, "entropy": 0.10564009845256805, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:05.970877Z", "loop": 7506, "env_steps": 4612300799, "loss": 0.023274853825569153, "avg_return": 0.856877863407135, "regret": 0.0015293469186872244, "entropy": 0.11873884499073029, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:06.826227Z", "loop": 7507, "env_steps": 4612915199, "loss": 0.02346281334757805, "avg_return": 0.8549855947494507, "regret": 0.0015293469186872244, "entropy": 0.12139149010181427, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:07.680641Z", "loop": 7508, "env_steps": 4613529599, "loss": 0.020212097093462944, "avg_return": 0.8600109815597534, "regret": 0.0015293469186872244, "entropy": 0.1091734990477562, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:08.535964Z", "loop": 7509, "env_steps": 4614143999, "loss": 0.018555117771029472, "avg_return": 0.8586376309394836, "regret": 0.0015293469186872244, "entropy": 0.10094067454338074, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:09.432067Z", "loop": 7510, "env_steps": 4614758399, "loss": 0.016797130927443504, "avg_return": 0.8611568212509155, "regret": 0.003016514703631401, "entropy": 0.09569640457630157, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:10.288126Z", "loop": 7511, "env_steps": 4615372799, "loss": 0.0178969856351614, "avg_return": 0.8609879612922668, "regret": 0.003016514703631401, "entropy": 0.10037701576948166, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:11.143489Z", "loop": 7512, "env_steps": 4615987199, "loss": 0.0163122471421957, "avg_return": 0.8608157634735107, "regret": 0.003016514703631401, "entropy": 0.09606773406267166, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:11.998506Z", "loop": 7513, "env_steps": 4616601599, "loss": 0.017210237681865692, "avg_return": 0.8623189330101013, "regret": 0.003016514703631401, "entropy": 0.09452244639396667, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:12.853762Z", "loop": 7514, "env_steps": 4617215999, "loss": 0.01574118062853813, "avg_return": 0.861331582069397, "regret": 0.003016514703631401, "entropy": 0.0930129736661911, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:13.710078Z", "loop": 7515, "env_steps": 4617830399, "loss": 0.016212889924645424, "avg_return": 0.8604676723480225, "regret": 0.003016514703631401, "entropy": 0.09178052097558975, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:14.565049Z", "loop": 7516, "env_steps": 4618444799, "loss": 0.015218297950923443, "avg_return": 0.8615706562995911, "regret": 0.003016514703631401, "entropy": 0.08905129879713058, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:15.419685Z", "loop": 7517, "env_steps": 4619059199, "loss": 0.015106605365872383, "avg_return": 0.8617926239967346, "regret": 0.003016514703631401, "entropy": 0.0863199532032013, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:16.275057Z", "loop": 7518, "env_steps": 4619673599, "loss": 0.013826577924191952, "avg_return": 0.8617275953292847, "regret": 0.003016514703631401, "entropy": 0.08153272420167923, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:17.130602Z", "loop": 7519, "env_steps": 4620287999, "loss": 0.014755854383111, "avg_return": 0.8614259958267212, "regret": 0.003016514703631401, "entropy": 0.08343526721000671, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:18.027261Z", "loop": 7520, "env_steps": 4620902399, "loss": 0.015184806659817696, "avg_return": 0.8622064590454102, "regret": 0.001594752655364573, "entropy": 0.08702553808689117, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:18.882419Z", "loop": 7521, "env_steps": 4621516799, "loss": 0.015794796869158745, "avg_return": 0.8620666861534119, "regret": 0.001594752655364573, "entropy": 0.08402206748723984, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:19.736677Z", "loop": 7522, "env_steps": 4622131199, "loss": 0.015447260811924934, "avg_return": 0.862042248249054, "regret": 0.001594752655364573, "entropy": 0.08431508392095566, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:20.591122Z", "loop": 7523, "env_steps": 4622745599, "loss": 0.015346946194767952, "avg_return": 0.8602932691574097, "regret": 0.001594752655364573, "entropy": 0.08274921774864197, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:21.446790Z", "loop": 7524, "env_steps": 4623359999, "loss": 0.01637108065187931, "avg_return": 0.8620350360870361, "regret": 0.001594752655364573, "entropy": 0.08582448959350586, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:22.301935Z", "loop": 7525, "env_steps": 4623974399, "loss": 0.015066437423229218, "avg_return": 0.8597776293754578, "regret": 0.001594752655364573, "entropy": 0.08460535109043121, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:23.156668Z", "loop": 7526, "env_steps": 4624588799, "loss": 0.015503086149692535, "avg_return": 0.8613147139549255, "regret": 0.001594752655364573, "entropy": 0.08298584818840027, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:24.012535Z", "loop": 7527, "env_steps": 4625203199, "loss": 0.01472214050590992, "avg_return": 0.8603869080543518, "regret": 0.001594752655364573, "entropy": 0.08109555393457413, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:24.868095Z", "loop": 7528, "env_steps": 4625817599, "loss": 0.015521804802119732, "avg_return": 0.8607305288314819, "regret": 0.001594752655364573, "entropy": 0.0869952067732811, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:25.724069Z", "loop": 7529, "env_steps": 4626431999, "loss": 0.01539161242544651, "avg_return": 0.8604809045791626, "regret": 0.001594752655364573, "entropy": 0.08615601807832718, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:26.620075Z", "loop": 7530, "env_steps": 4627046399, "loss": 0.014375986531376839, "avg_return": 0.8618739247322083, "regret": 0.0017657080898061395, "entropy": 0.08088722825050354, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:27.475493Z", "loop": 7531, "env_steps": 4627660799, "loss": 0.015546256676316261, "avg_return": 0.8625470399856567, "regret": 0.0017657080898061395, "entropy": 0.0851389691233635, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:28.330554Z", "loop": 7532, "env_steps": 4628275199, "loss": 0.014573322609066963, "avg_return": 0.86310875415802, "regret": 0.0017657080898061395, "entropy": 0.08237002789974213, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:29.186137Z", "loop": 7533, "env_steps": 4628889599, "loss": 0.015481539070606232, "avg_return": 0.8623427748680115, "regret": 0.0017657080898061395, "entropy": 0.08400280028581619, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:30.041866Z", "loop": 7534, "env_steps": 4629503999, "loss": 0.014641748741269112, "avg_return": 0.8631185293197632, "regret": 0.0017657080898061395, "entropy": 0.08161164075136185, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:30.898356Z", "loop": 7535, "env_steps": 4630118399, "loss": 0.014767974615097046, "avg_return": 0.8624815344810486, "regret": 0.0017657080898061395, "entropy": 0.08125759661197662, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:31.753419Z", "loop": 7536, "env_steps": 4630732799, "loss": 0.016191935166716576, "avg_return": 0.86309814453125, "regret": 0.0017657080898061395, "entropy": 0.08418620377779007, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:32.608399Z", "loop": 7537, "env_steps": 4631347199, "loss": 0.014459771104156971, "avg_return": 0.8627903461456299, "regret": 0.0017657080898061395, "entropy": 0.08130624145269394, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:33.463529Z", "loop": 7538, "env_steps": 4631961599, "loss": 0.01588652841746807, "avg_return": 0.8630710244178772, "regret": 0.0017657080898061395, "entropy": 0.08498728275299072, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:34.320034Z", "loop": 7539, "env_steps": 4632575999, "loss": 0.014323219656944275, "avg_return": 0.8631520867347717, "regret": 0.0017657080898061395, "entropy": 0.08242303133010864, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:35.216253Z", "loop": 7540, "env_steps": 4633190399, "loss": 0.015542733483016491, "avg_return": 0.8623431324958801, "regret": 0.001254475791938603, "entropy": 0.08283615112304688, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:36.071144Z", "loop": 7541, "env_steps": 4633804799, "loss": 0.01504167914390564, "avg_return": 0.8613206148147583, "regret": 0.001254475791938603, "entropy": 0.08274754136800766, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:36.926302Z", "loop": 7542, "env_steps": 4634419199, "loss": 0.015483793802559376, "avg_return": 0.8623225092887878, "regret": 0.001254475791938603, "entropy": 0.08618892729282379, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:37.782893Z", "loop": 7543, "env_steps": 4635033599, "loss": 0.01564457267522812, "avg_return": 0.8618224263191223, "regret": 0.001254475791938603, "entropy": 0.08842185884714127, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:38.638769Z", "loop": 7544, "env_steps": 4635647999, "loss": 0.014547637663781643, "avg_return": 0.861266016960144, "regret": 0.001254475791938603, "entropy": 0.08266062289476395, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:39.494619Z", "loop": 7545, "env_steps": 4636262399, "loss": 0.014249110594391823, "avg_return": 0.8618410229682922, "regret": 0.001254475791938603, "entropy": 0.08164536952972412, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:40.350774Z", "loop": 7546, "env_steps": 4636876799, "loss": 0.016078727319836617, "avg_return": 0.8623508810997009, "regret": 0.001254475791938603, "entropy": 0.08457065373659134, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:41.208486Z", "loop": 7547, "env_steps": 4637491199, "loss": 0.01409172173589468, "avg_return": 0.8616188764572144, "regret": 0.001254475791938603, "entropy": 0.08173825591802597, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:42.065629Z", "loop": 7548, "env_steps": 4638105599, "loss": 0.014841536059975624, "avg_return": 0.8620754480361938, "regret": 0.001254475791938603, "entropy": 0.08708620816469193, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:42.920355Z", "loop": 7549, "env_steps": 4638719999, "loss": 0.014619700610637665, "avg_return": 0.8620939254760742, "regret": 0.001254475791938603, "entropy": 0.08497543632984161, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:43.816346Z", "loop": 7550, "env_steps": 4639334399, "loss": 0.01591847650706768, "avg_return": 0.8613066673278809, "regret": 0.0023349158000200987, "entropy": 0.0891309380531311, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:44.672962Z", "loop": 7551, "env_steps": 4639948799, "loss": 0.016134310513734818, "avg_return": 0.859531581401825, "regret": 0.0023349158000200987, "entropy": 0.09288646280765533, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:45.529657Z", "loop": 7552, "env_steps": 4640563199, "loss": 0.020087800920009613, "avg_return": 0.85624760389328, "regret": 0.0023349158000200987, "entropy": 0.11166826635599136, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:46.385704Z", "loop": 7553, "env_steps": 4641177599, "loss": 0.018701404333114624, "avg_return": 0.8563284277915955, "regret": 0.0023349158000200987, "entropy": 0.10406176745891571, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:47.241558Z", "loop": 7554, "env_steps": 4641791999, "loss": 0.018523842096328735, "avg_return": 0.8577181100845337, "regret": 0.0023349158000200987, "entropy": 0.10383035987615585, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:48.097563Z", "loop": 7555, "env_steps": 4642406399, "loss": 0.016915440559387207, "avg_return": 0.8599136471748352, "regret": 0.0023349158000200987, "entropy": 0.09199264645576477, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:48.954284Z", "loop": 7556, "env_steps": 4643020799, "loss": 0.01525169052183628, "avg_return": 0.8634560108184814, "regret": 0.0023349158000200987, "entropy": 0.08829635381698608, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:49.811092Z", "loop": 7557, "env_steps": 4643635199, "loss": 0.014815831556916237, "avg_return": 0.8626462817192078, "regret": 0.0023349158000200987, "entropy": 0.08313016593456268, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:50.668051Z", "loop": 7558, "env_steps": 4644249599, "loss": 0.014860163442790508, "avg_return": 0.8630488514900208, "regret": 0.0023349158000200987, "entropy": 0.07974697649478912, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:51.523608Z", "loop": 7559, "env_steps": 4644863999, "loss": 0.01493191160261631, "avg_return": 0.8627482056617737, "regret": 0.0023349158000200987, "entropy": 0.08327091485261917, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:52.421998Z", "loop": 7560, "env_steps": 4645478399, "loss": 0.01486287172883749, "avg_return": 0.860958456993103, "regret": 0.0008481726399622858, "entropy": 0.08005745708942413, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:53.278512Z", "loop": 7561, "env_steps": 4646092799, "loss": 0.0140857994556427, "avg_return": 0.8622994422912598, "regret": 0.0008481726399622858, "entropy": 0.08057976514101028, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:54.135475Z", "loop": 7562, "env_steps": 4646707199, "loss": 0.016112953424453735, "avg_return": 0.8627346158027649, "regret": 0.0008481726399622858, "entropy": 0.09056241065263748, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:54.991980Z", "loop": 7563, "env_steps": 4647321599, "loss": 0.015703313052654266, "avg_return": 0.8621657490730286, "regret": 0.0008481726399622858, "entropy": 0.0880538821220398, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:55.848258Z", "loop": 7564, "env_steps": 4647935999, "loss": 0.016304150223731995, "avg_return": 0.8622391819953918, "regret": 0.0008481726399622858, "entropy": 0.08789684623479843, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:56.704409Z", "loop": 7565, "env_steps": 4648550399, "loss": 0.01593805104494095, "avg_return": 0.8628383874893188, "regret": 0.0008481726399622858, "entropy": 0.08679027110338211, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:57.561068Z", "loop": 7566, "env_steps": 4649164799, "loss": 0.01588824950158596, "avg_return": 0.8624826073646545, "regret": 0.0008481726399622858, "entropy": 0.09111113846302032, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:58.416057Z", "loop": 7567, "env_steps": 4649779199, "loss": 0.01592353917658329, "avg_return": 0.8630079627037048, "regret": 0.0008481726399622858, "entropy": 0.09473267197608948, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:11:59.271218Z", "loop": 7568, "env_steps": 4650393599, "loss": 0.016725679859519005, "avg_return": 0.860852062702179, "regret": 0.0008481726399622858, "entropy": 0.0941312313079834, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:00.126997Z", "loop": 7569, "env_steps": 4651007999, "loss": 0.015793010592460632, "avg_return": 0.8612534999847412, "regret": 0.0008481726399622858, "entropy": 0.09132150560617447, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:01.025526Z", "loop": 7570, "env_steps": 4651622399, "loss": 0.01637837663292885, "avg_return": 0.8625547289848328, "regret": 0.002284994348883629, "entropy": 0.09310019016265869, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:01.883412Z", "loop": 7571, "env_steps": 4652236799, "loss": 0.017170468345284462, "avg_return": 0.8596487641334534, "regret": 0.002284994348883629, "entropy": 0.09733068943023682, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:02.738600Z", "loop": 7572, "env_steps": 4652851199, "loss": 0.015703251585364342, "avg_return": 0.8614068031311035, "regret": 0.002284994348883629, "entropy": 0.09385938942432404, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:03.593498Z", "loop": 7573, "env_steps": 4653465599, "loss": 0.015556964091956615, "avg_return": 0.8622250556945801, "regret": 0.002284994348883629, "entropy": 0.08802895992994308, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:04.449379Z", "loop": 7574, "env_steps": 4654079999, "loss": 0.01541165541857481, "avg_return": 0.8617917895317078, "regret": 0.002284994348883629, "entropy": 0.08850234746932983, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:05.304928Z", "loop": 7575, "env_steps": 4654694399, "loss": 0.01507929153740406, "avg_return": 0.8604915738105774, "regret": 0.002284994348883629, "entropy": 0.09171775728464127, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:06.160098Z", "loop": 7576, "env_steps": 4655308799, "loss": 0.014635694213211536, "avg_return": 0.8623816967010498, "regret": 0.002284994348883629, "entropy": 0.08711831271648407, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:07.016212Z", "loop": 7577, "env_steps": 4655923199, "loss": 0.015762442722916603, "avg_return": 0.8620033860206604, "regret": 0.002284994348883629, "entropy": 0.08789108693599701, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:07.872133Z", "loop": 7578, "env_steps": 4656537599, "loss": 0.015693146735429764, "avg_return": 0.8624163866043091, "regret": 0.002284994348883629, "entropy": 0.08401042968034744, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:08.727189Z", "loop": 7579, "env_steps": 4657151999, "loss": 0.015628857538104057, "avg_return": 0.8622655272483826, "regret": 0.002284994348883629, "entropy": 0.08744553476572037, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:09.623567Z", "loop": 7580, "env_steps": 4657766399, "loss": 0.014558578841388226, "avg_return": 0.8631327748298645, "regret": 0.0010889054974541068, "entropy": 0.08305302262306213, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:10.478761Z", "loop": 7581, "env_steps": 4658380799, "loss": 0.01445414312183857, "avg_return": 0.8624874353408813, "regret": 0.0010889054974541068, "entropy": 0.08049263805150986, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:11.334198Z", "loop": 7582, "env_steps": 4658995199, "loss": 0.015014106407761574, "avg_return": 0.8620246648788452, "regret": 0.0010889054974541068, "entropy": 0.08044986426830292, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:12.189449Z", "loop": 7583, "env_steps": 4659609599, "loss": 0.013943122699856758, "avg_return": 0.8630450367927551, "regret": 0.0010889054974541068, "entropy": 0.07941756397485733, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:13.045702Z", "loop": 7584, "env_steps": 4660223999, "loss": 0.0141830462962389, "avg_return": 0.8626757860183716, "regret": 0.0010889054974541068, "entropy": 0.0784139335155487, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:13.901677Z", "loop": 7585, "env_steps": 4660838399, "loss": 0.014604749158024788, "avg_return": 0.8639475703239441, "regret": 0.0010889054974541068, "entropy": 0.07870333641767502, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:14.756060Z", "loop": 7586, "env_steps": 4661452799, "loss": 0.013807802461087704, "avg_return": 0.8629469871520996, "regret": 0.0010889054974541068, "entropy": 0.07964999973773956, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:15.610670Z", "loop": 7587, "env_steps": 4662067199, "loss": 0.014459783211350441, "avg_return": 0.863124430179596, "regret": 0.0010889054974541068, "entropy": 0.0794651210308075, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:16.467176Z", "loop": 7588, "env_steps": 4662681599, "loss": 0.013661679811775684, "avg_return": 0.8625040054321289, "regret": 0.0010889054974541068, "entropy": 0.07940969616174698, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:17.322617Z", "loop": 7589, "env_steps": 4663295999, "loss": 0.013915165327489376, "avg_return": 0.8634326457977295, "regret": 0.0010889054974541068, "entropy": 0.07666478306055069, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:18.218234Z", "loop": 7590, "env_steps": 4663910399, "loss": 0.014413091354072094, "avg_return": 0.8630937933921814, "regret": 0.0006986832013353705, "entropy": 0.08087050169706345, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:19.073179Z", "loop": 7591, "env_steps": 4664524799, "loss": 0.01274693664163351, "avg_return": 0.8625581860542297, "regret": 0.0006986832013353705, "entropy": 0.07260985672473907, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:19.928100Z", "loop": 7592, "env_steps": 4665139199, "loss": 0.01464737206697464, "avg_return": 0.8638250827789307, "regret": 0.0006986832013353705, "entropy": 0.08208075910806656, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:20.784189Z", "loop": 7593, "env_steps": 4665753599, "loss": 0.015400434844195843, "avg_return": 0.8636500239372253, "regret": 0.0006986832013353705, "entropy": 0.0819176509976387, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:21.639586Z", "loop": 7594, "env_steps": 4666367999, "loss": 0.013641240075230598, "avg_return": 0.8629341721534729, "regret": 0.0006986832013353705, "entropy": 0.07518789172172546, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:22.493935Z", "loop": 7595, "env_steps": 4666982399, "loss": 0.014882683753967285, "avg_return": 0.862762987613678, "regret": 0.0006986832013353705, "entropy": 0.0806754007935524, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:23.349329Z", "loop": 7596, "env_steps": 4667596799, "loss": 0.015453845262527466, "avg_return": 0.8615092039108276, "regret": 0.0006986832013353705, "entropy": 0.08197612315416336, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:24.205584Z", "loop": 7597, "env_steps": 4668211199, "loss": 0.014606403186917305, "avg_return": 0.86099773645401, "regret": 0.0006986832013353705, "entropy": 0.08241375535726547, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:25.061138Z", "loop": 7598, "env_steps": 4668825599, "loss": 0.014649935066699982, "avg_return": 0.8623883128166199, "regret": 0.0006986832013353705, "entropy": 0.08138681203126907, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:25.916755Z", "loop": 7599, "env_steps": 4669439999, "loss": 0.015165519900619984, "avg_return": 0.8624621033668518, "regret": 0.0006986832013353705, "entropy": 0.0828227698802948, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:26.813435Z", "loop": 7600, "env_steps": 4670054399, "loss": 0.015865642577409744, "avg_return": 0.862429141998291, "regret": 0.0011237554717808962, "entropy": 0.0845320075750351, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:27.670106Z", "loop": 7601, "env_steps": 4670668799, "loss": 0.014869803562760353, "avg_return": 0.8632784485816956, "regret": 0.0011237554717808962, "entropy": 0.08267182856798172, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:28.525908Z", "loop": 7602, "env_steps": 4671283199, "loss": 0.014227322302758694, "avg_return": 0.8639265894889832, "regret": 0.0011237554717808962, "entropy": 0.08233072608709335, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:29.382559Z", "loop": 7603, "env_steps": 4671897599, "loss": 0.014829026535153389, "avg_return": 0.8634761571884155, "regret": 0.0011237554717808962, "entropy": 0.08071830123662949, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:30.238138Z", "loop": 7604, "env_steps": 4672511999, "loss": 0.015472831204533577, "avg_return": 0.8620882630348206, "regret": 0.0011237554717808962, "entropy": 0.08408068120479584, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:31.093197Z", "loop": 7605, "env_steps": 4673126399, "loss": 0.014862040989100933, "avg_return": 0.8628404140472412, "regret": 0.0011237554717808962, "entropy": 0.08506439626216888, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:31.949587Z", "loop": 7606, "env_steps": 4673740799, "loss": 0.017069652676582336, "avg_return": 0.861568033695221, "regret": 0.0011237554717808962, "entropy": 0.09219437092542648, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:32.805811Z", "loop": 7607, "env_steps": 4674355199, "loss": 0.017608819529414177, "avg_return": 0.8617988228797913, "regret": 0.0011237554717808962, "entropy": 0.0958179384469986, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:33.661836Z", "loop": 7608, "env_steps": 4674969599, "loss": 0.017622115090489388, "avg_return": 0.8615686297416687, "regret": 0.0011237554717808962, "entropy": 0.10026418417692184, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:34.518424Z", "loop": 7609, "env_steps": 4675583999, "loss": 0.018978573381900787, "avg_return": 0.8619719743728638, "regret": 0.0011237554717808962, "entropy": 0.10192589461803436, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:35.413854Z", "loop": 7610, "env_steps": 4676198399, "loss": 0.018333222717046738, "avg_return": 0.8607919812202454, "regret": 0.0015412033535540104, "entropy": 0.10329490900039673, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:36.270110Z", "loop": 7611, "env_steps": 4676812799, "loss": 0.019642090424895287, "avg_return": 0.8619168400764465, "regret": 0.0015412033535540104, "entropy": 0.10734394192695618, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:37.125501Z", "loop": 7612, "env_steps": 4677427199, "loss": 0.019412275403738022, "avg_return": 0.8618161082267761, "regret": 0.0015412033535540104, "entropy": 0.11062397807836533, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:37.980901Z", "loop": 7613, "env_steps": 4678041599, "loss": 0.01903725229203701, "avg_return": 0.8614956140518188, "regret": 0.0015412033535540104, "entropy": 0.10759926587343216, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:38.835322Z", "loop": 7614, "env_steps": 4678655999, "loss": 0.01855223812162876, "avg_return": 0.8627672791481018, "regret": 0.0015412033535540104, "entropy": 0.10502257943153381, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:39.689794Z", "loop": 7615, "env_steps": 4679270399, "loss": 0.017447758466005325, "avg_return": 0.8627253174781799, "regret": 0.0015412033535540104, "entropy": 0.10272838920354843, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:40.545108Z", "loop": 7616, "env_steps": 4679884799, "loss": 0.018937304615974426, "avg_return": 0.8632615208625793, "regret": 0.0015412033535540104, "entropy": 0.11035309731960297, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:41.401038Z", "loop": 7617, "env_steps": 4680499199, "loss": 0.019396014511585236, "avg_return": 0.8615248799324036, "regret": 0.0015412033535540104, "entropy": 0.10693947225809097, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:42.255486Z", "loop": 7618, "env_steps": 4681113599, "loss": 0.017731163650751114, "avg_return": 0.8619272112846375, "regret": 0.0015412033535540104, "entropy": 0.1013580709695816, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:43.110912Z", "loop": 7619, "env_steps": 4681727999, "loss": 0.01811203919351101, "avg_return": 0.8619787693023682, "regret": 0.0015412033535540104, "entropy": 0.09969901293516159, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:44.005913Z", "loop": 7620, "env_steps": 4682342399, "loss": 0.017207400873303413, "avg_return": 0.8639400601387024, "regret": 0.0008947960450313985, "entropy": 0.09430882334709167, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:44.861703Z", "loop": 7621, "env_steps": 4682956799, "loss": 0.015854455530643463, "avg_return": 0.8642851114273071, "regret": 0.0008947960450313985, "entropy": 0.08714034408330917, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:45.717400Z", "loop": 7622, "env_steps": 4683571199, "loss": 0.01625092513859272, "avg_return": 0.8640096187591553, "regret": 0.0008947960450313985, "entropy": 0.08683624118566513, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:46.571845Z", "loop": 7623, "env_steps": 4684185599, "loss": 0.016107706353068352, "avg_return": 0.8616152405738831, "regret": 0.0008947960450313985, "entropy": 0.08786306530237198, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:47.427452Z", "loop": 7624, "env_steps": 4684799999, "loss": 0.015004532411694527, "avg_return": 0.863749623298645, "regret": 0.0008947960450313985, "entropy": 0.08318238705396652, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:48.284160Z", "loop": 7625, "env_steps": 4685414399, "loss": 0.014679363928735256, "avg_return": 0.862849235534668, "regret": 0.0008947960450313985, "entropy": 0.07871629297733307, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:49.139265Z", "loop": 7626, "env_steps": 4686028799, "loss": 0.016438649967312813, "avg_return": 0.8637809157371521, "regret": 0.0008947960450313985, "entropy": 0.08578664064407349, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:49.994474Z", "loop": 7627, "env_steps": 4686643199, "loss": 0.014200671575963497, "avg_return": 0.8628352284431458, "regret": 0.0008947960450313985, "entropy": 0.08104617148637772, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:50.849688Z", "loop": 7628, "env_steps": 4687257599, "loss": 0.014551165513694286, "avg_return": 0.8632127046585083, "regret": 0.0008947960450313985, "entropy": 0.08206120133399963, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:51.705302Z", "loop": 7629, "env_steps": 4687871999, "loss": 0.014357166364789009, "avg_return": 0.8629631996154785, "regret": 0.0008947960450313985, "entropy": 0.07685425877571106, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:52.600301Z", "loop": 7630, "env_steps": 4688486399, "loss": 0.013957764022052288, "avg_return": 0.8622243404388428, "regret": 0.0007496345788240433, "entropy": 0.08025319874286652, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:53.455327Z", "loop": 7631, "env_steps": 4689100799, "loss": 0.01608225889503956, "avg_return": 0.8628643751144409, "regret": 0.0007496345788240433, "entropy": 0.08800645917654037, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:54.310380Z", "loop": 7632, "env_steps": 4689715199, "loss": 0.013865423388779163, "avg_return": 0.8630512952804565, "regret": 0.0007496345788240433, "entropy": 0.07982581108808517, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:55.166695Z", "loop": 7633, "env_steps": 4690329599, "loss": 0.0143005745485425, "avg_return": 0.8626432418823242, "regret": 0.0007496345788240433, "entropy": 0.08542603254318237, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:56.022328Z", "loop": 7634, "env_steps": 4690943999, "loss": 0.015060042031109333, "avg_return": 0.8619427680969238, "regret": 0.0007496345788240433, "entropy": 0.08365518599748611, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:56.878756Z", "loop": 7635, "env_steps": 4691558399, "loss": 0.014695572666823864, "avg_return": 0.8624435663223267, "regret": 0.0007496345788240433, "entropy": 0.08468756079673767, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:57.733582Z", "loop": 7636, "env_steps": 4692172799, "loss": 0.01484072394669056, "avg_return": 0.8630880117416382, "regret": 0.0007496345788240433, "entropy": 0.08242780715227127, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:58.589376Z", "loop": 7637, "env_steps": 4692787199, "loss": 0.015366124920547009, "avg_return": 0.8624967932701111, "regret": 0.0007496345788240433, "entropy": 0.08384765684604645, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:12:59.446035Z", "loop": 7638, "env_steps": 4693401599, "loss": 0.015559564344584942, "avg_return": 0.8621701002120972, "regret": 0.0007496345788240433, "entropy": 0.08569186925888062, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:00.302124Z", "loop": 7639, "env_steps": 4694015999, "loss": 0.01525925099849701, "avg_return": 0.8623663783073425, "regret": 0.0007496345788240433, "entropy": 0.08480510860681534, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:01.198958Z", "loop": 7640, "env_steps": 4694630399, "loss": 0.01418333686888218, "avg_return": 0.8618242740631104, "regret": 0.0012388667091727257, "entropy": 0.08302204310894012, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:02.054935Z", "loop": 7641, "env_steps": 4695244799, "loss": 0.014649649150669575, "avg_return": 0.8629286885261536, "regret": 0.0012388667091727257, "entropy": 0.08230248838663101, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:02.911173Z", "loop": 7642, "env_steps": 4695859199, "loss": 0.014418497681617737, "avg_return": 0.8622462153434753, "regret": 0.0012388667091727257, "entropy": 0.0764133632183075, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:03.766765Z", "loop": 7643, "env_steps": 4696473599, "loss": 0.013801109977066517, "avg_return": 0.8631458878517151, "regret": 0.0012388667091727257, "entropy": 0.07923176884651184, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:04.622405Z", "loop": 7644, "env_steps": 4697087999, "loss": 0.01618782989680767, "avg_return": 0.8628098964691162, "regret": 0.0012388667091727257, "entropy": 0.09189094603061676, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:05.478326Z", "loop": 7645, "env_steps": 4697702399, "loss": 0.015392961911857128, "avg_return": 0.861516535282135, "regret": 0.0012388667091727257, "entropy": 0.08706928044557571, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:06.334871Z", "loop": 7646, "env_steps": 4698316799, "loss": 0.01561937015503645, "avg_return": 0.8613808155059814, "regret": 0.0012388667091727257, "entropy": 0.09272333979606628, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:07.192459Z", "loop": 7647, "env_steps": 4698931199, "loss": 0.016625704243779182, "avg_return": 0.8621319532394409, "regret": 0.0012388667091727257, "entropy": 0.09329632669687271, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:08.049246Z", "loop": 7648, "env_steps": 4699545599, "loss": 0.018089406192302704, "avg_return": 0.8607773780822754, "regret": 0.0012388667091727257, "entropy": 0.10435421764850616, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:08.905571Z", "loop": 7649, "env_steps": 4700159999, "loss": 0.018868491053581238, "avg_return": 0.8602179288864136, "regret": 0.0012388667091727257, "entropy": 0.10627809166908264, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:09.802613Z", "loop": 7650, "env_steps": 4700774399, "loss": 0.01808081939816475, "avg_return": 0.8601731657981873, "regret": 0.003551381640136242, "entropy": 0.10297336429357529, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:10.658743Z", "loop": 7651, "env_steps": 4701388799, "loss": 0.017526661977171898, "avg_return": 0.8606753945350647, "regret": 0.003551381640136242, "entropy": 0.10113074630498886, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:11.514423Z", "loop": 7652, "env_steps": 4702003199, "loss": 0.01702979765832424, "avg_return": 0.8593323230743408, "regret": 0.003551381640136242, "entropy": 0.09926693886518478, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:12.370040Z", "loop": 7653, "env_steps": 4702617599, "loss": 0.0157325379550457, "avg_return": 0.8620350360870361, "regret": 0.003551381640136242, "entropy": 0.09269371628761292, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:13.224683Z", "loop": 7654, "env_steps": 4703231999, "loss": 0.016225900501012802, "avg_return": 0.8616585731506348, "regret": 0.003551381640136242, "entropy": 0.09058067947626114, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:14.079450Z", "loop": 7655, "env_steps": 4703846399, "loss": 0.01616751030087471, "avg_return": 0.8620783686637878, "regret": 0.003551381640136242, "entropy": 0.0849936380982399, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:14.935424Z", "loop": 7656, "env_steps": 4704460799, "loss": 0.01503640878945589, "avg_return": 0.862852931022644, "regret": 0.003551381640136242, "entropy": 0.08774596452713013, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:15.791414Z", "loop": 7657, "env_steps": 4705075199, "loss": 0.01609673909842968, "avg_return": 0.8622567057609558, "regret": 0.003551381640136242, "entropy": 0.09170109033584595, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:16.646263Z", "loop": 7658, "env_steps": 4705689599, "loss": 0.016958601772785187, "avg_return": 0.8639878630638123, "regret": 0.003551381640136242, "entropy": 0.09115440398454666, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:17.501488Z", "loop": 7659, "env_steps": 4706303999, "loss": 0.014920969493687153, "avg_return": 0.8625365495681763, "regret": 0.003551381640136242, "entropy": 0.08436907827854156, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:18.398669Z", "loop": 7660, "env_steps": 4706918399, "loss": 0.015484211035072803, "avg_return": 0.8646641373634338, "regret": 0.0007575824856758118, "entropy": 0.084608294069767, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:19.254847Z", "loop": 7661, "env_steps": 4707532799, "loss": 0.01548709999769926, "avg_return": 0.8624858856201172, "regret": 0.0007575824856758118, "entropy": 0.08653819561004639, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:20.110393Z", "loop": 7662, "env_steps": 4708147199, "loss": 0.014329922385513783, "avg_return": 0.8620072603225708, "regret": 0.0007575824856758118, "entropy": 0.0800585001707077, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:20.965203Z", "loop": 7663, "env_steps": 4708761599, "loss": 0.014672741293907166, "avg_return": 0.8631918430328369, "regret": 0.0007575824856758118, "entropy": 0.07916654646396637, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:21.821000Z", "loop": 7664, "env_steps": 4709375999, "loss": 0.014517954550683498, "avg_return": 0.8639890551567078, "regret": 0.0007575824856758118, "entropy": 0.08087212592363358, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:22.676830Z", "loop": 7665, "env_steps": 4709990399, "loss": 0.014247256331145763, "avg_return": 0.8619665503501892, "regret": 0.0007575824856758118, "entropy": 0.08154948800802231, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:23.532848Z", "loop": 7666, "env_steps": 4710604799, "loss": 0.014494242146611214, "avg_return": 0.8631517887115479, "regret": 0.0007575824856758118, "entropy": 0.07947907596826553, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:24.388232Z", "loop": 7667, "env_steps": 4711219199, "loss": 0.014737236313521862, "avg_return": 0.8615514039993286, "regret": 0.0007575824856758118, "entropy": 0.08042950928211212, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:25.243205Z", "loop": 7668, "env_steps": 4711833599, "loss": 0.014531699009239674, "avg_return": 0.8636692762374878, "regret": 0.0007575824856758118, "entropy": 0.07615240663290024, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:26.099024Z", "loop": 7669, "env_steps": 4712447999, "loss": 0.014482964761555195, "avg_return": 0.8625754714012146, "regret": 0.0007575824856758118, "entropy": 0.07564251124858856, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:26.994562Z", "loop": 7670, "env_steps": 4713062399, "loss": 0.014606117270886898, "avg_return": 0.863037645816803, "regret": 0.0006243825191631913, "entropy": 0.07966789603233337, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:27.851349Z", "loop": 7671, "env_steps": 4713676799, "loss": 0.012948311865329742, "avg_return": 0.8631803393363953, "regret": 0.0006243825191631913, "entropy": 0.07608188688755035, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:28.706621Z", "loop": 7672, "env_steps": 4714291199, "loss": 0.013316432945430279, "avg_return": 0.8621222972869873, "regret": 0.0006243825191631913, "entropy": 0.07585925608873367, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:29.561852Z", "loop": 7673, "env_steps": 4714905599, "loss": 0.013287325389683247, "avg_return": 0.8617017865180969, "regret": 0.0006243825191631913, "entropy": 0.07514111697673798, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:30.417512Z", "loop": 7674, "env_steps": 4715519999, "loss": 0.014710308983922005, "avg_return": 0.863844633102417, "regret": 0.0006243825191631913, "entropy": 0.07782498002052307, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:31.273169Z", "loop": 7675, "env_steps": 4716134399, "loss": 0.013678820803761482, "avg_return": 0.8624860048294067, "regret": 0.0006243825191631913, "entropy": 0.07604784518480301, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:32.128669Z", "loop": 7676, "env_steps": 4716748799, "loss": 0.015056425705552101, "avg_return": 0.8625198602676392, "regret": 0.0006243825191631913, "entropy": 0.07813853025436401, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:32.983737Z", "loop": 7677, "env_steps": 4717363199, "loss": 0.014409380964934826, "avg_return": 0.8631195425987244, "regret": 0.0006243825191631913, "entropy": 0.07721961289644241, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:33.841084Z", "loop": 7678, "env_steps": 4717977599, "loss": 0.0145563380792737, "avg_return": 0.863379955291748, "regret": 0.0006243825191631913, "entropy": 0.08002115041017532, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:34.698686Z", "loop": 7679, "env_steps": 4718591999, "loss": 0.014009460806846619, "avg_return": 0.8625680804252625, "regret": 0.0006243825191631913, "entropy": 0.0787462443113327, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:35.596554Z", "loop": 7680, "env_steps": 4719206399, "loss": 0.014636627398431301, "avg_return": 0.861778974533081, "regret": 0.0009148305980488658, "entropy": 0.07639273256063461, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:36.453699Z", "loop": 7681, "env_steps": 4719820799, "loss": 0.01378841232508421, "avg_return": 0.862945556640625, "regret": 0.0009148305980488658, "entropy": 0.07341533154249191, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:37.309914Z", "loop": 7682, "env_steps": 4720435199, "loss": 0.014468418434262276, "avg_return": 0.8625413179397583, "regret": 0.0009148305980488658, "entropy": 0.0783814936876297, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:38.167095Z", "loop": 7683, "env_steps": 4721049599, "loss": 0.015002885833382607, "avg_return": 0.8626729249954224, "regret": 0.0009148305980488658, "entropy": 0.0771830677986145, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:39.023596Z", "loop": 7684, "env_steps": 4721663999, "loss": 0.014472891576588154, "avg_return": 0.8624876141548157, "regret": 0.0009148305980488658, "entropy": 0.08024109899997711, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:39.880491Z", "loop": 7685, "env_steps": 4722278399, "loss": 0.01422214787453413, "avg_return": 0.8614986538887024, "regret": 0.0009148305980488658, "entropy": 0.07969574630260468, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:40.736921Z", "loop": 7686, "env_steps": 4722892799, "loss": 0.015141998417675495, "avg_return": 0.8605813980102539, "regret": 0.0009148305980488658, "entropy": 0.08192245662212372, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:41.593410Z", "loop": 7687, "env_steps": 4723507199, "loss": 0.014763309620320797, "avg_return": 0.8622168302536011, "regret": 0.0009148305980488658, "entropy": 0.07991129159927368, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:42.449937Z", "loop": 7688, "env_steps": 4724121599, "loss": 0.014503809623420238, "avg_return": 0.8614161610603333, "regret": 0.0009148305980488658, "entropy": 0.08063957840204239, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:43.306186Z", "loop": 7689, "env_steps": 4724735999, "loss": 0.014846369624137878, "avg_return": 0.8618929982185364, "regret": 0.0009148305980488658, "entropy": 0.0845341756939888, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:44.202987Z", "loop": 7690, "env_steps": 4725350399, "loss": 0.014099444262683392, "avg_return": 0.8602311611175537, "regret": 0.0029492073226720095, "entropy": 0.07940197736024857, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:45.059998Z", "loop": 7691, "env_steps": 4725964799, "loss": 0.016902083531022072, "avg_return": 0.8587213158607483, "regret": 0.0029492073226720095, "entropy": 0.08774092048406601, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:45.915023Z", "loop": 7692, "env_steps": 4726579199, "loss": 0.014801496639847755, "avg_return": 0.8595780730247498, "regret": 0.0029492073226720095, "entropy": 0.08126294612884521, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:46.770617Z", "loop": 7693, "env_steps": 4727193599, "loss": 0.013970538973808289, "avg_return": 0.8607693910598755, "regret": 0.0029492073226720095, "entropy": 0.07849528640508652, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:47.626473Z", "loop": 7694, "env_steps": 4727807999, "loss": 0.015179440379142761, "avg_return": 0.8607503175735474, "regret": 0.0029492073226720095, "entropy": 0.08258041739463806, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:48.482570Z", "loop": 7695, "env_steps": 4728422399, "loss": 0.013697315938770771, "avg_return": 0.8620884418487549, "regret": 0.0029492073226720095, "entropy": 0.08029235899448395, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:49.338361Z", "loop": 7696, "env_steps": 4729036799, "loss": 0.013945397920906544, "avg_return": 0.8631198406219482, "regret": 0.0029492073226720095, "entropy": 0.07958908379077911, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:50.194711Z", "loop": 7697, "env_steps": 4729651199, "loss": 0.013099412433803082, "avg_return": 0.8623829483985901, "regret": 0.0029492073226720095, "entropy": 0.07756318151950836, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:51.050215Z", "loop": 7698, "env_steps": 4730265599, "loss": 0.013840137980878353, "avg_return": 0.8637325167655945, "regret": 0.0029492073226720095, "entropy": 0.075926274061203, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:51.906734Z", "loop": 7699, "env_steps": 4730879999, "loss": 0.013495947234332561, "avg_return": 0.8616167306900024, "regret": 0.0029492073226720095, "entropy": 0.07362393289804459, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:52.799759Z", "loop": 7700, "env_steps": 4731494399, "loss": 0.013285678811371326, "avg_return": 0.8637551069259644, "regret": 0.000769126636441797, "entropy": 0.07676208764314651, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:53.655755Z", "loop": 7701, "env_steps": 4732108799, "loss": 0.013084878213703632, "avg_return": 0.8637219667434692, "regret": 0.000769126636441797, "entropy": 0.0773186907172203, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:54.512682Z", "loop": 7702, "env_steps": 4732723199, "loss": 0.014469104818999767, "avg_return": 0.864105224609375, "regret": 0.000769126636441797, "entropy": 0.07440003007650375, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:55.369257Z", "loop": 7703, "env_steps": 4733337599, "loss": 0.013637411408126354, "avg_return": 0.8631192445755005, "regret": 0.000769126636441797, "entropy": 0.07318279147148132, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:56.224280Z", "loop": 7704, "env_steps": 4733951999, "loss": 0.013594335876405239, "avg_return": 0.8620578050613403, "regret": 0.000769126636441797, "entropy": 0.07476437836885452, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:57.079577Z", "loop": 7705, "env_steps": 4734566399, "loss": 0.013831980526447296, "avg_return": 0.8624383807182312, "regret": 0.000769126636441797, "entropy": 0.0744759738445282, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:57.935461Z", "loop": 7706, "env_steps": 4735180799, "loss": 0.013053707778453827, "avg_return": 0.8607626557350159, "regret": 0.000769126636441797, "entropy": 0.07326640188694, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:58.792573Z", "loop": 7707, "env_steps": 4735795199, "loss": 0.013116225600242615, "avg_return": 0.8631191253662109, "regret": 0.000769126636441797, "entropy": 0.07258140295743942, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:13:59.648506Z", "loop": 7708, "env_steps": 4736409599, "loss": 0.014244942925870419, "avg_return": 0.8624086976051331, "regret": 0.000769126636441797, "entropy": 0.07542029023170471, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:00.503334Z", "loop": 7709, "env_steps": 4737023999, "loss": 0.013952764682471752, "avg_return": 0.8632603287696838, "regret": 0.000769126636441797, "entropy": 0.07779223471879959, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:01.399196Z", "loop": 7710, "env_steps": 4737638399, "loss": 0.013976785354316235, "avg_return": 0.8622100949287415, "regret": 0.0006923230248503387, "entropy": 0.07596106827259064, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:02.256948Z", "loop": 7711, "env_steps": 4738252799, "loss": 0.013872094452381134, "avg_return": 0.8627738356590271, "regret": 0.0006923230248503387, "entropy": 0.07628573477268219, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:03.112705Z", "loop": 7712, "env_steps": 4738867199, "loss": 0.013470395468175411, "avg_return": 0.8629670143127441, "regret": 0.0006923230248503387, "entropy": 0.07247558236122131, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:03.969001Z", "loop": 7713, "env_steps": 4739481599, "loss": 0.013527375645935535, "avg_return": 0.8626917004585266, "regret": 0.0006923230248503387, "entropy": 0.07574547827243805, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:04.825163Z", "loop": 7714, "env_steps": 4740095999, "loss": 0.01450850535184145, "avg_return": 0.8622995018959045, "regret": 0.0006923230248503387, "entropy": 0.07521867007017136, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:05.681625Z", "loop": 7715, "env_steps": 4740710399, "loss": 0.01386891771107912, "avg_return": 0.862242579460144, "regret": 0.0006923230248503387, "entropy": 0.07591415196657181, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:06.537633Z", "loop": 7716, "env_steps": 4741324799, "loss": 0.013544340617954731, "avg_return": 0.8624662756919861, "regret": 0.0006923230248503387, "entropy": 0.07399766147136688, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:07.393218Z", "loop": 7717, "env_steps": 4741939199, "loss": 0.014096163213253021, "avg_return": 0.8633443117141724, "regret": 0.0006923230248503387, "entropy": 0.0741095021367073, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:08.248953Z", "loop": 7718, "env_steps": 4742553599, "loss": 0.01482824981212616, "avg_return": 0.863280177116394, "regret": 0.0006923230248503387, "entropy": 0.07830836623907089, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:09.104162Z", "loop": 7719, "env_steps": 4743167999, "loss": 0.013802859000861645, "avg_return": 0.8631561398506165, "regret": 0.0006923230248503387, "entropy": 0.07794137299060822, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:10.001734Z", "loop": 7720, "env_steps": 4743782399, "loss": 0.014748804271221161, "avg_return": 0.8637520670890808, "regret": 0.0005573455127887428, "entropy": 0.0783257856965065, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:10.857449Z", "loop": 7721, "env_steps": 4744396799, "loss": 0.01437627524137497, "avg_return": 0.8641538619995117, "regret": 0.0005573455127887428, "entropy": 0.08051782101392746, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:11.713920Z", "loop": 7722, "env_steps": 4745011199, "loss": 0.014677241444587708, "avg_return": 0.8618841767311096, "regret": 0.0005573455127887428, "entropy": 0.08269605785608292, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:12.570278Z", "loop": 7723, "env_steps": 4745625599, "loss": 0.015540609136223793, "avg_return": 0.8637129664421082, "regret": 0.0005573455127887428, "entropy": 0.08509896695613861, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:13.425670Z", "loop": 7724, "env_steps": 4746239999, "loss": 0.01544987317174673, "avg_return": 0.8633309006690979, "regret": 0.0005573455127887428, "entropy": 0.08523056656122208, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:14.281439Z", "loop": 7725, "env_steps": 4746854399, "loss": 0.01587521843612194, "avg_return": 0.8633488416671753, "regret": 0.0005573455127887428, "entropy": 0.09135839343070984, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:15.138084Z", "loop": 7726, "env_steps": 4747468799, "loss": 0.016639044508337975, "avg_return": 0.8618770837783813, "regret": 0.0005573455127887428, "entropy": 0.09292516112327576, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:15.992489Z", "loop": 7727, "env_steps": 4748083199, "loss": 0.01823660358786583, "avg_return": 0.862712025642395, "regret": 0.0005573455127887428, "entropy": 0.09623190760612488, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:16.846989Z", "loop": 7728, "env_steps": 4748697599, "loss": 0.017419246956706047, "avg_return": 0.8618797063827515, "regret": 0.0005573455127887428, "entropy": 0.09546446055173874, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:17.703305Z", "loop": 7729, "env_steps": 4749311999, "loss": 0.018088260665535927, "avg_return": 0.8608559370040894, "regret": 0.0005573455127887428, "entropy": 0.10479574650526047, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:18.600920Z", "loop": 7730, "env_steps": 4749926399, "loss": 0.017824124544858932, "avg_return": 0.861835241317749, "regret": 0.0022164604160934687, "entropy": 0.1030612587928772, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:19.456268Z", "loop": 7731, "env_steps": 4750540799, "loss": 0.01891574077308178, "avg_return": 0.8592130541801453, "regret": 0.0022164604160934687, "entropy": 0.10447985678911209, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:20.310602Z", "loop": 7732, "env_steps": 4751155199, "loss": 0.01923220232129097, "avg_return": 0.8573533296585083, "regret": 0.0022164604160934687, "entropy": 0.10420544445514679, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:21.165079Z", "loop": 7733, "env_steps": 4751769599, "loss": 0.0211024172604084, "avg_return": 0.8555464148521423, "regret": 0.0022164604160934687, "entropy": 0.11134473979473114, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:22.021459Z", "loop": 7734, "env_steps": 4752383999, "loss": 0.02280758135020733, "avg_return": 0.8527630567550659, "regret": 0.0022164604160934687, "entropy": 0.1201539933681488, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:22.877578Z", "loop": 7735, "env_steps": 4752998399, "loss": 0.022786714136600494, "avg_return": 0.84906005859375, "regret": 0.0022164604160934687, "entropy": 0.1144416406750679, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:23.732960Z", "loop": 7736, "env_steps": 4753612799, "loss": 0.021328015252947807, "avg_return": 0.8471654653549194, "regret": 0.0022164604160934687, "entropy": 0.11194662004709244, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:24.588727Z", "loop": 7737, "env_steps": 4754227199, "loss": 0.020974721759557724, "avg_return": 0.8483738303184509, "regret": 0.0022164604160934687, "entropy": 0.11496321111917496, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:25.444652Z", "loop": 7738, "env_steps": 4754841599, "loss": 0.021490048617124557, "avg_return": 0.8502762317657471, "regret": 0.0022164604160934687, "entropy": 0.11167493462562561, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:26.301168Z", "loop": 7739, "env_steps": 4755455999, "loss": 0.021097572520375252, "avg_return": 0.8497557044029236, "regret": 0.0022164604160934687, "entropy": 0.11064257472753525, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:27.199477Z", "loop": 7740, "env_steps": 4756070399, "loss": 0.020896781235933304, "avg_return": 0.8542910218238831, "regret": 0.009616776369512081, "entropy": 0.11084849387407303, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:28.054899Z", "loop": 7741, "env_steps": 4756684799, "loss": 0.01995517499744892, "avg_return": 0.8558670282363892, "regret": 0.009616776369512081, "entropy": 0.10968849807977676, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:28.911310Z", "loop": 7742, "env_steps": 4757299199, "loss": 0.020342737436294556, "avg_return": 0.8575596213340759, "regret": 0.009616776369512081, "entropy": 0.11079563200473785, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:29.767738Z", "loop": 7743, "env_steps": 4757913599, "loss": 0.020122546702623367, "avg_return": 0.8585537672042847, "regret": 0.009616776369512081, "entropy": 0.1068042516708374, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:30.624485Z", "loop": 7744, "env_steps": 4758527999, "loss": 0.020098688080906868, "avg_return": 0.8565820455551147, "regret": 0.009616776369512081, "entropy": 0.11236030608415604, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:31.481422Z", "loop": 7745, "env_steps": 4759142399, "loss": 0.02076665498316288, "avg_return": 0.8598507642745972, "regret": 0.009616776369512081, "entropy": 0.11103086173534393, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:32.336952Z", "loop": 7746, "env_steps": 4759756799, "loss": 0.021811366081237793, "avg_return": 0.859294056892395, "regret": 0.009616776369512081, "entropy": 0.11572332680225372, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:33.193596Z", "loop": 7747, "env_steps": 4760371199, "loss": 0.023431312292814255, "avg_return": 0.8613999485969543, "regret": 0.009616776369512081, "entropy": 0.12223903089761734, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:34.049649Z", "loop": 7748, "env_steps": 4760985599, "loss": 0.022691387683153152, "avg_return": 0.8617199063301086, "regret": 0.009616776369512081, "entropy": 0.1146855279803276, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:34.905277Z", "loop": 7749, "env_steps": 4761599999, "loss": 0.020978791639208794, "avg_return": 0.862711489200592, "regret": 0.009616776369512081, "entropy": 0.1091882511973381, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:35.801849Z", "loop": 7750, "env_steps": 4762214399, "loss": 0.020343249663710594, "avg_return": 0.8635860681533813, "regret": 0.0012879178393632174, "entropy": 0.1081196516752243, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:36.656560Z", "loop": 7751, "env_steps": 4762828799, "loss": 0.020510192960500717, "avg_return": 0.8620583415031433, "regret": 0.0012879178393632174, "entropy": 0.1057494580745697, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:37.512656Z", "loop": 7752, "env_steps": 4763443199, "loss": 0.02117936871945858, "avg_return": 0.8628329634666443, "regret": 0.0012879178393632174, "entropy": 0.11084157973527908, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:38.368817Z", "loop": 7753, "env_steps": 4764057599, "loss": 0.020885605365037918, "avg_return": 0.8644112348556519, "regret": 0.0012879178393632174, "entropy": 0.10430959612131119, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:39.224304Z", "loop": 7754, "env_steps": 4764671999, "loss": 0.019668258726596832, "avg_return": 0.8620599508285522, "regret": 0.0012879178393632174, "entropy": 0.10376101732254028, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:40.080149Z", "loop": 7755, "env_steps": 4765286399, "loss": 0.020760681480169296, "avg_return": 0.8622182607650757, "regret": 0.0012879178393632174, "entropy": 0.10679402202367783, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:40.936020Z", "loop": 7756, "env_steps": 4765900799, "loss": 0.0192717295140028, "avg_return": 0.8620408177375793, "regret": 0.0012879178393632174, "entropy": 0.10261299461126328, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:41.791581Z", "loop": 7757, "env_steps": 4766515199, "loss": 0.020068984478712082, "avg_return": 0.8618744015693665, "regret": 0.0012879178393632174, "entropy": 0.10122286528348923, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:42.647588Z", "loop": 7758, "env_steps": 4767129599, "loss": 0.01972069777548313, "avg_return": 0.8624709248542786, "regret": 0.0012879178393632174, "entropy": 0.09904155880212784, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:43.502295Z", "loop": 7759, "env_steps": 4767743999, "loss": 0.019265320152044296, "avg_return": 0.8615460395812988, "regret": 0.0012879178393632174, "entropy": 0.10228388756513596, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:44.397460Z", "loop": 7760, "env_steps": 4768358399, "loss": 0.021285410970449448, "avg_return": 0.8606407642364502, "regret": 0.0024657314643263817, "entropy": 0.10701514780521393, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:45.252086Z", "loop": 7761, "env_steps": 4768972799, "loss": 0.020421642810106277, "avg_return": 0.860518217086792, "regret": 0.0024657314643263817, "entropy": 0.10315291583538055, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:46.107433Z", "loop": 7762, "env_steps": 4769587199, "loss": 0.02084382437169552, "avg_return": 0.859783947467804, "regret": 0.0024657314643263817, "entropy": 0.10359346866607666, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:46.962199Z", "loop": 7763, "env_steps": 4770201599, "loss": 0.01993332803249359, "avg_return": 0.8608946204185486, "regret": 0.0024657314643263817, "entropy": 0.1032269224524498, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:47.818405Z", "loop": 7764, "env_steps": 4770815999, "loss": 0.022117482498288155, "avg_return": 0.8604168891906738, "regret": 0.0024657314643263817, "entropy": 0.11028144508600235, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:48.672929Z", "loop": 7765, "env_steps": 4771430399, "loss": 0.021672740578651428, "avg_return": 0.8588865399360657, "regret": 0.0024657314643263817, "entropy": 0.10836987942457199, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:49.528057Z", "loop": 7766, "env_steps": 4772044799, "loss": 0.020022869110107422, "avg_return": 0.8594883680343628, "regret": 0.0024657314643263817, "entropy": 0.10513564944267273, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:50.383831Z", "loop": 7767, "env_steps": 4772659199, "loss": 0.020428817719221115, "avg_return": 0.8600828051567078, "regret": 0.0024657314643263817, "entropy": 0.1038566529750824, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:51.239504Z", "loop": 7768, "env_steps": 4773273599, "loss": 0.020448856055736542, "avg_return": 0.8599807024002075, "regret": 0.0024657314643263817, "entropy": 0.10262202471494675, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:52.095397Z", "loop": 7769, "env_steps": 4773887999, "loss": 0.02054247073829174, "avg_return": 0.8605225086212158, "regret": 0.0024657314643263817, "entropy": 0.10361403971910477, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:52.989661Z", "loop": 7770, "env_steps": 4774502399, "loss": 0.019705018028616905, "avg_return": 0.8600795865058899, "regret": 0.002372405957430601, "entropy": 0.10217325389385223, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:53.845641Z", "loop": 7771, "env_steps": 4775116799, "loss": 0.01907438039779663, "avg_return": 0.8622030019760132, "regret": 0.002372405957430601, "entropy": 0.10206684470176697, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:54.703552Z", "loop": 7772, "env_steps": 4775731199, "loss": 0.01990411803126335, "avg_return": 0.8611890077590942, "regret": 0.002372405957430601, "entropy": 0.10249705612659454, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:55.558593Z", "loop": 7773, "env_steps": 4776345599, "loss": 0.020285816863179207, "avg_return": 0.8630848526954651, "regret": 0.002372405957430601, "entropy": 0.10334199666976929, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:56.414270Z", "loop": 7774, "env_steps": 4776959999, "loss": 0.019275616854429245, "avg_return": 0.8620969653129578, "regret": 0.002372405957430601, "entropy": 0.10137299448251724, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:57.271073Z", "loop": 7775, "env_steps": 4777574399, "loss": 0.01809919811785221, "avg_return": 0.8617583513259888, "regret": 0.002372405957430601, "entropy": 0.09697803109884262, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:58.127287Z", "loop": 7776, "env_steps": 4778188799, "loss": 0.017058279365301132, "avg_return": 0.8644096255302429, "regret": 0.002372405957430601, "entropy": 0.09274368733167648, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:58.982830Z", "loop": 7777, "env_steps": 4778803199, "loss": 0.016548097133636475, "avg_return": 0.8628630042076111, "regret": 0.002372405957430601, "entropy": 0.08754811435937881, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:14:59.838186Z", "loop": 7778, "env_steps": 4779417599, "loss": 0.015981482341885567, "avg_return": 0.8625829219818115, "regret": 0.002372405957430601, "entropy": 0.08771027624607086, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:00.694366Z", "loop": 7779, "env_steps": 4780031999, "loss": 0.01652541197836399, "avg_return": 0.8622623085975647, "regret": 0.002372405957430601, "entropy": 0.08891770988702774, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:01.594388Z", "loop": 7780, "env_steps": 4780646399, "loss": 0.017668627202510834, "avg_return": 0.8639537692070007, "regret": 0.0006700619705952704, "entropy": 0.09241724014282227, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:02.451707Z", "loop": 7781, "env_steps": 4781260799, "loss": 0.016289308667182922, "avg_return": 0.862788736820221, "regret": 0.0006700619705952704, "entropy": 0.08897878974676132, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:03.309866Z", "loop": 7782, "env_steps": 4781875199, "loss": 0.01648685522377491, "avg_return": 0.8625407218933105, "regret": 0.0006700619705952704, "entropy": 0.0922592356801033, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:04.165005Z", "loop": 7783, "env_steps": 4782489599, "loss": 0.017142055556178093, "avg_return": 0.8616620302200317, "regret": 0.0006700619705952704, "entropy": 0.09081906080245972, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:05.021871Z", "loop": 7784, "env_steps": 4783103999, "loss": 0.015605352818965912, "avg_return": 0.8629676699638367, "regret": 0.0006700619705952704, "entropy": 0.08670666068792343, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:05.876927Z", "loop": 7785, "env_steps": 4783718399, "loss": 0.016238803043961525, "avg_return": 0.8615077137947083, "regret": 0.0006700619705952704, "entropy": 0.09292791038751602, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:06.732215Z", "loop": 7786, "env_steps": 4784332799, "loss": 0.01692729815840721, "avg_return": 0.8603963255882263, "regret": 0.0006700619705952704, "entropy": 0.09445859491825104, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:07.587371Z", "loop": 7787, "env_steps": 4784947199, "loss": 0.016483867540955544, "avg_return": 0.8598048090934753, "regret": 0.0006700619705952704, "entropy": 0.08986365795135498, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:08.444552Z", "loop": 7788, "env_steps": 4785561599, "loss": 0.015564416535198689, "avg_return": 0.8610278367996216, "regret": 0.0006700619705952704, "entropy": 0.08858092874288559, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:09.300233Z", "loop": 7789, "env_steps": 4786175999, "loss": 0.01488468050956726, "avg_return": 0.8611082434654236, "regret": 0.0006700619705952704, "entropy": 0.086527518928051, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:10.194538Z", "loop": 7790, "env_steps": 4786790399, "loss": 0.014920547604560852, "avg_return": 0.8615948557853699, "regret": 0.0014065542491152883, "entropy": 0.08176273107528687, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:11.049126Z", "loop": 7791, "env_steps": 4787404799, "loss": 0.014421124942600727, "avg_return": 0.8618108034133911, "regret": 0.0014065542491152883, "entropy": 0.08292628824710846, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:11.903880Z", "loop": 7792, "env_steps": 4788019199, "loss": 0.014333832077682018, "avg_return": 0.8618102073669434, "regret": 0.0014065542491152883, "entropy": 0.0774918869137764, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:12.759185Z", "loop": 7793, "env_steps": 4788633599, "loss": 0.01347518153488636, "avg_return": 0.8630779385566711, "regret": 0.0014065542491152883, "entropy": 0.07761966437101364, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:13.615456Z", "loop": 7794, "env_steps": 4789247999, "loss": 0.01344703882932663, "avg_return": 0.8633362054824829, "regret": 0.0014065542491152883, "entropy": 0.07705842703580856, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:14.470173Z", "loop": 7795, "env_steps": 4789862399, "loss": 0.014559934847056866, "avg_return": 0.8611619472503662, "regret": 0.0014065542491152883, "entropy": 0.07736135274171829, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:15.326390Z", "loop": 7796, "env_steps": 4790476799, "loss": 0.015608035027980804, "avg_return": 0.8639364838600159, "regret": 0.0014065542491152883, "entropy": 0.08280735462903976, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:16.182592Z", "loop": 7797, "env_steps": 4791091199, "loss": 0.014353403821587563, "avg_return": 0.8628841638565063, "regret": 0.0014065542491152883, "entropy": 0.08061593770980835, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:17.037975Z", "loop": 7798, "env_steps": 4791705599, "loss": 0.014463044703006744, "avg_return": 0.861279308795929, "regret": 0.0014065542491152883, "entropy": 0.07938496768474579, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:17.894251Z", "loop": 7799, "env_steps": 4792319999, "loss": 0.014920269139111042, "avg_return": 0.8596857786178589, "regret": 0.0014065542491152883, "entropy": 0.08003677427768707, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:18.788850Z", "loop": 7800, "env_steps": 4792934399, "loss": 0.015523681417107582, "avg_return": 0.8605945110321045, "regret": 0.0024975098203867674, "entropy": 0.08562464267015457, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:19.643378Z", "loop": 7801, "env_steps": 4793548799, "loss": 0.014218802563846111, "avg_return": 0.8601528406143188, "regret": 0.0024975098203867674, "entropy": 0.07986848056316376, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:20.498018Z", "loop": 7802, "env_steps": 4794163199, "loss": 0.014960701577365398, "avg_return": 0.8596107959747314, "regret": 0.0024975098203867674, "entropy": 0.08297445625066757, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:21.353605Z", "loop": 7803, "env_steps": 4794777599, "loss": 0.016151120886206627, "avg_return": 0.8575008511543274, "regret": 0.0024975098203867674, "entropy": 0.08645465970039368, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:22.208841Z", "loop": 7804, "env_steps": 4795391999, "loss": 0.0175006240606308, "avg_return": 0.8600034713745117, "regret": 0.0024975098203867674, "entropy": 0.09224833548069, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:23.063816Z", "loop": 7805, "env_steps": 4796006399, "loss": 0.018582498654723167, "avg_return": 0.8602406978607178, "regret": 0.0024975098203867674, "entropy": 0.09553053230047226, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:23.918112Z", "loop": 7806, "env_steps": 4796620799, "loss": 0.018025849014520645, "avg_return": 0.8604170083999634, "regret": 0.0024975098203867674, "entropy": 0.09497231990098953, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:24.773720Z", "loop": 7807, "env_steps": 4797235199, "loss": 0.017394661903381348, "avg_return": 0.8589965105056763, "regret": 0.0024975098203867674, "entropy": 0.09456070512533188, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:25.629172Z", "loop": 7808, "env_steps": 4797849599, "loss": 0.01783585734665394, "avg_return": 0.8616114258766174, "regret": 0.0024975098203867674, "entropy": 0.09284302592277527, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:26.483853Z", "loop": 7809, "env_steps": 4798463999, "loss": 0.017192797735333443, "avg_return": 0.8623970746994019, "regret": 0.0024975098203867674, "entropy": 0.09430422633886337, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:27.379304Z", "loop": 7810, "env_steps": 4799078399, "loss": 0.019007645547389984, "avg_return": 0.8612647652626038, "regret": 0.0018013104563578963, "entropy": 0.10031694173812866, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:28.235514Z", "loop": 7811, "env_steps": 4799692799, "loss": 0.017966145649552345, "avg_return": 0.861622154712677, "regret": 0.0018013104563578963, "entropy": 0.0972784236073494, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:29.091719Z", "loop": 7812, "env_steps": 4800307199, "loss": 0.0176799725741148, "avg_return": 0.8619340062141418, "regret": 0.0018013104563578963, "entropy": 0.09517690539360046, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:29.946607Z", "loop": 7813, "env_steps": 4800921599, "loss": 0.016380544751882553, "avg_return": 0.8618676066398621, "regret": 0.0018013104563578963, "entropy": 0.09171003848314285, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:30.801012Z", "loop": 7814, "env_steps": 4801535999, "loss": 0.019318902865052223, "avg_return": 0.8614569306373596, "regret": 0.0018013104563578963, "entropy": 0.09838346391916275, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:31.656007Z", "loop": 7815, "env_steps": 4802150399, "loss": 0.019370509311556816, "avg_return": 0.8607831001281738, "regret": 0.0018013104563578963, "entropy": 0.09686363488435745, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:32.511865Z", "loop": 7816, "env_steps": 4802764799, "loss": 0.019341327250003815, "avg_return": 0.8603125214576721, "regret": 0.0018013104563578963, "entropy": 0.09917142242193222, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:33.367764Z", "loop": 7817, "env_steps": 4803379199, "loss": 0.02150545082986355, "avg_return": 0.8593126535415649, "regret": 0.0018013104563578963, "entropy": 0.11132536083459854, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:34.222927Z", "loop": 7818, "env_steps": 4803993599, "loss": 0.019631071016192436, "avg_return": 0.8603881001472473, "regret": 0.0018013104563578963, "entropy": 0.10703982412815094, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:35.079179Z", "loop": 7819, "env_steps": 4804607999, "loss": 0.020137667655944824, "avg_return": 0.8576186299324036, "regret": 0.0018013104563578963, "entropy": 0.10935677587985992, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:35.974261Z", "loop": 7820, "env_steps": 4805222399, "loss": 0.01968514733016491, "avg_return": 0.8583689332008362, "regret": 0.0042701843194663525, "entropy": 0.10369064658880234, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:36.829539Z", "loop": 7821, "env_steps": 4805836799, "loss": 0.01952107809484005, "avg_return": 0.8574417233467102, "regret": 0.0042701843194663525, "entropy": 0.1043919175863266, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:37.685184Z", "loop": 7822, "env_steps": 4806451199, "loss": 0.02106059156358242, "avg_return": 0.8587925434112549, "regret": 0.0042701843194663525, "entropy": 0.10620199888944626, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:38.540994Z", "loop": 7823, "env_steps": 4807065599, "loss": 0.018920134752988815, "avg_return": 0.8599717617034912, "regret": 0.0042701843194663525, "entropy": 0.10253547132015228, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:39.396448Z", "loop": 7824, "env_steps": 4807679999, "loss": 0.017953360453248024, "avg_return": 0.8591241836547852, "regret": 0.0042701843194663525, "entropy": 0.0979088768362999, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:40.252211Z", "loop": 7825, "env_steps": 4808294399, "loss": 0.01852233335375786, "avg_return": 0.8576934933662415, "regret": 0.0042701843194663525, "entropy": 0.09826846420764923, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:41.107078Z", "loop": 7826, "env_steps": 4808908799, "loss": 0.018145134672522545, "avg_return": 0.8598347902297974, "regret": 0.0042701843194663525, "entropy": 0.09862467646598816, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:41.962873Z", "loop": 7827, "env_steps": 4809523199, "loss": 0.019250860437750816, "avg_return": 0.8595351576805115, "regret": 0.0042701843194663525, "entropy": 0.1013818085193634, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:42.818506Z", "loop": 7828, "env_steps": 4810137599, "loss": 0.018595559522509575, "avg_return": 0.8604157567024231, "regret": 0.0042701843194663525, "entropy": 0.10262174159288406, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:43.674602Z", "loop": 7829, "env_steps": 4810751999, "loss": 0.01755489408969879, "avg_return": 0.8597463965415955, "regret": 0.0042701843194663525, "entropy": 0.09639549255371094, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:44.571011Z", "loop": 7830, "env_steps": 4811366399, "loss": 0.01968991570174694, "avg_return": 0.8597162961959839, "regret": 0.003741975873708725, "entropy": 0.10476537048816681, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:45.427155Z", "loop": 7831, "env_steps": 4811980799, "loss": 0.019402403384447098, "avg_return": 0.8597396016120911, "regret": 0.003741975873708725, "entropy": 0.10461205989122391, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:46.282064Z", "loop": 7832, "env_steps": 4812595199, "loss": 0.019532673060894012, "avg_return": 0.8585042357444763, "regret": 0.003741975873708725, "entropy": 0.1064687967300415, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:47.136954Z", "loop": 7833, "env_steps": 4813209599, "loss": 0.01947041228413582, "avg_return": 0.8591172695159912, "regret": 0.003741975873708725, "entropy": 0.1037226989865303, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:47.992019Z", "loop": 7834, "env_steps": 4813823999, "loss": 0.017708566039800644, "avg_return": 0.8602660298347473, "regret": 0.003741975873708725, "entropy": 0.09746909886598587, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:48.847757Z", "loop": 7835, "env_steps": 4814438399, "loss": 0.018254917114973068, "avg_return": 0.8603096604347229, "regret": 0.003741975873708725, "entropy": 0.09839417785406113, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:49.702836Z", "loop": 7836, "env_steps": 4815052799, "loss": 0.016974925994873047, "avg_return": 0.8610766530036926, "regret": 0.003741975873708725, "entropy": 0.09186402708292007, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:50.558527Z", "loop": 7837, "env_steps": 4815667199, "loss": 0.01720883883535862, "avg_return": 0.8613161444664001, "regret": 0.003741975873708725, "entropy": 0.09381887316703796, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:51.416054Z", "loop": 7838, "env_steps": 4816281599, "loss": 0.017572060227394104, "avg_return": 0.8617639541625977, "regret": 0.003741975873708725, "entropy": 0.09376291930675507, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:52.272538Z", "loop": 7839, "env_steps": 4816895999, "loss": 0.0183318592607975, "avg_return": 0.86199951171875, "regret": 0.003741975873708725, "entropy": 0.0946916788816452, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:53.168958Z", "loop": 7840, "env_steps": 4817510399, "loss": 0.016825279220938683, "avg_return": 0.8609911203384399, "regret": 0.002920476021245122, "entropy": 0.09331691265106201, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:54.023595Z", "loop": 7841, "env_steps": 4818124799, "loss": 0.01736147701740265, "avg_return": 0.8591954708099365, "regret": 0.002920476021245122, "entropy": 0.09022080898284912, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:54.879844Z", "loop": 7842, "env_steps": 4818739199, "loss": 0.019378039985895157, "avg_return": 0.8602445721626282, "regret": 0.002920476021245122, "entropy": 0.10011231899261475, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:55.736170Z", "loop": 7843, "env_steps": 4819353599, "loss": 0.01979229412972927, "avg_return": 0.8610632419586182, "regret": 0.002920476021245122, "entropy": 0.09860822558403015, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:56.593095Z", "loop": 7844, "env_steps": 4819967999, "loss": 0.01875082030892372, "avg_return": 0.860560953617096, "regret": 0.002920476021245122, "entropy": 0.09732174128293991, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:57.448751Z", "loop": 7845, "env_steps": 4820582399, "loss": 0.018372487276792526, "avg_return": 0.8620914816856384, "regret": 0.002920476021245122, "entropy": 0.09556645154953003, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:58.305021Z", "loop": 7846, "env_steps": 4821196799, "loss": 0.017708437517285347, "avg_return": 0.8602561354637146, "regret": 0.002920476021245122, "entropy": 0.09212081134319305, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:15:59.160843Z", "loop": 7847, "env_steps": 4821811199, "loss": 0.017889423295855522, "avg_return": 0.8603891134262085, "regret": 0.002920476021245122, "entropy": 0.09447341412305832, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:00.017539Z", "loop": 7848, "env_steps": 4822425599, "loss": 0.016295967623591423, "avg_return": 0.8609362840652466, "regret": 0.002920476021245122, "entropy": 0.09022259712219238, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:00.873799Z", "loop": 7849, "env_steps": 4823039999, "loss": 0.017884960398077965, "avg_return": 0.8603140711784363, "regret": 0.002920476021245122, "entropy": 0.09419258683919907, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:01.770165Z", "loop": 7850, "env_steps": 4823654399, "loss": 0.01710430532693863, "avg_return": 0.8607393503189087, "regret": 0.003399698995053768, "entropy": 0.09079349040985107, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:02.625497Z", "loop": 7851, "env_steps": 4824268799, "loss": 0.01707361452281475, "avg_return": 0.8597433567047119, "regret": 0.003399698995053768, "entropy": 0.09105371683835983, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:03.481115Z", "loop": 7852, "env_steps": 4824883199, "loss": 0.017022639513015747, "avg_return": 0.8615923523902893, "regret": 0.003399698995053768, "entropy": 0.09199551492929459, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:04.336716Z", "loop": 7853, "env_steps": 4825497599, "loss": 0.01878717541694641, "avg_return": 0.8606643080711365, "regret": 0.003399698995053768, "entropy": 0.09649106860160828, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:05.191852Z", "loop": 7854, "env_steps": 4826111999, "loss": 0.0187066700309515, "avg_return": 0.8616077899932861, "regret": 0.003399698995053768, "entropy": 0.09981116652488708, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:06.046584Z", "loop": 7855, "env_steps": 4826726399, "loss": 0.019648483023047447, "avg_return": 0.8621742725372314, "regret": 0.003399698995053768, "entropy": 0.1000981405377388, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:06.901272Z", "loop": 7856, "env_steps": 4827340799, "loss": 0.019319714978337288, "avg_return": 0.8613008856773376, "regret": 0.003399698995053768, "entropy": 0.1067371666431427, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:07.756361Z", "loop": 7857, "env_steps": 4827955199, "loss": 0.02142702043056488, "avg_return": 0.8570606708526611, "regret": 0.003399698995053768, "entropy": 0.11032716929912567, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:08.611941Z", "loop": 7858, "env_steps": 4828569599, "loss": 0.019192364066839218, "avg_return": 0.8549371361732483, "regret": 0.003399698995053768, "entropy": 0.10432218015193939, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:09.466987Z", "loop": 7859, "env_steps": 4829183999, "loss": 0.020962076261639595, "avg_return": 0.8577008247375488, "regret": 0.003399698995053768, "entropy": 0.10623745620250702, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:10.362665Z", "loop": 7860, "env_steps": 4829798399, "loss": 0.018163302913308144, "avg_return": 0.8611221313476562, "regret": 0.002752867294475436, "entropy": 0.09704052656888962, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:11.219716Z", "loop": 7861, "env_steps": 4830412799, "loss": 0.01722538098692894, "avg_return": 0.8616716861724854, "regret": 0.002752867294475436, "entropy": 0.09653570502996445, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:12.075564Z", "loop": 7862, "env_steps": 4831027199, "loss": 0.01653500832617283, "avg_return": 0.8620317578315735, "regret": 0.002752867294475436, "entropy": 0.08571160584688187, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:12.931785Z", "loop": 7863, "env_steps": 4831641599, "loss": 0.016903409734368324, "avg_return": 0.8609165549278259, "regret": 0.002752867294475436, "entropy": 0.08879903703927994, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:13.787876Z", "loop": 7864, "env_steps": 4832255999, "loss": 0.018462756648659706, "avg_return": 0.8600296974182129, "regret": 0.002752867294475436, "entropy": 0.09615743905305862, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:14.643780Z", "loop": 7865, "env_steps": 4832870399, "loss": 0.019290026277303696, "avg_return": 0.8587528467178345, "regret": 0.002752867294475436, "entropy": 0.10114847868680954, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:15.499941Z", "loop": 7866, "env_steps": 4833484799, "loss": 0.020871669054031372, "avg_return": 0.8548294305801392, "regret": 0.002752867294475436, "entropy": 0.10765426605939865, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:16.355675Z", "loop": 7867, "env_steps": 4834099199, "loss": 0.025153174996376038, "avg_return": 0.8502388596534729, "regret": 0.002752867294475436, "entropy": 0.12348929047584534, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:17.211401Z", "loop": 7868, "env_steps": 4834713599, "loss": 0.02640492655336857, "avg_return": 0.8464492559432983, "regret": 0.002752867294475436, "entropy": 0.13323844969272614, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:18.068561Z", "loop": 7869, "env_steps": 4835327999, "loss": 0.028314009308815002, "avg_return": 0.8468974828720093, "regret": 0.002752867294475436, "entropy": 0.13973172008991241, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:18.964642Z", "loop": 7870, "env_steps": 4835942399, "loss": 0.028087807819247246, "avg_return": 0.8513637781143188, "regret": 0.011240498162806034, "entropy": 0.13391444087028503, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:19.820361Z", "loop": 7871, "env_steps": 4836556799, "loss": 0.027228152379393578, "avg_return": 0.856849193572998, "regret": 0.011240498162806034, "entropy": 0.13074007630348206, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:20.676543Z", "loop": 7872, "env_steps": 4837171199, "loss": 0.026123130694031715, "avg_return": 0.8587853312492371, "regret": 0.011240498162806034, "entropy": 0.1279626339673996, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:21.532195Z", "loop": 7873, "env_steps": 4837785599, "loss": 0.02426101267337799, "avg_return": 0.8587003946304321, "regret": 0.011240498162806034, "entropy": 0.12591877579689026, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:22.387715Z", "loop": 7874, "env_steps": 4838399999, "loss": 0.025572776794433594, "avg_return": 0.8594784736633301, "regret": 0.011240498162806034, "entropy": 0.12764741480350494, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:23.242790Z", "loop": 7875, "env_steps": 4839014399, "loss": 0.025546347722411156, "avg_return": 0.8581222891807556, "regret": 0.011240498162806034, "entropy": 0.13300716876983643, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:24.098268Z", "loop": 7876, "env_steps": 4839628799, "loss": 0.025153059512376785, "avg_return": 0.8562629222869873, "regret": 0.011240498162806034, "entropy": 0.13463567197322845, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:24.954995Z", "loop": 7877, "env_steps": 4840243199, "loss": 0.02572372369468212, "avg_return": 0.8554126024246216, "regret": 0.011240498162806034, "entropy": 0.13697999715805054, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:25.810714Z", "loop": 7878, "env_steps": 4840857599, "loss": 0.024312471970915794, "avg_return": 0.8550780415534973, "regret": 0.011240498162806034, "entropy": 0.12965691089630127, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:26.665358Z", "loop": 7879, "env_steps": 4841471999, "loss": 0.024440638720989227, "avg_return": 0.8594313859939575, "regret": 0.011240498162806034, "entropy": 0.1261259913444519, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:27.561575Z", "loop": 7880, "env_steps": 4842086399, "loss": 0.023667441681027412, "avg_return": 0.8596364259719849, "regret": 0.0035977535881102085, "entropy": 0.12397313863039017, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:28.417134Z", "loop": 7881, "env_steps": 4842700799, "loss": 0.022427920252084732, "avg_return": 0.8620320558547974, "regret": 0.0035977535881102085, "entropy": 0.11804497241973877, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:29.273771Z", "loop": 7882, "env_steps": 4843315199, "loss": 0.023012327030301094, "avg_return": 0.861598551273346, "regret": 0.0035977535881102085, "entropy": 0.12338898330926895, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:30.128336Z", "loop": 7883, "env_steps": 4843929599, "loss": 0.024676362052559853, "avg_return": 0.8611425757408142, "regret": 0.0035977535881102085, "entropy": 0.12704257667064667, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:30.983738Z", "loop": 7884, "env_steps": 4844543999, "loss": 0.027742454782128334, "avg_return": 0.8618847727775574, "regret": 0.0035977535881102085, "entropy": 0.13922634720802307, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:31.840310Z", "loop": 7885, "env_steps": 4845158399, "loss": 0.023540718480944633, "avg_return": 0.8622235059738159, "regret": 0.0035977535881102085, "entropy": 0.11899848282337189, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:32.695748Z", "loop": 7886, "env_steps": 4845772799, "loss": 0.020766455680131912, "avg_return": 0.8618395924568176, "regret": 0.0035977535881102085, "entropy": 0.10441721975803375, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:33.550759Z", "loop": 7887, "env_steps": 4846387199, "loss": 0.017319047823548317, "avg_return": 0.8621078729629517, "regret": 0.0035977535881102085, "entropy": 0.09666711091995239, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:34.406160Z", "loop": 7888, "env_steps": 4847001599, "loss": 0.016659481450915337, "avg_return": 0.861609935760498, "regret": 0.0035977535881102085, "entropy": 0.0907839834690094, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:35.261917Z", "loop": 7889, "env_steps": 4847615999, "loss": 0.01656344160437584, "avg_return": 0.8635809421539307, "regret": 0.0035977535881102085, "entropy": 0.08952009677886963, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:36.156646Z", "loop": 7890, "env_steps": 4848230399, "loss": 0.01698645018041134, "avg_return": 0.8623534440994263, "regret": 0.001260519027709961, "entropy": 0.09227454662322998, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:37.012395Z", "loop": 7891, "env_steps": 4848844799, "loss": 0.017634494230151176, "avg_return": 0.8606641888618469, "regret": 0.001260519027709961, "entropy": 0.09017980843782425, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:37.867766Z", "loop": 7892, "env_steps": 4849459199, "loss": 0.018109453842043877, "avg_return": 0.8616020083427429, "regret": 0.001260519027709961, "entropy": 0.09359154105186462, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:38.723518Z", "loop": 7893, "env_steps": 4850073599, "loss": 0.02091849409043789, "avg_return": 0.8624398112297058, "regret": 0.001260519027709961, "entropy": 0.10517812520265579, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:39.579632Z", "loop": 7894, "env_steps": 4850687999, "loss": 0.019255714491009712, "avg_return": 0.8629807829856873, "regret": 0.001260519027709961, "entropy": 0.10249309986829758, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:40.434703Z", "loop": 7895, "env_steps": 4851302399, "loss": 0.018965786322951317, "avg_return": 0.8612691164016724, "regret": 0.001260519027709961, "entropy": 0.10086177289485931, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:41.288974Z", "loop": 7896, "env_steps": 4851916799, "loss": 0.01898706704378128, "avg_return": 0.8605965375900269, "regret": 0.001260519027709961, "entropy": 0.09847047179937363, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:42.145416Z", "loop": 7897, "env_steps": 4852531199, "loss": 0.017282404005527496, "avg_return": 0.8596447110176086, "regret": 0.001260519027709961, "entropy": 0.09390703588724136, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:43.000861Z", "loop": 7898, "env_steps": 4853145599, "loss": 0.019015757367014885, "avg_return": 0.8606433272361755, "regret": 0.001260519027709961, "entropy": 0.09771579504013062, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:43.855997Z", "loop": 7899, "env_steps": 4853759999, "loss": 0.017699923366308212, "avg_return": 0.8601225018501282, "regret": 0.001260519027709961, "entropy": 0.09701699018478394, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:44.752910Z", "loop": 7900, "env_steps": 4854374399, "loss": 0.01696711964905262, "avg_return": 0.861901581287384, "regret": 0.0031572466250509024, "entropy": 0.0951351746916771, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:45.609572Z", "loop": 7901, "env_steps": 4854988799, "loss": 0.018487704917788506, "avg_return": 0.8622283935546875, "regret": 0.0031572466250509024, "entropy": 0.09619913250207901, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:46.466097Z", "loop": 7902, "env_steps": 4855603199, "loss": 0.018529681488871574, "avg_return": 0.8615412712097168, "regret": 0.0031572466250509024, "entropy": 0.0973561480641365, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:47.321307Z", "loop": 7903, "env_steps": 4856217599, "loss": 0.017855605110526085, "avg_return": 0.8615912199020386, "regret": 0.0031572466250509024, "entropy": 0.09878668934106827, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:48.177848Z", "loop": 7904, "env_steps": 4856831999, "loss": 0.018075384199619293, "avg_return": 0.8624957203865051, "regret": 0.0031572466250509024, "entropy": 0.09211308509111404, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:49.033930Z", "loop": 7905, "env_steps": 4857446399, "loss": 0.017230797559022903, "avg_return": 0.8627474904060364, "regret": 0.0031572466250509024, "entropy": 0.09117040783166885, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:49.889326Z", "loop": 7906, "env_steps": 4858060799, "loss": 0.017531923949718475, "avg_return": 0.8604689836502075, "regret": 0.0031572466250509024, "entropy": 0.09245306998491287, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:50.745283Z", "loop": 7907, "env_steps": 4858675199, "loss": 0.018373142927885056, "avg_return": 0.861972451210022, "regret": 0.0031572466250509024, "entropy": 0.09320749342441559, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:51.600961Z", "loop": 7908, "env_steps": 4859289599, "loss": 0.016995364800095558, "avg_return": 0.8625447750091553, "regret": 0.0031572466250509024, "entropy": 0.09140294790267944, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:52.457208Z", "loop": 7909, "env_steps": 4859903999, "loss": 0.016845189034938812, "avg_return": 0.8628751635551453, "regret": 0.0031572466250509024, "entropy": 0.09093222767114639, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:53.353491Z", "loop": 7910, "env_steps": 4860518399, "loss": 0.01715949736535549, "avg_return": 0.861507773399353, "regret": 0.0014216756680980325, "entropy": 0.09085983783006668, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:54.208814Z", "loop": 7911, "env_steps": 4861132799, "loss": 0.01871524564921856, "avg_return": 0.8615747094154358, "regret": 0.0014216756680980325, "entropy": 0.09348428249359131, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:55.063574Z", "loop": 7912, "env_steps": 4861747199, "loss": 0.018785184249281883, "avg_return": 0.8630707263946533, "regret": 0.0014216756680980325, "entropy": 0.10010819137096405, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:55.920358Z", "loop": 7913, "env_steps": 4862361599, "loss": 0.017583847045898438, "avg_return": 0.8605800867080688, "regret": 0.0014216756680980325, "entropy": 0.09153132885694504, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:56.775370Z", "loop": 7914, "env_steps": 4862975999, "loss": 0.017407191917300224, "avg_return": 0.8605621457099915, "regret": 0.0014216756680980325, "entropy": 0.09190469235181808, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:57.630159Z", "loop": 7915, "env_steps": 4863590399, "loss": 0.016453292220830917, "avg_return": 0.8617464303970337, "regret": 0.0014216756680980325, "entropy": 0.09105955809354782, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:58.485656Z", "loop": 7916, "env_steps": 4864204799, "loss": 0.016515348106622696, "avg_return": 0.8617718815803528, "regret": 0.0014216756680980325, "entropy": 0.08758820593357086, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:16:59.341939Z", "loop": 7917, "env_steps": 4864819199, "loss": 0.017511727288365364, "avg_return": 0.8612374067306519, "regret": 0.0014216756680980325, "entropy": 0.09382908046245575, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:00.197301Z", "loop": 7918, "env_steps": 4865433599, "loss": 0.016893833875656128, "avg_return": 0.8594982028007507, "regret": 0.0014216756680980325, "entropy": 0.08948180079460144, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:01.052051Z", "loop": 7919, "env_steps": 4866047999, "loss": 0.015611874870955944, "avg_return": 0.8598459959030151, "regret": 0.0014216756680980325, "entropy": 0.08447376638650894, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:01.945992Z", "loop": 7920, "env_steps": 4866662399, "loss": 0.015196921303868294, "avg_return": 0.85608971118927, "regret": 0.0045855059288442135, "entropy": 0.0806027427315712, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:02.801660Z", "loop": 7921, "env_steps": 4867276799, "loss": 0.015437512658536434, "avg_return": 0.8589661717414856, "regret": 0.0045855059288442135, "entropy": 0.08539502322673798, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:03.656706Z", "loop": 7922, "env_steps": 4867891199, "loss": 0.015905166044831276, "avg_return": 0.8575252294540405, "regret": 0.0045855059288442135, "entropy": 0.08691360056400299, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:04.510562Z", "loop": 7923, "env_steps": 4868505599, "loss": 0.015271225944161415, "avg_return": 0.8576940298080444, "regret": 0.0045855059288442135, "entropy": 0.08321696519851685, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:05.365087Z", "loop": 7924, "env_steps": 4869119999, "loss": 0.014464627020061016, "avg_return": 0.8580064177513123, "regret": 0.0045855059288442135, "entropy": 0.08073122799396515, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:06.221175Z", "loop": 7925, "env_steps": 4869734399, "loss": 0.014385181479156017, "avg_return": 0.859087347984314, "regret": 0.0045855059288442135, "entropy": 0.08021730184555054, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:07.077591Z", "loop": 7926, "env_steps": 4870348799, "loss": 0.01575884036719799, "avg_return": 0.8597450852394104, "regret": 0.0045855059288442135, "entropy": 0.08114483207464218, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:07.933875Z", "loop": 7927, "env_steps": 4870963199, "loss": 0.016293713822960854, "avg_return": 0.8614241480827332, "regret": 0.0045855059288442135, "entropy": 0.08552499115467072, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:08.789427Z", "loop": 7928, "env_steps": 4871577599, "loss": 0.014283944852650166, "avg_return": 0.8616226315498352, "regret": 0.0045855059288442135, "entropy": 0.07745649665594101, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:09.643272Z", "loop": 7929, "env_steps": 4872191999, "loss": 0.014672375284135342, "avg_return": 0.8603928685188293, "regret": 0.0045855059288442135, "entropy": 0.08204317092895508, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:10.537061Z", "loop": 7930, "env_steps": 4872806399, "loss": 0.01465949323028326, "avg_return": 0.8629511594772339, "regret": 0.0018512568203732371, "entropy": 0.08123677223920822, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:11.392126Z", "loop": 7931, "env_steps": 4873420799, "loss": 0.01596902310848236, "avg_return": 0.8618389964103699, "regret": 0.0018512568203732371, "entropy": 0.0837230384349823, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:12.247216Z", "loop": 7932, "env_steps": 4874035199, "loss": 0.01494048722088337, "avg_return": 0.8627268671989441, "regret": 0.0018512568203732371, "entropy": 0.08331812918186188, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:13.102670Z", "loop": 7933, "env_steps": 4874649599, "loss": 0.018099026754498482, "avg_return": 0.861579418182373, "regret": 0.0018512568203732371, "entropy": 0.09367891401052475, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:13.958393Z", "loop": 7934, "env_steps": 4875263999, "loss": 0.017338193953037262, "avg_return": 0.8606646656990051, "regret": 0.0018512568203732371, "entropy": 0.09390899538993835, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:14.813678Z", "loop": 7935, "env_steps": 4875878399, "loss": 0.017778191715478897, "avg_return": 0.8616469502449036, "regret": 0.0018512568203732371, "entropy": 0.08974714577198029, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:15.668667Z", "loop": 7936, "env_steps": 4876492799, "loss": 0.01712654158473015, "avg_return": 0.8622186779975891, "regret": 0.0018512568203732371, "entropy": 0.0893598422408104, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:16.523338Z", "loop": 7937, "env_steps": 4877107199, "loss": 0.016644751653075218, "avg_return": 0.8626750111579895, "regret": 0.0018512568203732371, "entropy": 0.08681782335042953, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:17.377973Z", "loop": 7938, "env_steps": 4877721599, "loss": 0.017338061705231667, "avg_return": 0.8613950610160828, "regret": 0.0018512568203732371, "entropy": 0.09266532957553864, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:18.233079Z", "loop": 7939, "env_steps": 4878335999, "loss": 0.017533179372549057, "avg_return": 0.8627431392669678, "regret": 0.0018512568203732371, "entropy": 0.09209717065095901, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:19.127824Z", "loop": 7940, "env_steps": 4878950399, "loss": 0.017990846186876297, "avg_return": 0.8622711300849915, "regret": 0.0012692251475527883, "entropy": 0.09527456760406494, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:19.984070Z", "loop": 7941, "env_steps": 4879564799, "loss": 0.01767183654010296, "avg_return": 0.8619304895401001, "regret": 0.0012692251475527883, "entropy": 0.09436521679162979, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:20.839012Z", "loop": 7942, "env_steps": 4880179199, "loss": 0.018232734873890877, "avg_return": 0.8636237978935242, "regret": 0.0012692251475527883, "entropy": 0.09484259784221649, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:21.695925Z", "loop": 7943, "env_steps": 4880793599, "loss": 0.019213156774640083, "avg_return": 0.8612568378448486, "regret": 0.0012692251475527883, "entropy": 0.0951942503452301, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:22.552292Z", "loop": 7944, "env_steps": 4881407999, "loss": 0.019578270614147186, "avg_return": 0.8610557317733765, "regret": 0.0012692251475527883, "entropy": 0.09716323018074036, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:23.408481Z", "loop": 7945, "env_steps": 4882022399, "loss": 0.019088435918092728, "avg_return": 0.8628660440444946, "regret": 0.0012692251475527883, "entropy": 0.0983780175447464, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:24.263310Z", "loop": 7946, "env_steps": 4882636799, "loss": 0.018526528030633926, "avg_return": 0.8629516959190369, "regret": 0.0012692251475527883, "entropy": 0.09663065522909164, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:25.117930Z", "loop": 7947, "env_steps": 4883251199, "loss": 0.018846115097403526, "avg_return": 0.8620181679725647, "regret": 0.0012692251475527883, "entropy": 0.09724211692810059, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:25.973036Z", "loop": 7948, "env_steps": 4883865599, "loss": 0.019277062267065048, "avg_return": 0.8619365692138672, "regret": 0.0012692251475527883, "entropy": 0.09970097243785858, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:26.828867Z", "loop": 7949, "env_steps": 4884479999, "loss": 0.019904756918549538, "avg_return": 0.8610872626304626, "regret": 0.0012692251475527883, "entropy": 0.10263947397470474, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:27.724893Z", "loop": 7950, "env_steps": 4885094399, "loss": 0.02240096963942051, "avg_return": 0.8619633316993713, "regret": 0.0025264841970056295, "entropy": 0.11146185547113419, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:28.579969Z", "loop": 7951, "env_steps": 4885708799, "loss": 0.02104121446609497, "avg_return": 0.8626378774642944, "regret": 0.0025264841970056295, "entropy": 0.10763505846261978, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:29.435662Z", "loop": 7952, "env_steps": 4886323199, "loss": 0.020909160375595093, "avg_return": 0.8607964515686035, "regret": 0.0025264841970056295, "entropy": 0.11138661950826645, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:30.292373Z", "loop": 7953, "env_steps": 4886937599, "loss": 0.02494199387729168, "avg_return": 0.8607600927352905, "regret": 0.0025264841970056295, "entropy": 0.12581543624401093, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:31.148786Z", "loop": 7954, "env_steps": 4887551999, "loss": 0.024438096210360527, "avg_return": 0.8621084690093994, "regret": 0.0025264841970056295, "entropy": 0.12346586585044861, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:32.003295Z", "loop": 7955, "env_steps": 4888166399, "loss": 0.025204500183463097, "avg_return": 0.8611238598823547, "regret": 0.0025264841970056295, "entropy": 0.124947689473629, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:32.857934Z", "loop": 7956, "env_steps": 4888780799, "loss": 0.024465864524245262, "avg_return": 0.8606339693069458, "regret": 0.0025264841970056295, "entropy": 0.12957115471363068, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:33.713954Z", "loop": 7957, "env_steps": 4889395199, "loss": 0.024872029200196266, "avg_return": 0.8607121109962463, "regret": 0.0025264841970056295, "entropy": 0.12655845284461975, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:34.569586Z", "loop": 7958, "env_steps": 4890009599, "loss": 0.02559155784547329, "avg_return": 0.8607452511787415, "regret": 0.0025264841970056295, "entropy": 0.12909209728240967, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:35.424159Z", "loop": 7959, "env_steps": 4890623999, "loss": 0.026182997971773148, "avg_return": 0.858974039554596, "regret": 0.0025264841970056295, "entropy": 0.13032087683677673, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:36.318260Z", "loop": 7960, "env_steps": 4891238399, "loss": 0.026050273329019547, "avg_return": 0.8600466847419739, "regret": 0.004129475448280573, "entropy": 0.13435544073581696, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:37.175129Z", "loop": 7961, "env_steps": 4891852799, "loss": 0.026792777702212334, "avg_return": 0.8580353260040283, "regret": 0.004129475448280573, "entropy": 0.13498982787132263, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:38.032308Z", "loop": 7962, "env_steps": 4892467199, "loss": 0.024805402383208275, "avg_return": 0.8598792552947998, "regret": 0.004129475448280573, "entropy": 0.12723331153392792, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:38.888793Z", "loop": 7963, "env_steps": 4893081599, "loss": 0.024764548987150192, "avg_return": 0.8596542477607727, "regret": 0.004129475448280573, "entropy": 0.12697172164916992, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:39.743326Z", "loop": 7964, "env_steps": 4893695999, "loss": 0.024985527619719505, "avg_return": 0.8614821434020996, "regret": 0.004129475448280573, "entropy": 0.12720318138599396, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:40.599384Z", "loop": 7965, "env_steps": 4894310399, "loss": 0.024333564564585686, "avg_return": 0.8604199290275574, "regret": 0.004129475448280573, "entropy": 0.12215545028448105, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:41.455400Z", "loop": 7966, "env_steps": 4894924799, "loss": 0.02405921369791031, "avg_return": 0.8623490333557129, "regret": 0.004129475448280573, "entropy": 0.1207110807299614, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:42.311957Z", "loop": 7967, "env_steps": 4895539199, "loss": 0.021400107070803642, "avg_return": 0.8600362539291382, "regret": 0.004129475448280573, "entropy": 0.10824023187160492, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:43.168831Z", "loop": 7968, "env_steps": 4896153599, "loss": 0.01861465722322464, "avg_return": 0.8616211414337158, "regret": 0.004129475448280573, "entropy": 0.09805059432983398, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:44.025665Z", "loop": 7969, "env_steps": 4896767999, "loss": 0.020013539120554924, "avg_return": 0.8632698655128479, "regret": 0.004129475448280573, "entropy": 0.1016879752278328, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:44.923672Z", "loop": 7970, "env_steps": 4897382399, "loss": 0.020774317905306816, "avg_return": 0.8624111413955688, "regret": 0.0015585047658532858, "entropy": 0.10266892611980438, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:45.780042Z", "loop": 7971, "env_steps": 4897996799, "loss": 0.020124070346355438, "avg_return": 0.8633272647857666, "regret": 0.0015585047658532858, "entropy": 0.09921689331531525, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:46.636402Z", "loop": 7972, "env_steps": 4898611199, "loss": 0.02096904069185257, "avg_return": 0.8607597947120667, "regret": 0.0015585047658532858, "entropy": 0.10215632617473602, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:47.493834Z", "loop": 7973, "env_steps": 4899225599, "loss": 0.019885228946805, "avg_return": 0.862130343914032, "regret": 0.0015585047658532858, "entropy": 0.10193049162626266, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:48.350097Z", "loop": 7974, "env_steps": 4899839999, "loss": 0.02033187635242939, "avg_return": 0.8615549802780151, "regret": 0.0015585047658532858, "entropy": 0.09986758977174759, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:49.207341Z", "loop": 7975, "env_steps": 4900454399, "loss": 0.019779741764068604, "avg_return": 0.86065673828125, "regret": 0.0015585047658532858, "entropy": 0.10213621705770493, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:50.063381Z", "loop": 7976, "env_steps": 4901068799, "loss": 0.019130218774080276, "avg_return": 0.8610121011734009, "regret": 0.0015585047658532858, "entropy": 0.0977606400847435, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:50.920599Z", "loop": 7977, "env_steps": 4901683199, "loss": 0.018595347180962563, "avg_return": 0.8623878955841064, "regret": 0.0015585047658532858, "entropy": 0.09502260386943817, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:51.776037Z", "loop": 7978, "env_steps": 4902297599, "loss": 0.01777677796781063, "avg_return": 0.8603169918060303, "regret": 0.0015585047658532858, "entropy": 0.09188774973154068, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:52.631697Z", "loop": 7979, "env_steps": 4902911999, "loss": 0.017478862777352333, "avg_return": 0.861238420009613, "regret": 0.0015585047658532858, "entropy": 0.08935026079416275, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:53.529927Z", "loop": 7980, "env_steps": 4903526399, "loss": 0.016406118869781494, "avg_return": 0.8605432510375977, "regret": 0.002568416064605117, "entropy": 0.08861087262630463, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:54.386111Z", "loop": 7981, "env_steps": 4904140799, "loss": 0.016935035586357117, "avg_return": 0.8604317307472229, "regret": 0.002568416064605117, "entropy": 0.08914852142333984, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:55.241456Z", "loop": 7982, "env_steps": 4904755199, "loss": 0.01504458673298359, "avg_return": 0.8611016869544983, "regret": 0.002568416064605117, "entropy": 0.08402298390865326, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:56.095835Z", "loop": 7983, "env_steps": 4905369599, "loss": 0.015241767279803753, "avg_return": 0.8619902729988098, "regret": 0.002568416064605117, "entropy": 0.08219482749700546, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:56.950472Z", "loop": 7984, "env_steps": 4905983999, "loss": 0.016435882076621056, "avg_return": 0.8611654043197632, "regret": 0.002568416064605117, "entropy": 0.09065253287553787, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:57.807018Z", "loop": 7985, "env_steps": 4906598399, "loss": 0.015253759920597076, "avg_return": 0.8614534735679626, "regret": 0.002568416064605117, "entropy": 0.0842074602842331, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:58.662182Z", "loop": 7986, "env_steps": 4907212799, "loss": 0.01656651310622692, "avg_return": 0.8632562756538391, "regret": 0.002568416064605117, "entropy": 0.08569575846195221, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:17:59.516642Z", "loop": 7987, "env_steps": 4907827199, "loss": 0.0160318985581398, "avg_return": 0.8628308176994324, "regret": 0.002568416064605117, "entropy": 0.08701375871896744, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:00.371117Z", "loop": 7988, "env_steps": 4908441599, "loss": 0.016050053760409355, "avg_return": 0.8634922504425049, "regret": 0.002568416064605117, "entropy": 0.08408049494028091, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:01.227200Z", "loop": 7989, "env_steps": 4909055999, "loss": 0.016407985240221024, "avg_return": 0.8627529144287109, "regret": 0.002568416064605117, "entropy": 0.08728320896625519, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:02.122862Z", "loop": 7990, "env_steps": 4909670399, "loss": 0.01593383587896824, "avg_return": 0.8614874482154846, "regret": 0.0007164121489040554, "entropy": 0.08575306832790375, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:02.978611Z", "loop": 7991, "env_steps": 4910284799, "loss": 0.016555342823266983, "avg_return": 0.8626497387886047, "regret": 0.0007164121489040554, "entropy": 0.08601094782352448, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:03.833455Z", "loop": 7992, "env_steps": 4910899199, "loss": 0.01590169034898281, "avg_return": 0.8634827136993408, "regret": 0.0007164121489040554, "entropy": 0.08731086552143097, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:04.689368Z", "loop": 7993, "env_steps": 4911513599, "loss": 0.016188114881515503, "avg_return": 0.862137496471405, "regret": 0.0007164121489040554, "entropy": 0.0884314551949501, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:05.545699Z", "loop": 7994, "env_steps": 4912127999, "loss": 0.017535990104079247, "avg_return": 0.8630530834197998, "regret": 0.0007164121489040554, "entropy": 0.09444987773895264, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:06.401439Z", "loop": 7995, "env_steps": 4912742399, "loss": 0.017348824068903923, "avg_return": 0.8625896573066711, "regret": 0.0007164121489040554, "entropy": 0.09231282025575638, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:07.256062Z", "loop": 7996, "env_steps": 4913356799, "loss": 0.01676269620656967, "avg_return": 0.8617681860923767, "regret": 0.0007164121489040554, "entropy": 0.08961167931556702, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:08.112492Z", "loop": 7997, "env_steps": 4913971199, "loss": 0.017596356570720673, "avg_return": 0.8643166422843933, "regret": 0.0007164121489040554, "entropy": 0.09414293617010117, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:08.968235Z", "loop": 7998, "env_steps": 4914585599, "loss": 0.01610494963824749, "avg_return": 0.8609421849250793, "regret": 0.0007164121489040554, "entropy": 0.09050089865922928, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:09.823718Z", "loop": 7999, "env_steps": 4915199999, "loss": 0.0171579010784626, "avg_return": 0.8615676164627075, "regret": 0.0007164121489040554, "entropy": 0.09163165092468262, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:10.718714Z", "loop": 8000, "env_steps": 4915814399, "loss": 0.01736992783844471, "avg_return": 0.8605259656906128, "regret": 0.002785034477710724, "entropy": 0.09593482315540314, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:11.573976Z", "loop": 8001, "env_steps": 4916428799, "loss": 0.018320268020033836, "avg_return": 0.8597076535224915, "regret": 0.002785034477710724, "entropy": 0.098151795566082, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:12.429229Z", "loop": 8002, "env_steps": 4917043199, "loss": 0.01850784569978714, "avg_return": 0.8609103560447693, "regret": 0.002785034477710724, "entropy": 0.09865651279687881, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:13.285462Z", "loop": 8003, "env_steps": 4917657599, "loss": 0.016140157356858253, "avg_return": 0.8614612817764282, "regret": 0.002785034477710724, "entropy": 0.08614640682935715, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:14.141493Z", "loop": 8004, "env_steps": 4918271999, "loss": 0.016743406653404236, "avg_return": 0.8611631393432617, "regret": 0.002785034477710724, "entropy": 0.0879071056842804, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:14.997522Z", "loop": 8005, "env_steps": 4918886399, "loss": 0.016470102593302727, "avg_return": 0.8622483611106873, "regret": 0.002785034477710724, "entropy": 0.08900442719459534, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:15.852822Z", "loop": 8006, "env_steps": 4919500799, "loss": 0.015127420425415039, "avg_return": 0.8632219433784485, "regret": 0.002785034477710724, "entropy": 0.08486002683639526, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:16.707918Z", "loop": 8007, "env_steps": 4920115199, "loss": 0.015477818436920643, "avg_return": 0.8625542521476746, "regret": 0.002785034477710724, "entropy": 0.08464707434177399, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:17.563455Z", "loop": 8008, "env_steps": 4920729599, "loss": 0.016482573002576828, "avg_return": 0.8622094988822937, "regret": 0.002785034477710724, "entropy": 0.08887986093759537, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:18.419089Z", "loop": 8009, "env_steps": 4921343999, "loss": 0.017655039206147194, "avg_return": 0.861965537071228, "regret": 0.002785034477710724, "entropy": 0.09014643728733063, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:19.313722Z", "loop": 8010, "env_steps": 4921958399, "loss": 0.017841050401329994, "avg_return": 0.8624768257141113, "regret": 0.0014333720318973064, "entropy": 0.09226266294717789, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:20.168973Z", "loop": 8011, "env_steps": 4922572799, "loss": 0.019282294437289238, "avg_return": 0.8627181053161621, "regret": 0.0014333720318973064, "entropy": 0.09890040010213852, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:21.024777Z", "loop": 8012, "env_steps": 4923187199, "loss": 0.020064640790224075, "avg_return": 0.8604056239128113, "regret": 0.0014333720318973064, "entropy": 0.10337116569280624, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:21.881415Z", "loop": 8013, "env_steps": 4923801599, "loss": 0.02076333574950695, "avg_return": 0.8612639307975769, "regret": 0.0014333720318973064, "entropy": 0.10626061260700226, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:22.736472Z", "loop": 8014, "env_steps": 4924415999, "loss": 0.019244764000177383, "avg_return": 0.8612794280052185, "regret": 0.0014333720318973064, "entropy": 0.09847628325223923, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:23.591447Z", "loop": 8015, "env_steps": 4925030399, "loss": 0.018808193504810333, "avg_return": 0.8611186742782593, "regret": 0.0014333720318973064, "entropy": 0.0984257161617279, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:24.446652Z", "loop": 8016, "env_steps": 4925644799, "loss": 0.01956699788570404, "avg_return": 0.8607924580574036, "regret": 0.0014333720318973064, "entropy": 0.09965504705905914, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:25.301887Z", "loop": 8017, "env_steps": 4926259199, "loss": 0.020965300500392914, "avg_return": 0.8630332350730896, "regret": 0.0014333720318973064, "entropy": 0.10377399623394012, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:26.157153Z", "loop": 8018, "env_steps": 4926873599, "loss": 0.021572910249233246, "avg_return": 0.8615370988845825, "regret": 0.0014333720318973064, "entropy": 0.1077258512377739, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:27.011189Z", "loop": 8019, "env_steps": 4927487999, "loss": 0.01804094761610031, "avg_return": 0.859673261642456, "regret": 0.0014333720318973064, "entropy": 0.0985964983701706, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:27.907223Z", "loop": 8020, "env_steps": 4928102399, "loss": 0.017698969691991806, "avg_return": 0.8618093132972717, "regret": 0.0022929836995899677, "entropy": 0.09304647892713547, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:28.763058Z", "loop": 8021, "env_steps": 4928716799, "loss": 0.016914715990424156, "avg_return": 0.8602860569953918, "regret": 0.0022929836995899677, "entropy": 0.09215633571147919, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:29.619437Z", "loop": 8022, "env_steps": 4929331199, "loss": 0.017155272886157036, "avg_return": 0.8611611127853394, "regret": 0.0022929836995899677, "entropy": 0.0891135185956955, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:30.475514Z", "loop": 8023, "env_steps": 4929945599, "loss": 0.01718880794942379, "avg_return": 0.8588792085647583, "regret": 0.0022929836995899677, "entropy": 0.09476520121097565, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:31.330112Z", "loop": 8024, "env_steps": 4930559999, "loss": 0.018388373777270317, "avg_return": 0.8586093187332153, "regret": 0.0022929836995899677, "entropy": 0.09673605114221573, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:32.186359Z", "loop": 8025, "env_steps": 4931174399, "loss": 0.019723286852240562, "avg_return": 0.857191801071167, "regret": 0.0022929836995899677, "entropy": 0.10153176635503769, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:33.041883Z", "loop": 8026, "env_steps": 4931788799, "loss": 0.021072572097182274, "avg_return": 0.8568110466003418, "regret": 0.0022929836995899677, "entropy": 0.11034907400608063, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:33.897092Z", "loop": 8027, "env_steps": 4932403199, "loss": 0.02006479911506176, "avg_return": 0.8575127124786377, "regret": 0.0022929836995899677, "entropy": 0.10699943453073502, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:34.752192Z", "loop": 8028, "env_steps": 4933017599, "loss": 0.020481877028942108, "avg_return": 0.858066201210022, "regret": 0.0022929836995899677, "entropy": 0.10327209532260895, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:35.607541Z", "loop": 8029, "env_steps": 4933631999, "loss": 0.02306894026696682, "avg_return": 0.8571165204048157, "regret": 0.0022929836995899677, "entropy": 0.11846668273210526, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:36.502418Z", "loop": 8030, "env_steps": 4934246399, "loss": 0.024744316935539246, "avg_return": 0.8567315936088562, "regret": 0.006817210931330919, "entropy": 0.12823635339736938, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:37.357864Z", "loop": 8031, "env_steps": 4934860799, "loss": 0.02330152876675129, "avg_return": 0.856559693813324, "regret": 0.006817210931330919, "entropy": 0.11864877492189407, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:38.212079Z", "loop": 8032, "env_steps": 4935475199, "loss": 0.02061811462044716, "avg_return": 0.8570569157600403, "regret": 0.006817210931330919, "entropy": 0.10817638039588928, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:39.066544Z", "loop": 8033, "env_steps": 4936089599, "loss": 0.02000376395881176, "avg_return": 0.8555774092674255, "regret": 0.006817210931330919, "entropy": 0.10364027321338654, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:39.921477Z", "loop": 8034, "env_steps": 4936703999, "loss": 0.022360727190971375, "avg_return": 0.856692910194397, "regret": 0.006817210931330919, "entropy": 0.1103694960474968, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:40.776596Z", "loop": 8035, "env_steps": 4937318399, "loss": 0.022349325940012932, "avg_return": 0.8568110466003418, "regret": 0.006817210931330919, "entropy": 0.11639231443405151, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:41.631480Z", "loop": 8036, "env_steps": 4937932799, "loss": 0.02185888960957527, "avg_return": 0.8593147993087769, "regret": 0.006817210931330919, "entropy": 0.11627829819917679, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:42.486375Z", "loop": 8037, "env_steps": 4938547199, "loss": 0.021228184923529625, "avg_return": 0.8595792651176453, "regret": 0.006817210931330919, "entropy": 0.11429391801357269, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:43.341255Z", "loop": 8038, "env_steps": 4939161599, "loss": 0.02140950784087181, "avg_return": 0.8591413497924805, "regret": 0.006817210931330919, "entropy": 0.11702223122119904, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:44.197042Z", "loop": 8039, "env_steps": 4939775999, "loss": 0.022840408608317375, "avg_return": 0.8598505854606628, "regret": 0.006817210931330919, "entropy": 0.12122970074415207, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:45.095236Z", "loop": 8040, "env_steps": 4940390399, "loss": 0.02238045446574688, "avg_return": 0.8606984615325928, "regret": 0.003225100925192237, "entropy": 0.11556784808635712, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:45.951549Z", "loop": 8041, "env_steps": 4941004799, "loss": 0.02346864901483059, "avg_return": 0.859940230846405, "regret": 0.003225100925192237, "entropy": 0.12745830416679382, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:46.805420Z", "loop": 8042, "env_steps": 4941619199, "loss": 0.025108084082603455, "avg_return": 0.8595591187477112, "regret": 0.003225100925192237, "entropy": 0.12723177671432495, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:47.660318Z", "loop": 8043, "env_steps": 4942233599, "loss": 0.024403566494584084, "avg_return": 0.8593727946281433, "regret": 0.003225100925192237, "entropy": 0.12890832126140594, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:48.516726Z", "loop": 8044, "env_steps": 4942847999, "loss": 0.025579053908586502, "avg_return": 0.8612762689590454, "regret": 0.003225100925192237, "entropy": 0.13370990753173828, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:49.371392Z", "loop": 8045, "env_steps": 4943462399, "loss": 0.0279567688703537, "avg_return": 0.860950767993927, "regret": 0.003225100925192237, "entropy": 0.1455131471157074, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:50.226166Z", "loop": 8046, "env_steps": 4944076799, "loss": 0.030417559668421745, "avg_return": 0.8594098091125488, "regret": 0.003225100925192237, "entropy": 0.14679273962974548, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:51.080525Z", "loop": 8047, "env_steps": 4944691199, "loss": 0.03010649047791958, "avg_return": 0.8604956269264221, "regret": 0.003225100925192237, "entropy": 0.14861422777175903, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:51.936900Z", "loop": 8048, "env_steps": 4945305599, "loss": 0.028794679790735245, "avg_return": 0.859714150428772, "regret": 0.003225100925192237, "entropy": 0.14617860317230225, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:52.792382Z", "loop": 8049, "env_steps": 4945919999, "loss": 0.02661021426320076, "avg_return": 0.8581692576408386, "regret": 0.003225100925192237, "entropy": 0.13375142216682434, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:53.686734Z", "loop": 8050, "env_steps": 4946534399, "loss": 0.023650851100683212, "avg_return": 0.8562437891960144, "regret": 0.007747367024421692, "entropy": 0.122468963265419, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:54.540883Z", "loop": 8051, "env_steps": 4947148799, "loss": 0.022327082231640816, "avg_return": 0.8527815937995911, "regret": 0.007747367024421692, "entropy": 0.1216326430439949, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:55.396369Z", "loop": 8052, "env_steps": 4947763199, "loss": 0.019516319036483765, "avg_return": 0.8571280837059021, "regret": 0.007747367024421692, "entropy": 0.11039567738771439, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:56.251129Z", "loop": 8053, "env_steps": 4948377599, "loss": 0.017737247049808502, "avg_return": 0.8615825772285461, "regret": 0.007747367024421692, "entropy": 0.09803072363138199, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:57.106242Z", "loop": 8054, "env_steps": 4948991999, "loss": 0.018010899424552917, "avg_return": 0.8640729188919067, "regret": 0.007747367024421692, "entropy": 0.09340237826108932, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:57.961312Z", "loop": 8055, "env_steps": 4949606399, "loss": 0.01564662717282772, "avg_return": 0.8635377287864685, "regret": 0.007747367024421692, "entropy": 0.08414096385240555, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:58.817682Z", "loop": 8056, "env_steps": 4950220799, "loss": 0.015898220241069794, "avg_return": 0.8623294234275818, "regret": 0.007747367024421692, "entropy": 0.08430082350969315, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:18:59.673281Z", "loop": 8057, "env_steps": 4950835199, "loss": 0.017309755086898804, "avg_return": 0.8613020777702332, "regret": 0.007747367024421692, "entropy": 0.09075118601322174, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:00.528379Z", "loop": 8058, "env_steps": 4951449599, "loss": 0.016604674980044365, "avg_return": 0.862704873085022, "regret": 0.007747367024421692, "entropy": 0.08975086361169815, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:01.384302Z", "loop": 8059, "env_steps": 4952063999, "loss": 0.017618805170059204, "avg_return": 0.8616703748703003, "regret": 0.007747367024421692, "entropy": 0.09243571758270264, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:02.277826Z", "loop": 8060, "env_steps": 4952678399, "loss": 0.017216576263308525, "avg_return": 0.8620890378952026, "regret": 0.0013091121800243855, "entropy": 0.09488706290721893, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:03.132456Z", "loop": 8061, "env_steps": 4953292799, "loss": 0.01684344932436943, "avg_return": 0.8618510365486145, "regret": 0.0013091121800243855, "entropy": 0.09075432270765305, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:03.987348Z", "loop": 8062, "env_steps": 4953907199, "loss": 0.018186062574386597, "avg_return": 0.8620865345001221, "regret": 0.0013091121800243855, "entropy": 0.09282145649194717, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:04.841938Z", "loop": 8063, "env_steps": 4954521599, "loss": 0.01790451630949974, "avg_return": 0.8602824211120605, "regret": 0.0013091121800243855, "entropy": 0.09519294649362564, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:05.696544Z", "loop": 8064, "env_steps": 4955135999, "loss": 0.018736792728304863, "avg_return": 0.8599373698234558, "regret": 0.0013091121800243855, "entropy": 0.09902668744325638, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:06.549908Z", "loop": 8065, "env_steps": 4955750399, "loss": 0.019587194547057152, "avg_return": 0.8610575795173645, "regret": 0.0013091121800243855, "entropy": 0.10583718866109848, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:07.402786Z", "loop": 8066, "env_steps": 4956364799, "loss": 0.020898951217532158, "avg_return": 0.8626157641410828, "regret": 0.0013091121800243855, "entropy": 0.10518234968185425, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:08.256468Z", "loop": 8067, "env_steps": 4956979199, "loss": 0.021024730056524277, "avg_return": 0.8613207936286926, "regret": 0.0013091121800243855, "entropy": 0.10658624023199081, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:09.110836Z", "loop": 8068, "env_steps": 4957593599, "loss": 0.01990826614201069, "avg_return": 0.862990140914917, "regret": 0.0013091121800243855, "entropy": 0.1014077365398407, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:09.964113Z", "loop": 8069, "env_steps": 4958207999, "loss": 0.02110552042722702, "avg_return": 0.8626195192337036, "regret": 0.0013091121800243855, "entropy": 0.1020093485713005, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:10.857185Z", "loop": 8070, "env_steps": 4958822399, "loss": 0.019699614495038986, "avg_return": 0.8622063398361206, "regret": 0.0020697324071079493, "entropy": 0.10236072540283203, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:11.710800Z", "loop": 8071, "env_steps": 4959436799, "loss": 0.02043123170733452, "avg_return": 0.8615975975990295, "regret": 0.0020697324071079493, "entropy": 0.10492222011089325, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:12.565243Z", "loop": 8072, "env_steps": 4960051199, "loss": 0.021618826314806938, "avg_return": 0.8609594106674194, "regret": 0.0020697324071079493, "entropy": 0.1057901605963707, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:13.418882Z", "loop": 8073, "env_steps": 4960665599, "loss": 0.02150721661746502, "avg_return": 0.8618782758712769, "regret": 0.0020697324071079493, "entropy": 0.109732985496521, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:14.271698Z", "loop": 8074, "env_steps": 4961279999, "loss": 0.019875938072800636, "avg_return": 0.8622655272483826, "regret": 0.0020697324071079493, "entropy": 0.10167065262794495, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:15.126261Z", "loop": 8075, "env_steps": 4961894399, "loss": 0.01970895379781723, "avg_return": 0.8620740175247192, "regret": 0.0020697324071079493, "entropy": 0.10129483789205551, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:15.979950Z", "loop": 8076, "env_steps": 4962508799, "loss": 0.02019094116985798, "avg_return": 0.8622158765792847, "regret": 0.0020697324071079493, "entropy": 0.09993275254964828, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:16.835233Z", "loop": 8077, "env_steps": 4963123199, "loss": 0.018836623057723045, "avg_return": 0.8619462251663208, "regret": 0.0020697324071079493, "entropy": 0.09766542166471481, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:17.688192Z", "loop": 8078, "env_steps": 4963737599, "loss": 0.020656386390328407, "avg_return": 0.8627409934997559, "regret": 0.0020697324071079493, "entropy": 0.10180588066577911, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:18.541783Z", "loop": 8079, "env_steps": 4964351999, "loss": 0.01869802549481392, "avg_return": 0.8630215525627136, "regret": 0.0020697324071079493, "entropy": 0.09357807040214539, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:19.438479Z", "loop": 8080, "env_steps": 4964966399, "loss": 0.017442142590880394, "avg_return": 0.8618700504302979, "regret": 0.0009723613620735705, "entropy": 0.08986219018697739, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:20.292582Z", "loop": 8081, "env_steps": 4965580799, "loss": 0.016039421781897545, "avg_return": 0.861336886882782, "regret": 0.0009723613620735705, "entropy": 0.08432430028915405, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:21.146343Z", "loop": 8082, "env_steps": 4966195199, "loss": 0.016964342445135117, "avg_return": 0.8622544407844543, "regret": 0.0009723613620735705, "entropy": 0.08598894625902176, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:21.999941Z", "loop": 8083, "env_steps": 4966809599, "loss": 0.017646823078393936, "avg_return": 0.8614087104797363, "regret": 0.0009723613620735705, "entropy": 0.09417661279439926, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:22.853999Z", "loop": 8084, "env_steps": 4967423999, "loss": 0.017729781568050385, "avg_return": 0.8621634840965271, "regret": 0.0009723613620735705, "entropy": 0.09432845562696457, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:23.707914Z", "loop": 8085, "env_steps": 4968038399, "loss": 0.017918450757861137, "avg_return": 0.8622348308563232, "regret": 0.0009723613620735705, "entropy": 0.09259461611509323, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:24.561982Z", "loop": 8086, "env_steps": 4968652799, "loss": 0.020992891862988472, "avg_return": 0.8620537519454956, "regret": 0.0009723613620735705, "entropy": 0.10424697399139404, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:25.415317Z", "loop": 8087, "env_steps": 4969267199, "loss": 0.0218659695237875, "avg_return": 0.8621018528938293, "regret": 0.0009723613620735705, "entropy": 0.10730253159999847, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:26.269358Z", "loop": 8088, "env_steps": 4969881599, "loss": 0.021388188004493713, "avg_return": 0.8616613149642944, "regret": 0.0009723613620735705, "entropy": 0.11247974634170532, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:27.123276Z", "loop": 8089, "env_steps": 4970495999, "loss": 0.022762974724173546, "avg_return": 0.8614538908004761, "regret": 0.0009723613620735705, "entropy": 0.11487365514039993, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:28.016681Z", "loop": 8090, "env_steps": 4971110399, "loss": 0.024639710783958435, "avg_return": 0.8594599366188049, "regret": 0.003318400587886572, "entropy": 0.12296567857265472, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:28.870369Z", "loop": 8091, "env_steps": 4971724799, "loss": 0.026561377570033073, "avg_return": 0.8601686954498291, "regret": 0.003318400587886572, "entropy": 0.1273622214794159, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:29.723414Z", "loop": 8092, "env_steps": 4972339199, "loss": 0.026455307379364967, "avg_return": 0.859492301940918, "regret": 0.003318400587886572, "entropy": 0.13025449216365814, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:30.577111Z", "loop": 8093, "env_steps": 4972953599, "loss": 0.026238610967993736, "avg_return": 0.8600390553474426, "regret": 0.003318400587886572, "entropy": 0.129292294383049, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:31.431341Z", "loop": 8094, "env_steps": 4973567999, "loss": 0.025626538321375847, "avg_return": 0.8597975969314575, "regret": 0.003318400587886572, "entropy": 0.1261213719844818, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:32.285157Z", "loop": 8095, "env_steps": 4974182399, "loss": 0.024649159982800484, "avg_return": 0.8602264523506165, "regret": 0.003318400587886572, "entropy": 0.12259837985038757, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:33.138159Z", "loop": 8096, "env_steps": 4974796799, "loss": 0.02381022833287716, "avg_return": 0.8601580858230591, "regret": 0.003318400587886572, "entropy": 0.11970654129981995, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:33.991185Z", "loop": 8097, "env_steps": 4975411199, "loss": 0.022683028131723404, "avg_return": 0.8608213663101196, "regret": 0.003318400587886572, "entropy": 0.11444183439016342, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:34.845548Z", "loop": 8098, "env_steps": 4976025599, "loss": 0.02144899219274521, "avg_return": 0.8608407974243164, "regret": 0.003318400587886572, "entropy": 0.11084651201963425, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:35.700591Z", "loop": 8099, "env_steps": 4976639999, "loss": 0.021366534754633904, "avg_return": 0.860568642616272, "regret": 0.003318400587886572, "entropy": 0.10895419865846634, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:36.594660Z", "loop": 8100, "env_steps": 4977254399, "loss": 0.020956050604581833, "avg_return": 0.8592484593391418, "regret": 0.0027986266650259495, "entropy": 0.10908916592597961, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:37.447988Z", "loop": 8101, "env_steps": 4977868799, "loss": 0.02048047073185444, "avg_return": 0.8598946332931519, "regret": 0.0027986266650259495, "entropy": 0.10771656781435013, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:38.302104Z", "loop": 8102, "env_steps": 4978483199, "loss": 0.020784132182598114, "avg_return": 0.861189603805542, "regret": 0.0027986266650259495, "entropy": 0.10773535072803497, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:39.158027Z", "loop": 8103, "env_steps": 4979097599, "loss": 0.021275950595736504, "avg_return": 0.8617914319038391, "regret": 0.0027986266650259495, "entropy": 0.10970678925514221, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:40.011765Z", "loop": 8104, "env_steps": 4979711999, "loss": 0.022168569266796112, "avg_return": 0.8612167835235596, "regret": 0.0027986266650259495, "entropy": 0.11560782045125961, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:40.864714Z", "loop": 8105, "env_steps": 4980326399, "loss": 0.020556693896651268, "avg_return": 0.8614997267723083, "regret": 0.0027986266650259495, "entropy": 0.10719601809978485, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:41.718611Z", "loop": 8106, "env_steps": 4980940799, "loss": 0.020700355991721153, "avg_return": 0.8619723916053772, "regret": 0.0027986266650259495, "entropy": 0.11012610048055649, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:42.574424Z", "loop": 8107, "env_steps": 4981555199, "loss": 0.02209518849849701, "avg_return": 0.8624855875968933, "regret": 0.0027986266650259495, "entropy": 0.11305347084999084, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:43.428556Z", "loop": 8108, "env_steps": 4982169599, "loss": 0.020615022629499435, "avg_return": 0.8615454435348511, "regret": 0.0027986266650259495, "entropy": 0.10873956233263016, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:44.283047Z", "loop": 8109, "env_steps": 4982783999, "loss": 0.02166108973324299, "avg_return": 0.8626440763473511, "regret": 0.0027986266650259495, "entropy": 0.11176459491252899, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:45.177694Z", "loop": 8110, "env_steps": 4983398399, "loss": 0.02275521121919155, "avg_return": 0.8617546558380127, "regret": 0.0012734468327835202, "entropy": 0.1133628860116005, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:46.033407Z", "loop": 8111, "env_steps": 4984012799, "loss": 0.02149345725774765, "avg_return": 0.8624387979507446, "regret": 0.0012734468327835202, "entropy": 0.11409042030572891, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:46.888388Z", "loop": 8112, "env_steps": 4984627199, "loss": 0.022147759795188904, "avg_return": 0.8616211414337158, "regret": 0.0012734468327835202, "entropy": 0.11658027768135071, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:47.742292Z", "loop": 8113, "env_steps": 4985241599, "loss": 0.0226180087774992, "avg_return": 0.861700177192688, "regret": 0.0012734468327835202, "entropy": 0.11295159161090851, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:48.595716Z", "loop": 8114, "env_steps": 4985855999, "loss": 0.02224983647465706, "avg_return": 0.8620322942733765, "regret": 0.0012734468327835202, "entropy": 0.11301527172327042, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:49.450086Z", "loop": 8115, "env_steps": 4986470399, "loss": 0.02187504433095455, "avg_return": 0.8623535633087158, "regret": 0.0012734468327835202, "entropy": 0.11569132655858994, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:50.304616Z", "loop": 8116, "env_steps": 4987084799, "loss": 0.02192085236310959, "avg_return": 0.8621787428855896, "regret": 0.0012734468327835202, "entropy": 0.1132185235619545, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:51.159838Z", "loop": 8117, "env_steps": 4987699199, "loss": 0.022228064015507698, "avg_return": 0.8610994815826416, "regret": 0.0012734468327835202, "entropy": 0.11689919233322144, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:52.013846Z", "loop": 8118, "env_steps": 4988313599, "loss": 0.022231925278902054, "avg_return": 0.8601101040840149, "regret": 0.0012734468327835202, "entropy": 0.11527850478887558, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:52.868438Z", "loop": 8119, "env_steps": 4988927999, "loss": 0.022289728745818138, "avg_return": 0.8617307543754578, "regret": 0.0012734468327835202, "entropy": 0.11843904107809067, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:53.762088Z", "loop": 8120, "env_steps": 4989542399, "loss": 0.023102132603526115, "avg_return": 0.861016571521759, "regret": 0.002729747211560607, "entropy": 0.12124184519052505, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:54.615751Z", "loop": 8121, "env_steps": 4990156799, "loss": 0.025016164407134056, "avg_return": 0.861316442489624, "regret": 0.002729747211560607, "entropy": 0.12926085293293, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:55.469778Z", "loop": 8122, "env_steps": 4990771199, "loss": 0.02581426315009594, "avg_return": 0.8611151576042175, "regret": 0.002729747211560607, "entropy": 0.13906367123126984, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:56.325086Z", "loop": 8123, "env_steps": 4991385599, "loss": 0.029365623369812965, "avg_return": 0.8586859107017517, "regret": 0.002729747211560607, "entropy": 0.1489790678024292, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:57.179261Z", "loop": 8124, "env_steps": 4991999999, "loss": 0.026838256046175957, "avg_return": 0.8600293397903442, "regret": 0.002729747211560607, "entropy": 0.1431334912776947, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:58.034139Z", "loop": 8125, "env_steps": 4992614399, "loss": 0.027720982208848, "avg_return": 0.859785795211792, "regret": 0.002729747211560607, "entropy": 0.14457786083221436, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:58.889353Z", "loop": 8126, "env_steps": 4993228799, "loss": 0.026179680600762367, "avg_return": 0.8598472476005554, "regret": 0.002729747211560607, "entropy": 0.1385307013988495, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:19:59.743852Z", "loop": 8127, "env_steps": 4993843199, "loss": 0.025899222120642662, "avg_return": 0.8589900135993958, "regret": 0.002729747211560607, "entropy": 0.13860486447811127, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:00.597045Z", "loop": 8128, "env_steps": 4994457599, "loss": 0.024691520258784294, "avg_return": 0.8595384955406189, "regret": 0.002729747211560607, "entropy": 0.1327979862689972, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:01.449731Z", "loop": 8129, "env_steps": 4995071999, "loss": 0.02383972704410553, "avg_return": 0.8613066077232361, "regret": 0.002729747211560607, "entropy": 0.12679287791252136, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:02.344711Z", "loop": 8130, "env_steps": 4995686399, "loss": 0.02252786234021187, "avg_return": 0.8619698286056519, "regret": 0.002549096941947937, "entropy": 0.1191854402422905, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:03.199776Z", "loop": 8131, "env_steps": 4996300799, "loss": 0.021202219650149345, "avg_return": 0.8624303340911865, "regret": 0.002549096941947937, "entropy": 0.11172077804803848, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:04.053007Z", "loop": 8132, "env_steps": 4996915199, "loss": 0.020450664684176445, "avg_return": 0.8616214394569397, "regret": 0.002549096941947937, "entropy": 0.1089700311422348, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:04.907000Z", "loop": 8133, "env_steps": 4997529599, "loss": 0.022001834586262703, "avg_return": 0.86283940076828, "regret": 0.002549096941947937, "entropy": 0.1089363619685173, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:05.760875Z", "loop": 8134, "env_steps": 4998143999, "loss": 0.02200278267264366, "avg_return": 0.8616657853126526, "regret": 0.002549096941947937, "entropy": 0.11048734188079834, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:06.614537Z", "loop": 8135, "env_steps": 4998758399, "loss": 0.022190429270267487, "avg_return": 0.8619610667228699, "regret": 0.002549096941947937, "entropy": 0.1125841811299324, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:07.468293Z", "loop": 8136, "env_steps": 4999372799, "loss": 0.023261141031980515, "avg_return": 0.8636518716812134, "regret": 0.002549096941947937, "entropy": 0.11299330741167068, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:08.321238Z", "loop": 8137, "env_steps": 4999987199, "loss": 0.02492302656173706, "avg_return": 0.861794650554657, "regret": 0.002549096941947937, "entropy": 0.12094277143478394, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:09.173829Z", "loop": 8138, "env_steps": 5000601599, "loss": 0.02403847686946392, "avg_return": 0.8619762659072876, "regret": 0.002549096941947937, "entropy": 0.11661960184574127, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:10.027887Z", "loop": 8139, "env_steps": 5001215999, "loss": 0.02401576191186905, "avg_return": 0.8613937497138977, "regret": 0.002549096941947937, "entropy": 0.11913542449474335, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:10.921325Z", "loop": 8140, "env_steps": 5001830399, "loss": 0.0241041611880064, "avg_return": 0.8624570965766907, "regret": 0.0013163411058485508, "entropy": 0.12072496116161346, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:11.775195Z", "loop": 8141, "env_steps": 5002444799, "loss": 0.025411710143089294, "avg_return": 0.8633635640144348, "regret": 0.0013163411058485508, "entropy": 0.12274980545043945, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:12.629376Z", "loop": 8142, "env_steps": 5003059199, "loss": 0.022668274119496346, "avg_return": 0.8627830147743225, "regret": 0.0013163411058485508, "entropy": 0.11257005482912064, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:13.482502Z", "loop": 8143, "env_steps": 5003673599, "loss": 0.018571659922599792, "avg_return": 0.8627268671989441, "regret": 0.0013163411058485508, "entropy": 0.09493973106145859, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:14.335933Z", "loop": 8144, "env_steps": 5004287999, "loss": 0.017791518941521645, "avg_return": 0.8620952367782593, "regret": 0.0013163411058485508, "entropy": 0.09168840199708939, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:15.189917Z", "loop": 8145, "env_steps": 5004902399, "loss": 0.01908107101917267, "avg_return": 0.8628954291343689, "regret": 0.0013163411058485508, "entropy": 0.0978785827755928, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:16.044306Z", "loop": 8146, "env_steps": 5005516799, "loss": 0.020322542637586594, "avg_return": 0.8609698414802551, "regret": 0.0013163411058485508, "entropy": 0.10127759724855423, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:16.898374Z", "loop": 8147, "env_steps": 5006131199, "loss": 0.019092969596385956, "avg_return": 0.8614164590835571, "regret": 0.0013163411058485508, "entropy": 0.1018110066652298, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:17.752459Z", "loop": 8148, "env_steps": 5006745599, "loss": 0.018351472914218903, "avg_return": 0.861060380935669, "regret": 0.0013163411058485508, "entropy": 0.09793829917907715, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:18.605768Z", "loop": 8149, "env_steps": 5007359999, "loss": 0.01775508001446724, "avg_return": 0.86115562915802, "regret": 0.0013163411058485508, "entropy": 0.08768344670534134, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:19.503996Z", "loop": 8150, "env_steps": 5007974399, "loss": 0.01922798715531826, "avg_return": 0.8597672581672668, "regret": 0.004770967643707991, "entropy": 0.10218531638383865, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:20.356419Z", "loop": 8151, "env_steps": 5008588799, "loss": 0.020652325823903084, "avg_return": 0.8586631417274475, "regret": 0.004770967643707991, "entropy": 0.10296569764614105, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:21.210034Z", "loop": 8152, "env_steps": 5009203199, "loss": 0.019274527207016945, "avg_return": 0.8586826920509338, "regret": 0.004770967643707991, "entropy": 0.09987248480319977, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:22.064047Z", "loop": 8153, "env_steps": 5009817599, "loss": 0.018827399238944054, "avg_return": 0.8569561243057251, "regret": 0.004770967643707991, "entropy": 0.09914948791265488, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:22.918444Z", "loop": 8154, "env_steps": 5010431999, "loss": 0.018302788957953453, "avg_return": 0.8579684495925903, "regret": 0.004770967643707991, "entropy": 0.09558325260877609, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:23.771620Z", "loop": 8155, "env_steps": 5011046399, "loss": 0.017498180270195007, "avg_return": 0.8585495948791504, "regret": 0.004770967643707991, "entropy": 0.09207994490861893, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:24.624573Z", "loop": 8156, "env_steps": 5011660799, "loss": 0.017543964087963104, "avg_return": 0.8608893752098083, "regret": 0.004770967643707991, "entropy": 0.09192173182964325, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:25.479130Z", "loop": 8157, "env_steps": 5012275199, "loss": 0.0178289245814085, "avg_return": 0.8588537573814392, "regret": 0.004770967643707991, "entropy": 0.09426664561033249, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:26.333238Z", "loop": 8158, "env_steps": 5012889599, "loss": 0.018201520666480064, "avg_return": 0.8610832691192627, "regret": 0.004770967643707991, "entropy": 0.09520281851291656, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:27.186348Z", "loop": 8159, "env_steps": 5013503999, "loss": 0.01681268773972988, "avg_return": 0.8630949258804321, "regret": 0.004770967643707991, "entropy": 0.09015137702226639, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:28.079047Z", "loop": 8160, "env_steps": 5014118399, "loss": 0.01741713099181652, "avg_return": 0.8609799146652222, "regret": 0.0011490461183711886, "entropy": 0.08728127181529999, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:28.932737Z", "loop": 8161, "env_steps": 5014732799, "loss": 0.017826389521360397, "avg_return": 0.8624807000160217, "regret": 0.0011490461183711886, "entropy": 0.09240496158599854, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:29.786453Z", "loop": 8162, "env_steps": 5015347199, "loss": 0.017656341195106506, "avg_return": 0.8636993765830994, "regret": 0.0011490461183711886, "entropy": 0.0944705531001091, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:30.640362Z", "loop": 8163, "env_steps": 5015961599, "loss": 0.019031889736652374, "avg_return": 0.8629730343818665, "regret": 0.0011490461183711886, "entropy": 0.09777262061834335, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:31.493929Z", "loop": 8164, "env_steps": 5016575999, "loss": 0.01910017989575863, "avg_return": 0.8625613451004028, "regret": 0.0011490461183711886, "entropy": 0.09875886887311935, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:32.347589Z", "loop": 8165, "env_steps": 5017190399, "loss": 0.019007882103323936, "avg_return": 0.8624280095100403, "regret": 0.0011490461183711886, "entropy": 0.09724920988082886, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:33.202953Z", "loop": 8166, "env_steps": 5017804799, "loss": 0.01767611689865589, "avg_return": 0.8627640008926392, "regret": 0.0011490461183711886, "entropy": 0.09233743697404861, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:34.058075Z", "loop": 8167, "env_steps": 5018419199, "loss": 0.017152536660432816, "avg_return": 0.8626792430877686, "regret": 0.0011490461183711886, "entropy": 0.0959799587726593, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:34.914047Z", "loop": 8168, "env_steps": 5019033599, "loss": 0.016106506809592247, "avg_return": 0.8624907732009888, "regret": 0.0011490461183711886, "entropy": 0.08789213746786118, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:35.768383Z", "loop": 8169, "env_steps": 5019647999, "loss": 0.018808525055646896, "avg_return": 0.863116979598999, "regret": 0.0011490461183711886, "entropy": 0.09721378982067108, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:36.664227Z", "loop": 8170, "env_steps": 5020262399, "loss": 0.019040241837501526, "avg_return": 0.8614072799682617, "regret": 0.0014179619029164314, "entropy": 0.10087999701499939, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:37.518849Z", "loop": 8171, "env_steps": 5020876799, "loss": 0.020656060427427292, "avg_return": 0.861812174320221, "regret": 0.0014179619029164314, "entropy": 0.10472158342599869, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:38.373254Z", "loop": 8172, "env_steps": 5021491199, "loss": 0.020612550899386406, "avg_return": 0.8617708683013916, "regret": 0.0014179619029164314, "entropy": 0.1085338294506073, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:39.226413Z", "loop": 8173, "env_steps": 5022105599, "loss": 0.02161393128335476, "avg_return": 0.8627381324768066, "regret": 0.0014179619029164314, "entropy": 0.10615433007478714, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:40.081235Z", "loop": 8174, "env_steps": 5022719999, "loss": 0.022824149578809738, "avg_return": 0.8624686002731323, "regret": 0.0014179619029164314, "entropy": 0.11259608715772629, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:40.934528Z", "loop": 8175, "env_steps": 5023334399, "loss": 0.023714259266853333, "avg_return": 0.8619670867919922, "regret": 0.0014179619029164314, "entropy": 0.11973580718040466, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:41.789799Z", "loop": 8176, "env_steps": 5023948799, "loss": 0.024258075281977654, "avg_return": 0.8610812425613403, "regret": 0.0014179619029164314, "entropy": 0.12421250343322754, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:42.643629Z", "loop": 8177, "env_steps": 5024563199, "loss": 0.024895314127206802, "avg_return": 0.8606764078140259, "regret": 0.0014179619029164314, "entropy": 0.12442311644554138, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:43.497644Z", "loop": 8178, "env_steps": 5025177599, "loss": 0.024746501818299294, "avg_return": 0.8608142137527466, "regret": 0.0014179619029164314, "entropy": 0.12334466725587845, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:44.351106Z", "loop": 8179, "env_steps": 5025791999, "loss": 0.02505646087229252, "avg_return": 0.8604602217674255, "regret": 0.0014179619029164314, "entropy": 0.12486132979393005, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:45.244697Z", "loop": 8180, "env_steps": 5026406399, "loss": 0.024926381185650826, "avg_return": 0.8607655763626099, "regret": 0.002311214804649353, "entropy": 0.12363673746585846, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:46.099404Z", "loop": 8181, "env_steps": 5027020799, "loss": 0.02425486408174038, "avg_return": 0.8613682389259338, "regret": 0.002311214804649353, "entropy": 0.1216755285859108, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:46.953508Z", "loop": 8182, "env_steps": 5027635199, "loss": 0.02448260597884655, "avg_return": 0.8604918718338013, "regret": 0.002311214804649353, "entropy": 0.12230492383241653, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:47.806960Z", "loop": 8183, "env_steps": 5028249599, "loss": 0.023405088111758232, "avg_return": 0.8606452345848083, "regret": 0.002311214804649353, "entropy": 0.11770904809236526, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:48.660960Z", "loop": 8184, "env_steps": 5028863999, "loss": 0.025814523920416832, "avg_return": 0.8606892228126526, "regret": 0.002311214804649353, "entropy": 0.1242840513586998, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:49.516618Z", "loop": 8185, "env_steps": 5029478399, "loss": 0.024744242429733276, "avg_return": 0.8612346649169922, "regret": 0.002311214804649353, "entropy": 0.12642063200473785, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:50.370363Z", "loop": 8186, "env_steps": 5030092799, "loss": 0.025598561391234398, "avg_return": 0.8604400753974915, "regret": 0.002311214804649353, "entropy": 0.12141842395067215, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:51.223440Z", "loop": 8187, "env_steps": 5030707199, "loss": 0.02390252985060215, "avg_return": 0.8606376051902771, "regret": 0.002311214804649353, "entropy": 0.12066571414470673, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:52.076963Z", "loop": 8188, "env_steps": 5031321599, "loss": 0.024118008092045784, "avg_return": 0.8622172474861145, "regret": 0.002311214804649353, "entropy": 0.12283959984779358, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:52.932058Z", "loop": 8189, "env_steps": 5031935999, "loss": 0.024604756385087967, "avg_return": 0.8619293570518494, "regret": 0.002311214804649353, "entropy": 0.1223968118429184, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:53.826664Z", "loop": 8190, "env_steps": 5032550399, "loss": 0.023169158026576042, "avg_return": 0.8628571033477783, "regret": 0.0019614025950431824, "entropy": 0.11927317082881927, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:54.680896Z", "loop": 8191, "env_steps": 5033164799, "loss": 0.02127213589847088, "avg_return": 0.8616871237754822, "regret": 0.0019614025950431824, "entropy": 0.10711587965488434, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:55.535328Z", "loop": 8192, "env_steps": 5033779199, "loss": 0.01986015774309635, "avg_return": 0.8613361716270447, "regret": 0.0019614025950431824, "entropy": 0.10502935200929642, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:56.390131Z", "loop": 8193, "env_steps": 5034393599, "loss": 0.02056839130818844, "avg_return": 0.8606256246566772, "regret": 0.0019614025950431824, "entropy": 0.10412713885307312, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:57.244354Z", "loop": 8194, "env_steps": 5035007999, "loss": 0.022036617621779442, "avg_return": 0.8612944483757019, "regret": 0.0019614025950431824, "entropy": 0.11073769629001617, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:58.098163Z", "loop": 8195, "env_steps": 5035622399, "loss": 0.022439366206526756, "avg_return": 0.85944664478302, "regret": 0.0019614025950431824, "entropy": 0.11789742112159729, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:58.951781Z", "loop": 8196, "env_steps": 5036236799, "loss": 0.02281399816274643, "avg_return": 0.8596533536911011, "regret": 0.0019614025950431824, "entropy": 0.12003837525844574, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:20:59.806835Z", "loop": 8197, "env_steps": 5036851199, "loss": 0.023255465552210808, "avg_return": 0.8593589663505554, "regret": 0.0019614025950431824, "entropy": 0.12342199683189392, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:00.661586Z", "loop": 8198, "env_steps": 5037465599, "loss": 0.02818179503083229, "avg_return": 0.8584149479866028, "regret": 0.0019614025950431824, "entropy": 0.14142458140850067, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:01.516030Z", "loop": 8199, "env_steps": 5038079999, "loss": 0.030243396759033203, "avg_return": 0.8585744500160217, "regret": 0.0019614025950431824, "entropy": 0.15045639872550964, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:02.410845Z", "loop": 8200, "env_steps": 5038694399, "loss": 0.02809860371053219, "avg_return": 0.860531747341156, "regret": 0.004004940390586853, "entropy": 0.1411994844675064, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:03.266402Z", "loop": 8201, "env_steps": 5039308799, "loss": 0.025078603997826576, "avg_return": 0.8620603680610657, "regret": 0.004004940390586853, "entropy": 0.12875087559223175, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:04.122068Z", "loop": 8202, "env_steps": 5039923199, "loss": 0.022702256217598915, "avg_return": 0.8618264198303223, "regret": 0.004004940390586853, "entropy": 0.11553586274385452, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:04.976936Z", "loop": 8203, "env_steps": 5040537599, "loss": 0.019889751449227333, "avg_return": 0.8632332682609558, "regret": 0.004004940390586853, "entropy": 0.10690352320671082, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:05.831667Z", "loop": 8204, "env_steps": 5041151999, "loss": 0.01971227489411831, "avg_return": 0.8614603877067566, "regret": 0.004004940390586853, "entropy": 0.10720506310462952, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:06.685394Z", "loop": 8205, "env_steps": 5041766399, "loss": 0.02231294848024845, "avg_return": 0.8601924777030945, "regret": 0.004004940390586853, "entropy": 0.11323238164186478, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:07.539128Z", "loop": 8206, "env_steps": 5042380799, "loss": 0.020856274291872978, "avg_return": 0.8621134757995605, "regret": 0.004004940390586853, "entropy": 0.1097227931022644, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:08.392661Z", "loop": 8207, "env_steps": 5042995199, "loss": 0.02152368240058422, "avg_return": 0.862240195274353, "regret": 0.004004940390586853, "entropy": 0.10848655551671982, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:09.246499Z", "loop": 8208, "env_steps": 5043609599, "loss": 0.020510787144303322, "avg_return": 0.8605307936668396, "regret": 0.004004940390586853, "entropy": 0.10669465363025665, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:10.100366Z", "loop": 8209, "env_steps": 5044223999, "loss": 0.021701689809560776, "avg_return": 0.8622596263885498, "regret": 0.004004940390586853, "entropy": 0.1079261377453804, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:10.993788Z", "loop": 8210, "env_steps": 5044838399, "loss": 0.020859919488430023, "avg_return": 0.8601236939430237, "regret": 0.001365551957860589, "entropy": 0.10864633321762085, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:11.848726Z", "loop": 8211, "env_steps": 5045452799, "loss": 0.021244710311293602, "avg_return": 0.8611705899238586, "regret": 0.001365551957860589, "entropy": 0.10651539266109467, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:12.704022Z", "loop": 8212, "env_steps": 5046067199, "loss": 0.020516037940979004, "avg_return": 0.8632570505142212, "regret": 0.001365551957860589, "entropy": 0.10369157791137695, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:13.558232Z", "loop": 8213, "env_steps": 5046681599, "loss": 0.02086983621120453, "avg_return": 0.8630464673042297, "regret": 0.001365551957860589, "entropy": 0.10544027388095856, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:14.411967Z", "loop": 8214, "env_steps": 5047295999, "loss": 0.019793879240751266, "avg_return": 0.8621855974197388, "regret": 0.001365551957860589, "entropy": 0.10590112209320068, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:15.266252Z", "loop": 8215, "env_steps": 5047910399, "loss": 0.021480558440089226, "avg_return": 0.8630053997039795, "regret": 0.001365551957860589, "entropy": 0.10899098962545395, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:16.121690Z", "loop": 8216, "env_steps": 5048524799, "loss": 0.022042496129870415, "avg_return": 0.8613039255142212, "regret": 0.001365551957860589, "entropy": 0.109989695250988, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:16.976922Z", "loop": 8217, "env_steps": 5049139199, "loss": 0.021316980943083763, "avg_return": 0.8615921139717102, "regret": 0.001365551957860589, "entropy": 0.11041643470525742, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:17.832063Z", "loop": 8218, "env_steps": 5049753599, "loss": 0.020175306126475334, "avg_return": 0.8618805408477783, "regret": 0.001365551957860589, "entropy": 0.10675235837697983, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:18.686512Z", "loop": 8219, "env_steps": 5050367999, "loss": 0.018563952296972275, "avg_return": 0.860225260257721, "regret": 0.001365551957860589, "entropy": 0.09493660181760788, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:19.584025Z", "loop": 8220, "env_steps": 5050982399, "loss": 0.015878697857260704, "avg_return": 0.8623208999633789, "regret": 0.002518310211598873, "entropy": 0.09105080366134644, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:20.438657Z", "loop": 8221, "env_steps": 5051596799, "loss": 0.016745351254940033, "avg_return": 0.8598056435585022, "regret": 0.002518310211598873, "entropy": 0.09394463151693344, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:21.293234Z", "loop": 8222, "env_steps": 5052211199, "loss": 0.019132833927869797, "avg_return": 0.8591479659080505, "regret": 0.002518310211598873, "entropy": 0.1027313619852066, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:22.147042Z", "loop": 8223, "env_steps": 5052825599, "loss": 0.020151466131210327, "avg_return": 0.8590826392173767, "regret": 0.002518310211598873, "entropy": 0.1058463454246521, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:23.000992Z", "loop": 8224, "env_steps": 5053439999, "loss": 0.02014797367155552, "avg_return": 0.8601714372634888, "regret": 0.002518310211598873, "entropy": 0.10438043624162674, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:23.856420Z", "loop": 8225, "env_steps": 5054054399, "loss": 0.018989859148859978, "avg_return": 0.8599270582199097, "regret": 0.002518310211598873, "entropy": 0.1021914854645729, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:24.711805Z", "loop": 8226, "env_steps": 5054668799, "loss": 0.01916699856519699, "avg_return": 0.8601798415184021, "regret": 0.002518310211598873, "entropy": 0.0983312800526619, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:25.566195Z", "loop": 8227, "env_steps": 5055283199, "loss": 0.01917334273457527, "avg_return": 0.8611451387405396, "regret": 0.002518310211598873, "entropy": 0.10063368827104568, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:26.421776Z", "loop": 8228, "env_steps": 5055897599, "loss": 0.018570443615317345, "avg_return": 0.8620153069496155, "regret": 0.002518310211598873, "entropy": 0.10309780389070511, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:27.277387Z", "loop": 8229, "env_steps": 5056511999, "loss": 0.018829578533768654, "avg_return": 0.8593915104866028, "regret": 0.002518310211598873, "entropy": 0.0969865545630455, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:28.172566Z", "loop": 8230, "env_steps": 5057126399, "loss": 0.01958518661558628, "avg_return": 0.8600130677223206, "regret": 0.0027849639300256968, "entropy": 0.10053450614213943, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:29.027001Z", "loop": 8231, "env_steps": 5057740799, "loss": 0.018555833026766777, "avg_return": 0.8617705702781677, "regret": 0.0027849639300256968, "entropy": 0.10062984377145767, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:29.881147Z", "loop": 8232, "env_steps": 5058355199, "loss": 0.017083436250686646, "avg_return": 0.8612988591194153, "regret": 0.0027849639300256968, "entropy": 0.0935836210846901, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:30.733907Z", "loop": 8233, "env_steps": 5058969599, "loss": 0.018239060416817665, "avg_return": 0.8612083196640015, "regret": 0.0027849639300256968, "entropy": 0.09589653462171555, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:31.587994Z", "loop": 8234, "env_steps": 5059583999, "loss": 0.01648343913257122, "avg_return": 0.862199604511261, "regret": 0.0027849639300256968, "entropy": 0.08915162086486816, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:32.442344Z", "loop": 8235, "env_steps": 5060198399, "loss": 0.017929336056113243, "avg_return": 0.8613374829292297, "regret": 0.0027849639300256968, "entropy": 0.09702211618423462, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:33.297741Z", "loop": 8236, "env_steps": 5060812799, "loss": 0.01861274242401123, "avg_return": 0.8624868988990784, "regret": 0.0027849639300256968, "entropy": 0.09758522361516953, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:34.151659Z", "loop": 8237, "env_steps": 5061427199, "loss": 0.017014533281326294, "avg_return": 0.8625484704971313, "regret": 0.0027849639300256968, "entropy": 0.09295597672462463, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:35.005396Z", "loop": 8238, "env_steps": 5062041599, "loss": 0.017367098480463028, "avg_return": 0.8627091646194458, "regret": 0.0027849639300256968, "entropy": 0.09508790075778961, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:35.859228Z", "loop": 8239, "env_steps": 5062655999, "loss": 0.0177623238414526, "avg_return": 0.8632891774177551, "regret": 0.0027849639300256968, "entropy": 0.09166592359542847, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:36.751987Z", "loop": 8240, "env_steps": 5063270399, "loss": 0.017457544803619385, "avg_return": 0.8638538718223572, "regret": 0.0009436187683604658, "entropy": 0.09284906834363937, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:37.604984Z", "loop": 8241, "env_steps": 5063884799, "loss": 0.01794816553592682, "avg_return": 0.8625720143318176, "regret": 0.0009436187683604658, "entropy": 0.0938754603266716, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:38.459411Z", "loop": 8242, "env_steps": 5064499199, "loss": 0.018198465928435326, "avg_return": 0.8627678751945496, "regret": 0.0009436187683604658, "entropy": 0.09359889477491379, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:39.313827Z", "loop": 8243, "env_steps": 5065113599, "loss": 0.018703622743487358, "avg_return": 0.8638436198234558, "regret": 0.0009436187683604658, "entropy": 0.098383828997612, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:40.169287Z", "loop": 8244, "env_steps": 5065727999, "loss": 0.020304031670093536, "avg_return": 0.864081621170044, "regret": 0.0009436187683604658, "entropy": 0.10314765572547913, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:41.022773Z", "loop": 8245, "env_steps": 5066342399, "loss": 0.01968269608914852, "avg_return": 0.861846923828125, "regret": 0.0009436187683604658, "entropy": 0.101622074842453, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:41.875491Z", "loop": 8246, "env_steps": 5066956799, "loss": 0.020808329805731773, "avg_return": 0.8618118762969971, "regret": 0.0009436187683604658, "entropy": 0.10244066268205643, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:42.729046Z", "loop": 8247, "env_steps": 5067571199, "loss": 0.020574554800987244, "avg_return": 0.8614448308944702, "regret": 0.0009436187683604658, "entropy": 0.11160900443792343, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:43.582865Z", "loop": 8248, "env_steps": 5068185599, "loss": 0.019977105781435966, "avg_return": 0.8622778654098511, "regret": 0.0009436187683604658, "entropy": 0.10853690654039383, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:44.436717Z", "loop": 8249, "env_steps": 5068799999, "loss": 0.022683393210172653, "avg_return": 0.8583508729934692, "regret": 0.0009436187683604658, "entropy": 0.1187935546040535, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:45.330829Z", "loop": 8250, "env_steps": 5069414399, "loss": 0.023849012330174446, "avg_return": 0.8591032028198242, "regret": 0.004515713546425104, "entropy": 0.12487797439098358, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:46.185234Z", "loop": 8251, "env_steps": 5070028799, "loss": 0.024396298453211784, "avg_return": 0.8597863912582397, "regret": 0.004515713546425104, "entropy": 0.12427860498428345, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:47.039458Z", "loop": 8252, "env_steps": 5070643199, "loss": 0.02315870299935341, "avg_return": 0.8620988130569458, "regret": 0.004515713546425104, "entropy": 0.11408482491970062, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:47.893672Z", "loop": 8253, "env_steps": 5071257599, "loss": 0.023241912946105003, "avg_return": 0.8616942763328552, "regret": 0.004515713546425104, "entropy": 0.11323459446430206, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:48.747782Z", "loop": 8254, "env_steps": 5071871999, "loss": 0.022626182064414024, "avg_return": 0.8620668649673462, "regret": 0.004515713546425104, "entropy": 0.11377063393592834, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:49.601152Z", "loop": 8255, "env_steps": 5072486399, "loss": 0.02398063614964485, "avg_return": 0.8634522557258606, "regret": 0.004515713546425104, "entropy": 0.1140841543674469, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:50.454466Z", "loop": 8256, "env_steps": 5073100799, "loss": 0.023402206599712372, "avg_return": 0.8633824586868286, "regret": 0.004515713546425104, "entropy": 0.11621510982513428, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:51.308158Z", "loop": 8257, "env_steps": 5073715199, "loss": 0.023185646161437035, "avg_return": 0.8615788221359253, "regret": 0.004515713546425104, "entropy": 0.11006983369588852, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:52.162992Z", "loop": 8258, "env_steps": 5074329599, "loss": 0.02278302237391472, "avg_return": 0.8621551990509033, "regret": 0.004515713546425104, "entropy": 0.11280883848667145, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:53.017423Z", "loop": 8259, "env_steps": 5074943999, "loss": 0.020687168464064598, "avg_return": 0.8624707460403442, "regret": 0.004515713546425104, "entropy": 0.10020671784877777, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:53.911999Z", "loop": 8260, "env_steps": 5075558399, "loss": 0.018484143540263176, "avg_return": 0.8623830080032349, "regret": 0.0008753532310947776, "entropy": 0.08963274955749512, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:54.766141Z", "loop": 8261, "env_steps": 5076172799, "loss": 0.015595140866935253, "avg_return": 0.8634527921676636, "regret": 0.0008753532310947776, "entropy": 0.08418713510036469, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:55.620674Z", "loop": 8262, "env_steps": 5076787199, "loss": 0.014806583523750305, "avg_return": 0.8620858192443848, "regret": 0.0008753532310947776, "entropy": 0.08317351341247559, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:56.475203Z", "loop": 8263, "env_steps": 5077401599, "loss": 0.01509343832731247, "avg_return": 0.8626804947853088, "regret": 0.0008753532310947776, "entropy": 0.08054248988628387, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:57.328444Z", "loop": 8264, "env_steps": 5078015999, "loss": 0.016384238377213478, "avg_return": 0.8632184863090515, "regret": 0.0008753532310947776, "entropy": 0.08235049992799759, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:58.182900Z", "loop": 8265, "env_steps": 5078630399, "loss": 0.014824352227151394, "avg_return": 0.8621841669082642, "regret": 0.0008753532310947776, "entropy": 0.08181904256343842, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:59.037410Z", "loop": 8266, "env_steps": 5079244799, "loss": 0.014867434278130531, "avg_return": 0.8615836501121521, "regret": 0.0008753532310947776, "entropy": 0.07935552299022675, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:21:59.891637Z", "loop": 8267, "env_steps": 5079859199, "loss": 0.01621004194021225, "avg_return": 0.8619446158409119, "regret": 0.0008753532310947776, "entropy": 0.08524688333272934, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:00.745163Z", "loop": 8268, "env_steps": 5080473599, "loss": 0.016505245119333267, "avg_return": 0.8613793253898621, "regret": 0.0008753532310947776, "entropy": 0.08849599212408066, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:01.599437Z", "loop": 8269, "env_steps": 5081087999, "loss": 0.018668338656425476, "avg_return": 0.8619479537010193, "regret": 0.0008753532310947776, "entropy": 0.09833464026451111, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:02.493158Z", "loop": 8270, "env_steps": 5081702399, "loss": 0.0205879807472229, "avg_return": 0.861439049243927, "regret": 0.0014091599732637405, "entropy": 0.10113999247550964, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:03.347407Z", "loop": 8271, "env_steps": 5082316799, "loss": 0.020853007212281227, "avg_return": 0.8615021705627441, "regret": 0.0014091599732637405, "entropy": 0.10142204165458679, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:04.201693Z", "loop": 8272, "env_steps": 5082931199, "loss": 0.019622165709733963, "avg_return": 0.8609643578529358, "regret": 0.0014091599732637405, "entropy": 0.10060335695743561, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:05.054994Z", "loop": 8273, "env_steps": 5083545599, "loss": 0.020438378676772118, "avg_return": 0.861474335193634, "regret": 0.0014091599732637405, "entropy": 0.10137288272380829, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:05.907891Z", "loop": 8274, "env_steps": 5084159999, "loss": 0.02033938094973564, "avg_return": 0.8627191185951233, "regret": 0.0014091599732637405, "entropy": 0.09881198406219482, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:06.763098Z", "loop": 8275, "env_steps": 5084774399, "loss": 0.020294373854994774, "avg_return": 0.8622599244117737, "regret": 0.0014091599732637405, "entropy": 0.09887176007032394, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:07.617650Z", "loop": 8276, "env_steps": 5085388799, "loss": 0.019675154238939285, "avg_return": 0.8632763028144836, "regret": 0.0014091599732637405, "entropy": 0.09608111530542374, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:08.471840Z", "loop": 8277, "env_steps": 5086003199, "loss": 0.018423186615109444, "avg_return": 0.8637418746948242, "regret": 0.0014091599732637405, "entropy": 0.09298613667488098, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:09.325128Z", "loop": 8278, "env_steps": 5086617599, "loss": 0.01863386295735836, "avg_return": 0.8629583120346069, "regret": 0.0014091599732637405, "entropy": 0.09215674549341202, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:10.179166Z", "loop": 8279, "env_steps": 5087231999, "loss": 0.018970033153891563, "avg_return": 0.8627736568450928, "regret": 0.0014091599732637405, "entropy": 0.0942288264632225, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:11.074277Z", "loop": 8280, "env_steps": 5087846399, "loss": 0.016873426735401154, "avg_return": 0.8630053997039795, "regret": 0.0006068928050808609, "entropy": 0.08774972707033157, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:11.928166Z", "loop": 8281, "env_steps": 5088460799, "loss": 0.016535038128495216, "avg_return": 0.8612885475158691, "regret": 0.0006068928050808609, "entropy": 0.08529815077781677, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:12.781749Z", "loop": 8282, "env_steps": 5089075199, "loss": 0.01606592908501625, "avg_return": 0.8631630539894104, "regret": 0.0006068928050808609, "entropy": 0.08154270052909851, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:13.635622Z", "loop": 8283, "env_steps": 5089689599, "loss": 0.014563380740582943, "avg_return": 0.863460123538971, "regret": 0.0006068928050808609, "entropy": 0.0781613439321518, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:14.489461Z", "loop": 8284, "env_steps": 5090303999, "loss": 0.015856295824050903, "avg_return": 0.862876832485199, "regret": 0.0006068928050808609, "entropy": 0.08187408745288849, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:15.343561Z", "loop": 8285, "env_steps": 5090918399, "loss": 0.017102954909205437, "avg_return": 0.8610504269599915, "regret": 0.0006068928050808609, "entropy": 0.08937430381774902, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:16.197159Z", "loop": 8286, "env_steps": 5091532799, "loss": 0.020131435245275497, "avg_return": 0.8590906262397766, "regret": 0.0006068928050808609, "entropy": 0.10044483095407486, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:17.051453Z", "loop": 8287, "env_steps": 5092147199, "loss": 0.021111411973834038, "avg_return": 0.8549292087554932, "regret": 0.0006068928050808609, "entropy": 0.1026860773563385, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:17.905439Z", "loop": 8288, "env_steps": 5092761599, "loss": 0.022255515679717064, "avg_return": 0.8546885251998901, "regret": 0.0006068928050808609, "entropy": 0.1102495864033699, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:18.759018Z", "loop": 8289, "env_steps": 5093375999, "loss": 0.020956195890903473, "avg_return": 0.8516072630882263, "regret": 0.0006068928050808609, "entropy": 0.1098918691277504, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:19.652436Z", "loop": 8290, "env_steps": 5093990399, "loss": 0.022136621177196503, "avg_return": 0.8554530143737793, "regret": 0.00737431924790144, "entropy": 0.10978496819734573, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:20.505898Z", "loop": 8291, "env_steps": 5094604799, "loss": 0.02156558446586132, "avg_return": 0.8576480150222778, "regret": 0.00737431924790144, "entropy": 0.10674118250608444, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:21.359213Z", "loop": 8292, "env_steps": 5095219199, "loss": 0.019729100167751312, "avg_return": 0.8605173826217651, "regret": 0.00737431924790144, "entropy": 0.1007976084947586, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:22.212675Z", "loop": 8293, "env_steps": 5095833599, "loss": 0.020589133724570274, "avg_return": 0.8590791821479797, "regret": 0.00737431924790144, "entropy": 0.09858522564172745, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:23.066432Z", "loop": 8294, "env_steps": 5096447999, "loss": 0.019990408793091774, "avg_return": 0.8599339127540588, "regret": 0.00737431924790144, "entropy": 0.10141491144895554, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:23.921061Z", "loop": 8295, "env_steps": 5097062399, "loss": 0.019133633002638817, "avg_return": 0.8613027930259705, "regret": 0.00737431924790144, "entropy": 0.09905625134706497, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:24.774037Z", "loop": 8296, "env_steps": 5097676799, "loss": 0.021027255803346634, "avg_return": 0.8621333837509155, "regret": 0.00737431924790144, "entropy": 0.09981481730937958, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:25.628253Z", "loop": 8297, "env_steps": 5098291199, "loss": 0.018317868933081627, "avg_return": 0.8624163866043091, "regret": 0.00737431924790144, "entropy": 0.09011415392160416, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:26.481752Z", "loop": 8298, "env_steps": 5098905599, "loss": 0.01719689927995205, "avg_return": 0.8617004752159119, "regret": 0.00737431924790144, "entropy": 0.08731729537248611, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:27.335909Z", "loop": 8299, "env_steps": 5099519999, "loss": 0.015727449208498, "avg_return": 0.861928403377533, "regret": 0.00737431924790144, "entropy": 0.08398991078138351, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:28.228835Z", "loop": 8300, "env_steps": 5100134399, "loss": 0.01583119109272957, "avg_return": 0.8627309203147888, "regret": 0.0007316078408621252, "entropy": 0.08528567105531693, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:29.082144Z", "loop": 8301, "env_steps": 5100748799, "loss": 0.01628326065838337, "avg_return": 0.8631353974342346, "regret": 0.0007316078408621252, "entropy": 0.08268885314464569, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:29.936820Z", "loop": 8302, "env_steps": 5101363199, "loss": 0.015152725391089916, "avg_return": 0.8623781800270081, "regret": 0.0007316078408621252, "entropy": 0.08026602864265442, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:30.791848Z", "loop": 8303, "env_steps": 5101977599, "loss": 0.014860063791275024, "avg_return": 0.8622535467147827, "regret": 0.0007316078408621252, "entropy": 0.08065333962440491, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:31.645769Z", "loop": 8304, "env_steps": 5102591999, "loss": 0.016684139147400856, "avg_return": 0.8620619773864746, "regret": 0.0007316078408621252, "entropy": 0.08598539233207703, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:32.499313Z", "loop": 8305, "env_steps": 5103206399, "loss": 0.017054570838809013, "avg_return": 0.8627487421035767, "regret": 0.0007316078408621252, "entropy": 0.08853202313184738, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:33.353772Z", "loop": 8306, "env_steps": 5103820799, "loss": 0.018955852836370468, "avg_return": 0.8624374866485596, "regret": 0.0007316078408621252, "entropy": 0.09496355801820755, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:34.207915Z", "loop": 8307, "env_steps": 5104435199, "loss": 0.01992437057197094, "avg_return": 0.8626455068588257, "regret": 0.0007316078408621252, "entropy": 0.09989799559116364, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:35.062057Z", "loop": 8308, "env_steps": 5105049599, "loss": 0.020617282018065453, "avg_return": 0.8614172339439392, "regret": 0.0007316078408621252, "entropy": 0.10304237902164459, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:35.915335Z", "loop": 8309, "env_steps": 5105663999, "loss": 0.020754987373948097, "avg_return": 0.8605021238327026, "regret": 0.0007316078408621252, "entropy": 0.1039917841553688, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:36.811698Z", "loop": 8310, "env_steps": 5106278399, "loss": 0.020975984632968903, "avg_return": 0.8616241812705994, "regret": 0.0011961522977799177, "entropy": 0.10533272475004196, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:37.665144Z", "loop": 8311, "env_steps": 5106892799, "loss": 0.021694593131542206, "avg_return": 0.8608301877975464, "regret": 0.0011961522977799177, "entropy": 0.1045619323849678, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:38.518868Z", "loop": 8312, "env_steps": 5107507199, "loss": 0.022563820704817772, "avg_return": 0.8625907301902771, "regret": 0.0011961522977799177, "entropy": 0.10846933722496033, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:39.372648Z", "loop": 8313, "env_steps": 5108121599, "loss": 0.022770440205931664, "avg_return": 0.8616093397140503, "regret": 0.0011961522977799177, "entropy": 0.1121191754937172, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:40.227149Z", "loop": 8314, "env_steps": 5108735999, "loss": 0.022569332271814346, "avg_return": 0.8626289963722229, "regret": 0.0011961522977799177, "entropy": 0.11563872545957565, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:41.080628Z", "loop": 8315, "env_steps": 5109350399, "loss": 0.02418188378214836, "avg_return": 0.8617019653320312, "regret": 0.0011961522977799177, "entropy": 0.12065498530864716, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:41.934261Z", "loop": 8316, "env_steps": 5109964799, "loss": 0.02152400277554989, "avg_return": 0.8617527484893799, "regret": 0.0011961522977799177, "entropy": 0.11118290573358536, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:42.788382Z", "loop": 8317, "env_steps": 5110579199, "loss": 0.022394901141524315, "avg_return": 0.8620619773864746, "regret": 0.0011961522977799177, "entropy": 0.11051131039857864, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:43.642130Z", "loop": 8318, "env_steps": 5111193599, "loss": 0.020946189761161804, "avg_return": 0.863210141658783, "regret": 0.0011961522977799177, "entropy": 0.10682940483093262, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:44.495355Z", "loop": 8319, "env_steps": 5111807999, "loss": 0.02007947489619255, "avg_return": 0.8628267645835876, "regret": 0.0011961522977799177, "entropy": 0.09967672824859619, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:45.388492Z", "loop": 8320, "env_steps": 5112422399, "loss": 0.018957480788230896, "avg_return": 0.8625465035438538, "regret": 0.0005576072726398706, "entropy": 0.09700936824083328, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:46.242888Z", "loop": 8321, "env_steps": 5113036799, "loss": 0.0179253239184618, "avg_return": 0.8630890250205994, "regret": 0.0005576072726398706, "entropy": 0.09162965416908264, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:47.097973Z", "loop": 8322, "env_steps": 5113651199, "loss": 0.017926231026649475, "avg_return": 0.8629505634307861, "regret": 0.0005576072726398706, "entropy": 0.09167671948671341, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:47.951871Z", "loop": 8323, "env_steps": 5114265599, "loss": 0.01761581562459469, "avg_return": 0.8636148571968079, "regret": 0.0005576072726398706, "entropy": 0.08933689445257187, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:48.806373Z", "loop": 8324, "env_steps": 5114879999, "loss": 0.01832936517894268, "avg_return": 0.8632313013076782, "regret": 0.0005576072726398706, "entropy": 0.09286585450172424, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:49.660503Z", "loop": 8325, "env_steps": 5115494399, "loss": 0.018113242462277412, "avg_return": 0.8639481663703918, "regret": 0.0005576072726398706, "entropy": 0.09251397103071213, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:50.515322Z", "loop": 8326, "env_steps": 5116108799, "loss": 0.01804472878575325, "avg_return": 0.861636757850647, "regret": 0.0005576072726398706, "entropy": 0.09224218130111694, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:51.368641Z", "loop": 8327, "env_steps": 5116723199, "loss": 0.01793328858911991, "avg_return": 0.8636503219604492, "regret": 0.0005576072726398706, "entropy": 0.09116710722446442, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:52.222406Z", "loop": 8328, "env_steps": 5117337599, "loss": 0.018685542047023773, "avg_return": 0.862306535243988, "regret": 0.0005576072726398706, "entropy": 0.09630078822374344, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:53.077059Z", "loop": 8329, "env_steps": 5117951999, "loss": 0.018938614055514336, "avg_return": 0.863869845867157, "regret": 0.0005576072726398706, "entropy": 0.09443599730730057, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:53.971928Z", "loop": 8330, "env_steps": 5118566399, "loss": 0.017766576260328293, "avg_return": 0.8629078269004822, "regret": 0.0008608184871263802, "entropy": 0.08937106281518936, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:54.826714Z", "loop": 8331, "env_steps": 5119180799, "loss": 0.017920996993780136, "avg_return": 0.8636049628257751, "regret": 0.0008608184871263802, "entropy": 0.08798695355653763, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:55.680859Z", "loop": 8332, "env_steps": 5119795199, "loss": 0.016970213502645493, "avg_return": 0.8631682395935059, "regret": 0.0008608184871263802, "entropy": 0.08655554801225662, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:56.533580Z", "loop": 8333, "env_steps": 5120409599, "loss": 0.016259340569376945, "avg_return": 0.8632888197898865, "regret": 0.0008608184871263802, "entropy": 0.08398263156414032, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:57.387578Z", "loop": 8334, "env_steps": 5121023999, "loss": 0.016247214749455452, "avg_return": 0.8632458448410034, "regret": 0.0008608184871263802, "entropy": 0.08422550559043884, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:58.241202Z", "loop": 8335, "env_steps": 5121638399, "loss": 0.015758197754621506, "avg_return": 0.8629971742630005, "regret": 0.0008608184871263802, "entropy": 0.08145511150360107, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:59.094275Z", "loop": 8336, "env_steps": 5122252799, "loss": 0.015508216805756092, "avg_return": 0.8617546558380127, "regret": 0.0008608184871263802, "entropy": 0.08104436099529266, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:22:59.947302Z", "loop": 8337, "env_steps": 5122867199, "loss": 0.015573847107589245, "avg_return": 0.8635761737823486, "regret": 0.0008608184871263802, "entropy": 0.07940755784511566, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:00.801868Z", "loop": 8338, "env_steps": 5123481599, "loss": 0.014517727307975292, "avg_return": 0.8634401559829712, "regret": 0.0008608184871263802, "entropy": 0.07654628902673721, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:01.656588Z", "loop": 8339, "env_steps": 5124095999, "loss": 0.015549764037132263, "avg_return": 0.8620327711105347, "regret": 0.0008608184871263802, "entropy": 0.0829412043094635, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:02.550129Z", "loop": 8340, "env_steps": 5124710399, "loss": 0.014250773005187511, "avg_return": 0.8619633316993713, "regret": 0.0011048426385968924, "entropy": 0.07577873766422272, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:03.403421Z", "loop": 8341, "env_steps": 5125324799, "loss": 0.014342631213366985, "avg_return": 0.8616581559181213, "regret": 0.0011048426385968924, "entropy": 0.07857459038496017, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:04.257395Z", "loop": 8342, "env_steps": 5125939199, "loss": 0.015665268525481224, "avg_return": 0.8612483739852905, "regret": 0.0011048426385968924, "entropy": 0.08354441821575165, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:05.111313Z", "loop": 8343, "env_steps": 5126553599, "loss": 0.014556127600371838, "avg_return": 0.8595497608184814, "regret": 0.0011048426385968924, "entropy": 0.07971140742301941, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:05.965279Z", "loop": 8344, "env_steps": 5127167999, "loss": 0.01594013348221779, "avg_return": 0.8591471314430237, "regret": 0.0011048426385968924, "entropy": 0.08075207471847534, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:06.817315Z", "loop": 8345, "env_steps": 5127782399, "loss": 0.016299262642860413, "avg_return": 0.860302746295929, "regret": 0.0011048426385968924, "entropy": 0.08189037442207336, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:07.670024Z", "loop": 8346, "env_steps": 5128396799, "loss": 0.014801024459302425, "avg_return": 0.8584414720535278, "regret": 0.0011048426385968924, "entropy": 0.07688745111227036, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:08.523806Z", "loop": 8347, "env_steps": 5129011199, "loss": 0.01506399642676115, "avg_return": 0.8592458367347717, "regret": 0.0011048426385968924, "entropy": 0.08246934413909912, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:09.378014Z", "loop": 8348, "env_steps": 5129625599, "loss": 0.014743263833224773, "avg_return": 0.8606258630752563, "regret": 0.0011048426385968924, "entropy": 0.07724156975746155, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:10.231986Z", "loop": 8349, "env_steps": 5130239999, "loss": 0.01604701764881611, "avg_return": 0.8629114031791687, "regret": 0.0011048426385968924, "entropy": 0.08524075150489807, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:11.124739Z", "loop": 8350, "env_steps": 5130854399, "loss": 0.01541652251034975, "avg_return": 0.8623530268669128, "regret": 0.0012472791131585836, "entropy": 0.0821002870798111, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:11.979011Z", "loop": 8351, "env_steps": 5131468799, "loss": 0.015140625648200512, "avg_return": 0.8631522059440613, "regret": 0.0012472791131585836, "entropy": 0.07921263575553894, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:12.833855Z", "loop": 8352, "env_steps": 5132083199, "loss": 0.015335695818066597, "avg_return": 0.8616734147071838, "regret": 0.0012472791131585836, "entropy": 0.08192360401153564, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:13.687635Z", "loop": 8353, "env_steps": 5132697599, "loss": 0.016483066603541374, "avg_return": 0.8634836077690125, "regret": 0.0012472791131585836, "entropy": 0.08670098334550858, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:14.542143Z", "loop": 8354, "env_steps": 5133311999, "loss": 0.01505099143832922, "avg_return": 0.863834023475647, "regret": 0.0012472791131585836, "entropy": 0.08205817639827728, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:15.396179Z", "loop": 8355, "env_steps": 5133926399, "loss": 0.016353299841284752, "avg_return": 0.8645553588867188, "regret": 0.0012472791131585836, "entropy": 0.08761879801750183, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:16.249937Z", "loop": 8356, "env_steps": 5134540799, "loss": 0.016308145597577095, "avg_return": 0.8637457489967346, "regret": 0.0012472791131585836, "entropy": 0.08531251549720764, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:17.104935Z", "loop": 8357, "env_steps": 5135155199, "loss": 0.016483623534440994, "avg_return": 0.8635233640670776, "regret": 0.0012472791131585836, "entropy": 0.086457259953022, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:17.960362Z", "loop": 8358, "env_steps": 5135769599, "loss": 0.017886677756905556, "avg_return": 0.8636640906333923, "regret": 0.0012472791131585836, "entropy": 0.0899302214384079, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:18.814074Z", "loop": 8359, "env_steps": 5136383999, "loss": 0.017952580004930496, "avg_return": 0.862776517868042, "regret": 0.0012472791131585836, "entropy": 0.09258318692445755, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:19.708056Z", "loop": 8360, "env_steps": 5136998399, "loss": 0.019354242831468582, "avg_return": 0.8643831610679626, "regret": 0.00040538187022320926, "entropy": 0.09343861788511276, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:20.562385Z", "loop": 8361, "env_steps": 5137612799, "loss": 0.01779852993786335, "avg_return": 0.8635423183441162, "regret": 0.00040538187022320926, "entropy": 0.09494245052337646, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:21.417469Z", "loop": 8362, "env_steps": 5138227199, "loss": 0.018572384491562843, "avg_return": 0.8642104268074036, "regret": 0.00040538187022320926, "entropy": 0.0940953865647316, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:22.271473Z", "loop": 8363, "env_steps": 5138841599, "loss": 0.01971837691962719, "avg_return": 0.8636944890022278, "regret": 0.00040538187022320926, "entropy": 0.09571953117847443, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:23.125266Z", "loop": 8364, "env_steps": 5139455999, "loss": 0.01860358566045761, "avg_return": 0.8629342913627625, "regret": 0.00040538187022320926, "entropy": 0.0920598953962326, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:23.980460Z", "loop": 8365, "env_steps": 5140070399, "loss": 0.018225980922579765, "avg_return": 0.8627656102180481, "regret": 0.00040538187022320926, "entropy": 0.09671525657176971, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:24.837371Z", "loop": 8366, "env_steps": 5140684799, "loss": 0.018464528024196625, "avg_return": 0.8622770309448242, "regret": 0.00040538187022320926, "entropy": 0.09967971593141556, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:25.691054Z", "loop": 8367, "env_steps": 5141299199, "loss": 0.020737776532769203, "avg_return": 0.8612333536148071, "regret": 0.00040538187022320926, "entropy": 0.10601751506328583, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:26.544487Z", "loop": 8368, "env_steps": 5141913599, "loss": 0.019118476659059525, "avg_return": 0.8620268106460571, "regret": 0.00040538187022320926, "entropy": 0.09635008126497269, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:27.397953Z", "loop": 8369, "env_steps": 5142527999, "loss": 0.020630408078432083, "avg_return": 0.8618025779724121, "regret": 0.00040538187022320926, "entropy": 0.10339212417602539, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:28.292144Z", "loop": 8370, "env_steps": 5143142399, "loss": 0.01911277137696743, "avg_return": 0.8604687452316284, "regret": 0.0014448348665609956, "entropy": 0.09924794733524323, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:29.146129Z", "loop": 8371, "env_steps": 5143756799, "loss": 0.019319938495755196, "avg_return": 0.8620074391365051, "regret": 0.0014448348665609956, "entropy": 0.0999559611082077, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:29.999949Z", "loop": 8372, "env_steps": 5144371199, "loss": 0.020498808473348618, "avg_return": 0.8603143692016602, "regret": 0.0014448348665609956, "entropy": 0.10423937439918518, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:30.853169Z", "loop": 8373, "env_steps": 5144985599, "loss": 0.020556632429361343, "avg_return": 0.86225426197052, "regret": 0.0014448348665609956, "entropy": 0.10422004014253616, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:31.707546Z", "loop": 8374, "env_steps": 5145599999, "loss": 0.020156800746917725, "avg_return": 0.8610747456550598, "regret": 0.0014448348665609956, "entropy": 0.10205428302288055, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:32.561166Z", "loop": 8375, "env_steps": 5146214399, "loss": 0.020185334607958794, "avg_return": 0.8621191382408142, "regret": 0.0014448348665609956, "entropy": 0.1020931676030159, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:33.414559Z", "loop": 8376, "env_steps": 5146828799, "loss": 0.01938686892390251, "avg_return": 0.8622151017189026, "regret": 0.0014448348665609956, "entropy": 0.09433863312005997, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:34.268198Z", "loop": 8377, "env_steps": 5147443199, "loss": 0.017691684886813164, "avg_return": 0.8637529611587524, "regret": 0.0014448348665609956, "entropy": 0.09245213866233826, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:35.121163Z", "loop": 8378, "env_steps": 5148057599, "loss": 0.016872446984052658, "avg_return": 0.8624191284179688, "regret": 0.0014448348665609956, "entropy": 0.09232275933027267, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:35.974759Z", "loop": 8379, "env_steps": 5148671999, "loss": 0.01809946447610855, "avg_return": 0.863460898399353, "regret": 0.0014448348665609956, "entropy": 0.09505348652601242, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:36.869651Z", "loop": 8380, "env_steps": 5149286399, "loss": 0.01722518913447857, "avg_return": 0.86288982629776, "regret": 0.0009433606173843145, "entropy": 0.09024851024150848, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:37.723196Z", "loop": 8381, "env_steps": 5149900799, "loss": 0.017849048599600792, "avg_return": 0.8620709180831909, "regret": 0.0009433606173843145, "entropy": 0.09283699095249176, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:38.577008Z", "loop": 8382, "env_steps": 5150515199, "loss": 0.017123350873589516, "avg_return": 0.8624120354652405, "regret": 0.0009433606173843145, "entropy": 0.09123528748750687, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:39.432007Z", "loop": 8383, "env_steps": 5151129599, "loss": 0.01941513828933239, "avg_return": 0.8632292747497559, "regret": 0.0009433606173843145, "entropy": 0.09954346716403961, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:40.285454Z", "loop": 8384, "env_steps": 5151743999, "loss": 0.018754318356513977, "avg_return": 0.863260805606842, "regret": 0.0009433606173843145, "entropy": 0.10161057114601135, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:41.139933Z", "loop": 8385, "env_steps": 5152358399, "loss": 0.021678222343325615, "avg_return": 0.8627983927726746, "regret": 0.0009433606173843145, "entropy": 0.10746096819639206, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:41.993449Z", "loop": 8386, "env_steps": 5152972799, "loss": 0.0204591266810894, "avg_return": 0.8631788492202759, "regret": 0.0009433606173843145, "entropy": 0.10476549714803696, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:42.847332Z", "loop": 8387, "env_steps": 5153587199, "loss": 0.02149420976638794, "avg_return": 0.8625824451446533, "regret": 0.0009433606173843145, "entropy": 0.11127105355262756, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:43.702561Z", "loop": 8388, "env_steps": 5154201599, "loss": 0.02325100637972355, "avg_return": 0.8618257641792297, "regret": 0.0009433606173843145, "entropy": 0.1154208555817604, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:44.556762Z", "loop": 8389, "env_steps": 5154815999, "loss": 0.022682175040245056, "avg_return": 0.8623842597007751, "regret": 0.0009433606173843145, "entropy": 0.11138866096735, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:45.451108Z", "loop": 8390, "env_steps": 5155430399, "loss": 0.024721259251236916, "avg_return": 0.8610086441040039, "regret": 0.0006475689588114619, "entropy": 0.11891663074493408, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:46.305718Z", "loop": 8391, "env_steps": 5156044799, "loss": 0.022892845794558525, "avg_return": 0.8630353212356567, "regret": 0.0006475689588114619, "entropy": 0.11722568422555923, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:47.160824Z", "loop": 8392, "env_steps": 5156659199, "loss": 0.022699547931551933, "avg_return": 0.8615350723266602, "regret": 0.0006475689588114619, "entropy": 0.11134882271289825, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:48.017318Z", "loop": 8393, "env_steps": 5157273599, "loss": 0.02035105973482132, "avg_return": 0.8627501726150513, "regret": 0.0006475689588114619, "entropy": 0.10638322681188583, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:48.873545Z", "loop": 8394, "env_steps": 5157887999, "loss": 0.01821913570165634, "avg_return": 0.8632609248161316, "regret": 0.0006475689588114619, "entropy": 0.09680962562561035, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:49.728308Z", "loop": 8395, "env_steps": 5158502399, "loss": 0.017496582120656967, "avg_return": 0.8627428412437439, "regret": 0.0006475689588114619, "entropy": 0.09288637340068817, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:50.582724Z", "loop": 8396, "env_steps": 5159116799, "loss": 0.016716368496418, "avg_return": 0.8638910055160522, "regret": 0.0006475689588114619, "entropy": 0.08937878906726837, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:51.438526Z", "loop": 8397, "env_steps": 5159731199, "loss": 0.016947759315371513, "avg_return": 0.8632364273071289, "regret": 0.0006475689588114619, "entropy": 0.08804769814014435, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:52.293746Z", "loop": 8398, "env_steps": 5160345599, "loss": 0.015706093981862068, "avg_return": 0.8638824820518494, "regret": 0.0006475689588114619, "entropy": 0.07836795598268509, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:53.147433Z", "loop": 8399, "env_steps": 5160959999, "loss": 0.014735236763954163, "avg_return": 0.8637079000473022, "regret": 0.0006475689588114619, "entropy": 0.07766880095005035, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:54.041487Z", "loop": 8400, "env_steps": 5161574399, "loss": 0.015513025224208832, "avg_return": 0.86262047290802, "regret": 0.00041461430373601615, "entropy": 0.08330083638429642, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:54.895916Z", "loop": 8401, "env_steps": 5162188799, "loss": 0.016390187665820122, "avg_return": 0.8631276488304138, "regret": 0.00041461430373601615, "entropy": 0.08472555130720139, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:55.749304Z", "loop": 8402, "env_steps": 5162803199, "loss": 0.015584717504680157, "avg_return": 0.8613200187683105, "regret": 0.00041461430373601615, "entropy": 0.0850483700633049, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:56.603624Z", "loop": 8403, "env_steps": 5163417599, "loss": 0.015265568159520626, "avg_return": 0.8635971546173096, "regret": 0.00041461430373601615, "entropy": 0.08229850232601166, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:57.457790Z", "loop": 8404, "env_steps": 5164031999, "loss": 0.015897592529654503, "avg_return": 0.8633915185928345, "regret": 0.00041461430373601615, "entropy": 0.0837140753865242, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:58.311963Z", "loop": 8405, "env_steps": 5164646399, "loss": 0.017325645312666893, "avg_return": 0.862483024597168, "regret": 0.00041461430373601615, "entropy": 0.08544882386922836, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:23:59.166404Z", "loop": 8406, "env_steps": 5165260799, "loss": 0.016322696581482887, "avg_return": 0.8651894330978394, "regret": 0.00041461430373601615, "entropy": 0.08560559153556824, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:00.021410Z", "loop": 8407, "env_steps": 5165875199, "loss": 0.01725812815129757, "avg_return": 0.8625325560569763, "regret": 0.00041461430373601615, "entropy": 0.09139910340309143, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:00.876295Z", "loop": 8408, "env_steps": 5166489599, "loss": 0.017539968714118004, "avg_return": 0.8628855347633362, "regret": 0.00041461430373601615, "entropy": 0.09131503850221634, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:01.731751Z", "loop": 8409, "env_steps": 5167103999, "loss": 0.0183622594922781, "avg_return": 0.8634169697761536, "regret": 0.00041461430373601615, "entropy": 0.09242172539234161, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:02.626284Z", "loop": 8410, "env_steps": 5167718399, "loss": 0.019568301737308502, "avg_return": 0.863064169883728, "regret": 0.0010869069956243038, "entropy": 0.09901183843612671, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:03.479984Z", "loop": 8411, "env_steps": 5168332799, "loss": 0.021469447761774063, "avg_return": 0.8629046082496643, "regret": 0.0010869069956243038, "entropy": 0.1057305783033371, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:04.334540Z", "loop": 8412, "env_steps": 5168947199, "loss": 0.02004791609942913, "avg_return": 0.8623508810997009, "regret": 0.0010869069956243038, "entropy": 0.10219896584749222, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:05.188207Z", "loop": 8413, "env_steps": 5169561599, "loss": 0.01975228264927864, "avg_return": 0.8607607483863831, "regret": 0.0010869069956243038, "entropy": 0.10434284806251526, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:06.041201Z", "loop": 8414, "env_steps": 5170175999, "loss": 0.02102147601544857, "avg_return": 0.8617822527885437, "regret": 0.0010869069956243038, "entropy": 0.103086918592453, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:06.894883Z", "loop": 8415, "env_steps": 5170790399, "loss": 0.021474037319421768, "avg_return": 0.8626486659049988, "regret": 0.0010869069956243038, "entropy": 0.1082194596529007, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:07.748837Z", "loop": 8416, "env_steps": 5171404799, "loss": 0.02125653438270092, "avg_return": 0.8607363104820251, "regret": 0.0010869069956243038, "entropy": 0.10680622607469559, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:08.603121Z", "loop": 8417, "env_steps": 5172019199, "loss": 0.01987798884510994, "avg_return": 0.8615562319755554, "regret": 0.0010869069956243038, "entropy": 0.10339778661727905, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:09.457282Z", "loop": 8418, "env_steps": 5172633599, "loss": 0.01975410059094429, "avg_return": 0.8626968860626221, "regret": 0.0010869069956243038, "entropy": 0.10177945345640182, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:10.310891Z", "loop": 8419, "env_steps": 5173247999, "loss": 0.017832065001130104, "avg_return": 0.8623121380805969, "regret": 0.0010869069956243038, "entropy": 0.09540414810180664, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:11.205934Z", "loop": 8420, "env_steps": 5173862399, "loss": 0.016747167333960533, "avg_return": 0.8634217381477356, "regret": 0.0012515031266957521, "entropy": 0.09091288596391678, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:12.060411Z", "loop": 8421, "env_steps": 5174476799, "loss": 0.017058825120329857, "avg_return": 0.8625525236129761, "regret": 0.0012515031266957521, "entropy": 0.09039462357759476, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:12.914223Z", "loop": 8422, "env_steps": 5175091199, "loss": 0.01754351519048214, "avg_return": 0.8619130849838257, "regret": 0.0012515031266957521, "entropy": 0.09618061780929565, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:13.768191Z", "loop": 8423, "env_steps": 5175705599, "loss": 0.017690040171146393, "avg_return": 0.862084686756134, "regret": 0.0012515031266957521, "entropy": 0.09527108073234558, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:14.623651Z", "loop": 8424, "env_steps": 5176319999, "loss": 0.01716645434498787, "avg_return": 0.8614868521690369, "regret": 0.0012515031266957521, "entropy": 0.0959644690155983, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:15.479198Z", "loop": 8425, "env_steps": 5176934399, "loss": 0.01859162747859955, "avg_return": 0.8624697327613831, "regret": 0.0012515031266957521, "entropy": 0.09625586122274399, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:16.334082Z", "loop": 8426, "env_steps": 5177548799, "loss": 0.018724121153354645, "avg_return": 0.86229008436203, "regret": 0.0012515031266957521, "entropy": 0.09669569134712219, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:17.189341Z", "loop": 8427, "env_steps": 5178163199, "loss": 0.015930822119116783, "avg_return": 0.8621824383735657, "regret": 0.0012515031266957521, "entropy": 0.08840349316596985, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:18.044591Z", "loop": 8428, "env_steps": 5178777599, "loss": 0.017266230657696724, "avg_return": 0.8623478412628174, "regret": 0.0012515031266957521, "entropy": 0.0943937599658966, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:18.900154Z", "loop": 8429, "env_steps": 5179391999, "loss": 0.01732439361512661, "avg_return": 0.8632246851921082, "regret": 0.0012515031266957521, "entropy": 0.0924474373459816, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:19.795954Z", "loop": 8430, "env_steps": 5180006399, "loss": 0.017845777794718742, "avg_return": 0.8625946044921875, "regret": 0.0004732687375508249, "entropy": 0.09318205714225769, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:20.649932Z", "loop": 8431, "env_steps": 5180620799, "loss": 0.017330309376120567, "avg_return": 0.8635457754135132, "regret": 0.0004732687375508249, "entropy": 0.08773723244667053, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:21.506739Z", "loop": 8432, "env_steps": 5181235199, "loss": 0.01655806042253971, "avg_return": 0.862990140914917, "regret": 0.0004732687375508249, "entropy": 0.0900287851691246, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:22.361326Z", "loop": 8433, "env_steps": 5181849599, "loss": 0.016540102660655975, "avg_return": 0.8638617396354675, "regret": 0.0004732687375508249, "entropy": 0.08758159726858139, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:23.215558Z", "loop": 8434, "env_steps": 5182463999, "loss": 0.016416294500231743, "avg_return": 0.8615311980247498, "regret": 0.0004732687375508249, "entropy": 0.08942592144012451, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:24.069197Z", "loop": 8435, "env_steps": 5183078399, "loss": 0.01637244038283825, "avg_return": 0.86350417137146, "regret": 0.0004732687375508249, "entropy": 0.08909419178962708, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:24.923293Z", "loop": 8436, "env_steps": 5183692799, "loss": 0.015853269025683403, "avg_return": 0.8630006909370422, "regret": 0.0004732687375508249, "entropy": 0.08345393091440201, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:25.778258Z", "loop": 8437, "env_steps": 5184307199, "loss": 0.016188299283385277, "avg_return": 0.8627013564109802, "regret": 0.0004732687375508249, "entropy": 0.0851404145359993, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:26.632581Z", "loop": 8438, "env_steps": 5184921599, "loss": 0.015018338337540627, "avg_return": 0.8640293478965759, "regret": 0.0004732687375508249, "entropy": 0.08007370680570602, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:27.486725Z", "loop": 8439, "env_steps": 5185535999, "loss": 0.015975849702954292, "avg_return": 0.8626345992088318, "regret": 0.0004732687375508249, "entropy": 0.08450816571712494, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:28.381931Z", "loop": 8440, "env_steps": 5186150399, "loss": 0.01436828263103962, "avg_return": 0.8622912764549255, "regret": 0.00046037050196900964, "entropy": 0.08109018206596375, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:29.235109Z", "loop": 8441, "env_steps": 5186764799, "loss": 0.015195158310234547, "avg_return": 0.8627634644508362, "regret": 0.00046037050196900964, "entropy": 0.07858534902334213, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:30.089730Z", "loop": 8442, "env_steps": 5187379199, "loss": 0.015444154851138592, "avg_return": 0.8629305362701416, "regret": 0.00046037050196900964, "entropy": 0.08036370575428009, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:30.944522Z", "loop": 8443, "env_steps": 5187993599, "loss": 0.015072165988385677, "avg_return": 0.8625773191452026, "regret": 0.00046037050196900964, "entropy": 0.08157908916473389, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:31.800020Z", "loop": 8444, "env_steps": 5188607999, "loss": 0.014818123541772366, "avg_return": 0.8626229166984558, "regret": 0.00046037050196900964, "entropy": 0.08089352399110794, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:32.653767Z", "loop": 8445, "env_steps": 5189222399, "loss": 0.014513951726257801, "avg_return": 0.8630884289741516, "regret": 0.00046037050196900964, "entropy": 0.07609027624130249, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:33.507038Z", "loop": 8446, "env_steps": 5189836799, "loss": 0.015461616218090057, "avg_return": 0.8632494211196899, "regret": 0.00046037050196900964, "entropy": 0.08276484161615372, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:34.362378Z", "loop": 8447, "env_steps": 5190451199, "loss": 0.015453032217919827, "avg_return": 0.8633488416671753, "regret": 0.00046037050196900964, "entropy": 0.07850650697946548, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:35.216705Z", "loop": 8448, "env_steps": 5191065599, "loss": 0.014501524157822132, "avg_return": 0.8611955046653748, "regret": 0.00046037050196900964, "entropy": 0.07688923180103302, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:36.070142Z", "loop": 8449, "env_steps": 5191679999, "loss": 0.015941962599754333, "avg_return": 0.8627392649650574, "regret": 0.00046037050196900964, "entropy": 0.08067528158426285, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:36.965295Z", "loop": 8450, "env_steps": 5192294399, "loss": 0.015584622509777546, "avg_return": 0.8626487255096436, "regret": 0.0005451393080875278, "entropy": 0.08569082617759705, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:37.821308Z", "loop": 8451, "env_steps": 5192908799, "loss": 0.01556742936372757, "avg_return": 0.8629857301712036, "regret": 0.0005451393080875278, "entropy": 0.08372615277767181, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:38.675253Z", "loop": 8452, "env_steps": 5193523199, "loss": 0.015349996276199818, "avg_return": 0.8633739352226257, "regret": 0.0005451393080875278, "entropy": 0.08025390654802322, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:39.529582Z", "loop": 8453, "env_steps": 5194137599, "loss": 0.015438842587172985, "avg_return": 0.8638588786125183, "regret": 0.0005451393080875278, "entropy": 0.07956139743328094, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:40.383283Z", "loop": 8454, "env_steps": 5194751999, "loss": 0.014882086776196957, "avg_return": 0.8621922135353088, "regret": 0.0005451393080875278, "entropy": 0.07860866189002991, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:41.237199Z", "loop": 8455, "env_steps": 5195366399, "loss": 0.014055000618100166, "avg_return": 0.8640990257263184, "regret": 0.0005451393080875278, "entropy": 0.07887568324804306, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:42.091153Z", "loop": 8456, "env_steps": 5195980799, "loss": 0.015380138531327248, "avg_return": 0.8634713888168335, "regret": 0.0005451393080875278, "entropy": 0.07949408888816833, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:42.945798Z", "loop": 8457, "env_steps": 5196595199, "loss": 0.015018859878182411, "avg_return": 0.8629698753356934, "regret": 0.0005451393080875278, "entropy": 0.08057764917612076, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:43.799555Z", "loop": 8458, "env_steps": 5197209599, "loss": 0.015283147804439068, "avg_return": 0.8626188635826111, "regret": 0.0005451393080875278, "entropy": 0.08074771612882614, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:44.654859Z", "loop": 8459, "env_steps": 5197823999, "loss": 0.015287565067410469, "avg_return": 0.863260805606842, "regret": 0.0005451393080875278, "entropy": 0.07913936674594879, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:45.549919Z", "loop": 8460, "env_steps": 5198438399, "loss": 0.014595436863601208, "avg_return": 0.8633952140808105, "regret": 0.0008017178042791784, "entropy": 0.07641144096851349, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:46.403956Z", "loop": 8461, "env_steps": 5199052799, "loss": 0.013901472091674805, "avg_return": 0.863283634185791, "regret": 0.0008017178042791784, "entropy": 0.07824045419692993, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:47.258749Z", "loop": 8462, "env_steps": 5199667199, "loss": 0.01461966522037983, "avg_return": 0.8639404773712158, "regret": 0.0008017178042791784, "entropy": 0.07964839041233063, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:48.114042Z", "loop": 8463, "env_steps": 5200281599, "loss": 0.015020220540463924, "avg_return": 0.8631542325019836, "regret": 0.0008017178042791784, "entropy": 0.07771662622690201, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:48.967532Z", "loop": 8464, "env_steps": 5200895999, "loss": 0.01442014891654253, "avg_return": 0.8622561097145081, "regret": 0.0008017178042791784, "entropy": 0.0789206400513649, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:49.821454Z", "loop": 8465, "env_steps": 5201510399, "loss": 0.01338858064264059, "avg_return": 0.8618471622467041, "regret": 0.0008017178042791784, "entropy": 0.0748353898525238, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:50.675779Z", "loop": 8466, "env_steps": 5202124799, "loss": 0.015309385024011135, "avg_return": 0.8627825975418091, "regret": 0.0008017178042791784, "entropy": 0.08166906982660294, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:51.531377Z", "loop": 8467, "env_steps": 5202739199, "loss": 0.015882370993494987, "avg_return": 0.8624244332313538, "regret": 0.0008017178042791784, "entropy": 0.08233056217432022, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:52.385457Z", "loop": 8468, "env_steps": 5203353599, "loss": 0.01594536565244198, "avg_return": 0.8619694113731384, "regret": 0.0008017178042791784, "entropy": 0.0844939798116684, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:53.238615Z", "loop": 8469, "env_steps": 5203967999, "loss": 0.01589108072221279, "avg_return": 0.8605301380157471, "regret": 0.0008017178042791784, "entropy": 0.08652181923389435, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:54.131516Z", "loop": 8470, "env_steps": 5204582399, "loss": 0.01599811017513275, "avg_return": 0.8620254993438721, "regret": 0.0012232454027980566, "entropy": 0.08543211966753006, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:54.986801Z", "loop": 8471, "env_steps": 5205196799, "loss": 0.017129873856902122, "avg_return": 0.8628257513046265, "regret": 0.0012232454027980566, "entropy": 0.08515189588069916, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:55.840732Z", "loop": 8472, "env_steps": 5205811199, "loss": 0.017372382804751396, "avg_return": 0.8626639246940613, "regret": 0.0012232454027980566, "entropy": 0.09096518158912659, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:56.694871Z", "loop": 8473, "env_steps": 5206425599, "loss": 0.01867106929421425, "avg_return": 0.8611879944801331, "regret": 0.0012232454027980566, "entropy": 0.09642598032951355, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:57.549722Z", "loop": 8474, "env_steps": 5207039999, "loss": 0.017620310187339783, "avg_return": 0.8636446595191956, "regret": 0.0012232454027980566, "entropy": 0.09088209271430969, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:58.404629Z", "loop": 8475, "env_steps": 5207654399, "loss": 0.017953602597117424, "avg_return": 0.8614925146102905, "regret": 0.0012232454027980566, "entropy": 0.09293855726718903, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:24:59.258980Z", "loop": 8476, "env_steps": 5208268799, "loss": 0.01834545098245144, "avg_return": 0.8622953295707703, "regret": 0.0012232454027980566, "entropy": 0.09238561987876892, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:00.113816Z", "loop": 8477, "env_steps": 5208883199, "loss": 0.01778256520628929, "avg_return": 0.8615354895591736, "regret": 0.0012232454027980566, "entropy": 0.0905279666185379, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:00.968521Z", "loop": 8478, "env_steps": 5209497599, "loss": 0.019770672544836998, "avg_return": 0.8604891896247864, "regret": 0.0012232454027980566, "entropy": 0.10013447701931, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:01.823123Z", "loop": 8479, "env_steps": 5210111999, "loss": 0.01834346167743206, "avg_return": 0.8629158735275269, "regret": 0.0012232454027980566, "entropy": 0.0946197584271431, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:02.718912Z", "loop": 8480, "env_steps": 5210726399, "loss": 0.01784963719546795, "avg_return": 0.8623841404914856, "regret": 0.0013670477783307433, "entropy": 0.09301730245351791, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:03.573095Z", "loop": 8481, "env_steps": 5211340799, "loss": 0.017027972266077995, "avg_return": 0.863074779510498, "regret": 0.0013670477783307433, "entropy": 0.08940482139587402, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:04.427522Z", "loop": 8482, "env_steps": 5211955199, "loss": 0.01691347546875477, "avg_return": 0.8625131249427795, "regret": 0.0013670477783307433, "entropy": 0.08635640889406204, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:05.282126Z", "loop": 8483, "env_steps": 5212569599, "loss": 0.015672745183110237, "avg_return": 0.8620432615280151, "regret": 0.0013670477783307433, "entropy": 0.088407963514328, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:06.136930Z", "loop": 8484, "env_steps": 5213183999, "loss": 0.014495395123958588, "avg_return": 0.8613634705543518, "regret": 0.0013670477783307433, "entropy": 0.08427218347787857, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:06.990399Z", "loop": 8485, "env_steps": 5213798399, "loss": 0.01570006087422371, "avg_return": 0.862901508808136, "regret": 0.0013670477783307433, "entropy": 0.08532305061817169, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:07.844144Z", "loop": 8486, "env_steps": 5214412799, "loss": 0.015880826860666275, "avg_return": 0.8625666499137878, "regret": 0.0013670477783307433, "entropy": 0.08463640511035919, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:08.698157Z", "loop": 8487, "env_steps": 5215027199, "loss": 0.01599164493381977, "avg_return": 0.8636356592178345, "regret": 0.0013670477783307433, "entropy": 0.08587291836738586, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:09.552730Z", "loop": 8488, "env_steps": 5215641599, "loss": 0.01599438302218914, "avg_return": 0.8626101016998291, "regret": 0.0013670477783307433, "entropy": 0.0868186354637146, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:10.406704Z", "loop": 8489, "env_steps": 5216255999, "loss": 0.01639537140727043, "avg_return": 0.862859308719635, "regret": 0.0013670477783307433, "entropy": 0.08637397736310959, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:11.301521Z", "loop": 8490, "env_steps": 5216870399, "loss": 0.018311530351638794, "avg_return": 0.8640345335006714, "regret": 0.0005302989156916738, "entropy": 0.08960714191198349, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:12.158244Z", "loop": 8491, "env_steps": 5217484799, "loss": 0.01755908504128456, "avg_return": 0.8634210228919983, "regret": 0.0005302989156916738, "entropy": 0.09073858708143234, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:13.012890Z", "loop": 8492, "env_steps": 5218099199, "loss": 0.018392737954854965, "avg_return": 0.8630733489990234, "regret": 0.0005302989156916738, "entropy": 0.09441880136728287, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:13.866679Z", "loop": 8493, "env_steps": 5218713599, "loss": 0.017410779371857643, "avg_return": 0.8625378608703613, "regret": 0.0005302989156916738, "entropy": 0.0926084890961647, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:14.720539Z", "loop": 8494, "env_steps": 5219327999, "loss": 0.017842859029769897, "avg_return": 0.8616548776626587, "regret": 0.0005302989156916738, "entropy": 0.09010408818721771, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:15.574384Z", "loop": 8495, "env_steps": 5219942399, "loss": 0.017581121996045113, "avg_return": 0.8636349439620972, "regret": 0.0005302989156916738, "entropy": 0.09201307594776154, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:16.428548Z", "loop": 8496, "env_steps": 5220556799, "loss": 0.018325557932257652, "avg_return": 0.8626764416694641, "regret": 0.0005302989156916738, "entropy": 0.09041052311658859, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:17.283519Z", "loop": 8497, "env_steps": 5221171199, "loss": 0.018057800829410553, "avg_return": 0.8626102805137634, "regret": 0.0005302989156916738, "entropy": 0.08926653861999512, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:18.138150Z", "loop": 8498, "env_steps": 5221785599, "loss": 0.01821984350681305, "avg_return": 0.8636444211006165, "regret": 0.0005302989156916738, "entropy": 0.09344424307346344, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:18.992404Z", "loop": 8499, "env_steps": 5222399999, "loss": 0.0183696486055851, "avg_return": 0.8640274405479431, "regret": 0.0005302989156916738, "entropy": 0.09509604424238205, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:19.885397Z", "loop": 8500, "env_steps": 5223014399, "loss": 0.018940765410661697, "avg_return": 0.8634930849075317, "regret": 0.00034022104227915406, "entropy": 0.09526511281728745, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:20.740753Z", "loop": 8501, "env_steps": 5223628799, "loss": 0.019088152796030045, "avg_return": 0.8617154359817505, "regret": 0.00034022104227915406, "entropy": 0.0974772498011589, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:21.595256Z", "loop": 8502, "env_steps": 5224243199, "loss": 0.01887044683098793, "avg_return": 0.8657951951026917, "regret": 0.00034022104227915406, "entropy": 0.09318177402019501, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:22.450757Z", "loop": 8503, "env_steps": 5224857599, "loss": 0.01988239400088787, "avg_return": 0.8624479174613953, "regret": 0.00034022104227915406, "entropy": 0.09814396500587463, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:23.306043Z", "loop": 8504, "env_steps": 5225471999, "loss": 0.01985124498605728, "avg_return": 0.8629380464553833, "regret": 0.00034022104227915406, "entropy": 0.0972142443060875, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:24.161299Z", "loop": 8505, "env_steps": 5226086399, "loss": 0.019010405987501144, "avg_return": 0.8641930222511292, "regret": 0.00034022104227915406, "entropy": 0.09701766818761826, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:25.016436Z", "loop": 8506, "env_steps": 5226700799, "loss": 0.01952308602631092, "avg_return": 0.8634254336357117, "regret": 0.00034022104227915406, "entropy": 0.09779103845357895, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:25.873470Z", "loop": 8507, "env_steps": 5227315199, "loss": 0.02035454474389553, "avg_return": 0.8616973161697388, "regret": 0.00034022104227915406, "entropy": 0.1033717691898346, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:26.728841Z", "loop": 8508, "env_steps": 5227929599, "loss": 0.01891334168612957, "avg_return": 0.8631628751754761, "regret": 0.00034022104227915406, "entropy": 0.09607210010290146, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:27.583953Z", "loop": 8509, "env_steps": 5228543999, "loss": 0.020324939861893654, "avg_return": 0.8639894723892212, "regret": 0.00034022104227915406, "entropy": 0.10078839957714081, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:28.479503Z", "loop": 8510, "env_steps": 5229158399, "loss": 0.019474541768431664, "avg_return": 0.8639473915100098, "regret": 0.00039577484130859375, "entropy": 0.09718427062034607, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:29.335390Z", "loop": 8511, "env_steps": 5229772799, "loss": 0.018968960270285606, "avg_return": 0.8625824451446533, "regret": 0.00039577484130859375, "entropy": 0.09696229547262192, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:30.190331Z", "loop": 8512, "env_steps": 5230387199, "loss": 0.020000340417027473, "avg_return": 0.8627487421035767, "regret": 0.00039577484130859375, "entropy": 0.10021873563528061, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:31.044180Z", "loop": 8513, "env_steps": 5231001599, "loss": 0.018866967409849167, "avg_return": 0.8634822964668274, "regret": 0.00039577484130859375, "entropy": 0.09510307759046555, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:31.897505Z", "loop": 8514, "env_steps": 5231615999, "loss": 0.018597403541207314, "avg_return": 0.8648806214332581, "regret": 0.00039577484130859375, "entropy": 0.09378047287464142, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:32.752072Z", "loop": 8515, "env_steps": 5232230399, "loss": 0.01742631196975708, "avg_return": 0.863044023513794, "regret": 0.00039577484130859375, "entropy": 0.0887477844953537, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:33.606500Z", "loop": 8516, "env_steps": 5232844799, "loss": 0.018382569774985313, "avg_return": 0.8629400730133057, "regret": 0.00039577484130859375, "entropy": 0.08970320224761963, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:34.460802Z", "loop": 8517, "env_steps": 5233459199, "loss": 0.018212774768471718, "avg_return": 0.8634847402572632, "regret": 0.00039577484130859375, "entropy": 0.09209361672401428, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:35.314144Z", "loop": 8518, "env_steps": 5234073599, "loss": 0.01826382987201214, "avg_return": 0.8629191517829895, "regret": 0.00039577484130859375, "entropy": 0.09568747133016586, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:36.168729Z", "loop": 8519, "env_steps": 5234687999, "loss": 0.017335548996925354, "avg_return": 0.8639538884162903, "regret": 0.00039577484130859375, "entropy": 0.08879372477531433, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:37.062962Z", "loop": 8520, "env_steps": 5235302399, "loss": 0.018024848774075508, "avg_return": 0.8639420866966248, "regret": 0.0003550084074959159, "entropy": 0.09335920959711075, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:37.917367Z", "loop": 8521, "env_steps": 5235916799, "loss": 0.01707601174712181, "avg_return": 0.8626583218574524, "regret": 0.0003550084074959159, "entropy": 0.08906533569097519, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:38.771440Z", "loop": 8522, "env_steps": 5236531199, "loss": 0.017934849485754967, "avg_return": 0.8638859391212463, "regret": 0.0003550084074959159, "entropy": 0.0900614932179451, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:39.626551Z", "loop": 8523, "env_steps": 5237145599, "loss": 0.01797139085829258, "avg_return": 0.8642134666442871, "regret": 0.0003550084074959159, "entropy": 0.09268522262573242, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:40.481435Z", "loop": 8524, "env_steps": 5237759999, "loss": 0.018897544592618942, "avg_return": 0.8635862469673157, "regret": 0.0003550084074959159, "entropy": 0.09197340160608292, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:41.336522Z", "loop": 8525, "env_steps": 5238374399, "loss": 0.01899818703532219, "avg_return": 0.8613865375518799, "regret": 0.0003550084074959159, "entropy": 0.09446875005960464, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:42.191825Z", "loop": 8526, "env_steps": 5238988799, "loss": 0.018115507438778877, "avg_return": 0.8634471893310547, "regret": 0.0003550084074959159, "entropy": 0.09579997509717941, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:43.046060Z", "loop": 8527, "env_steps": 5239603199, "loss": 0.018591510131955147, "avg_return": 0.8624330759048462, "regret": 0.0003550084074959159, "entropy": 0.09618454426527023, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:43.899601Z", "loop": 8528, "env_steps": 5240217599, "loss": 0.01743416115641594, "avg_return": 0.8619252443313599, "regret": 0.0003550084074959159, "entropy": 0.09401668608188629, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:44.753131Z", "loop": 8529, "env_steps": 5240831999, "loss": 0.01685367338359356, "avg_return": 0.8622980117797852, "regret": 0.0003550084074959159, "entropy": 0.08895044773817062, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:45.646449Z", "loop": 8530, "env_steps": 5241446399, "loss": 0.017660511657595634, "avg_return": 0.861825704574585, "regret": 0.0012291220482438803, "entropy": 0.09619288146495819, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:46.500661Z", "loop": 8531, "env_steps": 5242060799, "loss": 0.01809110678732395, "avg_return": 0.8630256056785583, "regret": 0.0012291220482438803, "entropy": 0.0917859598994255, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:47.354827Z", "loop": 8532, "env_steps": 5242675199, "loss": 0.017808988690376282, "avg_return": 0.8627871870994568, "regret": 0.0012291220482438803, "entropy": 0.09492739289999008, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:48.209873Z", "loop": 8533, "env_steps": 5243289599, "loss": 0.015949567779898643, "avg_return": 0.8626619577407837, "regret": 0.0012291220482438803, "entropy": 0.0889444425702095, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:49.064467Z", "loop": 8534, "env_steps": 5243903999, "loss": 0.01656232587993145, "avg_return": 0.8630547523498535, "regret": 0.0012291220482438803, "entropy": 0.0890394076704979, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:49.918826Z", "loop": 8535, "env_steps": 5244518399, "loss": 0.016931334510445595, "avg_return": 0.8622376918792725, "regret": 0.0012291220482438803, "entropy": 0.0910092368721962, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:50.772212Z", "loop": 8536, "env_steps": 5245132799, "loss": 0.017270980402827263, "avg_return": 0.8626841306686401, "regret": 0.0012291220482438803, "entropy": 0.09258799254894257, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:51.625616Z", "loop": 8537, "env_steps": 5245747199, "loss": 0.01741286925971508, "avg_return": 0.8629862666130066, "regret": 0.0012291220482438803, "entropy": 0.09173718839883804, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:52.480037Z", "loop": 8538, "env_steps": 5246361599, "loss": 0.016759758815169334, "avg_return": 0.8626747727394104, "regret": 0.0012291220482438803, "entropy": 0.08752356469631195, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:53.335154Z", "loop": 8539, "env_steps": 5246975999, "loss": 0.01692979410290718, "avg_return": 0.8641863465309143, "regret": 0.0012291220482438803, "entropy": 0.08731013536453247, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:54.230612Z", "loop": 8540, "env_steps": 5247590399, "loss": 0.018248090520501137, "avg_return": 0.8635005950927734, "regret": 0.0003174160956405103, "entropy": 0.09241924434900284, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:55.084209Z", "loop": 8541, "env_steps": 5248204799, "loss": 0.019200831651687622, "avg_return": 0.8634466528892517, "regret": 0.0003174160956405103, "entropy": 0.0935942530632019, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:55.938921Z", "loop": 8542, "env_steps": 5248819199, "loss": 0.018192557618021965, "avg_return": 0.8632295727729797, "regret": 0.0003174160956405103, "entropy": 0.09341342002153397, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:56.793620Z", "loop": 8543, "env_steps": 5249433599, "loss": 0.017830422148108482, "avg_return": 0.8628711104393005, "regret": 0.0003174160956405103, "entropy": 0.09178899973630905, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:57.648811Z", "loop": 8544, "env_steps": 5250047999, "loss": 0.016787497326731682, "avg_return": 0.8641571402549744, "regret": 0.0003174160956405103, "entropy": 0.09057313203811646, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:58.502974Z", "loop": 8545, "env_steps": 5250662399, "loss": 0.01923791691660881, "avg_return": 0.8623192310333252, "regret": 0.0003174160956405103, "entropy": 0.09674876928329468, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:25:59.358036Z", "loop": 8546, "env_steps": 5251276799, "loss": 0.01859482191503048, "avg_return": 0.8638017177581787, "regret": 0.0003174160956405103, "entropy": 0.0920652374625206, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:00.213614Z", "loop": 8547, "env_steps": 5251891199, "loss": 0.018055995926260948, "avg_return": 0.8640874624252319, "regret": 0.0003174160956405103, "entropy": 0.09392745047807693, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:01.068531Z", "loop": 8548, "env_steps": 5252505599, "loss": 0.019422536715865135, "avg_return": 0.8629305362701416, "regret": 0.0003174160956405103, "entropy": 0.09605427831411362, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:01.922385Z", "loop": 8549, "env_steps": 5253119999, "loss": 0.01935446821153164, "avg_return": 0.8633517622947693, "regret": 0.0003174160956405103, "entropy": 0.09916975349187851, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:02.816110Z", "loop": 8550, "env_steps": 5253734399, "loss": 0.018893109634518623, "avg_return": 0.8621237277984619, "regret": 0.0009428742341697216, "entropy": 0.09799177199602127, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:03.670964Z", "loop": 8551, "env_steps": 5254348799, "loss": 0.018632618710398674, "avg_return": 0.8607092499732971, "regret": 0.0009428742341697216, "entropy": 0.09552109986543655, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:04.525618Z", "loop": 8552, "env_steps": 5254963199, "loss": 0.018368979915976524, "avg_return": 0.8601745963096619, "regret": 0.0009428742341697216, "entropy": 0.10305489599704742, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:05.380417Z", "loop": 8553, "env_steps": 5255577599, "loss": 0.01984412968158722, "avg_return": 0.8600345849990845, "regret": 0.0009428742341697216, "entropy": 0.10893107950687408, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:06.234537Z", "loop": 8554, "env_steps": 5256191999, "loss": 0.01884402520954609, "avg_return": 0.8588119745254517, "regret": 0.0009428742341697216, "entropy": 0.10684360563755035, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:07.089413Z", "loop": 8555, "env_steps": 5256806399, "loss": 0.02017572708427906, "avg_return": 0.8584335446357727, "regret": 0.0009428742341697216, "entropy": 0.10770561546087265, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:07.944426Z", "loop": 8556, "env_steps": 5257420799, "loss": 0.016396664083003998, "avg_return": 0.860218346118927, "regret": 0.0009428742341697216, "entropy": 0.09350758790969849, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:08.798639Z", "loop": 8557, "env_steps": 5258035199, "loss": 0.017569877207279205, "avg_return": 0.8613001704216003, "regret": 0.0009428742341697216, "entropy": 0.09880717843770981, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:09.652574Z", "loop": 8558, "env_steps": 5258649599, "loss": 0.015649400651454926, "avg_return": 0.861436665058136, "regret": 0.0009428742341697216, "entropy": 0.08675339072942734, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:10.506554Z", "loop": 8559, "env_steps": 5259263999, "loss": 0.015672877430915833, "avg_return": 0.8611479997634888, "regret": 0.0009428742341697216, "entropy": 0.08655810356140137, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:11.400123Z", "loop": 8560, "env_steps": 5259878399, "loss": 0.015570013783872128, "avg_return": 0.8619431853294373, "regret": 0.0014303565258160233, "entropy": 0.08687727153301239, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:12.254990Z", "loop": 8561, "env_steps": 5260492799, "loss": 0.01414790004491806, "avg_return": 0.8622980117797852, "regret": 0.0014303565258160233, "entropy": 0.0786377340555191, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:13.110320Z", "loop": 8562, "env_steps": 5261107199, "loss": 0.014769688248634338, "avg_return": 0.862156093120575, "regret": 0.0014303565258160233, "entropy": 0.0832655131816864, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:13.963378Z", "loop": 8563, "env_steps": 5261721599, "loss": 0.014283019118010998, "avg_return": 0.8630471229553223, "regret": 0.0014303565258160233, "entropy": 0.0816144049167633, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:14.817601Z", "loop": 8564, "env_steps": 5262335999, "loss": 0.014756212010979652, "avg_return": 0.8624007105827332, "regret": 0.0014303565258160233, "entropy": 0.07990285009145737, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:15.671703Z", "loop": 8565, "env_steps": 5262950399, "loss": 0.01489182747900486, "avg_return": 0.8627148866653442, "regret": 0.0014303565258160233, "entropy": 0.0812465026974678, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:16.525398Z", "loop": 8566, "env_steps": 5263564799, "loss": 0.014333411119878292, "avg_return": 0.8627238273620605, "regret": 0.0014303565258160233, "entropy": 0.07696953415870667, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:17.379346Z", "loop": 8567, "env_steps": 5264179199, "loss": 0.014680139720439911, "avg_return": 0.8616071939468384, "regret": 0.0014303565258160233, "entropy": 0.08170958608388901, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:18.234656Z", "loop": 8568, "env_steps": 5264793599, "loss": 0.014921307563781738, "avg_return": 0.8633055090904236, "regret": 0.0014303565258160233, "entropy": 0.07979399710893631, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:19.089382Z", "loop": 8569, "env_steps": 5265407999, "loss": 0.015088279731571674, "avg_return": 0.8613706827163696, "regret": 0.0014303565258160233, "entropy": 0.08027058094739914, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:19.983915Z", "loop": 8570, "env_steps": 5266022399, "loss": 0.01493804156780243, "avg_return": 0.8621588349342346, "regret": 0.0008772521978244185, "entropy": 0.0823068916797638, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:20.838420Z", "loop": 8571, "env_steps": 5266636799, "loss": 0.01525106467306614, "avg_return": 0.8626996874809265, "regret": 0.0008772521978244185, "entropy": 0.07842804491519928, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:21.693113Z", "loop": 8572, "env_steps": 5267251199, "loss": 0.01573180966079235, "avg_return": 0.8620384931564331, "regret": 0.0008772521978244185, "entropy": 0.08468059450387955, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:22.547015Z", "loop": 8573, "env_steps": 5267865599, "loss": 0.015034588985145092, "avg_return": 0.8612496256828308, "regret": 0.0008772521978244185, "entropy": 0.08145534992218018, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:23.402016Z", "loop": 8574, "env_steps": 5268479999, "loss": 0.014369969256222248, "avg_return": 0.8611979484558105, "regret": 0.0008772521978244185, "entropy": 0.08072599023580551, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:24.257886Z", "loop": 8575, "env_steps": 5269094399, "loss": 0.015480189584195614, "avg_return": 0.8620566129684448, "regret": 0.0008772521978244185, "entropy": 0.08518851548433304, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:25.113200Z", "loop": 8576, "env_steps": 5269708799, "loss": 0.01554912980645895, "avg_return": 0.8605428338050842, "regret": 0.0008772521978244185, "entropy": 0.08865918964147568, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:25.967547Z", "loop": 8577, "env_steps": 5270323199, "loss": 0.017163211479783058, "avg_return": 0.8607476949691772, "regret": 0.0008772521978244185, "entropy": 0.08660966157913208, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:26.820966Z", "loop": 8578, "env_steps": 5270937599, "loss": 0.01579720340669155, "avg_return": 0.8620287179946899, "regret": 0.0008772521978244185, "entropy": 0.08339597284793854, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:27.676180Z", "loop": 8579, "env_steps": 5271551999, "loss": 0.017415672540664673, "avg_return": 0.8595433831214905, "regret": 0.0008772521978244185, "entropy": 0.09162052720785141, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:28.572271Z", "loop": 8580, "env_steps": 5272166399, "loss": 0.01654178462922573, "avg_return": 0.8591787815093994, "regret": 0.0032317491713911295, "entropy": 0.08961798995733261, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:29.425343Z", "loop": 8581, "env_steps": 5272780799, "loss": 0.01700069196522236, "avg_return": 0.8603302240371704, "regret": 0.0032317491713911295, "entropy": 0.09139811992645264, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:30.279599Z", "loop": 8582, "env_steps": 5273395199, "loss": 0.017390882596373558, "avg_return": 0.8630666136741638, "regret": 0.0032317491713911295, "entropy": 0.08833928406238556, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:31.133699Z", "loop": 8583, "env_steps": 5274009599, "loss": 0.016523195430636406, "avg_return": 0.8619734048843384, "regret": 0.0032317491713911295, "entropy": 0.0896725058555603, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:31.988886Z", "loop": 8584, "env_steps": 5274623999, "loss": 0.01797005534172058, "avg_return": 0.8631681799888611, "regret": 0.0032317491713911295, "entropy": 0.08985216170549393, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:32.842657Z", "loop": 8585, "env_steps": 5275238399, "loss": 0.01581992395222187, "avg_return": 0.8623594641685486, "regret": 0.0032317491713911295, "entropy": 0.08607011288404465, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:33.695343Z", "loop": 8586, "env_steps": 5275852799, "loss": 0.01786288619041443, "avg_return": 0.86243736743927, "regret": 0.0032317491713911295, "entropy": 0.08768393844366074, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:34.547979Z", "loop": 8587, "env_steps": 5276467199, "loss": 0.017107894644141197, "avg_return": 0.8629372119903564, "regret": 0.0032317491713911295, "entropy": 0.08809985220432281, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:35.402782Z", "loop": 8588, "env_steps": 5277081599, "loss": 0.016859145835042, "avg_return": 0.8638561964035034, "regret": 0.0032317491713911295, "entropy": 0.08745482563972473, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:36.256619Z", "loop": 8589, "env_steps": 5277695999, "loss": 0.019571248441934586, "avg_return": 0.8635704517364502, "regret": 0.0032317491713911295, "entropy": 0.09553685039281845, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:37.149801Z", "loop": 8590, "env_steps": 5278310399, "loss": 0.016320114955306053, "avg_return": 0.8621156811714172, "regret": 0.00039153758552856743, "entropy": 0.08877215534448624, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:38.003798Z", "loop": 8591, "env_steps": 5278924799, "loss": 0.017257986590266228, "avg_return": 0.8640918135643005, "regret": 0.00039153758552856743, "entropy": 0.09329024702310562, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:38.858955Z", "loop": 8592, "env_steps": 5279539199, "loss": 0.018194975331425667, "avg_return": 0.8625669479370117, "regret": 0.00039153758552856743, "entropy": 0.0936656966805458, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:39.714196Z", "loop": 8593, "env_steps": 5280153599, "loss": 0.017771868035197258, "avg_return": 0.8626978993415833, "regret": 0.00039153758552856743, "entropy": 0.09193000942468643, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:40.568423Z", "loop": 8594, "env_steps": 5280767999, "loss": 0.018125906586647034, "avg_return": 0.8622277975082397, "regret": 0.00039153758552856743, "entropy": 0.09552136063575745, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:41.422507Z", "loop": 8595, "env_steps": 5281382399, "loss": 0.017986109480261803, "avg_return": 0.8621818423271179, "regret": 0.00039153758552856743, "entropy": 0.09274501353502274, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:42.277108Z", "loop": 8596, "env_steps": 5281996799, "loss": 0.018363414332270622, "avg_return": 0.8635411858558655, "regret": 0.00039153758552856743, "entropy": 0.09208047389984131, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:43.131833Z", "loop": 8597, "env_steps": 5282611199, "loss": 0.01777377538383007, "avg_return": 0.8635066747665405, "regret": 0.00039153758552856743, "entropy": 0.09368923306465149, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:43.986107Z", "loop": 8598, "env_steps": 5283225599, "loss": 0.01721419394016266, "avg_return": 0.864199161529541, "regret": 0.00039153758552856743, "entropy": 0.09001197665929794, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:44.840523Z", "loop": 8599, "env_steps": 5283839999, "loss": 0.01819349080324173, "avg_return": 0.8624890446662903, "regret": 0.00039153758552856743, "entropy": 0.09535219520330429, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:45.736698Z", "loop": 8600, "env_steps": 5284454399, "loss": 0.01702926680445671, "avg_return": 0.8638800978660583, "regret": 0.00035119298263452947, "entropy": 0.089795783162117, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:46.591841Z", "loop": 8601, "env_steps": 5285068799, "loss": 0.018694905564188957, "avg_return": 0.8631592988967896, "regret": 0.00035119298263452947, "entropy": 0.0950564444065094, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:47.446594Z", "loop": 8602, "env_steps": 5285683199, "loss": 0.018493525683879852, "avg_return": 0.8646540641784668, "regret": 0.00035119298263452947, "entropy": 0.09064825624227524, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:48.300918Z", "loop": 8603, "env_steps": 5286297599, "loss": 0.016579044982790947, "avg_return": 0.8633794188499451, "regret": 0.00035119298263452947, "entropy": 0.09134425222873688, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:49.155171Z", "loop": 8604, "env_steps": 5286911999, "loss": 0.019273240119218826, "avg_return": 0.862170934677124, "regret": 0.00035119298263452947, "entropy": 0.10003022104501724, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:50.008804Z", "loop": 8605, "env_steps": 5287526399, "loss": 0.018291650339961052, "avg_return": 0.863649308681488, "regret": 0.00035119298263452947, "entropy": 0.09738925844430923, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:50.862439Z", "loop": 8606, "env_steps": 5288140799, "loss": 0.01748983934521675, "avg_return": 0.8627474904060364, "regret": 0.00035119298263452947, "entropy": 0.09510598331689835, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:51.716548Z", "loop": 8607, "env_steps": 5288755199, "loss": 0.01857108436524868, "avg_return": 0.8643412590026855, "regret": 0.00035119298263452947, "entropy": 0.09533438831567764, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:52.570057Z", "loop": 8608, "env_steps": 5289369599, "loss": 0.017009858042001724, "avg_return": 0.8637942671775818, "regret": 0.00035119298263452947, "entropy": 0.09205584973096848, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:53.423999Z", "loop": 8609, "env_steps": 5289983999, "loss": 0.017637403681874275, "avg_return": 0.863905131816864, "regret": 0.00035119298263452947, "entropy": 0.09368351846933365, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:54.318330Z", "loop": 8610, "env_steps": 5290598399, "loss": 0.016830995678901672, "avg_return": 0.8641682863235474, "regret": 0.000367897329851985, "entropy": 0.0921785831451416, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:55.172435Z", "loop": 8611, "env_steps": 5291212799, "loss": 0.016892997547984123, "avg_return": 0.8627376556396484, "regret": 0.000367897329851985, "entropy": 0.09315136075019836, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:56.027918Z", "loop": 8612, "env_steps": 5291827199, "loss": 0.01818571425974369, "avg_return": 0.8633872866630554, "regret": 0.000367897329851985, "entropy": 0.09549219161272049, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:56.882618Z", "loop": 8613, "env_steps": 5292441599, "loss": 0.019674435257911682, "avg_return": 0.8616034984588623, "regret": 0.000367897329851985, "entropy": 0.09955918788909912, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:57.737215Z", "loop": 8614, "env_steps": 5293055999, "loss": 0.01989821344614029, "avg_return": 0.8623436689376831, "regret": 0.000367897329851985, "entropy": 0.10197474807500839, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:58.591932Z", "loop": 8615, "env_steps": 5293670399, "loss": 0.0196000374853611, "avg_return": 0.8632910251617432, "regret": 0.000367897329851985, "entropy": 0.10368775576353073, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:26:59.446925Z", "loop": 8616, "env_steps": 5294284799, "loss": 0.020958425477147102, "avg_return": 0.864216148853302, "regret": 0.000367897329851985, "entropy": 0.10720254480838776, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:00.300632Z", "loop": 8617, "env_steps": 5294899199, "loss": 0.02004772052168846, "avg_return": 0.8628543019294739, "regret": 0.000367897329851985, "entropy": 0.10601212084293365, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:01.154314Z", "loop": 8618, "env_steps": 5295513599, "loss": 0.0208329688757658, "avg_return": 0.8625181317329407, "regret": 0.000367897329851985, "entropy": 0.10609181970357895, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:02.010760Z", "loop": 8619, "env_steps": 5296127999, "loss": 0.021238606423139572, "avg_return": 0.8615175485610962, "regret": 0.000367897329851985, "entropy": 0.10900669544935226, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:02.905700Z", "loop": 8620, "env_steps": 5296742399, "loss": 0.019958533346652985, "avg_return": 0.862106442451477, "regret": 0.0006916652782820165, "entropy": 0.099721260368824, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:03.760097Z", "loop": 8621, "env_steps": 5297356799, "loss": 0.02084660902619362, "avg_return": 0.8623608350753784, "regret": 0.0006916652782820165, "entropy": 0.10927590727806091, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:04.613407Z", "loop": 8622, "env_steps": 5297971199, "loss": 0.020128188654780388, "avg_return": 0.863273024559021, "regret": 0.0006916652782820165, "entropy": 0.107857845723629, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:05.466904Z", "loop": 8623, "env_steps": 5298585599, "loss": 0.021053751930594444, "avg_return": 0.8628227114677429, "regret": 0.0006916652782820165, "entropy": 0.11062147468328476, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:06.321051Z", "loop": 8624, "env_steps": 5299199999, "loss": 0.020582620054483414, "avg_return": 0.861950695514679, "regret": 0.0006916652782820165, "entropy": 0.11063578724861145, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:07.175092Z", "loop": 8625, "env_steps": 5299814399, "loss": 0.022049615159630775, "avg_return": 0.861986517906189, "regret": 0.0006916652782820165, "entropy": 0.11442866921424866, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:08.029756Z", "loop": 8626, "env_steps": 5300428799, "loss": 0.023122696205973625, "avg_return": 0.8632224798202515, "regret": 0.0006916652782820165, "entropy": 0.12288133054971695, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:08.885322Z", "loop": 8627, "env_steps": 5301043199, "loss": 0.022176776081323624, "avg_return": 0.8607447743415833, "regret": 0.0006916652782820165, "entropy": 0.11479072272777557, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:09.740867Z", "loop": 8628, "env_steps": 5301657599, "loss": 0.021730570122599602, "avg_return": 0.8629223704338074, "regret": 0.0006916652782820165, "entropy": 0.1121382936835289, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:10.596250Z", "loop": 8629, "env_steps": 5302271999, "loss": 0.022148704156279564, "avg_return": 0.8620834350585938, "regret": 0.0006916652782820165, "entropy": 0.11524469405412674, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:11.492072Z", "loop": 8630, "env_steps": 5302886399, "loss": 0.01992703601717949, "avg_return": 0.8636942505836487, "regret": 0.0011346661485731602, "entropy": 0.10562039166688919, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:12.347274Z", "loop": 8631, "env_steps": 5303500799, "loss": 0.019633298739790916, "avg_return": 0.862284779548645, "regret": 0.0011346661485731602, "entropy": 0.11004307121038437, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:13.201796Z", "loop": 8632, "env_steps": 5304115199, "loss": 0.02188878320157528, "avg_return": 0.8612843751907349, "regret": 0.0011346661485731602, "entropy": 0.1084822416305542, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:14.056649Z", "loop": 8633, "env_steps": 5304729599, "loss": 0.021130194887518883, "avg_return": 0.8625429272651672, "regret": 0.0011346661485731602, "entropy": 0.10776983946561813, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:14.912550Z", "loop": 8634, "env_steps": 5305343999, "loss": 0.01933163031935692, "avg_return": 0.8621666431427002, "regret": 0.0011346661485731602, "entropy": 0.11027851700782776, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:15.768573Z", "loop": 8635, "env_steps": 5305958399, "loss": 0.02109694294631481, "avg_return": 0.8639354705810547, "regret": 0.0011346661485731602, "entropy": 0.11085247993469238, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:16.622340Z", "loop": 8636, "env_steps": 5306572799, "loss": 0.0208940077573061, "avg_return": 0.8620086908340454, "regret": 0.0011346661485731602, "entropy": 0.1108027994632721, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:17.476897Z", "loop": 8637, "env_steps": 5307187199, "loss": 0.021681150421500206, "avg_return": 0.8612052798271179, "regret": 0.0011346661485731602, "entropy": 0.11221490800380707, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:18.332353Z", "loop": 8638, "env_steps": 5307801599, "loss": 0.02014128863811493, "avg_return": 0.8624794483184814, "regret": 0.0011346661485731602, "entropy": 0.1094210222363472, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:19.188628Z", "loop": 8639, "env_steps": 5308415999, "loss": 0.021614937111735344, "avg_return": 0.8619885444641113, "regret": 0.0011346661485731602, "entropy": 0.11008628457784653, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:20.084278Z", "loop": 8640, "env_steps": 5309030399, "loss": 0.021060310304164886, "avg_return": 0.8620932102203369, "regret": 0.0012638687621802092, "entropy": 0.11196719110012054, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:20.938487Z", "loop": 8641, "env_steps": 5309644799, "loss": 0.020097045227885246, "avg_return": 0.8638590574264526, "regret": 0.0012638687621802092, "entropy": 0.10776577889919281, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:21.792577Z", "loop": 8642, "env_steps": 5310259199, "loss": 0.020792579278349876, "avg_return": 0.8625360131263733, "regret": 0.0012638687621802092, "entropy": 0.10938537120819092, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:22.648292Z", "loop": 8643, "env_steps": 5310873599, "loss": 0.020332617685198784, "avg_return": 0.8620970845222473, "regret": 0.0012638687621802092, "entropy": 0.10633087158203125, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:23.502084Z", "loop": 8644, "env_steps": 5311487999, "loss": 0.019854120910167694, "avg_return": 0.864236056804657, "regret": 0.0012638687621802092, "entropy": 0.10147589445114136, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:24.355348Z", "loop": 8645, "env_steps": 5312102399, "loss": 0.019797703251242638, "avg_return": 0.8618090152740479, "regret": 0.0012638687621802092, "entropy": 0.10237617790699005, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:25.208146Z", "loop": 8646, "env_steps": 5312716799, "loss": 0.019350338727235794, "avg_return": 0.8633370399475098, "regret": 0.0012638687621802092, "entropy": 0.10163214802742004, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:26.061891Z", "loop": 8647, "env_steps": 5313331199, "loss": 0.021424399688839912, "avg_return": 0.8635666966438293, "regret": 0.0012638687621802092, "entropy": 0.10585666447877884, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:26.915931Z", "loop": 8648, "env_steps": 5313945599, "loss": 0.020601782947778702, "avg_return": 0.8622633814811707, "regret": 0.0012638687621802092, "entropy": 0.10505741834640503, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:27.769329Z", "loop": 8649, "env_steps": 5314559999, "loss": 0.018302343785762787, "avg_return": 0.8638699650764465, "regret": 0.0012638687621802092, "entropy": 0.09750311076641083, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:28.663147Z", "loop": 8650, "env_steps": 5315174399, "loss": 0.01938806287944317, "avg_return": 0.8622943162918091, "regret": 0.000434789399150759, "entropy": 0.1018618792295456, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:29.518210Z", "loop": 8651, "env_steps": 5315788799, "loss": 0.01812182180583477, "avg_return": 0.8636975288391113, "regret": 0.000434789399150759, "entropy": 0.09813695400953293, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:30.373004Z", "loop": 8652, "env_steps": 5316403199, "loss": 0.019251037389039993, "avg_return": 0.8622623085975647, "regret": 0.000434789399150759, "entropy": 0.09875764697790146, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:31.227186Z", "loop": 8653, "env_steps": 5317017599, "loss": 0.018401743844151497, "avg_return": 0.8624656200408936, "regret": 0.000434789399150759, "entropy": 0.096219003200531, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:32.080615Z", "loop": 8654, "env_steps": 5317631999, "loss": 0.01885361038148403, "avg_return": 0.863675057888031, "regret": 0.000434789399150759, "entropy": 0.09622599929571152, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:32.934658Z", "loop": 8655, "env_steps": 5318246399, "loss": 0.019336463883519173, "avg_return": 0.8624494671821594, "regret": 0.000434789399150759, "entropy": 0.09981691092252731, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:33.789703Z", "loop": 8656, "env_steps": 5318860799, "loss": 0.0186641663312912, "avg_return": 0.8636834025382996, "regret": 0.000434789399150759, "entropy": 0.09683731198310852, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:34.644307Z", "loop": 8657, "env_steps": 5319475199, "loss": 0.018543632701039314, "avg_return": 0.8631460666656494, "regret": 0.000434789399150759, "entropy": 0.09678720682859421, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:35.498653Z", "loop": 8658, "env_steps": 5320089599, "loss": 0.017965570092201233, "avg_return": 0.8629816174507141, "regret": 0.000434789399150759, "entropy": 0.09616153687238693, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:36.353220Z", "loop": 8659, "env_steps": 5320703999, "loss": 0.018644405528903008, "avg_return": 0.8641069531440735, "regret": 0.000434789399150759, "entropy": 0.0953245535492897, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:37.246975Z", "loop": 8660, "env_steps": 5321318399, "loss": 0.018599985167384148, "avg_return": 0.8625434637069702, "regret": 0.00023290872923098505, "entropy": 0.09524063020944595, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:38.101076Z", "loop": 8661, "env_steps": 5321932799, "loss": 0.017552388831973076, "avg_return": 0.8631205558776855, "regret": 0.00023290872923098505, "entropy": 0.09674618393182755, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:38.956079Z", "loop": 8662, "env_steps": 5322547199, "loss": 0.017905263230204582, "avg_return": 0.862143874168396, "regret": 0.00023290872923098505, "entropy": 0.09301359206438065, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:39.810066Z", "loop": 8663, "env_steps": 5323161599, "loss": 0.01926516368985176, "avg_return": 0.863427460193634, "regret": 0.00023290872923098505, "entropy": 0.09290017932653427, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:40.663303Z", "loop": 8664, "env_steps": 5323775999, "loss": 0.020976893603801727, "avg_return": 0.8634686470031738, "regret": 0.00023290872923098505, "entropy": 0.10315092653036118, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:41.517592Z", "loop": 8665, "env_steps": 5324390399, "loss": 0.019527455791831017, "avg_return": 0.8629959225654602, "regret": 0.00023290872923098505, "entropy": 0.09687155485153198, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:42.371982Z", "loop": 8666, "env_steps": 5325004799, "loss": 0.018510179594159126, "avg_return": 0.8633657097816467, "regret": 0.00023290872923098505, "entropy": 0.09389010816812515, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:43.226437Z", "loop": 8667, "env_steps": 5325619199, "loss": 0.0182611346244812, "avg_return": 0.865054726600647, "regret": 0.00023290872923098505, "entropy": 0.09526468068361282, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:44.081096Z", "loop": 8668, "env_steps": 5326233599, "loss": 0.018541039898991585, "avg_return": 0.8640590906143188, "regret": 0.00023290872923098505, "entropy": 0.09498348832130432, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:44.936618Z", "loop": 8669, "env_steps": 5326847999, "loss": 0.016686169430613518, "avg_return": 0.8655117154121399, "regret": 0.00023290872923098505, "entropy": 0.08742652833461761, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:45.832133Z", "loop": 8670, "env_steps": 5327462399, "loss": 0.018609242513775826, "avg_return": 0.8646726608276367, "regret": 0.00025169129366986454, "entropy": 0.09295487403869629, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:46.687000Z", "loop": 8671, "env_steps": 5328076799, "loss": 0.017140109091997147, "avg_return": 0.8635160326957703, "regret": 0.00025169129366986454, "entropy": 0.09371283650398254, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:47.541272Z", "loop": 8672, "env_steps": 5328691199, "loss": 0.017665261402726173, "avg_return": 0.8630592823028564, "regret": 0.00025169129366986454, "entropy": 0.08656267076730728, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:48.395250Z", "loop": 8673, "env_steps": 5329305599, "loss": 0.018088994547724724, "avg_return": 0.8634496331214905, "regret": 0.00025169129366986454, "entropy": 0.09025291353464127, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:49.249706Z", "loop": 8674, "env_steps": 5329919999, "loss": 0.017921416088938713, "avg_return": 0.863124430179596, "regret": 0.00025169129366986454, "entropy": 0.09221148490905762, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:50.103955Z", "loop": 8675, "env_steps": 5330534399, "loss": 0.01749531738460064, "avg_return": 0.8617987036705017, "regret": 0.00025169129366986454, "entropy": 0.09140754491090775, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:50.957498Z", "loop": 8676, "env_steps": 5331148799, "loss": 0.018604524433612823, "avg_return": 0.8624927997589111, "regret": 0.00025169129366986454, "entropy": 0.09079449623823166, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:51.811658Z", "loop": 8677, "env_steps": 5331763199, "loss": 0.018498260527849197, "avg_return": 0.8629066944122314, "regret": 0.00025169129366986454, "entropy": 0.0913410410284996, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:52.666795Z", "loop": 8678, "env_steps": 5332377599, "loss": 0.0187996719032526, "avg_return": 0.8657296895980835, "regret": 0.00025169129366986454, "entropy": 0.09762934595346451, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:53.520764Z", "loop": 8679, "env_steps": 5332991999, "loss": 0.017786571756005287, "avg_return": 0.8631998896598816, "regret": 0.00025169129366986454, "entropy": 0.0915609747171402, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:54.415545Z", "loop": 8680, "env_steps": 5333606399, "loss": 0.01586207188665867, "avg_return": 0.8624790906906128, "regret": 0.0005512361531145871, "entropy": 0.08648974448442459, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:55.269298Z", "loop": 8681, "env_steps": 5334220799, "loss": 0.0175456739962101, "avg_return": 0.863173246383667, "regret": 0.0005512361531145871, "entropy": 0.0899873822927475, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:56.123189Z", "loop": 8682, "env_steps": 5334835199, "loss": 0.0160340815782547, "avg_return": 0.8620662689208984, "regret": 0.0005512361531145871, "entropy": 0.08817210793495178, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:56.977405Z", "loop": 8683, "env_steps": 5335449599, "loss": 0.01770409569144249, "avg_return": 0.861941933631897, "regret": 0.0005512361531145871, "entropy": 0.09092400223016739, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:57.831839Z", "loop": 8684, "env_steps": 5336063999, "loss": 0.015951495617628098, "avg_return": 0.863079845905304, "regret": 0.0005512361531145871, "entropy": 0.08764403313398361, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:58.685858Z", "loop": 8685, "env_steps": 5336678399, "loss": 0.018474748358130455, "avg_return": 0.8618362545967102, "regret": 0.0005512361531145871, "entropy": 0.09347334504127502, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:27:59.540960Z", "loop": 8686, "env_steps": 5337292799, "loss": 0.016604268923401833, "avg_return": 0.8626365065574646, "regret": 0.0005512361531145871, "entropy": 0.08927790820598602, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:00.396192Z", "loop": 8687, "env_steps": 5337907199, "loss": 0.018073178827762604, "avg_return": 0.8622514009475708, "regret": 0.0005512361531145871, "entropy": 0.09490331262350082, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:01.251840Z", "loop": 8688, "env_steps": 5338521599, "loss": 0.017656439915299416, "avg_return": 0.8630961179733276, "regret": 0.0005512361531145871, "entropy": 0.09684571623802185, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:02.107180Z", "loop": 8689, "env_steps": 5339135999, "loss": 0.02008203975856304, "avg_return": 0.8614559173583984, "regret": 0.0005512361531145871, "entropy": 0.10289136320352554, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:02.999864Z", "loop": 8690, "env_steps": 5339750399, "loss": 0.019561301916837692, "avg_return": 0.8615225553512573, "regret": 0.001480144215747714, "entropy": 0.09751929342746735, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:03.853227Z", "loop": 8691, "env_steps": 5340364799, "loss": 0.019021358340978622, "avg_return": 0.8628296852111816, "regret": 0.001480144215747714, "entropy": 0.09882505238056183, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:04.706252Z", "loop": 8692, "env_steps": 5340979199, "loss": 0.018672233447432518, "avg_return": 0.8621715307235718, "regret": 0.001480144215747714, "entropy": 0.09925045073032379, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:05.560765Z", "loop": 8693, "env_steps": 5341593599, "loss": 0.018505848944187164, "avg_return": 0.8630280494689941, "regret": 0.001480144215747714, "entropy": 0.09732934832572937, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:06.415071Z", "loop": 8694, "env_steps": 5342207999, "loss": 0.01939902827143669, "avg_return": 0.8608418703079224, "regret": 0.001480144215747714, "entropy": 0.09961291402578354, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:07.268376Z", "loop": 8695, "env_steps": 5342822399, "loss": 0.01872028224170208, "avg_return": 0.8622573018074036, "regret": 0.001480144215747714, "entropy": 0.0971643477678299, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:08.121400Z", "loop": 8696, "env_steps": 5343436799, "loss": 0.018511315807700157, "avg_return": 0.861623227596283, "regret": 0.001480144215747714, "entropy": 0.09616653621196747, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:08.975152Z", "loop": 8697, "env_steps": 5344051199, "loss": 0.0190124548971653, "avg_return": 0.862855851650238, "regret": 0.001480144215747714, "entropy": 0.09683971852064133, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:09.829075Z", "loop": 8698, "env_steps": 5344665599, "loss": 0.02071073278784752, "avg_return": 0.862703263759613, "regret": 0.001480144215747714, "entropy": 0.10527347028255463, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:10.681751Z", "loop": 8699, "env_steps": 5345279999, "loss": 0.019346831366419792, "avg_return": 0.8625448942184448, "regret": 0.001480144215747714, "entropy": 0.10063322633504868, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:11.574046Z", "loop": 8700, "env_steps": 5345894399, "loss": 0.0193793848156929, "avg_return": 0.8620789647102356, "regret": 0.0012103895423933864, "entropy": 0.09878825396299362, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:12.428164Z", "loop": 8701, "env_steps": 5346508799, "loss": 0.019927315413951874, "avg_return": 0.8621938228607178, "regret": 0.0012103895423933864, "entropy": 0.10123331099748611, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:13.282469Z", "loop": 8702, "env_steps": 5347123199, "loss": 0.01847800426185131, "avg_return": 0.8632786273956299, "regret": 0.0012103895423933864, "entropy": 0.09399182349443436, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:14.136361Z", "loop": 8703, "env_steps": 5347737599, "loss": 0.019197866320610046, "avg_return": 0.8623512983322144, "regret": 0.0012103895423933864, "entropy": 0.09864434599876404, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:14.989273Z", "loop": 8704, "env_steps": 5348351999, "loss": 0.018940266221761703, "avg_return": 0.8631117939949036, "regret": 0.0012103895423933864, "entropy": 0.09604240208864212, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:15.843035Z", "loop": 8705, "env_steps": 5348966399, "loss": 0.020127400755882263, "avg_return": 0.8625701069831848, "regret": 0.0012103895423933864, "entropy": 0.09968819469213486, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:16.698015Z", "loop": 8706, "env_steps": 5349580799, "loss": 0.02010229602456093, "avg_return": 0.8632912635803223, "regret": 0.0012103895423933864, "entropy": 0.09889808297157288, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:17.551911Z", "loop": 8707, "env_steps": 5350195199, "loss": 0.018707100301980972, "avg_return": 0.8643128871917725, "regret": 0.0012103895423933864, "entropy": 0.09935393184423447, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:18.404892Z", "loop": 8708, "env_steps": 5350809599, "loss": 0.0189425777643919, "avg_return": 0.8628708124160767, "regret": 0.0012103895423933864, "entropy": 0.09590703994035721, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:19.258303Z", "loop": 8709, "env_steps": 5351423999, "loss": 0.017973626032471657, "avg_return": 0.8624798059463501, "regret": 0.0012103895423933864, "entropy": 0.09588580578565598, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:20.152759Z", "loop": 8710, "env_steps": 5352038399, "loss": 0.019845204427838326, "avg_return": 0.8633818626403809, "regret": 0.0004968214780092239, "entropy": 0.09910409152507782, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:21.008114Z", "loop": 8711, "env_steps": 5352652799, "loss": 0.01957947574555874, "avg_return": 0.8629557490348816, "regret": 0.0004968214780092239, "entropy": 0.09943874925374985, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:21.863600Z", "loop": 8712, "env_steps": 5353267199, "loss": 0.01854310929775238, "avg_return": 0.8635542988777161, "regret": 0.0004968214780092239, "entropy": 0.09442761540412903, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:22.717849Z", "loop": 8713, "env_steps": 5353881599, "loss": 0.01868342235684395, "avg_return": 0.8632581830024719, "regret": 0.0004968214780092239, "entropy": 0.09434866905212402, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:23.572846Z", "loop": 8714, "env_steps": 5354495999, "loss": 0.015976399183273315, "avg_return": 0.8629340529441833, "regret": 0.0004968214780092239, "entropy": 0.08798735588788986, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:24.428885Z", "loop": 8715, "env_steps": 5355110399, "loss": 0.017900072038173676, "avg_return": 0.8629916310310364, "regret": 0.0004968214780092239, "entropy": 0.09084019809961319, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:25.284197Z", "loop": 8716, "env_steps": 5355724799, "loss": 0.017594775184988976, "avg_return": 0.8629834055900574, "regret": 0.0004968214780092239, "entropy": 0.08998459577560425, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:26.139605Z", "loop": 8717, "env_steps": 5356339199, "loss": 0.017285970970988274, "avg_return": 0.8632965087890625, "regret": 0.0004968214780092239, "entropy": 0.09074521064758301, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:26.993898Z", "loop": 8718, "env_steps": 5356953599, "loss": 0.01624159887433052, "avg_return": 0.8632962107658386, "regret": 0.0004968214780092239, "entropy": 0.08748135715723038, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:27.848040Z", "loop": 8719, "env_steps": 5357567999, "loss": 0.017947928979992867, "avg_return": 0.8620144128799438, "regret": 0.0004968214780092239, "entropy": 0.09194482117891312, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:28.741397Z", "loop": 8720, "env_steps": 5358182399, "loss": 0.017994163557887077, "avg_return": 0.8616708517074585, "regret": 0.0010105854598805308, "entropy": 0.08942009508609772, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:29.594794Z", "loop": 8721, "env_steps": 5358796799, "loss": 0.017504515126347542, "avg_return": 0.863049328327179, "regret": 0.0010105854598805308, "entropy": 0.091842420399189, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:30.447958Z", "loop": 8722, "env_steps": 5359411199, "loss": 0.017771322280168533, "avg_return": 0.8626760840415955, "regret": 0.0010105854598805308, "entropy": 0.09295806288719177, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:31.302045Z", "loop": 8723, "env_steps": 5360025599, "loss": 0.01816602796316147, "avg_return": 0.8618257641792297, "regret": 0.0010105854598805308, "entropy": 0.09510008990764618, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:32.155889Z", "loop": 8724, "env_steps": 5360639999, "loss": 0.018103791400790215, "avg_return": 0.8622044324874878, "regret": 0.0010105854598805308, "entropy": 0.08905764669179916, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:33.009411Z", "loop": 8725, "env_steps": 5361254399, "loss": 0.019072504714131355, "avg_return": 0.8626047968864441, "regret": 0.0010105854598805308, "entropy": 0.0966062918305397, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:33.863255Z", "loop": 8726, "env_steps": 5361868799, "loss": 0.019832491874694824, "avg_return": 0.862043559551239, "regret": 0.0010105854598805308, "entropy": 0.10199601203203201, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:34.717491Z", "loop": 8727, "env_steps": 5362483199, "loss": 0.017893105745315552, "avg_return": 0.8633386492729187, "regret": 0.0010105854598805308, "entropy": 0.09144128859043121, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:35.571517Z", "loop": 8728, "env_steps": 5363097599, "loss": 0.019222795963287354, "avg_return": 0.8620782494544983, "regret": 0.0010105854598805308, "entropy": 0.09474074095487595, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:36.425139Z", "loop": 8729, "env_steps": 5363711999, "loss": 0.017734911292791367, "avg_return": 0.8623907566070557, "regret": 0.0010105854598805308, "entropy": 0.08963338285684586, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:37.318197Z", "loop": 8730, "env_steps": 5364326399, "loss": 0.017842566594481468, "avg_return": 0.8634375333786011, "regret": 0.000942908285651356, "entropy": 0.09055744856595993, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:38.172318Z", "loop": 8731, "env_steps": 5364940799, "loss": 0.01774515211582184, "avg_return": 0.862746000289917, "regret": 0.000942908285651356, "entropy": 0.09068905562162399, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:39.026920Z", "loop": 8732, "env_steps": 5365555199, "loss": 0.017406495288014412, "avg_return": 0.8634112477302551, "regret": 0.000942908285651356, "entropy": 0.08789554238319397, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:39.882763Z", "loop": 8733, "env_steps": 5366169599, "loss": 0.015818407759070396, "avg_return": 0.8620489835739136, "regret": 0.000942908285651356, "entropy": 0.08496690541505814, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:40.737796Z", "loop": 8734, "env_steps": 5366783999, "loss": 0.01642787829041481, "avg_return": 0.8630114793777466, "regret": 0.000942908285651356, "entropy": 0.08799412846565247, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:41.592770Z", "loop": 8735, "env_steps": 5367398399, "loss": 0.01652979850769043, "avg_return": 0.8630805611610413, "regret": 0.000942908285651356, "entropy": 0.08449617028236389, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:42.446759Z", "loop": 8736, "env_steps": 5368012799, "loss": 0.017286745831370354, "avg_return": 0.8629631996154785, "regret": 0.000942908285651356, "entropy": 0.09394008666276932, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:43.302336Z", "loop": 8737, "env_steps": 5368627199, "loss": 0.018034828826785088, "avg_return": 0.8629708290100098, "regret": 0.000942908285651356, "entropy": 0.09275856614112854, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:44.156842Z", "loop": 8738, "env_steps": 5369241599, "loss": 0.019096916541457176, "avg_return": 0.8636094331741333, "regret": 0.000942908285651356, "entropy": 0.09546356648206711, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:45.011629Z", "loop": 8739, "env_steps": 5369855999, "loss": 0.019668441265821457, "avg_return": 0.863456666469574, "regret": 0.000942908285651356, "entropy": 0.10103406012058258, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:45.906994Z", "loop": 8740, "env_steps": 5370470399, "loss": 0.019027093425393105, "avg_return": 0.8626638054847717, "regret": 0.0003595342568587512, "entropy": 0.0955805778503418, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:46.760991Z", "loop": 8741, "env_steps": 5371084799, "loss": 0.018443699926137924, "avg_return": 0.8651016354560852, "regret": 0.0003595342568587512, "entropy": 0.09335917234420776, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:47.616174Z", "loop": 8742, "env_steps": 5371699199, "loss": 0.017545748502016068, "avg_return": 0.8629673719406128, "regret": 0.0003595342568587512, "entropy": 0.08990151435136795, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:48.471348Z", "loop": 8743, "env_steps": 5372313599, "loss": 0.017092600464820862, "avg_return": 0.8639574646949768, "regret": 0.0003595342568587512, "entropy": 0.09039143472909927, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:49.325354Z", "loop": 8744, "env_steps": 5372927999, "loss": 0.016988588497042656, "avg_return": 0.8625161051750183, "regret": 0.0003595342568587512, "entropy": 0.08869936317205429, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:50.178919Z", "loop": 8745, "env_steps": 5373542399, "loss": 0.01793646812438965, "avg_return": 0.86187744140625, "regret": 0.0003595342568587512, "entropy": 0.08976316452026367, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:51.034154Z", "loop": 8746, "env_steps": 5374156799, "loss": 0.017233967781066895, "avg_return": 0.8631643056869507, "regret": 0.0003595342568587512, "entropy": 0.09022090584039688, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:51.888572Z", "loop": 8747, "env_steps": 5374771199, "loss": 0.018107013776898384, "avg_return": 0.8627911806106567, "regret": 0.0003595342568587512, "entropy": 0.0898299291729927, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:52.742254Z", "loop": 8748, "env_steps": 5375385599, "loss": 0.01894092746078968, "avg_return": 0.8623629212379456, "regret": 0.0003595342568587512, "entropy": 0.09778555482625961, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:53.595091Z", "loop": 8749, "env_steps": 5375999999, "loss": 0.01803039014339447, "avg_return": 0.8630824089050293, "regret": 0.0003595342568587512, "entropy": 0.08943205326795578, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:54.489243Z", "loop": 8750, "env_steps": 5376614399, "loss": 0.01769724301993847, "avg_return": 0.8624670505523682, "regret": 0.00044481095392256975, "entropy": 0.09207377582788467, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:55.343692Z", "loop": 8751, "env_steps": 5377228799, "loss": 0.01812722347676754, "avg_return": 0.8628135323524475, "regret": 0.00044481095392256975, "entropy": 0.09498612582683563, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:56.198741Z", "loop": 8752, "env_steps": 5377843199, "loss": 0.019780399277806282, "avg_return": 0.8639726042747498, "regret": 0.00044481095392256975, "entropy": 0.09821146726608276, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:57.052858Z", "loop": 8753, "env_steps": 5378457599, "loss": 0.018662704154849052, "avg_return": 0.8635414838790894, "regret": 0.00044481095392256975, "entropy": 0.09507337212562561, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:57.907276Z", "loop": 8754, "env_steps": 5379071999, "loss": 0.017748085781931877, "avg_return": 0.8620985150337219, "regret": 0.00044481095392256975, "entropy": 0.09658188372850418, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:58.763257Z", "loop": 8755, "env_steps": 5379686399, "loss": 0.018307672813534737, "avg_return": 0.8619236350059509, "regret": 0.00044481095392256975, "entropy": 0.09606382250785828, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:28:59.617090Z", "loop": 8756, "env_steps": 5380300799, "loss": 0.0180065780878067, "avg_return": 0.8638942837715149, "regret": 0.00044481095392256975, "entropy": 0.0913514643907547, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:00.472051Z", "loop": 8757, "env_steps": 5380915199, "loss": 0.019046492874622345, "avg_return": 0.861970841884613, "regret": 0.00044481095392256975, "entropy": 0.09652364253997803, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:01.325548Z", "loop": 8758, "env_steps": 5381529599, "loss": 0.017502961680293083, "avg_return": 0.8627297282218933, "regret": 0.00044481095392256975, "entropy": 0.09107569605112076, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:02.178473Z", "loop": 8759, "env_steps": 5382143999, "loss": 0.01728822849690914, "avg_return": 0.8626095652580261, "regret": 0.00044481095392256975, "entropy": 0.090766042470932, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:03.071986Z", "loop": 8760, "env_steps": 5382758399, "loss": 0.017163123935461044, "avg_return": 0.8623890280723572, "regret": 0.0007686598692089319, "entropy": 0.08734209835529327, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:03.926531Z", "loop": 8761, "env_steps": 5383372799, "loss": 0.018257785588502884, "avg_return": 0.8618229627609253, "regret": 0.0007686598692089319, "entropy": 0.09127005189657211, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:04.780235Z", "loop": 8762, "env_steps": 5383987199, "loss": 0.017011940479278564, "avg_return": 0.860158383846283, "regret": 0.0007686598692089319, "entropy": 0.09111163020133972, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:05.633213Z", "loop": 8763, "env_steps": 5384601599, "loss": 0.01722600869834423, "avg_return": 0.858443021774292, "regret": 0.0007686598692089319, "entropy": 0.09090519696474075, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:06.486173Z", "loop": 8764, "env_steps": 5385215999, "loss": 0.018273860216140747, "avg_return": 0.8586598634719849, "regret": 0.0007686598692089319, "entropy": 0.0941343680024147, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:07.340728Z", "loop": 8765, "env_steps": 5385830399, "loss": 0.018249018117785454, "avg_return": 0.8607946038246155, "regret": 0.0007686598692089319, "entropy": 0.09305644035339355, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:08.195478Z", "loop": 8766, "env_steps": 5386444799, "loss": 0.01741979829967022, "avg_return": 0.8622106909751892, "regret": 0.0007686598692089319, "entropy": 0.09119388461112976, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:09.048514Z", "loop": 8767, "env_steps": 5387059199, "loss": 0.01797279343008995, "avg_return": 0.8621621131896973, "regret": 0.0007686598692089319, "entropy": 0.0915072113275528, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:09.901441Z", "loop": 8768, "env_steps": 5387673599, "loss": 0.017335882410407066, "avg_return": 0.8628373146057129, "regret": 0.0007686598692089319, "entropy": 0.08962125331163406, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:10.755789Z", "loop": 8769, "env_steps": 5388287999, "loss": 0.015649667009711266, "avg_return": 0.8616662621498108, "regret": 0.0007686598692089319, "entropy": 0.08705786615610123, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:11.651638Z", "loop": 8770, "env_steps": 5388902399, "loss": 0.015709765255451202, "avg_return": 0.8627447485923767, "regret": 0.0017266840441152453, "entropy": 0.08244670182466507, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:12.506726Z", "loop": 8771, "env_steps": 5389516799, "loss": 0.01675792597234249, "avg_return": 0.8629480004310608, "regret": 0.0017266840441152453, "entropy": 0.08703869581222534, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:13.360738Z", "loop": 8772, "env_steps": 5390131199, "loss": 0.016708113253116608, "avg_return": 0.8630076050758362, "regret": 0.0017266840441152453, "entropy": 0.08839061111211777, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:14.216088Z", "loop": 8773, "env_steps": 5390745599, "loss": 0.01707579754292965, "avg_return": 0.8619636297225952, "regret": 0.0017266840441152453, "entropy": 0.09171345084905624, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:15.071986Z", "loop": 8774, "env_steps": 5391359999, "loss": 0.0169098861515522, "avg_return": 0.8629143238067627, "regret": 0.0017266840441152453, "entropy": 0.08650445938110352, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:15.927240Z", "loop": 8775, "env_steps": 5391974399, "loss": 0.015316404402256012, "avg_return": 0.8620060682296753, "regret": 0.0017266840441152453, "entropy": 0.08165691792964935, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:16.781490Z", "loop": 8776, "env_steps": 5392588799, "loss": 0.01674567721784115, "avg_return": 0.863548219203949, "regret": 0.0017266840441152453, "entropy": 0.08612525463104248, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:17.636970Z", "loop": 8777, "env_steps": 5393203199, "loss": 0.016044216230511665, "avg_return": 0.8626538515090942, "regret": 0.0017266840441152453, "entropy": 0.08290694653987885, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:18.492168Z", "loop": 8778, "env_steps": 5393817599, "loss": 0.015989545732736588, "avg_return": 0.8616815209388733, "regret": 0.0017266840441152453, "entropy": 0.08539815992116928, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:19.347729Z", "loop": 8779, "env_steps": 5394431999, "loss": 0.015727665275335312, "avg_return": 0.8631722331047058, "regret": 0.0017266840441152453, "entropy": 0.08219840377569199, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:20.241457Z", "loop": 8780, "env_steps": 5395046399, "loss": 0.016512487083673477, "avg_return": 0.8620992302894592, "regret": 0.000729172897990793, "entropy": 0.08995988965034485, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:21.097709Z", "loop": 8781, "env_steps": 5395660799, "loss": 0.01695163920521736, "avg_return": 0.863135814666748, "regret": 0.000729172897990793, "entropy": 0.08627884835004807, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:21.952805Z", "loop": 8782, "env_steps": 5396275199, "loss": 0.01693420484662056, "avg_return": 0.8631289601325989, "regret": 0.000729172897990793, "entropy": 0.08744022250175476, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:22.808361Z", "loop": 8783, "env_steps": 5396889599, "loss": 0.017434503883123398, "avg_return": 0.8648737072944641, "regret": 0.000729172897990793, "entropy": 0.08822636306285858, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:23.663699Z", "loop": 8784, "env_steps": 5397503999, "loss": 0.01796717755496502, "avg_return": 0.8630481362342834, "regret": 0.000729172897990793, "entropy": 0.09072280675172806, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:24.519763Z", "loop": 8785, "env_steps": 5398118399, "loss": 0.017377128824591637, "avg_return": 0.8637385368347168, "regret": 0.000729172897990793, "entropy": 0.09181457757949829, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:25.375414Z", "loop": 8786, "env_steps": 5398732799, "loss": 0.017825184389948845, "avg_return": 0.86109459400177, "regret": 0.000729172897990793, "entropy": 0.08828063309192657, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:26.230452Z", "loop": 8787, "env_steps": 5399347199, "loss": 0.018670151010155678, "avg_return": 0.8600948452949524, "regret": 0.000729172897990793, "entropy": 0.09524542838335037, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:27.085592Z", "loop": 8788, "env_steps": 5399961599, "loss": 0.017463352531194687, "avg_return": 0.8632552027702332, "regret": 0.000729172897990793, "entropy": 0.09122955799102783, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:27.940281Z", "loop": 8789, "env_steps": 5400575999, "loss": 0.01723814755678177, "avg_return": 0.8629197478294373, "regret": 0.000729172897990793, "entropy": 0.09016504883766174, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:28.836714Z", "loop": 8790, "env_steps": 5401190399, "loss": 0.016916893422603607, "avg_return": 0.8622113466262817, "regret": 0.001580335316248238, "entropy": 0.08960918337106705, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:29.691322Z", "loop": 8791, "env_steps": 5401804799, "loss": 0.016865961253643036, "avg_return": 0.8627398610115051, "regret": 0.001580335316248238, "entropy": 0.08726232498884201, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:30.547092Z", "loop": 8792, "env_steps": 5402419199, "loss": 0.018281446769833565, "avg_return": 0.861957848072052, "regret": 0.001580335316248238, "entropy": 0.09208148717880249, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:31.402193Z", "loop": 8793, "env_steps": 5403033599, "loss": 0.017158351838588715, "avg_return": 0.8622259497642517, "regret": 0.001580335316248238, "entropy": 0.09018494933843613, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:32.256388Z", "loop": 8794, "env_steps": 5403647999, "loss": 0.017077067866921425, "avg_return": 0.8625583052635193, "regret": 0.001580335316248238, "entropy": 0.08956283330917358, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:33.110697Z", "loop": 8795, "env_steps": 5404262399, "loss": 0.01812051609158516, "avg_return": 0.8630096912384033, "regret": 0.001580335316248238, "entropy": 0.09052751213312149, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:33.965848Z", "loop": 8796, "env_steps": 5404876799, "loss": 0.017674244940280914, "avg_return": 0.8631522059440613, "regret": 0.001580335316248238, "entropy": 0.0891994833946228, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:34.821164Z", "loop": 8797, "env_steps": 5405491199, "loss": 0.016017736867070198, "avg_return": 0.8629311323165894, "regret": 0.001580335316248238, "entropy": 0.0828443393111229, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:35.675469Z", "loop": 8798, "env_steps": 5406105599, "loss": 0.016127804294228554, "avg_return": 0.863450825214386, "regret": 0.001580335316248238, "entropy": 0.08089453727006912, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:36.530011Z", "loop": 8799, "env_steps": 5406719999, "loss": 0.016651995480060577, "avg_return": 0.8618409633636475, "regret": 0.001580335316248238, "entropy": 0.08479683846235275, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:37.426162Z", "loop": 8800, "env_steps": 5407334399, "loss": 0.016387008130550385, "avg_return": 0.8621548414230347, "regret": 0.0016630978789180517, "entropy": 0.08788125216960907, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:38.280791Z", "loop": 8801, "env_steps": 5407948799, "loss": 0.01567300222814083, "avg_return": 0.861073911190033, "regret": 0.0016630978789180517, "entropy": 0.0830267146229744, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:39.136456Z", "loop": 8802, "env_steps": 5408563199, "loss": 0.01689213700592518, "avg_return": 0.8608803749084473, "regret": 0.0016630978789180517, "entropy": 0.08877268433570862, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:39.991552Z", "loop": 8803, "env_steps": 5409177599, "loss": 0.016303634271025658, "avg_return": 0.8612567186355591, "regret": 0.0016630978789180517, "entropy": 0.08618520200252533, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:40.845812Z", "loop": 8804, "env_steps": 5409791999, "loss": 0.01645011268556118, "avg_return": 0.8609126806259155, "regret": 0.0016630978789180517, "entropy": 0.08623097836971283, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:41.700202Z", "loop": 8805, "env_steps": 5410406399, "loss": 0.016811396926641464, "avg_return": 0.8596669435501099, "regret": 0.0016630978789180517, "entropy": 0.08611752092838287, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:42.555155Z", "loop": 8806, "env_steps": 5411020799, "loss": 0.016413763165473938, "avg_return": 0.8599823117256165, "regret": 0.0016630978789180517, "entropy": 0.08771146833896637, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:43.409825Z", "loop": 8807, "env_steps": 5411635199, "loss": 0.017733396962285042, "avg_return": 0.8604575991630554, "regret": 0.0016630978789180517, "entropy": 0.09197523444890976, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:44.263727Z", "loop": 8808, "env_steps": 5412249599, "loss": 0.018011394888162613, "avg_return": 0.8596954345703125, "regret": 0.0016630978789180517, "entropy": 0.09113617241382599, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:45.117671Z", "loop": 8809, "env_steps": 5412863999, "loss": 0.015424194745719433, "avg_return": 0.8605208396911621, "regret": 0.0016630978789180517, "entropy": 0.08519414812326431, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:46.011366Z", "loop": 8810, "env_steps": 5413478399, "loss": 0.015050088055431843, "avg_return": 0.8594807386398315, "regret": 0.0038620829582214355, "entropy": 0.08208397775888443, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:46.865672Z", "loop": 8811, "env_steps": 5414092799, "loss": 0.014648173935711384, "avg_return": 0.8578786253929138, "regret": 0.0038620829582214355, "entropy": 0.08270285278558731, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:47.719500Z", "loop": 8812, "env_steps": 5414707199, "loss": 0.01577179506421089, "avg_return": 0.8606358170509338, "regret": 0.0038620829582214355, "entropy": 0.08487316966056824, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:48.572515Z", "loop": 8813, "env_steps": 5415321599, "loss": 0.013969577848911285, "avg_return": 0.8596015572547913, "regret": 0.0038620829582214355, "entropy": 0.07954680174589157, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:49.425986Z", "loop": 8814, "env_steps": 5415935999, "loss": 0.015012073330581188, "avg_return": 0.8611995577812195, "regret": 0.0038620829582214355, "entropy": 0.08373114466667175, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:50.279964Z", "loop": 8815, "env_steps": 5416550399, "loss": 0.015247531235218048, "avg_return": 0.8628330826759338, "regret": 0.0038620829582214355, "entropy": 0.0811164528131485, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:51.134196Z", "loop": 8816, "env_steps": 5417164799, "loss": 0.014225936494767666, "avg_return": 0.8623422384262085, "regret": 0.0038620829582214355, "entropy": 0.07774724811315536, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:51.988448Z", "loop": 8817, "env_steps": 5417779199, "loss": 0.014619885943830013, "avg_return": 0.8613749146461487, "regret": 0.0038620829582214355, "entropy": 0.07790057361125946, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:52.842076Z", "loop": 8818, "env_steps": 5418393599, "loss": 0.01366895716637373, "avg_return": 0.8623971939086914, "regret": 0.0038620829582214355, "entropy": 0.07566676288843155, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:53.695905Z", "loop": 8819, "env_steps": 5419007999, "loss": 0.01489762682467699, "avg_return": 0.8629584908485413, "regret": 0.0038620829582214355, "entropy": 0.07898671180009842, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:54.591835Z", "loop": 8820, "env_steps": 5419622399, "loss": 0.01401668693870306, "avg_return": 0.8621174097061157, "regret": 0.0008764667436480522, "entropy": 0.07788044959306717, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:55.446932Z", "loop": 8821, "env_steps": 5420236799, "loss": 0.01418659370392561, "avg_return": 0.8630906343460083, "regret": 0.0008764667436480522, "entropy": 0.0747729167342186, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:56.299949Z", "loop": 8822, "env_steps": 5420851199, "loss": 0.01575777307152748, "avg_return": 0.8632782101631165, "regret": 0.0008764667436480522, "entropy": 0.08227253705263138, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:57.152922Z", "loop": 8823, "env_steps": 5421465599, "loss": 0.01580396667122841, "avg_return": 0.862776517868042, "regret": 0.0008764667436480522, "entropy": 0.08711008727550507, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:58.007820Z", "loop": 8824, "env_steps": 5422079999, "loss": 0.01603349857032299, "avg_return": 0.8632755875587463, "regret": 0.0008764667436480522, "entropy": 0.0841854065656662, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:58.862964Z", "loop": 8825, "env_steps": 5422694399, "loss": 0.015459072776138783, "avg_return": 0.8613783717155457, "regret": 0.0008764667436480522, "entropy": 0.08191820979118347, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:29:59.716154Z", "loop": 8826, "env_steps": 5423308799, "loss": 0.01618189364671707, "avg_return": 0.8630828261375427, "regret": 0.0008764667436480522, "entropy": 0.08815556019544601, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:00.569234Z", "loop": 8827, "env_steps": 5423923199, "loss": 0.016763128340244293, "avg_return": 0.8638415932655334, "regret": 0.0008764667436480522, "entropy": 0.08668000996112823, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:01.424170Z", "loop": 8828, "env_steps": 5424537599, "loss": 0.016400840133428574, "avg_return": 0.8625521063804626, "regret": 0.0008764667436480522, "entropy": 0.08535124361515045, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:02.279841Z", "loop": 8829, "env_steps": 5425151999, "loss": 0.016771040856838226, "avg_return": 0.8629132509231567, "regret": 0.0008764667436480522, "entropy": 0.0886073186993599, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:03.174506Z", "loop": 8830, "env_steps": 5425766399, "loss": 0.016964316368103027, "avg_return": 0.8626466989517212, "regret": 0.000711164204403758, "entropy": 0.08474652469158173, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:04.027590Z", "loop": 8831, "env_steps": 5426380799, "loss": 0.016873307526111603, "avg_return": 0.8628076314926147, "regret": 0.000711164204403758, "entropy": 0.08699329942464828, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:04.881497Z", "loop": 8832, "env_steps": 5426995199, "loss": 0.015532816760241985, "avg_return": 0.8625748753547668, "regret": 0.000711164204403758, "entropy": 0.08575676381587982, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:05.736810Z", "loop": 8833, "env_steps": 5427609599, "loss": 0.016773171722888947, "avg_return": 0.862231969833374, "regret": 0.000711164204403758, "entropy": 0.08756361156702042, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:06.591235Z", "loop": 8834, "env_steps": 5428223999, "loss": 0.016113637015223503, "avg_return": 0.8633408546447754, "regret": 0.000711164204403758, "entropy": 0.08647332340478897, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:07.446017Z", "loop": 8835, "env_steps": 5428838399, "loss": 0.015797864645719528, "avg_return": 0.8627647161483765, "regret": 0.000711164204403758, "entropy": 0.08672264963388443, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:08.300647Z", "loop": 8836, "env_steps": 5429452799, "loss": 0.015746330842375755, "avg_return": 0.8626503944396973, "regret": 0.000711164204403758, "entropy": 0.08809904009103775, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:09.154826Z", "loop": 8837, "env_steps": 5430067199, "loss": 0.016545554623007774, "avg_return": 0.8633193969726562, "regret": 0.000711164204403758, "entropy": 0.08586696535348892, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:10.009568Z", "loop": 8838, "env_steps": 5430681599, "loss": 0.015374775044620037, "avg_return": 0.8629924654960632, "regret": 0.000711164204403758, "entropy": 0.08456140756607056, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:10.862978Z", "loop": 8839, "env_steps": 5431295999, "loss": 0.01583566889166832, "avg_return": 0.8628761768341064, "regret": 0.000711164204403758, "entropy": 0.08292815089225769, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:11.758156Z", "loop": 8840, "env_steps": 5431910399, "loss": 0.015933988615870476, "avg_return": 0.8623671531677246, "regret": 0.0010384556371718645, "entropy": 0.08692032098770142, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:12.611084Z", "loop": 8841, "env_steps": 5432524799, "loss": 0.016576817259192467, "avg_return": 0.8635499477386475, "regret": 0.0010384556371718645, "entropy": 0.08568419516086578, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:13.465362Z", "loop": 8842, "env_steps": 5433139199, "loss": 0.0161844901740551, "avg_return": 0.8622269034385681, "regret": 0.0010384556371718645, "entropy": 0.08444692194461823, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:14.318967Z", "loop": 8843, "env_steps": 5433753599, "loss": 0.016714690253138542, "avg_return": 0.8627961277961731, "regret": 0.0010384556371718645, "entropy": 0.08727875351905823, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:15.173202Z", "loop": 8844, "env_steps": 5434367999, "loss": 0.017119240015745163, "avg_return": 0.8631091713905334, "regret": 0.0010384556371718645, "entropy": 0.0872703269124031, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:16.028202Z", "loop": 8845, "env_steps": 5434982399, "loss": 0.017809804528951645, "avg_return": 0.862873375415802, "regret": 0.0010384556371718645, "entropy": 0.08793530613183975, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:16.882948Z", "loop": 8846, "env_steps": 5435596799, "loss": 0.016615774482488632, "avg_return": 0.8614985346794128, "regret": 0.0010384556371718645, "entropy": 0.08841922134160995, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:17.737108Z", "loop": 8847, "env_steps": 5436211199, "loss": 0.0167001411318779, "avg_return": 0.8635982275009155, "regret": 0.0010384556371718645, "entropy": 0.08896179497241974, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:18.591612Z", "loop": 8848, "env_steps": 5436825599, "loss": 0.017156697809696198, "avg_return": 0.8634592890739441, "regret": 0.0010384556371718645, "entropy": 0.08806786686182022, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:19.444470Z", "loop": 8849, "env_steps": 5437439999, "loss": 0.0164816752076149, "avg_return": 0.8619433641433716, "regret": 0.0010384556371718645, "entropy": 0.08471662551164627, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:20.339296Z", "loop": 8850, "env_steps": 5438054399, "loss": 0.017146999016404152, "avg_return": 0.8633117079734802, "regret": 0.0006039483705535531, "entropy": 0.08897264301776886, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:21.194248Z", "loop": 8851, "env_steps": 5438668799, "loss": 0.017277872189879417, "avg_return": 0.8626312613487244, "regret": 0.0006039483705535531, "entropy": 0.08854851126670837, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:22.048617Z", "loop": 8852, "env_steps": 5439283199, "loss": 0.017977682873606682, "avg_return": 0.8630967140197754, "regret": 0.0006039483705535531, "entropy": 0.09009746462106705, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:22.902712Z", "loop": 8853, "env_steps": 5439897599, "loss": 0.01735302247107029, "avg_return": 0.8630457520484924, "regret": 0.0006039483705535531, "entropy": 0.09302093833684921, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:23.756657Z", "loop": 8854, "env_steps": 5440511999, "loss": 0.01801389269530773, "avg_return": 0.8633486032485962, "regret": 0.0006039483705535531, "entropy": 0.09245654940605164, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:24.611734Z", "loop": 8855, "env_steps": 5441126399, "loss": 0.019216498360037804, "avg_return": 0.8625882267951965, "regret": 0.0006039483705535531, "entropy": 0.09476899355649948, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:25.465322Z", "loop": 8856, "env_steps": 5441740799, "loss": 0.019587665796279907, "avg_return": 0.8610410690307617, "regret": 0.0006039483705535531, "entropy": 0.09755689650774002, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:26.319550Z", "loop": 8857, "env_steps": 5442355199, "loss": 0.018856506794691086, "avg_return": 0.8624617457389832, "regret": 0.0006039483705535531, "entropy": 0.09260494261980057, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:27.172979Z", "loop": 8858, "env_steps": 5442969599, "loss": 0.018312791362404823, "avg_return": 0.8620855808258057, "regret": 0.0006039483705535531, "entropy": 0.09659337252378464, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:28.027972Z", "loop": 8859, "env_steps": 5443583999, "loss": 0.018921125680208206, "avg_return": 0.8626400232315063, "regret": 0.0006039483705535531, "entropy": 0.09814044833183289, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:28.922793Z", "loop": 8860, "env_steps": 5444198399, "loss": 0.018696285784244537, "avg_return": 0.8621543645858765, "regret": 0.0012235331814736128, "entropy": 0.09368226677179337, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:29.777224Z", "loop": 8861, "env_steps": 5444812799, "loss": 0.018450191244482994, "avg_return": 0.8624643087387085, "regret": 0.0012235331814736128, "entropy": 0.09508907049894333, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:30.631801Z", "loop": 8862, "env_steps": 5445427199, "loss": 0.01900099776685238, "avg_return": 0.860643744468689, "regret": 0.0012235331814736128, "entropy": 0.09636399894952774, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:31.485480Z", "loop": 8863, "env_steps": 5446041599, "loss": 0.019352393224835396, "avg_return": 0.861693263053894, "regret": 0.0012235331814736128, "entropy": 0.09818867594003677, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:32.339664Z", "loop": 8864, "env_steps": 5446655999, "loss": 0.019259044900536537, "avg_return": 0.8612231612205505, "regret": 0.0012235331814736128, "entropy": 0.09709179401397705, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:33.194050Z", "loop": 8865, "env_steps": 5447270399, "loss": 0.019535565748810768, "avg_return": 0.8609944581985474, "regret": 0.0012235331814736128, "entropy": 0.09971506893634796, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:34.048683Z", "loop": 8866, "env_steps": 5447884799, "loss": 0.017820242792367935, "avg_return": 0.8606702089309692, "regret": 0.0012235331814736128, "entropy": 0.09666052460670471, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:34.902207Z", "loop": 8867, "env_steps": 5448499199, "loss": 0.019186509773135185, "avg_return": 0.8619406223297119, "regret": 0.0012235331814736128, "entropy": 0.09657200425863266, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:35.756174Z", "loop": 8868, "env_steps": 5449113599, "loss": 0.018436020240187645, "avg_return": 0.8631439208984375, "regret": 0.0012235331814736128, "entropy": 0.09455123543739319, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:36.610233Z", "loop": 8869, "env_steps": 5449727999, "loss": 0.01972196064889431, "avg_return": 0.8641190528869629, "regret": 0.0012235331814736128, "entropy": 0.09649350494146347, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:37.504514Z", "loop": 8870, "env_steps": 5450342399, "loss": 0.018027333542704582, "avg_return": 0.8635725975036621, "regret": 0.0007520414656028152, "entropy": 0.09606525301933289, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:38.358694Z", "loop": 8871, "env_steps": 5450956799, "loss": 0.018037112429738045, "avg_return": 0.8632516860961914, "regret": 0.0007520414656028152, "entropy": 0.09196796268224716, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:39.214207Z", "loop": 8872, "env_steps": 5451571199, "loss": 0.017892858013510704, "avg_return": 0.861506462097168, "regret": 0.0007520414656028152, "entropy": 0.09142478555440903, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:40.068814Z", "loop": 8873, "env_steps": 5452185599, "loss": 0.01902860589325428, "avg_return": 0.8635010123252869, "regret": 0.0007520414656028152, "entropy": 0.09424424916505814, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:40.923661Z", "loop": 8874, "env_steps": 5452799999, "loss": 0.01842678338289261, "avg_return": 0.8627117276191711, "regret": 0.0007520414656028152, "entropy": 0.0940786600112915, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:41.779003Z", "loop": 8875, "env_steps": 5453414399, "loss": 0.017631126567721367, "avg_return": 0.8630402684211731, "regret": 0.0007520414656028152, "entropy": 0.09417232125997543, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:42.633943Z", "loop": 8876, "env_steps": 5454028799, "loss": 0.01863924227654934, "avg_return": 0.8631903529167175, "regret": 0.0007520414656028152, "entropy": 0.09492615610361099, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:43.488717Z", "loop": 8877, "env_steps": 5454643199, "loss": 0.01795092783868313, "avg_return": 0.8639094233512878, "regret": 0.0007520414656028152, "entropy": 0.09538958221673965, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:44.344359Z", "loop": 8878, "env_steps": 5455257599, "loss": 0.01940995454788208, "avg_return": 0.8628963232040405, "regret": 0.0007520414656028152, "entropy": 0.09792811423540115, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:45.199595Z", "loop": 8879, "env_steps": 5455871999, "loss": 0.020254431292414665, "avg_return": 0.863429069519043, "regret": 0.0007520414656028152, "entropy": 0.09886632114648819, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:46.095834Z", "loop": 8880, "env_steps": 5456486399, "loss": 0.017736634239554405, "avg_return": 0.8635867238044739, "regret": 0.00039309755084104836, "entropy": 0.09142805635929108, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:46.950954Z", "loop": 8881, "env_steps": 5457100799, "loss": 0.017926163971424103, "avg_return": 0.862457275390625, "regret": 0.00039309755084104836, "entropy": 0.09189844876527786, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:47.804684Z", "loop": 8882, "env_steps": 5457715199, "loss": 0.017281876876950264, "avg_return": 0.8647459149360657, "regret": 0.00039309755084104836, "entropy": 0.09067836403846741, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:48.658668Z", "loop": 8883, "env_steps": 5458329599, "loss": 0.017430145293474197, "avg_return": 0.8632729053497314, "regret": 0.00039309755084104836, "entropy": 0.09052477031946182, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:49.513782Z", "loop": 8884, "env_steps": 5458943999, "loss": 0.017206719145178795, "avg_return": 0.8624648451805115, "regret": 0.00039309755084104836, "entropy": 0.08878155052661896, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:50.367039Z", "loop": 8885, "env_steps": 5459558399, "loss": 0.016939641907811165, "avg_return": 0.8642105460166931, "regret": 0.00039309755084104836, "entropy": 0.08914390206336975, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:51.220188Z", "loop": 8886, "env_steps": 5460172799, "loss": 0.017217855900526047, "avg_return": 0.8621517419815063, "regret": 0.00039309755084104836, "entropy": 0.08768508583307266, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:52.074937Z", "loop": 8887, "env_steps": 5460787199, "loss": 0.01592649333178997, "avg_return": 0.8621616959571838, "regret": 0.00039309755084104836, "entropy": 0.08602568507194519, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:52.929214Z", "loop": 8888, "env_steps": 5461401599, "loss": 0.015387642197310925, "avg_return": 0.8622196912765503, "regret": 0.00039309755084104836, "entropy": 0.08365291357040405, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:53.783587Z", "loop": 8889, "env_steps": 5462015999, "loss": 0.01551455445587635, "avg_return": 0.8633384108543396, "regret": 0.00039309755084104836, "entropy": 0.08262570947408676, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:54.676811Z", "loop": 8890, "env_steps": 5462630399, "loss": 0.014810820110142231, "avg_return": 0.8631541132926941, "regret": 0.000375192379578948, "entropy": 0.07797972857952118, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:55.529997Z", "loop": 8891, "env_steps": 5463244799, "loss": 0.013785861432552338, "avg_return": 0.8635491132736206, "regret": 0.000375192379578948, "entropy": 0.07530861347913742, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:56.384310Z", "loop": 8892, "env_steps": 5463859199, "loss": 0.014787298627197742, "avg_return": 0.8627548217773438, "regret": 0.000375192379578948, "entropy": 0.07797214388847351, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:57.238603Z", "loop": 8893, "env_steps": 5464473599, "loss": 0.014634097926318645, "avg_return": 0.8636494874954224, "regret": 0.000375192379578948, "entropy": 0.07502748817205429, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:58.093159Z", "loop": 8894, "env_steps": 5465087999, "loss": 0.013505441136658192, "avg_return": 0.8627527952194214, "regret": 0.000375192379578948, "entropy": 0.07380761206150055, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:58.946880Z", "loop": 8895, "env_steps": 5465702399, "loss": 0.012960726395249367, "avg_return": 0.8618254065513611, "regret": 0.000375192379578948, "entropy": 0.07254621386528015, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:30:59.801719Z", "loop": 8896, "env_steps": 5466316799, "loss": 0.013734242878854275, "avg_return": 0.8623580932617188, "regret": 0.000375192379578948, "entropy": 0.07417768239974976, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:00.655854Z", "loop": 8897, "env_steps": 5466931199, "loss": 0.014087854884564877, "avg_return": 0.8634247183799744, "regret": 0.000375192379578948, "entropy": 0.07339996844530106, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:01.510107Z", "loop": 8898, "env_steps": 5467545599, "loss": 0.01487561222165823, "avg_return": 0.8627814054489136, "regret": 0.000375192379578948, "entropy": 0.07815105468034744, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:02.364354Z", "loop": 8899, "env_steps": 5468159999, "loss": 0.014497028663754463, "avg_return": 0.8636708855628967, "regret": 0.000375192379578948, "entropy": 0.07892411947250366, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:03.257557Z", "loop": 8900, "env_steps": 5468774399, "loss": 0.013130269944667816, "avg_return": 0.8630195260047913, "regret": 0.0007087461417540908, "entropy": 0.07434893399477005, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:04.111078Z", "loop": 8901, "env_steps": 5469388799, "loss": 0.014281774871051311, "avg_return": 0.8636157512664795, "regret": 0.0007087461417540908, "entropy": 0.073940210044384, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:04.965983Z", "loop": 8902, "env_steps": 5470003199, "loss": 0.014799730852246284, "avg_return": 0.8623321652412415, "regret": 0.0007087461417540908, "entropy": 0.08135567605495453, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:05.819939Z", "loop": 8903, "env_steps": 5470617599, "loss": 0.014605755917727947, "avg_return": 0.8621981143951416, "regret": 0.0007087461417540908, "entropy": 0.07878939807415009, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:06.674418Z", "loop": 8904, "env_steps": 5471231999, "loss": 0.014130639843642712, "avg_return": 0.8610626459121704, "regret": 0.0007087461417540908, "entropy": 0.07965107262134552, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:07.528225Z", "loop": 8905, "env_steps": 5471846399, "loss": 0.015289917588233948, "avg_return": 0.8624204993247986, "regret": 0.0007087461417540908, "entropy": 0.08360037207603455, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:08.382467Z", "loop": 8906, "env_steps": 5472460799, "loss": 0.015504538081586361, "avg_return": 0.8626275658607483, "regret": 0.0007087461417540908, "entropy": 0.08244690299034119, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:09.236569Z", "loop": 8907, "env_steps": 5473075199, "loss": 0.015918005257844925, "avg_return": 0.8614017963409424, "regret": 0.0007087461417540908, "entropy": 0.08097483217716217, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:10.089676Z", "loop": 8908, "env_steps": 5473689599, "loss": 0.015129568055272102, "avg_return": 0.8630700707435608, "regret": 0.0007087461417540908, "entropy": 0.08328156918287277, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:10.943206Z", "loop": 8909, "env_steps": 5474303999, "loss": 0.014893813990056515, "avg_return": 0.8607485294342041, "regret": 0.0007087461417540908, "entropy": 0.08317693322896957, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:11.839922Z", "loop": 8910, "env_steps": 5474918399, "loss": 0.013514475896954536, "avg_return": 0.8618338108062744, "regret": 0.0017681935569271445, "entropy": 0.07540477812290192, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:12.694709Z", "loop": 8911, "env_steps": 5475532799, "loss": 0.014201722107827663, "avg_return": 0.8609172701835632, "regret": 0.0017681935569271445, "entropy": 0.0792429968714714, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:13.548390Z", "loop": 8912, "env_steps": 5476147199, "loss": 0.014564627781510353, "avg_return": 0.8614829778671265, "regret": 0.0017681935569271445, "entropy": 0.07933475822210312, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:14.403181Z", "loop": 8913, "env_steps": 5476761599, "loss": 0.015236079692840576, "avg_return": 0.8644322752952576, "regret": 0.0017681935569271445, "entropy": 0.08223298192024231, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:15.257527Z", "loop": 8914, "env_steps": 5477375999, "loss": 0.01398305594921112, "avg_return": 0.8631265759468079, "regret": 0.0017681935569271445, "entropy": 0.07480771094560623, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:16.112735Z", "loop": 8915, "env_steps": 5477990399, "loss": 0.015227078460156918, "avg_return": 0.8634241223335266, "regret": 0.0017681935569271445, "entropy": 0.08053768426179886, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:16.967093Z", "loop": 8916, "env_steps": 5478604799, "loss": 0.015206958167254925, "avg_return": 0.8634660840034485, "regret": 0.0017681935569271445, "entropy": 0.08109559118747711, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:17.820750Z", "loop": 8917, "env_steps": 5479219199, "loss": 0.01333752553910017, "avg_return": 0.8629640936851501, "regret": 0.0017681935569271445, "entropy": 0.07394004613161087, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:18.674366Z", "loop": 8918, "env_steps": 5479833599, "loss": 0.014195834286510944, "avg_return": 0.8626524209976196, "regret": 0.0017681935569271445, "entropy": 0.07692018151283264, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:19.528636Z", "loop": 8919, "env_steps": 5480447999, "loss": 0.013285716064274311, "avg_return": 0.8629980683326721, "regret": 0.0017681935569271445, "entropy": 0.07418039441108704, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:20.422633Z", "loop": 8920, "env_steps": 5481062399, "loss": 0.01413738913834095, "avg_return": 0.864388644695282, "regret": 0.0005120310815982521, "entropy": 0.07575957477092743, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:21.276477Z", "loop": 8921, "env_steps": 5481676799, "loss": 0.013121983967721462, "avg_return": 0.8619063496589661, "regret": 0.0005120310815982521, "entropy": 0.07415414601564407, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:22.130007Z", "loop": 8922, "env_steps": 5482291199, "loss": 0.014009663835167885, "avg_return": 0.862955629825592, "regret": 0.0005120310815982521, "entropy": 0.07098563760519028, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:22.984489Z", "loop": 8923, "env_steps": 5482905599, "loss": 0.013555002398788929, "avg_return": 0.8631699681282043, "regret": 0.0005120310815982521, "entropy": 0.07192632555961609, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:23.838830Z", "loop": 8924, "env_steps": 5483519999, "loss": 0.012956512160599232, "avg_return": 0.8624523878097534, "regret": 0.0005120310815982521, "entropy": 0.07118498533964157, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:24.693417Z", "loop": 8925, "env_steps": 5484134399, "loss": 0.012910010293126106, "avg_return": 0.8625790476799011, "regret": 0.0005120310815982521, "entropy": 0.07120607793331146, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:25.547014Z", "loop": 8926, "env_steps": 5484748799, "loss": 0.013052812777459621, "avg_return": 0.8632452487945557, "regret": 0.0005120310815982521, "entropy": 0.0679946318268776, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:26.400497Z", "loop": 8927, "env_steps": 5485363199, "loss": 0.012155614793300629, "avg_return": 0.8628800511360168, "regret": 0.0005120310815982521, "entropy": 0.06645617634057999, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:27.254357Z", "loop": 8928, "env_steps": 5485977599, "loss": 0.013639709912240505, "avg_return": 0.8627350926399231, "regret": 0.0005120310815982521, "entropy": 0.0745134949684143, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:28.107773Z", "loop": 8929, "env_steps": 5486591999, "loss": 0.012669171206653118, "avg_return": 0.8636137247085571, "regret": 0.0005120310815982521, "entropy": 0.0711732879281044, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:29.003063Z", "loop": 8930, "env_steps": 5487206399, "loss": 0.013119434006512165, "avg_return": 0.863259494304657, "regret": 0.000724065350368619, "entropy": 0.0703682079911232, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:29.859048Z", "loop": 8931, "env_steps": 5487820799, "loss": 0.012707928195595741, "avg_return": 0.863094687461853, "regret": 0.000724065350368619, "entropy": 0.07344084233045578, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:30.713367Z", "loop": 8932, "env_steps": 5488435199, "loss": 0.01338794082403183, "avg_return": 0.8618906736373901, "regret": 0.000724065350368619, "entropy": 0.07195387035608292, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:31.568633Z", "loop": 8933, "env_steps": 5489049599, "loss": 0.012682303786277771, "avg_return": 0.8623610734939575, "regret": 0.000724065350368619, "entropy": 0.0698113813996315, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:32.424224Z", "loop": 8934, "env_steps": 5489663999, "loss": 0.013142782263457775, "avg_return": 0.8633655905723572, "regret": 0.000724065350368619, "entropy": 0.07179983705282211, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:33.279033Z", "loop": 8935, "env_steps": 5490278399, "loss": 0.012988974340260029, "avg_return": 0.8614190816879272, "regret": 0.000724065350368619, "entropy": 0.07593873888254166, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:34.133709Z", "loop": 8936, "env_steps": 5490892799, "loss": 0.013306512497365475, "avg_return": 0.8626930713653564, "regret": 0.000724065350368619, "entropy": 0.07063823938369751, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:34.988975Z", "loop": 8937, "env_steps": 5491507199, "loss": 0.013805173337459564, "avg_return": 0.8636992573738098, "regret": 0.000724065350368619, "entropy": 0.07555712759494781, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:35.845493Z", "loop": 8938, "env_steps": 5492121599, "loss": 0.012671037577092648, "avg_return": 0.8640283346176147, "regret": 0.000724065350368619, "entropy": 0.06938198208808899, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:36.699714Z", "loop": 8939, "env_steps": 5492735999, "loss": 0.0131639763712883, "avg_return": 0.8629763126373291, "regret": 0.000724065350368619, "entropy": 0.06929345428943634, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:37.592980Z", "loop": 8940, "env_steps": 5493350399, "loss": 0.012597816996276379, "avg_return": 0.862986147403717, "regret": 0.0005065588047727942, "entropy": 0.06813894212245941, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:38.447995Z", "loop": 8941, "env_steps": 5493964799, "loss": 0.013074024580419064, "avg_return": 0.8640297651290894, "regret": 0.0005065588047727942, "entropy": 0.07292784750461578, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:39.302354Z", "loop": 8942, "env_steps": 5494579199, "loss": 0.012445416301488876, "avg_return": 0.8619944453239441, "regret": 0.0005065588047727942, "entropy": 0.07088825106620789, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:40.156361Z", "loop": 8943, "env_steps": 5495193599, "loss": 0.012723742984235287, "avg_return": 0.8621675968170166, "regret": 0.0005065588047727942, "entropy": 0.06826885044574738, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:41.010884Z", "loop": 8944, "env_steps": 5495807999, "loss": 0.013291466049849987, "avg_return": 0.8621689081192017, "regret": 0.0005065588047727942, "entropy": 0.07143882662057877, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:41.864965Z", "loop": 8945, "env_steps": 5496422399, "loss": 0.013326088897883892, "avg_return": 0.8636125922203064, "regret": 0.0005065588047727942, "entropy": 0.07301201671361923, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:42.719447Z", "loop": 8946, "env_steps": 5497036799, "loss": 0.012096445076167583, "avg_return": 0.8626354932785034, "regret": 0.0005065588047727942, "entropy": 0.06921789050102234, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:43.573736Z", "loop": 8947, "env_steps": 5497651199, "loss": 0.01290164329111576, "avg_return": 0.8626636862754822, "regret": 0.0005065588047727942, "entropy": 0.07549180835485458, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:44.428508Z", "loop": 8948, "env_steps": 5498265599, "loss": 0.012041986919939518, "avg_return": 0.8617385029792786, "regret": 0.0005065588047727942, "entropy": 0.07051171362400055, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:45.282305Z", "loop": 8949, "env_steps": 5498879999, "loss": 0.01266566850244999, "avg_return": 0.8639011979103088, "regret": 0.0005065588047727942, "entropy": 0.06918735802173615, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:46.177752Z", "loop": 8950, "env_steps": 5499494399, "loss": 0.012805192731320858, "avg_return": 0.8630160689353943, "regret": 0.0009101021569222212, "entropy": 0.07229393720626831, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:47.032144Z", "loop": 8951, "env_steps": 5500108799, "loss": 0.014952427707612514, "avg_return": 0.8620612621307373, "regret": 0.0009101021569222212, "entropy": 0.07643114030361176, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:47.886429Z", "loop": 8952, "env_steps": 5500723199, "loss": 0.014050844125449657, "avg_return": 0.8622866868972778, "regret": 0.0009101021569222212, "entropy": 0.07727450877428055, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:48.740743Z", "loop": 8953, "env_steps": 5501337599, "loss": 0.01537622231990099, "avg_return": 0.8626004457473755, "regret": 0.0009101021569222212, "entropy": 0.08109597116708755, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:49.595751Z", "loop": 8954, "env_steps": 5501951999, "loss": 0.01639152504503727, "avg_return": 0.8597737550735474, "regret": 0.0009101021569222212, "entropy": 0.08332028239965439, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:50.450167Z", "loop": 8955, "env_steps": 5502566399, "loss": 0.014645084738731384, "avg_return": 0.8591967225074768, "regret": 0.0009101021569222212, "entropy": 0.08122115582227707, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:51.304479Z", "loop": 8956, "env_steps": 5503180799, "loss": 0.01625949516892433, "avg_return": 0.8606030344963074, "regret": 0.0009101021569222212, "entropy": 0.08636327087879181, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:52.158907Z", "loop": 8957, "env_steps": 5503795199, "loss": 0.015668049454689026, "avg_return": 0.8604433536529541, "regret": 0.0009101021569222212, "entropy": 0.08060962706804276, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:53.014081Z", "loop": 8958, "env_steps": 5504409599, "loss": 0.014033893123269081, "avg_return": 0.8610143065452576, "regret": 0.0009101021569222212, "entropy": 0.07738592475652695, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:53.867590Z", "loop": 8959, "env_steps": 5505023999, "loss": 0.013242701068520546, "avg_return": 0.8630611300468445, "regret": 0.0009101021569222212, "entropy": 0.07428544759750366, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:54.763303Z", "loop": 8960, "env_steps": 5505638399, "loss": 0.012621697969734669, "avg_return": 0.8624340891838074, "regret": 0.0016600069357082248, "entropy": 0.0710572898387909, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:55.616865Z", "loop": 8961, "env_steps": 5506252799, "loss": 0.012218195013701916, "avg_return": 0.8621125221252441, "regret": 0.0016600069357082248, "entropy": 0.06510911881923676, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:56.471641Z", "loop": 8962, "env_steps": 5506867199, "loss": 0.013722012750804424, "avg_return": 0.8621677756309509, "regret": 0.0016600069357082248, "entropy": 0.07464441657066345, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:57.325697Z", "loop": 8963, "env_steps": 5507481599, "loss": 0.012652816250920296, "avg_return": 0.8631352186203003, "regret": 0.0016600069357082248, "entropy": 0.0704074501991272, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:58.179889Z", "loop": 8964, "env_steps": 5508095999, "loss": 0.013315192423760891, "avg_return": 0.8614060878753662, "regret": 0.0016600069357082248, "entropy": 0.06946298480033875, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:59.033139Z", "loop": 8965, "env_steps": 5508710399, "loss": 0.012630553916096687, "avg_return": 0.8634195923805237, "regret": 0.0016600069357082248, "entropy": 0.07083824276924133, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:31:59.887856Z", "loop": 8966, "env_steps": 5509324799, "loss": 0.01169101893901825, "avg_return": 0.8632725477218628, "regret": 0.0016600069357082248, "entropy": 0.0655420795083046, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:00.740478Z", "loop": 8967, "env_steps": 5509939199, "loss": 0.012483461759984493, "avg_return": 0.8624011278152466, "regret": 0.0016600069357082248, "entropy": 0.06905492395162582, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:01.594037Z", "loop": 8968, "env_steps": 5510553599, "loss": 0.013347472064197063, "avg_return": 0.8635004162788391, "regret": 0.0016600069357082248, "entropy": 0.07147194445133209, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:02.448462Z", "loop": 8969, "env_steps": 5511167999, "loss": 0.013136829249560833, "avg_return": 0.8626279830932617, "regret": 0.0016600069357082248, "entropy": 0.07078377902507782, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:03.342957Z", "loop": 8970, "env_steps": 5511782399, "loss": 0.01258213259279728, "avg_return": 0.863766074180603, "regret": 0.0005296925664879382, "entropy": 0.07046858966350555, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:04.196297Z", "loop": 8971, "env_steps": 5512396799, "loss": 0.012267268262803555, "avg_return": 0.8624964356422424, "regret": 0.0005296925664879382, "entropy": 0.0658356100320816, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:05.051815Z", "loop": 8972, "env_steps": 5513011199, "loss": 0.012679548934102058, "avg_return": 0.8634780049324036, "regret": 0.0005296925664879382, "entropy": 0.0727122500538826, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:05.905927Z", "loop": 8973, "env_steps": 5513625599, "loss": 0.013742983341217041, "avg_return": 0.8636592030525208, "regret": 0.0005296925664879382, "entropy": 0.07190611213445663, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:06.760856Z", "loop": 8974, "env_steps": 5514239999, "loss": 0.01371224969625473, "avg_return": 0.8627679944038391, "regret": 0.0005296925664879382, "entropy": 0.0743686631321907, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:07.614960Z", "loop": 8975, "env_steps": 5514854399, "loss": 0.014535302296280861, "avg_return": 0.8641539812088013, "regret": 0.0005296925664879382, "entropy": 0.07194750756025314, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:08.468233Z", "loop": 8976, "env_steps": 5515468799, "loss": 0.012713814154267311, "avg_return": 0.8640002608299255, "regret": 0.0005296925664879382, "entropy": 0.07180537283420563, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:09.321834Z", "loop": 8977, "env_steps": 5516083199, "loss": 0.012778534553945065, "avg_return": 0.8626888394355774, "regret": 0.0005296925664879382, "entropy": 0.07167885452508926, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:10.176498Z", "loop": 8978, "env_steps": 5516697599, "loss": 0.012895839288830757, "avg_return": 0.8627231121063232, "regret": 0.0005296925664879382, "entropy": 0.07077726721763611, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:11.031276Z", "loop": 8979, "env_steps": 5517311999, "loss": 0.014078146778047085, "avg_return": 0.8630572557449341, "regret": 0.0005296925664879382, "entropy": 0.07609623670578003, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:11.925513Z", "loop": 8980, "env_steps": 5517926399, "loss": 0.012464757077395916, "avg_return": 0.8612141013145447, "regret": 0.0012107567163184285, "entropy": 0.0680694505572319, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:12.781057Z", "loop": 8981, "env_steps": 5518540799, "loss": 0.013236181810498238, "avg_return": 0.86137455701828, "regret": 0.0012107567163184285, "entropy": 0.07128135859966278, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:13.636370Z", "loop": 8982, "env_steps": 5519155199, "loss": 0.013020959682762623, "avg_return": 0.8614476919174194, "regret": 0.0012107567163184285, "entropy": 0.0715315192937851, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:14.491400Z", "loop": 8983, "env_steps": 5519769599, "loss": 0.014441343955695629, "avg_return": 0.8615803122520447, "regret": 0.0012107567163184285, "entropy": 0.07319217175245285, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:15.345776Z", "loop": 8984, "env_steps": 5520383999, "loss": 0.01356610655784607, "avg_return": 0.8633639812469482, "regret": 0.0012107567163184285, "entropy": 0.07067491859197617, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:16.199803Z", "loop": 8985, "env_steps": 5520998399, "loss": 0.012607966549694538, "avg_return": 0.8631944060325623, "regret": 0.0012107567163184285, "entropy": 0.06819453835487366, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:17.053550Z", "loop": 8986, "env_steps": 5521612799, "loss": 0.011783785186707973, "avg_return": 0.8607577681541443, "regret": 0.0012107567163184285, "entropy": 0.06864649057388306, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:17.907356Z", "loop": 8987, "env_steps": 5522227199, "loss": 0.012232962995767593, "avg_return": 0.8614981174468994, "regret": 0.0012107567163184285, "entropy": 0.06724300980567932, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:18.761147Z", "loop": 8988, "env_steps": 5522841599, "loss": 0.012392989359796047, "avg_return": 0.8608447313308716, "regret": 0.0012107567163184285, "entropy": 0.06670073419809341, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:19.615465Z", "loop": 8989, "env_steps": 5523455999, "loss": 0.012455767020583153, "avg_return": 0.8614543080329895, "regret": 0.0012107567163184285, "entropy": 0.06848985701799393, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:20.509654Z", "loop": 8990, "env_steps": 5524070399, "loss": 0.013468258082866669, "avg_return": 0.8622137904167175, "regret": 0.0018511289963498712, "entropy": 0.07427986711263657, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:21.363326Z", "loop": 8991, "env_steps": 5524684799, "loss": 0.014127290807664394, "avg_return": 0.8624109029769897, "regret": 0.0018511289963498712, "entropy": 0.07728289067745209, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:22.218409Z", "loop": 8992, "env_steps": 5525299199, "loss": 0.013631495647132397, "avg_return": 0.8621159195899963, "regret": 0.0018511289963498712, "entropy": 0.07334258407354355, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:23.072968Z", "loop": 8993, "env_steps": 5525913599, "loss": 0.012665837071835995, "avg_return": 0.862053632736206, "regret": 0.0018511289963498712, "entropy": 0.07055900990962982, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:23.925845Z", "loop": 8994, "env_steps": 5526527999, "loss": 0.013276347890496254, "avg_return": 0.8636560440063477, "regret": 0.0018511289963498712, "entropy": 0.07300711423158646, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:24.778568Z", "loop": 8995, "env_steps": 5527142399, "loss": 0.012836885638535023, "avg_return": 0.8626756072044373, "regret": 0.0018511289963498712, "entropy": 0.07004500925540924, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:25.632053Z", "loop": 8996, "env_steps": 5527756799, "loss": 0.012733585201203823, "avg_return": 0.8627832531929016, "regret": 0.0018511289963498712, "entropy": 0.06892573088407516, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:26.486418Z", "loop": 8997, "env_steps": 5528371199, "loss": 0.013394216075539589, "avg_return": 0.8645760416984558, "regret": 0.0018511289963498712, "entropy": 0.07338228076696396, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:27.340164Z", "loop": 8998, "env_steps": 5528985599, "loss": 0.013143027201294899, "avg_return": 0.8632619380950928, "regret": 0.0018511289963498712, "entropy": 0.07254162430763245, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:28.193082Z", "loop": 8999, "env_steps": 5529599999, "loss": 0.01303844153881073, "avg_return": 0.8620491623878479, "regret": 0.0018511289963498712, "entropy": 0.07228940725326538, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:29.089968Z", "loop": 9000, "env_steps": 5530214399, "loss": 0.01292200107127428, "avg_return": 0.8631404638290405, "regret": 0.0007680689450353384, "entropy": 0.07258839905261993, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:29.944589Z", "loop": 9001, "env_steps": 5530828799, "loss": 0.013763022609055042, "avg_return": 0.8626821041107178, "regret": 0.0007680689450353384, "entropy": 0.07263264060020447, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:30.798870Z", "loop": 9002, "env_steps": 5531443199, "loss": 0.014864963479340076, "avg_return": 0.8626236319541931, "regret": 0.0007680689450353384, "entropy": 0.07794509083032608, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:31.652985Z", "loop": 9003, "env_steps": 5532057599, "loss": 0.01380593329668045, "avg_return": 0.8626176118850708, "regret": 0.0007680689450353384, "entropy": 0.07841639965772629, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:32.506539Z", "loop": 9004, "env_steps": 5532671999, "loss": 0.013551092706620693, "avg_return": 0.8626393675804138, "regret": 0.0007680689450353384, "entropy": 0.07647944241762161, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:33.361140Z", "loop": 9005, "env_steps": 5533286399, "loss": 0.013903363607823849, "avg_return": 0.8627666234970093, "regret": 0.0007680689450353384, "entropy": 0.07565145939588547, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:34.216265Z", "loop": 9006, "env_steps": 5533900799, "loss": 0.014738504774868488, "avg_return": 0.862191915512085, "regret": 0.0007680689450353384, "entropy": 0.08056911081075668, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:35.071286Z", "loop": 9007, "env_steps": 5534515199, "loss": 0.014522462151944637, "avg_return": 0.8612945675849915, "regret": 0.0007680689450353384, "entropy": 0.07848232239484787, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:35.924594Z", "loop": 9008, "env_steps": 5535129599, "loss": 0.014820021577179432, "avg_return": 0.8628628849983215, "regret": 0.0007680689450353384, "entropy": 0.08049733191728592, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:36.778187Z", "loop": 9009, "env_steps": 5535743999, "loss": 0.015099707059562206, "avg_return": 0.8631048798561096, "regret": 0.0007680689450353384, "entropy": 0.07795269787311554, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:37.674561Z", "loop": 9010, "env_steps": 5536358399, "loss": 0.014889535494148731, "avg_return": 0.8618719577789307, "regret": 0.0010179381351917982, "entropy": 0.0782640129327774, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:38.527903Z", "loop": 9011, "env_steps": 5536972799, "loss": 0.016862845048308372, "avg_return": 0.8632509708404541, "regret": 0.0010179381351917982, "entropy": 0.08711763471364975, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:39.381910Z", "loop": 9012, "env_steps": 5537587199, "loss": 0.01621869206428528, "avg_return": 0.8622893691062927, "regret": 0.0010179381351917982, "entropy": 0.08417357504367828, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:40.237259Z", "loop": 9013, "env_steps": 5538201599, "loss": 0.018041986972093582, "avg_return": 0.8600771427154541, "regret": 0.0010179381351917982, "entropy": 0.09088928997516632, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:41.091100Z", "loop": 9014, "env_steps": 5538815999, "loss": 0.016392646357417107, "avg_return": 0.8613436818122864, "regret": 0.0010179381351917982, "entropy": 0.08431302011013031, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:41.945392Z", "loop": 9015, "env_steps": 5539430399, "loss": 0.01643620990216732, "avg_return": 0.8603937029838562, "regret": 0.0010179381351917982, "entropy": 0.08448749035596848, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:42.798649Z", "loop": 9016, "env_steps": 5540044799, "loss": 0.01657715067267418, "avg_return": 0.8602874875068665, "regret": 0.0010179381351917982, "entropy": 0.08573200553655624, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:43.652754Z", "loop": 9017, "env_steps": 5540659199, "loss": 0.01765432022511959, "avg_return": 0.8623976707458496, "regret": 0.0010179381351917982, "entropy": 0.0863441675901413, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:44.507651Z", "loop": 9018, "env_steps": 5541273599, "loss": 0.016754452139139175, "avg_return": 0.863505482673645, "regret": 0.0010179381351917982, "entropy": 0.08442868292331696, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:45.361999Z", "loop": 9019, "env_steps": 5541887999, "loss": 0.01595654897391796, "avg_return": 0.8629842400550842, "regret": 0.0010179381351917982, "entropy": 0.08277204632759094, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:46.256212Z", "loop": 9020, "env_steps": 5542502399, "loss": 0.016307810321450233, "avg_return": 0.8633968234062195, "regret": 0.0005892078625038266, "entropy": 0.08440552651882172, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:47.111178Z", "loop": 9021, "env_steps": 5543116799, "loss": 0.016101250424981117, "avg_return": 0.8633883595466614, "regret": 0.0005892078625038266, "entropy": 0.08327312022447586, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:47.966268Z", "loop": 9022, "env_steps": 5543731199, "loss": 0.0152731416746974, "avg_return": 0.8636122941970825, "regret": 0.0005892078625038266, "entropy": 0.08085476607084274, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:48.822462Z", "loop": 9023, "env_steps": 5544345599, "loss": 0.015019631944596767, "avg_return": 0.8628237247467041, "regret": 0.0005892078625038266, "entropy": 0.08404266834259033, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:49.678000Z", "loop": 9024, "env_steps": 5544959999, "loss": 0.017663108184933662, "avg_return": 0.863449215888977, "regret": 0.0005892078625038266, "entropy": 0.0891168862581253, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:50.532950Z", "loop": 9025, "env_steps": 5545574399, "loss": 0.016192296519875526, "avg_return": 0.8635406494140625, "regret": 0.0005892078625038266, "entropy": 0.08476422727108002, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:51.388277Z", "loop": 9026, "env_steps": 5546188799, "loss": 0.01750098541378975, "avg_return": 0.8614369034767151, "regret": 0.0005892078625038266, "entropy": 0.09047798067331314, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:52.243302Z", "loop": 9027, "env_steps": 5546803199, "loss": 0.016970312222838402, "avg_return": 0.8634716272354126, "regret": 0.0005892078625038266, "entropy": 0.09060391038656235, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:53.098354Z", "loop": 9028, "env_steps": 5547417599, "loss": 0.017619015648961067, "avg_return": 0.8610485792160034, "regret": 0.0005892078625038266, "entropy": 0.0927504450082779, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:53.953847Z", "loop": 9029, "env_steps": 5548031999, "loss": 0.017993463203310966, "avg_return": 0.8632609248161316, "regret": 0.0005892078625038266, "entropy": 0.09371090680360794, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:54.851085Z", "loop": 9030, "env_steps": 5548646399, "loss": 0.01970933936536312, "avg_return": 0.8607603311538696, "regret": 0.0015445619355887175, "entropy": 0.09829011559486389, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:55.705589Z", "loop": 9031, "env_steps": 5549260799, "loss": 0.017528299242258072, "avg_return": 0.8604567646980286, "regret": 0.0015445619355887175, "entropy": 0.08969873189926147, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:56.560228Z", "loop": 9032, "env_steps": 5549875199, "loss": 0.019490515813231468, "avg_return": 0.8591013550758362, "regret": 0.0015445619355887175, "entropy": 0.09835502505302429, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:57.413927Z", "loop": 9033, "env_steps": 5550489599, "loss": 0.020663628354668617, "avg_return": 0.8544682264328003, "regret": 0.0015445619355887175, "entropy": 0.10496790707111359, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:58.268416Z", "loop": 9034, "env_steps": 5551103999, "loss": 0.020148344337940216, "avg_return": 0.8564765453338623, "regret": 0.0015445619355887175, "entropy": 0.10377779603004456, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:59.121592Z", "loop": 9035, "env_steps": 5551718399, "loss": 0.021526968106627464, "avg_return": 0.8556201457977295, "regret": 0.0015445619355887175, "entropy": 0.10386278480291367, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:32:59.975052Z", "loop": 9036, "env_steps": 5552332799, "loss": 0.02147877775132656, "avg_return": 0.858283281326294, "regret": 0.0015445619355887175, "entropy": 0.1059260219335556, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:00.829583Z", "loop": 9037, "env_steps": 5552947199, "loss": 0.020428486168384552, "avg_return": 0.861089289188385, "regret": 0.0015445619355887175, "entropy": 0.10094892978668213, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:01.684233Z", "loop": 9038, "env_steps": 5553561599, "loss": 0.01870250329375267, "avg_return": 0.8628084659576416, "regret": 0.0015445619355887175, "entropy": 0.09952348470687866, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:02.537940Z", "loop": 9039, "env_steps": 5554175999, "loss": 0.01718199998140335, "avg_return": 0.8616837859153748, "regret": 0.0015445619355887175, "entropy": 0.09297044575214386, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:03.433064Z", "loop": 9040, "env_steps": 5554790399, "loss": 0.018654590472579002, "avg_return": 0.8623504638671875, "regret": 0.0011765811359509826, "entropy": 0.09847213327884674, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:04.286848Z", "loop": 9041, "env_steps": 5555404799, "loss": 0.019499992951750755, "avg_return": 0.8617771863937378, "regret": 0.0011765811359509826, "entropy": 0.09792239964008331, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:05.141876Z", "loop": 9042, "env_steps": 5556019199, "loss": 0.020086035132408142, "avg_return": 0.8613499999046326, "regret": 0.0011765811359509826, "entropy": 0.1044936552643776, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:05.997734Z", "loop": 9043, "env_steps": 5556633599, "loss": 0.02063365839421749, "avg_return": 0.8607603311538696, "regret": 0.0011765811359509826, "entropy": 0.107062429189682, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:06.850700Z", "loop": 9044, "env_steps": 5557247999, "loss": 0.02122480981051922, "avg_return": 0.8575929999351501, "regret": 0.0011765811359509826, "entropy": 0.10504966229200363, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:07.702993Z", "loop": 9045, "env_steps": 5557862399, "loss": 0.02125953882932663, "avg_return": 0.8586661219596863, "regret": 0.0011765811359509826, "entropy": 0.10914072394371033, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:08.557472Z", "loop": 9046, "env_steps": 5558476799, "loss": 0.02045428194105625, "avg_return": 0.8583613038063049, "regret": 0.0011765811359509826, "entropy": 0.1014842689037323, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:09.411565Z", "loop": 9047, "env_steps": 5559091199, "loss": 0.017990976572036743, "avg_return": 0.8604730367660522, "regret": 0.0011765811359509826, "entropy": 0.09469849616289139, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:10.265127Z", "loop": 9048, "env_steps": 5559705599, "loss": 0.019106615334749222, "avg_return": 0.8618677258491516, "regret": 0.0011765811359509826, "entropy": 0.09402919560670853, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:11.119235Z", "loop": 9049, "env_steps": 5560319999, "loss": 0.016575351357460022, "avg_return": 0.8626728653907776, "regret": 0.0011765811359509826, "entropy": 0.08734006434679031, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:12.013936Z", "loop": 9050, "env_steps": 5560934399, "loss": 0.016505099833011627, "avg_return": 0.863758385181427, "regret": 0.0003970950492657721, "entropy": 0.085691437125206, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:12.869289Z", "loop": 9051, "env_steps": 5561548799, "loss": 0.016988055780529976, "avg_return": 0.8628676533699036, "regret": 0.0003970950492657721, "entropy": 0.08677767217159271, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:13.723881Z", "loop": 9052, "env_steps": 5562163199, "loss": 0.015602621249854565, "avg_return": 0.8636153340339661, "regret": 0.0003970950492657721, "entropy": 0.08497775346040726, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:14.577611Z", "loop": 9053, "env_steps": 5562777599, "loss": 0.015254663303494453, "avg_return": 0.8637358546257019, "regret": 0.0003970950492657721, "entropy": 0.08324463665485382, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:15.431999Z", "loop": 9054, "env_steps": 5563391999, "loss": 0.01604064553976059, "avg_return": 0.8635048866271973, "regret": 0.0003970950492657721, "entropy": 0.08678187429904938, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:16.286321Z", "loop": 9055, "env_steps": 5564006399, "loss": 0.015627017244696617, "avg_return": 0.8644086718559265, "regret": 0.0003970950492657721, "entropy": 0.0834122896194458, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:17.140270Z", "loop": 9056, "env_steps": 5564620799, "loss": 0.014820719137787819, "avg_return": 0.8637319207191467, "regret": 0.0003970950492657721, "entropy": 0.08242183178663254, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:17.994415Z", "loop": 9057, "env_steps": 5565235199, "loss": 0.015530248172581196, "avg_return": 0.8628777265548706, "regret": 0.0003970950492657721, "entropy": 0.08392149955034256, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:18.848351Z", "loop": 9058, "env_steps": 5565849599, "loss": 0.014946669340133667, "avg_return": 0.8625338077545166, "regret": 0.0003970950492657721, "entropy": 0.08485147356987, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:19.701692Z", "loop": 9059, "env_steps": 5566463999, "loss": 0.01613381691277027, "avg_return": 0.8609851002693176, "regret": 0.0003970950492657721, "entropy": 0.08620575815439224, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:20.595146Z", "loop": 9060, "env_steps": 5567078399, "loss": 0.01657710038125515, "avg_return": 0.8615006804466248, "regret": 0.0014069083845242858, "entropy": 0.08661041408777237, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:21.450070Z", "loop": 9061, "env_steps": 5567692799, "loss": 0.01809859089553356, "avg_return": 0.8621954321861267, "regret": 0.0014069083845242858, "entropy": 0.09468104690313339, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:22.304162Z", "loop": 9062, "env_steps": 5568307199, "loss": 0.016884861513972282, "avg_return": 0.8611592054367065, "regret": 0.0014069083845242858, "entropy": 0.08638254553079605, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:23.157646Z", "loop": 9063, "env_steps": 5568921599, "loss": 0.017761051654815674, "avg_return": 0.8601800799369812, "regret": 0.0014069083845242858, "entropy": 0.09041273593902588, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:24.012610Z", "loop": 9064, "env_steps": 5569535999, "loss": 0.015873385593295097, "avg_return": 0.860385537147522, "regret": 0.0014069083845242858, "entropy": 0.08466733992099762, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:24.867203Z", "loop": 9065, "env_steps": 5570150399, "loss": 0.017765164375305176, "avg_return": 0.8607210516929626, "regret": 0.0014069083845242858, "entropy": 0.09345940500497818, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:25.720971Z", "loop": 9066, "env_steps": 5570764799, "loss": 0.017565283924341202, "avg_return": 0.8594421744346619, "regret": 0.0014069083845242858, "entropy": 0.09420683979988098, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:26.573634Z", "loop": 9067, "env_steps": 5571379199, "loss": 0.018155261874198914, "avg_return": 0.8606632947921753, "regret": 0.0014069083845242858, "entropy": 0.09600452333688736, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:27.426544Z", "loop": 9068, "env_steps": 5571993599, "loss": 0.019974328577518463, "avg_return": 0.8607944846153259, "regret": 0.0014069083845242858, "entropy": 0.09748509526252747, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:28.280805Z", "loop": 9069, "env_steps": 5572607999, "loss": 0.020510435104370117, "avg_return": 0.8596762418746948, "regret": 0.0014069083845242858, "entropy": 0.1042635515332222, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:29.174798Z", "loop": 9070, "env_steps": 5573222399, "loss": 0.01921055279672146, "avg_return": 0.8599585294723511, "regret": 0.0044320691376924515, "entropy": 0.09632924944162369, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:30.029185Z", "loop": 9071, "env_steps": 5573836799, "loss": 0.020148752257227898, "avg_return": 0.8599802851676941, "regret": 0.0044320691376924515, "entropy": 0.09894602745771408, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:30.883218Z", "loop": 9072, "env_steps": 5574451199, "loss": 0.020728835836052895, "avg_return": 0.8590624332427979, "regret": 0.0044320691376924515, "entropy": 0.10450667142868042, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:31.737772Z", "loop": 9073, "env_steps": 5575065599, "loss": 0.019444052129983902, "avg_return": 0.8603340983390808, "regret": 0.0044320691376924515, "entropy": 0.09977830946445465, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:32.591727Z", "loop": 9074, "env_steps": 5575679999, "loss": 0.018886523321270943, "avg_return": 0.8611075282096863, "regret": 0.0044320691376924515, "entropy": 0.0962887778878212, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:33.445391Z", "loop": 9075, "env_steps": 5576294399, "loss": 0.019928863272070885, "avg_return": 0.859926700592041, "regret": 0.0044320691376924515, "entropy": 0.10016704350709915, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:34.299456Z", "loop": 9076, "env_steps": 5576908799, "loss": 0.01863204501569271, "avg_return": 0.8612850904464722, "regret": 0.0044320691376924515, "entropy": 0.09632664918899536, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:35.153440Z", "loop": 9077, "env_steps": 5577523199, "loss": 0.019534427672624588, "avg_return": 0.8609480261802673, "regret": 0.0044320691376924515, "entropy": 0.1001819521188736, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:36.008246Z", "loop": 9078, "env_steps": 5578137599, "loss": 0.01915944181382656, "avg_return": 0.8602186441421509, "regret": 0.0044320691376924515, "entropy": 0.09290879219770432, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:36.862012Z", "loop": 9079, "env_steps": 5578751999, "loss": 0.020422056317329407, "avg_return": 0.8594149947166443, "regret": 0.0044320691376924515, "entropy": 0.09729661792516708, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:37.764586Z", "loop": 9080, "env_steps": 5579366399, "loss": 0.019030539318919182, "avg_return": 0.8610821962356567, "regret": 0.0032860995270311832, "entropy": 0.09773992747068405, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:38.619798Z", "loop": 9081, "env_steps": 5579980799, "loss": 0.020454559475183487, "avg_return": 0.860439658164978, "regret": 0.0032860995270311832, "entropy": 0.10327426344156265, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:39.473650Z", "loop": 9082, "env_steps": 5580595199, "loss": 0.02035258337855339, "avg_return": 0.8609873652458191, "regret": 0.0032860995270311832, "entropy": 0.10182004421949387, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:40.329139Z", "loop": 9083, "env_steps": 5581209599, "loss": 0.02020169422030449, "avg_return": 0.8595348596572876, "regret": 0.0032860995270311832, "entropy": 0.09831976890563965, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:41.184325Z", "loop": 9084, "env_steps": 5581823999, "loss": 0.019549913704395294, "avg_return": 0.8582600951194763, "regret": 0.0032860995270311832, "entropy": 0.09589281678199768, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:42.038112Z", "loop": 9085, "env_steps": 5582438399, "loss": 0.020618731155991554, "avg_return": 0.8604207634925842, "regret": 0.0032860995270311832, "entropy": 0.10247330367565155, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:42.892967Z", "loop": 9086, "env_steps": 5583052799, "loss": 0.019394516944885254, "avg_return": 0.8610894083976746, "regret": 0.0032860995270311832, "entropy": 0.09694138169288635, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:43.746767Z", "loop": 9087, "env_steps": 5583667199, "loss": 0.020792648196220398, "avg_return": 0.8613121509552002, "regret": 0.0032860995270311832, "entropy": 0.10122364014387131, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:44.601414Z", "loop": 9088, "env_steps": 5584281599, "loss": 0.019425641745328903, "avg_return": 0.8613802194595337, "regret": 0.0032860995270311832, "entropy": 0.09754326939582825, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:45.454212Z", "loop": 9089, "env_steps": 5584895999, "loss": 0.018925277516245842, "avg_return": 0.863359272480011, "regret": 0.0032860995270311832, "entropy": 0.09463942050933838, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:46.349100Z", "loop": 9090, "env_steps": 5585510399, "loss": 0.01924123987555504, "avg_return": 0.8623694181442261, "regret": 0.0011681286850944161, "entropy": 0.09777727723121643, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:47.204908Z", "loop": 9091, "env_steps": 5586124799, "loss": 0.018200941383838654, "avg_return": 0.8627679944038391, "regret": 0.0011681286850944161, "entropy": 0.09317050129175186, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:48.059496Z", "loop": 9092, "env_steps": 5586739199, "loss": 0.01797695830464363, "avg_return": 0.8621185421943665, "regret": 0.0011681286850944161, "entropy": 0.09163007140159607, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:48.912602Z", "loop": 9093, "env_steps": 5587353599, "loss": 0.01910557597875595, "avg_return": 0.863129198551178, "regret": 0.0011681286850944161, "entropy": 0.09475316107273102, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:49.766869Z", "loop": 9094, "env_steps": 5587967999, "loss": 0.015816988423466682, "avg_return": 0.8630553483963013, "regret": 0.0011681286850944161, "entropy": 0.08750206232070923, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:50.622375Z", "loop": 9095, "env_steps": 5588582399, "loss": 0.017963264137506485, "avg_return": 0.8632407784461975, "regret": 0.0011681286850944161, "entropy": 0.090978242456913, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:51.478108Z", "loop": 9096, "env_steps": 5589196799, "loss": 0.018695300444960594, "avg_return": 0.8639960885047913, "regret": 0.0011681286850944161, "entropy": 0.09514126926660538, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:52.331956Z", "loop": 9097, "env_steps": 5589811199, "loss": 0.019256750121712685, "avg_return": 0.8631581664085388, "regret": 0.0011681286850944161, "entropy": 0.09609530121088028, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:53.185214Z", "loop": 9098, "env_steps": 5590425599, "loss": 0.01977664604783058, "avg_return": 0.8629946112632751, "regret": 0.0011681286850944161, "entropy": 0.09932416677474976, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:54.038903Z", "loop": 9099, "env_steps": 5591039999, "loss": 0.018197795376181602, "avg_return": 0.8635823726654053, "regret": 0.0011681286850944161, "entropy": 0.09183737635612488, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:54.933606Z", "loop": 9100, "env_steps": 5591654399, "loss": 0.018717901781201363, "avg_return": 0.8621905446052551, "regret": 0.0008159191347658634, "entropy": 0.09375990927219391, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:55.788921Z", "loop": 9101, "env_steps": 5592268799, "loss": 0.018314393237233162, "avg_return": 0.8627057075500488, "regret": 0.0008159191347658634, "entropy": 0.0976332500576973, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:56.643746Z", "loop": 9102, "env_steps": 5592883199, "loss": 0.01883094199001789, "avg_return": 0.8629142642021179, "regret": 0.0008159191347658634, "entropy": 0.09640970826148987, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:57.498155Z", "loop": 9103, "env_steps": 5593497599, "loss": 0.020933516323566437, "avg_return": 0.862070620059967, "regret": 0.0008159191347658634, "entropy": 0.10470353066921234, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:58.353779Z", "loop": 9104, "env_steps": 5594111999, "loss": 0.01987522654235363, "avg_return": 0.8608553409576416, "regret": 0.0008159191347658634, "entropy": 0.10390713065862656, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:33:59.208465Z", "loop": 9105, "env_steps": 5594726399, "loss": 0.020840508863329887, "avg_return": 0.8598629832267761, "regret": 0.0008159191347658634, "entropy": 0.10987263172864914, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:00.063407Z", "loop": 9106, "env_steps": 5595340799, "loss": 0.02031243033707142, "avg_return": 0.862528920173645, "regret": 0.0008159191347658634, "entropy": 0.10715065896511078, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:00.918728Z", "loop": 9107, "env_steps": 5595955199, "loss": 0.020072398707270622, "avg_return": 0.8606386780738831, "regret": 0.0008159191347658634, "entropy": 0.1047866940498352, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:01.774243Z", "loop": 9108, "env_steps": 5596569599, "loss": 0.021157970651984215, "avg_return": 0.8611831068992615, "regret": 0.0008159191347658634, "entropy": 0.11272342503070831, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:02.628156Z", "loop": 9109, "env_steps": 5597183999, "loss": 0.021173615008592606, "avg_return": 0.8618830442428589, "regret": 0.0008159191347658634, "entropy": 0.11110804229974747, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:03.522510Z", "loop": 9110, "env_steps": 5597798399, "loss": 0.0194681528955698, "avg_return": 0.8623095750808716, "regret": 0.0011593988165259361, "entropy": 0.1042325422167778, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:04.377503Z", "loop": 9111, "env_steps": 5598412799, "loss": 0.020085319876670837, "avg_return": 0.8624001145362854, "regret": 0.0011593988165259361, "entropy": 0.10476920008659363, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:05.231168Z", "loop": 9112, "env_steps": 5599027199, "loss": 0.02021140605211258, "avg_return": 0.8631228804588318, "regret": 0.0011593988165259361, "entropy": 0.10308428108692169, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:06.085377Z", "loop": 9113, "env_steps": 5599641599, "loss": 0.020395081490278244, "avg_return": 0.8626587390899658, "regret": 0.0011593988165259361, "entropy": 0.10492228716611862, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:06.939303Z", "loop": 9114, "env_steps": 5600255999, "loss": 0.019661372527480125, "avg_return": 0.8627665638923645, "regret": 0.0011593988165259361, "entropy": 0.10015428066253662, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:07.794216Z", "loop": 9115, "env_steps": 5600870399, "loss": 0.01871347986161709, "avg_return": 0.8640735149383545, "regret": 0.0011593988165259361, "entropy": 0.09607214480638504, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:08.647700Z", "loop": 9116, "env_steps": 5601484799, "loss": 0.01834852434694767, "avg_return": 0.8627196550369263, "regret": 0.0011593988165259361, "entropy": 0.0949324443936348, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:09.501200Z", "loop": 9117, "env_steps": 5602099199, "loss": 0.01797660067677498, "avg_return": 0.8616902828216553, "regret": 0.0011593988165259361, "entropy": 0.09546200931072235, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:10.355098Z", "loop": 9118, "env_steps": 5602713599, "loss": 0.018136726692318916, "avg_return": 0.8630039691925049, "regret": 0.0011593988165259361, "entropy": 0.09285861998796463, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:11.209494Z", "loop": 9119, "env_steps": 5603327999, "loss": 0.017972087487578392, "avg_return": 0.8621720671653748, "regret": 0.0011593988165259361, "entropy": 0.09186538308858871, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:12.103688Z", "loop": 9120, "env_steps": 5603942399, "loss": 0.019184380769729614, "avg_return": 0.8627378344535828, "regret": 0.0011438875226303935, "entropy": 0.09885222464799881, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:12.957105Z", "loop": 9121, "env_steps": 5604556799, "loss": 0.019488928839564323, "avg_return": 0.8628466129302979, "regret": 0.0011438875226303935, "entropy": 0.10080026835203171, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:13.812067Z", "loop": 9122, "env_steps": 5605171199, "loss": 0.019958456978201866, "avg_return": 0.8609369397163391, "regret": 0.0011438875226303935, "entropy": 0.10008105635643005, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:14.666273Z", "loop": 9123, "env_steps": 5605785599, "loss": 0.02010519616305828, "avg_return": 0.8621185421943665, "regret": 0.0011438875226303935, "entropy": 0.09985972195863724, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:15.519850Z", "loop": 9124, "env_steps": 5606399999, "loss": 0.0189806055277586, "avg_return": 0.8602645993232727, "regret": 0.0011438875226303935, "entropy": 0.09601930528879166, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:16.373385Z", "loop": 9125, "env_steps": 5607014399, "loss": 0.01950211636722088, "avg_return": 0.8604482412338257, "regret": 0.0011438875226303935, "entropy": 0.09985422343015671, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:17.227040Z", "loop": 9126, "env_steps": 5607628799, "loss": 0.019339866936206818, "avg_return": 0.860344648361206, "regret": 0.0011438875226303935, "entropy": 0.10144063830375671, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:18.080719Z", "loop": 9127, "env_steps": 5608243199, "loss": 0.01968316361308098, "avg_return": 0.8604020476341248, "regret": 0.0011438875226303935, "entropy": 0.10101602971553802, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:18.934318Z", "loop": 9128, "env_steps": 5608857599, "loss": 0.01864580623805523, "avg_return": 0.8619417548179626, "regret": 0.0011438875226303935, "entropy": 0.09829621016979218, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:19.788169Z", "loop": 9129, "env_steps": 5609471999, "loss": 0.01874389313161373, "avg_return": 0.8623730540275574, "regret": 0.0011438875226303935, "entropy": 0.09446173161268234, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:20.684066Z", "loop": 9130, "env_steps": 5610086399, "loss": 0.017917310819029808, "avg_return": 0.8619484901428223, "regret": 0.0009920955635607243, "entropy": 0.09491124004125595, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:21.539077Z", "loop": 9131, "env_steps": 5610700799, "loss": 0.018686240538954735, "avg_return": 0.8624349236488342, "regret": 0.0009920955635607243, "entropy": 0.09213413298130035, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:22.393335Z", "loop": 9132, "env_steps": 5611315199, "loss": 0.017448728904128075, "avg_return": 0.8618041276931763, "regret": 0.0009920955635607243, "entropy": 0.08798591792583466, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:23.247874Z", "loop": 9133, "env_steps": 5611929599, "loss": 0.016769710928201675, "avg_return": 0.8622130751609802, "regret": 0.0009920955635607243, "entropy": 0.08542992919683456, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:24.100646Z", "loop": 9134, "env_steps": 5612543999, "loss": 0.017893455922603607, "avg_return": 0.8634006977081299, "regret": 0.0009920955635607243, "entropy": 0.09017614275217056, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:24.954082Z", "loop": 9135, "env_steps": 5613158399, "loss": 0.016957221552729607, "avg_return": 0.862819254398346, "regret": 0.0009920955635607243, "entropy": 0.08896699547767639, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:25.808161Z", "loop": 9136, "env_steps": 5613772799, "loss": 0.019638268277049065, "avg_return": 0.861777663230896, "regret": 0.0009920955635607243, "entropy": 0.09795831888914108, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:26.663721Z", "loop": 9137, "env_steps": 5614387199, "loss": 0.019130127504467964, "avg_return": 0.8629571795463562, "regret": 0.0009920955635607243, "entropy": 0.09300623089075089, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:27.517419Z", "loop": 9138, "env_steps": 5615001599, "loss": 0.020050710067152977, "avg_return": 0.8628328442573547, "regret": 0.0009920955635607243, "entropy": 0.09684914350509644, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:28.372982Z", "loop": 9139, "env_steps": 5615615999, "loss": 0.01926867477595806, "avg_return": 0.862554132938385, "regret": 0.0009920955635607243, "entropy": 0.09693419188261032, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:29.269097Z", "loop": 9140, "env_steps": 5616230399, "loss": 0.018971648067235947, "avg_return": 0.8630608320236206, "regret": 0.0006376034580171108, "entropy": 0.09538692235946655, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:30.123867Z", "loop": 9141, "env_steps": 5616844799, "loss": 0.020566267892718315, "avg_return": 0.8612404465675354, "regret": 0.0006376034580171108, "entropy": 0.10056863725185394, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:30.978007Z", "loop": 9142, "env_steps": 5617459199, "loss": 0.019283631816506386, "avg_return": 0.862703263759613, "regret": 0.0006376034580171108, "entropy": 0.09960407018661499, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:31.832386Z", "loop": 9143, "env_steps": 5618073599, "loss": 0.019150054082274437, "avg_return": 0.8623008131980896, "regret": 0.0006376034580171108, "entropy": 0.09304790198802948, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:32.685685Z", "loop": 9144, "env_steps": 5618687999, "loss": 0.018413837999105453, "avg_return": 0.8645456433296204, "regret": 0.0006376034580171108, "entropy": 0.09658791869878769, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:33.539987Z", "loop": 9145, "env_steps": 5619302399, "loss": 0.019474118947982788, "avg_return": 0.863159716129303, "regret": 0.0006376034580171108, "entropy": 0.10102745145559311, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:34.394694Z", "loop": 9146, "env_steps": 5619916799, "loss": 0.01879696361720562, "avg_return": 0.8622185587882996, "regret": 0.0006376034580171108, "entropy": 0.09451501816511154, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:35.248826Z", "loop": 9147, "env_steps": 5620531199, "loss": 0.017163388431072235, "avg_return": 0.8633571863174438, "regret": 0.0006376034580171108, "entropy": 0.09225273132324219, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:36.102747Z", "loop": 9148, "env_steps": 5621145599, "loss": 0.017369985580444336, "avg_return": 0.8623419404029846, "regret": 0.0006376034580171108, "entropy": 0.09086764603853226, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:36.956227Z", "loop": 9149, "env_steps": 5621759999, "loss": 0.018847404047846794, "avg_return": 0.8617905974388123, "regret": 0.0006376034580171108, "entropy": 0.09682879596948624, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:37.852002Z", "loop": 9150, "env_steps": 5622374399, "loss": 0.017483385279774666, "avg_return": 0.8616053462028503, "regret": 0.0009361159172840416, "entropy": 0.0907597690820694, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:38.705776Z", "loop": 9151, "env_steps": 5622988799, "loss": 0.016801370307803154, "avg_return": 0.8631505370140076, "regret": 0.0009361159172840416, "entropy": 0.08870440721511841, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:39.558948Z", "loop": 9152, "env_steps": 5623603199, "loss": 0.016863582655787468, "avg_return": 0.8632516860961914, "regret": 0.0009361159172840416, "entropy": 0.08707760274410248, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:40.412824Z", "loop": 9153, "env_steps": 5624217599, "loss": 0.017412709072232246, "avg_return": 0.8632513880729675, "regret": 0.0009361159172840416, "entropy": 0.08830199390649796, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:41.267766Z", "loop": 9154, "env_steps": 5624831999, "loss": 0.018584752455353737, "avg_return": 0.8627716302871704, "regret": 0.0009361159172840416, "entropy": 0.09086771309375763, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:42.122440Z", "loop": 9155, "env_steps": 5625446399, "loss": 0.01886053942143917, "avg_return": 0.8628892302513123, "regret": 0.0009361159172840416, "entropy": 0.0918402373790741, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:42.976271Z", "loop": 9156, "env_steps": 5626060799, "loss": 0.018801210448145866, "avg_return": 0.8627175092697144, "regret": 0.0009361159172840416, "entropy": 0.09239780902862549, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:43.830139Z", "loop": 9157, "env_steps": 5626675199, "loss": 0.018187979236245155, "avg_return": 0.8616377711296082, "regret": 0.0009361159172840416, "entropy": 0.09643442183732986, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:44.684354Z", "loop": 9158, "env_steps": 5627289599, "loss": 0.018134964630007744, "avg_return": 0.8615175485610962, "regret": 0.0009361159172840416, "entropy": 0.09738794714212418, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:45.538157Z", "loop": 9159, "env_steps": 5627903999, "loss": 0.01875423453748226, "avg_return": 0.8613839149475098, "regret": 0.0009361159172840416, "entropy": 0.09356730431318283, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:46.434020Z", "loop": 9160, "env_steps": 5628518399, "loss": 0.017143940553069115, "avg_return": 0.8602205514907837, "regret": 0.0027367223519831896, "entropy": 0.09512393921613693, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:47.287840Z", "loop": 9161, "env_steps": 5629132799, "loss": 0.015847211703658104, "avg_return": 0.860884428024292, "regret": 0.0027367223519831896, "entropy": 0.0894181951880455, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:48.141925Z", "loop": 9162, "env_steps": 5629747199, "loss": 0.01829150691628456, "avg_return": 0.860565185546875, "regret": 0.0027367223519831896, "entropy": 0.09706620126962662, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:48.995364Z", "loop": 9163, "env_steps": 5630361599, "loss": 0.018654899671673775, "avg_return": 0.8598242402076721, "regret": 0.0027367223519831896, "entropy": 0.09825868904590607, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:49.849830Z", "loop": 9164, "env_steps": 5630975999, "loss": 0.019981689751148224, "avg_return": 0.8583501577377319, "regret": 0.0027367223519831896, "entropy": 0.10269366949796677, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:50.703812Z", "loop": 9165, "env_steps": 5631590399, "loss": 0.020440032705664635, "avg_return": 0.8582390546798706, "regret": 0.0027367223519831896, "entropy": 0.10598932206630707, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:51.557258Z", "loop": 9166, "env_steps": 5632204799, "loss": 0.02082393318414688, "avg_return": 0.8594967722892761, "regret": 0.0027367223519831896, "entropy": 0.1071561947464943, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:52.410853Z", "loop": 9167, "env_steps": 5632819199, "loss": 0.020021244883537292, "avg_return": 0.8602471947669983, "regret": 0.0027367223519831896, "entropy": 0.10439835488796234, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:53.264814Z", "loop": 9168, "env_steps": 5633433599, "loss": 0.017679324373602867, "avg_return": 0.8613619208335876, "regret": 0.0027367223519831896, "entropy": 0.0957358181476593, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:54.118897Z", "loop": 9169, "env_steps": 5634047999, "loss": 0.01753939315676689, "avg_return": 0.8605718016624451, "regret": 0.0027367223519831896, "entropy": 0.09388339519500732, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:55.014229Z", "loop": 9170, "env_steps": 5634662399, "loss": 0.017438234761357307, "avg_return": 0.8622571229934692, "regret": 0.0013179212110117078, "entropy": 0.08786691725254059, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:55.868785Z", "loop": 9171, "env_steps": 5635276799, "loss": 0.017416637390851974, "avg_return": 0.8608115911483765, "regret": 0.0013179212110117078, "entropy": 0.09239709377288818, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:56.723562Z", "loop": 9172, "env_steps": 5635891199, "loss": 0.018765797838568687, "avg_return": 0.8631899952888489, "regret": 0.0013179212110117078, "entropy": 0.09429876506328583, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:57.578745Z", "loop": 9173, "env_steps": 5636505599, "loss": 0.018809305503964424, "avg_return": 0.8624213933944702, "regret": 0.0013179212110117078, "entropy": 0.09340011328458786, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:58.434213Z", "loop": 9174, "env_steps": 5637119999, "loss": 0.019388576969504356, "avg_return": 0.8636124730110168, "regret": 0.0013179212110117078, "entropy": 0.09692578762769699, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:34:59.289839Z", "loop": 9175, "env_steps": 5637734399, "loss": 0.01894509792327881, "avg_return": 0.8631421327590942, "regret": 0.0013179212110117078, "entropy": 0.09775751084089279, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:00.145018Z", "loop": 9176, "env_steps": 5638348799, "loss": 0.018773121759295464, "avg_return": 0.8618794679641724, "regret": 0.0013179212110117078, "entropy": 0.09608838707208633, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:01.000148Z", "loop": 9177, "env_steps": 5638963199, "loss": 0.01801520399749279, "avg_return": 0.8621858954429626, "regret": 0.0013179212110117078, "entropy": 0.0918465331196785, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:01.856432Z", "loop": 9178, "env_steps": 5639577599, "loss": 0.018447834998369217, "avg_return": 0.8629435300827026, "regret": 0.0013179212110117078, "entropy": 0.09570050239562988, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:02.711094Z", "loop": 9179, "env_steps": 5640191999, "loss": 0.01717325858771801, "avg_return": 0.8620341420173645, "regret": 0.0013179212110117078, "entropy": 0.09141750633716583, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:03.605237Z", "loop": 9180, "env_steps": 5640806399, "loss": 0.017033135518431664, "avg_return": 0.8623136878013611, "regret": 0.0010821755276992917, "entropy": 0.09307599812746048, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:04.459692Z", "loop": 9181, "env_steps": 5641420799, "loss": 0.017725126817822456, "avg_return": 0.8632729053497314, "regret": 0.0010821755276992917, "entropy": 0.0955875888466835, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:05.315107Z", "loop": 9182, "env_steps": 5642035199, "loss": 0.018520044162869453, "avg_return": 0.8618711829185486, "regret": 0.0010821755276992917, "entropy": 0.09847946465015411, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:06.168905Z", "loop": 9183, "env_steps": 5642649599, "loss": 0.019964013248682022, "avg_return": 0.8611481189727783, "regret": 0.0010821755276992917, "entropy": 0.1041877493262291, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:07.023360Z", "loop": 9184, "env_steps": 5643263999, "loss": 0.023273726925253868, "avg_return": 0.8608331680297852, "regret": 0.0010821755276992917, "entropy": 0.11792325228452682, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:07.876878Z", "loop": 9185, "env_steps": 5643878399, "loss": 0.02893245592713356, "avg_return": 0.8583658933639526, "regret": 0.0010821755276992917, "entropy": 0.14769132435321808, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:08.731290Z", "loop": 9186, "env_steps": 5644492799, "loss": 0.03262326493859291, "avg_return": 0.8591780662536621, "regret": 0.0010821755276992917, "entropy": 0.16845545172691345, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:09.584808Z", "loop": 9187, "env_steps": 5645107199, "loss": 0.03174765035510063, "avg_return": 0.8565541505813599, "regret": 0.0010821755276992917, "entropy": 0.16501650214195251, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:10.438859Z", "loop": 9188, "env_steps": 5645721599, "loss": 0.03551030158996582, "avg_return": 0.8575901389122009, "regret": 0.0010821755276992917, "entropy": 0.1744365245103836, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:11.293432Z", "loop": 9189, "env_steps": 5646335999, "loss": 0.031457073986530304, "avg_return": 0.8590323328971863, "regret": 0.0010821755276992917, "entropy": 0.15646716952323914, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:12.188189Z", "loop": 9190, "env_steps": 5646950399, "loss": 0.029049590229988098, "avg_return": 0.8604767322540283, "regret": 0.002765282057225704, "entropy": 0.14487867057323456, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:13.042824Z", "loop": 9191, "env_steps": 5647564799, "loss": 0.0264606773853302, "avg_return": 0.8617272973060608, "regret": 0.002765282057225704, "entropy": 0.13541384041309357, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:13.897109Z", "loop": 9192, "env_steps": 5648179199, "loss": 0.025039801374077797, "avg_return": 0.8614508509635925, "regret": 0.002765282057225704, "entropy": 0.1318906992673874, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:14.750713Z", "loop": 9193, "env_steps": 5648793599, "loss": 0.02684519998729229, "avg_return": 0.8628197312355042, "regret": 0.002765282057225704, "entropy": 0.13096487522125244, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:15.605645Z", "loop": 9194, "env_steps": 5649407999, "loss": 0.026880919933319092, "avg_return": 0.8627031445503235, "regret": 0.002765282057225704, "entropy": 0.1290494203567505, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:16.460760Z", "loop": 9195, "env_steps": 5650022399, "loss": 0.02503548562526703, "avg_return": 0.863074541091919, "regret": 0.002765282057225704, "entropy": 0.1258859932422638, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:17.314607Z", "loop": 9196, "env_steps": 5650636799, "loss": 0.026309652253985405, "avg_return": 0.8627848625183105, "regret": 0.002765282057225704, "entropy": 0.13032706081867218, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:18.168209Z", "loop": 9197, "env_steps": 5651251199, "loss": 0.0244820024818182, "avg_return": 0.8615331053733826, "regret": 0.002765282057225704, "entropy": 0.12329664826393127, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:19.022706Z", "loop": 9198, "env_steps": 5651865599, "loss": 0.025983864441514015, "avg_return": 0.8613914251327515, "regret": 0.002765282057225704, "entropy": 0.12996619939804077, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:19.876559Z", "loop": 9199, "env_steps": 5652479999, "loss": 0.025014584884047508, "avg_return": 0.8630884289741516, "regret": 0.002765282057225704, "entropy": 0.12405027449131012, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:20.770590Z", "loop": 9200, "env_steps": 5653094399, "loss": 0.02417599968612194, "avg_return": 0.8629629611968994, "regret": 0.0014682257315143943, "entropy": 0.11803936213254929, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:21.624789Z", "loop": 9201, "env_steps": 5653708799, "loss": 0.02210972271859646, "avg_return": 0.8629076480865479, "regret": 0.0014682257315143943, "entropy": 0.1124810203909874, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:22.478287Z", "loop": 9202, "env_steps": 5654323199, "loss": 0.0215053241699934, "avg_return": 0.8626015186309814, "regret": 0.0014682257315143943, "entropy": 0.10874715447425842, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:23.331317Z", "loop": 9203, "env_steps": 5654937599, "loss": 0.0226479172706604, "avg_return": 0.8625770211219788, "regret": 0.0014682257315143943, "entropy": 0.10959567129611969, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:24.185501Z", "loop": 9204, "env_steps": 5655551999, "loss": 0.02226906456053257, "avg_return": 0.8615155220031738, "regret": 0.0014682257315143943, "entropy": 0.11000938713550568, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:25.039710Z", "loop": 9205, "env_steps": 5656166399, "loss": 0.020499931648373604, "avg_return": 0.8621166348457336, "regret": 0.0014682257315143943, "entropy": 0.105594702064991, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:25.894270Z", "loop": 9206, "env_steps": 5656780799, "loss": 0.021536989137530327, "avg_return": 0.862106442451477, "regret": 0.0014682257315143943, "entropy": 0.1113181933760643, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:26.747831Z", "loop": 9207, "env_steps": 5657395199, "loss": 0.02101811207830906, "avg_return": 0.8615830540657043, "regret": 0.0014682257315143943, "entropy": 0.10586225986480713, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:27.601662Z", "loop": 9208, "env_steps": 5658009599, "loss": 0.021788902580738068, "avg_return": 0.8614478707313538, "regret": 0.0014682257315143943, "entropy": 0.10926882922649384, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:28.457032Z", "loop": 9209, "env_steps": 5658623999, "loss": 0.020980043336749077, "avg_return": 0.8609892129898071, "regret": 0.0014682257315143943, "entropy": 0.10986869037151337, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:29.351834Z", "loop": 9210, "env_steps": 5659238399, "loss": 0.021719930693507195, "avg_return": 0.8614398241043091, "regret": 0.002690621418878436, "entropy": 0.10562118142843246, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:30.204880Z", "loop": 9211, "env_steps": 5659852799, "loss": 0.020191507413983345, "avg_return": 0.8607147336006165, "regret": 0.002690621418878436, "entropy": 0.10700155049562454, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:31.058895Z", "loop": 9212, "env_steps": 5660467199, "loss": 0.019790776073932648, "avg_return": 0.861336886882782, "regret": 0.002690621418878436, "entropy": 0.10328419506549835, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:31.912674Z", "loop": 9213, "env_steps": 5661081599, "loss": 0.019999373704195023, "avg_return": 0.862399697303772, "regret": 0.002690621418878436, "entropy": 0.10508701205253601, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:32.766959Z", "loop": 9214, "env_steps": 5661695999, "loss": 0.02148330584168434, "avg_return": 0.8608875870704651, "regret": 0.002690621418878436, "entropy": 0.10750948637723923, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:33.620653Z", "loop": 9215, "env_steps": 5662310399, "loss": 0.020048590376973152, "avg_return": 0.8611438274383545, "regret": 0.002690621418878436, "entropy": 0.10819925367832184, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:34.474649Z", "loop": 9216, "env_steps": 5662924799, "loss": 0.020487524569034576, "avg_return": 0.8611019253730774, "regret": 0.002690621418878436, "entropy": 0.10688100755214691, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:35.329445Z", "loop": 9217, "env_steps": 5663539199, "loss": 0.02036762423813343, "avg_return": 0.8615887761116028, "regret": 0.002690621418878436, "entropy": 0.10404817014932632, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:36.183330Z", "loop": 9218, "env_steps": 5664153599, "loss": 0.01915864646434784, "avg_return": 0.8620790839195251, "regret": 0.002690621418878436, "entropy": 0.10040976852178574, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:37.038145Z", "loop": 9219, "env_steps": 5664767999, "loss": 0.019472965970635414, "avg_return": 0.8626328706741333, "regret": 0.002690621418878436, "entropy": 0.09950201213359833, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:37.932275Z", "loop": 9220, "env_steps": 5665382399, "loss": 0.018509646877646446, "avg_return": 0.8617230653762817, "regret": 0.0012706094421446323, "entropy": 0.09774196147918701, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:38.785922Z", "loop": 9221, "env_steps": 5665996799, "loss": 0.019194720312952995, "avg_return": 0.8619443774223328, "regret": 0.0012706094421446323, "entropy": 0.09944543987512589, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:39.639806Z", "loop": 9222, "env_steps": 5666611199, "loss": 0.01991794817149639, "avg_return": 0.8626243472099304, "regret": 0.0012706094421446323, "entropy": 0.09974268078804016, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:40.494384Z", "loop": 9223, "env_steps": 5667225599, "loss": 0.01917331852018833, "avg_return": 0.861815333366394, "regret": 0.0012706094421446323, "entropy": 0.10227760672569275, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:41.348910Z", "loop": 9224, "env_steps": 5667839999, "loss": 0.0194892268627882, "avg_return": 0.862623393535614, "regret": 0.0012706094421446323, "entropy": 0.10137706249952316, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:42.202099Z", "loop": 9225, "env_steps": 5668454399, "loss": 0.019430818036198616, "avg_return": 0.8613580465316772, "regret": 0.0012706094421446323, "entropy": 0.1038600280880928, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:43.055061Z", "loop": 9226, "env_steps": 5669068799, "loss": 0.01915603317320347, "avg_return": 0.8623497486114502, "regret": 0.0012706094421446323, "entropy": 0.09973961859941483, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:43.908495Z", "loop": 9227, "env_steps": 5669683199, "loss": 0.0204303078353405, "avg_return": 0.8621200919151306, "regret": 0.0012706094421446323, "entropy": 0.10902346670627594, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:44.763273Z", "loop": 9228, "env_steps": 5670297599, "loss": 0.022398261353373528, "avg_return": 0.8612857460975647, "regret": 0.0012706094421446323, "entropy": 0.11302582174539566, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:45.617008Z", "loop": 9229, "env_steps": 5670911999, "loss": 0.023755867034196854, "avg_return": 0.8597484827041626, "regret": 0.0012706094421446323, "entropy": 0.1213488057255745, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:46.511668Z", "loop": 9230, "env_steps": 5671526399, "loss": 0.025614464655518532, "avg_return": 0.8577919602394104, "regret": 0.005412308499217033, "entropy": 0.13174305856227875, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:47.365226Z", "loop": 9231, "env_steps": 5672140799, "loss": 0.02597842924296856, "avg_return": 0.8576076626777649, "regret": 0.005412308499217033, "entropy": 0.13287508487701416, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:48.219145Z", "loop": 9232, "env_steps": 5672755199, "loss": 0.024228442460298538, "avg_return": 0.8596034049987793, "regret": 0.005412308499217033, "entropy": 0.12527082860469818, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:49.072321Z", "loop": 9233, "env_steps": 5673369599, "loss": 0.02282634936273098, "avg_return": 0.8602553606033325, "regret": 0.005412308499217033, "entropy": 0.11677108705043793, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:49.925718Z", "loop": 9234, "env_steps": 5673983999, "loss": 0.022061457857489586, "avg_return": 0.8613826632499695, "regret": 0.005412308499217033, "entropy": 0.11430557817220688, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:50.778870Z", "loop": 9235, "env_steps": 5674598399, "loss": 0.02243317849934101, "avg_return": 0.8623279929161072, "regret": 0.005412308499217033, "entropy": 0.11383362859487534, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:51.633120Z", "loop": 9236, "env_steps": 5675212799, "loss": 0.022146349772810936, "avg_return": 0.8625761270523071, "regret": 0.005412308499217033, "entropy": 0.11533921957015991, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:52.487085Z", "loop": 9237, "env_steps": 5675827199, "loss": 0.022651607170701027, "avg_return": 0.8630936145782471, "regret": 0.005412308499217033, "entropy": 0.11013910919427872, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:53.340216Z", "loop": 9238, "env_steps": 5676441599, "loss": 0.022582395002245903, "avg_return": 0.8630043864250183, "regret": 0.005412308499217033, "entropy": 0.11299890279769897, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:54.193487Z", "loop": 9239, "env_steps": 5677055999, "loss": 0.02284461259841919, "avg_return": 0.8629374504089355, "regret": 0.005412308499217033, "entropy": 0.11131938546895981, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:55.088081Z", "loop": 9240, "env_steps": 5677670399, "loss": 0.023136792704463005, "avg_return": 0.8626682758331299, "regret": 0.0003486328641884029, "entropy": 0.11161984503269196, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:55.941921Z", "loop": 9241, "env_steps": 5678284799, "loss": 0.02151118591427803, "avg_return": 0.8635888695716858, "regret": 0.0003486328641884029, "entropy": 0.10703375190496445, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:56.796085Z", "loop": 9242, "env_steps": 5678899199, "loss": 0.020718736574053764, "avg_return": 0.8637296557426453, "regret": 0.0003486328641884029, "entropy": 0.10062126815319061, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:57.650642Z", "loop": 9243, "env_steps": 5679513599, "loss": 0.019837722182273865, "avg_return": 0.8629986643791199, "regret": 0.0003486328641884029, "entropy": 0.09562724828720093, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:58.505286Z", "loop": 9244, "env_steps": 5680127999, "loss": 0.018783504143357277, "avg_return": 0.8641728758811951, "regret": 0.0003486328641884029, "entropy": 0.09511735290288925, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:35:59.359802Z", "loop": 9245, "env_steps": 5680742399, "loss": 0.01887919008731842, "avg_return": 0.8624433875083923, "regret": 0.0003486328641884029, "entropy": 0.09498527646064758, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:00.213872Z", "loop": 9246, "env_steps": 5681356799, "loss": 0.018955595791339874, "avg_return": 0.8623467087745667, "regret": 0.0003486328641884029, "entropy": 0.09664766490459442, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:01.067824Z", "loop": 9247, "env_steps": 5681971199, "loss": 0.01930038444697857, "avg_return": 0.8634224534034729, "regret": 0.0003486328641884029, "entropy": 0.09427957236766815, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:01.925299Z", "loop": 9248, "env_steps": 5682585599, "loss": 0.01969297230243683, "avg_return": 0.8623163104057312, "regret": 0.0003486328641884029, "entropy": 0.09644588083028793, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:02.779837Z", "loop": 9249, "env_steps": 5683199999, "loss": 0.019178127869963646, "avg_return": 0.8623747825622559, "regret": 0.0003486328641884029, "entropy": 0.09424811601638794, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:03.682914Z", "loop": 9250, "env_steps": 5683814399, "loss": 0.018737278878688812, "avg_return": 0.8624895215034485, "regret": 0.0016470125410705805, "entropy": 0.09294416010379791, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:04.540943Z", "loop": 9251, "env_steps": 5684428799, "loss": 0.018874438479542732, "avg_return": 0.8630720973014832, "regret": 0.0016470125410705805, "entropy": 0.09284374117851257, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:05.395970Z", "loop": 9252, "env_steps": 5685043199, "loss": 0.019208142533898354, "avg_return": 0.861805260181427, "regret": 0.0016470125410705805, "entropy": 0.09222247451543808, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:06.251151Z", "loop": 9253, "env_steps": 5685657599, "loss": 0.018072960898280144, "avg_return": 0.8617138862609863, "regret": 0.0016470125410705805, "entropy": 0.09122234582901001, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:07.105775Z", "loop": 9254, "env_steps": 5686271999, "loss": 0.017808672040700912, "avg_return": 0.8639991283416748, "regret": 0.0016470125410705805, "entropy": 0.08837885409593582, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:07.959486Z", "loop": 9255, "env_steps": 5686886399, "loss": 0.01546510774642229, "avg_return": 0.8646602630615234, "regret": 0.0016470125410705805, "entropy": 0.07992654293775558, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:08.813898Z", "loop": 9256, "env_steps": 5687500799, "loss": 0.016191545873880386, "avg_return": 0.864362895488739, "regret": 0.0016470125410705805, "entropy": 0.07982837408781052, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:09.667414Z", "loop": 9257, "env_steps": 5688115199, "loss": 0.01477012038230896, "avg_return": 0.8630827069282532, "regret": 0.0016470125410705805, "entropy": 0.07609567046165466, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:10.521271Z", "loop": 9258, "env_steps": 5688729599, "loss": 0.013776115141808987, "avg_return": 0.8627086877822876, "regret": 0.0016470125410705805, "entropy": 0.07647665590047836, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:11.374770Z", "loop": 9259, "env_steps": 5689343999, "loss": 0.016814349219202995, "avg_return": 0.863498866558075, "regret": 0.0016470125410705805, "entropy": 0.08742110431194305, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:12.268736Z", "loop": 9260, "env_steps": 5689958399, "loss": 0.01624964363873005, "avg_return": 0.8629363179206848, "regret": 0.0006861362489871681, "entropy": 0.08379919081926346, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:13.122719Z", "loop": 9261, "env_steps": 5690572799, "loss": 0.01565769501030445, "avg_return": 0.8631649017333984, "regret": 0.0006861362489871681, "entropy": 0.07747327536344528, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:13.977012Z", "loop": 9262, "env_steps": 5691187199, "loss": 0.015408599749207497, "avg_return": 0.8612192273139954, "regret": 0.0006861362489871681, "entropy": 0.07925751060247421, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:14.832768Z", "loop": 9263, "env_steps": 5691801599, "loss": 0.017413832247257233, "avg_return": 0.8591652512550354, "regret": 0.0006861362489871681, "entropy": 0.09125940501689911, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:15.688498Z", "loop": 9264, "env_steps": 5692415999, "loss": 0.018147269263863564, "avg_return": 0.8566060662269592, "regret": 0.0006861362489871681, "entropy": 0.09318702667951584, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:16.543142Z", "loop": 9265, "env_steps": 5693030399, "loss": 0.018939930945634842, "avg_return": 0.8566225171089172, "regret": 0.0006861362489871681, "entropy": 0.0966256782412529, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:17.397542Z", "loop": 9266, "env_steps": 5693644799, "loss": 0.018042106181383133, "avg_return": 0.8571674823760986, "regret": 0.0006861362489871681, "entropy": 0.09326725453138351, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:18.252945Z", "loop": 9267, "env_steps": 5694259199, "loss": 0.01748484931886196, "avg_return": 0.8593113422393799, "regret": 0.0006861362489871681, "entropy": 0.09293682128190994, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:19.107862Z", "loop": 9268, "env_steps": 5694873599, "loss": 0.01770971715450287, "avg_return": 0.8602779507637024, "regret": 0.0006861362489871681, "entropy": 0.08845653384923935, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:19.961170Z", "loop": 9269, "env_steps": 5695487999, "loss": 0.0172528438270092, "avg_return": 0.8620607852935791, "regret": 0.0006861362489871681, "entropy": 0.09110851585865021, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:20.855414Z", "loop": 9270, "env_steps": 5696102399, "loss": 0.016795294359326363, "avg_return": 0.8607911467552185, "regret": 0.0019066801760345697, "entropy": 0.08858978748321533, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:21.709053Z", "loop": 9271, "env_steps": 5696716799, "loss": 0.01669475995004177, "avg_return": 0.8604236841201782, "regret": 0.0019066801760345697, "entropy": 0.0860666036605835, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:22.562901Z", "loop": 9272, "env_steps": 5697331199, "loss": 0.016499103978276253, "avg_return": 0.8633711934089661, "regret": 0.0019066801760345697, "entropy": 0.08405821025371552, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:23.416719Z", "loop": 9273, "env_steps": 5697945599, "loss": 0.016924509778618813, "avg_return": 0.8618906140327454, "regret": 0.0019066801760345697, "entropy": 0.08637163043022156, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:24.270750Z", "loop": 9274, "env_steps": 5698559999, "loss": 0.0162618737667799, "avg_return": 0.8621552586555481, "regret": 0.0019066801760345697, "entropy": 0.08291418105363846, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:25.124858Z", "loop": 9275, "env_steps": 5699174399, "loss": 0.016311725601553917, "avg_return": 0.8627890944480896, "regret": 0.0019066801760345697, "entropy": 0.0839434489607811, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:25.978524Z", "loop": 9276, "env_steps": 5699788799, "loss": 0.016204264014959335, "avg_return": 0.8628352880477905, "regret": 0.0019066801760345697, "entropy": 0.08267220854759216, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:26.832147Z", "loop": 9277, "env_steps": 5700403199, "loss": 0.015651043504476547, "avg_return": 0.8620115518569946, "regret": 0.0019066801760345697, "entropy": 0.0791732519865036, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:27.687220Z", "loop": 9278, "env_steps": 5701017599, "loss": 0.01509940531104803, "avg_return": 0.8618142008781433, "regret": 0.0019066801760345697, "entropy": 0.07944457232952118, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:28.540859Z", "loop": 9279, "env_steps": 5701631999, "loss": 0.01607208140194416, "avg_return": 0.8627122044563293, "regret": 0.0019066801760345697, "entropy": 0.08103412389755249, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:29.434549Z", "loop": 9280, "env_steps": 5702246399, "loss": 0.015284414403140545, "avg_return": 0.8613898754119873, "regret": 0.0010544703109189868, "entropy": 0.07926162332296371, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:30.289011Z", "loop": 9281, "env_steps": 5702860799, "loss": 0.016985571011900902, "avg_return": 0.861887514591217, "regret": 0.0010544703109189868, "entropy": 0.08771505951881409, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:31.143911Z", "loop": 9282, "env_steps": 5703475199, "loss": 0.01687932014465332, "avg_return": 0.8620212078094482, "regret": 0.0010544703109189868, "entropy": 0.09169062227010727, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:31.998972Z", "loop": 9283, "env_steps": 5704089599, "loss": 0.01749303750693798, "avg_return": 0.8625077605247498, "regret": 0.0010544703109189868, "entropy": 0.0910567045211792, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:32.852833Z", "loop": 9284, "env_steps": 5704703999, "loss": 0.016971750184893608, "avg_return": 0.8609994649887085, "regret": 0.0010544703109189868, "entropy": 0.09033645689487457, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:33.707837Z", "loop": 9285, "env_steps": 5705318399, "loss": 0.018988700583577156, "avg_return": 0.8613397479057312, "regret": 0.0010544703109189868, "entropy": 0.09804913401603699, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:34.561873Z", "loop": 9286, "env_steps": 5705932799, "loss": 0.01943274214863777, "avg_return": 0.8581820130348206, "regret": 0.0010544703109189868, "entropy": 0.09919103980064392, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:35.415847Z", "loop": 9287, "env_steps": 5706547199, "loss": 0.02047167718410492, "avg_return": 0.8559584617614746, "regret": 0.0010544703109189868, "entropy": 0.10390066355466843, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:36.268678Z", "loop": 9288, "env_steps": 5707161599, "loss": 0.022654203698039055, "avg_return": 0.8528640866279602, "regret": 0.0010544703109189868, "entropy": 0.11596190929412842, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:37.121590Z", "loop": 9289, "env_steps": 5707775999, "loss": 0.018351266160607338, "avg_return": 0.8560293912887573, "regret": 0.0010544703109189868, "entropy": 0.10339616984128952, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:38.015065Z", "loop": 9290, "env_steps": 5708390399, "loss": 0.019725311547517776, "avg_return": 0.8577867746353149, "regret": 0.005392163060605526, "entropy": 0.10451184213161469, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:38.869538Z", "loop": 9291, "env_steps": 5709004799, "loss": 0.01744748465716839, "avg_return": 0.8589721918106079, "regret": 0.005392163060605526, "entropy": 0.09304635226726532, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:39.723946Z", "loop": 9292, "env_steps": 5709619199, "loss": 0.018095964565873146, "avg_return": 0.859863817691803, "regret": 0.005392163060605526, "entropy": 0.08958896994590759, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:40.577553Z", "loop": 9293, "env_steps": 5710233599, "loss": 0.017474455758929253, "avg_return": 0.8607854247093201, "regret": 0.005392163060605526, "entropy": 0.09341863542795181, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:41.431220Z", "loop": 9294, "env_steps": 5710847999, "loss": 0.01702304556965828, "avg_return": 0.8602850437164307, "regret": 0.005392163060605526, "entropy": 0.09057727456092834, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:42.286033Z", "loop": 9295, "env_steps": 5711462399, "loss": 0.01797577552497387, "avg_return": 0.861595869064331, "regret": 0.005392163060605526, "entropy": 0.09025520086288452, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:43.140722Z", "loop": 9296, "env_steps": 5712076799, "loss": 0.017537709325551987, "avg_return": 0.8615128993988037, "regret": 0.005392163060605526, "entropy": 0.09007593989372253, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:43.995018Z", "loop": 9297, "env_steps": 5712691199, "loss": 0.017702598124742508, "avg_return": 0.8624019622802734, "regret": 0.005392163060605526, "entropy": 0.0931803286075592, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:44.848868Z", "loop": 9298, "env_steps": 5713305599, "loss": 0.018416665494441986, "avg_return": 0.8630863428115845, "regret": 0.005392163060605526, "entropy": 0.08966299146413803, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:45.704233Z", "loop": 9299, "env_steps": 5713919999, "loss": 0.017620140686631203, "avg_return": 0.8616777658462524, "regret": 0.005392163060605526, "entropy": 0.088898666203022, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:46.598850Z", "loop": 9300, "env_steps": 5714534399, "loss": 0.017651868984103203, "avg_return": 0.8609927296638489, "regret": 0.0011982055148109794, "entropy": 0.08534077554941177, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:47.452640Z", "loop": 9301, "env_steps": 5715148799, "loss": 0.017727229744195938, "avg_return": 0.8638462424278259, "regret": 0.0011982055148109794, "entropy": 0.08707462251186371, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:48.307130Z", "loop": 9302, "env_steps": 5715763199, "loss": 0.016714898869395256, "avg_return": 0.8641304969787598, "regret": 0.0011982055148109794, "entropy": 0.08418599516153336, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:49.161578Z", "loop": 9303, "env_steps": 5716377599, "loss": 0.01600070670247078, "avg_return": 0.8611635565757751, "regret": 0.0011982055148109794, "entropy": 0.08524538576602936, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:50.015972Z", "loop": 9304, "env_steps": 5716991999, "loss": 0.016851088032126427, "avg_return": 0.8620664477348328, "regret": 0.0011982055148109794, "entropy": 0.0846540778875351, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:50.869319Z", "loop": 9305, "env_steps": 5717606399, "loss": 0.016020948067307472, "avg_return": 0.863016664981842, "regret": 0.0011982055148109794, "entropy": 0.08280331641435623, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:51.722533Z", "loop": 9306, "env_steps": 5718220799, "loss": 0.017539171501994133, "avg_return": 0.86369389295578, "regret": 0.0011982055148109794, "entropy": 0.0848008543252945, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:52.576905Z", "loop": 9307, "env_steps": 5718835199, "loss": 0.016738658770918846, "avg_return": 0.8624839186668396, "regret": 0.0011982055148109794, "entropy": 0.08517945557832718, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:53.430803Z", "loop": 9308, "env_steps": 5719449599, "loss": 0.01718813367187977, "avg_return": 0.8633890748023987, "regret": 0.0011982055148109794, "entropy": 0.08596228063106537, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:54.284591Z", "loop": 9309, "env_steps": 5720063999, "loss": 0.017268696799874306, "avg_return": 0.8627870678901672, "regret": 0.0011982055148109794, "entropy": 0.08570817857980728, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:55.178177Z", "loop": 9310, "env_steps": 5720678399, "loss": 0.01772495172917843, "avg_return": 0.8625584840774536, "regret": 0.0008794133900664747, "entropy": 0.08737067133188248, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:56.031774Z", "loop": 9311, "env_steps": 5721292799, "loss": 0.017656324431300163, "avg_return": 0.8626002073287964, "regret": 0.0008794133900664747, "entropy": 0.09017521142959595, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:56.886706Z", "loop": 9312, "env_steps": 5721907199, "loss": 0.01706334762275219, "avg_return": 0.8625807166099548, "regret": 0.0008794133900664747, "entropy": 0.08997242152690887, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:57.741074Z", "loop": 9313, "env_steps": 5722521599, "loss": 0.017422713339328766, "avg_return": 0.8613762855529785, "regret": 0.0008794133900664747, "entropy": 0.09005402028560638, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:58.595099Z", "loop": 9314, "env_steps": 5723135999, "loss": 0.01842328906059265, "avg_return": 0.8628861904144287, "regret": 0.0008794133900664747, "entropy": 0.09128782153129578, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:36:59.448794Z", "loop": 9315, "env_steps": 5723750399, "loss": 0.018784772604703903, "avg_return": 0.8644728660583496, "regret": 0.0008794133900664747, "entropy": 0.09069422632455826, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:00.301925Z", "loop": 9316, "env_steps": 5724364799, "loss": 0.017624393105506897, "avg_return": 0.8623302578926086, "regret": 0.0008794133900664747, "entropy": 0.08844415843486786, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:01.157057Z", "loop": 9317, "env_steps": 5724979199, "loss": 0.017753152176737785, "avg_return": 0.8623252511024475, "regret": 0.0008794133900664747, "entropy": 0.08840318024158478, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:02.012174Z", "loop": 9318, "env_steps": 5725593599, "loss": 0.01664240099489689, "avg_return": 0.8629553318023682, "regret": 0.0008794133900664747, "entropy": 0.08959166705608368, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:02.866616Z", "loop": 9319, "env_steps": 5726207999, "loss": 0.018060341477394104, "avg_return": 0.8630656003952026, "regret": 0.0008794133900664747, "entropy": 0.08790922164916992, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:03.760742Z", "loop": 9320, "env_steps": 5726822399, "loss": 0.018338164314627647, "avg_return": 0.8633242249488831, "regret": 0.0005825561820529401, "entropy": 0.0931585505604744, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:04.614110Z", "loop": 9321, "env_steps": 5727436799, "loss": 0.01894744485616684, "avg_return": 0.8633439540863037, "regret": 0.0005825561820529401, "entropy": 0.09270395338535309, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:05.470174Z", "loop": 9322, "env_steps": 5728051199, "loss": 0.018578704446554184, "avg_return": 0.8624080419540405, "regret": 0.0005825561820529401, "entropy": 0.09617836773395538, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:06.324761Z", "loop": 9323, "env_steps": 5728665599, "loss": 0.01947682537138462, "avg_return": 0.8624446988105774, "regret": 0.0005825561820529401, "entropy": 0.09743383526802063, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:07.179518Z", "loop": 9324, "env_steps": 5729279999, "loss": 0.020299969241023064, "avg_return": 0.8624863624572754, "regret": 0.0005825561820529401, "entropy": 0.10134711116552353, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:08.034376Z", "loop": 9325, "env_steps": 5729894399, "loss": 0.018879178911447525, "avg_return": 0.861689567565918, "regret": 0.0005825561820529401, "entropy": 0.10018646717071533, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:08.889366Z", "loop": 9326, "env_steps": 5730508799, "loss": 0.01941334269940853, "avg_return": 0.859724760055542, "regret": 0.0005825561820529401, "entropy": 0.10090499371290207, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:09.744309Z", "loop": 9327, "env_steps": 5731123199, "loss": 0.018870271742343903, "avg_return": 0.8606535196304321, "regret": 0.0005825561820529401, "entropy": 0.0958092212677002, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:10.598418Z", "loop": 9328, "env_steps": 5731737599, "loss": 0.018169546499848366, "avg_return": 0.8594810962677002, "regret": 0.0005825561820529401, "entropy": 0.0951075628399849, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:11.451795Z", "loop": 9329, "env_steps": 5732351999, "loss": 0.017434891313314438, "avg_return": 0.8583371043205261, "regret": 0.0005825561820529401, "entropy": 0.09136024117469788, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:12.348352Z", "loop": 9330, "env_steps": 5732966399, "loss": 0.016995694488286972, "avg_return": 0.8593994379043579, "regret": 0.004960667807608843, "entropy": 0.08787115663290024, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:13.202178Z", "loop": 9331, "env_steps": 5733580799, "loss": 0.016831031069159508, "avg_return": 0.8579325675964355, "regret": 0.004960667807608843, "entropy": 0.09081438928842545, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:14.056634Z", "loop": 9332, "env_steps": 5734195199, "loss": 0.016695639118552208, "avg_return": 0.8570938110351562, "regret": 0.004960667807608843, "entropy": 0.08949757367372513, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:14.910923Z", "loop": 9333, "env_steps": 5734809599, "loss": 0.016713395714759827, "avg_return": 0.8574617505073547, "regret": 0.004960667807608843, "entropy": 0.09000904858112335, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:15.766168Z", "loop": 9334, "env_steps": 5735423999, "loss": 0.016838176175951958, "avg_return": 0.8583332300186157, "regret": 0.004960667807608843, "entropy": 0.09022007137537003, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:16.620324Z", "loop": 9335, "env_steps": 5736038399, "loss": 0.014920624904334545, "avg_return": 0.8599640130996704, "regret": 0.004960667807608843, "entropy": 0.08331312239170074, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:17.473746Z", "loop": 9336, "env_steps": 5736652799, "loss": 0.01389111578464508, "avg_return": 0.8607456684112549, "regret": 0.004960667807608843, "entropy": 0.07779296487569809, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:18.327748Z", "loop": 9337, "env_steps": 5737267199, "loss": 0.013330074027180672, "avg_return": 0.8613218665122986, "regret": 0.004960667807608843, "entropy": 0.07423447072505951, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:19.182096Z", "loop": 9338, "env_steps": 5737881599, "loss": 0.014108237810432911, "avg_return": 0.861142098903656, "regret": 0.004960667807608843, "entropy": 0.07565101236104965, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:20.035592Z", "loop": 9339, "env_steps": 5738495999, "loss": 0.013315645046532154, "avg_return": 0.8607159852981567, "regret": 0.004960667807608843, "entropy": 0.07052703201770782, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:20.929237Z", "loop": 9340, "env_steps": 5739110399, "loss": 0.013522924855351448, "avg_return": 0.860655665397644, "regret": 0.0017598849954083562, "entropy": 0.07283159345388412, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:21.785014Z", "loop": 9341, "env_steps": 5739724799, "loss": 0.012997428886592388, "avg_return": 0.8635518550872803, "regret": 0.0017598849954083562, "entropy": 0.06935887783765793, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:22.640693Z", "loop": 9342, "env_steps": 5740339199, "loss": 0.013381007127463818, "avg_return": 0.8636468648910522, "regret": 0.0017598849954083562, "entropy": 0.07078345865011215, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:23.494988Z", "loop": 9343, "env_steps": 5740953599, "loss": 0.01228274218738079, "avg_return": 0.8627194166183472, "regret": 0.0017598849954083562, "entropy": 0.06995188444852829, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:24.350442Z", "loop": 9344, "env_steps": 5741567999, "loss": 0.013088494539260864, "avg_return": 0.8615031242370605, "regret": 0.0017598849954083562, "entropy": 0.07290185987949371, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:25.204958Z", "loop": 9345, "env_steps": 5742182399, "loss": 0.012965383939445019, "avg_return": 0.8615822792053223, "regret": 0.0017598849954083562, "entropy": 0.070343516767025, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:26.060973Z", "loop": 9346, "env_steps": 5742796799, "loss": 0.013112823478877544, "avg_return": 0.8625905513763428, "regret": 0.0017598849954083562, "entropy": 0.0724482387304306, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:26.915331Z", "loop": 9347, "env_steps": 5743411199, "loss": 0.013565815053880215, "avg_return": 0.8624222874641418, "regret": 0.0017598849954083562, "entropy": 0.07378718256950378, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:27.769950Z", "loop": 9348, "env_steps": 5744025599, "loss": 0.012703396379947662, "avg_return": 0.8625404834747314, "regret": 0.0017598849954083562, "entropy": 0.0715319812297821, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:28.624724Z", "loop": 9349, "env_steps": 5744639999, "loss": 0.013106723316013813, "avg_return": 0.862093448638916, "regret": 0.0017598849954083562, "entropy": 0.07227350026369095, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:29.519942Z", "loop": 9350, "env_steps": 5745254399, "loss": 0.012967035174369812, "avg_return": 0.8624554872512817, "regret": 0.0010873068822547793, "entropy": 0.07046081870794296, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:30.373643Z", "loop": 9351, "env_steps": 5745868799, "loss": 0.013298774138092995, "avg_return": 0.862535297870636, "regret": 0.0010873068822547793, "entropy": 0.07154533267021179, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:31.226506Z", "loop": 9352, "env_steps": 5746483199, "loss": 0.013641329482197762, "avg_return": 0.8632715344429016, "regret": 0.0010873068822547793, "entropy": 0.07103432714939117, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:32.080279Z", "loop": 9353, "env_steps": 5747097599, "loss": 0.012961501255631447, "avg_return": 0.8635227680206299, "regret": 0.0010873068822547793, "entropy": 0.07096575945615768, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:32.934559Z", "loop": 9354, "env_steps": 5747711999, "loss": 0.01348208636045456, "avg_return": 0.863978922367096, "regret": 0.0010873068822547793, "entropy": 0.07282698899507523, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:33.789096Z", "loop": 9355, "env_steps": 5748326399, "loss": 0.01459082867950201, "avg_return": 0.862747848033905, "regret": 0.0010873068822547793, "entropy": 0.0751742422580719, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:34.642278Z", "loop": 9356, "env_steps": 5748940799, "loss": 0.015030919574201107, "avg_return": 0.863425612449646, "regret": 0.0010873068822547793, "entropy": 0.07360222935676575, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:35.496115Z", "loop": 9357, "env_steps": 5749555199, "loss": 0.0133981853723526, "avg_return": 0.862586498260498, "regret": 0.0010873068822547793, "entropy": 0.0720018595457077, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:36.349715Z", "loop": 9358, "env_steps": 5750169599, "loss": 0.014133644290268421, "avg_return": 0.862673282623291, "regret": 0.0010873068822547793, "entropy": 0.07493219524621964, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:37.204343Z", "loop": 9359, "env_steps": 5750783999, "loss": 0.013985360972583294, "avg_return": 0.862738847732544, "regret": 0.0010873068822547793, "entropy": 0.07272354513406754, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:38.097342Z", "loop": 9360, "env_steps": 5751398399, "loss": 0.013838154263794422, "avg_return": 0.8629282116889954, "regret": 0.0008353068260475993, "entropy": 0.07580973953008652, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:38.950631Z", "loop": 9361, "env_steps": 5752012799, "loss": 0.013495217077434063, "avg_return": 0.8628847599029541, "regret": 0.0008353068260475993, "entropy": 0.07285899668931961, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:39.804508Z", "loop": 9362, "env_steps": 5752627199, "loss": 0.0142293069511652, "avg_return": 0.8623649477958679, "regret": 0.0008353068260475993, "entropy": 0.07720412313938141, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:40.658946Z", "loop": 9363, "env_steps": 5753241599, "loss": 0.014254731126129627, "avg_return": 0.8603139519691467, "regret": 0.0008353068260475993, "entropy": 0.07933173328638077, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:41.513719Z", "loop": 9364, "env_steps": 5753855999, "loss": 0.01544063538312912, "avg_return": 0.8599068522453308, "regret": 0.0008353068260475993, "entropy": 0.08481517434120178, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:42.367523Z", "loop": 9365, "env_steps": 5754470399, "loss": 0.0160516407340765, "avg_return": 0.8605019450187683, "regret": 0.0008353068260475993, "entropy": 0.08415426313877106, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:43.222116Z", "loop": 9366, "env_steps": 5755084799, "loss": 0.012112746015191078, "avg_return": 0.8614799380302429, "regret": 0.0008353068260475993, "entropy": 0.07021065056324005, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:44.076137Z", "loop": 9367, "env_steps": 5755699199, "loss": 0.013093548826873302, "avg_return": 0.8608802556991577, "regret": 0.0008353068260475993, "entropy": 0.07174233347177505, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:44.930551Z", "loop": 9368, "env_steps": 5756313599, "loss": 0.013611040078103542, "avg_return": 0.8618149161338806, "regret": 0.0008353068260475993, "entropy": 0.07284800708293915, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:45.784517Z", "loop": 9369, "env_steps": 5756927999, "loss": 0.01318878959864378, "avg_return": 0.8636791110038757, "regret": 0.0008353068260475993, "entropy": 0.07027993351221085, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:46.678225Z", "loop": 9370, "env_steps": 5757542399, "loss": 0.012911267578601837, "avg_return": 0.861550509929657, "regret": 0.0012605235679075122, "entropy": 0.07064873725175858, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:47.531818Z", "loop": 9371, "env_steps": 5758156799, "loss": 0.01224153209477663, "avg_return": 0.8622921109199524, "regret": 0.0012605235679075122, "entropy": 0.06851694732904434, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:48.386060Z", "loop": 9372, "env_steps": 5758771199, "loss": 0.013245441019535065, "avg_return": 0.861945390701294, "regret": 0.0012605235679075122, "entropy": 0.07019809633493423, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:49.239777Z", "loop": 9373, "env_steps": 5759385599, "loss": 0.012785263359546661, "avg_return": 0.8625262379646301, "regret": 0.0012605235679075122, "entropy": 0.06985842436552048, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:50.092644Z", "loop": 9374, "env_steps": 5759999999, "loss": 0.012175005860626698, "avg_return": 0.8615521192550659, "regret": 0.0012605235679075122, "entropy": 0.07158172875642776, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:50.945478Z", "loop": 9375, "env_steps": 5760614399, "loss": 0.013440513983368874, "avg_return": 0.8620600700378418, "regret": 0.0012605235679075122, "entropy": 0.07646840810775757, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:51.799201Z", "loop": 9376, "env_steps": 5761228799, "loss": 0.013537353835999966, "avg_return": 0.8613812327384949, "regret": 0.0012605235679075122, "entropy": 0.07585170120000839, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:52.653241Z", "loop": 9377, "env_steps": 5761843199, "loss": 0.013079424388706684, "avg_return": 0.8616669774055481, "regret": 0.0012605235679075122, "entropy": 0.06821618974208832, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:53.507516Z", "loop": 9378, "env_steps": 5762457599, "loss": 0.013187222182750702, "avg_return": 0.8625805974006653, "regret": 0.0012605235679075122, "entropy": 0.07149861752986908, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:54.360274Z", "loop": 9379, "env_steps": 5763071999, "loss": 0.012417647056281567, "avg_return": 0.8609971404075623, "regret": 0.0012605235679075122, "entropy": 0.06946664303541183, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:55.252548Z", "loop": 9380, "env_steps": 5763686399, "loss": 0.01275112759321928, "avg_return": 0.8600401878356934, "regret": 0.0019839671440422535, "entropy": 0.07095473259687424, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:56.107083Z", "loop": 9381, "env_steps": 5764300799, "loss": 0.013571462593972683, "avg_return": 0.8628489375114441, "regret": 0.0019839671440422535, "entropy": 0.07212533056735992, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:56.961710Z", "loop": 9382, "env_steps": 5764915199, "loss": 0.011577855795621872, "avg_return": 0.8614359498023987, "regret": 0.0019839671440422535, "entropy": 0.0634448379278183, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:57.815402Z", "loop": 9383, "env_steps": 5765529599, "loss": 0.012350625358521938, "avg_return": 0.8634006977081299, "regret": 0.0019839671440422535, "entropy": 0.06885264813899994, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:58.669661Z", "loop": 9384, "env_steps": 5766143999, "loss": 0.012231793254613876, "avg_return": 0.8617922067642212, "regret": 0.0019839671440422535, "entropy": 0.0655985176563263, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:37:59.524342Z", "loop": 9385, "env_steps": 5766758399, "loss": 0.013974693603813648, "avg_return": 0.8628501296043396, "regret": 0.0019839671440422535, "entropy": 0.07198075205087662, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:00.381678Z", "loop": 9386, "env_steps": 5767372799, "loss": 0.014419637620449066, "avg_return": 0.8630306124687195, "regret": 0.0019839671440422535, "entropy": 0.07462705671787262, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:01.235810Z", "loop": 9387, "env_steps": 5767987199, "loss": 0.015211174264550209, "avg_return": 0.8628015518188477, "regret": 0.0019839671440422535, "entropy": 0.07597008347511292, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:02.089623Z", "loop": 9388, "env_steps": 5768601599, "loss": 0.013761283829808235, "avg_return": 0.8626857995986938, "regret": 0.0019839671440422535, "entropy": 0.07746073603630066, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:02.942677Z", "loop": 9389, "env_steps": 5769215999, "loss": 0.01473701000213623, "avg_return": 0.862269937992096, "regret": 0.0019839671440422535, "entropy": 0.07773753255605698, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:03.837800Z", "loop": 9390, "env_steps": 5769830399, "loss": 0.015134088695049286, "avg_return": 0.8630370497703552, "regret": 0.0004217141540721059, "entropy": 0.08113256841897964, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:04.692902Z", "loop": 9391, "env_steps": 5770444799, "loss": 0.014581196010112762, "avg_return": 0.8624988794326782, "regret": 0.0004217141540721059, "entropy": 0.08042711019515991, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:05.547925Z", "loop": 9392, "env_steps": 5771059199, "loss": 0.016190802678465843, "avg_return": 0.8636023998260498, "regret": 0.0004217141540721059, "entropy": 0.08626562356948853, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:06.403508Z", "loop": 9393, "env_steps": 5771673599, "loss": 0.01538512110710144, "avg_return": 0.8638198971748352, "regret": 0.0004217141540721059, "entropy": 0.0867346003651619, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:07.259003Z", "loop": 9394, "env_steps": 5772287999, "loss": 0.01697169803082943, "avg_return": 0.8631111979484558, "regret": 0.0004217141540721059, "entropy": 0.08609876036643982, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:08.113719Z", "loop": 9395, "env_steps": 5772902399, "loss": 0.01781981810927391, "avg_return": 0.8625824451446533, "regret": 0.0004217141540721059, "entropy": 0.08926805853843689, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:08.968319Z", "loop": 9396, "env_steps": 5773516799, "loss": 0.01771133951842785, "avg_return": 0.865329384803772, "regret": 0.0004217141540721059, "entropy": 0.09428378939628601, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:09.822718Z", "loop": 9397, "env_steps": 5774131199, "loss": 0.01978343352675438, "avg_return": 0.8637548089027405, "regret": 0.0004217141540721059, "entropy": 0.1008249968290329, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:10.677421Z", "loop": 9398, "env_steps": 5774745599, "loss": 0.020007653161883354, "avg_return": 0.8626524806022644, "regret": 0.0004217141540721059, "entropy": 0.0984700620174408, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:11.531455Z", "loop": 9399, "env_steps": 5775359999, "loss": 0.01961803250014782, "avg_return": 0.862517237663269, "regret": 0.0004217141540721059, "entropy": 0.0964946299791336, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:12.424658Z", "loop": 9400, "env_steps": 5775974399, "loss": 0.01869073323905468, "avg_return": 0.8630617260932922, "regret": 0.000464198412373662, "entropy": 0.09462829679250717, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:13.279840Z", "loop": 9401, "env_steps": 5776588799, "loss": 0.018497293815016747, "avg_return": 0.8626487255096436, "regret": 0.000464198412373662, "entropy": 0.09159784764051437, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:14.134081Z", "loop": 9402, "env_steps": 5777203199, "loss": 0.01777832768857479, "avg_return": 0.8633215427398682, "regret": 0.000464198412373662, "entropy": 0.08955450356006622, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:14.988657Z", "loop": 9403, "env_steps": 5777817599, "loss": 0.01811905764043331, "avg_return": 0.8624752163887024, "regret": 0.000464198412373662, "entropy": 0.08821917325258255, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:15.843392Z", "loop": 9404, "env_steps": 5778431999, "loss": 0.01769362948834896, "avg_return": 0.8631846308708191, "regret": 0.000464198412373662, "entropy": 0.09081179648637772, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:16.698089Z", "loop": 9405, "env_steps": 5779046399, "loss": 0.01695489138364792, "avg_return": 0.8619099259376526, "regret": 0.000464198412373662, "entropy": 0.08916576951742172, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:17.551517Z", "loop": 9406, "env_steps": 5779660799, "loss": 0.018083786591887474, "avg_return": 0.860503077507019, "regret": 0.000464198412373662, "entropy": 0.09249264746904373, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:18.404709Z", "loop": 9407, "env_steps": 5780275199, "loss": 0.017665255814790726, "avg_return": 0.8630108833312988, "regret": 0.000464198412373662, "entropy": 0.09159018099308014, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:19.258539Z", "loop": 9408, "env_steps": 5780889599, "loss": 0.019381973892450333, "avg_return": 0.8629651069641113, "regret": 0.000464198412373662, "entropy": 0.09787944704294205, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:20.112859Z", "loop": 9409, "env_steps": 5781503999, "loss": 0.018625177443027496, "avg_return": 0.8634877800941467, "regret": 0.000464198412373662, "entropy": 0.09401185065507889, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:21.008032Z", "loop": 9410, "env_steps": 5782118399, "loss": 0.019420092925429344, "avg_return": 0.8628458976745605, "regret": 0.0009524207562208176, "entropy": 0.09776301681995392, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:21.860988Z", "loop": 9411, "env_steps": 5782732799, "loss": 0.01871812902390957, "avg_return": 0.8615447282791138, "regret": 0.0009524207562208176, "entropy": 0.09427952021360397, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:22.714169Z", "loop": 9412, "env_steps": 5783347199, "loss": 0.01867561601102352, "avg_return": 0.8631166815757751, "regret": 0.0009524207562208176, "entropy": 0.09494853764772415, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:23.568508Z", "loop": 9413, "env_steps": 5783961599, "loss": 0.019118161872029305, "avg_return": 0.8630446791648865, "regret": 0.0009524207562208176, "entropy": 0.09580124914646149, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:24.423846Z", "loop": 9414, "env_steps": 5784575999, "loss": 0.018961600959300995, "avg_return": 0.862991988658905, "regret": 0.0009524207562208176, "entropy": 0.09910804778337479, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:25.277829Z", "loop": 9415, "env_steps": 5785190399, "loss": 0.019329115748405457, "avg_return": 0.8616211414337158, "regret": 0.0009524207562208176, "entropy": 0.09553468972444534, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:26.131614Z", "loop": 9416, "env_steps": 5785804799, "loss": 0.018361391499638557, "avg_return": 0.8624582290649414, "regret": 0.0009524207562208176, "entropy": 0.09798222780227661, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:26.986089Z", "loop": 9417, "env_steps": 5786419199, "loss": 0.01937701553106308, "avg_return": 0.8631190061569214, "regret": 0.0009524207562208176, "entropy": 0.09904487431049347, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:27.839985Z", "loop": 9418, "env_steps": 5787033599, "loss": 0.018876610323786736, "avg_return": 0.863296627998352, "regret": 0.0009524207562208176, "entropy": 0.09748531132936478, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:28.694236Z", "loop": 9419, "env_steps": 5787647999, "loss": 0.019214190542697906, "avg_return": 0.8637129068374634, "regret": 0.0009524207562208176, "entropy": 0.09602349996566772, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:29.589362Z", "loop": 9420, "env_steps": 5788262399, "loss": 0.018900921568274498, "avg_return": 0.8632080554962158, "regret": 0.0008944541332311928, "entropy": 0.09758342057466507, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:30.443405Z", "loop": 9421, "env_steps": 5788876799, "loss": 0.01870044693350792, "avg_return": 0.8625775575637817, "regret": 0.0008944541332311928, "entropy": 0.09817291796207428, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:31.297966Z", "loop": 9422, "env_steps": 5789491199, "loss": 0.019147973507642746, "avg_return": 0.8632110953330994, "regret": 0.0008944541332311928, "entropy": 0.09583138674497604, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:32.152244Z", "loop": 9423, "env_steps": 5790105599, "loss": 0.01929275505244732, "avg_return": 0.8634237051010132, "regret": 0.0008944541332311928, "entropy": 0.09639932960271835, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:33.006803Z", "loop": 9424, "env_steps": 5790719999, "loss": 0.018832767382264137, "avg_return": 0.8636420965194702, "regret": 0.0008944541332311928, "entropy": 0.09305071085691452, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:33.861534Z", "loop": 9425, "env_steps": 5791334399, "loss": 0.017753129824995995, "avg_return": 0.8628259301185608, "regret": 0.0008944541332311928, "entropy": 0.0929974913597107, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:34.715817Z", "loop": 9426, "env_steps": 5791948799, "loss": 0.018715545535087585, "avg_return": 0.8632266521453857, "regret": 0.0008944541332311928, "entropy": 0.09437521547079086, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:35.570846Z", "loop": 9427, "env_steps": 5792563199, "loss": 0.016787031665444374, "avg_return": 0.8634670376777649, "regret": 0.0008944541332311928, "entropy": 0.08756223320960999, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:36.426476Z", "loop": 9428, "env_steps": 5793177599, "loss": 0.017160428687930107, "avg_return": 0.8617067933082581, "regret": 0.0008944541332311928, "entropy": 0.08623141795396805, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:37.282161Z", "loop": 9429, "env_steps": 5793791999, "loss": 0.018261270597577095, "avg_return": 0.8631638884544373, "regret": 0.0008944541332311928, "entropy": 0.08981157839298248, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:38.176513Z", "loop": 9430, "env_steps": 5794406399, "loss": 0.017883433029055595, "avg_return": 0.8616414666175842, "regret": 0.0017869711155071855, "entropy": 0.0893716886639595, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:39.031283Z", "loop": 9431, "env_steps": 5795020799, "loss": 0.019016513600945473, "avg_return": 0.860551655292511, "regret": 0.0017869711155071855, "entropy": 0.09290739893913269, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:39.885950Z", "loop": 9432, "env_steps": 5795635199, "loss": 0.017472459003329277, "avg_return": 0.8606731295585632, "regret": 0.0017869711155071855, "entropy": 0.09222870320081711, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:40.739500Z", "loop": 9433, "env_steps": 5796249599, "loss": 0.019762566313147545, "avg_return": 0.8604958057403564, "regret": 0.0017869711155071855, "entropy": 0.09579256922006607, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:41.593075Z", "loop": 9434, "env_steps": 5796863999, "loss": 0.019438892602920532, "avg_return": 0.8607479333877563, "regret": 0.0017869711155071855, "entropy": 0.09308235347270966, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:42.447231Z", "loop": 9435, "env_steps": 5797478399, "loss": 0.01770920865237713, "avg_return": 0.8622862100601196, "regret": 0.0017869711155071855, "entropy": 0.08919302374124527, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:43.302195Z", "loop": 9436, "env_steps": 5798092799, "loss": 0.01904044859111309, "avg_return": 0.8636373281478882, "regret": 0.0017869711155071855, "entropy": 0.0917552262544632, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:44.156365Z", "loop": 9437, "env_steps": 5798707199, "loss": 0.018195202574133873, "avg_return": 0.8627183437347412, "regret": 0.0017869711155071855, "entropy": 0.08983185142278671, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:45.009211Z", "loop": 9438, "env_steps": 5799321599, "loss": 0.019436759874224663, "avg_return": 0.8645181655883789, "regret": 0.0017869711155071855, "entropy": 0.09589311480522156, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:45.862852Z", "loop": 9439, "env_steps": 5799935999, "loss": 0.018856780603528023, "avg_return": 0.862871527671814, "regret": 0.0017869711155071855, "entropy": 0.09488332271575928, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:46.757102Z", "loop": 9440, "env_steps": 5800550399, "loss": 0.016912465915083885, "avg_return": 0.8624212741851807, "regret": 0.00017635320546105504, "entropy": 0.08880595117807388, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:47.611213Z", "loop": 9441, "env_steps": 5801164799, "loss": 0.017049303278326988, "avg_return": 0.8632977604866028, "regret": 0.00017635320546105504, "entropy": 0.08656197041273117, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:48.465040Z", "loop": 9442, "env_steps": 5801779199, "loss": 0.017398815602064133, "avg_return": 0.8628996014595032, "regret": 0.00017635320546105504, "entropy": 0.08776285499334335, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:49.319298Z", "loop": 9443, "env_steps": 5802393599, "loss": 0.017737802118062973, "avg_return": 0.8634218573570251, "regret": 0.00017635320546105504, "entropy": 0.08924708515405655, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:50.174074Z", "loop": 9444, "env_steps": 5803007999, "loss": 0.016770441085100174, "avg_return": 0.8631715178489685, "regret": 0.00017635320546105504, "entropy": 0.08632463961839676, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:51.028901Z", "loop": 9445, "env_steps": 5803622399, "loss": 0.018922079354524612, "avg_return": 0.8637038469314575, "regret": 0.00017635320546105504, "entropy": 0.09128693491220474, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:51.882935Z", "loop": 9446, "env_steps": 5804236799, "loss": 0.018847979605197906, "avg_return": 0.8629960417747498, "regret": 0.00017635320546105504, "entropy": 0.09381041675806046, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:52.736126Z", "loop": 9447, "env_steps": 5804851199, "loss": 0.01888298988342285, "avg_return": 0.8627376556396484, "regret": 0.00017635320546105504, "entropy": 0.09207955002784729, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:53.589770Z", "loop": 9448, "env_steps": 5805465599, "loss": 0.01906239055097103, "avg_return": 0.8635227680206299, "regret": 0.00017635320546105504, "entropy": 0.0907215029001236, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:54.444931Z", "loop": 9449, "env_steps": 5806079999, "loss": 0.018122075125575066, "avg_return": 0.8629056811332703, "regret": 0.00017635320546105504, "entropy": 0.09061400592327118, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:55.339684Z", "loop": 9450, "env_steps": 5806694399, "loss": 0.0184614360332489, "avg_return": 0.8624172210693359, "regret": 0.00015358705422841012, "entropy": 0.09303522855043411, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:56.193358Z", "loop": 9451, "env_steps": 5807308799, "loss": 0.017878277227282524, "avg_return": 0.8649585247039795, "regret": 0.00015358705422841012, "entropy": 0.08840055763721466, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:57.048038Z", "loop": 9452, "env_steps": 5807923199, "loss": 0.016843797639012337, "avg_return": 0.8632112741470337, "regret": 0.00015358705422841012, "entropy": 0.08886159956455231, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:57.904102Z", "loop": 9453, "env_steps": 5808537599, "loss": 0.017068324610590935, "avg_return": 0.8625596165657043, "regret": 0.00015358705422841012, "entropy": 0.08558836579322815, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:58.758403Z", "loop": 9454, "env_steps": 5809151999, "loss": 0.016786513850092888, "avg_return": 0.8624323010444641, "regret": 0.00015358705422841012, "entropy": 0.08746397495269775, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:38:59.612471Z", "loop": 9455, "env_steps": 5809766399, "loss": 0.016760386526584625, "avg_return": 0.8623054027557373, "regret": 0.00015358705422841012, "entropy": 0.08779101818799973, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:00.467280Z", "loop": 9456, "env_steps": 5810380799, "loss": 0.016903262585401535, "avg_return": 0.8623486757278442, "regret": 0.00015358705422841012, "entropy": 0.08313985913991928, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:01.322087Z", "loop": 9457, "env_steps": 5810995199, "loss": 0.016026131808757782, "avg_return": 0.8626279830932617, "regret": 0.00015358705422841012, "entropy": 0.08479437232017517, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:02.176765Z", "loop": 9458, "env_steps": 5811609599, "loss": 0.017028359696269035, "avg_return": 0.863156259059906, "regret": 0.00015358705422841012, "entropy": 0.08973319083452225, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:03.032078Z", "loop": 9459, "env_steps": 5812223999, "loss": 0.016359416767954826, "avg_return": 0.8627889156341553, "regret": 0.00015358705422841012, "entropy": 0.08835119754076004, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:03.927771Z", "loop": 9460, "env_steps": 5812838399, "loss": 0.017060501500964165, "avg_return": 0.8626101016998291, "regret": 0.0005843251710757613, "entropy": 0.08818145096302032, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:04.781961Z", "loop": 9461, "env_steps": 5813452799, "loss": 0.0172673799097538, "avg_return": 0.8627166748046875, "regret": 0.0005843251710757613, "entropy": 0.08917474746704102, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:05.636732Z", "loop": 9462, "env_steps": 5814067199, "loss": 0.017082538455724716, "avg_return": 0.8637670874595642, "regret": 0.0005843251710757613, "entropy": 0.08623480796813965, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:06.491302Z", "loop": 9463, "env_steps": 5814681599, "loss": 0.01629834994673729, "avg_return": 0.8634352684020996, "regret": 0.0005843251710757613, "entropy": 0.08698315173387527, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:07.346410Z", "loop": 9464, "env_steps": 5815295999, "loss": 0.01722577027976513, "avg_return": 0.862274169921875, "regret": 0.0005843251710757613, "entropy": 0.08630245178937912, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:08.200786Z", "loop": 9465, "env_steps": 5815910399, "loss": 0.018113965168595314, "avg_return": 0.8635754585266113, "regret": 0.0005843251710757613, "entropy": 0.09022421389818192, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:09.054805Z", "loop": 9466, "env_steps": 5816524799, "loss": 0.017747683450579643, "avg_return": 0.8627013564109802, "regret": 0.0005843251710757613, "entropy": 0.08703078329563141, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:09.909364Z", "loop": 9467, "env_steps": 5817139199, "loss": 0.01802327111363411, "avg_return": 0.8633779287338257, "regret": 0.0005843251710757613, "entropy": 0.09144894033670425, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:10.764094Z", "loop": 9468, "env_steps": 5817753599, "loss": 0.01892940141260624, "avg_return": 0.8630928993225098, "regret": 0.0005843251710757613, "entropy": 0.09226647764444351, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:11.618675Z", "loop": 9469, "env_steps": 5818367999, "loss": 0.017501335591077805, "avg_return": 0.8624569773674011, "regret": 0.0005843251710757613, "entropy": 0.0885126069188118, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:12.513822Z", "loop": 9470, "env_steps": 5818982399, "loss": 0.017571846023201942, "avg_return": 0.862868070602417, "regret": 0.00044330311357043684, "entropy": 0.08696414530277252, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:13.367787Z", "loop": 9471, "env_steps": 5819596799, "loss": 0.017923234030604362, "avg_return": 0.8636733293533325, "regret": 0.00044330311357043684, "entropy": 0.0897815078496933, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:14.222519Z", "loop": 9472, "env_steps": 5820211199, "loss": 0.01707482896745205, "avg_return": 0.864834725856781, "regret": 0.00044330311357043684, "entropy": 0.08532610535621643, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:15.077326Z", "loop": 9473, "env_steps": 5820825599, "loss": 0.017729103565216064, "avg_return": 0.8623468279838562, "regret": 0.00044330311357043684, "entropy": 0.08935821801424026, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:15.931443Z", "loop": 9474, "env_steps": 5821439999, "loss": 0.018117627128958702, "avg_return": 0.8618463277816772, "regret": 0.00044330311357043684, "entropy": 0.08902831375598907, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:16.785098Z", "loop": 9475, "env_steps": 5822054399, "loss": 0.017991557717323303, "avg_return": 0.8625423312187195, "regret": 0.00044330311357043684, "entropy": 0.09066623449325562, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:17.640300Z", "loop": 9476, "env_steps": 5822668799, "loss": 0.017668254673480988, "avg_return": 0.8625413179397583, "regret": 0.00044330311357043684, "entropy": 0.08847013115882874, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:18.495590Z", "loop": 9477, "env_steps": 5823283199, "loss": 0.016516299918293953, "avg_return": 0.8607478141784668, "regret": 0.00044330311357043684, "entropy": 0.08629783242940903, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:19.349998Z", "loop": 9478, "env_steps": 5823897599, "loss": 0.016865568235516548, "avg_return": 0.8633700013160706, "regret": 0.00044330311357043684, "entropy": 0.08150389045476913, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:20.204963Z", "loop": 9479, "env_steps": 5824511999, "loss": 0.017018280923366547, "avg_return": 0.8618170619010925, "regret": 0.00044330311357043684, "entropy": 0.08860728144645691, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:21.099526Z", "loop": 9480, "env_steps": 5825126399, "loss": 0.01646866649389267, "avg_return": 0.8625964522361755, "regret": 0.0013439289759844542, "entropy": 0.08498797565698624, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:21.954389Z", "loop": 9481, "env_steps": 5825740799, "loss": 0.016044555231928825, "avg_return": 0.8617162108421326, "regret": 0.0013439289759844542, "entropy": 0.08687995374202728, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:22.809104Z", "loop": 9482, "env_steps": 5826355199, "loss": 0.017082752659916878, "avg_return": 0.8624579310417175, "regret": 0.0013439289759844542, "entropy": 0.08315467834472656, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:23.662325Z", "loop": 9483, "env_steps": 5826969599, "loss": 0.016283707693219185, "avg_return": 0.862776517868042, "regret": 0.0013439289759844542, "entropy": 0.0845886692404747, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:24.516520Z", "loop": 9484, "env_steps": 5827583999, "loss": 0.014527869410812855, "avg_return": 0.8622292280197144, "regret": 0.0013439289759844542, "entropy": 0.07978612184524536, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:25.370189Z", "loop": 9485, "env_steps": 5828198399, "loss": 0.01505298912525177, "avg_return": 0.8615431785583496, "regret": 0.0013439289759844542, "entropy": 0.0808667540550232, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:26.226636Z", "loop": 9486, "env_steps": 5828812799, "loss": 0.01607968471944332, "avg_return": 0.8621460199356079, "regret": 0.0013439289759844542, "entropy": 0.08447080105543137, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:27.080889Z", "loop": 9487, "env_steps": 5829427199, "loss": 0.015246634371578693, "avg_return": 0.8619897961616516, "regret": 0.0013439289759844542, "entropy": 0.08234687894582748, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:27.933889Z", "loop": 9488, "env_steps": 5830041599, "loss": 0.014774485491216183, "avg_return": 0.8629435300827026, "regret": 0.0013439289759844542, "entropy": 0.08212985098361969, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:28.788216Z", "loop": 9489, "env_steps": 5830655999, "loss": 0.01615077815949917, "avg_return": 0.862932026386261, "regret": 0.0013439289759844542, "entropy": 0.08136159181594849, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:29.683856Z", "loop": 9490, "env_steps": 5831270399, "loss": 0.014430669136345387, "avg_return": 0.8626485466957092, "regret": 0.001012542168609798, "entropy": 0.07771613448858261, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:30.537277Z", "loop": 9491, "env_steps": 5831884799, "loss": 0.014008072204887867, "avg_return": 0.8638291358947754, "regret": 0.001012542168609798, "entropy": 0.07346297800540924, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:31.391718Z", "loop": 9492, "env_steps": 5832499199, "loss": 0.01308418344706297, "avg_return": 0.863120973110199, "regret": 0.001012542168609798, "entropy": 0.07160066068172455, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:32.245548Z", "loop": 9493, "env_steps": 5833113599, "loss": 0.013245046138763428, "avg_return": 0.8612380027770996, "regret": 0.001012542168609798, "entropy": 0.0706171840429306, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:33.099505Z", "loop": 9494, "env_steps": 5833727999, "loss": 0.012242007069289684, "avg_return": 0.8626424074172974, "regret": 0.001012542168609798, "entropy": 0.06669653952121735, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:33.953843Z", "loop": 9495, "env_steps": 5834342399, "loss": 0.012515679001808167, "avg_return": 0.8632566332817078, "regret": 0.001012542168609798, "entropy": 0.06722404807806015, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:34.809632Z", "loop": 9496, "env_steps": 5834956799, "loss": 0.011195290833711624, "avg_return": 0.8630198240280151, "regret": 0.001012542168609798, "entropy": 0.0656731128692627, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:35.663921Z", "loop": 9497, "env_steps": 5835571199, "loss": 0.012468395754694939, "avg_return": 0.8610423803329468, "regret": 0.001012542168609798, "entropy": 0.0709056556224823, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:36.517798Z", "loop": 9498, "env_steps": 5836185599, "loss": 0.012829141691327095, "avg_return": 0.8622546792030334, "regret": 0.001012542168609798, "entropy": 0.06767777353525162, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:37.373019Z", "loop": 9499, "env_steps": 5836799999, "loss": 0.011402575299143791, "avg_return": 0.8628977537155151, "regret": 0.001012542168609798, "entropy": 0.06419174373149872, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:38.267019Z", "loop": 9500, "env_steps": 5837414399, "loss": 0.012320616282522678, "avg_return": 0.8610923290252686, "regret": 0.0013339314609766006, "entropy": 0.06780951470136642, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:39.119753Z", "loop": 9501, "env_steps": 5838028799, "loss": 0.012428266927599907, "avg_return": 0.8621519207954407, "regret": 0.0013339314609766006, "entropy": 0.07064878195524216, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:39.973730Z", "loop": 9502, "env_steps": 5838643199, "loss": 0.013036498799920082, "avg_return": 0.8629302978515625, "regret": 0.0013339314609766006, "entropy": 0.0695345401763916, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:40.829386Z", "loop": 9503, "env_steps": 5839257599, "loss": 0.012189844623208046, "avg_return": 0.8614603877067566, "regret": 0.0013339314609766006, "entropy": 0.06736981123685837, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:41.683726Z", "loop": 9504, "env_steps": 5839871999, "loss": 0.011742238886654377, "avg_return": 0.8618526458740234, "regret": 0.0013339314609766006, "entropy": 0.06493278592824936, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:42.537234Z", "loop": 9505, "env_steps": 5840486399, "loss": 0.011064662598073483, "avg_return": 0.8628359436988831, "regret": 0.0013339314609766006, "entropy": 0.06360505521297455, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:43.390206Z", "loop": 9506, "env_steps": 5841100799, "loss": 0.013065673410892487, "avg_return": 0.8636383414268494, "regret": 0.0013339314609766006, "entropy": 0.06724664568901062, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:44.244374Z", "loop": 9507, "env_steps": 5841715199, "loss": 0.012723212130367756, "avg_return": 0.863616943359375, "regret": 0.0013339314609766006, "entropy": 0.06702645868062973, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:45.099095Z", "loop": 9508, "env_steps": 5842329599, "loss": 0.012489519082009792, "avg_return": 0.8647817373275757, "regret": 0.0013339314609766006, "entropy": 0.06625030189752579, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:45.954131Z", "loop": 9509, "env_steps": 5842943999, "loss": 0.012028112076222897, "avg_return": 0.8620036244392395, "regret": 0.0013339314609766006, "entropy": 0.06667458266019821, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:46.849805Z", "loop": 9510, "env_steps": 5843558399, "loss": 0.013327357359230518, "avg_return": 0.8623982667922974, "regret": 0.0003683442191686481, "entropy": 0.0694703608751297, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:47.704584Z", "loop": 9511, "env_steps": 5844172799, "loss": 0.012938856147229671, "avg_return": 0.8626043796539307, "regret": 0.0003683442191686481, "entropy": 0.07023987919092178, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:48.560280Z", "loop": 9512, "env_steps": 5844787199, "loss": 0.01308014988899231, "avg_return": 0.8642491102218628, "regret": 0.0003683442191686481, "entropy": 0.0695510283112526, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:49.415336Z", "loop": 9513, "env_steps": 5845401599, "loss": 0.013979794457554817, "avg_return": 0.8642354607582092, "regret": 0.0003683442191686481, "entropy": 0.07425066828727722, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:50.270124Z", "loop": 9514, "env_steps": 5846015999, "loss": 0.014654909260571003, "avg_return": 0.8633524775505066, "regret": 0.0003683442191686481, "entropy": 0.07508689910173416, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:51.124643Z", "loop": 9515, "env_steps": 5846630399, "loss": 0.01377823669463396, "avg_return": 0.8636664748191833, "regret": 0.0003683442191686481, "entropy": 0.07468809932470322, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:51.979167Z", "loop": 9516, "env_steps": 5847244799, "loss": 0.0135387247428298, "avg_return": 0.8622350096702576, "regret": 0.0003683442191686481, "entropy": 0.07489896565675735, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:52.834890Z", "loop": 9517, "env_steps": 5847859199, "loss": 0.013268917798995972, "avg_return": 0.8635258078575134, "regret": 0.0003683442191686481, "entropy": 0.07163291424512863, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:53.688460Z", "loop": 9518, "env_steps": 5848473599, "loss": 0.013938580639660358, "avg_return": 0.8624981045722961, "regret": 0.0003683442191686481, "entropy": 0.07495810836553574, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:54.542456Z", "loop": 9519, "env_steps": 5849087999, "loss": 0.012984739616513252, "avg_return": 0.8622058033943176, "regret": 0.0003683442191686481, "entropy": 0.07195128500461578, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:55.437660Z", "loop": 9520, "env_steps": 5849702399, "loss": 0.012928557582199574, "avg_return": 0.8630536198616028, "regret": 0.0004052674921695143, "entropy": 0.06660454720258713, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:56.291031Z", "loop": 9521, "env_steps": 5850316799, "loss": 0.0124996742233634, "avg_return": 0.8642641305923462, "regret": 0.0004052674921695143, "entropy": 0.06629164516925812, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:57.144915Z", "loop": 9522, "env_steps": 5850931199, "loss": 0.011792730540037155, "avg_return": 0.8616511225700378, "regret": 0.0004052674921695143, "entropy": 0.06533213704824448, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:58.000280Z", "loop": 9523, "env_steps": 5851545599, "loss": 0.013076692819595337, "avg_return": 0.861977756023407, "regret": 0.0004052674921695143, "entropy": 0.06732923537492752, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:58.853443Z", "loop": 9524, "env_steps": 5852159999, "loss": 0.012647747062146664, "avg_return": 0.8642780780792236, "regret": 0.0004052674921695143, "entropy": 0.06811337918043137, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:39:59.706614Z", "loop": 9525, "env_steps": 5852774399, "loss": 0.012226162478327751, "avg_return": 0.8630245923995972, "regret": 0.0004052674921695143, "entropy": 0.06665784120559692, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:00.560511Z", "loop": 9526, "env_steps": 5853388799, "loss": 0.012062310241162777, "avg_return": 0.8626568913459778, "regret": 0.0004052674921695143, "entropy": 0.06443276256322861, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:01.416165Z", "loop": 9527, "env_steps": 5854003199, "loss": 0.012257218360900879, "avg_return": 0.863348126411438, "regret": 0.0004052674921695143, "entropy": 0.06617426872253418, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:02.271787Z", "loop": 9528, "env_steps": 5854617599, "loss": 0.011962874792516232, "avg_return": 0.860893189907074, "regret": 0.0004052674921695143, "entropy": 0.06794121116399765, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:03.125393Z", "loop": 9529, "env_steps": 5855231999, "loss": 0.013119897805154324, "avg_return": 0.8611304759979248, "regret": 0.0004052674921695143, "entropy": 0.07060813903808594, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:04.019762Z", "loop": 9530, "env_steps": 5855846399, "loss": 0.012847363948822021, "avg_return": 0.8623181581497192, "regret": 0.0016627280274406075, "entropy": 0.07070357352495193, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:04.874354Z", "loop": 9531, "env_steps": 5856460799, "loss": 0.013042792677879333, "avg_return": 0.8614762425422668, "regret": 0.0016627280274406075, "entropy": 0.07181556522846222, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:05.728347Z", "loop": 9532, "env_steps": 5857075199, "loss": 0.013364933431148529, "avg_return": 0.8623659610748291, "regret": 0.0016627280274406075, "entropy": 0.07381273061037064, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:06.581351Z", "loop": 9533, "env_steps": 5857689599, "loss": 0.013306825421750546, "avg_return": 0.8610576391220093, "regret": 0.0016627280274406075, "entropy": 0.0724843367934227, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:07.434749Z", "loop": 9534, "env_steps": 5858303999, "loss": 0.012790299952030182, "avg_return": 0.8603165149688721, "regret": 0.0016627280274406075, "entropy": 0.06950026750564575, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:08.288674Z", "loop": 9535, "env_steps": 5858918399, "loss": 0.014211065135896206, "avg_return": 0.8590339422225952, "regret": 0.0016627280274406075, "entropy": 0.07424657791852951, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:09.142009Z", "loop": 9536, "env_steps": 5859532799, "loss": 0.012514166533946991, "avg_return": 0.8586455583572388, "regret": 0.0016627280274406075, "entropy": 0.06934807449579239, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:09.995725Z", "loop": 9537, "env_steps": 5860147199, "loss": 0.012306521646678448, "avg_return": 0.8621236085891724, "regret": 0.0016627280274406075, "entropy": 0.06831497699022293, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:10.850869Z", "loop": 9538, "env_steps": 5860761599, "loss": 0.012412644922733307, "avg_return": 0.8613878488540649, "regret": 0.0016627280274406075, "entropy": 0.06890519708395004, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:11.706823Z", "loop": 9539, "env_steps": 5861375999, "loss": 0.012441882863640785, "avg_return": 0.861579418182373, "regret": 0.0016627280274406075, "entropy": 0.0655016079545021, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:12.601119Z", "loop": 9540, "env_steps": 5861990399, "loss": 0.012351750396192074, "avg_return": 0.8618597388267517, "regret": 0.0018283671233803034, "entropy": 0.06603524088859558, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:13.455616Z", "loop": 9541, "env_steps": 5862604799, "loss": 0.011969110928475857, "avg_return": 0.8613232374191284, "regret": 0.0018283671233803034, "entropy": 0.067855104804039, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:14.310181Z", "loop": 9542, "env_steps": 5863219199, "loss": 0.013088586740195751, "avg_return": 0.8625466227531433, "regret": 0.0018283671233803034, "entropy": 0.06947697699069977, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:15.165502Z", "loop": 9543, "env_steps": 5863833599, "loss": 0.012093868106603622, "avg_return": 0.861859142780304, "regret": 0.0018283671233803034, "entropy": 0.06705233454704285, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:16.018903Z", "loop": 9544, "env_steps": 5864447999, "loss": 0.012601526454091072, "avg_return": 0.8616729974746704, "regret": 0.0018283671233803034, "entropy": 0.06811320036649704, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:16.872750Z", "loop": 9545, "env_steps": 5865062399, "loss": 0.012349817901849747, "avg_return": 0.8631455898284912, "regret": 0.0018283671233803034, "entropy": 0.07005210220813751, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:17.726715Z", "loop": 9546, "env_steps": 5865676799, "loss": 0.013119257986545563, "avg_return": 0.8638635277748108, "regret": 0.0018283671233803034, "entropy": 0.0691867545247078, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:18.580381Z", "loop": 9547, "env_steps": 5866291199, "loss": 0.013735917396843433, "avg_return": 0.8624100685119629, "regret": 0.0018283671233803034, "entropy": 0.07173150032758713, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:19.435162Z", "loop": 9548, "env_steps": 5866905599, "loss": 0.015315055847167969, "avg_return": 0.861988365650177, "regret": 0.0018283671233803034, "entropy": 0.08084841072559357, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:20.289677Z", "loop": 9549, "env_steps": 5867519999, "loss": 0.01631893776357174, "avg_return": 0.8618191480636597, "regret": 0.0018283671233803034, "entropy": 0.08255395293235779, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:21.185230Z", "loop": 9550, "env_steps": 5868134399, "loss": 0.015207330696284771, "avg_return": 0.8610050678253174, "regret": 0.0015603307401761413, "entropy": 0.08225693553686142, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:22.039693Z", "loop": 9551, "env_steps": 5868748799, "loss": 0.016585128381848335, "avg_return": 0.8605140447616577, "regret": 0.0015603307401761413, "entropy": 0.08894871175289154, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:22.894011Z", "loop": 9552, "env_steps": 5869363199, "loss": 0.017273081466555595, "avg_return": 0.8603924512863159, "regret": 0.0015603307401761413, "entropy": 0.09240730851888657, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:23.748289Z", "loop": 9553, "env_steps": 5869977599, "loss": 0.019576681777834892, "avg_return": 0.8582350015640259, "regret": 0.0015603307401761413, "entropy": 0.09711293131113052, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:24.603054Z", "loop": 9554, "env_steps": 5870591999, "loss": 0.020890094339847565, "avg_return": 0.8562825918197632, "regret": 0.0015603307401761413, "entropy": 0.10174726694822311, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:25.457742Z", "loop": 9555, "env_steps": 5871206399, "loss": 0.02349095605313778, "avg_return": 0.8554104566574097, "regret": 0.0015603307401761413, "entropy": 0.1112770289182663, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:26.310962Z", "loop": 9556, "env_steps": 5871820799, "loss": 0.022514596581459045, "avg_return": 0.8556469082832336, "regret": 0.0015603307401761413, "entropy": 0.1105564758181572, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:27.164394Z", "loop": 9557, "env_steps": 5872435199, "loss": 0.02219538204371929, "avg_return": 0.8560246229171753, "regret": 0.0015603307401761413, "entropy": 0.10813982784748077, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:28.020067Z", "loop": 9558, "env_steps": 5873049599, "loss": 0.020940987393260002, "avg_return": 0.8567650318145752, "regret": 0.0015603307401761413, "entropy": 0.10060279071331024, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:28.875303Z", "loop": 9559, "env_steps": 5873663999, "loss": 0.020718663930892944, "avg_return": 0.8588940501213074, "regret": 0.0015603307401761413, "entropy": 0.0995151624083519, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:29.770460Z", "loop": 9560, "env_steps": 5874278399, "loss": 0.019171079620718956, "avg_return": 0.8590172529220581, "regret": 0.0039194743148982525, "entropy": 0.096619613468647, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:30.624572Z", "loop": 9561, "env_steps": 5874892799, "loss": 0.018775897100567818, "avg_return": 0.8607245087623596, "regret": 0.0039194743148982525, "entropy": 0.09287548810243607, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:31.479265Z", "loop": 9562, "env_steps": 5875507199, "loss": 0.018655329942703247, "avg_return": 0.8604980707168579, "regret": 0.0039194743148982525, "entropy": 0.09655123203992844, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:32.333047Z", "loop": 9563, "env_steps": 5876121599, "loss": 0.019724620506167412, "avg_return": 0.8613747358322144, "regret": 0.0039194743148982525, "entropy": 0.10216470062732697, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:33.186372Z", "loop": 9564, "env_steps": 5876735999, "loss": 0.020749399438500404, "avg_return": 0.8620004653930664, "regret": 0.0039194743148982525, "entropy": 0.10527369379997253, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:34.039555Z", "loop": 9565, "env_steps": 5877350399, "loss": 0.01802474446594715, "avg_return": 0.8612958192825317, "regret": 0.0039194743148982525, "entropy": 0.09511909633874893, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:34.893941Z", "loop": 9566, "env_steps": 5877964799, "loss": 0.018490668386220932, "avg_return": 0.8609734177589417, "regret": 0.0039194743148982525, "entropy": 0.09002946317195892, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:35.748031Z", "loop": 9567, "env_steps": 5878579199, "loss": 0.018172714859247208, "avg_return": 0.8615896701812744, "regret": 0.0039194743148982525, "entropy": 0.09338796138763428, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:36.601861Z", "loop": 9568, "env_steps": 5879193599, "loss": 0.018212448805570602, "avg_return": 0.8622809052467346, "regret": 0.0039194743148982525, "entropy": 0.09432444721460342, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:37.456321Z", "loop": 9569, "env_steps": 5879807999, "loss": 0.01977524533867836, "avg_return": 0.862733781337738, "regret": 0.0039194743148982525, "entropy": 0.10344844311475754, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:38.351353Z", "loop": 9570, "env_steps": 5880422399, "loss": 0.02079991064965725, "avg_return": 0.8622312545776367, "regret": 0.000927237153518945, "entropy": 0.10607929527759552, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:39.204798Z", "loop": 9571, "env_steps": 5881036799, "loss": 0.022493062540888786, "avg_return": 0.8625227212905884, "regret": 0.000927237153518945, "entropy": 0.11015696823596954, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:40.059258Z", "loop": 9572, "env_steps": 5881651199, "loss": 0.024451086297631264, "avg_return": 0.8627252578735352, "regret": 0.000927237153518945, "entropy": 0.12102355062961578, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:40.913006Z", "loop": 9573, "env_steps": 5882265599, "loss": 0.025862524285912514, "avg_return": 0.8619588613510132, "regret": 0.000927237153518945, "entropy": 0.1314104050397873, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:41.766691Z", "loop": 9574, "env_steps": 5882879999, "loss": 0.028524253517389297, "avg_return": 0.860945463180542, "regret": 0.000927237153518945, "entropy": 0.14132951200008392, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:42.619855Z", "loop": 9575, "env_steps": 5883494399, "loss": 0.02892826870083809, "avg_return": 0.8624818325042725, "regret": 0.000927237153518945, "entropy": 0.14474709331989288, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:43.473944Z", "loop": 9576, "env_steps": 5884108799, "loss": 0.02816365659236908, "avg_return": 0.8622648119926453, "regret": 0.000927237153518945, "entropy": 0.14431270956993103, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:44.327407Z", "loop": 9577, "env_steps": 5884723199, "loss": 0.02845393680036068, "avg_return": 0.8617183566093445, "regret": 0.000927237153518945, "entropy": 0.14232750236988068, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:45.181572Z", "loop": 9578, "env_steps": 5885337599, "loss": 0.029213203117251396, "avg_return": 0.8617342114448547, "regret": 0.000927237153518945, "entropy": 0.1439753621816635, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:46.035179Z", "loop": 9579, "env_steps": 5885951999, "loss": 0.030085274949669838, "avg_return": 0.8625394105911255, "regret": 0.000927237153518945, "entropy": 0.1468360871076584, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:46.929607Z", "loop": 9580, "env_steps": 5886566399, "loss": 0.029017260298132896, "avg_return": 0.8606139421463013, "regret": 0.002185097197070718, "entropy": 0.14342962205410004, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:47.783004Z", "loop": 9581, "env_steps": 5887180799, "loss": 0.028122399002313614, "avg_return": 0.8618274331092834, "regret": 0.002185097197070718, "entropy": 0.14378048479557037, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:48.637695Z", "loop": 9582, "env_steps": 5887795199, "loss": 0.026372132822871208, "avg_return": 0.860835075378418, "regret": 0.002185097197070718, "entropy": 0.13811315596103668, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:49.490946Z", "loop": 9583, "env_steps": 5888409599, "loss": 0.02714938297867775, "avg_return": 0.8615108728408813, "regret": 0.002185097197070718, "entropy": 0.13811378180980682, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:50.344541Z", "loop": 9584, "env_steps": 5889023999, "loss": 0.02792222797870636, "avg_return": 0.8601347208023071, "regret": 0.002185097197070718, "entropy": 0.14179274439811707, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:51.198950Z", "loop": 9585, "env_steps": 5889638399, "loss": 0.02753129042685032, "avg_return": 0.8620280027389526, "regret": 0.002185097197070718, "entropy": 0.14030253887176514, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:52.052685Z", "loop": 9586, "env_steps": 5890252799, "loss": 0.02739153802394867, "avg_return": 0.8601943254470825, "regret": 0.002185097197070718, "entropy": 0.14240309596061707, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:52.907295Z", "loop": 9587, "env_steps": 5890867199, "loss": 0.027973461896181107, "avg_return": 0.8603149652481079, "regret": 0.002185097197070718, "entropy": 0.14557498693466187, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:53.761129Z", "loop": 9588, "env_steps": 5891481599, "loss": 0.026222605258226395, "avg_return": 0.8604903221130371, "regret": 0.002185097197070718, "entropy": 0.13657358288764954, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:54.615478Z", "loop": 9589, "env_steps": 5892095999, "loss": 0.02348872646689415, "avg_return": 0.8606734275817871, "regret": 0.002185097197070718, "entropy": 0.12791599333286285, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:55.510834Z", "loop": 9590, "env_steps": 5892710399, "loss": 0.024746904149651527, "avg_return": 0.8606444597244263, "regret": 0.0026270770467817783, "entropy": 0.12356626987457275, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:56.364844Z", "loop": 9591, "env_steps": 5893324799, "loss": 0.022165687754750252, "avg_return": 0.8610066175460815, "regret": 0.0026270770467817783, "entropy": 0.11918093264102936, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:57.217920Z", "loop": 9592, "env_steps": 5893939199, "loss": 0.021903403103351593, "avg_return": 0.8613235950469971, "regret": 0.0026270770467817783, "entropy": 0.11078480631113052, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:58.071250Z", "loop": 9593, "env_steps": 5894553599, "loss": 0.021845201030373573, "avg_return": 0.859585165977478, "regret": 0.0026270770467817783, "entropy": 0.11220060288906097, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:58.925607Z", "loop": 9594, "env_steps": 5895167999, "loss": 0.02063189446926117, "avg_return": 0.8597003221511841, "regret": 0.0026270770467817783, "entropy": 0.10918959230184555, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:40:59.779599Z", "loop": 9595, "env_steps": 5895782399, "loss": 0.02040388621389866, "avg_return": 0.8593064546585083, "regret": 0.0026270770467817783, "entropy": 0.1091884970664978, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:00.633204Z", "loop": 9596, "env_steps": 5896396799, "loss": 0.021052462980151176, "avg_return": 0.8577120304107666, "regret": 0.0026270770467817783, "entropy": 0.10783432424068451, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:01.487860Z", "loop": 9597, "env_steps": 5897011199, "loss": 0.02139243483543396, "avg_return": 0.8561779260635376, "regret": 0.0026270770467817783, "entropy": 0.10706688463687897, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:02.341849Z", "loop": 9598, "env_steps": 5897625599, "loss": 0.021715812385082245, "avg_return": 0.8541721701622009, "regret": 0.0026270770467817783, "entropy": 0.1125025525689125, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:03.195963Z", "loop": 9599, "env_steps": 5898239999, "loss": 0.02223663590848446, "avg_return": 0.8561002016067505, "regret": 0.0026270770467817783, "entropy": 0.11449674516916275, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:04.089305Z", "loop": 9600, "env_steps": 5898854399, "loss": 0.0234422255307436, "avg_return": 0.8569918274879456, "regret": 0.006986659485846758, "entropy": 0.11772089451551437, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:04.942734Z", "loop": 9601, "env_steps": 5899468799, "loss": 0.024133939296007156, "avg_return": 0.8584535121917725, "regret": 0.006986659485846758, "entropy": 0.11841260641813278, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:05.796730Z", "loop": 9602, "env_steps": 5900083199, "loss": 0.024589261040091515, "avg_return": 0.859096109867096, "regret": 0.006986659485846758, "entropy": 0.12147644907236099, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:06.650754Z", "loop": 9603, "env_steps": 5900697599, "loss": 0.02555507980287075, "avg_return": 0.8613079786300659, "regret": 0.006986659485846758, "entropy": 0.12826313078403473, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:07.504113Z", "loop": 9604, "env_steps": 5901311999, "loss": 0.02461455948650837, "avg_return": 0.8620741963386536, "regret": 0.006986659485846758, "entropy": 0.11902504414319992, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:08.358093Z", "loop": 9605, "env_steps": 5901926399, "loss": 0.020381905138492584, "avg_return": 0.8635912537574768, "regret": 0.006986659485846758, "entropy": 0.10287513583898544, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:09.211094Z", "loop": 9606, "env_steps": 5902540799, "loss": 0.017006538808345795, "avg_return": 0.8645390868186951, "regret": 0.006986659485846758, "entropy": 0.09132643043994904, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:10.065792Z", "loop": 9607, "env_steps": 5903155199, "loss": 0.015893494710326195, "avg_return": 0.8643123507499695, "regret": 0.006986659485846758, "entropy": 0.08171292394399643, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:10.919845Z", "loop": 9608, "env_steps": 5903769599, "loss": 0.017012305557727814, "avg_return": 0.8624686002731323, "regret": 0.006986659485846758, "entropy": 0.08697299659252167, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:11.774266Z", "loop": 9609, "env_steps": 5904383999, "loss": 0.01824333332479, "avg_return": 0.8631260395050049, "regret": 0.006986659485846758, "entropy": 0.09051426500082016, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:12.667182Z", "loop": 9610, "env_steps": 5904998399, "loss": 0.0184223223477602, "avg_return": 0.8635809421539307, "regret": 0.00025293033104389906, "entropy": 0.0901750698685646, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:13.520522Z", "loop": 9611, "env_steps": 5905612799, "loss": 0.01725906692445278, "avg_return": 0.8636305928230286, "regret": 0.00025293033104389906, "entropy": 0.08571753650903702, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:14.375003Z", "loop": 9612, "env_steps": 5906227199, "loss": 0.017802977934479713, "avg_return": 0.8630815744400024, "regret": 0.00025293033104389906, "entropy": 0.08601811528205872, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:15.230129Z", "loop": 9613, "env_steps": 5906841599, "loss": 0.01695532165467739, "avg_return": 0.862130343914032, "regret": 0.00025293033104389906, "entropy": 0.08474622666835785, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:16.084039Z", "loop": 9614, "env_steps": 5907455999, "loss": 0.017970001325011253, "avg_return": 0.8616315126419067, "regret": 0.00025293033104389906, "entropy": 0.09016599506139755, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:16.938343Z", "loop": 9615, "env_steps": 5908070399, "loss": 0.016700761392712593, "avg_return": 0.8605337738990784, "regret": 0.00025293033104389906, "entropy": 0.088734932243824, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:17.792326Z", "loop": 9616, "env_steps": 5908684799, "loss": 0.015742111951112747, "avg_return": 0.8611812591552734, "regret": 0.00025293033104389906, "entropy": 0.0830976814031601, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:18.647634Z", "loop": 9617, "env_steps": 5909299199, "loss": 0.018199853599071503, "avg_return": 0.8600772023200989, "regret": 0.00025293033104389906, "entropy": 0.08973972499370575, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:19.502678Z", "loop": 9618, "env_steps": 5909913599, "loss": 0.01791941188275814, "avg_return": 0.8620127439498901, "regret": 0.00025293033104389906, "entropy": 0.08871740847826004, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:20.355622Z", "loop": 9619, "env_steps": 5910527999, "loss": 0.01634473167359829, "avg_return": 0.8618019819259644, "regret": 0.00025293033104389906, "entropy": 0.08617522567510605, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:21.247716Z", "loop": 9620, "env_steps": 5911142399, "loss": 0.01686864160001278, "avg_return": 0.862078070640564, "regret": 0.0008812693995423615, "entropy": 0.08548255264759064, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:22.102542Z", "loop": 9621, "env_steps": 5911756799, "loss": 0.016355616971850395, "avg_return": 0.8630402684211731, "regret": 0.0008812693995423615, "entropy": 0.0846942663192749, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:22.957723Z", "loop": 9622, "env_steps": 5912371199, "loss": 0.01642276905477047, "avg_return": 0.8634788393974304, "regret": 0.0008812693995423615, "entropy": 0.08265883475542068, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:23.811264Z", "loop": 9623, "env_steps": 5912985599, "loss": 0.017472749575972557, "avg_return": 0.8633955121040344, "regret": 0.0008812693995423615, "entropy": 0.08081647753715515, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:24.665371Z", "loop": 9624, "env_steps": 5913599999, "loss": 0.017021922394633293, "avg_return": 0.8638344407081604, "regret": 0.0008812693995423615, "entropy": 0.08583364635705948, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:25.519598Z", "loop": 9625, "env_steps": 5914214399, "loss": 0.017729056999087334, "avg_return": 0.861769437789917, "regret": 0.0008812693995423615, "entropy": 0.08945433795452118, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:26.372934Z", "loop": 9626, "env_steps": 5914828799, "loss": 0.01784818433225155, "avg_return": 0.8642236590385437, "regret": 0.0008812693995423615, "entropy": 0.08556988090276718, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:27.226932Z", "loop": 9627, "env_steps": 5915443199, "loss": 0.0183089692145586, "avg_return": 0.863341212272644, "regret": 0.0008812693995423615, "entropy": 0.09068816900253296, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:28.080532Z", "loop": 9628, "env_steps": 5916057599, "loss": 0.017013227567076683, "avg_return": 0.862044095993042, "regret": 0.0008812693995423615, "entropy": 0.08648598194122314, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:28.934325Z", "loop": 9629, "env_steps": 5916671999, "loss": 0.016384005546569824, "avg_return": 0.8627043962478638, "regret": 0.0008812693995423615, "entropy": 0.08525609970092773, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:29.827767Z", "loop": 9630, "env_steps": 5917286399, "loss": 0.01655229926109314, "avg_return": 0.862790048122406, "regret": 0.0006539209862239659, "entropy": 0.08455097675323486, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:30.681338Z", "loop": 9631, "env_steps": 5917900799, "loss": 0.01631859503686428, "avg_return": 0.8643674850463867, "regret": 0.0006539209862239659, "entropy": 0.08270033448934555, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:31.535688Z", "loop": 9632, "env_steps": 5918515199, "loss": 0.016041850671172142, "avg_return": 0.8633752465248108, "regret": 0.0006539209862239659, "entropy": 0.08107444643974304, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:32.389018Z", "loop": 9633, "env_steps": 5919129599, "loss": 0.016608212143182755, "avg_return": 0.8641299605369568, "regret": 0.0006539209862239659, "entropy": 0.08379663527011871, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:33.242696Z", "loop": 9634, "env_steps": 5919743999, "loss": 0.016432614997029305, "avg_return": 0.8637451529502869, "regret": 0.0006539209862239659, "entropy": 0.07969251275062561, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:34.096611Z", "loop": 9635, "env_steps": 5920358399, "loss": 0.01664305478334427, "avg_return": 0.8626959323883057, "regret": 0.0006539209862239659, "entropy": 0.08379044383764267, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:34.951042Z", "loop": 9636, "env_steps": 5920972799, "loss": 0.01540413498878479, "avg_return": 0.8628227114677429, "regret": 0.0006539209862239659, "entropy": 0.07888689637184143, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:35.805244Z", "loop": 9637, "env_steps": 5921587199, "loss": 0.01624283753335476, "avg_return": 0.863727331161499, "regret": 0.0006539209862239659, "entropy": 0.08060899376869202, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:36.658328Z", "loop": 9638, "env_steps": 5922201599, "loss": 0.01604512147605419, "avg_return": 0.8649275898933411, "regret": 0.0006539209862239659, "entropy": 0.0802980437874794, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:37.512487Z", "loop": 9639, "env_steps": 5922815999, "loss": 0.01635933667421341, "avg_return": 0.8616068959236145, "regret": 0.0006539209862239659, "entropy": 0.08013971149921417, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:38.407413Z", "loop": 9640, "env_steps": 5923430399, "loss": 0.015658652409911156, "avg_return": 0.8637025952339172, "regret": 0.00036548220668919384, "entropy": 0.08064267039299011, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:39.261480Z", "loop": 9641, "env_steps": 5924044799, "loss": 0.016002602875232697, "avg_return": 0.8618780970573425, "regret": 0.00036548220668919384, "entropy": 0.08268255740404129, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:40.115057Z", "loop": 9642, "env_steps": 5924659199, "loss": 0.016535134986042976, "avg_return": 0.8625574111938477, "regret": 0.00036548220668919384, "entropy": 0.08068425953388214, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:40.970155Z", "loop": 9643, "env_steps": 5925273599, "loss": 0.017074206843972206, "avg_return": 0.8632712960243225, "regret": 0.00036548220668919384, "entropy": 0.08424322307109833, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:41.825428Z", "loop": 9644, "env_steps": 5925887999, "loss": 0.017332887277007103, "avg_return": 0.8632429242134094, "regret": 0.00036548220668919384, "entropy": 0.08215507864952087, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:42.679420Z", "loop": 9645, "env_steps": 5926502399, "loss": 0.017642401158809662, "avg_return": 0.8624186515808105, "regret": 0.00036548220668919384, "entropy": 0.08739365637302399, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:43.533582Z", "loop": 9646, "env_steps": 5927116799, "loss": 0.018008027225732803, "avg_return": 0.8639636635780334, "regret": 0.00036548220668919384, "entropy": 0.08775827288627625, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:44.388207Z", "loop": 9647, "env_steps": 5927731199, "loss": 0.017504071816802025, "avg_return": 0.8630843162536621, "regret": 0.00036548220668919384, "entropy": 0.08638795465230942, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:45.243778Z", "loop": 9648, "env_steps": 5928345599, "loss": 0.01621594838798046, "avg_return": 0.8630785346031189, "regret": 0.00036548220668919384, "entropy": 0.08395249396562576, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:46.099816Z", "loop": 9649, "env_steps": 5928959999, "loss": 0.01743585802614689, "avg_return": 0.8637427687644958, "regret": 0.00036548220668919384, "entropy": 0.08500292152166367, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:46.993815Z", "loop": 9650, "env_steps": 5929574399, "loss": 0.016764814034104347, "avg_return": 0.8633280396461487, "regret": 0.00027288973797112703, "entropy": 0.08033976703882217, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:47.847291Z", "loop": 9651, "env_steps": 5930188799, "loss": 0.015715157613158226, "avg_return": 0.8623295426368713, "regret": 0.00027288973797112703, "entropy": 0.07935139536857605, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:48.701553Z", "loop": 9652, "env_steps": 5930803199, "loss": 0.01591949723660946, "avg_return": 0.8641781806945801, "regret": 0.00027288973797112703, "entropy": 0.07896407693624496, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:49.556173Z", "loop": 9653, "env_steps": 5931417599, "loss": 0.01638263277709484, "avg_return": 0.8643641471862793, "regret": 0.00027288973797112703, "entropy": 0.08253659307956696, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:50.410062Z", "loop": 9654, "env_steps": 5932031999, "loss": 0.018463900312781334, "avg_return": 0.8629573583602905, "regret": 0.00027288973797112703, "entropy": 0.0893562063574791, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:51.263517Z", "loop": 9655, "env_steps": 5932646399, "loss": 0.017013823613524437, "avg_return": 0.8625273108482361, "regret": 0.00027288973797112703, "entropy": 0.08385064452886581, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:52.119367Z", "loop": 9656, "env_steps": 5933260799, "loss": 0.016434360295534134, "avg_return": 0.8638981580734253, "regret": 0.00027288973797112703, "entropy": 0.08217482268810272, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:52.974633Z", "loop": 9657, "env_steps": 5933875199, "loss": 0.016701344400644302, "avg_return": 0.8628851771354675, "regret": 0.00027288973797112703, "entropy": 0.08452127873897552, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:53.829599Z", "loop": 9658, "env_steps": 5934489599, "loss": 0.01756773144006729, "avg_return": 0.8596969842910767, "regret": 0.00027288973797112703, "entropy": 0.08886987715959549, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:54.683806Z", "loop": 9659, "env_steps": 5935103999, "loss": 0.019149458035826683, "avg_return": 0.8604233860969543, "regret": 0.00027288973797112703, "entropy": 0.0943911075592041, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:55.580711Z", "loop": 9660, "env_steps": 5935718399, "loss": 0.0186923798173666, "avg_return": 0.8594555854797363, "regret": 0.0044276099652051926, "entropy": 0.09367569535970688, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:56.434357Z", "loop": 9661, "env_steps": 5936332799, "loss": 0.02008768729865551, "avg_return": 0.8592047095298767, "regret": 0.0044276099652051926, "entropy": 0.09676722437143326, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:57.289051Z", "loop": 9662, "env_steps": 5936947199, "loss": 0.019867125898599625, "avg_return": 0.858001708984375, "regret": 0.0044276099652051926, "entropy": 0.09580803662538528, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:58.143455Z", "loop": 9663, "env_steps": 5937561599, "loss": 0.018896963447332382, "avg_return": 0.8569432497024536, "regret": 0.0044276099652051926, "entropy": 0.09515834599733353, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:58.998527Z", "loop": 9664, "env_steps": 5938175999, "loss": 0.020185260102152824, "avg_return": 0.8581463694572449, "regret": 0.0044276099652051926, "entropy": 0.09469306468963623, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:41:59.852586Z", "loop": 9665, "env_steps": 5938790399, "loss": 0.018889104947447777, "avg_return": 0.8595114350318909, "regret": 0.0044276099652051926, "entropy": 0.09238807111978531, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:00.707945Z", "loop": 9666, "env_steps": 5939404799, "loss": 0.01934863068163395, "avg_return": 0.8622522950172424, "regret": 0.0044276099652051926, "entropy": 0.09215957671403885, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:01.562252Z", "loop": 9667, "env_steps": 5940019199, "loss": 0.017968403175473213, "avg_return": 0.8612349629402161, "regret": 0.0044276099652051926, "entropy": 0.08580122143030167, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:02.418055Z", "loop": 9668, "env_steps": 5940633599, "loss": 0.01758628711104393, "avg_return": 0.8632204532623291, "regret": 0.0044276099652051926, "entropy": 0.08819596469402313, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:03.271989Z", "loop": 9669, "env_steps": 5941247999, "loss": 0.01892242766916752, "avg_return": 0.8621290326118469, "regret": 0.0044276099652051926, "entropy": 0.09447595477104187, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:04.165063Z", "loop": 9670, "env_steps": 5941862399, "loss": 0.017108777537941933, "avg_return": 0.8636026978492737, "regret": 0.0002301494823768735, "entropy": 0.0878659263253212, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:05.019456Z", "loop": 9671, "env_steps": 5942476799, "loss": 0.016484234482049942, "avg_return": 0.8644832372665405, "regret": 0.0002301494823768735, "entropy": 0.08336622267961502, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:05.874630Z", "loop": 9672, "env_steps": 5943091199, "loss": 0.016321778297424316, "avg_return": 0.8640671968460083, "regret": 0.0002301494823768735, "entropy": 0.08539573848247528, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:06.729377Z", "loop": 9673, "env_steps": 5943705599, "loss": 0.016278693452477455, "avg_return": 0.8629602193832397, "regret": 0.0002301494823768735, "entropy": 0.08571898937225342, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:07.583939Z", "loop": 9674, "env_steps": 5944319999, "loss": 0.01662355102598667, "avg_return": 0.8632583022117615, "regret": 0.0002301494823768735, "entropy": 0.08438722789287567, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:08.439402Z", "loop": 9675, "env_steps": 5944934399, "loss": 0.018517786636948586, "avg_return": 0.8622310757637024, "regret": 0.0002301494823768735, "entropy": 0.09032942354679108, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:09.295257Z", "loop": 9676, "env_steps": 5945548799, "loss": 0.01851177029311657, "avg_return": 0.8619110584259033, "regret": 0.0002301494823768735, "entropy": 0.09466316550970078, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:10.150337Z", "loop": 9677, "env_steps": 5946163199, "loss": 0.018734483048319817, "avg_return": 0.8616915345191956, "regret": 0.0002301494823768735, "entropy": 0.09474610537290573, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:11.003525Z", "loop": 9678, "env_steps": 5946777599, "loss": 0.019353283569216728, "avg_return": 0.8608160614967346, "regret": 0.0002301494823768735, "entropy": 0.09644569456577301, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:11.856746Z", "loop": 9679, "env_steps": 5947391999, "loss": 0.01858334429562092, "avg_return": 0.8577114343643188, "regret": 0.0002301494823768735, "entropy": 0.09516438096761703, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:12.751853Z", "loop": 9680, "env_steps": 5948006399, "loss": 0.019726695492863655, "avg_return": 0.857333779335022, "regret": 0.006444703321903944, "entropy": 0.09765172749757767, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:13.606678Z", "loop": 9681, "env_steps": 5948620799, "loss": 0.01859222911298275, "avg_return": 0.8594861030578613, "regret": 0.006444703321903944, "entropy": 0.0940384566783905, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:14.461375Z", "loop": 9682, "env_steps": 5949235199, "loss": 0.017662061378359795, "avg_return": 0.8607935905456543, "regret": 0.006444703321903944, "entropy": 0.09029476344585419, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:15.315182Z", "loop": 9683, "env_steps": 5949849599, "loss": 0.016747498884797096, "avg_return": 0.8606427311897278, "regret": 0.006444703321903944, "entropy": 0.08545753359794617, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:16.169760Z", "loop": 9684, "env_steps": 5950463999, "loss": 0.016818305477499962, "avg_return": 0.8616355657577515, "regret": 0.006444703321903944, "entropy": 0.08500083535909653, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:17.025372Z", "loop": 9685, "env_steps": 5951078399, "loss": 0.016669854521751404, "avg_return": 0.8630736470222473, "regret": 0.006444703321903944, "entropy": 0.08308407664299011, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:17.880427Z", "loop": 9686, "env_steps": 5951692799, "loss": 0.017252018675208092, "avg_return": 0.862489640712738, "regret": 0.006444703321903944, "entropy": 0.08559457957744598, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:18.733856Z", "loop": 9687, "env_steps": 5952307199, "loss": 0.017089523375034332, "avg_return": 0.8627041578292847, "regret": 0.006444703321903944, "entropy": 0.08330956101417542, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:19.587879Z", "loop": 9688, "env_steps": 5952921599, "loss": 0.018383577466011047, "avg_return": 0.8637136220932007, "regret": 0.006444703321903944, "entropy": 0.08658631891012192, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:20.441894Z", "loop": 9689, "env_steps": 5953535999, "loss": 0.017458977177739143, "avg_return": 0.8638010621070862, "regret": 0.006444703321903944, "entropy": 0.08830919116735458, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:21.338243Z", "loop": 9690, "env_steps": 5954150399, "loss": 0.017272530123591423, "avg_return": 0.8637431263923645, "regret": 0.00012759647506754845, "entropy": 0.08580009639263153, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:22.193241Z", "loop": 9691, "env_steps": 5954764799, "loss": 0.01652016118168831, "avg_return": 0.8608816862106323, "regret": 0.00012759647506754845, "entropy": 0.08439426124095917, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:23.048123Z", "loop": 9692, "env_steps": 5955379199, "loss": 0.017606621608138084, "avg_return": 0.8643396496772766, "regret": 0.00012759647506754845, "entropy": 0.08420739322900772, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:23.902108Z", "loop": 9693, "env_steps": 5955993599, "loss": 0.016493475064635277, "avg_return": 0.8642629981040955, "regret": 0.00012759647506754845, "entropy": 0.08313538879156113, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:24.756882Z", "loop": 9694, "env_steps": 5956607999, "loss": 0.0174881499260664, "avg_return": 0.8646360635757446, "regret": 0.00012759647506754845, "entropy": 0.08895725011825562, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:25.611280Z", "loop": 9695, "env_steps": 5957222399, "loss": 0.016812605783343315, "avg_return": 0.8632475137710571, "regret": 0.00012759647506754845, "entropy": 0.08755137771368027, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:26.466068Z", "loop": 9696, "env_steps": 5957836799, "loss": 0.018240969628095627, "avg_return": 0.8631510734558105, "regret": 0.00012759647506754845, "entropy": 0.08971117436885834, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:27.320043Z", "loop": 9697, "env_steps": 5958451199, "loss": 0.018057506531476974, "avg_return": 0.8633115887641907, "regret": 0.00012759647506754845, "entropy": 0.09241433441638947, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:28.173854Z", "loop": 9698, "env_steps": 5959065599, "loss": 0.016953198239207268, "avg_return": 0.863440990447998, "regret": 0.00012759647506754845, "entropy": 0.0863843485713005, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:29.028626Z", "loop": 9699, "env_steps": 5959679999, "loss": 0.01921587809920311, "avg_return": 0.8618192672729492, "regret": 0.00012759647506754845, "entropy": 0.09297928959131241, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:29.922988Z", "loop": 9700, "env_steps": 5960294399, "loss": 0.017956804484128952, "avg_return": 0.8625670671463013, "regret": 0.0005186601192690432, "entropy": 0.08765054494142532, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:30.775387Z", "loop": 9701, "env_steps": 5960908799, "loss": 0.01799815706908703, "avg_return": 0.8632701635360718, "regret": 0.0005186601192690432, "entropy": 0.09090583771467209, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:31.628989Z", "loop": 9702, "env_steps": 5961523199, "loss": 0.017594872042536736, "avg_return": 0.8625734448432922, "regret": 0.0005186601192690432, "entropy": 0.08860298246145248, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:32.483203Z", "loop": 9703, "env_steps": 5962137599, "loss": 0.018720155581831932, "avg_return": 0.8625428676605225, "regret": 0.0005186601192690432, "entropy": 0.09246108680963516, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:33.337620Z", "loop": 9704, "env_steps": 5962751999, "loss": 0.018116803839802742, "avg_return": 0.861813485622406, "regret": 0.0005186601192690432, "entropy": 0.09167975932359695, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:34.190940Z", "loop": 9705, "env_steps": 5963366399, "loss": 0.01925080083310604, "avg_return": 0.8616227507591248, "regret": 0.0005186601192690432, "entropy": 0.09249480813741684, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:35.044547Z", "loop": 9706, "env_steps": 5963980799, "loss": 0.017681017518043518, "avg_return": 0.8618329167366028, "regret": 0.0005186601192690432, "entropy": 0.09367989748716354, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:35.898435Z", "loop": 9707, "env_steps": 5964595199, "loss": 0.019071459770202637, "avg_return": 0.8617867231369019, "regret": 0.0005186601192690432, "entropy": 0.09286434948444366, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:36.752885Z", "loop": 9708, "env_steps": 5965209599, "loss": 0.018870756030082703, "avg_return": 0.8615942597389221, "regret": 0.0005186601192690432, "entropy": 0.09485439211130142, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:37.606585Z", "loop": 9709, "env_steps": 5965823999, "loss": 0.018232552334666252, "avg_return": 0.8617603778839111, "regret": 0.0005186601192690432, "entropy": 0.09507282823324203, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:38.499243Z", "loop": 9710, "env_steps": 5966438399, "loss": 0.018078595399856567, "avg_return": 0.8637704849243164, "regret": 0.0010660701664164662, "entropy": 0.09035416692495346, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:39.352314Z", "loop": 9711, "env_steps": 5967052799, "loss": 0.01758008822798729, "avg_return": 0.8626729249954224, "regret": 0.0010660701664164662, "entropy": 0.08921728283166885, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:40.207136Z", "loop": 9712, "env_steps": 5967667199, "loss": 0.017930282279849052, "avg_return": 0.8627104163169861, "regret": 0.0010660701664164662, "entropy": 0.09049852937459946, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:41.061717Z", "loop": 9713, "env_steps": 5968281599, "loss": 0.01623736135661602, "avg_return": 0.8627203702926636, "regret": 0.0010660701664164662, "entropy": 0.08494873344898224, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:41.915735Z", "loop": 9714, "env_steps": 5968895999, "loss": 0.016141075640916824, "avg_return": 0.8634195923805237, "regret": 0.0010660701664164662, "entropy": 0.08465242385864258, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:42.769407Z", "loop": 9715, "env_steps": 5969510399, "loss": 0.01702350564301014, "avg_return": 0.8632150292396545, "regret": 0.0010660701664164662, "entropy": 0.08799836784601212, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:43.624282Z", "loop": 9716, "env_steps": 5970124799, "loss": 0.01807076297700405, "avg_return": 0.8641915321350098, "regret": 0.0010660701664164662, "entropy": 0.0865064337849617, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:44.478600Z", "loop": 9717, "env_steps": 5970739199, "loss": 0.018061617389321327, "avg_return": 0.8627153635025024, "regret": 0.0010660701664164662, "entropy": 0.09244496375322342, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:45.332400Z", "loop": 9718, "env_steps": 5971353599, "loss": 0.018094375729560852, "avg_return": 0.8637968301773071, "regret": 0.0010660701664164662, "entropy": 0.09032826125621796, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:46.185056Z", "loop": 9719, "env_steps": 5971967999, "loss": 0.01859360747039318, "avg_return": 0.8631973266601562, "regret": 0.0010660701664164662, "entropy": 0.08877608180046082, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:47.079625Z", "loop": 9720, "env_steps": 5972582399, "loss": 0.018286682665348053, "avg_return": 0.8632264137268066, "regret": 0.0003426560142543167, "entropy": 0.09068512171506882, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:47.935384Z", "loop": 9721, "env_steps": 5973196799, "loss": 0.019029973074793816, "avg_return": 0.8648494482040405, "regret": 0.0003426560142543167, "entropy": 0.09323684871196747, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:48.791241Z", "loop": 9722, "env_steps": 5973811199, "loss": 0.019124796614050865, "avg_return": 0.8642165064811707, "regret": 0.0003426560142543167, "entropy": 0.09366381168365479, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:49.645610Z", "loop": 9723, "env_steps": 5974425599, "loss": 0.018642514944076538, "avg_return": 0.8631240129470825, "regret": 0.0003426560142543167, "entropy": 0.09349901229143143, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:50.501300Z", "loop": 9724, "env_steps": 5975039999, "loss": 0.016292298212647438, "avg_return": 0.8634330630302429, "regret": 0.0003426560142543167, "entropy": 0.08915520459413528, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:51.355960Z", "loop": 9725, "env_steps": 5975654399, "loss": 0.01536780595779419, "avg_return": 0.8614959716796875, "regret": 0.0003426560142543167, "entropy": 0.08182190358638763, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:52.211397Z", "loop": 9726, "env_steps": 5976268799, "loss": 0.015967033803462982, "avg_return": 0.862269937992096, "regret": 0.0003426560142543167, "entropy": 0.08224085718393326, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:53.067130Z", "loop": 9727, "env_steps": 5976883199, "loss": 0.014701147563755512, "avg_return": 0.8623639345169067, "regret": 0.0003426560142543167, "entropy": 0.08010689914226532, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:53.921756Z", "loop": 9728, "env_steps": 5977497599, "loss": 0.013896559365093708, "avg_return": 0.8622575998306274, "regret": 0.0003426560142543167, "entropy": 0.07091455161571503, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:54.775193Z", "loop": 9729, "env_steps": 5978111999, "loss": 0.014628863893449306, "avg_return": 0.8609068989753723, "regret": 0.0003426560142543167, "entropy": 0.07960359752178192, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:55.670291Z", "loop": 9730, "env_steps": 5978726399, "loss": 0.014487815089523792, "avg_return": 0.8617380857467651, "regret": 0.0022202967666089535, "entropy": 0.07660948485136032, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:56.524402Z", "loop": 9731, "env_steps": 5979340799, "loss": 0.014274450950324535, "avg_return": 0.8604360222816467, "regret": 0.0022202967666089535, "entropy": 0.07697110623121262, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:57.379046Z", "loop": 9732, "env_steps": 5979955199, "loss": 0.014053951017558575, "avg_return": 0.8611065745353699, "regret": 0.0022202967666089535, "entropy": 0.07670393586158752, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:58.232596Z", "loop": 9733, "env_steps": 5980569599, "loss": 0.015794120728969574, "avg_return": 0.8603397607803345, "regret": 0.0022202967666089535, "entropy": 0.07974079996347427, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:59.085905Z", "loop": 9734, "env_steps": 5981183999, "loss": 0.014991387724876404, "avg_return": 0.8605484962463379, "regret": 0.0022202967666089535, "entropy": 0.08122947812080383, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:42:59.939601Z", "loop": 9735, "env_steps": 5981798399, "loss": 0.014993580989539623, "avg_return": 0.8604544997215271, "regret": 0.0022202967666089535, "entropy": 0.08327611535787582, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:00.793997Z", "loop": 9736, "env_steps": 5982412799, "loss": 0.015455408953130245, "avg_return": 0.8596174120903015, "regret": 0.0022202967666089535, "entropy": 0.08148963004350662, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:01.647575Z", "loop": 9737, "env_steps": 5983027199, "loss": 0.01622636243700981, "avg_return": 0.859807550907135, "regret": 0.0022202967666089535, "entropy": 0.08262048661708832, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:02.501201Z", "loop": 9738, "env_steps": 5983641599, "loss": 0.016082635149359703, "avg_return": 0.8595015406608582, "regret": 0.0022202967666089535, "entropy": 0.08490953594446182, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:03.355107Z", "loop": 9739, "env_steps": 5984255999, "loss": 0.016724130138754845, "avg_return": 0.8602607250213623, "regret": 0.0022202967666089535, "entropy": 0.0872589722275734, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:04.249169Z", "loop": 9740, "env_steps": 5984870399, "loss": 0.016529979184269905, "avg_return": 0.8611127138137817, "regret": 0.0019096375908702612, "entropy": 0.08343573659658432, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:05.103477Z", "loop": 9741, "env_steps": 5985484799, "loss": 0.015719052404165268, "avg_return": 0.8615056276321411, "regret": 0.0019096375908702612, "entropy": 0.08314809948205948, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:05.956564Z", "loop": 9742, "env_steps": 5986099199, "loss": 0.01718876324594021, "avg_return": 0.8635011911392212, "regret": 0.0019096375908702612, "entropy": 0.08744911104440689, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:06.810371Z", "loop": 9743, "env_steps": 5986713599, "loss": 0.016066333279013634, "avg_return": 0.8634518384933472, "regret": 0.0019096375908702612, "entropy": 0.08545486629009247, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:07.665061Z", "loop": 9744, "env_steps": 5987327999, "loss": 0.017091862857341766, "avg_return": 0.8637601137161255, "regret": 0.0019096375908702612, "entropy": 0.08862969279289246, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:08.520926Z", "loop": 9745, "env_steps": 5987942399, "loss": 0.01988709717988968, "avg_return": 0.8632739186286926, "regret": 0.0019096375908702612, "entropy": 0.09544234722852707, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:09.374885Z", "loop": 9746, "env_steps": 5988556799, "loss": 0.020599881187081337, "avg_return": 0.8638535737991333, "regret": 0.0019096375908702612, "entropy": 0.09941556304693222, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:10.227826Z", "loop": 9747, "env_steps": 5989171199, "loss": 0.01862802542746067, "avg_return": 0.8621923923492432, "regret": 0.0019096375908702612, "entropy": 0.094858318567276, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:11.082759Z", "loop": 9748, "env_steps": 5989785599, "loss": 0.019436312839388847, "avg_return": 0.8628931045532227, "regret": 0.0019096375908702612, "entropy": 0.09886881709098816, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:11.937127Z", "loop": 9749, "env_steps": 5990399999, "loss": 0.019674358889460564, "avg_return": 0.863213837146759, "regret": 0.0019096375908702612, "entropy": 0.0930568128824234, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:12.831661Z", "loop": 9750, "env_steps": 5991014399, "loss": 0.019770871847867966, "avg_return": 0.8634039759635925, "regret": 0.0001709006610326469, "entropy": 0.09744859486818314, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:13.685012Z", "loop": 9751, "env_steps": 5991628799, "loss": 0.018410053104162216, "avg_return": 0.863358199596405, "regret": 0.0001709006610326469, "entropy": 0.09286458045244217, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:14.539197Z", "loop": 9752, "env_steps": 5992243199, "loss": 0.018105650320649147, "avg_return": 0.8643746376037598, "regret": 0.0001709006610326469, "entropy": 0.09077539294958115, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:15.395192Z", "loop": 9753, "env_steps": 5992857599, "loss": 0.01842048205435276, "avg_return": 0.863371729850769, "regret": 0.0001709006610326469, "entropy": 0.09057919681072235, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:16.248582Z", "loop": 9754, "env_steps": 5993471999, "loss": 0.019186750054359436, "avg_return": 0.8635233640670776, "regret": 0.0001709006610326469, "entropy": 0.09831731021404266, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:17.102260Z", "loop": 9755, "env_steps": 5994086399, "loss": 0.01852227933704853, "avg_return": 0.8639809489250183, "regret": 0.0001709006610326469, "entropy": 0.09541814029216766, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:17.956545Z", "loop": 9756, "env_steps": 5994700799, "loss": 0.019984496757388115, "avg_return": 0.8625960350036621, "regret": 0.0001709006610326469, "entropy": 0.10223587602376938, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:18.811465Z", "loop": 9757, "env_steps": 5995315199, "loss": 0.019850457087159157, "avg_return": 0.8633037805557251, "regret": 0.0001709006610326469, "entropy": 0.10422036051750183, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:19.665840Z", "loop": 9758, "env_steps": 5995929599, "loss": 0.01916555128991604, "avg_return": 0.8613957166671753, "regret": 0.0001709006610326469, "entropy": 0.10229253768920898, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:20.519625Z", "loop": 9759, "env_steps": 5996543999, "loss": 0.02075294218957424, "avg_return": 0.8628689050674438, "regret": 0.0001709006610326469, "entropy": 0.1042293906211853, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:21.413638Z", "loop": 9760, "env_steps": 5997158399, "loss": 0.020649820566177368, "avg_return": 0.8620687127113342, "regret": 0.0015838874969631433, "entropy": 0.10744722187519073, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:22.267170Z", "loop": 9761, "env_steps": 5997772799, "loss": 0.021343795582652092, "avg_return": 0.8618011474609375, "regret": 0.0015838874969631433, "entropy": 0.10478757321834564, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:23.121321Z", "loop": 9762, "env_steps": 5998387199, "loss": 0.01932886801660061, "avg_return": 0.8615242838859558, "regret": 0.0015838874969631433, "entropy": 0.10483527928590775, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:23.975492Z", "loop": 9763, "env_steps": 5999001599, "loss": 0.02031000889837742, "avg_return": 0.8616047501564026, "regret": 0.0015838874969631433, "entropy": 0.10631878674030304, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:24.829092Z", "loop": 9764, "env_steps": 5999615999, "loss": 0.018592223525047302, "avg_return": 0.8620078563690186, "regret": 0.0015838874969631433, "entropy": 0.09853866696357727, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:25.683328Z", "loop": 9765, "env_steps": 6000230399, "loss": 0.019290180876851082, "avg_return": 0.8627915382385254, "regret": 0.0015838874969631433, "entropy": 0.10101622343063354, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:26.537513Z", "loop": 9766, "env_steps": 6000844799, "loss": 0.01937161386013031, "avg_return": 0.8634401559829712, "regret": 0.0015838874969631433, "entropy": 0.10120319575071335, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:27.393128Z", "loop": 9767, "env_steps": 6001459199, "loss": 0.019933804869651794, "avg_return": 0.8619781732559204, "regret": 0.0015838874969631433, "entropy": 0.10036927461624146, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:28.247365Z", "loop": 9768, "env_steps": 6002073599, "loss": 0.01959562487900257, "avg_return": 0.8625767230987549, "regret": 0.0015838874969631433, "entropy": 0.10358059406280518, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:29.101235Z", "loop": 9769, "env_steps": 6002687999, "loss": 0.019709866493940353, "avg_return": 0.8609867691993713, "regret": 0.0015838874969631433, "entropy": 0.10219795256853104, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:29.996342Z", "loop": 9770, "env_steps": 6003302399, "loss": 0.01963544264435768, "avg_return": 0.8636740446090698, "regret": 0.000604763743467629, "entropy": 0.10550641268491745, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:30.850773Z", "loop": 9771, "env_steps": 6003916799, "loss": 0.0210394486784935, "avg_return": 0.8621163368225098, "regret": 0.000604763743467629, "entropy": 0.10815228521823883, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:31.704408Z", "loop": 9772, "env_steps": 6004531199, "loss": 0.02126733958721161, "avg_return": 0.8634939789772034, "regret": 0.000604763743467629, "entropy": 0.10497058928012848, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:32.558181Z", "loop": 9773, "env_steps": 6005145599, "loss": 0.021206168457865715, "avg_return": 0.8619874119758606, "regret": 0.000604763743467629, "entropy": 0.10645653307437897, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:33.412044Z", "loop": 9774, "env_steps": 6005759999, "loss": 0.020807618275284767, "avg_return": 0.8620806932449341, "regret": 0.000604763743467629, "entropy": 0.10922235250473022, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:34.267095Z", "loop": 9775, "env_steps": 6006374399, "loss": 0.021871358156204224, "avg_return": 0.8637214303016663, "regret": 0.000604763743467629, "entropy": 0.11156976222991943, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:35.121555Z", "loop": 9776, "env_steps": 6006988799, "loss": 0.02138100191950798, "avg_return": 0.8637018203735352, "regret": 0.000604763743467629, "entropy": 0.1123720183968544, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:35.976254Z", "loop": 9777, "env_steps": 6007603199, "loss": 0.022312402725219727, "avg_return": 0.8627761006355286, "regret": 0.000604763743467629, "entropy": 0.11779463291168213, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:36.829770Z", "loop": 9778, "env_steps": 6008217599, "loss": 0.022575443610548973, "avg_return": 0.8622922897338867, "regret": 0.000604763743467629, "entropy": 0.11860412359237671, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:37.684322Z", "loop": 9779, "env_steps": 6008831999, "loss": 0.023083902895450592, "avg_return": 0.8622778654098511, "regret": 0.000604763743467629, "entropy": 0.11893501877784729, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:38.579056Z", "loop": 9780, "env_steps": 6009446399, "loss": 0.02489871345460415, "avg_return": 0.8615137934684753, "regret": 0.001365370349958539, "entropy": 0.12622590363025665, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:39.433294Z", "loop": 9781, "env_steps": 6010060799, "loss": 0.026210516691207886, "avg_return": 0.8626412153244019, "regret": 0.001365370349958539, "entropy": 0.13687960803508759, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:40.287284Z", "loop": 9782, "env_steps": 6010675199, "loss": 0.026801904663443565, "avg_return": 0.8615937232971191, "regret": 0.001365370349958539, "entropy": 0.14093554019927979, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:41.142059Z", "loop": 9783, "env_steps": 6011289599, "loss": 0.028770139440894127, "avg_return": 0.8597433567047119, "regret": 0.001365370349958539, "entropy": 0.1463560163974762, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:41.997377Z", "loop": 9784, "env_steps": 6011903999, "loss": 0.029842782765626907, "avg_return": 0.8598540425300598, "regret": 0.001365370349958539, "entropy": 0.1517971158027649, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:42.851056Z", "loop": 9785, "env_steps": 6012518399, "loss": 0.02998475171625614, "avg_return": 0.8594905734062195, "regret": 0.001365370349958539, "entropy": 0.15203511714935303, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:43.704214Z", "loop": 9786, "env_steps": 6013132799, "loss": 0.03056260757148266, "avg_return": 0.8578503727912903, "regret": 0.001365370349958539, "entropy": 0.154148668050766, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:44.558222Z", "loop": 9787, "env_steps": 6013747199, "loss": 0.030099231749773026, "avg_return": 0.8591963052749634, "regret": 0.001365370349958539, "entropy": 0.154696986079216, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:45.411705Z", "loop": 9788, "env_steps": 6014361599, "loss": 0.02737308479845524, "avg_return": 0.8599979877471924, "regret": 0.001365370349958539, "entropy": 0.1427634209394455, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:46.266972Z", "loop": 9789, "env_steps": 6014975999, "loss": 0.027244219556450844, "avg_return": 0.8600329756736755, "regret": 0.001365370349958539, "entropy": 0.14213255047798157, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:47.162717Z", "loop": 9790, "env_steps": 6015590399, "loss": 0.02606041729450226, "avg_return": 0.8607662320137024, "regret": 0.0028510887641459703, "entropy": 0.1330273449420929, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:48.017219Z", "loop": 9791, "env_steps": 6016204799, "loss": 0.025927072390913963, "avg_return": 0.8601524233818054, "regret": 0.0028510887641459703, "entropy": 0.1325199007987976, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:48.870640Z", "loop": 9792, "env_steps": 6016819199, "loss": 0.02546325884759426, "avg_return": 0.8594954609870911, "regret": 0.0028510887641459703, "entropy": 0.13199879229068756, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:49.724271Z", "loop": 9793, "env_steps": 6017433599, "loss": 0.024871647357940674, "avg_return": 0.8618192672729492, "regret": 0.0028510887641459703, "entropy": 0.13157030940055847, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:50.577982Z", "loop": 9794, "env_steps": 6018047999, "loss": 0.024621903896331787, "avg_return": 0.8630942106246948, "regret": 0.0028510887641459703, "entropy": 0.12717418372631073, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:51.432419Z", "loop": 9795, "env_steps": 6018662399, "loss": 0.02669648826122284, "avg_return": 0.8619102239608765, "regret": 0.0028510887641459703, "entropy": 0.1309480518102646, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:52.285291Z", "loop": 9796, "env_steps": 6019276799, "loss": 0.02504323422908783, "avg_return": 0.8641351461410522, "regret": 0.0028510887641459703, "entropy": 0.11968304961919785, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:53.138289Z", "loop": 9797, "env_steps": 6019891199, "loss": 0.0238921120762825, "avg_return": 0.8633888959884644, "regret": 0.0028510887641459703, "entropy": 0.11882773041725159, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:53.992285Z", "loop": 9798, "env_steps": 6020505599, "loss": 0.02395930141210556, "avg_return": 0.8636676073074341, "regret": 0.0028510887641459703, "entropy": 0.11925166845321655, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:54.847955Z", "loop": 9799, "env_steps": 6021119999, "loss": 0.022946886718273163, "avg_return": 0.8642494678497314, "regret": 0.0028510887641459703, "entropy": 0.11709582060575485, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:55.742169Z", "loop": 9800, "env_steps": 6021734399, "loss": 0.02298547513782978, "avg_return": 0.862092912197113, "regret": 0.000610023271292448, "entropy": 0.11493678390979767, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:56.596215Z", "loop": 9801, "env_steps": 6022348799, "loss": 0.021237200126051903, "avg_return": 0.8636590838432312, "regret": 0.000610023271292448, "entropy": 0.11464942991733551, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:57.450810Z", "loop": 9802, "env_steps": 6022963199, "loss": 0.022334009408950806, "avg_return": 0.8626371622085571, "regret": 0.000610023271292448, "entropy": 0.1158837229013443, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:58.305636Z", "loop": 9803, "env_steps": 6023577599, "loss": 0.021414393559098244, "avg_return": 0.8629049062728882, "regret": 0.000610023271292448, "entropy": 0.11165722459554672, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:43:59.161237Z", "loop": 9804, "env_steps": 6024191999, "loss": 0.021258411929011345, "avg_return": 0.8640691041946411, "regret": 0.000610023271292448, "entropy": 0.11031768471002579, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:00.014126Z", "loop": 9805, "env_steps": 6024806399, "loss": 0.021549101918935776, "avg_return": 0.8641557097434998, "regret": 0.000610023271292448, "entropy": 0.11221481114625931, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:00.866637Z", "loop": 9806, "env_steps": 6025420799, "loss": 0.019600076600909233, "avg_return": 0.8632312417030334, "regret": 0.000610023271292448, "entropy": 0.10028751939535141, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:01.720830Z", "loop": 9807, "env_steps": 6026035199, "loss": 0.02127731591463089, "avg_return": 0.8630897998809814, "regret": 0.000610023271292448, "entropy": 0.10606348514556885, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:02.574909Z", "loop": 9808, "env_steps": 6026649599, "loss": 0.019877413287758827, "avg_return": 0.8628015518188477, "regret": 0.000610023271292448, "entropy": 0.10455303639173508, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:03.429245Z", "loop": 9809, "env_steps": 6027263999, "loss": 0.02009419910609722, "avg_return": 0.8616880774497986, "regret": 0.000610023271292448, "entropy": 0.10392768681049347, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:04.322598Z", "loop": 9810, "env_steps": 6027878399, "loss": 0.02026221714913845, "avg_return": 0.8611366748809814, "regret": 0.0017595372628420591, "entropy": 0.10149446129798889, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:05.177416Z", "loop": 9811, "env_steps": 6028492799, "loss": 0.020377280190587044, "avg_return": 0.8622021675109863, "regret": 0.0017595372628420591, "entropy": 0.1040119007229805, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:06.032174Z", "loop": 9812, "env_steps": 6029107199, "loss": 0.02109866589307785, "avg_return": 0.8607468605041504, "regret": 0.0017595372628420591, "entropy": 0.10402660071849823, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:06.887244Z", "loop": 9813, "env_steps": 6029721599, "loss": 0.020904073491692543, "avg_return": 0.8618428707122803, "regret": 0.0017595372628420591, "entropy": 0.10633545368909836, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:07.741069Z", "loop": 9814, "env_steps": 6030335999, "loss": 0.021732164546847343, "avg_return": 0.8621238470077515, "regret": 0.0017595372628420591, "entropy": 0.10763520002365112, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:08.595177Z", "loop": 9815, "env_steps": 6030950399, "loss": 0.020163893699645996, "avg_return": 0.8627209663391113, "regret": 0.0017595372628420591, "entropy": 0.10381988435983658, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:09.451196Z", "loop": 9816, "env_steps": 6031564799, "loss": 0.01992318034172058, "avg_return": 0.8623354434967041, "regret": 0.0017595372628420591, "entropy": 0.10363870114088058, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:10.307084Z", "loop": 9817, "env_steps": 6032179199, "loss": 0.019488193094730377, "avg_return": 0.8629492521286011, "regret": 0.0017595372628420591, "entropy": 0.09909874200820923, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:11.162544Z", "loop": 9818, "env_steps": 6032793599, "loss": 0.020917002111673355, "avg_return": 0.8636314272880554, "regret": 0.0017595372628420591, "entropy": 0.10540986806154251, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:12.017689Z", "loop": 9819, "env_steps": 6033407999, "loss": 0.021429304033517838, "avg_return": 0.8624675869941711, "regret": 0.0017595372628420591, "entropy": 0.11127105355262756, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:12.911749Z", "loop": 9820, "env_steps": 6034022399, "loss": 0.02482621930539608, "avg_return": 0.8639987111091614, "regret": 0.0005510188639163971, "entropy": 0.11876628547906876, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:13.766581Z", "loop": 9821, "env_steps": 6034636799, "loss": 0.023841077461838722, "avg_return": 0.8629888296127319, "regret": 0.0005510188639163971, "entropy": 0.11568573862314224, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:14.621804Z", "loop": 9822, "env_steps": 6035251199, "loss": 0.0220987256616354, "avg_return": 0.8647876381874084, "regret": 0.0005510188639163971, "entropy": 0.11219118535518646, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:15.476428Z", "loop": 9823, "env_steps": 6035865599, "loss": 0.021947568282485008, "avg_return": 0.8637387156486511, "regret": 0.0005510188639163971, "entropy": 0.11257433146238327, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:16.330076Z", "loop": 9824, "env_steps": 6036479999, "loss": 0.022341981530189514, "avg_return": 0.862581193447113, "regret": 0.0005510188639163971, "entropy": 0.11601568013429642, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:17.184338Z", "loop": 9825, "env_steps": 6037094399, "loss": 0.02050669863820076, "avg_return": 0.8635023236274719, "regret": 0.0005510188639163971, "entropy": 0.10079929232597351, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:18.039434Z", "loop": 9826, "env_steps": 6037708799, "loss": 0.018220435827970505, "avg_return": 0.8631990551948547, "regret": 0.0005510188639163971, "entropy": 0.09549904614686966, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:18.893563Z", "loop": 9827, "env_steps": 6038323199, "loss": 0.016300702467560768, "avg_return": 0.8623244166374207, "regret": 0.0005510188639163971, "entropy": 0.08777095377445221, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:19.747351Z", "loop": 9828, "env_steps": 6038937599, "loss": 0.017780786380171776, "avg_return": 0.8628977537155151, "regret": 0.0005510188639163971, "entropy": 0.0902685821056366, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:20.601422Z", "loop": 9829, "env_steps": 6039551999, "loss": 0.017658552154898643, "avg_return": 0.8632549047470093, "regret": 0.0005510188639163971, "entropy": 0.08937031775712967, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:21.495673Z", "loop": 9830, "env_steps": 6040166399, "loss": 0.02029258944094181, "avg_return": 0.8643640279769897, "regret": 0.00028482344350777566, "entropy": 0.09678930044174194, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:22.351459Z", "loop": 9831, "env_steps": 6040780799, "loss": 0.018426954746246338, "avg_return": 0.8631182909011841, "regret": 0.00028482344350777566, "entropy": 0.09097626805305481, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:23.206221Z", "loop": 9832, "env_steps": 6041395199, "loss": 0.017145082354545593, "avg_return": 0.8629292845726013, "regret": 0.00028482344350777566, "entropy": 0.0865531638264656, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:24.061454Z", "loop": 9833, "env_steps": 6042009599, "loss": 0.01808060333132744, "avg_return": 0.8625286817550659, "regret": 0.00028482344350777566, "entropy": 0.09505686908960342, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:24.918189Z", "loop": 9834, "env_steps": 6042623999, "loss": 0.017817234620451927, "avg_return": 0.8635714054107666, "regret": 0.00028482344350777566, "entropy": 0.08837874233722687, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:25.773580Z", "loop": 9835, "env_steps": 6043238399, "loss": 0.018514683470129967, "avg_return": 0.8629384636878967, "regret": 0.00028482344350777566, "entropy": 0.09405399858951569, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:26.628135Z", "loop": 9836, "env_steps": 6043852799, "loss": 0.018091389909386635, "avg_return": 0.862960934638977, "regret": 0.00028482344350777566, "entropy": 0.09091629087924957, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:27.481646Z", "loop": 9837, "env_steps": 6044467199, "loss": 0.017367124557495117, "avg_return": 0.8633888959884644, "regret": 0.00028482344350777566, "entropy": 0.08867156505584717, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:28.336919Z", "loop": 9838, "env_steps": 6045081599, "loss": 0.018949521705508232, "avg_return": 0.8635138869285583, "regret": 0.00028482344350777566, "entropy": 0.09550993889570236, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:29.191403Z", "loop": 9839, "env_steps": 6045695999, "loss": 0.018194148316979408, "avg_return": 0.8641741871833801, "regret": 0.00028482344350777566, "entropy": 0.08593013137578964, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:30.083862Z", "loop": 9840, "env_steps": 6046310399, "loss": 0.01830197684466839, "avg_return": 0.8633831739425659, "regret": 0.00026598290423862636, "entropy": 0.0899195745587349, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:30.938087Z", "loop": 9841, "env_steps": 6046924799, "loss": 0.018113484606146812, "avg_return": 0.8613773584365845, "regret": 0.00026598290423862636, "entropy": 0.09215843677520752, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:31.793965Z", "loop": 9842, "env_steps": 6047539199, "loss": 0.01781093329191208, "avg_return": 0.8624392747879028, "regret": 0.00026598290423862636, "entropy": 0.08938761055469513, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:32.649385Z", "loop": 9843, "env_steps": 6048153599, "loss": 0.019132109358906746, "avg_return": 0.8631283044815063, "regret": 0.00026598290423862636, "entropy": 0.09284413605928421, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:33.503090Z", "loop": 9844, "env_steps": 6048767999, "loss": 0.01859930343925953, "avg_return": 0.8630059957504272, "regret": 0.00026598290423862636, "entropy": 0.08864675462245941, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:34.357892Z", "loop": 9845, "env_steps": 6049382399, "loss": 0.017733970656991005, "avg_return": 0.863288164138794, "regret": 0.00026598290423862636, "entropy": 0.08962313830852509, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:35.212260Z", "loop": 9846, "env_steps": 6049996799, "loss": 0.016545036807656288, "avg_return": 0.8646950721740723, "regret": 0.00026598290423862636, "entropy": 0.08798427879810333, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:36.066482Z", "loop": 9847, "env_steps": 6050611199, "loss": 0.01762462966144085, "avg_return": 0.8634999990463257, "regret": 0.00026598290423862636, "entropy": 0.08686146885156631, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:36.921441Z", "loop": 9848, "env_steps": 6051225599, "loss": 0.017650308087468147, "avg_return": 0.8627808094024658, "regret": 0.00026598290423862636, "entropy": 0.08620936423540115, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:37.775924Z", "loop": 9849, "env_steps": 6051839999, "loss": 0.01728781871497631, "avg_return": 0.8629280924797058, "regret": 0.00026598290423862636, "entropy": 0.08408313244581223, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:38.672953Z", "loop": 9850, "env_steps": 6052454399, "loss": 0.01662055030465126, "avg_return": 0.861342191696167, "regret": 0.0009011747315526009, "entropy": 0.0820036455988884, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:39.528260Z", "loop": 9851, "env_steps": 6053068799, "loss": 0.01782149448990822, "avg_return": 0.8629757165908813, "regret": 0.0009011747315526009, "entropy": 0.0867580994963646, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:40.382276Z", "loop": 9852, "env_steps": 6053683199, "loss": 0.01682581938803196, "avg_return": 0.8625800013542175, "regret": 0.0009011747315526009, "entropy": 0.08378054946660995, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:41.236788Z", "loop": 9853, "env_steps": 6054297599, "loss": 0.01733643002808094, "avg_return": 0.8622621893882751, "regret": 0.0009011747315526009, "entropy": 0.08367608487606049, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:42.091758Z", "loop": 9854, "env_steps": 6054911999, "loss": 0.016907548531889915, "avg_return": 0.8627105951309204, "regret": 0.0009011747315526009, "entropy": 0.08580489456653595, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:42.945381Z", "loop": 9855, "env_steps": 6055526399, "loss": 0.017067810520529747, "avg_return": 0.8627051711082458, "regret": 0.0009011747315526009, "entropy": 0.08702483773231506, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:43.798648Z", "loop": 9856, "env_steps": 6056140799, "loss": 0.016579989343881607, "avg_return": 0.8620933294296265, "regret": 0.0009011747315526009, "entropy": 0.08200301229953766, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:44.652226Z", "loop": 9857, "env_steps": 6056755199, "loss": 0.01559416949748993, "avg_return": 0.863714337348938, "regret": 0.0009011747315526009, "entropy": 0.08428750932216644, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:45.506825Z", "loop": 9858, "env_steps": 6057369599, "loss": 0.016708554700016975, "avg_return": 0.8618011474609375, "regret": 0.0009011747315526009, "entropy": 0.08349283039569855, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:46.360640Z", "loop": 9859, "env_steps": 6057983999, "loss": 0.01695236563682556, "avg_return": 0.8627752065658569, "regret": 0.0009011747315526009, "entropy": 0.08582328259944916, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:47.253408Z", "loop": 9860, "env_steps": 6058598399, "loss": 0.016502398997545242, "avg_return": 0.8620115518569946, "regret": 0.0008100611157715321, "entropy": 0.0817502960562706, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:48.106493Z", "loop": 9861, "env_steps": 6059212799, "loss": 0.016482515260577202, "avg_return": 0.8628113269805908, "regret": 0.0008100611157715321, "entropy": 0.08405444025993347, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:48.960792Z", "loop": 9862, "env_steps": 6059827199, "loss": 0.016826441511511803, "avg_return": 0.8631922602653503, "regret": 0.0008100611157715321, "entropy": 0.08572488278150558, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:49.814789Z", "loop": 9863, "env_steps": 6060441599, "loss": 0.017162080854177475, "avg_return": 0.8636112809181213, "regret": 0.0008100611157715321, "entropy": 0.08571722358465195, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:50.667957Z", "loop": 9864, "env_steps": 6061055999, "loss": 0.01685536466538906, "avg_return": 0.8631139397621155, "regret": 0.0008100611157715321, "entropy": 0.08919495344161987, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:51.521439Z", "loop": 9865, "env_steps": 6061670399, "loss": 0.016555478796362877, "avg_return": 0.8627135157585144, "regret": 0.0008100611157715321, "entropy": 0.08698379993438721, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:52.375757Z", "loop": 9866, "env_steps": 6062284799, "loss": 0.017990341410040855, "avg_return": 0.8634847402572632, "regret": 0.0008100611157715321, "entropy": 0.09036784619092941, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:53.228685Z", "loop": 9867, "env_steps": 6062899199, "loss": 0.017437025904655457, "avg_return": 0.8628401756286621, "regret": 0.0008100611157715321, "entropy": 0.08712980896234512, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:54.082508Z", "loop": 9868, "env_steps": 6063513599, "loss": 0.01763784885406494, "avg_return": 0.8634282350540161, "regret": 0.0008100611157715321, "entropy": 0.08843188732862473, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:54.935090Z", "loop": 9869, "env_steps": 6064127999, "loss": 0.018329603597521782, "avg_return": 0.864734411239624, "regret": 0.0008100611157715321, "entropy": 0.09249714016914368, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:55.828204Z", "loop": 9870, "env_steps": 6064742399, "loss": 0.0173801202327013, "avg_return": 0.8634322285652161, "regret": 0.00028253308846615255, "entropy": 0.08709348738193512, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:56.682181Z", "loop": 9871, "env_steps": 6065356799, "loss": 0.01799137331545353, "avg_return": 0.8631668090820312, "regret": 0.00028253308846615255, "entropy": 0.0905948206782341, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:57.536271Z", "loop": 9872, "env_steps": 6065971199, "loss": 0.01764201931655407, "avg_return": 0.8649334907531738, "regret": 0.00028253308846615255, "entropy": 0.08779419958591461, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:58.390458Z", "loop": 9873, "env_steps": 6066585599, "loss": 0.01780560240149498, "avg_return": 0.861962616443634, "regret": 0.00028253308846615255, "entropy": 0.08733256161212921, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:44:59.244959Z", "loop": 9874, "env_steps": 6067199999, "loss": 0.018251819536089897, "avg_return": 0.863734245300293, "regret": 0.00028253308846615255, "entropy": 0.09197035431861877, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:00.099074Z", "loop": 9875, "env_steps": 6067814399, "loss": 0.017638975754380226, "avg_return": 0.863962709903717, "regret": 0.00028253308846615255, "entropy": 0.08647893369197845, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:00.953263Z", "loop": 9876, "env_steps": 6068428799, "loss": 0.018053559586405754, "avg_return": 0.8631520867347717, "regret": 0.00028253308846615255, "entropy": 0.0903250128030777, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:01.807975Z", "loop": 9877, "env_steps": 6069043199, "loss": 0.01823393814265728, "avg_return": 0.8627257347106934, "regret": 0.00028253308846615255, "entropy": 0.09120894223451614, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:02.663224Z", "loop": 9878, "env_steps": 6069657599, "loss": 0.017196768894791603, "avg_return": 0.8626953363418579, "regret": 0.00028253308846615255, "entropy": 0.0868726298213005, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:03.518239Z", "loop": 9879, "env_steps": 6070271999, "loss": 0.01842135190963745, "avg_return": 0.8632570505142212, "regret": 0.00028253308846615255, "entropy": 0.09263307601213455, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:04.413357Z", "loop": 9880, "env_steps": 6070886399, "loss": 0.019238248467445374, "avg_return": 0.8635179996490479, "regret": 0.00020184801542200148, "entropy": 0.0947621762752533, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:05.268729Z", "loop": 9881, "env_steps": 6071500799, "loss": 0.018708286806941032, "avg_return": 0.8639693260192871, "regret": 0.00020184801542200148, "entropy": 0.09249842166900635, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:06.122572Z", "loop": 9882, "env_steps": 6072115199, "loss": 0.018326323479413986, "avg_return": 0.8621785640716553, "regret": 0.00020184801542200148, "entropy": 0.09251151233911514, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:06.975687Z", "loop": 9883, "env_steps": 6072729599, "loss": 0.01820421777665615, "avg_return": 0.8632033467292786, "regret": 0.00020184801542200148, "entropy": 0.09132735431194305, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:07.829497Z", "loop": 9884, "env_steps": 6073343999, "loss": 0.019355760887265205, "avg_return": 0.8634371161460876, "regret": 0.00020184801542200148, "entropy": 0.09472836554050446, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:08.684492Z", "loop": 9885, "env_steps": 6073958399, "loss": 0.01797430031001568, "avg_return": 0.8636019229888916, "regret": 0.00020184801542200148, "entropy": 0.09290048480033875, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:09.538398Z", "loop": 9886, "env_steps": 6074572799, "loss": 0.019874369725584984, "avg_return": 0.862777829170227, "regret": 0.00020184801542200148, "entropy": 0.09712425619363785, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:10.392709Z", "loop": 9887, "env_steps": 6075187199, "loss": 0.01841421239078045, "avg_return": 0.8637401461601257, "regret": 0.00020184801542200148, "entropy": 0.09291690587997437, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:11.247005Z", "loop": 9888, "env_steps": 6075801599, "loss": 0.019663875922560692, "avg_return": 0.8639406561851501, "regret": 0.00020184801542200148, "entropy": 0.0962383970618248, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:12.102539Z", "loop": 9889, "env_steps": 6076415999, "loss": 0.018942123278975487, "avg_return": 0.8627301454544067, "regret": 0.00020184801542200148, "entropy": 0.09463738650083542, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:12.998356Z", "loop": 9890, "env_steps": 6077030399, "loss": 0.018161674961447716, "avg_return": 0.8637717962265015, "regret": 0.00040904872003011405, "entropy": 0.09262784570455551, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:13.853413Z", "loop": 9891, "env_steps": 6077644799, "loss": 0.01843293197453022, "avg_return": 0.8635990619659424, "regret": 0.00040904872003011405, "entropy": 0.09415702521800995, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:14.707697Z", "loop": 9892, "env_steps": 6078259199, "loss": 0.018905311822891235, "avg_return": 0.8628145456314087, "regret": 0.00040904872003011405, "entropy": 0.0935317724943161, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:15.562660Z", "loop": 9893, "env_steps": 6078873599, "loss": 0.018591072410345078, "avg_return": 0.8630963563919067, "regret": 0.00040904872003011405, "entropy": 0.09412552416324615, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:16.417533Z", "loop": 9894, "env_steps": 6079487999, "loss": 0.018400011584162712, "avg_return": 0.8635037541389465, "regret": 0.00040904872003011405, "entropy": 0.09524090588092804, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:17.271909Z", "loop": 9895, "env_steps": 6080102399, "loss": 0.01774340681731701, "avg_return": 0.8620516061782837, "regret": 0.00040904872003011405, "entropy": 0.09155776351690292, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:18.125517Z", "loop": 9896, "env_steps": 6080716799, "loss": 0.01765657775104046, "avg_return": 0.8640687465667725, "regret": 0.00040904872003011405, "entropy": 0.09001624584197998, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:18.979863Z", "loop": 9897, "env_steps": 6081331199, "loss": 0.017328232526779175, "avg_return": 0.8631328344345093, "regret": 0.00040904872003011405, "entropy": 0.09042271226644516, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:19.834812Z", "loop": 9898, "env_steps": 6081945599, "loss": 0.017311371862888336, "avg_return": 0.8618358373641968, "regret": 0.00040904872003011405, "entropy": 0.08747609704732895, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:20.688733Z", "loop": 9899, "env_steps": 6082559999, "loss": 0.01789400540292263, "avg_return": 0.8628381490707397, "regret": 0.00040904872003011405, "entropy": 0.08826424926519394, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:21.582271Z", "loop": 9900, "env_steps": 6083174399, "loss": 0.019170446321368217, "avg_return": 0.8626745939254761, "regret": 0.0010195383802056313, "entropy": 0.09153574705123901, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:22.436273Z", "loop": 9901, "env_steps": 6083788799, "loss": 0.017675509676337242, "avg_return": 0.8629651069641113, "regret": 0.0010195383802056313, "entropy": 0.09139334410429001, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:23.290591Z", "loop": 9902, "env_steps": 6084403199, "loss": 0.018969733268022537, "avg_return": 0.8621071577072144, "regret": 0.0010195383802056313, "entropy": 0.0936775729060173, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:24.144726Z", "loop": 9903, "env_steps": 6085017599, "loss": 0.018716827034950256, "avg_return": 0.8613755702972412, "regret": 0.0010195383802056313, "entropy": 0.08949912339448929, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:24.999524Z", "loop": 9904, "env_steps": 6085631999, "loss": 0.01877707988023758, "avg_return": 0.8612073063850403, "regret": 0.0010195383802056313, "entropy": 0.09568842500448227, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:25.852942Z", "loop": 9905, "env_steps": 6086246399, "loss": 0.01952558010816574, "avg_return": 0.8620511889457703, "regret": 0.0010195383802056313, "entropy": 0.09642965346574783, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:26.706288Z", "loop": 9906, "env_steps": 6086860799, "loss": 0.018341699615120888, "avg_return": 0.8607603907585144, "regret": 0.0010195383802056313, "entropy": 0.09396502375602722, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:27.560767Z", "loop": 9907, "env_steps": 6087475199, "loss": 0.01838909648358822, "avg_return": 0.8600675463676453, "regret": 0.0010195383802056313, "entropy": 0.09015530347824097, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:28.415628Z", "loop": 9908, "env_steps": 6088089599, "loss": 0.017416875809431076, "avg_return": 0.8603060841560364, "regret": 0.0010195383802056313, "entropy": 0.09130239486694336, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:29.269505Z", "loop": 9909, "env_steps": 6088703999, "loss": 0.016189849004149437, "avg_return": 0.8609342575073242, "regret": 0.0010195383802056313, "entropy": 0.09000018984079361, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:30.163631Z", "loop": 9910, "env_steps": 6089318399, "loss": 0.01834065467119217, "avg_return": 0.8620625734329224, "regret": 0.0022606514394283295, "entropy": 0.09584464877843857, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:31.019375Z", "loop": 9911, "env_steps": 6089932799, "loss": 0.017099173739552498, "avg_return": 0.8624981641769409, "regret": 0.0022606514394283295, "entropy": 0.08958055078983307, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:31.873950Z", "loop": 9912, "env_steps": 6090547199, "loss": 0.018017152324318886, "avg_return": 0.8616591691970825, "regret": 0.0022606514394283295, "entropy": 0.08981002867221832, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:32.728141Z", "loop": 9913, "env_steps": 6091161599, "loss": 0.016878759488463402, "avg_return": 0.8620551824569702, "regret": 0.0022606514394283295, "entropy": 0.09148294478654861, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:33.581403Z", "loop": 9914, "env_steps": 6091775999, "loss": 0.01865612529218197, "avg_return": 0.8614858388900757, "regret": 0.0022606514394283295, "entropy": 0.0908462405204773, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:34.434700Z", "loop": 9915, "env_steps": 6092390399, "loss": 0.017553001642227173, "avg_return": 0.8616226315498352, "regret": 0.0022606514394283295, "entropy": 0.09055015444755554, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:35.289108Z", "loop": 9916, "env_steps": 6093004799, "loss": 0.017620204016566277, "avg_return": 0.8635148406028748, "regret": 0.0022606514394283295, "entropy": 0.08825773000717163, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:36.143460Z", "loop": 9917, "env_steps": 6093619199, "loss": 0.016234232112765312, "avg_return": 0.8629730343818665, "regret": 0.0022606514394283295, "entropy": 0.08508572727441788, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:36.997667Z", "loop": 9918, "env_steps": 6094233599, "loss": 0.017327778041362762, "avg_return": 0.8639550805091858, "regret": 0.0022606514394283295, "entropy": 0.08563011884689331, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:37.852333Z", "loop": 9919, "env_steps": 6094847999, "loss": 0.016439922153949738, "avg_return": 0.8623851537704468, "regret": 0.0022606514394283295, "entropy": 0.08372589945793152, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:38.748275Z", "loop": 9920, "env_steps": 6095462399, "loss": 0.01708752103149891, "avg_return": 0.8631581664085388, "regret": 0.000372882786905393, "entropy": 0.08510810136795044, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:39.603386Z", "loop": 9921, "env_steps": 6096076799, "loss": 0.01623113453388214, "avg_return": 0.8645678758621216, "regret": 0.000372882786905393, "entropy": 0.08466491848230362, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:40.459594Z", "loop": 9922, "env_steps": 6096691199, "loss": 0.015644950792193413, "avg_return": 0.8645533323287964, "regret": 0.000372882786905393, "entropy": 0.0841975212097168, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:41.314025Z", "loop": 9923, "env_steps": 6097305599, "loss": 0.017682617530226707, "avg_return": 0.8625814914703369, "regret": 0.000372882786905393, "entropy": 0.08598759770393372, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:42.168924Z", "loop": 9924, "env_steps": 6097919999, "loss": 0.016262834891676903, "avg_return": 0.8637685179710388, "regret": 0.000372882786905393, "entropy": 0.08467760682106018, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:43.025045Z", "loop": 9925, "env_steps": 6098534399, "loss": 0.01559726893901825, "avg_return": 0.8637235760688782, "regret": 0.000372882786905393, "entropy": 0.08310113102197647, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:43.880287Z", "loop": 9926, "env_steps": 6099148799, "loss": 0.016699960455298424, "avg_return": 0.8630601167678833, "regret": 0.000372882786905393, "entropy": 0.08600103855133057, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:44.736394Z", "loop": 9927, "env_steps": 6099763199, "loss": 0.01722513884305954, "avg_return": 0.8633716106414795, "regret": 0.000372882786905393, "entropy": 0.08383527398109436, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:45.591423Z", "loop": 9928, "env_steps": 6100377599, "loss": 0.017176801338791847, "avg_return": 0.863685131072998, "regret": 0.000372882786905393, "entropy": 0.08673128485679626, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:46.447096Z", "loop": 9929, "env_steps": 6100991999, "loss": 0.0170051921159029, "avg_return": 0.8624542355537415, "regret": 0.000372882786905393, "entropy": 0.08429079502820969, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:47.342043Z", "loop": 9930, "env_steps": 6101606399, "loss": 0.015208698809146881, "avg_return": 0.8631260395050049, "regret": 0.00019393432012293488, "entropy": 0.08172604441642761, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:48.196721Z", "loop": 9931, "env_steps": 6102220799, "loss": 0.015157625079154968, "avg_return": 0.8633858561515808, "regret": 0.00019393432012293488, "entropy": 0.07991074025630951, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:49.051374Z", "loop": 9932, "env_steps": 6102835199, "loss": 0.0159403495490551, "avg_return": 0.8630326390266418, "regret": 0.00019393432012293488, "entropy": 0.07786921411752701, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:49.906848Z", "loop": 9933, "env_steps": 6103449599, "loss": 0.0161015372723341, "avg_return": 0.8637506365776062, "regret": 0.00019393432012293488, "entropy": 0.07911960035562515, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:50.762587Z", "loop": 9934, "env_steps": 6104063999, "loss": 0.016814151778817177, "avg_return": 0.8637715578079224, "regret": 0.00019393432012293488, "entropy": 0.08304393291473389, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:51.617986Z", "loop": 9935, "env_steps": 6104678399, "loss": 0.01875225268304348, "avg_return": 0.863365113735199, "regret": 0.00019393432012293488, "entropy": 0.09147830307483673, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:52.472970Z", "loop": 9936, "env_steps": 6105292799, "loss": 0.018245695158839226, "avg_return": 0.8623145818710327, "regret": 0.00019393432012293488, "entropy": 0.08978481590747833, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:53.328951Z", "loop": 9937, "env_steps": 6105907199, "loss": 0.018523015081882477, "avg_return": 0.8619310855865479, "regret": 0.00019393432012293488, "entropy": 0.08736022561788559, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:54.183601Z", "loop": 9938, "env_steps": 6106521599, "loss": 0.018451401963829994, "avg_return": 0.8630075454711914, "regret": 0.00019393432012293488, "entropy": 0.08698193728923798, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:55.038545Z", "loop": 9939, "env_steps": 6107135999, "loss": 0.016786502674221992, "avg_return": 0.8637303709983826, "regret": 0.00019393432012293488, "entropy": 0.08306987583637238, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:55.933608Z", "loop": 9940, "env_steps": 6107750399, "loss": 0.01648752950131893, "avg_return": 0.8629150390625, "regret": 0.00022953690495342016, "entropy": 0.08183644711971283, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:56.788568Z", "loop": 9941, "env_steps": 6108364799, "loss": 0.016036253422498703, "avg_return": 0.8634519577026367, "regret": 0.00022953690495342016, "entropy": 0.07975120842456818, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:57.642721Z", "loop": 9942, "env_steps": 6108979199, "loss": 0.015401782467961311, "avg_return": 0.8616585731506348, "regret": 0.00022953690495342016, "entropy": 0.07909662276506424, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:58.498370Z", "loop": 9943, "env_steps": 6109593599, "loss": 0.015064236707985401, "avg_return": 0.862561047077179, "regret": 0.00022953690495342016, "entropy": 0.07862681150436401, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:45:59.353403Z", "loop": 9944, "env_steps": 6110207999, "loss": 0.016085542738437653, "avg_return": 0.8633759021759033, "regret": 0.00022953690495342016, "entropy": 0.08113761246204376, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:00.208884Z", "loop": 9945, "env_steps": 6110822399, "loss": 0.01658199541270733, "avg_return": 0.8621972799301147, "regret": 0.00022953690495342016, "entropy": 0.0868586078286171, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:01.062737Z", "loop": 9946, "env_steps": 6111436799, "loss": 0.016836946830153465, "avg_return": 0.8618467450141907, "regret": 0.00022953690495342016, "entropy": 0.08553417772054672, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:01.916200Z", "loop": 9947, "env_steps": 6112051199, "loss": 0.016460036858916283, "avg_return": 0.8628037571907043, "regret": 0.00022953690495342016, "entropy": 0.08501502871513367, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:02.770319Z", "loop": 9948, "env_steps": 6112665599, "loss": 0.016814153641462326, "avg_return": 0.8634009957313538, "regret": 0.00022953690495342016, "entropy": 0.0837378203868866, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:03.626596Z", "loop": 9949, "env_steps": 6113279999, "loss": 0.017629342153668404, "avg_return": 0.862432599067688, "regret": 0.00022953690495342016, "entropy": 0.08782947063446045, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:04.519880Z", "loop": 9950, "env_steps": 6113894399, "loss": 0.01624748483300209, "avg_return": 0.8623366355895996, "regret": 0.0006621634238399565, "entropy": 0.08382570743560791, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:05.374606Z", "loop": 9951, "env_steps": 6114508799, "loss": 0.015342754311859608, "avg_return": 0.8613566160202026, "regret": 0.0006621634238399565, "entropy": 0.0801083967089653, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:06.230031Z", "loop": 9952, "env_steps": 6115123199, "loss": 0.01576942577958107, "avg_return": 0.8626760840415955, "regret": 0.0006621634238399565, "entropy": 0.07970777899026871, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:07.085460Z", "loop": 9953, "env_steps": 6115737599, "loss": 0.01527220755815506, "avg_return": 0.8615466356277466, "regret": 0.0006621634238399565, "entropy": 0.08047619462013245, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:07.939398Z", "loop": 9954, "env_steps": 6116351999, "loss": 0.015245887450873852, "avg_return": 0.8614796996116638, "regret": 0.0006621634238399565, "entropy": 0.07779953628778458, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:08.793588Z", "loop": 9955, "env_steps": 6116966399, "loss": 0.015650508925318718, "avg_return": 0.8616341352462769, "regret": 0.0006621634238399565, "entropy": 0.08198577910661697, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:09.648265Z", "loop": 9956, "env_steps": 6117580799, "loss": 0.01574735902249813, "avg_return": 0.8616230487823486, "regret": 0.0006621634238399565, "entropy": 0.08247348666191101, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:10.504978Z", "loop": 9957, "env_steps": 6118195199, "loss": 0.01751156896352768, "avg_return": 0.8624307513237, "regret": 0.0006621634238399565, "entropy": 0.08420790731906891, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:11.360023Z", "loop": 9958, "env_steps": 6118809599, "loss": 0.015566021203994751, "avg_return": 0.8612157106399536, "regret": 0.0006621634238399565, "entropy": 0.08205827325582504, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:12.214599Z", "loop": 9959, "env_steps": 6119423999, "loss": 0.017688825726509094, "avg_return": 0.8611334562301636, "regret": 0.0006621634238399565, "entropy": 0.08656980097293854, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:13.108541Z", "loop": 9960, "env_steps": 6120038399, "loss": 0.01791938953101635, "avg_return": 0.8604616522789001, "regret": 0.0021812180057168007, "entropy": 0.08814436197280884, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:13.964415Z", "loop": 9961, "env_steps": 6120652799, "loss": 0.017537524923682213, "avg_return": 0.8607603907585144, "regret": 0.0021812180057168007, "entropy": 0.08694321662187576, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:14.820071Z", "loop": 9962, "env_steps": 6121267199, "loss": 0.01779612898826599, "avg_return": 0.8611039519309998, "regret": 0.0021812180057168007, "entropy": 0.08602060377597809, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:15.675141Z", "loop": 9963, "env_steps": 6121881599, "loss": 0.016355164349079132, "avg_return": 0.8617917895317078, "regret": 0.0021812180057168007, "entropy": 0.08718995004892349, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:16.530589Z", "loop": 9964, "env_steps": 6122495999, "loss": 0.01569344662129879, "avg_return": 0.8609064221382141, "regret": 0.0021812180057168007, "entropy": 0.08399917930364609, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:17.385782Z", "loop": 9965, "env_steps": 6123110399, "loss": 0.015359848737716675, "avg_return": 0.8611719012260437, "regret": 0.0021812180057168007, "entropy": 0.08202037960290909, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:18.240867Z", "loop": 9966, "env_steps": 6123724799, "loss": 0.015115777961909771, "avg_return": 0.8602520823478699, "regret": 0.0021812180057168007, "entropy": 0.08015677332878113, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:19.095916Z", "loop": 9967, "env_steps": 6124339199, "loss": 0.014616424217820168, "avg_return": 0.8605120778083801, "regret": 0.0021812180057168007, "entropy": 0.08371403068304062, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:19.950524Z", "loop": 9968, "env_steps": 6124953599, "loss": 0.01607552170753479, "avg_return": 0.8600918054580688, "regret": 0.0021812180057168007, "entropy": 0.08378324657678604, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:20.805697Z", "loop": 9969, "env_steps": 6125567999, "loss": 0.01518253143876791, "avg_return": 0.861240029335022, "regret": 0.0021812180057168007, "entropy": 0.08163172006607056, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:21.702195Z", "loop": 9970, "env_steps": 6126182399, "loss": 0.016015086323022842, "avg_return": 0.8607122898101807, "regret": 0.0024700486101210117, "entropy": 0.07993264496326447, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:22.557043Z", "loop": 9971, "env_steps": 6126796799, "loss": 0.015838434919714928, "avg_return": 0.8604183197021484, "regret": 0.0024700486101210117, "entropy": 0.08429103344678879, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:23.411895Z", "loop": 9972, "env_steps": 6127411199, "loss": 0.016208713874220848, "avg_return": 0.8623552918434143, "regret": 0.0024700486101210117, "entropy": 0.08381674438714981, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:24.265806Z", "loop": 9973, "env_steps": 6128025599, "loss": 0.017420323565602303, "avg_return": 0.8606740236282349, "regret": 0.0024700486101210117, "entropy": 0.08618031442165375, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:25.119257Z", "loop": 9974, "env_steps": 6128639999, "loss": 0.01764032058417797, "avg_return": 0.8622548580169678, "regret": 0.0024700486101210117, "entropy": 0.08625460416078568, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:25.973159Z", "loop": 9975, "env_steps": 6129254399, "loss": 0.01674187369644642, "avg_return": 0.8624991774559021, "regret": 0.0024700486101210117, "entropy": 0.083144411444664, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:26.827369Z", "loop": 9976, "env_steps": 6129868799, "loss": 0.015934038907289505, "avg_return": 0.8616658449172974, "regret": 0.0024700486101210117, "entropy": 0.08398663997650146, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:27.681279Z", "loop": 9977, "env_steps": 6130483199, "loss": 0.01821308396756649, "avg_return": 0.8612788915634155, "regret": 0.0024700486101210117, "entropy": 0.09040255844593048, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:28.535121Z", "loop": 9978, "env_steps": 6131097599, "loss": 0.018100572749972343, "avg_return": 0.860247015953064, "regret": 0.0024700486101210117, "entropy": 0.09055007249116898, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:29.388947Z", "loop": 9979, "env_steps": 6131711999, "loss": 0.01706063188612461, "avg_return": 0.8625516891479492, "regret": 0.0024700486101210117, "entropy": 0.08605839312076569, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:30.282801Z", "loop": 9980, "env_steps": 6132326399, "loss": 0.016071327030658722, "avg_return": 0.8609639406204224, "regret": 0.0015872552758082747, "entropy": 0.08046534657478333, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:31.137267Z", "loop": 9981, "env_steps": 6132940799, "loss": 0.014714792370796204, "avg_return": 0.8621241450309753, "regret": 0.0015872552758082747, "entropy": 0.0782608687877655, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:31.991722Z", "loop": 9982, "env_steps": 6133555199, "loss": 0.015725187957286835, "avg_return": 0.8621872067451477, "regret": 0.0015872552758082747, "entropy": 0.07959071546792984, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:32.844914Z", "loop": 9983, "env_steps": 6134169599, "loss": 0.016262732446193695, "avg_return": 0.8619519472122192, "regret": 0.0015872552758082747, "entropy": 0.07896631956100464, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:33.699547Z", "loop": 9984, "env_steps": 6134783999, "loss": 0.016345225274562836, "avg_return": 0.8615295886993408, "regret": 0.0015872552758082747, "entropy": 0.0789562240242958, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:34.554110Z", "loop": 9985, "env_steps": 6135398399, "loss": 0.016862809658050537, "avg_return": 0.8634527921676636, "regret": 0.0015872552758082747, "entropy": 0.08162292093038559, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:35.408779Z", "loop": 9986, "env_steps": 6136012799, "loss": 0.015642398968338966, "avg_return": 0.8634371161460876, "regret": 0.0015872552758082747, "entropy": 0.08335833996534348, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:36.262473Z", "loop": 9987, "env_steps": 6136627199, "loss": 0.01649288274347782, "avg_return": 0.8630173802375793, "regret": 0.0015872552758082747, "entropy": 0.08384621143341064, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:37.116836Z", "loop": 9988, "env_steps": 6137241599, "loss": 0.016137942671775818, "avg_return": 0.8635783195495605, "regret": 0.0015872552758082747, "entropy": 0.08538956195116043, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:37.970578Z", "loop": 9989, "env_steps": 6137855999, "loss": 0.01728254370391369, "avg_return": 0.8631234169006348, "regret": 0.0015872552758082747, "entropy": 0.08751163631677628, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:38.862776Z", "loop": 9990, "env_steps": 6138470399, "loss": 0.017566386610269547, "avg_return": 0.8642226457595825, "regret": 0.0008887166623026133, "entropy": 0.09206855297088623, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:39.717295Z", "loop": 9991, "env_steps": 6139084799, "loss": 0.017616719007492065, "avg_return": 0.8621052503585815, "regret": 0.0008887166623026133, "entropy": 0.08957973122596741, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:40.571282Z", "loop": 9992, "env_steps": 6139699199, "loss": 0.018096594139933586, "avg_return": 0.8621727824211121, "regret": 0.0008887166623026133, "entropy": 0.08865150064229965, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:41.425846Z", "loop": 9993, "env_steps": 6140313599, "loss": 0.018578138202428818, "avg_return": 0.8621639013290405, "regret": 0.0008887166623026133, "entropy": 0.09029825031757355, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:42.280061Z", "loop": 9994, "env_steps": 6140927999, "loss": 0.019040632992982864, "avg_return": 0.8633179664611816, "regret": 0.0008887166623026133, "entropy": 0.09150383621454239, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:43.134743Z", "loop": 9995, "env_steps": 6141542399, "loss": 0.01795465126633644, "avg_return": 0.8636755347251892, "regret": 0.0008887166623026133, "entropy": 0.09376559406518936, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:43.988949Z", "loop": 9996, "env_steps": 6142156799, "loss": 0.018745748326182365, "avg_return": 0.8637306094169617, "regret": 0.0008887166623026133, "entropy": 0.09609104692935944, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:44.843834Z", "loop": 9997, "env_steps": 6142771199, "loss": 0.01911548711359501, "avg_return": 0.8630180954933167, "regret": 0.0008887166623026133, "entropy": 0.09539399296045303, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:45.698301Z", "loop": 9998, "env_steps": 6143385599, "loss": 0.018571611493825912, "avg_return": 0.8640594482421875, "regret": 0.0008887166623026133, "entropy": 0.09075872600078583, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:46.553265Z", "loop": 9999, "env_steps": 6143999999, "loss": 0.01841764897108078, "avg_return": 0.8635998964309692, "regret": 0.0008887166623026133, "entropy": 0.09639082103967667, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:47.449114Z", "loop": 10000, "env_steps": 6144614399, "loss": 0.018380600959062576, "avg_return": 0.8647320866584778, "regret": 0.0006348696770146489, "entropy": 0.09286117553710938, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:48.302389Z", "loop": 10001, "env_steps": 6145228799, "loss": 0.018603233620524406, "avg_return": 0.8631328344345093, "regret": 0.0006348696770146489, "entropy": 0.09582823514938354, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:49.156332Z", "loop": 10002, "env_steps": 6145843199, "loss": 0.01961464248597622, "avg_return": 0.8626462817192078, "regret": 0.0006348696770146489, "entropy": 0.10284856706857681, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:50.010436Z", "loop": 10003, "env_steps": 6146457599, "loss": 0.020887792110443115, "avg_return": 0.8620835542678833, "regret": 0.0006348696770146489, "entropy": 0.10421497374773026, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:50.864332Z", "loop": 10004, "env_steps": 6147071999, "loss": 0.020807567983865738, "avg_return": 0.8627582788467407, "regret": 0.0006348696770146489, "entropy": 0.10916783660650253, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:51.717780Z", "loop": 10005, "env_steps": 6147686399, "loss": 0.021469999104738235, "avg_return": 0.8625777363777161, "regret": 0.0006348696770146489, "entropy": 0.10984375327825546, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:52.571792Z", "loop": 10006, "env_steps": 6148300799, "loss": 0.021565182134509087, "avg_return": 0.8633949756622314, "regret": 0.0006348696770146489, "entropy": 0.10767415165901184, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:53.426192Z", "loop": 10007, "env_steps": 6148915199, "loss": 0.021187134087085724, "avg_return": 0.8632473945617676, "regret": 0.0006348696770146489, "entropy": 0.10503225773572922, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:54.280399Z", "loop": 10008, "env_steps": 6149529599, "loss": 0.018965264782309532, "avg_return": 0.8636106848716736, "regret": 0.0006348696770146489, "entropy": 0.09829720109701157, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:55.133286Z", "loop": 10009, "env_steps": 6150143999, "loss": 0.018220268189907074, "avg_return": 0.8635848164558411, "regret": 0.0006348696770146489, "entropy": 0.09451181441545486, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:56.026756Z", "loop": 10010, "env_steps": 6150758399, "loss": 0.017396949231624603, "avg_return": 0.8628100752830505, "regret": 0.0004447404353413731, "entropy": 0.09261444956064224, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:56.882015Z", "loop": 10011, "env_steps": 6151372799, "loss": 0.01658017560839653, "avg_return": 0.8628751039505005, "regret": 0.0004447404353413731, "entropy": 0.08650915324687958, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:57.736709Z", "loop": 10012, "env_steps": 6151987199, "loss": 0.016774458810687065, "avg_return": 0.8634527921676636, "regret": 0.0004447404353413731, "entropy": 0.08651776611804962, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:58.591437Z", "loop": 10013, "env_steps": 6152601599, "loss": 0.01628282107412815, "avg_return": 0.8650561571121216, "regret": 0.0004447404353413731, "entropy": 0.08611614257097244, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:46:59.445311Z", "loop": 10014, "env_steps": 6153215999, "loss": 0.01680859550833702, "avg_return": 0.8619297742843628, "regret": 0.0004447404353413731, "entropy": 0.08942335844039917, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:00.299659Z", "loop": 10015, "env_steps": 6153830399, "loss": 0.017033418640494347, "avg_return": 0.8635343909263611, "regret": 0.0004447404353413731, "entropy": 0.08909090608358383, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:01.154981Z", "loop": 10016, "env_steps": 6154444799, "loss": 0.016770241782069206, "avg_return": 0.8626819252967834, "regret": 0.0004447404353413731, "entropy": 0.08243097364902496, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:02.009189Z", "loop": 10017, "env_steps": 6155059199, "loss": 0.016939347609877586, "avg_return": 0.8633435368537903, "regret": 0.0004447404353413731, "entropy": 0.08796706795692444, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:02.862774Z", "loop": 10018, "env_steps": 6155673599, "loss": 0.014680685475468636, "avg_return": 0.8627166748046875, "regret": 0.0004447404353413731, "entropy": 0.07853995263576508, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:03.716785Z", "loop": 10019, "env_steps": 6156287999, "loss": 0.014833422377705574, "avg_return": 0.8622695207595825, "regret": 0.0004447404353413731, "entropy": 0.0782972052693367, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:04.612152Z", "loop": 10020, "env_steps": 6156902399, "loss": 0.014892630279064178, "avg_return": 0.863478422164917, "regret": 0.00032022499362938106, "entropy": 0.07886318117380142, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:05.465825Z", "loop": 10021, "env_steps": 6157516799, "loss": 0.015709232538938522, "avg_return": 0.862550675868988, "regret": 0.00032022499362938106, "entropy": 0.08140445500612259, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:06.320028Z", "loop": 10022, "env_steps": 6158131199, "loss": 0.016204025596380234, "avg_return": 0.8620036244392395, "regret": 0.00032022499362938106, "entropy": 0.08158238977193832, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:07.174333Z", "loop": 10023, "env_steps": 6158745599, "loss": 0.015066524036228657, "avg_return": 0.8632175922393799, "regret": 0.00032022499362938106, "entropy": 0.08020897954702377, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:08.028986Z", "loop": 10024, "env_steps": 6159359999, "loss": 0.014702918007969856, "avg_return": 0.8633508682250977, "regret": 0.00032022499362938106, "entropy": 0.07489333301782608, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:08.883047Z", "loop": 10025, "env_steps": 6159974399, "loss": 0.013906707055866718, "avg_return": 0.8620893359184265, "regret": 0.00032022499362938106, "entropy": 0.07696155458688736, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:09.737252Z", "loop": 10026, "env_steps": 6160588799, "loss": 0.014150701463222504, "avg_return": 0.8630570769309998, "regret": 0.00032022499362938106, "entropy": 0.07706135511398315, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:10.591287Z", "loop": 10027, "env_steps": 6161203199, "loss": 0.015509567223489285, "avg_return": 0.8626005053520203, "regret": 0.00032022499362938106, "entropy": 0.08311326056718826, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:11.445489Z", "loop": 10028, "env_steps": 6161817599, "loss": 0.016154978424310684, "avg_return": 0.8630489110946655, "regret": 0.00032022499362938106, "entropy": 0.08136039972305298, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:12.300311Z", "loop": 10029, "env_steps": 6162431999, "loss": 0.016169413924217224, "avg_return": 0.8636481761932373, "regret": 0.00032022499362938106, "entropy": 0.08182168751955032, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:13.194114Z", "loop": 10030, "env_steps": 6163046399, "loss": 0.015081104822456837, "avg_return": 0.8632145524024963, "regret": 0.0008641103631816804, "entropy": 0.08018379658460617, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:14.048444Z", "loop": 10031, "env_steps": 6163660799, "loss": 0.015548999421298504, "avg_return": 0.8631343841552734, "regret": 0.0008641103631816804, "entropy": 0.08020798116922379, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:14.901748Z", "loop": 10032, "env_steps": 6164275199, "loss": 0.01665673963725567, "avg_return": 0.8624788522720337, "regret": 0.0008641103631816804, "entropy": 0.08426592499017715, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:15.754803Z", "loop": 10033, "env_steps": 6164889599, "loss": 0.01421902235597372, "avg_return": 0.8638548254966736, "regret": 0.0008641103631816804, "entropy": 0.07771407067775726, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:16.609048Z", "loop": 10034, "env_steps": 6165503999, "loss": 0.015570624731481075, "avg_return": 0.8624311685562134, "regret": 0.0008641103631816804, "entropy": 0.08055783063173294, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:17.464076Z", "loop": 10035, "env_steps": 6166118399, "loss": 0.015659254044294357, "avg_return": 0.8638273477554321, "regret": 0.0008641103631816804, "entropy": 0.0776701495051384, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:18.318139Z", "loop": 10036, "env_steps": 6166732799, "loss": 0.014260895550251007, "avg_return": 0.8624935150146484, "regret": 0.0008641103631816804, "entropy": 0.07426115870475769, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:19.173541Z", "loop": 10037, "env_steps": 6167347199, "loss": 0.01404628437012434, "avg_return": 0.8630537986755371, "regret": 0.0008641103631816804, "entropy": 0.0733836367726326, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:20.029955Z", "loop": 10038, "env_steps": 6167961599, "loss": 0.014271284453570843, "avg_return": 0.8627943396568298, "regret": 0.0008641103631816804, "entropy": 0.07304101437330246, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:20.885750Z", "loop": 10039, "env_steps": 6168575999, "loss": 0.014674273319542408, "avg_return": 0.8634792566299438, "regret": 0.0008641103631816804, "entropy": 0.07270245999097824, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:21.779767Z", "loop": 10040, "env_steps": 6169190399, "loss": 0.014929661527276039, "avg_return": 0.8634148240089417, "regret": 0.0004027355753351003, "entropy": 0.07866431772708893, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:22.633758Z", "loop": 10041, "env_steps": 6169804799, "loss": 0.016935905441641808, "avg_return": 0.8628332614898682, "regret": 0.0004027355753351003, "entropy": 0.08368154615163803, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:23.487549Z", "loop": 10042, "env_steps": 6170419199, "loss": 0.017771460115909576, "avg_return": 0.8638759851455688, "regret": 0.0004027355753351003, "entropy": 0.08710964769124985, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:24.343338Z", "loop": 10043, "env_steps": 6171033599, "loss": 0.018112709745764732, "avg_return": 0.8643408417701721, "regret": 0.0004027355753351003, "entropy": 0.08856046199798584, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:25.197793Z", "loop": 10044, "env_steps": 6171647999, "loss": 0.01538542378693819, "avg_return": 0.8642669916152954, "regret": 0.0004027355753351003, "entropy": 0.07868853211402893, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:26.051785Z", "loop": 10045, "env_steps": 6172262399, "loss": 0.014484881423413754, "avg_return": 0.863254189491272, "regret": 0.0004027355753351003, "entropy": 0.07631172239780426, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:26.904116Z", "loop": 10046, "env_steps": 6172876799, "loss": 0.01494557410478592, "avg_return": 0.8625757098197937, "regret": 0.0004027355753351003, "entropy": 0.07756158709526062, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:27.757111Z", "loop": 10047, "env_steps": 6173491199, "loss": 0.016447458416223526, "avg_return": 0.8635333180427551, "regret": 0.0004027355753351003, "entropy": 0.07984086871147156, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:28.611253Z", "loop": 10048, "env_steps": 6174105599, "loss": 0.015203493647277355, "avg_return": 0.8610685467720032, "regret": 0.0004027355753351003, "entropy": 0.07721462845802307, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:29.465619Z", "loop": 10049, "env_steps": 6174719999, "loss": 0.015329621732234955, "avg_return": 0.8613283634185791, "regret": 0.0004027355753351003, "entropy": 0.07491499930620193, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:30.357726Z", "loop": 10050, "env_steps": 6175334399, "loss": 0.01561840157955885, "avg_return": 0.86093670129776, "regret": 0.003111559199169278, "entropy": 0.0784691721200943, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:31.212537Z", "loop": 10051, "env_steps": 6175948799, "loss": 0.017003459855914116, "avg_return": 0.8612188696861267, "regret": 0.003111559199169278, "entropy": 0.0862707793712616, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:32.067700Z", "loop": 10052, "env_steps": 6176563199, "loss": 0.0164736770093441, "avg_return": 0.8617833852767944, "regret": 0.003111559199169278, "entropy": 0.08185483515262604, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:32.922355Z", "loop": 10053, "env_steps": 6177177599, "loss": 0.015424917452037334, "avg_return": 0.8608028292655945, "regret": 0.003111559199169278, "entropy": 0.07885508239269257, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:33.775597Z", "loop": 10054, "env_steps": 6177791999, "loss": 0.015870435163378716, "avg_return": 0.8610658049583435, "regret": 0.003111559199169278, "entropy": 0.07800164818763733, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:34.628960Z", "loop": 10055, "env_steps": 6178406399, "loss": 0.01457845140248537, "avg_return": 0.8630556464195251, "regret": 0.003111559199169278, "entropy": 0.07648464292287827, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:35.482678Z", "loop": 10056, "env_steps": 6179020799, "loss": 0.015724269673228264, "avg_return": 0.8635875582695007, "regret": 0.003111559199169278, "entropy": 0.07929059863090515, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:36.336345Z", "loop": 10057, "env_steps": 6179635199, "loss": 0.014590977691113949, "avg_return": 0.8630880117416382, "regret": 0.003111559199169278, "entropy": 0.07656557112932205, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:37.190208Z", "loop": 10058, "env_steps": 6180249599, "loss": 0.014725579880177975, "avg_return": 0.8644116520881653, "regret": 0.003111559199169278, "entropy": 0.07208354026079178, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:38.043895Z", "loop": 10059, "env_steps": 6180863999, "loss": 0.015417966060340405, "avg_return": 0.8628625869750977, "regret": 0.003111559199169278, "entropy": 0.0756649374961853, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:38.936788Z", "loop": 10060, "env_steps": 6181478399, "loss": 0.014969964511692524, "avg_return": 0.8617243766784668, "regret": 0.0004103656974621117, "entropy": 0.07563276588916779, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:39.791112Z", "loop": 10061, "env_steps": 6182092799, "loss": 0.014343020506203175, "avg_return": 0.8647991418838501, "regret": 0.0004103656974621117, "entropy": 0.07224372029304504, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:40.646489Z", "loop": 10062, "env_steps": 6182707199, "loss": 0.015896836295723915, "avg_return": 0.8633862733840942, "regret": 0.0004103656974621117, "entropy": 0.07932915538549423, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:41.501031Z", "loop": 10063, "env_steps": 6183321599, "loss": 0.01491324882954359, "avg_return": 0.861932098865509, "regret": 0.0004103656974621117, "entropy": 0.07969461381435394, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:42.355139Z", "loop": 10064, "env_steps": 6183935999, "loss": 0.014413594268262386, "avg_return": 0.8628839254379272, "regret": 0.0004103656974621117, "entropy": 0.07722092419862747, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:43.208850Z", "loop": 10065, "env_steps": 6184550399, "loss": 0.015104874037206173, "avg_return": 0.8626061081886292, "regret": 0.0004103656974621117, "entropy": 0.07710260152816772, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:44.063532Z", "loop": 10066, "env_steps": 6185164799, "loss": 0.015584021806716919, "avg_return": 0.8643238544464111, "regret": 0.0004103656974621117, "entropy": 0.07688788324594498, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:44.917595Z", "loop": 10067, "env_steps": 6185779199, "loss": 0.016220469027757645, "avg_return": 0.8639001846313477, "regret": 0.0004103656974621117, "entropy": 0.08078715950250626, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:45.770583Z", "loop": 10068, "env_steps": 6186393599, "loss": 0.016948020085692406, "avg_return": 0.8626783490180969, "regret": 0.0004103656974621117, "entropy": 0.0812406986951828, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:46.623863Z", "loop": 10069, "env_steps": 6187007999, "loss": 0.014935122802853584, "avg_return": 0.8629797697067261, "regret": 0.0004103656974621117, "entropy": 0.07744888961315155, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:47.518033Z", "loop": 10070, "env_steps": 6187622399, "loss": 0.014657882042229176, "avg_return": 0.8634428977966309, "regret": 0.0006457027047872543, "entropy": 0.07394054532051086, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:48.371659Z", "loop": 10071, "env_steps": 6188236799, "loss": 0.013533559627830982, "avg_return": 0.8622729778289795, "regret": 0.0006457027047872543, "entropy": 0.07353304326534271, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:49.225385Z", "loop": 10072, "env_steps": 6188851199, "loss": 0.014148451387882233, "avg_return": 0.8635197877883911, "regret": 0.0006457027047872543, "entropy": 0.07149431854486465, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:50.077861Z", "loop": 10073, "env_steps": 6189465599, "loss": 0.012765876948833466, "avg_return": 0.864280641078949, "regret": 0.0006457027047872543, "entropy": 0.06955846399068832, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:50.932270Z", "loop": 10074, "env_steps": 6190079999, "loss": 0.013816110789775848, "avg_return": 0.8636041283607483, "regret": 0.0006457027047872543, "entropy": 0.06967673450708389, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:51.787182Z", "loop": 10075, "env_steps": 6190694399, "loss": 0.014020383358001709, "avg_return": 0.8629586100578308, "regret": 0.0006457027047872543, "entropy": 0.07296837866306305, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:52.641067Z", "loop": 10076, "env_steps": 6191308799, "loss": 0.013918650336563587, "avg_return": 0.862136960029602, "regret": 0.0006457027047872543, "entropy": 0.07161835581064224, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:53.494979Z", "loop": 10077, "env_steps": 6191923199, "loss": 0.013541887514293194, "avg_return": 0.862998366355896, "regret": 0.0006457027047872543, "entropy": 0.07190393656492233, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:54.350075Z", "loop": 10078, "env_steps": 6192537599, "loss": 0.013555364683270454, "avg_return": 0.8633447289466858, "regret": 0.0006457027047872543, "entropy": 0.0722687616944313, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:55.205331Z", "loop": 10079, "env_steps": 6193151999, "loss": 0.013398678973317146, "avg_return": 0.862087607383728, "regret": 0.0006457027047872543, "entropy": 0.06854960322380066, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:56.100606Z", "loop": 10080, "env_steps": 6193766399, "loss": 0.012459575198590755, "avg_return": 0.862930953502655, "regret": 0.0010164844570681453, "entropy": 0.06837538629770279, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:56.955537Z", "loop": 10081, "env_steps": 6194380799, "loss": 0.01232080440968275, "avg_return": 0.8615277409553528, "regret": 0.0010164844570681453, "entropy": 0.06547491252422333, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:57.809035Z", "loop": 10082, "env_steps": 6194995199, "loss": 0.012977033853530884, "avg_return": 0.861121416091919, "regret": 0.0010164844570681453, "entropy": 0.06836052238941193, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:58.662144Z", "loop": 10083, "env_steps": 6195609599, "loss": 0.01294634398072958, "avg_return": 0.8612808585166931, "regret": 0.0010164844570681453, "entropy": 0.06693277508020401, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:47:59.515678Z", "loop": 10084, "env_steps": 6196223999, "loss": 0.012980750761926174, "avg_return": 0.8621417284011841, "regret": 0.0010164844570681453, "entropy": 0.0672224685549736, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:00.371355Z", "loop": 10085, "env_steps": 6196838399, "loss": 0.012017722241580486, "avg_return": 0.8625030517578125, "regret": 0.0010164844570681453, "entropy": 0.06461913883686066, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:01.225792Z", "loop": 10086, "env_steps": 6197452799, "loss": 0.012370875105261803, "avg_return": 0.8621190786361694, "regret": 0.0010164844570681453, "entropy": 0.0656435638666153, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:02.080112Z", "loop": 10087, "env_steps": 6198067199, "loss": 0.010645612142980099, "avg_return": 0.8614071011543274, "regret": 0.0010164844570681453, "entropy": 0.06233232095837593, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:02.935113Z", "loop": 10088, "env_steps": 6198681599, "loss": 0.01188984140753746, "avg_return": 0.8616347312927246, "regret": 0.0010164844570681453, "entropy": 0.06717483699321747, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:03.790280Z", "loop": 10089, "env_steps": 6199295999, "loss": 0.011310955509543419, "avg_return": 0.860504150390625, "regret": 0.0010164844570681453, "entropy": 0.062318190932273865, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:04.682873Z", "loop": 10090, "env_steps": 6199910399, "loss": 0.01195231918245554, "avg_return": 0.8626229166984558, "regret": 0.001809937646612525, "entropy": 0.06439294666051865, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:05.536978Z", "loop": 10091, "env_steps": 6200524799, "loss": 0.010890385136008263, "avg_return": 0.861367404460907, "regret": 0.001809937646612525, "entropy": 0.060440994799137115, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:06.390524Z", "loop": 10092, "env_steps": 6201139199, "loss": 0.01090442668646574, "avg_return": 0.861536979675293, "regret": 0.001809937646612525, "entropy": 0.06373457610607147, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:07.244763Z", "loop": 10093, "env_steps": 6201753599, "loss": 0.012216037139296532, "avg_return": 0.8620461225509644, "regret": 0.001809937646612525, "entropy": 0.06577534973621368, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:08.098807Z", "loop": 10094, "env_steps": 6202367999, "loss": 0.012347080744802952, "avg_return": 0.8613150119781494, "regret": 0.001809937646612525, "entropy": 0.06745385378599167, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:08.953098Z", "loop": 10095, "env_steps": 6202982399, "loss": 0.012141966260969639, "avg_return": 0.862048864364624, "regret": 0.001809937646612525, "entropy": 0.06825704872608185, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:09.806721Z", "loop": 10096, "env_steps": 6203596799, "loss": 0.01124502532184124, "avg_return": 0.8623494505882263, "regret": 0.001809937646612525, "entropy": 0.0636214017868042, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:10.660655Z", "loop": 10097, "env_steps": 6204211199, "loss": 0.012521082535386086, "avg_return": 0.8624939322471619, "regret": 0.001809937646612525, "entropy": 0.06333862245082855, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:11.515537Z", "loop": 10098, "env_steps": 6204825599, "loss": 0.012215092778205872, "avg_return": 0.8625525832176208, "regret": 0.001809937646612525, "entropy": 0.06568888574838638, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:12.370085Z", "loop": 10099, "env_steps": 6205439999, "loss": 0.013076250441372395, "avg_return": 0.8632558584213257, "regret": 0.001809937646612525, "entropy": 0.07038833945989609, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:13.261470Z", "loop": 10100, "env_steps": 6206054399, "loss": 0.011102656833827496, "avg_return": 0.8628184199333191, "regret": 0.0012259014183655381, "entropy": 0.06044957786798477, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:14.115479Z", "loop": 10101, "env_steps": 6206668799, "loss": 0.011534124612808228, "avg_return": 0.8618242740631104, "regret": 0.0012259014183655381, "entropy": 0.06258350610733032, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:14.969520Z", "loop": 10102, "env_steps": 6207283199, "loss": 0.012137713842093945, "avg_return": 0.8634414672851562, "regret": 0.0012259014183655381, "entropy": 0.0638909786939621, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:15.824524Z", "loop": 10103, "env_steps": 6207897599, "loss": 0.010831848718225956, "avg_return": 0.8636510372161865, "regret": 0.0012259014183655381, "entropy": 0.06171698868274689, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:16.678908Z", "loop": 10104, "env_steps": 6208511999, "loss": 0.0113292271271348, "avg_return": 0.863121747970581, "regret": 0.0012259014183655381, "entropy": 0.06303399056196213, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:17.534247Z", "loop": 10105, "env_steps": 6209126399, "loss": 0.011695432476699352, "avg_return": 0.8622229099273682, "regret": 0.0012259014183655381, "entropy": 0.06247502565383911, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:18.388581Z", "loop": 10106, "env_steps": 6209740799, "loss": 0.011792256496846676, "avg_return": 0.8609958291053772, "regret": 0.0012259014183655381, "entropy": 0.06422444432973862, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:19.242503Z", "loop": 10107, "env_steps": 6210355199, "loss": 0.01155183557420969, "avg_return": 0.8615938425064087, "regret": 0.0012259014183655381, "entropy": 0.06263655424118042, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:20.096854Z", "loop": 10108, "env_steps": 6210969599, "loss": 0.011677933856844902, "avg_return": 0.8627811670303345, "regret": 0.0012259014183655381, "entropy": 0.06501299142837524, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:20.950633Z", "loop": 10109, "env_steps": 6211583999, "loss": 0.011890902183949947, "avg_return": 0.8613722920417786, "regret": 0.0012259014183655381, "entropy": 0.06287685036659241, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:21.845342Z", "loop": 10110, "env_steps": 6212198399, "loss": 0.010934588499367237, "avg_return": 0.8619747161865234, "regret": 0.0010586370481178164, "entropy": 0.061449047178030014, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:22.699038Z", "loop": 10111, "env_steps": 6212812799, "loss": 0.011023862287402153, "avg_return": 0.8630717992782593, "regret": 0.0010586370481178164, "entropy": 0.0653286948800087, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:23.554397Z", "loop": 10112, "env_steps": 6213427199, "loss": 0.010647743009030819, "avg_return": 0.8629871010780334, "regret": 0.0010586370481178164, "entropy": 0.05861698463559151, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:24.409956Z", "loop": 10113, "env_steps": 6214041599, "loss": 0.011415409855544567, "avg_return": 0.8622061610221863, "regret": 0.0010586370481178164, "entropy": 0.05955690145492554, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:25.264790Z", "loop": 10114, "env_steps": 6214655999, "loss": 0.011840020306408405, "avg_return": 0.862733781337738, "regret": 0.0010586370481178164, "entropy": 0.06250514090061188, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:26.119812Z", "loop": 10115, "env_steps": 6215270399, "loss": 0.012268672697246075, "avg_return": 0.8633993864059448, "regret": 0.0010586370481178164, "entropy": 0.06542190909385681, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:26.976260Z", "loop": 10116, "env_steps": 6215884799, "loss": 0.012770368717610836, "avg_return": 0.8644897937774658, "regret": 0.0010586370481178164, "entropy": 0.06701566278934479, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:27.830457Z", "loop": 10117, "env_steps": 6216499199, "loss": 0.013085952959954739, "avg_return": 0.8629016280174255, "regret": 0.0010586370481178164, "entropy": 0.06864960491657257, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:28.684539Z", "loop": 10118, "env_steps": 6217113599, "loss": 0.01366859208792448, "avg_return": 0.8632639646530151, "regret": 0.0010586370481178164, "entropy": 0.07013419270515442, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:29.537844Z", "loop": 10119, "env_steps": 6217727999, "loss": 0.014535023830831051, "avg_return": 0.8632550239562988, "regret": 0.0010586370481178164, "entropy": 0.07591677457094193, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:30.431906Z", "loop": 10120, "env_steps": 6218342399, "loss": 0.013525350950658321, "avg_return": 0.8641263842582703, "regret": 0.00015135729336179793, "entropy": 0.07236073911190033, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:31.286288Z", "loop": 10121, "env_steps": 6218956799, "loss": 0.014617008157074451, "avg_return": 0.86227947473526, "regret": 0.00015135729336179793, "entropy": 0.07590637356042862, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:32.140383Z", "loop": 10122, "env_steps": 6219571199, "loss": 0.01469445414841175, "avg_return": 0.8630284667015076, "regret": 0.00015135729336179793, "entropy": 0.07840310782194138, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:32.994357Z", "loop": 10123, "env_steps": 6220185599, "loss": 0.013971707783639431, "avg_return": 0.862408459186554, "regret": 0.00015135729336179793, "entropy": 0.07381480932235718, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:33.848951Z", "loop": 10124, "env_steps": 6220799999, "loss": 0.014473038725554943, "avg_return": 0.8630048036575317, "regret": 0.00015135729336179793, "entropy": 0.07682085782289505, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:34.703905Z", "loop": 10125, "env_steps": 6221414399, "loss": 0.014568882063031197, "avg_return": 0.8625832200050354, "regret": 0.00015135729336179793, "entropy": 0.07841227948665619, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:35.558221Z", "loop": 10126, "env_steps": 6222028799, "loss": 0.015151669271290302, "avg_return": 0.8641131520271301, "regret": 0.00015135729336179793, "entropy": 0.07940562814474106, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:36.412515Z", "loop": 10127, "env_steps": 6222643199, "loss": 0.01467289961874485, "avg_return": 0.862566351890564, "regret": 0.00015135729336179793, "entropy": 0.07741033285856247, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:37.267839Z", "loop": 10128, "env_steps": 6223257599, "loss": 0.015067127533257008, "avg_return": 0.8630183339118958, "regret": 0.00015135729336179793, "entropy": 0.07762802392244339, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:38.122669Z", "loop": 10129, "env_steps": 6223871999, "loss": 0.01391015388071537, "avg_return": 0.8625030517578125, "regret": 0.00015135729336179793, "entropy": 0.0750676840543747, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:39.018818Z", "loop": 10130, "env_steps": 6224486399, "loss": 0.014709599316120148, "avg_return": 0.862861156463623, "regret": 0.00033788805012591183, "entropy": 0.07512403279542923, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:39.873241Z", "loop": 10131, "env_steps": 6225100799, "loss": 0.015045709908008575, "avg_return": 0.8626260757446289, "regret": 0.00033788805012591183, "entropy": 0.0789843425154686, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:40.727872Z", "loop": 10132, "env_steps": 6225715199, "loss": 0.015074977651238441, "avg_return": 0.8623560070991516, "regret": 0.00033788805012591183, "entropy": 0.07968951016664505, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:41.582477Z", "loop": 10133, "env_steps": 6226329599, "loss": 0.016159918159246445, "avg_return": 0.8621206879615784, "regret": 0.00033788805012591183, "entropy": 0.08789508789777756, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:42.437050Z", "loop": 10134, "env_steps": 6226943999, "loss": 0.015480815432965755, "avg_return": 0.8626238107681274, "regret": 0.00033788805012591183, "entropy": 0.08575273305177689, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:43.291527Z", "loop": 10135, "env_steps": 6227558399, "loss": 0.015428616665303707, "avg_return": 0.8618239760398865, "regret": 0.00033788805012591183, "entropy": 0.081893689930439, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:44.145491Z", "loop": 10136, "env_steps": 6228172799, "loss": 0.016093919053673744, "avg_return": 0.8614641427993774, "regret": 0.00033788805012591183, "entropy": 0.08663919568061829, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:44.999437Z", "loop": 10137, "env_steps": 6228787199, "loss": 0.01643887721002102, "avg_return": 0.8596287965774536, "regret": 0.00033788805012591183, "entropy": 0.08831299096345901, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:45.853035Z", "loop": 10138, "env_steps": 6229401599, "loss": 0.01650659553706646, "avg_return": 0.8615065813064575, "regret": 0.00033788805012591183, "entropy": 0.08325172960758209, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:46.707148Z", "loop": 10139, "env_steps": 6230015999, "loss": 0.015553695149719715, "avg_return": 0.8614117503166199, "regret": 0.00033788805012591183, "entropy": 0.084774449467659, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:47.600951Z", "loop": 10140, "env_steps": 6230630399, "loss": 0.014868629164993763, "avg_return": 0.8620480298995972, "regret": 0.0009368144674226642, "entropy": 0.08005679398775101, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:48.454522Z", "loop": 10141, "env_steps": 6231244799, "loss": 0.015256461687386036, "avg_return": 0.862822413444519, "regret": 0.0009368144674226642, "entropy": 0.0825965479016304, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:49.307709Z", "loop": 10142, "env_steps": 6231859199, "loss": 0.014875518158078194, "avg_return": 0.8632082343101501, "regret": 0.0009368144674226642, "entropy": 0.08144884556531906, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:50.162883Z", "loop": 10143, "env_steps": 6232473599, "loss": 0.015382778830826283, "avg_return": 0.8633943796157837, "regret": 0.0009368144674226642, "entropy": 0.07907916605472565, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:51.018949Z", "loop": 10144, "env_steps": 6233087999, "loss": 0.016478409990668297, "avg_return": 0.8648220300674438, "regret": 0.0009368144674226642, "entropy": 0.08263526111841202, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:51.872736Z", "loop": 10145, "env_steps": 6233702399, "loss": 0.01590692810714245, "avg_return": 0.863676905632019, "regret": 0.0009368144674226642, "entropy": 0.08356374502182007, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:52.726343Z", "loop": 10146, "env_steps": 6234316799, "loss": 0.01724356599152088, "avg_return": 0.8631270527839661, "regret": 0.0009368144674226642, "entropy": 0.08914933353662491, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:53.580418Z", "loop": 10147, "env_steps": 6234931199, "loss": 0.01811828278005123, "avg_return": 0.8631084561347961, "regret": 0.0009368144674226642, "entropy": 0.09166651219129562, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:54.434577Z", "loop": 10148, "env_steps": 6235545599, "loss": 0.018758438527584076, "avg_return": 0.8627786636352539, "regret": 0.0009368144674226642, "entropy": 0.09473036974668503, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:55.287564Z", "loop": 10149, "env_steps": 6236159999, "loss": 0.018440382555127144, "avg_return": 0.8618341088294983, "regret": 0.0009368144674226642, "entropy": 0.09029307961463928, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:56.179853Z", "loop": 10150, "env_steps": 6236774399, "loss": 0.01838630996644497, "avg_return": 0.8636558055877686, "regret": 0.000720590993296355, "entropy": 0.0921424999833107, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:57.033160Z", "loop": 10151, "env_steps": 6237388799, "loss": 0.019049372524023056, "avg_return": 0.8623532056808472, "regret": 0.000720590993296355, "entropy": 0.09765352308750153, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:57.887427Z", "loop": 10152, "env_steps": 6238003199, "loss": 0.01834961213171482, "avg_return": 0.859907865524292, "regret": 0.000720590993296355, "entropy": 0.09364422410726547, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:58.740634Z", "loop": 10153, "env_steps": 6238617599, "loss": 0.017442846670746803, "avg_return": 0.8622881174087524, "regret": 0.000720590993296355, "entropy": 0.09249822050333023, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:48:59.594566Z", "loop": 10154, "env_steps": 6239231999, "loss": 0.017072327435016632, "avg_return": 0.861391544342041, "regret": 0.000720590993296355, "entropy": 0.08558883517980576, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:00.448750Z", "loop": 10155, "env_steps": 6239846399, "loss": 0.01698119565844536, "avg_return": 0.8614512085914612, "regret": 0.000720590993296355, "entropy": 0.08930806070566177, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:01.302334Z", "loop": 10156, "env_steps": 6240460799, "loss": 0.017631638795137405, "avg_return": 0.8624697923660278, "regret": 0.000720590993296355, "entropy": 0.08911650627851486, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:02.156382Z", "loop": 10157, "env_steps": 6241075199, "loss": 0.01700325310230255, "avg_return": 0.860826849937439, "regret": 0.000720590993296355, "entropy": 0.08804239332675934, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:03.010677Z", "loop": 10158, "env_steps": 6241689599, "loss": 0.016848579049110413, "avg_return": 0.8626390695571899, "regret": 0.000720590993296355, "entropy": 0.08884719759225845, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:03.863556Z", "loop": 10159, "env_steps": 6242303999, "loss": 0.016848556697368622, "avg_return": 0.8614305853843689, "regret": 0.000720590993296355, "entropy": 0.08936771005392075, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:04.756826Z", "loop": 10160, "env_steps": 6242918399, "loss": 0.01595386676490307, "avg_return": 0.86158287525177, "regret": 0.0017187456833198667, "entropy": 0.085833840072155, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:05.610939Z", "loop": 10161, "env_steps": 6243532799, "loss": 0.01660154201090336, "avg_return": 0.8626834154129028, "regret": 0.0017187456833198667, "entropy": 0.0844903364777565, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:06.466654Z", "loop": 10162, "env_steps": 6244147199, "loss": 0.015670960769057274, "avg_return": 0.863848090171814, "regret": 0.0017187456833198667, "entropy": 0.08296085149049759, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:07.320983Z", "loop": 10163, "env_steps": 6244761599, "loss": 0.01595848985016346, "avg_return": 0.8627470135688782, "regret": 0.0017187456833198667, "entropy": 0.08138151466846466, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:08.174930Z", "loop": 10164, "env_steps": 6245375999, "loss": 0.016334054991602898, "avg_return": 0.863016664981842, "regret": 0.0017187456833198667, "entropy": 0.08594091981649399, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:09.030020Z", "loop": 10165, "env_steps": 6245990399, "loss": 0.014863185584545135, "avg_return": 0.8630977869033813, "regret": 0.0017187456833198667, "entropy": 0.0793904960155487, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:09.884682Z", "loop": 10166, "env_steps": 6246604799, "loss": 0.015239173546433449, "avg_return": 0.863664448261261, "regret": 0.0017187456833198667, "entropy": 0.08271947503089905, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:10.738543Z", "loop": 10167, "env_steps": 6247219199, "loss": 0.01554946880787611, "avg_return": 0.862605094909668, "regret": 0.0017187456833198667, "entropy": 0.08423565328121185, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:11.591819Z", "loop": 10168, "env_steps": 6247833599, "loss": 0.014816731214523315, "avg_return": 0.8618701100349426, "regret": 0.0017187456833198667, "entropy": 0.07833694666624069, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:12.445459Z", "loop": 10169, "env_steps": 6248447999, "loss": 0.014691464602947235, "avg_return": 0.8617164492607117, "regret": 0.0017187456833198667, "entropy": 0.077454574406147, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:13.339802Z", "loop": 10170, "env_steps": 6249062399, "loss": 0.013957293704152107, "avg_return": 0.8625903725624084, "regret": 0.0002160603180527687, "entropy": 0.07324084639549255, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:14.194032Z", "loop": 10171, "env_steps": 6249676799, "loss": 0.014015759341418743, "avg_return": 0.8622816205024719, "regret": 0.0002160603180527687, "entropy": 0.07345252484083176, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:15.048776Z", "loop": 10172, "env_steps": 6250291199, "loss": 0.012301817536354065, "avg_return": 0.862876832485199, "regret": 0.0002160603180527687, "entropy": 0.07012178748846054, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:15.902545Z", "loop": 10173, "env_steps": 6250905599, "loss": 0.013428287580609322, "avg_return": 0.8645867109298706, "regret": 0.0002160603180527687, "entropy": 0.07098262757062912, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:16.756262Z", "loop": 10174, "env_steps": 6251519999, "loss": 0.012995396740734577, "avg_return": 0.8630515933036804, "regret": 0.0002160603180527687, "entropy": 0.06967205554246902, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:17.611705Z", "loop": 10175, "env_steps": 6252134399, "loss": 0.013215680606663227, "avg_return": 0.8636379241943359, "regret": 0.0002160603180527687, "entropy": 0.07227260619401932, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:18.466339Z", "loop": 10176, "env_steps": 6252748799, "loss": 0.014285503886640072, "avg_return": 0.8629962205886841, "regret": 0.0002160603180527687, "entropy": 0.0747164636850357, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:19.320022Z", "loop": 10177, "env_steps": 6253363199, "loss": 0.012368328869342804, "avg_return": 0.8638498187065125, "regret": 0.0002160603180527687, "entropy": 0.06798999756574631, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:20.173381Z", "loop": 10178, "env_steps": 6253977599, "loss": 0.013416284695267677, "avg_return": 0.8638302087783813, "regret": 0.0002160603180527687, "entropy": 0.07230354100465775, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:21.027800Z", "loop": 10179, "env_steps": 6254591999, "loss": 0.013161121867597103, "avg_return": 0.8618525266647339, "regret": 0.0002160603180527687, "entropy": 0.07081114500761032, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:21.921946Z", "loop": 10180, "env_steps": 6255206399, "loss": 0.0129209253937006, "avg_return": 0.8637610077857971, "regret": 0.0001982895191758871, "entropy": 0.06923169642686844, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:22.776137Z", "loop": 10181, "env_steps": 6255820799, "loss": 0.012709014117717743, "avg_return": 0.8642786741256714, "regret": 0.0001982895191758871, "entropy": 0.06846170127391815, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:23.629416Z", "loop": 10182, "env_steps": 6256435199, "loss": 0.013826305978000164, "avg_return": 0.863614022731781, "regret": 0.0001982895191758871, "entropy": 0.07033591717481613, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:24.484598Z", "loop": 10183, "env_steps": 6257049599, "loss": 0.01381748914718628, "avg_return": 0.8639398217201233, "regret": 0.0001982895191758871, "entropy": 0.07240106910467148, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:25.339815Z", "loop": 10184, "env_steps": 6257663999, "loss": 0.012556700967252254, "avg_return": 0.8630523681640625, "regret": 0.0001982895191758871, "entropy": 0.06768345087766647, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:26.194757Z", "loop": 10185, "env_steps": 6258278399, "loss": 0.013364838436245918, "avg_return": 0.8624817132949829, "regret": 0.0001982895191758871, "entropy": 0.0704110637307167, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:27.048548Z", "loop": 10186, "env_steps": 6258892799, "loss": 0.011740882880985737, "avg_return": 0.8631618618965149, "regret": 0.0001982895191758871, "entropy": 0.06678769737482071, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:27.903845Z", "loop": 10187, "env_steps": 6259507199, "loss": 0.012325610965490341, "avg_return": 0.8636353611946106, "regret": 0.0001982895191758871, "entropy": 0.06630183756351471, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:28.758338Z", "loop": 10188, "env_steps": 6260121599, "loss": 0.012913462705910206, "avg_return": 0.8644063472747803, "regret": 0.0001982895191758871, "entropy": 0.07044052332639694, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:29.613806Z", "loop": 10189, "env_steps": 6260735999, "loss": 0.01254760380834341, "avg_return": 0.8627913594245911, "regret": 0.0001982895191758871, "entropy": 0.06727344542741776, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:30.511581Z", "loop": 10190, "env_steps": 6261350399, "loss": 0.012993650510907173, "avg_return": 0.8636835813522339, "regret": 0.00030745600815862417, "entropy": 0.06798910349607468, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:31.366569Z", "loop": 10191, "env_steps": 6261964799, "loss": 0.013421875424683094, "avg_return": 0.8653534054756165, "regret": 0.00030745600815862417, "entropy": 0.07022568583488464, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:32.222206Z", "loop": 10192, "env_steps": 6262579199, "loss": 0.012617620639503002, "avg_return": 0.8630245327949524, "regret": 0.00030745600815862417, "entropy": 0.0684794932603836, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:33.077615Z", "loop": 10193, "env_steps": 6263193599, "loss": 0.013802235014736652, "avg_return": 0.8623526096343994, "regret": 0.00030745600815862417, "entropy": 0.07771831005811691, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:33.932039Z", "loop": 10194, "env_steps": 6263807999, "loss": 0.013194787316024303, "avg_return": 0.8645563721656799, "regret": 0.00030745600815862417, "entropy": 0.07044504582881927, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:34.786939Z", "loop": 10195, "env_steps": 6264422399, "loss": 0.013722424395382404, "avg_return": 0.8644986152648926, "regret": 0.00030745600815862417, "entropy": 0.07274827361106873, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:35.641558Z", "loop": 10196, "env_steps": 6265036799, "loss": 0.01364555861800909, "avg_return": 0.8630865812301636, "regret": 0.00030745600815862417, "entropy": 0.07116575539112091, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:36.497064Z", "loop": 10197, "env_steps": 6265651199, "loss": 0.013105263002216816, "avg_return": 0.8622958660125732, "regret": 0.00030745600815862417, "entropy": 0.06924214214086533, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:37.352371Z", "loop": 10198, "env_steps": 6266265599, "loss": 0.012734835036098957, "avg_return": 0.8610995411872864, "regret": 0.00030745600815862417, "entropy": 0.07044070214033127, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:38.208099Z", "loop": 10199, "env_steps": 6266879999, "loss": 0.01373361237347126, "avg_return": 0.8624604344367981, "regret": 0.00030745600815862417, "entropy": 0.07097193598747253, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:39.105777Z", "loop": 10200, "env_steps": 6267494399, "loss": 0.013977636583149433, "avg_return": 0.8640087842941284, "regret": 0.0002369429130339995, "entropy": 0.07028841227293015, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:39.959543Z", "loop": 10201, "env_steps": 6268108799, "loss": 0.01316174864768982, "avg_return": 0.8634774088859558, "regret": 0.0002369429130339995, "entropy": 0.07359030097723007, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:40.813849Z", "loop": 10202, "env_steps": 6268723199, "loss": 0.014176130294799805, "avg_return": 0.8645952343940735, "regret": 0.0002369429130339995, "entropy": 0.07337955385446548, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:41.668466Z", "loop": 10203, "env_steps": 6269337599, "loss": 0.014278425835072994, "avg_return": 0.8629994988441467, "regret": 0.0002369429130339995, "entropy": 0.0758541151881218, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:42.523752Z", "loop": 10204, "env_steps": 6269951999, "loss": 0.013027503155171871, "avg_return": 0.8620983958244324, "regret": 0.0002369429130339995, "entropy": 0.07076402008533478, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:43.378236Z", "loop": 10205, "env_steps": 6270566399, "loss": 0.014481507241725922, "avg_return": 0.8652468919754028, "regret": 0.0002369429130339995, "entropy": 0.07344697415828705, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:44.232432Z", "loop": 10206, "env_steps": 6271180799, "loss": 0.014033972285687923, "avg_return": 0.8643237352371216, "regret": 0.0002369429130339995, "entropy": 0.07611116021871567, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:45.086766Z", "loop": 10207, "env_steps": 6271795199, "loss": 0.01640481874346733, "avg_return": 0.8642308712005615, "regret": 0.0002369429130339995, "entropy": 0.08489762246608734, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:45.941252Z", "loop": 10208, "env_steps": 6272409599, "loss": 0.015530777163803577, "avg_return": 0.8627379536628723, "regret": 0.0002369429130339995, "entropy": 0.07948470860719681, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:46.795798Z", "loop": 10209, "env_steps": 6273023999, "loss": 0.015617881901562214, "avg_return": 0.8639629483222961, "regret": 0.0002369429130339995, "entropy": 0.083708256483078, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:47.691803Z", "loop": 10210, "env_steps": 6273638399, "loss": 0.01552140899002552, "avg_return": 0.8633412718772888, "regret": 0.00024496877449564636, "entropy": 0.08244125545024872, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:48.547149Z", "loop": 10211, "env_steps": 6274252799, "loss": 0.0156335961073637, "avg_return": 0.8627358078956604, "regret": 0.00024496877449564636, "entropy": 0.08309495449066162, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:49.401213Z", "loop": 10212, "env_steps": 6274867199, "loss": 0.01570054702460766, "avg_return": 0.8628751039505005, "regret": 0.00024496877449564636, "entropy": 0.08119886368513107, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:50.255171Z", "loop": 10213, "env_steps": 6275481599, "loss": 0.016048705205321312, "avg_return": 0.8633280396461487, "regret": 0.00024496877449564636, "entropy": 0.085166335105896, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:51.109844Z", "loop": 10214, "env_steps": 6276095999, "loss": 0.01632247492671013, "avg_return": 0.8619594573974609, "regret": 0.00024496877449564636, "entropy": 0.08392217010259628, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:51.964293Z", "loop": 10215, "env_steps": 6276710399, "loss": 0.015994854271411896, "avg_return": 0.8630129098892212, "regret": 0.00024496877449564636, "entropy": 0.08402958512306213, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:52.818309Z", "loop": 10216, "env_steps": 6277324799, "loss": 0.016595108434557915, "avg_return": 0.8629581928253174, "regret": 0.00024496877449564636, "entropy": 0.0849233865737915, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:53.672840Z", "loop": 10217, "env_steps": 6277939199, "loss": 0.016197239980101585, "avg_return": 0.8625651001930237, "regret": 0.00024496877449564636, "entropy": 0.08560048043727875, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:54.527283Z", "loop": 10218, "env_steps": 6278553599, "loss": 0.017610516399145126, "avg_return": 0.8612726330757141, "regret": 0.00024496877449564636, "entropy": 0.08964238315820694, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:55.381105Z", "loop": 10219, "env_steps": 6279167999, "loss": 0.017231252044439316, "avg_return": 0.8621008396148682, "regret": 0.00024496877449564636, "entropy": 0.09369577467441559, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:56.275023Z", "loop": 10220, "env_steps": 6279782399, "loss": 0.016310324892401695, "avg_return": 0.8613086938858032, "regret": 0.0028102046344429255, "entropy": 0.08454827219247818, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:57.130352Z", "loop": 10221, "env_steps": 6280396799, "loss": 0.017645038664340973, "avg_return": 0.8598757386207581, "regret": 0.0028102046344429255, "entropy": 0.0881444439291954, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:57.985328Z", "loop": 10222, "env_steps": 6281011199, "loss": 0.017142286524176598, "avg_return": 0.8623877167701721, "regret": 0.0028102046344429255, "entropy": 0.08683432638645172, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:58.838525Z", "loop": 10223, "env_steps": 6281625599, "loss": 0.017267966642975807, "avg_return": 0.8611602783203125, "regret": 0.0028102046344429255, "entropy": 0.08954142034053802, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:49:59.691603Z", "loop": 10224, "env_steps": 6282239999, "loss": 0.017152011394500732, "avg_return": 0.8616980314254761, "regret": 0.0028102046344429255, "entropy": 0.08543932437896729, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:00.545681Z", "loop": 10225, "env_steps": 6282854399, "loss": 0.015727471560239792, "avg_return": 0.8624892234802246, "regret": 0.0028102046344429255, "entropy": 0.08300668746232986, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:01.400310Z", "loop": 10226, "env_steps": 6283468799, "loss": 0.015113243833184242, "avg_return": 0.8629145622253418, "regret": 0.0028102046344429255, "entropy": 0.08051887154579163, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:02.255679Z", "loop": 10227, "env_steps": 6284083199, "loss": 0.016386384144425392, "avg_return": 0.8633565306663513, "regret": 0.0028102046344429255, "entropy": 0.08318884670734406, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:03.109991Z", "loop": 10228, "env_steps": 6284697599, "loss": 0.01563265360891819, "avg_return": 0.8635358810424805, "regret": 0.0028102046344429255, "entropy": 0.08084014058113098, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:03.963820Z", "loop": 10229, "env_steps": 6285311999, "loss": 0.016323139891028404, "avg_return": 0.8632369041442871, "regret": 0.0028102046344429255, "entropy": 0.08216163516044617, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:04.860265Z", "loop": 10230, "env_steps": 6285926399, "loss": 0.014194970019161701, "avg_return": 0.8630969524383545, "regret": 0.0005678018205799162, "entropy": 0.0792313739657402, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:05.714650Z", "loop": 10231, "env_steps": 6286540799, "loss": 0.014836042188107967, "avg_return": 0.862503707408905, "regret": 0.0005678018205799162, "entropy": 0.08147728443145752, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:06.569141Z", "loop": 10232, "env_steps": 6287155199, "loss": 0.015838420018553734, "avg_return": 0.8619237542152405, "regret": 0.0005678018205799162, "entropy": 0.08327952772378922, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:07.423143Z", "loop": 10233, "env_steps": 6287769599, "loss": 0.015189917758107185, "avg_return": 0.8634071946144104, "regret": 0.0005678018205799162, "entropy": 0.0789933055639267, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:08.277710Z", "loop": 10234, "env_steps": 6288383999, "loss": 0.01729678176343441, "avg_return": 0.8634480834007263, "regret": 0.0005678018205799162, "entropy": 0.08748449385166168, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:09.132249Z", "loop": 10235, "env_steps": 6288998399, "loss": 0.0155166732147336, "avg_return": 0.8642489910125732, "regret": 0.0005678018205799162, "entropy": 0.08258406072854996, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:09.986360Z", "loop": 10236, "env_steps": 6289612799, "loss": 0.015974776819348335, "avg_return": 0.8627867102622986, "regret": 0.0005678018205799162, "entropy": 0.08627298474311829, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:10.840122Z", "loop": 10237, "env_steps": 6290227199, "loss": 0.016808046028017998, "avg_return": 0.8629578948020935, "regret": 0.0005678018205799162, "entropy": 0.09046325832605362, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:11.694762Z", "loop": 10238, "env_steps": 6290841599, "loss": 0.01892697624862194, "avg_return": 0.8626272678375244, "regret": 0.0005678018205799162, "entropy": 0.0930713564157486, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:12.549565Z", "loop": 10239, "env_steps": 6291455999, "loss": 0.018621409311890602, "avg_return": 0.8634591102600098, "regret": 0.0005678018205799162, "entropy": 0.09410656988620758, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:13.442849Z", "loop": 10240, "env_steps": 6292070399, "loss": 0.018993914127349854, "avg_return": 0.8623773455619812, "regret": 0.0008574798121117055, "entropy": 0.09753628075122833, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:14.295797Z", "loop": 10241, "env_steps": 6292684799, "loss": 0.019031260162591934, "avg_return": 0.8632983565330505, "regret": 0.0008574798121117055, "entropy": 0.09597071260213852, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:15.151431Z", "loop": 10242, "env_steps": 6293299199, "loss": 0.0196138396859169, "avg_return": 0.8624807000160217, "regret": 0.0008574798121117055, "entropy": 0.09782871603965759, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:16.006166Z", "loop": 10243, "env_steps": 6293913599, "loss": 0.01855744794011116, "avg_return": 0.862479567527771, "regret": 0.0008574798121117055, "entropy": 0.09386178106069565, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:16.860274Z", "loop": 10244, "env_steps": 6294527999, "loss": 0.01949615776538849, "avg_return": 0.8643910884857178, "regret": 0.0008574798121117055, "entropy": 0.09629979729652405, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:17.713804Z", "loop": 10245, "env_steps": 6295142399, "loss": 0.018830932676792145, "avg_return": 0.861774742603302, "regret": 0.0008574798121117055, "entropy": 0.09909683465957642, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:18.568341Z", "loop": 10246, "env_steps": 6295756799, "loss": 0.019301502034068108, "avg_return": 0.8626452088356018, "regret": 0.0008574798121117055, "entropy": 0.09655839949846268, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:19.421683Z", "loop": 10247, "env_steps": 6296371199, "loss": 0.01837862841784954, "avg_return": 0.8626853823661804, "regret": 0.0008574798121117055, "entropy": 0.09534940123558044, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:20.274991Z", "loop": 10248, "env_steps": 6296985599, "loss": 0.017402125522494316, "avg_return": 0.8629406690597534, "regret": 0.0008574798121117055, "entropy": 0.08868429064750671, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:21.128387Z", "loop": 10249, "env_steps": 6297599999, "loss": 0.017117124050855637, "avg_return": 0.8633036613464355, "regret": 0.0008574798121117055, "entropy": 0.08721143752336502, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:22.022580Z", "loop": 10250, "env_steps": 6298214399, "loss": 0.01660987176001072, "avg_return": 0.8627968430519104, "regret": 0.0012046124320477247, "entropy": 0.0871695950627327, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:22.876050Z", "loop": 10251, "env_steps": 6298828799, "loss": 0.01808609440922737, "avg_return": 0.8622597455978394, "regret": 0.0012046124320477247, "entropy": 0.09166541695594788, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:23.730117Z", "loop": 10252, "env_steps": 6299443199, "loss": 0.01762886717915535, "avg_return": 0.8637797236442566, "regret": 0.0012046124320477247, "entropy": 0.08929111808538437, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:24.584129Z", "loop": 10253, "env_steps": 6300057599, "loss": 0.0171212051063776, "avg_return": 0.8635793328285217, "regret": 0.0012046124320477247, "entropy": 0.08703521639108658, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:25.437957Z", "loop": 10254, "env_steps": 6300671999, "loss": 0.016435885801911354, "avg_return": 0.8623594641685486, "regret": 0.0012046124320477247, "entropy": 0.08772183209657669, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:26.290868Z", "loop": 10255, "env_steps": 6301286399, "loss": 0.017682885751128197, "avg_return": 0.8626477122306824, "regret": 0.0012046124320477247, "entropy": 0.09260952472686768, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:27.144117Z", "loop": 10256, "env_steps": 6301900799, "loss": 0.01793460175395012, "avg_return": 0.863243043422699, "regret": 0.0012046124320477247, "entropy": 0.09064191579818726, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:27.998652Z", "loop": 10257, "env_steps": 6302515199, "loss": 0.016677558422088623, "avg_return": 0.8619973063468933, "regret": 0.0012046124320477247, "entropy": 0.08632377535104752, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:28.852458Z", "loop": 10258, "env_steps": 6303129599, "loss": 0.017326630651950836, "avg_return": 0.8640778064727783, "regret": 0.0012046124320477247, "entropy": 0.09042614698410034, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:29.704758Z", "loop": 10259, "env_steps": 6303743999, "loss": 0.01766888238489628, "avg_return": 0.8628216981887817, "regret": 0.0012046124320477247, "entropy": 0.08770841360092163, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:30.599809Z", "loop": 10260, "env_steps": 6304358399, "loss": 0.016147926449775696, "avg_return": 0.8651863932609558, "regret": 0.0006866130279377103, "entropy": 0.08479643613100052, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:31.454534Z", "loop": 10261, "env_steps": 6304972799, "loss": 0.01749580167233944, "avg_return": 0.862011730670929, "regret": 0.0006866130279377103, "entropy": 0.09184300154447556, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:32.308692Z", "loop": 10262, "env_steps": 6305587199, "loss": 0.016377992928028107, "avg_return": 0.8636242747306824, "regret": 0.0006866130279377103, "entropy": 0.08797531574964523, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:33.162543Z", "loop": 10263, "env_steps": 6306201599, "loss": 0.01793798804283142, "avg_return": 0.8627291917800903, "regret": 0.0006866130279377103, "entropy": 0.09060145914554596, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:34.016593Z", "loop": 10264, "env_steps": 6306815999, "loss": 0.017219165340065956, "avg_return": 0.8626595139503479, "regret": 0.0006866130279377103, "entropy": 0.08904962241649628, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:34.871679Z", "loop": 10265, "env_steps": 6307430399, "loss": 0.01667986623942852, "avg_return": 0.8632827997207642, "regret": 0.0006866130279377103, "entropy": 0.08612535148859024, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:35.725815Z", "loop": 10266, "env_steps": 6308044799, "loss": 0.01883290894329548, "avg_return": 0.8627740740776062, "regret": 0.0006866130279377103, "entropy": 0.09194913506507874, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:36.579838Z", "loop": 10267, "env_steps": 6308659199, "loss": 0.019743366166949272, "avg_return": 0.8629732728004456, "regret": 0.0006866130279377103, "entropy": 0.09664483368396759, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:37.433851Z", "loop": 10268, "env_steps": 6309273599, "loss": 0.01908070594072342, "avg_return": 0.8636572360992432, "regret": 0.0006866130279377103, "entropy": 0.09277475625276566, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:38.288872Z", "loop": 10269, "env_steps": 6309887999, "loss": 0.018781783059239388, "avg_return": 0.862372636795044, "regret": 0.0006866130279377103, "entropy": 0.0964694619178772, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:39.184605Z", "loop": 10270, "env_steps": 6310502399, "loss": 0.019200406968593597, "avg_return": 0.8627602458000183, "regret": 0.0003706089046318084, "entropy": 0.09629058092832565, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:40.039211Z", "loop": 10271, "env_steps": 6311116799, "loss": 0.01795392669737339, "avg_return": 0.8638249635696411, "regret": 0.0003706089046318084, "entropy": 0.09360576421022415, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:40.893377Z", "loop": 10272, "env_steps": 6311731199, "loss": 0.01818327233195305, "avg_return": 0.8637301921844482, "regret": 0.0003706089046318084, "entropy": 0.0910327136516571, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:41.748707Z", "loop": 10273, "env_steps": 6312345599, "loss": 0.017493126913905144, "avg_return": 0.8615736365318298, "regret": 0.0003706089046318084, "entropy": 0.0927751213312149, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:42.603399Z", "loop": 10274, "env_steps": 6312959999, "loss": 0.019161580130457878, "avg_return": 0.8617296814918518, "regret": 0.0003706089046318084, "entropy": 0.0960647463798523, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:43.457632Z", "loop": 10275, "env_steps": 6313574399, "loss": 0.017662763595581055, "avg_return": 0.8638097047805786, "regret": 0.0003706089046318084, "entropy": 0.08940331637859344, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:44.311617Z", "loop": 10276, "env_steps": 6314188799, "loss": 0.017746170982718468, "avg_return": 0.8635962009429932, "regret": 0.0003706089046318084, "entropy": 0.08717518299818039, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:45.165823Z", "loop": 10277, "env_steps": 6314803199, "loss": 0.016050102189183235, "avg_return": 0.863542914390564, "regret": 0.0003706089046318084, "entropy": 0.08487503230571747, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:46.019832Z", "loop": 10278, "env_steps": 6315417599, "loss": 0.015048593282699585, "avg_return": 0.8634676337242126, "regret": 0.0003706089046318084, "entropy": 0.07872054725885391, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:46.873765Z", "loop": 10279, "env_steps": 6316031999, "loss": 0.015219047665596008, "avg_return": 0.8626373410224915, "regret": 0.0003706089046318084, "entropy": 0.0803230032324791, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:47.768052Z", "loop": 10280, "env_steps": 6316646399, "loss": 0.014883897267282009, "avg_return": 0.8635823726654053, "regret": 0.0005971895880065858, "entropy": 0.08060506731271744, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:48.622444Z", "loop": 10281, "env_steps": 6317260799, "loss": 0.015740325674414635, "avg_return": 0.8622987866401672, "regret": 0.0005971895880065858, "entropy": 0.08140799403190613, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:49.476045Z", "loop": 10282, "env_steps": 6317875199, "loss": 0.0162156131118536, "avg_return": 0.8648748993873596, "regret": 0.0005971895880065858, "entropy": 0.08161648362874985, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:50.329709Z", "loop": 10283, "env_steps": 6318489599, "loss": 0.015085555613040924, "avg_return": 0.862377941608429, "regret": 0.0005971895880065858, "entropy": 0.0788973942399025, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:51.183954Z", "loop": 10284, "env_steps": 6319103999, "loss": 0.015341537073254585, "avg_return": 0.8624180555343628, "regret": 0.0005971895880065858, "entropy": 0.08264385163784027, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:52.038836Z", "loop": 10285, "env_steps": 6319718399, "loss": 0.014736932702362537, "avg_return": 0.8627539277076721, "regret": 0.0005971895880065858, "entropy": 0.08009718358516693, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:52.891802Z", "loop": 10286, "env_steps": 6320332799, "loss": 0.01444892305880785, "avg_return": 0.8626112937927246, "regret": 0.0005971895880065858, "entropy": 0.0805828720331192, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:53.744628Z", "loop": 10287, "env_steps": 6320947199, "loss": 0.01546927448362112, "avg_return": 0.8627327680587769, "regret": 0.0005971895880065858, "entropy": 0.08344460278749466, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:54.598601Z", "loop": 10288, "env_steps": 6321561599, "loss": 0.015633849427103996, "avg_return": 0.8608876466751099, "regret": 0.0005971895880065858, "entropy": 0.08566892147064209, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:55.453855Z", "loop": 10289, "env_steps": 6322175999, "loss": 0.014344540424644947, "avg_return": 0.8605934977531433, "regret": 0.0005971895880065858, "entropy": 0.08012942224740982, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:56.350339Z", "loop": 10290, "env_steps": 6322790399, "loss": 0.015505178831517696, "avg_return": 0.8602744936943054, "regret": 0.0028880969621241093, "entropy": 0.08112398535013199, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:57.204408Z", "loop": 10291, "env_steps": 6323404799, "loss": 0.013972488231956959, "avg_return": 0.8602093458175659, "regret": 0.0028880969621241093, "entropy": 0.0766008272767067, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:58.058245Z", "loop": 10292, "env_steps": 6324019199, "loss": 0.015127328224480152, "avg_return": 0.8582836389541626, "regret": 0.0028880969621241093, "entropy": 0.08028709143400192, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:58.913719Z", "loop": 10293, "env_steps": 6324633599, "loss": 0.015455384738743305, "avg_return": 0.8584793210029602, "regret": 0.0028880969621241093, "entropy": 0.07972854375839233, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:50:59.767804Z", "loop": 10294, "env_steps": 6325247999, "loss": 0.015405994839966297, "avg_return": 0.8586120009422302, "regret": 0.0028880969621241093, "entropy": 0.08127570897340775, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:00.622058Z", "loop": 10295, "env_steps": 6325862399, "loss": 0.015853077173233032, "avg_return": 0.8579691648483276, "regret": 0.0028880969621241093, "entropy": 0.08262232691049576, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:01.475677Z", "loop": 10296, "env_steps": 6326476799, "loss": 0.016524171456694603, "avg_return": 0.8585301637649536, "regret": 0.0028880969621241093, "entropy": 0.08246372640132904, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:02.330574Z", "loop": 10297, "env_steps": 6327091199, "loss": 0.014756265096366405, "avg_return": 0.8595194816589355, "regret": 0.0028880969621241093, "entropy": 0.07693057507276535, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:03.185168Z", "loop": 10298, "env_steps": 6327705599, "loss": 0.015512201003730297, "avg_return": 0.8595178723335266, "regret": 0.0028880969621241093, "entropy": 0.07961577922105789, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:04.040070Z", "loop": 10299, "env_steps": 6328319999, "loss": 0.01423000730574131, "avg_return": 0.8598400354385376, "regret": 0.0028880969621241093, "entropy": 0.07568149268627167, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:04.937212Z", "loop": 10300, "env_steps": 6328934399, "loss": 0.013170375488698483, "avg_return": 0.8616780042648315, "regret": 0.002090355148538947, "entropy": 0.07147269695997238, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:05.791929Z", "loop": 10301, "env_steps": 6329548799, "loss": 0.01543571799993515, "avg_return": 0.8627216815948486, "regret": 0.002090355148538947, "entropy": 0.0770004615187645, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:06.646989Z", "loop": 10302, "env_steps": 6330163199, "loss": 0.014553581364452839, "avg_return": 0.8612090349197388, "regret": 0.002090355148538947, "entropy": 0.07746464759111404, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:07.502024Z", "loop": 10303, "env_steps": 6330777599, "loss": 0.014532412402331829, "avg_return": 0.8627579212188721, "regret": 0.002090355148538947, "entropy": 0.07479251176118851, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:08.357121Z", "loop": 10304, "env_steps": 6331391999, "loss": 0.01495554018765688, "avg_return": 0.8648614883422852, "regret": 0.002090355148538947, "entropy": 0.07933895289897919, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:09.212573Z", "loop": 10305, "env_steps": 6332006399, "loss": 0.01376297790557146, "avg_return": 0.8628723621368408, "regret": 0.002090355148538947, "entropy": 0.0739489495754242, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:10.066482Z", "loop": 10306, "env_steps": 6332620799, "loss": 0.01468315627425909, "avg_return": 0.8635756373405457, "regret": 0.002090355148538947, "entropy": 0.07983298599720001, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:10.920724Z", "loop": 10307, "env_steps": 6333235199, "loss": 0.013474784791469574, "avg_return": 0.8636514544487, "regret": 0.002090355148538947, "entropy": 0.07272738218307495, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:11.776104Z", "loop": 10308, "env_steps": 6333849599, "loss": 0.013449256308376789, "avg_return": 0.8645144701004028, "regret": 0.002090355148538947, "entropy": 0.07412492483854294, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:12.633764Z", "loop": 10309, "env_steps": 6334463999, "loss": 0.013485549949109554, "avg_return": 0.863910973072052, "regret": 0.002090355148538947, "entropy": 0.07084101438522339, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:13.528447Z", "loop": 10310, "env_steps": 6335078399, "loss": 0.013631842099130154, "avg_return": 0.8634816408157349, "regret": 0.00015694285684730858, "entropy": 0.07307558506727219, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:14.383147Z", "loop": 10311, "env_steps": 6335692799, "loss": 0.013394986279308796, "avg_return": 0.8629547357559204, "regret": 0.00015694285684730858, "entropy": 0.07326751947402954, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:15.239123Z", "loop": 10312, "env_steps": 6336307199, "loss": 0.01375992875546217, "avg_return": 0.8625391125679016, "regret": 0.00015694285684730858, "entropy": 0.07262764126062393, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:16.094416Z", "loop": 10313, "env_steps": 6336921599, "loss": 0.01279656495898962, "avg_return": 0.8634361028671265, "regret": 0.00015694285684730858, "entropy": 0.07060007005929947, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:16.949023Z", "loop": 10314, "env_steps": 6337535999, "loss": 0.013237220235168934, "avg_return": 0.8638556003570557, "regret": 0.00015694285684730858, "entropy": 0.07202094793319702, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:17.804499Z", "loop": 10315, "env_steps": 6338150399, "loss": 0.013180054724216461, "avg_return": 0.8631909489631653, "regret": 0.00015694285684730858, "entropy": 0.06842054426670074, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:18.660370Z", "loop": 10316, "env_steps": 6338764799, "loss": 0.013984153978526592, "avg_return": 0.8625096678733826, "regret": 0.00015694285684730858, "entropy": 0.07342047989368439, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:19.516486Z", "loop": 10317, "env_steps": 6339379199, "loss": 0.014325566589832306, "avg_return": 0.863598644733429, "regret": 0.00015694285684730858, "entropy": 0.0727587416768074, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:20.370500Z", "loop": 10318, "env_steps": 6339993599, "loss": 0.013770614750683308, "avg_return": 0.8637185096740723, "regret": 0.00015694285684730858, "entropy": 0.0732257291674614, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:21.224726Z", "loop": 10319, "env_steps": 6340607999, "loss": 0.014016412198543549, "avg_return": 0.8633646965026855, "regret": 0.00015694285684730858, "entropy": 0.07481493055820465, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:22.123231Z", "loop": 10320, "env_steps": 6341222399, "loss": 0.01342015154659748, "avg_return": 0.8644022941589355, "regret": 0.00018350573373027146, "entropy": 0.07332810014486313, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:22.977782Z", "loop": 10321, "env_steps": 6341836799, "loss": 0.01340497750788927, "avg_return": 0.8632033467292786, "regret": 0.00018350573373027146, "entropy": 0.07128243893384933, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:23.832974Z", "loop": 10322, "env_steps": 6342451199, "loss": 0.013858089223504066, "avg_return": 0.8640202879905701, "regret": 0.00018350573373027146, "entropy": 0.07402873784303665, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:24.687504Z", "loop": 10323, "env_steps": 6343065599, "loss": 0.013807252049446106, "avg_return": 0.8644431829452515, "regret": 0.00018350573373027146, "entropy": 0.07186314463615417, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:25.543977Z", "loop": 10324, "env_steps": 6343679999, "loss": 0.013415500521659851, "avg_return": 0.8636922240257263, "regret": 0.00018350573373027146, "entropy": 0.07145892083644867, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:26.398550Z", "loop": 10325, "env_steps": 6344294399, "loss": 0.014250910840928555, "avg_return": 0.8629631996154785, "regret": 0.00018350573373027146, "entropy": 0.07695575058460236, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:27.252776Z", "loop": 10326, "env_steps": 6344908799, "loss": 0.014264324679970741, "avg_return": 0.863029420375824, "regret": 0.00018350573373027146, "entropy": 0.07164973020553589, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:28.106762Z", "loop": 10327, "env_steps": 6345523199, "loss": 0.013917583040893078, "avg_return": 0.8613970875740051, "regret": 0.00018350573373027146, "entropy": 0.07488521188497543, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:28.961645Z", "loop": 10328, "env_steps": 6346137599, "loss": 0.012961424887180328, "avg_return": 0.8629602193832397, "regret": 0.00018350573373027146, "entropy": 0.07265546172857285, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:29.817072Z", "loop": 10329, "env_steps": 6346751999, "loss": 0.014140396378934383, "avg_return": 0.8639484643936157, "regret": 0.00018350573373027146, "entropy": 0.07475782930850983, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:30.714646Z", "loop": 10330, "env_steps": 6347366399, "loss": 0.013476242311298847, "avg_return": 0.8633182048797607, "regret": 0.0005289784166961908, "entropy": 0.0757780447602272, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:31.570289Z", "loop": 10331, "env_steps": 6347980799, "loss": 0.014406169764697552, "avg_return": 0.8618523478507996, "regret": 0.0005289784166961908, "entropy": 0.07742812484502792, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:32.426563Z", "loop": 10332, "env_steps": 6348595199, "loss": 0.01349747646600008, "avg_return": 0.8620511889457703, "regret": 0.0005289784166961908, "entropy": 0.07324059307575226, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:33.280457Z", "loop": 10333, "env_steps": 6349209599, "loss": 0.013294415548443794, "avg_return": 0.861620306968689, "regret": 0.0005289784166961908, "entropy": 0.07700154185295105, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:34.135286Z", "loop": 10334, "env_steps": 6349823999, "loss": 0.013670258224010468, "avg_return": 0.8634126782417297, "regret": 0.0005289784166961908, "entropy": 0.07393201440572739, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:34.990137Z", "loop": 10335, "env_steps": 6350438399, "loss": 0.014747693203389645, "avg_return": 0.8618003726005554, "regret": 0.0005289784166961908, "entropy": 0.07819580286741257, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:35.844674Z", "loop": 10336, "env_steps": 6351052799, "loss": 0.013992267660796642, "avg_return": 0.8624482154846191, "regret": 0.0005289784166961908, "entropy": 0.07677789032459259, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:36.698330Z", "loop": 10337, "env_steps": 6351667199, "loss": 0.015107913874089718, "avg_return": 0.8645772337913513, "regret": 0.0005289784166961908, "entropy": 0.07983950525522232, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:37.553328Z", "loop": 10338, "env_steps": 6352281599, "loss": 0.013674959540367126, "avg_return": 0.8618285059928894, "regret": 0.0005289784166961908, "entropy": 0.07503920048475266, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:38.407202Z", "loop": 10339, "env_steps": 6352895999, "loss": 0.015083389356732368, "avg_return": 0.8644842505455017, "regret": 0.0005289784166961908, "entropy": 0.07505635172128677, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:39.303956Z", "loop": 10340, "env_steps": 6353510399, "loss": 0.013467894867062569, "avg_return": 0.8632305264472961, "regret": 0.0001595003268448636, "entropy": 0.07498952001333237, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:40.158048Z", "loop": 10341, "env_steps": 6354124799, "loss": 0.014168322086334229, "avg_return": 0.8633307814598083, "regret": 0.0001595003268448636, "entropy": 0.07468774914741516, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:41.012405Z", "loop": 10342, "env_steps": 6354739199, "loss": 0.014664128422737122, "avg_return": 0.8642075657844543, "regret": 0.0001595003268448636, "entropy": 0.07868986576795578, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:41.867325Z", "loop": 10343, "env_steps": 6355353599, "loss": 0.015086467377841473, "avg_return": 0.8646814227104187, "regret": 0.0001595003268448636, "entropy": 0.07724886387586594, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:42.722720Z", "loop": 10344, "env_steps": 6355967999, "loss": 0.01574975997209549, "avg_return": 0.8624926209449768, "regret": 0.0001595003268448636, "entropy": 0.07871902734041214, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:43.576342Z", "loop": 10345, "env_steps": 6356582399, "loss": 0.01438759546726942, "avg_return": 0.8632110953330994, "regret": 0.0001595003268448636, "entropy": 0.07750622928142548, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:44.429761Z", "loop": 10346, "env_steps": 6357196799, "loss": 0.015321830287575722, "avg_return": 0.8635239601135254, "regret": 0.0001595003268448636, "entropy": 0.077979177236557, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:45.284061Z", "loop": 10347, "env_steps": 6357811199, "loss": 0.014819805510342121, "avg_return": 0.8637036085128784, "regret": 0.0001595003268448636, "entropy": 0.07631106674671173, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:46.138901Z", "loop": 10348, "env_steps": 6358425599, "loss": 0.013852803967893124, "avg_return": 0.8623623847961426, "regret": 0.0001595003268448636, "entropy": 0.07470952719449997, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:46.993503Z", "loop": 10349, "env_steps": 6359039999, "loss": 0.014595985412597656, "avg_return": 0.8645697236061096, "regret": 0.0001595003268448636, "entropy": 0.07443825155496597, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:47.887286Z", "loop": 10350, "env_steps": 6359654399, "loss": 0.015103302896022797, "avg_return": 0.8615368008613586, "regret": 0.0006057763821445405, "entropy": 0.07822831720113754, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:48.741551Z", "loop": 10351, "env_steps": 6360268799, "loss": 0.014707922004163265, "avg_return": 0.8638489842414856, "regret": 0.0006057763821445405, "entropy": 0.07668887078762054, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:49.596715Z", "loop": 10352, "env_steps": 6360883199, "loss": 0.015335937030613422, "avg_return": 0.8627246022224426, "regret": 0.0006057763821445405, "entropy": 0.07938209176063538, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:50.451201Z", "loop": 10353, "env_steps": 6361497599, "loss": 0.014050789177417755, "avg_return": 0.8620432615280151, "regret": 0.0006057763821445405, "entropy": 0.07696673274040222, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:51.306404Z", "loop": 10354, "env_steps": 6362111999, "loss": 0.014501655474305153, "avg_return": 0.8616482615470886, "regret": 0.0006057763821445405, "entropy": 0.07606727629899979, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:52.160272Z", "loop": 10355, "env_steps": 6362726399, "loss": 0.015008526854217052, "avg_return": 0.8627300262451172, "regret": 0.0006057763821445405, "entropy": 0.07606255263090134, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:53.014600Z", "loop": 10356, "env_steps": 6363340799, "loss": 0.01456501241773367, "avg_return": 0.8611192107200623, "regret": 0.0006057763821445405, "entropy": 0.07634306699037552, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:53.869504Z", "loop": 10357, "env_steps": 6363955199, "loss": 0.014404462650418282, "avg_return": 0.8639581799507141, "regret": 0.0006057763821445405, "entropy": 0.07367993891239166, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:54.723651Z", "loop": 10358, "env_steps": 6364569599, "loss": 0.015796078369021416, "avg_return": 0.8634536862373352, "regret": 0.0006057763821445405, "entropy": 0.07852969318628311, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:55.577423Z", "loop": 10359, "env_steps": 6365183999, "loss": 0.014989378862082958, "avg_return": 0.8643448948860168, "regret": 0.0006057763821445405, "entropy": 0.07648499310016632, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:56.471282Z", "loop": 10360, "env_steps": 6365798399, "loss": 0.013530273921787739, "avg_return": 0.8628082275390625, "regret": 0.0004033893928863108, "entropy": 0.06948836892843246, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:57.325785Z", "loop": 10361, "env_steps": 6366412799, "loss": 0.013732573948800564, "avg_return": 0.861575722694397, "regret": 0.0004033893928863108, "entropy": 0.07410258054733276, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:58.180225Z", "loop": 10362, "env_steps": 6367027199, "loss": 0.013671894557774067, "avg_return": 0.8637990355491638, "regret": 0.0004033893928863108, "entropy": 0.07184003293514252, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:59.034251Z", "loop": 10363, "env_steps": 6367641599, "loss": 0.01352132298052311, "avg_return": 0.864585816860199, "regret": 0.0004033893928863108, "entropy": 0.07328496128320694, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:51:59.888324Z", "loop": 10364, "env_steps": 6368255999, "loss": 0.012521854601800442, "avg_return": 0.8630104660987854, "regret": 0.0004033893928863108, "entropy": 0.06667351722717285, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:00.742351Z", "loop": 10365, "env_steps": 6368870399, "loss": 0.013077633455395699, "avg_return": 0.8631774187088013, "regret": 0.0004033893928863108, "entropy": 0.06614957749843597, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:01.596568Z", "loop": 10366, "env_steps": 6369484799, "loss": 0.011807410977780819, "avg_return": 0.8633732199668884, "regret": 0.0004033893928863108, "entropy": 0.06510969996452332, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:02.451172Z", "loop": 10367, "env_steps": 6370099199, "loss": 0.01209134142845869, "avg_return": 0.8629626631736755, "regret": 0.0004033893928863108, "entropy": 0.0633997768163681, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:03.304291Z", "loop": 10368, "env_steps": 6370713599, "loss": 0.01170837040990591, "avg_return": 0.8639782667160034, "regret": 0.0004033893928863108, "entropy": 0.06153205409646034, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:04.158334Z", "loop": 10369, "env_steps": 6371327999, "loss": 0.013514737598598003, "avg_return": 0.8626936078071594, "regret": 0.0004033893928863108, "entropy": 0.07172229140996933, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:05.052020Z", "loop": 10370, "env_steps": 6371942399, "loss": 0.012704200111329556, "avg_return": 0.8630068302154541, "regret": 0.00035062417737208307, "entropy": 0.06725931167602539, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:05.907064Z", "loop": 10371, "env_steps": 6372556799, "loss": 0.012765474617481232, "avg_return": 0.8626052141189575, "regret": 0.00035062417737208307, "entropy": 0.06873118877410889, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:06.760848Z", "loop": 10372, "env_steps": 6373171199, "loss": 0.012764203362166882, "avg_return": 0.8637146353721619, "regret": 0.00035062417737208307, "entropy": 0.07093188166618347, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:07.614339Z", "loop": 10373, "env_steps": 6373785599, "loss": 0.012313896790146828, "avg_return": 0.8631385564804077, "regret": 0.00035062417737208307, "entropy": 0.065150186419487, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:08.468406Z", "loop": 10374, "env_steps": 6374399999, "loss": 0.012891413643956184, "avg_return": 0.86307293176651, "regret": 0.00035062417737208307, "entropy": 0.06998267769813538, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:09.323023Z", "loop": 10375, "env_steps": 6375014399, "loss": 0.012712244875729084, "avg_return": 0.8640103340148926, "regret": 0.00035062417737208307, "entropy": 0.0725327804684639, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:10.176910Z", "loop": 10376, "env_steps": 6375628799, "loss": 0.013628847897052765, "avg_return": 0.8620069622993469, "regret": 0.00035062417737208307, "entropy": 0.07121652364730835, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:11.030288Z", "loop": 10377, "env_steps": 6376243199, "loss": 0.013405664823949337, "avg_return": 0.8632508516311646, "regret": 0.00035062417737208307, "entropy": 0.06942461431026459, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:11.883680Z", "loop": 10378, "env_steps": 6376857599, "loss": 0.013249605894088745, "avg_return": 0.8621260523796082, "regret": 0.00035062417737208307, "entropy": 0.069574736058712, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:12.738479Z", "loop": 10379, "env_steps": 6377471999, "loss": 0.012202686630189419, "avg_return": 0.8629925847053528, "regret": 0.00035062417737208307, "entropy": 0.06645768880844116, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:13.632278Z", "loop": 10380, "env_steps": 6378086399, "loss": 0.012503399513661861, "avg_return": 0.861751139163971, "regret": 0.000932206166908145, "entropy": 0.0683126375079155, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:14.485975Z", "loop": 10381, "env_steps": 6378700799, "loss": 0.012155837379395962, "avg_return": 0.8622266054153442, "regret": 0.000932206166908145, "entropy": 0.06655659526586533, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:15.339906Z", "loop": 10382, "env_steps": 6379315199, "loss": 0.012594128958880901, "avg_return": 0.8621058464050293, "regret": 0.000932206166908145, "entropy": 0.06734798848628998, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:16.195101Z", "loop": 10383, "env_steps": 6379929599, "loss": 0.011665967293083668, "avg_return": 0.860592782497406, "regret": 0.000932206166908145, "entropy": 0.0667671263217926, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:17.051010Z", "loop": 10384, "env_steps": 6380543999, "loss": 0.012677207589149475, "avg_return": 0.8611938953399658, "regret": 0.000932206166908145, "entropy": 0.06963768601417542, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:17.905898Z", "loop": 10385, "env_steps": 6381158399, "loss": 0.011920665390789509, "avg_return": 0.8615286350250244, "regret": 0.000932206166908145, "entropy": 0.06540321558713913, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:18.760534Z", "loop": 10386, "env_steps": 6381772799, "loss": 0.011856988072395325, "avg_return": 0.8621090054512024, "regret": 0.000932206166908145, "entropy": 0.06647874414920807, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:19.615544Z", "loop": 10387, "env_steps": 6382387199, "loss": 0.012519958429038525, "avg_return": 0.862418532371521, "regret": 0.000932206166908145, "entropy": 0.06672925502061844, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:20.469830Z", "loop": 10388, "env_steps": 6383001599, "loss": 0.011622956953942776, "avg_return": 0.8624988794326782, "regret": 0.000932206166908145, "entropy": 0.06521246582269669, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:21.324133Z", "loop": 10389, "env_steps": 6383615999, "loss": 0.011757942847907543, "avg_return": 0.862507164478302, "regret": 0.000932206166908145, "entropy": 0.06502564251422882, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:22.218438Z", "loop": 10390, "env_steps": 6384230399, "loss": 0.01241337787359953, "avg_return": 0.8625537157058716, "regret": 0.0006724235136061907, "entropy": 0.06624451279640198, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:23.073518Z", "loop": 10391, "env_steps": 6384844799, "loss": 0.010713479481637478, "avg_return": 0.8622536659240723, "regret": 0.0006724235136061907, "entropy": 0.05774962529540062, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:23.928221Z", "loop": 10392, "env_steps": 6385459199, "loss": 0.011294051073491573, "avg_return": 0.8626412153244019, "regret": 0.0006724235136061907, "entropy": 0.06361072510480881, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:24.782143Z", "loop": 10393, "env_steps": 6386073599, "loss": 0.012389136478304863, "avg_return": 0.8632302284240723, "regret": 0.0006724235136061907, "entropy": 0.06565308570861816, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:25.637737Z", "loop": 10394, "env_steps": 6386687999, "loss": 0.011348547413945198, "avg_return": 0.863086462020874, "regret": 0.0006724235136061907, "entropy": 0.0618663914501667, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:26.491226Z", "loop": 10395, "env_steps": 6387302399, "loss": 0.01075863279402256, "avg_return": 0.8636573553085327, "regret": 0.0006724235136061907, "entropy": 0.05925632268190384, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:27.345225Z", "loop": 10396, "env_steps": 6387916799, "loss": 0.01154507789760828, "avg_return": 0.8631669282913208, "regret": 0.0006724235136061907, "entropy": 0.06454457342624664, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:28.199556Z", "loop": 10397, "env_steps": 6388531199, "loss": 0.013385849073529243, "avg_return": 0.8628853559494019, "regret": 0.0006724235136061907, "entropy": 0.06668819487094879, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:29.052979Z", "loop": 10398, "env_steps": 6389145599, "loss": 0.011620217002928257, "avg_return": 0.8641418814659119, "regret": 0.0006724235136061907, "entropy": 0.0642455667257309, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:29.907197Z", "loop": 10399, "env_steps": 6389759999, "loss": 0.011898896656930447, "avg_return": 0.8638249039649963, "regret": 0.0006724235136061907, "entropy": 0.06320320814847946, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:30.800668Z", "loop": 10400, "env_steps": 6390374399, "loss": 0.012165945954620838, "avg_return": 0.8630847334861755, "regret": 0.00020874587062280625, "entropy": 0.06674045324325562, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:31.655387Z", "loop": 10401, "env_steps": 6390988799, "loss": 0.012394904159009457, "avg_return": 0.8627328872680664, "regret": 0.00020874587062280625, "entropy": 0.06573018431663513, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:32.509814Z", "loop": 10402, "env_steps": 6391603199, "loss": 0.012690054252743721, "avg_return": 0.8637067079544067, "regret": 0.00020874587062280625, "entropy": 0.07089211791753769, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:33.366238Z", "loop": 10403, "env_steps": 6392217599, "loss": 0.011731799691915512, "avg_return": 0.8631970286369324, "regret": 0.00020874587062280625, "entropy": 0.06800373643636703, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:34.220361Z", "loop": 10404, "env_steps": 6392831999, "loss": 0.013998659327626228, "avg_return": 0.8615965247154236, "regret": 0.00020874587062280625, "entropy": 0.07293103635311127, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:35.073550Z", "loop": 10405, "env_steps": 6393446399, "loss": 0.013478326611220837, "avg_return": 0.8620790839195251, "regret": 0.00020874587062280625, "entropy": 0.07114287465810776, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:35.928021Z", "loop": 10406, "env_steps": 6394060799, "loss": 0.014869502745568752, "avg_return": 0.8595573902130127, "regret": 0.00020874587062280625, "entropy": 0.07850281894207001, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:36.783469Z", "loop": 10407, "env_steps": 6394675199, "loss": 0.014661991968750954, "avg_return": 0.8617427945137024, "regret": 0.00020874587062280625, "entropy": 0.07859411090612411, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:37.639361Z", "loop": 10408, "env_steps": 6395289599, "loss": 0.014700564555823803, "avg_return": 0.8607819080352783, "regret": 0.00020874587062280625, "entropy": 0.07664836943149567, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:38.492950Z", "loop": 10409, "env_steps": 6395903999, "loss": 0.013850144110620022, "avg_return": 0.862903356552124, "regret": 0.00020874587062280625, "entropy": 0.07630202174186707, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:39.386691Z", "loop": 10410, "env_steps": 6396518399, "loss": 0.01460616197437048, "avg_return": 0.8624873161315918, "regret": 0.0011207208735868335, "entropy": 0.07659737765789032, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:40.241543Z", "loop": 10411, "env_steps": 6397132799, "loss": 0.01295789610594511, "avg_return": 0.863464891910553, "regret": 0.0011207208735868335, "entropy": 0.07284674793481827, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:41.094865Z", "loop": 10412, "env_steps": 6397747199, "loss": 0.013560861349105835, "avg_return": 0.8625146746635437, "regret": 0.0011207208735868335, "entropy": 0.07164909690618515, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:41.948492Z", "loop": 10413, "env_steps": 6398361599, "loss": 0.01367565430700779, "avg_return": 0.8641921281814575, "regret": 0.0011207208735868335, "entropy": 0.07072386890649796, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:42.802419Z", "loop": 10414, "env_steps": 6398975999, "loss": 0.013690419495105743, "avg_return": 0.8626462817192078, "regret": 0.0011207208735868335, "entropy": 0.07165918499231339, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:43.656436Z", "loop": 10415, "env_steps": 6399590399, "loss": 0.012801173143088818, "avg_return": 0.8627378344535828, "regret": 0.0011207208735868335, "entropy": 0.07001906633377075, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:44.511557Z", "loop": 10416, "env_steps": 6400204799, "loss": 0.01338285207748413, "avg_return": 0.8642167448997498, "regret": 0.0011207208735868335, "entropy": 0.07157639414072037, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:45.365866Z", "loop": 10417, "env_steps": 6400819199, "loss": 0.014809787273406982, "avg_return": 0.8633819818496704, "regret": 0.0011207208735868335, "entropy": 0.07572715729475021, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:46.220904Z", "loop": 10418, "env_steps": 6401433599, "loss": 0.014214013703167439, "avg_return": 0.8625325560569763, "regret": 0.0011207208735868335, "entropy": 0.07585663348436356, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:47.075004Z", "loop": 10419, "env_steps": 6402047999, "loss": 0.012606200762093067, "avg_return": 0.8630271553993225, "regret": 0.0011207208735868335, "entropy": 0.06875347346067429, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:47.968408Z", "loop": 10420, "env_steps": 6402662399, "loss": 0.013196568004786968, "avg_return": 0.8639931678771973, "regret": 0.0002090393245453015, "entropy": 0.07399315387010574, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:48.822270Z", "loop": 10421, "env_steps": 6403276799, "loss": 0.013646135106682777, "avg_return": 0.8631079196929932, "regret": 0.0002090393245453015, "entropy": 0.0751449316740036, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:49.676615Z", "loop": 10422, "env_steps": 6403891199, "loss": 0.01477019488811493, "avg_return": 0.863846480846405, "regret": 0.0002090393245453015, "entropy": 0.07885488122701645, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:50.531567Z", "loop": 10423, "env_steps": 6404505599, "loss": 0.014396277256309986, "avg_return": 0.8629207611083984, "regret": 0.0002090393245453015, "entropy": 0.07820135354995728, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:51.385805Z", "loop": 10424, "env_steps": 6405119999, "loss": 0.012567711062729359, "avg_return": 0.8633290529251099, "regret": 0.0002090393245453015, "entropy": 0.07162214070558548, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:52.239877Z", "loop": 10425, "env_steps": 6405734399, "loss": 0.014453080482780933, "avg_return": 0.8620646595954895, "regret": 0.0002090393245453015, "entropy": 0.07565691322088242, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:53.093492Z", "loop": 10426, "env_steps": 6406348799, "loss": 0.01379025261849165, "avg_return": 0.8624143600463867, "regret": 0.0002090393245453015, "entropy": 0.07559696584939957, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:53.947004Z", "loop": 10427, "env_steps": 6406963199, "loss": 0.012990250252187252, "avg_return": 0.8649643063545227, "regret": 0.0002090393245453015, "entropy": 0.07175559550523758, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:54.800671Z", "loop": 10428, "env_steps": 6407577599, "loss": 0.013713672757148743, "avg_return": 0.8631395697593689, "regret": 0.0002090393245453015, "entropy": 0.07530350983142853, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:55.655525Z", "loop": 10429, "env_steps": 6408191999, "loss": 0.015199924819171429, "avg_return": 0.862705409526825, "regret": 0.0002090393245453015, "entropy": 0.08087325841188431, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:56.549393Z", "loop": 10430, "env_steps": 6408806399, "loss": 0.015687458217144012, "avg_return": 0.8629152774810791, "regret": 0.0003628304984886199, "entropy": 0.08012714236974716, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:57.403303Z", "loop": 10431, "env_steps": 6409420799, "loss": 0.015103831887245178, "avg_return": 0.8620756268501282, "regret": 0.0003628304984886199, "entropy": 0.07812882214784622, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:58.257358Z", "loop": 10432, "env_steps": 6410035199, "loss": 0.01467783935368061, "avg_return": 0.8618094325065613, "regret": 0.0003628304984886199, "entropy": 0.07854147255420685, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:59.111886Z", "loop": 10433, "env_steps": 6410649599, "loss": 0.014416013844311237, "avg_return": 0.8630827069282532, "regret": 0.0003628304984886199, "entropy": 0.07686642557382584, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:52:59.966445Z", "loop": 10434, "env_steps": 6411263999, "loss": 0.015587150119245052, "avg_return": 0.8623001575469971, "regret": 0.0003628304984886199, "entropy": 0.08336196094751358, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:00.820974Z", "loop": 10435, "env_steps": 6411878399, "loss": 0.015148296020925045, "avg_return": 0.8633819818496704, "regret": 0.0003628304984886199, "entropy": 0.08057750761508942, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:01.673851Z", "loop": 10436, "env_steps": 6412492799, "loss": 0.015548519790172577, "avg_return": 0.8623772263526917, "regret": 0.0003628304984886199, "entropy": 0.08441955596208572, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:02.526580Z", "loop": 10437, "env_steps": 6413107199, "loss": 0.014835181646049023, "avg_return": 0.8611624240875244, "regret": 0.0003628304984886199, "entropy": 0.08051853626966476, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:03.381825Z", "loop": 10438, "env_steps": 6413721599, "loss": 0.015614653006196022, "avg_return": 0.8625578880310059, "regret": 0.0003628304984886199, "entropy": 0.08140996843576431, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:04.235702Z", "loop": 10439, "env_steps": 6414335999, "loss": 0.015485499985516071, "avg_return": 0.8610242009162903, "regret": 0.0003628304984886199, "entropy": 0.08225373178720474, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:05.129610Z", "loop": 10440, "env_steps": 6414950399, "loss": 0.016133274883031845, "avg_return": 0.863182783126831, "regret": 0.0014968989416956902, "entropy": 0.0820038914680481, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:05.983951Z", "loop": 10441, "env_steps": 6415564799, "loss": 0.01600460708141327, "avg_return": 0.8609007000923157, "regret": 0.0014968989416956902, "entropy": 0.08430605381727219, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:06.840279Z", "loop": 10442, "env_steps": 6416179199, "loss": 0.015992343425750732, "avg_return": 0.8630484938621521, "regret": 0.0014968989416956902, "entropy": 0.08427664637565613, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:07.693993Z", "loop": 10443, "env_steps": 6416793599, "loss": 0.01504395343363285, "avg_return": 0.8630003929138184, "regret": 0.0014968989416956902, "entropy": 0.08334877341985703, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:08.548701Z", "loop": 10444, "env_steps": 6417407999, "loss": 0.01397700048983097, "avg_return": 0.8644901514053345, "regret": 0.0014968989416956902, "entropy": 0.0800839439034462, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:09.403563Z", "loop": 10445, "env_steps": 6418022399, "loss": 0.014559675939381123, "avg_return": 0.8632625341415405, "regret": 0.0014968989416956902, "entropy": 0.07843483239412308, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:10.258634Z", "loop": 10446, "env_steps": 6418636799, "loss": 0.013893540017306805, "avg_return": 0.8645690083503723, "regret": 0.0014968989416956902, "entropy": 0.07567733526229858, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:11.113795Z", "loop": 10447, "env_steps": 6419251199, "loss": 0.01371573656797409, "avg_return": 0.8628359436988831, "regret": 0.0014968989416956902, "entropy": 0.07694463431835175, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:11.970593Z", "loop": 10448, "env_steps": 6419865599, "loss": 0.014765861444175243, "avg_return": 0.8630483150482178, "regret": 0.0014968989416956902, "entropy": 0.07537867873907089, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:12.824701Z", "loop": 10449, "env_steps": 6420479999, "loss": 0.014311159960925579, "avg_return": 0.8630455732345581, "regret": 0.0014968989416956902, "entropy": 0.07767054438591003, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:13.717616Z", "loop": 10450, "env_steps": 6421094399, "loss": 0.014528989791870117, "avg_return": 0.8623383045196533, "regret": 0.0002580785658210516, "entropy": 0.08008785545825958, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:14.571608Z", "loop": 10451, "env_steps": 6421708799, "loss": 0.01396353542804718, "avg_return": 0.8620646595954895, "regret": 0.0002580785658210516, "entropy": 0.07934460043907166, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:15.426155Z", "loop": 10452, "env_steps": 6422323199, "loss": 0.014717819169163704, "avg_return": 0.8629946112632751, "regret": 0.0002580785658210516, "entropy": 0.07996590435504913, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:16.280782Z", "loop": 10453, "env_steps": 6422937599, "loss": 0.014802276156842709, "avg_return": 0.8642425537109375, "regret": 0.0002580785658210516, "entropy": 0.08221397548913956, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:17.135573Z", "loop": 10454, "env_steps": 6423551999, "loss": 0.01613672636449337, "avg_return": 0.8625144362449646, "regret": 0.0002580785658210516, "entropy": 0.08599453419446945, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:17.989195Z", "loop": 10455, "env_steps": 6424166399, "loss": 0.013675818219780922, "avg_return": 0.8631429076194763, "regret": 0.0002580785658210516, "entropy": 0.07558576762676239, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:18.843458Z", "loop": 10456, "env_steps": 6424780799, "loss": 0.016399530693888664, "avg_return": 0.8623389005661011, "regret": 0.0002580785658210516, "entropy": 0.08586003631353378, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:19.697993Z", "loop": 10457, "env_steps": 6425395199, "loss": 0.01504973042756319, "avg_return": 0.8612675070762634, "regret": 0.0002580785658210516, "entropy": 0.08584318310022354, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:20.553135Z", "loop": 10458, "env_steps": 6426009599, "loss": 0.014685168862342834, "avg_return": 0.8631944060325623, "regret": 0.0002580785658210516, "entropy": 0.08085181564092636, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:21.407020Z", "loop": 10459, "env_steps": 6426623999, "loss": 0.014529861509799957, "avg_return": 0.8630645871162415, "regret": 0.0002580785658210516, "entropy": 0.07964590191841125, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:22.298778Z", "loop": 10460, "env_steps": 6427238399, "loss": 0.015699632465839386, "avg_return": 0.8626836538314819, "regret": 0.00041752500692382455, "entropy": 0.08510113507509232, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:23.152523Z", "loop": 10461, "env_steps": 6427852799, "loss": 0.014955244027078152, "avg_return": 0.86371910572052, "regret": 0.00041752500692382455, "entropy": 0.08278768509626389, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:24.007577Z", "loop": 10462, "env_steps": 6428467199, "loss": 0.014607011340558529, "avg_return": 0.8635357618331909, "regret": 0.00041752500692382455, "entropy": 0.07825569063425064, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:24.861546Z", "loop": 10463, "env_steps": 6429081599, "loss": 0.014950861223042011, "avg_return": 0.8660056591033936, "regret": 0.00041752500692382455, "entropy": 0.0821530893445015, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:25.714962Z", "loop": 10464, "env_steps": 6429695999, "loss": 0.014317802153527737, "avg_return": 0.8645001649856567, "regret": 0.00041752500692382455, "entropy": 0.08250217139720917, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:26.568556Z", "loop": 10465, "env_steps": 6430310399, "loss": 0.015153976157307625, "avg_return": 0.8623232245445251, "regret": 0.00041752500692382455, "entropy": 0.08545757830142975, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:27.423960Z", "loop": 10466, "env_steps": 6430924799, "loss": 0.015514920465648174, "avg_return": 0.8616024255752563, "regret": 0.00041752500692382455, "entropy": 0.0859038233757019, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:28.278495Z", "loop": 10467, "env_steps": 6431539199, "loss": 0.015944233164191246, "avg_return": 0.8629814982414246, "regret": 0.00041752500692382455, "entropy": 0.08820383250713348, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:29.131607Z", "loop": 10468, "env_steps": 6432153599, "loss": 0.015178613364696503, "avg_return": 0.8634549975395203, "regret": 0.00041752500692382455, "entropy": 0.08690296113491058, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:29.984972Z", "loop": 10469, "env_steps": 6432767999, "loss": 0.015617205761373043, "avg_return": 0.8645185828208923, "regret": 0.00041752500692382455, "entropy": 0.08693039417266846, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:30.877315Z", "loop": 10470, "env_steps": 6433382399, "loss": 0.015627210959792137, "avg_return": 0.8643245697021484, "regret": 0.0010418647434562445, "entropy": 0.08949778974056244, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:31.732001Z", "loop": 10471, "env_steps": 6433996799, "loss": 0.016500024124979973, "avg_return": 0.8628774285316467, "regret": 0.0010418647434562445, "entropy": 0.09166866540908813, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:32.587148Z", "loop": 10472, "env_steps": 6434611199, "loss": 0.016105040907859802, "avg_return": 0.8620871901512146, "regret": 0.0010418647434562445, "entropy": 0.09074712544679642, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:33.442693Z", "loop": 10473, "env_steps": 6435225599, "loss": 0.015964023768901825, "avg_return": 0.8624386787414551, "regret": 0.0010418647434562445, "entropy": 0.09548067301511765, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:34.297304Z", "loop": 10474, "env_steps": 6435839999, "loss": 0.016707491129636765, "avg_return": 0.8622803092002869, "regret": 0.0010418647434562445, "entropy": 0.09779829531908035, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:35.150883Z", "loop": 10475, "env_steps": 6436454399, "loss": 0.017109744250774384, "avg_return": 0.8626807928085327, "regret": 0.0010418647434562445, "entropy": 0.09861806035041809, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:36.005882Z", "loop": 10476, "env_steps": 6437068799, "loss": 0.0163960512727499, "avg_return": 0.8623964786529541, "regret": 0.0010418647434562445, "entropy": 0.09571191668510437, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:36.861456Z", "loop": 10477, "env_steps": 6437683199, "loss": 0.015910614281892776, "avg_return": 0.8626131415367126, "regret": 0.0010418647434562445, "entropy": 0.0935591384768486, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:37.715634Z", "loop": 10478, "env_steps": 6438297599, "loss": 0.015890950337052345, "avg_return": 0.8626694679260254, "regret": 0.0010418647434562445, "entropy": 0.09128706157207489, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:38.570135Z", "loop": 10479, "env_steps": 6438911999, "loss": 0.017411498352885246, "avg_return": 0.862774670124054, "regret": 0.0010418647434562445, "entropy": 0.09921592473983765, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:39.463718Z", "loop": 10480, "env_steps": 6439526399, "loss": 0.016010146588087082, "avg_return": 0.8617525696754456, "regret": 0.0010228455066680908, "entropy": 0.09173663705587387, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:40.318685Z", "loop": 10481, "env_steps": 6440140799, "loss": 0.015468749217689037, "avg_return": 0.8629651069641113, "regret": 0.0010228455066680908, "entropy": 0.08874482661485672, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:41.173200Z", "loop": 10482, "env_steps": 6440755199, "loss": 0.015362314879894257, "avg_return": 0.8619420528411865, "regret": 0.0010228455066680908, "entropy": 0.09065975993871689, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:42.028842Z", "loop": 10483, "env_steps": 6441369599, "loss": 0.015048177912831306, "avg_return": 0.8638132810592651, "regret": 0.0010228455066680908, "entropy": 0.08725980669260025, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:42.883733Z", "loop": 10484, "env_steps": 6441983999, "loss": 0.015592253766953945, "avg_return": 0.8628389835357666, "regret": 0.0010228455066680908, "entropy": 0.08949048072099686, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:43.739162Z", "loop": 10485, "env_steps": 6442598399, "loss": 0.01587853394448757, "avg_return": 0.8621149063110352, "regret": 0.0010228455066680908, "entropy": 0.08695807307958603, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:44.593999Z", "loop": 10486, "env_steps": 6443212799, "loss": 0.014984245412051678, "avg_return": 0.8618103265762329, "regret": 0.0010228455066680908, "entropy": 0.0873243510723114, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:45.448797Z", "loop": 10487, "env_steps": 6443827199, "loss": 0.017124755308032036, "avg_return": 0.8620587587356567, "regret": 0.0010228455066680908, "entropy": 0.08934110403060913, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:46.302396Z", "loop": 10488, "env_steps": 6444441599, "loss": 0.015923338010907173, "avg_return": 0.8639039397239685, "regret": 0.0010228455066680908, "entropy": 0.08637599647045135, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:47.156281Z", "loop": 10489, "env_steps": 6445055999, "loss": 0.015074302442371845, "avg_return": 0.8636442422866821, "regret": 0.0010228455066680908, "entropy": 0.08414556831121445, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:48.050516Z", "loop": 10490, "env_steps": 6445670399, "loss": 0.016358917579054832, "avg_return": 0.8629443645477295, "regret": 0.00043603297672234476, "entropy": 0.08665519207715988, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:48.904545Z", "loop": 10491, "env_steps": 6446284799, "loss": 0.015342257916927338, "avg_return": 0.8637754321098328, "regret": 0.00043603297672234476, "entropy": 0.08317288011312485, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:49.759502Z", "loop": 10492, "env_steps": 6446899199, "loss": 0.01480312179774046, "avg_return": 0.8624262809753418, "regret": 0.00043603297672234476, "entropy": 0.08068296313285828, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:50.615426Z", "loop": 10493, "env_steps": 6447513599, "loss": 0.015567967668175697, "avg_return": 0.8640466332435608, "regret": 0.00043603297672234476, "entropy": 0.08175593614578247, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:51.470963Z", "loop": 10494, "env_steps": 6448127999, "loss": 0.013835116289556026, "avg_return": 0.8622030019760132, "regret": 0.00043603297672234476, "entropy": 0.07679343968629837, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:52.326080Z", "loop": 10495, "env_steps": 6448742399, "loss": 0.014545167796313763, "avg_return": 0.863005518913269, "regret": 0.00043603297672234476, "entropy": 0.07929268479347229, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:53.180999Z", "loop": 10496, "env_steps": 6449356799, "loss": 0.014233524911105633, "avg_return": 0.8629148602485657, "regret": 0.00043603297672234476, "entropy": 0.07565422356128693, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:54.035956Z", "loop": 10497, "env_steps": 6449971199, "loss": 0.01466789748519659, "avg_return": 0.8631348609924316, "regret": 0.00043603297672234476, "entropy": 0.0777459517121315, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:54.889583Z", "loop": 10498, "env_steps": 6450585599, "loss": 0.014138002879917622, "avg_return": 0.8637234568595886, "regret": 0.00043603297672234476, "entropy": 0.07722824066877365, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:55.744287Z", "loop": 10499, "env_steps": 6451199999, "loss": 0.014298697002232075, "avg_return": 0.8611605167388916, "regret": 0.00043603297672234476, "entropy": 0.07672883570194244, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:56.638608Z", "loop": 10500, "env_steps": 6451814399, "loss": 0.013348071835935116, "avg_return": 0.8643903732299805, "regret": 0.0006807802128605545, "entropy": 0.0707819014787674, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:57.493308Z", "loop": 10501, "env_steps": 6452428799, "loss": 0.013388234190642834, "avg_return": 0.8634699583053589, "regret": 0.0006807802128605545, "entropy": 0.07018522173166275, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:58.348211Z", "loop": 10502, "env_steps": 6453043199, "loss": 0.014333854429423809, "avg_return": 0.8612313270568848, "regret": 0.0006807802128605545, "entropy": 0.07783094048500061, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:53:59.203411Z", "loop": 10503, "env_steps": 6453657599, "loss": 0.013096431270241737, "avg_return": 0.8622249364852905, "regret": 0.0006807802128605545, "entropy": 0.07467745989561081, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:00.057594Z", "loop": 10504, "env_steps": 6454271999, "loss": 0.01331707090139389, "avg_return": 0.8627867698669434, "regret": 0.0006807802128605545, "entropy": 0.07235437631607056, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:00.911935Z", "loop": 10505, "env_steps": 6454886399, "loss": 0.014333175495266914, "avg_return": 0.8627284169197083, "regret": 0.0006807802128605545, "entropy": 0.07704218477010727, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:01.766098Z", "loop": 10506, "env_steps": 6455500799, "loss": 0.013234131038188934, "avg_return": 0.8630642890930176, "regret": 0.0006807802128605545, "entropy": 0.07050732523202896, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:02.620690Z", "loop": 10507, "env_steps": 6456115199, "loss": 0.01374304573982954, "avg_return": 0.8631433248519897, "regret": 0.0006807802128605545, "entropy": 0.074521005153656, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:03.474637Z", "loop": 10508, "env_steps": 6456729599, "loss": 0.01286537665873766, "avg_return": 0.8629132509231567, "regret": 0.0006807802128605545, "entropy": 0.0696788877248764, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:04.329698Z", "loop": 10509, "env_steps": 6457343999, "loss": 0.01345160510390997, "avg_return": 0.8630388379096985, "regret": 0.0006807802128605545, "entropy": 0.07174299657344818, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:05.223301Z", "loop": 10510, "env_steps": 6457958399, "loss": 0.012317806482315063, "avg_return": 0.8633683323860168, "regret": 0.00037278796662576497, "entropy": 0.0706910714507103, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:06.077780Z", "loop": 10511, "env_steps": 6458572799, "loss": 0.012475759722292423, "avg_return": 0.8621964454650879, "regret": 0.00037278796662576497, "entropy": 0.07048819959163666, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:06.932373Z", "loop": 10512, "env_steps": 6459187199, "loss": 0.013270454481244087, "avg_return": 0.8645191788673401, "regret": 0.00037278796662576497, "entropy": 0.0723227858543396, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:07.786565Z", "loop": 10513, "env_steps": 6459801599, "loss": 0.013035612180829048, "avg_return": 0.8630530834197998, "regret": 0.00037278796662576497, "entropy": 0.07175765931606293, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:08.640067Z", "loop": 10514, "env_steps": 6460415999, "loss": 0.01322678942233324, "avg_return": 0.8626635670661926, "regret": 0.00037278796662576497, "entropy": 0.07130621373653412, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:09.494542Z", "loop": 10515, "env_steps": 6461030399, "loss": 0.013602090068161488, "avg_return": 0.8624882102012634, "regret": 0.00037278796662576497, "entropy": 0.07030963897705078, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:10.349446Z", "loop": 10516, "env_steps": 6461644799, "loss": 0.013385121710598469, "avg_return": 0.8627492189407349, "regret": 0.00037278796662576497, "entropy": 0.07130062580108643, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:11.204150Z", "loop": 10517, "env_steps": 6462259199, "loss": 0.012572084553539753, "avg_return": 0.8624434471130371, "regret": 0.00037278796662576497, "entropy": 0.07048485428094864, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:12.057404Z", "loop": 10518, "env_steps": 6462873599, "loss": 0.012395505793392658, "avg_return": 0.862819254398346, "regret": 0.00037278796662576497, "entropy": 0.07083962857723236, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:12.911158Z", "loop": 10519, "env_steps": 6463487999, "loss": 0.013559420593082905, "avg_return": 0.8618652820587158, "regret": 0.00037278796662576497, "entropy": 0.07169244438409805, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:13.803720Z", "loop": 10520, "env_steps": 6464102399, "loss": 0.013570822775363922, "avg_return": 0.8634263277053833, "regret": 0.0006594029837287962, "entropy": 0.07376174628734589, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:14.658719Z", "loop": 10521, "env_steps": 6464716799, "loss": 0.014562328346073627, "avg_return": 0.8629392981529236, "regret": 0.0006594029837287962, "entropy": 0.07284361869096756, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:15.512051Z", "loop": 10522, "env_steps": 6465331199, "loss": 0.014816946350038052, "avg_return": 0.8622785806655884, "regret": 0.0006594029837287962, "entropy": 0.0739312395453453, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:16.365717Z", "loop": 10523, "env_steps": 6465945599, "loss": 0.014032438397407532, "avg_return": 0.8617509007453918, "regret": 0.0006594029837287962, "entropy": 0.07301971316337585, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:17.220405Z", "loop": 10524, "env_steps": 6466559999, "loss": 0.013520623557269573, "avg_return": 0.8623963594436646, "regret": 0.0006594029837287962, "entropy": 0.07546631991863251, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:18.074847Z", "loop": 10525, "env_steps": 6467174399, "loss": 0.013478226028382778, "avg_return": 0.863254725933075, "regret": 0.0006594029837287962, "entropy": 0.07466119527816772, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:18.928250Z", "loop": 10526, "env_steps": 6467788799, "loss": 0.014834976755082607, "avg_return": 0.8631607294082642, "regret": 0.0006594029837287962, "entropy": 0.07809797674417496, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:19.781198Z", "loop": 10527, "env_steps": 6468403199, "loss": 0.013635349459946156, "avg_return": 0.8624173998832703, "regret": 0.0006594029837287962, "entropy": 0.0727907344698906, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:20.635768Z", "loop": 10528, "env_steps": 6469017599, "loss": 0.013861733488738537, "avg_return": 0.8625819087028503, "regret": 0.0006594029837287962, "entropy": 0.0753229632973671, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:21.489998Z", "loop": 10529, "env_steps": 6469631999, "loss": 0.013769335113465786, "avg_return": 0.863016664981842, "regret": 0.0006594029837287962, "entropy": 0.073799267411232, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:22.381483Z", "loop": 10530, "env_steps": 6470246399, "loss": 0.013679874129593372, "avg_return": 0.8626939058303833, "regret": 0.0005200519226491451, "entropy": 0.0758911520242691, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:23.234762Z", "loop": 10531, "env_steps": 6470860799, "loss": 0.01332235336303711, "avg_return": 0.8622031807899475, "regret": 0.0005200519226491451, "entropy": 0.07240515947341919, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:24.089509Z", "loop": 10532, "env_steps": 6471475199, "loss": 0.01274812687188387, "avg_return": 0.8628712892532349, "regret": 0.0005200519226491451, "entropy": 0.06824754178524017, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:24.943419Z", "loop": 10533, "env_steps": 6472089599, "loss": 0.013221368193626404, "avg_return": 0.863246500492096, "regret": 0.0005200519226491451, "entropy": 0.07403405755758286, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:25.797484Z", "loop": 10534, "env_steps": 6472703999, "loss": 0.013034998439252377, "avg_return": 0.8634307980537415, "regret": 0.0005200519226491451, "entropy": 0.07180693745613098, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:26.650967Z", "loop": 10535, "env_steps": 6473318399, "loss": 0.01318639237433672, "avg_return": 0.8632566332817078, "regret": 0.0005200519226491451, "entropy": 0.07308345288038254, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:27.505748Z", "loop": 10536, "env_steps": 6473932799, "loss": 0.014088766649365425, "avg_return": 0.8640605807304382, "regret": 0.0005200519226491451, "entropy": 0.07130375504493713, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:28.359594Z", "loop": 10537, "env_steps": 6474547199, "loss": 0.01402483880519867, "avg_return": 0.8647557497024536, "regret": 0.0005200519226491451, "entropy": 0.07529284805059433, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:29.213675Z", "loop": 10538, "env_steps": 6475161599, "loss": 0.013255581259727478, "avg_return": 0.8638898134231567, "regret": 0.0005200519226491451, "entropy": 0.07280340790748596, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:30.067658Z", "loop": 10539, "env_steps": 6475775999, "loss": 0.014250173233449459, "avg_return": 0.8635191917419434, "regret": 0.0005200519226491451, "entropy": 0.07826317846775055, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:30.962367Z", "loop": 10540, "env_steps": 6476390399, "loss": 0.012634691782295704, "avg_return": 0.8627747893333435, "regret": 0.0003477234859019518, "entropy": 0.07177601009607315, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:31.817772Z", "loop": 10541, "env_steps": 6477004799, "loss": 0.013684726320207119, "avg_return": 0.8648747801780701, "regret": 0.0003477234859019518, "entropy": 0.07476513087749481, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:32.672425Z", "loop": 10542, "env_steps": 6477619199, "loss": 0.014320959337055683, "avg_return": 0.8639442920684814, "regret": 0.0003477234859019518, "entropy": 0.07673169672489166, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:33.526424Z", "loop": 10543, "env_steps": 6478233599, "loss": 0.014159596525132656, "avg_return": 0.8644346594810486, "regret": 0.0003477234859019518, "entropy": 0.07738236337900162, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:34.380549Z", "loop": 10544, "env_steps": 6478847999, "loss": 0.01509010512381792, "avg_return": 0.8628973364830017, "regret": 0.0003477234859019518, "entropy": 0.08027191460132599, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:35.233988Z", "loop": 10545, "env_steps": 6479462399, "loss": 0.016376737505197525, "avg_return": 0.8631002902984619, "regret": 0.0003477234859019518, "entropy": 0.08741333335638046, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:36.087996Z", "loop": 10546, "env_steps": 6480076799, "loss": 0.015526828356087208, "avg_return": 0.8609280586242676, "regret": 0.0003477234859019518, "entropy": 0.08502309024333954, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:36.943151Z", "loop": 10547, "env_steps": 6480691199, "loss": 0.01701454631984234, "avg_return": 0.8589163422584534, "regret": 0.0003477234859019518, "entropy": 0.09098821133375168, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:37.797599Z", "loop": 10548, "env_steps": 6481305599, "loss": 0.01833491586148739, "avg_return": 0.8560492992401123, "regret": 0.0003477234859019518, "entropy": 0.09840520471334457, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:38.651503Z", "loop": 10549, "env_steps": 6481919999, "loss": 0.017903482541441917, "avg_return": 0.8551123142242432, "regret": 0.0003477234859019518, "entropy": 0.09842943400144577, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:39.544201Z", "loop": 10550, "env_steps": 6482534399, "loss": 0.018886759877204895, "avg_return": 0.8584880828857422, "regret": 0.005423429422080517, "entropy": 0.09877923876047134, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:40.398755Z", "loop": 10551, "env_steps": 6483148799, "loss": 0.016668563708662987, "avg_return": 0.8626719117164612, "regret": 0.005423429422080517, "entropy": 0.08673867583274841, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:41.252895Z", "loop": 10552, "env_steps": 6483763199, "loss": 0.013415105640888214, "avg_return": 0.861728310585022, "regret": 0.005423429422080517, "entropy": 0.07871256023645401, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:42.106662Z", "loop": 10553, "env_steps": 6484377599, "loss": 0.014406931586563587, "avg_return": 0.8638530969619751, "regret": 0.005423429422080517, "entropy": 0.07688655704259872, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:42.959933Z", "loop": 10554, "env_steps": 6484991999, "loss": 0.014352562837302685, "avg_return": 0.862849771976471, "regret": 0.005423429422080517, "entropy": 0.07770363241434097, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:43.812921Z", "loop": 10555, "env_steps": 6485606399, "loss": 0.014415963552892208, "avg_return": 0.8641664981842041, "regret": 0.005423429422080517, "entropy": 0.07408303022384644, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:44.667735Z", "loop": 10556, "env_steps": 6486220799, "loss": 0.013412711210548878, "avg_return": 0.8634169697761536, "regret": 0.005423429422080517, "entropy": 0.0727069079875946, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:45.522218Z", "loop": 10557, "env_steps": 6486835199, "loss": 0.014799057506024837, "avg_return": 0.8638214468955994, "regret": 0.005423429422080517, "entropy": 0.07933665066957474, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:46.376162Z", "loop": 10558, "env_steps": 6487449599, "loss": 0.014527960680425167, "avg_return": 0.8629856705665588, "regret": 0.005423429422080517, "entropy": 0.07859061658382416, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:47.229241Z", "loop": 10559, "env_steps": 6488063999, "loss": 0.012754450552165508, "avg_return": 0.8648504614830017, "regret": 0.005423429422080517, "entropy": 0.06893526762723923, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:48.121191Z", "loop": 10560, "env_steps": 6488678399, "loss": 0.013494202867150307, "avg_return": 0.8627172112464905, "regret": 0.0001952258899109438, "entropy": 0.07463343441486359, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:48.976000Z", "loop": 10561, "env_steps": 6489292799, "loss": 0.014464079402387142, "avg_return": 0.8644446134567261, "regret": 0.0001952258899109438, "entropy": 0.07481388002634048, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:49.830537Z", "loop": 10562, "env_steps": 6489907199, "loss": 0.014924502931535244, "avg_return": 0.8640972971916199, "regret": 0.0001952258899109438, "entropy": 0.07749275118112564, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:50.683983Z", "loop": 10563, "env_steps": 6490521599, "loss": 0.014542466960847378, "avg_return": 0.8624902367591858, "regret": 0.0001952258899109438, "entropy": 0.0746791735291481, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:51.537599Z", "loop": 10564, "env_steps": 6491135999, "loss": 0.013708767481148243, "avg_return": 0.8623598217964172, "regret": 0.0001952258899109438, "entropy": 0.07570704072713852, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:52.393299Z", "loop": 10565, "env_steps": 6491750399, "loss": 0.013920827768743038, "avg_return": 0.8621323704719543, "regret": 0.0001952258899109438, "entropy": 0.0776023343205452, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:53.247605Z", "loop": 10566, "env_steps": 6492364799, "loss": 0.013071323744952679, "avg_return": 0.8634082078933716, "regret": 0.0001952258899109438, "entropy": 0.0754748061299324, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:54.102350Z", "loop": 10567, "env_steps": 6492979199, "loss": 0.013381321914494038, "avg_return": 0.8638138771057129, "regret": 0.0001952258899109438, "entropy": 0.07341521978378296, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:54.958112Z", "loop": 10568, "env_steps": 6493593599, "loss": 0.014418775215744972, "avg_return": 0.8634859323501587, "regret": 0.0001952258899109438, "entropy": 0.07535349577665329, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:55.813822Z", "loop": 10569, "env_steps": 6494207999, "loss": 0.014592967927455902, "avg_return": 0.8626924753189087, "regret": 0.0001952258899109438, "entropy": 0.07364583760499954, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:56.707101Z", "loop": 10570, "env_steps": 6494822399, "loss": 0.01288807112723589, "avg_return": 0.8620913624763489, "regret": 0.0006376099772751331, "entropy": 0.0727359801530838, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:57.562042Z", "loop": 10571, "env_steps": 6495436799, "loss": 0.014072271063923836, "avg_return": 0.8617680072784424, "regret": 0.0006376099772751331, "entropy": 0.07726191729307175, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:58.415998Z", "loop": 10572, "env_steps": 6496051199, "loss": 0.014187402091920376, "avg_return": 0.8630756735801697, "regret": 0.0006376099772751331, "entropy": 0.07715220749378204, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:54:59.269409Z", "loop": 10573, "env_steps": 6496665599, "loss": 0.013510364107787609, "avg_return": 0.8626618385314941, "regret": 0.0006376099772751331, "entropy": 0.07435882836580276, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:00.123276Z", "loop": 10574, "env_steps": 6497279999, "loss": 0.014215084724128246, "avg_return": 0.8619136810302734, "regret": 0.0006376099772751331, "entropy": 0.07539378106594086, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:00.978659Z", "loop": 10575, "env_steps": 6497894399, "loss": 0.013504542410373688, "avg_return": 0.8631477952003479, "regret": 0.0006376099772751331, "entropy": 0.07485634088516235, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:01.833689Z", "loop": 10576, "env_steps": 6498508799, "loss": 0.013137380592525005, "avg_return": 0.861738383769989, "regret": 0.0006376099772751331, "entropy": 0.07289880514144897, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:02.688594Z", "loop": 10577, "env_steps": 6499123199, "loss": 0.01398837473243475, "avg_return": 0.8635333180427551, "regret": 0.0006376099772751331, "entropy": 0.07851395756006241, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:03.543702Z", "loop": 10578, "env_steps": 6499737599, "loss": 0.014577924273908138, "avg_return": 0.8616493940353394, "regret": 0.0006376099772751331, "entropy": 0.075335793197155, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:04.398409Z", "loop": 10579, "env_steps": 6500351999, "loss": 0.014703243970870972, "avg_return": 0.8623961806297302, "regret": 0.0006376099772751331, "entropy": 0.07999023050069809, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:05.292442Z", "loop": 10580, "env_steps": 6500966399, "loss": 0.013524080626666546, "avg_return": 0.8624724745750427, "regret": 0.0005479864194057882, "entropy": 0.07387358695268631, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:06.146548Z", "loop": 10581, "env_steps": 6501580799, "loss": 0.013634057715535164, "avg_return": 0.8638166785240173, "regret": 0.0005479864194057882, "entropy": 0.07400212436914444, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:06.999662Z", "loop": 10582, "env_steps": 6502195199, "loss": 0.01405381690710783, "avg_return": 0.8612666130065918, "regret": 0.0005479864194057882, "entropy": 0.07418221235275269, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:07.854148Z", "loop": 10583, "env_steps": 6502809599, "loss": 0.012731440365314484, "avg_return": 0.8636360764503479, "regret": 0.0005479864194057882, "entropy": 0.06951192766427994, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:08.708750Z", "loop": 10584, "env_steps": 6503423999, "loss": 0.013019037432968616, "avg_return": 0.8622691035270691, "regret": 0.0005479864194057882, "entropy": 0.07384548336267471, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:09.563920Z", "loop": 10585, "env_steps": 6504038399, "loss": 0.012133498676121235, "avg_return": 0.8634377121925354, "regret": 0.0005479864194057882, "entropy": 0.07017439603805542, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:10.416920Z", "loop": 10586, "env_steps": 6504652799, "loss": 0.013142532669007778, "avg_return": 0.8647247552871704, "regret": 0.0005479864194057882, "entropy": 0.07417231798171997, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:11.270688Z", "loop": 10587, "env_steps": 6505267199, "loss": 0.014732643030583858, "avg_return": 0.8637350797653198, "regret": 0.0005479864194057882, "entropy": 0.07920902967453003, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:12.125602Z", "loop": 10588, "env_steps": 6505881599, "loss": 0.014113492332398891, "avg_return": 0.8655810952186584, "regret": 0.0005479864194057882, "entropy": 0.07586643099784851, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:12.979594Z", "loop": 10589, "env_steps": 6506495999, "loss": 0.012611635029315948, "avg_return": 0.8627563714981079, "regret": 0.0005479864194057882, "entropy": 0.07140886038541794, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:13.871765Z", "loop": 10590, "env_steps": 6507110399, "loss": 0.01358549203723669, "avg_return": 0.863898754119873, "regret": 0.00019096871255896986, "entropy": 0.07146710157394409, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:14.726180Z", "loop": 10591, "env_steps": 6507724799, "loss": 0.014514371752738953, "avg_return": 0.8644358515739441, "regret": 0.00019096871255896986, "entropy": 0.07556601613759995, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:15.580078Z", "loop": 10592, "env_steps": 6508339199, "loss": 0.013341470621526241, "avg_return": 0.8638930320739746, "regret": 0.00019096871255896986, "entropy": 0.07591648399829865, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:16.434581Z", "loop": 10593, "env_steps": 6508953599, "loss": 0.012923257425427437, "avg_return": 0.8626996278762817, "regret": 0.00019096871255896986, "entropy": 0.07338133454322815, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:17.288768Z", "loop": 10594, "env_steps": 6509567999, "loss": 0.014284825883805752, "avg_return": 0.8641617298126221, "regret": 0.00019096871255896986, "entropy": 0.07500926405191422, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:18.142991Z", "loop": 10595, "env_steps": 6510182399, "loss": 0.01421069260686636, "avg_return": 0.8635662198066711, "regret": 0.00019096871255896986, "entropy": 0.07580216228961945, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:18.998306Z", "loop": 10596, "env_steps": 6510796799, "loss": 0.013672682456672192, "avg_return": 0.8629820942878723, "regret": 0.00019096871255896986, "entropy": 0.07233485579490662, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:19.852685Z", "loop": 10597, "env_steps": 6511411199, "loss": 0.013550646603107452, "avg_return": 0.8640356659889221, "regret": 0.00019096871255896986, "entropy": 0.07484279572963715, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:20.706294Z", "loop": 10598, "env_steps": 6512025599, "loss": 0.013020679354667664, "avg_return": 0.864552915096283, "regret": 0.00019096871255896986, "entropy": 0.07309728115797043, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:21.560016Z", "loop": 10599, "env_steps": 6512639999, "loss": 0.01334584690630436, "avg_return": 0.8625032901763916, "regret": 0.00019096871255896986, "entropy": 0.07329440861940384, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:22.454460Z", "loop": 10600, "env_steps": 6513254399, "loss": 0.014222584664821625, "avg_return": 0.8625070452690125, "regret": 0.0005710759432986379, "entropy": 0.07583484798669815, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:23.308552Z", "loop": 10601, "env_steps": 6513868799, "loss": 0.013891047798097134, "avg_return": 0.8619305491447449, "regret": 0.0005710759432986379, "entropy": 0.07443393766880035, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:24.163235Z", "loop": 10602, "env_steps": 6514483199, "loss": 0.013882837258279324, "avg_return": 0.861879289150238, "regret": 0.0005710759432986379, "entropy": 0.07456935942173004, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:25.018052Z", "loop": 10603, "env_steps": 6515097599, "loss": 0.012921812944114208, "avg_return": 0.8627756834030151, "regret": 0.0005710759432986379, "entropy": 0.07123624533414841, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:25.871673Z", "loop": 10604, "env_steps": 6515711999, "loss": 0.014351720921695232, "avg_return": 0.862552285194397, "regret": 0.0005710759432986379, "entropy": 0.07623506337404251, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:26.725455Z", "loop": 10605, "env_steps": 6516326399, "loss": 0.013451531529426575, "avg_return": 0.8621022701263428, "regret": 0.0005710759432986379, "entropy": 0.07557718455791473, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:27.581072Z", "loop": 10606, "env_steps": 6516940799, "loss": 0.014808190055191517, "avg_return": 0.8622483611106873, "regret": 0.0005710759432986379, "entropy": 0.07713042944669724, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:28.435564Z", "loop": 10607, "env_steps": 6517555199, "loss": 0.01378690917044878, "avg_return": 0.8632827997207642, "regret": 0.0005710759432986379, "entropy": 0.07453346997499466, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:29.289654Z", "loop": 10608, "env_steps": 6518169599, "loss": 0.014990589581429958, "avg_return": 0.8612729907035828, "regret": 0.0005710759432986379, "entropy": 0.07865462452173233, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:30.144036Z", "loop": 10609, "env_steps": 6518783999, "loss": 0.014239593409001827, "avg_return": 0.861588180065155, "regret": 0.0005710759432986379, "entropy": 0.0767517164349556, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:31.040632Z", "loop": 10610, "env_steps": 6519398399, "loss": 0.015275957994163036, "avg_return": 0.8627291917800903, "regret": 0.0020268799271434546, "entropy": 0.08094710111618042, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:31.894548Z", "loop": 10611, "env_steps": 6520012799, "loss": 0.013624878600239754, "avg_return": 0.8617635369300842, "regret": 0.0020268799271434546, "entropy": 0.07290734350681305, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:32.748626Z", "loop": 10612, "env_steps": 6520627199, "loss": 0.014105615206062794, "avg_return": 0.8600184321403503, "regret": 0.0020268799271434546, "entropy": 0.07429946959018707, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:33.602225Z", "loop": 10613, "env_steps": 6521241599, "loss": 0.01551685482263565, "avg_return": 0.8605297207832336, "regret": 0.0020268799271434546, "entropy": 0.08049878478050232, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:34.456194Z", "loop": 10614, "env_steps": 6521855999, "loss": 0.014425975270569324, "avg_return": 0.8605819940567017, "regret": 0.0020268799271434546, "entropy": 0.0764218270778656, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:35.310497Z", "loop": 10615, "env_steps": 6522470399, "loss": 0.014122480526566505, "avg_return": 0.8603774309158325, "regret": 0.0020268799271434546, "entropy": 0.07570535689592361, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:36.163872Z", "loop": 10616, "env_steps": 6523084799, "loss": 0.016509652137756348, "avg_return": 0.8609852194786072, "regret": 0.0020268799271434546, "entropy": 0.08674921840429306, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:37.017584Z", "loop": 10617, "env_steps": 6523699199, "loss": 0.015030385926365852, "avg_return": 0.8606005907058716, "regret": 0.0020268799271434546, "entropy": 0.08244197070598602, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:37.871927Z", "loop": 10618, "env_steps": 6524313599, "loss": 0.014072383753955364, "avg_return": 0.8597052097320557, "regret": 0.0020268799271434546, "entropy": 0.07583826780319214, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:38.726010Z", "loop": 10619, "env_steps": 6524927999, "loss": 0.014224456623196602, "avg_return": 0.8600075244903564, "regret": 0.0020268799271434546, "entropy": 0.0756179690361023, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:39.618658Z", "loop": 10620, "env_steps": 6525542399, "loss": 0.014539043419063091, "avg_return": 0.8599263429641724, "regret": 0.0026925222482532263, "entropy": 0.07648328691720963, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:40.472274Z", "loop": 10621, "env_steps": 6526156799, "loss": 0.0143128028139472, "avg_return": 0.8604758977890015, "regret": 0.0026925222482532263, "entropy": 0.07730211317539215, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:41.326278Z", "loop": 10622, "env_steps": 6526771199, "loss": 0.014965160749852657, "avg_return": 0.8627381324768066, "regret": 0.0026925222482532263, "entropy": 0.07897339016199112, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:42.180038Z", "loop": 10623, "env_steps": 6527385599, "loss": 0.014258714392781258, "avg_return": 0.8609232902526855, "regret": 0.0026925222482532263, "entropy": 0.07363180071115494, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:43.034737Z", "loop": 10624, "env_steps": 6527999999, "loss": 0.014990453608334064, "avg_return": 0.8619835376739502, "regret": 0.0026925222482532263, "entropy": 0.07707291841506958, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:43.889122Z", "loop": 10625, "env_steps": 6528614399, "loss": 0.014340482652187347, "avg_return": 0.8637467622756958, "regret": 0.0026925222482532263, "entropy": 0.07691118121147156, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:44.742716Z", "loop": 10626, "env_steps": 6529228799, "loss": 0.013346560299396515, "avg_return": 0.8627599477767944, "regret": 0.0026925222482532263, "entropy": 0.07189721614122391, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:45.596801Z", "loop": 10627, "env_steps": 6529843199, "loss": 0.013052157126367092, "avg_return": 0.8633023500442505, "regret": 0.0026925222482532263, "entropy": 0.07286375761032104, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:46.451349Z", "loop": 10628, "env_steps": 6530457599, "loss": 0.012783725745975971, "avg_return": 0.8627974390983582, "regret": 0.0026925222482532263, "entropy": 0.07276538014411926, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:47.304644Z", "loop": 10629, "env_steps": 6531071999, "loss": 0.013527097180485725, "avg_return": 0.8638893961906433, "regret": 0.0026925222482532263, "entropy": 0.07315071672201157, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:48.195542Z", "loop": 10630, "env_steps": 6531686399, "loss": 0.013396413996815681, "avg_return": 0.8634527921676636, "regret": 0.0003945597563870251, "entropy": 0.07119913399219513, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:49.050372Z", "loop": 10631, "env_steps": 6532300799, "loss": 0.012729673646390438, "avg_return": 0.8618367910385132, "regret": 0.0003945597563870251, "entropy": 0.07090668380260468, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:49.905405Z", "loop": 10632, "env_steps": 6532915199, "loss": 0.013374604284763336, "avg_return": 0.8628855347633362, "regret": 0.0003945597563870251, "entropy": 0.07498738914728165, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:50.759638Z", "loop": 10633, "env_steps": 6533529599, "loss": 0.013562195003032684, "avg_return": 0.8632106781005859, "regret": 0.0003945597563870251, "entropy": 0.07511316984891891, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:51.614352Z", "loop": 10634, "env_steps": 6534143999, "loss": 0.012367293238639832, "avg_return": 0.8637917041778564, "regret": 0.0003945597563870251, "entropy": 0.07160426676273346, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:52.468938Z", "loop": 10635, "env_steps": 6534758399, "loss": 0.013783695176243782, "avg_return": 0.8631839156150818, "regret": 0.0003945597563870251, "entropy": 0.07376938313245773, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:53.322843Z", "loop": 10636, "env_steps": 6535372799, "loss": 0.013026736676692963, "avg_return": 0.8620291352272034, "regret": 0.0003945597563870251, "entropy": 0.07425782084465027, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:54.177170Z", "loop": 10637, "env_steps": 6535987199, "loss": 0.013652661815285683, "avg_return": 0.8621636033058167, "regret": 0.0003945597563870251, "entropy": 0.07632129639387131, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:55.031401Z", "loop": 10638, "env_steps": 6536601599, "loss": 0.012607576325535774, "avg_return": 0.8623566627502441, "regret": 0.0003945597563870251, "entropy": 0.07083084434270859, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:55.888562Z", "loop": 10639, "env_steps": 6537215999, "loss": 0.014113591983914375, "avg_return": 0.8617867231369019, "regret": 0.0003945597563870251, "entropy": 0.07626146823167801, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:56.780471Z", "loop": 10640, "env_steps": 6537830399, "loss": 0.014661319553852081, "avg_return": 0.8623292446136475, "regret": 0.0020400334615260363, "entropy": 0.0798785537481308, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:57.634341Z", "loop": 10641, "env_steps": 6538444799, "loss": 0.014500908553600311, "avg_return": 0.8594598770141602, "regret": 0.0020400334615260363, "entropy": 0.07480766624212265, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:58.489917Z", "loop": 10642, "env_steps": 6539059199, "loss": 0.014219741337001324, "avg_return": 0.8607505559921265, "regret": 0.0020400334615260363, "entropy": 0.07432872802019119, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:55:59.346303Z", "loop": 10643, "env_steps": 6539673599, "loss": 0.014976322650909424, "avg_return": 0.8604152798652649, "regret": 0.0020400334615260363, "entropy": 0.07573521882295609, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:00.200854Z", "loop": 10644, "env_steps": 6540287999, "loss": 0.014864127151668072, "avg_return": 0.8612861037254333, "regret": 0.0020400334615260363, "entropy": 0.0788741186261177, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:01.054680Z", "loop": 10645, "env_steps": 6540902399, "loss": 0.014106914401054382, "avg_return": 0.8624776601791382, "regret": 0.0020400334615260363, "entropy": 0.07584966719150543, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:01.910109Z", "loop": 10646, "env_steps": 6541516799, "loss": 0.014532558619976044, "avg_return": 0.8623960614204407, "regret": 0.0020400334615260363, "entropy": 0.07542845606803894, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:02.764894Z", "loop": 10647, "env_steps": 6542131199, "loss": 0.014123109169304371, "avg_return": 0.8634957075119019, "regret": 0.0020400334615260363, "entropy": 0.07548730075359344, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:03.618574Z", "loop": 10648, "env_steps": 6542745599, "loss": 0.015132575295865536, "avg_return": 0.8637331128120422, "regret": 0.0020400334615260363, "entropy": 0.07976116985082626, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:04.472119Z", "loop": 10649, "env_steps": 6543359999, "loss": 0.013744194991886616, "avg_return": 0.8624125123023987, "regret": 0.0020400334615260363, "entropy": 0.07333999872207642, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:05.364752Z", "loop": 10650, "env_steps": 6543974399, "loss": 0.012638821266591549, "avg_return": 0.8634144067764282, "regret": 0.0006278363871388137, "entropy": 0.06924932450056076, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:06.219654Z", "loop": 10651, "env_steps": 6544588799, "loss": 0.012594848871231079, "avg_return": 0.8632960319519043, "regret": 0.0006278363871388137, "entropy": 0.06910131871700287, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:07.074615Z", "loop": 10652, "env_steps": 6545203199, "loss": 0.013608952052891254, "avg_return": 0.8623226284980774, "regret": 0.0006278363871388137, "entropy": 0.07568687200546265, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:07.929355Z", "loop": 10653, "env_steps": 6545817599, "loss": 0.01358023565262556, "avg_return": 0.8619954586029053, "regret": 0.0006278363871388137, "entropy": 0.07506703585386276, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:08.784600Z", "loop": 10654, "env_steps": 6546431999, "loss": 0.014311636798083782, "avg_return": 0.8629250526428223, "regret": 0.0006278363871388137, "entropy": 0.07545562833547592, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:09.639817Z", "loop": 10655, "env_steps": 6547046399, "loss": 0.014205015264451504, "avg_return": 0.8617509007453918, "regret": 0.0006278363871388137, "entropy": 0.07523397356271744, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:10.494973Z", "loop": 10656, "env_steps": 6547660799, "loss": 0.014995405450463295, "avg_return": 0.8639455437660217, "regret": 0.0006278363871388137, "entropy": 0.07571718096733093, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:11.348943Z", "loop": 10657, "env_steps": 6548275199, "loss": 0.014093403704464436, "avg_return": 0.8646270036697388, "regret": 0.0006278363871388137, "entropy": 0.07624129205942154, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:12.203705Z", "loop": 10658, "env_steps": 6548889599, "loss": 0.01420621108263731, "avg_return": 0.8627258539199829, "regret": 0.0006278363871388137, "entropy": 0.07601115852594376, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:13.058210Z", "loop": 10659, "env_steps": 6549503999, "loss": 0.01560672651976347, "avg_return": 0.8628844618797302, "regret": 0.0006278363871388137, "entropy": 0.08411648124456406, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:13.950898Z", "loop": 10660, "env_steps": 6550118399, "loss": 0.015097426250576973, "avg_return": 0.8637228608131409, "regret": 0.0003323203418403864, "entropy": 0.07797308266162872, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:14.805368Z", "loop": 10661, "env_steps": 6550732799, "loss": 0.015303323045372963, "avg_return": 0.8616093397140503, "regret": 0.0003323203418403864, "entropy": 0.08053921908140182, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:15.661344Z", "loop": 10662, "env_steps": 6551347199, "loss": 0.01481299102306366, "avg_return": 0.8605427145957947, "regret": 0.0003323203418403864, "entropy": 0.07739394158124924, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:16.514481Z", "loop": 10663, "env_steps": 6551961599, "loss": 0.014106168411672115, "avg_return": 0.8637174963951111, "regret": 0.0003323203418403864, "entropy": 0.07524789124727249, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:17.368825Z", "loop": 10664, "env_steps": 6552575999, "loss": 0.015130849555134773, "avg_return": 0.8620854616165161, "regret": 0.0003323203418403864, "entropy": 0.07772866636514664, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:18.224151Z", "loop": 10665, "env_steps": 6553190399, "loss": 0.014120093546807766, "avg_return": 0.862105131149292, "regret": 0.0003323203418403864, "entropy": 0.07684724032878876, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:19.079580Z", "loop": 10666, "env_steps": 6553804799, "loss": 0.014966718852519989, "avg_return": 0.8628515601158142, "regret": 0.0003323203418403864, "entropy": 0.07887598872184753, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:19.933424Z", "loop": 10667, "env_steps": 6554419199, "loss": 0.015795348212122917, "avg_return": 0.8619264960289001, "regret": 0.0003323203418403864, "entropy": 0.08165676146745682, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:20.787518Z", "loop": 10668, "env_steps": 6555033599, "loss": 0.015829499810934067, "avg_return": 0.8638094067573547, "regret": 0.0003323203418403864, "entropy": 0.082697294652462, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:21.642142Z", "loop": 10669, "env_steps": 6555647999, "loss": 0.015021550469100475, "avg_return": 0.863746166229248, "regret": 0.0003323203418403864, "entropy": 0.07992347329854965, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:22.535588Z", "loop": 10670, "env_steps": 6556262399, "loss": 0.013741712085902691, "avg_return": 0.8632491230964661, "regret": 0.000376418320229277, "entropy": 0.0760708674788475, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:23.390653Z", "loop": 10671, "env_steps": 6556876799, "loss": 0.015062031336128712, "avg_return": 0.8635187149047852, "regret": 0.000376418320229277, "entropy": 0.08078133314847946, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:24.244774Z", "loop": 10672, "env_steps": 6557491199, "loss": 0.014576861634850502, "avg_return": 0.8640227317810059, "regret": 0.000376418320229277, "entropy": 0.0792393758893013, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:25.098436Z", "loop": 10673, "env_steps": 6558105599, "loss": 0.013921122066676617, "avg_return": 0.8614583611488342, "regret": 0.000376418320229277, "entropy": 0.07683981955051422, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:25.953431Z", "loop": 10674, "env_steps": 6558719999, "loss": 0.014504017308354378, "avg_return": 0.8644309639930725, "regret": 0.000376418320229277, "entropy": 0.07825737446546555, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:26.807331Z", "loop": 10675, "env_steps": 6559334399, "loss": 0.01394219882786274, "avg_return": 0.8635284900665283, "regret": 0.000376418320229277, "entropy": 0.07743308693170547, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:27.661654Z", "loop": 10676, "env_steps": 6559948799, "loss": 0.013345799408853054, "avg_return": 0.8627683520317078, "regret": 0.000376418320229277, "entropy": 0.07212018221616745, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:28.516555Z", "loop": 10677, "env_steps": 6560563199, "loss": 0.012976798228919506, "avg_return": 0.8640641570091248, "regret": 0.000376418320229277, "entropy": 0.06665851175785065, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:29.371734Z", "loop": 10678, "env_steps": 6561177599, "loss": 0.012363413348793983, "avg_return": 0.8616949915885925, "regret": 0.000376418320229277, "entropy": 0.06815048307180405, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:30.226240Z", "loop": 10679, "env_steps": 6561791999, "loss": 0.012289405800402164, "avg_return": 0.862544596195221, "regret": 0.000376418320229277, "entropy": 0.0712604820728302, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:31.120852Z", "loop": 10680, "env_steps": 6562406399, "loss": 0.013831235468387604, "avg_return": 0.8639923334121704, "regret": 0.00026371239800937474, "entropy": 0.07244337350130081, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:31.975146Z", "loop": 10681, "env_steps": 6563020799, "loss": 0.012936236336827278, "avg_return": 0.8626531958580017, "regret": 0.00026371239800937474, "entropy": 0.06966395676136017, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:32.830859Z", "loop": 10682, "env_steps": 6563635199, "loss": 0.01350340899080038, "avg_return": 0.8632251024246216, "regret": 0.00026371239800937474, "entropy": 0.07006354629993439, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:33.686393Z", "loop": 10683, "env_steps": 6564249599, "loss": 0.012697326950728893, "avg_return": 0.8631458878517151, "regret": 0.00026371239800937474, "entropy": 0.06972616910934448, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:34.541325Z", "loop": 10684, "env_steps": 6564863999, "loss": 0.013469916768372059, "avg_return": 0.8627811670303345, "regret": 0.00026371239800937474, "entropy": 0.06897812336683273, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:35.395268Z", "loop": 10685, "env_steps": 6565478399, "loss": 0.013316941447556019, "avg_return": 0.8633716106414795, "regret": 0.00026371239800937474, "entropy": 0.07196960598230362, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:36.249442Z", "loop": 10686, "env_steps": 6566092799, "loss": 0.012263383716344833, "avg_return": 0.8639439344406128, "regret": 0.00026371239800937474, "entropy": 0.0650903731584549, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:37.103093Z", "loop": 10687, "env_steps": 6566707199, "loss": 0.012748772278428078, "avg_return": 0.8644303679466248, "regret": 0.00026371239800937474, "entropy": 0.06882566213607788, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:37.956562Z", "loop": 10688, "env_steps": 6567321599, "loss": 0.013488373719155788, "avg_return": 0.8629379272460938, "regret": 0.00026371239800937474, "entropy": 0.07034960389137268, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:38.811023Z", "loop": 10689, "env_steps": 6567935999, "loss": 0.01319896336644888, "avg_return": 0.8641508221626282, "regret": 0.00026371239800937474, "entropy": 0.07232619822025299, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:39.703874Z", "loop": 10690, "env_steps": 6568550399, "loss": 0.012511136010289192, "avg_return": 0.862188458442688, "regret": 0.0004219851107336581, "entropy": 0.0682661309838295, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:40.558525Z", "loop": 10691, "env_steps": 6569164799, "loss": 0.011457808315753937, "avg_return": 0.8626282811164856, "regret": 0.0004219851107336581, "entropy": 0.06628771871328354, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:41.413486Z", "loop": 10692, "env_steps": 6569779199, "loss": 0.013053424656391144, "avg_return": 0.8646647334098816, "regret": 0.0004219851107336581, "entropy": 0.0659872367978096, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:42.269323Z", "loop": 10693, "env_steps": 6570393599, "loss": 0.013290655799210072, "avg_return": 0.8630684614181519, "regret": 0.0004219851107336581, "entropy": 0.07134158164262772, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:43.124408Z", "loop": 10694, "env_steps": 6571007999, "loss": 0.013129467144608498, "avg_return": 0.8620068430900574, "regret": 0.0004219851107336581, "entropy": 0.07059904932975769, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:43.977759Z", "loop": 10695, "env_steps": 6571622399, "loss": 0.013713712804019451, "avg_return": 0.8619502782821655, "regret": 0.0004219851107336581, "entropy": 0.0722079947590828, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:44.833785Z", "loop": 10696, "env_steps": 6572236799, "loss": 0.013046011328697205, "avg_return": 0.8631207346916199, "regret": 0.0004219851107336581, "entropy": 0.07061386108398438, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:45.689509Z", "loop": 10697, "env_steps": 6572851199, "loss": 0.01287816185504198, "avg_return": 0.86297607421875, "regret": 0.0004219851107336581, "entropy": 0.06996671855449677, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:46.543970Z", "loop": 10698, "env_steps": 6573465599, "loss": 0.013119759038090706, "avg_return": 0.8626015186309814, "regret": 0.0004219851107336581, "entropy": 0.0718725249171257, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:47.397624Z", "loop": 10699, "env_steps": 6574079999, "loss": 0.013102956116199493, "avg_return": 0.8626490235328674, "regret": 0.0004219851107336581, "entropy": 0.06845398247241974, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:48.291419Z", "loop": 10700, "env_steps": 6574694399, "loss": 0.012111512012779713, "avg_return": 0.8628572821617126, "regret": 0.0008853740291669965, "entropy": 0.06670410186052322, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:49.146034Z", "loop": 10701, "env_steps": 6575308799, "loss": 0.012134860269725323, "avg_return": 0.8622485399246216, "regret": 0.0008853740291669965, "entropy": 0.06510095298290253, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:50.000685Z", "loop": 10702, "env_steps": 6575923199, "loss": 0.012478615157306194, "avg_return": 0.8633919358253479, "regret": 0.0008853740291669965, "entropy": 0.06653213500976562, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:50.855880Z", "loop": 10703, "env_steps": 6576537599, "loss": 0.012696102261543274, "avg_return": 0.8624759912490845, "regret": 0.0008853740291669965, "entropy": 0.06849807500839233, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:51.709267Z", "loop": 10704, "env_steps": 6577151999, "loss": 0.012519306503236294, "avg_return": 0.8627334833145142, "regret": 0.0008853740291669965, "entropy": 0.06504995375871658, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:52.562927Z", "loop": 10705, "env_steps": 6577766399, "loss": 0.012698771432042122, "avg_return": 0.862105131149292, "regret": 0.0008853740291669965, "entropy": 0.06676860898733139, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:53.418269Z", "loop": 10706, "env_steps": 6578380799, "loss": 0.012360193766653538, "avg_return": 0.8629257678985596, "regret": 0.0008853740291669965, "entropy": 0.06904332339763641, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:54.272622Z", "loop": 10707, "env_steps": 6578995199, "loss": 0.01330585777759552, "avg_return": 0.8620522022247314, "regret": 0.0008853740291669965, "entropy": 0.06748528778553009, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:55.127117Z", "loop": 10708, "env_steps": 6579609599, "loss": 0.012162822298705578, "avg_return": 0.8607922792434692, "regret": 0.0008853740291669965, "entropy": 0.06847494840621948, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:55.981533Z", "loop": 10709, "env_steps": 6580223999, "loss": 0.013828965835273266, "avg_return": 0.8587378263473511, "regret": 0.0008853740291669965, "entropy": 0.07162534445524216, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:56.874762Z", "loop": 10710, "env_steps": 6580838399, "loss": 0.012762914411723614, "avg_return": 0.8620888590812683, "regret": 0.002635541372001171, "entropy": 0.06802400201559067, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:57.728921Z", "loop": 10711, "env_steps": 6581452799, "loss": 0.013749982230365276, "avg_return": 0.8618857860565186, "regret": 0.002635541372001171, "entropy": 0.07134778797626495, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:58.583091Z", "loop": 10712, "env_steps": 6582067199, "loss": 0.012365017086267471, "avg_return": 0.8612980246543884, "regret": 0.002635541372001171, "entropy": 0.06847498565912247, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:56:59.437533Z", "loop": 10713, "env_steps": 6582681599, "loss": 0.013608554378151894, "avg_return": 0.8592051267623901, "regret": 0.002635541372001171, "entropy": 0.07278290390968323, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:00.291679Z", "loop": 10714, "env_steps": 6583295999, "loss": 0.013563175685703754, "avg_return": 0.8600472211837769, "regret": 0.002635541372001171, "entropy": 0.07326184958219528, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:01.146262Z", "loop": 10715, "env_steps": 6583910399, "loss": 0.012218060903251171, "avg_return": 0.8597584962844849, "regret": 0.002635541372001171, "entropy": 0.06575081497430801, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:02.000158Z", "loop": 10716, "env_steps": 6584524799, "loss": 0.012488305568695068, "avg_return": 0.8602933883666992, "regret": 0.002635541372001171, "entropy": 0.06739392131567001, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:02.855460Z", "loop": 10717, "env_steps": 6585139199, "loss": 0.012959713116288185, "avg_return": 0.8606924414634705, "regret": 0.002635541372001171, "entropy": 0.06786702573299408, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:03.710313Z", "loop": 10718, "env_steps": 6585753599, "loss": 0.014504152350127697, "avg_return": 0.8606797456741333, "regret": 0.002635541372001171, "entropy": 0.07695336639881134, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:04.564186Z", "loop": 10719, "env_steps": 6586367999, "loss": 0.013571413233876228, "avg_return": 0.8605743646621704, "regret": 0.002635541372001171, "entropy": 0.070709228515625, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:05.456962Z", "loop": 10720, "env_steps": 6586982399, "loss": 0.013413532637059689, "avg_return": 0.8604941964149475, "regret": 0.003145847236737609, "entropy": 0.07065410912036896, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:06.311483Z", "loop": 10721, "env_steps": 6587596799, "loss": 0.01217738725244999, "avg_return": 0.8596867322921753, "regret": 0.003145847236737609, "entropy": 0.07020203769207001, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:07.164512Z", "loop": 10722, "env_steps": 6588211199, "loss": 0.013134526088833809, "avg_return": 0.8584210276603699, "regret": 0.003145847236737609, "entropy": 0.06972016394138336, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:08.017834Z", "loop": 10723, "env_steps": 6588825599, "loss": 0.012903690338134766, "avg_return": 0.8597148656845093, "regret": 0.003145847236737609, "entropy": 0.0699569433927536, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:08.872825Z", "loop": 10724, "env_steps": 6589439999, "loss": 0.012792060151696205, "avg_return": 0.8611639738082886, "regret": 0.003145847236737609, "entropy": 0.06729692220687866, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:09.727029Z", "loop": 10725, "env_steps": 6590054399, "loss": 0.01397428847849369, "avg_return": 0.8622860908508301, "regret": 0.003145847236737609, "entropy": 0.07186953723430634, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:10.580092Z", "loop": 10726, "env_steps": 6590668799, "loss": 0.012216881848871708, "avg_return": 0.861571192741394, "regret": 0.003145847236737609, "entropy": 0.06785408407449722, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:11.434629Z", "loop": 10727, "env_steps": 6591283199, "loss": 0.01233694888651371, "avg_return": 0.8617762327194214, "regret": 0.003145847236737609, "entropy": 0.06569398194551468, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:12.291110Z", "loop": 10728, "env_steps": 6591897599, "loss": 0.013719585724174976, "avg_return": 0.8633225560188293, "regret": 0.003145847236737609, "entropy": 0.07277495414018631, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:13.146662Z", "loop": 10729, "env_steps": 6592511999, "loss": 0.011729593388736248, "avg_return": 0.8612964153289795, "regret": 0.003145847236737609, "entropy": 0.0650472566485405, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:14.040819Z", "loop": 10730, "env_steps": 6593126399, "loss": 0.01152647752314806, "avg_return": 0.8606396913528442, "regret": 0.0014285885263234377, "entropy": 0.06380477547645569, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:14.894722Z", "loop": 10731, "env_steps": 6593740799, "loss": 0.011101199313998222, "avg_return": 0.861744225025177, "regret": 0.0014285885263234377, "entropy": 0.06123219430446625, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:15.749178Z", "loop": 10732, "env_steps": 6594355199, "loss": 0.012596790678799152, "avg_return": 0.8624566793441772, "regret": 0.0014285885263234377, "entropy": 0.0673636645078659, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:16.604051Z", "loop": 10733, "env_steps": 6594969599, "loss": 0.012135758064687252, "avg_return": 0.8626067042350769, "regret": 0.0014285885263234377, "entropy": 0.06835116446018219, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:17.458558Z", "loop": 10734, "env_steps": 6595583999, "loss": 0.011390010826289654, "avg_return": 0.8621179461479187, "regret": 0.0014285885263234377, "entropy": 0.0627550557255745, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:18.312475Z", "loop": 10735, "env_steps": 6596198399, "loss": 0.012355733662843704, "avg_return": 0.86279296875, "regret": 0.0014285885263234377, "entropy": 0.06448189169168472, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:19.166838Z", "loop": 10736, "env_steps": 6596812799, "loss": 0.011568121612071991, "avg_return": 0.8624299168586731, "regret": 0.0014285885263234377, "entropy": 0.06539195775985718, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:20.022774Z", "loop": 10737, "env_steps": 6597427199, "loss": 0.012488014064729214, "avg_return": 0.8633235692977905, "regret": 0.0014285885263234377, "entropy": 0.06542785465717316, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:20.877895Z", "loop": 10738, "env_steps": 6598041599, "loss": 0.011989831924438477, "avg_return": 0.8631497621536255, "regret": 0.0014285885263234377, "entropy": 0.06393494457006454, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:21.732979Z", "loop": 10739, "env_steps": 6598655999, "loss": 0.013541280291974545, "avg_return": 0.8634428977966309, "regret": 0.0014285885263234377, "entropy": 0.07117258012294769, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:22.628128Z", "loop": 10740, "env_steps": 6599270399, "loss": 0.01224516797810793, "avg_return": 0.8629267811775208, "regret": 0.0003372645587660372, "entropy": 0.06733869761228561, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:23.482270Z", "loop": 10741, "env_steps": 6599884799, "loss": 0.011523148976266384, "avg_return": 0.8630715012550354, "regret": 0.0003372645587660372, "entropy": 0.06605582684278488, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:24.337656Z", "loop": 10742, "env_steps": 6600499199, "loss": 0.012251545675098896, "avg_return": 0.8615602850914001, "regret": 0.0003372645587660372, "entropy": 0.06635027378797531, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:25.193783Z", "loop": 10743, "env_steps": 6601113599, "loss": 0.01144154742360115, "avg_return": 0.8625456094741821, "regret": 0.0003372645587660372, "entropy": 0.0636044517159462, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:26.050288Z", "loop": 10744, "env_steps": 6601727999, "loss": 0.012267756275832653, "avg_return": 0.8642026782035828, "regret": 0.0003372645587660372, "entropy": 0.06586875766515732, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:26.905328Z", "loop": 10745, "env_steps": 6602342399, "loss": 0.01211884617805481, "avg_return": 0.8628958463668823, "regret": 0.0003372645587660372, "entropy": 0.0644020065665245, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:27.760211Z", "loop": 10746, "env_steps": 6602956799, "loss": 0.011491728015244007, "avg_return": 0.8636599183082581, "regret": 0.0003372645587660372, "entropy": 0.06500567495822906, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:28.615465Z", "loop": 10747, "env_steps": 6603571199, "loss": 0.012263412587344646, "avg_return": 0.8636074066162109, "regret": 0.0003372645587660372, "entropy": 0.06645891815423965, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:29.470186Z", "loop": 10748, "env_steps": 6604185599, "loss": 0.012697874568402767, "avg_return": 0.8632014989852905, "regret": 0.0003372645587660372, "entropy": 0.06878884881734848, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:30.324759Z", "loop": 10749, "env_steps": 6604799999, "loss": 0.013760547153651714, "avg_return": 0.8640902042388916, "regret": 0.0003372645587660372, "entropy": 0.07212603837251663, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:31.216308Z", "loop": 10750, "env_steps": 6605414399, "loss": 0.012614652514457703, "avg_return": 0.8623786568641663, "regret": 0.0004161187680438161, "entropy": 0.07054749131202698, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:32.071116Z", "loop": 10751, "env_steps": 6606028799, "loss": 0.013365118764340878, "avg_return": 0.8644447922706604, "regret": 0.0004161187680438161, "entropy": 0.07058835029602051, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:32.926224Z", "loop": 10752, "env_steps": 6606643199, "loss": 0.013421406038105488, "avg_return": 0.863147497177124, "regret": 0.0004161187680438161, "entropy": 0.06881915777921677, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:33.781160Z", "loop": 10753, "env_steps": 6607257599, "loss": 0.013067173771560192, "avg_return": 0.8642226457595825, "regret": 0.0004161187680438161, "entropy": 0.07039640098810196, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:34.635652Z", "loop": 10754, "env_steps": 6607871999, "loss": 0.012134632095694542, "avg_return": 0.8632959127426147, "regret": 0.0004161187680438161, "entropy": 0.06697110086679459, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:35.489373Z", "loop": 10755, "env_steps": 6608486399, "loss": 0.012841942720115185, "avg_return": 0.8624811172485352, "regret": 0.0004161187680438161, "entropy": 0.07026295363903046, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:36.344957Z", "loop": 10756, "env_steps": 6609100799, "loss": 0.013784462586045265, "avg_return": 0.8627294898033142, "regret": 0.0004161187680438161, "entropy": 0.07082464545965195, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:37.201224Z", "loop": 10757, "env_steps": 6609715199, "loss": 0.012849899008870125, "avg_return": 0.8635815382003784, "regret": 0.0004161187680438161, "entropy": 0.07127465307712555, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:38.055406Z", "loop": 10758, "env_steps": 6610329599, "loss": 0.013372145593166351, "avg_return": 0.8631284832954407, "regret": 0.0004161187680438161, "entropy": 0.07134206593036652, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:38.909843Z", "loop": 10759, "env_steps": 6610943999, "loss": 0.012668788433074951, "avg_return": 0.8637251853942871, "regret": 0.0004161187680438161, "entropy": 0.06951191276311874, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:39.802985Z", "loop": 10760, "env_steps": 6611558399, "loss": 0.012883970513939857, "avg_return": 0.8650578260421753, "regret": 0.0005984176532365382, "entropy": 0.07012500613927841, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:40.656815Z", "loop": 10761, "env_steps": 6612172799, "loss": 0.012484549544751644, "avg_return": 0.8634127974510193, "regret": 0.0005984176532365382, "entropy": 0.07037482410669327, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:41.511965Z", "loop": 10762, "env_steps": 6612787199, "loss": 0.011220792308449745, "avg_return": 0.8628963232040405, "regret": 0.0005984176532365382, "entropy": 0.0644654855132103, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:42.366224Z", "loop": 10763, "env_steps": 6613401599, "loss": 0.011812550947070122, "avg_return": 0.8617982268333435, "regret": 0.0005984176532365382, "entropy": 0.06763453781604767, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:43.220394Z", "loop": 10764, "env_steps": 6614015999, "loss": 0.012351850979030132, "avg_return": 0.8621137738227844, "regret": 0.0005984176532365382, "entropy": 0.06681257486343384, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:44.075112Z", "loop": 10765, "env_steps": 6614630399, "loss": 0.012411477975547314, "avg_return": 0.8617900609970093, "regret": 0.0005984176532365382, "entropy": 0.06372395902872086, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:44.929666Z", "loop": 10766, "env_steps": 6615244799, "loss": 0.011910953558981419, "avg_return": 0.8630433082580566, "regret": 0.0005984176532365382, "entropy": 0.06784479320049286, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:45.784978Z", "loop": 10767, "env_steps": 6615859199, "loss": 0.011871405877172947, "avg_return": 0.8618948459625244, "regret": 0.0005984176532365382, "entropy": 0.06703795492649078, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:46.639671Z", "loop": 10768, "env_steps": 6616473599, "loss": 0.011614981107413769, "avg_return": 0.8614200949668884, "regret": 0.0005984176532365382, "entropy": 0.062384821474552155, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:47.494293Z", "loop": 10769, "env_steps": 6617087999, "loss": 0.012777142226696014, "avg_return": 0.8613489866256714, "regret": 0.0005984176532365382, "entropy": 0.06722774356603622, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:48.387122Z", "loop": 10770, "env_steps": 6617702399, "loss": 0.013563494198024273, "avg_return": 0.8618119359016418, "regret": 0.0020948555320501328, "entropy": 0.07124996185302734, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:49.241739Z", "loop": 10771, "env_steps": 6618316799, "loss": 0.013485326431691647, "avg_return": 0.8614314794540405, "regret": 0.0020948555320501328, "entropy": 0.06978309154510498, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:50.095484Z", "loop": 10772, "env_steps": 6618931199, "loss": 0.012888329103589058, "avg_return": 0.8608782887458801, "regret": 0.0020948555320501328, "entropy": 0.06889262795448303, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:50.949693Z", "loop": 10773, "env_steps": 6619545599, "loss": 0.012961545959115028, "avg_return": 0.8614506125450134, "regret": 0.0020948555320501328, "entropy": 0.06666310131549835, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:51.803631Z", "loop": 10774, "env_steps": 6620159999, "loss": 0.012977714650332928, "avg_return": 0.8633376359939575, "regret": 0.0020948555320501328, "entropy": 0.06474031507968903, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:52.657597Z", "loop": 10775, "env_steps": 6620774399, "loss": 0.013096203096210957, "avg_return": 0.8625611662864685, "regret": 0.0020948555320501328, "entropy": 0.06795265525579453, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:53.511619Z", "loop": 10776, "env_steps": 6621388799, "loss": 0.013066385872662067, "avg_return": 0.861867368221283, "regret": 0.0020948555320501328, "entropy": 0.07037900388240814, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:54.365220Z", "loop": 10777, "env_steps": 6622003199, "loss": 0.011986492201685905, "avg_return": 0.862649142742157, "regret": 0.0020948555320501328, "entropy": 0.06642138212919235, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:55.218733Z", "loop": 10778, "env_steps": 6622617599, "loss": 0.012124412693083286, "avg_return": 0.8618176579475403, "regret": 0.0020948555320501328, "entropy": 0.06430437415838242, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:56.072820Z", "loop": 10779, "env_steps": 6623231999, "loss": 0.012830257415771484, "avg_return": 0.862099826335907, "regret": 0.0020948555320501328, "entropy": 0.06743385642766953, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:56.963767Z", "loop": 10780, "env_steps": 6623846399, "loss": 0.01153466198593378, "avg_return": 0.8639419674873352, "regret": 0.0007939295028336346, "entropy": 0.06505285203456879, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:57.817717Z", "loop": 10781, "env_steps": 6624460799, "loss": 0.011757205240428448, "avg_return": 0.8620408177375793, "regret": 0.0007939295028336346, "entropy": 0.06618322432041168, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:58.672508Z", "loop": 10782, "env_steps": 6625075199, "loss": 0.01268902700394392, "avg_return": 0.8627942204475403, "regret": 0.0007939295028336346, "entropy": 0.06585647910833359, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:57:59.527676Z", "loop": 10783, "env_steps": 6625689599, "loss": 0.012110007926821709, "avg_return": 0.8632720112800598, "regret": 0.0007939295028336346, "entropy": 0.06681346893310547, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:00.381090Z", "loop": 10784, "env_steps": 6626303999, "loss": 0.012059720233082771, "avg_return": 0.8623318672180176, "regret": 0.0007939295028336346, "entropy": 0.06610582023859024, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:01.235950Z", "loop": 10785, "env_steps": 6626918399, "loss": 0.012043895199894905, "avg_return": 0.8631541132926941, "regret": 0.0007939295028336346, "entropy": 0.0669122114777565, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:02.090885Z", "loop": 10786, "env_steps": 6627532799, "loss": 0.011903760954737663, "avg_return": 0.8620400428771973, "regret": 0.0007939295028336346, "entropy": 0.06698876619338989, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:02.946276Z", "loop": 10787, "env_steps": 6628147199, "loss": 0.012233219109475613, "avg_return": 0.8618378639221191, "regret": 0.0007939295028336346, "entropy": 0.06940412521362305, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:03.800420Z", "loop": 10788, "env_steps": 6628761599, "loss": 0.011601717211306095, "avg_return": 0.8637492060661316, "regret": 0.0007939295028336346, "entropy": 0.06204706430435181, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:04.654858Z", "loop": 10789, "env_steps": 6629375999, "loss": 0.01233114954084158, "avg_return": 0.8635333180427551, "regret": 0.0007939295028336346, "entropy": 0.0692269504070282, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:05.548212Z", "loop": 10790, "env_steps": 6629990399, "loss": 0.011335959658026695, "avg_return": 0.8627979755401611, "regret": 0.0008095384109765291, "entropy": 0.0632268488407135, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:06.402409Z", "loop": 10791, "env_steps": 6630604799, "loss": 0.012525828555226326, "avg_return": 0.8635121583938599, "regret": 0.0008095384109765291, "entropy": 0.07166653126478195, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:07.256087Z", "loop": 10792, "env_steps": 6631219199, "loss": 0.011186662130057812, "avg_return": 0.863130509853363, "regret": 0.0008095384109765291, "entropy": 0.06417292356491089, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:08.110395Z", "loop": 10793, "env_steps": 6631833599, "loss": 0.012249850668013096, "avg_return": 0.8635746240615845, "regret": 0.0008095384109765291, "entropy": 0.06667493283748627, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:08.964279Z", "loop": 10794, "env_steps": 6632447999, "loss": 0.012519048526883125, "avg_return": 0.8629910349845886, "regret": 0.0008095384109765291, "entropy": 0.06723954528570175, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:09.818636Z", "loop": 10795, "env_steps": 6633062399, "loss": 0.011706617660820484, "avg_return": 0.8633158802986145, "regret": 0.0008095384109765291, "entropy": 0.06270845234394073, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:10.672937Z", "loop": 10796, "env_steps": 6633676799, "loss": 0.012756818905472755, "avg_return": 0.8630591034889221, "regret": 0.0008095384109765291, "entropy": 0.07015015184879303, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:11.528507Z", "loop": 10797, "env_steps": 6634291199, "loss": 0.012015788815915585, "avg_return": 0.8614509105682373, "regret": 0.0008095384109765291, "entropy": 0.0659421756863594, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:12.383166Z", "loop": 10798, "env_steps": 6634905599, "loss": 0.011925918981432915, "avg_return": 0.8625606298446655, "regret": 0.0008095384109765291, "entropy": 0.06812767684459686, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:13.237185Z", "loop": 10799, "env_steps": 6635519999, "loss": 0.012069637887179852, "avg_return": 0.8619500994682312, "regret": 0.0008095384109765291, "entropy": 0.0654621496796608, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:14.130079Z", "loop": 10800, "env_steps": 6636134399, "loss": 0.011902379803359509, "avg_return": 0.8625852465629578, "regret": 0.0007265081512741745, "entropy": 0.06576342135667801, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:14.984698Z", "loop": 10801, "env_steps": 6636748799, "loss": 0.01228097453713417, "avg_return": 0.8617191910743713, "regret": 0.0007265081512741745, "entropy": 0.06671977043151855, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:15.840257Z", "loop": 10802, "env_steps": 6637363199, "loss": 0.011502036824822426, "avg_return": 0.8628758192062378, "regret": 0.0007265081512741745, "entropy": 0.06532350927591324, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:16.695116Z", "loop": 10803, "env_steps": 6637977599, "loss": 0.011829058639705181, "avg_return": 0.8620995283126831, "regret": 0.0007265081512741745, "entropy": 0.06397080421447754, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:17.548784Z", "loop": 10804, "env_steps": 6638591999, "loss": 0.012271377258002758, "avg_return": 0.8637065887451172, "regret": 0.0007265081512741745, "entropy": 0.06628868728876114, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:18.403483Z", "loop": 10805, "env_steps": 6639206399, "loss": 0.011818320490419865, "avg_return": 0.8613702654838562, "regret": 0.0007265081512741745, "entropy": 0.06530845165252686, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:19.258836Z", "loop": 10806, "env_steps": 6639820799, "loss": 0.012212282977998257, "avg_return": 0.8630102872848511, "regret": 0.0007265081512741745, "entropy": 0.06499883532524109, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:20.113816Z", "loop": 10807, "env_steps": 6640435199, "loss": 0.011899318546056747, "avg_return": 0.8640667796134949, "regret": 0.0007265081512741745, "entropy": 0.06590472161769867, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:20.967264Z", "loop": 10808, "env_steps": 6641049599, "loss": 0.012178664095699787, "avg_return": 0.8628779053688049, "regret": 0.0007265081512741745, "entropy": 0.06617214530706406, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:21.820177Z", "loop": 10809, "env_steps": 6641663999, "loss": 0.012814800255000591, "avg_return": 0.8636391162872314, "regret": 0.0007265081512741745, "entropy": 0.06821359694004059, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:22.713579Z", "loop": 10810, "env_steps": 6642278399, "loss": 0.01261343527585268, "avg_return": 0.8621319532394409, "regret": 0.0005706933443434536, "entropy": 0.06768665462732315, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:23.567999Z", "loop": 10811, "env_steps": 6642892799, "loss": 0.011581134051084518, "avg_return": 0.8631381392478943, "regret": 0.0005706933443434536, "entropy": 0.0657220110297203, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:24.422528Z", "loop": 10812, "env_steps": 6643507199, "loss": 0.011832469142973423, "avg_return": 0.8622192740440369, "regret": 0.0005706933443434536, "entropy": 0.0668410211801529, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:25.276568Z", "loop": 10813, "env_steps": 6644121599, "loss": 0.011957868933677673, "avg_return": 0.8615461587905884, "regret": 0.0005706933443434536, "entropy": 0.06543581187725067, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:26.130921Z", "loop": 10814, "env_steps": 6644735999, "loss": 0.013263622298836708, "avg_return": 0.8644651770591736, "regret": 0.0005706933443434536, "entropy": 0.07306581735610962, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:26.987083Z", "loop": 10815, "env_steps": 6645350399, "loss": 0.011795897968113422, "avg_return": 0.8612651824951172, "regret": 0.0005706933443434536, "entropy": 0.06712280213832855, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:27.842460Z", "loop": 10816, "env_steps": 6645964799, "loss": 0.01308745052665472, "avg_return": 0.8630216717720032, "regret": 0.0005706933443434536, "entropy": 0.07081476598978043, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:28.696550Z", "loop": 10817, "env_steps": 6646579199, "loss": 0.0132351815700531, "avg_return": 0.8632330298423767, "regret": 0.0005706933443434536, "entropy": 0.07218517363071442, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:29.551318Z", "loop": 10818, "env_steps": 6647193599, "loss": 0.013719639740884304, "avg_return": 0.8626479506492615, "regret": 0.0005706933443434536, "entropy": 0.07393909245729446, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:30.406436Z", "loop": 10819, "env_steps": 6647807999, "loss": 0.014548218809068203, "avg_return": 0.8636783957481384, "regret": 0.0005706933443434536, "entropy": 0.07671011984348297, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:31.301608Z", "loop": 10820, "env_steps": 6648422399, "loss": 0.014521593227982521, "avg_return": 0.8608117699623108, "regret": 0.0024413091596215963, "entropy": 0.0798221156001091, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:32.155662Z", "loop": 10821, "env_steps": 6649036799, "loss": 0.01491469144821167, "avg_return": 0.8605035543441772, "regret": 0.0024413091596215963, "entropy": 0.07898826152086258, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:33.010030Z", "loop": 10822, "env_steps": 6649651199, "loss": 0.014999325387179852, "avg_return": 0.8601382374763489, "regret": 0.0024413091596215963, "entropy": 0.08130303025245667, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:33.864304Z", "loop": 10823, "env_steps": 6650265599, "loss": 0.014955026097595692, "avg_return": 0.8586847186088562, "regret": 0.0024413091596215963, "entropy": 0.08221492916345596, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:34.718423Z", "loop": 10824, "env_steps": 6650879999, "loss": 0.013130848295986652, "avg_return": 0.8622247576713562, "regret": 0.0024413091596215963, "entropy": 0.07811079174280167, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:35.573089Z", "loop": 10825, "env_steps": 6651494399, "loss": 0.013750306330621243, "avg_return": 0.8597845435142517, "regret": 0.0024413091596215963, "entropy": 0.07644017785787582, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:36.427593Z", "loop": 10826, "env_steps": 6652108799, "loss": 0.013457258231937885, "avg_return": 0.861347496509552, "regret": 0.0024413091596215963, "entropy": 0.07431509345769882, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:37.281059Z", "loop": 10827, "env_steps": 6652723199, "loss": 0.01210365816950798, "avg_return": 0.863512396812439, "regret": 0.0024413091596215963, "entropy": 0.0669214129447937, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:38.134741Z", "loop": 10828, "env_steps": 6653337599, "loss": 0.013288170099258423, "avg_return": 0.8626428246498108, "regret": 0.0024413091596215963, "entropy": 0.06824041903018951, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:38.988608Z", "loop": 10829, "env_steps": 6653951999, "loss": 0.013693456538021564, "avg_return": 0.863774836063385, "regret": 0.0024413091596215963, "entropy": 0.07235752046108246, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:39.880727Z", "loop": 10830, "env_steps": 6654566399, "loss": 0.012767878361046314, "avg_return": 0.8631376624107361, "regret": 0.0007906676037237048, "entropy": 0.06921757757663727, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:40.734281Z", "loop": 10831, "env_steps": 6655180799, "loss": 0.012442550621926785, "avg_return": 0.8616322875022888, "regret": 0.0007906676037237048, "entropy": 0.06600185483694077, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:41.587509Z", "loop": 10832, "env_steps": 6655795199, "loss": 0.011137542314827442, "avg_return": 0.8625370264053345, "regret": 0.0007906676037237048, "entropy": 0.0639839619398117, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:42.441664Z", "loop": 10833, "env_steps": 6656409599, "loss": 0.012324805371463299, "avg_return": 0.862453043460846, "regret": 0.0007906676037237048, "entropy": 0.06789635121822357, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:43.296164Z", "loop": 10834, "env_steps": 6657023999, "loss": 0.012547559104859829, "avg_return": 0.8625325560569763, "regret": 0.0007906676037237048, "entropy": 0.06752891093492508, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:44.150468Z", "loop": 10835, "env_steps": 6657638399, "loss": 0.01164335198700428, "avg_return": 0.8628379702568054, "regret": 0.0007906676037237048, "entropy": 0.06306734681129456, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:45.004778Z", "loop": 10836, "env_steps": 6658252799, "loss": 0.012393433600664139, "avg_return": 0.8612452149391174, "regret": 0.0007906676037237048, "entropy": 0.06602632999420166, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:45.859929Z", "loop": 10837, "env_steps": 6658867199, "loss": 0.01192624494433403, "avg_return": 0.8622395992279053, "regret": 0.0007906676037237048, "entropy": 0.0653802752494812, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:46.714099Z", "loop": 10838, "env_steps": 6659481599, "loss": 0.012218281626701355, "avg_return": 0.8613379001617432, "regret": 0.0007906676037237048, "entropy": 0.06488129496574402, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:47.568463Z", "loop": 10839, "env_steps": 6660095999, "loss": 0.01374991238117218, "avg_return": 0.8626724481582642, "regret": 0.0007906676037237048, "entropy": 0.07017838209867477, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:48.459013Z", "loop": 10840, "env_steps": 6660710399, "loss": 0.012049506418406963, "avg_return": 0.860920250415802, "regret": 0.002371283480897546, "entropy": 0.06646621227264404, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:49.312735Z", "loop": 10841, "env_steps": 6661324799, "loss": 0.011760723777115345, "avg_return": 0.861116886138916, "regret": 0.002371283480897546, "entropy": 0.06456797569990158, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:50.167175Z", "loop": 10842, "env_steps": 6661939199, "loss": 0.012248213402926922, "avg_return": 0.8613712787628174, "regret": 0.002371283480897546, "entropy": 0.0669836476445198, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:51.020498Z", "loop": 10843, "env_steps": 6662553599, "loss": 0.012850934639573097, "avg_return": 0.8604766130447388, "regret": 0.002371283480897546, "entropy": 0.07206659764051437, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:51.874308Z", "loop": 10844, "env_steps": 6663167999, "loss": 0.013141979463398457, "avg_return": 0.8612575531005859, "regret": 0.002371283480897546, "entropy": 0.06865482777357101, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:52.728531Z", "loop": 10845, "env_steps": 6663782399, "loss": 0.01342985313385725, "avg_return": 0.8617903590202332, "regret": 0.002371283480897546, "entropy": 0.07006799429655075, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:53.582810Z", "loop": 10846, "env_steps": 6664396799, "loss": 0.01198470126837492, "avg_return": 0.8628743886947632, "regret": 0.002371283480897546, "entropy": 0.0674387738108635, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:54.436134Z", "loop": 10847, "env_steps": 6665011199, "loss": 0.011868986301124096, "avg_return": 0.8614559173583984, "regret": 0.002371283480897546, "entropy": 0.06908629834651947, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:55.290373Z", "loop": 10848, "env_steps": 6665625599, "loss": 0.012330025434494019, "avg_return": 0.861099898815155, "regret": 0.002371283480897546, "entropy": 0.06731092184782028, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:56.142977Z", "loop": 10849, "env_steps": 6666239999, "loss": 0.011860549449920654, "avg_return": 0.8616863489151001, "regret": 0.002371283480897546, "entropy": 0.06448760628700256, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:57.034837Z", "loop": 10850, "env_steps": 6666854399, "loss": 0.011510637588799, "avg_return": 0.8613964915275574, "regret": 0.0022208953741937876, "entropy": 0.06507165729999542, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:57.888131Z", "loop": 10851, "env_steps": 6667468799, "loss": 0.011411504819989204, "avg_return": 0.8610364198684692, "regret": 0.0022208953741937876, "entropy": 0.06500425189733505, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:58.742161Z", "loop": 10852, "env_steps": 6668083199, "loss": 0.011979947797954082, "avg_return": 0.8622297644615173, "regret": 0.0022208953741937876, "entropy": 0.0645967349410057, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:58:59.595498Z", "loop": 10853, "env_steps": 6668697599, "loss": 0.013239974156022072, "avg_return": 0.8623435497283936, "regret": 0.0022208953741937876, "entropy": 0.06605660170316696, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:00.448684Z", "loop": 10854, "env_steps": 6669311999, "loss": 0.01187520008534193, "avg_return": 0.8624196648597717, "regret": 0.0022208953741937876, "entropy": 0.06769227236509323, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:01.303237Z", "loop": 10855, "env_steps": 6669926399, "loss": 0.01095369178801775, "avg_return": 0.8624153733253479, "regret": 0.0022208953741937876, "entropy": 0.05998975783586502, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:02.156679Z", "loop": 10856, "env_steps": 6670540799, "loss": 0.011844707652926445, "avg_return": 0.8627701997756958, "regret": 0.0022208953741937876, "entropy": 0.06362475454807281, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:03.011868Z", "loop": 10857, "env_steps": 6671155199, "loss": 0.012519570998847485, "avg_return": 0.862710177898407, "regret": 0.0022208953741937876, "entropy": 0.06752953678369522, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:03.864769Z", "loop": 10858, "env_steps": 6671769599, "loss": 0.013362082652747631, "avg_return": 0.8624444603919983, "regret": 0.0022208953741937876, "entropy": 0.067552350461483, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:04.717468Z", "loop": 10859, "env_steps": 6672383999, "loss": 0.011337300762534142, "avg_return": 0.8633722066879272, "regret": 0.0022208953741937876, "entropy": 0.06423172354698181, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:05.611525Z", "loop": 10860, "env_steps": 6672998399, "loss": 0.012385615147650242, "avg_return": 0.8634539842605591, "regret": 0.0007223448483273387, "entropy": 0.06808023899793625, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:06.466878Z", "loop": 10861, "env_steps": 6673612799, "loss": 0.012600027024745941, "avg_return": 0.862963080406189, "regret": 0.0007223448483273387, "entropy": 0.06443311274051666, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:07.321468Z", "loop": 10862, "env_steps": 6674227199, "loss": 0.012592503800988197, "avg_return": 0.8631431460380554, "regret": 0.0007223448483273387, "entropy": 0.06829984486103058, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:08.175496Z", "loop": 10863, "env_steps": 6674841599, "loss": 0.013601377606391907, "avg_return": 0.861947238445282, "regret": 0.0007223448483273387, "entropy": 0.0701407790184021, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:09.029468Z", "loop": 10864, "env_steps": 6675455999, "loss": 0.01249124389141798, "avg_return": 0.8639124035835266, "regret": 0.0007223448483273387, "entropy": 0.06462815403938293, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:09.885030Z", "loop": 10865, "env_steps": 6676070399, "loss": 0.013081083074212074, "avg_return": 0.8636277318000793, "regret": 0.0007223448483273387, "entropy": 0.06841956824064255, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:10.740541Z", "loop": 10866, "env_steps": 6676684799, "loss": 0.011941914446651936, "avg_return": 0.8642199635505676, "regret": 0.0007223448483273387, "entropy": 0.06511139869689941, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:11.594411Z", "loop": 10867, "env_steps": 6677299199, "loss": 0.012273102067410946, "avg_return": 0.8634306192398071, "regret": 0.0007223448483273387, "entropy": 0.06436073780059814, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:12.448393Z", "loop": 10868, "env_steps": 6677913599, "loss": 0.012811525724828243, "avg_return": 0.8625283241271973, "regret": 0.0007223448483273387, "entropy": 0.07217923551797867, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:13.302792Z", "loop": 10869, "env_steps": 6678527999, "loss": 0.013065519742667675, "avg_return": 0.8629364371299744, "regret": 0.0007223448483273387, "entropy": 0.07076320052146912, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:14.195399Z", "loop": 10870, "env_steps": 6679142399, "loss": 0.015711382031440735, "avg_return": 0.8647357225418091, "regret": 0.0003064436314161867, "entropy": 0.08020452409982681, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:15.049910Z", "loop": 10871, "env_steps": 6679756799, "loss": 0.014507847838103771, "avg_return": 0.8635351657867432, "regret": 0.0003064436314161867, "entropy": 0.0772247388958931, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:15.903441Z", "loop": 10872, "env_steps": 6680371199, "loss": 0.014191343449056149, "avg_return": 0.8626745939254761, "regret": 0.0003064436314161867, "entropy": 0.07601998001337051, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:16.757532Z", "loop": 10873, "env_steps": 6680985599, "loss": 0.01644785702228546, "avg_return": 0.8634812831878662, "regret": 0.0003064436314161867, "entropy": 0.08221655339002609, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:17.612080Z", "loop": 10874, "env_steps": 6681599999, "loss": 0.015634318813681602, "avg_return": 0.8628499507904053, "regret": 0.0003064436314161867, "entropy": 0.08091263473033905, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:18.467131Z", "loop": 10875, "env_steps": 6682214399, "loss": 0.015858320519328117, "avg_return": 0.8627921938896179, "regret": 0.0003064436314161867, "entropy": 0.08275037258863449, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:19.320487Z", "loop": 10876, "env_steps": 6682828799, "loss": 0.01565164141356945, "avg_return": 0.8632904291152954, "regret": 0.0003064436314161867, "entropy": 0.08401723951101303, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:20.173981Z", "loop": 10877, "env_steps": 6683443199, "loss": 0.015652475878596306, "avg_return": 0.8621464371681213, "regret": 0.0003064436314161867, "entropy": 0.08306930214166641, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:21.028197Z", "loop": 10878, "env_steps": 6684057599, "loss": 0.01593047007918358, "avg_return": 0.862381637096405, "regret": 0.0003064436314161867, "entropy": 0.08062537759542465, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:21.883100Z", "loop": 10879, "env_steps": 6684671999, "loss": 0.01555441040545702, "avg_return": 0.8622257709503174, "regret": 0.0003064436314161867, "entropy": 0.08412768691778183, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:22.775171Z", "loop": 10880, "env_steps": 6685286399, "loss": 0.01633509062230587, "avg_return": 0.8628643751144409, "regret": 0.00029549183091148734, "entropy": 0.0851815938949585, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:23.628841Z", "loop": 10881, "env_steps": 6685900799, "loss": 0.01587730273604393, "avg_return": 0.8631824851036072, "regret": 0.00029549183091148734, "entropy": 0.08239705115556717, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:24.483916Z", "loop": 10882, "env_steps": 6686515199, "loss": 0.016345323994755745, "avg_return": 0.8640735149383545, "regret": 0.00029549183091148734, "entropy": 0.08228370547294617, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:25.338692Z", "loop": 10883, "env_steps": 6687129599, "loss": 0.015617926605045795, "avg_return": 0.8625591397285461, "regret": 0.00029549183091148734, "entropy": 0.08087090402841568, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:26.192910Z", "loop": 10884, "env_steps": 6687743999, "loss": 0.014773713424801826, "avg_return": 0.8628382682800293, "regret": 0.00029549183091148734, "entropy": 0.07607174664735794, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:27.047385Z", "loop": 10885, "env_steps": 6688358399, "loss": 0.014493405818939209, "avg_return": 0.8626638054847717, "regret": 0.00029549183091148734, "entropy": 0.07548101991415024, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:27.902760Z", "loop": 10886, "env_steps": 6688972799, "loss": 0.013413602486252785, "avg_return": 0.8630972504615784, "regret": 0.00029549183091148734, "entropy": 0.0693054050207138, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:28.756467Z", "loop": 10887, "env_steps": 6689587199, "loss": 0.013048388063907623, "avg_return": 0.8637909293174744, "regret": 0.00029549183091148734, "entropy": 0.06913922727108002, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:29.610978Z", "loop": 10888, "env_steps": 6690201599, "loss": 0.012462393380701542, "avg_return": 0.8642764687538147, "regret": 0.00029549183091148734, "entropy": 0.06583067774772644, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:30.464710Z", "loop": 10889, "env_steps": 6690815999, "loss": 0.012718141078948975, "avg_return": 0.8643595576286316, "regret": 0.00029549183091148734, "entropy": 0.06806077063083649, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:31.363392Z", "loop": 10890, "env_steps": 6691430399, "loss": 0.013409525156021118, "avg_return": 0.8636314272880554, "regret": 0.0008946519228629768, "entropy": 0.06988221406936646, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:32.216872Z", "loop": 10891, "env_steps": 6692044799, "loss": 0.013100839219987392, "avg_return": 0.8621432781219482, "regret": 0.0008946519228629768, "entropy": 0.07039052993059158, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:33.071571Z", "loop": 10892, "env_steps": 6692659199, "loss": 0.012956072576344013, "avg_return": 0.8614924550056458, "regret": 0.0008946519228629768, "entropy": 0.07107973098754883, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:33.926127Z", "loop": 10893, "env_steps": 6693273599, "loss": 0.012582373805344105, "avg_return": 0.8614111542701721, "regret": 0.0008946519228629768, "entropy": 0.06760948896408081, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:34.780279Z", "loop": 10894, "env_steps": 6693887999, "loss": 0.011019445024430752, "avg_return": 0.8621984124183655, "regret": 0.0008946519228629768, "entropy": 0.062268804758787155, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:35.634362Z", "loop": 10895, "env_steps": 6694502399, "loss": 0.012194967828691006, "avg_return": 0.8630086183547974, "regret": 0.0008946519228629768, "entropy": 0.06200854480266571, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:36.489244Z", "loop": 10896, "env_steps": 6695116799, "loss": 0.012496842071413994, "avg_return": 0.8629286885261536, "regret": 0.0008946519228629768, "entropy": 0.06770496070384979, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:37.343901Z", "loop": 10897, "env_steps": 6695731199, "loss": 0.011929954402148724, "avg_return": 0.8644404411315918, "regret": 0.0008946519228629768, "entropy": 0.06446553766727448, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:38.198951Z", "loop": 10898, "env_steps": 6696345599, "loss": 0.012200242839753628, "avg_return": 0.863600492477417, "regret": 0.0008946519228629768, "entropy": 0.06637655198574066, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:39.052385Z", "loop": 10899, "env_steps": 6696959999, "loss": 0.011180487461388111, "avg_return": 0.8633989691734314, "regret": 0.0008946519228629768, "entropy": 0.0622713528573513, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:39.946491Z", "loop": 10900, "env_steps": 6697574399, "loss": 0.011675229296088219, "avg_return": 0.8630471229553223, "regret": 0.0004640785919036716, "entropy": 0.061802349984645844, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:40.801958Z", "loop": 10901, "env_steps": 6698188799, "loss": 0.012002686969935894, "avg_return": 0.8629366159439087, "regret": 0.0004640785919036716, "entropy": 0.06530740857124329, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:41.656813Z", "loop": 10902, "env_steps": 6698803199, "loss": 0.011482136324048042, "avg_return": 0.8633131980895996, "regret": 0.0004640785919036716, "entropy": 0.06283719092607498, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:42.510560Z", "loop": 10903, "env_steps": 6699417599, "loss": 0.011104150675237179, "avg_return": 0.8629359006881714, "regret": 0.0004640785919036716, "entropy": 0.06202826648950577, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:43.364655Z", "loop": 10904, "env_steps": 6700031999, "loss": 0.01109639648348093, "avg_return": 0.8625449538230896, "regret": 0.0004640785919036716, "entropy": 0.06069004163146019, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:44.220227Z", "loop": 10905, "env_steps": 6700646399, "loss": 0.01124949473887682, "avg_return": 0.8642605543136597, "regret": 0.0004640785919036716, "entropy": 0.061302829533815384, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:45.075208Z", "loop": 10906, "env_steps": 6701260799, "loss": 0.01144668459892273, "avg_return": 0.8616593480110168, "regret": 0.0004640785919036716, "entropy": 0.06295422464609146, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:45.930046Z", "loop": 10907, "env_steps": 6701875199, "loss": 0.011859876103699207, "avg_return": 0.8614866137504578, "regret": 0.0004640785919036716, "entropy": 0.06262384355068207, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:46.783873Z", "loop": 10908, "env_steps": 6702489599, "loss": 0.011245589703321457, "avg_return": 0.8621211051940918, "regret": 0.0004640785919036716, "entropy": 0.063802070915699, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:47.639085Z", "loop": 10909, "env_steps": 6703103999, "loss": 0.011989450082182884, "avg_return": 0.8619767427444458, "regret": 0.0004640785919036716, "entropy": 0.06317749619483948, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:48.532242Z", "loop": 10910, "env_steps": 6703718399, "loss": 0.012886038981378078, "avg_return": 0.8615535497665405, "regret": 0.0017915813950821757, "entropy": 0.0689258798956871, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:49.386506Z", "loop": 10911, "env_steps": 6704332799, "loss": 0.011915218085050583, "avg_return": 0.8625734448432922, "regret": 0.0017915813950821757, "entropy": 0.0648157000541687, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:50.241211Z", "loop": 10912, "env_steps": 6704947199, "loss": 0.012012801133096218, "avg_return": 0.8610494136810303, "regret": 0.0017915813950821757, "entropy": 0.0636390671133995, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:51.096079Z", "loop": 10913, "env_steps": 6705561599, "loss": 0.012410181574523449, "avg_return": 0.8610836267471313, "regret": 0.0017915813950821757, "entropy": 0.07027047127485275, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:51.951581Z", "loop": 10914, "env_steps": 6706175999, "loss": 0.012438597157597542, "avg_return": 0.8614919185638428, "regret": 0.0017915813950821757, "entropy": 0.06979020684957504, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:52.805994Z", "loop": 10915, "env_steps": 6706790399, "loss": 0.012118919752538204, "avg_return": 0.8624348044395447, "regret": 0.0017915813950821757, "entropy": 0.06672131270170212, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:53.660777Z", "loop": 10916, "env_steps": 6707404799, "loss": 0.0137235838919878, "avg_return": 0.8617843985557556, "regret": 0.0017915813950821757, "entropy": 0.07301149517297745, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:54.514771Z", "loop": 10917, "env_steps": 6708019199, "loss": 0.01260515209287405, "avg_return": 0.8602006435394287, "regret": 0.0017915813950821757, "entropy": 0.06995624303817749, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:55.368810Z", "loop": 10918, "env_steps": 6708633599, "loss": 0.013743218965828419, "avg_return": 0.859041154384613, "regret": 0.0017915813950821757, "entropy": 0.07296678423881531, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:56.223069Z", "loop": 10919, "env_steps": 6709247999, "loss": 0.014082074165344238, "avg_return": 0.8613739013671875, "regret": 0.0017915813950821757, "entropy": 0.07446953654289246, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:57.115044Z", "loop": 10920, "env_steps": 6709862399, "loss": 0.01351120788604021, "avg_return": 0.8598406910896301, "regret": 0.0032233400270342827, "entropy": 0.07142595201730728, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:57.969469Z", "loop": 10921, "env_steps": 6710476799, "loss": 0.01248006708920002, "avg_return": 0.8623679876327515, "regret": 0.0032233400270342827, "entropy": 0.06681925803422928, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:58.822956Z", "loop": 10922, "env_steps": 6711091199, "loss": 0.012639172375202179, "avg_return": 0.8610934615135193, "regret": 0.0032233400270342827, "entropy": 0.0664372444152832, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T19:59:59.676521Z", "loop": 10923, "env_steps": 6711705599, "loss": 0.010789553634822369, "avg_return": 0.861677348613739, "regret": 0.0032233400270342827, "entropy": 0.06150955706834793, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:00.531103Z", "loop": 10924, "env_steps": 6712319999, "loss": 0.011484824120998383, "avg_return": 0.862764835357666, "regret": 0.0032233400270342827, "entropy": 0.06316535919904709, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:01.386249Z", "loop": 10925, "env_steps": 6712934399, "loss": 0.011436820030212402, "avg_return": 0.8618277907371521, "regret": 0.0032233400270342827, "entropy": 0.06302133202552795, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:02.240141Z", "loop": 10926, "env_steps": 6713548799, "loss": 0.01037176139652729, "avg_return": 0.8619095087051392, "regret": 0.0032233400270342827, "entropy": 0.05981113389134407, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:03.094621Z", "loop": 10927, "env_steps": 6714163199, "loss": 0.011488955467939377, "avg_return": 0.863166332244873, "regret": 0.0032233400270342827, "entropy": 0.06325788795948029, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:03.948470Z", "loop": 10928, "env_steps": 6714777599, "loss": 0.010699202306568623, "avg_return": 0.8629673719406128, "regret": 0.0032233400270342827, "entropy": 0.059898074716329575, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:04.803594Z", "loop": 10929, "env_steps": 6715391999, "loss": 0.012326999567449093, "avg_return": 0.8631142377853394, "regret": 0.0032233400270342827, "entropy": 0.06106051802635193, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:05.695746Z", "loop": 10930, "env_steps": 6716006399, "loss": 0.011184620670974255, "avg_return": 0.8633632659912109, "regret": 0.0008880869136191905, "entropy": 0.06261071562767029, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:06.549319Z", "loop": 10931, "env_steps": 6716620799, "loss": 0.011246901005506516, "avg_return": 0.862679660320282, "regret": 0.0008880869136191905, "entropy": 0.06311244517564774, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:07.403247Z", "loop": 10932, "env_steps": 6717235199, "loss": 0.010559678077697754, "avg_return": 0.8639017939567566, "regret": 0.0008880869136191905, "entropy": 0.06007695198059082, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:08.258461Z", "loop": 10933, "env_steps": 6717849599, "loss": 0.012075109407305717, "avg_return": 0.8630683422088623, "regret": 0.0008880869136191905, "entropy": 0.06311924755573273, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:09.112769Z", "loop": 10934, "env_steps": 6718463999, "loss": 0.010719318874180317, "avg_return": 0.8627710342407227, "regret": 0.0008880869136191905, "entropy": 0.060068730264902115, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:09.966439Z", "loop": 10935, "env_steps": 6719078399, "loss": 0.011431454680860043, "avg_return": 0.8633807301521301, "regret": 0.0008880869136191905, "entropy": 0.06038782000541687, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:10.820590Z", "loop": 10936, "env_steps": 6719692799, "loss": 0.011686167679727077, "avg_return": 0.8634904026985168, "regret": 0.0008880869136191905, "entropy": 0.06406904757022858, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:11.676398Z", "loop": 10937, "env_steps": 6720307199, "loss": 0.011920074000954628, "avg_return": 0.8624735474586487, "regret": 0.0008880869136191905, "entropy": 0.06363770365715027, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:12.531040Z", "loop": 10938, "env_steps": 6720921599, "loss": 0.01121585350483656, "avg_return": 0.8638607263565063, "regret": 0.0008880869136191905, "entropy": 0.06212693825364113, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:13.385193Z", "loop": 10939, "env_steps": 6721535999, "loss": 0.01189910527318716, "avg_return": 0.8630894422531128, "regret": 0.0008880869136191905, "entropy": 0.06597401946783066, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:14.277592Z", "loop": 10940, "env_steps": 6722150399, "loss": 0.011988057754933834, "avg_return": 0.8635017275810242, "regret": 0.0003913475957233459, "entropy": 0.06296644359827042, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:15.132917Z", "loop": 10941, "env_steps": 6722764799, "loss": 0.010702752508223057, "avg_return": 0.8637434840202332, "regret": 0.0003913475957233459, "entropy": 0.06201482191681862, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:15.988200Z", "loop": 10942, "env_steps": 6723379199, "loss": 0.011626099236309528, "avg_return": 0.8638448119163513, "regret": 0.0003913475957233459, "entropy": 0.0655210018157959, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:16.843483Z", "loop": 10943, "env_steps": 6723993599, "loss": 0.012427626177668571, "avg_return": 0.8636490106582642, "regret": 0.0003913475957233459, "entropy": 0.06510955095291138, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:17.698734Z", "loop": 10944, "env_steps": 6724607999, "loss": 0.01195494458079338, "avg_return": 0.863997220993042, "regret": 0.0003913475957233459, "entropy": 0.06303853541612625, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:18.553400Z", "loop": 10945, "env_steps": 6725222399, "loss": 0.011533869430422783, "avg_return": 0.8637772798538208, "regret": 0.0003913475957233459, "entropy": 0.06107193976640701, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:19.408327Z", "loop": 10946, "env_steps": 6725836799, "loss": 0.012556328438222408, "avg_return": 0.8629131317138672, "regret": 0.0003913475957233459, "entropy": 0.06586267799139023, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:20.262185Z", "loop": 10947, "env_steps": 6726451199, "loss": 0.011320770718157291, "avg_return": 0.8639998435974121, "regret": 0.0003913475957233459, "entropy": 0.06241336464881897, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:21.116118Z", "loop": 10948, "env_steps": 6727065599, "loss": 0.012827917002141476, "avg_return": 0.8625247478485107, "regret": 0.0003913475957233459, "entropy": 0.06643062829971313, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:21.970725Z", "loop": 10949, "env_steps": 6727679999, "loss": 0.011287324130535126, "avg_return": 0.8635596036911011, "regret": 0.0003913475957233459, "entropy": 0.06409420073032379, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:22.862732Z", "loop": 10950, "env_steps": 6728294399, "loss": 0.012299816124141216, "avg_return": 0.8633356094360352, "regret": 0.00047587003791704774, "entropy": 0.06602123379707336, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:23.716990Z", "loop": 10951, "env_steps": 6728908799, "loss": 0.011971925385296345, "avg_return": 0.8630886077880859, "regret": 0.00047587003791704774, "entropy": 0.06623832881450653, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:24.571715Z", "loop": 10952, "env_steps": 6729523199, "loss": 0.013028182089328766, "avg_return": 0.8635215163230896, "regret": 0.00047587003791704774, "entropy": 0.06830904632806778, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:25.426781Z", "loop": 10953, "env_steps": 6730137599, "loss": 0.012865557335317135, "avg_return": 0.8618123531341553, "regret": 0.00047587003791704774, "entropy": 0.06855939328670502, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:26.281249Z", "loop": 10954, "env_steps": 6730751999, "loss": 0.010437073186039925, "avg_return": 0.8636756539344788, "regret": 0.00047587003791704774, "entropy": 0.06291984766721725, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:27.135620Z", "loop": 10955, "env_steps": 6731366399, "loss": 0.012436866760253906, "avg_return": 0.8638201951980591, "regret": 0.00047587003791704774, "entropy": 0.06754414737224579, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:27.990711Z", "loop": 10956, "env_steps": 6731980799, "loss": 0.01243415754288435, "avg_return": 0.8623056411743164, "regret": 0.00047587003791704774, "entropy": 0.0677129328250885, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:28.845668Z", "loop": 10957, "env_steps": 6732595199, "loss": 0.01243410911411047, "avg_return": 0.8616663813591003, "regret": 0.00047587003791704774, "entropy": 0.06856922805309296, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:29.699321Z", "loop": 10958, "env_steps": 6733209599, "loss": 0.012761766090989113, "avg_return": 0.8621184229850769, "regret": 0.00047587003791704774, "entropy": 0.07166086882352829, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:30.552753Z", "loop": 10959, "env_steps": 6733823999, "loss": 0.011680605821311474, "avg_return": 0.8610593676567078, "regret": 0.00047587003791704774, "entropy": 0.06641297042369843, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:31.445209Z", "loop": 10960, "env_steps": 6734438399, "loss": 0.013239162974059582, "avg_return": 0.8632678389549255, "regret": 0.000625906977802515, "entropy": 0.0682724341750145, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:32.299587Z", "loop": 10961, "env_steps": 6735052799, "loss": 0.01291468646377325, "avg_return": 0.8628381490707397, "regret": 0.000625906977802515, "entropy": 0.07134425640106201, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:33.153221Z", "loop": 10962, "env_steps": 6735667199, "loss": 0.012753183953464031, "avg_return": 0.8632385730743408, "regret": 0.000625906977802515, "entropy": 0.07033628225326538, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:34.007397Z", "loop": 10963, "env_steps": 6736281599, "loss": 0.011728473007678986, "avg_return": 0.8629150390625, "regret": 0.000625906977802515, "entropy": 0.06513768434524536, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:34.862054Z", "loop": 10964, "env_steps": 6736895999, "loss": 0.011462969705462456, "avg_return": 0.863115668296814, "regret": 0.000625906977802515, "entropy": 0.0683576837182045, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:35.716307Z", "loop": 10965, "env_steps": 6737510399, "loss": 0.013083775527775288, "avg_return": 0.8635583519935608, "regret": 0.000625906977802515, "entropy": 0.07093726098537445, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:36.571003Z", "loop": 10966, "env_steps": 6738124799, "loss": 0.012490890920162201, "avg_return": 0.8618837594985962, "regret": 0.000625906977802515, "entropy": 0.06699810922145844, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:37.424337Z", "loop": 10967, "env_steps": 6738739199, "loss": 0.012488910928368568, "avg_return": 0.8623501658439636, "regret": 0.000625906977802515, "entropy": 0.06862229108810425, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:38.278929Z", "loop": 10968, "env_steps": 6739353599, "loss": 0.013591989874839783, "avg_return": 0.8636418581008911, "regret": 0.000625906977802515, "entropy": 0.0705072358250618, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:39.132659Z", "loop": 10969, "env_steps": 6739967999, "loss": 0.013507160358130932, "avg_return": 0.8627265691757202, "regret": 0.000625906977802515, "entropy": 0.0715666189789772, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:40.026528Z", "loop": 10970, "env_steps": 6740582399, "loss": 0.012882493436336517, "avg_return": 0.8632102608680725, "regret": 0.0006634874735027552, "entropy": 0.07069499790668488, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:40.880762Z", "loop": 10971, "env_steps": 6741196799, "loss": 0.012491954490542412, "avg_return": 0.8630441427230835, "regret": 0.0006634874735027552, "entropy": 0.07026699930429459, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:41.734439Z", "loop": 10972, "env_steps": 6741811199, "loss": 0.013027026318013668, "avg_return": 0.8628538250923157, "regret": 0.0006634874735027552, "entropy": 0.07072404772043228, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:42.588774Z", "loop": 10973, "env_steps": 6742425599, "loss": 0.01255016215145588, "avg_return": 0.8630548119544983, "regret": 0.0006634874735027552, "entropy": 0.06950804591178894, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:43.442822Z", "loop": 10974, "env_steps": 6743039999, "loss": 0.012572159059345722, "avg_return": 0.8631011247634888, "regret": 0.0006634874735027552, "entropy": 0.07025815546512604, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:44.296434Z", "loop": 10975, "env_steps": 6743654399, "loss": 0.011820985935628414, "avg_return": 0.8631296753883362, "regret": 0.0006634874735027552, "entropy": 0.07027420401573181, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:45.149583Z", "loop": 10976, "env_steps": 6744268799, "loss": 0.013651114888489246, "avg_return": 0.8615762591362, "regret": 0.0006634874735027552, "entropy": 0.07627339661121368, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:46.003102Z", "loop": 10977, "env_steps": 6744883199, "loss": 0.013846173882484436, "avg_return": 0.8616616129875183, "regret": 0.0006634874735027552, "entropy": 0.07702916860580444, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:46.857698Z", "loop": 10978, "env_steps": 6745497599, "loss": 0.01467727031558752, "avg_return": 0.8623569011688232, "regret": 0.0006634874735027552, "entropy": 0.08099392801523209, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:47.713113Z", "loop": 10979, "env_steps": 6746111999, "loss": 0.014195146039128304, "avg_return": 0.8628352284431458, "regret": 0.0006634874735027552, "entropy": 0.07716114073991776, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:48.607782Z", "loop": 10980, "env_steps": 6746726399, "loss": 0.014767727814614773, "avg_return": 0.8612267374992371, "regret": 0.002500273287296295, "entropy": 0.08103406429290771, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:49.460354Z", "loop": 10981, "env_steps": 6747340799, "loss": 0.014880910515785217, "avg_return": 0.8608341813087463, "regret": 0.002500273287296295, "entropy": 0.0788566842675209, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:50.313405Z", "loop": 10982, "env_steps": 6747955199, "loss": 0.01535651832818985, "avg_return": 0.8619399070739746, "regret": 0.002500273287296295, "entropy": 0.08039654791355133, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:51.168739Z", "loop": 10983, "env_steps": 6748569599, "loss": 0.013283808715641499, "avg_return": 0.8638114333152771, "regret": 0.002500273287296295, "entropy": 0.0731484591960907, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:52.023521Z", "loop": 10984, "env_steps": 6749183999, "loss": 0.012679348699748516, "avg_return": 0.8630331754684448, "regret": 0.002500273287296295, "entropy": 0.07172742486000061, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:52.877021Z", "loop": 10985, "env_steps": 6749798399, "loss": 0.012376758269965649, "avg_return": 0.8633722066879272, "regret": 0.002500273287296295, "entropy": 0.06766297668218613, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:53.731065Z", "loop": 10986, "env_steps": 6750412799, "loss": 0.013072304427623749, "avg_return": 0.8655967116355896, "regret": 0.002500273287296295, "entropy": 0.07151652127504349, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:54.585991Z", "loop": 10987, "env_steps": 6751027199, "loss": 0.012211616151034832, "avg_return": 0.8635790944099426, "regret": 0.002500273287296295, "entropy": 0.06632718443870544, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:55.440982Z", "loop": 10988, "env_steps": 6751641599, "loss": 0.012783527374267578, "avg_return": 0.8621183633804321, "regret": 0.002500273287296295, "entropy": 0.06713460385799408, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:56.294478Z", "loop": 10989, "env_steps": 6752255999, "loss": 0.013166703283786774, "avg_return": 0.8640785813331604, "regret": 0.002500273287296295, "entropy": 0.07082690298557281, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:57.186590Z", "loop": 10990, "env_steps": 6752870399, "loss": 0.012038814835250378, "avg_return": 0.8623043298721313, "regret": 0.0001385994255542755, "entropy": 0.06873753666877747, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:58.041051Z", "loop": 10991, "env_steps": 6753484799, "loss": 0.012432210147380829, "avg_return": 0.8615900874137878, "regret": 0.0001385994255542755, "entropy": 0.06668364256620407, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:58.895801Z", "loop": 10992, "env_steps": 6754099199, "loss": 0.013855923898518085, "avg_return": 0.8627226948738098, "regret": 0.0001385994255542755, "entropy": 0.06885088980197906, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:00:59.749963Z", "loop": 10993, "env_steps": 6754713599, "loss": 0.01255839318037033, "avg_return": 0.8624697327613831, "regret": 0.0001385994255542755, "entropy": 0.06860187649726868, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:00.603420Z", "loop": 10994, "env_steps": 6755327999, "loss": 0.01240615826100111, "avg_return": 0.8641104102134705, "regret": 0.0001385994255542755, "entropy": 0.0660768672823906, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:01.457538Z", "loop": 10995, "env_steps": 6755942399, "loss": 0.012923411093652248, "avg_return": 0.8657856583595276, "regret": 0.0001385994255542755, "entropy": 0.07007351517677307, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:02.311861Z", "loop": 10996, "env_steps": 6756556799, "loss": 0.012283614836633205, "avg_return": 0.8635544776916504, "regret": 0.0001385994255542755, "entropy": 0.0670693889260292, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:03.166603Z", "loop": 10997, "env_steps": 6757171199, "loss": 0.01250587310642004, "avg_return": 0.8628702759742737, "regret": 0.0001385994255542755, "entropy": 0.06669971346855164, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:04.021122Z", "loop": 10998, "env_steps": 6757785599, "loss": 0.01225595735013485, "avg_return": 0.8630381226539612, "regret": 0.0001385994255542755, "entropy": 0.0689391940832138, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:04.876592Z", "loop": 10999, "env_steps": 6758399999, "loss": 0.013574103824794292, "avg_return": 0.8617215156555176, "regret": 0.0001385994255542755, "entropy": 0.07119086384773254, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:05.770470Z", "loop": 11000, "env_steps": 6759014399, "loss": 0.012560914270579815, "avg_return": 0.8636035323143005, "regret": 0.00017620933067519218, "entropy": 0.06869906187057495, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:06.625237Z", "loop": 11001, "env_steps": 6759628799, "loss": 0.013486943207681179, "avg_return": 0.863308310508728, "regret": 0.00017620933067519218, "entropy": 0.07194536179304123, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:07.478668Z", "loop": 11002, "env_steps": 6760243199, "loss": 0.012146328575909138, "avg_return": 0.8620071411132812, "regret": 0.00017620933067519218, "entropy": 0.06382998079061508, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:08.333040Z", "loop": 11003, "env_steps": 6760857599, "loss": 0.013453880324959755, "avg_return": 0.8627400994300842, "regret": 0.00017620933067519218, "entropy": 0.0716317817568779, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:09.186599Z", "loop": 11004, "env_steps": 6761471999, "loss": 0.013185669668018818, "avg_return": 0.8641100525856018, "regret": 0.00017620933067519218, "entropy": 0.07411714643239975, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:10.040758Z", "loop": 11005, "env_steps": 6762086399, "loss": 0.012787672691047192, "avg_return": 0.86481773853302, "regret": 0.00017620933067519218, "entropy": 0.06825900077819824, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:10.895055Z", "loop": 11006, "env_steps": 6762700799, "loss": 0.01340775191783905, "avg_return": 0.8626880049705505, "regret": 0.00017620933067519218, "entropy": 0.07124573737382889, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:11.749454Z", "loop": 11007, "env_steps": 6763315199, "loss": 0.013699091039597988, "avg_return": 0.8635551333427429, "regret": 0.00017620933067519218, "entropy": 0.07291968166828156, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:12.602540Z", "loop": 11008, "env_steps": 6763929599, "loss": 0.01399405486881733, "avg_return": 0.863268256187439, "regret": 0.00017620933067519218, "entropy": 0.07490821182727814, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:13.456016Z", "loop": 11009, "env_steps": 6764543999, "loss": 0.01568293757736683, "avg_return": 0.8641766309738159, "regret": 0.00017620933067519218, "entropy": 0.0763825848698616, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:14.348885Z", "loop": 11010, "env_steps": 6765158399, "loss": 0.015480960719287395, "avg_return": 0.863020658493042, "regret": 0.00032330528483726084, "entropy": 0.07842252403497696, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:15.202708Z", "loop": 11011, "env_steps": 6765772799, "loss": 0.014821857213973999, "avg_return": 0.8633257150650024, "regret": 0.00032330528483726084, "entropy": 0.0797058492898941, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:16.057203Z", "loop": 11012, "env_steps": 6766387199, "loss": 0.014296633191406727, "avg_return": 0.8608630299568176, "regret": 0.00032330528483726084, "entropy": 0.07807585597038269, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:16.911030Z", "loop": 11013, "env_steps": 6767001599, "loss": 0.015577579848468304, "avg_return": 0.8634365200996399, "regret": 0.00032330528483726084, "entropy": 0.08071395754814148, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:17.766327Z", "loop": 11014, "env_steps": 6767615999, "loss": 0.014819078147411346, "avg_return": 0.8635038733482361, "regret": 0.00032330528483726084, "entropy": 0.0774388536810875, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:18.622333Z", "loop": 11015, "env_steps": 6768230399, "loss": 0.016109412536025047, "avg_return": 0.8635396361351013, "regret": 0.00032330528483726084, "entropy": 0.08479155600070953, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:19.478638Z", "loop": 11016, "env_steps": 6768844799, "loss": 0.015076442621648312, "avg_return": 0.8622898459434509, "regret": 0.00032330528483726084, "entropy": 0.08258344233036041, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:20.333586Z", "loop": 11017, "env_steps": 6769459199, "loss": 0.015707487240433693, "avg_return": 0.8638888001441956, "regret": 0.00032330528483726084, "entropy": 0.08282578736543655, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:21.189351Z", "loop": 11018, "env_steps": 6770073599, "loss": 0.015534721314907074, "avg_return": 0.8621402978897095, "regret": 0.00032330528483726084, "entropy": 0.08112995326519012, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:22.045625Z", "loop": 11019, "env_steps": 6770687999, "loss": 0.017749182879924774, "avg_return": 0.8591842651367188, "regret": 0.00032330528483726084, "entropy": 0.08587618172168732, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:22.939746Z", "loop": 11020, "env_steps": 6771302399, "loss": 0.0159610603004694, "avg_return": 0.8608002066612244, "regret": 0.002792775398120284, "entropy": 0.08236385881900787, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:23.793911Z", "loop": 11021, "env_steps": 6771916799, "loss": 0.016066065058112144, "avg_return": 0.8607377409934998, "regret": 0.002792775398120284, "entropy": 0.08653734624385834, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:24.649549Z", "loop": 11022, "env_steps": 6772531199, "loss": 0.01715012453496456, "avg_return": 0.8595979809761047, "regret": 0.002792775398120284, "entropy": 0.08637598901987076, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:25.505237Z", "loop": 11023, "env_steps": 6773145599, "loss": 0.01669914834201336, "avg_return": 0.8609362840652466, "regret": 0.002792775398120284, "entropy": 0.08421093225479126, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:26.359372Z", "loop": 11024, "env_steps": 6773759999, "loss": 0.016884183511137962, "avg_return": 0.8598549365997314, "regret": 0.002792775398120284, "entropy": 0.09146761149168015, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:27.214004Z", "loop": 11025, "env_steps": 6774374399, "loss": 0.015763014554977417, "avg_return": 0.8614874482154846, "regret": 0.002792775398120284, "entropy": 0.08445113152265549, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:28.067877Z", "loop": 11026, "env_steps": 6774988799, "loss": 0.017546147108078003, "avg_return": 0.8639388084411621, "regret": 0.002792775398120284, "entropy": 0.08942440152168274, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:28.922867Z", "loop": 11027, "env_steps": 6775603199, "loss": 0.015665149316191673, "avg_return": 0.8615891933441162, "regret": 0.002792775398120284, "entropy": 0.08215054124593735, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:29.776582Z", "loop": 11028, "env_steps": 6776217599, "loss": 0.01691586710512638, "avg_return": 0.8625834584236145, "regret": 0.002792775398120284, "entropy": 0.08654308319091797, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:30.631094Z", "loop": 11029, "env_steps": 6776831999, "loss": 0.016454285010695457, "avg_return": 0.8625574707984924, "regret": 0.002792775398120284, "entropy": 0.08521892875432968, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:31.524338Z", "loop": 11030, "env_steps": 6777446399, "loss": 0.01621079258620739, "avg_return": 0.8629559278488159, "regret": 0.0005287756212055683, "entropy": 0.0841783881187439, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:32.378788Z", "loop": 11031, "env_steps": 6778060799, "loss": 0.014974350109696388, "avg_return": 0.8614144325256348, "regret": 0.0005287756212055683, "entropy": 0.08026812970638275, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:33.233028Z", "loop": 11032, "env_steps": 6778675199, "loss": 0.014797493815422058, "avg_return": 0.8638983368873596, "regret": 0.0005287756212055683, "entropy": 0.07928051799535751, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:34.087275Z", "loop": 11033, "env_steps": 6779289599, "loss": 0.015177549794316292, "avg_return": 0.8635870814323425, "regret": 0.0005287756212055683, "entropy": 0.08086316287517548, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:34.942292Z", "loop": 11034, "env_steps": 6779903999, "loss": 0.016499090939760208, "avg_return": 0.8616066575050354, "regret": 0.0005287756212055683, "entropy": 0.08308455348014832, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:35.795431Z", "loop": 11035, "env_steps": 6780518399, "loss": 0.015413484536111355, "avg_return": 0.8618833422660828, "regret": 0.0005287756212055683, "entropy": 0.08452994376420975, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:36.648773Z", "loop": 11036, "env_steps": 6781132799, "loss": 0.015512785874307156, "avg_return": 0.862518846988678, "regret": 0.0005287756212055683, "entropy": 0.08139607310295105, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:37.503161Z", "loop": 11037, "env_steps": 6781747199, "loss": 0.01576772890985012, "avg_return": 0.8635355830192566, "regret": 0.0005287756212055683, "entropy": 0.08364123106002808, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:38.358427Z", "loop": 11038, "env_steps": 6782361599, "loss": 0.01531239878386259, "avg_return": 0.8601304292678833, "regret": 0.0005287756212055683, "entropy": 0.08169461041688919, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:39.212776Z", "loop": 11039, "env_steps": 6782975999, "loss": 0.015927981585264206, "avg_return": 0.8633939027786255, "regret": 0.0005287756212055683, "entropy": 0.08311504125595093, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:40.105470Z", "loop": 11040, "env_steps": 6783590399, "loss": 0.015765411779284477, "avg_return": 0.862327516078949, "regret": 0.0007452034624293447, "entropy": 0.07942996919155121, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:40.958932Z", "loop": 11041, "env_steps": 6784204799, "loss": 0.01508913654834032, "avg_return": 0.8636999726295471, "regret": 0.0007452034624293447, "entropy": 0.0770740732550621, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:41.814165Z", "loop": 11042, "env_steps": 6784819199, "loss": 0.013443062081933022, "avg_return": 0.8623573780059814, "regret": 0.0007452034624293447, "entropy": 0.07279938459396362, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:42.669104Z", "loop": 11043, "env_steps": 6785433599, "loss": 0.013418564572930336, "avg_return": 0.8629968762397766, "regret": 0.0007452034624293447, "entropy": 0.07048875093460083, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:43.523365Z", "loop": 11044, "env_steps": 6786047999, "loss": 0.012629340402781963, "avg_return": 0.863825798034668, "regret": 0.0007452034624293447, "entropy": 0.06338173896074295, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:44.377551Z", "loop": 11045, "env_steps": 6786662399, "loss": 0.012772740796208382, "avg_return": 0.8627474308013916, "regret": 0.0007452034624293447, "entropy": 0.06633895635604858, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:45.232610Z", "loop": 11046, "env_steps": 6787276799, "loss": 0.012126576155424118, "avg_return": 0.8627797365188599, "regret": 0.0007452034624293447, "entropy": 0.06180322542786598, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:46.087928Z", "loop": 11047, "env_steps": 6787891199, "loss": 0.012985552661120892, "avg_return": 0.8639176487922668, "regret": 0.0007452034624293447, "entropy": 0.06854656338691711, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:46.942976Z", "loop": 11048, "env_steps": 6788505599, "loss": 0.012030995450913906, "avg_return": 0.8627952337265015, "regret": 0.0007452034624293447, "entropy": 0.06809384375810623, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:47.796947Z", "loop": 11049, "env_steps": 6789119999, "loss": 0.012596920132637024, "avg_return": 0.8638967871665955, "regret": 0.0007452034624293447, "entropy": 0.06654899567365646, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:48.690214Z", "loop": 11050, "env_steps": 6789734399, "loss": 0.013735808432102203, "avg_return": 0.864604115486145, "regret": 0.00013526486873161048, "entropy": 0.07102399319410324, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:49.544262Z", "loop": 11051, "env_steps": 6790348799, "loss": 0.013678225688636303, "avg_return": 0.8638930320739746, "regret": 0.00013526486873161048, "entropy": 0.06993618607521057, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:50.398983Z", "loop": 11052, "env_steps": 6790963199, "loss": 0.013791853561997414, "avg_return": 0.8638057708740234, "regret": 0.00013526486873161048, "entropy": 0.06946072727441788, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:51.252411Z", "loop": 11053, "env_steps": 6791577599, "loss": 0.012353559024631977, "avg_return": 0.8649352192878723, "regret": 0.00013526486873161048, "entropy": 0.06526152044534683, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:52.106646Z", "loop": 11054, "env_steps": 6792191999, "loss": 0.012441598810255527, "avg_return": 0.8631451725959778, "regret": 0.00013526486873161048, "entropy": 0.06626331806182861, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:52.961740Z", "loop": 11055, "env_steps": 6792806399, "loss": 0.013798526488244534, "avg_return": 0.8624131679534912, "regret": 0.00013526486873161048, "entropy": 0.07045581191778183, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:53.817027Z", "loop": 11056, "env_steps": 6793420799, "loss": 0.013116803951561451, "avg_return": 0.8640507459640503, "regret": 0.00013526486873161048, "entropy": 0.06739608943462372, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:54.670713Z", "loop": 11057, "env_steps": 6794035199, "loss": 0.012795999646186829, "avg_return": 0.8624554872512817, "regret": 0.00013526486873161048, "entropy": 0.06759743392467499, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:55.524394Z", "loop": 11058, "env_steps": 6794649599, "loss": 0.013384168036282063, "avg_return": 0.86283278465271, "regret": 0.00013526486873161048, "entropy": 0.06738483160734177, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:56.377904Z", "loop": 11059, "env_steps": 6795263999, "loss": 0.012737572193145752, "avg_return": 0.8615419864654541, "regret": 0.00013526486873161048, "entropy": 0.07129831612110138, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:57.271894Z", "loop": 11060, "env_steps": 6795878399, "loss": 0.01373261958360672, "avg_return": 0.8626314401626587, "regret": 0.0017943474231287837, "entropy": 0.07442297041416168, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:58.126299Z", "loop": 11061, "env_steps": 6796492799, "loss": 0.014400563202798367, "avg_return": 0.8602048754692078, "regret": 0.0017943474231287837, "entropy": 0.07398297637701035, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:58.980241Z", "loop": 11062, "env_steps": 6797107199, "loss": 0.014114759862422943, "avg_return": 0.8583394289016724, "regret": 0.0017943474231287837, "entropy": 0.07283036410808563, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:01:59.834400Z", "loop": 11063, "env_steps": 6797721599, "loss": 0.015256437472999096, "avg_return": 0.8559204339981079, "regret": 0.0017943474231287837, "entropy": 0.07585106045007706, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:00.688753Z", "loop": 11064, "env_steps": 6798335999, "loss": 0.013573357835412025, "avg_return": 0.8581816554069519, "regret": 0.0017943474231287837, "entropy": 0.0758211687207222, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:01.543662Z", "loop": 11065, "env_steps": 6798950399, "loss": 0.01455379743129015, "avg_return": 0.8601399660110474, "regret": 0.0017943474231287837, "entropy": 0.07610596716403961, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:02.398041Z", "loop": 11066, "env_steps": 6799564799, "loss": 0.014588810503482819, "avg_return": 0.8621019721031189, "regret": 0.0017943474231287837, "entropy": 0.07281781733036041, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:03.251257Z", "loop": 11067, "env_steps": 6800179199, "loss": 0.012678905390202999, "avg_return": 0.8630707263946533, "regret": 0.0017943474231287837, "entropy": 0.06660196930170059, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:04.104630Z", "loop": 11068, "env_steps": 6800793599, "loss": 0.012634244747459888, "avg_return": 0.863288164138794, "regret": 0.0017943474231287837, "entropy": 0.06820902228355408, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:04.959624Z", "loop": 11069, "env_steps": 6801407999, "loss": 0.012973572127521038, "avg_return": 0.8639062643051147, "regret": 0.0017943474231287837, "entropy": 0.07274355739355087, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:05.851613Z", "loop": 11070, "env_steps": 6802022399, "loss": 0.013176783919334412, "avg_return": 0.8644106388092041, "regret": 0.0002913002099376172, "entropy": 0.06981758028268814, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:06.706295Z", "loop": 11071, "env_steps": 6802636799, "loss": 0.012674974277615547, "avg_return": 0.8627317547798157, "regret": 0.0002913002099376172, "entropy": 0.06818266957998276, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:07.560983Z", "loop": 11072, "env_steps": 6803251199, "loss": 0.013130766339600086, "avg_return": 0.8648026585578918, "regret": 0.0002913002099376172, "entropy": 0.0714765265583992, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:08.417153Z", "loop": 11073, "env_steps": 6803865599, "loss": 0.012764425948262215, "avg_return": 0.863454282283783, "regret": 0.0002913002099376172, "entropy": 0.06720619648694992, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:09.271693Z", "loop": 11074, "env_steps": 6804479999, "loss": 0.013671877793967724, "avg_return": 0.8624461889266968, "regret": 0.0002913002099376172, "entropy": 0.07586980611085892, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:10.125432Z", "loop": 11075, "env_steps": 6805094399, "loss": 0.013614237308502197, "avg_return": 0.8636367917060852, "regret": 0.0002913002099376172, "entropy": 0.07044288516044617, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:10.979396Z", "loop": 11076, "env_steps": 6805708799, "loss": 0.014184410683810711, "avg_return": 0.8634633421897888, "regret": 0.0002913002099376172, "entropy": 0.07460278272628784, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:11.833923Z", "loop": 11077, "env_steps": 6806323199, "loss": 0.013847152702510357, "avg_return": 0.8639111518859863, "regret": 0.0002913002099376172, "entropy": 0.07216402888298035, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:12.688872Z", "loop": 11078, "env_steps": 6806937599, "loss": 0.01479379739612341, "avg_return": 0.8622080683708191, "regret": 0.0002913002099376172, "entropy": 0.07516656070947647, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:13.542955Z", "loop": 11079, "env_steps": 6807551999, "loss": 0.014635338447988033, "avg_return": 0.8632586002349854, "regret": 0.0002913002099376172, "entropy": 0.0797138586640358, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:14.436165Z", "loop": 11080, "env_steps": 6808166399, "loss": 0.015564545057713985, "avg_return": 0.8636472821235657, "regret": 0.0001870642154244706, "entropy": 0.07820070534944534, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:15.291727Z", "loop": 11081, "env_steps": 6808780799, "loss": 0.013971695676445961, "avg_return": 0.8624318838119507, "regret": 0.0001870642154244706, "entropy": 0.07414562255144119, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:16.146095Z", "loop": 11082, "env_steps": 6809395199, "loss": 0.014311554841697216, "avg_return": 0.8624882102012634, "regret": 0.0001870642154244706, "entropy": 0.07300468534231186, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:17.000149Z", "loop": 11083, "env_steps": 6810009599, "loss": 0.015555855818092823, "avg_return": 0.8638866543769836, "regret": 0.0001870642154244706, "entropy": 0.08193735033273697, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:17.854901Z", "loop": 11084, "env_steps": 6810623999, "loss": 0.016304640099406242, "avg_return": 0.8634248971939087, "regret": 0.0001870642154244706, "entropy": 0.08151537925004959, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:18.709672Z", "loop": 11085, "env_steps": 6811238399, "loss": 0.01570822484791279, "avg_return": 0.8629041910171509, "regret": 0.0001870642154244706, "entropy": 0.08310475945472717, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:19.564067Z", "loop": 11086, "env_steps": 6811852799, "loss": 0.014808468520641327, "avg_return": 0.8640989661216736, "regret": 0.0001870642154244706, "entropy": 0.0806087851524353, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:20.419884Z", "loop": 11087, "env_steps": 6812467199, "loss": 0.01481711771339178, "avg_return": 0.8631622791290283, "regret": 0.0001870642154244706, "entropy": 0.07780317217111588, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:21.274579Z", "loop": 11088, "env_steps": 6813081599, "loss": 0.01748797670006752, "avg_return": 0.8629864454269409, "regret": 0.0001870642154244706, "entropy": 0.0915539488196373, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:22.130113Z", "loop": 11089, "env_steps": 6813695999, "loss": 0.016975045204162598, "avg_return": 0.8623695969581604, "regret": 0.0001870642154244706, "entropy": 0.08626947551965714, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:23.026816Z", "loop": 11090, "env_steps": 6814310399, "loss": 0.01686066947877407, "avg_return": 0.8637490272521973, "regret": 0.0006560856709256768, "entropy": 0.08528167754411697, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:23.881409Z", "loop": 11091, "env_steps": 6814924799, "loss": 0.016404060646891594, "avg_return": 0.8624870777130127, "regret": 0.0006560856709256768, "entropy": 0.0860922709107399, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:24.735420Z", "loop": 11092, "env_steps": 6815539199, "loss": 0.017489604651927948, "avg_return": 0.8638303875923157, "regret": 0.0006560856709256768, "entropy": 0.08929149806499481, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:25.590199Z", "loop": 11093, "env_steps": 6816153599, "loss": 0.017314279451966286, "avg_return": 0.8615041375160217, "regret": 0.0006560856709256768, "entropy": 0.09173525869846344, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:26.444788Z", "loop": 11094, "env_steps": 6816767999, "loss": 0.016760852187871933, "avg_return": 0.8612490892410278, "regret": 0.0006560856709256768, "entropy": 0.0878637358546257, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:27.299407Z", "loop": 11095, "env_steps": 6817382399, "loss": 0.016140632331371307, "avg_return": 0.8615004420280457, "regret": 0.0006560856709256768, "entropy": 0.08687122911214828, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:28.155058Z", "loop": 11096, "env_steps": 6817996799, "loss": 0.01673978380858898, "avg_return": 0.8623903393745422, "regret": 0.0006560856709256768, "entropy": 0.08736345171928406, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:29.010574Z", "loop": 11097, "env_steps": 6818611199, "loss": 0.014287213794887066, "avg_return": 0.8618038296699524, "regret": 0.0006560856709256768, "entropy": 0.07600215822458267, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:29.865484Z", "loop": 11098, "env_steps": 6819225599, "loss": 0.013848714530467987, "avg_return": 0.8608678579330444, "regret": 0.0006560856709256768, "entropy": 0.07615243643522263, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:30.720287Z", "loop": 11099, "env_steps": 6819839999, "loss": 0.013560025952756405, "avg_return": 0.8623937368392944, "regret": 0.0006560856709256768, "entropy": 0.07355325669050217, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:31.617640Z", "loop": 11100, "env_steps": 6820454399, "loss": 0.013321392238140106, "avg_return": 0.8621781468391418, "regret": 0.0005937537061981857, "entropy": 0.074801504611969, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:32.472864Z", "loop": 11101, "env_steps": 6821068799, "loss": 0.013311381451785564, "avg_return": 0.8636824488639832, "regret": 0.0005937537061981857, "entropy": 0.07354326546192169, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:33.327475Z", "loop": 11102, "env_steps": 6821683199, "loss": 0.014367016032338142, "avg_return": 0.863660991191864, "regret": 0.0005937537061981857, "entropy": 0.0774463340640068, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:34.181623Z", "loop": 11103, "env_steps": 6822297599, "loss": 0.013780111446976662, "avg_return": 0.8640814423561096, "regret": 0.0005937537061981857, "entropy": 0.07602360099554062, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:35.035310Z", "loop": 11104, "env_steps": 6822911999, "loss": 0.013953310437500477, "avg_return": 0.8629645109176636, "regret": 0.0005937537061981857, "entropy": 0.07245656102895737, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:35.890809Z", "loop": 11105, "env_steps": 6823526399, "loss": 0.012364004738628864, "avg_return": 0.864254355430603, "regret": 0.0005937537061981857, "entropy": 0.07102834433317184, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:36.747206Z", "loop": 11106, "env_steps": 6824140799, "loss": 0.013311236165463924, "avg_return": 0.8621693253517151, "regret": 0.0005937537061981857, "entropy": 0.07231751084327698, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:37.601077Z", "loop": 11107, "env_steps": 6824755199, "loss": 0.013688414357602596, "avg_return": 0.8614889979362488, "regret": 0.0005937537061981857, "entropy": 0.07254499197006226, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:38.454484Z", "loop": 11108, "env_steps": 6825369599, "loss": 0.012714579701423645, "avg_return": 0.8635016083717346, "regret": 0.0005937537061981857, "entropy": 0.07166913896799088, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:39.309638Z", "loop": 11109, "env_steps": 6825983999, "loss": 0.014371024444699287, "avg_return": 0.8638797998428345, "regret": 0.0005937537061981857, "entropy": 0.07710673660039902, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:40.202033Z", "loop": 11110, "env_steps": 6826598399, "loss": 0.012923474423587322, "avg_return": 0.8623816967010498, "regret": 0.0010388060472905636, "entropy": 0.07133036851882935, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:41.056294Z", "loop": 11111, "env_steps": 6827212799, "loss": 0.014071415178477764, "avg_return": 0.8621681928634644, "regret": 0.0010388060472905636, "entropy": 0.07721132040023804, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:41.910145Z", "loop": 11112, "env_steps": 6827827199, "loss": 0.014588450081646442, "avg_return": 0.8608580827713013, "regret": 0.0010388060472905636, "entropy": 0.08221801370382309, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:42.765428Z", "loop": 11113, "env_steps": 6828441599, "loss": 0.014270021580159664, "avg_return": 0.8609350919723511, "regret": 0.0010388060472905636, "entropy": 0.07924675196409225, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:43.619862Z", "loop": 11114, "env_steps": 6829055999, "loss": 0.014343983493745327, "avg_return": 0.860084056854248, "regret": 0.0010388060472905636, "entropy": 0.07955309748649597, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:44.474451Z", "loop": 11115, "env_steps": 6829670399, "loss": 0.014142552390694618, "avg_return": 0.8599357008934021, "regret": 0.0010388060472905636, "entropy": 0.07718268036842346, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:45.328492Z", "loop": 11116, "env_steps": 6830284799, "loss": 0.014025205746293068, "avg_return": 0.8614703416824341, "regret": 0.0010388060472905636, "entropy": 0.07660002261400223, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:46.181807Z", "loop": 11117, "env_steps": 6830899199, "loss": 0.013715236447751522, "avg_return": 0.8621137738227844, "regret": 0.0010388060472905636, "entropy": 0.07238540053367615, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:47.035784Z", "loop": 11118, "env_steps": 6831513599, "loss": 0.013432313688099384, "avg_return": 0.8622125387191772, "regret": 0.0010388060472905636, "entropy": 0.07578286528587341, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:47.889886Z", "loop": 11119, "env_steps": 6832127999, "loss": 0.01265474408864975, "avg_return": 0.8635214567184448, "regret": 0.0010388060472905636, "entropy": 0.07251901924610138, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:48.784394Z", "loop": 11120, "env_steps": 6832742399, "loss": 0.01288820244371891, "avg_return": 0.8639729022979736, "regret": 0.0006040958687663078, "entropy": 0.0714385062456131, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:49.637555Z", "loop": 11121, "env_steps": 6833356799, "loss": 0.013685332611203194, "avg_return": 0.8623701930046082, "regret": 0.0006040958687663078, "entropy": 0.07172606140375137, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:50.491313Z", "loop": 11122, "env_steps": 6833971199, "loss": 0.012710942886769772, "avg_return": 0.8637346625328064, "regret": 0.0006040958687663078, "entropy": 0.06980746239423752, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:51.345676Z", "loop": 11123, "env_steps": 6834585599, "loss": 0.01239061914384365, "avg_return": 0.8628440499305725, "regret": 0.0006040958687663078, "entropy": 0.06837484240531921, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:52.200256Z", "loop": 11124, "env_steps": 6835199999, "loss": 0.013594696298241615, "avg_return": 0.8633574843406677, "regret": 0.0006040958687663078, "entropy": 0.07033465057611465, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:53.054136Z", "loop": 11125, "env_steps": 6835814399, "loss": 0.012929985299706459, "avg_return": 0.8624807000160217, "regret": 0.0006040958687663078, "entropy": 0.07087916135787964, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:53.906432Z", "loop": 11126, "env_steps": 6836428799, "loss": 0.013346140272915363, "avg_return": 0.8630110621452332, "regret": 0.0006040958687663078, "entropy": 0.07367457449436188, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:54.759654Z", "loop": 11127, "env_steps": 6837043199, "loss": 0.015070676803588867, "avg_return": 0.8623930811882019, "regret": 0.0006040958687663078, "entropy": 0.07865174859762192, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:55.614592Z", "loop": 11128, "env_steps": 6837657599, "loss": 0.013998063281178474, "avg_return": 0.8628196120262146, "regret": 0.0006040958687663078, "entropy": 0.07366422563791275, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:56.468523Z", "loop": 11129, "env_steps": 6838271999, "loss": 0.014057615771889687, "avg_return": 0.8616184592247009, "regret": 0.0006040958687663078, "entropy": 0.07477033883333206, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:57.362017Z", "loop": 11130, "env_steps": 6838886399, "loss": 0.012997972778975964, "avg_return": 0.8612024188041687, "regret": 0.001902223564684391, "entropy": 0.0704597756266594, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:58.215313Z", "loop": 11131, "env_steps": 6839500799, "loss": 0.01563856191933155, "avg_return": 0.8596077561378479, "regret": 0.001902223564684391, "entropy": 0.0827646479010582, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:59.069798Z", "loop": 11132, "env_steps": 6840115199, "loss": 0.015845950692892075, "avg_return": 0.8622768521308899, "regret": 0.001902223564684391, "entropy": 0.08292289078235626, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:02:59.923506Z", "loop": 11133, "env_steps": 6840729599, "loss": 0.014148570597171783, "avg_return": 0.8618177771568298, "regret": 0.001902223564684391, "entropy": 0.07469462603330612, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:00.777361Z", "loop": 11134, "env_steps": 6841343999, "loss": 0.013763772323727608, "avg_return": 0.861992597579956, "regret": 0.001902223564684391, "entropy": 0.07431476563215256, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:01.631370Z", "loop": 11135, "env_steps": 6841958399, "loss": 0.013864921405911446, "avg_return": 0.8618471622467041, "regret": 0.001902223564684391, "entropy": 0.0742163360118866, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:02.485120Z", "loop": 11136, "env_steps": 6842572799, "loss": 0.013801432214677334, "avg_return": 0.8627409934997559, "regret": 0.001902223564684391, "entropy": 0.06931676715612411, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:03.338999Z", "loop": 11137, "env_steps": 6843187199, "loss": 0.013587518595159054, "avg_return": 0.8618398308753967, "regret": 0.001902223564684391, "entropy": 0.07181499898433685, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:04.193106Z", "loop": 11138, "env_steps": 6843801599, "loss": 0.01365968119353056, "avg_return": 0.863595724105835, "regret": 0.001902223564684391, "entropy": 0.07390766590833664, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:05.047131Z", "loop": 11139, "env_steps": 6844415999, "loss": 0.012101218104362488, "avg_return": 0.8644421696662903, "regret": 0.001902223564684391, "entropy": 0.06980347633361816, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:05.939208Z", "loop": 11140, "env_steps": 6845030399, "loss": 0.013364776037633419, "avg_return": 0.8641343116760254, "regret": 0.0003451357188168913, "entropy": 0.07402405887842178, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:06.793173Z", "loop": 11141, "env_steps": 6845644799, "loss": 0.013525131158530712, "avg_return": 0.8651288151741028, "regret": 0.0003451357188168913, "entropy": 0.07514156401157379, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:07.647304Z", "loop": 11142, "env_steps": 6846259199, "loss": 0.012281895615160465, "avg_return": 0.8626623749732971, "regret": 0.0003451357188168913, "entropy": 0.07066750526428223, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:08.501589Z", "loop": 11143, "env_steps": 6846873599, "loss": 0.01286367792636156, "avg_return": 0.8627368211746216, "regret": 0.0003451357188168913, "entropy": 0.07109065353870392, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:09.355861Z", "loop": 11144, "env_steps": 6847487999, "loss": 0.012912166304886341, "avg_return": 0.861945629119873, "regret": 0.0003451357188168913, "entropy": 0.07059858739376068, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:10.209947Z", "loop": 11145, "env_steps": 6848102399, "loss": 0.01312988717108965, "avg_return": 0.8639099597930908, "regret": 0.0003451357188168913, "entropy": 0.07283154129981995, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:11.064722Z", "loop": 11146, "env_steps": 6848716799, "loss": 0.012575226835906506, "avg_return": 0.8632923364639282, "regret": 0.0003451357188168913, "entropy": 0.06948959082365036, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:11.919200Z", "loop": 11147, "env_steps": 6849331199, "loss": 0.012027382850646973, "avg_return": 0.8622859716415405, "regret": 0.0003451357188168913, "entropy": 0.06897687911987305, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:12.773971Z", "loop": 11148, "env_steps": 6849945599, "loss": 0.013095383532345295, "avg_return": 0.862174391746521, "regret": 0.0003451357188168913, "entropy": 0.07224136590957642, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:13.628105Z", "loop": 11149, "env_steps": 6850559999, "loss": 0.011660581454634666, "avg_return": 0.8605916500091553, "regret": 0.0003451357188168913, "entropy": 0.06650050729513168, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:14.521435Z", "loop": 11150, "env_steps": 6851174399, "loss": 0.013315831311047077, "avg_return": 0.8620298504829407, "regret": 0.0025485316291451454, "entropy": 0.07216428220272064, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:15.374527Z", "loop": 11151, "env_steps": 6851788799, "loss": 0.013554470613598824, "avg_return": 0.8616682291030884, "regret": 0.0025485316291451454, "entropy": 0.07232553511857986, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:16.230207Z", "loop": 11152, "env_steps": 6852403199, "loss": 0.014653518795967102, "avg_return": 0.8609195351600647, "regret": 0.0025485316291451454, "entropy": 0.07571009546518326, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:17.083821Z", "loop": 11153, "env_steps": 6853017599, "loss": 0.014330754056572914, "avg_return": 0.8619228601455688, "regret": 0.0025485316291451454, "entropy": 0.07576976716518402, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:17.936686Z", "loop": 11154, "env_steps": 6853631999, "loss": 0.013497265055775642, "avg_return": 0.8604923486709595, "regret": 0.0025485316291451454, "entropy": 0.07235840708017349, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:18.790847Z", "loop": 11155, "env_steps": 6854246399, "loss": 0.014101939275860786, "avg_return": 0.8602160811424255, "regret": 0.0025485316291451454, "entropy": 0.07583238184452057, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:19.645212Z", "loop": 11156, "env_steps": 6854860799, "loss": 0.013832774944603443, "avg_return": 0.8604596257209778, "regret": 0.0025485316291451454, "entropy": 0.07502561062574387, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:20.499452Z", "loop": 11157, "env_steps": 6855475199, "loss": 0.01368655264377594, "avg_return": 0.8610419034957886, "regret": 0.0025485316291451454, "entropy": 0.07771650701761246, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:21.352764Z", "loop": 11158, "env_steps": 6856089599, "loss": 0.014159244485199451, "avg_return": 0.8622925877571106, "regret": 0.0025485316291451454, "entropy": 0.07020368427038193, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:22.206583Z", "loop": 11159, "env_steps": 6856703999, "loss": 0.014156344346702099, "avg_return": 0.861703097820282, "regret": 0.0025485316291451454, "entropy": 0.07399757206439972, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:23.098866Z", "loop": 11160, "env_steps": 6857318399, "loss": 0.014193549752235413, "avg_return": 0.8637343645095825, "regret": 0.0013330315705388784, "entropy": 0.07522251456975937, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:23.953447Z", "loop": 11161, "env_steps": 6857932799, "loss": 0.014386223629117012, "avg_return": 0.8614529371261597, "regret": 0.0013330315705388784, "entropy": 0.07538772374391556, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:24.806736Z", "loop": 11162, "env_steps": 6858547199, "loss": 0.014153524301946163, "avg_return": 0.862023115158081, "regret": 0.0013330315705388784, "entropy": 0.07962104678153992, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:25.660154Z", "loop": 11163, "env_steps": 6859161599, "loss": 0.01584049127995968, "avg_return": 0.8622581362724304, "regret": 0.0013330315705388784, "entropy": 0.08134866505861282, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:26.514562Z", "loop": 11164, "env_steps": 6859775999, "loss": 0.015772243961691856, "avg_return": 0.8607403039932251, "regret": 0.0013330315705388784, "entropy": 0.07982856780290604, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:27.368758Z", "loop": 11165, "env_steps": 6860390399, "loss": 0.014893295243382454, "avg_return": 0.8622052073478699, "regret": 0.0013330315705388784, "entropy": 0.08250997215509415, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:28.222368Z", "loop": 11166, "env_steps": 6861004799, "loss": 0.015988333150744438, "avg_return": 0.8617221117019653, "regret": 0.0013330315705388784, "entropy": 0.08598033338785172, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:29.076088Z", "loop": 11167, "env_steps": 6861619199, "loss": 0.01611883006989956, "avg_return": 0.862657904624939, "regret": 0.0013330315705388784, "entropy": 0.08255694806575775, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:29.929687Z", "loop": 11168, "env_steps": 6862233599, "loss": 0.016031334176659584, "avg_return": 0.8617329001426697, "regret": 0.0013330315705388784, "entropy": 0.08334416151046753, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:30.783939Z", "loop": 11169, "env_steps": 6862847999, "loss": 0.016274189576506615, "avg_return": 0.8633652925491333, "regret": 0.0013330315705388784, "entropy": 0.08743302524089813, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:31.676825Z", "loop": 11170, "env_steps": 6863462399, "loss": 0.015762798488140106, "avg_return": 0.86357182264328, "regret": 0.0012728782603517175, "entropy": 0.08279351145029068, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:32.530380Z", "loop": 11171, "env_steps": 6864076799, "loss": 0.014980100095272064, "avg_return": 0.8622764348983765, "regret": 0.0012728782603517175, "entropy": 0.08054226636886597, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:33.383900Z", "loop": 11172, "env_steps": 6864691199, "loss": 0.014957836829125881, "avg_return": 0.8634052872657776, "regret": 0.0012728782603517175, "entropy": 0.08360529690980911, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:34.237773Z", "loop": 11173, "env_steps": 6865305599, "loss": 0.017283989116549492, "avg_return": 0.8623677492141724, "regret": 0.0012728782603517175, "entropy": 0.09154968708753586, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:35.092271Z", "loop": 11174, "env_steps": 6865919999, "loss": 0.016488341614603996, "avg_return": 0.8621075749397278, "regret": 0.0012728782603517175, "entropy": 0.08518268913030624, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:35.947311Z", "loop": 11175, "env_steps": 6866534399, "loss": 0.01606772467494011, "avg_return": 0.8625970482826233, "regret": 0.0012728782603517175, "entropy": 0.0875851958990097, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:36.799827Z", "loop": 11176, "env_steps": 6867148799, "loss": 0.015843985602259636, "avg_return": 0.8630657196044922, "regret": 0.0012728782603517175, "entropy": 0.08861538022756577, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:37.653093Z", "loop": 11177, "env_steps": 6867763199, "loss": 0.016129830852150917, "avg_return": 0.8617717623710632, "regret": 0.0012728782603517175, "entropy": 0.0880679339170456, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:38.506870Z", "loop": 11178, "env_steps": 6868377599, "loss": 0.01721808686852455, "avg_return": 0.8638582825660706, "regret": 0.0012728782603517175, "entropy": 0.08820026367902756, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:39.361852Z", "loop": 11179, "env_steps": 6868991999, "loss": 0.01723792776465416, "avg_return": 0.8623976111412048, "regret": 0.0012728782603517175, "entropy": 0.09405167400836945, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:40.252901Z", "loop": 11180, "env_steps": 6869606399, "loss": 0.01859128102660179, "avg_return": 0.8623014688491821, "regret": 0.001217491109855473, "entropy": 0.09293874353170395, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:41.106917Z", "loop": 11181, "env_steps": 6870220799, "loss": 0.017575008794665337, "avg_return": 0.8609591126441956, "regret": 0.001217491109855473, "entropy": 0.09120715409517288, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:41.960602Z", "loop": 11182, "env_steps": 6870835199, "loss": 0.019211789593100548, "avg_return": 0.8619924187660217, "regret": 0.001217491109855473, "entropy": 0.09743352234363556, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:42.815812Z", "loop": 11183, "env_steps": 6871449599, "loss": 0.01890210434794426, "avg_return": 0.8609570264816284, "regret": 0.001217491109855473, "entropy": 0.09582443535327911, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:43.669814Z", "loop": 11184, "env_steps": 6872063999, "loss": 0.019054396077990532, "avg_return": 0.8620100021362305, "regret": 0.001217491109855473, "entropy": 0.09859278798103333, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:44.523192Z", "loop": 11185, "env_steps": 6872678399, "loss": 0.018495609983801842, "avg_return": 0.8616873621940613, "regret": 0.001217491109855473, "entropy": 0.09591522812843323, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:45.376918Z", "loop": 11186, "env_steps": 6873292799, "loss": 0.017977440729737282, "avg_return": 0.8620790839195251, "regret": 0.001217491109855473, "entropy": 0.09842178970575333, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:46.231438Z", "loop": 11187, "env_steps": 6873907199, "loss": 0.019232532009482384, "avg_return": 0.86176598072052, "regret": 0.001217491109855473, "entropy": 0.09824670851230621, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:47.085454Z", "loop": 11188, "env_steps": 6874521599, "loss": 0.018697230145335197, "avg_return": 0.8614235520362854, "regret": 0.001217491109855473, "entropy": 0.09779180586338043, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:47.939159Z", "loop": 11189, "env_steps": 6875135999, "loss": 0.018572604283690453, "avg_return": 0.8643695116043091, "regret": 0.001217491109855473, "entropy": 0.10122527182102203, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:48.830679Z", "loop": 11190, "env_steps": 6875750399, "loss": 0.018981358036398888, "avg_return": 0.8632419109344482, "regret": 0.0008749051485210657, "entropy": 0.10080016404390335, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:49.684630Z", "loop": 11191, "env_steps": 6876364799, "loss": 0.02028779126703739, "avg_return": 0.8615712523460388, "regret": 0.0008749051485210657, "entropy": 0.10520210862159729, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:50.538832Z", "loop": 11192, "env_steps": 6876979199, "loss": 0.018874404951930046, "avg_return": 0.862550675868988, "regret": 0.0008749051485210657, "entropy": 0.10069581121206284, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:51.392692Z", "loop": 11193, "env_steps": 6877593599, "loss": 0.019285326823592186, "avg_return": 0.862471342086792, "regret": 0.0008749051485210657, "entropy": 0.10094117373228073, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:52.247397Z", "loop": 11194, "env_steps": 6878207999, "loss": 0.018120592460036278, "avg_return": 0.862252414226532, "regret": 0.0008749051485210657, "entropy": 0.09584134817123413, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:53.102028Z", "loop": 11195, "env_steps": 6878822399, "loss": 0.017407767474651337, "avg_return": 0.8633726239204407, "regret": 0.0008749051485210657, "entropy": 0.09287799894809723, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:53.956697Z", "loop": 11196, "env_steps": 6879436799, "loss": 0.016969842836260796, "avg_return": 0.8615307807922363, "regret": 0.0008749051485210657, "entropy": 0.09134884178638458, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:54.811097Z", "loop": 11197, "env_steps": 6880051199, "loss": 0.01841253601014614, "avg_return": 0.8624688982963562, "regret": 0.0008749051485210657, "entropy": 0.10112671554088593, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:55.664456Z", "loop": 11198, "env_steps": 6880665599, "loss": 0.017331339418888092, "avg_return": 0.863423764705658, "regret": 0.0008749051485210657, "entropy": 0.09548356384038925, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:56.518107Z", "loop": 11199, "env_steps": 6881279999, "loss": 0.019516071304678917, "avg_return": 0.8614877462387085, "regret": 0.0008749051485210657, "entropy": 0.09995085746049881, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:57.411059Z", "loop": 11200, "env_steps": 6881894399, "loss": 0.017735417932271957, "avg_return": 0.8620085120201111, "regret": 0.0006624953239224851, "entropy": 0.09678524732589722, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:58.266253Z", "loop": 11201, "env_steps": 6882508799, "loss": 0.018620116636157036, "avg_return": 0.8640139698982239, "regret": 0.0006624953239224851, "entropy": 0.09882992506027222, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:59.120575Z", "loop": 11202, "env_steps": 6883123199, "loss": 0.017545070499181747, "avg_return": 0.8633534908294678, "regret": 0.0006624953239224851, "entropy": 0.0966300219297409, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:03:59.974284Z", "loop": 11203, "env_steps": 6883737599, "loss": 0.01761176809668541, "avg_return": 0.8628515601158142, "regret": 0.0006624953239224851, "entropy": 0.09302394837141037, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:00.828558Z", "loop": 11204, "env_steps": 6884351999, "loss": 0.018093518912792206, "avg_return": 0.8628072142601013, "regret": 0.0006624953239224851, "entropy": 0.09706726670265198, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:01.682992Z", "loop": 11205, "env_steps": 6884966399, "loss": 0.01745462603867054, "avg_return": 0.8619423508644104, "regret": 0.0006624953239224851, "entropy": 0.09452826529741287, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:02.538001Z", "loop": 11206, "env_steps": 6885580799, "loss": 0.018630897626280785, "avg_return": 0.8622987866401672, "regret": 0.0006624953239224851, "entropy": 0.09560387581586838, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:03.391565Z", "loop": 11207, "env_steps": 6886195199, "loss": 0.018319902941584587, "avg_return": 0.8614699244499207, "regret": 0.0006624953239224851, "entropy": 0.09871998429298401, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:04.244934Z", "loop": 11208, "env_steps": 6886809599, "loss": 0.017407797276973724, "avg_return": 0.8630521893501282, "regret": 0.0006624953239224851, "entropy": 0.09580677002668381, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:05.098938Z", "loop": 11209, "env_steps": 6887423999, "loss": 0.016457239165902138, "avg_return": 0.8631040453910828, "regret": 0.0006624953239224851, "entropy": 0.09065081179141998, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:05.992546Z", "loop": 11210, "env_steps": 6888038399, "loss": 0.017664922401309013, "avg_return": 0.8637644648551941, "regret": 0.00044432125287130475, "entropy": 0.09479779005050659, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:06.847356Z", "loop": 11211, "env_steps": 6888652799, "loss": 0.015814870595932007, "avg_return": 0.8628239035606384, "regret": 0.00044432125287130475, "entropy": 0.08693931251764297, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:07.701063Z", "loop": 11212, "env_steps": 6889267199, "loss": 0.016071157529950142, "avg_return": 0.8625221848487854, "regret": 0.00044432125287130475, "entropy": 0.08732001483440399, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:08.555149Z", "loop": 11213, "env_steps": 6889881599, "loss": 0.016648782417178154, "avg_return": 0.8630673289299011, "regret": 0.00044432125287130475, "entropy": 0.08765381574630737, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:09.410814Z", "loop": 11214, "env_steps": 6890495999, "loss": 0.01617983914911747, "avg_return": 0.8626288175582886, "regret": 0.00044432125287130475, "entropy": 0.0872284397482872, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:10.265138Z", "loop": 11215, "env_steps": 6891110399, "loss": 0.0168793685734272, "avg_return": 0.8622129559516907, "regret": 0.00044432125287130475, "entropy": 0.08802133053541183, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:11.118319Z", "loop": 11216, "env_steps": 6891724799, "loss": 0.015715178102254868, "avg_return": 0.8624395728111267, "regret": 0.00044432125287130475, "entropy": 0.08198232203722, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:11.972302Z", "loop": 11217, "env_steps": 6892339199, "loss": 0.014114429242908955, "avg_return": 0.8625189661979675, "regret": 0.00044432125287130475, "entropy": 0.07904484868049622, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:12.826825Z", "loop": 11218, "env_steps": 6892953599, "loss": 0.014094928279519081, "avg_return": 0.8618260025978088, "regret": 0.00044432125287130475, "entropy": 0.07919448614120483, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:13.681749Z", "loop": 11219, "env_steps": 6893567999, "loss": 0.01344763208180666, "avg_return": 0.864460289478302, "regret": 0.00044432125287130475, "entropy": 0.07189053297042847, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:14.573253Z", "loop": 11220, "env_steps": 6894182399, "loss": 0.013192516751587391, "avg_return": 0.8631008267402649, "regret": 0.0003560449986252934, "entropy": 0.07254108786582947, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:15.426996Z", "loop": 11221, "env_steps": 6894796799, "loss": 0.013408905826508999, "avg_return": 0.8632411956787109, "regret": 0.0003560449986252934, "entropy": 0.07546684890985489, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:16.280769Z", "loop": 11222, "env_steps": 6895411199, "loss": 0.013409595005214214, "avg_return": 0.8633356094360352, "regret": 0.0003560449986252934, "entropy": 0.07366969436407089, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:17.134955Z", "loop": 11223, "env_steps": 6896025599, "loss": 0.013290710747241974, "avg_return": 0.8635095357894897, "regret": 0.0003560449986252934, "entropy": 0.06869208067655563, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:17.989577Z", "loop": 11224, "env_steps": 6896639999, "loss": 0.01294343639165163, "avg_return": 0.862826943397522, "regret": 0.0003560449986252934, "entropy": 0.07356195896863937, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:18.844122Z", "loop": 11225, "env_steps": 6897254399, "loss": 0.01305301208049059, "avg_return": 0.8633835911750793, "regret": 0.0003560449986252934, "entropy": 0.0688885897397995, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:19.698310Z", "loop": 11226, "env_steps": 6897868799, "loss": 0.012436478398740292, "avg_return": 0.8627631068229675, "regret": 0.0003560449986252934, "entropy": 0.06755763292312622, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:20.552622Z", "loop": 11227, "env_steps": 6898483199, "loss": 0.012918439693748951, "avg_return": 0.8643625974655151, "regret": 0.0003560449986252934, "entropy": 0.06715231388807297, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:21.407881Z", "loop": 11228, "env_steps": 6899097599, "loss": 0.011788432486355305, "avg_return": 0.8638593554496765, "regret": 0.0003560449986252934, "entropy": 0.06772707402706146, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:22.262512Z", "loop": 11229, "env_steps": 6899711999, "loss": 0.011366921477019787, "avg_return": 0.8628080487251282, "regret": 0.0003560449986252934, "entropy": 0.06404750794172287, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:23.154802Z", "loop": 11230, "env_steps": 6900326399, "loss": 0.011742549948394299, "avg_return": 0.86290043592453, "regret": 0.0005820168880745769, "entropy": 0.0651119202375412, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:24.009029Z", "loop": 11231, "env_steps": 6900940799, "loss": 0.01228537131100893, "avg_return": 0.8626061081886292, "regret": 0.0005820168880745769, "entropy": 0.06952385604381561, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:24.863531Z", "loop": 11232, "env_steps": 6901555199, "loss": 0.012120016850531101, "avg_return": 0.8618159294128418, "regret": 0.0005820168880745769, "entropy": 0.06648927927017212, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:25.717894Z", "loop": 11233, "env_steps": 6902169599, "loss": 0.012634878046810627, "avg_return": 0.8624451160430908, "regret": 0.0005820168880745769, "entropy": 0.06650947034358978, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:26.572456Z", "loop": 11234, "env_steps": 6902783999, "loss": 0.011694775894284248, "avg_return": 0.8616986274719238, "regret": 0.0005820168880745769, "entropy": 0.06428100913763046, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:27.426883Z", "loop": 11235, "env_steps": 6903398399, "loss": 0.014929451048374176, "avg_return": 0.8603545427322388, "regret": 0.0005820168880745769, "entropy": 0.07785014808177948, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:28.281052Z", "loop": 11236, "env_steps": 6904012799, "loss": 0.015421737916767597, "avg_return": 0.8595724701881409, "regret": 0.0005820168880745769, "entropy": 0.0786079466342926, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:29.135788Z", "loop": 11237, "env_steps": 6904627199, "loss": 0.014975951984524727, "avg_return": 0.8575078248977661, "regret": 0.0005820168880745769, "entropy": 0.08336824178695679, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:29.990501Z", "loop": 11238, "env_steps": 6905241599, "loss": 0.014020408503711224, "avg_return": 0.8605725169181824, "regret": 0.0005820168880745769, "entropy": 0.07918371260166168, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:30.843830Z", "loop": 11239, "env_steps": 6905855999, "loss": 0.015877656638622284, "avg_return": 0.8580952882766724, "regret": 0.0005820168880745769, "entropy": 0.07870804518461227, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:31.736137Z", "loop": 11240, "env_steps": 6906470399, "loss": 0.01378593873232603, "avg_return": 0.8589860200881958, "regret": 0.004345869179815054, "entropy": 0.0748978704214096, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:32.590098Z", "loop": 11241, "env_steps": 6907084799, "loss": 0.01397734321653843, "avg_return": 0.8593708276748657, "regret": 0.004345869179815054, "entropy": 0.07361310720443726, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:33.444386Z", "loop": 11242, "env_steps": 6907699199, "loss": 0.013052629306912422, "avg_return": 0.8597283959388733, "regret": 0.004345869179815054, "entropy": 0.07106530666351318, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:34.299250Z", "loop": 11243, "env_steps": 6908313599, "loss": 0.012559162452816963, "avg_return": 0.8598639965057373, "regret": 0.004345869179815054, "entropy": 0.07203101366758347, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:35.153297Z", "loop": 11244, "env_steps": 6908927999, "loss": 0.011877725832164288, "avg_return": 0.8613371253013611, "regret": 0.004345869179815054, "entropy": 0.06642625480890274, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:36.008683Z", "loop": 11245, "env_steps": 6909542399, "loss": 0.01143275573849678, "avg_return": 0.860683798789978, "regret": 0.004345869179815054, "entropy": 0.06552239507436752, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:36.864031Z", "loop": 11246, "env_steps": 6910156799, "loss": 0.012891081161797047, "avg_return": 0.860655665397644, "regret": 0.004345869179815054, "entropy": 0.07084546238183975, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:37.718855Z", "loop": 11247, "env_steps": 6910771199, "loss": 0.011529771611094475, "avg_return": 0.8616766333580017, "regret": 0.004345869179815054, "entropy": 0.06719452142715454, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:38.572740Z", "loop": 11248, "env_steps": 6911385599, "loss": 0.01209182571619749, "avg_return": 0.8616239428520203, "regret": 0.004345869179815054, "entropy": 0.06716826558113098, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:39.427987Z", "loop": 11249, "env_steps": 6911999999, "loss": 0.01192610152065754, "avg_return": 0.8631101846694946, "regret": 0.004345869179815054, "entropy": 0.064926378428936, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:40.321042Z", "loop": 11250, "env_steps": 6912614399, "loss": 0.012602153234183788, "avg_return": 0.8633331656455994, "regret": 0.0009550288086757064, "entropy": 0.06685695797204971, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:41.175451Z", "loop": 11251, "env_steps": 6913228799, "loss": 0.01212385855615139, "avg_return": 0.8628800511360168, "regret": 0.0009550288086757064, "entropy": 0.06666870415210724, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:42.029620Z", "loop": 11252, "env_steps": 6913843199, "loss": 0.012786167673766613, "avg_return": 0.8617340326309204, "regret": 0.0009550288086757064, "entropy": 0.07012497633695602, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:42.884222Z", "loop": 11253, "env_steps": 6914457599, "loss": 0.013095478527247906, "avg_return": 0.8637139201164246, "regret": 0.0009550288086757064, "entropy": 0.06913449615240097, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:43.738144Z", "loop": 11254, "env_steps": 6915071999, "loss": 0.011623668484389782, "avg_return": 0.8631895184516907, "regret": 0.0009550288086757064, "entropy": 0.06459915637969971, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:44.592566Z", "loop": 11255, "env_steps": 6915686399, "loss": 0.013477063737809658, "avg_return": 0.8631102442741394, "regret": 0.0009550288086757064, "entropy": 0.0681164488196373, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:45.446344Z", "loop": 11256, "env_steps": 6916300799, "loss": 0.012054172344505787, "avg_return": 0.8621382713317871, "regret": 0.0009550288086757064, "entropy": 0.06533253192901611, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:46.299422Z", "loop": 11257, "env_steps": 6916915199, "loss": 0.013035117648541927, "avg_return": 0.8636556267738342, "regret": 0.0009550288086757064, "entropy": 0.06739240139722824, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:47.152932Z", "loop": 11258, "env_steps": 6917529599, "loss": 0.012121779844164848, "avg_return": 0.8612339496612549, "regret": 0.0009550288086757064, "entropy": 0.0681697353720665, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:48.007066Z", "loop": 11259, "env_steps": 6918143999, "loss": 0.013651415705680847, "avg_return": 0.8620854616165161, "regret": 0.0009550288086757064, "entropy": 0.0726558119058609, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:48.900324Z", "loop": 11260, "env_steps": 6918758399, "loss": 0.01340318750590086, "avg_return": 0.8639248013496399, "regret": 0.0007718444103375077, "entropy": 0.06932593882083893, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:49.754670Z", "loop": 11261, "env_steps": 6919372799, "loss": 0.013747833669185638, "avg_return": 0.8629471063613892, "regret": 0.0007718444103375077, "entropy": 0.07287828624248505, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:50.607996Z", "loop": 11262, "env_steps": 6919987199, "loss": 0.013685840182006359, "avg_return": 0.8613309860229492, "regret": 0.0007718444103375077, "entropy": 0.07218736410140991, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:51.462485Z", "loop": 11263, "env_steps": 6920601599, "loss": 0.014142188243567944, "avg_return": 0.8621132373809814, "regret": 0.0007718444103375077, "entropy": 0.07633384317159653, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:52.316675Z", "loop": 11264, "env_steps": 6921215999, "loss": 0.013615389354526997, "avg_return": 0.863076388835907, "regret": 0.0007718444103375077, "entropy": 0.0745687335729599, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:53.171517Z", "loop": 11265, "env_steps": 6921830399, "loss": 0.013511627912521362, "avg_return": 0.8622051477432251, "regret": 0.0007718444103375077, "entropy": 0.072245292365551, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:54.025056Z", "loop": 11266, "env_steps": 6922444799, "loss": 0.012847340665757656, "avg_return": 0.8642401099205017, "regret": 0.0007718444103375077, "entropy": 0.07361306995153427, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:54.878582Z", "loop": 11267, "env_steps": 6923059199, "loss": 0.013593313284218311, "avg_return": 0.8640455603599548, "regret": 0.0007718444103375077, "entropy": 0.07208859175443649, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:55.733397Z", "loop": 11268, "env_steps": 6923673599, "loss": 0.013905147090554237, "avg_return": 0.8614488840103149, "regret": 0.0007718444103375077, "entropy": 0.07430294901132584, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:56.588483Z", "loop": 11269, "env_steps": 6924287999, "loss": 0.014531484805047512, "avg_return": 0.8620195984840393, "regret": 0.0007718444103375077, "entropy": 0.07611656934022903, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:57.480961Z", "loop": 11270, "env_steps": 6924902399, "loss": 0.013859114609658718, "avg_return": 0.8626278638839722, "regret": 0.0005068943719379604, "entropy": 0.07600800693035126, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:58.334990Z", "loop": 11271, "env_steps": 6925516799, "loss": 0.014969591982662678, "avg_return": 0.862704873085022, "regret": 0.0005068943719379604, "entropy": 0.08033531159162521, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:04:59.190550Z", "loop": 11272, "env_steps": 6926131199, "loss": 0.0158626027405262, "avg_return": 0.8644028902053833, "regret": 0.0005068943719379604, "entropy": 0.08462804555892944, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:00.046177Z", "loop": 11273, "env_steps": 6926745599, "loss": 0.015340866521000862, "avg_return": 0.8639174699783325, "regret": 0.0005068943719379604, "entropy": 0.08523822575807571, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:00.901377Z", "loop": 11274, "env_steps": 6927359999, "loss": 0.016082782298326492, "avg_return": 0.862910270690918, "regret": 0.0005068943719379604, "entropy": 0.08431842178106308, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:01.756365Z", "loop": 11275, "env_steps": 6927974399, "loss": 0.01701524667441845, "avg_return": 0.8630129098892212, "regret": 0.0005068943719379604, "entropy": 0.08900251984596252, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:02.613423Z", "loop": 11276, "env_steps": 6928588799, "loss": 0.015984853729605675, "avg_return": 0.8638119697570801, "regret": 0.0005068943719379604, "entropy": 0.08744464069604874, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:03.468166Z", "loop": 11277, "env_steps": 6929203199, "loss": 0.01663823239505291, "avg_return": 0.8621534705162048, "regret": 0.0005068943719379604, "entropy": 0.08855000138282776, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:04.323880Z", "loop": 11278, "env_steps": 6929817599, "loss": 0.016018366441130638, "avg_return": 0.8637155294418335, "regret": 0.0005068943719379604, "entropy": 0.08217456191778183, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:05.178362Z", "loop": 11279, "env_steps": 6930431999, "loss": 0.016120148822665215, "avg_return": 0.8630011081695557, "regret": 0.0005068943719379604, "entropy": 0.08290828764438629, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:06.071553Z", "loop": 11280, "env_steps": 6931046399, "loss": 0.01521365251392126, "avg_return": 0.863975465297699, "regret": 0.0001791067043086514, "entropy": 0.07858874648809433, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:06.924933Z", "loop": 11281, "env_steps": 6931660799, "loss": 0.014224131591618061, "avg_return": 0.8632112741470337, "regret": 0.0001791067043086514, "entropy": 0.07763903588056564, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:07.779476Z", "loop": 11282, "env_steps": 6932275199, "loss": 0.013168464414775372, "avg_return": 0.8635013103485107, "regret": 0.0001791067043086514, "entropy": 0.06978244334459305, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:08.634317Z", "loop": 11283, "env_steps": 6932889599, "loss": 0.013916537165641785, "avg_return": 0.8643749952316284, "regret": 0.0001791067043086514, "entropy": 0.07245485484600067, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:09.488253Z", "loop": 11284, "env_steps": 6933503999, "loss": 0.012980465777218342, "avg_return": 0.8628279566764832, "regret": 0.0001791067043086514, "entropy": 0.06918949633836746, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:10.341470Z", "loop": 11285, "env_steps": 6934118399, "loss": 0.013935095630586147, "avg_return": 0.8643926978111267, "regret": 0.0001791067043086514, "entropy": 0.071517713367939, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:11.196607Z", "loop": 11286, "env_steps": 6934732799, "loss": 0.013426235876977444, "avg_return": 0.8639028072357178, "regret": 0.0001791067043086514, "entropy": 0.07148777693510056, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:12.051871Z", "loop": 11287, "env_steps": 6935347199, "loss": 0.013021985068917274, "avg_return": 0.864595890045166, "regret": 0.0001791067043086514, "entropy": 0.06807702034711838, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:12.907617Z", "loop": 11288, "env_steps": 6935961599, "loss": 0.012730847112834454, "avg_return": 0.8631695508956909, "regret": 0.0001791067043086514, "entropy": 0.0711316466331482, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:13.760709Z", "loop": 11289, "env_steps": 6936575999, "loss": 0.013890476897358894, "avg_return": 0.8644296526908875, "regret": 0.0001791067043086514, "entropy": 0.07280626147985458, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:14.653021Z", "loop": 11290, "env_steps": 6937190399, "loss": 0.01346519310027361, "avg_return": 0.8633077144622803, "regret": 0.00019567992421798408, "entropy": 0.07192245870828629, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:15.507970Z", "loop": 11291, "env_steps": 6937804799, "loss": 0.013718483038246632, "avg_return": 0.86328125, "regret": 0.00019567992421798408, "entropy": 0.07387129962444305, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:16.362299Z", "loop": 11292, "env_steps": 6938419199, "loss": 0.01254166942089796, "avg_return": 0.8621415495872498, "regret": 0.00019567992421798408, "entropy": 0.06987615674734116, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:17.216927Z", "loop": 11293, "env_steps": 6939033599, "loss": 0.01323131937533617, "avg_return": 0.8629177212715149, "regret": 0.00019567992421798408, "entropy": 0.07227438688278198, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:18.070843Z", "loop": 11294, "env_steps": 6939647999, "loss": 0.013034775853157043, "avg_return": 0.8625262379646301, "regret": 0.00019567992421798408, "entropy": 0.07025346159934998, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:18.925400Z", "loop": 11295, "env_steps": 6940262399, "loss": 0.012415619567036629, "avg_return": 0.8629041910171509, "regret": 0.00019567992421798408, "entropy": 0.06824389100074768, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:19.779170Z", "loop": 11296, "env_steps": 6940876799, "loss": 0.012727989815175533, "avg_return": 0.8643181324005127, "regret": 0.00019567992421798408, "entropy": 0.06937864422798157, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:20.633803Z", "loop": 11297, "env_steps": 6941491199, "loss": 0.012182668782770634, "avg_return": 0.8640986084938049, "regret": 0.00019567992421798408, "entropy": 0.06793936342000961, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:21.487162Z", "loop": 11298, "env_steps": 6942105599, "loss": 0.013842681422829628, "avg_return": 0.8635556101799011, "regret": 0.00019567992421798408, "entropy": 0.07054402679204941, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:22.340993Z", "loop": 11299, "env_steps": 6942719999, "loss": 0.011768702417612076, "avg_return": 0.8622978925704956, "regret": 0.00019567992421798408, "entropy": 0.06559742242097855, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:23.232314Z", "loop": 11300, "env_steps": 6943334399, "loss": 0.013703410513699055, "avg_return": 0.8631638884544373, "regret": 0.00041924536344595253, "entropy": 0.07369071990251541, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:24.087065Z", "loop": 11301, "env_steps": 6943948799, "loss": 0.012301554903388023, "avg_return": 0.8630152344703674, "regret": 0.00041924536344595253, "entropy": 0.06888048350811005, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:24.942347Z", "loop": 11302, "env_steps": 6944563199, "loss": 0.012300457805395126, "avg_return": 0.8624576926231384, "regret": 0.00041924536344595253, "entropy": 0.06741328537464142, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:25.797420Z", "loop": 11303, "env_steps": 6945177599, "loss": 0.012969925068318844, "avg_return": 0.8630520105361938, "regret": 0.00041924536344595253, "entropy": 0.07216393202543259, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:26.651343Z", "loop": 11304, "env_steps": 6945791999, "loss": 0.012173783965408802, "avg_return": 0.8631063103675842, "regret": 0.00041924536344595253, "entropy": 0.06922507286071777, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:27.505745Z", "loop": 11305, "env_steps": 6946406399, "loss": 0.013946165330708027, "avg_return": 0.8637349605560303, "regret": 0.00041924536344595253, "entropy": 0.07345756143331528, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:28.360047Z", "loop": 11306, "env_steps": 6947020799, "loss": 0.013660172931849957, "avg_return": 0.8648841381072998, "regret": 0.00041924536344595253, "entropy": 0.0739218071103096, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:29.213542Z", "loop": 11307, "env_steps": 6947635199, "loss": 0.013865332119166851, "avg_return": 0.8620730042457581, "regret": 0.00041924536344595253, "entropy": 0.07647731155157089, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:30.066722Z", "loop": 11308, "env_steps": 6948249599, "loss": 0.014478678815066814, "avg_return": 0.8609269261360168, "regret": 0.00041924536344595253, "entropy": 0.07505903393030167, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:30.920200Z", "loop": 11309, "env_steps": 6948863999, "loss": 0.013147148303687572, "avg_return": 0.8622006177902222, "regret": 0.00041924536344595253, "entropy": 0.07056531310081482, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:31.813515Z", "loop": 11310, "env_steps": 6949478399, "loss": 0.01487182267010212, "avg_return": 0.8596763014793396, "regret": 0.002876739948987961, "entropy": 0.07857944816350937, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:32.668236Z", "loop": 11311, "env_steps": 6950092799, "loss": 0.014245484955608845, "avg_return": 0.8601963520050049, "regret": 0.002876739948987961, "entropy": 0.0761219710111618, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:33.522506Z", "loop": 11312, "env_steps": 6950707199, "loss": 0.014109875075519085, "avg_return": 0.8594489693641663, "regret": 0.002876739948987961, "entropy": 0.07671111822128296, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:34.376660Z", "loop": 11313, "env_steps": 6951321599, "loss": 0.014972922392189503, "avg_return": 0.8590823411941528, "regret": 0.002876739948987961, "entropy": 0.07786639779806137, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:35.230987Z", "loop": 11314, "env_steps": 6951935999, "loss": 0.015004904940724373, "avg_return": 0.8596733808517456, "regret": 0.002876739948987961, "entropy": 0.07681640237569809, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:36.086307Z", "loop": 11315, "env_steps": 6952550399, "loss": 0.014277838170528412, "avg_return": 0.8621001243591309, "regret": 0.002876739948987961, "entropy": 0.07749468833208084, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:36.939475Z", "loop": 11316, "env_steps": 6953164799, "loss": 0.013256891630589962, "avg_return": 0.8629190325737, "regret": 0.002876739948987961, "entropy": 0.07444959133863449, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:37.793080Z", "loop": 11317, "env_steps": 6953779199, "loss": 0.012971870601177216, "avg_return": 0.8621568083763123, "regret": 0.002876739948987961, "entropy": 0.07066521793603897, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:38.647578Z", "loop": 11318, "env_steps": 6954393599, "loss": 0.013240364380180836, "avg_return": 0.8613309860229492, "regret": 0.002876739948987961, "entropy": 0.07058770209550858, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:39.502218Z", "loop": 11319, "env_steps": 6955007999, "loss": 0.013551520183682442, "avg_return": 0.86358642578125, "regret": 0.002876739948987961, "entropy": 0.07255116105079651, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:40.395445Z", "loop": 11320, "env_steps": 6955622399, "loss": 0.014158673584461212, "avg_return": 0.8623384833335876, "regret": 0.0005560250720009208, "entropy": 0.07207343727350235, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:41.248263Z", "loop": 11321, "env_steps": 6956236799, "loss": 0.014630043879151344, "avg_return": 0.8635028004646301, "regret": 0.0005560250720009208, "entropy": 0.07957612723112106, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:42.102557Z", "loop": 11322, "env_steps": 6956851199, "loss": 0.01287503819912672, "avg_return": 0.8638522624969482, "regret": 0.0005560250720009208, "entropy": 0.07202431559562683, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:42.956787Z", "loop": 11323, "env_steps": 6957465599, "loss": 0.011975464411079884, "avg_return": 0.8630588054656982, "regret": 0.0005560250720009208, "entropy": 0.06928113847970963, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:43.811125Z", "loop": 11324, "env_steps": 6958079999, "loss": 0.012767250649631023, "avg_return": 0.8635456562042236, "regret": 0.0005560250720009208, "entropy": 0.06716695427894592, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:44.664181Z", "loop": 11325, "env_steps": 6958694399, "loss": 0.013707316480576992, "avg_return": 0.8628988862037659, "regret": 0.0005560250720009208, "entropy": 0.06922850757837296, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:45.517902Z", "loop": 11326, "env_steps": 6959308799, "loss": 0.012775549665093422, "avg_return": 0.8648228049278259, "regret": 0.0005560250720009208, "entropy": 0.07242314517498016, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:46.372777Z", "loop": 11327, "env_steps": 6959923199, "loss": 0.012510940432548523, "avg_return": 0.861871063709259, "regret": 0.0005560250720009208, "entropy": 0.06635341048240662, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:47.228257Z", "loop": 11328, "env_steps": 6960537599, "loss": 0.013230214826762676, "avg_return": 0.8633325695991516, "regret": 0.0005560250720009208, "entropy": 0.07228392362594604, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:48.082052Z", "loop": 11329, "env_steps": 6961151999, "loss": 0.013799461536109447, "avg_return": 0.8628979921340942, "regret": 0.0005560250720009208, "entropy": 0.07293543219566345, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:48.974563Z", "loop": 11330, "env_steps": 6961766399, "loss": 0.01295483112335205, "avg_return": 0.8618198037147522, "regret": 0.00025451459805481136, "entropy": 0.07075759023427963, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:49.828391Z", "loop": 11331, "env_steps": 6962380799, "loss": 0.01361414697021246, "avg_return": 0.8634234666824341, "regret": 0.00025451459805481136, "entropy": 0.07816540449857712, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:50.683326Z", "loop": 11332, "env_steps": 6962995199, "loss": 0.013656209222972393, "avg_return": 0.863846480846405, "regret": 0.00025451459805481136, "entropy": 0.07268964499235153, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:51.537147Z", "loop": 11333, "env_steps": 6963609599, "loss": 0.014413799159228802, "avg_return": 0.8631335496902466, "regret": 0.00025451459805481136, "entropy": 0.07617183774709702, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:52.392111Z", "loop": 11334, "env_steps": 6964223999, "loss": 0.013480016961693764, "avg_return": 0.863756537437439, "regret": 0.00025451459805481136, "entropy": 0.07279771566390991, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:53.246140Z", "loop": 11335, "env_steps": 6964838399, "loss": 0.013592488132417202, "avg_return": 0.864246666431427, "regret": 0.00025451459805481136, "entropy": 0.07271986454725266, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:54.100643Z", "loop": 11336, "env_steps": 6965452799, "loss": 0.013372167013585567, "avg_return": 0.8626590371131897, "regret": 0.00025451459805481136, "entropy": 0.07521183788776398, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:54.955928Z", "loop": 11337, "env_steps": 6966067199, "loss": 0.014895111322402954, "avg_return": 0.8627073168754578, "regret": 0.00025451459805481136, "entropy": 0.08103612810373306, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:55.810852Z", "loop": 11338, "env_steps": 6966681599, "loss": 0.014919196255505085, "avg_return": 0.8621896505355835, "regret": 0.00025451459805481136, "entropy": 0.07987383753061295, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:56.664872Z", "loop": 11339, "env_steps": 6967295999, "loss": 0.013861765153706074, "avg_return": 0.8600925803184509, "regret": 0.00025451459805481136, "entropy": 0.07608882337808609, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:57.557953Z", "loop": 11340, "env_steps": 6967910399, "loss": 0.01397615671157837, "avg_return": 0.8607794642448425, "regret": 0.002693988149985671, "entropy": 0.07763311266899109, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:58.413582Z", "loop": 11341, "env_steps": 6968524799, "loss": 0.014628665521740913, "avg_return": 0.8611615300178528, "regret": 0.002693988149985671, "entropy": 0.07996800541877747, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:05:59.267929Z", "loop": 11342, "env_steps": 6969139199, "loss": 0.014231394045054913, "avg_return": 0.8619974851608276, "regret": 0.002693988149985671, "entropy": 0.07737821340560913, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:00.122284Z", "loop": 11343, "env_steps": 6969753599, "loss": 0.015597625635564327, "avg_return": 0.8618835806846619, "regret": 0.002693988149985671, "entropy": 0.08219881355762482, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:00.976019Z", "loop": 11344, "env_steps": 6970367999, "loss": 0.014705314300954342, "avg_return": 0.8602715134620667, "regret": 0.002693988149985671, "entropy": 0.08178867399692535, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:01.831405Z", "loop": 11345, "env_steps": 6970982399, "loss": 0.01432231068611145, "avg_return": 0.8624858856201172, "regret": 0.002693988149985671, "entropy": 0.07759113609790802, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:02.685711Z", "loop": 11346, "env_steps": 6971596799, "loss": 0.013530479744076729, "avg_return": 0.8624507784843445, "regret": 0.002693988149985671, "entropy": 0.07658179849386215, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:03.539119Z", "loop": 11347, "env_steps": 6972211199, "loss": 0.013736513443291187, "avg_return": 0.8630433082580566, "regret": 0.002693988149985671, "entropy": 0.07559234648942947, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:04.392003Z", "loop": 11348, "env_steps": 6972825599, "loss": 0.014521143399178982, "avg_return": 0.8615967035293579, "regret": 0.002693988149985671, "entropy": 0.07911209762096405, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:05.245451Z", "loop": 11349, "env_steps": 6973439999, "loss": 0.012089787051081657, "avg_return": 0.8618974089622498, "regret": 0.002693988149985671, "entropy": 0.07143520563840866, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:06.140438Z", "loop": 11350, "env_steps": 6974054399, "loss": 0.01426386833190918, "avg_return": 0.8629242181777954, "regret": 0.000847552961204201, "entropy": 0.07511549443006516, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:06.995494Z", "loop": 11351, "env_steps": 6974668799, "loss": 0.014079811051487923, "avg_return": 0.8625972867012024, "regret": 0.000847552961204201, "entropy": 0.07476460188627243, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:07.849723Z", "loop": 11352, "env_steps": 6975283199, "loss": 0.012905183248221874, "avg_return": 0.8622339963912964, "regret": 0.000847552961204201, "entropy": 0.07100844383239746, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:08.704028Z", "loop": 11353, "env_steps": 6975897599, "loss": 0.013600030913949013, "avg_return": 0.862949550151825, "regret": 0.000847552961204201, "entropy": 0.07197294384241104, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:09.558781Z", "loop": 11354, "env_steps": 6976511999, "loss": 0.014047816395759583, "avg_return": 0.8635352849960327, "regret": 0.000847552961204201, "entropy": 0.07629364728927612, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:10.412256Z", "loop": 11355, "env_steps": 6977126399, "loss": 0.012478225864470005, "avg_return": 0.8624475598335266, "regret": 0.000847552961204201, "entropy": 0.07300052791833878, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:11.266265Z", "loop": 11356, "env_steps": 6977740799, "loss": 0.01408065389841795, "avg_return": 0.8616953492164612, "regret": 0.000847552961204201, "entropy": 0.07597462087869644, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:12.120534Z", "loop": 11357, "env_steps": 6978355199, "loss": 0.012194476090371609, "avg_return": 0.8628442883491516, "regret": 0.000847552961204201, "entropy": 0.07247154414653778, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:12.973875Z", "loop": 11358, "env_steps": 6978969599, "loss": 0.014008727855980396, "avg_return": 0.862008810043335, "regret": 0.000847552961204201, "entropy": 0.07618554681539536, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:13.828091Z", "loop": 11359, "env_steps": 6979583999, "loss": 0.014493966475129128, "avg_return": 0.8625372648239136, "regret": 0.000847552961204201, "entropy": 0.07873108237981796, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:14.720283Z", "loop": 11360, "env_steps": 6980198399, "loss": 0.014646882191300392, "avg_return": 0.8627550601959229, "regret": 0.0014690692769363523, "entropy": 0.07734885066747665, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:15.574496Z", "loop": 11361, "env_steps": 6980812799, "loss": 0.014728299342095852, "avg_return": 0.8609146475791931, "regret": 0.0014690692769363523, "entropy": 0.0818416178226471, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:16.427570Z", "loop": 11362, "env_steps": 6981427199, "loss": 0.014794505201280117, "avg_return": 0.859843373298645, "regret": 0.0014690692769363523, "entropy": 0.07997157424688339, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:17.280721Z", "loop": 11363, "env_steps": 6982041599, "loss": 0.01705154776573181, "avg_return": 0.8602868914604187, "regret": 0.0014690692769363523, "entropy": 0.0871131494641304, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:18.135544Z", "loop": 11364, "env_steps": 6982655999, "loss": 0.016054056584835052, "avg_return": 0.8593355417251587, "regret": 0.0014690692769363523, "entropy": 0.08314471691846848, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:18.989692Z", "loop": 11365, "env_steps": 6983270399, "loss": 0.013551919721066952, "avg_return": 0.8615941405296326, "regret": 0.0014690692769363523, "entropy": 0.07596774399280548, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:19.843268Z", "loop": 11366, "env_steps": 6983884799, "loss": 0.015113882720470428, "avg_return": 0.8614585399627686, "regret": 0.0014690692769363523, "entropy": 0.0798601433634758, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:20.696855Z", "loop": 11367, "env_steps": 6984499199, "loss": 0.013072197325527668, "avg_return": 0.8623484373092651, "regret": 0.0014690692769363523, "entropy": 0.07197459787130356, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:21.550734Z", "loop": 11368, "env_steps": 6985113599, "loss": 0.01378574687987566, "avg_return": 0.8628981709480286, "regret": 0.0014690692769363523, "entropy": 0.07068867981433868, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:22.404868Z", "loop": 11369, "env_steps": 6985727999, "loss": 0.01369920838624239, "avg_return": 0.8639878630638123, "regret": 0.0014690692769363523, "entropy": 0.07440625876188278, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:23.297895Z", "loop": 11370, "env_steps": 6986342399, "loss": 0.013525635004043579, "avg_return": 0.8622069358825684, "regret": 0.0004948138375766575, "entropy": 0.06931077688932419, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:24.152506Z", "loop": 11371, "env_steps": 6986956799, "loss": 0.012572923675179482, "avg_return": 0.8630666136741638, "regret": 0.0004948138375766575, "entropy": 0.06793583929538727, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:25.007732Z", "loop": 11372, "env_steps": 6987571199, "loss": 0.013056784868240356, "avg_return": 0.8631506562232971, "regret": 0.0004948138375766575, "entropy": 0.06861724704504013, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:25.863124Z", "loop": 11373, "env_steps": 6988185599, "loss": 0.013065491802990437, "avg_return": 0.8633961081504822, "regret": 0.0004948138375766575, "entropy": 0.06977736949920654, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:26.718737Z", "loop": 11374, "env_steps": 6988799999, "loss": 0.01254186499863863, "avg_return": 0.8634029626846313, "regret": 0.0004948138375766575, "entropy": 0.07176609337329865, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:27.573702Z", "loop": 11375, "env_steps": 6989414399, "loss": 0.012543185614049435, "avg_return": 0.8620835542678833, "regret": 0.0004948138375766575, "entropy": 0.070154570043087, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:28.428926Z", "loop": 11376, "env_steps": 6990028799, "loss": 0.012971351854503155, "avg_return": 0.8624788522720337, "regret": 0.0004948138375766575, "entropy": 0.0691048726439476, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:29.284319Z", "loop": 11377, "env_steps": 6990643199, "loss": 0.013157363049685955, "avg_return": 0.861391007900238, "regret": 0.0004948138375766575, "entropy": 0.07275460660457611, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:30.140123Z", "loop": 11378, "env_steps": 6991257599, "loss": 0.01232803426682949, "avg_return": 0.8632489442825317, "regret": 0.0004948138375766575, "entropy": 0.07153155654668808, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:30.995695Z", "loop": 11379, "env_steps": 6991871999, "loss": 0.012908709235489368, "avg_return": 0.8643286228179932, "regret": 0.0004948138375766575, "entropy": 0.06938694417476654, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:31.891550Z", "loop": 11380, "env_steps": 6992486399, "loss": 0.013389934785664082, "avg_return": 0.8626698851585388, "regret": 0.00046802195720374584, "entropy": 0.07062165439128876, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:32.746294Z", "loop": 11381, "env_steps": 6993100799, "loss": 0.012108664028346539, "avg_return": 0.8625457882881165, "regret": 0.00046802195720374584, "entropy": 0.0672212466597557, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:33.601003Z", "loop": 11382, "env_steps": 6993715199, "loss": 0.012806057929992676, "avg_return": 0.8631299138069153, "regret": 0.00046802195720374584, "entropy": 0.06961046904325485, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:34.455718Z", "loop": 11383, "env_steps": 6994329599, "loss": 0.014225038699805737, "avg_return": 0.8631308078765869, "regret": 0.00046802195720374584, "entropy": 0.07374336570501328, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:35.311251Z", "loop": 11384, "env_steps": 6994943999, "loss": 0.01274151261895895, "avg_return": 0.8624717593193054, "regret": 0.00046802195720374584, "entropy": 0.06718092411756516, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:36.165372Z", "loop": 11385, "env_steps": 6995558399, "loss": 0.011984149925410748, "avg_return": 0.8632466793060303, "regret": 0.00046802195720374584, "entropy": 0.06689378619194031, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:37.020312Z", "loop": 11386, "env_steps": 6996172799, "loss": 0.013032105751335621, "avg_return": 0.8621857762336731, "regret": 0.00046802195720374584, "entropy": 0.0677342414855957, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:37.875247Z", "loop": 11387, "env_steps": 6996787199, "loss": 0.01277498621493578, "avg_return": 0.8634116649627686, "regret": 0.00046802195720374584, "entropy": 0.06772587448358536, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:38.729665Z", "loop": 11388, "env_steps": 6997401599, "loss": 0.011759351938962936, "avg_return": 0.8629587888717651, "regret": 0.00046802195720374584, "entropy": 0.0653323084115982, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:39.582965Z", "loop": 11389, "env_steps": 6998015999, "loss": 0.013449079357087612, "avg_return": 0.8622809052467346, "regret": 0.00046802195720374584, "entropy": 0.06684552878141403, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:40.474270Z", "loop": 11390, "env_steps": 6998630399, "loss": 0.012610792182385921, "avg_return": 0.8631572723388672, "regret": 0.0009525212226435542, "entropy": 0.06767778098583221, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:41.328978Z", "loop": 11391, "env_steps": 6999244799, "loss": 0.011934056878089905, "avg_return": 0.8635972142219543, "regret": 0.0009525212226435542, "entropy": 0.06453670561313629, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:42.183800Z", "loop": 11392, "env_steps": 6999859199, "loss": 0.010937489569187164, "avg_return": 0.8621942400932312, "regret": 0.0009525212226435542, "entropy": 0.06236009672284126, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:43.037988Z", "loop": 11393, "env_steps": 7000473599, "loss": 0.013195742852985859, "avg_return": 0.862829327583313, "regret": 0.0009525212226435542, "entropy": 0.06906347721815109, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:43.892221Z", "loop": 11394, "env_steps": 7001087999, "loss": 0.013759152963757515, "avg_return": 0.8614017963409424, "regret": 0.0009525212226435542, "entropy": 0.06963662058115005, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:44.746509Z", "loop": 11395, "env_steps": 7001702399, "loss": 0.013001165352761745, "avg_return": 0.8607741594314575, "regret": 0.0009525212226435542, "entropy": 0.07339978963136673, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:45.602755Z", "loop": 11396, "env_steps": 7002316799, "loss": 0.013242143206298351, "avg_return": 0.8611357808113098, "regret": 0.0009525212226435542, "entropy": 0.07012125849723816, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:46.457334Z", "loop": 11397, "env_steps": 7002931199, "loss": 0.012806153856217861, "avg_return": 0.8614495992660522, "regret": 0.0009525212226435542, "entropy": 0.06991080194711685, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:47.310965Z", "loop": 11398, "env_steps": 7003545599, "loss": 0.014162765815854073, "avg_return": 0.8606656193733215, "regret": 0.0009525212226435542, "entropy": 0.0711846873164177, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:48.163980Z", "loop": 11399, "env_steps": 7004159999, "loss": 0.012843615375459194, "avg_return": 0.8616681098937988, "regret": 0.0009525212226435542, "entropy": 0.06909910589456558, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:49.057504Z", "loop": 11400, "env_steps": 7004774399, "loss": 0.01340015884488821, "avg_return": 0.8606948256492615, "regret": 0.001805078354664147, "entropy": 0.06706112623214722, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:49.911819Z", "loop": 11401, "env_steps": 7005388799, "loss": 0.011521684005856514, "avg_return": 0.8628175258636475, "regret": 0.001805078354664147, "entropy": 0.06396684050559998, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:50.768053Z", "loop": 11402, "env_steps": 7006003199, "loss": 0.011079201474785805, "avg_return": 0.8618510961532593, "regret": 0.001805078354664147, "entropy": 0.06292776763439178, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:51.622861Z", "loop": 11403, "env_steps": 7006617599, "loss": 0.011457947082817554, "avg_return": 0.8617720603942871, "regret": 0.001805078354664147, "entropy": 0.06464223563671112, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:52.477660Z", "loop": 11404, "env_steps": 7007231999, "loss": 0.012550721876323223, "avg_return": 0.8616869449615479, "regret": 0.001805078354664147, "entropy": 0.06953929364681244, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:53.332311Z", "loop": 11405, "env_steps": 7007846399, "loss": 0.011448433622717857, "avg_return": 0.8630043864250183, "regret": 0.001805078354664147, "entropy": 0.06293431669473648, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:54.187731Z", "loop": 11406, "env_steps": 7008460799, "loss": 0.012005173601210117, "avg_return": 0.8620164394378662, "regret": 0.001805078354664147, "entropy": 0.0662217065691948, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:55.041500Z", "loop": 11407, "env_steps": 7009075199, "loss": 0.01232381071895361, "avg_return": 0.8619470596313477, "regret": 0.001805078354664147, "entropy": 0.0659215971827507, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:55.896094Z", "loop": 11408, "env_steps": 7009689599, "loss": 0.011264362372457981, "avg_return": 0.862449586391449, "regret": 0.001805078354664147, "entropy": 0.06695766746997833, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:56.751764Z", "loop": 11409, "env_steps": 7010303999, "loss": 0.011167331598699093, "avg_return": 0.8625149726867676, "regret": 0.001805078354664147, "entropy": 0.06426754593849182, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:57.647218Z", "loop": 11410, "env_steps": 7010918399, "loss": 0.012197195552289486, "avg_return": 0.8610819578170776, "regret": 0.0009905888000503182, "entropy": 0.06670217961072922, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:58.501209Z", "loop": 11411, "env_steps": 7011532799, "loss": 0.011742934584617615, "avg_return": 0.8615651726722717, "regret": 0.0009905888000503182, "entropy": 0.06613849848508835, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:06:59.355417Z", "loop": 11412, "env_steps": 7012147199, "loss": 0.012708233669400215, "avg_return": 0.8619840741157532, "regret": 0.0009905888000503182, "entropy": 0.06605751067399979, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:00.209433Z", "loop": 11413, "env_steps": 7012761599, "loss": 0.012658009305596352, "avg_return": 0.8625247478485107, "regret": 0.0009905888000503182, "entropy": 0.06610870361328125, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:01.063627Z", "loop": 11414, "env_steps": 7013375999, "loss": 0.011505745351314545, "avg_return": 0.8638405799865723, "regret": 0.0009905888000503182, "entropy": 0.06329505145549774, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:01.917815Z", "loop": 11415, "env_steps": 7013990399, "loss": 0.012145076878368855, "avg_return": 0.8622561097145081, "regret": 0.0009905888000503182, "entropy": 0.06534416973590851, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:02.771623Z", "loop": 11416, "env_steps": 7014604799, "loss": 0.012177075259387493, "avg_return": 0.8616859316825867, "regret": 0.0009905888000503182, "entropy": 0.06620278209447861, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:03.625023Z", "loop": 11417, "env_steps": 7015219199, "loss": 0.013015891425311565, "avg_return": 0.8615991473197937, "regret": 0.0009905888000503182, "entropy": 0.0667332112789154, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:04.478822Z", "loop": 11418, "env_steps": 7015833599, "loss": 0.01137124840170145, "avg_return": 0.8629297018051147, "regret": 0.0009905888000503182, "entropy": 0.06550140678882599, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:05.333438Z", "loop": 11419, "env_steps": 7016447999, "loss": 0.012491188012063503, "avg_return": 0.8629232048988342, "regret": 0.0009905888000503182, "entropy": 0.0632668286561966, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:06.226368Z", "loop": 11420, "env_steps": 7017062399, "loss": 0.012330680154263973, "avg_return": 0.8636994361877441, "regret": 0.0006941693718545139, "entropy": 0.06473850458860397, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:07.079399Z", "loop": 11421, "env_steps": 7017676799, "loss": 0.012387956492602825, "avg_return": 0.8636157512664795, "regret": 0.0006941693718545139, "entropy": 0.06664762645959854, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:07.933148Z", "loop": 11422, "env_steps": 7018291199, "loss": 0.013692515902221203, "avg_return": 0.862403392791748, "regret": 0.0006941693718545139, "entropy": 0.07010473310947418, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:08.787929Z", "loop": 11423, "env_steps": 7018905599, "loss": 0.013380770571529865, "avg_return": 0.8619797825813293, "regret": 0.0006941693718545139, "entropy": 0.06850156933069229, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:09.643627Z", "loop": 11424, "env_steps": 7019519999, "loss": 0.012434401549398899, "avg_return": 0.8638902902603149, "regret": 0.0006941693718545139, "entropy": 0.06711723655462265, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:10.498124Z", "loop": 11425, "env_steps": 7020134399, "loss": 0.01349949836730957, "avg_return": 0.8635380268096924, "regret": 0.0006941693718545139, "entropy": 0.07009420543909073, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:11.351754Z", "loop": 11426, "env_steps": 7020748799, "loss": 0.01223182212561369, "avg_return": 0.8621885180473328, "regret": 0.0006941693718545139, "entropy": 0.06427984684705734, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:12.205834Z", "loop": 11427, "env_steps": 7021363199, "loss": 0.014211306348443031, "avg_return": 0.8632614612579346, "regret": 0.0006941693718545139, "entropy": 0.0732688307762146, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:13.061915Z", "loop": 11428, "env_steps": 7021977599, "loss": 0.013357813470065594, "avg_return": 0.8633486032485962, "regret": 0.0006941693718545139, "entropy": 0.07074452936649323, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:13.916307Z", "loop": 11429, "env_steps": 7022591999, "loss": 0.01429783459752798, "avg_return": 0.8620192408561707, "regret": 0.0006941693718545139, "entropy": 0.07153269648551941, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:14.808174Z", "loop": 11430, "env_steps": 7023206399, "loss": 0.014798738062381744, "avg_return": 0.8635843992233276, "regret": 0.000734209839720279, "entropy": 0.07881004363298416, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:15.661732Z", "loop": 11431, "env_steps": 7023820799, "loss": 0.016517335548996925, "avg_return": 0.862632691860199, "regret": 0.000734209839720279, "entropy": 0.08574791252613068, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:16.517764Z", "loop": 11432, "env_steps": 7024435199, "loss": 0.01643305830657482, "avg_return": 0.8626642227172852, "regret": 0.000734209839720279, "entropy": 0.08549369126558304, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:17.372330Z", "loop": 11433, "env_steps": 7025049599, "loss": 0.01769624836742878, "avg_return": 0.86075359582901, "regret": 0.000734209839720279, "entropy": 0.09125565737485886, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:18.226575Z", "loop": 11434, "env_steps": 7025663999, "loss": 0.019925899803638458, "avg_return": 0.8617265820503235, "regret": 0.000734209839720279, "entropy": 0.09997531026601791, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:19.082102Z", "loop": 11435, "env_steps": 7026278399, "loss": 0.021371541544795036, "avg_return": 0.860344648361206, "regret": 0.000734209839720279, "entropy": 0.10728316009044647, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:19.936105Z", "loop": 11436, "env_steps": 7026892799, "loss": 0.02259725145995617, "avg_return": 0.8618343472480774, "regret": 0.000734209839720279, "entropy": 0.11378539353609085, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:20.790322Z", "loop": 11437, "env_steps": 7027507199, "loss": 0.02248852141201496, "avg_return": 0.8603594303131104, "regret": 0.000734209839720279, "entropy": 0.11398506909608841, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:21.644024Z", "loop": 11438, "env_steps": 7028121599, "loss": 0.02039370685815811, "avg_return": 0.8619133830070496, "regret": 0.000734209839720279, "entropy": 0.10618656873703003, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:22.497291Z", "loop": 11439, "env_steps": 7028735999, "loss": 0.02255740389227867, "avg_return": 0.8611969947814941, "regret": 0.000734209839720279, "entropy": 0.11262261867523193, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:23.388927Z", "loop": 11440, "env_steps": 7029350399, "loss": 0.02366095967590809, "avg_return": 0.8605241179466248, "regret": 0.0032304469496011734, "entropy": 0.12349025905132294, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:24.242854Z", "loop": 11441, "env_steps": 7029964799, "loss": 0.025407394394278526, "avg_return": 0.8587689399719238, "regret": 0.0032304469496011734, "entropy": 0.1300707906484604, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:25.096151Z", "loop": 11442, "env_steps": 7030579199, "loss": 0.02591310814023018, "avg_return": 0.8578230738639832, "regret": 0.0032304469496011734, "entropy": 0.13261479139328003, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:25.949453Z", "loop": 11443, "env_steps": 7031193599, "loss": 0.025799712166190147, "avg_return": 0.8550618886947632, "regret": 0.0032304469496011734, "entropy": 0.13869209587574005, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:26.803503Z", "loop": 11444, "env_steps": 7031807999, "loss": 0.028942469507455826, "avg_return": 0.8527067303657532, "regret": 0.0032304469496011734, "entropy": 0.14958785474300385, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:27.657733Z", "loop": 11445, "env_steps": 7032422399, "loss": 0.028162319213151932, "avg_return": 0.8517966270446777, "regret": 0.0032304469496011734, "entropy": 0.152881920337677, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:28.512353Z", "loop": 11446, "env_steps": 7033036799, "loss": 0.028111552819609642, "avg_return": 0.8564523458480835, "regret": 0.0032304469496011734, "entropy": 0.15383540093898773, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:29.366162Z", "loop": 11447, "env_steps": 7033651199, "loss": 0.02723551169037819, "avg_return": 0.8587280511856079, "regret": 0.0032304469496011734, "entropy": 0.13809624314308167, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:30.219382Z", "loop": 11448, "env_steps": 7034265599, "loss": 0.023429200053215027, "avg_return": 0.8602643013000488, "regret": 0.0032304469496011734, "entropy": 0.12169347703456879, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:31.073080Z", "loop": 11449, "env_steps": 7034879999, "loss": 0.02232022024691105, "avg_return": 0.8631872534751892, "regret": 0.0032304469496011734, "entropy": 0.11374475806951523, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:31.966127Z", "loop": 11450, "env_steps": 7035494399, "loss": 0.020848846063017845, "avg_return": 0.8624885082244873, "regret": 0.0008853903855197132, "entropy": 0.10501983761787415, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:32.820870Z", "loop": 11451, "env_steps": 7036108799, "loss": 0.019591839984059334, "avg_return": 0.8638206124305725, "regret": 0.0008853903855197132, "entropy": 0.0969044640660286, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:33.675404Z", "loop": 11452, "env_steps": 7036723199, "loss": 0.01901855133473873, "avg_return": 0.8627824187278748, "regret": 0.0008853903855197132, "entropy": 0.09627954661846161, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:34.529606Z", "loop": 11453, "env_steps": 7037337599, "loss": 0.018590139225125313, "avg_return": 0.8627409338951111, "regret": 0.0008853903855197132, "entropy": 0.09429781883955002, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:35.384625Z", "loop": 11454, "env_steps": 7037951999, "loss": 0.019826775416731834, "avg_return": 0.8621729016304016, "regret": 0.0008853903855197132, "entropy": 0.09558901935815811, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:36.237882Z", "loop": 11455, "env_steps": 7038566399, "loss": 0.01871306262910366, "avg_return": 0.8612987399101257, "regret": 0.0008853903855197132, "entropy": 0.0955863669514656, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:37.091571Z", "loop": 11456, "env_steps": 7039180799, "loss": 0.01755213923752308, "avg_return": 0.8628224730491638, "regret": 0.0008853903855197132, "entropy": 0.09310703724622726, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:37.945068Z", "loop": 11457, "env_steps": 7039795199, "loss": 0.018745509907603264, "avg_return": 0.8613736033439636, "regret": 0.0008853903855197132, "entropy": 0.09565390646457672, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:38.798644Z", "loop": 11458, "env_steps": 7040409599, "loss": 0.018624909222126007, "avg_return": 0.8623272180557251, "regret": 0.0008853903855197132, "entropy": 0.09482349455356598, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:39.653143Z", "loop": 11459, "env_steps": 7041023999, "loss": 0.01783319003880024, "avg_return": 0.8613412976264954, "regret": 0.0008853903855197132, "entropy": 0.08995870500802994, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:40.545953Z", "loop": 11460, "env_steps": 7041638399, "loss": 0.019019659608602524, "avg_return": 0.8620976209640503, "regret": 0.001566156162880361, "entropy": 0.09788808971643448, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:41.399610Z", "loop": 11461, "env_steps": 7042252799, "loss": 0.0185337346047163, "avg_return": 0.8632662892341614, "regret": 0.001566156162880361, "entropy": 0.09321796894073486, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:42.253755Z", "loop": 11462, "env_steps": 7042867199, "loss": 0.019500350579619408, "avg_return": 0.8628981709480286, "regret": 0.001566156162880361, "entropy": 0.10011283308267593, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:43.108453Z", "loop": 11463, "env_steps": 7043481599, "loss": 0.019921960309147835, "avg_return": 0.8633255958557129, "regret": 0.001566156162880361, "entropy": 0.10105361044406891, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:43.962454Z", "loop": 11464, "env_steps": 7044095999, "loss": 0.017741987481713295, "avg_return": 0.8617754578590393, "regret": 0.001566156162880361, "entropy": 0.09255789965391159, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:44.816470Z", "loop": 11465, "env_steps": 7044710399, "loss": 0.018582748249173164, "avg_return": 0.8624946475028992, "regret": 0.001566156162880361, "entropy": 0.09857980161905289, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:45.669319Z", "loop": 11466, "env_steps": 7045324799, "loss": 0.01828780025243759, "avg_return": 0.8618403077125549, "regret": 0.001566156162880361, "entropy": 0.09575583040714264, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:46.522364Z", "loop": 11467, "env_steps": 7045939199, "loss": 0.020255617797374725, "avg_return": 0.8599920868873596, "regret": 0.001566156162880361, "entropy": 0.10233690589666367, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:47.376607Z", "loop": 11468, "env_steps": 7046553599, "loss": 0.02005365863442421, "avg_return": 0.8595322966575623, "regret": 0.001566156162880361, "entropy": 0.10410867631435394, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:48.230754Z", "loop": 11469, "env_steps": 7047167999, "loss": 0.019257403910160065, "avg_return": 0.8591030240058899, "regret": 0.001566156162880361, "entropy": 0.1028413325548172, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:49.125182Z", "loop": 11470, "env_steps": 7047782399, "loss": 0.02023180201649666, "avg_return": 0.8609218597412109, "regret": 0.002360474318265915, "entropy": 0.10374370217323303, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:49.979520Z", "loop": 11471, "env_steps": 7048396799, "loss": 0.020070571452379227, "avg_return": 0.86167311668396, "regret": 0.002360474318265915, "entropy": 0.10378121584653854, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:50.833972Z", "loop": 11472, "env_steps": 7049011199, "loss": 0.01827886514365673, "avg_return": 0.8618003726005554, "regret": 0.002360474318265915, "entropy": 0.09822779148817062, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:51.688318Z", "loop": 11473, "env_steps": 7049625599, "loss": 0.019490836188197136, "avg_return": 0.8626160621643066, "regret": 0.002360474318265915, "entropy": 0.09818815439939499, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:52.543079Z", "loop": 11474, "env_steps": 7050239999, "loss": 0.017802612856030464, "avg_return": 0.8624143600463867, "regret": 0.002360474318265915, "entropy": 0.09055010974407196, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:53.397271Z", "loop": 11475, "env_steps": 7050854399, "loss": 0.01790274679660797, "avg_return": 0.8625685572624207, "regret": 0.002360474318265915, "entropy": 0.09196628630161285, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:54.250924Z", "loop": 11476, "env_steps": 7051468799, "loss": 0.01915324479341507, "avg_return": 0.8627697825431824, "regret": 0.002360474318265915, "entropy": 0.09756166487932205, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:55.104807Z", "loop": 11477, "env_steps": 7052083199, "loss": 0.019744159653782845, "avg_return": 0.8634027242660522, "regret": 0.002360474318265915, "entropy": 0.09817559272050858, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:55.958800Z", "loop": 11478, "env_steps": 7052697599, "loss": 0.019145332276821136, "avg_return": 0.8637620210647583, "regret": 0.002360474318265915, "entropy": 0.09890720248222351, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:56.813350Z", "loop": 11479, "env_steps": 7053311999, "loss": 0.018381180241703987, "avg_return": 0.862776517868042, "regret": 0.002360474318265915, "entropy": 0.0901295393705368, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:57.706642Z", "loop": 11480, "env_steps": 7053926399, "loss": 0.017454614862799644, "avg_return": 0.8637819886207581, "regret": 0.0006232043961063027, "entropy": 0.08774390816688538, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:58.560648Z", "loop": 11481, "env_steps": 7054540799, "loss": 0.01706397533416748, "avg_return": 0.8629767298698425, "regret": 0.0006232043961063027, "entropy": 0.08964211493730545, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:07:59.415410Z", "loop": 11482, "env_steps": 7055155199, "loss": 0.015874870121479034, "avg_return": 0.8626546263694763, "regret": 0.0006232043961063027, "entropy": 0.08292398601770401, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:00.269908Z", "loop": 11483, "env_steps": 7055769599, "loss": 0.017579341307282448, "avg_return": 0.8632246851921082, "regret": 0.0006232043961063027, "entropy": 0.0900464728474617, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:01.124004Z", "loop": 11484, "env_steps": 7056383999, "loss": 0.01809181272983551, "avg_return": 0.8611927628517151, "regret": 0.0006232043961063027, "entropy": 0.09562381356954575, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:01.977310Z", "loop": 11485, "env_steps": 7056998399, "loss": 0.019250959157943726, "avg_return": 0.8621070384979248, "regret": 0.0006232043961063027, "entropy": 0.09854075312614441, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:02.832548Z", "loop": 11486, "env_steps": 7057612799, "loss": 0.022709619253873825, "avg_return": 0.8627020716667175, "regret": 0.0006232043961063027, "entropy": 0.11022139340639114, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:03.688415Z", "loop": 11487, "env_steps": 7058227199, "loss": 0.023314081132411957, "avg_return": 0.8620591163635254, "regret": 0.0006232043961063027, "entropy": 0.11686515063047409, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:04.542565Z", "loop": 11488, "env_steps": 7058841599, "loss": 0.0243558119982481, "avg_return": 0.8626164197921753, "regret": 0.0006232043961063027, "entropy": 0.12314741313457489, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:05.397081Z", "loop": 11489, "env_steps": 7059455999, "loss": 0.025164619088172913, "avg_return": 0.8618685007095337, "regret": 0.0006232043961063027, "entropy": 0.11968861520290375, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:06.292424Z", "loop": 11490, "env_steps": 7060070399, "loss": 0.025944391265511513, "avg_return": 0.8614088892936707, "regret": 0.0018913927488029003, "entropy": 0.12958166003227234, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:07.147999Z", "loop": 11491, "env_steps": 7060684799, "loss": 0.026148930191993713, "avg_return": 0.8612897992134094, "regret": 0.0018913927488029003, "entropy": 0.12548047304153442, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:08.002035Z", "loop": 11492, "env_steps": 7061299199, "loss": 0.026169156655669212, "avg_return": 0.8625525236129761, "regret": 0.0018913927488029003, "entropy": 0.13250119984149933, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:08.855370Z", "loop": 11493, "env_steps": 7061913599, "loss": 0.023609859868884087, "avg_return": 0.8623573780059814, "regret": 0.0018913927488029003, "entropy": 0.1176304817199707, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:09.708639Z", "loop": 11494, "env_steps": 7062527999, "loss": 0.022165421396493912, "avg_return": 0.8618674874305725, "regret": 0.0018913927488029003, "entropy": 0.11173485964536667, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:10.562598Z", "loop": 11495, "env_steps": 7063142399, "loss": 0.019683055579662323, "avg_return": 0.861152172088623, "regret": 0.0018913927488029003, "entropy": 0.10215811431407928, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:11.416327Z", "loop": 11496, "env_steps": 7063756799, "loss": 0.018481697887182236, "avg_return": 0.8637939691543579, "regret": 0.0018913927488029003, "entropy": 0.09550531953573227, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:12.270457Z", "loop": 11497, "env_steps": 7064371199, "loss": 0.018083466216921806, "avg_return": 0.8626158833503723, "regret": 0.0018913927488029003, "entropy": 0.0918726995587349, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:13.123452Z", "loop": 11498, "env_steps": 7064985599, "loss": 0.01577821932733059, "avg_return": 0.8614503145217896, "regret": 0.0018913927488029003, "entropy": 0.08407671004533768, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:13.977266Z", "loop": 11499, "env_steps": 7065599999, "loss": 0.015807051211595535, "avg_return": 0.8621609807014465, "regret": 0.0018913927488029003, "entropy": 0.0863039642572403, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:14.869293Z", "loop": 11500, "env_steps": 7066214399, "loss": 0.01615939289331436, "avg_return": 0.8641567230224609, "regret": 0.0009668111451901495, "entropy": 0.0864802747964859, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:15.723160Z", "loop": 11501, "env_steps": 7066828799, "loss": 0.016931412741541862, "avg_return": 0.8629812002182007, "regret": 0.0009668111451901495, "entropy": 0.08544586598873138, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:16.577436Z", "loop": 11502, "env_steps": 7067443199, "loss": 0.01562557741999626, "avg_return": 0.8618448972702026, "regret": 0.0009668111451901495, "entropy": 0.08225465565919876, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:17.433537Z", "loop": 11503, "env_steps": 7068057599, "loss": 0.016215069219470024, "avg_return": 0.862481415271759, "regret": 0.0009668111451901495, "entropy": 0.08477090299129486, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:18.288206Z", "loop": 11504, "env_steps": 7068671999, "loss": 0.01709161140024662, "avg_return": 0.8618995547294617, "regret": 0.0009668111451901495, "entropy": 0.08637166023254395, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:19.143561Z", "loop": 11505, "env_steps": 7069286399, "loss": 0.01627606898546219, "avg_return": 0.8607655763626099, "regret": 0.0009668111451901495, "entropy": 0.08375227451324463, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:19.998182Z", "loop": 11506, "env_steps": 7069900799, "loss": 0.016770416870713234, "avg_return": 0.8634436130523682, "regret": 0.0009668111451901495, "entropy": 0.08262798190116882, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:20.852211Z", "loop": 11507, "env_steps": 7070515199, "loss": 0.019046621397137642, "avg_return": 0.8625763058662415, "regret": 0.0009668111451901495, "entropy": 0.09360483288764954, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:21.706693Z", "loop": 11508, "env_steps": 7071129599, "loss": 0.01785895973443985, "avg_return": 0.8629389405250549, "regret": 0.0009668111451901495, "entropy": 0.08556564897298813, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:22.561435Z", "loop": 11509, "env_steps": 7071743999, "loss": 0.01704779453575611, "avg_return": 0.861843466758728, "regret": 0.0009668111451901495, "entropy": 0.08655983954668045, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:23.458044Z", "loop": 11510, "env_steps": 7072358399, "loss": 0.01687096618115902, "avg_return": 0.8622918128967285, "regret": 0.0005965214804746211, "entropy": 0.08714965730905533, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:24.311965Z", "loop": 11511, "env_steps": 7072972799, "loss": 0.016635460779070854, "avg_return": 0.8631827235221863, "regret": 0.0005965214804746211, "entropy": 0.08279877156019211, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:25.165149Z", "loop": 11512, "env_steps": 7073587199, "loss": 0.016766740009188652, "avg_return": 0.8634681105613708, "regret": 0.0005965214804746211, "entropy": 0.08235454559326172, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:26.019056Z", "loop": 11513, "env_steps": 7074201599, "loss": 0.017112096771597862, "avg_return": 0.86368328332901, "regret": 0.0005965214804746211, "entropy": 0.08350290358066559, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:26.873641Z", "loop": 11514, "env_steps": 7074815999, "loss": 0.016482485458254814, "avg_return": 0.8631749749183655, "regret": 0.0005965214804746211, "entropy": 0.08388467133045197, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:27.727801Z", "loop": 11515, "env_steps": 7075430399, "loss": 0.015821119770407677, "avg_return": 0.8643117547035217, "regret": 0.0005965214804746211, "entropy": 0.07709156721830368, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:28.581019Z", "loop": 11516, "env_steps": 7076044799, "loss": 0.016693169251084328, "avg_return": 0.86273193359375, "regret": 0.0005965214804746211, "entropy": 0.08099893480539322, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:29.433982Z", "loop": 11517, "env_steps": 7076659199, "loss": 0.015585141256451607, "avg_return": 0.8626171946525574, "regret": 0.0005965214804746211, "entropy": 0.07779200375080109, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:30.288481Z", "loop": 11518, "env_steps": 7077273599, "loss": 0.015799855813384056, "avg_return": 0.8635494112968445, "regret": 0.0005965214804746211, "entropy": 0.07939853519201279, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:31.141927Z", "loop": 11519, "env_steps": 7077887999, "loss": 0.014957422390580177, "avg_return": 0.8619204759597778, "regret": 0.0005965214804746211, "entropy": 0.07960100471973419, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:32.035100Z", "loop": 11520, "env_steps": 7078502399, "loss": 0.016424451023340225, "avg_return": 0.8631921410560608, "regret": 0.0008063004934228957, "entropy": 0.08451119810342789, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:32.888681Z", "loop": 11521, "env_steps": 7079116799, "loss": 0.015384797938168049, "avg_return": 0.8616076111793518, "regret": 0.0008063004934228957, "entropy": 0.0784069076180458, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:33.743249Z", "loop": 11522, "env_steps": 7079731199, "loss": 0.017043769359588623, "avg_return": 0.8625766038894653, "regret": 0.0008063004934228957, "entropy": 0.08701483905315399, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:34.597368Z", "loop": 11523, "env_steps": 7080345599, "loss": 0.018474958837032318, "avg_return": 0.8610045313835144, "regret": 0.0008063004934228957, "entropy": 0.09225677698850632, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:35.450615Z", "loop": 11524, "env_steps": 7080959999, "loss": 0.01773887127637863, "avg_return": 0.8627386689186096, "regret": 0.0008063004934228957, "entropy": 0.08941590785980225, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:36.303999Z", "loop": 11525, "env_steps": 7081574399, "loss": 0.017133932560682297, "avg_return": 0.8617993593215942, "regret": 0.0008063004934228957, "entropy": 0.08366676419973373, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:37.158472Z", "loop": 11526, "env_steps": 7082188799, "loss": 0.01640557125210762, "avg_return": 0.8613430261611938, "regret": 0.0008063004934228957, "entropy": 0.08474820107221603, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:38.012816Z", "loop": 11527, "env_steps": 7082803199, "loss": 0.015754854306578636, "avg_return": 0.8620138764381409, "regret": 0.0008063004934228957, "entropy": 0.08338359743356705, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:38.867062Z", "loop": 11528, "env_steps": 7083417599, "loss": 0.016264313831925392, "avg_return": 0.8598880171775818, "regret": 0.0008063004934228957, "entropy": 0.0871090218424797, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:39.721382Z", "loop": 11529, "env_steps": 7084031999, "loss": 0.017785588279366493, "avg_return": 0.8613293766975403, "regret": 0.0008063004934228957, "entropy": 0.09140600264072418, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:40.617346Z", "loop": 11530, "env_steps": 7084646399, "loss": 0.018141262233257294, "avg_return": 0.8611335158348083, "regret": 0.0023023365065455437, "entropy": 0.0908798798918724, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:41.471178Z", "loop": 11531, "env_steps": 7085260799, "loss": 0.01930839754641056, "avg_return": 0.8603613376617432, "regret": 0.0023023365065455437, "entropy": 0.1005905419588089, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:42.325064Z", "loop": 11532, "env_steps": 7085875199, "loss": 0.019975148141384125, "avg_return": 0.8613241910934448, "regret": 0.0023023365065455437, "entropy": 0.10172613710165024, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:43.179418Z", "loop": 11533, "env_steps": 7086489599, "loss": 0.020302699878811836, "avg_return": 0.860418438911438, "regret": 0.0023023365065455437, "entropy": 0.10147352516651154, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:44.032376Z", "loop": 11534, "env_steps": 7087103999, "loss": 0.020036472007632256, "avg_return": 0.8601970672607422, "regret": 0.0023023365065455437, "entropy": 0.1039629727602005, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:44.885168Z", "loop": 11535, "env_steps": 7087718399, "loss": 0.020973531529307365, "avg_return": 0.8604313135147095, "regret": 0.0023023365065455437, "entropy": 0.1055813655257225, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:45.738461Z", "loop": 11536, "env_steps": 7088332799, "loss": 0.01972695253789425, "avg_return": 0.861724853515625, "regret": 0.0023023365065455437, "entropy": 0.09804220497608185, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:46.592318Z", "loop": 11537, "env_steps": 7088947199, "loss": 0.01884862594306469, "avg_return": 0.8609570264816284, "regret": 0.0023023365065455437, "entropy": 0.09665081650018692, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:47.446756Z", "loop": 11538, "env_steps": 7089561599, "loss": 0.019577480852603912, "avg_return": 0.8630350232124329, "regret": 0.0023023365065455437, "entropy": 0.1005016416311264, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:48.299989Z", "loop": 11539, "env_steps": 7090175999, "loss": 0.01907031238079071, "avg_return": 0.8618667721748352, "regret": 0.0023023365065455437, "entropy": 0.09754771739244461, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:49.192878Z", "loop": 11540, "env_steps": 7090790399, "loss": 0.018440593034029007, "avg_return": 0.8619930148124695, "regret": 0.0012925600167363882, "entropy": 0.09392867237329483, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:50.046760Z", "loop": 11541, "env_steps": 7091404799, "loss": 0.018118569627404213, "avg_return": 0.8623800873756409, "regret": 0.0012925600167363882, "entropy": 0.09597644209861755, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:50.901705Z", "loop": 11542, "env_steps": 7092019199, "loss": 0.01744813658297062, "avg_return": 0.863822877407074, "regret": 0.0012925600167363882, "entropy": 0.093202143907547, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:51.755574Z", "loop": 11543, "env_steps": 7092633599, "loss": 0.016825562343001366, "avg_return": 0.8632531762123108, "regret": 0.0012925600167363882, "entropy": 0.08788015693426132, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:52.609402Z", "loop": 11544, "env_steps": 7093247999, "loss": 0.016817869618535042, "avg_return": 0.8620489835739136, "regret": 0.0012925600167363882, "entropy": 0.08986268192529678, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:53.463056Z", "loop": 11545, "env_steps": 7093862399, "loss": 0.016723908483982086, "avg_return": 0.8638454675674438, "regret": 0.0012925600167363882, "entropy": 0.0866425558924675, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:54.317343Z", "loop": 11546, "env_steps": 7094476799, "loss": 0.016141286119818687, "avg_return": 0.8618119359016418, "regret": 0.0012925600167363882, "entropy": 0.08560090512037277, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:55.170646Z", "loop": 11547, "env_steps": 7095091199, "loss": 0.0160613264888525, "avg_return": 0.8639360666275024, "regret": 0.0012925600167363882, "entropy": 0.08683961629867554, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:56.024920Z", "loop": 11548, "env_steps": 7095705599, "loss": 0.014896963723003864, "avg_return": 0.8616728186607361, "regret": 0.0012925600167363882, "entropy": 0.08006338775157928, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:56.879655Z", "loop": 11549, "env_steps": 7096319999, "loss": 0.014843054115772247, "avg_return": 0.8619817495346069, "regret": 0.0012925600167363882, "entropy": 0.07912041246891022, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:57.773452Z", "loop": 11550, "env_steps": 7096934399, "loss": 0.015961695462465286, "avg_return": 0.86261385679245, "regret": 0.0008207387290894985, "entropy": 0.08289240300655365, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:58.627770Z", "loop": 11551, "env_steps": 7097548799, "loss": 0.015251271426677704, "avg_return": 0.8621106147766113, "regret": 0.0008207387290894985, "entropy": 0.08006210625171661, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:08:59.480941Z", "loop": 11552, "env_steps": 7098163199, "loss": 0.0156792514026165, "avg_return": 0.8625319600105286, "regret": 0.0008207387290894985, "entropy": 0.08344472944736481, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:00.335629Z", "loop": 11553, "env_steps": 7098777599, "loss": 0.016004223376512527, "avg_return": 0.8625492453575134, "regret": 0.0008207387290894985, "entropy": 0.0843735933303833, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:01.190381Z", "loop": 11554, "env_steps": 7099391999, "loss": 0.014600466005504131, "avg_return": 0.8625248670578003, "regret": 0.0008207387290894985, "entropy": 0.07768446207046509, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:02.045967Z", "loop": 11555, "env_steps": 7100006399, "loss": 0.014790411107242107, "avg_return": 0.8642401099205017, "regret": 0.0008207387290894985, "entropy": 0.0789809450507164, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:02.900140Z", "loop": 11556, "env_steps": 7100620799, "loss": 0.014481805264949799, "avg_return": 0.8626483082771301, "regret": 0.0008207387290894985, "entropy": 0.07889565080404282, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:03.755812Z", "loop": 11557, "env_steps": 7101235199, "loss": 0.01576758548617363, "avg_return": 0.8614750504493713, "regret": 0.0008207387290894985, "entropy": 0.08201146870851517, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:04.610632Z", "loop": 11558, "env_steps": 7101849599, "loss": 0.013842001557350159, "avg_return": 0.8624877333641052, "regret": 0.0008207387290894985, "entropy": 0.07999621331691742, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:05.465011Z", "loop": 11559, "env_steps": 7102463999, "loss": 0.01526314951479435, "avg_return": 0.8629549145698547, "regret": 0.0008207387290894985, "entropy": 0.07903299480676651, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:06.358387Z", "loop": 11560, "env_steps": 7103078399, "loss": 0.014326735399663448, "avg_return": 0.8623278737068176, "regret": 0.0008421176462434232, "entropy": 0.07947568595409393, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:07.212418Z", "loop": 11561, "env_steps": 7103692799, "loss": 0.014803819358348846, "avg_return": 0.8626043796539307, "regret": 0.0008421176462434232, "entropy": 0.07947513461112976, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:08.066695Z", "loop": 11562, "env_steps": 7104307199, "loss": 0.015652552247047424, "avg_return": 0.8625714182853699, "regret": 0.0008421176462434232, "entropy": 0.07809954136610031, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:08.920668Z", "loop": 11563, "env_steps": 7104921599, "loss": 0.015591996721923351, "avg_return": 0.8620478510856628, "regret": 0.0008421176462434232, "entropy": 0.07921041548252106, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:09.775648Z", "loop": 11564, "env_steps": 7105535999, "loss": 0.016011055558919907, "avg_return": 0.862991988658905, "regret": 0.0008421176462434232, "entropy": 0.07983105629682541, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:10.631719Z", "loop": 11565, "env_steps": 7106150399, "loss": 0.015389124862849712, "avg_return": 0.8616909980773926, "regret": 0.0008421176462434232, "entropy": 0.0791146457195282, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:11.485985Z", "loop": 11566, "env_steps": 7106764799, "loss": 0.016620183363556862, "avg_return": 0.8618921041488647, "regret": 0.0008421176462434232, "entropy": 0.08694539219141006, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:12.340348Z", "loop": 11567, "env_steps": 7107379199, "loss": 0.01629916951060295, "avg_return": 0.8633366227149963, "regret": 0.0008421176462434232, "entropy": 0.08019217103719711, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:13.196340Z", "loop": 11568, "env_steps": 7107993599, "loss": 0.01621701382100582, "avg_return": 0.8615019917488098, "regret": 0.0008421176462434232, "entropy": 0.08320977538824081, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:14.050856Z", "loop": 11569, "env_steps": 7108607999, "loss": 0.017298324033617973, "avg_return": 0.8608422875404358, "regret": 0.0008421176462434232, "entropy": 0.0837312787771225, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:14.945322Z", "loop": 11570, "env_steps": 7109222399, "loss": 0.017309552058577538, "avg_return": 0.8618528246879578, "regret": 0.001450179610401392, "entropy": 0.08627351373434067, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:15.798340Z", "loop": 11571, "env_steps": 7109836799, "loss": 0.017144205048680305, "avg_return": 0.8611505627632141, "regret": 0.001450179610401392, "entropy": 0.08654053509235382, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:16.652900Z", "loop": 11572, "env_steps": 7110451199, "loss": 0.016972476616501808, "avg_return": 0.8619582056999207, "regret": 0.001450179610401392, "entropy": 0.08520781993865967, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:17.508032Z", "loop": 11573, "env_steps": 7111065599, "loss": 0.016763867810368538, "avg_return": 0.8618418574333191, "regret": 0.001450179610401392, "entropy": 0.08264462649822235, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:18.361445Z", "loop": 11574, "env_steps": 7111679999, "loss": 0.016622914001345634, "avg_return": 0.8615198135375977, "regret": 0.001450179610401392, "entropy": 0.08101591467857361, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:19.214736Z", "loop": 11575, "env_steps": 7112294399, "loss": 0.018142057582736015, "avg_return": 0.8623380661010742, "regret": 0.001450179610401392, "entropy": 0.08604081720113754, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:20.068469Z", "loop": 11576, "env_steps": 7112908799, "loss": 0.015843315050005913, "avg_return": 0.8605015277862549, "regret": 0.001450179610401392, "entropy": 0.082938551902771, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:20.923565Z", "loop": 11577, "env_steps": 7113523199, "loss": 0.015581296756863594, "avg_return": 0.8623496890068054, "regret": 0.001450179610401392, "entropy": 0.08008340746164322, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:21.777159Z", "loop": 11578, "env_steps": 7114137599, "loss": 0.015554222278296947, "avg_return": 0.8615965247154236, "regret": 0.001450179610401392, "entropy": 0.07991088926792145, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:22.632666Z", "loop": 11579, "env_steps": 7114751999, "loss": 0.015772273764014244, "avg_return": 0.8609001040458679, "regret": 0.001450179610401392, "entropy": 0.08385113626718521, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:23.526447Z", "loop": 11580, "env_steps": 7115366399, "loss": 0.016502745449543, "avg_return": 0.8622339963912964, "regret": 0.001717168022878468, "entropy": 0.08066986501216888, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:24.381434Z", "loop": 11581, "env_steps": 7115980799, "loss": 0.017209041863679886, "avg_return": 0.8623367547988892, "regret": 0.001717168022878468, "entropy": 0.08303174376487732, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:25.236929Z", "loop": 11582, "env_steps": 7116595199, "loss": 0.01543697901070118, "avg_return": 0.8621436953544617, "regret": 0.001717168022878468, "entropy": 0.07785151153802872, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:26.092308Z", "loop": 11583, "env_steps": 7117209599, "loss": 0.016379764303565025, "avg_return": 0.8613328337669373, "regret": 0.001717168022878468, "entropy": 0.08268781006336212, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:26.947236Z", "loop": 11584, "env_steps": 7117823999, "loss": 0.016500970348715782, "avg_return": 0.8623416423797607, "regret": 0.001717168022878468, "entropy": 0.08078688383102417, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:27.802140Z", "loop": 11585, "env_steps": 7118438399, "loss": 0.01660565845668316, "avg_return": 0.8619646430015564, "regret": 0.001717168022878468, "entropy": 0.08247997611761093, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:28.656460Z", "loop": 11586, "env_steps": 7119052799, "loss": 0.017012884840369225, "avg_return": 0.8634477853775024, "regret": 0.001717168022878468, "entropy": 0.08178696781396866, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:29.510211Z", "loop": 11587, "env_steps": 7119667199, "loss": 0.016996007412672043, "avg_return": 0.8618664741516113, "regret": 0.001717168022878468, "entropy": 0.08483332395553589, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:30.363989Z", "loop": 11588, "env_steps": 7120281599, "loss": 0.016232645139098167, "avg_return": 0.8620137572288513, "regret": 0.001717168022878468, "entropy": 0.08502764999866486, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:31.217681Z", "loop": 11589, "env_steps": 7120895999, "loss": 0.01578168198466301, "avg_return": 0.8616601824760437, "regret": 0.001717168022878468, "entropy": 0.07936354726552963, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:32.111005Z", "loop": 11590, "env_steps": 7121510399, "loss": 0.015393072739243507, "avg_return": 0.8624638319015503, "regret": 0.0008715496514923871, "entropy": 0.07871214300394058, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:32.965899Z", "loop": 11591, "env_steps": 7122124799, "loss": 0.015205003321170807, "avg_return": 0.863562822341919, "regret": 0.0008715496514923871, "entropy": 0.08135081827640533, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:33.819789Z", "loop": 11592, "env_steps": 7122739199, "loss": 0.015230386517941952, "avg_return": 0.8638538718223572, "regret": 0.0008715496514923871, "entropy": 0.07994015514850616, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:34.674380Z", "loop": 11593, "env_steps": 7123353599, "loss": 0.015356932766735554, "avg_return": 0.8629457950592041, "regret": 0.0008715496514923871, "entropy": 0.07707135379314423, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:35.527858Z", "loop": 11594, "env_steps": 7123967999, "loss": 0.015171259641647339, "avg_return": 0.8630821704864502, "regret": 0.0008715496514923871, "entropy": 0.07879801094532013, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:36.382168Z", "loop": 11595, "env_steps": 7124582399, "loss": 0.015320795588195324, "avg_return": 0.8622077703475952, "regret": 0.0008715496514923871, "entropy": 0.07798400521278381, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:37.237494Z", "loop": 11596, "env_steps": 7125196799, "loss": 0.016201460734009743, "avg_return": 0.8631170988082886, "regret": 0.0008715496514923871, "entropy": 0.07969561219215393, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:38.093175Z", "loop": 11597, "env_steps": 7125811199, "loss": 0.015794044360518456, "avg_return": 0.8618496060371399, "regret": 0.0008715496514923871, "entropy": 0.07964304089546204, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:38.948979Z", "loop": 11598, "env_steps": 7126425599, "loss": 0.01625337265431881, "avg_return": 0.8625073432922363, "regret": 0.0008715496514923871, "entropy": 0.07927128672599792, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:39.804780Z", "loop": 11599, "env_steps": 7127039999, "loss": 0.0158963855355978, "avg_return": 0.8622080683708191, "regret": 0.0008715496514923871, "entropy": 0.07805401086807251, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:40.698520Z", "loop": 11600, "env_steps": 7127654399, "loss": 0.01649310812354088, "avg_return": 0.8621319532394409, "regret": 0.0011421192903071642, "entropy": 0.0805622935295105, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:41.553270Z", "loop": 11601, "env_steps": 7128268799, "loss": 0.016614211723208427, "avg_return": 0.861944317817688, "regret": 0.0011421192903071642, "entropy": 0.08117253333330154, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:42.408108Z", "loop": 11602, "env_steps": 7128883199, "loss": 0.015842383727431297, "avg_return": 0.8620282411575317, "regret": 0.0011421192903071642, "entropy": 0.0779031291604042, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:43.262174Z", "loop": 11603, "env_steps": 7129497599, "loss": 0.016534926369786263, "avg_return": 0.8632531762123108, "regret": 0.0011421192903071642, "entropy": 0.07862245291471481, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:44.117948Z", "loop": 11604, "env_steps": 7130111999, "loss": 0.01534146349877119, "avg_return": 0.8633776903152466, "regret": 0.0011421192903071642, "entropy": 0.07528087496757507, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:44.973019Z", "loop": 11605, "env_steps": 7130726399, "loss": 0.0147588225081563, "avg_return": 0.8622968792915344, "regret": 0.0011421192903071642, "entropy": 0.07283123582601547, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:45.827840Z", "loop": 11606, "env_steps": 7131340799, "loss": 0.015489808283746243, "avg_return": 0.8618694543838501, "regret": 0.0011421192903071642, "entropy": 0.07987097650766373, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:46.681696Z", "loop": 11607, "env_steps": 7131955199, "loss": 0.015472627244889736, "avg_return": 0.8602744936943054, "regret": 0.0011421192903071642, "entropy": 0.08099380880594254, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:47.537291Z", "loop": 11608, "env_steps": 7132569599, "loss": 0.017403805628418922, "avg_return": 0.8605316281318665, "regret": 0.0011421192903071642, "entropy": 0.08307484537363052, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:48.392255Z", "loop": 11609, "env_steps": 7133183999, "loss": 0.018199509009718895, "avg_return": 0.8595989942550659, "regret": 0.0011421192903071642, "entropy": 0.090550996363163, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:49.287330Z", "loop": 11610, "env_steps": 7133798399, "loss": 0.018519235774874687, "avg_return": 0.8576359152793884, "regret": 0.004779621493071318, "entropy": 0.09073318541049957, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:50.141281Z", "loop": 11611, "env_steps": 7134412799, "loss": 0.018242008984088898, "avg_return": 0.8591093420982361, "regret": 0.004779621493071318, "entropy": 0.08917196840047836, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:50.996200Z", "loop": 11612, "env_steps": 7135027199, "loss": 0.017884869128465652, "avg_return": 0.8548301458358765, "regret": 0.004779621493071318, "entropy": 0.08636363595724106, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:51.850226Z", "loop": 11613, "env_steps": 7135641599, "loss": 0.01765447109937668, "avg_return": 0.8579607605934143, "regret": 0.004779621493071318, "entropy": 0.08635158836841583, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:52.704406Z", "loop": 11614, "env_steps": 7136255999, "loss": 0.015934864059090614, "avg_return": 0.8590702414512634, "regret": 0.004779621493071318, "entropy": 0.08412831276655197, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:53.558199Z", "loop": 11615, "env_steps": 7136870399, "loss": 0.017163574695587158, "avg_return": 0.8611834645271301, "regret": 0.004779621493071318, "entropy": 0.08625167608261108, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:54.412400Z", "loop": 11616, "env_steps": 7137484799, "loss": 0.016389450058341026, "avg_return": 0.8623750805854797, "regret": 0.004779621493071318, "entropy": 0.0819358080625534, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:55.265847Z", "loop": 11617, "env_steps": 7138099199, "loss": 0.016405796632170677, "avg_return": 0.8613795042037964, "regret": 0.004779621493071318, "entropy": 0.08360663056373596, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:56.120309Z", "loop": 11618, "env_steps": 7138713599, "loss": 0.01570787839591503, "avg_return": 0.8637280464172363, "regret": 0.004779621493071318, "entropy": 0.08592233806848526, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:56.974591Z", "loop": 11619, "env_steps": 7139327999, "loss": 0.017007479444146156, "avg_return": 0.8632328510284424, "regret": 0.004779621493071318, "entropy": 0.08688626438379288, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:57.868117Z", "loop": 11620, "env_steps": 7139942399, "loss": 0.01731005311012268, "avg_return": 0.8621038794517517, "regret": 0.0003335121728014201, "entropy": 0.0839347392320633, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:58.721606Z", "loop": 11621, "env_steps": 7140556799, "loss": 0.016495555639266968, "avg_return": 0.8622633814811707, "regret": 0.0003335121728014201, "entropy": 0.08534824848175049, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:09:59.576548Z", "loop": 11622, "env_steps": 7141171199, "loss": 0.01598595641553402, "avg_return": 0.8639740943908691, "regret": 0.0003335121728014201, "entropy": 0.08244813978672028, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:00.432616Z", "loop": 11623, "env_steps": 7141785599, "loss": 0.01710749976336956, "avg_return": 0.8628952503204346, "regret": 0.0003335121728014201, "entropy": 0.08503690361976624, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:01.287095Z", "loop": 11624, "env_steps": 7142399999, "loss": 0.01668706350028515, "avg_return": 0.8637516498565674, "regret": 0.0003335121728014201, "entropy": 0.08753830939531326, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:02.142304Z", "loop": 11625, "env_steps": 7143014399, "loss": 0.01697200909256935, "avg_return": 0.8635097742080688, "regret": 0.0003335121728014201, "entropy": 0.08673994243144989, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:02.997831Z", "loop": 11626, "env_steps": 7143628799, "loss": 0.016531620174646378, "avg_return": 0.8621922135353088, "regret": 0.0003335121728014201, "entropy": 0.08666921406984329, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:03.853653Z", "loop": 11627, "env_steps": 7144243199, "loss": 0.018007272854447365, "avg_return": 0.8624090552330017, "regret": 0.0003335121728014201, "entropy": 0.09017650783061981, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:04.708791Z", "loop": 11628, "env_steps": 7144857599, "loss": 0.016846034675836563, "avg_return": 0.8626957535743713, "regret": 0.0003335121728014201, "entropy": 0.08494679629802704, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:05.563077Z", "loop": 11629, "env_steps": 7145471999, "loss": 0.016326947137713432, "avg_return": 0.8624151945114136, "regret": 0.0003335121728014201, "entropy": 0.08260077983140945, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:06.466845Z", "loop": 11630, "env_steps": 7146086399, "loss": 0.017398776486516, "avg_return": 0.8624855875968933, "regret": 0.0014505538856610656, "entropy": 0.08699765801429749, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:07.322189Z", "loop": 11631, "env_steps": 7146700799, "loss": 0.016900578513741493, "avg_return": 0.8614353537559509, "regret": 0.0014505538856610656, "entropy": 0.08931954950094223, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:08.177210Z", "loop": 11632, "env_steps": 7147315199, "loss": 0.017987428233027458, "avg_return": 0.8616327047348022, "regret": 0.0014505538856610656, "entropy": 0.08945253491401672, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:09.031546Z", "loop": 11633, "env_steps": 7147929599, "loss": 0.01794271171092987, "avg_return": 0.8607409596443176, "regret": 0.0014505538856610656, "entropy": 0.09503312408924103, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:09.885931Z", "loop": 11634, "env_steps": 7148543999, "loss": 0.018494905903935432, "avg_return": 0.8598818182945251, "regret": 0.0014505538856610656, "entropy": 0.0942344143986702, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:10.740856Z", "loop": 11635, "env_steps": 7149158399, "loss": 0.018383484333753586, "avg_return": 0.861189603805542, "regret": 0.0014505538856610656, "entropy": 0.09104424715042114, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:11.596456Z", "loop": 11636, "env_steps": 7149772799, "loss": 0.016885682940483093, "avg_return": 0.8615629076957703, "regret": 0.0014505538856610656, "entropy": 0.09009213000535965, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:12.451345Z", "loop": 11637, "env_steps": 7150387199, "loss": 0.017190763726830482, "avg_return": 0.8613266348838806, "regret": 0.0014505538856610656, "entropy": 0.08814780414104462, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:13.305227Z", "loop": 11638, "env_steps": 7151001599, "loss": 0.016972482204437256, "avg_return": 0.862636148929596, "regret": 0.0014505538856610656, "entropy": 0.08823998272418976, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:14.160976Z", "loop": 11639, "env_steps": 7151615999, "loss": 0.01603337936103344, "avg_return": 0.8629319667816162, "regret": 0.0014505538856610656, "entropy": 0.08525381237268448, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:15.057917Z", "loop": 11640, "env_steps": 7152230399, "loss": 0.015658648684620857, "avg_return": 0.8618546724319458, "regret": 0.0012677571503445506, "entropy": 0.08430201560258865, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:15.912204Z", "loop": 11641, "env_steps": 7152844799, "loss": 0.01640370301902294, "avg_return": 0.8625394701957703, "regret": 0.0012677571503445506, "entropy": 0.08684487640857697, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:16.766313Z", "loop": 11642, "env_steps": 7153459199, "loss": 0.016430942341685295, "avg_return": 0.8630225658416748, "regret": 0.0012677571503445506, "entropy": 0.08927512913942337, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:17.620740Z", "loop": 11643, "env_steps": 7154073599, "loss": 0.016199199482798576, "avg_return": 0.8636080026626587, "regret": 0.0012677571503445506, "entropy": 0.08397234976291656, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:18.473930Z", "loop": 11644, "env_steps": 7154687999, "loss": 0.01715170033276081, "avg_return": 0.8622430562973022, "regret": 0.0012677571503445506, "entropy": 0.09348525106906891, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:19.328320Z", "loop": 11645, "env_steps": 7155302399, "loss": 0.018696270883083344, "avg_return": 0.8636855483055115, "regret": 0.0012677571503445506, "entropy": 0.09551025182008743, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:20.183689Z", "loop": 11646, "env_steps": 7155916799, "loss": 0.018784036859869957, "avg_return": 0.8631359934806824, "regret": 0.0012677571503445506, "entropy": 0.09617119282484055, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:21.039168Z", "loop": 11647, "env_steps": 7156531199, "loss": 0.0170354675501585, "avg_return": 0.8629844188690186, "regret": 0.0012677571503445506, "entropy": 0.08872749656438828, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:21.892686Z", "loop": 11648, "env_steps": 7157145599, "loss": 0.01755407452583313, "avg_return": 0.8614575266838074, "regret": 0.0012677571503445506, "entropy": 0.08856489509344101, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:22.746394Z", "loop": 11649, "env_steps": 7157759999, "loss": 0.01624620519578457, "avg_return": 0.8626013398170471, "regret": 0.0012677571503445506, "entropy": 0.08513911068439484, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:23.639666Z", "loop": 11650, "env_steps": 7158374399, "loss": 0.01630706712603569, "avg_return": 0.8600683808326721, "regret": 0.0007608062005601823, "entropy": 0.08157897740602493, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:24.495132Z", "loop": 11651, "env_steps": 7158988799, "loss": 0.015475155785679817, "avg_return": 0.8621063232421875, "regret": 0.0007608062005601823, "entropy": 0.08202232420444489, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:25.349281Z", "loop": 11652, "env_steps": 7159603199, "loss": 0.014985278248786926, "avg_return": 0.8625805974006653, "regret": 0.0007608062005601823, "entropy": 0.07939708977937698, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:26.202520Z", "loop": 11653, "env_steps": 7160217599, "loss": 0.015070448629558086, "avg_return": 0.8629429340362549, "regret": 0.0007608062005601823, "entropy": 0.07987216114997864, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:27.056845Z", "loop": 11654, "env_steps": 7160831999, "loss": 0.014672410674393177, "avg_return": 0.8628175854682922, "regret": 0.0007608062005601823, "entropy": 0.07794757187366486, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:27.912007Z", "loop": 11655, "env_steps": 7161446399, "loss": 0.014329864643514156, "avg_return": 0.8630569577217102, "regret": 0.0007608062005601823, "entropy": 0.07862295210361481, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:28.766344Z", "loop": 11656, "env_steps": 7162060799, "loss": 0.015171539969742298, "avg_return": 0.8632823824882507, "regret": 0.0007608062005601823, "entropy": 0.0782632902264595, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:29.620155Z", "loop": 11657, "env_steps": 7162675199, "loss": 0.015843989327549934, "avg_return": 0.8634820580482483, "regret": 0.0007608062005601823, "entropy": 0.078969806432724, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:30.473609Z", "loop": 11658, "env_steps": 7163289599, "loss": 0.015262803994119167, "avg_return": 0.8642550110816956, "regret": 0.0007608062005601823, "entropy": 0.07736726105213165, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:31.327818Z", "loop": 11659, "env_steps": 7163903999, "loss": 0.016329450532794, "avg_return": 0.8625116348266602, "regret": 0.0007608062005601823, "entropy": 0.08162546902894974, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:32.222088Z", "loop": 11660, "env_steps": 7164518399, "loss": 0.015471555292606354, "avg_return": 0.8616650700569153, "regret": 0.000743325799703598, "entropy": 0.07789764553308487, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:33.076291Z", "loop": 11661, "env_steps": 7165132799, "loss": 0.014755288138985634, "avg_return": 0.8627457618713379, "regret": 0.000743325799703598, "entropy": 0.07803381979465485, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:33.929307Z", "loop": 11662, "env_steps": 7165747199, "loss": 0.01503186859190464, "avg_return": 0.864158570766449, "regret": 0.000743325799703598, "entropy": 0.07794705033302307, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:34.784060Z", "loop": 11663, "env_steps": 7166361599, "loss": 0.014845184050500393, "avg_return": 0.8622586131095886, "regret": 0.000743325799703598, "entropy": 0.0765107050538063, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:35.638213Z", "loop": 11664, "env_steps": 7166975999, "loss": 0.01629558764398098, "avg_return": 0.8637539148330688, "regret": 0.000743325799703598, "entropy": 0.0799986720085144, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:36.492044Z", "loop": 11665, "env_steps": 7167590399, "loss": 0.015829438343644142, "avg_return": 0.8634021282196045, "regret": 0.000743325799703598, "entropy": 0.07977654784917831, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:37.345748Z", "loop": 11666, "env_steps": 7168204799, "loss": 0.0162592101842165, "avg_return": 0.8631172776222229, "regret": 0.000743325799703598, "entropy": 0.07751849293708801, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:38.199152Z", "loop": 11667, "env_steps": 7168819199, "loss": 0.01611858606338501, "avg_return": 0.8613125681877136, "regret": 0.000743325799703598, "entropy": 0.08024101704359055, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:39.053065Z", "loop": 11668, "env_steps": 7169433599, "loss": 0.0174573864787817, "avg_return": 0.8623068332672119, "regret": 0.000743325799703598, "entropy": 0.07998554408550262, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:39.907170Z", "loop": 11669, "env_steps": 7170047999, "loss": 0.017214274033904076, "avg_return": 0.8619020581245422, "regret": 0.000743325799703598, "entropy": 0.08441700041294098, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:40.800911Z", "loop": 11670, "env_steps": 7170662399, "loss": 0.015902820974588394, "avg_return": 0.8625142574310303, "regret": 0.001037530368193984, "entropy": 0.07978194206953049, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:41.656816Z", "loop": 11671, "env_steps": 7171276799, "loss": 0.016120420768857002, "avg_return": 0.8627176284790039, "regret": 0.001037530368193984, "entropy": 0.08068865537643433, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:42.510433Z", "loop": 11672, "env_steps": 7171891199, "loss": 0.01743571273982525, "avg_return": 0.8627930879592896, "regret": 0.001037530368193984, "entropy": 0.08375735580921173, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:43.364890Z", "loop": 11673, "env_steps": 7172505599, "loss": 0.016276385635137558, "avg_return": 0.8610467910766602, "regret": 0.001037530368193984, "entropy": 0.08110351115465164, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:44.219555Z", "loop": 11674, "env_steps": 7173119999, "loss": 0.016947677358984947, "avg_return": 0.8627930879592896, "regret": 0.001037530368193984, "entropy": 0.08225242793560028, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:45.073873Z", "loop": 11675, "env_steps": 7173734399, "loss": 0.016185354441404343, "avg_return": 0.8616437911987305, "regret": 0.001037530368193984, "entropy": 0.08314767479896545, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:45.928478Z", "loop": 11676, "env_steps": 7174348799, "loss": 0.017273740842938423, "avg_return": 0.8625484704971313, "regret": 0.001037530368193984, "entropy": 0.08470003306865692, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:46.782709Z", "loop": 11677, "env_steps": 7174963199, "loss": 0.016525687649846077, "avg_return": 0.8622907996177673, "regret": 0.001037530368193984, "entropy": 0.07964042574167252, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:47.637718Z", "loop": 11678, "env_steps": 7175577599, "loss": 0.016676312312483788, "avg_return": 0.8621870279312134, "regret": 0.001037530368193984, "entropy": 0.07898101955652237, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:48.491463Z", "loop": 11679, "env_steps": 7176191999, "loss": 0.015669576823711395, "avg_return": 0.862667441368103, "regret": 0.001037530368193984, "entropy": 0.0752938911318779, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:49.384418Z", "loop": 11680, "env_steps": 7176806399, "loss": 0.016091132536530495, "avg_return": 0.8620430827140808, "regret": 0.0013875359436497092, "entropy": 0.07856295257806778, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:50.238028Z", "loop": 11681, "env_steps": 7177420799, "loss": 0.014589148573577404, "avg_return": 0.861040472984314, "regret": 0.0013875359436497092, "entropy": 0.07671817392110825, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:51.093094Z", "loop": 11682, "env_steps": 7178035199, "loss": 0.014052996411919594, "avg_return": 0.8621773719787598, "regret": 0.0013875359436497092, "entropy": 0.07360626012086868, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:51.946870Z", "loop": 11683, "env_steps": 7178649599, "loss": 0.01370126474648714, "avg_return": 0.862557590007782, "regret": 0.0013875359436497092, "entropy": 0.07385168969631195, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:52.799586Z", "loop": 11684, "env_steps": 7179263999, "loss": 0.01565570943057537, "avg_return": 0.8620116114616394, "regret": 0.0013875359436497092, "entropy": 0.07801281660795212, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:53.653222Z", "loop": 11685, "env_steps": 7179878399, "loss": 0.015539092011749744, "avg_return": 0.8630943894386292, "regret": 0.0013875359436497092, "entropy": 0.0745505765080452, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:54.508276Z", "loop": 11686, "env_steps": 7180492799, "loss": 0.0143921272829175, "avg_return": 0.8629693984985352, "regret": 0.0013875359436497092, "entropy": 0.07396113127470016, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:55.362879Z", "loop": 11687, "env_steps": 7181107199, "loss": 0.013751556165516376, "avg_return": 0.8632246255874634, "regret": 0.0013875359436497092, "entropy": 0.07238592952489853, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:56.215980Z", "loop": 11688, "env_steps": 7181721599, "loss": 0.01443656999617815, "avg_return": 0.8622341156005859, "regret": 0.0013875359436497092, "entropy": 0.0749509260058403, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:57.069556Z", "loop": 11689, "env_steps": 7182335999, "loss": 0.013836214318871498, "avg_return": 0.863513708114624, "regret": 0.0013875359436497092, "entropy": 0.07272718846797943, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:57.963009Z", "loop": 11690, "env_steps": 7182950399, "loss": 0.014095555059611797, "avg_return": 0.8631380200386047, "regret": 0.0006185745005495846, "entropy": 0.07486996799707413, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:58.816818Z", "loop": 11691, "env_steps": 7183564799, "loss": 0.014194493182003498, "avg_return": 0.8636845946311951, "regret": 0.0006185745005495846, "entropy": 0.07506410777568817, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:10:59.670397Z", "loop": 11692, "env_steps": 7184179199, "loss": 0.016713958233594894, "avg_return": 0.8596383929252625, "regret": 0.0006185745005495846, "entropy": 0.08294400572776794, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:00.523685Z", "loop": 11693, "env_steps": 7184793599, "loss": 0.017566589638590813, "avg_return": 0.8622552752494812, "regret": 0.0006185745005495846, "entropy": 0.08549557626247406, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:01.378536Z", "loop": 11694, "env_steps": 7185407999, "loss": 0.015443356707692146, "avg_return": 0.8591616153717041, "regret": 0.0006185745005495846, "entropy": 0.07757315784692764, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:02.234322Z", "loop": 11695, "env_steps": 7186022399, "loss": 0.014248120598495007, "avg_return": 0.8581965565681458, "regret": 0.0006185745005495846, "entropy": 0.07584676891565323, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:03.089164Z", "loop": 11696, "env_steps": 7186636799, "loss": 0.01483908761292696, "avg_return": 0.8568660616874695, "regret": 0.0006185745005495846, "entropy": 0.07728423178195953, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:03.943557Z", "loop": 11697, "env_steps": 7187251199, "loss": 0.014987199567258358, "avg_return": 0.8578431606292725, "regret": 0.0006185745005495846, "entropy": 0.07913639396429062, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:04.798921Z", "loop": 11698, "env_steps": 7187865599, "loss": 0.015781639143824577, "avg_return": 0.8565656542778015, "regret": 0.0006185745005495846, "entropy": 0.07923466712236404, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:05.653620Z", "loop": 11699, "env_steps": 7188479999, "loss": 0.016591517254710197, "avg_return": 0.8568484783172607, "regret": 0.0006185745005495846, "entropy": 0.08361700922250748, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:06.547417Z", "loop": 11700, "env_steps": 7189094399, "loss": 0.015487168915569782, "avg_return": 0.8574978709220886, "regret": 0.005952737759798765, "entropy": 0.07908330112695694, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:07.401830Z", "loop": 11701, "env_steps": 7189708799, "loss": 0.014809898100793362, "avg_return": 0.8586018085479736, "regret": 0.005952737759798765, "entropy": 0.08149617910385132, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:08.255295Z", "loop": 11702, "env_steps": 7190323199, "loss": 0.014402048662304878, "avg_return": 0.8591247797012329, "regret": 0.005952737759798765, "entropy": 0.07712250202894211, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:09.109527Z", "loop": 11703, "env_steps": 7190937599, "loss": 0.014906211756169796, "avg_return": 0.8614014983177185, "regret": 0.005952737759798765, "entropy": 0.08062771707773209, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:09.963411Z", "loop": 11704, "env_steps": 7191551999, "loss": 0.014238186180591583, "avg_return": 0.8596596717834473, "regret": 0.005952737759798765, "entropy": 0.0723789855837822, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:10.818450Z", "loop": 11705, "env_steps": 7192166399, "loss": 0.013438097201287746, "avg_return": 0.8611171841621399, "regret": 0.005952737759798765, "entropy": 0.0736176148056984, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:11.672322Z", "loop": 11706, "env_steps": 7192780799, "loss": 0.01376708596944809, "avg_return": 0.8626836538314819, "regret": 0.005952737759798765, "entropy": 0.07294942438602448, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:12.525946Z", "loop": 11707, "env_steps": 7193395199, "loss": 0.013982372358441353, "avg_return": 0.8620203733444214, "regret": 0.005952737759798765, "entropy": 0.07397934794425964, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:13.379392Z", "loop": 11708, "env_steps": 7194009599, "loss": 0.01484792958945036, "avg_return": 0.8632371425628662, "regret": 0.005952737759798765, "entropy": 0.07778112590312958, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:14.232974Z", "loop": 11709, "env_steps": 7194623999, "loss": 0.01429064106196165, "avg_return": 0.8624566793441772, "regret": 0.005952737759798765, "entropy": 0.07387776672840118, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:15.128650Z", "loop": 11710, "env_steps": 7195238399, "loss": 0.013247174210846424, "avg_return": 0.8628653883934021, "regret": 0.0009400304988957942, "entropy": 0.06901711225509644, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:15.981815Z", "loop": 11711, "env_steps": 7195852799, "loss": 0.014233550988137722, "avg_return": 0.8641846179962158, "regret": 0.0009400304988957942, "entropy": 0.07352879643440247, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:16.834165Z", "loop": 11712, "env_steps": 7196467199, "loss": 0.014225316233932972, "avg_return": 0.8619235157966614, "regret": 0.0009400304988957942, "entropy": 0.07489670813083649, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:17.687783Z", "loop": 11713, "env_steps": 7197081599, "loss": 0.014481506310403347, "avg_return": 0.8637306690216064, "regret": 0.0009400304988957942, "entropy": 0.07684339582920074, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:18.542965Z", "loop": 11714, "env_steps": 7197695999, "loss": 0.015904953703284264, "avg_return": 0.8632970452308655, "regret": 0.0009400304988957942, "entropy": 0.08082498610019684, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:19.396745Z", "loop": 11715, "env_steps": 7198310399, "loss": 0.016391612589359283, "avg_return": 0.8621690273284912, "regret": 0.0009400304988957942, "entropy": 0.08261688798666, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:20.250720Z", "loop": 11716, "env_steps": 7198924799, "loss": 0.01721009612083435, "avg_return": 0.8630728125572205, "regret": 0.0009400304988957942, "entropy": 0.08667591959238052, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:21.103913Z", "loop": 11717, "env_steps": 7199539199, "loss": 0.016596121713519096, "avg_return": 0.8637648820877075, "regret": 0.0009400304988957942, "entropy": 0.0836772620677948, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:21.958459Z", "loop": 11718, "env_steps": 7200153599, "loss": 0.016702814027667046, "avg_return": 0.8634037375450134, "regret": 0.0009400304988957942, "entropy": 0.08397269248962402, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:22.812427Z", "loop": 11719, "env_steps": 7200767999, "loss": 0.014502066187560558, "avg_return": 0.8631477952003479, "regret": 0.0009400304988957942, "entropy": 0.07598090916872025, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:23.705695Z", "loop": 11720, "env_steps": 7201382399, "loss": 0.014099011197686195, "avg_return": 0.8640320301055908, "regret": 0.00032506967545486987, "entropy": 0.07184451818466187, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:24.559927Z", "loop": 11721, "env_steps": 7201996799, "loss": 0.014226934872567654, "avg_return": 0.8627200722694397, "regret": 0.00032506967545486987, "entropy": 0.07651206851005554, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:25.415827Z", "loop": 11722, "env_steps": 7202611199, "loss": 0.015330473892390728, "avg_return": 0.8622481226921082, "regret": 0.00032506967545486987, "entropy": 0.07921181619167328, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:26.269453Z", "loop": 11723, "env_steps": 7203225599, "loss": 0.017783084884285927, "avg_return": 0.8618612885475159, "regret": 0.00032506967545486987, "entropy": 0.08731064945459366, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:27.123490Z", "loop": 11724, "env_steps": 7203839999, "loss": 0.018073013052344322, "avg_return": 0.8633959889411926, "regret": 0.00032506967545486987, "entropy": 0.08990908414125443, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:27.976756Z", "loop": 11725, "env_steps": 7204454399, "loss": 0.017551302909851074, "avg_return": 0.8636560440063477, "regret": 0.00032506967545486987, "entropy": 0.08607323467731476, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:28.830438Z", "loop": 11726, "env_steps": 7205068799, "loss": 0.018286189064383507, "avg_return": 0.8622600436210632, "regret": 0.00032506967545486987, "entropy": 0.09144478291273117, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:29.683957Z", "loop": 11727, "env_steps": 7205683199, "loss": 0.019601929932832718, "avg_return": 0.8643909096717834, "regret": 0.00032506967545486987, "entropy": 0.09430211782455444, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:30.538111Z", "loop": 11728, "env_steps": 7206297599, "loss": 0.019054634496569633, "avg_return": 0.8638922572135925, "regret": 0.00032506967545486987, "entropy": 0.09383781999349594, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:31.391575Z", "loop": 11729, "env_steps": 7206911999, "loss": 0.01873870939016342, "avg_return": 0.8619012832641602, "regret": 0.00032506967545486987, "entropy": 0.0948166772723198, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:32.285284Z", "loop": 11730, "env_steps": 7207526399, "loss": 0.0184298325330019, "avg_return": 0.8623132705688477, "regret": 0.0018504193285480142, "entropy": 0.09073016792535782, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:33.139721Z", "loop": 11731, "env_steps": 7208140799, "loss": 0.017666727304458618, "avg_return": 0.8605221509933472, "regret": 0.0018504193285480142, "entropy": 0.09056729078292847, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:33.994340Z", "loop": 11732, "env_steps": 7208755199, "loss": 0.019192837178707123, "avg_return": 0.8591607809066772, "regret": 0.0018504193285480142, "entropy": 0.09580850601196289, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:34.848572Z", "loop": 11733, "env_steps": 7209369599, "loss": 0.01880774460732937, "avg_return": 0.8555700778961182, "regret": 0.0018504193285480142, "entropy": 0.096110999584198, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:35.702176Z", "loop": 11734, "env_steps": 7209983999, "loss": 0.019677551463246346, "avg_return": 0.856075644493103, "regret": 0.0018504193285480142, "entropy": 0.10033967345952988, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:36.555760Z", "loop": 11735, "env_steps": 7210598399, "loss": 0.016728965565562248, "avg_return": 0.8593658804893494, "regret": 0.0018504193285480142, "entropy": 0.08831391483545303, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:37.410436Z", "loop": 11736, "env_steps": 7211212799, "loss": 0.01604141853749752, "avg_return": 0.8614839911460876, "regret": 0.0018504193285480142, "entropy": 0.08245144784450531, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:38.265233Z", "loop": 11737, "env_steps": 7211827199, "loss": 0.01595856063067913, "avg_return": 0.8626059889793396, "regret": 0.0018504193285480142, "entropy": 0.08273055404424667, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:39.119360Z", "loop": 11738, "env_steps": 7212441599, "loss": 0.015709253028035164, "avg_return": 0.8614340424537659, "regret": 0.0018504193285480142, "entropy": 0.07918521016836166, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:39.972444Z", "loop": 11739, "env_steps": 7213055999, "loss": 0.016550201922655106, "avg_return": 0.8618667721748352, "regret": 0.0018504193285480142, "entropy": 0.08246306329965591, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:40.865215Z", "loop": 11740, "env_steps": 7213670399, "loss": 0.018188154324889183, "avg_return": 0.8639591932296753, "regret": 0.0005606953636743128, "entropy": 0.08855882287025452, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:41.719505Z", "loop": 11741, "env_steps": 7214284799, "loss": 0.019500361755490303, "avg_return": 0.8622393012046814, "regret": 0.0005606953636743128, "entropy": 0.09365999698638916, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:42.573291Z", "loop": 11742, "env_steps": 7214899199, "loss": 0.017679981887340546, "avg_return": 0.8631948232650757, "regret": 0.0005606953636743128, "entropy": 0.08722629398107529, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:43.426968Z", "loop": 11743, "env_steps": 7215513599, "loss": 0.01601383090019226, "avg_return": 0.862345814704895, "regret": 0.0005606953636743128, "entropy": 0.07999175786972046, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:44.280788Z", "loop": 11744, "env_steps": 7216127999, "loss": 0.015447263605892658, "avg_return": 0.8629333972930908, "regret": 0.0005606953636743128, "entropy": 0.07773321866989136, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:45.136220Z", "loop": 11745, "env_steps": 7216742399, "loss": 0.015949061140418053, "avg_return": 0.86442631483078, "regret": 0.0005606953636743128, "entropy": 0.07958553731441498, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:45.990293Z", "loop": 11746, "env_steps": 7217356799, "loss": 0.015425062738358974, "avg_return": 0.8631215691566467, "regret": 0.0005606953636743128, "entropy": 0.07989154011011124, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:46.843454Z", "loop": 11747, "env_steps": 7217971199, "loss": 0.015498623251914978, "avg_return": 0.863013505935669, "regret": 0.0005606953636743128, "entropy": 0.07678871601819992, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:47.697122Z", "loop": 11748, "env_steps": 7218585599, "loss": 0.016786500811576843, "avg_return": 0.862362265586853, "regret": 0.0005606953636743128, "entropy": 0.08345361053943634, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:48.551758Z", "loop": 11749, "env_steps": 7219199999, "loss": 0.01708943583071232, "avg_return": 0.8623635172843933, "regret": 0.0005606953636743128, "entropy": 0.08865725994110107, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:49.445741Z", "loop": 11750, "env_steps": 7219814399, "loss": 0.017649313434958458, "avg_return": 0.8624009490013123, "regret": 0.0003990127006545663, "entropy": 0.08718721568584442, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:50.299724Z", "loop": 11751, "env_steps": 7220428799, "loss": 0.017843768000602722, "avg_return": 0.8640769720077515, "regret": 0.0003990127006545663, "entropy": 0.08949683606624603, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:51.153118Z", "loop": 11752, "env_steps": 7221043199, "loss": 0.018641609698534012, "avg_return": 0.8640030026435852, "regret": 0.0003990127006545663, "entropy": 0.09049878269433975, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:52.007194Z", "loop": 11753, "env_steps": 7221657599, "loss": 0.01768413931131363, "avg_return": 0.8639128804206848, "regret": 0.0003990127006545663, "entropy": 0.08742251992225647, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:52.862021Z", "loop": 11754, "env_steps": 7222271999, "loss": 0.01791493408381939, "avg_return": 0.8630772233009338, "regret": 0.0003990127006545663, "entropy": 0.09030121564865112, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:53.716696Z", "loop": 11755, "env_steps": 7222886399, "loss": 0.016433028504252434, "avg_return": 0.862281322479248, "regret": 0.0003990127006545663, "entropy": 0.08448966592550278, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:54.571079Z", "loop": 11756, "env_steps": 7223500799, "loss": 0.016994357109069824, "avg_return": 0.8631244897842407, "regret": 0.0003990127006545663, "entropy": 0.08859356492757797, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:55.427149Z", "loop": 11757, "env_steps": 7224115199, "loss": 0.01636998914182186, "avg_return": 0.8613805174827576, "regret": 0.0003990127006545663, "entropy": 0.08433892577886581, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:56.282480Z", "loop": 11758, "env_steps": 7224729599, "loss": 0.015284438617527485, "avg_return": 0.8619833588600159, "regret": 0.0003990127006545663, "entropy": 0.08386879414319992, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:57.137573Z", "loop": 11759, "env_steps": 7225343999, "loss": 0.01683344505727291, "avg_return": 0.8628905415534973, "regret": 0.0003990127006545663, "entropy": 0.08898312598466873, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:58.031371Z", "loop": 11760, "env_steps": 7225958399, "loss": 0.01732238382101059, "avg_return": 0.8620301485061646, "regret": 0.0018815221264958382, "entropy": 0.09474848955869675, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:58.885238Z", "loop": 11761, "env_steps": 7226572799, "loss": 0.020803231745958328, "avg_return": 0.860770583152771, "regret": 0.0018815221264958382, "entropy": 0.10003165900707245, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:11:59.738709Z", "loop": 11762, "env_steps": 7227187199, "loss": 0.021177217364311218, "avg_return": 0.8610243201255798, "regret": 0.0018815221264958382, "entropy": 0.10477223992347717, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:00.592230Z", "loop": 11763, "env_steps": 7227801599, "loss": 0.021697981283068657, "avg_return": 0.8606856465339661, "regret": 0.0018815221264958382, "entropy": 0.11263779550790787, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:01.445689Z", "loop": 11764, "env_steps": 7228415999, "loss": 0.02314729429781437, "avg_return": 0.8607161641120911, "regret": 0.0018815221264958382, "entropy": 0.11472529172897339, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:02.299963Z", "loop": 11765, "env_steps": 7229030399, "loss": 0.023287950083613396, "avg_return": 0.8597115278244019, "regret": 0.0018815221264958382, "entropy": 0.11600270122289658, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:03.153490Z", "loop": 11766, "env_steps": 7229644799, "loss": 0.023485874757170677, "avg_return": 0.8605976700782776, "regret": 0.0018815221264958382, "entropy": 0.11976709961891174, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:04.007338Z", "loop": 11767, "env_steps": 7230259199, "loss": 0.02690032497048378, "avg_return": 0.8598923087120056, "regret": 0.0018815221264958382, "entropy": 0.1310441941022873, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:04.861639Z", "loop": 11768, "env_steps": 7230873599, "loss": 0.02674996666610241, "avg_return": 0.8603042960166931, "regret": 0.0018815221264958382, "entropy": 0.1337556540966034, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:05.717006Z", "loop": 11769, "env_steps": 7231487999, "loss": 0.027457579970359802, "avg_return": 0.8592014908790588, "regret": 0.0018815221264958382, "entropy": 0.13703960180282593, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:06.610263Z", "loop": 11770, "env_steps": 7232102399, "loss": 0.02705063298344612, "avg_return": 0.8602572083473206, "regret": 0.0036961473524570465, "entropy": 0.12993024289608002, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:07.464242Z", "loop": 11771, "env_steps": 7232716799, "loss": 0.02607908844947815, "avg_return": 0.8590749502182007, "regret": 0.0036961473524570465, "entropy": 0.13211238384246826, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:08.318907Z", "loop": 11772, "env_steps": 7233331199, "loss": 0.025157010182738304, "avg_return": 0.8590540885925293, "regret": 0.0036961473524570465, "entropy": 0.12535277009010315, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:09.174229Z", "loop": 11773, "env_steps": 7233945599, "loss": 0.023646755144000053, "avg_return": 0.8612768650054932, "regret": 0.0036961473524570465, "entropy": 0.11687624454498291, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:10.028806Z", "loop": 11774, "env_steps": 7234559999, "loss": 0.023187758401036263, "avg_return": 0.86130690574646, "regret": 0.0036961473524570465, "entropy": 0.11746863275766373, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:10.882920Z", "loop": 11775, "env_steps": 7235174399, "loss": 0.024043621495366096, "avg_return": 0.8610520362854004, "regret": 0.0036961473524570465, "entropy": 0.12314418703317642, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:11.738004Z", "loop": 11776, "env_steps": 7235788799, "loss": 0.024227123707532883, "avg_return": 0.8608574867248535, "regret": 0.0036961473524570465, "entropy": 0.12041359394788742, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:12.593562Z", "loop": 11777, "env_steps": 7236403199, "loss": 0.02601475454866886, "avg_return": 0.8609689474105835, "regret": 0.0036961473524570465, "entropy": 0.12593190371990204, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:13.449270Z", "loop": 11778, "env_steps": 7237017599, "loss": 0.024723434820771217, "avg_return": 0.85904461145401, "regret": 0.0036961473524570465, "entropy": 0.12528488039970398, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:14.302960Z", "loop": 11779, "env_steps": 7237631999, "loss": 0.025290489196777344, "avg_return": 0.8594551682472229, "regret": 0.0036961473524570465, "entropy": 0.12992653250694275, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:15.196093Z", "loop": 11780, "env_steps": 7238246399, "loss": 0.026048729196190834, "avg_return": 0.8590942621231079, "regret": 0.0038708809297531843, "entropy": 0.12913912534713745, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:16.049365Z", "loop": 11781, "env_steps": 7238860799, "loss": 0.026858240365982056, "avg_return": 0.8588302731513977, "regret": 0.0038708809297531843, "entropy": 0.13038179278373718, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:16.903305Z", "loop": 11782, "env_steps": 7239475199, "loss": 0.025385454297065735, "avg_return": 0.8604229092597961, "regret": 0.0038708809297531843, "entropy": 0.12515461444854736, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:17.756483Z", "loop": 11783, "env_steps": 7240089599, "loss": 0.023664087057113647, "avg_return": 0.8592959642410278, "regret": 0.0038708809297531843, "entropy": 0.11669599264860153, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:18.610355Z", "loop": 11784, "env_steps": 7240703999, "loss": 0.025533577427268028, "avg_return": 0.8622125387191772, "regret": 0.0038708809297531843, "entropy": 0.11999048292636871, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:19.463429Z", "loop": 11785, "env_steps": 7241318399, "loss": 0.023591570556163788, "avg_return": 0.8607800602912903, "regret": 0.0038708809297531843, "entropy": 0.11778369545936584, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:20.316752Z", "loop": 11786, "env_steps": 7241932799, "loss": 0.023354623466730118, "avg_return": 0.8630098700523376, "regret": 0.0038708809297531843, "entropy": 0.11538197845220566, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:21.171199Z", "loop": 11787, "env_steps": 7242547199, "loss": 0.022577932104468346, "avg_return": 0.8628513813018799, "regret": 0.0038708809297531843, "entropy": 0.10761719197034836, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:22.024790Z", "loop": 11788, "env_steps": 7243161599, "loss": 0.02201036922633648, "avg_return": 0.8634604811668396, "regret": 0.0038708809297531843, "entropy": 0.10787414014339447, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:22.878314Z", "loop": 11789, "env_steps": 7243775999, "loss": 0.01865554414689541, "avg_return": 0.862890362739563, "regret": 0.0038708809297531843, "entropy": 0.09522120654582977, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:23.771956Z", "loop": 11790, "env_steps": 7244390399, "loss": 0.0194097887724638, "avg_return": 0.8641179800033569, "regret": 0.0006937397411093116, "entropy": 0.09527070075273514, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:24.627562Z", "loop": 11791, "env_steps": 7245004799, "loss": 0.018786294385790825, "avg_return": 0.8623546361923218, "regret": 0.0006937397411093116, "entropy": 0.09066586941480637, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:25.481479Z", "loop": 11792, "env_steps": 7245619199, "loss": 0.01752479374408722, "avg_return": 0.8629056811332703, "regret": 0.0006937397411093116, "entropy": 0.08841433376073837, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:26.334294Z", "loop": 11793, "env_steps": 7246233599, "loss": 0.019334645941853523, "avg_return": 0.8617051243782043, "regret": 0.0006937397411093116, "entropy": 0.10058365762233734, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:27.188158Z", "loop": 11794, "env_steps": 7246847999, "loss": 0.020209871232509613, "avg_return": 0.8623281121253967, "regret": 0.0006937397411093116, "entropy": 0.0995989665389061, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:28.042522Z", "loop": 11795, "env_steps": 7247462399, "loss": 0.02069784700870514, "avg_return": 0.8633626699447632, "regret": 0.0006937397411093116, "entropy": 0.10306528955698013, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:28.897043Z", "loop": 11796, "env_steps": 7248076799, "loss": 0.023744096979498863, "avg_return": 0.8627976775169373, "regret": 0.0006937397411093116, "entropy": 0.11688993126153946, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:29.751361Z", "loop": 11797, "env_steps": 7248691199, "loss": 0.024961523711681366, "avg_return": 0.8632336854934692, "regret": 0.0006937397411093116, "entropy": 0.12016449123620987, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:30.605344Z", "loop": 11798, "env_steps": 7249305599, "loss": 0.02384909801185131, "avg_return": 0.8638973236083984, "regret": 0.0006937397411093116, "entropy": 0.11367516964673996, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:31.459480Z", "loop": 11799, "env_steps": 7249919999, "loss": 0.02197316102683544, "avg_return": 0.8625175356864929, "regret": 0.0006937397411093116, "entropy": 0.11343788355588913, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:32.355825Z", "loop": 11800, "env_steps": 7250534399, "loss": 0.023454850539565086, "avg_return": 0.8621723651885986, "regret": 0.001190374605357647, "entropy": 0.11674237251281738, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:33.210162Z", "loop": 11801, "env_steps": 7251148799, "loss": 0.022957896813750267, "avg_return": 0.8625370264053345, "regret": 0.001190374605357647, "entropy": 0.10803642868995667, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:34.063930Z", "loop": 11802, "env_steps": 7251763199, "loss": 0.02305818907916546, "avg_return": 0.8618589639663696, "regret": 0.001190374605357647, "entropy": 0.1125393882393837, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:34.918327Z", "loop": 11803, "env_steps": 7252377599, "loss": 0.025231754407286644, "avg_return": 0.8631061911582947, "regret": 0.001190374605357647, "entropy": 0.1197228953242302, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:35.773569Z", "loop": 11804, "env_steps": 7252991999, "loss": 0.02290964312851429, "avg_return": 0.8630124926567078, "regret": 0.001190374605357647, "entropy": 0.1101585403084755, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:36.627974Z", "loop": 11805, "env_steps": 7253606399, "loss": 0.018397847190499306, "avg_return": 0.8632031679153442, "regret": 0.001190374605357647, "entropy": 0.08952733129262924, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:37.483108Z", "loop": 11806, "env_steps": 7254220799, "loss": 0.01566709391772747, "avg_return": 0.8633101582527161, "regret": 0.001190374605357647, "entropy": 0.0798938050866127, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:38.336765Z", "loop": 11807, "env_steps": 7254835199, "loss": 0.01370395440608263, "avg_return": 0.8639658689498901, "regret": 0.001190374605357647, "entropy": 0.07554291188716888, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:39.192227Z", "loop": 11808, "env_steps": 7255449599, "loss": 0.01422478910535574, "avg_return": 0.8634442090988159, "regret": 0.001190374605357647, "entropy": 0.07012965530157089, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:40.047032Z", "loop": 11809, "env_steps": 7256063999, "loss": 0.013979921117424965, "avg_return": 0.8647068738937378, "regret": 0.001190374605357647, "entropy": 0.07660768181085587, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:40.943369Z", "loop": 11810, "env_steps": 7256678399, "loss": 0.016547791659832, "avg_return": 0.8642616868019104, "regret": 0.00022942510258872062, "entropy": 0.08142398297786713, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:41.798227Z", "loop": 11811, "env_steps": 7257292799, "loss": 0.016230391338467598, "avg_return": 0.8634709119796753, "regret": 0.00022942510258872062, "entropy": 0.07974577695131302, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:42.653076Z", "loop": 11812, "env_steps": 7257907199, "loss": 0.01600906252861023, "avg_return": 0.8634997606277466, "regret": 0.00022942510258872062, "entropy": 0.07803826779127121, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:43.508637Z", "loop": 11813, "env_steps": 7258521599, "loss": 0.014344786293804646, "avg_return": 0.8641879558563232, "regret": 0.00022942510258872062, "entropy": 0.07400630414485931, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:44.363979Z", "loop": 11814, "env_steps": 7259135999, "loss": 0.013702036812901497, "avg_return": 0.8640896081924438, "regret": 0.00022942510258872062, "entropy": 0.07392233610153198, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:45.217592Z", "loop": 11815, "env_steps": 7259750399, "loss": 0.013917498290538788, "avg_return": 0.8624674677848816, "regret": 0.00022942510258872062, "entropy": 0.07296565920114517, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:46.071992Z", "loop": 11816, "env_steps": 7260364799, "loss": 0.012454810552299023, "avg_return": 0.8625014424324036, "regret": 0.00022942510258872062, "entropy": 0.0662584975361824, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:46.926906Z", "loop": 11817, "env_steps": 7260979199, "loss": 0.014011635445058346, "avg_return": 0.8633906245231628, "regret": 0.00022942510258872062, "entropy": 0.0691886618733406, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:47.782003Z", "loop": 11818, "env_steps": 7261593599, "loss": 0.014166967943310738, "avg_return": 0.8638523817062378, "regret": 0.00022942510258872062, "entropy": 0.07275916635990143, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:48.636857Z", "loop": 11819, "env_steps": 7262207999, "loss": 0.015575842931866646, "avg_return": 0.863344132900238, "regret": 0.00022942510258872062, "entropy": 0.07697413116693497, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:49.530554Z", "loop": 11820, "env_steps": 7262822399, "loss": 0.015649542212486267, "avg_return": 0.8623571991920471, "regret": 0.0003783986030612141, "entropy": 0.07720982283353806, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:50.385334Z", "loop": 11821, "env_steps": 7263436799, "loss": 0.014638564549386501, "avg_return": 0.8640021085739136, "regret": 0.0003783986030612141, "entropy": 0.07697238028049469, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:51.240667Z", "loop": 11822, "env_steps": 7264051199, "loss": 0.015406602993607521, "avg_return": 0.86203932762146, "regret": 0.0003783986030612141, "entropy": 0.07535544037818909, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:52.097981Z", "loop": 11823, "env_steps": 7264665599, "loss": 0.015640540048480034, "avg_return": 0.8631444573402405, "regret": 0.0003783986030612141, "entropy": 0.07565834373235703, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:52.952077Z", "loop": 11824, "env_steps": 7265279999, "loss": 0.01590452715754509, "avg_return": 0.861894965171814, "regret": 0.0003783986030612141, "entropy": 0.0763070285320282, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:53.805578Z", "loop": 11825, "env_steps": 7265894399, "loss": 0.015813928097486496, "avg_return": 0.861626923084259, "regret": 0.0003783986030612141, "entropy": 0.08202605694532394, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:54.659096Z", "loop": 11826, "env_steps": 7266508799, "loss": 0.017281541600823402, "avg_return": 0.8630478978157043, "regret": 0.0003783986030612141, "entropy": 0.08056207001209259, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:55.514392Z", "loop": 11827, "env_steps": 7267123199, "loss": 0.017681507393717766, "avg_return": 0.8615932464599609, "regret": 0.0003783986030612141, "entropy": 0.08312993496656418, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:56.369071Z", "loop": 11828, "env_steps": 7267737599, "loss": 0.017465723678469658, "avg_return": 0.8618794679641724, "regret": 0.0003783986030612141, "entropy": 0.08500123023986816, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:57.222673Z", "loop": 11829, "env_steps": 7268351999, "loss": 0.01776924729347229, "avg_return": 0.8590457439422607, "regret": 0.0003783986030612141, "entropy": 0.08800637722015381, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:58.115612Z", "loop": 11830, "env_steps": 7268966399, "loss": 0.01757771335542202, "avg_return": 0.856909990310669, "regret": 0.006595988292247057, "entropy": 0.08281578123569489, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:58.970834Z", "loop": 11831, "env_steps": 7269580799, "loss": 0.015971986576914787, "avg_return": 0.8522962331771851, "regret": 0.006595988292247057, "entropy": 0.07864703238010406, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:12:59.825154Z", "loop": 11832, "env_steps": 7270195199, "loss": 0.01611490175127983, "avg_return": 0.8543974757194519, "regret": 0.006595988292247057, "entropy": 0.08237732946872711, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:00.680121Z", "loop": 11833, "env_steps": 7270809599, "loss": 0.01530886348336935, "avg_return": 0.8560473918914795, "regret": 0.006595988292247057, "entropy": 0.07777408510446548, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:01.534098Z", "loop": 11834, "env_steps": 7271423999, "loss": 0.01370963454246521, "avg_return": 0.8585060834884644, "regret": 0.006595988292247057, "entropy": 0.07372079789638519, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:02.388604Z", "loop": 11835, "env_steps": 7272038399, "loss": 0.015190400183200836, "avg_return": 0.8607804775238037, "regret": 0.006595988292247057, "entropy": 0.07749439030885696, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:03.242085Z", "loop": 11836, "env_steps": 7272652799, "loss": 0.015061058104038239, "avg_return": 0.860527753829956, "regret": 0.006595988292247057, "entropy": 0.07639654725790024, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:04.096673Z", "loop": 11837, "env_steps": 7273267199, "loss": 0.015222673304378986, "avg_return": 0.8616021871566772, "regret": 0.006595988292247057, "entropy": 0.07403133064508438, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:04.951111Z", "loop": 11838, "env_steps": 7273881599, "loss": 0.013999290764331818, "avg_return": 0.8634533882141113, "regret": 0.006595988292247057, "entropy": 0.07242725789546967, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:05.804724Z", "loop": 11839, "env_steps": 7274495999, "loss": 0.013535878621041775, "avg_return": 0.8614762425422668, "regret": 0.006595988292247057, "entropy": 0.07045655697584152, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:06.698193Z", "loop": 11840, "env_steps": 7275110399, "loss": 0.01457421388477087, "avg_return": 0.8621343970298767, "regret": 0.0015393405919894576, "entropy": 0.07310453057289124, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:07.552519Z", "loop": 11841, "env_steps": 7275724799, "loss": 0.013674150221049786, "avg_return": 0.8621697425842285, "regret": 0.0015393405919894576, "entropy": 0.07263732701539993, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:08.406094Z", "loop": 11842, "env_steps": 7276339199, "loss": 0.013453507795929909, "avg_return": 0.8625804781913757, "regret": 0.0015393405919894576, "entropy": 0.0702999010682106, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:09.259802Z", "loop": 11843, "env_steps": 7276953599, "loss": 0.014513636939227581, "avg_return": 0.8638694286346436, "regret": 0.0015393405919894576, "entropy": 0.07310708612203598, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:10.113688Z", "loop": 11844, "env_steps": 7277567999, "loss": 0.013634088449180126, "avg_return": 0.8628552556037903, "regret": 0.0015393405919894576, "entropy": 0.07028481364250183, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:10.968298Z", "loop": 11845, "env_steps": 7278182399, "loss": 0.014101902022957802, "avg_return": 0.8622214794158936, "regret": 0.0015393405919894576, "entropy": 0.07320674508810043, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:11.822152Z", "loop": 11846, "env_steps": 7278796799, "loss": 0.013190226629376411, "avg_return": 0.8621880412101746, "regret": 0.0015393405919894576, "entropy": 0.07006005942821503, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:12.675741Z", "loop": 11847, "env_steps": 7279411199, "loss": 0.013682332821190357, "avg_return": 0.8624204993247986, "regret": 0.0015393405919894576, "entropy": 0.0723486915230751, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:13.529843Z", "loop": 11848, "env_steps": 7280025599, "loss": 0.014371900819242, "avg_return": 0.8612768650054932, "regret": 0.0015393405919894576, "entropy": 0.07041841000318527, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:14.383511Z", "loop": 11849, "env_steps": 7280639999, "loss": 0.013699652627110481, "avg_return": 0.8636106848716736, "regret": 0.0015393405919894576, "entropy": 0.06989557296037674, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:15.276010Z", "loop": 11850, "env_steps": 7281254399, "loss": 0.014168602414429188, "avg_return": 0.8632013201713562, "regret": 0.0011728592216968536, "entropy": 0.07214201241731644, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:16.129354Z", "loop": 11851, "env_steps": 7281868799, "loss": 0.013201037421822548, "avg_return": 0.8629605174064636, "regret": 0.0011728592216968536, "entropy": 0.06703367829322815, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:16.982908Z", "loop": 11852, "env_steps": 7282483199, "loss": 0.013067117892205715, "avg_return": 0.8621077537536621, "regret": 0.0011728592216968536, "entropy": 0.06626400351524353, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:17.836142Z", "loop": 11853, "env_steps": 7283097599, "loss": 0.013497056439518929, "avg_return": 0.8631579875946045, "regret": 0.0011728592216968536, "entropy": 0.07007478922605515, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:18.690232Z", "loop": 11854, "env_steps": 7283711999, "loss": 0.013224837370216846, "avg_return": 0.8623659610748291, "regret": 0.0011728592216968536, "entropy": 0.06562969088554382, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:19.544764Z", "loop": 11855, "env_steps": 7284326399, "loss": 0.013525540940463543, "avg_return": 0.863834023475647, "regret": 0.0011728592216968536, "entropy": 0.0699707567691803, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:20.398535Z", "loop": 11856, "env_steps": 7284940799, "loss": 0.01345593761652708, "avg_return": 0.8619753122329712, "regret": 0.0011728592216968536, "entropy": 0.06834503263235092, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:21.252603Z", "loop": 11857, "env_steps": 7285555199, "loss": 0.014658448286354542, "avg_return": 0.8620001673698425, "regret": 0.0011728592216968536, "entropy": 0.07269031554460526, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:22.107303Z", "loop": 11858, "env_steps": 7286169599, "loss": 0.014929826371371746, "avg_return": 0.8637542724609375, "regret": 0.0011728592216968536, "entropy": 0.07444433122873306, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:22.961637Z", "loop": 11859, "env_steps": 7286783999, "loss": 0.014907799661159515, "avg_return": 0.8635166883468628, "regret": 0.0011728592216968536, "entropy": 0.07535752654075623, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:23.855827Z", "loop": 11860, "env_steps": 7287398399, "loss": 0.014255550689995289, "avg_return": 0.8622408509254456, "regret": 0.00026819028425961733, "entropy": 0.0730622410774231, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:24.709254Z", "loop": 11861, "env_steps": 7288012799, "loss": 0.015862470492720604, "avg_return": 0.8632059693336487, "regret": 0.00026819028425961733, "entropy": 0.08016462624073029, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:25.563085Z", "loop": 11862, "env_steps": 7288627199, "loss": 0.017432041466236115, "avg_return": 0.8639966249465942, "regret": 0.00026819028425961733, "entropy": 0.08288771659135818, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:26.418412Z", "loop": 11863, "env_steps": 7289241599, "loss": 0.016828421503305435, "avg_return": 0.8641664981842041, "regret": 0.00026819028425961733, "entropy": 0.08506882190704346, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:27.273113Z", "loop": 11864, "env_steps": 7289855999, "loss": 0.019326386973261833, "avg_return": 0.8629840016365051, "regret": 0.00026819028425961733, "entropy": 0.09206642955541611, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:28.127169Z", "loop": 11865, "env_steps": 7290470399, "loss": 0.018581731244921684, "avg_return": 0.8637680411338806, "regret": 0.00026819028425961733, "entropy": 0.09136621654033661, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:28.982475Z", "loop": 11866, "env_steps": 7291084799, "loss": 0.01869984157383442, "avg_return": 0.8626964688301086, "regret": 0.00026819028425961733, "entropy": 0.09398162364959717, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:29.837807Z", "loop": 11867, "env_steps": 7291699199, "loss": 0.017886092886328697, "avg_return": 0.863972008228302, "regret": 0.00026819028425961733, "entropy": 0.08585107326507568, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:30.691631Z", "loop": 11868, "env_steps": 7292313599, "loss": 0.017191147431731224, "avg_return": 0.8635426759719849, "regret": 0.00026819028425961733, "entropy": 0.08682777732610703, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:31.545808Z", "loop": 11869, "env_steps": 7292927999, "loss": 0.017638972029089928, "avg_return": 0.8627545237541199, "regret": 0.00026819028425961733, "entropy": 0.08522751927375793, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:32.439597Z", "loop": 11870, "env_steps": 7293542399, "loss": 0.016899487003684044, "avg_return": 0.8627226948738098, "regret": 0.0004627332091331482, "entropy": 0.08581336587667465, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:33.293410Z", "loop": 11871, "env_steps": 7294156799, "loss": 0.01683127135038376, "avg_return": 0.8639631271362305, "regret": 0.0004627332091331482, "entropy": 0.08235565572977066, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:34.147385Z", "loop": 11872, "env_steps": 7294771199, "loss": 0.016965821385383606, "avg_return": 0.8620281219482422, "regret": 0.0004627332091331482, "entropy": 0.08051227778196335, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:35.001324Z", "loop": 11873, "env_steps": 7295385599, "loss": 0.01492761354893446, "avg_return": 0.8633337616920471, "regret": 0.0004627332091331482, "entropy": 0.07731065899133682, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:35.856288Z", "loop": 11874, "env_steps": 7295999999, "loss": 0.015208556316792965, "avg_return": 0.8631133437156677, "regret": 0.0004627332091331482, "entropy": 0.07753537595272064, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:36.710507Z", "loop": 11875, "env_steps": 7296614399, "loss": 0.015292750671505928, "avg_return": 0.8620800971984863, "regret": 0.0004627332091331482, "entropy": 0.07776550948619843, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:37.564845Z", "loop": 11876, "env_steps": 7297228799, "loss": 0.01387057639658451, "avg_return": 0.8626851439476013, "regret": 0.0004627332091331482, "entropy": 0.07295068353414536, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:38.419605Z", "loop": 11877, "env_steps": 7297843199, "loss": 0.014406154863536358, "avg_return": 0.8634265065193176, "regret": 0.0004627332091331482, "entropy": 0.07617150992155075, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:39.274504Z", "loop": 11878, "env_steps": 7298457599, "loss": 0.014582820236682892, "avg_return": 0.8627508878707886, "regret": 0.0004627332091331482, "entropy": 0.07473375648260117, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:40.127454Z", "loop": 11879, "env_steps": 7299071999, "loss": 0.01496317982673645, "avg_return": 0.8617663979530334, "regret": 0.0004627332091331482, "entropy": 0.07659993320703506, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:41.020341Z", "loop": 11880, "env_steps": 7299686399, "loss": 0.014135084114968777, "avg_return": 0.8612306714057922, "regret": 0.0015834217192605138, "entropy": 0.06879165023565292, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:41.874796Z", "loop": 11881, "env_steps": 7300300799, "loss": 0.014420886524021626, "avg_return": 0.8597528338432312, "regret": 0.0015834217192605138, "entropy": 0.07455594092607498, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:42.730109Z", "loop": 11882, "env_steps": 7300915199, "loss": 0.014006598852574825, "avg_return": 0.8620255589485168, "regret": 0.0015834217192605138, "entropy": 0.07344158738851547, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:43.583947Z", "loop": 11883, "env_steps": 7301529599, "loss": 0.014290767721831799, "avg_return": 0.862232506275177, "regret": 0.0015834217192605138, "entropy": 0.07524045556783676, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:44.438417Z", "loop": 11884, "env_steps": 7302143999, "loss": 0.016105158254504204, "avg_return": 0.861297607421875, "regret": 0.0015834217192605138, "entropy": 0.08069112151861191, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:45.292816Z", "loop": 11885, "env_steps": 7302758399, "loss": 0.01599440909922123, "avg_return": 0.8613533973693848, "regret": 0.0015834217192605138, "entropy": 0.07853133231401443, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:46.148583Z", "loop": 11886, "env_steps": 7303372799, "loss": 0.015621981583535671, "avg_return": 0.8601546287536621, "regret": 0.0015834217192605138, "entropy": 0.07910584658384323, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:47.003932Z", "loop": 11887, "env_steps": 7303987199, "loss": 0.015822086483240128, "avg_return": 0.8617598414421082, "regret": 0.0015834217192605138, "entropy": 0.07823003828525543, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:47.857236Z", "loop": 11888, "env_steps": 7304601599, "loss": 0.016470741480588913, "avg_return": 0.8609724044799805, "regret": 0.0015834217192605138, "entropy": 0.08380027115345001, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:48.710682Z", "loop": 11889, "env_steps": 7305215999, "loss": 0.015821926295757294, "avg_return": 0.8621009588241577, "regret": 0.0015834217192605138, "entropy": 0.08236435800790787, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:49.604899Z", "loop": 11890, "env_steps": 7305830399, "loss": 0.015376786701381207, "avg_return": 0.8628309369087219, "regret": 0.0015734502812847495, "entropy": 0.07996299117803574, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:50.459115Z", "loop": 11891, "env_steps": 7306444799, "loss": 0.015844076871871948, "avg_return": 0.8621798157691956, "regret": 0.0015734502812847495, "entropy": 0.07906368374824524, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:51.313473Z", "loop": 11892, "env_steps": 7307059199, "loss": 0.016070038080215454, "avg_return": 0.8638383150100708, "regret": 0.0015734502812847495, "entropy": 0.0813501849770546, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:52.166593Z", "loop": 11893, "env_steps": 7307673599, "loss": 0.01620691828429699, "avg_return": 0.8632564544677734, "regret": 0.0015734502812847495, "entropy": 0.08078211545944214, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:53.020487Z", "loop": 11894, "env_steps": 7308287999, "loss": 0.015397761948406696, "avg_return": 0.8638346791267395, "regret": 0.0015734502812847495, "entropy": 0.07513123750686646, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:53.874343Z", "loop": 11895, "env_steps": 7308902399, "loss": 0.013825302012264729, "avg_return": 0.8632423877716064, "regret": 0.0015734502812847495, "entropy": 0.07426568865776062, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:54.728807Z", "loop": 11896, "env_steps": 7309516799, "loss": 0.015093430876731873, "avg_return": 0.8634254932403564, "regret": 0.0015734502812847495, "entropy": 0.07655104249715805, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:55.583050Z", "loop": 11897, "env_steps": 7310131199, "loss": 0.014203712344169617, "avg_return": 0.8645443916320801, "regret": 0.0015734502812847495, "entropy": 0.07325111329555511, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:56.437190Z", "loop": 11898, "env_steps": 7310745599, "loss": 0.015769323334097862, "avg_return": 0.8634743690490723, "regret": 0.0015734502812847495, "entropy": 0.0798058733344078, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:57.291986Z", "loop": 11899, "env_steps": 7311359999, "loss": 0.015953650698065758, "avg_return": 0.863115668296814, "regret": 0.0015734502812847495, "entropy": 0.07975764572620392, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:58.187207Z", "loop": 11900, "env_steps": 7311974399, "loss": 0.016211381182074547, "avg_return": 0.8633852601051331, "regret": 0.00029168379842303693, "entropy": 0.07834727317094803, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:59.042255Z", "loop": 11901, "env_steps": 7312588799, "loss": 0.016934365034103394, "avg_return": 0.863081693649292, "regret": 0.00029168379842303693, "entropy": 0.07846155017614365, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:13:59.897883Z", "loop": 11902, "env_steps": 7313203199, "loss": 0.015249716117978096, "avg_return": 0.8630897998809814, "regret": 0.00029168379842303693, "entropy": 0.07957473397254944, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:00.752183Z", "loop": 11903, "env_steps": 7313817599, "loss": 0.014862336218357086, "avg_return": 0.8641788959503174, "regret": 0.00029168379842303693, "entropy": 0.0757080465555191, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:01.606586Z", "loop": 11904, "env_steps": 7314431999, "loss": 0.015407382510602474, "avg_return": 0.8636782169342041, "regret": 0.00029168379842303693, "entropy": 0.07774713635444641, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:02.461185Z", "loop": 11905, "env_steps": 7315046399, "loss": 0.01518850028514862, "avg_return": 0.8634142279624939, "regret": 0.00029168379842303693, "entropy": 0.07983393967151642, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:03.315037Z", "loop": 11906, "env_steps": 7315660799, "loss": 0.014077424071729183, "avg_return": 0.8637562394142151, "regret": 0.00029168379842303693, "entropy": 0.07341839373111725, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:04.170108Z", "loop": 11907, "env_steps": 7316275199, "loss": 0.014109713025391102, "avg_return": 0.8627304434776306, "regret": 0.00029168379842303693, "entropy": 0.07330728322267532, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:05.023936Z", "loop": 11908, "env_steps": 7316889599, "loss": 0.01476107258349657, "avg_return": 0.8633705973625183, "regret": 0.00029168379842303693, "entropy": 0.07606400549411774, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:05.878941Z", "loop": 11909, "env_steps": 7317503999, "loss": 0.015076115727424622, "avg_return": 0.8622686862945557, "regret": 0.00029168379842303693, "entropy": 0.07650703936815262, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:06.772475Z", "loop": 11910, "env_steps": 7318118399, "loss": 0.015016498044133186, "avg_return": 0.8627933859825134, "regret": 0.0008317201863974333, "entropy": 0.07317382842302322, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:07.625976Z", "loop": 11911, "env_steps": 7318732799, "loss": 0.014848056249320507, "avg_return": 0.8617071509361267, "regret": 0.0008317201863974333, "entropy": 0.07389990985393524, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:08.479666Z", "loop": 11912, "env_steps": 7319347199, "loss": 0.015294837765395641, "avg_return": 0.862347424030304, "regret": 0.0008317201863974333, "entropy": 0.07834666967391968, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:09.334754Z", "loop": 11913, "env_steps": 7319961599, "loss": 0.016402659937739372, "avg_return": 0.8613901734352112, "regret": 0.0008317201863974333, "entropy": 0.07828056067228317, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:10.188673Z", "loop": 11914, "env_steps": 7320575999, "loss": 0.017489125952124596, "avg_return": 0.8609824776649475, "regret": 0.0008317201863974333, "entropy": 0.08373641967773438, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:11.042523Z", "loop": 11915, "env_steps": 7321190399, "loss": 0.017279556021094322, "avg_return": 0.860901415348053, "regret": 0.0008317201863974333, "entropy": 0.08623525500297546, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:11.897857Z", "loop": 11916, "env_steps": 7321804799, "loss": 0.017028670758008957, "avg_return": 0.8619193434715271, "regret": 0.0008317201863974333, "entropy": 0.08657050877809525, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:12.754263Z", "loop": 11917, "env_steps": 7322419199, "loss": 0.016534656286239624, "avg_return": 0.8612037301063538, "regret": 0.0008317201863974333, "entropy": 0.08541756123304367, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:13.609219Z", "loop": 11918, "env_steps": 7323033599, "loss": 0.016402259469032288, "avg_return": 0.8627504706382751, "regret": 0.0008317201863974333, "entropy": 0.08206890523433685, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:14.463065Z", "loop": 11919, "env_steps": 7323647999, "loss": 0.01606648974120617, "avg_return": 0.8625563979148865, "regret": 0.0008317201863974333, "entropy": 0.07882402837276459, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:15.356938Z", "loop": 11920, "env_steps": 7324262399, "loss": 0.017365967854857445, "avg_return": 0.8628421425819397, "regret": 0.0003466284542810172, "entropy": 0.08574958890676498, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:16.211501Z", "loop": 11921, "env_steps": 7324876799, "loss": 0.017664460465312004, "avg_return": 0.8627598285675049, "regret": 0.0003466284542810172, "entropy": 0.09017451107501984, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:17.065937Z", "loop": 11922, "env_steps": 7325491199, "loss": 0.0180108230561018, "avg_return": 0.8619979023933411, "regret": 0.0003466284542810172, "entropy": 0.09065544605255127, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:17.919568Z", "loop": 11923, "env_steps": 7326105599, "loss": 0.016649149358272552, "avg_return": 0.8635655045509338, "regret": 0.0003466284542810172, "entropy": 0.0850643664598465, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:18.772347Z", "loop": 11924, "env_steps": 7326719999, "loss": 0.01779162511229515, "avg_return": 0.8634793162345886, "regret": 0.0003466284542810172, "entropy": 0.08724088966846466, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:19.625974Z", "loop": 11925, "env_steps": 7327334399, "loss": 0.016824644058942795, "avg_return": 0.8616762757301331, "regret": 0.0003466284542810172, "entropy": 0.08464870601892471, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:20.481562Z", "loop": 11926, "env_steps": 7327948799, "loss": 0.016502635553479195, "avg_return": 0.8633661866188049, "regret": 0.0003466284542810172, "entropy": 0.08341384679079056, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:21.335680Z", "loop": 11927, "env_steps": 7328563199, "loss": 0.016361551359295845, "avg_return": 0.8641302585601807, "regret": 0.0003466284542810172, "entropy": 0.08335961401462555, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:22.189216Z", "loop": 11928, "env_steps": 7329177599, "loss": 0.015919990837574005, "avg_return": 0.862311601638794, "regret": 0.0003466284542810172, "entropy": 0.08413928747177124, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:23.041973Z", "loop": 11929, "env_steps": 7329791999, "loss": 0.015869086608290672, "avg_return": 0.8639054298400879, "regret": 0.0003466284542810172, "entropy": 0.08178947120904922, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:23.935160Z", "loop": 11930, "env_steps": 7330406399, "loss": 0.014835542999207973, "avg_return": 0.8618919849395752, "regret": 0.00046940689207985997, "entropy": 0.07865233719348907, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:24.790093Z", "loop": 11931, "env_steps": 7331020799, "loss": 0.01601908914744854, "avg_return": 0.863666832447052, "regret": 0.00046940689207985997, "entropy": 0.0807107612490654, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:25.645204Z", "loop": 11932, "env_steps": 7331635199, "loss": 0.014225735329091549, "avg_return": 0.8627856373786926, "regret": 0.00046940689207985997, "entropy": 0.07853513211011887, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:26.500468Z", "loop": 11933, "env_steps": 7332249599, "loss": 0.015687329694628716, "avg_return": 0.8620437979698181, "regret": 0.00046940689207985997, "entropy": 0.08133392035961151, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:27.354607Z", "loop": 11934, "env_steps": 7332863999, "loss": 0.01600547321140766, "avg_return": 0.8643713593482971, "regret": 0.00046940689207985997, "entropy": 0.08241833746433258, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:28.209637Z", "loop": 11935, "env_steps": 7333478399, "loss": 0.015040873549878597, "avg_return": 0.8638483881950378, "regret": 0.00046940689207985997, "entropy": 0.08173865079879761, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:29.064921Z", "loop": 11936, "env_steps": 7334092799, "loss": 0.01581491529941559, "avg_return": 0.861922025680542, "regret": 0.00046940689207985997, "entropy": 0.08465103060007095, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:29.918797Z", "loop": 11937, "env_steps": 7334707199, "loss": 0.014800707809627056, "avg_return": 0.8632127046585083, "regret": 0.00046940689207985997, "entropy": 0.08234939724206924, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:30.772254Z", "loop": 11938, "env_steps": 7335321599, "loss": 0.015976056456565857, "avg_return": 0.8634805679321289, "regret": 0.00046940689207985997, "entropy": 0.08311504125595093, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:31.625209Z", "loop": 11939, "env_steps": 7335935999, "loss": 0.01666683703660965, "avg_return": 0.8624280095100403, "regret": 0.00046940689207985997, "entropy": 0.08399365842342377, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:32.520535Z", "loop": 11940, "env_steps": 7336550399, "loss": 0.01595836877822876, "avg_return": 0.8627380728721619, "regret": 0.0006534166168421507, "entropy": 0.08049360662698746, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:33.375471Z", "loop": 11941, "env_steps": 7337164799, "loss": 0.0163682010024786, "avg_return": 0.8623769283294678, "regret": 0.0006534166168421507, "entropy": 0.08875410258769989, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:34.229043Z", "loop": 11942, "env_steps": 7337779199, "loss": 0.017526285722851753, "avg_return": 0.8631683588027954, "regret": 0.0006534166168421507, "entropy": 0.08964674174785614, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:35.083613Z", "loop": 11943, "env_steps": 7338393599, "loss": 0.017437482252717018, "avg_return": 0.863006591796875, "regret": 0.0006534166168421507, "entropy": 0.09019055217504501, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:35.939097Z", "loop": 11944, "env_steps": 7339007999, "loss": 0.019283410161733627, "avg_return": 0.8634663820266724, "regret": 0.0006534166168421507, "entropy": 0.0985492691397667, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:36.793623Z", "loop": 11945, "env_steps": 7339622399, "loss": 0.020577022805809975, "avg_return": 0.8629913330078125, "regret": 0.0006534166168421507, "entropy": 0.10769118368625641, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:37.649016Z", "loop": 11946, "env_steps": 7340236799, "loss": 0.022065963596105576, "avg_return": 0.8622950315475464, "regret": 0.0006534166168421507, "entropy": 0.11390937864780426, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:38.503352Z", "loop": 11947, "env_steps": 7340851199, "loss": 0.023797497153282166, "avg_return": 0.8619533777236938, "regret": 0.0006534166168421507, "entropy": 0.11765085905790329, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:39.357032Z", "loop": 11948, "env_steps": 7341465599, "loss": 0.025276703760027885, "avg_return": 0.8601810932159424, "regret": 0.0006534166168421507, "entropy": 0.12351270020008087, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:40.210366Z", "loop": 11949, "env_steps": 7342079999, "loss": 0.028287678956985474, "avg_return": 0.8598175048828125, "regret": 0.0006534166168421507, "entropy": 0.13733051717281342, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:41.104716Z", "loop": 11950, "env_steps": 7342694399, "loss": 0.02818567492067814, "avg_return": 0.8587906956672668, "regret": 0.004128873813897371, "entropy": 0.14342795312404633, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:41.957944Z", "loop": 11951, "env_steps": 7343308799, "loss": 0.02969629503786564, "avg_return": 0.8592948317527771, "regret": 0.004128873813897371, "entropy": 0.14416024088859558, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:42.811085Z", "loop": 11952, "env_steps": 7343923199, "loss": 0.02724917232990265, "avg_return": 0.8622968792915344, "regret": 0.004128873813897371, "entropy": 0.1369875818490982, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:43.664306Z", "loop": 11953, "env_steps": 7344537599, "loss": 0.027115557342767715, "avg_return": 0.8628414273262024, "regret": 0.004128873813897371, "entropy": 0.12761029601097107, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:44.518085Z", "loop": 11954, "env_steps": 7345151999, "loss": 0.024344423785805702, "avg_return": 0.8629340529441833, "regret": 0.004128873813897371, "entropy": 0.11952393501996994, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:45.372686Z", "loop": 11955, "env_steps": 7345766399, "loss": 0.024649282917380333, "avg_return": 0.8627901673316956, "regret": 0.004128873813897371, "entropy": 0.12164782732725143, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:46.226339Z", "loop": 11956, "env_steps": 7346380799, "loss": 0.02249128744006157, "avg_return": 0.8622486591339111, "regret": 0.004128873813897371, "entropy": 0.1141292154788971, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:47.079720Z", "loop": 11957, "env_steps": 7346995199, "loss": 0.02247125655412674, "avg_return": 0.8625092506408691, "regret": 0.004128873813897371, "entropy": 0.11114367097616196, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:47.934145Z", "loop": 11958, "env_steps": 7347609599, "loss": 0.02340872772037983, "avg_return": 0.8627743721008301, "regret": 0.004128873813897371, "entropy": 0.11689536273479462, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:48.789069Z", "loop": 11959, "env_steps": 7348223999, "loss": 0.022805429995059967, "avg_return": 0.8635580539703369, "regret": 0.004128873813897371, "entropy": 0.11230751127004623, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:49.682748Z", "loop": 11960, "env_steps": 7348838399, "loss": 0.024210555478930473, "avg_return": 0.863711953163147, "regret": 0.00045795453479513526, "entropy": 0.11834736913442612, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:50.536197Z", "loop": 11961, "env_steps": 7349452799, "loss": 0.023564821109175682, "avg_return": 0.8632737398147583, "regret": 0.00045795453479513526, "entropy": 0.11742741614580154, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:51.390486Z", "loop": 11962, "env_steps": 7350067199, "loss": 0.02492241933941841, "avg_return": 0.8635709881782532, "regret": 0.00045795453479513526, "entropy": 0.11697359383106232, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:52.246470Z", "loop": 11963, "env_steps": 7350681599, "loss": 0.025956569239497185, "avg_return": 0.8625785708427429, "regret": 0.00045795453479513526, "entropy": 0.1195051446557045, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:53.101997Z", "loop": 11964, "env_steps": 7351295999, "loss": 0.024444634094834328, "avg_return": 0.862988293170929, "regret": 0.00045795453479513526, "entropy": 0.11801508814096451, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:53.956799Z", "loop": 11965, "env_steps": 7351910399, "loss": 0.023797808215022087, "avg_return": 0.8637118935585022, "regret": 0.00045795453479513526, "entropy": 0.11905306577682495, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:54.811826Z", "loop": 11966, "env_steps": 7352524799, "loss": 0.02387188747525215, "avg_return": 0.8639461398124695, "regret": 0.00045795453479513526, "entropy": 0.11613358557224274, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:55.667390Z", "loop": 11967, "env_steps": 7353139199, "loss": 0.022746127098798752, "avg_return": 0.8639146089553833, "regret": 0.00045795453479513526, "entropy": 0.10760616511106491, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:56.523376Z", "loop": 11968, "env_steps": 7353753599, "loss": 0.022267470136284828, "avg_return": 0.8619858026504517, "regret": 0.00045795453479513526, "entropy": 0.11195653676986694, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:57.377302Z", "loop": 11969, "env_steps": 7354367999, "loss": 0.02091568149626255, "avg_return": 0.8638797402381897, "regret": 0.00045795453479513526, "entropy": 0.10179337859153748, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:58.270786Z", "loop": 11970, "env_steps": 7354982399, "loss": 0.020383864641189575, "avg_return": 0.8625662326812744, "regret": 0.0003766616864595562, "entropy": 0.10075264424085617, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:59.125487Z", "loop": 11971, "env_steps": 7355596799, "loss": 0.020006289705634117, "avg_return": 0.8625230193138123, "regret": 0.0003766616864595562, "entropy": 0.09898475557565689, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:14:59.980378Z", "loop": 11972, "env_steps": 7356211199, "loss": 0.017652861773967743, "avg_return": 0.8635451197624207, "regret": 0.0003766616864595562, "entropy": 0.08960757404565811, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:00.834695Z", "loop": 11973, "env_steps": 7356825599, "loss": 0.016932345926761627, "avg_return": 0.8637337684631348, "regret": 0.0003766616864595562, "entropy": 0.08348140865564346, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:01.688681Z", "loop": 11974, "env_steps": 7357439999, "loss": 0.014151711948215961, "avg_return": 0.8637868165969849, "regret": 0.0003766616864595562, "entropy": 0.072571761906147, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:02.543710Z", "loop": 11975, "env_steps": 7358054399, "loss": 0.013285510241985321, "avg_return": 0.8625502586364746, "regret": 0.0003766616864595562, "entropy": 0.07448524236679077, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:03.398398Z", "loop": 11976, "env_steps": 7358668799, "loss": 0.014798032119870186, "avg_return": 0.8631566762924194, "regret": 0.0003766616864595562, "entropy": 0.0768289640545845, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:04.252529Z", "loop": 11977, "env_steps": 7359283199, "loss": 0.013935848139226437, "avg_return": 0.8628026247024536, "regret": 0.0003766616864595562, "entropy": 0.0739474967122078, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:05.107666Z", "loop": 11978, "env_steps": 7359897599, "loss": 0.015312634408473969, "avg_return": 0.8635357022285461, "regret": 0.0003766616864595562, "entropy": 0.07777467370033264, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:05.961650Z", "loop": 11979, "env_steps": 7360511999, "loss": 0.01494317501783371, "avg_return": 0.864022433757782, "regret": 0.0003766616864595562, "entropy": 0.07777802646160126, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:06.856248Z", "loop": 11980, "env_steps": 7361126399, "loss": 0.015607674606144428, "avg_return": 0.8625997304916382, "regret": 0.000477711291750893, "entropy": 0.07710891216993332, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:07.711463Z", "loop": 11981, "env_steps": 7361740799, "loss": 0.016524063423275948, "avg_return": 0.8616728186607361, "regret": 0.000477711291750893, "entropy": 0.08325958997011185, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:08.566995Z", "loop": 11982, "env_steps": 7362355199, "loss": 0.01679822988808155, "avg_return": 0.8631556630134583, "regret": 0.000477711291750893, "entropy": 0.08168300241231918, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:09.422811Z", "loop": 11983, "env_steps": 7362969599, "loss": 0.01630176231265068, "avg_return": 0.8631571531295776, "regret": 0.000477711291750893, "entropy": 0.08113320171833038, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:10.277600Z", "loop": 11984, "env_steps": 7363583999, "loss": 0.01622280851006508, "avg_return": 0.8636307716369629, "regret": 0.000477711291750893, "entropy": 0.08252093195915222, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:11.132948Z", "loop": 11985, "env_steps": 7364198399, "loss": 0.01703306846320629, "avg_return": 0.8629130125045776, "regret": 0.000477711291750893, "entropy": 0.08257504552602768, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:11.987450Z", "loop": 11986, "env_steps": 7364812799, "loss": 0.015364891849458218, "avg_return": 0.8637592792510986, "regret": 0.000477711291750893, "entropy": 0.07838068157434464, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:12.843043Z", "loop": 11987, "env_steps": 7365427199, "loss": 0.015119954943656921, "avg_return": 0.8618598580360413, "regret": 0.000477711291750893, "entropy": 0.07786638289690018, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:13.696556Z", "loop": 11988, "env_steps": 7366041599, "loss": 0.014539922587573528, "avg_return": 0.8626656532287598, "regret": 0.000477711291750893, "entropy": 0.07554049044847488, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:14.550625Z", "loop": 11989, "env_steps": 7366655999, "loss": 0.015742851421236992, "avg_return": 0.8650076389312744, "regret": 0.000477711291750893, "entropy": 0.07763756811618805, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:15.448294Z", "loop": 11990, "env_steps": 7367270399, "loss": 0.01633051410317421, "avg_return": 0.862267255783081, "regret": 0.0005442133406177163, "entropy": 0.08058977872133255, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:16.302684Z", "loop": 11991, "env_steps": 7367884799, "loss": 0.01475568301975727, "avg_return": 0.8631542921066284, "regret": 0.0005442133406177163, "entropy": 0.07611871510744095, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:17.157303Z", "loop": 11992, "env_steps": 7368499199, "loss": 0.016867736354470253, "avg_return": 0.8636769652366638, "regret": 0.0005442133406177163, "entropy": 0.08228985965251923, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:18.011927Z", "loop": 11993, "env_steps": 7369113599, "loss": 0.014256049878895283, "avg_return": 0.8625168204307556, "regret": 0.0005442133406177163, "entropy": 0.07424727827310562, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:18.866755Z", "loop": 11994, "env_steps": 7369727999, "loss": 0.016474973410367966, "avg_return": 0.8634421825408936, "regret": 0.0005442133406177163, "entropy": 0.0827915221452713, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:19.720919Z", "loop": 11995, "env_steps": 7370342399, "loss": 0.017552224919199944, "avg_return": 0.863318920135498, "regret": 0.0005442133406177163, "entropy": 0.08533042669296265, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:20.575888Z", "loop": 11996, "env_steps": 7370956799, "loss": 0.017000477761030197, "avg_return": 0.8643025755882263, "regret": 0.0005442133406177163, "entropy": 0.08278053253889084, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:21.430597Z", "loop": 11997, "env_steps": 7371571199, "loss": 0.017995696514844894, "avg_return": 0.8629049062728882, "regret": 0.0005442133406177163, "entropy": 0.08693768829107285, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:22.284268Z", "loop": 11998, "env_steps": 7372185599, "loss": 0.01769549958407879, "avg_return": 0.862115204334259, "regret": 0.0005442133406177163, "entropy": 0.08666951209306717, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:23.138399Z", "loop": 11999, "env_steps": 7372799999, "loss": 0.018332568928599358, "avg_return": 0.8620783686637878, "regret": 0.0005442133406177163, "entropy": 0.09014906734228134, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:24.034015Z", "loop": 12000, "env_steps": 7373414399, "loss": 0.01776733063161373, "avg_return": 0.8636944890022278, "regret": 0.001026924466714263, "entropy": 0.08380135893821716, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:24.887927Z", "loop": 12001, "env_steps": 7374028799, "loss": 0.018320702016353607, "avg_return": 0.8614892959594727, "regret": 0.001026924466714263, "entropy": 0.08808736503124237, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:25.743225Z", "loop": 12002, "env_steps": 7374643199, "loss": 0.015852000564336777, "avg_return": 0.8616576194763184, "regret": 0.001026924466714263, "entropy": 0.08278845250606537, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:26.597261Z", "loop": 12003, "env_steps": 7375257599, "loss": 0.017942504957318306, "avg_return": 0.8632181882858276, "regret": 0.001026924466714263, "entropy": 0.08720514178276062, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:27.451386Z", "loop": 12004, "env_steps": 7375871999, "loss": 0.01821713335812092, "avg_return": 0.8631565570831299, "regret": 0.001026924466714263, "entropy": 0.08988369256258011, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:28.306577Z", "loop": 12005, "env_steps": 7376486399, "loss": 0.019252492114901543, "avg_return": 0.8619349598884583, "regret": 0.001026924466714263, "entropy": 0.09077482670545578, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:29.161315Z", "loop": 12006, "env_steps": 7377100799, "loss": 0.019227279350161552, "avg_return": 0.8628395795822144, "regret": 0.001026924466714263, "entropy": 0.09410709142684937, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:30.017087Z", "loop": 12007, "env_steps": 7377715199, "loss": 0.019477015361189842, "avg_return": 0.863246500492096, "regret": 0.001026924466714263, "entropy": 0.09152182191610336, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:30.872590Z", "loop": 12008, "env_steps": 7378329599, "loss": 0.017246421426534653, "avg_return": 0.86289381980896, "regret": 0.001026924466714263, "entropy": 0.08435429632663727, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:31.728998Z", "loop": 12009, "env_steps": 7378943999, "loss": 0.016884760931134224, "avg_return": 0.8635017275810242, "regret": 0.001026924466714263, "entropy": 0.08381569385528564, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:32.623762Z", "loop": 12010, "env_steps": 7379558399, "loss": 0.016342759132385254, "avg_return": 0.8647005558013916, "regret": 0.00022401358000934124, "entropy": 0.08061874657869339, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:33.477094Z", "loop": 12011, "env_steps": 7380172799, "loss": 0.016085460782051086, "avg_return": 0.8636635541915894, "regret": 0.00022401358000934124, "entropy": 0.07580313086509705, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:34.331520Z", "loop": 12012, "env_steps": 7380787199, "loss": 0.015179291367530823, "avg_return": 0.8628604412078857, "regret": 0.00022401358000934124, "entropy": 0.07535101473331451, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:35.186971Z", "loop": 12013, "env_steps": 7381401599, "loss": 0.015071799047291279, "avg_return": 0.8637551069259644, "regret": 0.00022401358000934124, "entropy": 0.07300742715597153, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:36.040707Z", "loop": 12014, "env_steps": 7382015999, "loss": 0.01512643601745367, "avg_return": 0.8630552291870117, "regret": 0.00022401358000934124, "entropy": 0.07438523322343826, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:36.894666Z", "loop": 12015, "env_steps": 7382630399, "loss": 0.01583739183843136, "avg_return": 0.8642914295196533, "regret": 0.00022401358000934124, "entropy": 0.07862988859415054, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:37.748579Z", "loop": 12016, "env_steps": 7383244799, "loss": 0.016163518652319908, "avg_return": 0.8642857074737549, "regret": 0.00022401358000934124, "entropy": 0.08348555862903595, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:38.602930Z", "loop": 12017, "env_steps": 7383859199, "loss": 0.01716124825179577, "avg_return": 0.8620142936706543, "regret": 0.00022401358000934124, "entropy": 0.08800607174634933, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:39.457363Z", "loop": 12018, "env_steps": 7384473599, "loss": 0.015735222026705742, "avg_return": 0.8627114295959473, "regret": 0.00022401358000934124, "entropy": 0.07898299396038055, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:40.311077Z", "loop": 12019, "env_steps": 7385087999, "loss": 0.013762155547738075, "avg_return": 0.8622859716415405, "regret": 0.00022401358000934124, "entropy": 0.07554514706134796, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:41.203727Z", "loop": 12020, "env_steps": 7385702399, "loss": 0.015394753776490688, "avg_return": 0.8616407513618469, "regret": 0.0018656885949894786, "entropy": 0.07913850247859955, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:42.058386Z", "loop": 12021, "env_steps": 7386316799, "loss": 0.018092965707182884, "avg_return": 0.8611393570899963, "regret": 0.0018656885949894786, "entropy": 0.08977492153644562, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:42.913072Z", "loop": 12022, "env_steps": 7386931199, "loss": 0.020859163254499435, "avg_return": 0.8594118356704712, "regret": 0.0018656885949894786, "entropy": 0.0964980497956276, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:43.767963Z", "loop": 12023, "env_steps": 7387545599, "loss": 0.020796917378902435, "avg_return": 0.8590580224990845, "regret": 0.0018656885949894786, "entropy": 0.10188017785549164, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:44.622131Z", "loop": 12024, "env_steps": 7388159999, "loss": 0.020786236971616745, "avg_return": 0.8587997555732727, "regret": 0.0018656885949894786, "entropy": 0.10111197084188461, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:45.476269Z", "loop": 12025, "env_steps": 7388774399, "loss": 0.019872693344950676, "avg_return": 0.8586739301681519, "regret": 0.0018656885949894786, "entropy": 0.0980287417769432, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:46.330626Z", "loop": 12026, "env_steps": 7389388799, "loss": 0.019688492640852928, "avg_return": 0.8586373925209045, "regret": 0.0018656885949894786, "entropy": 0.09556573629379272, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:47.185893Z", "loop": 12027, "env_steps": 7390003199, "loss": 0.018886949867010117, "avg_return": 0.8605088591575623, "regret": 0.0018656885949894786, "entropy": 0.09374324232339859, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:48.040048Z", "loop": 12028, "env_steps": 7390617599, "loss": 0.019475379958748817, "avg_return": 0.8599146008491516, "regret": 0.0018656885949894786, "entropy": 0.09668334573507309, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:48.894444Z", "loop": 12029, "env_steps": 7391231999, "loss": 0.020580003038048744, "avg_return": 0.8584861159324646, "regret": 0.0018656885949894786, "entropy": 0.09875886142253876, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:49.787882Z", "loop": 12030, "env_steps": 7391846399, "loss": 0.01945365220308304, "avg_return": 0.8612236976623535, "regret": 0.002933243755251169, "entropy": 0.09928929805755615, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:50.642121Z", "loop": 12031, "env_steps": 7392460799, "loss": 0.018280019983649254, "avg_return": 0.8605919480323792, "regret": 0.002933243755251169, "entropy": 0.09383267164230347, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:51.495983Z", "loop": 12032, "env_steps": 7393075199, "loss": 0.01929650828242302, "avg_return": 0.8595229387283325, "regret": 0.002933243755251169, "entropy": 0.09471207112073898, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:52.350034Z", "loop": 12033, "env_steps": 7393689599, "loss": 0.01812560297548771, "avg_return": 0.8609681129455566, "regret": 0.002933243755251169, "entropy": 0.09159231930971146, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:53.204519Z", "loop": 12034, "env_steps": 7394303999, "loss": 0.01732208952307701, "avg_return": 0.8604384660720825, "regret": 0.002933243755251169, "entropy": 0.08915458619594574, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:54.059362Z", "loop": 12035, "env_steps": 7394918399, "loss": 0.01768415980041027, "avg_return": 0.8604686856269836, "regret": 0.002933243755251169, "entropy": 0.08875657618045807, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:54.914343Z", "loop": 12036, "env_steps": 7395532799, "loss": 0.017740868031978607, "avg_return": 0.8605421185493469, "regret": 0.002933243755251169, "entropy": 0.09025458246469498, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:55.770456Z", "loop": 12037, "env_steps": 7396147199, "loss": 0.016962312161922455, "avg_return": 0.8605786561965942, "regret": 0.002933243755251169, "entropy": 0.08938589692115784, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:56.623659Z", "loop": 12038, "env_steps": 7396761599, "loss": 0.01721920631825924, "avg_return": 0.8609222769737244, "regret": 0.002933243755251169, "entropy": 0.08885147422552109, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:57.476933Z", "loop": 12039, "env_steps": 7397375999, "loss": 0.018032444640994072, "avg_return": 0.8591982126235962, "regret": 0.002933243755251169, "entropy": 0.09331239759922028, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:58.373159Z", "loop": 12040, "env_steps": 7397990399, "loss": 0.019098078832030296, "avg_return": 0.861369252204895, "regret": 0.0017233188264071941, "entropy": 0.09687268733978271, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:15:59.227817Z", "loop": 12041, "env_steps": 7398604799, "loss": 0.019190942868590355, "avg_return": 0.8617821335792542, "regret": 0.0017233188264071941, "entropy": 0.09857049584388733, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:00.081475Z", "loop": 12042, "env_steps": 7399219199, "loss": 0.019764376804232597, "avg_return": 0.8622099161148071, "regret": 0.0017233188264071941, "entropy": 0.09657742828130722, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:00.935436Z", "loop": 12043, "env_steps": 7399833599, "loss": 0.019389471039175987, "avg_return": 0.8622886538505554, "regret": 0.0017233188264071941, "entropy": 0.0937533751130104, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:01.790876Z", "loop": 12044, "env_steps": 7400447999, "loss": 0.02004505880177021, "avg_return": 0.8626165986061096, "regret": 0.0017233188264071941, "entropy": 0.09904243797063828, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:02.645524Z", "loop": 12045, "env_steps": 7401062399, "loss": 0.021434444934129715, "avg_return": 0.8626247644424438, "regret": 0.0017233188264071941, "entropy": 0.10325929522514343, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:03.500265Z", "loop": 12046, "env_steps": 7401676799, "loss": 0.021572008728981018, "avg_return": 0.8633075952529907, "regret": 0.0017233188264071941, "entropy": 0.10242702811956406, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:04.353262Z", "loop": 12047, "env_steps": 7402291199, "loss": 0.021759871393442154, "avg_return": 0.8617112636566162, "regret": 0.0017233188264071941, "entropy": 0.10258536785840988, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:05.207336Z", "loop": 12048, "env_steps": 7402905599, "loss": 0.020917102694511414, "avg_return": 0.8628301024436951, "regret": 0.0017233188264071941, "entropy": 0.10014274716377258, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:06.065111Z", "loop": 12049, "env_steps": 7403519999, "loss": 0.020769141614437103, "avg_return": 0.8646627068519592, "regret": 0.0017233188264071941, "entropy": 0.1002054437994957, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:06.960443Z", "loop": 12050, "env_steps": 7404134399, "loss": 0.02021561563014984, "avg_return": 0.8631158471107483, "regret": 0.00030099094146862626, "entropy": 0.09993847459554672, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:07.814811Z", "loop": 12051, "env_steps": 7404748799, "loss": 0.020678972825407982, "avg_return": 0.8634653687477112, "regret": 0.00030099094146862626, "entropy": 0.09838183969259262, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:08.668714Z", "loop": 12052, "env_steps": 7405363199, "loss": 0.020011497661471367, "avg_return": 0.8642043471336365, "regret": 0.00030099094146862626, "entropy": 0.0967443510890007, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:09.522500Z", "loop": 12053, "env_steps": 7405977599, "loss": 0.018642595037817955, "avg_return": 0.8637427091598511, "regret": 0.00030099094146862626, "entropy": 0.09320701658725739, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:10.376801Z", "loop": 12054, "env_steps": 7406591999, "loss": 0.019846705719828606, "avg_return": 0.8652927875518799, "regret": 0.00030099094146862626, "entropy": 0.0950789526104927, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:11.230965Z", "loop": 12055, "env_steps": 7407206399, "loss": 0.018771139904856682, "avg_return": 0.8636387586593628, "regret": 0.00030099094146862626, "entropy": 0.08825609087944031, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:12.084609Z", "loop": 12056, "env_steps": 7407820799, "loss": 0.01830165646970272, "avg_return": 0.8630948066711426, "regret": 0.00030099094146862626, "entropy": 0.09205442667007446, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:12.939346Z", "loop": 12057, "env_steps": 7408435199, "loss": 0.01856434904038906, "avg_return": 0.8638190031051636, "regret": 0.00030099094146862626, "entropy": 0.09304732084274292, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:13.793609Z", "loop": 12058, "env_steps": 7409049599, "loss": 0.018214337527751923, "avg_return": 0.8630316257476807, "regret": 0.00030099094146862626, "entropy": 0.08894523233175278, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:14.648471Z", "loop": 12059, "env_steps": 7409663999, "loss": 0.016378022730350494, "avg_return": 0.8636019825935364, "regret": 0.00030099094146862626, "entropy": 0.08522114902734756, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:15.541199Z", "loop": 12060, "env_steps": 7410278399, "loss": 0.016236985102295876, "avg_return": 0.8641352653503418, "regret": 0.0001790538663044572, "entropy": 0.08053477853536606, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:16.395071Z", "loop": 12061, "env_steps": 7410892799, "loss": 0.014295627363026142, "avg_return": 0.8627854585647583, "regret": 0.0001790538663044572, "entropy": 0.07498852908611298, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:17.248379Z", "loop": 12062, "env_steps": 7411507199, "loss": 0.01483754999935627, "avg_return": 0.8628177046775818, "regret": 0.0001790538663044572, "entropy": 0.0713530033826828, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:18.103034Z", "loop": 12063, "env_steps": 7412121599, "loss": 0.014344044029712677, "avg_return": 0.8634646534919739, "regret": 0.0001790538663044572, "entropy": 0.07018689066171646, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:18.958016Z", "loop": 12064, "env_steps": 7412735999, "loss": 0.015003296546638012, "avg_return": 0.8630725145339966, "regret": 0.0001790538663044572, "entropy": 0.07348939776420593, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:19.811611Z", "loop": 12065, "env_steps": 7413350399, "loss": 0.013938632793724537, "avg_return": 0.8629084229469299, "regret": 0.0001790538663044572, "entropy": 0.0741802230477333, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:20.664885Z", "loop": 12066, "env_steps": 7413964799, "loss": 0.013713422231376171, "avg_return": 0.8632925748825073, "regret": 0.0001790538663044572, "entropy": 0.07095000147819519, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:21.518613Z", "loop": 12067, "env_steps": 7414579199, "loss": 0.013491056859493256, "avg_return": 0.8636391162872314, "regret": 0.0001790538663044572, "entropy": 0.07034367322921753, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:22.373897Z", "loop": 12068, "env_steps": 7415193599, "loss": 0.01434315461665392, "avg_return": 0.8632972240447998, "regret": 0.0001790538663044572, "entropy": 0.07490982115268707, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:23.228662Z", "loop": 12069, "env_steps": 7415807999, "loss": 0.013334608636796474, "avg_return": 0.8621193766593933, "regret": 0.0001790538663044572, "entropy": 0.06822742521762848, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:24.120982Z", "loop": 12070, "env_steps": 7416422399, "loss": 0.01449873298406601, "avg_return": 0.8618758320808411, "regret": 0.00044883269583806396, "entropy": 0.07359739392995834, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:24.974253Z", "loop": 12071, "env_steps": 7417036799, "loss": 0.013706048019230366, "avg_return": 0.8619946241378784, "regret": 0.00044883269583806396, "entropy": 0.07056420296430588, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:25.830095Z", "loop": 12072, "env_steps": 7417651199, "loss": 0.014466904103755951, "avg_return": 0.8632494211196899, "regret": 0.00044883269583806396, "entropy": 0.07419964671134949, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:26.684125Z", "loop": 12073, "env_steps": 7418265599, "loss": 0.014664207585155964, "avg_return": 0.8638541102409363, "regret": 0.00044883269583806396, "entropy": 0.07396768033504486, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:27.537811Z", "loop": 12074, "env_steps": 7418879999, "loss": 0.013982117176055908, "avg_return": 0.8638869524002075, "regret": 0.00044883269583806396, "entropy": 0.0705215185880661, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:28.391904Z", "loop": 12075, "env_steps": 7419494399, "loss": 0.01466391235589981, "avg_return": 0.862144410610199, "regret": 0.00044883269583806396, "entropy": 0.07553128898143768, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:29.246984Z", "loop": 12076, "env_steps": 7420108799, "loss": 0.015622525475919247, "avg_return": 0.863044261932373, "regret": 0.00044883269583806396, "entropy": 0.07707525789737701, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:30.101548Z", "loop": 12077, "env_steps": 7420723199, "loss": 0.01565149612724781, "avg_return": 0.863115668296814, "regret": 0.00044883269583806396, "entropy": 0.07999775558710098, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:30.955494Z", "loop": 12078, "env_steps": 7421337599, "loss": 0.016537373885512352, "avg_return": 0.862362265586853, "regret": 0.00044883269583806396, "entropy": 0.07962136715650558, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:31.809136Z", "loop": 12079, "env_steps": 7421951999, "loss": 0.01709781400859356, "avg_return": 0.8629274964332581, "regret": 0.00044883269583806396, "entropy": 0.07915908843278885, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:32.704133Z", "loop": 12080, "env_steps": 7422566399, "loss": 0.016566647216677666, "avg_return": 0.8617464303970337, "regret": 0.0010633994825184345, "entropy": 0.08438540250062943, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:33.558684Z", "loop": 12081, "env_steps": 7423180799, "loss": 0.015915265306830406, "avg_return": 0.8624111413955688, "regret": 0.0010633994825184345, "entropy": 0.08245028555393219, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:34.413696Z", "loop": 12082, "env_steps": 7423795199, "loss": 0.015617619268596172, "avg_return": 0.8627992868423462, "regret": 0.0010633994825184345, "entropy": 0.07633601129055023, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:35.268332Z", "loop": 12083, "env_steps": 7424409599, "loss": 0.014110413379967213, "avg_return": 0.8629785180091858, "regret": 0.0010633994825184345, "entropy": 0.0736999362707138, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:36.124301Z", "loop": 12084, "env_steps": 7425023999, "loss": 0.01492283958941698, "avg_return": 0.8626613616943359, "regret": 0.0010633994825184345, "entropy": 0.07444833219051361, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:36.978591Z", "loop": 12085, "env_steps": 7425638399, "loss": 0.013837873004376888, "avg_return": 0.8634170889854431, "regret": 0.0010633994825184345, "entropy": 0.07398838549852371, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:37.832836Z", "loop": 12086, "env_steps": 7426252799, "loss": 0.014647801406681538, "avg_return": 0.8629063367843628, "regret": 0.0010633994825184345, "entropy": 0.07401673495769501, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:38.686783Z", "loop": 12087, "env_steps": 7426867199, "loss": 0.014317045919597149, "avg_return": 0.8628814816474915, "regret": 0.0010633994825184345, "entropy": 0.07401978224515915, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:39.541181Z", "loop": 12088, "env_steps": 7427481599, "loss": 0.015952369198203087, "avg_return": 0.8625322580337524, "regret": 0.0010633994825184345, "entropy": 0.07912664860486984, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:40.395125Z", "loop": 12089, "env_steps": 7428095999, "loss": 0.016499856486916542, "avg_return": 0.8650985956192017, "regret": 0.0010633994825184345, "entropy": 0.08213938027620316, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:41.289854Z", "loop": 12090, "env_steps": 7428710399, "loss": 0.015110461972653866, "avg_return": 0.8642975091934204, "regret": 0.00019197781512048095, "entropy": 0.07794882357120514, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:42.144070Z", "loop": 12091, "env_steps": 7429324799, "loss": 0.01615813933312893, "avg_return": 0.864142656326294, "regret": 0.00019197781512048095, "entropy": 0.08300767093896866, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:42.999523Z", "loop": 12092, "env_steps": 7429939199, "loss": 0.016977645456790924, "avg_return": 0.8639952540397644, "regret": 0.00019197781512048095, "entropy": 0.08528818190097809, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:43.854035Z", "loop": 12093, "env_steps": 7430553599, "loss": 0.0178378876298666, "avg_return": 0.8636124730110168, "regret": 0.00019197781512048095, "entropy": 0.09022145718336105, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:44.709327Z", "loop": 12094, "env_steps": 7431167999, "loss": 0.017734332010149956, "avg_return": 0.8635228872299194, "regret": 0.00019197781512048095, "entropy": 0.08770298957824707, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:45.564282Z", "loop": 12095, "env_steps": 7431782399, "loss": 0.018843378871679306, "avg_return": 0.8641942739486694, "regret": 0.00019197781512048095, "entropy": 0.0897136703133583, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:46.419719Z", "loop": 12096, "env_steps": 7432396799, "loss": 0.018020974472165108, "avg_return": 0.8637217283248901, "regret": 0.00019197781512048095, "entropy": 0.09142889082431793, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:47.273784Z", "loop": 12097, "env_steps": 7433011199, "loss": 0.017982380464673042, "avg_return": 0.8633970618247986, "regret": 0.00019197781512048095, "entropy": 0.08642521500587463, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:48.128883Z", "loop": 12098, "env_steps": 7433625599, "loss": 0.01821531169116497, "avg_return": 0.8628296256065369, "regret": 0.00019197781512048095, "entropy": 0.08857569098472595, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:48.983905Z", "loop": 12099, "env_steps": 7434239999, "loss": 0.018215931951999664, "avg_return": 0.8626655340194702, "regret": 0.00019197781512048095, "entropy": 0.08827312290668488, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:49.879152Z", "loop": 12100, "env_steps": 7434854399, "loss": 0.018460523337125778, "avg_return": 0.863040566444397, "regret": 0.00048321971553377807, "entropy": 0.09151355922222137, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:50.733436Z", "loop": 12101, "env_steps": 7435468799, "loss": 0.01990940421819687, "avg_return": 0.8622550368309021, "regret": 0.00048321971553377807, "entropy": 0.09790458530187607, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:51.588855Z", "loop": 12102, "env_steps": 7436083199, "loss": 0.02038308046758175, "avg_return": 0.8620933294296265, "regret": 0.00048321971553377807, "entropy": 0.09954135119915009, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:52.444134Z", "loop": 12103, "env_steps": 7436697599, "loss": 0.019903777167201042, "avg_return": 0.8628891110420227, "regret": 0.00048321971553377807, "entropy": 0.09860809892416, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:53.299771Z", "loop": 12104, "env_steps": 7437311999, "loss": 0.018885089084506035, "avg_return": 0.8621628284454346, "regret": 0.00048321971553377807, "entropy": 0.09442391991615295, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:54.154639Z", "loop": 12105, "env_steps": 7437926399, "loss": 0.019774390384554863, "avg_return": 0.8630871772766113, "regret": 0.00048321971553377807, "entropy": 0.09646537154912949, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:55.008085Z", "loop": 12106, "env_steps": 7438540799, "loss": 0.02009591832756996, "avg_return": 0.8616964817047119, "regret": 0.00048321971553377807, "entropy": 0.0998769998550415, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:55.862193Z", "loop": 12107, "env_steps": 7439155199, "loss": 0.02098248340189457, "avg_return": 0.8629536032676697, "regret": 0.00048321971553377807, "entropy": 0.1061183512210846, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:56.719356Z", "loop": 12108, "env_steps": 7439769599, "loss": 0.02156008780002594, "avg_return": 0.8629454970359802, "regret": 0.00048321971553377807, "entropy": 0.1083124503493309, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:57.573636Z", "loop": 12109, "env_steps": 7440383999, "loss": 0.021104030311107635, "avg_return": 0.8623524904251099, "regret": 0.00048321971553377807, "entropy": 0.11094371974468231, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:58.469890Z", "loop": 12110, "env_steps": 7440998399, "loss": 0.02105705253779888, "avg_return": 0.8605491518974304, "regret": 0.002078915713354945, "entropy": 0.10350355505943298, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:16:59.323988Z", "loop": 12111, "env_steps": 7441612799, "loss": 0.01799737475812435, "avg_return": 0.8602641224861145, "regret": 0.002078915713354945, "entropy": 0.09480208903551102, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:00.177243Z", "loop": 12112, "env_steps": 7442227199, "loss": 0.01829044334590435, "avg_return": 0.8599801659584045, "regret": 0.002078915713354945, "entropy": 0.0920669436454773, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:01.031580Z", "loop": 12113, "env_steps": 7442841599, "loss": 0.020797042176127434, "avg_return": 0.8596000075340271, "regret": 0.002078915713354945, "entropy": 0.09938211739063263, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:01.885369Z", "loop": 12114, "env_steps": 7443455999, "loss": 0.02043565735220909, "avg_return": 0.8590167164802551, "regret": 0.002078915713354945, "entropy": 0.10516709089279175, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:02.740528Z", "loop": 12115, "env_steps": 7444070399, "loss": 0.020410684868693352, "avg_return": 0.8591868281364441, "regret": 0.002078915713354945, "entropy": 0.10832890123128891, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:03.594704Z", "loop": 12116, "env_steps": 7444684799, "loss": 0.022152837365865707, "avg_return": 0.856675922870636, "regret": 0.002078915713354945, "entropy": 0.11406660079956055, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:04.448599Z", "loop": 12117, "env_steps": 7445299199, "loss": 0.022122465074062347, "avg_return": 0.8581892251968384, "regret": 0.002078915713354945, "entropy": 0.11040119081735611, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:05.303513Z", "loop": 12118, "env_steps": 7445913599, "loss": 0.021427035331726074, "avg_return": 0.8574684858322144, "regret": 0.002078915713354945, "entropy": 0.1052645668387413, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:06.157667Z", "loop": 12119, "env_steps": 7446527999, "loss": 0.02295929752290249, "avg_return": 0.8584906458854675, "regret": 0.002078915713354945, "entropy": 0.11223455518484116, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:07.053562Z", "loop": 12120, "env_steps": 7447142399, "loss": 0.02218586765229702, "avg_return": 0.856172502040863, "regret": 0.006682112347334623, "entropy": 0.10994341224431992, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:07.907850Z", "loop": 12121, "env_steps": 7447756799, "loss": 0.02282610349357128, "avg_return": 0.855730414390564, "regret": 0.006682112347334623, "entropy": 0.11311674118041992, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:08.763250Z", "loop": 12122, "env_steps": 7448371199, "loss": 0.022184880450367928, "avg_return": 0.8549131751060486, "regret": 0.006682112347334623, "entropy": 0.1100144162774086, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:09.618506Z", "loop": 12123, "env_steps": 7448985599, "loss": 0.02217770181596279, "avg_return": 0.8553637862205505, "regret": 0.006682112347334623, "entropy": 0.11301945894956589, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:10.472160Z", "loop": 12124, "env_steps": 7449599999, "loss": 0.023997405543923378, "avg_return": 0.8575320839881897, "regret": 0.006682112347334623, "entropy": 0.11415841430425644, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:11.324938Z", "loop": 12125, "env_steps": 7450214399, "loss": 0.02244442328810692, "avg_return": 0.8597545623779297, "regret": 0.006682112347334623, "entropy": 0.11128691583871841, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:12.178109Z", "loop": 12126, "env_steps": 7450828799, "loss": 0.023695938289165497, "avg_return": 0.860121488571167, "regret": 0.006682112347334623, "entropy": 0.11316084116697311, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:13.032468Z", "loop": 12127, "env_steps": 7451443199, "loss": 0.02223576419055462, "avg_return": 0.859851598739624, "regret": 0.006682112347334623, "entropy": 0.11205022037029266, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:13.886923Z", "loop": 12128, "env_steps": 7452057599, "loss": 0.024470359086990356, "avg_return": 0.8593983054161072, "regret": 0.006682112347334623, "entropy": 0.11976058781147003, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:14.739729Z", "loop": 12129, "env_steps": 7452671999, "loss": 0.024697162210941315, "avg_return": 0.8582780957221985, "regret": 0.006682112347334623, "entropy": 0.11994238197803497, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:15.632466Z", "loop": 12130, "env_steps": 7453286399, "loss": 0.023908741772174835, "avg_return": 0.8620343208312988, "regret": 0.003532291855663061, "entropy": 0.11278411000967026, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:16.486505Z", "loop": 12131, "env_steps": 7453900799, "loss": 0.024380307644605637, "avg_return": 0.8604121208190918, "regret": 0.003532291855663061, "entropy": 0.12063246220350266, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:17.340487Z", "loop": 12132, "env_steps": 7454515199, "loss": 0.024454554542899132, "avg_return": 0.8598523139953613, "regret": 0.003532291855663061, "entropy": 0.1199953630566597, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:18.194826Z", "loop": 12133, "env_steps": 7455129599, "loss": 0.023966778069734573, "avg_return": 0.8608030676841736, "regret": 0.003532291855663061, "entropy": 0.11918959021568298, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:19.048778Z", "loop": 12134, "env_steps": 7455743999, "loss": 0.023916123434901237, "avg_return": 0.8614205121994019, "regret": 0.003532291855663061, "entropy": 0.11814071983098984, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:19.903909Z", "loop": 12135, "env_steps": 7456358399, "loss": 0.02229269966483116, "avg_return": 0.8621761202812195, "regret": 0.003532291855663061, "entropy": 0.11326929181814194, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:20.758398Z", "loop": 12136, "env_steps": 7456972799, "loss": 0.023274818435311317, "avg_return": 0.862738847732544, "regret": 0.003532291855663061, "entropy": 0.11618537455797195, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:21.612549Z", "loop": 12137, "env_steps": 7457587199, "loss": 0.02394053153693676, "avg_return": 0.8598311543464661, "regret": 0.003532291855663061, "entropy": 0.11992872506380081, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:22.466757Z", "loop": 12138, "env_steps": 7458201599, "loss": 0.02383315935730934, "avg_return": 0.8609142303466797, "regret": 0.003532291855663061, "entropy": 0.11741707473993301, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:23.320385Z", "loop": 12139, "env_steps": 7458815999, "loss": 0.024411682039499283, "avg_return": 0.8606423139572144, "regret": 0.003532291855663061, "entropy": 0.11984003335237503, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:24.216432Z", "loop": 12140, "env_steps": 7459430399, "loss": 0.023483268916606903, "avg_return": 0.8616880774497986, "regret": 0.0020830552093684673, "entropy": 0.11865298449993134, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:25.069763Z", "loop": 12141, "env_steps": 7460044799, "loss": 0.02477535605430603, "avg_return": 0.860234797000885, "regret": 0.0020830552093684673, "entropy": 0.12239018082618713, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:25.923753Z", "loop": 12142, "env_steps": 7460659199, "loss": 0.023403504863381386, "avg_return": 0.8608219623565674, "regret": 0.0020830552093684673, "entropy": 0.1168820932507515, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:26.778079Z", "loop": 12143, "env_steps": 7461273599, "loss": 0.025601059198379517, "avg_return": 0.8626112341880798, "regret": 0.0020830552093684673, "entropy": 0.11826995760202408, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:27.632856Z", "loop": 12144, "env_steps": 7461887999, "loss": 0.023709231987595558, "avg_return": 0.8617019653320312, "regret": 0.0020830552093684673, "entropy": 0.11986043304204941, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:28.485857Z", "loop": 12145, "env_steps": 7462502399, "loss": 0.024167325347661972, "avg_return": 0.8626611828804016, "regret": 0.0020830552093684673, "entropy": 0.12087229639291763, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:29.339369Z", "loop": 12146, "env_steps": 7463116799, "loss": 0.025274932384490967, "avg_return": 0.8623877167701721, "regret": 0.0020830552093684673, "entropy": 0.12156900763511658, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:30.193339Z", "loop": 12147, "env_steps": 7463731199, "loss": 0.025161076337099075, "avg_return": 0.8617869019508362, "regret": 0.0020830552093684673, "entropy": 0.12149737775325775, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:31.046883Z", "loop": 12148, "env_steps": 7464345599, "loss": 0.024100061506032944, "avg_return": 0.8627958297729492, "regret": 0.0020830552093684673, "entropy": 0.1198897734284401, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:31.901008Z", "loop": 12149, "env_steps": 7464959999, "loss": 0.023197367787361145, "avg_return": 0.8600171208381653, "regret": 0.0020830552093684673, "entropy": 0.11679619550704956, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:32.795815Z", "loop": 12150, "env_steps": 7465574399, "loss": 0.022152064368128777, "avg_return": 0.8624133467674255, "regret": 0.0018076928099617362, "entropy": 0.11691486090421677, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:33.649346Z", "loop": 12151, "env_steps": 7466188799, "loss": 0.022600239142775536, "avg_return": 0.86179119348526, "regret": 0.0018076928099617362, "entropy": 0.1151127740740776, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:34.503678Z", "loop": 12152, "env_steps": 7466803199, "loss": 0.022374801337718964, "avg_return": 0.8596645593643188, "regret": 0.0018076928099617362, "entropy": 0.11856892704963684, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:35.358528Z", "loop": 12153, "env_steps": 7467417599, "loss": 0.02279164455831051, "avg_return": 0.8612092137336731, "regret": 0.0018076928099617362, "entropy": 0.11737047135829926, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:36.213173Z", "loop": 12154, "env_steps": 7468031999, "loss": 0.025224367156624794, "avg_return": 0.8621746301651001, "regret": 0.0018076928099617362, "entropy": 0.12250058352947235, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:37.066557Z", "loop": 12155, "env_steps": 7468646399, "loss": 0.024726627394557, "avg_return": 0.8600310683250427, "regret": 0.0018076928099617362, "entropy": 0.12614506483078003, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:37.919112Z", "loop": 12156, "env_steps": 7469260799, "loss": 0.026007650420069695, "avg_return": 0.8605623841285706, "regret": 0.0018076928099617362, "entropy": 0.13006114959716797, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:38.772583Z", "loop": 12157, "env_steps": 7469875199, "loss": 0.025877896696329117, "avg_return": 0.8597182631492615, "regret": 0.0018076928099617362, "entropy": 0.13702361285686493, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:39.626789Z", "loop": 12158, "env_steps": 7470489599, "loss": 0.025064876303076744, "avg_return": 0.8600201606750488, "regret": 0.0018076928099617362, "entropy": 0.12997904419898987, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:40.480299Z", "loop": 12159, "env_steps": 7471103999, "loss": 0.02617516927421093, "avg_return": 0.8598674535751343, "regret": 0.0018076928099617362, "entropy": 0.12911628186702728, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:41.373847Z", "loop": 12160, "env_steps": 7471718399, "loss": 0.02400779351592064, "avg_return": 0.8607707023620605, "regret": 0.002487742342054844, "entropy": 0.12521973252296448, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:42.227960Z", "loop": 12161, "env_steps": 7472332799, "loss": 0.022885559126734734, "avg_return": 0.8609861731529236, "regret": 0.002487742342054844, "entropy": 0.11925886571407318, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:43.083608Z", "loop": 12162, "env_steps": 7472947199, "loss": 0.022571513429284096, "avg_return": 0.8619683980941772, "regret": 0.002487742342054844, "entropy": 0.11719675362110138, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:43.938852Z", "loop": 12163, "env_steps": 7473561599, "loss": 0.02358224056661129, "avg_return": 0.861132025718689, "regret": 0.002487742342054844, "entropy": 0.12005919963121414, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:44.793149Z", "loop": 12164, "env_steps": 7474175999, "loss": 0.024747630581259727, "avg_return": 0.8619869351387024, "regret": 0.002487742342054844, "entropy": 0.12517552077770233, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:45.646125Z", "loop": 12165, "env_steps": 7474790399, "loss": 0.025135992094874382, "avg_return": 0.8609577417373657, "regret": 0.002487742342054844, "entropy": 0.1254734843969345, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:46.501136Z", "loop": 12166, "env_steps": 7475404799, "loss": 0.025798041373491287, "avg_return": 0.8623413443565369, "regret": 0.002487742342054844, "entropy": 0.12831315398216248, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:47.355246Z", "loop": 12167, "env_steps": 7476019199, "loss": 0.026021674275398254, "avg_return": 0.8601461052894592, "regret": 0.002487742342054844, "entropy": 0.12413210421800613, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:48.208972Z", "loop": 12168, "env_steps": 7476633599, "loss": 0.025099391117691994, "avg_return": 0.8624863028526306, "regret": 0.002487742342054844, "entropy": 0.12188670784235, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:49.062475Z", "loop": 12169, "env_steps": 7477247999, "loss": 0.025062590837478638, "avg_return": 0.8616999387741089, "regret": 0.002487742342054844, "entropy": 0.12369124591350555, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:49.956655Z", "loop": 12170, "env_steps": 7477862399, "loss": 0.025543157011270523, "avg_return": 0.8625667691230774, "regret": 0.0012239995412528515, "entropy": 0.12059938907623291, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:50.810737Z", "loop": 12171, "env_steps": 7478476799, "loss": 0.024190504103899002, "avg_return": 0.8626014590263367, "regret": 0.0012239995412528515, "entropy": 0.12196293473243713, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:51.665019Z", "loop": 12172, "env_steps": 7479091199, "loss": 0.025070175528526306, "avg_return": 0.8626729249954224, "regret": 0.0012239995412528515, "entropy": 0.12565046548843384, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:52.519521Z", "loop": 12173, "env_steps": 7479705599, "loss": 0.02574082277715206, "avg_return": 0.8631414771080017, "regret": 0.0012239995412528515, "entropy": 0.12158073484897614, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:53.373234Z", "loop": 12174, "env_steps": 7480319999, "loss": 0.025172948837280273, "avg_return": 0.8635798096656799, "regret": 0.0012239995412528515, "entropy": 0.12486229836940765, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:54.226555Z", "loop": 12175, "env_steps": 7480934399, "loss": 0.02427895925939083, "avg_return": 0.8628911375999451, "regret": 0.0012239995412528515, "entropy": 0.12412697821855545, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:55.080865Z", "loop": 12176, "env_steps": 7481548799, "loss": 0.02437548153102398, "avg_return": 0.8635768890380859, "regret": 0.0012239995412528515, "entropy": 0.12170407921075821, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:55.935568Z", "loop": 12177, "env_steps": 7482163199, "loss": 0.023646563291549683, "avg_return": 0.8638879656791687, "regret": 0.0012239995412528515, "entropy": 0.12029721587896347, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:56.790199Z", "loop": 12178, "env_steps": 7482777599, "loss": 0.022583596408367157, "avg_return": 0.861965537071228, "regret": 0.0012239995412528515, "entropy": 0.10953284800052643, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:57.644026Z", "loop": 12179, "env_steps": 7483391999, "loss": 0.021549677476286888, "avg_return": 0.86314457654953, "regret": 0.0012239995412528515, "entropy": 0.10877675563097, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:58.538943Z", "loop": 12180, "env_steps": 7484006399, "loss": 0.020620254799723625, "avg_return": 0.8638308048248291, "regret": 0.0009289902518503368, "entropy": 0.10686508566141129, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:17:59.394306Z", "loop": 12181, "env_steps": 7484620799, "loss": 0.021187707781791687, "avg_return": 0.8628619313240051, "regret": 0.0009289902518503368, "entropy": 0.10764332115650177, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:00.249183Z", "loop": 12182, "env_steps": 7485235199, "loss": 0.021093890070915222, "avg_return": 0.8620636463165283, "regret": 0.0009289902518503368, "entropy": 0.11075921356678009, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:01.103574Z", "loop": 12183, "env_steps": 7485849599, "loss": 0.020777573809027672, "avg_return": 0.8624419569969177, "regret": 0.0009289902518503368, "entropy": 0.11022736132144928, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:01.957769Z", "loop": 12184, "env_steps": 7486463999, "loss": 0.022741924971342087, "avg_return": 0.8624914884567261, "regret": 0.0009289902518503368, "entropy": 0.1161811500787735, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:02.812887Z", "loop": 12185, "env_steps": 7487078399, "loss": 0.025427943095564842, "avg_return": 0.8599987030029297, "regret": 0.0009289902518503368, "entropy": 0.1299336701631546, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:03.668135Z", "loop": 12186, "env_steps": 7487692799, "loss": 0.02777772583067417, "avg_return": 0.8611575365066528, "regret": 0.0009289902518503368, "entropy": 0.13808892667293549, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:04.522808Z", "loop": 12187, "env_steps": 7488307199, "loss": 0.027145057916641235, "avg_return": 0.8590930104255676, "regret": 0.0009289902518503368, "entropy": 0.14020472764968872, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:05.375880Z", "loop": 12188, "env_steps": 7488921599, "loss": 0.02993256226181984, "avg_return": 0.8583231568336487, "regret": 0.0009289902518503368, "entropy": 0.14964602887630463, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:06.230624Z", "loop": 12189, "env_steps": 7489535999, "loss": 0.030623996630311012, "avg_return": 0.8560645580291748, "regret": 0.0009289902518503368, "entropy": 0.15154336392879486, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:07.126161Z", "loop": 12190, "env_steps": 7490150399, "loss": 0.031071284785866737, "avg_return": 0.8565051555633545, "regret": 0.007131163962185383, "entropy": 0.1522703617811203, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:07.979308Z", "loop": 12191, "env_steps": 7490764799, "loss": 0.02900587022304535, "avg_return": 0.8592307567596436, "regret": 0.007131163962185383, "entropy": 0.14223681390285492, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:08.833592Z", "loop": 12192, "env_steps": 7491379199, "loss": 0.024999186396598816, "avg_return": 0.8593434691429138, "regret": 0.007131163962185383, "entropy": 0.12761111557483673, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:09.688778Z", "loop": 12193, "env_steps": 7491993599, "loss": 0.025089580565690994, "avg_return": 0.8609916567802429, "regret": 0.007131163962185383, "entropy": 0.12061475962400436, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:10.543939Z", "loop": 12194, "env_steps": 7492607999, "loss": 0.02334452234208584, "avg_return": 0.8588731288909912, "regret": 0.007131163962185383, "entropy": 0.11529066413640976, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:11.398592Z", "loop": 12195, "env_steps": 7493222399, "loss": 0.02429313212633133, "avg_return": 0.8622724413871765, "regret": 0.007131163962185383, "entropy": 0.11571372300386429, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:12.253679Z", "loop": 12196, "env_steps": 7493836799, "loss": 0.022884046658873558, "avg_return": 0.8594508171081543, "regret": 0.007131163962185383, "entropy": 0.1133081316947937, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:13.108663Z", "loop": 12197, "env_steps": 7494451199, "loss": 0.021593280136585236, "avg_return": 0.8591322898864746, "regret": 0.007131163962185383, "entropy": 0.11140532791614532, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:13.963056Z", "loop": 12198, "env_steps": 7495065599, "loss": 0.022449318319559097, "avg_return": 0.8582724332809448, "regret": 0.007131163962185383, "entropy": 0.10923381894826889, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:14.818312Z", "loop": 12199, "env_steps": 7495679999, "loss": 0.02221239171922207, "avg_return": 0.8577588200569153, "regret": 0.007131163962185383, "entropy": 0.11007436364889145, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:15.711755Z", "loop": 12200, "env_steps": 7496294399, "loss": 0.021599646657705307, "avg_return": 0.8575385808944702, "regret": 0.004540476948022842, "entropy": 0.10453464090824127, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:16.567140Z", "loop": 12201, "env_steps": 7496908799, "loss": 0.021616054698824883, "avg_return": 0.858293890953064, "regret": 0.004540476948022842, "entropy": 0.11148800700902939, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:17.420942Z", "loop": 12202, "env_steps": 7497523199, "loss": 0.022524049505591393, "avg_return": 0.857078492641449, "regret": 0.004540476948022842, "entropy": 0.11010898649692535, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:18.274713Z", "loop": 12203, "env_steps": 7498137599, "loss": 0.021682970225811005, "avg_return": 0.8582086563110352, "regret": 0.004540476948022842, "entropy": 0.1045662984251976, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:19.128754Z", "loop": 12204, "env_steps": 7498751999, "loss": 0.0223292987793684, "avg_return": 0.8584632277488708, "regret": 0.004540476948022842, "entropy": 0.11031550168991089, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:19.983940Z", "loop": 12205, "env_steps": 7499366399, "loss": 0.021469514816999435, "avg_return": 0.858443021774292, "regret": 0.004540476948022842, "entropy": 0.10369016975164413, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:20.837307Z", "loop": 12206, "env_steps": 7499980799, "loss": 0.01995997130870819, "avg_return": 0.8569926023483276, "regret": 0.004540476948022842, "entropy": 0.10228299349546432, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:21.690216Z", "loop": 12207, "env_steps": 7500595199, "loss": 0.022212376818060875, "avg_return": 0.8575299382209778, "regret": 0.004540476948022842, "entropy": 0.10767941921949387, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:22.543720Z", "loop": 12208, "env_steps": 7501209599, "loss": 0.02123190276324749, "avg_return": 0.8568314909934998, "regret": 0.004540476948022842, "entropy": 0.10760031640529633, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:23.399339Z", "loop": 12209, "env_steps": 7501823999, "loss": 0.021611249074339867, "avg_return": 0.8576855659484863, "regret": 0.004540476948022842, "entropy": 0.10705093294382095, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:24.296196Z", "loop": 12210, "env_steps": 7502438399, "loss": 0.02149384468793869, "avg_return": 0.8602070212364197, "regret": 0.0034478772431612015, "entropy": 0.10834817588329315, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:25.150716Z", "loop": 12211, "env_steps": 7503052799, "loss": 0.02092399261891842, "avg_return": 0.8623319864273071, "regret": 0.0034478772431612015, "entropy": 0.10224814713001251, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:26.004580Z", "loop": 12212, "env_steps": 7503667199, "loss": 0.018691429868340492, "avg_return": 0.8598242402076721, "regret": 0.0034478772431612015, "entropy": 0.09318359941244125, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:26.858796Z", "loop": 12213, "env_steps": 7504281599, "loss": 0.015219718217849731, "avg_return": 0.8616832494735718, "regret": 0.0034478772431612015, "entropy": 0.08203639835119247, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:27.713254Z", "loop": 12214, "env_steps": 7504895999, "loss": 0.015903117135167122, "avg_return": 0.863664448261261, "regret": 0.0034478772431612015, "entropy": 0.0822334811091423, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:28.566491Z", "loop": 12215, "env_steps": 7505510399, "loss": 0.01668979413807392, "avg_return": 0.8623993396759033, "regret": 0.0034478772431612015, "entropy": 0.08490309864282608, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:29.420144Z", "loop": 12216, "env_steps": 7506124799, "loss": 0.019439449533820152, "avg_return": 0.8642519116401672, "regret": 0.0034478772431612015, "entropy": 0.09383924305438995, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:30.273730Z", "loop": 12217, "env_steps": 7506739199, "loss": 0.021581431850790977, "avg_return": 0.8644207715988159, "regret": 0.0034478772431612015, "entropy": 0.10466396808624268, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:31.127480Z", "loop": 12218, "env_steps": 7507353599, "loss": 0.022796055302023888, "avg_return": 0.8624330759048462, "regret": 0.0034478772431612015, "entropy": 0.10815263539552689, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:31.981313Z", "loop": 12219, "env_steps": 7507967999, "loss": 0.021478740498423576, "avg_return": 0.8636802434921265, "regret": 0.0034478772431612015, "entropy": 0.1002163290977478, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:32.875754Z", "loop": 12220, "env_steps": 7508582399, "loss": 0.021420331671833992, "avg_return": 0.8636923432350159, "regret": 0.00025267968885600567, "entropy": 0.09735500067472458, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:33.729381Z", "loop": 12221, "env_steps": 7509196799, "loss": 0.019675344228744507, "avg_return": 0.8631453514099121, "regret": 0.00025267968885600567, "entropy": 0.09206193685531616, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:34.583476Z", "loop": 12222, "env_steps": 7509811199, "loss": 0.018290922045707703, "avg_return": 0.8636327385902405, "regret": 0.00025267968885600567, "entropy": 0.08881235867738724, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:35.438008Z", "loop": 12223, "env_steps": 7510425599, "loss": 0.017774298787117004, "avg_return": 0.8627498745918274, "regret": 0.00025267968885600567, "entropy": 0.08607039600610733, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:36.291677Z", "loop": 12224, "env_steps": 7511039999, "loss": 0.018198398873209953, "avg_return": 0.863383412361145, "regret": 0.00025267968885600567, "entropy": 0.08930222690105438, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:37.146230Z", "loop": 12225, "env_steps": 7511654399, "loss": 0.01744874194264412, "avg_return": 0.8630664348602295, "regret": 0.00025267968885600567, "entropy": 0.08835791051387787, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:38.000345Z", "loop": 12226, "env_steps": 7512268799, "loss": 0.01685023121535778, "avg_return": 0.8625665307044983, "regret": 0.00025267968885600567, "entropy": 0.08109249174594879, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:38.855671Z", "loop": 12227, "env_steps": 7512883199, "loss": 0.015397131443023682, "avg_return": 0.8641769886016846, "regret": 0.00025267968885600567, "entropy": 0.07884886115789413, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:39.710143Z", "loop": 12228, "env_steps": 7513497599, "loss": 0.013964501209557056, "avg_return": 0.8630247116088867, "regret": 0.00025267968885600567, "entropy": 0.07210736721754074, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:40.564614Z", "loop": 12229, "env_steps": 7514111999, "loss": 0.01409976463764906, "avg_return": 0.8617681860923767, "regret": 0.00025267968885600567, "entropy": 0.07390794903039932, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:41.460245Z", "loop": 12230, "env_steps": 7514726399, "loss": 0.014674290083348751, "avg_return": 0.8621323704719543, "regret": 0.0007833775016479194, "entropy": 0.07493378967046738, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:42.315076Z", "loop": 12231, "env_steps": 7515340799, "loss": 0.016481388360261917, "avg_return": 0.861894428730011, "regret": 0.0007833775016479194, "entropy": 0.07912305742502213, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:43.169757Z", "loop": 12232, "env_steps": 7515955199, "loss": 0.017285555601119995, "avg_return": 0.8617666959762573, "regret": 0.0007833775016479194, "entropy": 0.08396533876657486, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:44.023553Z", "loop": 12233, "env_steps": 7516569599, "loss": 0.01731136254966259, "avg_return": 0.86261385679245, "regret": 0.0007833775016479194, "entropy": 0.08537276834249496, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:44.877169Z", "loop": 12234, "env_steps": 7517183999, "loss": 0.016359051689505577, "avg_return": 0.8616325259208679, "regret": 0.0007833775016479194, "entropy": 0.08034899085760117, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:45.730222Z", "loop": 12235, "env_steps": 7517798399, "loss": 0.01621514931321144, "avg_return": 0.8608208298683167, "regret": 0.0007833775016479194, "entropy": 0.08113104850053787, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:46.584633Z", "loop": 12236, "env_steps": 7518412799, "loss": 0.015491202473640442, "avg_return": 0.8598884344100952, "regret": 0.0007833775016479194, "entropy": 0.07733145356178284, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:47.439919Z", "loop": 12237, "env_steps": 7519027199, "loss": 0.016024237498641014, "avg_return": 0.8616689443588257, "regret": 0.0007833775016479194, "entropy": 0.07768170535564423, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:48.293230Z", "loop": 12238, "env_steps": 7519641599, "loss": 0.014867792837321758, "avg_return": 0.8617472648620605, "regret": 0.0007833775016479194, "entropy": 0.07556777447462082, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:49.146703Z", "loop": 12239, "env_steps": 7520255999, "loss": 0.016328001394867897, "avg_return": 0.8601866960525513, "regret": 0.0007833775016479194, "entropy": 0.07834295183420181, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:50.041324Z", "loop": 12240, "env_steps": 7520870399, "loss": 0.014322017319500446, "avg_return": 0.861852765083313, "regret": 0.0021512662060558796, "entropy": 0.0766940787434578, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:50.895749Z", "loop": 12241, "env_steps": 7521484799, "loss": 0.015207047574222088, "avg_return": 0.8621842861175537, "regret": 0.0021512662060558796, "entropy": 0.07818826287984848, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:51.749417Z", "loop": 12242, "env_steps": 7522099199, "loss": 0.01547303982079029, "avg_return": 0.8611124753952026, "regret": 0.0021512662060558796, "entropy": 0.08132889866828918, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:52.602491Z", "loop": 12243, "env_steps": 7522713599, "loss": 0.016821619123220444, "avg_return": 0.8618605732917786, "regret": 0.0021512662060558796, "entropy": 0.080967016518116, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:53.457269Z", "loop": 12244, "env_steps": 7523327999, "loss": 0.01586342416703701, "avg_return": 0.8611086010932922, "regret": 0.0021512662060558796, "entropy": 0.08038713783025742, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:54.311401Z", "loop": 12245, "env_steps": 7523942399, "loss": 0.014805467799305916, "avg_return": 0.8606681227684021, "regret": 0.0021512662060558796, "entropy": 0.07518603652715683, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:55.164964Z", "loop": 12246, "env_steps": 7524556799, "loss": 0.015316120348870754, "avg_return": 0.8634916543960571, "regret": 0.0021512662060558796, "entropy": 0.07769539207220078, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:56.018376Z", "loop": 12247, "env_steps": 7525171199, "loss": 0.016328759491443634, "avg_return": 0.8628064393997192, "regret": 0.0021512662060558796, "entropy": 0.077783964574337, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:56.872580Z", "loop": 12248, "env_steps": 7525785599, "loss": 0.016170021146535873, "avg_return": 0.8619315028190613, "regret": 0.0021512662060558796, "entropy": 0.08305240422487259, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:57.727161Z", "loop": 12249, "env_steps": 7526399999, "loss": 0.016753656789660454, "avg_return": 0.8616563081741333, "regret": 0.0021512662060558796, "entropy": 0.08007758855819702, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:58.620489Z", "loop": 12250, "env_steps": 7527014399, "loss": 0.017623430117964745, "avg_return": 0.8621786832809448, "regret": 0.001107875956222415, "entropy": 0.08275926113128662, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:18:59.474051Z", "loop": 12251, "env_steps": 7527628799, "loss": 0.017104187980294228, "avg_return": 0.8629046082496643, "regret": 0.001107875956222415, "entropy": 0.07944289594888687, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:00.328139Z", "loop": 12252, "env_steps": 7528243199, "loss": 0.017533479258418083, "avg_return": 0.8635908961296082, "regret": 0.001107875956222415, "entropy": 0.08498333394527435, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:01.182508Z", "loop": 12253, "env_steps": 7528857599, "loss": 0.01739559695124626, "avg_return": 0.8627846240997314, "regret": 0.001107875956222415, "entropy": 0.08306329697370529, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:02.036499Z", "loop": 12254, "env_steps": 7529471999, "loss": 0.015389451757073402, "avg_return": 0.8631783127784729, "regret": 0.001107875956222415, "entropy": 0.08100567758083344, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:02.891671Z", "loop": 12255, "env_steps": 7530086399, "loss": 0.0160988699644804, "avg_return": 0.8629646897315979, "regret": 0.001107875956222415, "entropy": 0.08239065110683441, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:03.745155Z", "loop": 12256, "env_steps": 7530700799, "loss": 0.01685301773250103, "avg_return": 0.8636332154273987, "regret": 0.001107875956222415, "entropy": 0.08250197768211365, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:04.598804Z", "loop": 12257, "env_steps": 7531315199, "loss": 0.01624407060444355, "avg_return": 0.8634480834007263, "regret": 0.001107875956222415, "entropy": 0.08003934472799301, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:05.452459Z", "loop": 12258, "env_steps": 7531929599, "loss": 0.01716216653585434, "avg_return": 0.8625374436378479, "regret": 0.001107875956222415, "entropy": 0.08282129466533661, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:06.306607Z", "loop": 12259, "env_steps": 7532543999, "loss": 0.016582071781158447, "avg_return": 0.8631194233894348, "regret": 0.001107875956222415, "entropy": 0.08136643469333649, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:07.201627Z", "loop": 12260, "env_steps": 7533158399, "loss": 0.015859467908740044, "avg_return": 0.8637674450874329, "regret": 0.0004321039014030248, "entropy": 0.07954291999340057, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:08.054838Z", "loop": 12261, "env_steps": 7533772799, "loss": 0.015854237601161003, "avg_return": 0.8622449040412903, "regret": 0.0004321039014030248, "entropy": 0.07917933166027069, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:08.909062Z", "loop": 12262, "env_steps": 7534387199, "loss": 0.01628420501947403, "avg_return": 0.8637830018997192, "regret": 0.0004321039014030248, "entropy": 0.08336836099624634, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:09.764675Z", "loop": 12263, "env_steps": 7535001599, "loss": 0.017957760021090508, "avg_return": 0.8647895455360413, "regret": 0.0004321039014030248, "entropy": 0.08442196995019913, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:10.618960Z", "loop": 12264, "env_steps": 7535615999, "loss": 0.016024770215153694, "avg_return": 0.8638014197349548, "regret": 0.0004321039014030248, "entropy": 0.07790403813123703, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:11.472855Z", "loop": 12265, "env_steps": 7536230399, "loss": 0.014701190404593945, "avg_return": 0.8636765480041504, "regret": 0.0004321039014030248, "entropy": 0.07757916301488876, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:12.326167Z", "loop": 12266, "env_steps": 7536844799, "loss": 0.014900597743690014, "avg_return": 0.8641669154167175, "regret": 0.0004321039014030248, "entropy": 0.0752326101064682, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:13.180599Z", "loop": 12267, "env_steps": 7537459199, "loss": 0.015489942394196987, "avg_return": 0.8640562891960144, "regret": 0.0004321039014030248, "entropy": 0.0742676630616188, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:14.033992Z", "loop": 12268, "env_steps": 7538073599, "loss": 0.016431670635938644, "avg_return": 0.861950695514679, "regret": 0.0004321039014030248, "entropy": 0.07815362513065338, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:14.887935Z", "loop": 12269, "env_steps": 7538687999, "loss": 0.016413720324635506, "avg_return": 0.8633307814598083, "regret": 0.0004321039014030248, "entropy": 0.07963310927152634, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:15.781816Z", "loop": 12270, "env_steps": 7539302399, "loss": 0.01589019037783146, "avg_return": 0.8632272481918335, "regret": 0.0003966382937505841, "entropy": 0.08048549294471741, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:16.636338Z", "loop": 12271, "env_steps": 7539916799, "loss": 0.016423963010311127, "avg_return": 0.8642635345458984, "regret": 0.0003966382937505841, "entropy": 0.07901690900325775, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:17.491757Z", "loop": 12272, "env_steps": 7540531199, "loss": 0.015947818756103516, "avg_return": 0.8635098338127136, "regret": 0.0003966382937505841, "entropy": 0.08016403764486313, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:18.346740Z", "loop": 12273, "env_steps": 7541145599, "loss": 0.016172777861356735, "avg_return": 0.8634663820266724, "regret": 0.0003966382937505841, "entropy": 0.07788057625293732, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:19.201356Z", "loop": 12274, "env_steps": 7541759999, "loss": 0.014304123818874359, "avg_return": 0.8633028268814087, "regret": 0.0003966382937505841, "entropy": 0.07316907495260239, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:20.056402Z", "loop": 12275, "env_steps": 7542374399, "loss": 0.014830531552433968, "avg_return": 0.86395663022995, "regret": 0.0003966382937505841, "entropy": 0.07510671764612198, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:20.911245Z", "loop": 12276, "env_steps": 7542988799, "loss": 0.013512629084289074, "avg_return": 0.8625867962837219, "regret": 0.0003966382937505841, "entropy": 0.07304311543703079, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:21.766427Z", "loop": 12277, "env_steps": 7543603199, "loss": 0.015550774522125721, "avg_return": 0.8634905219078064, "regret": 0.0003966382937505841, "entropy": 0.07577890157699585, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:22.620068Z", "loop": 12278, "env_steps": 7544217599, "loss": 0.014443396590650082, "avg_return": 0.8640032410621643, "regret": 0.0003966382937505841, "entropy": 0.07494363188743591, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:23.473163Z", "loop": 12279, "env_steps": 7544831999, "loss": 0.015355299226939678, "avg_return": 0.8616475462913513, "regret": 0.0003966382937505841, "entropy": 0.07465434819459915, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:24.366770Z", "loop": 12280, "env_steps": 7545446399, "loss": 0.013922460377216339, "avg_return": 0.8627787232398987, "regret": 0.0007608757587149739, "entropy": 0.07008539885282516, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:25.220839Z", "loop": 12281, "env_steps": 7546060799, "loss": 0.015637747943401337, "avg_return": 0.8632590770721436, "regret": 0.0007608757587149739, "entropy": 0.07288842648267746, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:26.075296Z", "loop": 12282, "env_steps": 7546675199, "loss": 0.014113758690655231, "avg_return": 0.8624988198280334, "regret": 0.0007608757587149739, "entropy": 0.0693182647228241, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:26.928919Z", "loop": 12283, "env_steps": 7547289599, "loss": 0.013449402526021004, "avg_return": 0.8613306879997253, "regret": 0.0007608757587149739, "entropy": 0.07053934782743454, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:27.782873Z", "loop": 12284, "env_steps": 7547903999, "loss": 0.012679199688136578, "avg_return": 0.8607398867607117, "regret": 0.0007608757587149739, "entropy": 0.0633731409907341, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:28.637490Z", "loop": 12285, "env_steps": 7548518399, "loss": 0.013835514895617962, "avg_return": 0.8620852828025818, "regret": 0.0007608757587149739, "entropy": 0.07407201826572418, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:29.491983Z", "loop": 12286, "env_steps": 7549132799, "loss": 0.013625151477754116, "avg_return": 0.8605162501335144, "regret": 0.0007608757587149739, "entropy": 0.07098212838172913, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:30.346226Z", "loop": 12287, "env_steps": 7549747199, "loss": 0.01639374904334545, "avg_return": 0.8596193790435791, "regret": 0.0007608757587149739, "entropy": 0.08108537644147873, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:31.200179Z", "loop": 12288, "env_steps": 7550361599, "loss": 0.014900149777531624, "avg_return": 0.861934244632721, "regret": 0.0007608757587149739, "entropy": 0.07760544121265411, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:32.053707Z", "loop": 12289, "env_steps": 7550975999, "loss": 0.015472561120986938, "avg_return": 0.8612374067306519, "regret": 0.0007608757587149739, "entropy": 0.07999858260154724, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:32.948104Z", "loop": 12290, "env_steps": 7551590399, "loss": 0.017100635915994644, "avg_return": 0.8622810244560242, "regret": 0.0017306336667388678, "entropy": 0.08488509058952332, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:33.802741Z", "loop": 12291, "env_steps": 7552204799, "loss": 0.016836268827319145, "avg_return": 0.86151123046875, "regret": 0.0017306336667388678, "entropy": 0.08231931179761887, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:34.656203Z", "loop": 12292, "env_steps": 7552819199, "loss": 0.01638987474143505, "avg_return": 0.8618756532669067, "regret": 0.0017306336667388678, "entropy": 0.0800534337759018, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:35.509777Z", "loop": 12293, "env_steps": 7553433599, "loss": 0.01774344965815544, "avg_return": 0.8625500798225403, "regret": 0.0017306336667388678, "entropy": 0.08364933729171753, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:36.363936Z", "loop": 12294, "env_steps": 7554047999, "loss": 0.01660863868892193, "avg_return": 0.862453818321228, "regret": 0.0017306336667388678, "entropy": 0.08161579072475433, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:37.219228Z", "loop": 12295, "env_steps": 7554662399, "loss": 0.01636168360710144, "avg_return": 0.8619480729103088, "regret": 0.0017306336667388678, "entropy": 0.08310285210609436, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:38.072887Z", "loop": 12296, "env_steps": 7555276799, "loss": 0.015485922805964947, "avg_return": 0.8634637594223022, "regret": 0.0017306336667388678, "entropy": 0.07814154773950577, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:38.925959Z", "loop": 12297, "env_steps": 7555891199, "loss": 0.014481722377240658, "avg_return": 0.863986611366272, "regret": 0.0017306336667388678, "entropy": 0.0752812922000885, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:39.779666Z", "loop": 12298, "env_steps": 7556505599, "loss": 0.014561699703335762, "avg_return": 0.8631952404975891, "regret": 0.0017306336667388678, "entropy": 0.07493489980697632, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:40.634482Z", "loop": 12299, "env_steps": 7557119999, "loss": 0.01335106696933508, "avg_return": 0.8627204298973083, "regret": 0.0017306336667388678, "entropy": 0.07197628170251846, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:41.528583Z", "loop": 12300, "env_steps": 7557734399, "loss": 0.014326907694339752, "avg_return": 0.8637350797653198, "regret": 0.0001206405577249825, "entropy": 0.07334516942501068, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:42.382407Z", "loop": 12301, "env_steps": 7558348799, "loss": 0.015849750488996506, "avg_return": 0.8635095357894897, "regret": 0.0001206405577249825, "entropy": 0.07893146574497223, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:43.236920Z", "loop": 12302, "env_steps": 7558963199, "loss": 0.015328525565564632, "avg_return": 0.8633791208267212, "regret": 0.0001206405577249825, "entropy": 0.0772641971707344, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:44.091868Z", "loop": 12303, "env_steps": 7559577599, "loss": 0.0161270834505558, "avg_return": 0.8627164959907532, "regret": 0.0001206405577249825, "entropy": 0.08144566416740417, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:44.945341Z", "loop": 12304, "env_steps": 7560191999, "loss": 0.016767147928476334, "avg_return": 0.8645561933517456, "regret": 0.0001206405577249825, "entropy": 0.08465646207332611, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:45.798915Z", "loop": 12305, "env_steps": 7560806399, "loss": 0.015536288730800152, "avg_return": 0.8642295598983765, "regret": 0.0001206405577249825, "entropy": 0.07712798565626144, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:46.652355Z", "loop": 12306, "env_steps": 7561420799, "loss": 0.014316185377538204, "avg_return": 0.8646212220191956, "regret": 0.0001206405577249825, "entropy": 0.07489762455224991, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:47.506198Z", "loop": 12307, "env_steps": 7562035199, "loss": 0.013673816807568073, "avg_return": 0.8628551363945007, "regret": 0.0001206405577249825, "entropy": 0.0715138167142868, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:48.360022Z", "loop": 12308, "env_steps": 7562649599, "loss": 0.014673830941319466, "avg_return": 0.8636195063591003, "regret": 0.0001206405577249825, "entropy": 0.07312539964914322, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:49.213510Z", "loop": 12309, "env_steps": 7563263999, "loss": 0.013873444870114326, "avg_return": 0.864447832107544, "regret": 0.0001206405577249825, "entropy": 0.07064223289489746, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:50.109728Z", "loop": 12310, "env_steps": 7563878399, "loss": 0.015907809138298035, "avg_return": 0.8633522987365723, "regret": 0.0003791126364376396, "entropy": 0.07514546811580658, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:50.964355Z", "loop": 12311, "env_steps": 7564492799, "loss": 0.015721837058663368, "avg_return": 0.8637719750404358, "regret": 0.0003791126364376396, "entropy": 0.0767473578453064, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:51.819472Z", "loop": 12312, "env_steps": 7565107199, "loss": 0.017296843230724335, "avg_return": 0.8636045455932617, "regret": 0.0003791126364376396, "entropy": 0.08228550106287003, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:52.674052Z", "loop": 12313, "env_steps": 7565721599, "loss": 0.017008891329169273, "avg_return": 0.8613258004188538, "regret": 0.0003791126364376396, "entropy": 0.08207878470420837, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:53.527918Z", "loop": 12314, "env_steps": 7566335999, "loss": 0.016698656603693962, "avg_return": 0.862976610660553, "regret": 0.0003791126364376396, "entropy": 0.08519717305898666, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:54.383362Z", "loop": 12315, "env_steps": 7566950399, "loss": 0.01799408160150051, "avg_return": 0.8617343306541443, "regret": 0.0003791126364376396, "entropy": 0.08692469447851181, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:55.238196Z", "loop": 12316, "env_steps": 7567564799, "loss": 0.017244158312678337, "avg_return": 0.8625443577766418, "regret": 0.0003791126364376396, "entropy": 0.08864329755306244, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:56.092755Z", "loop": 12317, "env_steps": 7568179199, "loss": 0.017590375617146492, "avg_return": 0.8627023696899414, "regret": 0.0003791126364376396, "entropy": 0.08676227927207947, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:56.946580Z", "loop": 12318, "env_steps": 7568793599, "loss": 0.017823610454797745, "avg_return": 0.860048234462738, "regret": 0.0003791126364376396, "entropy": 0.08832158148288727, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:57.801924Z", "loop": 12319, "env_steps": 7569407999, "loss": 0.018502764403820038, "avg_return": 0.8624672889709473, "regret": 0.0003791126364376396, "entropy": 0.0911560133099556, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:58.695710Z", "loop": 12320, "env_steps": 7570022399, "loss": 0.01897280290722847, "avg_return": 0.8624634146690369, "regret": 0.001391363563016057, "entropy": 0.08999822288751602, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:19:59.549845Z", "loop": 12321, "env_steps": 7570636799, "loss": 0.017549196258187294, "avg_return": 0.8609504103660583, "regret": 0.001391363563016057, "entropy": 0.08835411816835403, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:00.403563Z", "loop": 12322, "env_steps": 7571251199, "loss": 0.01768200285732746, "avg_return": 0.8622583150863647, "regret": 0.001391363563016057, "entropy": 0.08637285977602005, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:01.258439Z", "loop": 12323, "env_steps": 7571865599, "loss": 0.01932285539805889, "avg_return": 0.8606091737747192, "regret": 0.001391363563016057, "entropy": 0.09384346753358841, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:02.112803Z", "loop": 12324, "env_steps": 7572479999, "loss": 0.018263107165694237, "avg_return": 0.8601024746894836, "regret": 0.001391363563016057, "entropy": 0.09014184772968292, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:02.968622Z", "loop": 12325, "env_steps": 7573094399, "loss": 0.01841033808887005, "avg_return": 0.8603835105895996, "regret": 0.001391363563016057, "entropy": 0.0894199013710022, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:03.822163Z", "loop": 12326, "env_steps": 7573708799, "loss": 0.018789837136864662, "avg_return": 0.8599117398262024, "regret": 0.001391363563016057, "entropy": 0.08922852575778961, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:04.676605Z", "loop": 12327, "env_steps": 7574323199, "loss": 0.01792268641293049, "avg_return": 0.8592989444732666, "regret": 0.001391363563016057, "entropy": 0.08660920709371567, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:05.529393Z", "loop": 12328, "env_steps": 7574937599, "loss": 0.01784735731780529, "avg_return": 0.8587191104888916, "regret": 0.001391363563016057, "entropy": 0.08693540096282959, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:06.383709Z", "loop": 12329, "env_steps": 7575551999, "loss": 0.018052242696285248, "avg_return": 0.8582704663276672, "regret": 0.001391363563016057, "entropy": 0.08779004961252213, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:07.276839Z", "loop": 12330, "env_steps": 7576166399, "loss": 0.016218164935708046, "avg_return": 0.8589420914649963, "regret": 0.0058929831720888615, "entropy": 0.08273950219154358, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:08.130876Z", "loop": 12331, "env_steps": 7576780799, "loss": 0.016696136444807053, "avg_return": 0.8570345044136047, "regret": 0.0058929831720888615, "entropy": 0.07992469519376755, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:08.984728Z", "loop": 12332, "env_steps": 7577395199, "loss": 0.015051277354359627, "avg_return": 0.8577657341957092, "regret": 0.0058929831720888615, "entropy": 0.07868265360593796, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:09.838005Z", "loop": 12333, "env_steps": 7578009599, "loss": 0.015332824550569057, "avg_return": 0.8561210036277771, "regret": 0.0058929831720888615, "entropy": 0.07689961045980453, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:10.691709Z", "loop": 12334, "env_steps": 7578623999, "loss": 0.015511457808315754, "avg_return": 0.8565933704376221, "regret": 0.0058929831720888615, "entropy": 0.0773056373000145, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:11.545890Z", "loop": 12335, "env_steps": 7579238399, "loss": 0.015020717866718769, "avg_return": 0.8562154173851013, "regret": 0.0058929831720888615, "entropy": 0.07601862400770187, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:12.399142Z", "loop": 12336, "env_steps": 7579852799, "loss": 0.015145194716751575, "avg_return": 0.8581929802894592, "regret": 0.0058929831720888615, "entropy": 0.08216171711683273, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:13.252790Z", "loop": 12337, "env_steps": 7580467199, "loss": 0.015940047800540924, "avg_return": 0.8587905168533325, "regret": 0.0058929831720888615, "entropy": 0.0759744867682457, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:14.105552Z", "loop": 12338, "env_steps": 7581081599, "loss": 0.01614372618496418, "avg_return": 0.8587374091148376, "regret": 0.0058929831720888615, "entropy": 0.07807694375514984, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:14.959545Z", "loop": 12339, "env_steps": 7581695999, "loss": 0.01653156243264675, "avg_return": 0.8585857152938843, "regret": 0.0058929831720888615, "entropy": 0.08056801557540894, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:15.851764Z", "loop": 12340, "env_steps": 7582310399, "loss": 0.01672784797847271, "avg_return": 0.8602423071861267, "regret": 0.00311027723364532, "entropy": 0.0870087668299675, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:16.706817Z", "loop": 12341, "env_steps": 7582924799, "loss": 0.018849974498152733, "avg_return": 0.8599898219108582, "regret": 0.00311027723364532, "entropy": 0.09436579048633575, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:17.561604Z", "loop": 12342, "env_steps": 7583539199, "loss": 0.019969332963228226, "avg_return": 0.8611159324645996, "regret": 0.00311027723364532, "entropy": 0.09558694064617157, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:18.416883Z", "loop": 12343, "env_steps": 7584153599, "loss": 0.019379833713173866, "avg_return": 0.8620575070381165, "regret": 0.00311027723364532, "entropy": 0.09631945937871933, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:19.272882Z", "loop": 12344, "env_steps": 7584767999, "loss": 0.01926272362470627, "avg_return": 0.8624471426010132, "regret": 0.00311027723364532, "entropy": 0.0934164896607399, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:20.128458Z", "loop": 12345, "env_steps": 7585382399, "loss": 0.016608893871307373, "avg_return": 0.861391007900238, "regret": 0.00311027723364532, "entropy": 0.0823066309094429, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:20.983197Z", "loop": 12346, "env_steps": 7585996799, "loss": 0.01536261010915041, "avg_return": 0.862269401550293, "regret": 0.00311027723364532, "entropy": 0.07791877537965775, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:21.838177Z", "loop": 12347, "env_steps": 7586611199, "loss": 0.01631605438888073, "avg_return": 0.8624281287193298, "regret": 0.00311027723364532, "entropy": 0.08130336552858353, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:22.691749Z", "loop": 12348, "env_steps": 7587225599, "loss": 0.016155680641531944, "avg_return": 0.8631837964057922, "regret": 0.00311027723364532, "entropy": 0.07661020010709763, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:23.546026Z", "loop": 12349, "env_steps": 7587839999, "loss": 0.016196629032492638, "avg_return": 0.8645913004875183, "regret": 0.00311027723364532, "entropy": 0.07835688441991806, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:24.439015Z", "loop": 12350, "env_steps": 7588454399, "loss": 0.01589401625096798, "avg_return": 0.8627247214317322, "regret": 0.0003006459737662226, "entropy": 0.07884922623634338, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:25.294072Z", "loop": 12351, "env_steps": 7589068799, "loss": 0.01707008294761181, "avg_return": 0.8648501038551331, "regret": 0.0003006459737662226, "entropy": 0.081485316157341, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:26.148951Z", "loop": 12352, "env_steps": 7589683199, "loss": 0.015916835516691208, "avg_return": 0.8637122511863708, "regret": 0.0003006459737662226, "entropy": 0.07861805707216263, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:27.003618Z", "loop": 12353, "env_steps": 7590297599, "loss": 0.014223071746528149, "avg_return": 0.8642897605895996, "regret": 0.0003006459737662226, "entropy": 0.07575877755880356, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:27.858830Z", "loop": 12354, "env_steps": 7590911999, "loss": 0.015259327366948128, "avg_return": 0.864385187625885, "regret": 0.0003006459737662226, "entropy": 0.07724221050739288, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:28.712686Z", "loop": 12355, "env_steps": 7591526399, "loss": 0.01420364249497652, "avg_return": 0.8628358244895935, "regret": 0.0003006459737662226, "entropy": 0.0738915354013443, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:29.566355Z", "loop": 12356, "env_steps": 7592140799, "loss": 0.014579668641090393, "avg_return": 0.8623431324958801, "regret": 0.0003006459737662226, "entropy": 0.07441655546426773, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:30.419757Z", "loop": 12357, "env_steps": 7592755199, "loss": 0.01536011416465044, "avg_return": 0.8642355799674988, "regret": 0.0003006459737662226, "entropy": 0.07926438748836517, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:31.275232Z", "loop": 12358, "env_steps": 7593369599, "loss": 0.016150696203112602, "avg_return": 0.8630655407905579, "regret": 0.0003006459737662226, "entropy": 0.07778922468423843, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:32.130139Z", "loop": 12359, "env_steps": 7593983999, "loss": 0.015482597053050995, "avg_return": 0.8640490174293518, "regret": 0.0003006459737662226, "entropy": 0.07912664860486984, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:33.025593Z", "loop": 12360, "env_steps": 7594598399, "loss": 0.016655301675200462, "avg_return": 0.8646748065948486, "regret": 0.00019964971579611301, "entropy": 0.0792243704199791, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:33.879506Z", "loop": 12361, "env_steps": 7595212799, "loss": 0.015996349975466728, "avg_return": 0.8633179664611816, "regret": 0.00019964971579611301, "entropy": 0.0819210484623909, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:34.733577Z", "loop": 12362, "env_steps": 7595827199, "loss": 0.0158490352332592, "avg_return": 0.8629758954048157, "regret": 0.00019964971579611301, "entropy": 0.0814647525548935, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:35.588654Z", "loop": 12363, "env_steps": 7596441599, "loss": 0.015432107262313366, "avg_return": 0.862362265586853, "regret": 0.00019964971579611301, "entropy": 0.08021069318056107, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:36.442597Z", "loop": 12364, "env_steps": 7597055999, "loss": 0.016523240134119987, "avg_return": 0.8624439835548401, "regret": 0.00019964971579611301, "entropy": 0.08241703361272812, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:37.296872Z", "loop": 12365, "env_steps": 7597670399, "loss": 0.01555826235562563, "avg_return": 0.8634666204452515, "regret": 0.00019964971579611301, "entropy": 0.07873889058828354, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:38.151840Z", "loop": 12366, "env_steps": 7598284799, "loss": 0.01453439425677061, "avg_return": 0.8631424903869629, "regret": 0.00019964971579611301, "entropy": 0.08007939904928207, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:39.007498Z", "loop": 12367, "env_steps": 7598899199, "loss": 0.01547704916447401, "avg_return": 0.8627653121948242, "regret": 0.00019964971579611301, "entropy": 0.07746278494596481, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:39.863139Z", "loop": 12368, "env_steps": 7599513599, "loss": 0.015098275616765022, "avg_return": 0.864179790019989, "regret": 0.00019964971579611301, "entropy": 0.07749136537313461, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:40.716767Z", "loop": 12369, "env_steps": 7600127999, "loss": 0.015933217480778694, "avg_return": 0.8640754222869873, "regret": 0.00019964971579611301, "entropy": 0.07983130216598511, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:41.610944Z", "loop": 12370, "env_steps": 7600742399, "loss": 0.015254668891429901, "avg_return": 0.8638787269592285, "regret": 0.0002153142268070951, "entropy": 0.07808831334114075, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:42.465922Z", "loop": 12371, "env_steps": 7601356799, "loss": 0.01715201325714588, "avg_return": 0.8628603219985962, "regret": 0.0002153142268070951, "entropy": 0.08178862184286118, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:43.321550Z", "loop": 12372, "env_steps": 7601971199, "loss": 0.015387386083602905, "avg_return": 0.8637168407440186, "regret": 0.0002153142268070951, "entropy": 0.07844747602939606, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:44.177138Z", "loop": 12373, "env_steps": 7602585599, "loss": 0.015831921249628067, "avg_return": 0.8643480539321899, "regret": 0.0002153142268070951, "entropy": 0.08005903661251068, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:45.031368Z", "loop": 12374, "env_steps": 7603199999, "loss": 0.0150613309815526, "avg_return": 0.8632540106773376, "regret": 0.0002153142268070951, "entropy": 0.07648811489343643, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:45.886071Z", "loop": 12375, "env_steps": 7603814399, "loss": 0.014204874634742737, "avg_return": 0.8634473085403442, "regret": 0.0002153142268070951, "entropy": 0.07216325402259827, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:46.741249Z", "loop": 12376, "env_steps": 7604428799, "loss": 0.014253896661102772, "avg_return": 0.8631774187088013, "regret": 0.0002153142268070951, "entropy": 0.0706462413072586, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:47.596292Z", "loop": 12377, "env_steps": 7605043199, "loss": 0.014671580865979195, "avg_return": 0.8637607097625732, "regret": 0.0002153142268070951, "entropy": 0.07357747107744217, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:48.451153Z", "loop": 12378, "env_steps": 7605657599, "loss": 0.01506507582962513, "avg_return": 0.8635750412940979, "regret": 0.0002153142268070951, "entropy": 0.07569629698991776, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:49.305342Z", "loop": 12379, "env_steps": 7606271999, "loss": 0.017113661393523216, "avg_return": 0.8630486130714417, "regret": 0.0002153142268070951, "entropy": 0.08464980125427246, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:50.201658Z", "loop": 12380, "env_steps": 7606886399, "loss": 0.01590932533144951, "avg_return": 0.8619637489318848, "regret": 0.0005709049291908741, "entropy": 0.08002516627311707, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:51.057174Z", "loop": 12381, "env_steps": 7607500799, "loss": 0.01833873800933361, "avg_return": 0.86347496509552, "regret": 0.0005709049291908741, "entropy": 0.0813356265425682, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:51.911882Z", "loop": 12382, "env_steps": 7608115199, "loss": 0.015680404379963875, "avg_return": 0.8623298406600952, "regret": 0.0005709049291908741, "entropy": 0.07990885525941849, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:52.766851Z", "loop": 12383, "env_steps": 7608729599, "loss": 0.01641899161040783, "avg_return": 0.8618953824043274, "regret": 0.0005709049291908741, "entropy": 0.08028125017881393, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:53.621451Z", "loop": 12384, "env_steps": 7609343999, "loss": 0.016061116009950638, "avg_return": 0.8612889051437378, "regret": 0.0005709049291908741, "entropy": 0.08057140558958054, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:54.476772Z", "loop": 12385, "env_steps": 7609958399, "loss": 0.016265500336885452, "avg_return": 0.8639959692955017, "regret": 0.0005709049291908741, "entropy": 0.0812777578830719, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:55.332545Z", "loop": 12386, "env_steps": 7610572799, "loss": 0.01714242994785309, "avg_return": 0.8624579906463623, "regret": 0.0005709049291908741, "entropy": 0.08247130364179611, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:56.187793Z", "loop": 12387, "env_steps": 7611187199, "loss": 0.015751779079437256, "avg_return": 0.8612922430038452, "regret": 0.0005709049291908741, "entropy": 0.08227147161960602, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:57.042804Z", "loop": 12388, "env_steps": 7611801599, "loss": 0.015589641407132149, "avg_return": 0.8621271848678589, "regret": 0.0005709049291908741, "entropy": 0.08298922330141068, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:57.898860Z", "loop": 12389, "env_steps": 7612415999, "loss": 0.01474756933748722, "avg_return": 0.861059308052063, "regret": 0.0005709049291908741, "entropy": 0.08054830133914948, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:58.794799Z", "loop": 12390, "env_steps": 7613030399, "loss": 0.01744558848440647, "avg_return": 0.8611158728599548, "regret": 0.002157478826120496, "entropy": 0.08564510941505432, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:20:59.648973Z", "loop": 12391, "env_steps": 7613644799, "loss": 0.016003774479031563, "avg_return": 0.8618856072425842, "regret": 0.002157478826120496, "entropy": 0.08006109297275543, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:00.503071Z", "loop": 12392, "env_steps": 7614259199, "loss": 0.015033276751637459, "avg_return": 0.86106938123703, "regret": 0.002157478826120496, "entropy": 0.07824841886758804, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:01.358106Z", "loop": 12393, "env_steps": 7614873599, "loss": 0.016971686854958534, "avg_return": 0.8610484004020691, "regret": 0.002157478826120496, "entropy": 0.0820956900715828, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:02.213054Z", "loop": 12394, "env_steps": 7615487999, "loss": 0.01632523350417614, "avg_return": 0.8627840280532837, "regret": 0.002157478826120496, "entropy": 0.0813974142074585, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:03.069221Z", "loop": 12395, "env_steps": 7616102399, "loss": 0.01673414744436741, "avg_return": 0.8611804246902466, "regret": 0.002157478826120496, "entropy": 0.08079215884208679, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:03.926397Z", "loop": 12396, "env_steps": 7616716799, "loss": 0.017632782459259033, "avg_return": 0.860317587852478, "regret": 0.002157478826120496, "entropy": 0.08427954465150833, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:04.783818Z", "loop": 12397, "env_steps": 7617331199, "loss": 0.016558177769184113, "avg_return": 0.8608994483947754, "regret": 0.002157478826120496, "entropy": 0.08635289967060089, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:05.639342Z", "loop": 12398, "env_steps": 7617945599, "loss": 0.018261294811964035, "avg_return": 0.859825849533081, "regret": 0.002157478826120496, "entropy": 0.08595985174179077, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:06.494706Z", "loop": 12399, "env_steps": 7618559999, "loss": 0.01760113053023815, "avg_return": 0.8605235815048218, "regret": 0.002157478826120496, "entropy": 0.08692494034767151, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:07.396738Z", "loop": 12400, "env_steps": 7619174399, "loss": 0.017894485965371132, "avg_return": 0.8609243035316467, "regret": 0.0018947446951642632, "entropy": 0.08738001435995102, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:08.252534Z", "loop": 12401, "env_steps": 7619788799, "loss": 0.017803391441702843, "avg_return": 0.8619252443313599, "regret": 0.0018947446951642632, "entropy": 0.08799739181995392, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:09.108316Z", "loop": 12402, "env_steps": 7620403199, "loss": 0.016647834330797195, "avg_return": 0.8614516258239746, "regret": 0.0018947446951642632, "entropy": 0.08581031858921051, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:09.963925Z", "loop": 12403, "env_steps": 7621017599, "loss": 0.017559710890054703, "avg_return": 0.8614035248756409, "regret": 0.0018947446951642632, "entropy": 0.08613459020853043, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:10.819968Z", "loop": 12404, "env_steps": 7621631999, "loss": 0.017075542360544205, "avg_return": 0.8618489503860474, "regret": 0.0018947446951642632, "entropy": 0.08307170867919922, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:11.677422Z", "loop": 12405, "env_steps": 7622246399, "loss": 0.017195437103509903, "avg_return": 0.8604337573051453, "regret": 0.0018947446951642632, "entropy": 0.0872536450624466, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:12.532173Z", "loop": 12406, "env_steps": 7622860799, "loss": 0.02003367617726326, "avg_return": 0.8613336682319641, "regret": 0.0018947446951642632, "entropy": 0.09361157566308975, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:13.386810Z", "loop": 12407, "env_steps": 7623475199, "loss": 0.0195317380130291, "avg_return": 0.8625317811965942, "regret": 0.0018947446951642632, "entropy": 0.09365794062614441, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:14.241279Z", "loop": 12408, "env_steps": 7624089599, "loss": 0.019541097804903984, "avg_return": 0.8619836568832397, "regret": 0.0018947446951642632, "entropy": 0.08895300328731537, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:15.096795Z", "loop": 12409, "env_steps": 7624703999, "loss": 0.01766144670546055, "avg_return": 0.8617033958435059, "regret": 0.0018947446951642632, "entropy": 0.09390928596258163, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:15.993064Z", "loop": 12410, "env_steps": 7625318399, "loss": 0.01908390410244465, "avg_return": 0.8627977967262268, "regret": 0.0013491910649463534, "entropy": 0.09301265329122543, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:16.847764Z", "loop": 12411, "env_steps": 7625932799, "loss": 0.018321966752409935, "avg_return": 0.8614068627357483, "regret": 0.0013491910649463534, "entropy": 0.09262819588184357, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:17.702011Z", "loop": 12412, "env_steps": 7626547199, "loss": 0.017912160605192184, "avg_return": 0.8622260689735413, "regret": 0.0013491910649463534, "entropy": 0.09033767879009247, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:18.558315Z", "loop": 12413, "env_steps": 7627161599, "loss": 0.018654707819223404, "avg_return": 0.8623171448707581, "regret": 0.0013491910649463534, "entropy": 0.08991167694330215, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:19.414370Z", "loop": 12414, "env_steps": 7627775999, "loss": 0.0185729768127203, "avg_return": 0.8615352511405945, "regret": 0.0013491910649463534, "entropy": 0.0948537215590477, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:20.274581Z", "loop": 12415, "env_steps": 7628390399, "loss": 0.01792243681848049, "avg_return": 0.8627432584762573, "regret": 0.0013491910649463534, "entropy": 0.09381894022226334, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:21.133598Z", "loop": 12416, "env_steps": 7629004799, "loss": 0.01922190934419632, "avg_return": 0.8626649975776672, "regret": 0.0013491910649463534, "entropy": 0.09715116769075394, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:21.988717Z", "loop": 12417, "env_steps": 7629619199, "loss": 0.021107329055666924, "avg_return": 0.8614449501037598, "regret": 0.0013491910649463534, "entropy": 0.10461026430130005, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:22.844076Z", "loop": 12418, "env_steps": 7630233599, "loss": 0.02298240177333355, "avg_return": 0.8611938953399658, "regret": 0.0013491910649463534, "entropy": 0.11053669452667236, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:23.698739Z", "loop": 12419, "env_steps": 7630847999, "loss": 0.0245243851095438, "avg_return": 0.8628743886947632, "regret": 0.0013491910649463534, "entropy": 0.11380590498447418, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:24.591936Z", "loop": 12420, "env_steps": 7631462399, "loss": 0.023288216441869736, "avg_return": 0.8627707958221436, "regret": 0.0009802350541576743, "entropy": 0.11661507189273834, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:25.446230Z", "loop": 12421, "env_steps": 7632076799, "loss": 0.02421940118074417, "avg_return": 0.862342119216919, "regret": 0.0009802350541576743, "entropy": 0.11715269833803177, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:26.300414Z", "loop": 12422, "env_steps": 7632691199, "loss": 0.024374231696128845, "avg_return": 0.8642112612724304, "regret": 0.0009802350541576743, "entropy": 0.11829300224781036, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:27.155131Z", "loop": 12423, "env_steps": 7633305599, "loss": 0.02446666732430458, "avg_return": 0.8632792234420776, "regret": 0.0009802350541576743, "entropy": 0.11978624016046524, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:28.008422Z", "loop": 12424, "env_steps": 7633919999, "loss": 0.02460707537829876, "avg_return": 0.862391471862793, "regret": 0.0009802350541576743, "entropy": 0.11816287785768509, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:28.863189Z", "loop": 12425, "env_steps": 7634534399, "loss": 0.025659918785095215, "avg_return": 0.8621414303779602, "regret": 0.0009802350541576743, "entropy": 0.12168657779693604, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:29.716592Z", "loop": 12426, "env_steps": 7635148799, "loss": 0.025027034804224968, "avg_return": 0.863137423992157, "regret": 0.0009802350541576743, "entropy": 0.12440209835767746, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:30.570486Z", "loop": 12427, "env_steps": 7635763199, "loss": 0.024850979447364807, "avg_return": 0.8629494309425354, "regret": 0.0009802350541576743, "entropy": 0.12160666286945343, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:31.425602Z", "loop": 12428, "env_steps": 7636377599, "loss": 0.02625107578933239, "avg_return": 0.8628817200660706, "regret": 0.0009802350541576743, "entropy": 0.12367414683103561, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:32.280308Z", "loop": 12429, "env_steps": 7636991999, "loss": 0.024600336328148842, "avg_return": 0.8647124171257019, "regret": 0.0009802350541576743, "entropy": 0.12248506397008896, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:33.174507Z", "loop": 12430, "env_steps": 7637606399, "loss": 0.02429584227502346, "avg_return": 0.8633570671081543, "regret": 0.0007016987074166536, "entropy": 0.12120825052261353, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:34.029008Z", "loop": 12431, "env_steps": 7638220799, "loss": 0.02523944340646267, "avg_return": 0.8629273772239685, "regret": 0.0007016987074166536, "entropy": 0.12422405928373337, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:34.884181Z", "loop": 12432, "env_steps": 7638835199, "loss": 0.024912675842642784, "avg_return": 0.8620843887329102, "regret": 0.0007016987074166536, "entropy": 0.12262210994958878, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:35.738842Z", "loop": 12433, "env_steps": 7639449599, "loss": 0.025560785084962845, "avg_return": 0.8613499402999878, "regret": 0.0007016987074166536, "entropy": 0.12569330632686615, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:36.592886Z", "loop": 12434, "env_steps": 7640063999, "loss": 0.02738124690949917, "avg_return": 0.8631716370582581, "regret": 0.0007016987074166536, "entropy": 0.12940238416194916, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:37.446633Z", "loop": 12435, "env_steps": 7640678399, "loss": 0.025454236194491386, "avg_return": 0.8632753491401672, "regret": 0.0007016987074166536, "entropy": 0.12271228432655334, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:38.301237Z", "loop": 12436, "env_steps": 7641292799, "loss": 0.02536914125084877, "avg_return": 0.8636678457260132, "regret": 0.0007016987074166536, "entropy": 0.12562838196754456, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:39.155842Z", "loop": 12437, "env_steps": 7641907199, "loss": 0.024998856708407402, "avg_return": 0.8628397583961487, "regret": 0.0007016987074166536, "entropy": 0.12253094464540482, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:40.009186Z", "loop": 12438, "env_steps": 7642521599, "loss": 0.02428092621266842, "avg_return": 0.8637719750404358, "regret": 0.0007016987074166536, "entropy": 0.12055552750825882, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:40.862629Z", "loop": 12439, "env_steps": 7643135999, "loss": 0.02438455820083618, "avg_return": 0.8628369569778442, "regret": 0.0007016987074166536, "entropy": 0.11754239350557327, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:41.756586Z", "loop": 12440, "env_steps": 7643750399, "loss": 0.02406848594546318, "avg_return": 0.8627927899360657, "regret": 0.0005418192013166845, "entropy": 0.11909698694944382, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:42.611475Z", "loop": 12441, "env_steps": 7644364799, "loss": 0.02453490160405636, "avg_return": 0.8626440763473511, "regret": 0.0005418192013166845, "entropy": 0.11915029585361481, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:43.465768Z", "loop": 12442, "env_steps": 7644979199, "loss": 0.02484316937625408, "avg_return": 0.8627651929855347, "regret": 0.0005418192013166845, "entropy": 0.12211362272500992, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:44.320333Z", "loop": 12443, "env_steps": 7645593599, "loss": 0.025770246982574463, "avg_return": 0.8631232976913452, "regret": 0.0005418192013166845, "entropy": 0.11898190528154373, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:45.173500Z", "loop": 12444, "env_steps": 7646207999, "loss": 0.025598345324397087, "avg_return": 0.8621023893356323, "regret": 0.0005418192013166845, "entropy": 0.12473724037408829, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:46.027049Z", "loop": 12445, "env_steps": 7646822399, "loss": 0.02583024837076664, "avg_return": 0.8637806177139282, "regret": 0.0005418192013166845, "entropy": 0.12235096842050552, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:46.882006Z", "loop": 12446, "env_steps": 7647436799, "loss": 0.02595599554479122, "avg_return": 0.8633168935775757, "regret": 0.0005418192013166845, "entropy": 0.12142311036586761, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:47.736408Z", "loop": 12447, "env_steps": 7648051199, "loss": 0.02603890933096409, "avg_return": 0.8627744913101196, "regret": 0.0005418192013166845, "entropy": 0.1257132887840271, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:48.589931Z", "loop": 12448, "env_steps": 7648665599, "loss": 0.02441667579114437, "avg_return": 0.8632492423057556, "regret": 0.0005418192013166845, "entropy": 0.11994149535894394, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:49.443553Z", "loop": 12449, "env_steps": 7649279999, "loss": 0.023413602262735367, "avg_return": 0.8624168038368225, "regret": 0.0005418192013166845, "entropy": 0.11319415271282196, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:50.338119Z", "loop": 12450, "env_steps": 7649894399, "loss": 0.021772651001811028, "avg_return": 0.8625596165657043, "regret": 0.0009437153930775821, "entropy": 0.10804453492164612, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:51.192065Z", "loop": 12451, "env_steps": 7650508799, "loss": 0.02040230482816696, "avg_return": 0.8622706532478333, "regret": 0.0009437153930775821, "entropy": 0.10769124329090118, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:52.047948Z", "loop": 12452, "env_steps": 7651123199, "loss": 0.02129797451198101, "avg_return": 0.8625057935714722, "regret": 0.0009437153930775821, "entropy": 0.10860058665275574, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:52.901620Z", "loop": 12453, "env_steps": 7651737599, "loss": 0.021727172657847404, "avg_return": 0.8623349070549011, "regret": 0.0009437153930775821, "entropy": 0.11174630373716354, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:53.754782Z", "loop": 12454, "env_steps": 7652351999, "loss": 0.023754043504595757, "avg_return": 0.8602648377418518, "regret": 0.0009437153930775821, "entropy": 0.12076728790998459, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:54.608411Z", "loop": 12455, "env_steps": 7652966399, "loss": 0.024790439754724503, "avg_return": 0.8599159717559814, "regret": 0.0009437153930775821, "entropy": 0.11972931027412415, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:55.462861Z", "loop": 12456, "env_steps": 7653580799, "loss": 0.025431150570511818, "avg_return": 0.8614884614944458, "regret": 0.0009437153930775821, "entropy": 0.12314264476299286, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:56.317775Z", "loop": 12457, "env_steps": 7654195199, "loss": 0.025724157691001892, "avg_return": 0.8607403635978699, "regret": 0.0009437153930775821, "entropy": 0.12768632173538208, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:57.172002Z", "loop": 12458, "env_steps": 7654809599, "loss": 0.026800865307450294, "avg_return": 0.8617600798606873, "regret": 0.0009437153930775821, "entropy": 0.12942522764205933, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:58.025714Z", "loop": 12459, "env_steps": 7655423999, "loss": 0.026932556182146072, "avg_return": 0.8621222376823425, "regret": 0.0009437153930775821, "entropy": 0.13216863572597504, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:58.920445Z", "loop": 12460, "env_steps": 7656038399, "loss": 0.02742409147322178, "avg_return": 0.8609076142311096, "regret": 0.0021978244185447693, "entropy": 0.13446566462516785, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:21:59.775195Z", "loop": 12461, "env_steps": 7656652799, "loss": 0.026608040556311607, "avg_return": 0.8618900775909424, "regret": 0.0021978244185447693, "entropy": 0.1328357309103012, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:00.627947Z", "loop": 12462, "env_steps": 7657267199, "loss": 0.02730013243854046, "avg_return": 0.8605349063873291, "regret": 0.0021978244185447693, "entropy": 0.13506974279880524, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:01.480825Z", "loop": 12463, "env_steps": 7657881599, "loss": 0.027751613408327103, "avg_return": 0.8618257641792297, "regret": 0.0021978244185447693, "entropy": 0.13385766744613647, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:02.334782Z", "loop": 12464, "env_steps": 7658495999, "loss": 0.027979660779237747, "avg_return": 0.860757052898407, "regret": 0.0021978244185447693, "entropy": 0.14093464612960815, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:03.189176Z", "loop": 12465, "env_steps": 7659110399, "loss": 0.025994285941123962, "avg_return": 0.8617047071456909, "regret": 0.0021978244185447693, "entropy": 0.132524311542511, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:04.042497Z", "loop": 12466, "env_steps": 7659724799, "loss": 0.026572907343506813, "avg_return": 0.8626111149787903, "regret": 0.0021978244185447693, "entropy": 0.1289723962545395, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:04.895443Z", "loop": 12467, "env_steps": 7660339199, "loss": 0.025715071707963943, "avg_return": 0.8628015518188477, "regret": 0.0021978244185447693, "entropy": 0.12707073986530304, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:05.748820Z", "loop": 12468, "env_steps": 7660953599, "loss": 0.024038543924689293, "avg_return": 0.8626214861869812, "regret": 0.0021978244185447693, "entropy": 0.11835067719221115, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:06.602480Z", "loop": 12469, "env_steps": 7661567999, "loss": 0.022130899131298065, "avg_return": 0.8629549145698547, "regret": 0.0021978244185447693, "entropy": 0.11019553989171982, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:07.495289Z", "loop": 12470, "env_steps": 7662182399, "loss": 0.021380655467510223, "avg_return": 0.8652437329292297, "regret": 0.00108470325358212, "entropy": 0.10723511874675751, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:08.348478Z", "loop": 12471, "env_steps": 7662796799, "loss": 0.02019333653151989, "avg_return": 0.8625345230102539, "regret": 0.00108470325358212, "entropy": 0.1003158912062645, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:09.201624Z", "loop": 12472, "env_steps": 7663411199, "loss": 0.020086435601115227, "avg_return": 0.8608386516571045, "regret": 0.00108470325358212, "entropy": 0.10435653477907181, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:10.055948Z", "loop": 12473, "env_steps": 7664025599, "loss": 0.020535293966531754, "avg_return": 0.8633021116256714, "regret": 0.00108470325358212, "entropy": 0.1028032973408699, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:10.910242Z", "loop": 12474, "env_steps": 7664639999, "loss": 0.021978802978992462, "avg_return": 0.8622898459434509, "regret": 0.00108470325358212, "entropy": 0.10789433121681213, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:11.763300Z", "loop": 12475, "env_steps": 7665254399, "loss": 0.022956890985369682, "avg_return": 0.8623790740966797, "regret": 0.00108470325358212, "entropy": 0.11440254002809525, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:12.616157Z", "loop": 12476, "env_steps": 7665868799, "loss": 0.02397632971405983, "avg_return": 0.8608425855636597, "regret": 0.00108470325358212, "entropy": 0.11228957027196884, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:13.469505Z", "loop": 12477, "env_steps": 7666483199, "loss": 0.023734798654913902, "avg_return": 0.8592374920845032, "regret": 0.00108470325358212, "entropy": 0.1171259954571724, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:14.323454Z", "loop": 12478, "env_steps": 7667097599, "loss": 0.02402333728969097, "avg_return": 0.8596777319908142, "regret": 0.00108470325358212, "entropy": 0.11873600631952286, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:15.176734Z", "loop": 12479, "env_steps": 7667711999, "loss": 0.023249085992574692, "avg_return": 0.8610613942146301, "regret": 0.00108470325358212, "entropy": 0.1137779951095581, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:16.068966Z", "loop": 12480, "env_steps": 7668326399, "loss": 0.02342286705970764, "avg_return": 0.8622792959213257, "regret": 0.0013400078751146793, "entropy": 0.11804374307394028, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:16.924213Z", "loop": 12481, "env_steps": 7668940799, "loss": 0.023590480908751488, "avg_return": 0.862484335899353, "regret": 0.0013400078751146793, "entropy": 0.11344260722398758, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:17.777715Z", "loop": 12482, "env_steps": 7669555199, "loss": 0.0227819737046957, "avg_return": 0.8634565472602844, "regret": 0.0013400078751146793, "entropy": 0.1144997850060463, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:18.631786Z", "loop": 12483, "env_steps": 7670169599, "loss": 0.022485310211777687, "avg_return": 0.8623061180114746, "regret": 0.0013400078751146793, "entropy": 0.11004336923360825, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:19.485342Z", "loop": 12484, "env_steps": 7670783999, "loss": 0.022225575521588326, "avg_return": 0.8634366989135742, "regret": 0.0013400078751146793, "entropy": 0.10908763110637665, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:20.339456Z", "loop": 12485, "env_steps": 7671398399, "loss": 0.020924055948853493, "avg_return": 0.8631437420845032, "regret": 0.0013400078751146793, "entropy": 0.10155816376209259, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:21.193455Z", "loop": 12486, "env_steps": 7672012799, "loss": 0.018422776833176613, "avg_return": 0.8625842332839966, "regret": 0.0013400078751146793, "entropy": 0.08966134488582611, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:22.048465Z", "loop": 12487, "env_steps": 7672627199, "loss": 0.016695091500878334, "avg_return": 0.8635619282722473, "regret": 0.0013400078751146793, "entropy": 0.08427620679140091, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:22.902728Z", "loop": 12488, "env_steps": 7673241599, "loss": 0.016286471858620644, "avg_return": 0.8629580736160278, "regret": 0.0013400078751146793, "entropy": 0.07873483002185822, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:23.756025Z", "loop": 12489, "env_steps": 7673855999, "loss": 0.015390305779874325, "avg_return": 0.8644335865974426, "regret": 0.0013400078751146793, "entropy": 0.07781487703323364, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:24.647621Z", "loop": 12490, "env_steps": 7674470399, "loss": 0.015499149449169636, "avg_return": 0.8634355664253235, "regret": 0.0005155755206942558, "entropy": 0.0782482922077179, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:25.501904Z", "loop": 12491, "env_steps": 7675084799, "loss": 0.015845773741602898, "avg_return": 0.8607965111732483, "regret": 0.0005155755206942558, "entropy": 0.07807546854019165, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:26.357408Z", "loop": 12492, "env_steps": 7675699199, "loss": 0.016662614420056343, "avg_return": 0.862946093082428, "regret": 0.0005155755206942558, "entropy": 0.07788752019405365, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:27.211218Z", "loop": 12493, "env_steps": 7676313599, "loss": 0.016553141176700592, "avg_return": 0.8628361225128174, "regret": 0.0005155755206942558, "entropy": 0.08296752721071243, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:28.064785Z", "loop": 12494, "env_steps": 7676927999, "loss": 0.017139200121164322, "avg_return": 0.8638455271720886, "regret": 0.0005155755206942558, "entropy": 0.08144965767860413, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:28.918780Z", "loop": 12495, "env_steps": 7677542399, "loss": 0.016575336456298828, "avg_return": 0.8636006712913513, "regret": 0.0005155755206942558, "entropy": 0.07883428037166595, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:29.774758Z", "loop": 12496, "env_steps": 7678156799, "loss": 0.01473432220518589, "avg_return": 0.8634703755378723, "regret": 0.0005155755206942558, "entropy": 0.07597673684358597, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:30.629150Z", "loop": 12497, "env_steps": 7678771199, "loss": 0.0141484085470438, "avg_return": 0.8617340326309204, "regret": 0.0005155755206942558, "entropy": 0.07266511768102646, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:31.482455Z", "loop": 12498, "env_steps": 7679385599, "loss": 0.015429121442139149, "avg_return": 0.8629677295684814, "regret": 0.0005155755206942558, "entropy": 0.07453504204750061, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:32.335823Z", "loop": 12499, "env_steps": 7679999999, "loss": 0.016029102727770805, "avg_return": 0.8624871969223022, "regret": 0.0005155755206942558, "entropy": 0.07824759930372238, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:33.228661Z", "loop": 12500, "env_steps": 7680614399, "loss": 0.017117587849497795, "avg_return": 0.8620641231536865, "regret": 0.001193147269077599, "entropy": 0.08116326481103897, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:34.082456Z", "loop": 12501, "env_steps": 7681228799, "loss": 0.015968142077326775, "avg_return": 0.8621171116828918, "regret": 0.001193147269077599, "entropy": 0.08034730702638626, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:34.936190Z", "loop": 12502, "env_steps": 7681843199, "loss": 0.015064281411468983, "avg_return": 0.8635954260826111, "regret": 0.001193147269077599, "entropy": 0.07459136843681335, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:35.790291Z", "loop": 12503, "env_steps": 7682457599, "loss": 0.01551024615764618, "avg_return": 0.8617329001426697, "regret": 0.001193147269077599, "entropy": 0.07229163497686386, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:36.645676Z", "loop": 12504, "env_steps": 7683071999, "loss": 0.015268797986209393, "avg_return": 0.861717164516449, "regret": 0.001193147269077599, "entropy": 0.07618177682161331, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:37.501179Z", "loop": 12505, "env_steps": 7683686399, "loss": 0.014627638272941113, "avg_return": 0.8615837693214417, "regret": 0.001193147269077599, "entropy": 0.07282097637653351, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:38.356323Z", "loop": 12506, "env_steps": 7684300799, "loss": 0.014395839534699917, "avg_return": 0.8614916205406189, "regret": 0.001193147269077599, "entropy": 0.07226027548313141, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:39.211471Z", "loop": 12507, "env_steps": 7684915199, "loss": 0.014779219403862953, "avg_return": 0.8625172972679138, "regret": 0.001193147269077599, "entropy": 0.07602064311504364, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:40.067440Z", "loop": 12508, "env_steps": 7685529599, "loss": 0.016162153333425522, "avg_return": 0.8624476194381714, "regret": 0.001193147269077599, "entropy": 0.07868171483278275, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:40.921831Z", "loop": 12509, "env_steps": 7686143999, "loss": 0.017292825505137444, "avg_return": 0.8605572581291199, "regret": 0.001193147269077599, "entropy": 0.08294255286455154, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:41.814647Z", "loop": 12510, "env_steps": 7686758399, "loss": 0.018749341368675232, "avg_return": 0.8607742786407471, "regret": 0.0023209606297314167, "entropy": 0.08969885855913162, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:42.670495Z", "loop": 12511, "env_steps": 7687372799, "loss": 0.018239082768559456, "avg_return": 0.8614360690116882, "regret": 0.0023209606297314167, "entropy": 0.08935868740081787, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:43.523870Z", "loop": 12512, "env_steps": 7687987199, "loss": 0.018474595621228218, "avg_return": 0.8603631854057312, "regret": 0.0023209606297314167, "entropy": 0.09364921599626541, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:44.377115Z", "loop": 12513, "env_steps": 7688601599, "loss": 0.020219245925545692, "avg_return": 0.8625380396842957, "regret": 0.0023209606297314167, "entropy": 0.0946052297949791, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:45.232116Z", "loop": 12514, "env_steps": 7689215999, "loss": 0.019137343391776085, "avg_return": 0.8608335852622986, "regret": 0.0023209606297314167, "entropy": 0.09319310635328293, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:46.086061Z", "loop": 12515, "env_steps": 7689830399, "loss": 0.01695767045021057, "avg_return": 0.860584557056427, "regret": 0.0023209606297314167, "entropy": 0.08815053105354309, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:46.942105Z", "loop": 12516, "env_steps": 7690444799, "loss": 0.015559650026261806, "avg_return": 0.8599607348442078, "regret": 0.0023209606297314167, "entropy": 0.08139992505311966, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:47.795182Z", "loop": 12517, "env_steps": 7691059199, "loss": 0.015731198713183403, "avg_return": 0.8573147058486938, "regret": 0.0023209606297314167, "entropy": 0.07741130143404007, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:48.649713Z", "loop": 12518, "env_steps": 7691673599, "loss": 0.01616845093667507, "avg_return": 0.8561924695968628, "regret": 0.0023209606297314167, "entropy": 0.07879266887903214, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:49.503943Z", "loop": 12519, "env_steps": 7692287999, "loss": 0.01423213817179203, "avg_return": 0.855767548084259, "regret": 0.0023209606297314167, "entropy": 0.07669733464717865, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:50.398033Z", "loop": 12520, "env_steps": 7692902399, "loss": 0.015206773765385151, "avg_return": 0.8560517430305481, "regret": 0.00795035995543003, "entropy": 0.0757911428809166, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:51.251924Z", "loop": 12521, "env_steps": 7693516799, "loss": 0.015763742849230766, "avg_return": 0.8575246334075928, "regret": 0.00795035995543003, "entropy": 0.07850154489278793, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:52.105976Z", "loop": 12522, "env_steps": 7694131199, "loss": 0.01548798382282257, "avg_return": 0.8572207689285278, "regret": 0.00795035995543003, "entropy": 0.07889807969331741, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:52.960434Z", "loop": 12523, "env_steps": 7694745599, "loss": 0.014646862633526325, "avg_return": 0.8585989475250244, "regret": 0.00795035995543003, "entropy": 0.07550915330648422, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:53.815396Z", "loop": 12524, "env_steps": 7695359999, "loss": 0.01379656232893467, "avg_return": 0.85794597864151, "regret": 0.00795035995543003, "entropy": 0.07290958613157272, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:54.669472Z", "loop": 12525, "env_steps": 7695974399, "loss": 0.014539062976837158, "avg_return": 0.8590570092201233, "regret": 0.00795035995543003, "entropy": 0.07709477841854095, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:55.523209Z", "loop": 12526, "env_steps": 7696588799, "loss": 0.014320097863674164, "avg_return": 0.8596677780151367, "regret": 0.00795035995543003, "entropy": 0.0768834725022316, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:56.377561Z", "loop": 12527, "env_steps": 7697203199, "loss": 0.01448178943246603, "avg_return": 0.8598158955574036, "regret": 0.00795035995543003, "entropy": 0.07433276623487473, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:57.232765Z", "loop": 12528, "env_steps": 7697817599, "loss": 0.014124149456620216, "avg_return": 0.8603092432022095, "regret": 0.00795035995543003, "entropy": 0.0724119246006012, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:58.087764Z", "loop": 12529, "env_steps": 7698431999, "loss": 0.014783513732254505, "avg_return": 0.8597362637519836, "regret": 0.00795035995543003, "entropy": 0.0779179111123085, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:58.979527Z", "loop": 12530, "env_steps": 7699046399, "loss": 0.015514505095779896, "avg_return": 0.8597276210784912, "regret": 0.0035448623821139336, "entropy": 0.08124105632305145, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:22:59.834049Z", "loop": 12531, "env_steps": 7699660799, "loss": 0.015788912773132324, "avg_return": 0.8611564040184021, "regret": 0.0035448623821139336, "entropy": 0.08064760267734528, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:00.687894Z", "loop": 12532, "env_steps": 7700275199, "loss": 0.015735836699604988, "avg_return": 0.8607691526412964, "regret": 0.0035448623821139336, "entropy": 0.08247192203998566, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:01.541310Z", "loop": 12533, "env_steps": 7700889599, "loss": 0.01712328940629959, "avg_return": 0.8605166673660278, "regret": 0.0035448623821139336, "entropy": 0.08542349189519882, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:02.394603Z", "loop": 12534, "env_steps": 7701503999, "loss": 0.01606808789074421, "avg_return": 0.8604181408882141, "regret": 0.0035448623821139336, "entropy": 0.08353730291128159, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:03.247658Z", "loop": 12535, "env_steps": 7702118399, "loss": 0.01694188266992569, "avg_return": 0.8634417653083801, "regret": 0.0035448623821139336, "entropy": 0.08566875755786896, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:04.100867Z", "loop": 12536, "env_steps": 7702732799, "loss": 0.01751059480011463, "avg_return": 0.8613497018814087, "regret": 0.0035448623821139336, "entropy": 0.08943276852369308, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:04.954437Z", "loop": 12537, "env_steps": 7703347199, "loss": 0.01676362380385399, "avg_return": 0.860348105430603, "regret": 0.0035448623821139336, "entropy": 0.08545619249343872, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:05.808645Z", "loop": 12538, "env_steps": 7703961599, "loss": 0.017739884555339813, "avg_return": 0.8611745238304138, "regret": 0.0035448623821139336, "entropy": 0.09153348952531815, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:06.661710Z", "loop": 12539, "env_steps": 7704575999, "loss": 0.0176315326243639, "avg_return": 0.8633233904838562, "regret": 0.0035448623821139336, "entropy": 0.08546259999275208, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:07.553212Z", "loop": 12540, "env_steps": 7705190399, "loss": 0.018624713644385338, "avg_return": 0.8604278564453125, "regret": 0.0014872790779918432, "entropy": 0.09311407059431076, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:08.406333Z", "loop": 12541, "env_steps": 7705804799, "loss": 0.01794360764324665, "avg_return": 0.8630637526512146, "regret": 0.0014872790779918432, "entropy": 0.08902865648269653, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:09.259991Z", "loop": 12542, "env_steps": 7706419199, "loss": 0.01799643598496914, "avg_return": 0.8628332614898682, "regret": 0.0014872790779918432, "entropy": 0.09046297520399094, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:10.114619Z", "loop": 12543, "env_steps": 7707033599, "loss": 0.018919607624411583, "avg_return": 0.8628355860710144, "regret": 0.0014872790779918432, "entropy": 0.09467484802007675, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:10.968226Z", "loop": 12544, "env_steps": 7707647999, "loss": 0.01747886836528778, "avg_return": 0.862551212310791, "regret": 0.0014872790779918432, "entropy": 0.08804348856210709, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:11.822272Z", "loop": 12545, "env_steps": 7708262399, "loss": 0.016336774453520775, "avg_return": 0.8647069334983826, "regret": 0.0014872790779918432, "entropy": 0.08440947532653809, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:12.676344Z", "loop": 12546, "env_steps": 7708876799, "loss": 0.0180988609790802, "avg_return": 0.8621009588241577, "regret": 0.0014872790779918432, "entropy": 0.09060642123222351, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:13.531248Z", "loop": 12547, "env_steps": 7709491199, "loss": 0.0162121020257473, "avg_return": 0.8631195425987244, "regret": 0.0014872790779918432, "entropy": 0.08029553294181824, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:14.384280Z", "loop": 12548, "env_steps": 7710105599, "loss": 0.01633918099105358, "avg_return": 0.8632020354270935, "regret": 0.0014872790779918432, "entropy": 0.08381573855876923, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:15.237346Z", "loop": 12549, "env_steps": 7710719999, "loss": 0.01632755808532238, "avg_return": 0.862694501876831, "regret": 0.0014872790779918432, "entropy": 0.07975750416517258, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:16.131221Z", "loop": 12550, "env_steps": 7711334399, "loss": 0.014252334833145142, "avg_return": 0.8636861443519592, "regret": 0.0006104212370701134, "entropy": 0.07552860677242279, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:16.985536Z", "loop": 12551, "env_steps": 7711948799, "loss": 0.014643055386841297, "avg_return": 0.8629974722862244, "regret": 0.0006104212370701134, "entropy": 0.07791396975517273, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:17.839446Z", "loop": 12552, "env_steps": 7712563199, "loss": 0.014952498488128185, "avg_return": 0.8629456758499146, "regret": 0.0006104212370701134, "entropy": 0.07774582505226135, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:18.692723Z", "loop": 12553, "env_steps": 7713177599, "loss": 0.014349873177707195, "avg_return": 0.8639914989471436, "regret": 0.0006104212370701134, "entropy": 0.0725138932466507, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:19.546928Z", "loop": 12554, "env_steps": 7713791999, "loss": 0.015102731995284557, "avg_return": 0.8621000647544861, "regret": 0.0006104212370701134, "entropy": 0.07609932124614716, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:20.402402Z", "loop": 12555, "env_steps": 7714406399, "loss": 0.013987870886921883, "avg_return": 0.8638678193092346, "regret": 0.0006104212370701134, "entropy": 0.07486926764249802, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:21.256127Z", "loop": 12556, "env_steps": 7715020799, "loss": 0.014111791737377644, "avg_return": 0.8630177974700928, "regret": 0.0006104212370701134, "entropy": 0.07437034696340561, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:22.110263Z", "loop": 12557, "env_steps": 7715635199, "loss": 0.014371799305081367, "avg_return": 0.8620700240135193, "regret": 0.0006104212370701134, "entropy": 0.07296062260866165, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:22.964606Z", "loop": 12558, "env_steps": 7716249599, "loss": 0.01308106817305088, "avg_return": 0.8608928918838501, "regret": 0.0006104212370701134, "entropy": 0.06918129324913025, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:23.818368Z", "loop": 12559, "env_steps": 7716863999, "loss": 0.012408695183694363, "avg_return": 0.8619158864021301, "regret": 0.0006104212370701134, "entropy": 0.06923627853393555, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:24.711244Z", "loop": 12560, "env_steps": 7717478399, "loss": 0.012840998359024525, "avg_return": 0.8617295622825623, "regret": 0.0017256836872547865, "entropy": 0.06377152353525162, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:25.565007Z", "loop": 12561, "env_steps": 7718092799, "loss": 0.013381599448621273, "avg_return": 0.8608373999595642, "regret": 0.0017256836872547865, "entropy": 0.06865565478801727, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:26.418158Z", "loop": 12562, "env_steps": 7718707199, "loss": 0.013238086365163326, "avg_return": 0.8614931702613831, "regret": 0.0017256836872547865, "entropy": 0.06924138218164444, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:27.271995Z", "loop": 12563, "env_steps": 7719321599, "loss": 0.012267171405255795, "avg_return": 0.8608464598655701, "regret": 0.0017256836872547865, "entropy": 0.06599657982587814, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:28.126728Z", "loop": 12564, "env_steps": 7719935999, "loss": 0.013019949197769165, "avg_return": 0.8620564937591553, "regret": 0.0017256836872547865, "entropy": 0.06424722820520401, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:28.981618Z", "loop": 12565, "env_steps": 7720550399, "loss": 0.013556817546486855, "avg_return": 0.8623250722885132, "regret": 0.0017256836872547865, "entropy": 0.07172627747058868, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:29.835488Z", "loop": 12566, "env_steps": 7721164799, "loss": 0.013567580841481686, "avg_return": 0.8618376851081848, "regret": 0.0017256836872547865, "entropy": 0.06958787888288498, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:30.690028Z", "loop": 12567, "env_steps": 7721779199, "loss": 0.013545552268624306, "avg_return": 0.8613110780715942, "regret": 0.0017256836872547865, "entropy": 0.06665922701358795, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:31.544329Z", "loop": 12568, "env_steps": 7722393599, "loss": 0.013105419464409351, "avg_return": 0.8618723750114441, "regret": 0.0017256836872547865, "entropy": 0.0696689561009407, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:32.399173Z", "loop": 12569, "env_steps": 7723007999, "loss": 0.013297691009938717, "avg_return": 0.861344039440155, "regret": 0.0017256836872547865, "entropy": 0.07293342798948288, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:33.293499Z", "loop": 12570, "env_steps": 7723622399, "loss": 0.013316869735717773, "avg_return": 0.8634633421897888, "regret": 0.001181058119982481, "entropy": 0.07147934287786484, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:34.146634Z", "loop": 12571, "env_steps": 7724236799, "loss": 0.012748554348945618, "avg_return": 0.8630282878875732, "regret": 0.001181058119982481, "entropy": 0.06978169083595276, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:35.000783Z", "loop": 12572, "env_steps": 7724851199, "loss": 0.01301463134586811, "avg_return": 0.8611432313919067, "regret": 0.001181058119982481, "entropy": 0.06914655864238739, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:35.856133Z", "loop": 12573, "env_steps": 7725465599, "loss": 0.01319228857755661, "avg_return": 0.8634470105171204, "regret": 0.001181058119982481, "entropy": 0.06811664253473282, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:36.710883Z", "loop": 12574, "env_steps": 7726079999, "loss": 0.013119458220899105, "avg_return": 0.86175537109375, "regret": 0.001181058119982481, "entropy": 0.06894184648990631, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:37.565551Z", "loop": 12575, "env_steps": 7726694399, "loss": 0.011989865452051163, "avg_return": 0.8621245622634888, "regret": 0.001181058119982481, "entropy": 0.0659741759300232, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:38.420053Z", "loop": 12576, "env_steps": 7727308799, "loss": 0.014284349046647549, "avg_return": 0.8620599508285522, "regret": 0.001181058119982481, "entropy": 0.07343415170907974, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:39.274516Z", "loop": 12577, "env_steps": 7727923199, "loss": 0.013100624084472656, "avg_return": 0.8633009791374207, "regret": 0.001181058119982481, "entropy": 0.07058027386665344, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:40.129597Z", "loop": 12578, "env_steps": 7728537599, "loss": 0.01364120002835989, "avg_return": 0.8627603650093079, "regret": 0.001181058119982481, "entropy": 0.0728575736284256, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:40.984466Z", "loop": 12579, "env_steps": 7729151999, "loss": 0.013910180889070034, "avg_return": 0.8628449440002441, "regret": 0.001181058119982481, "entropy": 0.07253855466842651, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:41.876083Z", "loop": 12580, "env_steps": 7729766399, "loss": 0.01388608105480671, "avg_return": 0.8613947033882141, "regret": 0.0011262726038694382, "entropy": 0.07129372656345367, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:42.729137Z", "loop": 12581, "env_steps": 7730380799, "loss": 0.013334686867892742, "avg_return": 0.8624981641769409, "regret": 0.0011262726038694382, "entropy": 0.07338447868824005, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:43.583841Z", "loop": 12582, "env_steps": 7730995199, "loss": 0.012609011493623257, "avg_return": 0.8620237708091736, "regret": 0.0011262726038694382, "entropy": 0.07102596759796143, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:44.439404Z", "loop": 12583, "env_steps": 7731609599, "loss": 0.01306616235524416, "avg_return": 0.8622554540634155, "regret": 0.0011262726038694382, "entropy": 0.0703493133187294, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:45.293214Z", "loop": 12584, "env_steps": 7732223999, "loss": 0.013389438390731812, "avg_return": 0.8624216914176941, "regret": 0.0011262726038694382, "entropy": 0.07303420454263687, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:46.147002Z", "loop": 12585, "env_steps": 7732838399, "loss": 0.012888960540294647, "avg_return": 0.8631418943405151, "regret": 0.0011262726038694382, "entropy": 0.06938915699720383, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:47.001523Z", "loop": 12586, "env_steps": 7733452799, "loss": 0.013148604892194271, "avg_return": 0.8611623048782349, "regret": 0.0011262726038694382, "entropy": 0.07195915281772614, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:47.855702Z", "loop": 12587, "env_steps": 7734067199, "loss": 0.013862723484635353, "avg_return": 0.8626068234443665, "regret": 0.0011262726038694382, "entropy": 0.07130109518766403, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:48.709205Z", "loop": 12588, "env_steps": 7734681599, "loss": 0.012595715932548046, "avg_return": 0.8635382056236267, "regret": 0.0011262726038694382, "entropy": 0.06924758106470108, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:49.562399Z", "loop": 12589, "env_steps": 7735295999, "loss": 0.013323180377483368, "avg_return": 0.8622263073921204, "regret": 0.0011262726038694382, "entropy": 0.0717901960015297, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:50.455317Z", "loop": 12590, "env_steps": 7735910399, "loss": 0.013632695190608501, "avg_return": 0.8619381189346313, "regret": 0.0011208272771909833, "entropy": 0.07221036404371262, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:51.309189Z", "loop": 12591, "env_steps": 7736524799, "loss": 0.013814965263009071, "avg_return": 0.8617438077926636, "regret": 0.0011208272771909833, "entropy": 0.07614632695913315, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:52.163323Z", "loop": 12592, "env_steps": 7737139199, "loss": 0.014500795863568783, "avg_return": 0.8633023500442505, "regret": 0.0011208272771909833, "entropy": 0.0771411806344986, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:53.017112Z", "loop": 12593, "env_steps": 7737753599, "loss": 0.013565095141530037, "avg_return": 0.8611283302307129, "regret": 0.0011208272771909833, "entropy": 0.07527013123035431, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:53.871818Z", "loop": 12594, "env_steps": 7738367999, "loss": 0.015139072202146053, "avg_return": 0.8629201650619507, "regret": 0.0011208272771909833, "entropy": 0.07678797841072083, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:54.726923Z", "loop": 12595, "env_steps": 7738982399, "loss": 0.014507235959172249, "avg_return": 0.8623800873756409, "regret": 0.0011208272771909833, "entropy": 0.07792440056800842, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:55.581379Z", "loop": 12596, "env_steps": 7739596799, "loss": 0.013227169401943684, "avg_return": 0.8615521192550659, "regret": 0.0011208272771909833, "entropy": 0.06892208755016327, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:56.436395Z", "loop": 12597, "env_steps": 7740211199, "loss": 0.013440352864563465, "avg_return": 0.862678050994873, "regret": 0.0011208272771909833, "entropy": 0.0723387748003006, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:57.290495Z", "loop": 12598, "env_steps": 7740825599, "loss": 0.01417145412415266, "avg_return": 0.8631442189216614, "regret": 0.0011208272771909833, "entropy": 0.07430098950862885, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:58.144584Z", "loop": 12599, "env_steps": 7741439999, "loss": 0.013312709517776966, "avg_return": 0.8609529733657837, "regret": 0.0011208272771909833, "entropy": 0.07142209261655807, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:59.037462Z", "loop": 12600, "env_steps": 7742054399, "loss": 0.012149997986853123, "avg_return": 0.863435685634613, "regret": 0.0011574741220101714, "entropy": 0.06716921925544739, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:23:59.892602Z", "loop": 12601, "env_steps": 7742668799, "loss": 0.01275710016489029, "avg_return": 0.8634124994277954, "regret": 0.0011574741220101714, "entropy": 0.07134504616260529, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:00.747266Z", "loop": 12602, "env_steps": 7743283199, "loss": 0.013807958923280239, "avg_return": 0.8623989224433899, "regret": 0.0011574741220101714, "entropy": 0.07066716998815536, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:01.601117Z", "loop": 12603, "env_steps": 7743897599, "loss": 0.013044345192611217, "avg_return": 0.8613377809524536, "regret": 0.0011574741220101714, "entropy": 0.0707717165350914, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:02.456495Z", "loop": 12604, "env_steps": 7744511999, "loss": 0.013229082338511944, "avg_return": 0.862438976764679, "regret": 0.0011574741220101714, "entropy": 0.06990464776754379, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:03.310571Z", "loop": 12605, "env_steps": 7745126399, "loss": 0.012789993546903133, "avg_return": 0.8630870580673218, "regret": 0.0011574741220101714, "entropy": 0.0696229562163353, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:04.164273Z", "loop": 12606, "env_steps": 7745740799, "loss": 0.01258622296154499, "avg_return": 0.8620307445526123, "regret": 0.0011574741220101714, "entropy": 0.06716426461935043, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:05.019087Z", "loop": 12607, "env_steps": 7746355199, "loss": 0.012919731438159943, "avg_return": 0.8621923923492432, "regret": 0.0011574741220101714, "entropy": 0.07083701342344284, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:05.874707Z", "loop": 12608, "env_steps": 7746969599, "loss": 0.01290170755237341, "avg_return": 0.8609904050827026, "regret": 0.0011574741220101714, "entropy": 0.07375343143939972, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:06.728358Z", "loop": 12609, "env_steps": 7747583999, "loss": 0.013626678846776485, "avg_return": 0.8598099946975708, "regret": 0.0011574741220101714, "entropy": 0.0740310549736023, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:07.621763Z", "loop": 12610, "env_steps": 7748198399, "loss": 0.014007319696247578, "avg_return": 0.8608487248420715, "regret": 0.0025383022148162127, "entropy": 0.0705488845705986, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:08.476710Z", "loop": 12611, "env_steps": 7748812799, "loss": 0.014380429871380329, "avg_return": 0.8621883392333984, "regret": 0.0025383022148162127, "entropy": 0.0733206495642662, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:09.331606Z", "loop": 12612, "env_steps": 7749427199, "loss": 0.012811307795345783, "avg_return": 0.8609480261802673, "regret": 0.0025383022148162127, "entropy": 0.07251054048538208, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:10.185611Z", "loop": 12613, "env_steps": 7750041599, "loss": 0.013486896641552448, "avg_return": 0.8625966310501099, "regret": 0.0025383022148162127, "entropy": 0.07361675053834915, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:11.040163Z", "loop": 12614, "env_steps": 7750655999, "loss": 0.01395459659397602, "avg_return": 0.8618062734603882, "regret": 0.0025383022148162127, "entropy": 0.07507863640785217, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:11.894994Z", "loop": 12615, "env_steps": 7751270399, "loss": 0.01364209782332182, "avg_return": 0.8609609007835388, "regret": 0.0025383022148162127, "entropy": 0.07461028546094894, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:12.747873Z", "loop": 12616, "env_steps": 7751884799, "loss": 0.014294560067355633, "avg_return": 0.8606997132301331, "regret": 0.0025383022148162127, "entropy": 0.07732734829187393, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:13.600764Z", "loop": 12617, "env_steps": 7752499199, "loss": 0.014810358174145222, "avg_return": 0.8620540499687195, "regret": 0.0025383022148162127, "entropy": 0.07957641780376434, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:14.454787Z", "loop": 12618, "env_steps": 7753113599, "loss": 0.01568419300019741, "avg_return": 0.8630703687667847, "regret": 0.0025383022148162127, "entropy": 0.08172868192195892, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:15.310050Z", "loop": 12619, "env_steps": 7753727999, "loss": 0.014975580386817455, "avg_return": 0.8629493117332458, "regret": 0.0025383022148162127, "entropy": 0.07937557250261307, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:16.203391Z", "loop": 12620, "env_steps": 7754342399, "loss": 0.016239266842603683, "avg_return": 0.8614463210105896, "regret": 0.0015442389994859695, "entropy": 0.08245603740215302, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:17.056608Z", "loop": 12621, "env_steps": 7754956799, "loss": 0.016827015206217766, "avg_return": 0.862774670124054, "regret": 0.0015442389994859695, "entropy": 0.08775699138641357, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:17.910875Z", "loop": 12622, "env_steps": 7755571199, "loss": 0.017298836261034012, "avg_return": 0.8621795773506165, "regret": 0.0015442389994859695, "entropy": 0.08904021978378296, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:18.766523Z", "loop": 12623, "env_steps": 7756185599, "loss": 0.017082450911402702, "avg_return": 0.8625791668891907, "regret": 0.0015442389994859695, "entropy": 0.08686543256044388, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:19.619986Z", "loop": 12624, "env_steps": 7756799999, "loss": 0.018198492005467415, "avg_return": 0.8636585474014282, "regret": 0.0015442389994859695, "entropy": 0.09070754796266556, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:20.472711Z", "loop": 12625, "env_steps": 7757414399, "loss": 0.018434971570968628, "avg_return": 0.8630418181419373, "regret": 0.0015442389994859695, "entropy": 0.09483671933412552, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:21.326388Z", "loop": 12626, "env_steps": 7758028799, "loss": 0.017570381984114647, "avg_return": 0.8624981045722961, "regret": 0.0015442389994859695, "entropy": 0.09084459394216537, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:22.181964Z", "loop": 12627, "env_steps": 7758643199, "loss": 0.01700526289641857, "avg_return": 0.8631023168563843, "regret": 0.0015442389994859695, "entropy": 0.08740789443254471, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:23.037263Z", "loop": 12628, "env_steps": 7759257599, "loss": 0.016224361956119537, "avg_return": 0.8633373975753784, "regret": 0.0015442389994859695, "entropy": 0.08722581714391708, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:23.892373Z", "loop": 12629, "env_steps": 7759871999, "loss": 0.017055457457900047, "avg_return": 0.8638437390327454, "regret": 0.0015442389994859695, "entropy": 0.08746295422315598, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:24.787741Z", "loop": 12630, "env_steps": 7760486399, "loss": 0.017640497535467148, "avg_return": 0.8631107807159424, "regret": 0.0003693281323648989, "entropy": 0.0863635390996933, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:25.643126Z", "loop": 12631, "env_steps": 7761100799, "loss": 0.015688350424170494, "avg_return": 0.8638571500778198, "regret": 0.0003693281323648989, "entropy": 0.08460652828216553, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:26.498384Z", "loop": 12632, "env_steps": 7761715199, "loss": 0.014759545214474201, "avg_return": 0.8615546822547913, "regret": 0.0003693281323648989, "entropy": 0.07845637202262878, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:27.353337Z", "loop": 12633, "env_steps": 7762329599, "loss": 0.014712752774357796, "avg_return": 0.8615666031837463, "regret": 0.0003693281323648989, "entropy": 0.08027487248182297, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:28.210051Z", "loop": 12634, "env_steps": 7762943999, "loss": 0.016143789514899254, "avg_return": 0.8630592226982117, "regret": 0.0003693281323648989, "entropy": 0.08048711717128754, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:29.065339Z", "loop": 12635, "env_steps": 7763558399, "loss": 0.014545640908181667, "avg_return": 0.8633968234062195, "regret": 0.0003693281323648989, "entropy": 0.07501795142889023, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:29.919742Z", "loop": 12636, "env_steps": 7764172799, "loss": 0.014133192598819733, "avg_return": 0.8644030690193176, "regret": 0.0003693281323648989, "entropy": 0.07655270397663116, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:30.773527Z", "loop": 12637, "env_steps": 7764787199, "loss": 0.014353147707879543, "avg_return": 0.8631477952003479, "regret": 0.0003693281323648989, "entropy": 0.07642979919910431, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:31.628865Z", "loop": 12638, "env_steps": 7765401599, "loss": 0.01603081077337265, "avg_return": 0.8648254871368408, "regret": 0.0003693281323648989, "entropy": 0.07896171510219574, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:32.484865Z", "loop": 12639, "env_steps": 7766015999, "loss": 0.01571393944323063, "avg_return": 0.8645050525665283, "regret": 0.0003693281323648989, "entropy": 0.07967455685138702, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:33.379617Z", "loop": 12640, "env_steps": 7766630399, "loss": 0.01621345803141594, "avg_return": 0.864081621170044, "regret": 9.089444938581437e-05, "entropy": 0.0814162939786911, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:34.234527Z", "loop": 12641, "env_steps": 7767244799, "loss": 0.016447581350803375, "avg_return": 0.8636981248855591, "regret": 9.089444938581437e-05, "entropy": 0.08349571377038956, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:35.089727Z", "loop": 12642, "env_steps": 7767859199, "loss": 0.015665780752897263, "avg_return": 0.8638131022453308, "regret": 9.089444938581437e-05, "entropy": 0.08443087339401245, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:35.944768Z", "loop": 12643, "env_steps": 7768473599, "loss": 0.01527771819382906, "avg_return": 0.8638737201690674, "regret": 9.089444938581437e-05, "entropy": 0.08311320096254349, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:36.800884Z", "loop": 12644, "env_steps": 7769087999, "loss": 0.015410631895065308, "avg_return": 0.863676905632019, "regret": 9.089444938581437e-05, "entropy": 0.08180069923400879, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:37.655600Z", "loop": 12645, "env_steps": 7769702399, "loss": 0.015258065424859524, "avg_return": 0.8639582395553589, "regret": 9.089444938581437e-05, "entropy": 0.08114717155694962, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:38.509965Z", "loop": 12646, "env_steps": 7770316799, "loss": 0.017348850145936012, "avg_return": 0.8632097840309143, "regret": 9.089444938581437e-05, "entropy": 0.08985836058855057, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:39.364604Z", "loop": 12647, "env_steps": 7770931199, "loss": 0.015187683515250683, "avg_return": 0.8623318672180176, "regret": 9.089444938581437e-05, "entropy": 0.07989601045846939, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:40.218248Z", "loop": 12648, "env_steps": 7771545599, "loss": 0.01577046513557434, "avg_return": 0.8629510998725891, "regret": 9.089444938581437e-05, "entropy": 0.08313819766044617, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:41.071820Z", "loop": 12649, "env_steps": 7772159999, "loss": 0.016709690913558006, "avg_return": 0.8635134100914001, "regret": 9.089444938581437e-05, "entropy": 0.0893109142780304, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:41.964973Z", "loop": 12650, "env_steps": 7772774399, "loss": 0.017647692933678627, "avg_return": 0.8644655346870422, "regret": 0.001227382104843855, "entropy": 0.09087145328521729, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:42.819608Z", "loop": 12651, "env_steps": 7773388799, "loss": 0.017319707199931145, "avg_return": 0.862091600894928, "regret": 0.001227382104843855, "entropy": 0.0881890058517456, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:43.673974Z", "loop": 12652, "env_steps": 7774003199, "loss": 0.018082648515701294, "avg_return": 0.8587976098060608, "regret": 0.001227382104843855, "entropy": 0.09531046450138092, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:44.527456Z", "loop": 12653, "env_steps": 7774617599, "loss": 0.018371528014540672, "avg_return": 0.8577824234962463, "regret": 0.001227382104843855, "entropy": 0.09424812346696854, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:45.381317Z", "loop": 12654, "env_steps": 7775231999, "loss": 0.018061893060803413, "avg_return": 0.8587923645973206, "regret": 0.001227382104843855, "entropy": 0.09184543043375015, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:46.235522Z", "loop": 12655, "env_steps": 7775846399, "loss": 0.016531655564904213, "avg_return": 0.8611335158348083, "regret": 0.001227382104843855, "entropy": 0.08998849242925644, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:47.090114Z", "loop": 12656, "env_steps": 7776460799, "loss": 0.017336919903755188, "avg_return": 0.8613623380661011, "regret": 0.001227382104843855, "entropy": 0.0902826189994812, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:47.943106Z", "loop": 12657, "env_steps": 7777075199, "loss": 0.017977125942707062, "avg_return": 0.8624951243400574, "regret": 0.001227382104843855, "entropy": 0.09135692566633224, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:48.796372Z", "loop": 12658, "env_steps": 7777689599, "loss": 0.01707683876156807, "avg_return": 0.8630108833312988, "regret": 0.001227382104843855, "entropy": 0.09198350459337234, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:49.650535Z", "loop": 12659, "env_steps": 7778303999, "loss": 0.018396614119410515, "avg_return": 0.8625152707099915, "regret": 0.001227382104843855, "entropy": 0.0955352932214737, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:50.546499Z", "loop": 12660, "env_steps": 7778918399, "loss": 0.01658298820257187, "avg_return": 0.8628765940666199, "regret": 0.0009293926414102316, "entropy": 0.08832581341266632, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:51.400644Z", "loop": 12661, "env_steps": 7779532799, "loss": 0.017701037228107452, "avg_return": 0.8615769743919373, "regret": 0.0009293926414102316, "entropy": 0.0940815806388855, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:52.255127Z", "loop": 12662, "env_steps": 7780147199, "loss": 0.016878336668014526, "avg_return": 0.8632746338844299, "regret": 0.0009293926414102316, "entropy": 0.08915221691131592, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:53.111136Z", "loop": 12663, "env_steps": 7780761599, "loss": 0.015066683292388916, "avg_return": 0.8630505800247192, "regret": 0.0009293926414102316, "entropy": 0.08035585284233093, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:53.966321Z", "loop": 12664, "env_steps": 7781375999, "loss": 0.0170656256377697, "avg_return": 0.8636606931686401, "regret": 0.0009293926414102316, "entropy": 0.08570349216461182, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:54.820849Z", "loop": 12665, "env_steps": 7781990399, "loss": 0.016613483428955078, "avg_return": 0.8632574677467346, "regret": 0.0009293926414102316, "entropy": 0.08652976900339127, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:55.675271Z", "loop": 12666, "env_steps": 7782604799, "loss": 0.01672223024070263, "avg_return": 0.8627176284790039, "regret": 0.0009293926414102316, "entropy": 0.08963383734226227, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:56.528820Z", "loop": 12667, "env_steps": 7783219199, "loss": 0.016531895846128464, "avg_return": 0.8634882569313049, "regret": 0.0009293926414102316, "entropy": 0.08702316880226135, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:57.382806Z", "loop": 12668, "env_steps": 7783833599, "loss": 0.01787731610238552, "avg_return": 0.8625311255455017, "regret": 0.0009293926414102316, "entropy": 0.09483388811349869, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:58.238211Z", "loop": 12669, "env_steps": 7784447999, "loss": 0.017249679192900658, "avg_return": 0.8628725409507751, "regret": 0.0009293926414102316, "entropy": 0.09172118455171585, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:59.132382Z", "loop": 12670, "env_steps": 7785062399, "loss": 0.01702682301402092, "avg_return": 0.8634332418441772, "regret": 0.00044146980508230627, "entropy": 0.09318184107542038, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:24:59.985698Z", "loop": 12671, "env_steps": 7785676799, "loss": 0.019170835614204407, "avg_return": 0.8630334734916687, "regret": 0.00044146980508230627, "entropy": 0.09890282899141312, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:00.839375Z", "loop": 12672, "env_steps": 7786291199, "loss": 0.019362717866897583, "avg_return": 0.8628896474838257, "regret": 0.00044146980508230627, "entropy": 0.10474199056625366, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:01.696400Z", "loop": 12673, "env_steps": 7786905599, "loss": 0.02023388259112835, "avg_return": 0.8623889088630676, "regret": 0.00044146980508230627, "entropy": 0.10672204196453094, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:02.551636Z", "loop": 12674, "env_steps": 7787519999, "loss": 0.022815993055701256, "avg_return": 0.8631974458694458, "regret": 0.00044146980508230627, "entropy": 0.11847522109746933, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:03.405356Z", "loop": 12675, "env_steps": 7788134399, "loss": 0.023475471884012222, "avg_return": 0.8608044385910034, "regret": 0.00044146980508230627, "entropy": 0.12182952463626862, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:04.259312Z", "loop": 12676, "env_steps": 7788748799, "loss": 0.02292751893401146, "avg_return": 0.8612545132637024, "regret": 0.00044146980508230627, "entropy": 0.11759591847658157, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:05.113045Z", "loop": 12677, "env_steps": 7789363199, "loss": 0.023412909358739853, "avg_return": 0.8648674488067627, "regret": 0.00044146980508230627, "entropy": 0.11836477369070053, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:05.967170Z", "loop": 12678, "env_steps": 7789977599, "loss": 0.021238071843981743, "avg_return": 0.8635413646697998, "regret": 0.00044146980508230627, "entropy": 0.11281182616949081, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:06.821097Z", "loop": 12679, "env_steps": 7790591999, "loss": 0.022131366655230522, "avg_return": 0.8620059490203857, "regret": 0.00044146980508230627, "entropy": 0.11479026824235916, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:07.713908Z", "loop": 12680, "env_steps": 7791206399, "loss": 0.02208608202636242, "avg_return": 0.8640999794006348, "regret": 0.0011345773236826062, "entropy": 0.11479467898607254, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:08.568275Z", "loop": 12681, "env_steps": 7791820799, "loss": 0.019986988976597786, "avg_return": 0.8623486757278442, "regret": 0.0011345773236826062, "entropy": 0.1049363762140274, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:09.422007Z", "loop": 12682, "env_steps": 7792435199, "loss": 0.019130099564790726, "avg_return": 0.8620186448097229, "regret": 0.0011345773236826062, "entropy": 0.10381589829921722, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:10.275912Z", "loop": 12683, "env_steps": 7793049599, "loss": 0.018270650878548622, "avg_return": 0.8623172044754028, "regret": 0.0011345773236826062, "entropy": 0.09755898267030716, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:11.130139Z", "loop": 12684, "env_steps": 7793663999, "loss": 0.01864464394748211, "avg_return": 0.8614147305488586, "regret": 0.0011345773236826062, "entropy": 0.10390938818454742, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:11.983912Z", "loop": 12685, "env_steps": 7794278399, "loss": 0.017514288425445557, "avg_return": 0.8609397411346436, "regret": 0.0011345773236826062, "entropy": 0.10216918587684631, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:12.837544Z", "loop": 12686, "env_steps": 7794892799, "loss": 0.01946972869336605, "avg_return": 0.85942143201828, "regret": 0.0011345773236826062, "entropy": 0.10813108831644058, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:13.691139Z", "loop": 12687, "env_steps": 7795507199, "loss": 0.020671801641583443, "avg_return": 0.8597835302352905, "regret": 0.0011345773236826062, "entropy": 0.11063535511493683, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:14.545364Z", "loop": 12688, "env_steps": 7796121599, "loss": 0.020370787009596825, "avg_return": 0.8594826459884644, "regret": 0.0011345773236826062, "entropy": 0.10736673325300217, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:15.398214Z", "loop": 12689, "env_steps": 7796735999, "loss": 0.019065838307142258, "avg_return": 0.8607222437858582, "regret": 0.0011345773236826062, "entropy": 0.10235042124986649, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:16.290367Z", "loop": 12690, "env_steps": 7797350399, "loss": 0.01711360365152359, "avg_return": 0.8606694936752319, "regret": 0.002724939025938511, "entropy": 0.09555406868457794, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:17.145139Z", "loop": 12691, "env_steps": 7797964799, "loss": 0.016343584284186363, "avg_return": 0.8605015277862549, "regret": 0.002724939025938511, "entropy": 0.09220816195011139, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:17.999430Z", "loop": 12692, "env_steps": 7798579199, "loss": 0.015994742512702942, "avg_return": 0.8606259226799011, "regret": 0.002724939025938511, "entropy": 0.08987779915332794, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:18.853665Z", "loop": 12693, "env_steps": 7799193599, "loss": 0.015408593229949474, "avg_return": 0.8613747358322144, "regret": 0.002724939025938511, "entropy": 0.08377571403980255, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:19.707718Z", "loop": 12694, "env_steps": 7799807999, "loss": 0.01536713819950819, "avg_return": 0.8636285662651062, "regret": 0.002724939025938511, "entropy": 0.08458991348743439, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:20.562864Z", "loop": 12695, "env_steps": 7800422399, "loss": 0.014755758456885815, "avg_return": 0.862740695476532, "regret": 0.002724939025938511, "entropy": 0.08038950711488724, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:21.418095Z", "loop": 12696, "env_steps": 7801036799, "loss": 0.015410125255584717, "avg_return": 0.8633437156677246, "regret": 0.002724939025938511, "entropy": 0.07902463525533676, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:22.273413Z", "loop": 12697, "env_steps": 7801651199, "loss": 0.014869727194309235, "avg_return": 0.862841010093689, "regret": 0.002724939025938511, "entropy": 0.07651019841432571, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:23.128063Z", "loop": 12698, "env_steps": 7802265599, "loss": 0.013834582641720772, "avg_return": 0.8633629679679871, "regret": 0.002724939025938511, "entropy": 0.07395250350236893, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:23.982088Z", "loop": 12699, "env_steps": 7802879999, "loss": 0.013145658187568188, "avg_return": 0.8628824353218079, "regret": 0.002724939025938511, "entropy": 0.07119613140821457, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:24.874537Z", "loop": 12700, "env_steps": 7803494399, "loss": 0.01255414541810751, "avg_return": 0.8634933829307556, "regret": 0.0005238174926489592, "entropy": 0.06861130893230438, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:25.730222Z", "loop": 12701, "env_steps": 7804108799, "loss": 0.013822929933667183, "avg_return": 0.8639818429946899, "regret": 0.0005238174926489592, "entropy": 0.07090123742818832, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:26.584590Z", "loop": 12702, "env_steps": 7804723199, "loss": 0.01331599522382021, "avg_return": 0.8630110621452332, "regret": 0.0005238174926489592, "entropy": 0.07008344680070877, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:27.439915Z", "loop": 12703, "env_steps": 7805337599, "loss": 0.012397410348057747, "avg_return": 0.863226056098938, "regret": 0.0005238174926489592, "entropy": 0.06703308969736099, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:28.294239Z", "loop": 12704, "env_steps": 7805951999, "loss": 0.012286009266972542, "avg_return": 0.8627910614013672, "regret": 0.0005238174926489592, "entropy": 0.06768867373466492, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:29.148606Z", "loop": 12705, "env_steps": 7806566399, "loss": 0.012149515561759472, "avg_return": 0.8623122572898865, "regret": 0.0005238174926489592, "entropy": 0.06600415706634521, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:30.003256Z", "loop": 12706, "env_steps": 7807180799, "loss": 0.013011082075536251, "avg_return": 0.8623716235160828, "regret": 0.0005238174926489592, "entropy": 0.06802081316709518, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:30.857970Z", "loop": 12707, "env_steps": 7807795199, "loss": 0.01292179711163044, "avg_return": 0.8610062003135681, "regret": 0.0005238174926489592, "entropy": 0.06693176180124283, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:31.712416Z", "loop": 12708, "env_steps": 7808409599, "loss": 0.012773619964718819, "avg_return": 0.8640589714050293, "regret": 0.0005238174926489592, "entropy": 0.06891972571611404, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:32.567371Z", "loop": 12709, "env_steps": 7809023999, "loss": 0.013236179947853088, "avg_return": 0.8633731007575989, "regret": 0.0005238174926489592, "entropy": 0.07012243568897247, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:33.461710Z", "loop": 12710, "env_steps": 7809638399, "loss": 0.013066679239273071, "avg_return": 0.8601893186569214, "regret": 0.0012078353902325034, "entropy": 0.06824010610580444, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:34.316070Z", "loop": 12711, "env_steps": 7810252799, "loss": 0.012790567241609097, "avg_return": 0.8620813488960266, "regret": 0.0012078353902325034, "entropy": 0.0708591490983963, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:35.170485Z", "loop": 12712, "env_steps": 7810867199, "loss": 0.013136887922883034, "avg_return": 0.8617414832115173, "regret": 0.0012078353902325034, "entropy": 0.0708039402961731, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:36.025449Z", "loop": 12713, "env_steps": 7811481599, "loss": 0.013066858053207397, "avg_return": 0.8639619946479797, "regret": 0.0012078353902325034, "entropy": 0.07011264562606812, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:36.879561Z", "loop": 12714, "env_steps": 7812095999, "loss": 0.014132543466985226, "avg_return": 0.8634955286979675, "regret": 0.0012078353902325034, "entropy": 0.07137541472911835, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:37.734516Z", "loop": 12715, "env_steps": 7812710399, "loss": 0.012391827069222927, "avg_return": 0.8612074851989746, "regret": 0.0012078353902325034, "entropy": 0.06710868328809738, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:38.587538Z", "loop": 12716, "env_steps": 7813324799, "loss": 0.012723224237561226, "avg_return": 0.8627350330352783, "regret": 0.0012078353902325034, "entropy": 0.06867446005344391, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:39.441497Z", "loop": 12717, "env_steps": 7813939199, "loss": 0.01263592578470707, "avg_return": 0.8613371253013611, "regret": 0.0012078353902325034, "entropy": 0.06557196378707886, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:40.295794Z", "loop": 12718, "env_steps": 7814553599, "loss": 0.012944144196808338, "avg_return": 0.8639137744903564, "regret": 0.0012078353902325034, "entropy": 0.06819579005241394, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:41.150211Z", "loop": 12719, "env_steps": 7815167999, "loss": 0.012307041324675083, "avg_return": 0.8636811375617981, "regret": 0.0012078353902325034, "entropy": 0.06716816127300262, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:42.044600Z", "loop": 12720, "env_steps": 7815782399, "loss": 0.013689123094081879, "avg_return": 0.8644627332687378, "regret": 0.0002560084976721555, "entropy": 0.07066893577575684, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:42.897917Z", "loop": 12721, "env_steps": 7816396799, "loss": 0.012921102344989777, "avg_return": 0.8632569313049316, "regret": 0.0002560084976721555, "entropy": 0.06934705376625061, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:43.751945Z", "loop": 12722, "env_steps": 7817011199, "loss": 0.01274735014885664, "avg_return": 0.8628454804420471, "regret": 0.0002560084976721555, "entropy": 0.06936994194984436, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:44.606732Z", "loop": 12723, "env_steps": 7817625599, "loss": 0.013700544834136963, "avg_return": 0.8627731800079346, "regret": 0.0002560084976721555, "entropy": 0.07183847576379776, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:45.460348Z", "loop": 12724, "env_steps": 7818239999, "loss": 0.015055580995976925, "avg_return": 0.863772988319397, "regret": 0.0002560084976721555, "entropy": 0.07609909027814865, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:46.313609Z", "loop": 12725, "env_steps": 7818854399, "loss": 0.014849431812763214, "avg_return": 0.8630275726318359, "regret": 0.0002560084976721555, "entropy": 0.0767102763056755, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:47.167464Z", "loop": 12726, "env_steps": 7819468799, "loss": 0.013630536384880543, "avg_return": 0.8632704615592957, "regret": 0.0002560084976721555, "entropy": 0.07443324476480484, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:48.022575Z", "loop": 12727, "env_steps": 7820083199, "loss": 0.014012503437697887, "avg_return": 0.8616605997085571, "regret": 0.0002560084976721555, "entropy": 0.07548804581165314, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:48.877796Z", "loop": 12728, "env_steps": 7820697599, "loss": 0.01394595392048359, "avg_return": 0.863446056842804, "regret": 0.0002560084976721555, "entropy": 0.07554730772972107, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:49.732964Z", "loop": 12729, "env_steps": 7821311999, "loss": 0.014830346219241619, "avg_return": 0.8643915057182312, "regret": 0.0002560084976721555, "entropy": 0.07819095253944397, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:50.626707Z", "loop": 12730, "env_steps": 7821926399, "loss": 0.015375512652099133, "avg_return": 0.8633623719215393, "regret": 9.764648712007329e-05, "entropy": 0.07671205699443817, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:51.480686Z", "loop": 12731, "env_steps": 7822540799, "loss": 0.016086025163531303, "avg_return": 0.8646805882453918, "regret": 9.764648712007329e-05, "entropy": 0.08353093266487122, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:52.335387Z", "loop": 12732, "env_steps": 7823155199, "loss": 0.015311824157834053, "avg_return": 0.863083004951477, "regret": 9.764648712007329e-05, "entropy": 0.07859522104263306, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:53.189094Z", "loop": 12733, "env_steps": 7823769599, "loss": 0.015776121988892555, "avg_return": 0.8626111149787903, "regret": 9.764648712007329e-05, "entropy": 0.08180856704711914, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:54.042412Z", "loop": 12734, "env_steps": 7824383999, "loss": 0.016326898708939552, "avg_return": 0.8628956079483032, "regret": 9.764648712007329e-05, "entropy": 0.08320269733667374, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:54.897828Z", "loop": 12735, "env_steps": 7824998399, "loss": 0.01613490842282772, "avg_return": 0.8623915910720825, "regret": 9.764648712007329e-05, "entropy": 0.08643759787082672, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:55.752684Z", "loop": 12736, "env_steps": 7825612799, "loss": 0.015602822415530682, "avg_return": 0.8630592226982117, "regret": 9.764648712007329e-05, "entropy": 0.0836171954870224, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:56.607749Z", "loop": 12737, "env_steps": 7826227199, "loss": 0.016749156638979912, "avg_return": 0.8640046119689941, "regret": 9.764648712007329e-05, "entropy": 0.08602168411016464, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:57.461804Z", "loop": 12738, "env_steps": 7826841599, "loss": 0.01717459224164486, "avg_return": 0.8633775115013123, "regret": 9.764648712007329e-05, "entropy": 0.08196434378623962, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:58.316349Z", "loop": 12739, "env_steps": 7827455999, "loss": 0.01558600552380085, "avg_return": 0.8635205030441284, "regret": 9.764648712007329e-05, "entropy": 0.08299459517002106, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:25:59.207908Z", "loop": 12740, "env_steps": 7828070399, "loss": 0.016876274719834328, "avg_return": 0.865362286567688, "regret": 0.00010428956738905981, "entropy": 0.0825500637292862, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:00.062995Z", "loop": 12741, "env_steps": 7828684799, "loss": 0.016384290531277657, "avg_return": 0.8635393381118774, "regret": 0.00010428956738905981, "entropy": 0.08285845816135406, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:00.918821Z", "loop": 12742, "env_steps": 7829299199, "loss": 0.016696317121386528, "avg_return": 0.8633878827095032, "regret": 0.00010428956738905981, "entropy": 0.08347733318805695, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:01.775377Z", "loop": 12743, "env_steps": 7829913599, "loss": 0.016125217080116272, "avg_return": 0.8625993132591248, "regret": 0.00010428956738905981, "entropy": 0.08164887875318527, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:02.630100Z", "loop": 12744, "env_steps": 7830527999, "loss": 0.016078177839517593, "avg_return": 0.8632937073707581, "regret": 0.00010428956738905981, "entropy": 0.08385158330202103, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:03.484986Z", "loop": 12745, "env_steps": 7831142399, "loss": 0.017081357538700104, "avg_return": 0.8642656803131104, "regret": 0.00010428956738905981, "entropy": 0.09031225740909576, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:04.339359Z", "loop": 12746, "env_steps": 7831756799, "loss": 0.017399901524186134, "avg_return": 0.8636703491210938, "regret": 0.00010428956738905981, "entropy": 0.09227745234966278, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:05.195187Z", "loop": 12747, "env_steps": 7832371199, "loss": 0.017934365198016167, "avg_return": 0.8629071116447449, "regret": 0.00010428956738905981, "entropy": 0.09086085110902786, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:06.049711Z", "loop": 12748, "env_steps": 7832985599, "loss": 0.01968083158135414, "avg_return": 0.8632704615592957, "regret": 0.00010428956738905981, "entropy": 0.09757263958454132, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:06.904576Z", "loop": 12749, "env_steps": 7833599999, "loss": 0.02182707004249096, "avg_return": 0.8629704713821411, "regret": 0.00010428956738905981, "entropy": 0.10577992349863052, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:07.798556Z", "loop": 12750, "env_steps": 7834214399, "loss": 0.022587953135371208, "avg_return": 0.86341392993927, "regret": 0.0015688902931287885, "entropy": 0.10701016336679459, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:08.653642Z", "loop": 12751, "env_steps": 7834828799, "loss": 0.020710937678813934, "avg_return": 0.8625070452690125, "regret": 0.0015688902931287885, "entropy": 0.10261982679367065, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:09.508310Z", "loop": 12752, "env_steps": 7835443199, "loss": 0.0195396076887846, "avg_return": 0.859954833984375, "regret": 0.0015688902931287885, "entropy": 0.09790821373462677, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:10.362350Z", "loop": 12753, "env_steps": 7836057599, "loss": 0.018139028921723366, "avg_return": 0.862918496131897, "regret": 0.0015688902931287885, "entropy": 0.0892399400472641, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:11.216526Z", "loop": 12754, "env_steps": 7836671999, "loss": 0.016916556283831596, "avg_return": 0.8635221719741821, "regret": 0.0015688902931287885, "entropy": 0.08784380555152893, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:12.070970Z", "loop": 12755, "env_steps": 7837286399, "loss": 0.01508828904479742, "avg_return": 0.8632910251617432, "regret": 0.0015688902931287885, "entropy": 0.08115611970424652, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:12.925243Z", "loop": 12756, "env_steps": 7837900799, "loss": 0.015409024432301521, "avg_return": 0.8636729121208191, "regret": 0.0015688902931287885, "entropy": 0.0797460600733757, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:13.778871Z", "loop": 12757, "env_steps": 7838515199, "loss": 0.015211174264550209, "avg_return": 0.8638606071472168, "regret": 0.0015688902931287885, "entropy": 0.07788017392158508, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:14.633278Z", "loop": 12758, "env_steps": 7839129599, "loss": 0.015084576793015003, "avg_return": 0.8643172383308411, "regret": 0.0015688902931287885, "entropy": 0.07799985259771347, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:15.487032Z", "loop": 12759, "env_steps": 7839743999, "loss": 0.014052028767764568, "avg_return": 0.8618984222412109, "regret": 0.0015688902931287885, "entropy": 0.07358111441135406, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:16.379398Z", "loop": 12760, "env_steps": 7840358399, "loss": 0.014239397831261158, "avg_return": 0.8620612025260925, "regret": 0.0003649677964858711, "entropy": 0.07327654212713242, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:17.233571Z", "loop": 12761, "env_steps": 7840972799, "loss": 0.013661161065101624, "avg_return": 0.864047646522522, "regret": 0.0003649677964858711, "entropy": 0.0727783590555191, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:18.088577Z", "loop": 12762, "env_steps": 7841587199, "loss": 0.014153395779430866, "avg_return": 0.8627111911773682, "regret": 0.0003649677964858711, "entropy": 0.07494212687015533, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:18.943310Z", "loop": 12763, "env_steps": 7842201599, "loss": 0.01332117523998022, "avg_return": 0.8621487617492676, "regret": 0.0003649677964858711, "entropy": 0.07077089697122574, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:19.797400Z", "loop": 12764, "env_steps": 7842815999, "loss": 0.013753524981439114, "avg_return": 0.862544059753418, "regret": 0.0003649677964858711, "entropy": 0.07053739577531815, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:20.652091Z", "loop": 12765, "env_steps": 7843430399, "loss": 0.013421346433460712, "avg_return": 0.8633675575256348, "regret": 0.0003649677964858711, "entropy": 0.06745461374521255, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:21.507233Z", "loop": 12766, "env_steps": 7844044799, "loss": 0.013295394368469715, "avg_return": 0.8626042604446411, "regret": 0.0003649677964858711, "entropy": 0.07048715651035309, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:22.360507Z", "loop": 12767, "env_steps": 7844659199, "loss": 0.01368655450642109, "avg_return": 0.8625891208648682, "regret": 0.0003649677964858711, "entropy": 0.06912337988615036, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:23.214453Z", "loop": 12768, "env_steps": 7845273599, "loss": 0.013315687887370586, "avg_return": 0.8623809218406677, "regret": 0.0003649677964858711, "entropy": 0.07089050859212875, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:24.069622Z", "loop": 12769, "env_steps": 7845887999, "loss": 0.013668516650795937, "avg_return": 0.8622431755065918, "regret": 0.0003649677964858711, "entropy": 0.07015710324048996, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:24.961698Z", "loop": 12770, "env_steps": 7846502399, "loss": 0.013353714719414711, "avg_return": 0.8626987934112549, "regret": 0.0012770984321832657, "entropy": 0.06908563524484634, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:25.814981Z", "loop": 12771, "env_steps": 7847116799, "loss": 0.012746970169246197, "avg_return": 0.861667275428772, "regret": 0.0012770984321832657, "entropy": 0.0660797581076622, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:26.668961Z", "loop": 12772, "env_steps": 7847731199, "loss": 0.012798914685845375, "avg_return": 0.8615188002586365, "regret": 0.0012770984321832657, "entropy": 0.06648623198270798, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:27.524471Z", "loop": 12773, "env_steps": 7848345599, "loss": 0.012784475460648537, "avg_return": 0.8611738085746765, "regret": 0.0012770984321832657, "entropy": 0.07159090787172318, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:28.379462Z", "loop": 12774, "env_steps": 7848959999, "loss": 0.012280905619263649, "avg_return": 0.8612176775932312, "regret": 0.0012770984321832657, "entropy": 0.06543348729610443, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:29.233546Z", "loop": 12775, "env_steps": 7849574399, "loss": 0.013595758937299252, "avg_return": 0.8619074821472168, "regret": 0.0012770984321832657, "entropy": 0.06726082414388657, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:30.088872Z", "loop": 12776, "env_steps": 7850188799, "loss": 0.013525743968784809, "avg_return": 0.8617106080055237, "regret": 0.0012770984321832657, "entropy": 0.06904227286577225, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:30.943348Z", "loop": 12777, "env_steps": 7850803199, "loss": 0.013570706360042095, "avg_return": 0.860714316368103, "regret": 0.0012770984321832657, "entropy": 0.06989168375730515, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:31.798125Z", "loop": 12778, "env_steps": 7851417599, "loss": 0.013243012130260468, "avg_return": 0.8628237247467041, "regret": 0.0012770984321832657, "entropy": 0.07034127414226532, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:32.651931Z", "loop": 12779, "env_steps": 7852031999, "loss": 0.013066855259239674, "avg_return": 0.862098217010498, "regret": 0.0012770984321832657, "entropy": 0.07060488313436508, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:33.544381Z", "loop": 12780, "env_steps": 7852646399, "loss": 0.013493241742253304, "avg_return": 0.8630143404006958, "regret": 0.0017536442028358579, "entropy": 0.072211354970932, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:34.398144Z", "loop": 12781, "env_steps": 7853260799, "loss": 0.01264007855206728, "avg_return": 0.8615087866783142, "regret": 0.0017536442028358579, "entropy": 0.07055345177650452, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:35.253136Z", "loop": 12782, "env_steps": 7853875199, "loss": 0.013406114652752876, "avg_return": 0.8610832095146179, "regret": 0.0017536442028358579, "entropy": 0.07070429623126984, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:36.107434Z", "loop": 12783, "env_steps": 7854489599, "loss": 0.012892061844468117, "avg_return": 0.8612303137779236, "regret": 0.0017536442028358579, "entropy": 0.06759009510278702, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:36.961143Z", "loop": 12784, "env_steps": 7855103999, "loss": 0.01281175296753645, "avg_return": 0.8611311316490173, "regret": 0.0017536442028358579, "entropy": 0.06975392252206802, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:37.813972Z", "loop": 12785, "env_steps": 7855718399, "loss": 0.011971603147685528, "avg_return": 0.8628302216529846, "regret": 0.0017536442028358579, "entropy": 0.06424003094434738, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:38.668316Z", "loop": 12786, "env_steps": 7856332799, "loss": 0.011913707479834557, "avg_return": 0.8623006343841553, "regret": 0.0017536442028358579, "entropy": 0.0652257427573204, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:39.523407Z", "loop": 12787, "env_steps": 7856947199, "loss": 0.012311656028032303, "avg_return": 0.8643168210983276, "regret": 0.0017536442028358579, "entropy": 0.06509017944335938, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:40.377236Z", "loop": 12788, "env_steps": 7857561599, "loss": 0.01260241586714983, "avg_return": 0.8634023070335388, "regret": 0.0017536442028358579, "entropy": 0.06554622948169708, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:41.229583Z", "loop": 12789, "env_steps": 7858175999, "loss": 0.01318826712667942, "avg_return": 0.8614518642425537, "regret": 0.0017536442028358579, "entropy": 0.06670759618282318, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:42.120927Z", "loop": 12790, "env_steps": 7858790399, "loss": 0.011639109812676907, "avg_return": 0.8629606366157532, "regret": 0.0006051099044270813, "entropy": 0.06406804174184799, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:42.975874Z", "loop": 12791, "env_steps": 7859404799, "loss": 0.012039375491440296, "avg_return": 0.8632973432540894, "regret": 0.0006051099044270813, "entropy": 0.06297364085912704, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:43.830072Z", "loop": 12792, "env_steps": 7860019199, "loss": 0.011091708205640316, "avg_return": 0.8630186319351196, "regret": 0.0006051099044270813, "entropy": 0.06171104311943054, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:44.684992Z", "loop": 12793, "env_steps": 7860633599, "loss": 0.012039043009281158, "avg_return": 0.863273561000824, "regret": 0.0006051099044270813, "entropy": 0.0630401149392128, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:45.539764Z", "loop": 12794, "env_steps": 7861247999, "loss": 0.01236898172646761, "avg_return": 0.8615860939025879, "regret": 0.0006051099044270813, "entropy": 0.06609585881233215, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:46.395248Z", "loop": 12795, "env_steps": 7861862399, "loss": 0.011518150568008423, "avg_return": 0.8614491820335388, "regret": 0.0006051099044270813, "entropy": 0.06248610094189644, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:47.250698Z", "loop": 12796, "env_steps": 7862476799, "loss": 0.011664465069770813, "avg_return": 0.8639999628067017, "regret": 0.0006051099044270813, "entropy": 0.061743367463350296, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:48.105464Z", "loop": 12797, "env_steps": 7863091199, "loss": 0.012012477032840252, "avg_return": 0.8626003265380859, "regret": 0.0006051099044270813, "entropy": 0.0630531907081604, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:48.960211Z", "loop": 12798, "env_steps": 7863705599, "loss": 0.013506132178008556, "avg_return": 0.8637677431106567, "regret": 0.0006051099044270813, "entropy": 0.06719101965427399, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:49.814856Z", "loop": 12799, "env_steps": 7864319999, "loss": 0.012772093527019024, "avg_return": 0.8631311058998108, "regret": 0.0006051099044270813, "entropy": 0.06766599416732788, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:50.709667Z", "loop": 12800, "env_steps": 7864934399, "loss": 0.012809780426323414, "avg_return": 0.8627205491065979, "regret": 0.0004295038525015116, "entropy": 0.06664110720157623, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:51.565554Z", "loop": 12801, "env_steps": 7865548799, "loss": 0.01285489834845066, "avg_return": 0.863566517829895, "regret": 0.0004295038525015116, "entropy": 0.06690548360347748, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:52.420601Z", "loop": 12802, "env_steps": 7866163199, "loss": 0.013070866465568542, "avg_return": 0.8641942739486694, "regret": 0.0004295038525015116, "entropy": 0.06825431436300278, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:53.275307Z", "loop": 12803, "env_steps": 7866777599, "loss": 0.013794749975204468, "avg_return": 0.8636245131492615, "regret": 0.0004295038525015116, "entropy": 0.07572978734970093, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:54.129839Z", "loop": 12804, "env_steps": 7867391999, "loss": 0.013213333673775196, "avg_return": 0.8637924194335938, "regret": 0.0004295038525015116, "entropy": 0.07270762324333191, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:54.984254Z", "loop": 12805, "env_steps": 7868006399, "loss": 0.01570131815969944, "avg_return": 0.8632848262786865, "regret": 0.0004295038525015116, "entropy": 0.08019314706325531, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:55.838924Z", "loop": 12806, "env_steps": 7868620799, "loss": 0.01557698380202055, "avg_return": 0.8629339933395386, "regret": 0.0004295038525015116, "entropy": 0.07822377979755402, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:56.692396Z", "loop": 12807, "env_steps": 7869235199, "loss": 0.0168959591537714, "avg_return": 0.8631278872489929, "regret": 0.0004295038525015116, "entropy": 0.08500569313764572, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:57.545828Z", "loop": 12808, "env_steps": 7869849599, "loss": 0.018179545179009438, "avg_return": 0.862259030342102, "regret": 0.0004295038525015116, "entropy": 0.0880168154835701, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:58.400028Z", "loop": 12809, "env_steps": 7870463999, "loss": 0.018027668818831444, "avg_return": 0.8628218770027161, "regret": 0.0004295038525015116, "entropy": 0.09069803357124329, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:26:59.293431Z", "loop": 12810, "env_steps": 7871078399, "loss": 0.018914271146059036, "avg_return": 0.8618634343147278, "regret": 0.0007677684770897031, "entropy": 0.09981530904769897, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:00.148787Z", "loop": 12811, "env_steps": 7871692799, "loss": 0.01931591145694256, "avg_return": 0.8634578585624695, "regret": 0.0007677684770897031, "entropy": 0.09828189760446548, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:01.002890Z", "loop": 12812, "env_steps": 7872307199, "loss": 0.019632330164313316, "avg_return": 0.8641504049301147, "regret": 0.0007677684770897031, "entropy": 0.09812169522047043, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:01.857145Z", "loop": 12813, "env_steps": 7872921599, "loss": 0.02039436064660549, "avg_return": 0.8622385859489441, "regret": 0.0007677684770897031, "entropy": 0.10190828889608383, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:02.712154Z", "loop": 12814, "env_steps": 7873535999, "loss": 0.02297285944223404, "avg_return": 0.8626127243041992, "regret": 0.0007677684770897031, "entropy": 0.11230791360139847, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:03.566044Z", "loop": 12815, "env_steps": 7874150399, "loss": 0.02335825376212597, "avg_return": 0.862145185470581, "regret": 0.0007677684770897031, "entropy": 0.1147129014134407, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:04.418519Z", "loop": 12816, "env_steps": 7874764799, "loss": 0.02329597994685173, "avg_return": 0.8608536124229431, "regret": 0.0007677684770897031, "entropy": 0.11408495157957077, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:05.272128Z", "loop": 12817, "env_steps": 7875379199, "loss": 0.021758873015642166, "avg_return": 0.8605816960334778, "regret": 0.0007677684770897031, "entropy": 0.10681106895208359, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:06.125768Z", "loop": 12818, "env_steps": 7875993599, "loss": 0.023445868864655495, "avg_return": 0.859226405620575, "regret": 0.0007677684770897031, "entropy": 0.1122116968035698, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:06.980033Z", "loop": 12819, "env_steps": 7876607999, "loss": 0.021891385316848755, "avg_return": 0.8617255091667175, "regret": 0.0007677684770897031, "entropy": 0.11139751225709915, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:07.875642Z", "loop": 12820, "env_steps": 7877222399, "loss": 0.022464869543910027, "avg_return": 0.8613659143447876, "regret": 0.0016009814571589231, "entropy": 0.10802163928747177, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:08.729013Z", "loop": 12821, "env_steps": 7877836799, "loss": 0.021874556317925453, "avg_return": 0.8622522950172424, "regret": 0.0016009814571589231, "entropy": 0.10587532818317413, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:09.583629Z", "loop": 12822, "env_steps": 7878451199, "loss": 0.020463746041059494, "avg_return": 0.8630416989326477, "regret": 0.0016009814571589231, "entropy": 0.10391714423894882, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:10.438264Z", "loop": 12823, "env_steps": 7879065599, "loss": 0.017610637471079826, "avg_return": 0.8634504675865173, "regret": 0.0016009814571589231, "entropy": 0.09094233065843582, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:11.294481Z", "loop": 12824, "env_steps": 7879679999, "loss": 0.017007892951369286, "avg_return": 0.863941490650177, "regret": 0.0016009814571589231, "entropy": 0.08616850525140762, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:12.148233Z", "loop": 12825, "env_steps": 7880294399, "loss": 0.015998434275388718, "avg_return": 0.8619767427444458, "regret": 0.0016009814571589231, "entropy": 0.08303049951791763, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:13.001153Z", "loop": 12826, "env_steps": 7880908799, "loss": 0.013822968117892742, "avg_return": 0.8640719056129456, "regret": 0.0016009814571589231, "entropy": 0.0789022147655487, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:13.855354Z", "loop": 12827, "env_steps": 7881523199, "loss": 0.015199939720332623, "avg_return": 0.8623924851417542, "regret": 0.0016009814571589231, "entropy": 0.0784948542714119, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:14.710060Z", "loop": 12828, "env_steps": 7882137599, "loss": 0.013328242115676403, "avg_return": 0.863559365272522, "regret": 0.0016009814571589231, "entropy": 0.07478053122758865, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:15.564129Z", "loop": 12829, "env_steps": 7882751999, "loss": 0.015258769504725933, "avg_return": 0.8628456592559814, "regret": 0.0016009814571589231, "entropy": 0.0765729770064354, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:16.457185Z", "loop": 12830, "env_steps": 7883366399, "loss": 0.013681908138096333, "avg_return": 0.8636359572410583, "regret": 0.00011934951908187941, "entropy": 0.0715344101190567, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:17.310272Z", "loop": 12831, "env_steps": 7883980799, "loss": 0.013392691500484943, "avg_return": 0.8637202978134155, "regret": 0.00011934951908187941, "entropy": 0.07326840609312057, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:18.165312Z", "loop": 12832, "env_steps": 7884595199, "loss": 0.01381064485758543, "avg_return": 0.8639706373214722, "regret": 0.00011934951908187941, "entropy": 0.06987179815769196, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:19.018978Z", "loop": 12833, "env_steps": 7885209599, "loss": 0.013209179043769836, "avg_return": 0.86290043592453, "regret": 0.00011934951908187941, "entropy": 0.06797187030315399, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:19.872325Z", "loop": 12834, "env_steps": 7885823999, "loss": 0.013110915198922157, "avg_return": 0.8628076314926147, "regret": 0.00011934951908187941, "entropy": 0.07018500566482544, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:20.725822Z", "loop": 12835, "env_steps": 7886438399, "loss": 0.012723504565656185, "avg_return": 0.8649356365203857, "regret": 0.00011934951908187941, "entropy": 0.06723664700984955, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:21.580511Z", "loop": 12836, "env_steps": 7887052799, "loss": 0.011594041250646114, "avg_return": 0.8635455369949341, "regret": 0.00011934951908187941, "entropy": 0.059830278158187866, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:22.435586Z", "loop": 12837, "env_steps": 7887667199, "loss": 0.011488609947264194, "avg_return": 0.8617448210716248, "regret": 0.00011934951908187941, "entropy": 0.06330971419811249, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:23.289149Z", "loop": 12838, "env_steps": 7888281599, "loss": 0.012242673896253109, "avg_return": 0.8631296753883362, "regret": 0.00011934951908187941, "entropy": 0.06773658841848373, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:24.142472Z", "loop": 12839, "env_steps": 7888895999, "loss": 0.01126194093376398, "avg_return": 0.8638265132904053, "regret": 0.00011934951908187941, "entropy": 0.05948095768690109, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:25.035830Z", "loop": 12840, "env_steps": 7889510399, "loss": 0.010884751565754414, "avg_return": 0.8636231422424316, "regret": 0.00046156448661349714, "entropy": 0.059329498559236526, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:25.890024Z", "loop": 12841, "env_steps": 7890124799, "loss": 0.011305177584290504, "avg_return": 0.8627140522003174, "regret": 0.00046156448661349714, "entropy": 0.061808813363313675, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:26.744094Z", "loop": 12842, "env_steps": 7890739199, "loss": 0.011381958611309528, "avg_return": 0.8617567420005798, "regret": 0.00046156448661349714, "entropy": 0.06043417751789093, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:27.598932Z", "loop": 12843, "env_steps": 7891353599, "loss": 0.012889357283711433, "avg_return": 0.862004816532135, "regret": 0.00046156448661349714, "entropy": 0.06631135195493698, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:28.453168Z", "loop": 12844, "env_steps": 7891967999, "loss": 0.012499507516622543, "avg_return": 0.862223744392395, "regret": 0.00046156448661349714, "entropy": 0.06642769277095795, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:29.308350Z", "loop": 12845, "env_steps": 7892582399, "loss": 0.012545798905193806, "avg_return": 0.8618040084838867, "regret": 0.00046156448661349714, "entropy": 0.06631502509117126, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:30.162986Z", "loop": 12846, "env_steps": 7893196799, "loss": 0.01364475954324007, "avg_return": 0.8612102270126343, "regret": 0.00046156448661349714, "entropy": 0.07132028043270111, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:31.017046Z", "loop": 12847, "env_steps": 7893811199, "loss": 0.014739103615283966, "avg_return": 0.8606453537940979, "regret": 0.00046156448661349714, "entropy": 0.07190022617578506, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:31.870477Z", "loop": 12848, "env_steps": 7894425599, "loss": 0.013449281454086304, "avg_return": 0.8635884523391724, "regret": 0.00046156448661349714, "entropy": 0.07112257927656174, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:32.723900Z", "loop": 12849, "env_steps": 7895039999, "loss": 0.013455255888402462, "avg_return": 0.8608666062355042, "regret": 0.00046156448661349714, "entropy": 0.06629260629415512, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:33.616319Z", "loop": 12850, "env_steps": 7895654399, "loss": 0.012628057971596718, "avg_return": 0.8635031580924988, "regret": 0.0012131341500207782, "entropy": 0.067437082529068, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:34.470487Z", "loop": 12851, "env_steps": 7896268799, "loss": 0.012125537730753422, "avg_return": 0.8619480729103088, "regret": 0.0012131341500207782, "entropy": 0.06397027522325516, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:35.324773Z", "loop": 12852, "env_steps": 7896883199, "loss": 0.011756702326238155, "avg_return": 0.8637434840202332, "regret": 0.0012131341500207782, "entropy": 0.0633944422006607, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:36.178538Z", "loop": 12853, "env_steps": 7897497599, "loss": 0.012314784340560436, "avg_return": 0.8623514771461487, "regret": 0.0012131341500207782, "entropy": 0.0651199147105217, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:37.032255Z", "loop": 12854, "env_steps": 7898111999, "loss": 0.012048563919961452, "avg_return": 0.8615413904190063, "regret": 0.0012131341500207782, "entropy": 0.06637641787528992, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:37.887406Z", "loop": 12855, "env_steps": 7898726399, "loss": 0.011194265447556973, "avg_return": 0.8625852465629578, "regret": 0.0012131341500207782, "entropy": 0.06308706849813461, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:38.741170Z", "loop": 12856, "env_steps": 7899340799, "loss": 0.011484634131193161, "avg_return": 0.8633425235748291, "regret": 0.0012131341500207782, "entropy": 0.06541701406240463, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:39.594086Z", "loop": 12857, "env_steps": 7899955199, "loss": 0.011423756368458271, "avg_return": 0.8625870943069458, "regret": 0.0012131341500207782, "entropy": 0.06288952380418777, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:40.447669Z", "loop": 12858, "env_steps": 7900569599, "loss": 0.01281015109270811, "avg_return": 0.8637758493423462, "regret": 0.0012131341500207782, "entropy": 0.06843537092208862, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:41.301755Z", "loop": 12859, "env_steps": 7901183999, "loss": 0.010840139351785183, "avg_return": 0.8641964197158813, "regret": 0.0012131341500207782, "entropy": 0.06193414703011513, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:42.194673Z", "loop": 12860, "env_steps": 7901798399, "loss": 0.012096719816327095, "avg_return": 0.8643803000450134, "regret": 0.0007319874712266028, "entropy": 0.06870241463184357, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:43.048341Z", "loop": 12861, "env_steps": 7902412799, "loss": 0.010975094512104988, "avg_return": 0.8642280101776123, "regret": 0.0007319874712266028, "entropy": 0.06330179423093796, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:43.902162Z", "loop": 12862, "env_steps": 7903027199, "loss": 0.010954718105494976, "avg_return": 0.8621867299079895, "regret": 0.0007319874712266028, "entropy": 0.0622941330075264, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:44.756583Z", "loop": 12863, "env_steps": 7903641599, "loss": 0.01125703752040863, "avg_return": 0.8629323244094849, "regret": 0.0007319874712266028, "entropy": 0.06401748955249786, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:45.610700Z", "loop": 12864, "env_steps": 7904255999, "loss": 0.012806358747184277, "avg_return": 0.8635053634643555, "regret": 0.0007319874712266028, "entropy": 0.06695292145013809, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:46.465132Z", "loop": 12865, "env_steps": 7904870399, "loss": 0.011413929052650928, "avg_return": 0.8636724948883057, "regret": 0.0007319874712266028, "entropy": 0.06340564787387848, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:47.318420Z", "loop": 12866, "env_steps": 7905484799, "loss": 0.012557240203022957, "avg_return": 0.8624072670936584, "regret": 0.0007319874712266028, "entropy": 0.06770367920398712, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:48.172412Z", "loop": 12867, "env_steps": 7906099199, "loss": 0.012237059883773327, "avg_return": 0.8635461926460266, "regret": 0.0007319874712266028, "entropy": 0.06599245220422745, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:49.026278Z", "loop": 12868, "env_steps": 7906713599, "loss": 0.01227381732314825, "avg_return": 0.8627081513404846, "regret": 0.0007319874712266028, "entropy": 0.06789213418960571, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:49.879721Z", "loop": 12869, "env_steps": 7907327999, "loss": 0.012355916202068329, "avg_return": 0.8630021214485168, "regret": 0.0007319874712266028, "entropy": 0.06968233734369278, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:50.772274Z", "loop": 12870, "env_steps": 7907942399, "loss": 0.01230142917484045, "avg_return": 0.8629191517829895, "regret": 0.00039100373396649957, "entropy": 0.06487810611724854, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:51.627447Z", "loop": 12871, "env_steps": 7908556799, "loss": 0.01271725632250309, "avg_return": 0.8645672798156738, "regret": 0.00039100373396649957, "entropy": 0.06678704172372818, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:52.482165Z", "loop": 12872, "env_steps": 7909171199, "loss": 0.011668477207422256, "avg_return": 0.8633608222007751, "regret": 0.00039100373396649957, "entropy": 0.06671694666147232, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:53.336271Z", "loop": 12873, "env_steps": 7909785599, "loss": 0.011506847105920315, "avg_return": 0.8626821041107178, "regret": 0.00039100373396649957, "entropy": 0.06357374042272568, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:54.190544Z", "loop": 12874, "env_steps": 7910399999, "loss": 0.012681140564382076, "avg_return": 0.8641649484634399, "regret": 0.00039100373396649957, "entropy": 0.06833596527576447, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:55.044588Z", "loop": 12875, "env_steps": 7911014399, "loss": 0.012105880305171013, "avg_return": 0.8631837964057922, "regret": 0.00039100373396649957, "entropy": 0.06943251937627792, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:55.897798Z", "loop": 12876, "env_steps": 7911628799, "loss": 0.013420631177723408, "avg_return": 0.8636179566383362, "regret": 0.00039100373396649957, "entropy": 0.07308866083621979, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:56.752905Z", "loop": 12877, "env_steps": 7912243199, "loss": 0.013494282960891724, "avg_return": 0.8635441064834595, "regret": 0.00039100373396649957, "entropy": 0.07211499661207199, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:57.605919Z", "loop": 12878, "env_steps": 7912857599, "loss": 0.013797814026474953, "avg_return": 0.8631443381309509, "regret": 0.00039100373396649957, "entropy": 0.07111184298992157, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:58.460516Z", "loop": 12879, "env_steps": 7913471999, "loss": 0.013040147721767426, "avg_return": 0.8617826700210571, "regret": 0.00039100373396649957, "entropy": 0.06789755821228027, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:27:59.353840Z", "loop": 12880, "env_steps": 7914086399, "loss": 0.013136778958141804, "avg_return": 0.8635624647140503, "regret": 0.0001327733334619552, "entropy": 0.07389267534017563, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:00.208061Z", "loop": 12881, "env_steps": 7914700799, "loss": 0.012686477974057198, "avg_return": 0.8632149696350098, "regret": 0.0001327733334619552, "entropy": 0.06858944892883301, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:01.061772Z", "loop": 12882, "env_steps": 7915315199, "loss": 0.013157020322978497, "avg_return": 0.8637605905532837, "regret": 0.0001327733334619552, "entropy": 0.07407813519239426, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:01.917350Z", "loop": 12883, "env_steps": 7915929599, "loss": 0.014037610962986946, "avg_return": 0.8636928796768188, "regret": 0.0001327733334619552, "entropy": 0.0740518867969513, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:02.771095Z", "loop": 12884, "env_steps": 7916543999, "loss": 0.011730766855180264, "avg_return": 0.8635227680206299, "regret": 0.0001327733334619552, "entropy": 0.07060384005308151, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:03.624659Z", "loop": 12885, "env_steps": 7917158399, "loss": 0.012834453955292702, "avg_return": 0.8628449440002441, "regret": 0.0001327733334619552, "entropy": 0.06898397207260132, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:04.477655Z", "loop": 12886, "env_steps": 7917772799, "loss": 0.01409381628036499, "avg_return": 0.8631541132926941, "regret": 0.0001327733334619552, "entropy": 0.07228866964578629, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:05.331410Z", "loop": 12887, "env_steps": 7918387199, "loss": 0.013988146558403969, "avg_return": 0.8637951612472534, "regret": 0.0001327733334619552, "entropy": 0.0729922503232956, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:06.185650Z", "loop": 12888, "env_steps": 7919001599, "loss": 0.01340041495859623, "avg_return": 0.8635824918746948, "regret": 0.0001327733334619552, "entropy": 0.06889654695987701, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:07.040284Z", "loop": 12889, "env_steps": 7919615999, "loss": 0.013678460381925106, "avg_return": 0.863015353679657, "regret": 0.0001327733334619552, "entropy": 0.07317497581243515, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:07.935600Z", "loop": 12890, "env_steps": 7920230399, "loss": 0.013011748902499676, "avg_return": 0.8624974489212036, "regret": 0.0001469279668526724, "entropy": 0.07346903532743454, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:08.790039Z", "loop": 12891, "env_steps": 7920844799, "loss": 0.013094174675643444, "avg_return": 0.86329185962677, "regret": 0.0001469279668526724, "entropy": 0.06836681067943573, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:09.644578Z", "loop": 12892, "env_steps": 7921459199, "loss": 0.014010131359100342, "avg_return": 0.8641738891601562, "regret": 0.0001469279668526724, "entropy": 0.07039743661880493, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:10.497597Z", "loop": 12893, "env_steps": 7922073599, "loss": 0.011427203193306923, "avg_return": 0.8629528880119324, "regret": 0.0001469279668526724, "entropy": 0.0660371407866478, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:11.351397Z", "loop": 12894, "env_steps": 7922687999, "loss": 0.0124218063428998, "avg_return": 0.863390326499939, "regret": 0.0001469279668526724, "entropy": 0.06742794811725616, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:12.206273Z", "loop": 12895, "env_steps": 7923302399, "loss": 0.01310883928090334, "avg_return": 0.8624117374420166, "regret": 0.0001469279668526724, "entropy": 0.06954371929168701, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:13.060118Z", "loop": 12896, "env_steps": 7923916799, "loss": 0.012554769404232502, "avg_return": 0.8635424971580505, "regret": 0.0001469279668526724, "entropy": 0.06536266207695007, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:13.914053Z", "loop": 12897, "env_steps": 7924531199, "loss": 0.012866764329373837, "avg_return": 0.8626084327697754, "regret": 0.0001469279668526724, "entropy": 0.06741636991500854, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:14.769181Z", "loop": 12898, "env_steps": 7925145599, "loss": 0.012940692715346813, "avg_return": 0.8634961247444153, "regret": 0.0001469279668526724, "entropy": 0.06757334619760513, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:15.624687Z", "loop": 12899, "env_steps": 7925759999, "loss": 0.012324552051723003, "avg_return": 0.8640134930610657, "regret": 0.0001469279668526724, "entropy": 0.06620784103870392, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:16.518764Z", "loop": 12900, "env_steps": 7926374399, "loss": 0.011885478161275387, "avg_return": 0.8631834983825684, "regret": 0.00025203695986419916, "entropy": 0.06407450884580612, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:17.374620Z", "loop": 12901, "env_steps": 7926988799, "loss": 0.01191022153943777, "avg_return": 0.8635730147361755, "regret": 0.00025203695986419916, "entropy": 0.06395947188138962, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:18.230511Z", "loop": 12902, "env_steps": 7927603199, "loss": 0.01263090968132019, "avg_return": 0.8629434704780579, "regret": 0.00025203695986419916, "entropy": 0.06575889885425568, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:19.085364Z", "loop": 12903, "env_steps": 7928217599, "loss": 0.012051297351717949, "avg_return": 0.8634521961212158, "regret": 0.00025203695986419916, "entropy": 0.0663272961974144, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:19.941300Z", "loop": 12904, "env_steps": 7928831999, "loss": 0.012008333578705788, "avg_return": 0.8631218671798706, "regret": 0.00025203695986419916, "entropy": 0.06778262555599213, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:20.795732Z", "loop": 12905, "env_steps": 7929446399, "loss": 0.011870356276631355, "avg_return": 0.8639568090438843, "regret": 0.00025203695986419916, "entropy": 0.06601349264383316, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:21.649968Z", "loop": 12906, "env_steps": 7930060799, "loss": 0.012169591151177883, "avg_return": 0.8615018725395203, "regret": 0.00025203695986419916, "entropy": 0.0650121346116066, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:22.503657Z", "loop": 12907, "env_steps": 7930675199, "loss": 0.012121183797717094, "avg_return": 0.8622942566871643, "regret": 0.00025203695986419916, "entropy": 0.06667210906744003, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:23.357421Z", "loop": 12908, "env_steps": 7931289599, "loss": 0.012676593847572803, "avg_return": 0.8630606532096863, "regret": 0.00025203695986419916, "entropy": 0.06769862771034241, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:24.211931Z", "loop": 12909, "env_steps": 7931903999, "loss": 0.013117814436554909, "avg_return": 0.8635056018829346, "regret": 0.00025203695986419916, "entropy": 0.06872934848070145, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:25.104914Z", "loop": 12910, "env_steps": 7932518399, "loss": 0.012861295603215694, "avg_return": 0.8626265525817871, "regret": 0.00043179470230825245, "entropy": 0.06706724315881729, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:25.959484Z", "loop": 12911, "env_steps": 7933132799, "loss": 0.013112579472362995, "avg_return": 0.8632009029388428, "regret": 0.00043179470230825245, "entropy": 0.0661982074379921, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:26.814097Z", "loop": 12912, "env_steps": 7933747199, "loss": 0.011906864121556282, "avg_return": 0.8629689812660217, "regret": 0.00043179470230825245, "entropy": 0.06639350950717926, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:27.668791Z", "loop": 12913, "env_steps": 7934361599, "loss": 0.012077052146196365, "avg_return": 0.8623131513595581, "regret": 0.00043179470230825245, "entropy": 0.06510557979345322, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:28.525237Z", "loop": 12914, "env_steps": 7934975999, "loss": 0.011639303527772427, "avg_return": 0.8622224926948547, "regret": 0.00043179470230825245, "entropy": 0.06612513959407806, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:29.380206Z", "loop": 12915, "env_steps": 7935590399, "loss": 0.011810198426246643, "avg_return": 0.861394464969635, "regret": 0.00043179470230825245, "entropy": 0.06826143711805344, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:30.233280Z", "loop": 12916, "env_steps": 7936204799, "loss": 0.012480662204325199, "avg_return": 0.8619804978370667, "regret": 0.00043179470230825245, "entropy": 0.0679350197315216, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:31.086670Z", "loop": 12917, "env_steps": 7936819199, "loss": 0.013255687430500984, "avg_return": 0.8617041110992432, "regret": 0.00043179470230825245, "entropy": 0.07197830080986023, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:31.941626Z", "loop": 12918, "env_steps": 7937433599, "loss": 0.01264999806880951, "avg_return": 0.8625050783157349, "regret": 0.00043179470230825245, "entropy": 0.06930731236934662, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:32.795683Z", "loop": 12919, "env_steps": 7938047999, "loss": 0.012881468050181866, "avg_return": 0.8614526391029358, "regret": 0.00043179470230825245, "entropy": 0.06989575922489166, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:33.690233Z", "loop": 12920, "env_steps": 7938662399, "loss": 0.012472396716475487, "avg_return": 0.862322211265564, "regret": 0.001539092161692679, "entropy": 0.0658765584230423, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:34.544553Z", "loop": 12921, "env_steps": 7939276799, "loss": 0.0126988859847188, "avg_return": 0.8618190884590149, "regret": 0.001539092161692679, "entropy": 0.06779249757528305, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:35.399905Z", "loop": 12922, "env_steps": 7939891199, "loss": 0.012631668709218502, "avg_return": 0.8611536622047424, "regret": 0.001539092161692679, "entropy": 0.06856964528560638, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:36.254986Z", "loop": 12923, "env_steps": 7940505599, "loss": 0.012956543825566769, "avg_return": 0.862450361251831, "regret": 0.001539092161692679, "entropy": 0.06764686107635498, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:37.110685Z", "loop": 12924, "env_steps": 7941119999, "loss": 0.01290105190128088, "avg_return": 0.862123966217041, "regret": 0.001539092161692679, "entropy": 0.0711386576294899, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:37.964827Z", "loop": 12925, "env_steps": 7941734399, "loss": 0.013553704135119915, "avg_return": 0.8617865443229675, "regret": 0.001539092161692679, "entropy": 0.07457529753446579, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:38.819227Z", "loop": 12926, "env_steps": 7942348799, "loss": 0.012502196244895458, "avg_return": 0.8619734644889832, "regret": 0.001539092161692679, "entropy": 0.07167278975248337, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:39.674294Z", "loop": 12927, "env_steps": 7942963199, "loss": 0.011942153796553612, "avg_return": 0.8623926043510437, "regret": 0.001539092161692679, "entropy": 0.06715583056211472, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:40.528467Z", "loop": 12928, "env_steps": 7943577599, "loss": 0.012800968252122402, "avg_return": 0.8623773455619812, "regret": 0.001539092161692679, "entropy": 0.07075463980436325, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:41.382009Z", "loop": 12929, "env_steps": 7944191999, "loss": 0.01357299368828535, "avg_return": 0.8633484840393066, "regret": 0.001539092161692679, "entropy": 0.06952212750911713, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:42.275045Z", "loop": 12930, "env_steps": 7944806399, "loss": 0.012178110890090466, "avg_return": 0.8620655536651611, "regret": 0.0010428924579173326, "entropy": 0.06806858628988266, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:43.129321Z", "loop": 12931, "env_steps": 7945420799, "loss": 0.012264668941497803, "avg_return": 0.8611981272697449, "regret": 0.0010428924579173326, "entropy": 0.06636370718479156, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:43.983587Z", "loop": 12932, "env_steps": 7946035199, "loss": 0.012111930176615715, "avg_return": 0.862056314945221, "regret": 0.0010428924579173326, "entropy": 0.06129174679517746, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:44.840178Z", "loop": 12933, "env_steps": 7946649599, "loss": 0.012409090995788574, "avg_return": 0.8618241548538208, "regret": 0.0010428924579173326, "entropy": 0.06685297191143036, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:45.695293Z", "loop": 12934, "env_steps": 7947263999, "loss": 0.012137067504227161, "avg_return": 0.8619685173034668, "regret": 0.0010428924579173326, "entropy": 0.06543675810098648, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:46.549300Z", "loop": 12935, "env_steps": 7947878399, "loss": 0.01260008942335844, "avg_return": 0.8614715933799744, "regret": 0.0010428924579173326, "entropy": 0.06884370744228363, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:47.403852Z", "loop": 12936, "env_steps": 7948492799, "loss": 0.011702983640134335, "avg_return": 0.861996054649353, "regret": 0.0010428924579173326, "entropy": 0.06543461978435516, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:48.258842Z", "loop": 12937, "env_steps": 7949107199, "loss": 0.012823300436139107, "avg_return": 0.8621100187301636, "regret": 0.0010428924579173326, "entropy": 0.07025394588708878, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:49.111959Z", "loop": 12938, "env_steps": 7949721599, "loss": 0.012925967574119568, "avg_return": 0.8621463179588318, "regret": 0.0010428924579173326, "entropy": 0.06670869886875153, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:49.964664Z", "loop": 12939, "env_steps": 7950335999, "loss": 0.0123700937256217, "avg_return": 0.8625273704528809, "regret": 0.0010428924579173326, "entropy": 0.06719203293323517, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:50.856140Z", "loop": 12940, "env_steps": 7950950399, "loss": 0.012030656449496746, "avg_return": 0.8627873063087463, "regret": 0.000561489025130868, "entropy": 0.06531000137329102, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:51.710331Z", "loop": 12941, "env_steps": 7951564799, "loss": 0.013438872992992401, "avg_return": 0.8626143336296082, "regret": 0.000561489025130868, "entropy": 0.0710538923740387, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:52.564342Z", "loop": 12942, "env_steps": 7952179199, "loss": 0.012208445928990841, "avg_return": 0.863684892654419, "regret": 0.000561489025130868, "entropy": 0.06439857929944992, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:53.418025Z", "loop": 12943, "env_steps": 7952793599, "loss": 0.013507342897355556, "avg_return": 0.8634739518165588, "regret": 0.000561489025130868, "entropy": 0.06599748134613037, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:54.271294Z", "loop": 12944, "env_steps": 7953407999, "loss": 0.012536938302218914, "avg_return": 0.8629236221313477, "regret": 0.000561489025130868, "entropy": 0.06661637127399445, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:55.126069Z", "loop": 12945, "env_steps": 7954022399, "loss": 0.012374614365398884, "avg_return": 0.8633356094360352, "regret": 0.000561489025130868, "entropy": 0.06548881530761719, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:55.979654Z", "loop": 12946, "env_steps": 7954636799, "loss": 0.012265232391655445, "avg_return": 0.8627153635025024, "regret": 0.000561489025130868, "entropy": 0.0646425187587738, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:56.833110Z", "loop": 12947, "env_steps": 7955251199, "loss": 0.01370704174041748, "avg_return": 0.8638953566551208, "regret": 0.000561489025130868, "entropy": 0.06814850866794586, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:57.687184Z", "loop": 12948, "env_steps": 7955865599, "loss": 0.01376411784440279, "avg_return": 0.8630713224411011, "regret": 0.000561489025130868, "entropy": 0.07143040001392365, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:58.542830Z", "loop": 12949, "env_steps": 7956479999, "loss": 0.012913229875266552, "avg_return": 0.8641970753669739, "regret": 0.000561489025130868, "entropy": 0.06944678723812103, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:28:59.436047Z", "loop": 12950, "env_steps": 7957094399, "loss": 0.012843357399106026, "avg_return": 0.8625283241271973, "regret": 0.00020004833640996367, "entropy": 0.06924082338809967, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:00.291199Z", "loop": 12951, "env_steps": 7957708799, "loss": 0.01376021932810545, "avg_return": 0.862592875957489, "regret": 0.00020004833640996367, "entropy": 0.07044969499111176, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:01.145265Z", "loop": 12952, "env_steps": 7958323199, "loss": 0.014104706235229969, "avg_return": 0.862833559513092, "regret": 0.00020004833640996367, "entropy": 0.0703611671924591, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:02.000362Z", "loop": 12953, "env_steps": 7958937599, "loss": 0.01379135251045227, "avg_return": 0.8628352880477905, "regret": 0.00020004833640996367, "entropy": 0.07104811817407608, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:02.853828Z", "loop": 12954, "env_steps": 7959551999, "loss": 0.01339874416589737, "avg_return": 0.8630837202072144, "regret": 0.00020004833640996367, "entropy": 0.07281521707773209, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:03.707363Z", "loop": 12955, "env_steps": 7960166399, "loss": 0.013834582641720772, "avg_return": 0.8632481098175049, "regret": 0.00020004833640996367, "entropy": 0.0746355801820755, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:04.561994Z", "loop": 12956, "env_steps": 7960780799, "loss": 0.012442238628864288, "avg_return": 0.862605631351471, "regret": 0.00020004833640996367, "entropy": 0.06649471074342728, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:05.417441Z", "loop": 12957, "env_steps": 7961395199, "loss": 0.013617075979709625, "avg_return": 0.863335907459259, "regret": 0.00020004833640996367, "entropy": 0.07099300622940063, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:06.271981Z", "loop": 12958, "env_steps": 7962009599, "loss": 0.013721711933612823, "avg_return": 0.8626658320426941, "regret": 0.00020004833640996367, "entropy": 0.07196692377328873, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:07.125580Z", "loop": 12959, "env_steps": 7962623999, "loss": 0.015175210312008858, "avg_return": 0.8633508682250977, "regret": 0.00020004833640996367, "entropy": 0.07856013625860214, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:08.019098Z", "loop": 12960, "env_steps": 7963238399, "loss": 0.01418510265648365, "avg_return": 0.8626839518547058, "regret": 0.00017812903388403356, "entropy": 0.07464202493429184, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:08.873745Z", "loop": 12961, "env_steps": 7963852799, "loss": 0.013397458009421825, "avg_return": 0.8641483783721924, "regret": 0.00017812903388403356, "entropy": 0.0751492902636528, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:09.727380Z", "loop": 12962, "env_steps": 7964467199, "loss": 0.012888153083622456, "avg_return": 0.8643066883087158, "regret": 0.00017812903388403356, "entropy": 0.07036934792995453, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:10.581753Z", "loop": 12963, "env_steps": 7965081599, "loss": 0.014502703212201595, "avg_return": 0.8634154200553894, "regret": 0.00017812903388403356, "entropy": 0.07557181268930435, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:11.436619Z", "loop": 12964, "env_steps": 7965695999, "loss": 0.013841590844094753, "avg_return": 0.8628584742546082, "regret": 0.00017812903388403356, "entropy": 0.07229122519493103, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:12.290131Z", "loop": 12965, "env_steps": 7966310399, "loss": 0.014796027913689613, "avg_return": 0.8631299138069153, "regret": 0.00017812903388403356, "entropy": 0.07773706316947937, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:13.144579Z", "loop": 12966, "env_steps": 7966924799, "loss": 0.0135306715965271, "avg_return": 0.8637142181396484, "regret": 0.00017812903388403356, "entropy": 0.07321412861347198, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:13.999149Z", "loop": 12967, "env_steps": 7967539199, "loss": 0.014552034437656403, "avg_return": 0.8625308275222778, "regret": 0.00017812903388403356, "entropy": 0.07821474224328995, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:14.853987Z", "loop": 12968, "env_steps": 7968153599, "loss": 0.014573807828128338, "avg_return": 0.8641031384468079, "regret": 0.00017812903388403356, "entropy": 0.07674982398748398, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:15.708429Z", "loop": 12969, "env_steps": 7968767999, "loss": 0.014592300169169903, "avg_return": 0.8620741963386536, "regret": 0.00017812903388403356, "entropy": 0.07521829009056091, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:16.600198Z", "loop": 12970, "env_steps": 7969382399, "loss": 0.014174905605614185, "avg_return": 0.8629976511001587, "regret": 0.0008138825069181621, "entropy": 0.07532542943954468, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:17.453534Z", "loop": 12971, "env_steps": 7969996799, "loss": 0.014196167699992657, "avg_return": 0.8627645969390869, "regret": 0.0008138825069181621, "entropy": 0.07672925293445587, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:18.308248Z", "loop": 12972, "env_steps": 7970611199, "loss": 0.014841864816844463, "avg_return": 0.8642964959144592, "regret": 0.0008138825069181621, "entropy": 0.07697929441928864, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:19.163341Z", "loop": 12973, "env_steps": 7971225599, "loss": 0.014361551962792873, "avg_return": 0.8622862696647644, "regret": 0.0008138825069181621, "entropy": 0.07760631293058395, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:20.017033Z", "loop": 12974, "env_steps": 7971839999, "loss": 0.01574189029633999, "avg_return": 0.8612663149833679, "regret": 0.0008138825069181621, "entropy": 0.08504766970872879, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:20.871000Z", "loop": 12975, "env_steps": 7972454399, "loss": 0.0161302350461483, "avg_return": 0.8609100580215454, "regret": 0.0008138825069181621, "entropy": 0.08314713090658188, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:21.724876Z", "loop": 12976, "env_steps": 7973068799, "loss": 0.01619148813188076, "avg_return": 0.8601420521736145, "regret": 0.0008138825069181621, "entropy": 0.08473791182041168, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:22.578070Z", "loop": 12977, "env_steps": 7973683199, "loss": 0.016915928572416306, "avg_return": 0.8617760539054871, "regret": 0.0008138825069181621, "entropy": 0.08462701737880707, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:23.432531Z", "loop": 12978, "env_steps": 7974297599, "loss": 0.017871521413326263, "avg_return": 0.8605878949165344, "regret": 0.0008138825069181621, "entropy": 0.09059061110019684, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:24.285889Z", "loop": 12979, "env_steps": 7974911999, "loss": 0.017908042296767235, "avg_return": 0.8616632223129272, "regret": 0.0008138825069181621, "entropy": 0.0917554572224617, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:25.179937Z", "loop": 12980, "env_steps": 7975526399, "loss": 0.01800118386745453, "avg_return": 0.861886203289032, "regret": 0.001768638612702489, "entropy": 0.09479127079248428, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:26.033661Z", "loop": 12981, "env_steps": 7976140799, "loss": 0.017673486843705177, "avg_return": 0.8612699508666992, "regret": 0.001768638612702489, "entropy": 0.09143270552158356, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:26.888021Z", "loop": 12982, "env_steps": 7976755199, "loss": 0.016889553517103195, "avg_return": 0.8616581559181213, "regret": 0.001768638612702489, "entropy": 0.08720189332962036, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:27.741768Z", "loop": 12983, "env_steps": 7977369599, "loss": 0.01785070262849331, "avg_return": 0.8616765737533569, "regret": 0.001768638612702489, "entropy": 0.08762501180171967, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:28.595600Z", "loop": 12984, "env_steps": 7977983999, "loss": 0.018761809915304184, "avg_return": 0.8616686463356018, "regret": 0.001768638612702489, "entropy": 0.09353534877300262, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:29.449034Z", "loop": 12985, "env_steps": 7978598399, "loss": 0.0193514171987772, "avg_return": 0.8605405688285828, "regret": 0.001768638612702489, "entropy": 0.09571202099323273, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:30.303108Z", "loop": 12986, "env_steps": 7979212799, "loss": 0.020422345027327538, "avg_return": 0.8612275123596191, "regret": 0.001768638612702489, "entropy": 0.09963983297348022, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:31.156336Z", "loop": 12987, "env_steps": 7979827199, "loss": 0.0199431162327528, "avg_return": 0.8616229295730591, "regret": 0.001768638612702489, "entropy": 0.10149460285902023, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:32.010080Z", "loop": 12988, "env_steps": 7980441599, "loss": 0.019898584112524986, "avg_return": 0.8614805340766907, "regret": 0.001768638612702489, "entropy": 0.09798173606395721, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:32.864550Z", "loop": 12989, "env_steps": 7981055999, "loss": 0.020660795271396637, "avg_return": 0.8618004322052002, "regret": 0.001768638612702489, "entropy": 0.10376549512147903, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:33.757162Z", "loop": 12990, "env_steps": 7981670399, "loss": 0.020442260429263115, "avg_return": 0.8603830337524414, "regret": 0.0033027376048266888, "entropy": 0.10120643675327301, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:34.610286Z", "loop": 12991, "env_steps": 7982284799, "loss": 0.0207469891756773, "avg_return": 0.8604316115379333, "regret": 0.0033027376048266888, "entropy": 0.1020088717341423, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:35.464654Z", "loop": 12992, "env_steps": 7982899199, "loss": 0.019310249015688896, "avg_return": 0.8601058125495911, "regret": 0.0033027376048266888, "entropy": 0.09375729411840439, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:36.317825Z", "loop": 12993, "env_steps": 7983513599, "loss": 0.018399929627776146, "avg_return": 0.860496461391449, "regret": 0.0033027376048266888, "entropy": 0.0940951406955719, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:37.171861Z", "loop": 12994, "env_steps": 7984127999, "loss": 0.019316961988806725, "avg_return": 0.8611187934875488, "regret": 0.0033027376048266888, "entropy": 0.09228851646184921, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:38.026483Z", "loop": 12995, "env_steps": 7984742399, "loss": 0.016354357823729515, "avg_return": 0.8615431785583496, "regret": 0.0033027376048266888, "entropy": 0.0867517739534378, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:38.881771Z", "loop": 12996, "env_steps": 7985356799, "loss": 0.01787039078772068, "avg_return": 0.8633310198783875, "regret": 0.0033027376048266888, "entropy": 0.09158714860677719, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:39.735655Z", "loop": 12997, "env_steps": 7985971199, "loss": 0.02086169831454754, "avg_return": 0.8631696701049805, "regret": 0.0033027376048266888, "entropy": 0.09878059476613998, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:40.589286Z", "loop": 12998, "env_steps": 7986585599, "loss": 0.020345231518149376, "avg_return": 0.863574743270874, "regret": 0.0033027376048266888, "entropy": 0.09762521088123322, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:41.444251Z", "loop": 12999, "env_steps": 7987199999, "loss": 0.020053643733263016, "avg_return": 0.8630542159080505, "regret": 0.0033027376048266888, "entropy": 0.10174098610877991, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:42.337319Z", "loop": 13000, "env_steps": 7987814399, "loss": 0.018221890553832054, "avg_return": 0.8631104826927185, "regret": 0.0005749235861003399, "entropy": 0.09299129247665405, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:43.191220Z", "loop": 13001, "env_steps": 7988428799, "loss": 0.017985887825489044, "avg_return": 0.8614748120307922, "regret": 0.0005749235861003399, "entropy": 0.09049935638904572, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:44.044283Z", "loop": 13002, "env_steps": 7989043199, "loss": 0.016712883487343788, "avg_return": 0.8633008003234863, "regret": 0.0005749235861003399, "entropy": 0.08376780152320862, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:44.897726Z", "loop": 13003, "env_steps": 7989657599, "loss": 0.01625184901058674, "avg_return": 0.8626354336738586, "regret": 0.0005749235861003399, "entropy": 0.0825163722038269, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:45.752639Z", "loop": 13004, "env_steps": 7990271999, "loss": 0.015623765997588634, "avg_return": 0.8641542792320251, "regret": 0.0005749235861003399, "entropy": 0.07857947796583176, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:46.606750Z", "loop": 13005, "env_steps": 7990886399, "loss": 0.01663942262530327, "avg_return": 0.8628859519958496, "regret": 0.0005749235861003399, "entropy": 0.08152154833078384, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:47.460141Z", "loop": 13006, "env_steps": 7991500799, "loss": 0.015527704730629921, "avg_return": 0.8625535368919373, "regret": 0.0005749235861003399, "entropy": 0.08234313130378723, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:48.314490Z", "loop": 13007, "env_steps": 7992115199, "loss": 0.01501407753676176, "avg_return": 0.8617289662361145, "regret": 0.0005749235861003399, "entropy": 0.07557439059019089, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:49.169461Z", "loop": 13008, "env_steps": 7992729599, "loss": 0.013565326109528542, "avg_return": 0.8629270792007446, "regret": 0.0005749235861003399, "entropy": 0.07236331701278687, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:50.024622Z", "loop": 13009, "env_steps": 7993343999, "loss": 0.015048371627926826, "avg_return": 0.8632309436798096, "regret": 0.0005749235861003399, "entropy": 0.08000126481056213, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:50.918143Z", "loop": 13010, "env_steps": 7993958399, "loss": 0.014125448651611805, "avg_return": 0.8623303174972534, "regret": 0.0006010804791003466, "entropy": 0.07396191358566284, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:51.772160Z", "loop": 13011, "env_steps": 7994572799, "loss": 0.013837357051670551, "avg_return": 0.8629984855651855, "regret": 0.0006010804791003466, "entropy": 0.07161425799131393, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:52.627129Z", "loop": 13012, "env_steps": 7995187199, "loss": 0.013461406342685223, "avg_return": 0.8633818030357361, "regret": 0.0006010804791003466, "entropy": 0.07287684082984924, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:53.480900Z", "loop": 13013, "env_steps": 7995801599, "loss": 0.013468350283801556, "avg_return": 0.8618369698524475, "regret": 0.0006010804791003466, "entropy": 0.06940581649541855, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:54.334207Z", "loop": 13014, "env_steps": 7996415999, "loss": 0.014009100385010242, "avg_return": 0.8628189563751221, "regret": 0.0006010804791003466, "entropy": 0.07180367410182953, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:55.188270Z", "loop": 13015, "env_steps": 7997030399, "loss": 0.013650894165039062, "avg_return": 0.8635115623474121, "regret": 0.0006010804791003466, "entropy": 0.06878188997507095, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:56.044275Z", "loop": 13016, "env_steps": 7997644799, "loss": 0.013014324009418488, "avg_return": 0.8624012470245361, "regret": 0.0006010804791003466, "entropy": 0.0674666091799736, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:56.898479Z", "loop": 13017, "env_steps": 7998259199, "loss": 0.01343678217381239, "avg_return": 0.8630041480064392, "regret": 0.0006010804791003466, "entropy": 0.06699471920728683, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:57.751913Z", "loop": 13018, "env_steps": 7998873599, "loss": 0.013019347563385963, "avg_return": 0.8630214929580688, "regret": 0.0006010804791003466, "entropy": 0.0671299621462822, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:58.605760Z", "loop": 13019, "env_steps": 7999487999, "loss": 0.011829448863863945, "avg_return": 0.8647288084030151, "regret": 0.0006010804791003466, "entropy": 0.06229596585035324, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:29:59.499609Z", "loop": 13020, "env_steps": 8000102399, "loss": 0.012754044495522976, "avg_return": 0.8613480925559998, "regret": 0.0006355019868351519, "entropy": 0.06650998443365097, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:00.353463Z", "loop": 13021, "env_steps": 8000716799, "loss": 0.01197344996035099, "avg_return": 0.8621565699577332, "regret": 0.0006355019868351519, "entropy": 0.06411439925432205, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:01.209200Z", "loop": 13022, "env_steps": 8001331199, "loss": 0.013077087700366974, "avg_return": 0.8622273802757263, "regret": 0.0006355019868351519, "entropy": 0.06551655381917953, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:02.064476Z", "loop": 13023, "env_steps": 8001945599, "loss": 0.011397692374885082, "avg_return": 0.8620399236679077, "regret": 0.0006355019868351519, "entropy": 0.059748049825429916, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:02.918724Z", "loop": 13024, "env_steps": 8002559999, "loss": 0.012476409785449505, "avg_return": 0.8624333739280701, "regret": 0.0006355019868351519, "entropy": 0.0658222958445549, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:03.772702Z", "loop": 13025, "env_steps": 8003174399, "loss": 0.011843199841678143, "avg_return": 0.8626786470413208, "regret": 0.0006355019868351519, "entropy": 0.06254757195711136, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:04.627361Z", "loop": 13026, "env_steps": 8003788799, "loss": 0.011629126034677029, "avg_return": 0.8630428314208984, "regret": 0.0006355019868351519, "entropy": 0.06333824247121811, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:05.481969Z", "loop": 13027, "env_steps": 8004403199, "loss": 0.011530933901667595, "avg_return": 0.862537682056427, "regret": 0.0006355019868351519, "entropy": 0.0655675157904625, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:06.336706Z", "loop": 13028, "env_steps": 8005017599, "loss": 0.010852663777768612, "avg_return": 0.8613649606704712, "regret": 0.0006355019868351519, "entropy": 0.06233321875333786, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:07.190466Z", "loop": 13029, "env_steps": 8005631999, "loss": 0.011963619850575924, "avg_return": 0.8629152774810791, "regret": 0.0006355019868351519, "entropy": 0.06355255842208862, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:08.083261Z", "loop": 13030, "env_steps": 8006246399, "loss": 0.011768379248678684, "avg_return": 0.8629285097122192, "regret": 0.0015934903640300035, "entropy": 0.06415560096502304, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:08.937334Z", "loop": 13031, "env_steps": 8006860799, "loss": 0.012303530238568783, "avg_return": 0.8623703122138977, "regret": 0.0015934903640300035, "entropy": 0.06741327792406082, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:09.792631Z", "loop": 13032, "env_steps": 8007475199, "loss": 0.012296888045966625, "avg_return": 0.861184298992157, "regret": 0.0015934903640300035, "entropy": 0.06462202221155167, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:10.646225Z", "loop": 13033, "env_steps": 8008089599, "loss": 0.012751131318509579, "avg_return": 0.8632115721702576, "regret": 0.0015934903640300035, "entropy": 0.06722040474414825, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:11.499604Z", "loop": 13034, "env_steps": 8008703999, "loss": 0.012915684841573238, "avg_return": 0.8622317910194397, "regret": 0.0015934903640300035, "entropy": 0.06427431106567383, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:12.353820Z", "loop": 13035, "env_steps": 8009318399, "loss": 0.011605157516896725, "avg_return": 0.8627691864967346, "regret": 0.0015934903640300035, "entropy": 0.06181156635284424, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:13.208324Z", "loop": 13036, "env_steps": 8009932799, "loss": 0.012160827405750751, "avg_return": 0.8612695336341858, "regret": 0.0015934903640300035, "entropy": 0.06547558307647705, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:14.063206Z", "loop": 13037, "env_steps": 8010547199, "loss": 0.012059229426085949, "avg_return": 0.8631997108459473, "regret": 0.0015934903640300035, "entropy": 0.0644298642873764, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:14.916988Z", "loop": 13038, "env_steps": 8011161599, "loss": 0.012340324930846691, "avg_return": 0.8628020286560059, "regret": 0.0015934903640300035, "entropy": 0.06582440435886383, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:15.771115Z", "loop": 13039, "env_steps": 8011775999, "loss": 0.011448669247329235, "avg_return": 0.8603051900863647, "regret": 0.0015934903640300035, "entropy": 0.06711625307798386, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:16.665218Z", "loop": 13040, "env_steps": 8012390399, "loss": 0.012558718211948872, "avg_return": 0.8601987957954407, "regret": 0.0033389285672456026, "entropy": 0.07235640287399292, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:17.519169Z", "loop": 13041, "env_steps": 8013004799, "loss": 0.013446370139718056, "avg_return": 0.8599114418029785, "regret": 0.0033389285672456026, "entropy": 0.07348349690437317, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:18.373751Z", "loop": 13042, "env_steps": 8013619199, "loss": 0.014662514440715313, "avg_return": 0.859897255897522, "regret": 0.0033389285672456026, "entropy": 0.07604271173477173, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:19.228104Z", "loop": 13043, "env_steps": 8014233599, "loss": 0.013685178942978382, "avg_return": 0.859637975692749, "regret": 0.0033389285672456026, "entropy": 0.07543965429067612, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:20.082545Z", "loop": 13044, "env_steps": 8014847999, "loss": 0.013777310028672218, "avg_return": 0.8595510125160217, "regret": 0.0033389285672456026, "entropy": 0.07465723901987076, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:20.937245Z", "loop": 13045, "env_steps": 8015462399, "loss": 0.01395245362073183, "avg_return": 0.8610907196998596, "regret": 0.0033389285672456026, "entropy": 0.07324626296758652, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:21.791811Z", "loop": 13046, "env_steps": 8016076799, "loss": 0.012876736931502819, "avg_return": 0.8601226806640625, "regret": 0.0033389285672456026, "entropy": 0.06683458387851715, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:22.644760Z", "loop": 13047, "env_steps": 8016691199, "loss": 0.010714643634855747, "avg_return": 0.8608484268188477, "regret": 0.0033389285672456026, "entropy": 0.06083725765347481, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:23.497707Z", "loop": 13048, "env_steps": 8017305599, "loss": 0.01229033898562193, "avg_return": 0.8630039691925049, "regret": 0.0033389285672456026, "entropy": 0.06539972871541977, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:24.351594Z", "loop": 13049, "env_steps": 8017919999, "loss": 0.01155147422105074, "avg_return": 0.8628506660461426, "regret": 0.0033389285672456026, "entropy": 0.05935990810394287, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:25.245015Z", "loop": 13050, "env_steps": 8018534399, "loss": 0.011065621860325336, "avg_return": 0.8627169132232666, "regret": 0.0010844981297850609, "entropy": 0.059055883437395096, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:26.098556Z", "loop": 13051, "env_steps": 8019148799, "loss": 0.011597727425396442, "avg_return": 0.8631800413131714, "regret": 0.0010844981297850609, "entropy": 0.06102168932557106, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:26.952131Z", "loop": 13052, "env_steps": 8019763199, "loss": 0.011209587566554546, "avg_return": 0.8651033639907837, "regret": 0.0010844981297850609, "entropy": 0.05788436904549599, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:27.804873Z", "loop": 13053, "env_steps": 8020377599, "loss": 0.01160441804677248, "avg_return": 0.8639307618141174, "regret": 0.0010844981297850609, "entropy": 0.05905691161751747, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:28.659494Z", "loop": 13054, "env_steps": 8020991999, "loss": 0.01149259228259325, "avg_return": 0.8628185987472534, "regret": 0.0010844981297850609, "entropy": 0.05945519730448723, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:29.513257Z", "loop": 13055, "env_steps": 8021606399, "loss": 0.010642114095389843, "avg_return": 0.8636684417724609, "regret": 0.0010844981297850609, "entropy": 0.05695018172264099, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:30.366560Z", "loop": 13056, "env_steps": 8022220799, "loss": 0.010886693373322487, "avg_return": 0.8640167713165283, "regret": 0.0010844981297850609, "entropy": 0.05750850960612297, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:31.219843Z", "loop": 13057, "env_steps": 8022835199, "loss": 0.012197875417768955, "avg_return": 0.8617293238639832, "regret": 0.0010844981297850609, "entropy": 0.06146058440208435, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:32.074581Z", "loop": 13058, "env_steps": 8023449599, "loss": 0.01157293003052473, "avg_return": 0.8637357950210571, "regret": 0.0010844981297850609, "entropy": 0.061143908649683, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:32.928945Z", "loop": 13059, "env_steps": 8024063999, "loss": 0.01111097726970911, "avg_return": 0.8625712394714355, "regret": 0.0010844981297850609, "entropy": 0.061940018087625504, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:33.819298Z", "loop": 13060, "env_steps": 8024678399, "loss": 0.011777407489717007, "avg_return": 0.863098680973053, "regret": 0.0005028391606174409, "entropy": 0.0595443919301033, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:34.672394Z", "loop": 13061, "env_steps": 8025292799, "loss": 0.010714516043663025, "avg_return": 0.8632224798202515, "regret": 0.0005028391606174409, "entropy": 0.059124913066625595, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:35.527949Z", "loop": 13062, "env_steps": 8025907199, "loss": 0.011234539560973644, "avg_return": 0.8638603687286377, "regret": 0.0005028391606174409, "entropy": 0.06005162000656128, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:36.382562Z", "loop": 13063, "env_steps": 8026521599, "loss": 0.011831101961433887, "avg_return": 0.8635843992233276, "regret": 0.0005028391606174409, "entropy": 0.06163966655731201, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:37.236954Z", "loop": 13064, "env_steps": 8027135999, "loss": 0.012606057338416576, "avg_return": 0.8615627288818359, "regret": 0.0005028391606174409, "entropy": 0.06546127796173096, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:38.090887Z", "loop": 13065, "env_steps": 8027750399, "loss": 0.012326451018452644, "avg_return": 0.8612640500068665, "regret": 0.0005028391606174409, "entropy": 0.06274938583374023, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:38.946131Z", "loop": 13066, "env_steps": 8028364799, "loss": 0.011923669837415218, "avg_return": 0.8610389232635498, "regret": 0.0005028391606174409, "entropy": 0.06778103858232498, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:39.800222Z", "loop": 13067, "env_steps": 8028979199, "loss": 0.012267200276255608, "avg_return": 0.8627544641494751, "regret": 0.0005028391606174409, "entropy": 0.06742415577173233, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:40.654324Z", "loop": 13068, "env_steps": 8029593599, "loss": 0.014415244571864605, "avg_return": 0.8596611618995667, "regret": 0.0005028391606174409, "entropy": 0.07273763418197632, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:41.508512Z", "loop": 13069, "env_steps": 8030207999, "loss": 0.014269140549004078, "avg_return": 0.8597745895385742, "regret": 0.0005028391606174409, "entropy": 0.07666148245334625, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:42.402594Z", "loop": 13070, "env_steps": 8030822399, "loss": 0.01386608649045229, "avg_return": 0.8597485423088074, "regret": 0.003026376012712717, "entropy": 0.07674369215965271, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:43.256272Z", "loop": 13071, "env_steps": 8031436799, "loss": 0.013597275130450726, "avg_return": 0.8610547184944153, "regret": 0.003026376012712717, "entropy": 0.0734097808599472, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:44.110680Z", "loop": 13072, "env_steps": 8032051199, "loss": 0.011916430667042732, "avg_return": 0.8623098731040955, "regret": 0.003026376012712717, "entropy": 0.07084421068429947, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:44.964241Z", "loop": 13073, "env_steps": 8032665599, "loss": 0.012367191724479198, "avg_return": 0.8634578585624695, "regret": 0.003026376012712717, "entropy": 0.06806306540966034, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:45.818395Z", "loop": 13074, "env_steps": 8033279999, "loss": 0.012121738865971565, "avg_return": 0.862549364566803, "regret": 0.003026376012712717, "entropy": 0.06028104946017265, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:46.672137Z", "loop": 13075, "env_steps": 8033894399, "loss": 0.012214158661663532, "avg_return": 0.8628298044204712, "regret": 0.003026376012712717, "entropy": 0.0656018853187561, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:47.526870Z", "loop": 13076, "env_steps": 8034508799, "loss": 0.012607834301888943, "avg_return": 0.863433837890625, "regret": 0.003026376012712717, "entropy": 0.06782757490873337, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:48.381555Z", "loop": 13077, "env_steps": 8035123199, "loss": 0.01200226042419672, "avg_return": 0.8626537322998047, "regret": 0.003026376012712717, "entropy": 0.06495341658592224, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:49.235973Z", "loop": 13078, "env_steps": 8035737599, "loss": 0.011904294602572918, "avg_return": 0.8637852072715759, "regret": 0.003026376012712717, "entropy": 0.06212734431028366, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:50.089558Z", "loop": 13079, "env_steps": 8036351999, "loss": 0.012510525994002819, "avg_return": 0.8646166324615479, "regret": 0.003026376012712717, "entropy": 0.06723396480083466, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:50.982464Z", "loop": 13080, "env_steps": 8036966399, "loss": 0.01385862659662962, "avg_return": 0.8648346066474915, "regret": 0.0002520371344871819, "entropy": 0.06823322176933289, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:51.836895Z", "loop": 13081, "env_steps": 8037580799, "loss": 0.013241535983979702, "avg_return": 0.8639333248138428, "regret": 0.0002520371344871819, "entropy": 0.06907936185598373, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:52.691417Z", "loop": 13082, "env_steps": 8038195199, "loss": 0.014657503925263882, "avg_return": 0.863512396812439, "regret": 0.0002520371344871819, "entropy": 0.07475287467241287, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:53.545424Z", "loop": 13083, "env_steps": 8038809599, "loss": 0.014543621800839901, "avg_return": 0.8626598119735718, "regret": 0.0002520371344871819, "entropy": 0.0761224627494812, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:54.399404Z", "loop": 13084, "env_steps": 8039423999, "loss": 0.014520548284053802, "avg_return": 0.8622745871543884, "regret": 0.0002520371344871819, "entropy": 0.07129526138305664, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:55.254315Z", "loop": 13085, "env_steps": 8040038399, "loss": 0.015064507722854614, "avg_return": 0.8604933619499207, "regret": 0.0002520371344871819, "entropy": 0.07759823650121689, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:56.109894Z", "loop": 13086, "env_steps": 8040652799, "loss": 0.015803789719939232, "avg_return": 0.857326090335846, "regret": 0.0002520371344871819, "entropy": 0.08161718398332596, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:56.965624Z", "loop": 13087, "env_steps": 8041267199, "loss": 0.015324792824685574, "avg_return": 0.8556971549987793, "regret": 0.0002520371344871819, "entropy": 0.08204332739114761, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:57.819865Z", "loop": 13088, "env_steps": 8041881599, "loss": 0.016291433945298195, "avg_return": 0.8525615930557251, "regret": 0.0002520371344871819, "entropy": 0.08707843720912933, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:58.674199Z", "loop": 13089, "env_steps": 8042495999, "loss": 0.017567073926329613, "avg_return": 0.8531596660614014, "regret": 0.0002520371344871819, "entropy": 0.09056543558835983, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:30:59.570272Z", "loop": 13090, "env_steps": 8043110399, "loss": 0.017752645537257195, "avg_return": 0.8583986759185791, "regret": 0.005679829511791468, "entropy": 0.0909435823559761, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:00.425621Z", "loop": 13091, "env_steps": 8043724799, "loss": 0.0178985632956028, "avg_return": 0.8593131899833679, "regret": 0.005679829511791468, "entropy": 0.089308962225914, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:01.281007Z", "loop": 13092, "env_steps": 8044339199, "loss": 0.01899006776511669, "avg_return": 0.8622379899024963, "regret": 0.005679829511791468, "entropy": 0.09637577086687088, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:02.135968Z", "loop": 13093, "env_steps": 8044953599, "loss": 0.018737586215138435, "avg_return": 0.8619836568832397, "regret": 0.005679829511791468, "entropy": 0.09631798416376114, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:02.990773Z", "loop": 13094, "env_steps": 8045567999, "loss": 0.018954677507281303, "avg_return": 0.8638291358947754, "regret": 0.005679829511791468, "entropy": 0.09403090924024582, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:03.844219Z", "loop": 13095, "env_steps": 8046182399, "loss": 0.016537509858608246, "avg_return": 0.8649699091911316, "regret": 0.005679829511791468, "entropy": 0.08227091282606125, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:04.699858Z", "loop": 13096, "env_steps": 8046796799, "loss": 0.01672959513962269, "avg_return": 0.8631992936134338, "regret": 0.005679829511791468, "entropy": 0.08444012701511383, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:05.554027Z", "loop": 13097, "env_steps": 8047411199, "loss": 0.017928486689925194, "avg_return": 0.8621805906295776, "regret": 0.005679829511791468, "entropy": 0.08796260505914688, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:06.408330Z", "loop": 13098, "env_steps": 8048025599, "loss": 0.01687333919107914, "avg_return": 0.8635101318359375, "regret": 0.005679829511791468, "entropy": 0.08562422543764114, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:07.263691Z", "loop": 13099, "env_steps": 8048639999, "loss": 0.01638750545680523, "avg_return": 0.8636242747306824, "regret": 0.005679829511791468, "entropy": 0.08415120840072632, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:08.158162Z", "loop": 13100, "env_steps": 8049254399, "loss": 0.017117395997047424, "avg_return": 0.8629377484321594, "regret": 0.00034661623067222536, "entropy": 0.08531899005174637, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:09.013002Z", "loop": 13101, "env_steps": 8049868799, "loss": 0.016518212854862213, "avg_return": 0.8627346158027649, "regret": 0.00034661623067222536, "entropy": 0.08856151252985, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:09.867728Z", "loop": 13102, "env_steps": 8050483199, "loss": 0.018211714923381805, "avg_return": 0.8641397356987, "regret": 0.00034661623067222536, "entropy": 0.0889582708477974, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:10.721836Z", "loop": 13103, "env_steps": 8051097599, "loss": 0.017783865332603455, "avg_return": 0.8635792136192322, "regret": 0.00034661623067222536, "entropy": 0.0888613760471344, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:11.575772Z", "loop": 13104, "env_steps": 8051711999, "loss": 0.01987290009856224, "avg_return": 0.8636581897735596, "regret": 0.00034661623067222536, "entropy": 0.09450537711381912, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:12.429700Z", "loop": 13105, "env_steps": 8052326399, "loss": 0.019288700073957443, "avg_return": 0.8622953295707703, "regret": 0.00034661623067222536, "entropy": 0.09489244222640991, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:13.283632Z", "loop": 13106, "env_steps": 8052940799, "loss": 0.018951773643493652, "avg_return": 0.8631476759910583, "regret": 0.00034661623067222536, "entropy": 0.09449571371078491, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:14.136849Z", "loop": 13107, "env_steps": 8053555199, "loss": 0.02049003355205059, "avg_return": 0.8626319766044617, "regret": 0.00034661623067222536, "entropy": 0.09845557063817978, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:14.990457Z", "loop": 13108, "env_steps": 8054169599, "loss": 0.01895754411816597, "avg_return": 0.8632586002349854, "regret": 0.00034661623067222536, "entropy": 0.0948692113161087, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:15.844789Z", "loop": 13109, "env_steps": 8054783999, "loss": 0.018774928525090218, "avg_return": 0.8612767457962036, "regret": 0.00034661623067222536, "entropy": 0.09197178483009338, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:16.740498Z", "loop": 13110, "env_steps": 8055398399, "loss": 0.019743328914046288, "avg_return": 0.8630698919296265, "regret": 0.0012056156992912292, "entropy": 0.09763944149017334, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:17.594224Z", "loop": 13111, "env_steps": 8056012799, "loss": 0.019661081954836845, "avg_return": 0.8633875846862793, "regret": 0.0012056156992912292, "entropy": 0.09610976278781891, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:18.447821Z", "loop": 13112, "env_steps": 8056627199, "loss": 0.019119704142212868, "avg_return": 0.8631818890571594, "regret": 0.0012056156992912292, "entropy": 0.09176130592823029, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:19.302995Z", "loop": 13113, "env_steps": 8057241599, "loss": 0.018088625743985176, "avg_return": 0.8625009655952454, "regret": 0.0012056156992912292, "entropy": 0.08939559012651443, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:20.157726Z", "loop": 13114, "env_steps": 8057855999, "loss": 0.016621895134449005, "avg_return": 0.8619162440299988, "regret": 0.0012056156992912292, "entropy": 0.08449411392211914, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:21.011584Z", "loop": 13115, "env_steps": 8058470399, "loss": 0.017014307901263237, "avg_return": 0.8626070618629456, "regret": 0.0012056156992912292, "entropy": 0.08584964275360107, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:21.865121Z", "loop": 13116, "env_steps": 8059084799, "loss": 0.01667512021958828, "avg_return": 0.8624774217605591, "regret": 0.0012056156992912292, "entropy": 0.08312257379293442, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:22.721604Z", "loop": 13117, "env_steps": 8059699199, "loss": 0.016798073425889015, "avg_return": 0.8624377846717834, "regret": 0.0012056156992912292, "entropy": 0.08199803531169891, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:23.576149Z", "loop": 13118, "env_steps": 8060313599, "loss": 0.01833178848028183, "avg_return": 0.862689733505249, "regret": 0.0012056156992912292, "entropy": 0.09057685732841492, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:24.430239Z", "loop": 13119, "env_steps": 8060927999, "loss": 0.019912032410502434, "avg_return": 0.8628237247467041, "regret": 0.0012056156992912292, "entropy": 0.10001570731401443, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:25.324582Z", "loop": 13120, "env_steps": 8061542399, "loss": 0.021470556035637856, "avg_return": 0.8628419041633606, "regret": 0.0016375385457649827, "entropy": 0.10465461760759354, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:26.178898Z", "loop": 13121, "env_steps": 8062156799, "loss": 0.02006964199244976, "avg_return": 0.8616178631782532, "regret": 0.0016375385457649827, "entropy": 0.10167793929576874, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:27.032937Z", "loop": 13122, "env_steps": 8062771199, "loss": 0.01806398294866085, "avg_return": 0.8624457120895386, "regret": 0.0016375385457649827, "entropy": 0.089656300842762, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:27.886852Z", "loop": 13123, "env_steps": 8063385599, "loss": 0.0168432779610157, "avg_return": 0.8626025319099426, "regret": 0.0016375385457649827, "entropy": 0.08310870081186295, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:28.740464Z", "loop": 13124, "env_steps": 8063999999, "loss": 0.015735622495412827, "avg_return": 0.8604366183280945, "regret": 0.0016375385457649827, "entropy": 0.08370000869035721, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:29.594705Z", "loop": 13125, "env_steps": 8064614399, "loss": 0.016434310004115105, "avg_return": 0.8611063957214355, "regret": 0.0016375385457649827, "entropy": 0.0783001109957695, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:30.449389Z", "loop": 13126, "env_steps": 8065228799, "loss": 0.016122421249747276, "avg_return": 0.8615733981132507, "regret": 0.0016375385457649827, "entropy": 0.08425281941890717, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:31.304129Z", "loop": 13127, "env_steps": 8065843199, "loss": 0.016047101467847824, "avg_return": 0.8607214689254761, "regret": 0.0016375385457649827, "entropy": 0.08282044529914856, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:32.158580Z", "loop": 13128, "env_steps": 8066457599, "loss": 0.015214233659207821, "avg_return": 0.8610079288482666, "regret": 0.0016375385457649827, "entropy": 0.0791415274143219, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:33.013424Z", "loop": 13129, "env_steps": 8067071999, "loss": 0.014901923015713692, "avg_return": 0.8607137203216553, "regret": 0.0016375385457649827, "entropy": 0.0771971270442009, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:33.907063Z", "loop": 13130, "env_steps": 8067686399, "loss": 0.014053557999432087, "avg_return": 0.8618566989898682, "regret": 0.002800476038828492, "entropy": 0.07257147133350372, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:34.760948Z", "loop": 13131, "env_steps": 8068300799, "loss": 0.014940368011593819, "avg_return": 0.8600146770477295, "regret": 0.002800476038828492, "entropy": 0.07980649918317795, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:35.614159Z", "loop": 13132, "env_steps": 8068915199, "loss": 0.015667108818888664, "avg_return": 0.8597630262374878, "regret": 0.002800476038828492, "entropy": 0.08172863721847534, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:36.468522Z", "loop": 13133, "env_steps": 8069529599, "loss": 0.015318353660404682, "avg_return": 0.8586625456809998, "regret": 0.002800476038828492, "entropy": 0.08012025058269501, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:37.321730Z", "loop": 13134, "env_steps": 8070143999, "loss": 0.014639690518379211, "avg_return": 0.8603187203407288, "regret": 0.002800476038828492, "entropy": 0.07790017873048782, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:38.175853Z", "loop": 13135, "env_steps": 8070758399, "loss": 0.014504670165479183, "avg_return": 0.8577247262001038, "regret": 0.002800476038828492, "entropy": 0.07928332686424255, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:39.028804Z", "loop": 13136, "env_steps": 8071372799, "loss": 0.01419831532984972, "avg_return": 0.8587850332260132, "regret": 0.002800476038828492, "entropy": 0.0759032815694809, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:39.882932Z", "loop": 13137, "env_steps": 8071987199, "loss": 0.014514229260385036, "avg_return": 0.8593630194664001, "regret": 0.002800476038828492, "entropy": 0.07562284916639328, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:40.735782Z", "loop": 13138, "env_steps": 8072601599, "loss": 0.014030784368515015, "avg_return": 0.8593693971633911, "regret": 0.002800476038828492, "entropy": 0.07288961857557297, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:41.588670Z", "loop": 13139, "env_steps": 8073215999, "loss": 0.013707878068089485, "avg_return": 0.8591374158859253, "regret": 0.002800476038828492, "entropy": 0.07870540767908096, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:42.480649Z", "loop": 13140, "env_steps": 8073830399, "loss": 0.013858839869499207, "avg_return": 0.8598962426185608, "regret": 0.0041105845011770725, "entropy": 0.07861873507499695, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:43.335094Z", "loop": 13141, "env_steps": 8074444799, "loss": 0.013672246597707272, "avg_return": 0.858654797077179, "regret": 0.0041105845011770725, "entropy": 0.07331787794828415, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:44.189052Z", "loop": 13142, "env_steps": 8075059199, "loss": 0.013146042823791504, "avg_return": 0.8606764674186707, "regret": 0.0041105845011770725, "entropy": 0.07105721533298492, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:45.043189Z", "loop": 13143, "env_steps": 8075673599, "loss": 0.011362376622855663, "avg_return": 0.8616089224815369, "regret": 0.0041105845011770725, "entropy": 0.06599341332912445, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:45.898280Z", "loop": 13144, "env_steps": 8076287999, "loss": 0.011271602474153042, "avg_return": 0.8614720702171326, "regret": 0.0041105845011770725, "entropy": 0.06007669121026993, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:46.753551Z", "loop": 13145, "env_steps": 8076902399, "loss": 0.010671810247004032, "avg_return": 0.8626869916915894, "regret": 0.0041105845011770725, "entropy": 0.05962597206234932, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:47.608101Z", "loop": 13146, "env_steps": 8077516799, "loss": 0.011681778356432915, "avg_return": 0.8632052540779114, "regret": 0.0041105845011770725, "entropy": 0.061166297644376755, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:48.461064Z", "loop": 13147, "env_steps": 8078131199, "loss": 0.011202787049114704, "avg_return": 0.8638415932655334, "regret": 0.0041105845011770725, "entropy": 0.0596139132976532, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:49.313933Z", "loop": 13148, "env_steps": 8078745599, "loss": 0.010804473422467709, "avg_return": 0.862903356552124, "regret": 0.0041105845011770725, "entropy": 0.05722875893115997, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:50.168766Z", "loop": 13149, "env_steps": 8079359999, "loss": 0.009807017631828785, "avg_return": 0.8625956177711487, "regret": 0.0041105845011770725, "entropy": 0.05395311489701271, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:51.063065Z", "loop": 13150, "env_steps": 8079974399, "loss": 0.012121712788939476, "avg_return": 0.8633923530578613, "regret": 0.0005227251094765961, "entropy": 0.05950481444597244, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:51.917466Z", "loop": 13151, "env_steps": 8080588799, "loss": 0.010838225483894348, "avg_return": 0.8636175990104675, "regret": 0.0005227251094765961, "entropy": 0.057256557047367096, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:52.771939Z", "loop": 13152, "env_steps": 8081203199, "loss": 0.01054429728537798, "avg_return": 0.8640824556350708, "regret": 0.0005227251094765961, "entropy": 0.056988347321748734, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:53.626116Z", "loop": 13153, "env_steps": 8081817599, "loss": 0.010825945995748043, "avg_return": 0.863395094871521, "regret": 0.0005227251094765961, "entropy": 0.059509892016649246, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:54.480291Z", "loop": 13154, "env_steps": 8082431999, "loss": 0.011026761494576931, "avg_return": 0.8627339601516724, "regret": 0.0005227251094765961, "entropy": 0.05850646272301674, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:55.335292Z", "loop": 13155, "env_steps": 8083046399, "loss": 0.01133332122117281, "avg_return": 0.8616654872894287, "regret": 0.0005227251094765961, "entropy": 0.05994364619255066, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:56.189171Z", "loop": 13156, "env_steps": 8083660799, "loss": 0.010892434976994991, "avg_return": 0.8628123998641968, "regret": 0.0005227251094765961, "entropy": 0.056842606514692307, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:57.044043Z", "loop": 13157, "env_steps": 8084275199, "loss": 0.011160655878484249, "avg_return": 0.8645740151405334, "regret": 0.0005227251094765961, "entropy": 0.059041645377874374, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:57.898591Z", "loop": 13158, "env_steps": 8084889599, "loss": 0.011129978112876415, "avg_return": 0.8622954487800598, "regret": 0.0005227251094765961, "entropy": 0.05926370993256569, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:58.752280Z", "loop": 13159, "env_steps": 8085503999, "loss": 0.011071567423641682, "avg_return": 0.8608502149581909, "regret": 0.0005227251094765961, "entropy": 0.05973629653453827, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:31:59.646910Z", "loop": 13160, "env_steps": 8086118399, "loss": 0.012048070318996906, "avg_return": 0.8625521063804626, "regret": 0.0015643746592104435, "entropy": 0.0640953779220581, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:00.500814Z", "loop": 13161, "env_steps": 8086732799, "loss": 0.011761355213820934, "avg_return": 0.8615193963050842, "regret": 0.0015643746592104435, "entropy": 0.06154259294271469, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:01.355179Z", "loop": 13162, "env_steps": 8087347199, "loss": 0.01161254197359085, "avg_return": 0.8606488108634949, "regret": 0.0015643746592104435, "entropy": 0.06343575567007065, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:02.210254Z", "loop": 13163, "env_steps": 8087961599, "loss": 0.0122404545545578, "avg_return": 0.8613780736923218, "regret": 0.0015643746592104435, "entropy": 0.0657540112733841, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:03.064677Z", "loop": 13164, "env_steps": 8088575999, "loss": 0.011608757078647614, "avg_return": 0.8604084253311157, "regret": 0.0015643746592104435, "entropy": 0.06394610553979874, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:03.918351Z", "loop": 13165, "env_steps": 8089190399, "loss": 0.012692044489085674, "avg_return": 0.85990971326828, "regret": 0.0015643746592104435, "entropy": 0.06730912625789642, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:04.772129Z", "loop": 13166, "env_steps": 8089804799, "loss": 0.012749209068715572, "avg_return": 0.860360860824585, "regret": 0.0015643746592104435, "entropy": 0.06816095113754272, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:05.626994Z", "loop": 13167, "env_steps": 8090419199, "loss": 0.011982906609773636, "avg_return": 0.8599410057067871, "regret": 0.0015643746592104435, "entropy": 0.06654468923807144, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:06.482372Z", "loop": 13168, "env_steps": 8091033599, "loss": 0.011817194521427155, "avg_return": 0.8617527484893799, "regret": 0.0015643746592104435, "entropy": 0.06478037685155869, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:07.336642Z", "loop": 13169, "env_steps": 8091647999, "loss": 0.012019890360534191, "avg_return": 0.8605484366416931, "regret": 0.0015643746592104435, "entropy": 0.06471244990825653, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:08.230024Z", "loop": 13170, "env_steps": 8092262399, "loss": 0.012414555065333843, "avg_return": 0.8599774241447449, "regret": 0.002724063117057085, "entropy": 0.0656878873705864, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:09.083535Z", "loop": 13171, "env_steps": 8092876799, "loss": 0.011238961480557919, "avg_return": 0.8610333204269409, "regret": 0.002724063117057085, "entropy": 0.06354913860559464, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:09.937802Z", "loop": 13172, "env_steps": 8093491199, "loss": 0.01287996768951416, "avg_return": 0.8607576489448547, "regret": 0.002724063117057085, "entropy": 0.06680011749267578, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:10.791829Z", "loop": 13173, "env_steps": 8094105599, "loss": 0.01174867432564497, "avg_return": 0.8603163957595825, "regret": 0.002724063117057085, "entropy": 0.0664454996585846, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:11.645769Z", "loop": 13174, "env_steps": 8094719999, "loss": 0.011634583584964275, "avg_return": 0.8598480224609375, "regret": 0.002724063117057085, "entropy": 0.06450621038675308, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:12.499395Z", "loop": 13175, "env_steps": 8095334399, "loss": 0.01203202549368143, "avg_return": 0.8612233400344849, "regret": 0.002724063117057085, "entropy": 0.06441912055015564, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:13.353675Z", "loop": 13176, "env_steps": 8095948799, "loss": 0.01313660480082035, "avg_return": 0.8613728880882263, "regret": 0.002724063117057085, "entropy": 0.06994598358869553, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:14.207843Z", "loop": 13177, "env_steps": 8096563199, "loss": 0.013693518936634064, "avg_return": 0.8603000044822693, "regret": 0.002724063117057085, "entropy": 0.07666732370853424, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:15.061808Z", "loop": 13178, "env_steps": 8097177599, "loss": 0.013506914488971233, "avg_return": 0.8588046431541443, "regret": 0.002724063117057085, "entropy": 0.07183478772640228, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:15.915075Z", "loop": 13179, "env_steps": 8097791999, "loss": 0.014238712377846241, "avg_return": 0.8604161739349365, "regret": 0.002724063117057085, "entropy": 0.07631152868270874, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:16.808575Z", "loop": 13180, "env_steps": 8098406399, "loss": 0.014290429651737213, "avg_return": 0.8609539866447449, "regret": 0.0030565205961465836, "entropy": 0.07622615993022919, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:17.662766Z", "loop": 13181, "env_steps": 8099020799, "loss": 0.01383859571069479, "avg_return": 0.8610939979553223, "regret": 0.0030565205961465836, "entropy": 0.07179269939661026, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:18.517040Z", "loop": 13182, "env_steps": 8099635199, "loss": 0.012811805121600628, "avg_return": 0.8613863587379456, "regret": 0.0030565205961465836, "entropy": 0.06898271292448044, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:19.370380Z", "loop": 13183, "env_steps": 8100249599, "loss": 0.011664465069770813, "avg_return": 0.8619518280029297, "regret": 0.0030565205961465836, "entropy": 0.0690024122595787, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:20.225915Z", "loop": 13184, "env_steps": 8100863999, "loss": 0.013142083771526814, "avg_return": 0.8619620203971863, "regret": 0.0030565205961465836, "entropy": 0.06884842365980148, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:21.080025Z", "loop": 13185, "env_steps": 8101478399, "loss": 0.011331204324960709, "avg_return": 0.8633855581283569, "regret": 0.0030565205961465836, "entropy": 0.06440400332212448, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:21.934532Z", "loop": 13186, "env_steps": 8102092799, "loss": 0.011951006017625332, "avg_return": 0.8641744256019592, "regret": 0.0030565205961465836, "entropy": 0.06546369940042496, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:22.787688Z", "loop": 13187, "env_steps": 8102707199, "loss": 0.012212133966386318, "avg_return": 0.8639546036720276, "regret": 0.0030565205961465836, "entropy": 0.06512635201215744, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:23.641060Z", "loop": 13188, "env_steps": 8103321599, "loss": 0.013171473518013954, "avg_return": 0.8624963760375977, "regret": 0.0030565205961465836, "entropy": 0.06574774533510208, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:24.495607Z", "loop": 13189, "env_steps": 8103935999, "loss": 0.012323698960244656, "avg_return": 0.8638321161270142, "regret": 0.0030565205961465836, "entropy": 0.06708714365959167, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:25.388004Z", "loop": 13190, "env_steps": 8104550399, "loss": 0.011659067124128342, "avg_return": 0.8623750805854797, "regret": 0.00016188067093025893, "entropy": 0.06432277709245682, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:26.243059Z", "loop": 13191, "env_steps": 8105164799, "loss": 0.012458129785954952, "avg_return": 0.8646212816238403, "regret": 0.00016188067093025893, "entropy": 0.06069866567850113, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:27.098213Z", "loop": 13192, "env_steps": 8105779199, "loss": 0.012830364517867565, "avg_return": 0.8632230758666992, "regret": 0.00016188067093025893, "entropy": 0.06555455923080444, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:27.952910Z", "loop": 13193, "env_steps": 8106393599, "loss": 0.01173567958176136, "avg_return": 0.863569438457489, "regret": 0.00016188067093025893, "entropy": 0.06451033055782318, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:28.808031Z", "loop": 13194, "env_steps": 8107007999, "loss": 0.012533560395240784, "avg_return": 0.8634450435638428, "regret": 0.00016188067093025893, "entropy": 0.06405175477266312, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:29.662967Z", "loop": 13195, "env_steps": 8107622399, "loss": 0.01261996477842331, "avg_return": 0.863824188709259, "regret": 0.00016188067093025893, "entropy": 0.06454715877771378, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:30.517179Z", "loop": 13196, "env_steps": 8108236799, "loss": 0.01221711840480566, "avg_return": 0.8643922209739685, "regret": 0.00016188067093025893, "entropy": 0.06364375352859497, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:31.370812Z", "loop": 13197, "env_steps": 8108851199, "loss": 0.013883869163691998, "avg_return": 0.8633651733398438, "regret": 0.00016188067093025893, "entropy": 0.06849896162748337, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:32.224549Z", "loop": 13198, "env_steps": 8109465599, "loss": 0.012824016623198986, "avg_return": 0.8627211451530457, "regret": 0.00016188067093025893, "entropy": 0.06700394302606583, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:33.079319Z", "loop": 13199, "env_steps": 8110079999, "loss": 0.013273360207676888, "avg_return": 0.8636478781700134, "regret": 0.00016188067093025893, "entropy": 0.06938272714614868, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:33.971843Z", "loop": 13200, "env_steps": 8110694399, "loss": 0.013776055537164211, "avg_return": 0.8632816672325134, "regret": 0.0001537378557259217, "entropy": 0.06944049894809723, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:34.825653Z", "loop": 13201, "env_steps": 8111308799, "loss": 0.012727524153888226, "avg_return": 0.8633657097816467, "regret": 0.0001537378557259217, "entropy": 0.06797058135271072, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:35.680769Z", "loop": 13202, "env_steps": 8111923199, "loss": 0.013401523232460022, "avg_return": 0.863032341003418, "regret": 0.0001537378557259217, "entropy": 0.07041805237531662, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:36.535307Z", "loop": 13203, "env_steps": 8112537599, "loss": 0.012513706460595131, "avg_return": 0.8634319305419922, "regret": 0.0001537378557259217, "entropy": 0.06656499952077866, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:37.390572Z", "loop": 13204, "env_steps": 8113151999, "loss": 0.013429202139377594, "avg_return": 0.8630897998809814, "regret": 0.0001537378557259217, "entropy": 0.06677290797233582, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:38.245442Z", "loop": 13205, "env_steps": 8113766399, "loss": 0.0129292206838727, "avg_return": 0.8625807762145996, "regret": 0.0001537378557259217, "entropy": 0.06720218062400818, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:39.099184Z", "loop": 13206, "env_steps": 8114380799, "loss": 0.012703304179012775, "avg_return": 0.8627468943595886, "regret": 0.0001537378557259217, "entropy": 0.06510608643293381, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:39.953306Z", "loop": 13207, "env_steps": 8114995199, "loss": 0.0126996710896492, "avg_return": 0.862072765827179, "regret": 0.0001537378557259217, "entropy": 0.06614933907985687, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:40.807722Z", "loop": 13208, "env_steps": 8115609599, "loss": 0.01150027196854353, "avg_return": 0.8616412281990051, "regret": 0.0001537378557259217, "entropy": 0.06424219906330109, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:41.661990Z", "loop": 13209, "env_steps": 8116223999, "loss": 0.011215674690902233, "avg_return": 0.8624829053878784, "regret": 0.0001537378557259217, "entropy": 0.05942070484161377, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:42.555649Z", "loop": 13210, "env_steps": 8116838399, "loss": 0.012806646525859833, "avg_return": 0.861792802810669, "regret": 0.0020578699186444283, "entropy": 0.0654364600777626, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:43.409553Z", "loop": 13211, "env_steps": 8117452799, "loss": 0.012441220693290234, "avg_return": 0.8622990250587463, "regret": 0.0020578699186444283, "entropy": 0.0638132393360138, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:44.263572Z", "loop": 13212, "env_steps": 8118067199, "loss": 0.012367851100862026, "avg_return": 0.8609833121299744, "regret": 0.0020578699186444283, "entropy": 0.06744854152202606, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:45.117134Z", "loop": 13213, "env_steps": 8118681599, "loss": 0.011878683231770992, "avg_return": 0.8602113127708435, "regret": 0.0020578699186444283, "entropy": 0.06496181339025497, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:45.972031Z", "loop": 13214, "env_steps": 8119295999, "loss": 0.012165967375040054, "avg_return": 0.8606334924697876, "regret": 0.0020578699186444283, "entropy": 0.06595788151025772, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:46.827035Z", "loop": 13215, "env_steps": 8119910399, "loss": 0.013978256843984127, "avg_return": 0.8613234758377075, "regret": 0.0020578699186444283, "entropy": 0.07276220619678497, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:47.681001Z", "loop": 13216, "env_steps": 8120524799, "loss": 0.012235596776008606, "avg_return": 0.8605326414108276, "regret": 0.0020578699186444283, "entropy": 0.06829164922237396, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:48.536350Z", "loop": 13217, "env_steps": 8121139199, "loss": 0.013057579286396503, "avg_return": 0.8610642552375793, "regret": 0.0020578699186444283, "entropy": 0.06642850488424301, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:49.389823Z", "loop": 13218, "env_steps": 8121753599, "loss": 0.012988823466002941, "avg_return": 0.8615049719810486, "regret": 0.0020578699186444283, "entropy": 0.0685943067073822, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:50.243582Z", "loop": 13219, "env_steps": 8122367999, "loss": 0.013742007315158844, "avg_return": 0.8613749146461487, "regret": 0.0020578699186444283, "entropy": 0.07135220617055893, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:51.137086Z", "loop": 13220, "env_steps": 8122982399, "loss": 0.012697300873696804, "avg_return": 0.8631687760353088, "regret": 0.0016592864412814379, "entropy": 0.06824000924825668, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:51.991183Z", "loop": 13221, "env_steps": 8123596799, "loss": 0.014072592370212078, "avg_return": 0.8615774512290955, "regret": 0.0016592864412814379, "entropy": 0.07195828855037689, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:52.844846Z", "loop": 13222, "env_steps": 8124211199, "loss": 0.013367709703743458, "avg_return": 0.8626396059989929, "regret": 0.0016592864412814379, "entropy": 0.07153311371803284, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:53.699511Z", "loop": 13223, "env_steps": 8124825599, "loss": 0.01395912654697895, "avg_return": 0.8627091646194458, "regret": 0.0016592864412814379, "entropy": 0.07420913875102997, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:54.554062Z", "loop": 13224, "env_steps": 8125439999, "loss": 0.01502230204641819, "avg_return": 0.8621950745582581, "regret": 0.0016592864412814379, "entropy": 0.07319696992635727, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:55.406552Z", "loop": 13225, "env_steps": 8126054399, "loss": 0.013248155824840069, "avg_return": 0.8621814250946045, "regret": 0.0016592864412814379, "entropy": 0.07064666599035263, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:56.260213Z", "loop": 13226, "env_steps": 8126668799, "loss": 0.01414849516004324, "avg_return": 0.8624634742736816, "regret": 0.0016592864412814379, "entropy": 0.07559577375650406, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:57.115092Z", "loop": 13227, "env_steps": 8127283199, "loss": 0.01412996556609869, "avg_return": 0.8649694919586182, "regret": 0.0016592864412814379, "entropy": 0.0751609355211258, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:57.969051Z", "loop": 13228, "env_steps": 8127897599, "loss": 0.01385605800896883, "avg_return": 0.8631930947303772, "regret": 0.0016592864412814379, "entropy": 0.07149569690227509, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:58.822478Z", "loop": 13229, "env_steps": 8128511999, "loss": 0.013218775391578674, "avg_return": 0.8621125221252441, "regret": 0.0016592864412814379, "entropy": 0.07002110779285431, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:32:59.716010Z", "loop": 13230, "env_steps": 8129126399, "loss": 0.012522353790700436, "avg_return": 0.8629562854766846, "regret": 0.0008940271218307316, "entropy": 0.06632732599973679, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:00.571595Z", "loop": 13231, "env_steps": 8129740799, "loss": 0.012924452312290668, "avg_return": 0.863013505935669, "regret": 0.0008940271218307316, "entropy": 0.06941785663366318, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:01.425961Z", "loop": 13232, "env_steps": 8130355199, "loss": 0.01311601884663105, "avg_return": 0.8619700074195862, "regret": 0.0008940271218307316, "entropy": 0.06625523418188095, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:02.279970Z", "loop": 13233, "env_steps": 8130969599, "loss": 0.01223362423479557, "avg_return": 0.8635197281837463, "regret": 0.0008940271218307316, "entropy": 0.06625384837388992, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:03.133528Z", "loop": 13234, "env_steps": 8131583999, "loss": 0.012245862744748592, "avg_return": 0.8636800050735474, "regret": 0.0008940271218307316, "entropy": 0.06408192962408066, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:03.988405Z", "loop": 13235, "env_steps": 8132198399, "loss": 0.011454067192971706, "avg_return": 0.862811803817749, "regret": 0.0008940271218307316, "entropy": 0.0639081671833992, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:04.843101Z", "loop": 13236, "env_steps": 8132812799, "loss": 0.012452824972569942, "avg_return": 0.8640608787536621, "regret": 0.0008940271218307316, "entropy": 0.06414040178060532, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:05.697274Z", "loop": 13237, "env_steps": 8133427199, "loss": 0.012155408971011639, "avg_return": 0.8637915253639221, "regret": 0.0008940271218307316, "entropy": 0.06075161695480347, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:06.551051Z", "loop": 13238, "env_steps": 8134041599, "loss": 0.012023292481899261, "avg_return": 0.8608553409576416, "regret": 0.0008940271218307316, "entropy": 0.06428243219852448, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:07.405067Z", "loop": 13239, "env_steps": 8134655999, "loss": 0.012572729960083961, "avg_return": 0.8625105023384094, "regret": 0.0008940271218307316, "entropy": 0.0652790367603302, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:08.298993Z", "loop": 13240, "env_steps": 8135270399, "loss": 0.012679608538746834, "avg_return": 0.8638090491294861, "regret": 0.0003534556017257273, "entropy": 0.06604794412851334, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:09.153278Z", "loop": 13241, "env_steps": 8135884799, "loss": 0.011074884794652462, "avg_return": 0.8628328442573547, "regret": 0.0003534556017257273, "entropy": 0.06239600479602814, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:10.006601Z", "loop": 13242, "env_steps": 8136499199, "loss": 0.011068511754274368, "avg_return": 0.8633303046226501, "regret": 0.0003534556017257273, "entropy": 0.06231515854597092, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:10.861288Z", "loop": 13243, "env_steps": 8137113599, "loss": 0.011973457410931587, "avg_return": 0.865484356880188, "regret": 0.0003534556017257273, "entropy": 0.06235227733850479, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:11.716016Z", "loop": 13244, "env_steps": 8137727999, "loss": 0.01220221258699894, "avg_return": 0.8626262545585632, "regret": 0.0003534556017257273, "entropy": 0.06434354186058044, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:12.570390Z", "loop": 13245, "env_steps": 8138342399, "loss": 0.012362055480480194, "avg_return": 0.8640358448028564, "regret": 0.0003534556017257273, "entropy": 0.06306367367506027, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:13.425276Z", "loop": 13246, "env_steps": 8138956799, "loss": 0.011636769399046898, "avg_return": 0.8632957339286804, "regret": 0.0003534556017257273, "entropy": 0.06324264407157898, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:14.280127Z", "loop": 13247, "env_steps": 8139571199, "loss": 0.012033410370349884, "avg_return": 0.8625229001045227, "regret": 0.0003534556017257273, "entropy": 0.06302586942911148, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:15.135812Z", "loop": 13248, "env_steps": 8140185599, "loss": 0.012050547637045383, "avg_return": 0.8630645871162415, "regret": 0.0003534556017257273, "entropy": 0.06350179761648178, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:15.989843Z", "loop": 13249, "env_steps": 8140799999, "loss": 0.013059432618319988, "avg_return": 0.8633679151535034, "regret": 0.0003534556017257273, "entropy": 0.06984901428222656, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:16.884043Z", "loop": 13250, "env_steps": 8141414399, "loss": 0.012856312096118927, "avg_return": 0.862960934638977, "regret": 0.0006829912890680134, "entropy": 0.06787984073162079, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:17.738778Z", "loop": 13251, "env_steps": 8142028799, "loss": 0.01353651937097311, "avg_return": 0.8624801635742188, "regret": 0.0006829912890680134, "entropy": 0.07222053408622742, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:18.593069Z", "loop": 13252, "env_steps": 8142643199, "loss": 0.013478151522576809, "avg_return": 0.8613632321357727, "regret": 0.0006829912890680134, "entropy": 0.06988673657178879, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:19.448515Z", "loop": 13253, "env_steps": 8143257599, "loss": 0.013924372382462025, "avg_return": 0.862832248210907, "regret": 0.0006829912890680134, "entropy": 0.07186399400234222, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:20.303351Z", "loop": 13254, "env_steps": 8143871999, "loss": 0.013081328943371773, "avg_return": 0.8645293116569519, "regret": 0.0006829912890680134, "entropy": 0.07045300304889679, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:21.157567Z", "loop": 13255, "env_steps": 8144486399, "loss": 0.013721716590225697, "avg_return": 0.862898588180542, "regret": 0.0006829912890680134, "entropy": 0.07057017087936401, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:22.010976Z", "loop": 13256, "env_steps": 8145100799, "loss": 0.013742799870669842, "avg_return": 0.8611019253730774, "regret": 0.0006829912890680134, "entropy": 0.07281273603439331, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:22.864448Z", "loop": 13257, "env_steps": 8145715199, "loss": 0.014499291777610779, "avg_return": 0.8651894330978394, "regret": 0.0006829912890680134, "entropy": 0.07614632695913315, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:23.719898Z", "loop": 13258, "env_steps": 8146329599, "loss": 0.014285712502896786, "avg_return": 0.8630301356315613, "regret": 0.0006829912890680134, "entropy": 0.07247024029493332, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:24.574684Z", "loop": 13259, "env_steps": 8146943999, "loss": 0.013883473351597786, "avg_return": 0.8638380169868469, "regret": 0.0006829912890680134, "entropy": 0.07360776513814926, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:25.468376Z", "loop": 13260, "env_steps": 8147558399, "loss": 0.01395305898040533, "avg_return": 0.8629429340362549, "regret": 0.0001096764681278728, "entropy": 0.07185722887516022, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:26.321116Z", "loop": 13261, "env_steps": 8148172799, "loss": 0.012734885327517986, "avg_return": 0.8626707196235657, "regret": 0.0001096764681278728, "entropy": 0.0703597441315651, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:27.176085Z", "loop": 13262, "env_steps": 8148787199, "loss": 0.014595620334148407, "avg_return": 0.8640645742416382, "regret": 0.0001096764681278728, "entropy": 0.07443477213382721, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:28.030411Z", "loop": 13263, "env_steps": 8149401599, "loss": 0.01379818469285965, "avg_return": 0.8644185662269592, "regret": 0.0001096764681278728, "entropy": 0.07385051995515823, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:28.883953Z", "loop": 13264, "env_steps": 8150015999, "loss": 0.012970578856766224, "avg_return": 0.864064633846283, "regret": 0.0001096764681278728, "entropy": 0.06982062757015228, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:29.737684Z", "loop": 13265, "env_steps": 8150630399, "loss": 0.012530065141618252, "avg_return": 0.8633459806442261, "regret": 0.0001096764681278728, "entropy": 0.06846936792135239, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:30.591459Z", "loop": 13266, "env_steps": 8151244799, "loss": 0.012766179628670216, "avg_return": 0.8634284734725952, "regret": 0.0001096764681278728, "entropy": 0.0698264017701149, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:31.445649Z", "loop": 13267, "env_steps": 8151859199, "loss": 0.013168858364224434, "avg_return": 0.8642132878303528, "regret": 0.0001096764681278728, "entropy": 0.06864959746599197, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:32.299376Z", "loop": 13268, "env_steps": 8152473599, "loss": 0.012106495909392834, "avg_return": 0.8652621507644653, "regret": 0.0001096764681278728, "entropy": 0.06590858846902847, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:33.152596Z", "loop": 13269, "env_steps": 8153087999, "loss": 0.012266894802451134, "avg_return": 0.8627936840057373, "regret": 0.0001096764681278728, "entropy": 0.06685972213745117, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:34.047085Z", "loop": 13270, "env_steps": 8153702399, "loss": 0.012702791951596737, "avg_return": 0.8638449311256409, "regret": 7.32807966414839e-05, "entropy": 0.06686392426490784, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:34.901596Z", "loop": 13271, "env_steps": 8154316799, "loss": 0.013657216913998127, "avg_return": 0.8625522255897522, "regret": 7.32807966414839e-05, "entropy": 0.07142719626426697, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:35.755622Z", "loop": 13272, "env_steps": 8154931199, "loss": 0.014276765286922455, "avg_return": 0.8622637987136841, "regret": 7.32807966414839e-05, "entropy": 0.07244391739368439, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:36.609666Z", "loop": 13273, "env_steps": 8155545599, "loss": 0.01389891654253006, "avg_return": 0.8642027974128723, "regret": 7.32807966414839e-05, "entropy": 0.0737772062420845, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:37.463696Z", "loop": 13274, "env_steps": 8156159999, "loss": 0.013707756996154785, "avg_return": 0.8634237051010132, "regret": 7.32807966414839e-05, "entropy": 0.07402367144823074, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:38.317415Z", "loop": 13275, "env_steps": 8156774399, "loss": 0.013737643137574196, "avg_return": 0.8616398572921753, "regret": 7.32807966414839e-05, "entropy": 0.07397294789552689, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:39.172500Z", "loop": 13276, "env_steps": 8157388799, "loss": 0.015020037069916725, "avg_return": 0.8631673455238342, "regret": 7.32807966414839e-05, "entropy": 0.07960788905620575, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:40.028108Z", "loop": 13277, "env_steps": 8158003199, "loss": 0.014761598780751228, "avg_return": 0.8641104102134705, "regret": 7.32807966414839e-05, "entropy": 0.08123577386140823, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:40.883204Z", "loop": 13278, "env_steps": 8158617599, "loss": 0.013963756151497364, "avg_return": 0.8619224429130554, "regret": 7.32807966414839e-05, "entropy": 0.07754828780889511, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:41.737468Z", "loop": 13279, "env_steps": 8159231999, "loss": 0.014951655641198158, "avg_return": 0.8620019555091858, "regret": 7.32807966414839e-05, "entropy": 0.07715150713920593, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:42.632154Z", "loop": 13280, "env_steps": 8159846399, "loss": 0.01602485217154026, "avg_return": 0.8624200820922852, "regret": 0.0022077253088355064, "entropy": 0.08505945652723312, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:43.485131Z", "loop": 13281, "env_steps": 8160460799, "loss": 0.015458427369594574, "avg_return": 0.8619836568832397, "regret": 0.0022077253088355064, "entropy": 0.08131787925958633, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:44.339177Z", "loop": 13282, "env_steps": 8161075199, "loss": 0.015082967467606068, "avg_return": 0.8622208833694458, "regret": 0.0022077253088355064, "entropy": 0.08038780093193054, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:45.192591Z", "loop": 13283, "env_steps": 8161689599, "loss": 0.014869329519569874, "avg_return": 0.8616756200790405, "regret": 0.0022077253088355064, "entropy": 0.08048925548791885, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:46.046811Z", "loop": 13284, "env_steps": 8162303999, "loss": 0.01415517833083868, "avg_return": 0.8625551462173462, "regret": 0.0022077253088355064, "entropy": 0.06986790895462036, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:46.900777Z", "loop": 13285, "env_steps": 8162918399, "loss": 0.015330389142036438, "avg_return": 0.8624719381332397, "regret": 0.0022077253088355064, "entropy": 0.07628311961889267, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:47.754285Z", "loop": 13286, "env_steps": 8163532799, "loss": 0.014120484702289104, "avg_return": 0.862703263759613, "regret": 0.0022077253088355064, "entropy": 0.07551068067550659, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:48.607830Z", "loop": 13287, "env_steps": 8164147199, "loss": 0.013092346489429474, "avg_return": 0.8638415932655334, "regret": 0.0022077253088355064, "entropy": 0.07033227384090424, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:49.461123Z", "loop": 13288, "env_steps": 8164761599, "loss": 0.012585642747581005, "avg_return": 0.8620861768722534, "regret": 0.0022077253088355064, "entropy": 0.0698699802160263, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:50.314381Z", "loop": 13289, "env_steps": 8165375999, "loss": 0.013333543203771114, "avg_return": 0.8637467622756958, "regret": 0.0022077253088355064, "entropy": 0.06922712922096252, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:51.207727Z", "loop": 13290, "env_steps": 8165990399, "loss": 0.013197890482842922, "avg_return": 0.8631313443183899, "regret": 0.00034702903940342367, "entropy": 0.06992550194263458, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:52.062807Z", "loop": 13291, "env_steps": 8166604799, "loss": 0.014207595959305763, "avg_return": 0.8636147379875183, "regret": 0.00034702903940342367, "entropy": 0.07177548855543137, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:52.916787Z", "loop": 13292, "env_steps": 8167219199, "loss": 0.01378933060914278, "avg_return": 0.8624489307403564, "regret": 0.00034702903940342367, "entropy": 0.0683022066950798, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:53.770305Z", "loop": 13293, "env_steps": 8167833599, "loss": 0.013737577013671398, "avg_return": 0.8625741600990295, "regret": 0.00034702903940342367, "entropy": 0.0715533122420311, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:54.624759Z", "loop": 13294, "env_steps": 8168447999, "loss": 0.012496011331677437, "avg_return": 0.8631595969200134, "regret": 0.00034702903940342367, "entropy": 0.06547509133815765, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:55.479975Z", "loop": 13295, "env_steps": 8169062399, "loss": 0.012376493774354458, "avg_return": 0.8647196888923645, "regret": 0.00034702903940342367, "entropy": 0.06823725998401642, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:56.333794Z", "loop": 13296, "env_steps": 8169676799, "loss": 0.011226724833250046, "avg_return": 0.863659679889679, "regret": 0.00034702903940342367, "entropy": 0.0628918781876564, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:57.187953Z", "loop": 13297, "env_steps": 8170291199, "loss": 0.012784289196133614, "avg_return": 0.8635613322257996, "regret": 0.00034702903940342367, "entropy": 0.06858251988887787, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:58.042512Z", "loop": 13298, "env_steps": 8170905599, "loss": 0.012494164519011974, "avg_return": 0.8639223575592041, "regret": 0.00034702903940342367, "entropy": 0.06686791032552719, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:58.897145Z", "loop": 13299, "env_steps": 8171519999, "loss": 0.011355322785675526, "avg_return": 0.86301189661026, "regret": 0.00034702903940342367, "entropy": 0.06301000714302063, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:33:59.791810Z", "loop": 13300, "env_steps": 8172134399, "loss": 0.01248252484947443, "avg_return": 0.8643196821212769, "regret": 0.0004443263460416347, "entropy": 0.06691888719797134, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:00.646063Z", "loop": 13301, "env_steps": 8172748799, "loss": 0.01293596625328064, "avg_return": 0.8633912205696106, "regret": 0.0004443263460416347, "entropy": 0.06912845373153687, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:01.501659Z", "loop": 13302, "env_steps": 8173363199, "loss": 0.012405809946358204, "avg_return": 0.8633867502212524, "regret": 0.0004443263460416347, "entropy": 0.06173489987850189, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:02.356765Z", "loop": 13303, "env_steps": 8173977599, "loss": 0.012090397998690605, "avg_return": 0.8631088733673096, "regret": 0.0004443263460416347, "entropy": 0.06577306240797043, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:03.211703Z", "loop": 13304, "env_steps": 8174591999, "loss": 0.010835892520844936, "avg_return": 0.8630051612854004, "regret": 0.0004443263460416347, "entropy": 0.060018397867679596, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:04.065749Z", "loop": 13305, "env_steps": 8175206399, "loss": 0.01214546151459217, "avg_return": 0.8625192642211914, "regret": 0.0004443263460416347, "entropy": 0.06667179614305496, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:04.919512Z", "loop": 13306, "env_steps": 8175820799, "loss": 0.011599020101130009, "avg_return": 0.8612473607063293, "regret": 0.0004443263460416347, "entropy": 0.06415464729070663, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:05.773841Z", "loop": 13307, "env_steps": 8176435199, "loss": 0.011770631186664104, "avg_return": 0.8620587587356567, "regret": 0.0004443263460416347, "entropy": 0.06467902660369873, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:06.628205Z", "loop": 13308, "env_steps": 8177049599, "loss": 0.012173633091151714, "avg_return": 0.8623524904251099, "regret": 0.0004443263460416347, "entropy": 0.06344844400882721, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:07.483225Z", "loop": 13309, "env_steps": 8177663999, "loss": 0.012010964564979076, "avg_return": 0.8639686107635498, "regret": 0.0004443263460416347, "entropy": 0.061714787036180496, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:08.378346Z", "loop": 13310, "env_steps": 8178278399, "loss": 0.01232950296252966, "avg_return": 0.8626368641853333, "regret": 0.0005838114884682, "entropy": 0.06459733843803406, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:09.232634Z", "loop": 13311, "env_steps": 8178892799, "loss": 0.011847256682813168, "avg_return": 0.8635856509208679, "regret": 0.0005838114884682, "entropy": 0.06310129910707474, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:10.087008Z", "loop": 13312, "env_steps": 8179507199, "loss": 0.012094932608306408, "avg_return": 0.8634584546089172, "regret": 0.0005838114884682, "entropy": 0.06359918415546417, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:10.941961Z", "loop": 13313, "env_steps": 8180121599, "loss": 0.011647951789200306, "avg_return": 0.8652186393737793, "regret": 0.0005838114884682, "entropy": 0.061434242874383926, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:11.797244Z", "loop": 13314, "env_steps": 8180735999, "loss": 0.012548469007015228, "avg_return": 0.8636401295661926, "regret": 0.0005838114884682, "entropy": 0.06596222519874573, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:12.651432Z", "loop": 13315, "env_steps": 8181350399, "loss": 0.011439019814133644, "avg_return": 0.8628319501876831, "regret": 0.0005838114884682, "entropy": 0.06294378638267517, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:13.505028Z", "loop": 13316, "env_steps": 8181964799, "loss": 0.011717201210558414, "avg_return": 0.8641502857208252, "regret": 0.0005838114884682, "entropy": 0.06296371668577194, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:14.360933Z", "loop": 13317, "env_steps": 8182579199, "loss": 0.012261281721293926, "avg_return": 0.8631636500358582, "regret": 0.0005838114884682, "entropy": 0.06891337037086487, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:15.218298Z", "loop": 13318, "env_steps": 8183193599, "loss": 0.01136595569550991, "avg_return": 0.8634476661682129, "regret": 0.0005838114884682, "entropy": 0.06100358068943024, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:16.072471Z", "loop": 13319, "env_steps": 8183807999, "loss": 0.011255471035838127, "avg_return": 0.864625871181488, "regret": 0.0005838114884682, "entropy": 0.06245829164981842, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:16.965093Z", "loop": 13320, "env_steps": 8184422399, "loss": 0.01183021254837513, "avg_return": 0.8632272481918335, "regret": 0.0002789257268887013, "entropy": 0.0618065781891346, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:17.820540Z", "loop": 13321, "env_steps": 8185036799, "loss": 0.012000043876469135, "avg_return": 0.8643585443496704, "regret": 0.0002789257268887013, "entropy": 0.0637897253036499, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:18.675745Z", "loop": 13322, "env_steps": 8185651199, "loss": 0.01258773636072874, "avg_return": 0.863620936870575, "regret": 0.0002789257268887013, "entropy": 0.06545766443014145, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:19.530313Z", "loop": 13323, "env_steps": 8186265599, "loss": 0.012170057743787766, "avg_return": 0.8635426759719849, "regret": 0.0002789257268887013, "entropy": 0.06401218473911285, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:20.384855Z", "loop": 13324, "env_steps": 8186879999, "loss": 0.012567238882184029, "avg_return": 0.863030195236206, "regret": 0.0002789257268887013, "entropy": 0.06619810312986374, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:21.239203Z", "loop": 13325, "env_steps": 8187494399, "loss": 0.011850599199533463, "avg_return": 0.8631113767623901, "regret": 0.0002789257268887013, "entropy": 0.063803531229496, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:22.093376Z", "loop": 13326, "env_steps": 8188108799, "loss": 0.012372463941574097, "avg_return": 0.8643035292625427, "regret": 0.0002789257268887013, "entropy": 0.06824096292257309, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:22.947620Z", "loop": 13327, "env_steps": 8188723199, "loss": 0.011804817244410515, "avg_return": 0.861275851726532, "regret": 0.0002789257268887013, "entropy": 0.06474249064922333, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:23.801264Z", "loop": 13328, "env_steps": 8189337599, "loss": 0.0136283403262496, "avg_return": 0.8633370399475098, "regret": 0.0002789257268887013, "entropy": 0.07271253317594528, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:24.655829Z", "loop": 13329, "env_steps": 8189951999, "loss": 0.012255031615495682, "avg_return": 0.8631391525268555, "regret": 0.0002789257268887013, "entropy": 0.06966584920883179, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:25.549900Z", "loop": 13330, "env_steps": 8190566399, "loss": 0.01431591808795929, "avg_return": 0.8634153604507446, "regret": 0.0012635125312954187, "entropy": 0.06982604414224625, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:26.403807Z", "loop": 13331, "env_steps": 8191180799, "loss": 0.012963393703103065, "avg_return": 0.8632676601409912, "regret": 0.0012635125312954187, "entropy": 0.07257001101970673, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:27.257783Z", "loop": 13332, "env_steps": 8191795199, "loss": 0.012863828800618649, "avg_return": 0.861857533454895, "regret": 0.0012635125312954187, "entropy": 0.07029581069946289, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:28.111310Z", "loop": 13333, "env_steps": 8192409599, "loss": 0.0137339998036623, "avg_return": 0.8622843623161316, "regret": 0.0012635125312954187, "entropy": 0.07220669090747833, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:28.964746Z", "loop": 13334, "env_steps": 8193023999, "loss": 0.012905428186058998, "avg_return": 0.8628329634666443, "regret": 0.0012635125312954187, "entropy": 0.07136650383472443, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:29.819219Z", "loop": 13335, "env_steps": 8193638399, "loss": 0.013492110185325146, "avg_return": 0.8619039058685303, "regret": 0.0012635125312954187, "entropy": 0.07053180038928986, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:30.673445Z", "loop": 13336, "env_steps": 8194252799, "loss": 0.012864201329648495, "avg_return": 0.8622881174087524, "regret": 0.0012635125312954187, "entropy": 0.07220309972763062, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:31.527507Z", "loop": 13337, "env_steps": 8194867199, "loss": 0.013072292320430279, "avg_return": 0.863704264163971, "regret": 0.0012635125312954187, "entropy": 0.07002025097608566, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:32.381413Z", "loop": 13338, "env_steps": 8195481599, "loss": 0.012173393741250038, "avg_return": 0.8633832931518555, "regret": 0.0012635125312954187, "entropy": 0.06657037883996964, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:33.235850Z", "loop": 13339, "env_steps": 8196095999, "loss": 0.013696926645934582, "avg_return": 0.8623563647270203, "regret": 0.0012635125312954187, "entropy": 0.07029231637716293, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:34.129526Z", "loop": 13340, "env_steps": 8196710399, "loss": 0.012158829718828201, "avg_return": 0.8622660636901855, "regret": 0.0005424581468105316, "entropy": 0.06485429406166077, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:34.985094Z", "loop": 13341, "env_steps": 8197324799, "loss": 0.012813987210392952, "avg_return": 0.862578272819519, "regret": 0.0005424581468105316, "entropy": 0.0700034648180008, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:35.838960Z", "loop": 13342, "env_steps": 8197939199, "loss": 0.013499637134373188, "avg_return": 0.8624475598335266, "regret": 0.0005424581468105316, "entropy": 0.07202651351690292, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:36.692363Z", "loop": 13343, "env_steps": 8198553599, "loss": 0.01405172236263752, "avg_return": 0.8621244430541992, "regret": 0.0005424581468105316, "entropy": 0.07043039053678513, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:37.547178Z", "loop": 13344, "env_steps": 8199167999, "loss": 0.014173110015690327, "avg_return": 0.8631439208984375, "regret": 0.0005424581468105316, "entropy": 0.07468996196985245, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:38.402824Z", "loop": 13345, "env_steps": 8199782399, "loss": 0.014258590526878834, "avg_return": 0.8634154200553894, "regret": 0.0005424581468105316, "entropy": 0.0721026286482811, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:39.257276Z", "loop": 13346, "env_steps": 8200396799, "loss": 0.01297982782125473, "avg_return": 0.8630930781364441, "regret": 0.0005424581468105316, "entropy": 0.07095913589000702, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:40.111825Z", "loop": 13347, "env_steps": 8201011199, "loss": 0.012624706141650677, "avg_return": 0.8638091087341309, "regret": 0.0005424581468105316, "entropy": 0.07199329137802124, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:40.967233Z", "loop": 13348, "env_steps": 8201625599, "loss": 0.012377976439893246, "avg_return": 0.8626005053520203, "regret": 0.0005424581468105316, "entropy": 0.06760213524103165, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:41.823415Z", "loop": 13349, "env_steps": 8202239999, "loss": 0.013154088519513607, "avg_return": 0.8629984855651855, "regret": 0.0005424581468105316, "entropy": 0.06865733861923218, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:42.718779Z", "loop": 13350, "env_steps": 8202854399, "loss": 0.012228745967149734, "avg_return": 0.8631536960601807, "regret": 0.00048070549382828176, "entropy": 0.0661471039056778, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:43.573077Z", "loop": 13351, "env_steps": 8203468799, "loss": 0.012529946863651276, "avg_return": 0.86286461353302, "regret": 0.00048070549382828176, "entropy": 0.06809982657432556, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:44.427969Z", "loop": 13352, "env_steps": 8204083199, "loss": 0.011916328221559525, "avg_return": 0.8625047206878662, "regret": 0.00048070549382828176, "entropy": 0.06645626574754715, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:45.282842Z", "loop": 13353, "env_steps": 8204697599, "loss": 0.01231613103300333, "avg_return": 0.8634861707687378, "regret": 0.00048070549382828176, "entropy": 0.06579240411520004, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:46.137400Z", "loop": 13354, "env_steps": 8205311999, "loss": 0.011160054244101048, "avg_return": 0.8638548254966736, "regret": 0.00048070549382828176, "entropy": 0.057805854827165604, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:46.992247Z", "loop": 13355, "env_steps": 8205926399, "loss": 0.010962428525090218, "avg_return": 0.8642651438713074, "regret": 0.00048070549382828176, "entropy": 0.06073971465229988, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:47.846305Z", "loop": 13356, "env_steps": 8206540799, "loss": 0.011390372179448605, "avg_return": 0.8634387254714966, "regret": 0.00048070549382828176, "entropy": 0.059679027646780014, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:48.701131Z", "loop": 13357, "env_steps": 8207155199, "loss": 0.010744025930762291, "avg_return": 0.8631278872489929, "regret": 0.00048070549382828176, "entropy": 0.05781020596623421, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:49.555417Z", "loop": 13358, "env_steps": 8207769599, "loss": 0.010523082688450813, "avg_return": 0.8636714816093445, "regret": 0.00048070549382828176, "entropy": 0.058861106634140015, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:50.409359Z", "loop": 13359, "env_steps": 8208383999, "loss": 0.011503285728394985, "avg_return": 0.8630746603012085, "regret": 0.00048070549382828176, "entropy": 0.05783993750810623, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:51.303081Z", "loop": 13360, "env_steps": 8208998399, "loss": 0.011331434361636639, "avg_return": 0.8623946309089661, "regret": 0.0005995433311909437, "entropy": 0.06045129522681236, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:52.157213Z", "loop": 13361, "env_steps": 8209612799, "loss": 0.010545755736529827, "avg_return": 0.8626423478126526, "regret": 0.0005995433311909437, "entropy": 0.0594039224088192, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:53.011671Z", "loop": 13362, "env_steps": 8210227199, "loss": 0.011313717812299728, "avg_return": 0.8619535565376282, "regret": 0.0005995433311909437, "entropy": 0.05918604135513306, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:53.866035Z", "loop": 13363, "env_steps": 8210841599, "loss": 0.01149061881005764, "avg_return": 0.8624621629714966, "regret": 0.0005995433311909437, "entropy": 0.06189128756523132, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:54.720162Z", "loop": 13364, "env_steps": 8211455999, "loss": 0.011388120241463184, "avg_return": 0.8622666597366333, "regret": 0.0005995433311909437, "entropy": 0.060093995183706284, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:55.574323Z", "loop": 13365, "env_steps": 8212070399, "loss": 0.010997236706316471, "avg_return": 0.8623903393745422, "regret": 0.0005995433311909437, "entropy": 0.057690996676683426, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:56.429097Z", "loop": 13366, "env_steps": 8212684799, "loss": 0.01159258559346199, "avg_return": 0.8635827898979187, "regret": 0.0005995433311909437, "entropy": 0.06212925165891647, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:57.282306Z", "loop": 13367, "env_steps": 8213299199, "loss": 0.011305250227451324, "avg_return": 0.8651223182678223, "regret": 0.0005995433311909437, "entropy": 0.06131529435515404, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:58.136566Z", "loop": 13368, "env_steps": 8213913599, "loss": 0.011621051467955112, "avg_return": 0.8637823462486267, "regret": 0.0005995433311909437, "entropy": 0.06113768368959427, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:58.990067Z", "loop": 13369, "env_steps": 8214527999, "loss": 0.011295468546450138, "avg_return": 0.8625771403312683, "regret": 0.0005995433311909437, "entropy": 0.06262204796075821, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:34:59.883708Z", "loop": 13370, "env_steps": 8215142399, "loss": 0.012622629292309284, "avg_return": 0.8631207346916199, "regret": 0.0006251654704101384, "entropy": 0.06474048644304276, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:00.738105Z", "loop": 13371, "env_steps": 8215756799, "loss": 0.011317580007016659, "avg_return": 0.8626550436019897, "regret": 0.0006251654704101384, "entropy": 0.05971761792898178, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:01.593257Z", "loop": 13372, "env_steps": 8216371199, "loss": 0.012003227137029171, "avg_return": 0.8638993501663208, "regret": 0.0006251654704101384, "entropy": 0.06711672991514206, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:02.448373Z", "loop": 13373, "env_steps": 8216985599, "loss": 0.012028371915221214, "avg_return": 0.8627389669418335, "regret": 0.0006251654704101384, "entropy": 0.064459890127182, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:03.302710Z", "loop": 13374, "env_steps": 8217599999, "loss": 0.011788923293352127, "avg_return": 0.8620920181274414, "regret": 0.0006251654704101384, "entropy": 0.06439510732889175, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:04.155866Z", "loop": 13375, "env_steps": 8218214399, "loss": 0.013003756292164326, "avg_return": 0.8637591004371643, "regret": 0.0006251654704101384, "entropy": 0.06762956082820892, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:05.010764Z", "loop": 13376, "env_steps": 8218828799, "loss": 0.014002750627696514, "avg_return": 0.8611509203910828, "regret": 0.0006251654704101384, "entropy": 0.07215017080307007, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:05.865215Z", "loop": 13377, "env_steps": 8219443199, "loss": 0.01483038067817688, "avg_return": 0.861247181892395, "regret": 0.0006251654704101384, "entropy": 0.07506491243839264, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:06.718443Z", "loop": 13378, "env_steps": 8220057599, "loss": 0.015925927087664604, "avg_return": 0.8610309958457947, "regret": 0.0006251654704101384, "entropy": 0.07815136015415192, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:07.571346Z", "loop": 13379, "env_steps": 8220671999, "loss": 0.015022249892354012, "avg_return": 0.8614246845245361, "regret": 0.0006251654704101384, "entropy": 0.07506226003170013, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:08.467215Z", "loop": 13380, "env_steps": 8221286399, "loss": 0.015284053049981594, "avg_return": 0.8618816137313843, "regret": 0.0022341907024383545, "entropy": 0.0774693414568901, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:09.322375Z", "loop": 13381, "env_steps": 8221900799, "loss": 0.01678798906505108, "avg_return": 0.8618367910385132, "regret": 0.0022341907024383545, "entropy": 0.08218422532081604, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:10.176059Z", "loop": 13382, "env_steps": 8222515199, "loss": 0.01704222336411476, "avg_return": 0.8604315519332886, "regret": 0.0022341907024383545, "entropy": 0.08728066086769104, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:11.029645Z", "loop": 13383, "env_steps": 8223129599, "loss": 0.019527293741703033, "avg_return": 0.8575991988182068, "regret": 0.0022341907024383545, "entropy": 0.0884062796831131, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:11.883877Z", "loop": 13384, "env_steps": 8223743999, "loss": 0.016963740810751915, "avg_return": 0.8595841526985168, "regret": 0.0022341907024383545, "entropy": 0.08367966115474701, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:12.738292Z", "loop": 13385, "env_steps": 8224358399, "loss": 0.018703589215874672, "avg_return": 0.859164834022522, "regret": 0.0022341907024383545, "entropy": 0.08665481209754944, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:13.592493Z", "loop": 13386, "env_steps": 8224972799, "loss": 0.01835421659052372, "avg_return": 0.8598518967628479, "regret": 0.0022341907024383545, "entropy": 0.08654213696718216, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:14.446016Z", "loop": 13387, "env_steps": 8225587199, "loss": 0.014304744079709053, "avg_return": 0.8632885813713074, "regret": 0.0022341907024383545, "entropy": 0.07707539200782776, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:15.300334Z", "loop": 13388, "env_steps": 8226201599, "loss": 0.012968383729457855, "avg_return": 0.8627020716667175, "regret": 0.0022341907024383545, "entropy": 0.06778906285762787, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:16.153828Z", "loop": 13389, "env_steps": 8226815999, "loss": 0.013605976477265358, "avg_return": 0.8638355731964111, "regret": 0.0022341907024383545, "entropy": 0.07097026705741882, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:17.047924Z", "loop": 13390, "env_steps": 8227430399, "loss": 0.012702691368758678, "avg_return": 0.8627562522888184, "regret": 0.00028667855076491833, "entropy": 0.06652739644050598, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:17.902997Z", "loop": 13391, "env_steps": 8228044799, "loss": 0.011625668033957481, "avg_return": 0.8626301288604736, "regret": 0.00028667855076491833, "entropy": 0.06382578611373901, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:18.757523Z", "loop": 13392, "env_steps": 8228659199, "loss": 0.011829745955765247, "avg_return": 0.8636793494224548, "regret": 0.00028667855076491833, "entropy": 0.06360872089862823, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:19.610716Z", "loop": 13393, "env_steps": 8229273599, "loss": 0.013212655670940876, "avg_return": 0.8630478382110596, "regret": 0.00028667855076491833, "entropy": 0.06934010982513428, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:20.465061Z", "loop": 13394, "env_steps": 8229887999, "loss": 0.01268541719764471, "avg_return": 0.8631113767623901, "regret": 0.00028667855076491833, "entropy": 0.06864913552999496, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:21.319386Z", "loop": 13395, "env_steps": 8230502399, "loss": 0.012952014803886414, "avg_return": 0.8643819093704224, "regret": 0.00028667855076491833, "entropy": 0.0684974417090416, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:22.173038Z", "loop": 13396, "env_steps": 8231116799, "loss": 0.012739039957523346, "avg_return": 0.8644809126853943, "regret": 0.00028667855076491833, "entropy": 0.07319168001413345, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:23.028372Z", "loop": 13397, "env_steps": 8231731199, "loss": 0.014248983934521675, "avg_return": 0.8632902503013611, "regret": 0.00028667855076491833, "entropy": 0.07380685210227966, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:23.883746Z", "loop": 13398, "env_steps": 8232345599, "loss": 0.012425379827618599, "avg_return": 0.8630886077880859, "regret": 0.00028667855076491833, "entropy": 0.0664382129907608, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:24.738675Z", "loop": 13399, "env_steps": 8232959999, "loss": 0.012131067924201488, "avg_return": 0.8632315993309021, "regret": 0.00028667855076491833, "entropy": 0.06851208209991455, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:25.634698Z", "loop": 13400, "env_steps": 8233574399, "loss": 0.013328589498996735, "avg_return": 0.8634320497512817, "regret": 0.00012069263902958483, "entropy": 0.07245217263698578, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:26.488376Z", "loop": 13401, "env_steps": 8234188799, "loss": 0.01365519780665636, "avg_return": 0.8631402850151062, "regret": 0.00012069263902958483, "entropy": 0.07529798895120621, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:27.341622Z", "loop": 13402, "env_steps": 8234803199, "loss": 0.013320478610694408, "avg_return": 0.8634074926376343, "regret": 0.00012069263902958483, "entropy": 0.07357802987098694, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:28.196137Z", "loop": 13403, "env_steps": 8235417599, "loss": 0.013998858630657196, "avg_return": 0.8622379899024963, "regret": 0.00012069263902958483, "entropy": 0.07764826714992523, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:29.050562Z", "loop": 13404, "env_steps": 8236031999, "loss": 0.013587339781224728, "avg_return": 0.8646914958953857, "regret": 0.00012069263902958483, "entropy": 0.07424324750900269, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:29.903800Z", "loop": 13405, "env_steps": 8236646399, "loss": 0.014099597930908203, "avg_return": 0.863050639629364, "regret": 0.00012069263902958483, "entropy": 0.07776778936386108, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:30.756880Z", "loop": 13406, "env_steps": 8237260799, "loss": 0.014174528419971466, "avg_return": 0.8635518550872803, "regret": 0.00012069263902958483, "entropy": 0.07829569280147552, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:31.611401Z", "loop": 13407, "env_steps": 8237875199, "loss": 0.013262631371617317, "avg_return": 0.8632510304450989, "regret": 0.00012069263902958483, "entropy": 0.0730200782418251, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:32.465287Z", "loop": 13408, "env_steps": 8238489599, "loss": 0.014063797891139984, "avg_return": 0.8634787201881409, "regret": 0.00012069263902958483, "entropy": 0.07222536951303482, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:33.318820Z", "loop": 13409, "env_steps": 8239103999, "loss": 0.013344462029635906, "avg_return": 0.8642008900642395, "regret": 0.00012069263902958483, "entropy": 0.07214087247848511, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:34.212479Z", "loop": 13410, "env_steps": 8239718399, "loss": 0.013841602019965649, "avg_return": 0.8630064129829407, "regret": 0.00017517532978672534, "entropy": 0.07356058061122894, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:35.066470Z", "loop": 13411, "env_steps": 8240332799, "loss": 0.01325534749776125, "avg_return": 0.8636670112609863, "regret": 0.00017517532978672534, "entropy": 0.07147682458162308, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:35.919971Z", "loop": 13412, "env_steps": 8240947199, "loss": 0.013106276281177998, "avg_return": 0.8644962906837463, "regret": 0.00017517532978672534, "entropy": 0.07251976430416107, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:36.773570Z", "loop": 13413, "env_steps": 8241561599, "loss": 0.0131945526227355, "avg_return": 0.8632479310035706, "regret": 0.00017517532978672534, "entropy": 0.07149677723646164, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:37.627836Z", "loop": 13414, "env_steps": 8242175999, "loss": 0.013708390295505524, "avg_return": 0.8640230298042297, "regret": 0.00017517532978672534, "entropy": 0.07541502267122269, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:38.482957Z", "loop": 13415, "env_steps": 8242790399, "loss": 0.014541064389050007, "avg_return": 0.8637754321098328, "regret": 0.00017517532978672534, "entropy": 0.07214726507663727, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:39.337706Z", "loop": 13416, "env_steps": 8243404799, "loss": 0.013911937363445759, "avg_return": 0.8639203310012817, "regret": 0.00017517532978672534, "entropy": 0.0748106837272644, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:40.191816Z", "loop": 13417, "env_steps": 8244019199, "loss": 0.0143112912774086, "avg_return": 0.8640570044517517, "regret": 0.00017517532978672534, "entropy": 0.07555421441793442, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:41.046382Z", "loop": 13418, "env_steps": 8244633599, "loss": 0.013795241713523865, "avg_return": 0.8635947704315186, "regret": 0.00017517532978672534, "entropy": 0.07378526777029037, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:41.903846Z", "loop": 13419, "env_steps": 8245247999, "loss": 0.013060200028121471, "avg_return": 0.8633481860160828, "regret": 0.00017517532978672534, "entropy": 0.0699751153588295, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:42.800811Z", "loop": 13420, "env_steps": 8245862399, "loss": 0.013597299344837666, "avg_return": 0.8635187745094299, "regret": 0.00018896959954872727, "entropy": 0.07228962332010269, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:43.654413Z", "loop": 13421, "env_steps": 8246476799, "loss": 0.013044962659478188, "avg_return": 0.8632358908653259, "regret": 0.00018896959954872727, "entropy": 0.06880735605955124, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:44.509040Z", "loop": 13422, "env_steps": 8247091199, "loss": 0.01568002626299858, "avg_return": 0.8622642159461975, "regret": 0.00018896959954872727, "entropy": 0.07830671221017838, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:45.363136Z", "loop": 13423, "env_steps": 8247705599, "loss": 0.014133847318589687, "avg_return": 0.8625385761260986, "regret": 0.00018896959954872727, "entropy": 0.07317069917917252, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:46.216893Z", "loop": 13424, "env_steps": 8248319999, "loss": 0.015043141320347786, "avg_return": 0.8646882176399231, "regret": 0.00018896959954872727, "entropy": 0.0793071761727333, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:47.071058Z", "loop": 13425, "env_steps": 8248934399, "loss": 0.014357593841850758, "avg_return": 0.8629469871520996, "regret": 0.00018896959954872727, "entropy": 0.07716494053602219, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:47.925369Z", "loop": 13426, "env_steps": 8249548799, "loss": 0.015195123851299286, "avg_return": 0.8619692325592041, "regret": 0.00018896959954872727, "entropy": 0.07847929745912552, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:48.781239Z", "loop": 13427, "env_steps": 8250163199, "loss": 0.0156315378844738, "avg_return": 0.8632586598396301, "regret": 0.00018896959954872727, "entropy": 0.08068490773439407, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:49.635735Z", "loop": 13428, "env_steps": 8250777599, "loss": 0.015308159403502941, "avg_return": 0.8641824722290039, "regret": 0.00018896959954872727, "entropy": 0.07938304543495178, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:50.489746Z", "loop": 13429, "env_steps": 8251391999, "loss": 0.015911757946014404, "avg_return": 0.8620972633361816, "regret": 0.00018896959954872727, "entropy": 0.07789679616689682, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:51.384255Z", "loop": 13430, "env_steps": 8252006399, "loss": 0.01601487584412098, "avg_return": 0.862819254398346, "regret": 0.0006711929454468191, "entropy": 0.08059921860694885, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:52.239718Z", "loop": 13431, "env_steps": 8252620799, "loss": 0.01569051295518875, "avg_return": 0.8646021485328674, "regret": 0.0006711929454468191, "entropy": 0.08241929113864899, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:53.094017Z", "loop": 13432, "env_steps": 8253235199, "loss": 0.01659802906215191, "avg_return": 0.8628835082054138, "regret": 0.0006711929454468191, "entropy": 0.08457615226507187, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:53.947740Z", "loop": 13433, "env_steps": 8253849599, "loss": 0.01651204749941826, "avg_return": 0.8647978901863098, "regret": 0.0006711929454468191, "entropy": 0.08691004663705826, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:54.801937Z", "loop": 13434, "env_steps": 8254463999, "loss": 0.016620885580778122, "avg_return": 0.8638273477554321, "regret": 0.0006711929454468191, "entropy": 0.08572651445865631, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:55.656604Z", "loop": 13435, "env_steps": 8255078399, "loss": 0.015441265888512135, "avg_return": 0.8623904585838318, "regret": 0.0006711929454468191, "entropy": 0.08038362115621567, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:56.511410Z", "loop": 13436, "env_steps": 8255692799, "loss": 0.014616894535720348, "avg_return": 0.8638684153556824, "regret": 0.0006711929454468191, "entropy": 0.07531467080116272, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:57.367130Z", "loop": 13437, "env_steps": 8256307199, "loss": 0.014016816392540932, "avg_return": 0.8638836741447449, "regret": 0.0006711929454468191, "entropy": 0.0748707577586174, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:58.222549Z", "loop": 13438, "env_steps": 8256921599, "loss": 0.013628735207021236, "avg_return": 0.8636769652366638, "regret": 0.0006711929454468191, "entropy": 0.07425691932439804, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:59.075882Z", "loop": 13439, "env_steps": 8257535999, "loss": 0.014137898571789265, "avg_return": 0.8620056509971619, "regret": 0.0006711929454468191, "entropy": 0.07489839196205139, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:35:59.970189Z", "loop": 13440, "env_steps": 8258150399, "loss": 0.013845272362232208, "avg_return": 0.8639233708381653, "regret": 0.0005544269224628806, "entropy": 0.07278887927532196, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:00.823706Z", "loop": 13441, "env_steps": 8258764799, "loss": 0.014325574040412903, "avg_return": 0.863732635974884, "regret": 0.0005544269224628806, "entropy": 0.07581717520952225, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:01.677907Z", "loop": 13442, "env_steps": 8259379199, "loss": 0.014462949708104134, "avg_return": 0.8617004752159119, "regret": 0.0005544269224628806, "entropy": 0.08131035417318344, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:02.532267Z", "loop": 13443, "env_steps": 8259993599, "loss": 0.014097395353019238, "avg_return": 0.8621730804443359, "regret": 0.0005544269224628806, "entropy": 0.07762457430362701, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:03.386961Z", "loop": 13444, "env_steps": 8260607999, "loss": 0.015178287401795387, "avg_return": 0.8627086877822876, "regret": 0.0005544269224628806, "entropy": 0.0835903212428093, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:04.240690Z", "loop": 13445, "env_steps": 8261222399, "loss": 0.014302982948720455, "avg_return": 0.8623645305633545, "regret": 0.0005544269224628806, "entropy": 0.08089283853769302, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:05.094355Z", "loop": 13446, "env_steps": 8261836799, "loss": 0.015695208683609962, "avg_return": 0.862957775592804, "regret": 0.0005544269224628806, "entropy": 0.08926908671855927, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:05.948603Z", "loop": 13447, "env_steps": 8262451199, "loss": 0.016503944993019104, "avg_return": 0.8621577024459839, "regret": 0.0005544269224628806, "entropy": 0.09102955460548401, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:06.803832Z", "loop": 13448, "env_steps": 8263065599, "loss": 0.01758977584540844, "avg_return": 0.8600673675537109, "regret": 0.0005544269224628806, "entropy": 0.09997457265853882, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:07.659504Z", "loop": 13449, "env_steps": 8263679999, "loss": 0.017637770622968674, "avg_return": 0.8616085052490234, "regret": 0.0005544269224628806, "entropy": 0.09716030955314636, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:08.554725Z", "loop": 13450, "env_steps": 8264294399, "loss": 0.018138235434889793, "avg_return": 0.8609719276428223, "regret": 0.0015881250146776438, "entropy": 0.10336998105049133, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:09.407676Z", "loop": 13451, "env_steps": 8264908799, "loss": 0.017845239490270615, "avg_return": 0.8594220280647278, "regret": 0.0015881250146776438, "entropy": 0.09994146972894669, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:10.261159Z", "loop": 13452, "env_steps": 8265523199, "loss": 0.016757531091570854, "avg_return": 0.8625292181968689, "regret": 0.0015881250146776438, "entropy": 0.09654713422060013, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:11.115463Z", "loop": 13453, "env_steps": 8266137599, "loss": 0.016503239050507545, "avg_return": 0.862209677696228, "regret": 0.0015881250146776438, "entropy": 0.09498005360364914, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:11.971292Z", "loop": 13454, "env_steps": 8266751999, "loss": 0.01705947145819664, "avg_return": 0.8640795946121216, "regret": 0.0015881250146776438, "entropy": 0.09280849248170853, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:12.825602Z", "loop": 13455, "env_steps": 8267366399, "loss": 0.015703458338975906, "avg_return": 0.8634471893310547, "regret": 0.0015881250146776438, "entropy": 0.08650604635477066, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:13.679934Z", "loop": 13456, "env_steps": 8267980799, "loss": 0.01717095635831356, "avg_return": 0.8624377846717834, "regret": 0.0015881250146776438, "entropy": 0.0917346179485321, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:14.535104Z", "loop": 13457, "env_steps": 8268595199, "loss": 0.0181601382791996, "avg_return": 0.8629007339477539, "regret": 0.0015881250146776438, "entropy": 0.09558823704719543, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:15.390094Z", "loop": 13458, "env_steps": 8269209599, "loss": 0.016559291630983353, "avg_return": 0.8642891645431519, "regret": 0.0015881250146776438, "entropy": 0.08486539870500565, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:16.244625Z", "loop": 13459, "env_steps": 8269823999, "loss": 0.016800548881292343, "avg_return": 0.8623976111412048, "regret": 0.0015881250146776438, "entropy": 0.08999167382717133, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:17.138427Z", "loop": 13460, "env_steps": 8270438399, "loss": 0.016582464799284935, "avg_return": 0.8622257709503174, "regret": 0.0005376280751079321, "entropy": 0.08873258531093597, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:17.993654Z", "loop": 13461, "env_steps": 8271052799, "loss": 0.017151182517409325, "avg_return": 0.8633687496185303, "regret": 0.0005376280751079321, "entropy": 0.09271307289600372, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:18.848998Z", "loop": 13462, "env_steps": 8271667199, "loss": 0.01912185549736023, "avg_return": 0.8626843690872192, "regret": 0.0005376280751079321, "entropy": 0.09406519681215286, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:19.704197Z", "loop": 13463, "env_steps": 8272281599, "loss": 0.017320267856121063, "avg_return": 0.862508237361908, "regret": 0.0005376280751079321, "entropy": 0.09513535350561142, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:20.558196Z", "loop": 13464, "env_steps": 8272895999, "loss": 0.018238341435790062, "avg_return": 0.8635402917861938, "regret": 0.0005376280751079321, "entropy": 0.09355917572975159, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:21.413153Z", "loop": 13465, "env_steps": 8273510399, "loss": 0.017950033769011497, "avg_return": 0.8624333143234253, "regret": 0.0005376280751079321, "entropy": 0.0987212210893631, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:22.267340Z", "loop": 13466, "env_steps": 8274124799, "loss": 0.019329102709889412, "avg_return": 0.8639917373657227, "regret": 0.0005376280751079321, "entropy": 0.10111334174871445, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:23.121166Z", "loop": 13467, "env_steps": 8274739199, "loss": 0.020538149401545525, "avg_return": 0.863949179649353, "regret": 0.0005376280751079321, "entropy": 0.10686091333627701, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:23.975165Z", "loop": 13468, "env_steps": 8275353599, "loss": 0.02240767329931259, "avg_return": 0.8616763353347778, "regret": 0.0005376280751079321, "entropy": 0.11243367940187454, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:24.829545Z", "loop": 13469, "env_steps": 8275967999, "loss": 0.02304612658917904, "avg_return": 0.8640658855438232, "regret": 0.0005376280751079321, "entropy": 0.11398705095052719, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:25.722393Z", "loop": 13470, "env_steps": 8276582399, "loss": 0.025061016902327538, "avg_return": 0.8649235367774963, "regret": 0.0008822640520520508, "entropy": 0.12544770538806915, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:26.575730Z", "loop": 13471, "env_steps": 8277196799, "loss": 0.02603970840573311, "avg_return": 0.8618865013122559, "regret": 0.0008822640520520508, "entropy": 0.1278480887413025, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:27.430667Z", "loop": 13472, "env_steps": 8277811199, "loss": 0.026120051741600037, "avg_return": 0.8621883392333984, "regret": 0.0008822640520520508, "entropy": 0.1323210746049881, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:28.285262Z", "loop": 13473, "env_steps": 8278425599, "loss": 0.024141328409314156, "avg_return": 0.8622850775718689, "regret": 0.0008822640520520508, "entropy": 0.1223084032535553, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:29.139020Z", "loop": 13474, "env_steps": 8279039999, "loss": 0.023903964087367058, "avg_return": 0.8613120913505554, "regret": 0.0008822640520520508, "entropy": 0.12593986093997955, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:29.994099Z", "loop": 13475, "env_steps": 8279654399, "loss": 0.02418622374534607, "avg_return": 0.860855221748352, "regret": 0.0008822640520520508, "entropy": 0.1244363859295845, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:30.848779Z", "loop": 13476, "env_steps": 8280268799, "loss": 0.024096231907606125, "avg_return": 0.8629817962646484, "regret": 0.0008822640520520508, "entropy": 0.1288410872220993, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:31.704600Z", "loop": 13477, "env_steps": 8280883199, "loss": 0.02435377798974514, "avg_return": 0.8609326481819153, "regret": 0.0008822640520520508, "entropy": 0.13004779815673828, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:32.558574Z", "loop": 13478, "env_steps": 8281497599, "loss": 0.026239633560180664, "avg_return": 0.8621035218238831, "regret": 0.0008822640520520508, "entropy": 0.13668902218341827, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:33.413688Z", "loop": 13479, "env_steps": 8282111999, "loss": 0.02652149833738804, "avg_return": 0.8612599968910217, "regret": 0.0008822640520520508, "entropy": 0.13776424527168274, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:34.309692Z", "loop": 13480, "env_steps": 8282726399, "loss": 0.026607638224959373, "avg_return": 0.8609493970870972, "regret": 0.0026326680090278387, "entropy": 0.14129222929477692, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:35.164226Z", "loop": 13481, "env_steps": 8283340799, "loss": 0.027548033744096756, "avg_return": 0.8619935512542725, "regret": 0.0026326680090278387, "entropy": 0.14523063600063324, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:36.017850Z", "loop": 13482, "env_steps": 8283955199, "loss": 0.027884239330887794, "avg_return": 0.8605328798294067, "regret": 0.0026326680090278387, "entropy": 0.14692537486553192, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:36.870832Z", "loop": 13483, "env_steps": 8284569599, "loss": 0.028904661536216736, "avg_return": 0.8602030873298645, "regret": 0.0026326680090278387, "entropy": 0.14695878326892853, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:37.724717Z", "loop": 13484, "env_steps": 8285183999, "loss": 0.028208037838339806, "avg_return": 0.8603044748306274, "regret": 0.0026326680090278387, "entropy": 0.1417333334684372, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:38.579552Z", "loop": 13485, "env_steps": 8285798399, "loss": 0.028018508106470108, "avg_return": 0.8609919548034668, "regret": 0.0026326680090278387, "entropy": 0.14331920444965363, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:39.433028Z", "loop": 13486, "env_steps": 8286412799, "loss": 0.026606321334838867, "avg_return": 0.8598434925079346, "regret": 0.0026326680090278387, "entropy": 0.14041626453399658, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:40.285558Z", "loop": 13487, "env_steps": 8287027199, "loss": 0.02539943717420101, "avg_return": 0.8606853485107422, "regret": 0.0026326680090278387, "entropy": 0.13025422394275665, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:41.138451Z", "loop": 13488, "env_steps": 8287641599, "loss": 0.023206695914268494, "avg_return": 0.8612938523292542, "regret": 0.0026326680090278387, "entropy": 0.12408142536878586, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:41.993119Z", "loop": 13489, "env_steps": 8288255999, "loss": 0.021676747128367424, "avg_return": 0.8619469404220581, "regret": 0.0026326680090278387, "entropy": 0.11349911987781525, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:42.887936Z", "loop": 13490, "env_steps": 8288870399, "loss": 0.020039308816194534, "avg_return": 0.8624693155288696, "regret": 0.0018838347168639302, "entropy": 0.10795856267213821, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:43.741593Z", "loop": 13491, "env_steps": 8289484799, "loss": 0.019668392837047577, "avg_return": 0.8624080419540405, "regret": 0.0018838347168639302, "entropy": 0.1056952029466629, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:44.595280Z", "loop": 13492, "env_steps": 8290099199, "loss": 0.019312938675284386, "avg_return": 0.8616121411323547, "regret": 0.0018838347168639302, "entropy": 0.10092081129550934, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:45.449095Z", "loop": 13493, "env_steps": 8290713599, "loss": 0.017508614808321, "avg_return": 0.8628220558166504, "regret": 0.0018838347168639302, "entropy": 0.09596550464630127, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:46.303042Z", "loop": 13494, "env_steps": 8291327999, "loss": 0.018276892602443695, "avg_return": 0.8611147403717041, "regret": 0.0018838347168639302, "entropy": 0.0953025221824646, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:47.156221Z", "loop": 13495, "env_steps": 8291942399, "loss": 0.018707482144236565, "avg_return": 0.8622148633003235, "regret": 0.0018838347168639302, "entropy": 0.0933397188782692, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:48.009528Z", "loop": 13496, "env_steps": 8292556799, "loss": 0.018559444695711136, "avg_return": 0.8599485754966736, "regret": 0.0018838347168639302, "entropy": 0.09692306816577911, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:48.863742Z", "loop": 13497, "env_steps": 8293171199, "loss": 0.01825331710278988, "avg_return": 0.8619217276573181, "regret": 0.0018838347168639302, "entropy": 0.09638847410678864, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:49.717447Z", "loop": 13498, "env_steps": 8293785599, "loss": 0.018564339727163315, "avg_return": 0.8612498044967651, "regret": 0.0018838347168639302, "entropy": 0.09602658450603485, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:50.571835Z", "loop": 13499, "env_steps": 8294399999, "loss": 0.018123487010598183, "avg_return": 0.860514760017395, "regret": 0.0018838347168639302, "entropy": 0.09426368772983551, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:51.465541Z", "loop": 13500, "env_steps": 8295014399, "loss": 0.01957685686647892, "avg_return": 0.8606005907058716, "regret": 0.0029586064629256725, "entropy": 0.10034286975860596, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:52.318598Z", "loop": 13501, "env_steps": 8295628799, "loss": 0.018940521404147148, "avg_return": 0.8600435853004456, "regret": 0.0029586064629256725, "entropy": 0.09788326174020767, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:53.172177Z", "loop": 13502, "env_steps": 8296243199, "loss": 0.017715245485305786, "avg_return": 0.8623690009117126, "regret": 0.0029586064629256725, "entropy": 0.09167320281267166, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:54.026647Z", "loop": 13503, "env_steps": 8296857599, "loss": 0.017853181809186935, "avg_return": 0.8608047962188721, "regret": 0.0029586064629256725, "entropy": 0.091563381254673, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:54.881677Z", "loop": 13504, "env_steps": 8297471999, "loss": 0.017366483807563782, "avg_return": 0.8617578148841858, "regret": 0.0029586064629256725, "entropy": 0.08897681534290314, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:55.735547Z", "loop": 13505, "env_steps": 8298086399, "loss": 0.016911687329411507, "avg_return": 0.8619968891143799, "regret": 0.0029586064629256725, "entropy": 0.08563220500946045, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:56.589590Z", "loop": 13506, "env_steps": 8298700799, "loss": 0.01749902404844761, "avg_return": 0.8630121350288391, "regret": 0.0029586064629256725, "entropy": 0.08931169658899307, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:57.443555Z", "loop": 13507, "env_steps": 8299315199, "loss": 0.016256917268037796, "avg_return": 0.8633736371994019, "regret": 0.0029586064629256725, "entropy": 0.0852665975689888, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:58.298218Z", "loop": 13508, "env_steps": 8299929599, "loss": 0.01708747260272503, "avg_return": 0.8621326684951782, "regret": 0.0029586064629256725, "entropy": 0.08722337335348129, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:36:59.152132Z", "loop": 13509, "env_steps": 8300543999, "loss": 0.016468942165374756, "avg_return": 0.8637323379516602, "regret": 0.0029586064629256725, "entropy": 0.08598311990499496, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:00.044614Z", "loop": 13510, "env_steps": 8301158399, "loss": 0.017400750890374184, "avg_return": 0.8634052872657776, "regret": 0.0004762991738971323, "entropy": 0.08856981992721558, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:00.898859Z", "loop": 13511, "env_steps": 8301772799, "loss": 0.01839631050825119, "avg_return": 0.8617566227912903, "regret": 0.0004762991738971323, "entropy": 0.09256843477487564, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:01.754688Z", "loop": 13512, "env_steps": 8302387199, "loss": 0.018904875963926315, "avg_return": 0.8615909814834595, "regret": 0.0004762991738971323, "entropy": 0.09612679481506348, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:02.609632Z", "loop": 13513, "env_steps": 8303001599, "loss": 0.020038625225424767, "avg_return": 0.8625381588935852, "regret": 0.0004762991738971323, "entropy": 0.09682881087064743, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:03.463629Z", "loop": 13514, "env_steps": 8303615999, "loss": 0.02177264541387558, "avg_return": 0.862449586391449, "regret": 0.0004762991738971323, "entropy": 0.10741807520389557, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:04.316776Z", "loop": 13515, "env_steps": 8304230399, "loss": 0.02200457826256752, "avg_return": 0.8621745109558105, "regret": 0.0004762991738971323, "entropy": 0.10937200486660004, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:05.171286Z", "loop": 13516, "env_steps": 8304844799, "loss": 0.021256422623991966, "avg_return": 0.8616542816162109, "regret": 0.0004762991738971323, "entropy": 0.10286547988653183, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:06.025371Z", "loop": 13517, "env_steps": 8305459199, "loss": 0.021578697487711906, "avg_return": 0.8596904873847961, "regret": 0.0004762991738971323, "entropy": 0.10721646249294281, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:06.879738Z", "loop": 13518, "env_steps": 8306073599, "loss": 0.02142622135579586, "avg_return": 0.8562697768211365, "regret": 0.0004762991738971323, "entropy": 0.10282019525766373, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:07.732918Z", "loop": 13519, "env_steps": 8306687999, "loss": 0.020274922251701355, "avg_return": 0.8563477993011475, "regret": 0.0004762991738971323, "entropy": 0.10372540354728699, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:08.628325Z", "loop": 13520, "env_steps": 8307302399, "loss": 0.018210193142294884, "avg_return": 0.8607534766197205, "regret": 0.003104879753664136, "entropy": 0.09311138838529587, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:09.482206Z", "loop": 13521, "env_steps": 8307916799, "loss": 0.016520751640200615, "avg_return": 0.8619089722633362, "regret": 0.003104879753664136, "entropy": 0.08573991805315018, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:10.336469Z", "loop": 13522, "env_steps": 8308531199, "loss": 0.0147889768704772, "avg_return": 0.8622627854347229, "regret": 0.003104879753664136, "entropy": 0.07766757160425186, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:11.190278Z", "loop": 13523, "env_steps": 8309145599, "loss": 0.01456618495285511, "avg_return": 0.8643404245376587, "regret": 0.003104879753664136, "entropy": 0.07376112788915634, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:12.043288Z", "loop": 13524, "env_steps": 8309759999, "loss": 0.01336681004613638, "avg_return": 0.8645284175872803, "regret": 0.003104879753664136, "entropy": 0.07233920693397522, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:12.896481Z", "loop": 13525, "env_steps": 8310374399, "loss": 0.013524793088436127, "avg_return": 0.8638279438018799, "regret": 0.003104879753664136, "entropy": 0.07016976177692413, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:13.750381Z", "loop": 13526, "env_steps": 8310988799, "loss": 0.01336892880499363, "avg_return": 0.8646562695503235, "regret": 0.003104879753664136, "entropy": 0.06877688318490982, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:14.604909Z", "loop": 13527, "env_steps": 8311603199, "loss": 0.0126563785597682, "avg_return": 0.8640604615211487, "regret": 0.003104879753664136, "entropy": 0.06573205441236496, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:15.458840Z", "loop": 13528, "env_steps": 8312217599, "loss": 0.012036527507007122, "avg_return": 0.8638378381729126, "regret": 0.003104879753664136, "entropy": 0.06622915714979172, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:16.312267Z", "loop": 13529, "env_steps": 8312831999, "loss": 0.01221923716366291, "avg_return": 0.8638989329338074, "regret": 0.003104879753664136, "entropy": 0.06946799159049988, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:17.206425Z", "loop": 13530, "env_steps": 8313446399, "loss": 0.012246849946677685, "avg_return": 0.8639969229698181, "regret": 0.00016747282643336803, "entropy": 0.06843692809343338, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:18.061245Z", "loop": 13531, "env_steps": 8314060799, "loss": 0.013825908303260803, "avg_return": 0.8631492257118225, "regret": 0.00016747282643336803, "entropy": 0.07065984606742859, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:18.916320Z", "loop": 13532, "env_steps": 8314675199, "loss": 0.012406527064740658, "avg_return": 0.8638625144958496, "regret": 0.00016747282643336803, "entropy": 0.06522589176893234, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:19.769798Z", "loop": 13533, "env_steps": 8315289599, "loss": 0.011795255355536938, "avg_return": 0.8630654215812683, "regret": 0.00016747282643336803, "entropy": 0.06634120643138885, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:20.623590Z", "loop": 13534, "env_steps": 8315903999, "loss": 0.011900628916919231, "avg_return": 0.8646299242973328, "regret": 0.00016747282643336803, "entropy": 0.06291507929563522, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:21.477716Z", "loop": 13535, "env_steps": 8316518399, "loss": 0.012873499654233456, "avg_return": 0.8640452027320862, "regret": 0.00016747282643336803, "entropy": 0.06833887100219727, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:22.333286Z", "loop": 13536, "env_steps": 8317132799, "loss": 0.011942236684262753, "avg_return": 0.8637486100196838, "regret": 0.00016747282643336803, "entropy": 0.06546822935342789, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:23.187958Z", "loop": 13537, "env_steps": 8317747199, "loss": 0.012009897269308567, "avg_return": 0.8639098405838013, "regret": 0.00016747282643336803, "entropy": 0.06453591585159302, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:24.042047Z", "loop": 13538, "env_steps": 8318361599, "loss": 0.011322078295052052, "avg_return": 0.8630602955818176, "regret": 0.00016747282643336803, "entropy": 0.06450539082288742, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:24.896680Z", "loop": 13539, "env_steps": 8318975999, "loss": 0.011927624233067036, "avg_return": 0.8639101386070251, "regret": 0.00016747282643336803, "entropy": 0.0642063245177269, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:25.792697Z", "loop": 13540, "env_steps": 8319590399, "loss": 0.011772762052714825, "avg_return": 0.863296627998352, "regret": 0.0002237894805148244, "entropy": 0.06250595301389694, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:26.647399Z", "loop": 13541, "env_steps": 8320204799, "loss": 0.013467554934322834, "avg_return": 0.863720715045929, "regret": 0.0002237894805148244, "entropy": 0.06876478344202042, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:27.502462Z", "loop": 13542, "env_steps": 8320819199, "loss": 0.0128908297047019, "avg_return": 0.8642920851707458, "regret": 0.0002237894805148244, "entropy": 0.06687232106924057, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:28.357436Z", "loop": 13543, "env_steps": 8321433599, "loss": 0.012071880511939526, "avg_return": 0.8635725975036621, "regret": 0.0002237894805148244, "entropy": 0.06768080592155457, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:29.213529Z", "loop": 13544, "env_steps": 8322047999, "loss": 0.012579336762428284, "avg_return": 0.8621296286582947, "regret": 0.0002237894805148244, "entropy": 0.06784819066524506, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:30.068740Z", "loop": 13545, "env_steps": 8322662399, "loss": 0.01136702485382557, "avg_return": 0.8643338084220886, "regret": 0.0002237894805148244, "entropy": 0.0652959793806076, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:30.923073Z", "loop": 13546, "env_steps": 8323276799, "loss": 0.012684479355812073, "avg_return": 0.8623944520950317, "regret": 0.0002237894805148244, "entropy": 0.06868300586938858, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:31.777356Z", "loop": 13547, "env_steps": 8323891199, "loss": 0.012671120464801788, "avg_return": 0.864057719707489, "regret": 0.0002237894805148244, "entropy": 0.0676804631948471, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:32.631674Z", "loop": 13548, "env_steps": 8324505599, "loss": 0.01229803916066885, "avg_return": 0.8639976978302002, "regret": 0.0002237894805148244, "entropy": 0.06709106266498566, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:33.486143Z", "loop": 13549, "env_steps": 8325119999, "loss": 0.011704615317285061, "avg_return": 0.8632076382637024, "regret": 0.0002237894805148244, "entropy": 0.06372132897377014, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:34.379309Z", "loop": 13550, "env_steps": 8325734399, "loss": 0.012927457690238953, "avg_return": 0.8631986975669861, "regret": 0.0003619579365476966, "entropy": 0.06822329014539719, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:35.233164Z", "loop": 13551, "env_steps": 8326348799, "loss": 0.010998883284628391, "avg_return": 0.8632564544677734, "regret": 0.0003619579365476966, "entropy": 0.06001294031739235, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:36.087867Z", "loop": 13552, "env_steps": 8326963199, "loss": 0.012075955979526043, "avg_return": 0.8626933097839355, "regret": 0.0003619579365476966, "entropy": 0.06523621082305908, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:36.942751Z", "loop": 13553, "env_steps": 8327577599, "loss": 0.012460033409297466, "avg_return": 0.8631213307380676, "regret": 0.0003619579365476966, "entropy": 0.0653257891535759, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:37.796884Z", "loop": 13554, "env_steps": 8328191999, "loss": 0.014087885618209839, "avg_return": 0.8633776903152466, "regret": 0.0003619579365476966, "entropy": 0.07066173851490021, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:38.650562Z", "loop": 13555, "env_steps": 8328806399, "loss": 0.011139842681586742, "avg_return": 0.8636631369590759, "regret": 0.0003619579365476966, "entropy": 0.06506428122520447, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:39.505353Z", "loop": 13556, "env_steps": 8329420799, "loss": 0.013051713816821575, "avg_return": 0.8640568256378174, "regret": 0.0003619579365476966, "entropy": 0.06725189089775085, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:40.359847Z", "loop": 13557, "env_steps": 8330035199, "loss": 0.01216018944978714, "avg_return": 0.8638762831687927, "regret": 0.0003619579365476966, "entropy": 0.06612509489059448, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:41.214228Z", "loop": 13558, "env_steps": 8330649599, "loss": 0.01280784048140049, "avg_return": 0.8636248111724854, "regret": 0.0003619579365476966, "entropy": 0.06888313591480255, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:42.068015Z", "loop": 13559, "env_steps": 8331263999, "loss": 0.012009878642857075, "avg_return": 0.8633910417556763, "regret": 0.0003619579365476966, "entropy": 0.06834525614976883, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:42.963073Z", "loop": 13560, "env_steps": 8331878399, "loss": 0.011993242427706718, "avg_return": 0.8617851138114929, "regret": 0.0005028141313232481, "entropy": 0.0683162659406662, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:43.816657Z", "loop": 13561, "env_steps": 8332492799, "loss": 0.01185129676014185, "avg_return": 0.8626969456672668, "regret": 0.0005028141313232481, "entropy": 0.06604408472776413, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:44.670168Z", "loop": 13562, "env_steps": 8333107199, "loss": 0.013601568527519703, "avg_return": 0.8642815351486206, "regret": 0.0005028141313232481, "entropy": 0.0703914538025856, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:45.524590Z", "loop": 13563, "env_steps": 8333721599, "loss": 0.013760154135525227, "avg_return": 0.8639736175537109, "regret": 0.0005028141313232481, "entropy": 0.0717795118689537, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:46.378546Z", "loop": 13564, "env_steps": 8334335999, "loss": 0.013858606107532978, "avg_return": 0.8625797629356384, "regret": 0.0005028141313232481, "entropy": 0.0708371177315712, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:47.232116Z", "loop": 13565, "env_steps": 8334950399, "loss": 0.014388992451131344, "avg_return": 0.8627492189407349, "regret": 0.0005028141313232481, "entropy": 0.07666942477226257, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:48.086072Z", "loop": 13566, "env_steps": 8335564799, "loss": 0.013951676897704601, "avg_return": 0.8615393042564392, "regret": 0.0005028141313232481, "entropy": 0.07323397696018219, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:48.941080Z", "loop": 13567, "env_steps": 8336179199, "loss": 0.01581714116036892, "avg_return": 0.8607105612754822, "regret": 0.0005028141313232481, "entropy": 0.08087436109781265, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:49.795298Z", "loop": 13568, "env_steps": 8336793599, "loss": 0.016244148835539818, "avg_return": 0.8616138696670532, "regret": 0.0005028141313232481, "entropy": 0.08396848291158676, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:50.649905Z", "loop": 13569, "env_steps": 8337407999, "loss": 0.01620701514184475, "avg_return": 0.8599511981010437, "regret": 0.0005028141313232481, "entropy": 0.07945337891578674, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:51.543655Z", "loop": 13570, "env_steps": 8338022399, "loss": 0.01565484330058098, "avg_return": 0.8586271405220032, "regret": 0.004546656738966703, "entropy": 0.08286130428314209, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:52.398178Z", "loop": 13571, "env_steps": 8338636799, "loss": 0.018900757655501366, "avg_return": 0.8589394092559814, "regret": 0.004546656738966703, "entropy": 0.09241103380918503, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:53.252518Z", "loop": 13572, "env_steps": 8339251199, "loss": 0.019650710746645927, "avg_return": 0.8585922718048096, "regret": 0.004546656738966703, "entropy": 0.09818136692047119, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:54.107321Z", "loop": 13573, "env_steps": 8339865599, "loss": 0.019681690260767937, "avg_return": 0.8586006760597229, "regret": 0.004546656738966703, "entropy": 0.09949902445077896, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:54.961286Z", "loop": 13574, "env_steps": 8340479999, "loss": 0.019831540063023567, "avg_return": 0.8591269850730896, "regret": 0.004546656738966703, "entropy": 0.096230149269104, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:55.815529Z", "loop": 13575, "env_steps": 8341094399, "loss": 0.019323060289025307, "avg_return": 0.8589622378349304, "regret": 0.004546656738966703, "entropy": 0.0982586070895195, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:56.669118Z", "loop": 13576, "env_steps": 8341708799, "loss": 0.01981675997376442, "avg_return": 0.8598759174346924, "regret": 0.004546656738966703, "entropy": 0.09558463841676712, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:57.523827Z", "loop": 13577, "env_steps": 8342323199, "loss": 0.018652167171239853, "avg_return": 0.8621247410774231, "regret": 0.004546656738966703, "entropy": 0.09260192513465881, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:58.377097Z", "loop": 13578, "env_steps": 8342937599, "loss": 0.0190176609903574, "avg_return": 0.8608787059783936, "regret": 0.004546656738966703, "entropy": 0.08998140692710876, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:37:59.230313Z", "loop": 13579, "env_steps": 8343551999, "loss": 0.01747874543070793, "avg_return": 0.8615104556083679, "regret": 0.004546656738966703, "entropy": 0.08686139434576035, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:00.122782Z", "loop": 13580, "env_steps": 8344166399, "loss": 0.018363572657108307, "avg_return": 0.8628764152526855, "regret": 0.0014124134322628379, "entropy": 0.0895339846611023, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:00.976689Z", "loop": 13581, "env_steps": 8344780799, "loss": 0.01785806380212307, "avg_return": 0.862930417060852, "regret": 0.0014124134322628379, "entropy": 0.0857355147600174, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:01.830427Z", "loop": 13582, "env_steps": 8345395199, "loss": 0.016302652657032013, "avg_return": 0.863278329372406, "regret": 0.0014124134322628379, "entropy": 0.083490751683712, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:02.683819Z", "loop": 13583, "env_steps": 8346009599, "loss": 0.015400583855807781, "avg_return": 0.8637290596961975, "regret": 0.0014124134322628379, "entropy": 0.0816919207572937, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:03.536837Z", "loop": 13584, "env_steps": 8346623999, "loss": 0.015685180202126503, "avg_return": 0.8625535368919373, "regret": 0.0014124134322628379, "entropy": 0.08030881732702255, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:04.391216Z", "loop": 13585, "env_steps": 8347238399, "loss": 0.0148764718323946, "avg_return": 0.8632973432540894, "regret": 0.0014124134322628379, "entropy": 0.07827668637037277, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:05.245266Z", "loop": 13586, "env_steps": 8347852799, "loss": 0.01632116362452507, "avg_return": 0.862994909286499, "regret": 0.0014124134322628379, "entropy": 0.08465156704187393, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:06.099678Z", "loop": 13587, "env_steps": 8348467199, "loss": 0.01576857827603817, "avg_return": 0.8625956177711487, "regret": 0.0014124134322628379, "entropy": 0.0842188373208046, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:06.952718Z", "loop": 13588, "env_steps": 8349081599, "loss": 0.015731273218989372, "avg_return": 0.8633018136024475, "regret": 0.0014124134322628379, "entropy": 0.08082953095436096, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:07.806031Z", "loop": 13589, "env_steps": 8349695999, "loss": 0.016743620857596397, "avg_return": 0.8636794090270996, "regret": 0.0014124134322628379, "entropy": 0.0835355743765831, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:08.700445Z", "loop": 13590, "env_steps": 8350310399, "loss": 0.015902724117040634, "avg_return": 0.8643919229507446, "regret": 0.00018206806271336973, "entropy": 0.08152207732200623, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:09.554673Z", "loop": 13591, "env_steps": 8350924799, "loss": 0.016355810686945915, "avg_return": 0.864700436592102, "regret": 0.00018206806271336973, "entropy": 0.08066412806510925, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:10.408856Z", "loop": 13592, "env_steps": 8351539199, "loss": 0.015249413438141346, "avg_return": 0.8629377484321594, "regret": 0.00018206806271336973, "entropy": 0.07968677580356598, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:11.262452Z", "loop": 13593, "env_steps": 8352153599, "loss": 0.01613640785217285, "avg_return": 0.8630208373069763, "regret": 0.00018206806271336973, "entropy": 0.08122501522302628, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:12.117019Z", "loop": 13594, "env_steps": 8352767999, "loss": 0.016077328473329544, "avg_return": 0.8630381226539612, "regret": 0.00018206806271336973, "entropy": 0.08033860474824905, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:12.971228Z", "loop": 13595, "env_steps": 8353382399, "loss": 0.016302142292261124, "avg_return": 0.8633259534835815, "regret": 0.00018206806271336973, "entropy": 0.08342228084802628, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:13.825084Z", "loop": 13596, "env_steps": 8353996799, "loss": 0.016204968094825745, "avg_return": 0.86295086145401, "regret": 0.00018206806271336973, "entropy": 0.0839596763253212, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:14.678886Z", "loop": 13597, "env_steps": 8354611199, "loss": 0.015519194304943085, "avg_return": 0.8633274435997009, "regret": 0.00018206806271336973, "entropy": 0.0799611508846283, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:15.533357Z", "loop": 13598, "env_steps": 8355225599, "loss": 0.015353771857917309, "avg_return": 0.8626955151557922, "regret": 0.00018206806271336973, "entropy": 0.07874682545661926, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:16.388023Z", "loop": 13599, "env_steps": 8355839999, "loss": 0.01705183833837509, "avg_return": 0.862764298915863, "regret": 0.00018206806271336973, "entropy": 0.08503790944814682, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:17.280319Z", "loop": 13600, "env_steps": 8356454399, "loss": 0.01674726791679859, "avg_return": 0.8627030849456787, "regret": 0.000690928369294852, "entropy": 0.08713127672672272, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:18.133605Z", "loop": 13601, "env_steps": 8357068799, "loss": 0.017706090584397316, "avg_return": 0.8623899817466736, "regret": 0.000690928369294852, "entropy": 0.08590873330831528, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:18.987588Z", "loop": 13602, "env_steps": 8357683199, "loss": 0.018691333010792732, "avg_return": 0.863124430179596, "regret": 0.000690928369294852, "entropy": 0.09247958660125732, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:19.841571Z", "loop": 13603, "env_steps": 8358297599, "loss": 0.020755542442202568, "avg_return": 0.8643172383308411, "regret": 0.000690928369294852, "entropy": 0.09971098601818085, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:20.696346Z", "loop": 13604, "env_steps": 8358911999, "loss": 0.02350572682917118, "avg_return": 0.8617343306541443, "regret": 0.000690928369294852, "entropy": 0.1086273267865181, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:21.550103Z", "loop": 13605, "env_steps": 8359526399, "loss": 0.01986430399119854, "avg_return": 0.8613731265068054, "regret": 0.000690928369294852, "entropy": 0.09734000265598297, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:22.403456Z", "loop": 13606, "env_steps": 8360140799, "loss": 0.018205100670456886, "avg_return": 0.8580523133277893, "regret": 0.000690928369294852, "entropy": 0.09122073650360107, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:23.257811Z", "loop": 13607, "env_steps": 8360755199, "loss": 0.01965680718421936, "avg_return": 0.8556109666824341, "regret": 0.000690928369294852, "entropy": 0.09701664745807648, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:24.112614Z", "loop": 13608, "env_steps": 8361369599, "loss": 0.018125172704458237, "avg_return": 0.8571324944496155, "regret": 0.000690928369294852, "entropy": 0.09344363212585449, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:24.966661Z", "loop": 13609, "env_steps": 8361983999, "loss": 0.0181774590164423, "avg_return": 0.8596897721290588, "regret": 0.000690928369294852, "entropy": 0.09041160345077515, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:25.860570Z", "loop": 13610, "env_steps": 8362598399, "loss": 0.015240865759551525, "avg_return": 0.8605033755302429, "regret": 0.0020956997759640217, "entropy": 0.07841264456510544, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:26.714728Z", "loop": 13611, "env_steps": 8363212799, "loss": 0.012789522297680378, "avg_return": 0.8630884289741516, "regret": 0.0020956997759640217, "entropy": 0.06888217478990555, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:27.568957Z", "loop": 13612, "env_steps": 8363827199, "loss": 0.012660405598580837, "avg_return": 0.8618306517601013, "regret": 0.0020956997759640217, "entropy": 0.06631579995155334, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:28.423010Z", "loop": 13613, "env_steps": 8364441599, "loss": 0.01199908647686243, "avg_return": 0.8627510666847229, "regret": 0.0020956997759640217, "entropy": 0.06388324499130249, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:29.277778Z", "loop": 13614, "env_steps": 8365055999, "loss": 0.011198971420526505, "avg_return": 0.8627058863639832, "regret": 0.0020956997759640217, "entropy": 0.06227097660303116, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:30.132676Z", "loop": 13615, "env_steps": 8365670399, "loss": 0.011858917772769928, "avg_return": 0.8644843697547913, "regret": 0.0020956997759640217, "entropy": 0.06330565363168716, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:30.986635Z", "loop": 13616, "env_steps": 8366284799, "loss": 0.011786832474172115, "avg_return": 0.8635645508766174, "regret": 0.0020956997759640217, "entropy": 0.06336826831102371, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:31.841572Z", "loop": 13617, "env_steps": 8366899199, "loss": 0.011744823306798935, "avg_return": 0.8630631566047668, "regret": 0.0020956997759640217, "entropy": 0.059947796165943146, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:32.696684Z", "loop": 13618, "env_steps": 8367513599, "loss": 0.011477353982627392, "avg_return": 0.8646025061607361, "regret": 0.0020956997759640217, "entropy": 0.05830894783139229, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:33.549373Z", "loop": 13619, "env_steps": 8368127999, "loss": 0.010581610724329948, "avg_return": 0.8637188673019409, "regret": 0.0020956997759640217, "entropy": 0.05898965895175934, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:34.444530Z", "loop": 13620, "env_steps": 8368742399, "loss": 0.010784604586660862, "avg_return": 0.8628539443016052, "regret": 0.00013513118028640747, "entropy": 0.056721270084381104, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:35.300063Z", "loop": 13621, "env_steps": 8369356799, "loss": 0.011632648296654224, "avg_return": 0.8627183437347412, "regret": 0.00013513118028640747, "entropy": 0.06279221922159195, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:36.154528Z", "loop": 13622, "env_steps": 8369971199, "loss": 0.011219768784940243, "avg_return": 0.8626642227172852, "regret": 0.00013513118028640747, "entropy": 0.05652002617716789, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:37.009689Z", "loop": 13623, "env_steps": 8370585599, "loss": 0.011714057996869087, "avg_return": 0.862995445728302, "regret": 0.00013513118028640747, "entropy": 0.060196276754140854, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:37.864076Z", "loop": 13624, "env_steps": 8371199999, "loss": 0.011816169135272503, "avg_return": 0.8635905385017395, "regret": 0.00013513118028640747, "entropy": 0.06175057962536812, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:38.719250Z", "loop": 13625, "env_steps": 8371814399, "loss": 0.01087964978069067, "avg_return": 0.8621652722358704, "regret": 0.00013513118028640747, "entropy": 0.058521583676338196, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:39.574115Z", "loop": 13626, "env_steps": 8372428799, "loss": 0.010627093724906445, "avg_return": 0.8635669946670532, "regret": 0.00013513118028640747, "entropy": 0.05617200955748558, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:40.429104Z", "loop": 13627, "env_steps": 8373043199, "loss": 0.011122064664959908, "avg_return": 0.8625113368034363, "regret": 0.00013513118028640747, "entropy": 0.06039027124643326, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:41.283120Z", "loop": 13628, "env_steps": 8373657599, "loss": 0.011375459842383862, "avg_return": 0.8647755980491638, "regret": 0.00013513118028640747, "entropy": 0.06256610155105591, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:42.137405Z", "loop": 13629, "env_steps": 8374271999, "loss": 0.012172444723546505, "avg_return": 0.8641864061355591, "regret": 0.00013513118028640747, "entropy": 0.061693210154771805, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:43.033892Z", "loop": 13630, "env_steps": 8374886399, "loss": 0.010816216468811035, "avg_return": 0.8636519312858582, "regret": 0.0003245683910790831, "entropy": 0.05764950439333916, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:43.889998Z", "loop": 13631, "env_steps": 8375500799, "loss": 0.011259743012487888, "avg_return": 0.8644640445709229, "regret": 0.0003245683910790831, "entropy": 0.061932552605867386, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:44.744823Z", "loop": 13632, "env_steps": 8376115199, "loss": 0.011564508080482483, "avg_return": 0.8630176186561584, "regret": 0.0003245683910790831, "entropy": 0.06204322725534439, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:45.598677Z", "loop": 13633, "env_steps": 8376729599, "loss": 0.011769043281674385, "avg_return": 0.8627234101295471, "regret": 0.0003245683910790831, "entropy": 0.06159587949514389, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:46.452853Z", "loop": 13634, "env_steps": 8377343999, "loss": 0.010619628243148327, "avg_return": 0.8630350828170776, "regret": 0.0003245683910790831, "entropy": 0.05649758502840996, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:47.308627Z", "loop": 13635, "env_steps": 8377958399, "loss": 0.012077108956873417, "avg_return": 0.8634449243545532, "regret": 0.0003245683910790831, "entropy": 0.061879806220531464, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:48.162707Z", "loop": 13636, "env_steps": 8378572799, "loss": 0.011987334117293358, "avg_return": 0.8628169894218445, "regret": 0.0003245683910790831, "entropy": 0.06249701604247093, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:49.016690Z", "loop": 13637, "env_steps": 8379187199, "loss": 0.012406042777001858, "avg_return": 0.8647760152816772, "regret": 0.0003245683910790831, "entropy": 0.06262054294347763, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:49.870603Z", "loop": 13638, "env_steps": 8379801599, "loss": 0.011229414492845535, "avg_return": 0.8622800707817078, "regret": 0.0003245683910790831, "entropy": 0.06401600688695908, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:50.725338Z", "loop": 13639, "env_steps": 8380415999, "loss": 0.011506880633533001, "avg_return": 0.8627533912658691, "regret": 0.0003245683910790831, "entropy": 0.06100495532155037, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:51.619914Z", "loop": 13640, "env_steps": 8381030399, "loss": 0.0116343405097723, "avg_return": 0.8645365834236145, "regret": 0.0006240678485482931, "entropy": 0.06084268167614937, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:52.474420Z", "loop": 13641, "env_steps": 8381644799, "loss": 0.011931517161428928, "avg_return": 0.8626590967178345, "regret": 0.0006240678485482931, "entropy": 0.061685919761657715, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:53.327516Z", "loop": 13642, "env_steps": 8382259199, "loss": 0.011921918019652367, "avg_return": 0.8624913692474365, "regret": 0.0006240678485482931, "entropy": 0.06365250051021576, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:54.181903Z", "loop": 13643, "env_steps": 8382873599, "loss": 0.012677852995693684, "avg_return": 0.8619594573974609, "regret": 0.0006240678485482931, "entropy": 0.06283997744321823, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:55.035890Z", "loop": 13644, "env_steps": 8383487999, "loss": 0.012499622069299221, "avg_return": 0.8630257248878479, "regret": 0.0006240678485482931, "entropy": 0.06571974605321884, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:55.889671Z", "loop": 13645, "env_steps": 8384102399, "loss": 0.011270235292613506, "avg_return": 0.8619299530982971, "regret": 0.0006240678485482931, "entropy": 0.05967259407043457, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:56.743362Z", "loop": 13646, "env_steps": 8384716799, "loss": 0.011783916503190994, "avg_return": 0.8630972504615784, "regret": 0.0006240678485482931, "entropy": 0.06292208284139633, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:57.597598Z", "loop": 13647, "env_steps": 8385331199, "loss": 0.012412890791893005, "avg_return": 0.8608967065811157, "regret": 0.0006240678485482931, "entropy": 0.06705600768327713, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:58.452312Z", "loop": 13648, "env_steps": 8385945599, "loss": 0.011343248188495636, "avg_return": 0.8615053296089172, "regret": 0.0006240678485482931, "entropy": 0.06142660230398178, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:38:59.307991Z", "loop": 13649, "env_steps": 8386559999, "loss": 0.011736673302948475, "avg_return": 0.860683798789978, "regret": 0.0006240678485482931, "entropy": 0.06283709406852722, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:00.202617Z", "loop": 13650, "env_steps": 8387174399, "loss": 0.012357010506093502, "avg_return": 0.8615850806236267, "regret": 0.002537870081141591, "entropy": 0.0642264187335968, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:01.057340Z", "loop": 13651, "env_steps": 8387788799, "loss": 0.012762120924890041, "avg_return": 0.8603005409240723, "regret": 0.002537870081141591, "entropy": 0.06724235415458679, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:01.912308Z", "loop": 13652, "env_steps": 8388403199, "loss": 0.012794136069715023, "avg_return": 0.8604997992515564, "regret": 0.002537870081141591, "entropy": 0.06373388320207596, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:02.767843Z", "loop": 13653, "env_steps": 8389017599, "loss": 0.012779762037098408, "avg_return": 0.8613671064376831, "regret": 0.002537870081141591, "entropy": 0.06684637069702148, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:03.622789Z", "loop": 13654, "env_steps": 8389631999, "loss": 0.012381019070744514, "avg_return": 0.8592585325241089, "regret": 0.002537870081141591, "entropy": 0.06426981091499329, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:04.475984Z", "loop": 13655, "env_steps": 8390246399, "loss": 0.012079773470759392, "avg_return": 0.8613554239273071, "regret": 0.002537870081141591, "entropy": 0.06508441269397736, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:05.329163Z", "loop": 13656, "env_steps": 8390860799, "loss": 0.012187599204480648, "avg_return": 0.8585347533226013, "regret": 0.002537870081141591, "entropy": 0.06558194011449814, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:06.182409Z", "loop": 13657, "env_steps": 8391475199, "loss": 0.011715629138052464, "avg_return": 0.8610995411872864, "regret": 0.002537870081141591, "entropy": 0.06482911109924316, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:07.036329Z", "loop": 13658, "env_steps": 8392089599, "loss": 0.012609369121491909, "avg_return": 0.8603366017341614, "regret": 0.002537870081141591, "entropy": 0.06732284277677536, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:07.890992Z", "loop": 13659, "env_steps": 8392703999, "loss": 0.011736414395272732, "avg_return": 0.8608096241950989, "regret": 0.002537870081141591, "entropy": 0.06450625509023666, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:08.787093Z", "loop": 13660, "env_steps": 8393318399, "loss": 0.01250341534614563, "avg_return": 0.861431896686554, "regret": 0.002530038822442293, "entropy": 0.06521915644407272, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:09.641900Z", "loop": 13661, "env_steps": 8393932799, "loss": 0.014299541711807251, "avg_return": 0.8625637292861938, "regret": 0.002530038822442293, "entropy": 0.07051932066679001, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:10.496996Z", "loop": 13662, "env_steps": 8394547199, "loss": 0.012382264249026775, "avg_return": 0.8615399599075317, "regret": 0.002530038822442293, "entropy": 0.06406205892562866, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:11.350213Z", "loop": 13663, "env_steps": 8395161599, "loss": 0.012377521954476833, "avg_return": 0.8596273064613342, "regret": 0.002530038822442293, "entropy": 0.06466858834028244, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:12.204129Z", "loop": 13664, "env_steps": 8395775999, "loss": 0.0126377297565341, "avg_return": 0.8605583906173706, "regret": 0.002530038822442293, "entropy": 0.06787673383951187, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:13.058479Z", "loop": 13665, "env_steps": 8396390399, "loss": 0.013007126748561859, "avg_return": 0.8597429394721985, "regret": 0.002530038822442293, "entropy": 0.06930873543024063, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:13.913351Z", "loop": 13666, "env_steps": 8397004799, "loss": 0.012515253387391567, "avg_return": 0.8611767888069153, "regret": 0.002530038822442293, "entropy": 0.06852768361568451, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:14.767878Z", "loop": 13667, "env_steps": 8397619199, "loss": 0.012411657720804214, "avg_return": 0.8610559105873108, "regret": 0.002530038822442293, "entropy": 0.06491421908140182, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:15.622627Z", "loop": 13668, "env_steps": 8398233599, "loss": 0.011558555997908115, "avg_return": 0.8609455823898315, "regret": 0.002530038822442293, "entropy": 0.06283840537071228, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:16.476457Z", "loop": 13669, "env_steps": 8398847999, "loss": 0.012493113987147808, "avg_return": 0.8612564206123352, "regret": 0.002530038822442293, "entropy": 0.06655880808830261, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:17.371900Z", "loop": 13670, "env_steps": 8399462399, "loss": 0.01264454610645771, "avg_return": 0.8609884977340698, "regret": 0.0027694369200617075, "entropy": 0.06617239862680435, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:18.226874Z", "loop": 13671, "env_steps": 8400076799, "loss": 0.012087280862033367, "avg_return": 0.8609361052513123, "regret": 0.0027694369200617075, "entropy": 0.06748227775096893, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:19.081732Z", "loop": 13672, "env_steps": 8400691199, "loss": 0.011784627102315426, "avg_return": 0.8611378073692322, "regret": 0.0027694369200617075, "entropy": 0.0629224106669426, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:19.935763Z", "loop": 13673, "env_steps": 8401305599, "loss": 0.01242556981742382, "avg_return": 0.8610231876373291, "regret": 0.0027694369200617075, "entropy": 0.06745049357414246, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:20.791284Z", "loop": 13674, "env_steps": 8401919999, "loss": 0.013341428712010384, "avg_return": 0.8611226677894592, "regret": 0.0027694369200617075, "entropy": 0.06821423023939133, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:21.646644Z", "loop": 13675, "env_steps": 8402534399, "loss": 0.011470597237348557, "avg_return": 0.8622416257858276, "regret": 0.0027694369200617075, "entropy": 0.06365340203046799, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:22.500925Z", "loop": 13676, "env_steps": 8403148799, "loss": 0.011958783492445946, "avg_return": 0.8612412810325623, "regret": 0.0027694369200617075, "entropy": 0.06529951095581055, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:23.356060Z", "loop": 13677, "env_steps": 8403763199, "loss": 0.012555099092423916, "avg_return": 0.8623225092887878, "regret": 0.0027694369200617075, "entropy": 0.06515313684940338, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:24.211071Z", "loop": 13678, "env_steps": 8404377599, "loss": 0.01221400685608387, "avg_return": 0.8626731634140015, "regret": 0.0027694369200617075, "entropy": 0.06293310970067978, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:25.065349Z", "loop": 13679, "env_steps": 8404991999, "loss": 0.01244120579212904, "avg_return": 0.8618011474609375, "regret": 0.0027694369200617075, "entropy": 0.06391220539808273, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:25.962734Z", "loop": 13680, "env_steps": 8405606399, "loss": 0.01269445475190878, "avg_return": 0.86124187707901, "regret": 0.0005821137456223369, "entropy": 0.06554003804922104, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:26.817699Z", "loop": 13681, "env_steps": 8406220799, "loss": 0.011665844358503819, "avg_return": 0.8636838793754578, "regret": 0.0005821137456223369, "entropy": 0.06275156885385513, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:27.673844Z", "loop": 13682, "env_steps": 8406835199, "loss": 0.01147297490388155, "avg_return": 0.8634100556373596, "regret": 0.0005821137456223369, "entropy": 0.05997611954808235, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:28.528889Z", "loop": 13683, "env_steps": 8407449599, "loss": 0.012272468768060207, "avg_return": 0.8619610667228699, "regret": 0.0005821137456223369, "entropy": 0.06568516045808792, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:29.383906Z", "loop": 13684, "env_steps": 8408063999, "loss": 0.012515360489487648, "avg_return": 0.8643357753753662, "regret": 0.0005821137456223369, "entropy": 0.06603991985321045, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:30.239329Z", "loop": 13685, "env_steps": 8408678399, "loss": 0.012818025425076485, "avg_return": 0.8634840846061707, "regret": 0.0005821137456223369, "entropy": 0.06819258630275726, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:31.095817Z", "loop": 13686, "env_steps": 8409292799, "loss": 0.013567057438194752, "avg_return": 0.864610493183136, "regret": 0.0005821137456223369, "entropy": 0.07012741267681122, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:31.950377Z", "loop": 13687, "env_steps": 8409907199, "loss": 0.013658982701599598, "avg_return": 0.8624432682991028, "regret": 0.0005821137456223369, "entropy": 0.07019840180873871, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:32.804564Z", "loop": 13688, "env_steps": 8410521599, "loss": 0.014756451360881329, "avg_return": 0.8637040257453918, "regret": 0.0005821137456223369, "entropy": 0.07482310384511948, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:33.659786Z", "loop": 13689, "env_steps": 8411135999, "loss": 0.014754828996956348, "avg_return": 0.8635214567184448, "regret": 0.0005821137456223369, "entropy": 0.07603178173303604, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:34.556569Z", "loop": 13690, "env_steps": 8411750399, "loss": 0.013849702663719654, "avg_return": 0.8628371357917786, "regret": 0.00010308279888704419, "entropy": 0.07512179762125015, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:35.410948Z", "loop": 13691, "env_steps": 8412364799, "loss": 0.013946170918643475, "avg_return": 0.8638908863067627, "regret": 0.00010308279888704419, "entropy": 0.07108325511217117, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:36.265310Z", "loop": 13692, "env_steps": 8412979199, "loss": 0.014860831201076508, "avg_return": 0.8633416891098022, "regret": 0.00010308279888704419, "entropy": 0.07523301988840103, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:37.120008Z", "loop": 13693, "env_steps": 8413593599, "loss": 0.01550094224512577, "avg_return": 0.8629592061042786, "regret": 0.00010308279888704419, "entropy": 0.07470952719449997, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:37.975252Z", "loop": 13694, "env_steps": 8414207999, "loss": 0.014682941138744354, "avg_return": 0.8639743328094482, "regret": 0.00010308279888704419, "entropy": 0.07485606521368027, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:38.829519Z", "loop": 13695, "env_steps": 8414822399, "loss": 0.014481889083981514, "avg_return": 0.8640642762184143, "regret": 0.00010308279888704419, "entropy": 0.07438290864229202, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:39.682951Z", "loop": 13696, "env_steps": 8415436799, "loss": 0.014657653868198395, "avg_return": 0.8634361028671265, "regret": 0.00010308279888704419, "entropy": 0.07681497186422348, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:40.536160Z", "loop": 13697, "env_steps": 8416051199, "loss": 0.014569190330803394, "avg_return": 0.8645000457763672, "regret": 0.00010308279888704419, "entropy": 0.07685413956642151, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:41.391356Z", "loop": 13698, "env_steps": 8416665599, "loss": 0.014742733910679817, "avg_return": 0.8640884757041931, "regret": 0.00010308279888704419, "entropy": 0.07640664279460907, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:42.245831Z", "loop": 13699, "env_steps": 8417279999, "loss": 0.015270592644810677, "avg_return": 0.862406313419342, "regret": 0.00010308279888704419, "entropy": 0.07966330647468567, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:43.142720Z", "loop": 13700, "env_steps": 8417894399, "loss": 0.016014521941542625, "avg_return": 0.8636390566825867, "regret": 0.000251737714279443, "entropy": 0.08304561674594879, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:43.997275Z", "loop": 13701, "env_steps": 8418508799, "loss": 0.01712477020919323, "avg_return": 0.8642775416374207, "regret": 0.000251737714279443, "entropy": 0.08604026585817337, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:44.850738Z", "loop": 13702, "env_steps": 8419123199, "loss": 0.019295349717140198, "avg_return": 0.8623389005661011, "regret": 0.000251737714279443, "entropy": 0.09506745636463165, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:45.704728Z", "loop": 13703, "env_steps": 8419737599, "loss": 0.018823739141225815, "avg_return": 0.8630367517471313, "regret": 0.000251737714279443, "entropy": 0.09712687134742737, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:46.558978Z", "loop": 13704, "env_steps": 8420351999, "loss": 0.019670600071549416, "avg_return": 0.8632780313491821, "regret": 0.000251737714279443, "entropy": 0.09630542993545532, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:47.412958Z", "loop": 13705, "env_steps": 8420966399, "loss": 0.019432200118899345, "avg_return": 0.8645811080932617, "regret": 0.000251737714279443, "entropy": 0.09334699809551239, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:48.267267Z", "loop": 13706, "env_steps": 8421580799, "loss": 0.021267911419272423, "avg_return": 0.8634480834007263, "regret": 0.000251737714279443, "entropy": 0.10339096188545227, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:49.121354Z", "loop": 13707, "env_steps": 8422195199, "loss": 0.020530059933662415, "avg_return": 0.8634669184684753, "regret": 0.000251737714279443, "entropy": 0.10346081107854843, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:49.976495Z", "loop": 13708, "env_steps": 8422809599, "loss": 0.02034199796617031, "avg_return": 0.8627310395240784, "regret": 0.000251737714279443, "entropy": 0.09861965477466583, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:50.831256Z", "loop": 13709, "env_steps": 8423423999, "loss": 0.01811167597770691, "avg_return": 0.8624536395072937, "regret": 0.000251737714279443, "entropy": 0.09079175442457199, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:51.726733Z", "loop": 13710, "env_steps": 8424038399, "loss": 0.018290456384420395, "avg_return": 0.8622679710388184, "regret": 0.001252361573278904, "entropy": 0.09269648045301437, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:52.579998Z", "loop": 13711, "env_steps": 8424652799, "loss": 0.01694715954363346, "avg_return": 0.8626566529273987, "regret": 0.001252361573278904, "entropy": 0.0855683982372284, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:53.434155Z", "loop": 13712, "env_steps": 8425267199, "loss": 0.01777545176446438, "avg_return": 0.8613606691360474, "regret": 0.001252361573278904, "entropy": 0.08913062512874603, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:54.288514Z", "loop": 13713, "env_steps": 8425881599, "loss": 0.018566248938441277, "avg_return": 0.8613073825836182, "regret": 0.001252361573278904, "entropy": 0.09424785524606705, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:55.141962Z", "loop": 13714, "env_steps": 8426495999, "loss": 0.019604085013270378, "avg_return": 0.859589159488678, "regret": 0.001252361573278904, "entropy": 0.09378764033317566, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:55.995870Z", "loop": 13715, "env_steps": 8427110399, "loss": 0.018826814368367195, "avg_return": 0.8593752384185791, "regret": 0.001252361573278904, "entropy": 0.09411899000406265, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:56.850398Z", "loop": 13716, "env_steps": 8427724799, "loss": 0.018126262351870537, "avg_return": 0.8624818325042725, "regret": 0.001252361573278904, "entropy": 0.08898334950208664, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:57.705033Z", "loop": 13717, "env_steps": 8428339199, "loss": 0.01895431987941265, "avg_return": 0.8615601062774658, "regret": 0.001252361573278904, "entropy": 0.095699243247509, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:58.558290Z", "loop": 13718, "env_steps": 8428953599, "loss": 0.019018521532416344, "avg_return": 0.8608881831169128, "regret": 0.001252361573278904, "entropy": 0.09656564891338348, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:39:59.410802Z", "loop": 13719, "env_steps": 8429567999, "loss": 0.018261609598994255, "avg_return": 0.8630291223526001, "regret": 0.001252361573278904, "entropy": 0.09516707807779312, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:00.305250Z", "loop": 13720, "env_steps": 8430182399, "loss": 0.018479224294424057, "avg_return": 0.8634468913078308, "regret": 0.0009951700922101736, "entropy": 0.09871380031108856, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:01.160937Z", "loop": 13721, "env_steps": 8430796799, "loss": 0.018588772043585777, "avg_return": 0.8628041744232178, "regret": 0.0009951700922101736, "entropy": 0.0977533683180809, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:02.015471Z", "loop": 13722, "env_steps": 8431411199, "loss": 0.01838797517120838, "avg_return": 0.8634999990463257, "regret": 0.0009951700922101736, "entropy": 0.09537302702665329, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:02.871163Z", "loop": 13723, "env_steps": 8432025599, "loss": 0.017654094845056534, "avg_return": 0.8635538816452026, "regret": 0.0009951700922101736, "entropy": 0.0944124236702919, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:03.725303Z", "loop": 13724, "env_steps": 8432639999, "loss": 0.019442066550254822, "avg_return": 0.8614776730537415, "regret": 0.0009951700922101736, "entropy": 0.10050428658723831, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:04.580182Z", "loop": 13725, "env_steps": 8433254399, "loss": 0.019759925082325935, "avg_return": 0.8617587685585022, "regret": 0.0009951700922101736, "entropy": 0.09834500402212143, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:05.433409Z", "loop": 13726, "env_steps": 8433868799, "loss": 0.01915002427995205, "avg_return": 0.8625796437263489, "regret": 0.0009951700922101736, "entropy": 0.09816563129425049, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:06.287324Z", "loop": 13727, "env_steps": 8434483199, "loss": 0.01865033619105816, "avg_return": 0.8631885051727295, "regret": 0.0009951700922101736, "entropy": 0.09671811014413834, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:07.140483Z", "loop": 13728, "env_steps": 8435097599, "loss": 0.01925712451338768, "avg_return": 0.8642494082450867, "regret": 0.0009951700922101736, "entropy": 0.09645534306764603, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:07.994374Z", "loop": 13729, "env_steps": 8435711999, "loss": 0.01975095085799694, "avg_return": 0.8623490333557129, "regret": 0.0009951700922101736, "entropy": 0.09854069352149963, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:08.888342Z", "loop": 13730, "env_steps": 8436326399, "loss": 0.019067293033003807, "avg_return": 0.8624863624572754, "regret": 0.000749589002225548, "entropy": 0.09808088093996048, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:09.742736Z", "loop": 13731, "env_steps": 8436940799, "loss": 0.017603812739253044, "avg_return": 0.8624112010002136, "regret": 0.000749589002225548, "entropy": 0.09656029939651489, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:10.596559Z", "loop": 13732, "env_steps": 8437555199, "loss": 0.01802392303943634, "avg_return": 0.8633406758308411, "regret": 0.000749589002225548, "entropy": 0.0938800573348999, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:11.450696Z", "loop": 13733, "env_steps": 8438169599, "loss": 0.01668369770050049, "avg_return": 0.8626833558082581, "regret": 0.000749589002225548, "entropy": 0.09110131114721298, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:12.305300Z", "loop": 13734, "env_steps": 8438783999, "loss": 0.016946513205766678, "avg_return": 0.8621053099632263, "regret": 0.000749589002225548, "entropy": 0.08815646916627884, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:13.160194Z", "loop": 13735, "env_steps": 8439398399, "loss": 0.017971565946936607, "avg_return": 0.8632184267044067, "regret": 0.000749589002225548, "entropy": 0.08994075655937195, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:14.014846Z", "loop": 13736, "env_steps": 8440012799, "loss": 0.01626996323466301, "avg_return": 0.8624817132949829, "regret": 0.000749589002225548, "entropy": 0.08733733743429184, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:14.869554Z", "loop": 13737, "env_steps": 8440627199, "loss": 0.01696956343948841, "avg_return": 0.8625919818878174, "regret": 0.000749589002225548, "entropy": 0.08597288280725479, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:15.723877Z", "loop": 13738, "env_steps": 8441241599, "loss": 0.01667015068233013, "avg_return": 0.8629746437072754, "regret": 0.000749589002225548, "entropy": 0.08788920193910599, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:16.578543Z", "loop": 13739, "env_steps": 8441855999, "loss": 0.016045423224568367, "avg_return": 0.8616406321525574, "regret": 0.000749589002225548, "entropy": 0.08422712236642838, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:17.472008Z", "loop": 13740, "env_steps": 8442470399, "loss": 0.01688944175839424, "avg_return": 0.8621909022331238, "regret": 0.0005161918234080076, "entropy": 0.08839728683233261, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:18.326551Z", "loop": 13741, "env_steps": 8443084799, "loss": 0.017686473205685616, "avg_return": 0.8633404970169067, "regret": 0.0005161918234080076, "entropy": 0.08844340592622757, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:19.181085Z", "loop": 13742, "env_steps": 8443699199, "loss": 0.016515417024493217, "avg_return": 0.8638715744018555, "regret": 0.0005161918234080076, "entropy": 0.08673377335071564, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:20.036132Z", "loop": 13743, "env_steps": 8444313599, "loss": 0.01762673258781433, "avg_return": 0.8624253273010254, "regret": 0.0005161918234080076, "entropy": 0.08503446727991104, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:20.891472Z", "loop": 13744, "env_steps": 8444927999, "loss": 0.016231736168265343, "avg_return": 0.8630700707435608, "regret": 0.0005161918234080076, "entropy": 0.08895143866539001, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:21.749377Z", "loop": 13745, "env_steps": 8445542399, "loss": 0.017342105507850647, "avg_return": 0.8624579906463623, "regret": 0.0005161918234080076, "entropy": 0.08915847539901733, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:22.602820Z", "loop": 13746, "env_steps": 8446156799, "loss": 0.018225301057100296, "avg_return": 0.8622704148292542, "regret": 0.0005161918234080076, "entropy": 0.09210614114999771, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:23.456448Z", "loop": 13747, "env_steps": 8446771199, "loss": 0.01831214688718319, "avg_return": 0.8631929755210876, "regret": 0.0005161918234080076, "entropy": 0.09651181101799011, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:24.310758Z", "loop": 13748, "env_steps": 8447385599, "loss": 0.01965457759797573, "avg_return": 0.8639196157455444, "regret": 0.0005161918234080076, "entropy": 0.09700775891542435, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:25.165588Z", "loop": 13749, "env_steps": 8447999999, "loss": 0.02041580341756344, "avg_return": 0.8638308048248291, "regret": 0.0005161918234080076, "entropy": 0.09805694222450256, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:26.060026Z", "loop": 13750, "env_steps": 8448614399, "loss": 0.021886158734560013, "avg_return": 0.8626013398170471, "regret": 0.0003891952510457486, "entropy": 0.10406828671693802, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:26.913400Z", "loop": 13751, "env_steps": 8449228799, "loss": 0.02168816328048706, "avg_return": 0.8640572428703308, "regret": 0.0003891952510457486, "entropy": 0.10331793129444122, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:27.767351Z", "loop": 13752, "env_steps": 8449843199, "loss": 0.019746461883187294, "avg_return": 0.8624959588050842, "regret": 0.0003891952510457486, "entropy": 0.09655117243528366, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:28.622445Z", "loop": 13753, "env_steps": 8450457599, "loss": 0.01903916336596012, "avg_return": 0.863538920879364, "regret": 0.0003891952510457486, "entropy": 0.0961369201540947, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:29.477533Z", "loop": 13754, "env_steps": 8451071999, "loss": 0.018735678866505623, "avg_return": 0.8630204200744629, "regret": 0.0003891952510457486, "entropy": 0.09502043575048447, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:30.331214Z", "loop": 13755, "env_steps": 8451686399, "loss": 0.019851725548505783, "avg_return": 0.8643189668655396, "regret": 0.0003891952510457486, "entropy": 0.0938834473490715, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:31.184038Z", "loop": 13756, "env_steps": 8452300799, "loss": 0.019842801615595818, "avg_return": 0.8641537427902222, "regret": 0.0003891952510457486, "entropy": 0.09983028471469879, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:32.038701Z", "loop": 13757, "env_steps": 8452915199, "loss": 0.020548216998577118, "avg_return": 0.8631008267402649, "regret": 0.0003891952510457486, "entropy": 0.09984380751848221, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:32.892506Z", "loop": 13758, "env_steps": 8453529599, "loss": 0.01923811063170433, "avg_return": 0.8636963367462158, "regret": 0.0003891952510457486, "entropy": 0.09856323897838593, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:33.746709Z", "loop": 13759, "env_steps": 8454143999, "loss": 0.019734663888812065, "avg_return": 0.8639068603515625, "regret": 0.0003891952510457486, "entropy": 0.0996517613530159, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:34.642902Z", "loop": 13760, "env_steps": 8454758399, "loss": 0.02020031213760376, "avg_return": 0.86296147108078, "regret": 0.0003824046580120921, "entropy": 0.10309173166751862, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:35.497016Z", "loop": 13761, "env_steps": 8455372799, "loss": 0.0199150200933218, "avg_return": 0.8625409007072449, "regret": 0.0003824046580120921, "entropy": 0.09662485867738724, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:36.353125Z", "loop": 13762, "env_steps": 8455987199, "loss": 0.01818934455513954, "avg_return": 0.8629259467124939, "regret": 0.0003824046580120921, "entropy": 0.09036150574684143, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:37.208771Z", "loop": 13763, "env_steps": 8456601599, "loss": 0.01916009746491909, "avg_return": 0.8636047840118408, "regret": 0.0003824046580120921, "entropy": 0.09346180409193039, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:38.065310Z", "loop": 13764, "env_steps": 8457215999, "loss": 0.018942082300782204, "avg_return": 0.8626096844673157, "regret": 0.0003824046580120921, "entropy": 0.091862253844738, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:38.920135Z", "loop": 13765, "env_steps": 8457830399, "loss": 0.017715098336338997, "avg_return": 0.8631240129470825, "regret": 0.0003824046580120921, "entropy": 0.08955436199903488, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:39.775803Z", "loop": 13766, "env_steps": 8458444799, "loss": 0.018568789586424828, "avg_return": 0.8636980652809143, "regret": 0.0003824046580120921, "entropy": 0.09484531730413437, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:40.631137Z", "loop": 13767, "env_steps": 8459059199, "loss": 0.019227033481001854, "avg_return": 0.8620400428771973, "regret": 0.0003824046580120921, "entropy": 0.09620023518800735, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:41.485636Z", "loop": 13768, "env_steps": 8459673599, "loss": 0.018626399338245392, "avg_return": 0.8614068627357483, "regret": 0.0003824046580120921, "entropy": 0.09442051500082016, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:42.338616Z", "loop": 13769, "env_steps": 8460287999, "loss": 0.02002628706395626, "avg_return": 0.8625911474227905, "regret": 0.0003824046580120921, "entropy": 0.09576968103647232, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:43.231958Z", "loop": 13770, "env_steps": 8460902399, "loss": 0.019780358299613, "avg_return": 0.8607513904571533, "regret": 0.0020550377666950226, "entropy": 0.09803736209869385, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:44.086324Z", "loop": 13771, "env_steps": 8461516799, "loss": 0.020083045586943626, "avg_return": 0.8610712885856628, "regret": 0.0020550377666950226, "entropy": 0.09496058523654938, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:44.940516Z", "loop": 13772, "env_steps": 8462131199, "loss": 0.016992049291729927, "avg_return": 0.8613530397415161, "regret": 0.0020550377666950226, "entropy": 0.08574092388153076, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:45.794655Z", "loop": 13773, "env_steps": 8462745599, "loss": 0.018677057698369026, "avg_return": 0.8600478172302246, "regret": 0.0020550377666950226, "entropy": 0.0884091854095459, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:46.649074Z", "loop": 13774, "env_steps": 8463359999, "loss": 0.018108276650309563, "avg_return": 0.8594328165054321, "regret": 0.0020550377666950226, "entropy": 0.08923933655023575, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:47.502934Z", "loop": 13775, "env_steps": 8463974399, "loss": 0.016920318827033043, "avg_return": 0.8612392544746399, "regret": 0.0020550377666950226, "entropy": 0.0842570960521698, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:48.357628Z", "loop": 13776, "env_steps": 8464588799, "loss": 0.01676199398934841, "avg_return": 0.8618648648262024, "regret": 0.0020550377666950226, "entropy": 0.08606471866369247, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:49.211867Z", "loop": 13777, "env_steps": 8465203199, "loss": 0.01725781336426735, "avg_return": 0.8630965352058411, "regret": 0.0020550377666950226, "entropy": 0.08459647744894028, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:50.065212Z", "loop": 13778, "env_steps": 8465817599, "loss": 0.016307974234223366, "avg_return": 0.8629438281059265, "regret": 0.0020550377666950226, "entropy": 0.08362605422735214, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:50.918784Z", "loop": 13779, "env_steps": 8466431999, "loss": 0.0178391020745039, "avg_return": 0.8626385927200317, "regret": 0.0020550377666950226, "entropy": 0.08988344669342041, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:51.815127Z", "loop": 13780, "env_steps": 8467046399, "loss": 0.016461817547678947, "avg_return": 0.862594723701477, "regret": 0.0008204837795346975, "entropy": 0.08346328139305115, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:52.669850Z", "loop": 13781, "env_steps": 8467660799, "loss": 0.016050394624471664, "avg_return": 0.8620138764381409, "regret": 0.0008204837795346975, "entropy": 0.08348678052425385, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:53.524796Z", "loop": 13782, "env_steps": 8468275199, "loss": 0.016011254861950874, "avg_return": 0.8629980683326721, "regret": 0.0008204837795346975, "entropy": 0.08372742682695389, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:54.379513Z", "loop": 13783, "env_steps": 8468889599, "loss": 0.015645697712898254, "avg_return": 0.8629686832427979, "regret": 0.0008204837795346975, "entropy": 0.08508533239364624, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:55.235022Z", "loop": 13784, "env_steps": 8469503999, "loss": 0.016084758564829826, "avg_return": 0.8616738319396973, "regret": 0.0008204837795346975, "entropy": 0.08323793858289719, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:56.089627Z", "loop": 13785, "env_steps": 8470118399, "loss": 0.01709146983921528, "avg_return": 0.8638821840286255, "regret": 0.0008204837795346975, "entropy": 0.08170603215694427, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:56.942830Z", "loop": 13786, "env_steps": 8470732799, "loss": 0.01655125617980957, "avg_return": 0.862335205078125, "regret": 0.0008204837795346975, "entropy": 0.0824047327041626, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:57.795036Z", "loop": 13787, "env_steps": 8471347199, "loss": 0.017946772277355194, "avg_return": 0.8626875281333923, "regret": 0.0008204837795346975, "entropy": 0.08783714473247528, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:58.648418Z", "loop": 13788, "env_steps": 8471961599, "loss": 0.015647128224372864, "avg_return": 0.8626063466072083, "regret": 0.0008204837795346975, "entropy": 0.08415394276380539, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:40:59.504160Z", "loop": 13789, "env_steps": 8472575999, "loss": 0.015869904309511185, "avg_return": 0.8606914281845093, "regret": 0.0008204837795346975, "entropy": 0.0792403593659401, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:00.399001Z", "loop": 13790, "env_steps": 8473190399, "loss": 0.015789145603775978, "avg_return": 0.8630340695381165, "regret": 0.0010500604985281825, "entropy": 0.08046798408031464, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:01.252503Z", "loop": 13791, "env_steps": 8473804799, "loss": 0.015414095483720303, "avg_return": 0.8628391623497009, "regret": 0.0010500604985281825, "entropy": 0.08236338198184967, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:02.107999Z", "loop": 13792, "env_steps": 8474419199, "loss": 0.01591847464442253, "avg_return": 0.8641794919967651, "regret": 0.0010500604985281825, "entropy": 0.08349331468343735, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:02.962422Z", "loop": 13793, "env_steps": 8475033599, "loss": 0.015390253625810146, "avg_return": 0.8621622920036316, "regret": 0.0010500604985281825, "entropy": 0.08032705634832382, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:03.816943Z", "loop": 13794, "env_steps": 8475647999, "loss": 0.016020743176341057, "avg_return": 0.8635061979293823, "regret": 0.0010500604985281825, "entropy": 0.08140731602907181, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:04.670819Z", "loop": 13795, "env_steps": 8476262399, "loss": 0.016497502103447914, "avg_return": 0.863257884979248, "regret": 0.0010500604985281825, "entropy": 0.08518324047327042, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:05.524249Z", "loop": 13796, "env_steps": 8476876799, "loss": 0.016540123149752617, "avg_return": 0.8618468642234802, "regret": 0.0010500604985281825, "entropy": 0.08170697093009949, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:06.378284Z", "loop": 13797, "env_steps": 8477491199, "loss": 0.016821766272187233, "avg_return": 0.8625381588935852, "regret": 0.0010500604985281825, "entropy": 0.08735959976911545, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:07.233096Z", "loop": 13798, "env_steps": 8478105599, "loss": 0.016916319727897644, "avg_return": 0.8626623749732971, "regret": 0.0010500604985281825, "entropy": 0.08672354370355606, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:08.087220Z", "loop": 13799, "env_steps": 8478719999, "loss": 0.017470479011535645, "avg_return": 0.8617259860038757, "regret": 0.0010500604985281825, "entropy": 0.08598373830318451, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:08.983128Z", "loop": 13800, "env_steps": 8479334399, "loss": 0.016143320128321648, "avg_return": 0.8624793887138367, "regret": 0.0012135833967477083, "entropy": 0.08507592976093292, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:09.836883Z", "loop": 13801, "env_steps": 8479948799, "loss": 0.016447970643639565, "avg_return": 0.8611767888069153, "regret": 0.0012135833967477083, "entropy": 0.08483706414699554, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:10.690499Z", "loop": 13802, "env_steps": 8480563199, "loss": 0.014498293399810791, "avg_return": 0.8620180487632751, "regret": 0.0012135833967477083, "entropy": 0.07882461696863174, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:11.545105Z", "loop": 13803, "env_steps": 8481177599, "loss": 0.01571071147918701, "avg_return": 0.8614915013313293, "regret": 0.0012135833967477083, "entropy": 0.08548349142074585, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:12.399455Z", "loop": 13804, "env_steps": 8481791999, "loss": 0.0162256620824337, "avg_return": 0.8637681007385254, "regret": 0.0012135833967477083, "entropy": 0.07981974631547928, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:13.252354Z", "loop": 13805, "env_steps": 8482406399, "loss": 0.016752852126955986, "avg_return": 0.8633438348770142, "regret": 0.0012135833967477083, "entropy": 0.08626394718885422, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:14.105077Z", "loop": 13806, "env_steps": 8483020799, "loss": 0.014347760938107967, "avg_return": 0.8628896474838257, "regret": 0.0012135833967477083, "entropy": 0.07875572890043259, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:14.959705Z", "loop": 13807, "env_steps": 8483635199, "loss": 0.018114302307367325, "avg_return": 0.8617258667945862, "regret": 0.0012135833967477083, "entropy": 0.08812502771615982, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:15.813517Z", "loop": 13808, "env_steps": 8484249599, "loss": 0.016493048518896103, "avg_return": 0.8624565601348877, "regret": 0.0012135833967477083, "entropy": 0.08231095969676971, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:16.668644Z", "loop": 13809, "env_steps": 8484863999, "loss": 0.017551083117723465, "avg_return": 0.8631874918937683, "regret": 0.0012135833967477083, "entropy": 0.0851498395204544, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:17.563011Z", "loop": 13810, "env_steps": 8485478399, "loss": 0.016356447711586952, "avg_return": 0.8623203635215759, "regret": 0.000508698751218617, "entropy": 0.08768870681524277, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:18.418798Z", "loop": 13811, "env_steps": 8486092799, "loss": 0.017342759296298027, "avg_return": 0.8627384901046753, "regret": 0.000508698751218617, "entropy": 0.08468616008758545, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:19.273088Z", "loop": 13812, "env_steps": 8486707199, "loss": 0.01825028471648693, "avg_return": 0.8631348013877869, "regret": 0.000508698751218617, "entropy": 0.09180032461881638, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:20.127402Z", "loop": 13813, "env_steps": 8487321599, "loss": 0.016810743138194084, "avg_return": 0.8648837208747864, "regret": 0.000508698751218617, "entropy": 0.08500919491052628, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:20.980743Z", "loop": 13814, "env_steps": 8487935999, "loss": 0.016308750957250595, "avg_return": 0.8637498021125793, "regret": 0.000508698751218617, "entropy": 0.08340773731470108, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:21.834799Z", "loop": 13815, "env_steps": 8488550399, "loss": 0.016122298315167427, "avg_return": 0.8628572821617126, "regret": 0.000508698751218617, "entropy": 0.08428898453712463, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:22.688447Z", "loop": 13816, "env_steps": 8489164799, "loss": 0.01709134690463543, "avg_return": 0.8633919358253479, "regret": 0.000508698751218617, "entropy": 0.08524883538484573, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:23.542671Z", "loop": 13817, "env_steps": 8489779199, "loss": 0.016483163461089134, "avg_return": 0.8624398112297058, "regret": 0.000508698751218617, "entropy": 0.08609214425086975, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:24.396893Z", "loop": 13818, "env_steps": 8490393599, "loss": 0.015497996471822262, "avg_return": 0.8635465502738953, "regret": 0.000508698751218617, "entropy": 0.08561303466558456, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:25.250707Z", "loop": 13819, "env_steps": 8491007999, "loss": 0.015844743698835373, "avg_return": 0.8646925091743469, "regret": 0.000508698751218617, "entropy": 0.08559699356555939, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:26.146216Z", "loop": 13820, "env_steps": 8491622399, "loss": 0.016973845660686493, "avg_return": 0.863273024559021, "regret": 0.00036533211823552847, "entropy": 0.08556458353996277, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:26.999688Z", "loop": 13821, "env_steps": 8492236799, "loss": 0.016497565433382988, "avg_return": 0.8621755242347717, "regret": 0.00036533211823552847, "entropy": 0.0865478515625, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:27.855807Z", "loop": 13822, "env_steps": 8492851199, "loss": 0.017430974170565605, "avg_return": 0.862464189529419, "regret": 0.00036533211823552847, "entropy": 0.0918576717376709, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:28.709912Z", "loop": 13823, "env_steps": 8493465599, "loss": 0.0174847524613142, "avg_return": 0.8626737594604492, "regret": 0.00036533211823552847, "entropy": 0.09101841598749161, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:29.563579Z", "loop": 13824, "env_steps": 8494079999, "loss": 0.017130831256508827, "avg_return": 0.8624352216720581, "regret": 0.00036533211823552847, "entropy": 0.08832088857889175, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:30.418137Z", "loop": 13825, "env_steps": 8494694399, "loss": 0.017415238544344902, "avg_return": 0.8627126216888428, "regret": 0.00036533211823552847, "entropy": 0.08998949080705643, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:31.273672Z", "loop": 13826, "env_steps": 8495308799, "loss": 0.018240880221128464, "avg_return": 0.8635357022285461, "regret": 0.00036533211823552847, "entropy": 0.09053903073072433, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:32.128325Z", "loop": 13827, "env_steps": 8495923199, "loss": 0.01941761188209057, "avg_return": 0.8622578978538513, "regret": 0.00036533211823552847, "entropy": 0.09630732238292694, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:32.982477Z", "loop": 13828, "env_steps": 8496537599, "loss": 0.02155250869691372, "avg_return": 0.8638875484466553, "regret": 0.00036533211823552847, "entropy": 0.10512759536504745, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:33.836089Z", "loop": 13829, "env_steps": 8497151999, "loss": 0.022935641929507256, "avg_return": 0.863262951374054, "regret": 0.00036533211823552847, "entropy": 0.10912586748600006, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:34.730657Z", "loop": 13830, "env_steps": 8497766399, "loss": 0.021381443366408348, "avg_return": 0.863073468208313, "regret": 0.0003393346269149333, "entropy": 0.10496314615011215, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:35.583976Z", "loop": 13831, "env_steps": 8498380799, "loss": 0.021637296304106712, "avg_return": 0.8634119033813477, "regret": 0.0003393346269149333, "entropy": 0.1054331511259079, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:36.436957Z", "loop": 13832, "env_steps": 8498995199, "loss": 0.021462200209498405, "avg_return": 0.8635166883468628, "regret": 0.0003393346269149333, "entropy": 0.10595894604921341, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:37.290834Z", "loop": 13833, "env_steps": 8499609599, "loss": 0.020546747371554375, "avg_return": 0.8638430237770081, "regret": 0.0003393346269149333, "entropy": 0.09850060939788818, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:38.144668Z", "loop": 13834, "env_steps": 8500223999, "loss": 0.018641838803887367, "avg_return": 0.8631762862205505, "regret": 0.0003393346269149333, "entropy": 0.09524506330490112, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:38.999967Z", "loop": 13835, "env_steps": 8500838399, "loss": 0.01818959228694439, "avg_return": 0.8639987111091614, "regret": 0.0003393346269149333, "entropy": 0.09072311222553253, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:39.854138Z", "loop": 13836, "env_steps": 8501452799, "loss": 0.016956523060798645, "avg_return": 0.8642354607582092, "regret": 0.0003393346269149333, "entropy": 0.08470551669597626, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:40.707445Z", "loop": 13837, "env_steps": 8502067199, "loss": 0.01584634929895401, "avg_return": 0.8626548647880554, "regret": 0.0003393346269149333, "entropy": 0.08228712528944016, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:41.561581Z", "loop": 13838, "env_steps": 8502681599, "loss": 0.017261188477277756, "avg_return": 0.8637465834617615, "regret": 0.0003393346269149333, "entropy": 0.08215676248073578, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:42.415223Z", "loop": 13839, "env_steps": 8503295999, "loss": 0.01680818572640419, "avg_return": 0.8632039427757263, "regret": 0.0003393346269149333, "entropy": 0.08234716206789017, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:43.308228Z", "loop": 13840, "env_steps": 8503910399, "loss": 0.016730790957808495, "avg_return": 0.8638111352920532, "regret": 0.00032172215287573636, "entropy": 0.08532305061817169, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:44.161893Z", "loop": 13841, "env_steps": 8504524799, "loss": 0.01677773706614971, "avg_return": 0.8640645742416382, "regret": 0.00032172215287573636, "entropy": 0.07924934476613998, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:45.017048Z", "loop": 13842, "env_steps": 8505139199, "loss": 0.016827790066599846, "avg_return": 0.862266480922699, "regret": 0.00032172215287573636, "entropy": 0.08460023254156113, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:45.871804Z", "loop": 13843, "env_steps": 8505753599, "loss": 0.016047433018684387, "avg_return": 0.8638404607772827, "regret": 0.00032172215287573636, "entropy": 0.0857037752866745, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:46.727487Z", "loop": 13844, "env_steps": 8506367999, "loss": 0.016146091744303703, "avg_return": 0.8634166717529297, "regret": 0.00032172215287573636, "entropy": 0.08309229463338852, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:47.582398Z", "loop": 13845, "env_steps": 8506982399, "loss": 0.015811672434210777, "avg_return": 0.8635328412055969, "regret": 0.00032172215287573636, "entropy": 0.08146664500236511, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:48.436864Z", "loop": 13846, "env_steps": 8507596799, "loss": 0.01691218838095665, "avg_return": 0.8639654517173767, "regret": 0.00032172215287573636, "entropy": 0.08669360727071762, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:49.291766Z", "loop": 13847, "env_steps": 8508211199, "loss": 0.01736419089138508, "avg_return": 0.8628033399581909, "regret": 0.00032172215287573636, "entropy": 0.08786095678806305, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:50.147400Z", "loop": 13848, "env_steps": 8508825599, "loss": 0.01600497029721737, "avg_return": 0.8630750775337219, "regret": 0.00032172215287573636, "entropy": 0.08343400061130524, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:51.001397Z", "loop": 13849, "env_steps": 8509439999, "loss": 0.015861671417951584, "avg_return": 0.8624451160430908, "regret": 0.00032172215287573636, "entropy": 0.08389893919229507, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:51.897989Z", "loop": 13850, "env_steps": 8510054399, "loss": 0.01638980023562908, "avg_return": 0.8637516498565674, "regret": 0.0004088847490493208, "entropy": 0.08341684192419052, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:52.752089Z", "loop": 13851, "env_steps": 8510668799, "loss": 0.0164602342993021, "avg_return": 0.8625426292419434, "regret": 0.0004088847490493208, "entropy": 0.08142570406198502, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:53.606367Z", "loop": 13852, "env_steps": 8511283199, "loss": 0.015466307289898396, "avg_return": 0.861535370349884, "regret": 0.0004088847490493208, "entropy": 0.08273778110742569, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:54.461292Z", "loop": 13853, "env_steps": 8511897599, "loss": 0.016993911936879158, "avg_return": 0.861293375492096, "regret": 0.0004088847490493208, "entropy": 0.08543329685926437, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:55.316691Z", "loop": 13854, "env_steps": 8512511999, "loss": 0.016763342544436455, "avg_return": 0.8625065088272095, "regret": 0.0004088847490493208, "entropy": 0.08577113598585129, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:56.171052Z", "loop": 13855, "env_steps": 8513126399, "loss": 0.016935382038354874, "avg_return": 0.863598644733429, "regret": 0.0004088847490493208, "entropy": 0.087652288377285, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:57.025594Z", "loop": 13856, "env_steps": 8513740799, "loss": 0.015941211953759193, "avg_return": 0.8633432388305664, "regret": 0.0004088847490493208, "entropy": 0.08481964468955994, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:57.881497Z", "loop": 13857, "env_steps": 8514355199, "loss": 0.016838135197758675, "avg_return": 0.863288402557373, "regret": 0.0004088847490493208, "entropy": 0.0843292698264122, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:58.737048Z", "loop": 13858, "env_steps": 8514969599, "loss": 0.016889704391360283, "avg_return": 0.8635091185569763, "regret": 0.0004088847490493208, "entropy": 0.08534117043018341, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:41:59.590622Z", "loop": 13859, "env_steps": 8515583999, "loss": 0.016315214335918427, "avg_return": 0.8634691834449768, "regret": 0.0004088847490493208, "entropy": 0.08396364003419876, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:00.484543Z", "loop": 13860, "env_steps": 8516198399, "loss": 0.016573060303926468, "avg_return": 0.8629143238067627, "regret": 0.00037171292933635414, "entropy": 0.08413000404834747, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:01.339260Z", "loop": 13861, "env_steps": 8516812799, "loss": 0.016201646998524666, "avg_return": 0.8636525869369507, "regret": 0.00037171292933635414, "entropy": 0.08527703583240509, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:02.194820Z", "loop": 13862, "env_steps": 8517427199, "loss": 0.016394568607211113, "avg_return": 0.862230658531189, "regret": 0.00037171292933635414, "entropy": 0.0854312926530838, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:03.050129Z", "loop": 13863, "env_steps": 8518041599, "loss": 0.016719667240977287, "avg_return": 0.8631861805915833, "regret": 0.00037171292933635414, "entropy": 0.08449102938175201, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:03.904712Z", "loop": 13864, "env_steps": 8518655999, "loss": 0.01612110249698162, "avg_return": 0.862854540348053, "regret": 0.00037171292933635414, "entropy": 0.08488784730434418, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:04.758826Z", "loop": 13865, "env_steps": 8519270399, "loss": 0.01622973568737507, "avg_return": 0.862917423248291, "regret": 0.00037171292933635414, "entropy": 0.08533389866352081, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:05.613448Z", "loop": 13866, "env_steps": 8519884799, "loss": 0.01597987301647663, "avg_return": 0.8632832765579224, "regret": 0.00037171292933635414, "entropy": 0.08374467492103577, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:06.468051Z", "loop": 13867, "env_steps": 8520499199, "loss": 0.015806114301085472, "avg_return": 0.8634049892425537, "regret": 0.00037171292933635414, "entropy": 0.08536537736654282, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:07.324398Z", "loop": 13868, "env_steps": 8521113599, "loss": 0.016352131962776184, "avg_return": 0.8618330955505371, "regret": 0.00037171292933635414, "entropy": 0.08696552366018295, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:08.179657Z", "loop": 13869, "env_steps": 8521727999, "loss": 0.01703338883817196, "avg_return": 0.8638449311256409, "regret": 0.00037171292933635414, "entropy": 0.08699105679988861, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:09.074449Z", "loop": 13870, "env_steps": 8522342399, "loss": 0.016290856525301933, "avg_return": 0.8639035224914551, "regret": 0.000494521576911211, "entropy": 0.08435340225696564, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:09.928579Z", "loop": 13871, "env_steps": 8522956799, "loss": 0.016992537304759026, "avg_return": 0.8636320233345032, "regret": 0.000494521576911211, "entropy": 0.08566098660230637, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:10.783750Z", "loop": 13872, "env_steps": 8523571199, "loss": 0.017882395535707474, "avg_return": 0.862433910369873, "regret": 0.000494521576911211, "entropy": 0.08505616337060928, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:11.637634Z", "loop": 13873, "env_steps": 8524185599, "loss": 0.016622042283415794, "avg_return": 0.8636727333068848, "regret": 0.000494521576911211, "entropy": 0.08473841845989227, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:12.491666Z", "loop": 13874, "env_steps": 8524799999, "loss": 0.016219351440668106, "avg_return": 0.8631906509399414, "regret": 0.000494521576911211, "entropy": 0.08383716642856598, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:13.346414Z", "loop": 13875, "env_steps": 8525414399, "loss": 0.016573112457990646, "avg_return": 0.8612822890281677, "regret": 0.000494521576911211, "entropy": 0.08631859719753265, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:14.201047Z", "loop": 13876, "env_steps": 8526028799, "loss": 0.017208533361554146, "avg_return": 0.8636941909790039, "regret": 0.000494521576911211, "entropy": 0.08719593286514282, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:15.056191Z", "loop": 13877, "env_steps": 8526643199, "loss": 0.018000813201069832, "avg_return": 0.8632796406745911, "regret": 0.000494521576911211, "entropy": 0.08996022492647171, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:15.910777Z", "loop": 13878, "env_steps": 8527257599, "loss": 0.018305009230971336, "avg_return": 0.861299455165863, "regret": 0.000494521576911211, "entropy": 0.08986447751522064, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:16.765541Z", "loop": 13879, "env_steps": 8527871999, "loss": 0.01779615879058838, "avg_return": 0.8630107045173645, "regret": 0.000494521576911211, "entropy": 0.09092118591070175, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:17.660932Z", "loop": 13880, "env_steps": 8528486399, "loss": 0.017440814524888992, "avg_return": 0.8637747168540955, "regret": 0.0009540673927403986, "entropy": 0.08969561755657196, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:18.515446Z", "loop": 13881, "env_steps": 8529100799, "loss": 0.01707029901444912, "avg_return": 0.8628720045089722, "regret": 0.0009540673927403986, "entropy": 0.08800259232521057, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:19.368937Z", "loop": 13882, "env_steps": 8529715199, "loss": 0.017767442390322685, "avg_return": 0.8631781339645386, "regret": 0.0009540673927403986, "entropy": 0.09040410816669464, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:20.221882Z", "loop": 13883, "env_steps": 8530329599, "loss": 0.01836627535521984, "avg_return": 0.8616458177566528, "regret": 0.0009540673927403986, "entropy": 0.09028813242912292, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:21.074894Z", "loop": 13884, "env_steps": 8530943999, "loss": 0.017308147624135017, "avg_return": 0.863457977771759, "regret": 0.0009540673927403986, "entropy": 0.09082438796758652, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:21.929452Z", "loop": 13885, "env_steps": 8531558399, "loss": 0.017452679574489594, "avg_return": 0.862489640712738, "regret": 0.0009540673927403986, "entropy": 0.08595836162567139, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:22.784045Z", "loop": 13886, "env_steps": 8532172799, "loss": 0.017772508785128593, "avg_return": 0.8624807000160217, "regret": 0.0009540673927403986, "entropy": 0.09386738389730453, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:23.637194Z", "loop": 13887, "env_steps": 8532787199, "loss": 0.019871404394507408, "avg_return": 0.8617932200431824, "regret": 0.0009540673927403986, "entropy": 0.09676583856344223, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:24.490548Z", "loop": 13888, "env_steps": 8533401599, "loss": 0.02011476457118988, "avg_return": 0.8606703877449036, "regret": 0.0009540673927403986, "entropy": 0.09883766621351242, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:25.344633Z", "loop": 13889, "env_steps": 8534015999, "loss": 0.020718183368444443, "avg_return": 0.8623179197311401, "regret": 0.0009540673927403986, "entropy": 0.10296725481748581, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:26.237720Z", "loop": 13890, "env_steps": 8534630399, "loss": 0.02090277522802353, "avg_return": 0.8609073162078857, "regret": 0.0028525751549750566, "entropy": 0.10413902252912521, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:27.091787Z", "loop": 13891, "env_steps": 8535244799, "loss": 0.020203648135066032, "avg_return": 0.8608762621879578, "regret": 0.0028525751549750566, "entropy": 0.10183408856391907, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:27.946003Z", "loop": 13892, "env_steps": 8535859199, "loss": 0.022126173600554466, "avg_return": 0.861494243144989, "regret": 0.0028525751549750566, "entropy": 0.11009155213832855, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:28.800954Z", "loop": 13893, "env_steps": 8536473599, "loss": 0.022460905835032463, "avg_return": 0.8616166114807129, "regret": 0.0028525751549750566, "entropy": 0.10691418498754501, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:29.655208Z", "loop": 13894, "env_steps": 8537087999, "loss": 0.019914304837584496, "avg_return": 0.8630329370498657, "regret": 0.0028525751549750566, "entropy": 0.1019548550248146, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:30.508398Z", "loop": 13895, "env_steps": 8537702399, "loss": 0.01997421681880951, "avg_return": 0.8603094816207886, "regret": 0.0028525751549750566, "entropy": 0.10106462240219116, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:31.362675Z", "loop": 13896, "env_steps": 8538316799, "loss": 0.01993446610867977, "avg_return": 0.8604522943496704, "regret": 0.0028525751549750566, "entropy": 0.10061892122030258, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:32.217558Z", "loop": 13897, "env_steps": 8538931199, "loss": 0.020004751160740852, "avg_return": 0.861416757106781, "regret": 0.0028525751549750566, "entropy": 0.10196511447429657, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:33.072233Z", "loop": 13898, "env_steps": 8539545599, "loss": 0.019275065511465073, "avg_return": 0.8622904419898987, "regret": 0.0028525751549750566, "entropy": 0.09731481224298477, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:33.926330Z", "loop": 13899, "env_steps": 8540159999, "loss": 0.01969287358224392, "avg_return": 0.8619807362556458, "regret": 0.0028525751549750566, "entropy": 0.09789546579122543, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:34.822517Z", "loop": 13900, "env_steps": 8540774399, "loss": 0.019976040348410606, "avg_return": 0.8622196912765503, "regret": 0.0011259906459599733, "entropy": 0.10015694797039032, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:35.676427Z", "loop": 13901, "env_steps": 8541388799, "loss": 0.0198788121342659, "avg_return": 0.862191379070282, "regret": 0.0011259906459599733, "entropy": 0.1017984002828598, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:36.530847Z", "loop": 13902, "env_steps": 8542003199, "loss": 0.0198548324406147, "avg_return": 0.8621243238449097, "regret": 0.0011259906459599733, "entropy": 0.09985291212797165, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:37.385255Z", "loop": 13903, "env_steps": 8542617599, "loss": 0.020007435232400894, "avg_return": 0.8641490936279297, "regret": 0.0011259906459599733, "entropy": 0.09842698276042938, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:38.240162Z", "loop": 13904, "env_steps": 8543231999, "loss": 0.017809702083468437, "avg_return": 0.8636128902435303, "regret": 0.0011259906459599733, "entropy": 0.09435541182756424, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:39.097060Z", "loop": 13905, "env_steps": 8543846399, "loss": 0.017292486503720284, "avg_return": 0.8641401529312134, "regret": 0.0011259906459599733, "entropy": 0.088634192943573, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:39.950573Z", "loop": 13906, "env_steps": 8544460799, "loss": 0.016360381618142128, "avg_return": 0.8633314967155457, "regret": 0.0011259906459599733, "entropy": 0.08240291476249695, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:40.804729Z", "loop": 13907, "env_steps": 8545075199, "loss": 0.014783471822738647, "avg_return": 0.8633391261100769, "regret": 0.0011259906459599733, "entropy": 0.08067816495895386, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:41.658813Z", "loop": 13908, "env_steps": 8545689599, "loss": 0.016761958599090576, "avg_return": 0.8636277318000793, "regret": 0.0011259906459599733, "entropy": 0.08766598254442215, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:42.512210Z", "loop": 13909, "env_steps": 8546303999, "loss": 0.01761535368859768, "avg_return": 0.8632004857063293, "regret": 0.0011259906459599733, "entropy": 0.08646681904792786, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:43.406841Z", "loop": 13910, "env_steps": 8546918399, "loss": 0.016443902626633644, "avg_return": 0.8637928366661072, "regret": 0.00041393315768800676, "entropy": 0.08365383744239807, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:44.261715Z", "loop": 13911, "env_steps": 8547532799, "loss": 0.0170514564961195, "avg_return": 0.8635467886924744, "regret": 0.00041393315768800676, "entropy": 0.08680471032857895, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:45.117156Z", "loop": 13912, "env_steps": 8548147199, "loss": 0.017912648618221283, "avg_return": 0.86271071434021, "regret": 0.00041393315768800676, "entropy": 0.09011966735124588, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:45.972469Z", "loop": 13913, "env_steps": 8548761599, "loss": 0.016718365252017975, "avg_return": 0.8629084229469299, "regret": 0.00041393315768800676, "entropy": 0.08594303578138351, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:46.827060Z", "loop": 13914, "env_steps": 8549375999, "loss": 0.0175629872828722, "avg_return": 0.8624780774116516, "regret": 0.00041393315768800676, "entropy": 0.08572912961244583, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:47.680804Z", "loop": 13915, "env_steps": 8549990399, "loss": 0.0170612670481205, "avg_return": 0.8628491163253784, "regret": 0.00041393315768800676, "entropy": 0.08690571784973145, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:48.536073Z", "loop": 13916, "env_steps": 8550604799, "loss": 0.017318034544587135, "avg_return": 0.8626308441162109, "regret": 0.00041393315768800676, "entropy": 0.08835848420858383, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:49.390905Z", "loop": 13917, "env_steps": 8551219199, "loss": 0.016249792650341988, "avg_return": 0.862213134765625, "regret": 0.00041393315768800676, "entropy": 0.08533407747745514, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:50.245124Z", "loop": 13918, "env_steps": 8551833599, "loss": 0.015747519209980965, "avg_return": 0.8628674745559692, "regret": 0.00041393315768800676, "entropy": 0.08296050131320953, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:51.099698Z", "loop": 13919, "env_steps": 8552447999, "loss": 0.016661962494254112, "avg_return": 0.8622899651527405, "regret": 0.00041393315768800676, "entropy": 0.08892616629600525, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:51.993812Z", "loop": 13920, "env_steps": 8553062399, "loss": 0.016110489144921303, "avg_return": 0.8615002632141113, "regret": 0.001048872945830226, "entropy": 0.08312362432479858, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:52.847181Z", "loop": 13921, "env_steps": 8553676799, "loss": 0.016157392412424088, "avg_return": 0.8615949749946594, "regret": 0.001048872945830226, "entropy": 0.08182922005653381, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:53.701778Z", "loop": 13922, "env_steps": 8554291199, "loss": 0.017409436404705048, "avg_return": 0.861825168132782, "regret": 0.001048872945830226, "entropy": 0.09026116877794266, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:54.556872Z", "loop": 13923, "env_steps": 8554905599, "loss": 0.015610218048095703, "avg_return": 0.8626648187637329, "regret": 0.001048872945830226, "entropy": 0.08177806437015533, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:55.410829Z", "loop": 13924, "env_steps": 8555519999, "loss": 0.016713028773665428, "avg_return": 0.861487865447998, "regret": 0.001048872945830226, "entropy": 0.08597879856824875, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:56.264661Z", "loop": 13925, "env_steps": 8556134399, "loss": 0.016881948336958885, "avg_return": 0.8633283972740173, "regret": 0.001048872945830226, "entropy": 0.08856289088726044, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:57.119352Z", "loop": 13926, "env_steps": 8556748799, "loss": 0.015797710046172142, "avg_return": 0.8619630932807922, "regret": 0.001048872945830226, "entropy": 0.08012210577726364, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:57.973060Z", "loop": 13927, "env_steps": 8557363199, "loss": 0.016332551836967468, "avg_return": 0.8625418543815613, "regret": 0.001048872945830226, "entropy": 0.08587423712015152, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:58.827523Z", "loop": 13928, "env_steps": 8557977599, "loss": 0.01659027300775051, "avg_return": 0.8615070581436157, "regret": 0.001048872945830226, "entropy": 0.08609859645366669, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:42:59.681681Z", "loop": 13929, "env_steps": 8558591999, "loss": 0.01610286720097065, "avg_return": 0.862740695476532, "regret": 0.001048872945830226, "entropy": 0.0851210504770279, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:00.576020Z", "loop": 13930, "env_steps": 8559206399, "loss": 0.017226656898856163, "avg_return": 0.8623560667037964, "regret": 0.0013353711692616343, "entropy": 0.09165659546852112, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:01.429922Z", "loop": 13931, "env_steps": 8559820799, "loss": 0.01726291887462139, "avg_return": 0.8627231121063232, "regret": 0.0013353711692616343, "entropy": 0.08784125745296478, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:02.283390Z", "loop": 13932, "env_steps": 8560435199, "loss": 0.01749017834663391, "avg_return": 0.8605654239654541, "regret": 0.0013353711692616343, "entropy": 0.09066762030124664, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:03.136393Z", "loop": 13933, "env_steps": 8561049599, "loss": 0.017838967964053154, "avg_return": 0.862294614315033, "regret": 0.0013353711692616343, "entropy": 0.09156864881515503, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:03.989451Z", "loop": 13934, "env_steps": 8561663999, "loss": 0.019219836220145226, "avg_return": 0.8608294725418091, "regret": 0.0013353711692616343, "entropy": 0.0966922715306282, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:04.843203Z", "loop": 13935, "env_steps": 8562278399, "loss": 0.01987001672387123, "avg_return": 0.8602568507194519, "regret": 0.0013353711692616343, "entropy": 0.10180456191301346, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:05.697352Z", "loop": 13936, "env_steps": 8562892799, "loss": 0.01904376409947872, "avg_return": 0.8611487150192261, "regret": 0.0013353711692616343, "entropy": 0.09951338171958923, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:06.550368Z", "loop": 13937, "env_steps": 8563507199, "loss": 0.020515140146017075, "avg_return": 0.860931932926178, "regret": 0.0013353711692616343, "entropy": 0.10617367923259735, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:07.403903Z", "loop": 13938, "env_steps": 8564121599, "loss": 0.019773678854107857, "avg_return": 0.8601361513137817, "regret": 0.0013353711692616343, "entropy": 0.0995820090174675, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:08.258252Z", "loop": 13939, "env_steps": 8564735999, "loss": 0.01804271899163723, "avg_return": 0.8621170520782471, "regret": 0.0013353711692616343, "entropy": 0.09563928097486496, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:09.154857Z", "loop": 13940, "env_steps": 8565350399, "loss": 0.017558855935931206, "avg_return": 0.8618077635765076, "regret": 0.0017926819855347276, "entropy": 0.09705895185470581, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:10.008744Z", "loop": 13941, "env_steps": 8565964799, "loss": 0.01658601500093937, "avg_return": 0.8626157641410828, "regret": 0.0017926819855347276, "entropy": 0.09293783456087112, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:10.862397Z", "loop": 13942, "env_steps": 8566579199, "loss": 0.017786113545298576, "avg_return": 0.8622446656227112, "regret": 0.0017926819855347276, "entropy": 0.09320025891065598, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:11.716524Z", "loop": 13943, "env_steps": 8567193599, "loss": 0.017969729378819466, "avg_return": 0.8626357316970825, "regret": 0.0017926819855347276, "entropy": 0.09577053785324097, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:12.570365Z", "loop": 13944, "env_steps": 8567807999, "loss": 0.017202166840434074, "avg_return": 0.8620808124542236, "regret": 0.0017926819855347276, "entropy": 0.09894579648971558, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:13.424290Z", "loop": 13945, "env_steps": 8568422399, "loss": 0.01870858669281006, "avg_return": 0.8615332245826721, "regret": 0.0017926819855347276, "entropy": 0.09566379338502884, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:14.277716Z", "loop": 13946, "env_steps": 8569036799, "loss": 0.018390556797385216, "avg_return": 0.8615320324897766, "regret": 0.0017926819855347276, "entropy": 0.09874972701072693, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:15.131772Z", "loop": 13947, "env_steps": 8569651199, "loss": 0.018038025125861168, "avg_return": 0.8610479831695557, "regret": 0.0017926819855347276, "entropy": 0.09558071196079254, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:15.985811Z", "loop": 13948, "env_steps": 8570265599, "loss": 0.018641624599695206, "avg_return": 0.8622156977653503, "regret": 0.0017926819855347276, "entropy": 0.09680429846048355, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:16.839967Z", "loop": 13949, "env_steps": 8570879999, "loss": 0.017178839072585106, "avg_return": 0.8614782094955444, "regret": 0.0017926819855347276, "entropy": 0.09286122024059296, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:17.734140Z", "loop": 13950, "env_steps": 8571494399, "loss": 0.01812809891998768, "avg_return": 0.8610731959342957, "regret": 0.0017680232413113117, "entropy": 0.09692949056625366, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:18.589138Z", "loop": 13951, "env_steps": 8572108799, "loss": 0.017267979681491852, "avg_return": 0.8626360297203064, "regret": 0.0017680232413113117, "entropy": 0.09209248423576355, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:19.443738Z", "loop": 13952, "env_steps": 8572723199, "loss": 0.016339397057890892, "avg_return": 0.8618530631065369, "regret": 0.0017680232413113117, "entropy": 0.08897334337234497, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:20.297910Z", "loop": 13953, "env_steps": 8573337599, "loss": 0.016140509396791458, "avg_return": 0.8618878126144409, "regret": 0.0017680232413113117, "entropy": 0.0878622978925705, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:21.152077Z", "loop": 13954, "env_steps": 8573951999, "loss": 0.014885184355080128, "avg_return": 0.8626308441162109, "regret": 0.0017680232413113117, "entropy": 0.08363336324691772, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:22.006549Z", "loop": 13955, "env_steps": 8574566399, "loss": 0.01616615056991577, "avg_return": 0.863505482673645, "regret": 0.0017680232413113117, "entropy": 0.08600753545761108, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:22.860895Z", "loop": 13956, "env_steps": 8575180799, "loss": 0.015338149853050709, "avg_return": 0.8631977438926697, "regret": 0.0017680232413113117, "entropy": 0.08383709192276001, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:23.714799Z", "loop": 13957, "env_steps": 8575795199, "loss": 0.016296032816171646, "avg_return": 0.8621327877044678, "regret": 0.0017680232413113117, "entropy": 0.08680270612239838, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:24.568754Z", "loop": 13958, "env_steps": 8576409599, "loss": 0.0165623240172863, "avg_return": 0.8625317811965942, "regret": 0.0017680232413113117, "entropy": 0.08425182104110718, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:25.422862Z", "loop": 13959, "env_steps": 8577023999, "loss": 0.01583787053823471, "avg_return": 0.8619641065597534, "regret": 0.0017680232413113117, "entropy": 0.0856315940618515, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:26.316351Z", "loop": 13960, "env_steps": 8577638399, "loss": 0.015085001476109028, "avg_return": 0.8629348874092102, "regret": 0.000538657302968204, "entropy": 0.07965198159217834, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:27.170298Z", "loop": 13961, "env_steps": 8578252799, "loss": 0.01501000951975584, "avg_return": 0.8631119728088379, "regret": 0.000538657302968204, "entropy": 0.08053997159004211, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:28.024803Z", "loop": 13962, "env_steps": 8578867199, "loss": 0.015036185272037983, "avg_return": 0.8633065223693848, "regret": 0.000538657302968204, "entropy": 0.08126313239336014, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:28.879659Z", "loop": 13963, "env_steps": 8579481599, "loss": 0.015238421969115734, "avg_return": 0.8635004162788391, "regret": 0.000538657302968204, "entropy": 0.0796523466706276, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:29.733295Z", "loop": 13964, "env_steps": 8580095999, "loss": 0.015799783170223236, "avg_return": 0.8621795773506165, "regret": 0.000538657302968204, "entropy": 0.0808168575167656, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:30.587259Z", "loop": 13965, "env_steps": 8580710399, "loss": 0.014007436111569405, "avg_return": 0.8623625040054321, "regret": 0.000538657302968204, "entropy": 0.07661991566419601, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:31.441873Z", "loop": 13966, "env_steps": 8581324799, "loss": 0.01563304476439953, "avg_return": 0.8627435564994812, "regret": 0.000538657302968204, "entropy": 0.0797286406159401, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:32.297318Z", "loop": 13967, "env_steps": 8581939199, "loss": 0.014709673821926117, "avg_return": 0.8623082637786865, "regret": 0.000538657302968204, "entropy": 0.08107057958841324, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:33.151617Z", "loop": 13968, "env_steps": 8582553599, "loss": 0.015598888508975506, "avg_return": 0.8620164394378662, "regret": 0.000538657302968204, "entropy": 0.07674974203109741, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:34.005445Z", "loop": 13969, "env_steps": 8583167999, "loss": 0.015645384788513184, "avg_return": 0.8629160523414612, "regret": 0.000538657302968204, "entropy": 0.07993420213460922, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:34.900647Z", "loop": 13970, "env_steps": 8583782399, "loss": 0.015684572979807854, "avg_return": 0.8629533052444458, "regret": 0.0005940155824646354, "entropy": 0.07981246709823608, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:35.754772Z", "loop": 13971, "env_steps": 8584396799, "loss": 0.015376107767224312, "avg_return": 0.8628214597702026, "regret": 0.0005940155824646354, "entropy": 0.08379988372325897, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:36.608752Z", "loop": 13972, "env_steps": 8585011199, "loss": 0.015789149329066277, "avg_return": 0.8631330728530884, "regret": 0.0005940155824646354, "entropy": 0.08035355061292648, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:37.462562Z", "loop": 13973, "env_steps": 8585625599, "loss": 0.015185452066361904, "avg_return": 0.8637152314186096, "regret": 0.0005940155824646354, "entropy": 0.07904832810163498, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:38.316252Z", "loop": 13974, "env_steps": 8586239999, "loss": 0.015709003433585167, "avg_return": 0.8613523840904236, "regret": 0.0005940155824646354, "entropy": 0.08315035700798035, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:39.171155Z", "loop": 13975, "env_steps": 8586854399, "loss": 0.015226326882839203, "avg_return": 0.8648675680160522, "regret": 0.0005940155824646354, "entropy": 0.07905986905097961, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:40.025081Z", "loop": 13976, "env_steps": 8587468799, "loss": 0.015393458306789398, "avg_return": 0.8635579347610474, "regret": 0.0005940155824646354, "entropy": 0.0784941017627716, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:40.879331Z", "loop": 13977, "env_steps": 8588083199, "loss": 0.01662135124206543, "avg_return": 0.8631095290184021, "regret": 0.0005940155824646354, "entropy": 0.08505649864673615, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:41.733576Z", "loop": 13978, "env_steps": 8588697599, "loss": 0.015229408629238605, "avg_return": 0.8631575703620911, "regret": 0.0005940155824646354, "entropy": 0.08157094568014145, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:42.588088Z", "loop": 13979, "env_steps": 8589311999, "loss": 0.015598686411976814, "avg_return": 0.8632973432540894, "regret": 0.0005940155824646354, "entropy": 0.08133444935083389, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:43.482448Z", "loop": 13980, "env_steps": 8589926399, "loss": 0.015479139983654022, "avg_return": 0.8631446361541748, "regret": 0.0005383479292504489, "entropy": 0.08173111081123352, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:44.336467Z", "loop": 13981, "env_steps": 8590540799, "loss": 0.015682164579629898, "avg_return": 0.8632668256759644, "regret": 0.0005383479292504489, "entropy": 0.0828850120306015, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:45.189548Z", "loop": 13982, "env_steps": 8591155199, "loss": 0.01560488622635603, "avg_return": 0.8620518445968628, "regret": 0.0005383479292504489, "entropy": 0.08188829571008682, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:46.043451Z", "loop": 13983, "env_steps": 8591769599, "loss": 0.015742063522338867, "avg_return": 0.8630516529083252, "regret": 0.0005383479292504489, "entropy": 0.08285649120807648, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:46.897429Z", "loop": 13984, "env_steps": 8592383999, "loss": 0.015903202816843987, "avg_return": 0.8618147969245911, "regret": 0.0005383479292504489, "entropy": 0.08385423570871353, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:47.750815Z", "loop": 13985, "env_steps": 8592998399, "loss": 0.016189223155379295, "avg_return": 0.8628145456314087, "regret": 0.0005383479292504489, "entropy": 0.07993070781230927, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:48.604927Z", "loop": 13986, "env_steps": 8593612799, "loss": 0.015425952151417732, "avg_return": 0.8634414076805115, "regret": 0.0005383479292504489, "entropy": 0.08078370243310928, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:49.459309Z", "loop": 13987, "env_steps": 8594227199, "loss": 0.01702025718986988, "avg_return": 0.8635269403457642, "regret": 0.0005383479292504489, "entropy": 0.08544060587882996, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:50.313921Z", "loop": 13988, "env_steps": 8594841599, "loss": 0.01634812541306019, "avg_return": 0.8625447750091553, "regret": 0.0005383479292504489, "entropy": 0.08645135909318924, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:51.167999Z", "loop": 13989, "env_steps": 8595455999, "loss": 0.016198655590415, "avg_return": 0.8619290590286255, "regret": 0.0005383479292504489, "entropy": 0.08320022374391556, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:52.060640Z", "loop": 13990, "env_steps": 8596070399, "loss": 0.016843615099787712, "avg_return": 0.8612604141235352, "regret": 0.0010251995408907533, "entropy": 0.08743570744991302, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:52.915556Z", "loop": 13991, "env_steps": 8596684799, "loss": 0.01633867248892784, "avg_return": 0.8625714182853699, "regret": 0.0010251995408907533, "entropy": 0.08795520663261414, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:53.769169Z", "loop": 13992, "env_steps": 8597299199, "loss": 0.01676289737224579, "avg_return": 0.8628252148628235, "regret": 0.0010251995408907533, "entropy": 0.08754992485046387, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:54.623379Z", "loop": 13993, "env_steps": 8597913599, "loss": 0.01647474244236946, "avg_return": 0.8631342649459839, "regret": 0.0010251995408907533, "entropy": 0.087221659719944, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:55.477092Z", "loop": 13994, "env_steps": 8598527999, "loss": 0.01702205091714859, "avg_return": 0.8629148602485657, "regret": 0.0010251995408907533, "entropy": 0.09414144605398178, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:56.332344Z", "loop": 13995, "env_steps": 8599142399, "loss": 0.01732543110847473, "avg_return": 0.8622342944145203, "regret": 0.0010251995408907533, "entropy": 0.09066653251647949, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:57.186123Z", "loop": 13996, "env_steps": 8599756799, "loss": 0.018353736028075218, "avg_return": 0.8611815571784973, "regret": 0.0010251995408907533, "entropy": 0.09527791291475296, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:58.040298Z", "loop": 13997, "env_steps": 8600371199, "loss": 0.018022749572992325, "avg_return": 0.8628255128860474, "regret": 0.0010251995408907533, "entropy": 0.09394938498735428, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:58.893800Z", "loop": 13998, "env_steps": 8600985599, "loss": 0.018879560753703117, "avg_return": 0.8641427755355835, "regret": 0.0010251995408907533, "entropy": 0.09728740900754929, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:43:59.748799Z", "loop": 13999, "env_steps": 8601599999, "loss": 0.019626948982477188, "avg_return": 0.8611031174659729, "regret": 0.0010251995408907533, "entropy": 0.10293007642030716, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:00.642797Z", "loop": 14000, "env_steps": 8602214399, "loss": 0.018802925944328308, "avg_return": 0.8615303635597229, "regret": 0.001985996961593628, "entropy": 0.09891119599342346, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:01.496267Z", "loop": 14001, "env_steps": 8602828799, "loss": 0.019093716517090797, "avg_return": 0.8620491623878479, "regret": 0.001985996961593628, "entropy": 0.0974845290184021, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:02.350013Z", "loop": 14002, "env_steps": 8603443199, "loss": 0.018949396908283234, "avg_return": 0.8621826171875, "regret": 0.001985996961593628, "entropy": 0.10214348882436752, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:03.205078Z", "loop": 14003, "env_steps": 8604057599, "loss": 0.018940327689051628, "avg_return": 0.8622555732727051, "regret": 0.001985996961593628, "entropy": 0.10249128937721252, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:04.058658Z", "loop": 14004, "env_steps": 8604671999, "loss": 0.0209522508084774, "avg_return": 0.8617430925369263, "regret": 0.001985996961593628, "entropy": 0.10634465515613556, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:04.912726Z", "loop": 14005, "env_steps": 8605286399, "loss": 0.020934851840138435, "avg_return": 0.8613852858543396, "regret": 0.001985996961593628, "entropy": 0.11290045082569122, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:05.766816Z", "loop": 14006, "env_steps": 8605900799, "loss": 0.019635692238807678, "avg_return": 0.861274242401123, "regret": 0.001985996961593628, "entropy": 0.11174874752759933, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:06.620767Z", "loop": 14007, "env_steps": 8606515199, "loss": 0.019106587395071983, "avg_return": 0.8625834584236145, "regret": 0.001985996961593628, "entropy": 0.10319072008132935, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:07.474586Z", "loop": 14008, "env_steps": 8607129599, "loss": 0.01922854408621788, "avg_return": 0.8625451922416687, "regret": 0.001985996961593628, "entropy": 0.10281281918287277, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:08.327617Z", "loop": 14009, "env_steps": 8607743999, "loss": 0.01824512518942356, "avg_return": 0.8615522384643555, "regret": 0.001985996961593628, "entropy": 0.10127788037061691, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:09.221911Z", "loop": 14010, "env_steps": 8608358399, "loss": 0.019736506044864655, "avg_return": 0.8629079461097717, "regret": 0.0010770905064418912, "entropy": 0.10188421607017517, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:10.076114Z", "loop": 14011, "env_steps": 8608972799, "loss": 0.019191129133105278, "avg_return": 0.8634509444236755, "regret": 0.0010770905064418912, "entropy": 0.0986647978425026, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:10.930270Z", "loop": 14012, "env_steps": 8609587199, "loss": 0.017706183716654778, "avg_return": 0.8618261814117432, "regret": 0.0010770905064418912, "entropy": 0.09465674310922623, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:11.784204Z", "loop": 14013, "env_steps": 8610201599, "loss": 0.017128780484199524, "avg_return": 0.8632747530937195, "regret": 0.0010770905064418912, "entropy": 0.09241020679473877, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:12.637933Z", "loop": 14014, "env_steps": 8610815999, "loss": 0.01685970276594162, "avg_return": 0.8625845313072205, "regret": 0.0010770905064418912, "entropy": 0.0887102484703064, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:13.491949Z", "loop": 14015, "env_steps": 8611430399, "loss": 0.01786608248949051, "avg_return": 0.8628730177879333, "regret": 0.0010770905064418912, "entropy": 0.09191416949033737, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:14.346303Z", "loop": 14016, "env_steps": 8612044799, "loss": 0.016440393403172493, "avg_return": 0.8632852435112, "regret": 0.0010770905064418912, "entropy": 0.08582653850317001, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:15.200439Z", "loop": 14017, "env_steps": 8612659199, "loss": 0.015466063283383846, "avg_return": 0.8635604977607727, "regret": 0.0010770905064418912, "entropy": 0.07970115542411804, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:16.054976Z", "loop": 14018, "env_steps": 8613273599, "loss": 0.014748875983059406, "avg_return": 0.8627861738204956, "regret": 0.0010770905064418912, "entropy": 0.07835178077220917, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:16.908398Z", "loop": 14019, "env_steps": 8613887999, "loss": 0.015999509021639824, "avg_return": 0.8619121313095093, "regret": 0.0010770905064418912, "entropy": 0.07711268961429596, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:17.802398Z", "loop": 14020, "env_steps": 8614502399, "loss": 0.016308356076478958, "avg_return": 0.8622784614562988, "regret": 0.0005676253349520266, "entropy": 0.08321433514356613, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:18.655778Z", "loop": 14021, "env_steps": 8615116799, "loss": 0.015331536531448364, "avg_return": 0.8630194067955017, "regret": 0.0005676253349520266, "entropy": 0.08052780479192734, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:19.510660Z", "loop": 14022, "env_steps": 8615731199, "loss": 0.015936894342303276, "avg_return": 0.8626920580863953, "regret": 0.0005676253349520266, "entropy": 0.08184731006622314, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:20.364383Z", "loop": 14023, "env_steps": 8616345599, "loss": 0.015092057175934315, "avg_return": 0.8635410666465759, "regret": 0.0005676253349520266, "entropy": 0.07690262049436569, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:21.220266Z", "loop": 14024, "env_steps": 8616959999, "loss": 0.015420086681842804, "avg_return": 0.8636082410812378, "regret": 0.0005676253349520266, "entropy": 0.07880594581365585, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:22.075725Z", "loop": 14025, "env_steps": 8617574399, "loss": 0.015489173121750355, "avg_return": 0.8623837232589722, "regret": 0.0005676253349520266, "entropy": 0.07911641150712967, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:22.930590Z", "loop": 14026, "env_steps": 8618188799, "loss": 0.015232442878186703, "avg_return": 0.863522469997406, "regret": 0.0005676253349520266, "entropy": 0.08151844888925552, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:23.784900Z", "loop": 14027, "env_steps": 8618803199, "loss": 0.014497150667011738, "avg_return": 0.863408625125885, "regret": 0.0005676253349520266, "entropy": 0.0765213668346405, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:24.639442Z", "loop": 14028, "env_steps": 8619417599, "loss": 0.01546839065849781, "avg_return": 0.8634684681892395, "regret": 0.0005676253349520266, "entropy": 0.07965079694986343, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:25.494478Z", "loop": 14029, "env_steps": 8620031999, "loss": 0.016460856422781944, "avg_return": 0.8622137904167175, "regret": 0.0005676253349520266, "entropy": 0.08184994012117386, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:26.392101Z", "loop": 14030, "env_steps": 8620646399, "loss": 0.01601279526948929, "avg_return": 0.8637830018997192, "regret": 0.0006701394449919462, "entropy": 0.08322691917419434, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:27.246456Z", "loop": 14031, "env_steps": 8621260799, "loss": 0.015159904956817627, "avg_return": 0.8629603385925293, "regret": 0.0006701394449919462, "entropy": 0.0801101103425026, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:28.100386Z", "loop": 14032, "env_steps": 8621875199, "loss": 0.016131959855556488, "avg_return": 0.8639107346534729, "regret": 0.0006701394449919462, "entropy": 0.08021870255470276, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:28.954309Z", "loop": 14033, "env_steps": 8622489599, "loss": 0.016796408221125603, "avg_return": 0.8628700971603394, "regret": 0.0006701394449919462, "entropy": 0.0829489678144455, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:29.808712Z", "loop": 14034, "env_steps": 8623103999, "loss": 0.01663721166551113, "avg_return": 0.86290043592453, "regret": 0.0006701394449919462, "entropy": 0.08402834832668304, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:30.662635Z", "loop": 14035, "env_steps": 8623718399, "loss": 0.01746094785630703, "avg_return": 0.8624163269996643, "regret": 0.0006701394449919462, "entropy": 0.08433316648006439, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:31.515638Z", "loop": 14036, "env_steps": 8624332799, "loss": 0.018830178305506706, "avg_return": 0.8618777394294739, "regret": 0.0006701394449919462, "entropy": 0.09138096123933792, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:32.371112Z", "loop": 14037, "env_steps": 8624947199, "loss": 0.01899525336921215, "avg_return": 0.8615930676460266, "regret": 0.0006701394449919462, "entropy": 0.09426380693912506, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:33.226406Z", "loop": 14038, "env_steps": 8625561599, "loss": 0.019641617313027382, "avg_return": 0.8615493178367615, "regret": 0.0006701394449919462, "entropy": 0.09692923724651337, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:34.081773Z", "loop": 14039, "env_steps": 8626175999, "loss": 0.01970752887427807, "avg_return": 0.8611442446708679, "regret": 0.0006701394449919462, "entropy": 0.09582551568746567, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:34.976082Z", "loop": 14040, "env_steps": 8626790399, "loss": 0.020763088017702103, "avg_return": 0.8609542846679688, "regret": 0.0025175237096846104, "entropy": 0.10186946392059326, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:35.828881Z", "loop": 14041, "env_steps": 8627404799, "loss": 0.02137422375380993, "avg_return": 0.8592820167541504, "regret": 0.0025175237096846104, "entropy": 0.1062823086977005, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:36.682822Z", "loop": 14042, "env_steps": 8628019199, "loss": 0.022369004786014557, "avg_return": 0.8583469986915588, "regret": 0.0025175237096846104, "entropy": 0.10903327912092209, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:37.537830Z", "loop": 14043, "env_steps": 8628633599, "loss": 0.02111390419304371, "avg_return": 0.8571447134017944, "regret": 0.0025175237096846104, "entropy": 0.10871116071939468, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:38.393483Z", "loop": 14044, "env_steps": 8629247999, "loss": 0.021832237020134926, "avg_return": 0.856464684009552, "regret": 0.0025175237096846104, "entropy": 0.10969217866659164, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:39.248771Z", "loop": 14045, "env_steps": 8629862399, "loss": 0.021945137530565262, "avg_return": 0.8593733906745911, "regret": 0.0025175237096846104, "entropy": 0.10573505610227585, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:40.103542Z", "loop": 14046, "env_steps": 8630476799, "loss": 0.019608858972787857, "avg_return": 0.8617209792137146, "regret": 0.0025175237096846104, "entropy": 0.09573881328105927, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:40.959519Z", "loop": 14047, "env_steps": 8631091199, "loss": 0.018795086070895195, "avg_return": 0.8625614643096924, "regret": 0.0025175237096846104, "entropy": 0.0918755978345871, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:41.814377Z", "loop": 14048, "env_steps": 8631705599, "loss": 0.017614496871829033, "avg_return": 0.8616357445716858, "regret": 0.0025175237096846104, "entropy": 0.08472177386283875, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:42.668859Z", "loop": 14049, "env_steps": 8632319999, "loss": 0.01608276180922985, "avg_return": 0.8617098331451416, "regret": 0.0025175237096846104, "entropy": 0.08041885495185852, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:43.563873Z", "loop": 14050, "env_steps": 8632934399, "loss": 0.01718214526772499, "avg_return": 0.862123966217041, "regret": 0.0006949075032025576, "entropy": 0.0862160176038742, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:44.417833Z", "loop": 14051, "env_steps": 8633548799, "loss": 0.01672528311610222, "avg_return": 0.8656467795372009, "regret": 0.0006949075032025576, "entropy": 0.0817575678229332, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:45.271872Z", "loop": 14052, "env_steps": 8634163199, "loss": 0.016903696581721306, "avg_return": 0.8613916039466858, "regret": 0.0006949075032025576, "entropy": 0.08579158782958984, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:46.127329Z", "loop": 14053, "env_steps": 8634777599, "loss": 0.016307072713971138, "avg_return": 0.8627371191978455, "regret": 0.0006949075032025576, "entropy": 0.08653134107589722, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:46.981617Z", "loop": 14054, "env_steps": 8635391999, "loss": 0.016272379085421562, "avg_return": 0.8631024360656738, "regret": 0.0006949075032025576, "entropy": 0.08393280953168869, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:47.836240Z", "loop": 14055, "env_steps": 8636006399, "loss": 0.017068861052393913, "avg_return": 0.863800585269928, "regret": 0.0006949075032025576, "entropy": 0.08772238343954086, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:48.689947Z", "loop": 14056, "env_steps": 8636620799, "loss": 0.016504961997270584, "avg_return": 0.8630395531654358, "regret": 0.0006949075032025576, "entropy": 0.08647404611110687, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:49.544624Z", "loop": 14057, "env_steps": 8637235199, "loss": 0.01655535213649273, "avg_return": 0.8631154298782349, "regret": 0.0006949075032025576, "entropy": 0.08687345683574677, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:50.399242Z", "loop": 14058, "env_steps": 8637849599, "loss": 0.01663554087281227, "avg_return": 0.8624405264854431, "regret": 0.0006949075032025576, "entropy": 0.0861964300274849, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:51.252871Z", "loop": 14059, "env_steps": 8638463999, "loss": 0.016789382323622704, "avg_return": 0.8625069260597229, "regret": 0.0006949075032025576, "entropy": 0.08943095803260803, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:52.146667Z", "loop": 14060, "env_steps": 8639078399, "loss": 0.017670877277851105, "avg_return": 0.8619250655174255, "regret": 0.0005195482517592609, "entropy": 0.09020534157752991, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:53.001743Z", "loop": 14061, "env_steps": 8639692799, "loss": 0.01698923483490944, "avg_return": 0.8625054359436035, "regret": 0.0005195482517592609, "entropy": 0.09105738997459412, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:53.856072Z", "loop": 14062, "env_steps": 8640307199, "loss": 0.015882717445492744, "avg_return": 0.8640883564949036, "regret": 0.0005195482517592609, "entropy": 0.08410076051950455, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:54.709691Z", "loop": 14063, "env_steps": 8640921599, "loss": 0.01640193909406662, "avg_return": 0.8624585270881653, "regret": 0.0005195482517592609, "entropy": 0.08750946074724197, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:55.563520Z", "loop": 14064, "env_steps": 8641535999, "loss": 0.017411809414625168, "avg_return": 0.8635750412940979, "regret": 0.0005195482517592609, "entropy": 0.0844755694270134, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:56.418076Z", "loop": 14065, "env_steps": 8642150399, "loss": 0.01637420989573002, "avg_return": 0.8619322180747986, "regret": 0.0005195482517592609, "entropy": 0.0848865881562233, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:57.271845Z", "loop": 14066, "env_steps": 8642764799, "loss": 0.017177144065499306, "avg_return": 0.8618879318237305, "regret": 0.0005195482517592609, "entropy": 0.08710390329360962, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:58.126149Z", "loop": 14067, "env_steps": 8643379199, "loss": 0.018226373940706253, "avg_return": 0.8638853430747986, "regret": 0.0005195482517592609, "entropy": 0.09116478264331818, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:58.979682Z", "loop": 14068, "env_steps": 8643993599, "loss": 0.017435414716601372, "avg_return": 0.8624657392501831, "regret": 0.0005195482517592609, "entropy": 0.09069492667913437, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:44:59.833657Z", "loop": 14069, "env_steps": 8644607999, "loss": 0.01810726523399353, "avg_return": 0.8627127408981323, "regret": 0.0005195482517592609, "entropy": 0.09169428050518036, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:00.728241Z", "loop": 14070, "env_steps": 8645222399, "loss": 0.017647646367549896, "avg_return": 0.8631157875061035, "regret": 0.0007379293674603105, "entropy": 0.09190136939287186, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:01.582887Z", "loop": 14071, "env_steps": 8645836799, "loss": 0.017724093049764633, "avg_return": 0.8627449870109558, "regret": 0.0007379293674603105, "entropy": 0.0867004245519638, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:02.437983Z", "loop": 14072, "env_steps": 8646451199, "loss": 0.019269512966275215, "avg_return": 0.8610342741012573, "regret": 0.0007379293674603105, "entropy": 0.09386692196130753, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:03.291878Z", "loop": 14073, "env_steps": 8647065599, "loss": 0.018594658002257347, "avg_return": 0.8617304563522339, "regret": 0.0007379293674603105, "entropy": 0.09477617591619492, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:04.146224Z", "loop": 14074, "env_steps": 8647679999, "loss": 0.019271425902843475, "avg_return": 0.864466667175293, "regret": 0.0007379293674603105, "entropy": 0.09773637354373932, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:05.001480Z", "loop": 14075, "env_steps": 8648294399, "loss": 0.019773149862885475, "avg_return": 0.861796498298645, "regret": 0.0007379293674603105, "entropy": 0.09722424298524857, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:05.855481Z", "loop": 14076, "env_steps": 8648908799, "loss": 0.021677616983652115, "avg_return": 0.8636855483055115, "regret": 0.0007379293674603105, "entropy": 0.10479795187711716, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:06.709140Z", "loop": 14077, "env_steps": 8649523199, "loss": 0.019359242171049118, "avg_return": 0.8603309392929077, "regret": 0.0007379293674603105, "entropy": 0.09731204062700272, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:07.562405Z", "loop": 14078, "env_steps": 8650137599, "loss": 0.02100188098847866, "avg_return": 0.8603799939155579, "regret": 0.0007379293674603105, "entropy": 0.10456135869026184, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:08.415775Z", "loop": 14079, "env_steps": 8650751999, "loss": 0.020610136911273003, "avg_return": 0.8600881099700928, "regret": 0.0007379293674603105, "entropy": 0.10297366231679916, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:09.310677Z", "loop": 14080, "env_steps": 8651366399, "loss": 0.02124287188053131, "avg_return": 0.8612836003303528, "regret": 0.0027550410013645887, "entropy": 0.10203766822814941, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:10.165214Z", "loop": 14081, "env_steps": 8651980799, "loss": 0.018509721383452415, "avg_return": 0.8602677583694458, "regret": 0.0027550410013645887, "entropy": 0.09708576649427414, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:11.018115Z", "loop": 14082, "env_steps": 8652595199, "loss": 0.020135194063186646, "avg_return": 0.8619817495346069, "regret": 0.0027550410013645887, "entropy": 0.09907486289739609, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:11.871380Z", "loop": 14083, "env_steps": 8653209599, "loss": 0.021703088656067848, "avg_return": 0.8602762818336487, "regret": 0.0027550410013645887, "entropy": 0.10623098164796829, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:12.725902Z", "loop": 14084, "env_steps": 8653823999, "loss": 0.022210223600268364, "avg_return": 0.8613970875740051, "regret": 0.0027550410013645887, "entropy": 0.10815255343914032, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:13.579446Z", "loop": 14085, "env_steps": 8654438399, "loss": 0.023039838299155235, "avg_return": 0.861111044883728, "regret": 0.0027550410013645887, "entropy": 0.11001736670732498, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:14.432809Z", "loop": 14086, "env_steps": 8655052799, "loss": 0.024990607053041458, "avg_return": 0.8604499697685242, "regret": 0.0027550410013645887, "entropy": 0.11697247624397278, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:15.286097Z", "loop": 14087, "env_steps": 8655667199, "loss": 0.02407759614288807, "avg_return": 0.8617852926254272, "regret": 0.0027550410013645887, "entropy": 0.11796880513429642, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:16.140392Z", "loop": 14088, "env_steps": 8656281599, "loss": 0.023986365646123886, "avg_return": 0.8602114915847778, "regret": 0.0027550410013645887, "entropy": 0.12001825869083405, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:16.995362Z", "loop": 14089, "env_steps": 8656895999, "loss": 0.023015586659312248, "avg_return": 0.8587862253189087, "regret": 0.0027550410013645887, "entropy": 0.11687538772821426, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:17.890770Z", "loop": 14090, "env_steps": 8657510399, "loss": 0.022527305409312248, "avg_return": 0.8592373132705688, "regret": 0.004311768338084221, "entropy": 0.11455639451742172, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:18.743410Z", "loop": 14091, "env_steps": 8658124799, "loss": 0.0216971505433321, "avg_return": 0.8600723743438721, "regret": 0.004311768338084221, "entropy": 0.11626231670379639, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:19.596888Z", "loop": 14092, "env_steps": 8658739199, "loss": 0.02238137274980545, "avg_return": 0.8582853674888611, "regret": 0.004311768338084221, "entropy": 0.11649926751852036, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:20.451769Z", "loop": 14093, "env_steps": 8659353599, "loss": 0.023400595411658287, "avg_return": 0.8569547533988953, "regret": 0.004311768338084221, "entropy": 0.12458210438489914, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:21.306417Z", "loop": 14094, "env_steps": 8659967999, "loss": 0.02458946220576763, "avg_return": 0.8570384979248047, "regret": 0.004311768338084221, "entropy": 0.12488853931427002, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:22.159530Z", "loop": 14095, "env_steps": 8660582399, "loss": 0.024967418983578682, "avg_return": 0.8575860857963562, "regret": 0.004311768338084221, "entropy": 0.12902048230171204, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:23.014117Z", "loop": 14096, "env_steps": 8661196799, "loss": 0.02402336336672306, "avg_return": 0.8603869676589966, "regret": 0.004311768338084221, "entropy": 0.11966423690319061, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:23.869150Z", "loop": 14097, "env_steps": 8661811199, "loss": 0.022772593423724174, "avg_return": 0.8620337843894958, "regret": 0.004311768338084221, "entropy": 0.1156812235713005, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:24.724376Z", "loop": 14098, "env_steps": 8662425599, "loss": 0.021061982959508896, "avg_return": 0.8611193895339966, "regret": 0.004311768338084221, "entropy": 0.11169087886810303, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:25.578869Z", "loop": 14099, "env_steps": 8663039999, "loss": 0.020802153274416924, "avg_return": 0.8627616763114929, "regret": 0.004311768338084221, "entropy": 0.10752993822097778, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:26.473454Z", "loop": 14100, "env_steps": 8663654399, "loss": 0.021612104028463364, "avg_return": 0.861199140548706, "regret": 0.0007591158500872552, "entropy": 0.10884646326303482, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:27.326670Z", "loop": 14101, "env_steps": 8664268799, "loss": 0.022338928654789925, "avg_return": 0.863532304763794, "regret": 0.0007591158500872552, "entropy": 0.10917121917009354, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:28.181527Z", "loop": 14102, "env_steps": 8664883199, "loss": 0.022510996088385582, "avg_return": 0.864005982875824, "regret": 0.0007591158500872552, "entropy": 0.11243972927331924, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:29.036662Z", "loop": 14103, "env_steps": 8665497599, "loss": 0.02420159988105297, "avg_return": 0.8625064492225647, "regret": 0.0007591158500872552, "entropy": 0.11689198017120361, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:29.890143Z", "loop": 14104, "env_steps": 8666111999, "loss": 0.02483532950282097, "avg_return": 0.862969696521759, "regret": 0.0007591158500872552, "entropy": 0.11732490360736847, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:30.743553Z", "loop": 14105, "env_steps": 8666726399, "loss": 0.023196237161755562, "avg_return": 0.8621538281440735, "regret": 0.0007591158500872552, "entropy": 0.10987719148397446, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:31.597562Z", "loop": 14106, "env_steps": 8667340799, "loss": 0.02224035933613777, "avg_return": 0.8624111413955688, "regret": 0.0007591158500872552, "entropy": 0.10569252818822861, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:32.452230Z", "loop": 14107, "env_steps": 8667955199, "loss": 0.020344635471701622, "avg_return": 0.8625671863555908, "regret": 0.0007591158500872552, "entropy": 0.0973234698176384, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:33.306452Z", "loop": 14108, "env_steps": 8668569599, "loss": 0.019222451373934746, "avg_return": 0.8621044158935547, "regret": 0.0007591158500872552, "entropy": 0.09565654397010803, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:34.159676Z", "loop": 14109, "env_steps": 8669183999, "loss": 0.016738751903176308, "avg_return": 0.8643507957458496, "regret": 0.0007591158500872552, "entropy": 0.082560233771801, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:35.053642Z", "loop": 14110, "env_steps": 8669798399, "loss": 0.01623605191707611, "avg_return": 0.8619564175605774, "regret": 0.00014698041195515543, "entropy": 0.07798150926828384, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:35.907958Z", "loop": 14111, "env_steps": 8670412799, "loss": 0.014565925113856792, "avg_return": 0.864113986492157, "regret": 0.00014698041195515543, "entropy": 0.07255423814058304, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:36.762190Z", "loop": 14112, "env_steps": 8671027199, "loss": 0.014131744392216206, "avg_return": 0.8638469576835632, "regret": 0.00014698041195515543, "entropy": 0.06670860946178436, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:37.617376Z", "loop": 14113, "env_steps": 8671641599, "loss": 0.013062539510428905, "avg_return": 0.8637129664421082, "regret": 0.00014698041195515543, "entropy": 0.06668280065059662, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:38.471628Z", "loop": 14114, "env_steps": 8672255999, "loss": 0.012805248610675335, "avg_return": 0.8629893064498901, "regret": 0.00014698041195515543, "entropy": 0.06649182736873627, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:39.326074Z", "loop": 14115, "env_steps": 8672870399, "loss": 0.012388649396598339, "avg_return": 0.862701416015625, "regret": 0.00014698041195515543, "entropy": 0.06260505318641663, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:40.179980Z", "loop": 14116, "env_steps": 8673484799, "loss": 0.01346299797296524, "avg_return": 0.8623555898666382, "regret": 0.00014698041195515543, "entropy": 0.06586642563343048, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:41.034753Z", "loop": 14117, "env_steps": 8674099199, "loss": 0.01401112973690033, "avg_return": 0.8637043237686157, "regret": 0.00014698041195515543, "entropy": 0.06644412875175476, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:41.888438Z", "loop": 14118, "env_steps": 8674713599, "loss": 0.015223500318825245, "avg_return": 0.8628601431846619, "regret": 0.00014698041195515543, "entropy": 0.07490412890911102, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:42.742171Z", "loop": 14119, "env_steps": 8675327999, "loss": 0.015087619423866272, "avg_return": 0.8606085181236267, "regret": 0.00014698041195515543, "entropy": 0.0760352835059166, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:43.635861Z", "loop": 14120, "env_steps": 8675942399, "loss": 0.01643606461584568, "avg_return": 0.8596358299255371, "regret": 0.0028699550312012434, "entropy": 0.07890733331441879, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:44.489670Z", "loop": 14121, "env_steps": 8676556799, "loss": 0.015699487179517746, "avg_return": 0.8608700037002563, "regret": 0.0028699550312012434, "entropy": 0.07983323931694031, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:45.343152Z", "loop": 14122, "env_steps": 8677171199, "loss": 0.01615273207426071, "avg_return": 0.861315131187439, "regret": 0.0028699550312012434, "entropy": 0.07700486481189728, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:46.197196Z", "loop": 14123, "env_steps": 8677785599, "loss": 0.014987761154770851, "avg_return": 0.8624503016471863, "regret": 0.0028699550312012434, "entropy": 0.07125489413738251, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:47.051121Z", "loop": 14124, "env_steps": 8678399999, "loss": 0.014821507036685944, "avg_return": 0.8613977432250977, "regret": 0.0028699550312012434, "entropy": 0.07131333649158478, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:47.906062Z", "loop": 14125, "env_steps": 8679014399, "loss": 0.013900448568165302, "avg_return": 0.8612896203994751, "regret": 0.0028699550312012434, "entropy": 0.06725256145000458, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:48.760328Z", "loop": 14126, "env_steps": 8679628799, "loss": 0.013892902992665768, "avg_return": 0.8620977997779846, "regret": 0.0028699550312012434, "entropy": 0.06947295367717743, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:49.613560Z", "loop": 14127, "env_steps": 8680243199, "loss": 0.012390024960041046, "avg_return": 0.8617568016052246, "regret": 0.0028699550312012434, "entropy": 0.06390995532274246, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:50.466973Z", "loop": 14128, "env_steps": 8680857599, "loss": 0.013791573233902454, "avg_return": 0.8635996580123901, "regret": 0.0028699550312012434, "entropy": 0.06557059288024902, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:51.321159Z", "loop": 14129, "env_steps": 8681471999, "loss": 0.013659759424626827, "avg_return": 0.8614245057106018, "regret": 0.0028699550312012434, "entropy": 0.06540842354297638, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:52.216788Z", "loop": 14130, "env_steps": 8682086399, "loss": 0.013625110499560833, "avg_return": 0.8614792823791504, "regret": 0.0012623099610209465, "entropy": 0.06820976734161377, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:53.070692Z", "loop": 14131, "env_steps": 8682700799, "loss": 0.01248782966285944, "avg_return": 0.8624902367591858, "regret": 0.0012623099610209465, "entropy": 0.0655813068151474, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:53.923723Z", "loop": 14132, "env_steps": 8683315199, "loss": 0.01231436338275671, "avg_return": 0.8623536229133606, "regret": 0.0012623099610209465, "entropy": 0.06260707229375839, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:54.777169Z", "loop": 14133, "env_steps": 8683929599, "loss": 0.01379916537553072, "avg_return": 0.8625431656837463, "regret": 0.0012623099610209465, "entropy": 0.06850168108940125, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:55.631148Z", "loop": 14134, "env_steps": 8684543999, "loss": 0.014194557443261147, "avg_return": 0.8628093600273132, "regret": 0.0012623099610209465, "entropy": 0.06798577308654785, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:56.485341Z", "loop": 14135, "env_steps": 8685158399, "loss": 0.01282858569175005, "avg_return": 0.8619248867034912, "regret": 0.0012623099610209465, "entropy": 0.0693376362323761, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:57.338123Z", "loop": 14136, "env_steps": 8685772799, "loss": 0.012817288748919964, "avg_return": 0.8625172972679138, "regret": 0.0012623099610209465, "entropy": 0.06592229008674622, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:58.191140Z", "loop": 14137, "env_steps": 8686387199, "loss": 0.013702613301575184, "avg_return": 0.8621857166290283, "regret": 0.0012623099610209465, "entropy": 0.0688600167632103, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:59.044488Z", "loop": 14138, "env_steps": 8687001599, "loss": 0.013544484972953796, "avg_return": 0.862464189529419, "regret": 0.0012623099610209465, "entropy": 0.06922286748886108, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:45:59.898743Z", "loop": 14139, "env_steps": 8687615999, "loss": 0.01409955509006977, "avg_return": 0.86313396692276, "regret": 0.0012623099610209465, "entropy": 0.07072936743497849, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:00.793916Z", "loop": 14140, "env_steps": 8688230399, "loss": 0.016082385554909706, "avg_return": 0.8634529709815979, "regret": 0.0012278227368369699, "entropy": 0.0769900232553482, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:01.647304Z", "loop": 14141, "env_steps": 8688844799, "loss": 0.01448998786509037, "avg_return": 0.8633148670196533, "regret": 0.0012278227368369699, "entropy": 0.0708354264497757, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:02.501780Z", "loop": 14142, "env_steps": 8689459199, "loss": 0.016081906855106354, "avg_return": 0.8624973893165588, "regret": 0.0012278227368369699, "entropy": 0.0721164271235466, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:03.356977Z", "loop": 14143, "env_steps": 8690073599, "loss": 0.01567009650170803, "avg_return": 0.8625741004943848, "regret": 0.0012278227368369699, "entropy": 0.07401986420154572, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:04.211148Z", "loop": 14144, "env_steps": 8690687999, "loss": 0.01438664086163044, "avg_return": 0.8627389669418335, "regret": 0.0012278227368369699, "entropy": 0.07329403609037399, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:05.063533Z", "loop": 14145, "env_steps": 8691302399, "loss": 0.014045188203454018, "avg_return": 0.8629608154296875, "regret": 0.0012278227368369699, "entropy": 0.06941723078489304, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:05.916132Z", "loop": 14146, "env_steps": 8691916799, "loss": 0.014794480986893177, "avg_return": 0.8619712591171265, "regret": 0.0012278227368369699, "entropy": 0.07093808799982071, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:06.770761Z", "loop": 14147, "env_steps": 8692531199, "loss": 0.0159359909594059, "avg_return": 0.8626115322113037, "regret": 0.0012278227368369699, "entropy": 0.07546478509902954, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:07.624871Z", "loop": 14148, "env_steps": 8693145599, "loss": 0.014443625696003437, "avg_return": 0.8635544776916504, "regret": 0.0012278227368369699, "entropy": 0.06883599609136581, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:08.478170Z", "loop": 14149, "env_steps": 8693759999, "loss": 0.013786573894321918, "avg_return": 0.8627991080284119, "regret": 0.0012278227368369699, "entropy": 0.06810908019542694, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:09.371772Z", "loop": 14150, "env_steps": 8694374399, "loss": 0.014705086126923561, "avg_return": 0.8639681339263916, "regret": 0.0003778024693019688, "entropy": 0.06890330463647842, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:10.225804Z", "loop": 14151, "env_steps": 8694988799, "loss": 0.015644630417227745, "avg_return": 0.8636398315429688, "regret": 0.0003778024693019688, "entropy": 0.07497517764568329, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:11.080229Z", "loop": 14152, "env_steps": 8695603199, "loss": 0.014559469185769558, "avg_return": 0.8617997169494629, "regret": 0.0003778024693019688, "entropy": 0.06966784596443176, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:11.933850Z", "loop": 14153, "env_steps": 8696217599, "loss": 0.014895486645400524, "avg_return": 0.8632588982582092, "regret": 0.0003778024693019688, "entropy": 0.07142357528209686, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:12.787978Z", "loop": 14154, "env_steps": 8696831999, "loss": 0.014517992734909058, "avg_return": 0.8636810779571533, "regret": 0.0003778024693019688, "entropy": 0.06892568618059158, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:13.641682Z", "loop": 14155, "env_steps": 8697446399, "loss": 0.014882947318255901, "avg_return": 0.863559901714325, "regret": 0.0003778024693019688, "entropy": 0.07323117554187775, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:14.495518Z", "loop": 14156, "env_steps": 8698060799, "loss": 0.013877162709832191, "avg_return": 0.8629984855651855, "regret": 0.0003778024693019688, "entropy": 0.06938397884368896, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:15.350163Z", "loop": 14157, "env_steps": 8698675199, "loss": 0.015550713054835796, "avg_return": 0.8620977997779846, "regret": 0.0003778024693019688, "entropy": 0.07227659970521927, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:16.204990Z", "loop": 14158, "env_steps": 8699289599, "loss": 0.016046686097979546, "avg_return": 0.8615601062774658, "regret": 0.0003778024693019688, "entropy": 0.07771561294794083, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:17.058888Z", "loop": 14159, "env_steps": 8699903999, "loss": 0.016260046511888504, "avg_return": 0.8630327582359314, "regret": 0.0003778024693019688, "entropy": 0.0810631662607193, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:17.953571Z", "loop": 14160, "env_steps": 8700518399, "loss": 0.016899680718779564, "avg_return": 0.8623989820480347, "regret": 0.0010529359569773078, "entropy": 0.08142609894275665, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:18.807680Z", "loop": 14161, "env_steps": 8701132799, "loss": 0.01787695102393627, "avg_return": 0.8626598119735718, "regret": 0.0010529359569773078, "entropy": 0.0831671953201294, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:19.663211Z", "loop": 14162, "env_steps": 8701747199, "loss": 0.01832391507923603, "avg_return": 0.8642619848251343, "regret": 0.0010529359569773078, "entropy": 0.08512856811285019, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:20.517163Z", "loop": 14163, "env_steps": 8702361599, "loss": 0.017047708854079247, "avg_return": 0.8630698919296265, "regret": 0.0010529359569773078, "entropy": 0.08046193420886993, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:21.371355Z", "loop": 14164, "env_steps": 8702975999, "loss": 0.016606470569968224, "avg_return": 0.8620721697807312, "regret": 0.0010529359569773078, "entropy": 0.08040254563093185, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:22.226264Z", "loop": 14165, "env_steps": 8703590399, "loss": 0.015540224500000477, "avg_return": 0.8635168671607971, "regret": 0.0010529359569773078, "entropy": 0.07507432997226715, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:23.082107Z", "loop": 14166, "env_steps": 8704204799, "loss": 0.013295202516019344, "avg_return": 0.8621706366539001, "regret": 0.0010529359569773078, "entropy": 0.07049654424190521, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:23.937007Z", "loop": 14167, "env_steps": 8704819199, "loss": 0.014724338427186012, "avg_return": 0.8643341064453125, "regret": 0.0010529359569773078, "entropy": 0.06856470555067062, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:24.790820Z", "loop": 14168, "env_steps": 8705433599, "loss": 0.013907680287957191, "avg_return": 0.8637168407440186, "regret": 0.0010529359569773078, "entropy": 0.07017616182565689, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:25.645661Z", "loop": 14169, "env_steps": 8706047999, "loss": 0.014170452952384949, "avg_return": 0.8624125123023987, "regret": 0.0010529359569773078, "entropy": 0.07188686728477478, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:26.541023Z", "loop": 14170, "env_steps": 8706662399, "loss": 0.01417523343116045, "avg_return": 0.8633238077163696, "regret": 0.00020991686324123293, "entropy": 0.06917206943035126, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:27.394882Z", "loop": 14171, "env_steps": 8707276799, "loss": 0.015327461063861847, "avg_return": 0.8633967041969299, "regret": 0.00020991686324123293, "entropy": 0.07097131758928299, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:28.249513Z", "loop": 14172, "env_steps": 8707891199, "loss": 0.013873246498405933, "avg_return": 0.8629375696182251, "regret": 0.00020991686324123293, "entropy": 0.07025614380836487, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:29.104229Z", "loop": 14173, "env_steps": 8708505599, "loss": 0.015016219578683376, "avg_return": 0.8637025356292725, "regret": 0.00020991686324123293, "entropy": 0.07036907225847244, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:29.958424Z", "loop": 14174, "env_steps": 8709119999, "loss": 0.014958870597183704, "avg_return": 0.8632674217224121, "regret": 0.00020991686324123293, "entropy": 0.07290475070476532, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:30.812739Z", "loop": 14175, "env_steps": 8709734399, "loss": 0.01488321553915739, "avg_return": 0.8640905022621155, "regret": 0.00020991686324123293, "entropy": 0.07014868408441544, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:31.667278Z", "loop": 14176, "env_steps": 8710348799, "loss": 0.014198395423591137, "avg_return": 0.8636630177497864, "regret": 0.00020991686324123293, "entropy": 0.07064808905124664, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:32.521954Z", "loop": 14177, "env_steps": 8710963199, "loss": 0.0158193688839674, "avg_return": 0.86346834897995, "regret": 0.00020991686324123293, "entropy": 0.07543668150901794, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:33.375391Z", "loop": 14178, "env_steps": 8711577599, "loss": 0.015051322057843208, "avg_return": 0.8634202480316162, "regret": 0.00020991686324123293, "entropy": 0.07344438880681992, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:34.229528Z", "loop": 14179, "env_steps": 8712191999, "loss": 0.01369677484035492, "avg_return": 0.8644405603408813, "regret": 0.00020991686324123293, "entropy": 0.06754786521196365, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:35.122857Z", "loop": 14180, "env_steps": 8712806399, "loss": 0.013633759692311287, "avg_return": 0.8622736930847168, "regret": 0.0001121643726946786, "entropy": 0.06545994430780411, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:35.978396Z", "loop": 14181, "env_steps": 8713420799, "loss": 0.013427242636680603, "avg_return": 0.8639996647834778, "regret": 0.0001121643726946786, "entropy": 0.06570541113615036, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:36.833521Z", "loop": 14182, "env_steps": 8714035199, "loss": 0.012645377777516842, "avg_return": 0.8630573749542236, "regret": 0.0001121643726946786, "entropy": 0.06479080021381378, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:37.688068Z", "loop": 14183, "env_steps": 8714649599, "loss": 0.013226255774497986, "avg_return": 0.8646990060806274, "regret": 0.0001121643726946786, "entropy": 0.06601494550704956, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:38.542491Z", "loop": 14184, "env_steps": 8715263999, "loss": 0.012820194475352764, "avg_return": 0.86460942029953, "regret": 0.0001121643726946786, "entropy": 0.06303896009922028, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:39.398037Z", "loop": 14185, "env_steps": 8715878399, "loss": 0.013539438135921955, "avg_return": 0.8636178970336914, "regret": 0.0001121643726946786, "entropy": 0.06614381074905396, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:40.251816Z", "loop": 14186, "env_steps": 8716492799, "loss": 0.01314515806734562, "avg_return": 0.863237738609314, "regret": 0.0001121643726946786, "entropy": 0.06436773389577866, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:41.105735Z", "loop": 14187, "env_steps": 8717107199, "loss": 0.013635043986141682, "avg_return": 0.8629963397979736, "regret": 0.0001121643726946786, "entropy": 0.06810839474201202, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:41.960593Z", "loop": 14188, "env_steps": 8717721599, "loss": 0.013195844367146492, "avg_return": 0.8639016151428223, "regret": 0.0001121643726946786, "entropy": 0.0688866674900055, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:42.816206Z", "loop": 14189, "env_steps": 8718335999, "loss": 0.014329664409160614, "avg_return": 0.8638027906417847, "regret": 0.0001121643726946786, "entropy": 0.07101283222436905, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:43.710113Z", "loop": 14190, "env_steps": 8718950399, "loss": 0.01487599778920412, "avg_return": 0.8632340431213379, "regret": 9.735474304761738e-05, "entropy": 0.07290875166654587, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:44.564154Z", "loop": 14191, "env_steps": 8719564799, "loss": 0.01299537718296051, "avg_return": 0.8623743653297424, "regret": 9.735474304761738e-05, "entropy": 0.06568615138530731, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:45.419183Z", "loop": 14192, "env_steps": 8720179199, "loss": 0.01225616317242384, "avg_return": 0.8637803196907043, "regret": 9.735474304761738e-05, "entropy": 0.06646797806024551, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:46.274650Z", "loop": 14193, "env_steps": 8720793599, "loss": 0.013130280189216137, "avg_return": 0.8644742965698242, "regret": 9.735474304761738e-05, "entropy": 0.06640613824129105, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:47.129453Z", "loop": 14194, "env_steps": 8721407999, "loss": 0.012963158078491688, "avg_return": 0.8635056018829346, "regret": 9.735474304761738e-05, "entropy": 0.0699920505285263, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:47.983399Z", "loop": 14195, "env_steps": 8722022399, "loss": 0.0139453811571002, "avg_return": 0.8636048436164856, "regret": 9.735474304761738e-05, "entropy": 0.07414312660694122, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:48.837020Z", "loop": 14196, "env_steps": 8722636799, "loss": 0.015286947600543499, "avg_return": 0.863768458366394, "regret": 9.735474304761738e-05, "entropy": 0.07565888017416, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:49.692284Z", "loop": 14197, "env_steps": 8723251199, "loss": 0.0166095569729805, "avg_return": 0.8631394505500793, "regret": 9.735474304761738e-05, "entropy": 0.081414133310318, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:50.546304Z", "loop": 14198, "env_steps": 8723865599, "loss": 0.018381392583251, "avg_return": 0.8636220693588257, "regret": 9.735474304761738e-05, "entropy": 0.0899103656411171, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:51.400196Z", "loop": 14199, "env_steps": 8724479999, "loss": 0.019203901290893555, "avg_return": 0.8626007437705994, "regret": 9.735474304761738e-05, "entropy": 0.08959104865789413, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:52.295044Z", "loop": 14200, "env_steps": 8725094399, "loss": 0.019029339775443077, "avg_return": 0.8623976707458496, "regret": 0.0007335434202104807, "entropy": 0.09118454903364182, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:53.150185Z", "loop": 14201, "env_steps": 8725708799, "loss": 0.019315816462039948, "avg_return": 0.8612930774688721, "regret": 0.0007335434202104807, "entropy": 0.09147750586271286, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:54.005709Z", "loop": 14202, "env_steps": 8726323199, "loss": 0.019279297441244125, "avg_return": 0.8626930713653564, "regret": 0.0007335434202104807, "entropy": 0.09180658310651779, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:54.860786Z", "loop": 14203, "env_steps": 8726937599, "loss": 0.01843240298330784, "avg_return": 0.861831784248352, "regret": 0.0007335434202104807, "entropy": 0.09089329093694687, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:55.714850Z", "loop": 14204, "env_steps": 8727551999, "loss": 0.01786903105676174, "avg_return": 0.8637876510620117, "regret": 0.0007335434202104807, "entropy": 0.08796564489603043, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:56.570302Z", "loop": 14205, "env_steps": 8728166399, "loss": 0.01942875050008297, "avg_return": 0.8630505800247192, "regret": 0.0007335434202104807, "entropy": 0.09347575902938843, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:57.424766Z", "loop": 14206, "env_steps": 8728780799, "loss": 0.01915300078690052, "avg_return": 0.8633283972740173, "regret": 0.0007335434202104807, "entropy": 0.09429814666509628, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:58.280188Z", "loop": 14207, "env_steps": 8729395199, "loss": 0.018571767956018448, "avg_return": 0.8616843819618225, "regret": 0.0007335434202104807, "entropy": 0.09074244648218155, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:59.135439Z", "loop": 14208, "env_steps": 8730009599, "loss": 0.01983681321144104, "avg_return": 0.864409327507019, "regret": 0.0007335434202104807, "entropy": 0.09625813364982605, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:46:59.990322Z", "loop": 14209, "env_steps": 8730623999, "loss": 0.019924771040678024, "avg_return": 0.8628538250923157, "regret": 0.0007335434202104807, "entropy": 0.0969485193490982, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:00.886475Z", "loop": 14210, "env_steps": 8731238399, "loss": 0.020613742992281914, "avg_return": 0.8625325560569763, "regret": 0.0006094452692195773, "entropy": 0.09622044116258621, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:01.742211Z", "loop": 14211, "env_steps": 8731852799, "loss": 0.02068217657506466, "avg_return": 0.8625449538230896, "regret": 0.0006094452692195773, "entropy": 0.10100442916154861, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:02.597887Z", "loop": 14212, "env_steps": 8732467199, "loss": 0.021429281681776047, "avg_return": 0.8629167079925537, "regret": 0.0006094452692195773, "entropy": 0.09893977642059326, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:03.451052Z", "loop": 14213, "env_steps": 8733081599, "loss": 0.021754270419478416, "avg_return": 0.8625774383544922, "regret": 0.0006094452692195773, "entropy": 0.10407164692878723, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:04.304483Z", "loop": 14214, "env_steps": 8733695999, "loss": 0.022220253944396973, "avg_return": 0.8624910712242126, "regret": 0.0006094452692195773, "entropy": 0.10810635983943939, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:05.157810Z", "loop": 14215, "env_steps": 8734310399, "loss": 0.022263316437602043, "avg_return": 0.8626402020454407, "regret": 0.0006094452692195773, "entropy": 0.10681141912937164, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:06.012538Z", "loop": 14216, "env_steps": 8734924799, "loss": 0.02249894104897976, "avg_return": 0.8630383610725403, "regret": 0.0006094452692195773, "entropy": 0.10661397874355316, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:06.865805Z", "loop": 14217, "env_steps": 8735539199, "loss": 0.02176506258547306, "avg_return": 0.8626644015312195, "regret": 0.0006094452692195773, "entropy": 0.10618507862091064, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:07.719379Z", "loop": 14218, "env_steps": 8736153599, "loss": 0.022589143365621567, "avg_return": 0.862857460975647, "regret": 0.0006094452692195773, "entropy": 0.10679440945386887, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:08.572567Z", "loop": 14219, "env_steps": 8736767999, "loss": 0.022482113912701607, "avg_return": 0.8646140694618225, "regret": 0.0006094452692195773, "entropy": 0.10498608648777008, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:09.466343Z", "loop": 14220, "env_steps": 8737382399, "loss": 0.02294927090406418, "avg_return": 0.862170934677124, "regret": 0.000525621057022363, "entropy": 0.10659241676330566, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:10.320379Z", "loop": 14221, "env_steps": 8737996799, "loss": 0.022088047116994858, "avg_return": 0.8632153272628784, "regret": 0.000525621057022363, "entropy": 0.10758243501186371, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:11.173826Z", "loop": 14222, "env_steps": 8738611199, "loss": 0.02120860107243061, "avg_return": 0.8623741865158081, "regret": 0.000525621057022363, "entropy": 0.10139571130275726, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:12.028092Z", "loop": 14223, "env_steps": 8739225599, "loss": 0.01992781274020672, "avg_return": 0.8622477650642395, "regret": 0.000525621057022363, "entropy": 0.09573455154895782, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:12.882829Z", "loop": 14224, "env_steps": 8739839999, "loss": 0.01814529113471508, "avg_return": 0.8637400269508362, "regret": 0.000525621057022363, "entropy": 0.08793728053569794, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:13.736024Z", "loop": 14225, "env_steps": 8740454399, "loss": 0.016476353630423546, "avg_return": 0.8631100654602051, "regret": 0.000525621057022363, "entropy": 0.08257840573787689, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:14.591689Z", "loop": 14226, "env_steps": 8741068799, "loss": 0.01682671718299389, "avg_return": 0.8636586666107178, "regret": 0.000525621057022363, "entropy": 0.08314196765422821, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:15.444756Z", "loop": 14227, "env_steps": 8741683199, "loss": 0.01724879816174507, "avg_return": 0.8617474436759949, "regret": 0.000525621057022363, "entropy": 0.0802404135465622, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:16.298123Z", "loop": 14228, "env_steps": 8742297599, "loss": 0.017508072778582573, "avg_return": 0.8634149432182312, "regret": 0.000525621057022363, "entropy": 0.08323373645544052, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:17.152331Z", "loop": 14229, "env_steps": 8742911999, "loss": 0.015644274652004242, "avg_return": 0.862659752368927, "regret": 0.000525621057022363, "entropy": 0.07882905751466751, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:18.046831Z", "loop": 14230, "env_steps": 8743526399, "loss": 0.01662573777139187, "avg_return": 0.8636033535003662, "regret": 0.0003312053740955889, "entropy": 0.07789922505617142, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:18.901344Z", "loop": 14231, "env_steps": 8744140799, "loss": 0.015768425539135933, "avg_return": 0.8630192279815674, "regret": 0.0003312053740955889, "entropy": 0.07706750929355621, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:19.755505Z", "loop": 14232, "env_steps": 8744755199, "loss": 0.014578430913388729, "avg_return": 0.8628517985343933, "regret": 0.0003312053740955889, "entropy": 0.07208887487649918, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:20.610876Z", "loop": 14233, "env_steps": 8745369599, "loss": 0.01557906437665224, "avg_return": 0.8628789186477661, "regret": 0.0003312053740955889, "entropy": 0.07708363980054855, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:21.464383Z", "loop": 14234, "env_steps": 8745983999, "loss": 0.014909905381500721, "avg_return": 0.8648961782455444, "regret": 0.0003312053740955889, "entropy": 0.07465695589780807, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:22.317831Z", "loop": 14235, "env_steps": 8746598399, "loss": 0.01436806470155716, "avg_return": 0.8643963932991028, "regret": 0.0003312053740955889, "entropy": 0.0744161456823349, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:23.171880Z", "loop": 14236, "env_steps": 8747212799, "loss": 0.0146451061591506, "avg_return": 0.8634952902793884, "regret": 0.0003312053740955889, "entropy": 0.07338455319404602, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:24.025815Z", "loop": 14237, "env_steps": 8747827199, "loss": 0.014653049409389496, "avg_return": 0.863074779510498, "regret": 0.0003312053740955889, "entropy": 0.07374721020460129, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:24.880332Z", "loop": 14238, "env_steps": 8748441599, "loss": 0.01535035204142332, "avg_return": 0.8629604578018188, "regret": 0.0003312053740955889, "entropy": 0.07614519447088242, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:25.733685Z", "loop": 14239, "env_steps": 8749055999, "loss": 0.015053371898829937, "avg_return": 0.8623974919319153, "regret": 0.0003312053740955889, "entropy": 0.07455013692378998, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:26.628605Z", "loop": 14240, "env_steps": 8749670399, "loss": 0.015779536217451096, "avg_return": 0.8634112477302551, "regret": 0.0005632067332044244, "entropy": 0.07733447849750519, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:27.482979Z", "loop": 14241, "env_steps": 8750284799, "loss": 0.014155633747577667, "avg_return": 0.8632385730743408, "regret": 0.0005632067332044244, "entropy": 0.07562336325645447, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:28.338633Z", "loop": 14242, "env_steps": 8750899199, "loss": 0.014278034679591656, "avg_return": 0.8634392619132996, "regret": 0.0005632067332044244, "entropy": 0.07062424719333649, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:29.192548Z", "loop": 14243, "env_steps": 8751513599, "loss": 0.014908301644027233, "avg_return": 0.8624866008758545, "regret": 0.0005632067332044244, "entropy": 0.0718502402305603, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:30.047571Z", "loop": 14244, "env_steps": 8752127999, "loss": 0.015029906295239925, "avg_return": 0.8624477386474609, "regret": 0.0005632067332044244, "entropy": 0.07402931898832321, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:30.900777Z", "loop": 14245, "env_steps": 8752742399, "loss": 0.014203570783138275, "avg_return": 0.8638766407966614, "regret": 0.0005632067332044244, "entropy": 0.07226530462503433, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:31.753849Z", "loop": 14246, "env_steps": 8753356799, "loss": 0.01455820631235838, "avg_return": 0.862794816493988, "regret": 0.0005632067332044244, "entropy": 0.07340579479932785, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:32.608396Z", "loop": 14247, "env_steps": 8753971199, "loss": 0.014784233644604683, "avg_return": 0.8620355725288391, "regret": 0.0005632067332044244, "entropy": 0.07816587388515472, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:33.462130Z", "loop": 14248, "env_steps": 8754585599, "loss": 0.015697741881012917, "avg_return": 0.8640486598014832, "regret": 0.0005632067332044244, "entropy": 0.07623638957738876, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:34.315566Z", "loop": 14249, "env_steps": 8755199999, "loss": 0.015126814134418964, "avg_return": 0.8623445630073547, "regret": 0.0005632067332044244, "entropy": 0.07486814260482788, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:35.209168Z", "loop": 14250, "env_steps": 8755814399, "loss": 0.01632840745151043, "avg_return": 0.8603951334953308, "regret": 0.0009186991374008358, "entropy": 0.07988926023244858, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:36.063539Z", "loop": 14251, "env_steps": 8756428799, "loss": 0.01789828948676586, "avg_return": 0.8620243668556213, "regret": 0.0009186991374008358, "entropy": 0.08346511423587799, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:36.916861Z", "loop": 14252, "env_steps": 8757043199, "loss": 0.017257867380976677, "avg_return": 0.861962080001831, "regret": 0.0009186991374008358, "entropy": 0.08351647853851318, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:37.770676Z", "loop": 14253, "env_steps": 8757657599, "loss": 0.018542801961302757, "avg_return": 0.8614546060562134, "regret": 0.0009186991374008358, "entropy": 0.08960570394992828, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:38.623627Z", "loop": 14254, "env_steps": 8758271999, "loss": 0.019413817673921585, "avg_return": 0.8603955507278442, "regret": 0.0009186991374008358, "entropy": 0.09163346141576767, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:39.477657Z", "loop": 14255, "env_steps": 8758886399, "loss": 0.01948562078177929, "avg_return": 0.86002117395401, "regret": 0.0009186991374008358, "entropy": 0.09316559880971909, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:40.331624Z", "loop": 14256, "env_steps": 8759500799, "loss": 0.01881863735616207, "avg_return": 0.860284149646759, "regret": 0.0009186991374008358, "entropy": 0.09098687022924423, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:41.185324Z", "loop": 14257, "env_steps": 8760115199, "loss": 0.01891450397670269, "avg_return": 0.8597193360328674, "regret": 0.0009186991374008358, "entropy": 0.09240049868822098, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:42.038825Z", "loop": 14258, "env_steps": 8760729599, "loss": 0.015877388417720795, "avg_return": 0.8615455031394958, "regret": 0.0009186991374008358, "entropy": 0.07842975854873657, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:42.893608Z", "loop": 14259, "env_steps": 8761343999, "loss": 0.015091115608811378, "avg_return": 0.8618009686470032, "regret": 0.0009186991374008358, "entropy": 0.0726977065205574, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:43.787911Z", "loop": 14260, "env_steps": 8761958399, "loss": 0.013105523772537708, "avg_return": 0.8619053363800049, "regret": 0.0010743944440037012, "entropy": 0.06731980293989182, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:44.641327Z", "loop": 14261, "env_steps": 8762572799, "loss": 0.012697160243988037, "avg_return": 0.8629631996154785, "regret": 0.0010743944440037012, "entropy": 0.06910037994384766, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:45.496228Z", "loop": 14262, "env_steps": 8763187199, "loss": 0.014213168993592262, "avg_return": 0.8610613942146301, "regret": 0.0010743944440037012, "entropy": 0.07005033642053604, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:46.349598Z", "loop": 14263, "env_steps": 8763801599, "loss": 0.013797186315059662, "avg_return": 0.864378809928894, "regret": 0.0010743944440037012, "entropy": 0.07080771774053574, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:47.203040Z", "loop": 14264, "env_steps": 8764415999, "loss": 0.013175551779568195, "avg_return": 0.8625990152359009, "regret": 0.0010743944440037012, "entropy": 0.06866864114999771, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:48.057565Z", "loop": 14265, "env_steps": 8765030399, "loss": 0.01386985182762146, "avg_return": 0.8631386756896973, "regret": 0.0010743944440037012, "entropy": 0.06908802688121796, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:48.912280Z", "loop": 14266, "env_steps": 8765644799, "loss": 0.014627660624682903, "avg_return": 0.8643878102302551, "regret": 0.0010743944440037012, "entropy": 0.07128427922725677, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:49.768305Z", "loop": 14267, "env_steps": 8766259199, "loss": 0.014068575575947762, "avg_return": 0.8642747402191162, "regret": 0.0010743944440037012, "entropy": 0.06954804062843323, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:50.621883Z", "loop": 14268, "env_steps": 8766873599, "loss": 0.01437166053801775, "avg_return": 0.8637946844100952, "regret": 0.0010743944440037012, "entropy": 0.07011082023382187, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:51.475684Z", "loop": 14269, "env_steps": 8767487999, "loss": 0.013432527892291546, "avg_return": 0.8634674549102783, "regret": 0.0010743944440037012, "entropy": 0.06626079231500626, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:52.368863Z", "loop": 14270, "env_steps": 8768102399, "loss": 0.013277179561555386, "avg_return": 0.86362624168396, "regret": 0.0003488893562462181, "entropy": 0.06302683055400848, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:53.222726Z", "loop": 14271, "env_steps": 8768716799, "loss": 0.01253095455467701, "avg_return": 0.863502025604248, "regret": 0.0003488893562462181, "entropy": 0.06379913538694382, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:54.076913Z", "loop": 14272, "env_steps": 8769331199, "loss": 0.011837251484394073, "avg_return": 0.8628771901130676, "regret": 0.0003488893562462181, "entropy": 0.060998618602752686, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:54.930772Z", "loop": 14273, "env_steps": 8769945599, "loss": 0.012686518020927906, "avg_return": 0.8640491962432861, "regret": 0.0003488893562462181, "entropy": 0.05946947634220123, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:55.785267Z", "loop": 14274, "env_steps": 8770559999, "loss": 0.014790317974984646, "avg_return": 0.8626469373703003, "regret": 0.0003488893562462181, "entropy": 0.07110821455717087, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:56.641157Z", "loop": 14275, "env_steps": 8771174399, "loss": 0.014700685627758503, "avg_return": 0.8640440106391907, "regret": 0.0003488893562462181, "entropy": 0.06882116198539734, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:57.496132Z", "loop": 14276, "env_steps": 8771788799, "loss": 0.015213826671242714, "avg_return": 0.8620813488960266, "regret": 0.0003488893562462181, "entropy": 0.07263694703578949, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:58.351310Z", "loop": 14277, "env_steps": 8772403199, "loss": 0.01633109152317047, "avg_return": 0.864022970199585, "regret": 0.0003488893562462181, "entropy": 0.07952455431222916, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:47:59.206497Z", "loop": 14278, "env_steps": 8773017599, "loss": 0.01760002039372921, "avg_return": 0.861872673034668, "regret": 0.0003488893562462181, "entropy": 0.08326272666454315, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:00.062418Z", "loop": 14279, "env_steps": 8773631999, "loss": 0.018452955409884453, "avg_return": 0.8612516522407532, "regret": 0.0003488893562462181, "entropy": 0.08922827988862991, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:00.956111Z", "loop": 14280, "env_steps": 8774246399, "loss": 0.01835092529654503, "avg_return": 0.8621988892555237, "regret": 0.0021118181757628918, "entropy": 0.08636294305324554, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:01.810251Z", "loop": 14281, "env_steps": 8774860799, "loss": 0.016491172835230827, "avg_return": 0.8619207739830017, "regret": 0.0021118181757628918, "entropy": 0.0836113691329956, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:02.664716Z", "loop": 14282, "env_steps": 8775475199, "loss": 0.016792336478829384, "avg_return": 0.861091136932373, "regret": 0.0021118181757628918, "entropy": 0.08887170255184174, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:03.519603Z", "loop": 14283, "env_steps": 8776089599, "loss": 0.01689048856496811, "avg_return": 0.8604485392570496, "regret": 0.0021118181757628918, "entropy": 0.08436335623264313, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:04.374175Z", "loop": 14284, "env_steps": 8776703999, "loss": 0.016309937462210655, "avg_return": 0.8600258827209473, "regret": 0.0021118181757628918, "entropy": 0.08458635956048965, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:05.228472Z", "loop": 14285, "env_steps": 8777318399, "loss": 0.01623794436454773, "avg_return": 0.8609331250190735, "regret": 0.0021118181757628918, "entropy": 0.08268099278211594, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:06.081963Z", "loop": 14286, "env_steps": 8777932799, "loss": 0.015323667787015438, "avg_return": 0.8612980246543884, "regret": 0.0021118181757628918, "entropy": 0.07907150685787201, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:06.935675Z", "loop": 14287, "env_steps": 8778547199, "loss": 0.017072631046175957, "avg_return": 0.8590905070304871, "regret": 0.0021118181757628918, "entropy": 0.08327214419841766, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:07.789720Z", "loop": 14288, "env_steps": 8779161599, "loss": 0.015622423961758614, "avg_return": 0.8606316447257996, "regret": 0.0021118181757628918, "entropy": 0.08273687958717346, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:08.643673Z", "loop": 14289, "env_steps": 8779775999, "loss": 0.016580160707235336, "avg_return": 0.8601025342941284, "regret": 0.0021118181757628918, "entropy": 0.08214683085680008, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:09.539329Z", "loop": 14290, "env_steps": 8780390399, "loss": 0.01342195924371481, "avg_return": 0.8603771924972534, "regret": 0.0030142036266624928, "entropy": 0.07205068320035934, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:10.393276Z", "loop": 14291, "env_steps": 8781004799, "loss": 0.014659411273896694, "avg_return": 0.860579252243042, "regret": 0.0030142036266624928, "entropy": 0.0752803236246109, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:11.248398Z", "loop": 14292, "env_steps": 8781619199, "loss": 0.01668667234480381, "avg_return": 0.8599215149879456, "regret": 0.0030142036266624928, "entropy": 0.07927653938531876, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:12.104106Z", "loop": 14293, "env_steps": 8782233599, "loss": 0.017141735181212425, "avg_return": 0.8605045676231384, "regret": 0.0030142036266624928, "entropy": 0.0798787847161293, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:12.958999Z", "loop": 14294, "env_steps": 8782847999, "loss": 0.017598219215869904, "avg_return": 0.8618735671043396, "regret": 0.0030142036266624928, "entropy": 0.08417568355798721, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:13.814715Z", "loop": 14295, "env_steps": 8783462399, "loss": 0.017396798357367516, "avg_return": 0.862527072429657, "regret": 0.0030142036266624928, "entropy": 0.08559177070856094, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:14.669179Z", "loop": 14296, "env_steps": 8784076799, "loss": 0.018703605979681015, "avg_return": 0.8624387979507446, "regret": 0.0030142036266624928, "entropy": 0.087494857609272, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:15.523390Z", "loop": 14297, "env_steps": 8784691199, "loss": 0.017979318276047707, "avg_return": 0.8616396188735962, "regret": 0.0030142036266624928, "entropy": 0.07834572345018387, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:16.379407Z", "loop": 14298, "env_steps": 8785305599, "loss": 0.014818467199802399, "avg_return": 0.8615751266479492, "regret": 0.0030142036266624928, "entropy": 0.07379163056612015, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:17.232875Z", "loop": 14299, "env_steps": 8785919999, "loss": 0.013829762116074562, "avg_return": 0.8618189692497253, "regret": 0.0030142036266624928, "entropy": 0.06846388429403305, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:18.126672Z", "loop": 14300, "env_steps": 8786534399, "loss": 0.013186238706111908, "avg_return": 0.8628813028335571, "regret": 0.0007119267829693854, "entropy": 0.06629782915115356, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:18.980302Z", "loop": 14301, "env_steps": 8787148799, "loss": 0.013283195905387402, "avg_return": 0.8631240129470825, "regret": 0.0007119267829693854, "entropy": 0.06558912992477417, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:19.835483Z", "loop": 14302, "env_steps": 8787763199, "loss": 0.012121519073843956, "avg_return": 0.8640402555465698, "regret": 0.0007119267829693854, "entropy": 0.062261730432510376, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:20.689826Z", "loop": 14303, "env_steps": 8788377599, "loss": 0.01452191174030304, "avg_return": 0.8635508418083191, "regret": 0.0007119267829693854, "entropy": 0.0684160441160202, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:21.543408Z", "loop": 14304, "env_steps": 8788991999, "loss": 0.014651677571237087, "avg_return": 0.8633481860160828, "regret": 0.0007119267829693854, "entropy": 0.06862201541662216, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:22.397744Z", "loop": 14305, "env_steps": 8789606399, "loss": 0.014952163212001324, "avg_return": 0.8644044995307922, "regret": 0.0007119267829693854, "entropy": 0.07202105224132538, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:23.253146Z", "loop": 14306, "env_steps": 8790220799, "loss": 0.01402929425239563, "avg_return": 0.8624162077903748, "regret": 0.0007119267829693854, "entropy": 0.0701480433344841, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:24.108226Z", "loop": 14307, "env_steps": 8790835199, "loss": 0.013583587482571602, "avg_return": 0.8636234998703003, "regret": 0.0007119267829693854, "entropy": 0.06995579600334167, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:24.963159Z", "loop": 14308, "env_steps": 8791449599, "loss": 0.014323288574814796, "avg_return": 0.8629679679870605, "regret": 0.0007119267829693854, "entropy": 0.07180940359830856, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:25.818032Z", "loop": 14309, "env_steps": 8792063999, "loss": 0.013667046092450619, "avg_return": 0.8623587489128113, "regret": 0.0007119267829693854, "entropy": 0.07044678926467896, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:26.715789Z", "loop": 14310, "env_steps": 8792678399, "loss": 0.01337730884552002, "avg_return": 0.8626148700714111, "regret": 0.0004055271565448493, "entropy": 0.06887689977884293, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:27.570252Z", "loop": 14311, "env_steps": 8793292799, "loss": 0.013465456664562225, "avg_return": 0.8629361987113953, "regret": 0.0004055271565448493, "entropy": 0.06966910511255264, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:28.425000Z", "loop": 14312, "env_steps": 8793907199, "loss": 0.01220750156790018, "avg_return": 0.8644316792488098, "regret": 0.0004055271565448493, "entropy": 0.06469980627298355, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:29.278308Z", "loop": 14313, "env_steps": 8794521599, "loss": 0.013637236319482327, "avg_return": 0.8633502125740051, "regret": 0.0004055271565448493, "entropy": 0.06842191517353058, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:30.132392Z", "loop": 14314, "env_steps": 8795135999, "loss": 0.014103814028203487, "avg_return": 0.8634851574897766, "regret": 0.0004055271565448493, "entropy": 0.0698004812002182, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:30.987462Z", "loop": 14315, "env_steps": 8795750399, "loss": 0.014510481618344784, "avg_return": 0.8625779151916504, "regret": 0.0004055271565448493, "entropy": 0.07450184226036072, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:31.842408Z", "loop": 14316, "env_steps": 8796364799, "loss": 0.015163046307861805, "avg_return": 0.8621184229850769, "regret": 0.0004055271565448493, "entropy": 0.07658542692661285, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:32.696595Z", "loop": 14317, "env_steps": 8796979199, "loss": 0.01494497712701559, "avg_return": 0.8635160326957703, "regret": 0.0004055271565448493, "entropy": 0.07416354864835739, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:33.551376Z", "loop": 14318, "env_steps": 8797593599, "loss": 0.015773078426718712, "avg_return": 0.8624887466430664, "regret": 0.0004055271565448493, "entropy": 0.07690748572349548, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:34.405429Z", "loop": 14319, "env_steps": 8798207999, "loss": 0.016180185601115227, "avg_return": 0.8619580268859863, "regret": 0.0004055271565448493, "entropy": 0.07949883490800858, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:35.298270Z", "loop": 14320, "env_steps": 8798822399, "loss": 0.015540841035544872, "avg_return": 0.8637706637382507, "regret": 0.0006856295512989163, "entropy": 0.07588520646095276, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:36.151660Z", "loop": 14321, "env_steps": 8799436799, "loss": 0.0161071065813303, "avg_return": 0.8638354539871216, "regret": 0.0006856295512989163, "entropy": 0.0779176652431488, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:37.005816Z", "loop": 14322, "env_steps": 8800051199, "loss": 0.016562623903155327, "avg_return": 0.861781656742096, "regret": 0.0006856295512989163, "entropy": 0.08021187037229538, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:37.859011Z", "loop": 14323, "env_steps": 8800665599, "loss": 0.014036595821380615, "avg_return": 0.8629312515258789, "regret": 0.0006856295512989163, "entropy": 0.07410068809986115, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:38.714093Z", "loop": 14324, "env_steps": 8801279999, "loss": 0.01567140594124794, "avg_return": 0.8630936741828918, "regret": 0.0006856295512989163, "entropy": 0.07540257275104523, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:39.568471Z", "loop": 14325, "env_steps": 8801894399, "loss": 0.01475588884204626, "avg_return": 0.8643450140953064, "regret": 0.0006856295512989163, "entropy": 0.07087322324514389, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:40.422937Z", "loop": 14326, "env_steps": 8802508799, "loss": 0.013785513117909431, "avg_return": 0.8627065420150757, "regret": 0.0006856295512989163, "entropy": 0.07112699002027512, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:41.276727Z", "loop": 14327, "env_steps": 8803123199, "loss": 0.013748764991760254, "avg_return": 0.863111674785614, "regret": 0.0006856295512989163, "entropy": 0.06756819784641266, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:42.128906Z", "loop": 14328, "env_steps": 8803737599, "loss": 0.013718130066990852, "avg_return": 0.8626649975776672, "regret": 0.0006856295512989163, "entropy": 0.0672929584980011, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:42.983511Z", "loop": 14329, "env_steps": 8804351999, "loss": 0.013126879930496216, "avg_return": 0.8641740083694458, "regret": 0.0006856295512989163, "entropy": 0.06819053739309311, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:43.882463Z", "loop": 14330, "env_steps": 8804966399, "loss": 0.014596222899854183, "avg_return": 0.8636835217475891, "regret": 0.00017591455252841115, "entropy": 0.06929513067007065, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:44.736586Z", "loop": 14331, "env_steps": 8805580799, "loss": 0.014292214997112751, "avg_return": 0.863057553768158, "regret": 0.00017591455252841115, "entropy": 0.06795821338891983, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:45.590934Z", "loop": 14332, "env_steps": 8806195199, "loss": 0.014264336787164211, "avg_return": 0.8637679219245911, "regret": 0.00017591455252841115, "entropy": 0.06854578852653503, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:46.445790Z", "loop": 14333, "env_steps": 8806809599, "loss": 0.015413585118949413, "avg_return": 0.8643547892570496, "regret": 0.00017591455252841115, "entropy": 0.07099857926368713, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:47.302013Z", "loop": 14334, "env_steps": 8807423999, "loss": 0.013773932121694088, "avg_return": 0.8643362522125244, "regret": 0.00017591455252841115, "entropy": 0.06718545407056808, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:48.155801Z", "loop": 14335, "env_steps": 8808038399, "loss": 0.014012868516147137, "avg_return": 0.862650990486145, "regret": 0.00017591455252841115, "entropy": 0.06829848140478134, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:49.008757Z", "loop": 14336, "env_steps": 8808652799, "loss": 0.014431637711822987, "avg_return": 0.8638807535171509, "regret": 0.00017591455252841115, "entropy": 0.07042451202869415, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:49.862264Z", "loop": 14337, "env_steps": 8809267199, "loss": 0.013018590398132801, "avg_return": 0.863490641117096, "regret": 0.00017591455252841115, "entropy": 0.0624859593808651, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:50.716415Z", "loop": 14338, "env_steps": 8809881599, "loss": 0.013217920437455177, "avg_return": 0.862406849861145, "regret": 0.00017591455252841115, "entropy": 0.06734158843755722, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:51.570218Z", "loop": 14339, "env_steps": 8810495999, "loss": 0.013605213724076748, "avg_return": 0.8628950119018555, "regret": 0.00017591455252841115, "entropy": 0.06601517647504807, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:52.466663Z", "loop": 14340, "env_steps": 8811110399, "loss": 0.01405057031661272, "avg_return": 0.862910270690918, "regret": 0.0009601910132914782, "entropy": 0.06992670148611069, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:53.320116Z", "loop": 14341, "env_steps": 8811724799, "loss": 0.013773453421890736, "avg_return": 0.8619645237922668, "regret": 0.0009601910132914782, "entropy": 0.06844242662191391, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:54.174259Z", "loop": 14342, "env_steps": 8812339199, "loss": 0.014506205916404724, "avg_return": 0.8633626699447632, "regret": 0.0009601910132914782, "entropy": 0.06990258395671844, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:55.028130Z", "loop": 14343, "env_steps": 8812953599, "loss": 0.014844267629086971, "avg_return": 0.8617807030677795, "regret": 0.0009601910132914782, "entropy": 0.07412384450435638, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:55.882352Z", "loop": 14344, "env_steps": 8813567999, "loss": 0.015298779122531414, "avg_return": 0.8623948097229004, "regret": 0.0009601910132914782, "entropy": 0.07308091223239899, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:56.734907Z", "loop": 14345, "env_steps": 8814182399, "loss": 0.015385258011519909, "avg_return": 0.8615849018096924, "regret": 0.0009601910132914782, "entropy": 0.07683063298463821, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:57.587359Z", "loop": 14346, "env_steps": 8814796799, "loss": 0.01759166643023491, "avg_return": 0.8613753318786621, "regret": 0.0009601910132914782, "entropy": 0.08124510198831558, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:58.441847Z", "loop": 14347, "env_steps": 8815411199, "loss": 0.017388610169291496, "avg_return": 0.8613894581794739, "regret": 0.0009601910132914782, "entropy": 0.08132961392402649, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:48:59.295119Z", "loop": 14348, "env_steps": 8816025599, "loss": 0.01720224693417549, "avg_return": 0.8623970746994019, "regret": 0.0009601910132914782, "entropy": 0.08081762492656708, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:00.149131Z", "loop": 14349, "env_steps": 8816639999, "loss": 0.016666453331708908, "avg_return": 0.8614775538444519, "regret": 0.0009601910132914782, "entropy": 0.0796145498752594, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:01.044809Z", "loop": 14350, "env_steps": 8817254399, "loss": 0.015868740156292915, "avg_return": 0.8617240786552429, "regret": 0.0010250553023070097, "entropy": 0.07886484265327454, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:01.900545Z", "loop": 14351, "env_steps": 8817868799, "loss": 0.014560897834599018, "avg_return": 0.8637548089027405, "regret": 0.0010250553023070097, "entropy": 0.07167970389127731, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:02.754427Z", "loop": 14352, "env_steps": 8818483199, "loss": 0.014314177446067333, "avg_return": 0.8632623553276062, "regret": 0.0010250553023070097, "entropy": 0.06985775381326675, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:03.608002Z", "loop": 14353, "env_steps": 8819097599, "loss": 0.013336318545043468, "avg_return": 0.8621705174446106, "regret": 0.0010250553023070097, "entropy": 0.06766949594020844, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:04.463917Z", "loop": 14354, "env_steps": 8819711999, "loss": 0.014249267987906933, "avg_return": 0.8634830713272095, "regret": 0.0010250553023070097, "entropy": 0.06798296421766281, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:05.317765Z", "loop": 14355, "env_steps": 8820326399, "loss": 0.014146484434604645, "avg_return": 0.8637676239013672, "regret": 0.0010250553023070097, "entropy": 0.0682729110121727, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:06.171732Z", "loop": 14356, "env_steps": 8820940799, "loss": 0.014134468510746956, "avg_return": 0.8635069727897644, "regret": 0.0010250553023070097, "entropy": 0.0684293881058693, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:07.027071Z", "loop": 14357, "env_steps": 8821555199, "loss": 0.013096186332404613, "avg_return": 0.8632410168647766, "regret": 0.0010250553023070097, "entropy": 0.06381623446941376, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:07.881182Z", "loop": 14358, "env_steps": 8822169599, "loss": 0.013155926950275898, "avg_return": 0.8629024624824524, "regret": 0.0010250553023070097, "entropy": 0.06521295756101608, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:08.735374Z", "loop": 14359, "env_steps": 8822783999, "loss": 0.012000984512269497, "avg_return": 0.8647365570068359, "regret": 0.0010250553023070097, "entropy": 0.06368682533502579, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:09.630096Z", "loop": 14360, "env_steps": 8823398399, "loss": 0.01372766774147749, "avg_return": 0.8633585572242737, "regret": 0.00016003586642909795, "entropy": 0.06538210064172745, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:10.485688Z", "loop": 14361, "env_steps": 8824012799, "loss": 0.013911828398704529, "avg_return": 0.8628227710723877, "regret": 0.00016003586642909795, "entropy": 0.06550144404172897, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:11.343590Z", "loop": 14362, "env_steps": 8824627199, "loss": 0.01278475858271122, "avg_return": 0.863595187664032, "regret": 0.00016003586642909795, "entropy": 0.06711392104625702, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:12.197085Z", "loop": 14363, "env_steps": 8825241599, "loss": 0.01290354784578085, "avg_return": 0.8639664649963379, "regret": 0.00016003586642909795, "entropy": 0.06093478575348854, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:13.050591Z", "loop": 14364, "env_steps": 8825855999, "loss": 0.012704822234809399, "avg_return": 0.862450897693634, "regret": 0.00016003586642909795, "entropy": 0.06417427211999893, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:13.904140Z", "loop": 14365, "env_steps": 8826470399, "loss": 0.012740547768771648, "avg_return": 0.8637251853942871, "regret": 0.00016003586642909795, "entropy": 0.06514479219913483, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:14.758113Z", "loop": 14366, "env_steps": 8827084799, "loss": 0.01206988375633955, "avg_return": 0.863557755947113, "regret": 0.00016003586642909795, "entropy": 0.0631447583436966, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:15.611833Z", "loop": 14367, "env_steps": 8827699199, "loss": 0.01208732184022665, "avg_return": 0.8632331490516663, "regret": 0.00016003586642909795, "entropy": 0.06330651789903641, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:16.465575Z", "loop": 14368, "env_steps": 8828313599, "loss": 0.01198927965015173, "avg_return": 0.8647162318229675, "regret": 0.00016003586642909795, "entropy": 0.06136349216103554, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:17.319058Z", "loop": 14369, "env_steps": 8828927999, "loss": 0.012863348238170147, "avg_return": 0.864031195640564, "regret": 0.00016003586642909795, "entropy": 0.06217281520366669, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:18.213945Z", "loop": 14370, "env_steps": 8829542399, "loss": 0.012567798607051373, "avg_return": 0.863237738609314, "regret": 0.00024927675258368254, "entropy": 0.06333247572183609, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:19.068391Z", "loop": 14371, "env_steps": 8830156799, "loss": 0.012149941176176071, "avg_return": 0.8635489344596863, "regret": 0.00024927675258368254, "entropy": 0.062295783311128616, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:19.922241Z", "loop": 14372, "env_steps": 8830771199, "loss": 0.012867780402302742, "avg_return": 0.8621968030929565, "regret": 0.00024927675258368254, "entropy": 0.064042828977108, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:20.775827Z", "loop": 14373, "env_steps": 8831385599, "loss": 0.012118808925151825, "avg_return": 0.8638283610343933, "regret": 0.00024927675258368254, "entropy": 0.062308795750141144, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:21.630793Z", "loop": 14374, "env_steps": 8831999999, "loss": 0.012848212383687496, "avg_return": 0.8640292286872864, "regret": 0.00024927675258368254, "entropy": 0.06389956176280975, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:22.484656Z", "loop": 14375, "env_steps": 8832614399, "loss": 0.011911965906620026, "avg_return": 0.863959550857544, "regret": 0.00024927675258368254, "entropy": 0.05984323471784592, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:23.338148Z", "loop": 14376, "env_steps": 8833228799, "loss": 0.013077348470687866, "avg_return": 0.863437294960022, "regret": 0.00024927675258368254, "entropy": 0.0656532496213913, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:24.192428Z", "loop": 14377, "env_steps": 8833843199, "loss": 0.012767602689564228, "avg_return": 0.8615410327911377, "regret": 0.00024927675258368254, "entropy": 0.06627725809812546, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:25.046475Z", "loop": 14378, "env_steps": 8834457599, "loss": 0.014514981769025326, "avg_return": 0.8635158538818359, "regret": 0.00024927675258368254, "entropy": 0.07273148000240326, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:25.901159Z", "loop": 14379, "env_steps": 8835071999, "loss": 0.01626407913863659, "avg_return": 0.8623799085617065, "regret": 0.00024927675258368254, "entropy": 0.07562049478292465, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:26.795024Z", "loop": 14380, "env_steps": 8835686399, "loss": 0.014947694726288319, "avg_return": 0.8632230758666992, "regret": 0.00036769889993593097, "entropy": 0.07441573590040207, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:27.648932Z", "loop": 14381, "env_steps": 8836300799, "loss": 0.014073880389332771, "avg_return": 0.8631874918937683, "regret": 0.00036769889993593097, "entropy": 0.0668775886297226, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:28.502844Z", "loop": 14382, "env_steps": 8836915199, "loss": 0.013916323892772198, "avg_return": 0.8616307973861694, "regret": 0.00036769889993593097, "entropy": 0.06842564046382904, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:29.356781Z", "loop": 14383, "env_steps": 8837529599, "loss": 0.012778738513588905, "avg_return": 0.8634719252586365, "regret": 0.00036769889993593097, "entropy": 0.06612339615821838, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:30.211527Z", "loop": 14384, "env_steps": 8838143999, "loss": 0.013677348382771015, "avg_return": 0.8638700842857361, "regret": 0.00036769889993593097, "entropy": 0.06760333478450775, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:31.066179Z", "loop": 14385, "env_steps": 8838758399, "loss": 0.014806193299591541, "avg_return": 0.8626206517219543, "regret": 0.00036769889993593097, "entropy": 0.07209470123052597, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:31.919584Z", "loop": 14386, "env_steps": 8839372799, "loss": 0.01627429574728012, "avg_return": 0.8628638982772827, "regret": 0.00036769889993593097, "entropy": 0.07525704801082611, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:32.773464Z", "loop": 14387, "env_steps": 8839987199, "loss": 0.018375704064965248, "avg_return": 0.8629381656646729, "regret": 0.00036769889993593097, "entropy": 0.08480948209762573, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:33.627424Z", "loop": 14388, "env_steps": 8840601599, "loss": 0.02095996029675007, "avg_return": 0.8632069826126099, "regret": 0.00036769889993593097, "entropy": 0.09964510053396225, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:34.482113Z", "loop": 14389, "env_steps": 8841215999, "loss": 0.022345425561070442, "avg_return": 0.8616558909416199, "regret": 0.00036769889993593097, "entropy": 0.10578285157680511, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:35.375959Z", "loop": 14390, "env_steps": 8841830399, "loss": 0.022944489493966103, "avg_return": 0.8615326285362244, "regret": 0.0012648551492020488, "entropy": 0.10568445920944214, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:36.228772Z", "loop": 14391, "env_steps": 8842444799, "loss": 0.021220514550805092, "avg_return": 0.8612457513809204, "regret": 0.0012648551492020488, "entropy": 0.1041015014052391, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:37.082741Z", "loop": 14392, "env_steps": 8843059199, "loss": 0.02233925461769104, "avg_return": 0.8618190884590149, "regret": 0.0012648551492020488, "entropy": 0.10641653835773468, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:37.937269Z", "loop": 14393, "env_steps": 8843673599, "loss": 0.0227217860519886, "avg_return": 0.8603515625, "regret": 0.0012648551492020488, "entropy": 0.1061977744102478, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:38.790799Z", "loop": 14394, "env_steps": 8844287999, "loss": 0.022154580801725388, "avg_return": 0.8621378540992737, "regret": 0.0012648551492020488, "entropy": 0.10610689222812653, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:39.643526Z", "loop": 14395, "env_steps": 8844902399, "loss": 0.021629273891448975, "avg_return": 0.8608480095863342, "regret": 0.0012648551492020488, "entropy": 0.10515788942575455, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:40.496794Z", "loop": 14396, "env_steps": 8845516799, "loss": 0.022070782259106636, "avg_return": 0.861670970916748, "regret": 0.0012648551492020488, "entropy": 0.10742592811584473, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:41.351183Z", "loop": 14397, "env_steps": 8846131199, "loss": 0.021486440673470497, "avg_return": 0.8628780245780945, "regret": 0.0012648551492020488, "entropy": 0.10263010114431381, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:42.205297Z", "loop": 14398, "env_steps": 8846745599, "loss": 0.02287670411169529, "avg_return": 0.8619645237922668, "regret": 0.0012648551492020488, "entropy": 0.10849548131227493, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:43.057419Z", "loop": 14399, "env_steps": 8847359999, "loss": 0.022213593125343323, "avg_return": 0.8627223968505859, "regret": 0.0012648551492020488, "entropy": 0.10583996027708054, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:43.950142Z", "loop": 14400, "env_steps": 8847974399, "loss": 0.02224321849644184, "avg_return": 0.8627851605415344, "regret": 0.0007335245609283447, "entropy": 0.10429080575704575, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:44.805527Z", "loop": 14401, "env_steps": 8848588799, "loss": 0.020665518939495087, "avg_return": 0.8629905581474304, "regret": 0.0007335245609283447, "entropy": 0.09984131157398224, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:45.659695Z", "loop": 14402, "env_steps": 8849203199, "loss": 0.01897876150906086, "avg_return": 0.8626805543899536, "regret": 0.0007335245609283447, "entropy": 0.08854836970567703, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:46.513727Z", "loop": 14403, "env_steps": 8849817599, "loss": 0.019035227596759796, "avg_return": 0.861403226852417, "regret": 0.0007335245609283447, "entropy": 0.09274375438690186, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:47.366298Z", "loop": 14404, "env_steps": 8850431999, "loss": 0.018321549519896507, "avg_return": 0.8603343963623047, "regret": 0.0007335245609283447, "entropy": 0.09569799900054932, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:48.220868Z", "loop": 14405, "env_steps": 8851046399, "loss": 0.018789639696478844, "avg_return": 0.8613406419754028, "regret": 0.0007335245609283447, "entropy": 0.09522371739149094, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:49.075432Z", "loop": 14406, "env_steps": 8851660799, "loss": 0.019414609298110008, "avg_return": 0.8613404631614685, "regret": 0.0007335245609283447, "entropy": 0.09657255560159683, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:49.929718Z", "loop": 14407, "env_steps": 8852275199, "loss": 0.019525857642292976, "avg_return": 0.8614988327026367, "regret": 0.0007335245609283447, "entropy": 0.0999029353260994, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:50.784468Z", "loop": 14408, "env_steps": 8852889599, "loss": 0.019222848117351532, "avg_return": 0.8634424209594727, "regret": 0.0007335245609283447, "entropy": 0.09720274806022644, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:51.639261Z", "loop": 14409, "env_steps": 8853503999, "loss": 0.018110929057002068, "avg_return": 0.8634970188140869, "regret": 0.0007335245609283447, "entropy": 0.0892612412571907, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:52.536096Z", "loop": 14410, "env_steps": 8854118399, "loss": 0.017461763694882393, "avg_return": 0.8625549674034119, "regret": 0.0004823532362934202, "entropy": 0.08796244114637375, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:53.390384Z", "loop": 14411, "env_steps": 8854732799, "loss": 0.017605029046535492, "avg_return": 0.8624936938285828, "regret": 0.0004823532362934202, "entropy": 0.08982494473457336, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:54.244772Z", "loop": 14412, "env_steps": 8855347199, "loss": 0.01613856852054596, "avg_return": 0.8616546988487244, "regret": 0.0004823532362934202, "entropy": 0.08770245313644409, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:55.099189Z", "loop": 14413, "env_steps": 8855961599, "loss": 0.01637164317071438, "avg_return": 0.8624601364135742, "regret": 0.0004823532362934202, "entropy": 0.08052106201648712, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:55.953214Z", "loop": 14414, "env_steps": 8856575999, "loss": 0.015961116179823875, "avg_return": 0.8629589080810547, "regret": 0.0004823532362934202, "entropy": 0.0831010714173317, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:56.807960Z", "loop": 14415, "env_steps": 8857190399, "loss": 0.015427323058247566, "avg_return": 0.8632281422615051, "regret": 0.0004823532362934202, "entropy": 0.07749652117490768, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:57.662287Z", "loop": 14416, "env_steps": 8857804799, "loss": 0.015396147035062313, "avg_return": 0.8636891841888428, "regret": 0.0004823532362934202, "entropy": 0.07807870209217072, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:58.516307Z", "loop": 14417, "env_steps": 8858419199, "loss": 0.016953906044363976, "avg_return": 0.8636134266853333, "regret": 0.0004823532362934202, "entropy": 0.08286100625991821, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:49:59.370226Z", "loop": 14418, "env_steps": 8859033599, "loss": 0.016816481947898865, "avg_return": 0.8643916845321655, "regret": 0.0004823532362934202, "entropy": 0.0860050693154335, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:00.224408Z", "loop": 14419, "env_steps": 8859647999, "loss": 0.020021522417664528, "avg_return": 0.8632358908653259, "regret": 0.0004823532362934202, "entropy": 0.09352311491966248, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:01.119417Z", "loop": 14420, "env_steps": 8860262399, "loss": 0.021549047902226448, "avg_return": 0.8640769720077515, "regret": 9.232280717696995e-05, "entropy": 0.10272800922393799, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:01.974777Z", "loop": 14421, "env_steps": 8860876799, "loss": 0.02161782793700695, "avg_return": 0.8635143041610718, "regret": 9.232280717696995e-05, "entropy": 0.1035974845290184, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:02.830776Z", "loop": 14422, "env_steps": 8861491199, "loss": 0.020992454141378403, "avg_return": 0.8638971447944641, "regret": 9.232280717696995e-05, "entropy": 0.10060547292232513, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:03.684623Z", "loop": 14423, "env_steps": 8862105599, "loss": 0.018370328471064568, "avg_return": 0.8647003173828125, "regret": 9.232280717696995e-05, "entropy": 0.08873127400875092, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:04.540207Z", "loop": 14424, "env_steps": 8862719999, "loss": 0.015850897878408432, "avg_return": 0.8641225099563599, "regret": 9.232280717696995e-05, "entropy": 0.08091412484645844, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:05.395099Z", "loop": 14425, "env_steps": 8863334399, "loss": 0.016624167561531067, "avg_return": 0.8641228675842285, "regret": 9.232280717696995e-05, "entropy": 0.0783187672495842, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:06.249325Z", "loop": 14426, "env_steps": 8863948799, "loss": 0.016590572893619537, "avg_return": 0.8651202321052551, "regret": 9.232280717696995e-05, "entropy": 0.07962630689144135, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:07.104848Z", "loop": 14427, "env_steps": 8864563199, "loss": 0.017620807513594627, "avg_return": 0.8642065525054932, "regret": 9.232280717696995e-05, "entropy": 0.08121740818023682, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:07.960346Z", "loop": 14428, "env_steps": 8865177599, "loss": 0.01729927770793438, "avg_return": 0.8636608123779297, "regret": 9.232280717696995e-05, "entropy": 0.0807708352804184, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:08.815235Z", "loop": 14429, "env_steps": 8865791999, "loss": 0.01652534306049347, "avg_return": 0.8626396059989929, "regret": 9.232280717696995e-05, "entropy": 0.07963479310274124, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:09.711887Z", "loop": 14430, "env_steps": 8866406399, "loss": 0.015244928188621998, "avg_return": 0.8635178804397583, "regret": 0.0002733552537392825, "entropy": 0.07558529078960419, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:10.565300Z", "loop": 14431, "env_steps": 8867020799, "loss": 0.014199549332261086, "avg_return": 0.863612711429596, "regret": 0.0002733552537392825, "entropy": 0.0708116888999939, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:11.419165Z", "loop": 14432, "env_steps": 8867635199, "loss": 0.014287032186985016, "avg_return": 0.8645013570785522, "regret": 0.0002733552537392825, "entropy": 0.07048434764146805, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:12.273720Z", "loop": 14433, "env_steps": 8868249599, "loss": 0.014114843681454659, "avg_return": 0.8641329407691956, "regret": 0.0002733552537392825, "entropy": 0.07021661102771759, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:13.128449Z", "loop": 14434, "env_steps": 8868863999, "loss": 0.014032800681889057, "avg_return": 0.8629146814346313, "regret": 0.0002733552537392825, "entropy": 0.06896405667066574, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:13.982467Z", "loop": 14435, "env_steps": 8869478399, "loss": 0.014061237685382366, "avg_return": 0.8639347553253174, "regret": 0.0002733552537392825, "entropy": 0.07020263373851776, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:14.836160Z", "loop": 14436, "env_steps": 8870092799, "loss": 0.014108771458268166, "avg_return": 0.8632127046585083, "regret": 0.0002733552537392825, "entropy": 0.07102920860052109, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:15.690874Z", "loop": 14437, "env_steps": 8870707199, "loss": 0.013934343121945858, "avg_return": 0.8640373945236206, "regret": 0.0002733552537392825, "entropy": 0.07048793137073517, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:16.545235Z", "loop": 14438, "env_steps": 8871321599, "loss": 0.013625063002109528, "avg_return": 0.8623872995376587, "regret": 0.0002733552537392825, "entropy": 0.06962501257658005, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:17.398612Z", "loop": 14439, "env_steps": 8871935999, "loss": 0.013066067360341549, "avg_return": 0.8629804849624634, "regret": 0.0002733552537392825, "entropy": 0.06642904877662659, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:18.290744Z", "loop": 14440, "env_steps": 8872550399, "loss": 0.013510589487850666, "avg_return": 0.8629059195518494, "regret": 0.00010941806976916268, "entropy": 0.06313006579875946, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:19.145860Z", "loop": 14441, "env_steps": 8873164799, "loss": 0.014235438778996468, "avg_return": 0.8630844354629517, "regret": 0.00010941806976916268, "entropy": 0.0696442574262619, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:20.000563Z", "loop": 14442, "env_steps": 8873779199, "loss": 0.01368639525026083, "avg_return": 0.8639727234840393, "regret": 0.00010941806976916268, "entropy": 0.06845394521951675, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:20.854975Z", "loop": 14443, "env_steps": 8874393599, "loss": 0.013029590249061584, "avg_return": 0.8631084561347961, "regret": 0.00010941806976916268, "entropy": 0.06570135056972504, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:21.708631Z", "loop": 14444, "env_steps": 8875007999, "loss": 0.012466417625546455, "avg_return": 0.8638346791267395, "regret": 0.00010941806976916268, "entropy": 0.06355464458465576, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:22.562667Z", "loop": 14445, "env_steps": 8875622399, "loss": 0.01173560693860054, "avg_return": 0.863926112651825, "regret": 0.00010941806976916268, "entropy": 0.05897488072514534, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:23.416819Z", "loop": 14446, "env_steps": 8876236799, "loss": 0.012697415426373482, "avg_return": 0.8629319667816162, "regret": 0.00010941806976916268, "entropy": 0.06653233617544174, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:24.271717Z", "loop": 14447, "env_steps": 8876851199, "loss": 0.011771748773753643, "avg_return": 0.8627114295959473, "regret": 0.00010941806976916268, "entropy": 0.06275462359189987, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:25.126647Z", "loop": 14448, "env_steps": 8877465599, "loss": 0.0129115404561162, "avg_return": 0.8643792867660522, "regret": 0.00010941806976916268, "entropy": 0.06348755955696106, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:25.980898Z", "loop": 14449, "env_steps": 8878079999, "loss": 0.013360105454921722, "avg_return": 0.8628290295600891, "regret": 0.00010941806976916268, "entropy": 0.06776506453752518, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:26.874783Z", "loop": 14450, "env_steps": 8878694399, "loss": 0.01230616495013237, "avg_return": 0.8642613887786865, "regret": 0.00020679747103713453, "entropy": 0.061577536165714264, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:27.728601Z", "loop": 14451, "env_steps": 8879308799, "loss": 0.011917109601199627, "avg_return": 0.8628189563751221, "regret": 0.00020679747103713453, "entropy": 0.06374307721853256, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:28.583549Z", "loop": 14452, "env_steps": 8879923199, "loss": 0.012440885417163372, "avg_return": 0.8624215126037598, "regret": 0.00020679747103713453, "entropy": 0.06349647790193558, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:29.437596Z", "loop": 14453, "env_steps": 8880537599, "loss": 0.012330781668424606, "avg_return": 0.8631116151809692, "regret": 0.00020679747103713453, "entropy": 0.0616716668009758, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:30.290229Z", "loop": 14454, "env_steps": 8881151999, "loss": 0.012173552997410297, "avg_return": 0.8618642091751099, "regret": 0.00020679747103713453, "entropy": 0.06451699882745743, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:31.143095Z", "loop": 14455, "env_steps": 8881766399, "loss": 0.011448108591139317, "avg_return": 0.8614803552627563, "regret": 0.00020679747103713453, "entropy": 0.06272649019956589, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:31.998023Z", "loop": 14456, "env_steps": 8882380799, "loss": 0.012468786910176277, "avg_return": 0.8634989857673645, "regret": 0.00020679747103713453, "entropy": 0.06308858841657639, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:32.852750Z", "loop": 14457, "env_steps": 8882995199, "loss": 0.012477898970246315, "avg_return": 0.8638708591461182, "regret": 0.00020679747103713453, "entropy": 0.06390172243118286, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:33.705971Z", "loop": 14458, "env_steps": 8883609599, "loss": 0.012227296829223633, "avg_return": 0.862662672996521, "regret": 0.00020679747103713453, "entropy": 0.06557507067918777, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:34.559473Z", "loop": 14459, "env_steps": 8884223999, "loss": 0.012714427895843983, "avg_return": 0.8625090718269348, "regret": 0.00020679747103713453, "entropy": 0.0633169561624527, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:35.454013Z", "loop": 14460, "env_steps": 8884838399, "loss": 0.012479494325816631, "avg_return": 0.8633866310119629, "regret": 0.00021479418501257896, "entropy": 0.06382515281438828, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:36.308455Z", "loop": 14461, "env_steps": 8885452799, "loss": 0.011437601409852505, "avg_return": 0.8635156750679016, "regret": 0.00021479418501257896, "entropy": 0.060172323137521744, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:37.164184Z", "loop": 14462, "env_steps": 8886067199, "loss": 0.011613022536039352, "avg_return": 0.8629652261734009, "regret": 0.00021479418501257896, "entropy": 0.062231987714767456, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:38.018632Z", "loop": 14463, "env_steps": 8886681599, "loss": 0.0122245317324996, "avg_return": 0.8630838990211487, "regret": 0.00021479418501257896, "entropy": 0.06261619925498962, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:38.874033Z", "loop": 14464, "env_steps": 8887295999, "loss": 0.011703566648066044, "avg_return": 0.8640210032463074, "regret": 0.00021479418501257896, "entropy": 0.058229003101587296, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:39.729489Z", "loop": 14465, "env_steps": 8887910399, "loss": 0.011756240390241146, "avg_return": 0.863906979560852, "regret": 0.00021479418501257896, "entropy": 0.059223271906375885, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:40.584194Z", "loop": 14466, "env_steps": 8888524799, "loss": 0.012054607272148132, "avg_return": 0.8633571863174438, "regret": 0.00021479418501257896, "entropy": 0.05971498042345047, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:41.438100Z", "loop": 14467, "env_steps": 8889139199, "loss": 0.011080296710133553, "avg_return": 0.8623294234275818, "regret": 0.00021479418501257896, "entropy": 0.0604407899081707, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:42.292222Z", "loop": 14468, "env_steps": 8889753599, "loss": 0.01196459773927927, "avg_return": 0.8629940152168274, "regret": 0.00021479418501257896, "entropy": 0.0634559914469719, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:43.146315Z", "loop": 14469, "env_steps": 8890367999, "loss": 0.012284285388886929, "avg_return": 0.8635091185569763, "regret": 0.00021479418501257896, "entropy": 0.06303344666957855, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:44.040057Z", "loop": 14470, "env_steps": 8890982399, "loss": 0.01224435493350029, "avg_return": 0.8640732169151306, "regret": 5.9242807765258476e-05, "entropy": 0.061491601169109344, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:44.893870Z", "loop": 14471, "env_steps": 8891596799, "loss": 0.013342422433197498, "avg_return": 0.86374831199646, "regret": 5.9242807765258476e-05, "entropy": 0.06386159360408783, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:45.748571Z", "loop": 14472, "env_steps": 8892211199, "loss": 0.014223314821720123, "avg_return": 0.8632556200027466, "regret": 5.9242807765258476e-05, "entropy": 0.06928970664739609, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:46.601915Z", "loop": 14473, "env_steps": 8892825599, "loss": 0.015048831701278687, "avg_return": 0.864175021648407, "regret": 5.9242807765258476e-05, "entropy": 0.07257622480392456, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:47.455409Z", "loop": 14474, "env_steps": 8893439999, "loss": 0.01467555295675993, "avg_return": 0.8642553091049194, "regret": 5.9242807765258476e-05, "entropy": 0.07171260565519333, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:48.309304Z", "loop": 14475, "env_steps": 8894054399, "loss": 0.016084851697087288, "avg_return": 0.8629235029220581, "regret": 5.9242807765258476e-05, "entropy": 0.07536573708057404, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:49.164012Z", "loop": 14476, "env_steps": 8894668799, "loss": 0.016813058406114578, "avg_return": 0.863049328327179, "regret": 5.9242807765258476e-05, "entropy": 0.08128728717565536, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:50.018811Z", "loop": 14477, "env_steps": 8895283199, "loss": 0.016822604462504387, "avg_return": 0.8639087080955505, "regret": 5.9242807765258476e-05, "entropy": 0.08080009371042252, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:50.872443Z", "loop": 14478, "env_steps": 8895897599, "loss": 0.01666243188083172, "avg_return": 0.8634676337242126, "regret": 5.9242807765258476e-05, "entropy": 0.07772719115018845, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:51.725473Z", "loop": 14479, "env_steps": 8896511999, "loss": 0.015223043039441109, "avg_return": 0.8623257875442505, "regret": 5.9242807765258476e-05, "entropy": 0.07247530668973923, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:52.619212Z", "loop": 14480, "env_steps": 8897126399, "loss": 0.014197111129760742, "avg_return": 0.8638961911201477, "regret": 0.0001979338558157906, "entropy": 0.07257244735956192, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:53.471687Z", "loop": 14481, "env_steps": 8897740799, "loss": 0.013617184944450855, "avg_return": 0.8629062175750732, "regret": 0.0001979338558157906, "entropy": 0.0666946992278099, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:54.323771Z", "loop": 14482, "env_steps": 8898355199, "loss": 0.011650105006992817, "avg_return": 0.8630400896072388, "regret": 0.0001979338558157906, "entropy": 0.06366174668073654, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:55.177624Z", "loop": 14483, "env_steps": 8898969599, "loss": 0.013499321416020393, "avg_return": 0.8643084764480591, "regret": 0.0001979338558157906, "entropy": 0.06909257918596268, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:56.032115Z", "loop": 14484, "env_steps": 8899583999, "loss": 0.013923810794949532, "avg_return": 0.8623694777488708, "regret": 0.0001979338558157906, "entropy": 0.07200776040554047, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:56.886596Z", "loop": 14485, "env_steps": 8900198399, "loss": 0.015257452614605427, "avg_return": 0.8634254932403564, "regret": 0.0001979338558157906, "entropy": 0.07754301279783249, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:57.740472Z", "loop": 14486, "env_steps": 8900812799, "loss": 0.0156853049993515, "avg_return": 0.8625954389572144, "regret": 0.0001979338558157906, "entropy": 0.07786824554204941, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:58.594360Z", "loop": 14487, "env_steps": 8901427199, "loss": 0.016236696392297745, "avg_return": 0.8596552014350891, "regret": 0.0001979338558157906, "entropy": 0.08177278935909271, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:50:59.449302Z", "loop": 14488, "env_steps": 8902041599, "loss": 0.01765257492661476, "avg_return": 0.8565583229064941, "regret": 0.0001979338558157906, "entropy": 0.08769366145133972, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:00.303263Z", "loop": 14489, "env_steps": 8902655999, "loss": 0.01764279045164585, "avg_return": 0.8582487106323242, "regret": 0.0001979338558157906, "entropy": 0.08607276529073715, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:01.196576Z", "loop": 14490, "env_steps": 8903270399, "loss": 0.018214194104075432, "avg_return": 0.8592200875282288, "regret": 0.004544172901660204, "entropy": 0.08653981238603592, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:02.049647Z", "loop": 14491, "env_steps": 8903884799, "loss": 0.018669618293642998, "avg_return": 0.8604272603988647, "regret": 0.004544172901660204, "entropy": 0.08752629160881042, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:02.904761Z", "loop": 14492, "env_steps": 8904499199, "loss": 0.01860755868256092, "avg_return": 0.8612954020500183, "regret": 0.004544172901660204, "entropy": 0.0871366411447525, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:03.759454Z", "loop": 14493, "env_steps": 8905113599, "loss": 0.018329868093132973, "avg_return": 0.862018346786499, "regret": 0.004544172901660204, "entropy": 0.08629021793603897, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:04.613559Z", "loop": 14494, "env_steps": 8905727999, "loss": 0.018064627423882484, "avg_return": 0.861433744430542, "regret": 0.004544172901660204, "entropy": 0.08788367360830307, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:05.467117Z", "loop": 14495, "env_steps": 8906342399, "loss": 0.01741911843419075, "avg_return": 0.861380934715271, "regret": 0.004544172901660204, "entropy": 0.08570272475481033, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:06.321760Z", "loop": 14496, "env_steps": 8906956799, "loss": 0.016178816556930542, "avg_return": 0.8614640235900879, "regret": 0.004544172901660204, "entropy": 0.08198767155408859, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:07.175688Z", "loop": 14497, "env_steps": 8907571199, "loss": 0.016172725707292557, "avg_return": 0.8623808026313782, "regret": 0.004544172901660204, "entropy": 0.07949144393205643, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:08.030229Z", "loop": 14498, "env_steps": 8908185599, "loss": 0.015479611232876778, "avg_return": 0.8623316884040833, "regret": 0.004544172901660204, "entropy": 0.07304435968399048, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:08.884716Z", "loop": 14499, "env_steps": 8908799999, "loss": 0.01552795059978962, "avg_return": 0.8620582222938538, "regret": 0.004544172901660204, "entropy": 0.07181771844625473, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:09.778705Z", "loop": 14500, "env_steps": 8909414399, "loss": 0.013214297592639923, "avg_return": 0.8597843647003174, "regret": 0.002307858318090439, "entropy": 0.06906217336654663, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:10.632366Z", "loop": 14501, "env_steps": 8910028799, "loss": 0.01310413982719183, "avg_return": 0.8617295622825623, "regret": 0.002307858318090439, "entropy": 0.06255002319812775, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:11.486603Z", "loop": 14502, "env_steps": 8910643199, "loss": 0.011930616572499275, "avg_return": 0.8607856631278992, "regret": 0.002307858318090439, "entropy": 0.061723459511995316, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:12.340652Z", "loop": 14503, "env_steps": 8911257599, "loss": 0.012344256974756718, "avg_return": 0.8634365200996399, "regret": 0.002307858318090439, "entropy": 0.060904599726200104, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:13.193537Z", "loop": 14504, "env_steps": 8911871999, "loss": 0.01157326903194189, "avg_return": 0.8622363209724426, "regret": 0.002307858318090439, "entropy": 0.061579637229442596, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:14.046856Z", "loop": 14505, "env_steps": 8912486399, "loss": 0.011923938989639282, "avg_return": 0.8634800314903259, "regret": 0.002307858318090439, "entropy": 0.060575224459171295, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:14.901174Z", "loop": 14506, "env_steps": 8913100799, "loss": 0.012002875097095966, "avg_return": 0.8633884787559509, "regret": 0.002307858318090439, "entropy": 0.0603315532207489, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:15.755796Z", "loop": 14507, "env_steps": 8913715199, "loss": 0.012947400100529194, "avg_return": 0.862162709236145, "regret": 0.002307858318090439, "entropy": 0.06564722955226898, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:16.608721Z", "loop": 14508, "env_steps": 8914329599, "loss": 0.013722242787480354, "avg_return": 0.8634006977081299, "regret": 0.002307858318090439, "entropy": 0.06739415973424911, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:17.461073Z", "loop": 14509, "env_steps": 8914943999, "loss": 0.01190892979502678, "avg_return": 0.8631958365440369, "regret": 0.002307858318090439, "entropy": 0.0627794861793518, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:18.354255Z", "loop": 14510, "env_steps": 8915558399, "loss": 0.011660009622573853, "avg_return": 0.8631108999252319, "regret": 0.001088534714654088, "entropy": 0.06230946630239487, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:19.208128Z", "loop": 14511, "env_steps": 8916172799, "loss": 0.011545353569090366, "avg_return": 0.8609269261360168, "regret": 0.001088534714654088, "entropy": 0.0614459402859211, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:20.062657Z", "loop": 14512, "env_steps": 8916787199, "loss": 0.012817436829209328, "avg_return": 0.861648678779602, "regret": 0.001088534714654088, "entropy": 0.064276784658432, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:20.917286Z", "loop": 14513, "env_steps": 8917401599, "loss": 0.01252409815788269, "avg_return": 0.8624825477600098, "regret": 0.001088534714654088, "entropy": 0.06422979384660721, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:21.772068Z", "loop": 14514, "env_steps": 8918015999, "loss": 0.012050439603626728, "avg_return": 0.8618307709693909, "regret": 0.001088534714654088, "entropy": 0.06451692432165146, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:22.628193Z", "loop": 14515, "env_steps": 8918630399, "loss": 0.011495915241539478, "avg_return": 0.8622358441352844, "regret": 0.001088534714654088, "entropy": 0.06511370837688446, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:23.484366Z", "loop": 14516, "env_steps": 8919244799, "loss": 0.012204811908304691, "avg_return": 0.8611848950386047, "regret": 0.001088534714654088, "entropy": 0.06472256034612656, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:24.340024Z", "loop": 14517, "env_steps": 8919859199, "loss": 0.013214632868766785, "avg_return": 0.8615036010742188, "regret": 0.001088534714654088, "entropy": 0.06464328616857529, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:25.194287Z", "loop": 14518, "env_steps": 8920473599, "loss": 0.013079563155770302, "avg_return": 0.8631376624107361, "regret": 0.001088534714654088, "entropy": 0.06551320850849152, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:26.050047Z", "loop": 14519, "env_steps": 8921087999, "loss": 0.011371119879186153, "avg_return": 0.8624309301376343, "regret": 0.001088534714654088, "entropy": 0.060147397220134735, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:26.945317Z", "loop": 14520, "env_steps": 8921702399, "loss": 0.012568962760269642, "avg_return": 0.8635563254356384, "regret": 0.0008373787277378142, "entropy": 0.0649733766913414, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:27.800799Z", "loop": 14521, "env_steps": 8922316799, "loss": 0.013702630996704102, "avg_return": 0.8628678321838379, "regret": 0.0008373787277378142, "entropy": 0.06887524574995041, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:28.655582Z", "loop": 14522, "env_steps": 8922931199, "loss": 0.013253618963062763, "avg_return": 0.862260639667511, "regret": 0.0008373787277378142, "entropy": 0.06839200109243393, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:29.509559Z", "loop": 14523, "env_steps": 8923545599, "loss": 0.015613391064107418, "avg_return": 0.8618293404579163, "regret": 0.0008373787277378142, "entropy": 0.07895585149526596, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:30.363610Z", "loop": 14524, "env_steps": 8924159999, "loss": 0.016643205657601357, "avg_return": 0.8631476163864136, "regret": 0.0008373787277378142, "entropy": 0.07802984118461609, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:31.217050Z", "loop": 14525, "env_steps": 8924774399, "loss": 0.015253583900630474, "avg_return": 0.8617793917655945, "regret": 0.0008373787277378142, "entropy": 0.07782959192991257, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:32.071482Z", "loop": 14526, "env_steps": 8925388799, "loss": 0.016138872131705284, "avg_return": 0.8623673915863037, "regret": 0.0008373787277378142, "entropy": 0.07823999971151352, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:32.926133Z", "loop": 14527, "env_steps": 8926003199, "loss": 0.016257576644420624, "avg_return": 0.8620420694351196, "regret": 0.0008373787277378142, "entropy": 0.07837151736021042, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:33.780933Z", "loop": 14528, "env_steps": 8926617599, "loss": 0.015511618927121162, "avg_return": 0.8628595471382141, "regret": 0.0008373787277378142, "entropy": 0.07638278603553772, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:34.635669Z", "loop": 14529, "env_steps": 8927231999, "loss": 0.015688670799136162, "avg_return": 0.864342451095581, "regret": 0.0008373787277378142, "entropy": 0.07734628021717072, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:35.530077Z", "loop": 14530, "env_steps": 8927846399, "loss": 0.015664076432585716, "avg_return": 0.8642725944519043, "regret": 0.0002511323255021125, "entropy": 0.07335983961820602, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:36.384396Z", "loop": 14531, "env_steps": 8928460799, "loss": 0.014788630418479443, "avg_return": 0.8640382885932922, "regret": 0.0002511323255021125, "entropy": 0.07204841077327728, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:37.238642Z", "loop": 14532, "env_steps": 8929075199, "loss": 0.014483352191746235, "avg_return": 0.8646730780601501, "regret": 0.0002511323255021125, "entropy": 0.07110186666250229, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:38.092933Z", "loop": 14533, "env_steps": 8929689599, "loss": 0.015679335221648216, "avg_return": 0.8635897040367126, "regret": 0.0002511323255021125, "entropy": 0.07098137587308884, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:38.947351Z", "loop": 14534, "env_steps": 8930303999, "loss": 0.014733386225998402, "avg_return": 0.8646424412727356, "regret": 0.0002511323255021125, "entropy": 0.06909167021512985, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:39.801647Z", "loop": 14535, "env_steps": 8930918399, "loss": 0.015047694556415081, "avg_return": 0.8627554774284363, "regret": 0.0002511323255021125, "entropy": 0.07570353150367737, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:40.656006Z", "loop": 14536, "env_steps": 8931532799, "loss": 0.014994184486567974, "avg_return": 0.8634798526763916, "regret": 0.0002511323255021125, "entropy": 0.07211019098758698, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:41.510896Z", "loop": 14537, "env_steps": 8932147199, "loss": 0.016463065519928932, "avg_return": 0.8630720376968384, "regret": 0.0002511323255021125, "entropy": 0.0747767984867096, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:42.364457Z", "loop": 14538, "env_steps": 8932761599, "loss": 0.014506920240819454, "avg_return": 0.8626593351364136, "regret": 0.0002511323255021125, "entropy": 0.07161739468574524, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:43.218916Z", "loop": 14539, "env_steps": 8933375999, "loss": 0.014531669206917286, "avg_return": 0.8627723455429077, "regret": 0.0002511323255021125, "entropy": 0.07080164551734924, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:44.112272Z", "loop": 14540, "env_steps": 8933990399, "loss": 0.014640680514276028, "avg_return": 0.8632226586341858, "regret": 7.400891627185047e-05, "entropy": 0.07305008918046951, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:44.966536Z", "loop": 14541, "env_steps": 8934604799, "loss": 0.015149499289691448, "avg_return": 0.8627119064331055, "regret": 7.400891627185047e-05, "entropy": 0.07562413811683655, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:45.821010Z", "loop": 14542, "env_steps": 8935219199, "loss": 0.015645604580640793, "avg_return": 0.8623420596122742, "regret": 7.400891627185047e-05, "entropy": 0.07525786012411118, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:46.676028Z", "loop": 14543, "env_steps": 8935833599, "loss": 0.015539678744971752, "avg_return": 0.8636717796325684, "regret": 7.400891627185047e-05, "entropy": 0.07446528226137161, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:47.529776Z", "loop": 14544, "env_steps": 8936447999, "loss": 0.014181554317474365, "avg_return": 0.8631412982940674, "regret": 7.400891627185047e-05, "entropy": 0.07077735662460327, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:48.383833Z", "loop": 14545, "env_steps": 8937062399, "loss": 0.01236949022859335, "avg_return": 0.8631677627563477, "regret": 7.400891627185047e-05, "entropy": 0.0628051608800888, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:49.237596Z", "loop": 14546, "env_steps": 8937676799, "loss": 0.012676033191382885, "avg_return": 0.8631001710891724, "regret": 7.400891627185047e-05, "entropy": 0.06401239335536957, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:50.093099Z", "loop": 14547, "env_steps": 8938291199, "loss": 0.01103234849870205, "avg_return": 0.8627132177352905, "regret": 7.400891627185047e-05, "entropy": 0.058388300240039825, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:50.947697Z", "loop": 14548, "env_steps": 8938905599, "loss": 0.012164735235273838, "avg_return": 0.8645209074020386, "regret": 7.400891627185047e-05, "entropy": 0.06329397857189178, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:51.801296Z", "loop": 14549, "env_steps": 8939519999, "loss": 0.012608437798917294, "avg_return": 0.8633920550346375, "regret": 7.400891627185047e-05, "entropy": 0.06393260508775711, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:52.695100Z", "loop": 14550, "env_steps": 8940134399, "loss": 0.011717153713107109, "avg_return": 0.8634893894195557, "regret": 0.00021894092787988484, "entropy": 0.060820695012807846, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:53.550681Z", "loop": 14551, "env_steps": 8940748799, "loss": 0.01266345102339983, "avg_return": 0.8637856245040894, "regret": 0.00021894092787988484, "entropy": 0.061916667968034744, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:54.406078Z", "loop": 14552, "env_steps": 8941363199, "loss": 0.012711373157799244, "avg_return": 0.8628824949264526, "regret": 0.00021894092787988484, "entropy": 0.06413983553647995, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:55.260244Z", "loop": 14553, "env_steps": 8941977599, "loss": 0.011830350384116173, "avg_return": 0.8640837669372559, "regret": 0.00021894092787988484, "entropy": 0.06037304550409317, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:56.114204Z", "loop": 14554, "env_steps": 8942591999, "loss": 0.011353117413818836, "avg_return": 0.8629276752471924, "regret": 0.00021894092787988484, "entropy": 0.06261551380157471, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:56.969445Z", "loop": 14555, "env_steps": 8943206399, "loss": 0.011918386444449425, "avg_return": 0.8635774850845337, "regret": 0.00021894092787988484, "entropy": 0.06054067611694336, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:57.823612Z", "loop": 14556, "env_steps": 8943820799, "loss": 0.0114264702424407, "avg_return": 0.8628109097480774, "regret": 0.00021894092787988484, "entropy": 0.062213972210884094, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:58.678499Z", "loop": 14557, "env_steps": 8944435199, "loss": 0.012431102804839611, "avg_return": 0.8640146851539612, "regret": 0.00021894092787988484, "entropy": 0.06423827260732651, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:51:59.531900Z", "loop": 14558, "env_steps": 8945049599, "loss": 0.012818780727684498, "avg_return": 0.8630954027175903, "regret": 0.00021894092787988484, "entropy": 0.06512793153524399, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:00.386156Z", "loop": 14559, "env_steps": 8945663999, "loss": 0.011886472813785076, "avg_return": 0.8619440197944641, "regret": 0.00021894092787988484, "entropy": 0.06417986750602722, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:01.280401Z", "loop": 14560, "env_steps": 8946278399, "loss": 0.013330756686627865, "avg_return": 0.8625734448432922, "regret": 0.00012678968778345734, "entropy": 0.06524866819381714, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:02.134831Z", "loop": 14561, "env_steps": 8946892799, "loss": 0.01209511049091816, "avg_return": 0.8640651702880859, "regret": 0.00012678968778345734, "entropy": 0.06474490463733673, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:02.988557Z", "loop": 14562, "env_steps": 8947507199, "loss": 0.011184181086719036, "avg_return": 0.8630771040916443, "regret": 0.00012678968778345734, "entropy": 0.06017474830150604, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:03.842522Z", "loop": 14563, "env_steps": 8948121599, "loss": 0.012135309167206287, "avg_return": 0.8634886145591736, "regret": 0.00012678968778345734, "entropy": 0.06386299431324005, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:04.697031Z", "loop": 14564, "env_steps": 8948735999, "loss": 0.01275326032191515, "avg_return": 0.8638491034507751, "regret": 0.00012678968778345734, "entropy": 0.06255374848842621, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:05.552166Z", "loop": 14565, "env_steps": 8949350399, "loss": 0.01212317030876875, "avg_return": 0.8629232048988342, "regret": 0.00012678968778345734, "entropy": 0.06436082720756531, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:06.406567Z", "loop": 14566, "env_steps": 8949964799, "loss": 0.01261079590767622, "avg_return": 0.8626263737678528, "regret": 0.00012678968778345734, "entropy": 0.06553449481725693, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:07.261088Z", "loop": 14567, "env_steps": 8950579199, "loss": 0.012037708424031734, "avg_return": 0.8639661073684692, "regret": 0.00012678968778345734, "entropy": 0.06167661398649216, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:08.115144Z", "loop": 14568, "env_steps": 8951193599, "loss": 0.011390292085707188, "avg_return": 0.8638037443161011, "regret": 0.00012678968778345734, "entropy": 0.05931117385625839, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:08.969715Z", "loop": 14569, "env_steps": 8951807999, "loss": 0.011394924484193325, "avg_return": 0.8643941283226013, "regret": 0.00012678968778345734, "entropy": 0.06233173608779907, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:09.863965Z", "loop": 14570, "env_steps": 8952422399, "loss": 0.012213789857923985, "avg_return": 0.8628109097480774, "regret": 0.00012664857786148787, "entropy": 0.06347684562206268, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:10.718191Z", "loop": 14571, "env_steps": 8953036799, "loss": 0.011638286523520947, "avg_return": 0.8640521168708801, "regret": 0.00012664857786148787, "entropy": 0.06317593157291412, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:11.572278Z", "loop": 14572, "env_steps": 8953651199, "loss": 0.012225234881043434, "avg_return": 0.8641858100891113, "regret": 0.00012664857786148787, "entropy": 0.06367477029561996, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:12.425886Z", "loop": 14573, "env_steps": 8954265599, "loss": 0.01214621216058731, "avg_return": 0.8622997999191284, "regret": 0.00012664857786148787, "entropy": 0.0645224004983902, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:13.280511Z", "loop": 14574, "env_steps": 8954879999, "loss": 0.012369154952466488, "avg_return": 0.8644914031028748, "regret": 0.00012664857786148787, "entropy": 0.06240560859441757, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:14.135772Z", "loop": 14575, "env_steps": 8955494399, "loss": 0.012351786717772484, "avg_return": 0.8634393811225891, "regret": 0.00012664857786148787, "entropy": 0.06343904137611389, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:14.988806Z", "loop": 14576, "env_steps": 8956108799, "loss": 0.014311159960925579, "avg_return": 0.8625476360321045, "regret": 0.00012664857786148787, "entropy": 0.06755095720291138, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:15.841561Z", "loop": 14577, "env_steps": 8956723199, "loss": 0.015807708725333214, "avg_return": 0.8634942770004272, "regret": 0.00012664857786148787, "entropy": 0.07533614337444305, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:16.695551Z", "loop": 14578, "env_steps": 8957337599, "loss": 0.016196375712752342, "avg_return": 0.8633130192756653, "regret": 0.00012664857786148787, "entropy": 0.07556391507387161, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:17.550727Z", "loop": 14579, "env_steps": 8957951999, "loss": 0.015118195675313473, "avg_return": 0.8625698089599609, "regret": 0.00012664857786148787, "entropy": 0.07164730131626129, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:18.445384Z", "loop": 14580, "env_steps": 8958566399, "loss": 0.014948722906410694, "avg_return": 0.8642789721488953, "regret": 8.692606934346259e-05, "entropy": 0.07007163017988205, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:19.298789Z", "loop": 14581, "env_steps": 8959180799, "loss": 0.013806277886033058, "avg_return": 0.8639252185821533, "regret": 8.692606934346259e-05, "entropy": 0.06506321579217911, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:20.152652Z", "loop": 14582, "env_steps": 8959795199, "loss": 0.013403870165348053, "avg_return": 0.8642145991325378, "regret": 8.692606934346259e-05, "entropy": 0.06524164974689484, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:21.006857Z", "loop": 14583, "env_steps": 8960409599, "loss": 0.01331851352006197, "avg_return": 0.863145649433136, "regret": 8.692606934346259e-05, "entropy": 0.06473122537136078, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:21.861222Z", "loop": 14584, "env_steps": 8961023999, "loss": 0.01255432516336441, "avg_return": 0.8650217652320862, "regret": 8.692606934346259e-05, "entropy": 0.064240001142025, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:22.715613Z", "loop": 14585, "env_steps": 8961638399, "loss": 0.012201122008264065, "avg_return": 0.8637239933013916, "regret": 8.692606934346259e-05, "entropy": 0.06244722753763199, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:23.569276Z", "loop": 14586, "env_steps": 8962252799, "loss": 0.01158121693879366, "avg_return": 0.8632434010505676, "regret": 8.692606934346259e-05, "entropy": 0.05838742107152939, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:24.422949Z", "loop": 14587, "env_steps": 8962867199, "loss": 0.012454287149012089, "avg_return": 0.8633277416229248, "regret": 8.692606934346259e-05, "entropy": 0.05941392108798027, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:25.277947Z", "loop": 14588, "env_steps": 8963481599, "loss": 0.011846869252622128, "avg_return": 0.8639841675758362, "regret": 8.692606934346259e-05, "entropy": 0.0589296855032444, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:26.132317Z", "loop": 14589, "env_steps": 8964095999, "loss": 0.01413486897945404, "avg_return": 0.8625285029411316, "regret": 8.692606934346259e-05, "entropy": 0.06521551311016083, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:27.025174Z", "loop": 14590, "env_steps": 8964710399, "loss": 0.014115958474576473, "avg_return": 0.8628248572349548, "regret": 0.0008818577043712139, "entropy": 0.06711869686841965, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:27.879147Z", "loop": 14591, "env_steps": 8965324799, "loss": 0.014107788912951946, "avg_return": 0.8633263111114502, "regret": 0.0008818577043712139, "entropy": 0.0656009241938591, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:28.734084Z", "loop": 14592, "env_steps": 8965939199, "loss": 0.014647074043750763, "avg_return": 0.862784743309021, "regret": 0.0008818577043712139, "entropy": 0.06844152510166168, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:29.588145Z", "loop": 14593, "env_steps": 8966553599, "loss": 0.013037403114140034, "avg_return": 0.8612644672393799, "regret": 0.0008818577043712139, "entropy": 0.06230706721544266, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:30.442466Z", "loop": 14594, "env_steps": 8967167999, "loss": 0.013819699175655842, "avg_return": 0.8622424602508545, "regret": 0.0008818577043712139, "entropy": 0.06678814440965652, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:31.297369Z", "loop": 14595, "env_steps": 8967782399, "loss": 0.013110781088471413, "avg_return": 0.862206757068634, "regret": 0.0008818577043712139, "entropy": 0.06349847465753555, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:32.151745Z", "loop": 14596, "env_steps": 8968396799, "loss": 0.01461965311318636, "avg_return": 0.8617019057273865, "regret": 0.0008818577043712139, "entropy": 0.06440392881631851, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:33.005561Z", "loop": 14597, "env_steps": 8969011199, "loss": 0.014122101478278637, "avg_return": 0.8618968725204468, "regret": 0.0008818577043712139, "entropy": 0.0672903060913086, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:33.859396Z", "loop": 14598, "env_steps": 8969625599, "loss": 0.013420993462204933, "avg_return": 0.8631306886672974, "regret": 0.0008818577043712139, "entropy": 0.06674052774906158, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:34.712416Z", "loop": 14599, "env_steps": 8970239999, "loss": 0.013164112344384193, "avg_return": 0.8615654706954956, "regret": 0.0008818577043712139, "entropy": 0.06439178436994553, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:35.606469Z", "loop": 14600, "env_steps": 8970854399, "loss": 0.011288496665656567, "avg_return": 0.8605293035507202, "regret": 0.0022628207225352526, "entropy": 0.05726308375597, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:36.460036Z", "loop": 14601, "env_steps": 8971468799, "loss": 0.010746733285486698, "avg_return": 0.8581432104110718, "regret": 0.0022628207225352526, "entropy": 0.05504601076245308, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:37.313754Z", "loop": 14602, "env_steps": 8972083199, "loss": 0.01153708528727293, "avg_return": 0.8620072603225708, "regret": 0.0022628207225352526, "entropy": 0.05996324494481087, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:38.167933Z", "loop": 14603, "env_steps": 8972697599, "loss": 0.01052070688456297, "avg_return": 0.860805869102478, "regret": 0.0022628207225352526, "entropy": 0.0541631355881691, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:39.022665Z", "loop": 14604, "env_steps": 8973311999, "loss": 0.011017086915671825, "avg_return": 0.8605464100837708, "regret": 0.0022628207225352526, "entropy": 0.05462541803717613, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:39.876256Z", "loop": 14605, "env_steps": 8973926399, "loss": 0.011821935884654522, "avg_return": 0.8623822331428528, "regret": 0.0022628207225352526, "entropy": 0.0577198788523674, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:40.730085Z", "loop": 14606, "env_steps": 8974540799, "loss": 0.011703110300004482, "avg_return": 0.8616858124732971, "regret": 0.0022628207225352526, "entropy": 0.056024398654699326, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:41.584521Z", "loop": 14607, "env_steps": 8975155199, "loss": 0.011347150430083275, "avg_return": 0.8628705143928528, "regret": 0.0022628207225352526, "entropy": 0.059294093400239944, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:42.438551Z", "loop": 14608, "env_steps": 8975769599, "loss": 0.011194772087037563, "avg_return": 0.8621531128883362, "regret": 0.0022628207225352526, "entropy": 0.058963991701602936, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:43.292307Z", "loop": 14609, "env_steps": 8976383999, "loss": 0.013026105239987373, "avg_return": 0.8630470037460327, "regret": 0.0022628207225352526, "entropy": 0.0626860186457634, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:44.185899Z", "loop": 14610, "env_steps": 8976998399, "loss": 0.011940899305045605, "avg_return": 0.862788736820221, "regret": 0.0006109211826696992, "entropy": 0.05973046272993088, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:45.039841Z", "loop": 14611, "env_steps": 8977612799, "loss": 0.012528404593467712, "avg_return": 0.8629227876663208, "regret": 0.0006109211826696992, "entropy": 0.06197892874479294, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:45.894625Z", "loop": 14612, "env_steps": 8978227199, "loss": 0.013643818907439709, "avg_return": 0.8628568649291992, "regret": 0.0006109211826696992, "entropy": 0.06901752948760986, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:46.749135Z", "loop": 14613, "env_steps": 8978841599, "loss": 0.01281111128628254, "avg_return": 0.8638927340507507, "regret": 0.0006109211826696992, "entropy": 0.06602757424116135, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:47.604573Z", "loop": 14614, "env_steps": 8979455999, "loss": 0.01453002542257309, "avg_return": 0.863298773765564, "regret": 0.0006109211826696992, "entropy": 0.06881844252347946, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:48.458868Z", "loop": 14615, "env_steps": 8980070399, "loss": 0.013371869921684265, "avg_return": 0.8629209399223328, "regret": 0.0006109211826696992, "entropy": 0.06391675770282745, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:49.313430Z", "loop": 14616, "env_steps": 8980684799, "loss": 0.012846539728343487, "avg_return": 0.8623407483100891, "regret": 0.0006109211826696992, "entropy": 0.06402260810136795, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:50.166584Z", "loop": 14617, "env_steps": 8981299199, "loss": 0.013804512098431587, "avg_return": 0.8650429248809814, "regret": 0.0006109211826696992, "entropy": 0.06646381318569183, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:51.019819Z", "loop": 14618, "env_steps": 8981913599, "loss": 0.012286986224353313, "avg_return": 0.8634136915206909, "regret": 0.0006109211826696992, "entropy": 0.06408753246068954, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:51.874993Z", "loop": 14619, "env_steps": 8982527999, "loss": 0.01373771857470274, "avg_return": 0.8624666333198547, "regret": 0.0006109211826696992, "entropy": 0.06651055067777634, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:52.769446Z", "loop": 14620, "env_steps": 8983142399, "loss": 0.012177429161965847, "avg_return": 0.8632854223251343, "regret": 0.0002967342152260244, "entropy": 0.06066248565912247, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:53.623648Z", "loop": 14621, "env_steps": 8983756799, "loss": 0.012574488297104836, "avg_return": 0.8643864989280701, "regret": 0.0002967342152260244, "entropy": 0.06114055588841438, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:54.479076Z", "loop": 14622, "env_steps": 8984371199, "loss": 0.012190270237624645, "avg_return": 0.8622159957885742, "regret": 0.0002967342152260244, "entropy": 0.06324946135282516, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:55.333649Z", "loop": 14623, "env_steps": 8984985599, "loss": 0.012275023385882378, "avg_return": 0.8638485670089722, "regret": 0.0002967342152260244, "entropy": 0.06336669623851776, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:56.189629Z", "loop": 14624, "env_steps": 8985599999, "loss": 0.01091283280402422, "avg_return": 0.8635388612747192, "regret": 0.0002967342152260244, "entropy": 0.05948931723833084, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:57.044309Z", "loop": 14625, "env_steps": 8986214399, "loss": 0.014049604535102844, "avg_return": 0.8641251921653748, "regret": 0.0002967342152260244, "entropy": 0.06592793762683868, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:57.897904Z", "loop": 14626, "env_steps": 8986828799, "loss": 0.012003847397863865, "avg_return": 0.8627601265907288, "regret": 0.0002967342152260244, "entropy": 0.06194501370191574, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:58.751448Z", "loop": 14627, "env_steps": 8987443199, "loss": 0.013045008294284344, "avg_return": 0.8640985488891602, "regret": 0.0002967342152260244, "entropy": 0.06169445067644119, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:52:59.605645Z", "loop": 14628, "env_steps": 8988057599, "loss": 0.01247065793722868, "avg_return": 0.8631830215454102, "regret": 0.0002967342152260244, "entropy": 0.06591379642486572, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:00.462466Z", "loop": 14629, "env_steps": 8988671999, "loss": 0.013543970882892609, "avg_return": 0.8628109097480774, "regret": 0.0002967342152260244, "entropy": 0.0661265030503273, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:01.357112Z", "loop": 14630, "env_steps": 8989286399, "loss": 0.014538566581904888, "avg_return": 0.8630516529083252, "regret": 0.0002340553910471499, "entropy": 0.07104102522134781, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:02.210874Z", "loop": 14631, "env_steps": 8989900799, "loss": 0.01329535711556673, "avg_return": 0.862917423248291, "regret": 0.0002340553910471499, "entropy": 0.06628413498401642, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:03.065781Z", "loop": 14632, "env_steps": 8990515199, "loss": 0.014445613138377666, "avg_return": 0.8634498119354248, "regret": 0.0002340553910471499, "entropy": 0.07020523399114609, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:03.919934Z", "loop": 14633, "env_steps": 8991129599, "loss": 0.01700481027364731, "avg_return": 0.8631500601768494, "regret": 0.0002340553910471499, "entropy": 0.08104827255010605, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:04.775239Z", "loop": 14634, "env_steps": 8991743999, "loss": 0.01783428154885769, "avg_return": 0.8631072044372559, "regret": 0.0002340553910471499, "entropy": 0.0804147943854332, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:05.628339Z", "loop": 14635, "env_steps": 8992358399, "loss": 0.01633363775908947, "avg_return": 0.8646360635757446, "regret": 0.0002340553910471499, "entropy": 0.0793059691786766, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:06.482666Z", "loop": 14636, "env_steps": 8992972799, "loss": 0.015530139207839966, "avg_return": 0.8643843531608582, "regret": 0.0002340553910471499, "entropy": 0.07638698071241379, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:07.336868Z", "loop": 14637, "env_steps": 8993587199, "loss": 0.015862395986914635, "avg_return": 0.8642702698707581, "regret": 0.0002340553910471499, "entropy": 0.0761072114109993, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:08.191477Z", "loop": 14638, "env_steps": 8994201599, "loss": 0.01658298820257187, "avg_return": 0.8633502125740051, "regret": 0.0002340553910471499, "entropy": 0.08083853125572205, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:09.045944Z", "loop": 14639, "env_steps": 8994815999, "loss": 0.016621096059679985, "avg_return": 0.8624451756477356, "regret": 0.0002340553910471499, "entropy": 0.08039195090532303, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:09.940778Z", "loop": 14640, "env_steps": 8995430399, "loss": 0.01613774523139, "avg_return": 0.8620620965957642, "regret": 8.916069782571867e-05, "entropy": 0.07875150442123413, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:10.794456Z", "loop": 14641, "env_steps": 8996044799, "loss": 0.016344664618372917, "avg_return": 0.8638044595718384, "regret": 8.916069782571867e-05, "entropy": 0.07858051359653473, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:11.649627Z", "loop": 14642, "env_steps": 8996659199, "loss": 0.017701920121908188, "avg_return": 0.863944947719574, "regret": 8.916069782571867e-05, "entropy": 0.08037501573562622, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:12.503399Z", "loop": 14643, "env_steps": 8997273599, "loss": 0.018072595819830894, "avg_return": 0.86180180311203, "regret": 8.916069782571867e-05, "entropy": 0.0852428749203682, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:13.358293Z", "loop": 14644, "env_steps": 8997887999, "loss": 0.018353065475821495, "avg_return": 0.8639842867851257, "regret": 8.916069782571867e-05, "entropy": 0.08740640431642532, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:14.212342Z", "loop": 14645, "env_steps": 8998502399, "loss": 0.018121963366866112, "avg_return": 0.8634326457977295, "regret": 8.916069782571867e-05, "entropy": 0.0898236408829689, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:15.067385Z", "loop": 14646, "env_steps": 8999116799, "loss": 0.018896423280239105, "avg_return": 0.8635016083717346, "regret": 8.916069782571867e-05, "entropy": 0.08806221187114716, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:15.921325Z", "loop": 14647, "env_steps": 8999731199, "loss": 0.017373686656355858, "avg_return": 0.8643984198570251, "regret": 8.916069782571867e-05, "entropy": 0.08529070764780045, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:16.777275Z", "loop": 14648, "env_steps": 9000345599, "loss": 0.016959862783551216, "avg_return": 0.8632000684738159, "regret": 8.916069782571867e-05, "entropy": 0.08054259419441223, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:17.631004Z", "loop": 14649, "env_steps": 9000959999, "loss": 0.017370296642184258, "avg_return": 0.8621673583984375, "regret": 8.916069782571867e-05, "entropy": 0.08375879377126694, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:18.525395Z", "loop": 14650, "env_steps": 9001574399, "loss": 0.015513529069721699, "avg_return": 0.863644540309906, "regret": 0.00010443640348967165, "entropy": 0.07803637534379959, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:19.379978Z", "loop": 14651, "env_steps": 9002188799, "loss": 0.016131673008203506, "avg_return": 0.8626534342765808, "regret": 0.00010443640348967165, "entropy": 0.07803932577371597, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:20.235598Z", "loop": 14652, "env_steps": 9002803199, "loss": 0.01834290847182274, "avg_return": 0.8630180954933167, "regret": 0.00010443640348967165, "entropy": 0.08460921049118042, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:21.091625Z", "loop": 14653, "env_steps": 9003417599, "loss": 0.017682336270809174, "avg_return": 0.8620937466621399, "regret": 0.00010443640348967165, "entropy": 0.08596330136060715, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:21.946931Z", "loop": 14654, "env_steps": 9004031999, "loss": 0.019172679632902145, "avg_return": 0.8616528511047363, "regret": 0.00010443640348967165, "entropy": 0.08913759142160416, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:22.800834Z", "loop": 14655, "env_steps": 9004646399, "loss": 0.018930653110146523, "avg_return": 0.8642979860305786, "regret": 0.00010443640348967165, "entropy": 0.08844347298145294, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:23.655334Z", "loop": 14656, "env_steps": 9005260799, "loss": 0.01818595826625824, "avg_return": 0.8635370135307312, "regret": 0.00010443640348967165, "entropy": 0.08659329265356064, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:24.509697Z", "loop": 14657, "env_steps": 9005875199, "loss": 0.0180493351072073, "avg_return": 0.8633579611778259, "regret": 0.00010443640348967165, "entropy": 0.08302371203899384, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:25.362867Z", "loop": 14658, "env_steps": 9006489599, "loss": 0.017061596736311913, "avg_return": 0.8629799485206604, "regret": 0.00010443640348967165, "entropy": 0.08149453997612, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:26.216030Z", "loop": 14659, "env_steps": 9007103999, "loss": 0.01452233549207449, "avg_return": 0.8632364273071289, "regret": 0.00010443640348967165, "entropy": 0.07368399202823639, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:27.109897Z", "loop": 14660, "env_steps": 9007718399, "loss": 0.014053313992917538, "avg_return": 0.863710343837738, "regret": 8.953511132858694e-05, "entropy": 0.07046826928853989, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:27.963876Z", "loop": 14661, "env_steps": 9008332799, "loss": 0.015006544068455696, "avg_return": 0.862389326095581, "regret": 8.953511132858694e-05, "entropy": 0.0728636384010315, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:28.818337Z", "loop": 14662, "env_steps": 9008947199, "loss": 0.013829200528562069, "avg_return": 0.8632069826126099, "regret": 8.953511132858694e-05, "entropy": 0.07284671813249588, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:29.672196Z", "loop": 14663, "env_steps": 9009561599, "loss": 0.014959667809307575, "avg_return": 0.8632538914680481, "regret": 8.953511132858694e-05, "entropy": 0.07234560698270798, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:30.526520Z", "loop": 14664, "env_steps": 9010175999, "loss": 0.014626759104430676, "avg_return": 0.8650935292243958, "regret": 8.953511132858694e-05, "entropy": 0.06987957656383514, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:31.381598Z", "loop": 14665, "env_steps": 9010790399, "loss": 0.013927452266216278, "avg_return": 0.8638867139816284, "regret": 8.953511132858694e-05, "entropy": 0.06949996948242188, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:32.235579Z", "loop": 14666, "env_steps": 9011404799, "loss": 0.0136641850695014, "avg_return": 0.8623270988464355, "regret": 8.953511132858694e-05, "entropy": 0.07060626149177551, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:33.088693Z", "loop": 14667, "env_steps": 9012019199, "loss": 0.014158193953335285, "avg_return": 0.863939642906189, "regret": 8.953511132858694e-05, "entropy": 0.06710861623287201, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:33.942228Z", "loop": 14668, "env_steps": 9012633599, "loss": 0.013800126500427723, "avg_return": 0.8641849756240845, "regret": 8.953511132858694e-05, "entropy": 0.06834100186824799, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:34.796062Z", "loop": 14669, "env_steps": 9013247999, "loss": 0.014299899339675903, "avg_return": 0.8644974827766418, "regret": 8.953511132858694e-05, "entropy": 0.07017198204994202, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:35.689840Z", "loop": 14670, "env_steps": 9013862399, "loss": 0.013696570880711079, "avg_return": 0.8645188808441162, "regret": 8.266165241366252e-05, "entropy": 0.06778176873922348, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:36.544298Z", "loop": 14671, "env_steps": 9014476799, "loss": 0.013502830639481544, "avg_return": 0.8633769750595093, "regret": 8.266165241366252e-05, "entropy": 0.06802797317504883, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:37.399122Z", "loop": 14672, "env_steps": 9015091199, "loss": 0.014391700737178326, "avg_return": 0.8627497553825378, "regret": 8.266165241366252e-05, "entropy": 0.07036962360143661, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:38.254083Z", "loop": 14673, "env_steps": 9015705599, "loss": 0.013800864107906818, "avg_return": 0.8640631437301636, "regret": 8.266165241366252e-05, "entropy": 0.06974110007286072, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:39.108540Z", "loop": 14674, "env_steps": 9016319999, "loss": 0.013046026229858398, "avg_return": 0.8629704117774963, "regret": 8.266165241366252e-05, "entropy": 0.06462559103965759, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:39.962908Z", "loop": 14675, "env_steps": 9016934399, "loss": 0.013808786869049072, "avg_return": 0.8635280728340149, "regret": 8.266165241366252e-05, "entropy": 0.06888549029827118, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:40.816889Z", "loop": 14676, "env_steps": 9017548799, "loss": 0.014429268427193165, "avg_return": 0.8629475831985474, "regret": 8.266165241366252e-05, "entropy": 0.07089594751596451, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:41.670636Z", "loop": 14677, "env_steps": 9018163199, "loss": 0.014982789754867554, "avg_return": 0.8639450073242188, "regret": 8.266165241366252e-05, "entropy": 0.07306396216154099, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:42.525078Z", "loop": 14678, "env_steps": 9018777599, "loss": 0.014906877651810646, "avg_return": 0.8637638688087463, "regret": 8.266165241366252e-05, "entropy": 0.06948576867580414, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:43.380779Z", "loop": 14679, "env_steps": 9019391999, "loss": 0.014522626996040344, "avg_return": 0.863331139087677, "regret": 8.266165241366252e-05, "entropy": 0.07096734642982483, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:44.274976Z", "loop": 14680, "env_steps": 9020006399, "loss": 0.0152854910120368, "avg_return": 0.8643679022789001, "regret": 0.0001538015203550458, "entropy": 0.07421630620956421, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:45.127703Z", "loop": 14681, "env_steps": 9020620799, "loss": 0.014884027652442455, "avg_return": 0.8639910817146301, "regret": 0.0001538015203550458, "entropy": 0.07341641932725906, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:45.980637Z", "loop": 14682, "env_steps": 9021235199, "loss": 0.014554783701896667, "avg_return": 0.8624485731124878, "regret": 0.0001538015203550458, "entropy": 0.07283048331737518, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:46.835562Z", "loop": 14683, "env_steps": 9021849599, "loss": 0.014996376819908619, "avg_return": 0.863849937915802, "regret": 0.0001538015203550458, "entropy": 0.07336041331291199, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:47.689287Z", "loop": 14684, "env_steps": 9022463999, "loss": 0.01500608678907156, "avg_return": 0.8623809218406677, "regret": 0.0001538015203550458, "entropy": 0.0767291933298111, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:48.542319Z", "loop": 14685, "env_steps": 9023078399, "loss": 0.015379677526652813, "avg_return": 0.8638787269592285, "regret": 0.0001538015203550458, "entropy": 0.07796448469161987, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:49.395460Z", "loop": 14686, "env_steps": 9023692799, "loss": 0.013152641244232655, "avg_return": 0.8634920716285706, "regret": 0.0001538015203550458, "entropy": 0.07044779509305954, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:50.250100Z", "loop": 14687, "env_steps": 9024307199, "loss": 0.01466268952935934, "avg_return": 0.8636841177940369, "regret": 0.0001538015203550458, "entropy": 0.07327362149953842, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:51.104004Z", "loop": 14688, "env_steps": 9024921599, "loss": 0.014360100030899048, "avg_return": 0.8650404810905457, "regret": 0.0001538015203550458, "entropy": 0.06943219900131226, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:51.958318Z", "loop": 14689, "env_steps": 9025535999, "loss": 0.014468756504356861, "avg_return": 0.8630039691925049, "regret": 0.0001538015203550458, "entropy": 0.07037987560033798, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:52.852799Z", "loop": 14690, "env_steps": 9026150399, "loss": 0.013699774630367756, "avg_return": 0.8627288937568665, "regret": 0.0001256842806469649, "entropy": 0.07013481110334396, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:53.712677Z", "loop": 14691, "env_steps": 9026764799, "loss": 0.014088155701756477, "avg_return": 0.8636168837547302, "regret": 0.0001256842806469649, "entropy": 0.068482905626297, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:54.567100Z", "loop": 14692, "env_steps": 9027379199, "loss": 0.014102096669375896, "avg_return": 0.8626350164413452, "regret": 0.0001256842806469649, "entropy": 0.071269690990448, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:55.421591Z", "loop": 14693, "env_steps": 9027993599, "loss": 0.014461985789239407, "avg_return": 0.8626684546470642, "regret": 0.0001256842806469649, "entropy": 0.07318109273910522, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:56.275409Z", "loop": 14694, "env_steps": 9028607999, "loss": 0.01318348478525877, "avg_return": 0.8634842038154602, "regret": 0.0001256842806469649, "entropy": 0.06986214965581894, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:57.129664Z", "loop": 14695, "env_steps": 9029222399, "loss": 0.013411441817879677, "avg_return": 0.8629268407821655, "regret": 0.0001256842806469649, "entropy": 0.0690336599946022, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:57.983768Z", "loop": 14696, "env_steps": 9029836799, "loss": 0.013289994560182095, "avg_return": 0.8632672429084778, "regret": 0.0001256842806469649, "entropy": 0.06538162380456924, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:58.837338Z", "loop": 14697, "env_steps": 9030451199, "loss": 0.012792023830115795, "avg_return": 0.8631138205528259, "regret": 0.0001256842806469649, "entropy": 0.06883148849010468, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:53:59.692044Z", "loop": 14698, "env_steps": 9031065599, "loss": 0.012823973782360554, "avg_return": 0.8632981777191162, "regret": 0.0001256842806469649, "entropy": 0.06805124133825302, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:00.545274Z", "loop": 14699, "env_steps": 9031679999, "loss": 0.013381934724748135, "avg_return": 0.8635807633399963, "regret": 0.0001256842806469649, "entropy": 0.06617236882448196, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:01.439562Z", "loop": 14700, "env_steps": 9032294399, "loss": 0.014671641401946545, "avg_return": 0.862687885761261, "regret": 7.738724525552243e-05, "entropy": 0.06884045898914337, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:02.293820Z", "loop": 14701, "env_steps": 9032908799, "loss": 0.013515365310013294, "avg_return": 0.8643032908439636, "regret": 7.738724525552243e-05, "entropy": 0.06523948907852173, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:03.149131Z", "loop": 14702, "env_steps": 9033523199, "loss": 0.014430887997150421, "avg_return": 0.86369389295578, "regret": 7.738724525552243e-05, "entropy": 0.07151714712381363, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:04.003823Z", "loop": 14703, "env_steps": 9034137599, "loss": 0.01422086264938116, "avg_return": 0.8627444505691528, "regret": 7.738724525552243e-05, "entropy": 0.06756263226270676, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:04.857794Z", "loop": 14704, "env_steps": 9034751999, "loss": 0.015173785388469696, "avg_return": 0.8621415495872498, "regret": 7.738724525552243e-05, "entropy": 0.07196167856454849, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:05.711703Z", "loop": 14705, "env_steps": 9035366399, "loss": 0.014902794733643532, "avg_return": 0.8613148927688599, "regret": 7.738724525552243e-05, "entropy": 0.07107818126678467, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:06.566068Z", "loop": 14706, "env_steps": 9035980799, "loss": 0.014896610751748085, "avg_return": 0.8617509007453918, "regret": 7.738724525552243e-05, "entropy": 0.07296852022409439, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:07.421104Z", "loop": 14707, "env_steps": 9036595199, "loss": 0.01584911346435547, "avg_return": 0.8613265156745911, "regret": 7.738724525552243e-05, "entropy": 0.07520975172519684, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:08.274972Z", "loop": 14708, "env_steps": 9037209599, "loss": 0.014352980069816113, "avg_return": 0.8611461520195007, "regret": 7.738724525552243e-05, "entropy": 0.07225017994642258, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:09.128774Z", "loop": 14709, "env_steps": 9037823999, "loss": 0.014564486220479012, "avg_return": 0.8621764183044434, "regret": 7.738724525552243e-05, "entropy": 0.07268549501895905, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:10.023191Z", "loop": 14710, "env_steps": 9038438399, "loss": 0.01379937119781971, "avg_return": 0.8627530932426453, "regret": 0.0010090229334309697, "entropy": 0.06427335739135742, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:10.878723Z", "loop": 14711, "env_steps": 9039052799, "loss": 0.012885845266282558, "avg_return": 0.8631265759468079, "regret": 0.0010090229334309697, "entropy": 0.06420085579156876, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:11.732622Z", "loop": 14712, "env_steps": 9039667199, "loss": 0.01251392811536789, "avg_return": 0.8630287647247314, "regret": 0.0010090229334309697, "entropy": 0.06274604797363281, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:12.587050Z", "loop": 14713, "env_steps": 9040281599, "loss": 0.013168330304324627, "avg_return": 0.8637948036193848, "regret": 0.0010090229334309697, "entropy": 0.06616862863302231, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:13.442128Z", "loop": 14714, "env_steps": 9040895999, "loss": 0.012822389602661133, "avg_return": 0.8625748157501221, "regret": 0.0010090229334309697, "entropy": 0.0625380128622055, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:14.296546Z", "loop": 14715, "env_steps": 9041510399, "loss": 0.012471694499254227, "avg_return": 0.8628990054130554, "regret": 0.0010090229334309697, "entropy": 0.06136725842952728, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:15.150452Z", "loop": 14716, "env_steps": 9042124799, "loss": 0.012955470941960812, "avg_return": 0.8623002171516418, "regret": 0.0010090229334309697, "entropy": 0.066399946808815, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:16.003961Z", "loop": 14717, "env_steps": 9042739199, "loss": 0.011886962689459324, "avg_return": 0.8626905679702759, "regret": 0.0010090229334309697, "entropy": 0.0629020631313324, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:16.857494Z", "loop": 14718, "env_steps": 9043353599, "loss": 0.013538985513150692, "avg_return": 0.8629918694496155, "regret": 0.0010090229334309697, "entropy": 0.06728258728981018, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:17.711058Z", "loop": 14719, "env_steps": 9043967999, "loss": 0.012742948718369007, "avg_return": 0.8626866936683655, "regret": 0.0010090229334309697, "entropy": 0.06557046622037888, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:18.604367Z", "loop": 14720, "env_steps": 9044582399, "loss": 0.013560468330979347, "avg_return": 0.863166332244873, "regret": 0.0006174013251438737, "entropy": 0.0674537867307663, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:19.458647Z", "loop": 14721, "env_steps": 9045196799, "loss": 0.01302273478358984, "avg_return": 0.8634887933731079, "regret": 0.0006174013251438737, "entropy": 0.06501348316669464, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:20.312779Z", "loop": 14722, "env_steps": 9045811199, "loss": 0.012849262915551662, "avg_return": 0.8632954359054565, "regret": 0.0006174013251438737, "entropy": 0.06401170790195465, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:21.166549Z", "loop": 14723, "env_steps": 9046425599, "loss": 0.013567375019192696, "avg_return": 0.8621231317520142, "regret": 0.0006174013251438737, "entropy": 0.06965998560190201, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:22.020967Z", "loop": 14724, "env_steps": 9047039999, "loss": 0.01400233805179596, "avg_return": 0.862288236618042, "regret": 0.0006174013251438737, "entropy": 0.06815865635871887, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:22.875291Z", "loop": 14725, "env_steps": 9047654399, "loss": 0.014874609187245369, "avg_return": 0.8627728223800659, "regret": 0.0006174013251438737, "entropy": 0.07390683144330978, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:23.729976Z", "loop": 14726, "env_steps": 9048268799, "loss": 0.015339580364525318, "avg_return": 0.8622096180915833, "regret": 0.0006174013251438737, "entropy": 0.07367036491632462, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:24.584194Z", "loop": 14727, "env_steps": 9048883199, "loss": 0.015980560332536697, "avg_return": 0.8621557950973511, "regret": 0.0006174013251438737, "entropy": 0.0765451118350029, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:25.438841Z", "loop": 14728, "env_steps": 9049497599, "loss": 0.015002943575382233, "avg_return": 0.863688588142395, "regret": 0.0006174013251438737, "entropy": 0.0720885619521141, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:26.293900Z", "loop": 14729, "env_steps": 9050111999, "loss": 0.015244235284626484, "avg_return": 0.8617852926254272, "regret": 0.0006174013251438737, "entropy": 0.07289164513349533, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:27.191704Z", "loop": 14730, "env_steps": 9050726399, "loss": 0.014391972683370113, "avg_return": 0.8645672798156738, "regret": 0.0007520184153690934, "entropy": 0.07329298555850983, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:28.045578Z", "loop": 14731, "env_steps": 9051340799, "loss": 0.01482668798416853, "avg_return": 0.8628438711166382, "regret": 0.0007520184153690934, "entropy": 0.07058554887771606, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:28.898760Z", "loop": 14732, "env_steps": 9051955199, "loss": 0.015118040144443512, "avg_return": 0.8635779023170471, "regret": 0.0007520184153690934, "entropy": 0.07298988103866577, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:29.754266Z", "loop": 14733, "env_steps": 9052569599, "loss": 0.014360352419316769, "avg_return": 0.8634581565856934, "regret": 0.0007520184153690934, "entropy": 0.0718090757727623, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:30.609705Z", "loop": 14734, "env_steps": 9053183999, "loss": 0.014382815919816494, "avg_return": 0.8631772994995117, "regret": 0.0007520184153690934, "entropy": 0.07097474485635757, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:31.463275Z", "loop": 14735, "env_steps": 9053798399, "loss": 0.014234921894967556, "avg_return": 0.8631843328475952, "regret": 0.0007520184153690934, "entropy": 0.07013605535030365, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:32.317824Z", "loop": 14736, "env_steps": 9054412799, "loss": 0.014685024507343769, "avg_return": 0.8614692091941833, "regret": 0.0007520184153690934, "entropy": 0.07267696410417557, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:33.173130Z", "loop": 14737, "env_steps": 9055027199, "loss": 0.014890819787979126, "avg_return": 0.8609045743942261, "regret": 0.0007520184153690934, "entropy": 0.07409223169088364, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:34.027756Z", "loop": 14738, "env_steps": 9055641599, "loss": 0.014435607008635998, "avg_return": 0.8622497916221619, "regret": 0.0007520184153690934, "entropy": 0.07277722656726837, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:34.880914Z", "loop": 14739, "env_steps": 9056255999, "loss": 0.01590205542743206, "avg_return": 0.862358033657074, "regret": 0.0007520184153690934, "entropy": 0.07376417517662048, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:35.772311Z", "loop": 14740, "env_steps": 9056870399, "loss": 0.014544330537319183, "avg_return": 0.8627380728721619, "regret": 0.0012960819294676185, "entropy": 0.0725487545132637, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:36.627033Z", "loop": 14741, "env_steps": 9057484799, "loss": 0.015038929879665375, "avg_return": 0.8619629144668579, "regret": 0.0012960819294676185, "entropy": 0.07474494725465775, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:37.482555Z", "loop": 14742, "env_steps": 9058099199, "loss": 0.014664431102573872, "avg_return": 0.8629283905029297, "regret": 0.0012960819294676185, "entropy": 0.07066504657268524, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:38.337121Z", "loop": 14743, "env_steps": 9058713599, "loss": 0.012436982244253159, "avg_return": 0.864237368106842, "regret": 0.0012960819294676185, "entropy": 0.0642424151301384, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:39.192035Z", "loop": 14744, "env_steps": 9059327999, "loss": 0.011982622556388378, "avg_return": 0.8635456562042236, "regret": 0.0012960819294676185, "entropy": 0.06494885683059692, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:40.046252Z", "loop": 14745, "env_steps": 9059942399, "loss": 0.013412544503808022, "avg_return": 0.8626553416252136, "regret": 0.0012960819294676185, "entropy": 0.0660393014550209, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:40.900107Z", "loop": 14746, "env_steps": 9060556799, "loss": 0.012923285365104675, "avg_return": 0.8617082834243774, "regret": 0.0012960819294676185, "entropy": 0.06630384922027588, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:41.753570Z", "loop": 14747, "env_steps": 9061171199, "loss": 0.01286990474909544, "avg_return": 0.8613628149032593, "regret": 0.0012960819294676185, "entropy": 0.06537588685750961, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:42.607110Z", "loop": 14748, "env_steps": 9061785599, "loss": 0.01464302558451891, "avg_return": 0.8630147576332092, "regret": 0.0012960819294676185, "entropy": 0.06977228075265884, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:43.460422Z", "loop": 14749, "env_steps": 9062399999, "loss": 0.014701065607368946, "avg_return": 0.8617810010910034, "regret": 0.0012960819294676185, "entropy": 0.07115906476974487, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:44.353842Z", "loop": 14750, "env_steps": 9063014399, "loss": 0.01512987818568945, "avg_return": 0.8641347289085388, "regret": 0.0005553559167310596, "entropy": 0.07490776479244232, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:45.207979Z", "loop": 14751, "env_steps": 9063628799, "loss": 0.014924215152859688, "avg_return": 0.8628562688827515, "regret": 0.0005553559167310596, "entropy": 0.07105907052755356, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:46.062962Z", "loop": 14752, "env_steps": 9064243199, "loss": 0.015205278061330318, "avg_return": 0.863260805606842, "regret": 0.0005553559167310596, "entropy": 0.07227960973978043, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:46.917199Z", "loop": 14753, "env_steps": 9064857599, "loss": 0.014436358585953712, "avg_return": 0.8630654215812683, "regret": 0.0005553559167310596, "entropy": 0.07200591266155243, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:47.771879Z", "loop": 14754, "env_steps": 9065471999, "loss": 0.014524327591061592, "avg_return": 0.8626977801322937, "regret": 0.0005553559167310596, "entropy": 0.07084272056818008, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:48.627130Z", "loop": 14755, "env_steps": 9066086399, "loss": 0.01389263290911913, "avg_return": 0.8615598678588867, "regret": 0.0005553559167310596, "entropy": 0.06713459640741348, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:49.482080Z", "loop": 14756, "env_steps": 9066700799, "loss": 0.015278147533535957, "avg_return": 0.8619565963745117, "regret": 0.0005553559167310596, "entropy": 0.07316648215055466, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:50.338411Z", "loop": 14757, "env_steps": 9067315199, "loss": 0.016303403303027153, "avg_return": 0.8624277710914612, "regret": 0.0005553559167310596, "entropy": 0.0779617577791214, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:51.193011Z", "loop": 14758, "env_steps": 9067929599, "loss": 0.01916978321969509, "avg_return": 0.8619748950004578, "regret": 0.0005553559167310596, "entropy": 0.08790691941976547, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:52.047983Z", "loop": 14759, "env_steps": 9068543999, "loss": 0.01687893643975258, "avg_return": 0.8630573749542236, "regret": 0.0005553559167310596, "entropy": 0.08254993706941605, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:52.942011Z", "loop": 14760, "env_steps": 9069158399, "loss": 0.01551771629601717, "avg_return": 0.8626777529716492, "regret": 0.001091807964257896, "entropy": 0.07662411034107208, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:53.796430Z", "loop": 14761, "env_steps": 9069772799, "loss": 0.014882064424455166, "avg_return": 0.8614845871925354, "regret": 0.001091807964257896, "entropy": 0.07117397338151932, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:54.650826Z", "loop": 14762, "env_steps": 9070387199, "loss": 0.013927034102380276, "avg_return": 0.8622252345085144, "regret": 0.001091807964257896, "entropy": 0.06899440288543701, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:55.503662Z", "loop": 14763, "env_steps": 9071001599, "loss": 0.013749266974627972, "avg_return": 0.8637040257453918, "regret": 0.001091807964257896, "entropy": 0.07107310742139816, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:56.356595Z", "loop": 14764, "env_steps": 9071615999, "loss": 0.014325263909995556, "avg_return": 0.8634331226348877, "regret": 0.001091807964257896, "entropy": 0.07337503135204315, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:57.210330Z", "loop": 14765, "env_steps": 9072230399, "loss": 0.013423464260995388, "avg_return": 0.8621673583984375, "regret": 0.001091807964257896, "entropy": 0.06789898127317429, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:58.064114Z", "loop": 14766, "env_steps": 9072844799, "loss": 0.012747841887176037, "avg_return": 0.8609784245491028, "regret": 0.001091807964257896, "entropy": 0.06543700397014618, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:58.916932Z", "loop": 14767, "env_steps": 9073459199, "loss": 0.014318457804620266, "avg_return": 0.8635284900665283, "regret": 0.001091807964257896, "entropy": 0.07079672813415527, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:54:59.769704Z", "loop": 14768, "env_steps": 9074073599, "loss": 0.014745748601853848, "avg_return": 0.8621297478675842, "regret": 0.001091807964257896, "entropy": 0.07035960257053375, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:00.623497Z", "loop": 14769, "env_steps": 9074687999, "loss": 0.014030742458999157, "avg_return": 0.8600341081619263, "regret": 0.001091807964257896, "entropy": 0.07290312647819519, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:01.518439Z", "loop": 14770, "env_steps": 9075302399, "loss": 0.014937631785869598, "avg_return": 0.8594267964363098, "regret": 0.0035935291089117527, "entropy": 0.07789498567581177, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:02.372708Z", "loop": 14771, "env_steps": 9075916799, "loss": 0.015230193734169006, "avg_return": 0.8598945140838623, "regret": 0.0035935291089117527, "entropy": 0.07692912220954895, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:03.228630Z", "loop": 14772, "env_steps": 9076531199, "loss": 0.014363124035298824, "avg_return": 0.8606883883476257, "regret": 0.0035935291089117527, "entropy": 0.07294902950525284, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:04.084136Z", "loop": 14773, "env_steps": 9077145599, "loss": 0.013606460765004158, "avg_return": 0.861911416053772, "regret": 0.0035935291089117527, "entropy": 0.07309218496084213, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:04.938906Z", "loop": 14774, "env_steps": 9077759999, "loss": 0.013988465070724487, "avg_return": 0.8619112372398376, "regret": 0.0035935291089117527, "entropy": 0.06953020393848419, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:05.792787Z", "loop": 14775, "env_steps": 9078374399, "loss": 0.013824911788105965, "avg_return": 0.8623871803283691, "regret": 0.0035935291089117527, "entropy": 0.06802235543727875, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:06.646315Z", "loop": 14776, "env_steps": 9078988799, "loss": 0.014253849163651466, "avg_return": 0.8628231287002563, "regret": 0.0035935291089117527, "entropy": 0.06876962631940842, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:07.501591Z", "loop": 14777, "env_steps": 9079603199, "loss": 0.013897429220378399, "avg_return": 0.8619592785835266, "regret": 0.0035935291089117527, "entropy": 0.06865457445383072, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:08.355329Z", "loop": 14778, "env_steps": 9080217599, "loss": 0.015240817330777645, "avg_return": 0.8639184832572937, "regret": 0.0035935291089117527, "entropy": 0.06983084976673126, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:09.210313Z", "loop": 14779, "env_steps": 9080831999, "loss": 0.014591542072594166, "avg_return": 0.8642425537109375, "regret": 0.0035935291089117527, "entropy": 0.0726790502667427, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:10.103892Z", "loop": 14780, "env_steps": 9081446399, "loss": 0.015040712431073189, "avg_return": 0.862739086151123, "regret": 0.0003294455527793616, "entropy": 0.07507161796092987, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:10.958518Z", "loop": 14781, "env_steps": 9082060799, "loss": 0.015353395603597164, "avg_return": 0.864447832107544, "regret": 0.0003294455527793616, "entropy": 0.07478804886341095, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:11.812152Z", "loop": 14782, "env_steps": 9082675199, "loss": 0.015478107146918774, "avg_return": 0.8630021214485168, "regret": 0.0003294455527793616, "entropy": 0.07641308754682541, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:12.667340Z", "loop": 14783, "env_steps": 9083289599, "loss": 0.017207680270075798, "avg_return": 0.8631842136383057, "regret": 0.0003294455527793616, "entropy": 0.07965083420276642, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:13.522907Z", "loop": 14784, "env_steps": 9083903999, "loss": 0.017196403816342354, "avg_return": 0.8638655543327332, "regret": 0.0003294455527793616, "entropy": 0.08069277554750443, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:14.378471Z", "loop": 14785, "env_steps": 9084518399, "loss": 0.016485219821333885, "avg_return": 0.8645890355110168, "regret": 0.0003294455527793616, "entropy": 0.07830850780010223, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:15.233063Z", "loop": 14786, "env_steps": 9085132799, "loss": 0.015234941616654396, "avg_return": 0.8631783127784729, "regret": 0.0003294455527793616, "entropy": 0.07342677563428879, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:16.087599Z", "loop": 14787, "env_steps": 9085747199, "loss": 0.01324579119682312, "avg_return": 0.8618506193161011, "regret": 0.0003294455527793616, "entropy": 0.06688932329416275, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:16.941778Z", "loop": 14788, "env_steps": 9086361599, "loss": 0.013873383402824402, "avg_return": 0.8623338937759399, "regret": 0.0003294455527793616, "entropy": 0.06624803692102432, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:17.796468Z", "loop": 14789, "env_steps": 9086975999, "loss": 0.01358777191489935, "avg_return": 0.8642137050628662, "regret": 0.0003294455527793616, "entropy": 0.06618180871009827, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:18.689982Z", "loop": 14790, "env_steps": 9087590399, "loss": 0.013036409392952919, "avg_return": 0.8638391494750977, "regret": 0.00025904917856678367, "entropy": 0.0659150630235672, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:19.543828Z", "loop": 14791, "env_steps": 9088204799, "loss": 0.013021528720855713, "avg_return": 0.8628175258636475, "regret": 0.00025904917856678367, "entropy": 0.06259801238775253, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:20.398741Z", "loop": 14792, "env_steps": 9088819199, "loss": 0.01288424152880907, "avg_return": 0.8640198707580566, "regret": 0.00025904917856678367, "entropy": 0.0634370744228363, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:21.252986Z", "loop": 14793, "env_steps": 9089433599, "loss": 0.012995565310120583, "avg_return": 0.863277792930603, "regret": 0.00025904917856678367, "entropy": 0.06821700930595398, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:22.108187Z", "loop": 14794, "env_steps": 9090047999, "loss": 0.012561787851154804, "avg_return": 0.8631438612937927, "regret": 0.00025904917856678367, "entropy": 0.06666362285614014, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:22.962286Z", "loop": 14795, "env_steps": 9090662399, "loss": 0.012726311571896076, "avg_return": 0.8633341789245605, "regret": 0.00025904917856678367, "entropy": 0.06481359153985977, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:23.818054Z", "loop": 14796, "env_steps": 9091276799, "loss": 0.011997374705970287, "avg_return": 0.8623265624046326, "regret": 0.00025904917856678367, "entropy": 0.06284628063440323, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:24.672921Z", "loop": 14797, "env_steps": 9091891199, "loss": 0.011972244828939438, "avg_return": 0.86285400390625, "regret": 0.00025904917856678367, "entropy": 0.06083378195762634, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:25.527595Z", "loop": 14798, "env_steps": 9092505599, "loss": 0.011462396942079067, "avg_return": 0.8620700240135193, "regret": 0.00025904917856678367, "entropy": 0.06274787336587906, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:26.381377Z", "loop": 14799, "env_steps": 9093119999, "loss": 0.011769390664994717, "avg_return": 0.860614538192749, "regret": 0.00025904917856678367, "entropy": 0.06220553070306778, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:27.275437Z", "loop": 14800, "env_steps": 9093734399, "loss": 0.013037269003689289, "avg_return": 0.8597099184989929, "regret": 0.0035537071526050568, "entropy": 0.06810140609741211, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:28.130782Z", "loop": 14801, "env_steps": 9094348799, "loss": 0.014209854416549206, "avg_return": 0.8584051728248596, "regret": 0.0035537071526050568, "entropy": 0.07227121293544769, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:28.985006Z", "loop": 14802, "env_steps": 9094963199, "loss": 0.013487945310771465, "avg_return": 0.85898357629776, "regret": 0.0035537071526050568, "entropy": 0.07275974005460739, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:29.839528Z", "loop": 14803, "env_steps": 9095577599, "loss": 0.012669213116168976, "avg_return": 0.8600872159004211, "regret": 0.0035537071526050568, "entropy": 0.07063101977109909, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:30.693011Z", "loop": 14804, "env_steps": 9096191999, "loss": 0.011458848603069782, "avg_return": 0.8581050038337708, "regret": 0.0035537071526050568, "entropy": 0.06693322211503983, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:31.546138Z", "loop": 14805, "env_steps": 9096806399, "loss": 0.012217997573316097, "avg_return": 0.8595945239067078, "regret": 0.0035537071526050568, "entropy": 0.067315474152565, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:32.399799Z", "loop": 14806, "env_steps": 9097420799, "loss": 0.01268193032592535, "avg_return": 0.8579235076904297, "regret": 0.0035537071526050568, "entropy": 0.06763243675231934, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:33.254270Z", "loop": 14807, "env_steps": 9098035199, "loss": 0.012475494295358658, "avg_return": 0.8584577441215515, "regret": 0.0035537071526050568, "entropy": 0.06553708016872406, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:34.107402Z", "loop": 14808, "env_steps": 9098649599, "loss": 0.012670177035033703, "avg_return": 0.8598764538764954, "regret": 0.0035537071526050568, "entropy": 0.06479714810848236, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:34.960863Z", "loop": 14809, "env_steps": 9099263999, "loss": 0.011868863366544247, "avg_return": 0.859809160232544, "regret": 0.0035537071526050568, "entropy": 0.06544443219900131, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:35.855983Z", "loop": 14810, "env_steps": 9099878399, "loss": 0.010839059017598629, "avg_return": 0.860535204410553, "regret": 0.002810309873893857, "entropy": 0.061548203229904175, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:36.711275Z", "loop": 14811, "env_steps": 9100492799, "loss": 0.010476703755557537, "avg_return": 0.8623736500740051, "regret": 0.002810309873893857, "entropy": 0.05584879219532013, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:37.565332Z", "loop": 14812, "env_steps": 9101107199, "loss": 0.010283435694873333, "avg_return": 0.8620021939277649, "regret": 0.002810309873893857, "entropy": 0.054378870874643326, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:38.419735Z", "loop": 14813, "env_steps": 9101721599, "loss": 0.01087106205523014, "avg_return": 0.8626777529716492, "regret": 0.002810309873893857, "entropy": 0.059855345636606216, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:39.274247Z", "loop": 14814, "env_steps": 9102335999, "loss": 0.010927892290055752, "avg_return": 0.8617498874664307, "regret": 0.002810309873893857, "entropy": 0.057408422231674194, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:40.129229Z", "loop": 14815, "env_steps": 9102950399, "loss": 0.011019384488463402, "avg_return": 0.8619541525840759, "regret": 0.002810309873893857, "entropy": 0.05630730465054512, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:40.984560Z", "loop": 14816, "env_steps": 9103564799, "loss": 0.01067084725946188, "avg_return": 0.8638309836387634, "regret": 0.002810309873893857, "entropy": 0.0602334663271904, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:41.840530Z", "loop": 14817, "env_steps": 9104179199, "loss": 0.011196555569767952, "avg_return": 0.8624631762504578, "regret": 0.002810309873893857, "entropy": 0.0578552670776844, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:42.694669Z", "loop": 14818, "env_steps": 9104793599, "loss": 0.012029314413666725, "avg_return": 0.8628542423248291, "regret": 0.002810309873893857, "entropy": 0.06214595213532448, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:43.549591Z", "loop": 14819, "env_steps": 9105407999, "loss": 0.010970047675073147, "avg_return": 0.8650420308113098, "regret": 0.002810309873893857, "entropy": 0.05653272941708565, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:44.444846Z", "loop": 14820, "env_steps": 9106022399, "loss": 0.010867824777960777, "avg_return": 0.8621048927307129, "regret": 0.000537042273208499, "entropy": 0.057710547000169754, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:45.300035Z", "loop": 14821, "env_steps": 9106636799, "loss": 0.011283463798463345, "avg_return": 0.8635398745536804, "regret": 0.000537042273208499, "entropy": 0.06172800809144974, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:46.153650Z", "loop": 14822, "env_steps": 9107251199, "loss": 0.011358694173395634, "avg_return": 0.8642051219940186, "regret": 0.000537042273208499, "entropy": 0.05783476307988167, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:47.007944Z", "loop": 14823, "env_steps": 9107865599, "loss": 0.010887081734836102, "avg_return": 0.8640352487564087, "regret": 0.000537042273208499, "entropy": 0.05866774544119835, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:47.862833Z", "loop": 14824, "env_steps": 9108479999, "loss": 0.011536064557731152, "avg_return": 0.8629117012023926, "regret": 0.000537042273208499, "entropy": 0.05862179026007652, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:48.717812Z", "loop": 14825, "env_steps": 9109094399, "loss": 0.010640440508723259, "avg_return": 0.8624148964881897, "regret": 0.000537042273208499, "entropy": 0.0559212863445282, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:49.572321Z", "loop": 14826, "env_steps": 9109708799, "loss": 0.011434557847678661, "avg_return": 0.8639740347862244, "regret": 0.000537042273208499, "entropy": 0.06050499901175499, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:50.426306Z", "loop": 14827, "env_steps": 9110323199, "loss": 0.01204799022525549, "avg_return": 0.8636528849601746, "regret": 0.000537042273208499, "entropy": 0.06284255534410477, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:51.280811Z", "loop": 14828, "env_steps": 9110937599, "loss": 0.013089710846543312, "avg_return": 0.863582193851471, "regret": 0.000537042273208499, "entropy": 0.06386761367321014, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:52.135265Z", "loop": 14829, "env_steps": 9111551999, "loss": 0.01095456164330244, "avg_return": 0.864108681678772, "regret": 0.000537042273208499, "entropy": 0.057501211762428284, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:53.028373Z", "loop": 14830, "env_steps": 9112166399, "loss": 0.010930544696748257, "avg_return": 0.8632681369781494, "regret": 0.00018839197582565248, "entropy": 0.06170308217406273, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:53.883964Z", "loop": 14831, "env_steps": 9112780799, "loss": 0.013151365332305431, "avg_return": 0.8642401099205017, "regret": 0.00018839197582565248, "entropy": 0.06617732346057892, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:54.738290Z", "loop": 14832, "env_steps": 9113395199, "loss": 0.012544496916234493, "avg_return": 0.8630183339118958, "regret": 0.00018839197582565248, "entropy": 0.06264124065637589, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:55.592543Z", "loop": 14833, "env_steps": 9114009599, "loss": 0.011832041665911674, "avg_return": 0.86286461353302, "regret": 0.00018839197582565248, "entropy": 0.0636836364865303, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:56.447080Z", "loop": 14834, "env_steps": 9114623999, "loss": 0.01167608704417944, "avg_return": 0.8638160228729248, "regret": 0.00018839197582565248, "entropy": 0.06380867213010788, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:57.300997Z", "loop": 14835, "env_steps": 9115238399, "loss": 0.01069901417940855, "avg_return": 0.8628416061401367, "regret": 0.00018839197582565248, "entropy": 0.05962172895669937, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:58.155593Z", "loop": 14836, "env_steps": 9115852799, "loss": 0.012288232333958149, "avg_return": 0.8622778654098511, "regret": 0.00018839197582565248, "entropy": 0.0611601360142231, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:59.010805Z", "loop": 14837, "env_steps": 9116467199, "loss": 0.01187332533299923, "avg_return": 0.863693356513977, "regret": 0.00018839197582565248, "entropy": 0.06131305173039436, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:55:59.865044Z", "loop": 14838, "env_steps": 9117081599, "loss": 0.011215617880225182, "avg_return": 0.8644376993179321, "regret": 0.00018839197582565248, "entropy": 0.060271237045526505, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:00.719650Z", "loop": 14839, "env_steps": 9117695999, "loss": 0.01173479575663805, "avg_return": 0.862683117389679, "regret": 0.00018839197582565248, "entropy": 0.0642673671245575, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:01.615012Z", "loop": 14840, "env_steps": 9118310399, "loss": 0.01160353235900402, "avg_return": 0.8630815744400024, "regret": 0.00022155723127070814, "entropy": 0.0638643205165863, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:02.469849Z", "loop": 14841, "env_steps": 9118924799, "loss": 0.012559287250041962, "avg_return": 0.8641842603683472, "regret": 0.00022155723127070814, "entropy": 0.06263547390699387, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:03.325302Z", "loop": 14842, "env_steps": 9119539199, "loss": 0.012683192268013954, "avg_return": 0.8640156388282776, "regret": 0.00022155723127070814, "entropy": 0.06286771595478058, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:04.182102Z", "loop": 14843, "env_steps": 9120153599, "loss": 0.011797945015132427, "avg_return": 0.8619241714477539, "regret": 0.00022155723127070814, "entropy": 0.06437521427869797, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:05.037910Z", "loop": 14844, "env_steps": 9120767999, "loss": 0.012181350030004978, "avg_return": 0.8634775876998901, "regret": 0.00022155723127070814, "entropy": 0.0632086917757988, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:05.894104Z", "loop": 14845, "env_steps": 9121382399, "loss": 0.01258269976824522, "avg_return": 0.8630210757255554, "regret": 0.00022155723127070814, "entropy": 0.06592942774295807, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:06.749820Z", "loop": 14846, "env_steps": 9121996799, "loss": 0.011417238973081112, "avg_return": 0.8636953830718994, "regret": 0.00022155723127070814, "entropy": 0.059831321239471436, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:07.605216Z", "loop": 14847, "env_steps": 9122611199, "loss": 0.012129719369113445, "avg_return": 0.8634265065193176, "regret": 0.00022155723127070814, "entropy": 0.06068522483110428, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:08.460627Z", "loop": 14848, "env_steps": 9123225599, "loss": 0.011648246087133884, "avg_return": 0.8626121282577515, "regret": 0.00022155723127070814, "entropy": 0.06173726171255112, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:09.316715Z", "loop": 14849, "env_steps": 9123839999, "loss": 0.01166741456836462, "avg_return": 0.8628820180892944, "regret": 0.00022155723127070814, "entropy": 0.06561589986085892, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:10.213051Z", "loop": 14850, "env_steps": 9124454399, "loss": 0.012726048938930035, "avg_return": 0.8637024164199829, "regret": 0.00039812721661292017, "entropy": 0.06609036773443222, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:11.068925Z", "loop": 14851, "env_steps": 9125068799, "loss": 0.011959313414990902, "avg_return": 0.86224764585495, "regret": 0.00039812721661292017, "entropy": 0.06360742449760437, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:11.924532Z", "loop": 14852, "env_steps": 9125683199, "loss": 0.012309848330914974, "avg_return": 0.8632219433784485, "regret": 0.00039812721661292017, "entropy": 0.0642894059419632, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:12.779628Z", "loop": 14853, "env_steps": 9126297599, "loss": 0.011836891062557697, "avg_return": 0.8638979196548462, "regret": 0.00039812721661292017, "entropy": 0.06394857168197632, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:13.635029Z", "loop": 14854, "env_steps": 9126911999, "loss": 0.012180602177977562, "avg_return": 0.8616172671318054, "regret": 0.00039812721661292017, "entropy": 0.06407210975885391, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:14.490274Z", "loop": 14855, "env_steps": 9127526399, "loss": 0.012097402475774288, "avg_return": 0.8634241223335266, "regret": 0.00039812721661292017, "entropy": 0.06320971995592117, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:15.344653Z", "loop": 14856, "env_steps": 9128140799, "loss": 0.012556763365864754, "avg_return": 0.8647688031196594, "regret": 0.00039812721661292017, "entropy": 0.06676870584487915, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:16.202149Z", "loop": 14857, "env_steps": 9128755199, "loss": 0.012840828858315945, "avg_return": 0.8638430237770081, "regret": 0.00039812721661292017, "entropy": 0.06691686809062958, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:17.056914Z", "loop": 14858, "env_steps": 9129369599, "loss": 0.013744938187301159, "avg_return": 0.8627033829689026, "regret": 0.00039812721661292017, "entropy": 0.0675867423415184, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:17.911957Z", "loop": 14859, "env_steps": 9129983999, "loss": 0.012776161544024944, "avg_return": 0.8642812371253967, "regret": 0.00039812721661292017, "entropy": 0.06722504645586014, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:18.807971Z", "loop": 14860, "env_steps": 9130598399, "loss": 0.01299378927797079, "avg_return": 0.8628489375114441, "regret": 0.00027201996999792755, "entropy": 0.06697683781385422, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:19.663108Z", "loop": 14861, "env_steps": 9131212799, "loss": 0.014592726714909077, "avg_return": 0.862968385219574, "regret": 0.00027201996999792755, "entropy": 0.07363007962703705, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:20.517882Z", "loop": 14862, "env_steps": 9131827199, "loss": 0.014604915864765644, "avg_return": 0.8633117079734802, "regret": 0.00027201996999792755, "entropy": 0.07463008910417557, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:21.373093Z", "loop": 14863, "env_steps": 9132441599, "loss": 0.014945427887141705, "avg_return": 0.8630310297012329, "regret": 0.00027201996999792755, "entropy": 0.07345982640981674, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:22.228427Z", "loop": 14864, "env_steps": 9133055999, "loss": 0.01437748409807682, "avg_return": 0.8626711368560791, "regret": 0.00027201996999792755, "entropy": 0.07555101066827774, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:23.090124Z", "loop": 14865, "env_steps": 9133670399, "loss": 0.014502410776913166, "avg_return": 0.864027738571167, "regret": 0.00027201996999792755, "entropy": 0.07313387840986252, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:23.950506Z", "loop": 14866, "env_steps": 9134284799, "loss": 0.014687477611005306, "avg_return": 0.8629370331764221, "regret": 0.00027201996999792755, "entropy": 0.0754823237657547, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:24.805112Z", "loop": 14867, "env_steps": 9134899199, "loss": 0.014499952085316181, "avg_return": 0.8640611171722412, "regret": 0.00027201996999792755, "entropy": 0.07445582002401352, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:25.657907Z", "loop": 14868, "env_steps": 9135513599, "loss": 0.01431052666157484, "avg_return": 0.8640788197517395, "regret": 0.00027201996999792755, "entropy": 0.07012055814266205, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:26.511114Z", "loop": 14869, "env_steps": 9136127999, "loss": 0.01462602149695158, "avg_return": 0.8633207678794861, "regret": 0.00027201996999792755, "entropy": 0.07112661749124527, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:27.404571Z", "loop": 14870, "env_steps": 9136742399, "loss": 0.01203584298491478, "avg_return": 0.8624070286750793, "regret": 0.00020562225836329162, "entropy": 0.0662120059132576, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:28.258883Z", "loop": 14871, "env_steps": 9137356799, "loss": 0.011818910948932171, "avg_return": 0.8630924820899963, "regret": 0.00020562225836329162, "entropy": 0.06220448389649391, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:29.113301Z", "loop": 14872, "env_steps": 9137971199, "loss": 0.011520249769091606, "avg_return": 0.8633440136909485, "regret": 0.00020562225836329162, "entropy": 0.06239517778158188, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:29.967395Z", "loop": 14873, "env_steps": 9138585599, "loss": 0.012191577814519405, "avg_return": 0.8628581762313843, "regret": 0.00020562225836329162, "entropy": 0.06334680318832397, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:30.821518Z", "loop": 14874, "env_steps": 9139199999, "loss": 0.011584903113543987, "avg_return": 0.8631771206855774, "regret": 0.00020562225836329162, "entropy": 0.06284230202436447, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:31.676724Z", "loop": 14875, "env_steps": 9139814399, "loss": 0.011301054619252682, "avg_return": 0.8623514771461487, "regret": 0.00020562225836329162, "entropy": 0.061989154666662216, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:32.531024Z", "loop": 14876, "env_steps": 9140428799, "loss": 0.01265565026551485, "avg_return": 0.8627245426177979, "regret": 0.00020562225836329162, "entropy": 0.06472434848546982, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:33.385143Z", "loop": 14877, "env_steps": 9141043199, "loss": 0.011520998552441597, "avg_return": 0.863571286201477, "regret": 0.00020562225836329162, "entropy": 0.05948371812701225, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:34.238960Z", "loop": 14878, "env_steps": 9141657599, "loss": 0.011605179868638515, "avg_return": 0.8616594672203064, "regret": 0.00020562225836329162, "entropy": 0.06012621149420738, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:35.092938Z", "loop": 14879, "env_steps": 9142271999, "loss": 0.011770864948630333, "avg_return": 0.8639920353889465, "regret": 0.00020562225836329162, "entropy": 0.06083562597632408, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:35.987172Z", "loop": 14880, "env_steps": 9142886399, "loss": 0.012054558843374252, "avg_return": 0.8643815517425537, "regret": 0.0009115582215599716, "entropy": 0.06473288685083389, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:36.840544Z", "loop": 14881, "env_steps": 9143500799, "loss": 0.011841578409075737, "avg_return": 0.8648949265480042, "regret": 0.0009115582215599716, "entropy": 0.0640300065279007, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:37.694408Z", "loop": 14882, "env_steps": 9144115199, "loss": 0.011063605546951294, "avg_return": 0.8625778555870056, "regret": 0.0009115582215599716, "entropy": 0.06055218726396561, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:38.548076Z", "loop": 14883, "env_steps": 9144729599, "loss": 0.011230189353227615, "avg_return": 0.8646513819694519, "regret": 0.0009115582215599716, "entropy": 0.062048591673374176, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:39.402404Z", "loop": 14884, "env_steps": 9145343999, "loss": 0.011437341570854187, "avg_return": 0.8616276979446411, "regret": 0.0009115582215599716, "entropy": 0.05968237295746803, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:40.257094Z", "loop": 14885, "env_steps": 9145958399, "loss": 0.012432858347892761, "avg_return": 0.8636674284934998, "regret": 0.0009115582215599716, "entropy": 0.06518365442752838, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:41.111956Z", "loop": 14886, "env_steps": 9146572799, "loss": 0.01285551767796278, "avg_return": 0.8644057512283325, "regret": 0.0009115582215599716, "entropy": 0.06427258998155594, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:41.966122Z", "loop": 14887, "env_steps": 9147187199, "loss": 0.011547370813786983, "avg_return": 0.8641617894172668, "regret": 0.0009115582215599716, "entropy": 0.060187168419361115, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:42.821194Z", "loop": 14888, "env_steps": 9147801599, "loss": 0.01176503486931324, "avg_return": 0.8645527362823486, "regret": 0.0009115582215599716, "entropy": 0.06266064196825027, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:43.676080Z", "loop": 14889, "env_steps": 9148415999, "loss": 0.012103251181542873, "avg_return": 0.8636413812637329, "regret": 0.0009115582215599716, "entropy": 0.06418903917074203, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:44.570624Z", "loop": 14890, "env_steps": 9149030399, "loss": 0.012848861515522003, "avg_return": 0.8635151386260986, "regret": 0.0003822196158580482, "entropy": 0.0677810087800026, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:45.424666Z", "loop": 14891, "env_steps": 9149644799, "loss": 0.012369596399366856, "avg_return": 0.8646604418754578, "regret": 0.0003822196158580482, "entropy": 0.06408727169036865, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:46.278944Z", "loop": 14892, "env_steps": 9150259199, "loss": 0.010997457429766655, "avg_return": 0.8626766204833984, "regret": 0.0003822196158580482, "entropy": 0.0601496584713459, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:47.133293Z", "loop": 14893, "env_steps": 9150873599, "loss": 0.012112022377550602, "avg_return": 0.8628862500190735, "regret": 0.0003822196158580482, "entropy": 0.0628228709101677, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:47.987288Z", "loop": 14894, "env_steps": 9151487999, "loss": 0.011288581416010857, "avg_return": 0.8630842566490173, "regret": 0.0003822196158580482, "entropy": 0.06261768937110901, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:48.841450Z", "loop": 14895, "env_steps": 9152102399, "loss": 0.012394741177558899, "avg_return": 0.8634247183799744, "regret": 0.0003822196158580482, "entropy": 0.06155948340892792, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:49.695979Z", "loop": 14896, "env_steps": 9152716799, "loss": 0.012630400247871876, "avg_return": 0.8623521327972412, "regret": 0.0003822196158580482, "entropy": 0.06804266571998596, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:50.550734Z", "loop": 14897, "env_steps": 9153331199, "loss": 0.012395649217069149, "avg_return": 0.8629059791564941, "regret": 0.0003822196158580482, "entropy": 0.0666859894990921, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:51.405004Z", "loop": 14898, "env_steps": 9153945599, "loss": 0.012101518921554089, "avg_return": 0.8632935881614685, "regret": 0.0003822196158580482, "entropy": 0.06418875604867935, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:52.259972Z", "loop": 14899, "env_steps": 9154559999, "loss": 0.012061350047588348, "avg_return": 0.8626406192779541, "regret": 0.0003822196158580482, "entropy": 0.0629735067486763, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:53.152820Z", "loop": 14900, "env_steps": 9155174399, "loss": 0.011350485496222973, "avg_return": 0.8622188568115234, "regret": 0.000536243082024157, "entropy": 0.060658857226371765, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:54.006354Z", "loop": 14901, "env_steps": 9155788799, "loss": 0.011531423777341843, "avg_return": 0.8632921576499939, "regret": 0.000536243082024157, "entropy": 0.06290771812200546, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:54.860553Z", "loop": 14902, "env_steps": 9156403199, "loss": 0.011659818701446056, "avg_return": 0.8625203371047974, "regret": 0.000536243082024157, "entropy": 0.059105608612298965, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:55.715107Z", "loop": 14903, "env_steps": 9157017599, "loss": 0.011214791797101498, "avg_return": 0.8635557293891907, "regret": 0.000536243082024157, "entropy": 0.06080126389861107, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:56.569248Z", "loop": 14904, "env_steps": 9157631999, "loss": 0.011930163949728012, "avg_return": 0.8630570769309998, "regret": 0.000536243082024157, "entropy": 0.06441265344619751, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:57.423256Z", "loop": 14905, "env_steps": 9158246399, "loss": 0.012284570373594761, "avg_return": 0.8622581958770752, "regret": 0.000536243082024157, "entropy": 0.06335623562335968, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:58.278263Z", "loop": 14906, "env_steps": 9158860799, "loss": 0.01290691364556551, "avg_return": 0.8628706336021423, "regret": 0.000536243082024157, "entropy": 0.06736847758293152, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:59.133319Z", "loop": 14907, "env_steps": 9159475199, "loss": 0.012306276708841324, "avg_return": 0.8617442846298218, "regret": 0.000536243082024157, "entropy": 0.06359300762414932, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:56:59.987418Z", "loop": 14908, "env_steps": 9160089599, "loss": 0.013376543298363686, "avg_return": 0.8625696897506714, "regret": 0.000536243082024157, "entropy": 0.0700320303440094, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:00.840567Z", "loop": 14909, "env_steps": 9160703999, "loss": 0.013278891332447529, "avg_return": 0.8617023825645447, "regret": 0.000536243082024157, "entropy": 0.07098455727100372, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:01.733243Z", "loop": 14910, "env_steps": 9161318399, "loss": 0.016106044873595238, "avg_return": 0.8626265525817871, "regret": 0.002031841082498431, "entropy": 0.08111938089132309, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:02.588096Z", "loop": 14911, "env_steps": 9161932799, "loss": 0.015430382452905178, "avg_return": 0.8625486493110657, "regret": 0.002031841082498431, "entropy": 0.07789261639118195, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:03.442558Z", "loop": 14912, "env_steps": 9162547199, "loss": 0.01609935611486435, "avg_return": 0.8616951704025269, "regret": 0.002031841082498431, "entropy": 0.08028299361467361, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:04.297889Z", "loop": 14913, "env_steps": 9163161599, "loss": 0.016354765743017197, "avg_return": 0.8604468703269958, "regret": 0.002031841082498431, "entropy": 0.08244107663631439, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:05.152567Z", "loop": 14914, "env_steps": 9163775999, "loss": 0.017566712573170662, "avg_return": 0.8619135022163391, "regret": 0.002031841082498431, "entropy": 0.0832156091928482, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:06.008429Z", "loop": 14915, "env_steps": 9164390399, "loss": 0.016779540106654167, "avg_return": 0.8612312078475952, "regret": 0.002031841082498431, "entropy": 0.08494371175765991, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:06.863213Z", "loop": 14916, "env_steps": 9165004799, "loss": 0.018890980631113052, "avg_return": 0.859442949295044, "regret": 0.002031841082498431, "entropy": 0.08977463841438293, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:07.718371Z", "loop": 14917, "env_steps": 9165619199, "loss": 0.01819762960076332, "avg_return": 0.8615669012069702, "regret": 0.002031841082498431, "entropy": 0.08932683616876602, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:08.571784Z", "loop": 14918, "env_steps": 9166233599, "loss": 0.021150914952158928, "avg_return": 0.861748456954956, "regret": 0.002031841082498431, "entropy": 0.09915459901094437, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:09.427231Z", "loop": 14919, "env_steps": 9166847999, "loss": 0.019751733168959618, "avg_return": 0.8621553778648376, "regret": 0.002031841082498431, "entropy": 0.09463957697153091, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:10.322882Z", "loop": 14920, "env_steps": 9167462399, "loss": 0.01977638341486454, "avg_return": 0.8618974089622498, "regret": 0.0018276345217600465, "entropy": 0.0909307524561882, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:11.177869Z", "loop": 14921, "env_steps": 9168076799, "loss": 0.018736518919467926, "avg_return": 0.8626139760017395, "regret": 0.0018276345217600465, "entropy": 0.08956809341907501, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:12.032124Z", "loop": 14922, "env_steps": 9168691199, "loss": 0.015524603426456451, "avg_return": 0.8626410961151123, "regret": 0.0018276345217600465, "entropy": 0.08037106692790985, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:12.885897Z", "loop": 14923, "env_steps": 9169305599, "loss": 0.015197555534541607, "avg_return": 0.8628551363945007, "regret": 0.0018276345217600465, "entropy": 0.07810293883085251, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:13.739840Z", "loop": 14924, "env_steps": 9169919999, "loss": 0.015314755029976368, "avg_return": 0.8619698286056519, "regret": 0.0018276345217600465, "entropy": 0.07668367773294449, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:14.594307Z", "loop": 14925, "env_steps": 9170534399, "loss": 0.016497192904353142, "avg_return": 0.863201916217804, "regret": 0.0018276345217600465, "entropy": 0.0781521126627922, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:15.449419Z", "loop": 14926, "env_steps": 9171148799, "loss": 0.01544174738228321, "avg_return": 0.8633111715316772, "regret": 0.0018276345217600465, "entropy": 0.07718390226364136, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:16.302957Z", "loop": 14927, "env_steps": 9171763199, "loss": 0.015535051934421062, "avg_return": 0.8630596995353699, "regret": 0.0018276345217600465, "entropy": 0.07903601229190826, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:17.156098Z", "loop": 14928, "env_steps": 9172377599, "loss": 0.015402227640151978, "avg_return": 0.863138735294342, "regret": 0.0018276345217600465, "entropy": 0.07708553224802017, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:18.009650Z", "loop": 14929, "env_steps": 9172991999, "loss": 0.01481854822486639, "avg_return": 0.8630169630050659, "regret": 0.0018276345217600465, "entropy": 0.07789617031812668, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:18.904215Z", "loop": 14930, "env_steps": 9173606399, "loss": 0.01468732487410307, "avg_return": 0.8640322089195251, "regret": 0.0002574945683591068, "entropy": 0.07574032247066498, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:19.759368Z", "loop": 14931, "env_steps": 9174220799, "loss": 0.015601380728185177, "avg_return": 0.8626353144645691, "regret": 0.0002574945683591068, "entropy": 0.07827113568782806, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:20.612850Z", "loop": 14932, "env_steps": 9174835199, "loss": 0.016475660726428032, "avg_return": 0.8636109828948975, "regret": 0.0002574945683591068, "entropy": 0.0814642608165741, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:21.466638Z", "loop": 14933, "env_steps": 9175449599, "loss": 0.015252672135829926, "avg_return": 0.8642646670341492, "regret": 0.0002574945683591068, "entropy": 0.07681743800640106, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:22.321356Z", "loop": 14934, "env_steps": 9176063999, "loss": 0.01442679949104786, "avg_return": 0.8627952337265015, "regret": 0.0002574945683591068, "entropy": 0.07422129809856415, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:23.176422Z", "loop": 14935, "env_steps": 9176678399, "loss": 0.015270881354808807, "avg_return": 0.8636025190353394, "regret": 0.0002574945683591068, "entropy": 0.07783346623182297, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:24.030524Z", "loop": 14936, "env_steps": 9177292799, "loss": 0.015225785784423351, "avg_return": 0.8639799356460571, "regret": 0.0002574945683591068, "entropy": 0.07770494371652603, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:24.885462Z", "loop": 14937, "env_steps": 9177907199, "loss": 0.015390053391456604, "avg_return": 0.863557755947113, "regret": 0.0002574945683591068, "entropy": 0.07893425971269608, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:25.741272Z", "loop": 14938, "env_steps": 9178521599, "loss": 0.0157227274030447, "avg_return": 0.8641377687454224, "regret": 0.0002574945683591068, "entropy": 0.07779241353273392, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:26.597227Z", "loop": 14939, "env_steps": 9179135999, "loss": 0.01560659147799015, "avg_return": 0.863320529460907, "regret": 0.0002574945683591068, "entropy": 0.07831762731075287, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:27.490229Z", "loop": 14940, "env_steps": 9179750399, "loss": 0.01572532393038273, "avg_return": 0.8620802760124207, "regret": 0.0009633015724830329, "entropy": 0.07972357422113419, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:28.343272Z", "loop": 14941, "env_steps": 9180364799, "loss": 0.016739537939429283, "avg_return": 0.8642715811729431, "regret": 0.0009633015724830329, "entropy": 0.08596258610486984, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:29.197443Z", "loop": 14942, "env_steps": 9180979199, "loss": 0.017492173239588737, "avg_return": 0.863647997379303, "regret": 0.0009633015724830329, "entropy": 0.08768194913864136, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:30.051423Z", "loop": 14943, "env_steps": 9181593599, "loss": 0.01644035615026951, "avg_return": 0.8624811768531799, "regret": 0.0009633015724830329, "entropy": 0.08768417686223984, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:30.905963Z", "loop": 14944, "env_steps": 9182207999, "loss": 0.017623739317059517, "avg_return": 0.8607557415962219, "regret": 0.0009633015724830329, "entropy": 0.09214194864034653, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:31.759595Z", "loop": 14945, "env_steps": 9182822399, "loss": 0.0193635206669569, "avg_return": 0.8614541888237, "regret": 0.0009633015724830329, "entropy": 0.09658238291740417, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:32.613706Z", "loop": 14946, "env_steps": 9183436799, "loss": 0.020730432122945786, "avg_return": 0.8612080216407776, "regret": 0.0009633015724830329, "entropy": 0.10295268893241882, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:33.467896Z", "loop": 14947, "env_steps": 9184051199, "loss": 0.021175026893615723, "avg_return": 0.8605949878692627, "regret": 0.0009633015724830329, "entropy": 0.10626013576984406, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:34.322350Z", "loop": 14948, "env_steps": 9184665599, "loss": 0.01965118944644928, "avg_return": 0.8594799041748047, "regret": 0.0009633015724830329, "entropy": 0.10618119686841965, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:35.176322Z", "loop": 14949, "env_steps": 9185279999, "loss": 0.021377483382821083, "avg_return": 0.8599622845649719, "regret": 0.0009633015724830329, "entropy": 0.10993766039609909, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:36.069472Z", "loop": 14950, "env_steps": 9185894399, "loss": 0.023699212819337845, "avg_return": 0.8601568937301636, "regret": 0.002753817941993475, "entropy": 0.117406465113163, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:36.922625Z", "loop": 14951, "env_steps": 9186508799, "loss": 0.024239329621195793, "avg_return": 0.8617192506790161, "regret": 0.002753817941993475, "entropy": 0.11788079887628555, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:37.776278Z", "loop": 14952, "env_steps": 9187123199, "loss": 0.024572638794779778, "avg_return": 0.8609816431999207, "regret": 0.002753817941993475, "entropy": 0.12199188768863678, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:38.630799Z", "loop": 14953, "env_steps": 9187737599, "loss": 0.024610187858343124, "avg_return": 0.8619118332862854, "regret": 0.002753817941993475, "entropy": 0.12436327338218689, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:39.484345Z", "loop": 14954, "env_steps": 9188351999, "loss": 0.025020036846399307, "avg_return": 0.8622221946716309, "regret": 0.002753817941993475, "entropy": 0.12473143637180328, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:40.337522Z", "loop": 14955, "env_steps": 9188966399, "loss": 0.023327181115746498, "avg_return": 0.8627929091453552, "regret": 0.002753817941993475, "entropy": 0.11875205487012863, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:41.190788Z", "loop": 14956, "env_steps": 9189580799, "loss": 0.022203709930181503, "avg_return": 0.8620351552963257, "regret": 0.002753817941993475, "entropy": 0.11929918080568314, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:42.045030Z", "loop": 14957, "env_steps": 9190195199, "loss": 0.021835172548890114, "avg_return": 0.8617595434188843, "regret": 0.002753817941993475, "entropy": 0.11414214223623276, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:42.899608Z", "loop": 14958, "env_steps": 9190809599, "loss": 0.020904019474983215, "avg_return": 0.8620832562446594, "regret": 0.002753817941993475, "entropy": 0.10561064630746841, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:43.752860Z", "loop": 14959, "env_steps": 9191423999, "loss": 0.01993308775126934, "avg_return": 0.8623358607292175, "regret": 0.002753817941993475, "entropy": 0.10581297427415848, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:44.645020Z", "loop": 14960, "env_steps": 9192038399, "loss": 0.021295597776770592, "avg_return": 0.8630293011665344, "regret": 0.001110751647502184, "entropy": 0.10362500697374344, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:45.499787Z", "loop": 14961, "env_steps": 9192652799, "loss": 0.019976310431957245, "avg_return": 0.8615970015525818, "regret": 0.001110751647502184, "entropy": 0.10474490374326706, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:46.354907Z", "loop": 14962, "env_steps": 9193267199, "loss": 0.022128691896796227, "avg_return": 0.8622379899024963, "regret": 0.001110751647502184, "entropy": 0.10372953861951828, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:47.209515Z", "loop": 14963, "env_steps": 9193881599, "loss": 0.01979125663638115, "avg_return": 0.8614451289176941, "regret": 0.001110751647502184, "entropy": 0.10206156224012375, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:48.062485Z", "loop": 14964, "env_steps": 9194495999, "loss": 0.019961075857281685, "avg_return": 0.8628724217414856, "regret": 0.001110751647502184, "entropy": 0.103278748691082, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:48.917062Z", "loop": 14965, "env_steps": 9195110399, "loss": 0.02036086656153202, "avg_return": 0.8620107173919678, "regret": 0.001110751647502184, "entropy": 0.1035420224070549, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:49.770243Z", "loop": 14966, "env_steps": 9195724799, "loss": 0.020181341096758842, "avg_return": 0.8611130714416504, "regret": 0.001110751647502184, "entropy": 0.10184524953365326, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:50.624765Z", "loop": 14967, "env_steps": 9196339199, "loss": 0.019658206030726433, "avg_return": 0.8626570701599121, "regret": 0.001110751647502184, "entropy": 0.0972084254026413, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:51.478959Z", "loop": 14968, "env_steps": 9196953599, "loss": 0.019823869690299034, "avg_return": 0.8630742430686951, "regret": 0.001110751647502184, "entropy": 0.10057154297828674, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:52.333952Z", "loop": 14969, "env_steps": 9197567999, "loss": 0.019429948180913925, "avg_return": 0.8634670972824097, "regret": 0.001110751647502184, "entropy": 0.09662114828824997, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:53.227232Z", "loop": 14970, "env_steps": 9198182399, "loss": 0.01937815360724926, "avg_return": 0.8627867102622986, "regret": 0.0008758657495491207, "entropy": 0.10098110139369965, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:54.081741Z", "loop": 14971, "env_steps": 9198796799, "loss": 0.019784145057201385, "avg_return": 0.8626530170440674, "regret": 0.0008758657495491207, "entropy": 0.10083415359258652, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:54.936502Z", "loop": 14972, "env_steps": 9199411199, "loss": 0.021392442286014557, "avg_return": 0.8634961247444153, "regret": 0.0008758657495491207, "entropy": 0.10268092900514603, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:55.791564Z", "loop": 14973, "env_steps": 9200025599, "loss": 0.021450793370604515, "avg_return": 0.8636295795440674, "regret": 0.0008758657495491207, "entropy": 0.10441261529922485, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:56.646561Z", "loop": 14974, "env_steps": 9200639999, "loss": 0.02072042040526867, "avg_return": 0.8647552728652954, "regret": 0.0008758657495491207, "entropy": 0.10059565305709839, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:57.500993Z", "loop": 14975, "env_steps": 9201254399, "loss": 0.021700529381632805, "avg_return": 0.8623448610305786, "regret": 0.0008758657495491207, "entropy": 0.10335273295640945, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:58.356249Z", "loop": 14976, "env_steps": 9201868799, "loss": 0.020971685647964478, "avg_return": 0.8626947402954102, "regret": 0.0008758657495491207, "entropy": 0.0956253930926323, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:57:59.210323Z", "loop": 14977, "env_steps": 9202483199, "loss": 0.021142449229955673, "avg_return": 0.862745463848114, "regret": 0.0008758657495491207, "entropy": 0.09568373113870621, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:00.064131Z", "loop": 14978, "env_steps": 9203097599, "loss": 0.021453557536005974, "avg_return": 0.8629999160766602, "regret": 0.0008758657495491207, "entropy": 0.10321594774723053, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:00.918685Z", "loop": 14979, "env_steps": 9203711999, "loss": 0.022148214280605316, "avg_return": 0.8625757098197937, "regret": 0.0008758657495491207, "entropy": 0.10239464044570923, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:01.813247Z", "loop": 14980, "env_steps": 9204326399, "loss": 0.020823277533054352, "avg_return": 0.8628005385398865, "regret": 9.302971739089116e-05, "entropy": 0.10072114318609238, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:02.667069Z", "loop": 14981, "env_steps": 9204940799, "loss": 0.02165890298783779, "avg_return": 0.8642258644104004, "regret": 9.302971739089116e-05, "entropy": 0.09909012168645859, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:03.519972Z", "loop": 14982, "env_steps": 9205555199, "loss": 0.020735634490847588, "avg_return": 0.8638318181037903, "regret": 9.302971739089116e-05, "entropy": 0.09828777611255646, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:04.374358Z", "loop": 14983, "env_steps": 9206169599, "loss": 0.020835725590586662, "avg_return": 0.8633421063423157, "regret": 9.302971739089116e-05, "entropy": 0.09646622091531754, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:05.228349Z", "loop": 14984, "env_steps": 9206783999, "loss": 0.020719436928629875, "avg_return": 0.8642387986183167, "regret": 9.302971739089116e-05, "entropy": 0.10020024329423904, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:06.081763Z", "loop": 14985, "env_steps": 9207398399, "loss": 0.02180453948676586, "avg_return": 0.8644004464149475, "regret": 9.302971739089116e-05, "entropy": 0.10060202330350876, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:06.934917Z", "loop": 14986, "env_steps": 9208012799, "loss": 0.01706635020673275, "avg_return": 0.863834023475647, "regret": 9.302971739089116e-05, "entropy": 0.08405906707048416, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:07.787775Z", "loop": 14987, "env_steps": 9208627199, "loss": 0.015275736339390278, "avg_return": 0.8632076382637024, "regret": 9.302971739089116e-05, "entropy": 0.07797330617904663, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:08.641697Z", "loop": 14988, "env_steps": 9209241599, "loss": 0.01566673442721367, "avg_return": 0.8632110953330994, "regret": 9.302971739089116e-05, "entropy": 0.07856419682502747, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:09.496392Z", "loop": 14989, "env_steps": 9209855999, "loss": 0.015243313275277615, "avg_return": 0.8636724948883057, "regret": 9.302971739089116e-05, "entropy": 0.07648562639951706, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:10.387898Z", "loop": 14990, "env_steps": 9210470399, "loss": 0.01614176109433174, "avg_return": 0.8637944459915161, "regret": 0.00010308919445378706, "entropy": 0.07813220471143723, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:11.241325Z", "loop": 14991, "env_steps": 9211084799, "loss": 0.015617472119629383, "avg_return": 0.8652284145355225, "regret": 0.00010308919445378706, "entropy": 0.07547827810049057, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:12.094633Z", "loop": 14992, "env_steps": 9211699199, "loss": 0.014207175932824612, "avg_return": 0.8635403513908386, "regret": 0.00010308919445378706, "entropy": 0.07347781211137772, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:12.949280Z", "loop": 14993, "env_steps": 9212313599, "loss": 0.015043318271636963, "avg_return": 0.8637431859970093, "regret": 0.00010308919445378706, "entropy": 0.07484999299049377, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:13.802806Z", "loop": 14994, "env_steps": 9212927999, "loss": 0.01477795373648405, "avg_return": 0.8629075288772583, "regret": 0.00010308919445378706, "entropy": 0.07591069489717484, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:14.656737Z", "loop": 14995, "env_steps": 9213542399, "loss": 0.01525502372533083, "avg_return": 0.8630131483078003, "regret": 0.00010308919445378706, "entropy": 0.07716215401887894, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:15.510667Z", "loop": 14996, "env_steps": 9214156799, "loss": 0.01484813541173935, "avg_return": 0.8614248037338257, "regret": 0.00010308919445378706, "entropy": 0.07408218085765839, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:16.365118Z", "loop": 14997, "env_steps": 9214771199, "loss": 0.015158136375248432, "avg_return": 0.8620548844337463, "regret": 0.00010308919445378706, "entropy": 0.07870649546384811, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:17.219186Z", "loop": 14998, "env_steps": 9215385599, "loss": 0.015358454547822475, "avg_return": 0.8597466349601746, "regret": 0.00010308919445378706, "entropy": 0.0822029858827591, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:18.073585Z", "loop": 14999, "env_steps": 9215999999, "loss": 0.014758730307221413, "avg_return": 0.8617480397224426, "regret": 0.00010308919445378706, "entropy": 0.08362200856208801, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:18.966596Z", "loop": 15000, "env_steps": 9216614399, "loss": 0.01424427516758442, "avg_return": 0.862611711025238, "regret": 0.0014422397362068295, "entropy": 0.07406864315271378, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:19.820142Z", "loop": 15001, "env_steps": 9217228799, "loss": 0.014572419226169586, "avg_return": 0.8621993064880371, "regret": 0.0014422397362068295, "entropy": 0.07430653274059296, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:20.674815Z", "loop": 15002, "env_steps": 9217843199, "loss": 0.013668912462890148, "avg_return": 0.8630772233009338, "regret": 0.0014422397362068295, "entropy": 0.07037200778722763, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:21.528996Z", "loop": 15003, "env_steps": 9218457599, "loss": 0.014112616889178753, "avg_return": 0.8633199334144592, "regret": 0.0014422397362068295, "entropy": 0.07443206012248993, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:22.382907Z", "loop": 15004, "env_steps": 9219071999, "loss": 0.013602854683995247, "avg_return": 0.8636776208877563, "regret": 0.0014422397362068295, "entropy": 0.07065087556838989, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:23.236853Z", "loop": 15005, "env_steps": 9219686399, "loss": 0.012940706685185432, "avg_return": 0.8634686470031738, "regret": 0.0014422397362068295, "entropy": 0.06802500784397125, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:24.091879Z", "loop": 15006, "env_steps": 9220300799, "loss": 0.01394724752753973, "avg_return": 0.8640159368515015, "regret": 0.0014422397362068295, "entropy": 0.06907354295253754, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:24.946883Z", "loop": 15007, "env_steps": 9220915199, "loss": 0.01390460878610611, "avg_return": 0.8619772791862488, "regret": 0.0014422397362068295, "entropy": 0.06927266716957092, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:25.800897Z", "loop": 15008, "env_steps": 9221529599, "loss": 0.014350669458508492, "avg_return": 0.8636494874954224, "regret": 0.0014422397362068295, "entropy": 0.0720566138625145, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:26.655091Z", "loop": 15009, "env_steps": 9222143999, "loss": 0.013260453939437866, "avg_return": 0.8633897304534912, "regret": 0.0014422397362068295, "entropy": 0.06932877004146576, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:27.549431Z", "loop": 15010, "env_steps": 9222758399, "loss": 0.013857796788215637, "avg_return": 0.8638941645622253, "regret": 0.00011738570174202323, "entropy": 0.07069560885429382, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:28.403526Z", "loop": 15011, "env_steps": 9223372799, "loss": 0.01292501576244831, "avg_return": 0.8630703091621399, "regret": 0.00011738570174202323, "entropy": 0.06468318402767181, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:29.258181Z", "loop": 15012, "env_steps": 9223987199, "loss": 0.01233876682817936, "avg_return": 0.8635633587837219, "regret": 0.00011738570174202323, "entropy": 0.06337441504001617, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:30.112355Z", "loop": 15013, "env_steps": 9224601599, "loss": 0.012802014127373695, "avg_return": 0.8630576729774475, "regret": 0.00011738570174202323, "entropy": 0.0643312856554985, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:30.965969Z", "loop": 15014, "env_steps": 9225215999, "loss": 0.011227814480662346, "avg_return": 0.865570068359375, "regret": 0.00011738570174202323, "entropy": 0.05995284393429756, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:31.820133Z", "loop": 15015, "env_steps": 9225830399, "loss": 0.012163659557700157, "avg_return": 0.8640878796577454, "regret": 0.00011738570174202323, "entropy": 0.06127376854419708, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:32.674682Z", "loop": 15016, "env_steps": 9226444799, "loss": 0.011713729240000248, "avg_return": 0.8637344837188721, "regret": 0.00011738570174202323, "entropy": 0.06267198920249939, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:33.528924Z", "loop": 15017, "env_steps": 9227059199, "loss": 0.01197484415024519, "avg_return": 0.8624936938285828, "regret": 0.00011738570174202323, "entropy": 0.06516911834478378, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:34.382251Z", "loop": 15018, "env_steps": 9227673599, "loss": 0.011695792898535728, "avg_return": 0.8639164566993713, "regret": 0.00011738570174202323, "entropy": 0.06203065067529678, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:35.235400Z", "loop": 15019, "env_steps": 9228287999, "loss": 0.011676771566271782, "avg_return": 0.8640222549438477, "regret": 0.00011738570174202323, "entropy": 0.06080617383122444, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:36.131080Z", "loop": 15020, "env_steps": 9228902399, "loss": 0.010981570929288864, "avg_return": 0.863176703453064, "regret": 0.00012765855353791267, "entropy": 0.060898229479789734, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:36.986405Z", "loop": 15021, "env_steps": 9229516799, "loss": 0.01213325560092926, "avg_return": 0.8644028902053833, "regret": 0.00012765855353791267, "entropy": 0.0671420469880104, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:37.841086Z", "loop": 15022, "env_steps": 9230131199, "loss": 0.011247782967984676, "avg_return": 0.862693727016449, "regret": 0.00012765855353791267, "entropy": 0.05985163524746895, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:38.694694Z", "loop": 15023, "env_steps": 9230745599, "loss": 0.011291787959635258, "avg_return": 0.8638588786125183, "regret": 0.00012765855353791267, "entropy": 0.06147177517414093, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:39.549519Z", "loop": 15024, "env_steps": 9231359999, "loss": 0.011073707602918148, "avg_return": 0.8629531264305115, "regret": 0.00012765855353791267, "entropy": 0.05530364811420441, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:40.403467Z", "loop": 15025, "env_steps": 9231974399, "loss": 0.01213198620826006, "avg_return": 0.8622907996177673, "regret": 0.00012765855353791267, "entropy": 0.06303565204143524, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:41.258221Z", "loop": 15026, "env_steps": 9232588799, "loss": 0.011565121822059155, "avg_return": 0.8633445501327515, "regret": 0.00012765855353791267, "entropy": 0.06194356456398964, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:42.112178Z", "loop": 15027, "env_steps": 9233203199, "loss": 0.011572006158530712, "avg_return": 0.862758994102478, "regret": 0.00012765855353791267, "entropy": 0.06317929923534393, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:42.966175Z", "loop": 15028, "env_steps": 9233817599, "loss": 0.012245111167430878, "avg_return": 0.8630408644676208, "regret": 0.00012765855353791267, "entropy": 0.06518390774726868, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:43.819853Z", "loop": 15029, "env_steps": 9234431999, "loss": 0.011204936541616917, "avg_return": 0.8636026978492737, "regret": 0.00012765855353791267, "entropy": 0.05969647318124771, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:44.712522Z", "loop": 15030, "env_steps": 9235046399, "loss": 0.011084794998168945, "avg_return": 0.8622416257858276, "regret": 0.0004599280364345759, "entropy": 0.06079365685582161, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:45.566816Z", "loop": 15031, "env_steps": 9235660799, "loss": 0.011629614047706127, "avg_return": 0.8636369109153748, "regret": 0.0004599280364345759, "entropy": 0.05827074497938156, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:46.422659Z", "loop": 15032, "env_steps": 9236275199, "loss": 0.011227055452764034, "avg_return": 0.8644897937774658, "regret": 0.0004599280364345759, "entropy": 0.062869593501091, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:47.276713Z", "loop": 15033, "env_steps": 9236889599, "loss": 0.011466654017567635, "avg_return": 0.8635237812995911, "regret": 0.0004599280364345759, "entropy": 0.061197251081466675, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:48.130869Z", "loop": 15034, "env_steps": 9237503999, "loss": 0.011876764707267284, "avg_return": 0.8637431859970093, "regret": 0.0004599280364345759, "entropy": 0.06373463571071625, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:48.984734Z", "loop": 15035, "env_steps": 9238118399, "loss": 0.011913878843188286, "avg_return": 0.8628906607627869, "regret": 0.0004599280364345759, "entropy": 0.06412575393915176, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:49.838584Z", "loop": 15036, "env_steps": 9238732799, "loss": 0.011596724390983582, "avg_return": 0.8607982397079468, "regret": 0.0004599280364345759, "entropy": 0.060490626841783524, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:50.692528Z", "loop": 15037, "env_steps": 9239347199, "loss": 0.012275336310267448, "avg_return": 0.8623234033584595, "regret": 0.0004599280364345759, "entropy": 0.061854466795921326, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:51.546441Z", "loop": 15038, "env_steps": 9239961599, "loss": 0.012326071970164776, "avg_return": 0.8624076247215271, "regret": 0.0004599280364345759, "entropy": 0.06380888819694519, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:52.400970Z", "loop": 15039, "env_steps": 9240575999, "loss": 0.01207574363797903, "avg_return": 0.8626728653907776, "regret": 0.0004599280364345759, "entropy": 0.06396384537220001, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:53.296238Z", "loop": 15040, "env_steps": 9241190399, "loss": 0.01193743571639061, "avg_return": 0.863226056098938, "regret": 0.0009852094808593392, "entropy": 0.06389077752828598, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:54.150366Z", "loop": 15041, "env_steps": 9241804799, "loss": 0.012843377888202667, "avg_return": 0.862006425857544, "regret": 0.0009852094808593392, "entropy": 0.06541866809129715, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:55.004473Z", "loop": 15042, "env_steps": 9242419199, "loss": 0.012467237189412117, "avg_return": 0.862144410610199, "regret": 0.0009852094808593392, "entropy": 0.06659051030874252, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:55.860086Z", "loop": 15043, "env_steps": 9243033599, "loss": 0.012121456675231457, "avg_return": 0.8629897236824036, "regret": 0.0009852094808593392, "entropy": 0.06340081989765167, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:56.715990Z", "loop": 15044, "env_steps": 9243647999, "loss": 0.012671219184994698, "avg_return": 0.861809492111206, "regret": 0.0009852094808593392, "entropy": 0.06746136397123337, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:57.569247Z", "loop": 15045, "env_steps": 9244262399, "loss": 0.0134648522362113, "avg_return": 0.8627846240997314, "regret": 0.0009852094808593392, "entropy": 0.06761655956506729, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:58.422927Z", "loop": 15046, "env_steps": 9244876799, "loss": 0.013335744850337505, "avg_return": 0.8625620007514954, "regret": 0.0009852094808593392, "entropy": 0.06615294516086578, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:58:59.278009Z", "loop": 15047, "env_steps": 9245491199, "loss": 0.014109638519585133, "avg_return": 0.8637545108795166, "regret": 0.0009852094808593392, "entropy": 0.07078976929187775, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:00.132657Z", "loop": 15048, "env_steps": 9246105599, "loss": 0.014174498617649078, "avg_return": 0.8608638644218445, "regret": 0.0009852094808593392, "entropy": 0.07046745717525482, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:00.987195Z", "loop": 15049, "env_steps": 9246719999, "loss": 0.014031886123120785, "avg_return": 0.8618479371070862, "regret": 0.0009852094808593392, "entropy": 0.07085369527339935, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:01.881258Z", "loop": 15050, "env_steps": 9247334399, "loss": 0.014521049335598946, "avg_return": 0.8617438673973083, "regret": 0.0017867874121293426, "entropy": 0.07425116002559662, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:02.735792Z", "loop": 15051, "env_steps": 9247948799, "loss": 0.013814913108944893, "avg_return": 0.8616098165512085, "regret": 0.0017867874121293426, "entropy": 0.06977291405200958, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:03.590497Z", "loop": 15052, "env_steps": 9248563199, "loss": 0.01364252157509327, "avg_return": 0.8608448505401611, "regret": 0.0017867874121293426, "entropy": 0.07225369662046432, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:04.443958Z", "loop": 15053, "env_steps": 9249177599, "loss": 0.014368963427841663, "avg_return": 0.8614897131919861, "regret": 0.0017867874121293426, "entropy": 0.07351618260145187, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:05.297610Z", "loop": 15054, "env_steps": 9249791999, "loss": 0.01416065264493227, "avg_return": 0.8616354465484619, "regret": 0.0017867874121293426, "entropy": 0.0732770711183548, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:06.152813Z", "loop": 15055, "env_steps": 9250406399, "loss": 0.013843081891536713, "avg_return": 0.8610913157463074, "regret": 0.0017867874121293426, "entropy": 0.06823522597551346, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:07.006732Z", "loop": 15056, "env_steps": 9251020799, "loss": 0.014945737086236477, "avg_return": 0.8623541593551636, "regret": 0.0017867874121293426, "entropy": 0.07494961470365524, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:07.860037Z", "loop": 15057, "env_steps": 9251635199, "loss": 0.014687045477330685, "avg_return": 0.8617943525314331, "regret": 0.0017867874121293426, "entropy": 0.07305644452571869, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:08.713367Z", "loop": 15058, "env_steps": 9252249599, "loss": 0.014964192174375057, "avg_return": 0.8611295819282532, "regret": 0.0017867874121293426, "entropy": 0.0760769173502922, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:09.566817Z", "loop": 15059, "env_steps": 9252863999, "loss": 0.014579594135284424, "avg_return": 0.8609277606010437, "regret": 0.0017867874121293426, "entropy": 0.07540102303028107, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:10.461125Z", "loop": 15060, "env_steps": 9253478399, "loss": 0.015705060213804245, "avg_return": 0.862383246421814, "regret": 0.0016078130574896932, "entropy": 0.07517166435718536, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:11.315309Z", "loop": 15061, "env_steps": 9254092799, "loss": 0.015618867240846157, "avg_return": 0.8615323901176453, "regret": 0.0016078130574896932, "entropy": 0.07784900814294815, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:12.169161Z", "loop": 15062, "env_steps": 9254707199, "loss": 0.015058561228215694, "avg_return": 0.8617600798606873, "regret": 0.0016078130574896932, "entropy": 0.07587398588657379, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:13.022930Z", "loop": 15063, "env_steps": 9255321599, "loss": 0.01541245449334383, "avg_return": 0.8619028925895691, "regret": 0.0016078130574896932, "entropy": 0.07621074467897415, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:13.877291Z", "loop": 15064, "env_steps": 9255935999, "loss": 0.015196355059742928, "avg_return": 0.861093282699585, "regret": 0.0016078130574896932, "entropy": 0.07662244141101837, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:14.732419Z", "loop": 15065, "env_steps": 9256550399, "loss": 0.01634560339152813, "avg_return": 0.8616743087768555, "regret": 0.0016078130574896932, "entropy": 0.07981081306934357, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:15.587629Z", "loop": 15066, "env_steps": 9257164799, "loss": 0.016374235972762108, "avg_return": 0.8622255921363831, "regret": 0.0016078130574896932, "entropy": 0.079346664249897, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:16.442408Z", "loop": 15067, "env_steps": 9257779199, "loss": 0.01672985404729843, "avg_return": 0.8621896505355835, "regret": 0.0016078130574896932, "entropy": 0.0826902911067009, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:17.296628Z", "loop": 15068, "env_steps": 9258393599, "loss": 0.018698351457715034, "avg_return": 0.8611741065979004, "regret": 0.0016078130574896932, "entropy": 0.08500351011753082, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:18.151501Z", "loop": 15069, "env_steps": 9259007999, "loss": 0.016864793375134468, "avg_return": 0.8615349531173706, "regret": 0.0016078130574896932, "entropy": 0.08397418260574341, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:19.046130Z", "loop": 15070, "env_steps": 9259622399, "loss": 0.017671704292297363, "avg_return": 0.8603386878967285, "regret": 0.0022321383003145456, "entropy": 0.0877271443605423, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:19.901083Z", "loop": 15071, "env_steps": 9260236799, "loss": 0.016468366608023643, "avg_return": 0.8610361218452454, "regret": 0.0022321383003145456, "entropy": 0.08571984618902206, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:20.755311Z", "loop": 15072, "env_steps": 9260851199, "loss": 0.017112961038947105, "avg_return": 0.8605446815490723, "regret": 0.0022321383003145456, "entropy": 0.08699291199445724, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:21.610342Z", "loop": 15073, "env_steps": 9261465599, "loss": 0.01790359802544117, "avg_return": 0.8623816967010498, "regret": 0.0022321383003145456, "entropy": 0.08736706525087357, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:22.464729Z", "loop": 15074, "env_steps": 9262079999, "loss": 0.017531132325530052, "avg_return": 0.8611200451850891, "regret": 0.0022321383003145456, "entropy": 0.09189397841691971, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:23.318973Z", "loop": 15075, "env_steps": 9262694399, "loss": 0.018585283309221268, "avg_return": 0.8618249893188477, "regret": 0.0022321383003145456, "entropy": 0.09532909840345383, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:24.173538Z", "loop": 15076, "env_steps": 9263308799, "loss": 0.020081577822566032, "avg_return": 0.8611324429512024, "regret": 0.0022321383003145456, "entropy": 0.09903270751237869, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:25.026636Z", "loop": 15077, "env_steps": 9263923199, "loss": 0.021796463057398796, "avg_return": 0.8615673780441284, "regret": 0.0022321383003145456, "entropy": 0.10619404166936874, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:25.879441Z", "loop": 15078, "env_steps": 9264537599, "loss": 0.02129233255982399, "avg_return": 0.8617033362388611, "regret": 0.0022321383003145456, "entropy": 0.10436619073152542, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:26.734839Z", "loop": 15079, "env_steps": 9265151999, "loss": 0.02095000259578228, "avg_return": 0.8624812960624695, "regret": 0.0022321383003145456, "entropy": 0.09959564357995987, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:27.627154Z", "loop": 15080, "env_steps": 9265766399, "loss": 0.01802498660981655, "avg_return": 0.8624802827835083, "regret": 0.0010357628343626857, "entropy": 0.08819180727005005, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:28.481966Z", "loop": 15081, "env_steps": 9266380799, "loss": 0.017277369275689125, "avg_return": 0.8631278872489929, "regret": 0.0010357628343626857, "entropy": 0.08644139766693115, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:29.335575Z", "loop": 15082, "env_steps": 9266995199, "loss": 0.015936220064759254, "avg_return": 0.8625869750976562, "regret": 0.0010357628343626857, "entropy": 0.08155722171068192, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:30.190204Z", "loop": 15083, "env_steps": 9267609599, "loss": 0.016431322321295738, "avg_return": 0.8626912832260132, "regret": 0.0010357628343626857, "entropy": 0.08410123735666275, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:31.044318Z", "loop": 15084, "env_steps": 9268223999, "loss": 0.0166371688246727, "avg_return": 0.8638328313827515, "regret": 0.0010357628343626857, "entropy": 0.08391192555427551, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:31.898303Z", "loop": 15085, "env_steps": 9268838399, "loss": 0.015987932682037354, "avg_return": 0.8636606335639954, "regret": 0.0010357628343626857, "entropy": 0.08234216272830963, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:32.751810Z", "loop": 15086, "env_steps": 9269452799, "loss": 0.01615956425666809, "avg_return": 0.8631677627563477, "regret": 0.0010357628343626857, "entropy": 0.08139901608228683, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:33.606247Z", "loop": 15087, "env_steps": 9270067199, "loss": 0.01635216549038887, "avg_return": 0.8626885414123535, "regret": 0.0010357628343626857, "entropy": 0.08318303525447845, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:34.460076Z", "loop": 15088, "env_steps": 9270681599, "loss": 0.015786290168762207, "avg_return": 0.862986147403717, "regret": 0.0010357628343626857, "entropy": 0.08181460946798325, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:35.313745Z", "loop": 15089, "env_steps": 9271295999, "loss": 0.01529743429273367, "avg_return": 0.8643984198570251, "regret": 0.0010357628343626857, "entropy": 0.07857014983892441, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:36.206449Z", "loop": 15090, "env_steps": 9271910399, "loss": 0.015473896637558937, "avg_return": 0.8625437617301941, "regret": 0.00019114097813144326, "entropy": 0.08027907460927963, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:37.060917Z", "loop": 15091, "env_steps": 9272524799, "loss": 0.016137447208166122, "avg_return": 0.8630304932594299, "regret": 0.00019114097813144326, "entropy": 0.08122963458299637, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:37.914360Z", "loop": 15092, "env_steps": 9273139199, "loss": 0.016284963116049767, "avg_return": 0.8630631566047668, "regret": 0.00019114097813144326, "entropy": 0.08038054406642914, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:38.768387Z", "loop": 15093, "env_steps": 9273753599, "loss": 0.015398229472339153, "avg_return": 0.8636816740036011, "regret": 0.00019114097813144326, "entropy": 0.07767503708600998, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:39.621959Z", "loop": 15094, "env_steps": 9274367999, "loss": 0.015135866589844227, "avg_return": 0.863439679145813, "regret": 0.00019114097813144326, "entropy": 0.07903299480676651, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:40.477387Z", "loop": 15095, "env_steps": 9274982399, "loss": 0.017642058432102203, "avg_return": 0.8640247583389282, "regret": 0.00019114097813144326, "entropy": 0.0824950560927391, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:41.332039Z", "loop": 15096, "env_steps": 9275596799, "loss": 0.01687275618314743, "avg_return": 0.8628603219985962, "regret": 0.00019114097813144326, "entropy": 0.08188678324222565, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:42.186179Z", "loop": 15097, "env_steps": 9276211199, "loss": 0.014910041354596615, "avg_return": 0.8634633421897888, "regret": 0.00019114097813144326, "entropy": 0.07730651646852493, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:43.041182Z", "loop": 15098, "env_steps": 9276825599, "loss": 0.015461431816220284, "avg_return": 0.8627673387527466, "regret": 0.00019114097813144326, "entropy": 0.07983389496803284, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:43.896678Z", "loop": 15099, "env_steps": 9277439999, "loss": 0.01576821692287922, "avg_return": 0.8624590039253235, "regret": 0.00019114097813144326, "entropy": 0.07814996689558029, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:44.789339Z", "loop": 15100, "env_steps": 9278054399, "loss": 0.01599380560219288, "avg_return": 0.8638610243797302, "regret": 0.00020118533575441688, "entropy": 0.077793188393116, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:45.643490Z", "loop": 15101, "env_steps": 9278668799, "loss": 0.0158123467117548, "avg_return": 0.8631146550178528, "regret": 0.00020118533575441688, "entropy": 0.08128495514392853, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:46.499692Z", "loop": 15102, "env_steps": 9279283199, "loss": 0.016425760462880135, "avg_return": 0.8632571697235107, "regret": 0.00020118533575441688, "entropy": 0.08251035213470459, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:47.355794Z", "loop": 15103, "env_steps": 9279897599, "loss": 0.01564854010939598, "avg_return": 0.8636038303375244, "regret": 0.00020118533575441688, "entropy": 0.07911591976881027, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:48.210932Z", "loop": 15104, "env_steps": 9280511999, "loss": 0.014651075005531311, "avg_return": 0.8632403612136841, "regret": 0.00020118533575441688, "entropy": 0.0758833959698677, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:49.065603Z", "loop": 15105, "env_steps": 9281126399, "loss": 0.014561084099113941, "avg_return": 0.8642600774765015, "regret": 0.00020118533575441688, "entropy": 0.07569346576929092, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:49.920038Z", "loop": 15106, "env_steps": 9281740799, "loss": 0.014510941691696644, "avg_return": 0.8633759021759033, "regret": 0.00020118533575441688, "entropy": 0.0776696726679802, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:50.775902Z", "loop": 15107, "env_steps": 9282355199, "loss": 0.01485078688710928, "avg_return": 0.8620508909225464, "regret": 0.00020118533575441688, "entropy": 0.07615294307470322, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:51.630608Z", "loop": 15108, "env_steps": 9282969599, "loss": 0.015403039753437042, "avg_return": 0.8617848753929138, "regret": 0.00020118533575441688, "entropy": 0.0804653987288475, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:52.484938Z", "loop": 15109, "env_steps": 9283583999, "loss": 0.016347050666809082, "avg_return": 0.8634458780288696, "regret": 0.00020118533575441688, "entropy": 0.08132821321487427, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:53.396817Z", "loop": 15110, "env_steps": 9284198399, "loss": 0.015964573249220848, "avg_return": 0.862683117389679, "regret": 0.0017411933513358235, "entropy": 0.08174038678407669, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:54.253134Z", "loop": 15111, "env_steps": 9284812799, "loss": 0.01593652553856373, "avg_return": 0.8620085120201111, "regret": 0.0017411933513358235, "entropy": 0.08046375960111618, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:55.106875Z", "loop": 15112, "env_steps": 9285427199, "loss": 0.01683652587234974, "avg_return": 0.8623620867729187, "regret": 0.0017411933513358235, "entropy": 0.08547881990671158, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:55.960900Z", "loop": 15113, "env_steps": 9286041599, "loss": 0.016219070181250572, "avg_return": 0.864402711391449, "regret": 0.0017411933513358235, "entropy": 0.08539656549692154, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:56.815137Z", "loop": 15114, "env_steps": 9286655999, "loss": 0.015992652624845505, "avg_return": 0.8635501265525818, "regret": 0.0017411933513358235, "entropy": 0.08449522405862808, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:57.669571Z", "loop": 15115, "env_steps": 9287270399, "loss": 0.01573006808757782, "avg_return": 0.8626420497894287, "regret": 0.0017411933513358235, "entropy": 0.08436969667673111, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:58.523789Z", "loop": 15116, "env_steps": 9287884799, "loss": 0.015634505078196526, "avg_return": 0.8633282780647278, "regret": 0.0017411933513358235, "entropy": 0.08570319414138794, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T20:59:59.377882Z", "loop": 15117, "env_steps": 9288499199, "loss": 0.015241863206028938, "avg_return": 0.8627991676330566, "regret": 0.0017411933513358235, "entropy": 0.07994309067726135, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:00.231562Z", "loop": 15118, "env_steps": 9289113599, "loss": 0.015888391062617302, "avg_return": 0.8640599846839905, "regret": 0.0017411933513358235, "entropy": 0.08054706454277039, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:01.085462Z", "loop": 15119, "env_steps": 9289727999, "loss": 0.0164701659232378, "avg_return": 0.8631359934806824, "regret": 0.0017411933513358235, "entropy": 0.08222754299640656, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:01.983830Z", "loop": 15120, "env_steps": 9290342399, "loss": 0.016264019533991814, "avg_return": 0.8633372187614441, "regret": 0.0002604852488730103, "entropy": 0.08452479541301727, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:02.839537Z", "loop": 15121, "env_steps": 9290956799, "loss": 0.016318175941705704, "avg_return": 0.8632487058639526, "regret": 0.0002604852488730103, "entropy": 0.08200673013925552, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:03.694821Z", "loop": 15122, "env_steps": 9291571199, "loss": 0.01640509068965912, "avg_return": 0.8615849018096924, "regret": 0.0002604852488730103, "entropy": 0.08077870309352875, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:04.550202Z", "loop": 15123, "env_steps": 9292185599, "loss": 0.014819689095020294, "avg_return": 0.8633987903594971, "regret": 0.0002604852488730103, "entropy": 0.08063986152410507, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:05.404230Z", "loop": 15124, "env_steps": 9292799999, "loss": 0.014869088307023048, "avg_return": 0.8621585369110107, "regret": 0.0002604852488730103, "entropy": 0.07713621109724045, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:06.257973Z", "loop": 15125, "env_steps": 9293414399, "loss": 0.014743717387318611, "avg_return": 0.8635839223861694, "regret": 0.0002604852488730103, "entropy": 0.07553936541080475, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:07.111963Z", "loop": 15126, "env_steps": 9294028799, "loss": 0.014785348437726498, "avg_return": 0.8647768497467041, "regret": 0.0002604852488730103, "entropy": 0.07283583283424377, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:07.965417Z", "loop": 15127, "env_steps": 9294643199, "loss": 0.014183766208589077, "avg_return": 0.8635746240615845, "regret": 0.0002604852488730103, "entropy": 0.07368830591440201, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:08.818798Z", "loop": 15128, "env_steps": 9295257599, "loss": 0.013734474778175354, "avg_return": 0.8642722964286804, "regret": 0.0002604852488730103, "entropy": 0.07021007686853409, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:09.672384Z", "loop": 15129, "env_steps": 9295871999, "loss": 0.013735340908169746, "avg_return": 0.8632069826126099, "regret": 0.0002604852488730103, "entropy": 0.06813889741897583, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:10.564456Z", "loop": 15130, "env_steps": 9296486399, "loss": 0.014348161406815052, "avg_return": 0.8637132048606873, "regret": 0.00023492955369874835, "entropy": 0.07435371726751328, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:11.419275Z", "loop": 15131, "env_steps": 9297100799, "loss": 0.013804852031171322, "avg_return": 0.8633267283439636, "regret": 0.00023492955369874835, "entropy": 0.07098167389631271, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:12.273462Z", "loop": 15132, "env_steps": 9297715199, "loss": 0.014132201671600342, "avg_return": 0.8628159761428833, "regret": 0.00023492955369874835, "entropy": 0.07018241286277771, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:13.129804Z", "loop": 15133, "env_steps": 9298329599, "loss": 0.01406847219914198, "avg_return": 0.8631705641746521, "regret": 0.00023492955369874835, "entropy": 0.07301662117242813, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:13.983917Z", "loop": 15134, "env_steps": 9298943999, "loss": 0.013000892475247383, "avg_return": 0.8650451898574829, "regret": 0.00023492955369874835, "entropy": 0.06945108622312546, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:14.838400Z", "loop": 15135, "env_steps": 9299558399, "loss": 0.013927722349762917, "avg_return": 0.8633036613464355, "regret": 0.00023492955369874835, "entropy": 0.06782684475183487, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:15.691197Z", "loop": 15136, "env_steps": 9300172799, "loss": 0.012628920376300812, "avg_return": 0.8635921478271484, "regret": 0.00023492955369874835, "entropy": 0.06793321669101715, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:16.543851Z", "loop": 15137, "env_steps": 9300787199, "loss": 0.014335411600768566, "avg_return": 0.8638314008712769, "regret": 0.00023492955369874835, "entropy": 0.0702160894870758, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:17.398313Z", "loop": 15138, "env_steps": 9301401599, "loss": 0.014124629087746143, "avg_return": 0.8638151288032532, "regret": 0.00023492955369874835, "entropy": 0.07088682800531387, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:18.253683Z", "loop": 15139, "env_steps": 9302015999, "loss": 0.013295906595885754, "avg_return": 0.862491250038147, "regret": 0.00023492955369874835, "entropy": 0.06899894773960114, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:19.148107Z", "loop": 15140, "env_steps": 9302630399, "loss": 0.013277888298034668, "avg_return": 0.8616943359375, "regret": 0.0005662565818056464, "entropy": 0.07039859890937805, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:20.002354Z", "loop": 15141, "env_steps": 9303244799, "loss": 0.013102713041007519, "avg_return": 0.8620331287384033, "regret": 0.0005662565818056464, "entropy": 0.07155361771583557, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:20.856890Z", "loop": 15142, "env_steps": 9303859199, "loss": 0.012761950492858887, "avg_return": 0.8620426654815674, "regret": 0.0005662565818056464, "entropy": 0.06506592780351639, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:21.711160Z", "loop": 15143, "env_steps": 9304473599, "loss": 0.011506525799632072, "avg_return": 0.8634455800056458, "regret": 0.0005662565818056464, "entropy": 0.061744384467601776, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:22.565426Z", "loop": 15144, "env_steps": 9305087999, "loss": 0.010322270914912224, "avg_return": 0.8632293939590454, "regret": 0.0005662565818056464, "entropy": 0.05807826295495033, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:23.418793Z", "loop": 15145, "env_steps": 9305702399, "loss": 0.01140108983963728, "avg_return": 0.8606823682785034, "regret": 0.0005662565818056464, "entropy": 0.06434544175863266, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:24.271619Z", "loop": 15146, "env_steps": 9306316799, "loss": 0.013335986994206905, "avg_return": 0.8619590401649475, "regret": 0.0005662565818056464, "entropy": 0.06695692986249924, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:25.125370Z", "loop": 15147, "env_steps": 9306931199, "loss": 0.013092274777591228, "avg_return": 0.8604708313941956, "regret": 0.0005662565818056464, "entropy": 0.06576308608055115, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:25.978733Z", "loop": 15148, "env_steps": 9307545599, "loss": 0.01287254597991705, "avg_return": 0.8594511151313782, "regret": 0.0005662565818056464, "entropy": 0.06378494203090668, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:26.833370Z", "loop": 15149, "env_steps": 9308159999, "loss": 0.014097019098699093, "avg_return": 0.8594128489494324, "regret": 0.0005662565818056464, "entropy": 0.07310071587562561, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:27.725517Z", "loop": 15150, "env_steps": 9308774399, "loss": 0.014199608936905861, "avg_return": 0.8586455583572388, "regret": 0.0051801144145429134, "entropy": 0.0726904422044754, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:28.580074Z", "loop": 15151, "env_steps": 9309388799, "loss": 0.012763775885105133, "avg_return": 0.859437882900238, "regret": 0.0051801144145429134, "entropy": 0.06617409735918045, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:29.434482Z", "loop": 15152, "env_steps": 9310003199, "loss": 0.013385585509240627, "avg_return": 0.8592796921730042, "regret": 0.0051801144145429134, "entropy": 0.06751847267150879, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:30.288470Z", "loop": 15153, "env_steps": 9310617599, "loss": 0.0113363703712821, "avg_return": 0.8616610169410706, "regret": 0.0051801144145429134, "entropy": 0.062397412955760956, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:31.142365Z", "loop": 15154, "env_steps": 9311231999, "loss": 0.01178672630339861, "avg_return": 0.86097252368927, "regret": 0.0051801144145429134, "entropy": 0.06277690082788467, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:31.996482Z", "loop": 15155, "env_steps": 9311846399, "loss": 0.012428206391632557, "avg_return": 0.8616869449615479, "regret": 0.0051801144145429134, "entropy": 0.06411127001047134, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:32.850353Z", "loop": 15156, "env_steps": 9312460799, "loss": 0.011574777774512768, "avg_return": 0.8620972037315369, "regret": 0.0051801144145429134, "entropy": 0.06462981551885605, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:33.703891Z", "loop": 15157, "env_steps": 9313075199, "loss": 0.011624841019511223, "avg_return": 0.8611515760421753, "regret": 0.0051801144145429134, "entropy": 0.06237078085541725, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:34.557511Z", "loop": 15158, "env_steps": 9313689599, "loss": 0.011408346705138683, "avg_return": 0.8621752858161926, "regret": 0.0051801144145429134, "entropy": 0.06007387116551399, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:35.410799Z", "loop": 15159, "env_steps": 9314303999, "loss": 0.012220068834722042, "avg_return": 0.8628685474395752, "regret": 0.0051801144145429134, "entropy": 0.06229361146688461, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:36.303463Z", "loop": 15160, "env_steps": 9314918399, "loss": 0.011552928946912289, "avg_return": 0.8634063005447388, "regret": 0.0005740956985391676, "entropy": 0.061669833958148956, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:37.157585Z", "loop": 15161, "env_steps": 9315532799, "loss": 0.011913631111383438, "avg_return": 0.8633773922920227, "regret": 0.0005740956985391676, "entropy": 0.06187183037400246, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:38.013485Z", "loop": 15162, "env_steps": 9316147199, "loss": 0.012539093382656574, "avg_return": 0.861981213092804, "regret": 0.0005740956985391676, "entropy": 0.06334912031888962, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:38.867254Z", "loop": 15163, "env_steps": 9316761599, "loss": 0.012701665051281452, "avg_return": 0.8641411662101746, "regret": 0.0005740956985391676, "entropy": 0.06485774368047714, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:39.720634Z", "loop": 15164, "env_steps": 9317375999, "loss": 0.013179120607674122, "avg_return": 0.8639307022094727, "regret": 0.0005740956985391676, "entropy": 0.06540071964263916, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:40.575173Z", "loop": 15165, "env_steps": 9317990399, "loss": 0.012066690251231194, "avg_return": 0.8636438250541687, "regret": 0.0005740956985391676, "entropy": 0.06300804764032364, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:41.430142Z", "loop": 15166, "env_steps": 9318604799, "loss": 0.01310779806226492, "avg_return": 0.8633377552032471, "regret": 0.0005740956985391676, "entropy": 0.06298304349184036, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:42.285016Z", "loop": 15167, "env_steps": 9319219199, "loss": 0.01433410495519638, "avg_return": 0.8640122413635254, "regret": 0.0005740956985391676, "entropy": 0.07144776731729507, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:43.138786Z", "loop": 15168, "env_steps": 9319833599, "loss": 0.01435290277004242, "avg_return": 0.8628249168395996, "regret": 0.0005740956985391676, "entropy": 0.07177705317735672, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:43.993150Z", "loop": 15169, "env_steps": 9320447999, "loss": 0.015215042047202587, "avg_return": 0.8626686930656433, "regret": 0.0005740956985391676, "entropy": 0.07279042899608612, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:44.886594Z", "loop": 15170, "env_steps": 9321062399, "loss": 0.01512459572404623, "avg_return": 0.8630478382110596, "regret": 0.0006236917688511312, "entropy": 0.07438374310731888, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:45.741376Z", "loop": 15171, "env_steps": 9321676799, "loss": 0.01416891347616911, "avg_return": 0.8628664612770081, "regret": 0.0006236917688511312, "entropy": 0.07280095666646957, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:46.594964Z", "loop": 15172, "env_steps": 9322291199, "loss": 0.01544232852756977, "avg_return": 0.8642699122428894, "regret": 0.0006236917688511312, "entropy": 0.07442570477724075, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:47.448534Z", "loop": 15173, "env_steps": 9322905599, "loss": 0.015715336427092552, "avg_return": 0.8636810779571533, "regret": 0.0006236917688511312, "entropy": 0.07327358424663544, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:48.304011Z", "loop": 15174, "env_steps": 9323519999, "loss": 0.015354081988334656, "avg_return": 0.8625475168228149, "regret": 0.0006236917688511312, "entropy": 0.07521121203899384, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:49.158938Z", "loop": 15175, "env_steps": 9324134399, "loss": 0.015319901518523693, "avg_return": 0.8616522550582886, "regret": 0.0006236917688511312, "entropy": 0.074784055352211, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:50.013401Z", "loop": 15176, "env_steps": 9324748799, "loss": 0.01459371205419302, "avg_return": 0.8627378344535828, "regret": 0.0006236917688511312, "entropy": 0.07013490796089172, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:50.868140Z", "loop": 15177, "env_steps": 9325363199, "loss": 0.014095268212258816, "avg_return": 0.863209068775177, "regret": 0.0006236917688511312, "entropy": 0.07156110554933548, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:51.723598Z", "loop": 15178, "env_steps": 9325977599, "loss": 0.01571858674287796, "avg_return": 0.8623310327529907, "regret": 0.0006236917688511312, "entropy": 0.07519859820604324, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:52.579008Z", "loop": 15179, "env_steps": 9326591999, "loss": 0.015747085213661194, "avg_return": 0.8620263934135437, "regret": 0.0006236917688511312, "entropy": 0.07471277564764023, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:53.473431Z", "loop": 15180, "env_steps": 9327206399, "loss": 0.0146357212215662, "avg_return": 0.8625478148460388, "regret": 0.0012565160868689418, "entropy": 0.07251103222370148, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:54.327612Z", "loop": 15181, "env_steps": 9327820799, "loss": 0.014524245634675026, "avg_return": 0.8630792498588562, "regret": 0.0012565160868689418, "entropy": 0.07759597152471542, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:55.181391Z", "loop": 15182, "env_steps": 9328435199, "loss": 0.015114815905690193, "avg_return": 0.8624619841575623, "regret": 0.0012565160868689418, "entropy": 0.07337238639593124, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:56.034898Z", "loop": 15183, "env_steps": 9329049599, "loss": 0.014914623461663723, "avg_return": 0.8639013767242432, "regret": 0.0012565160868689418, "entropy": 0.0755821093916893, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:56.889571Z", "loop": 15184, "env_steps": 9329663999, "loss": 0.014260917901992798, "avg_return": 0.8630094528198242, "regret": 0.0012565160868689418, "entropy": 0.07108145207166672, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:57.743834Z", "loop": 15185, "env_steps": 9330278399, "loss": 0.014904404059052467, "avg_return": 0.8616123795509338, "regret": 0.0012565160868689418, "entropy": 0.07347423583269119, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:58.598126Z", "loop": 15186, "env_steps": 9330892799, "loss": 0.014059022068977356, "avg_return": 0.8621432781219482, "regret": 0.0012565160868689418, "entropy": 0.0746636763215065, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:00:59.451539Z", "loop": 15187, "env_steps": 9331507199, "loss": 0.014318406581878662, "avg_return": 0.8636962175369263, "regret": 0.0012565160868689418, "entropy": 0.07402893155813217, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:00.305193Z", "loop": 15188, "env_steps": 9332121599, "loss": 0.015566362999379635, "avg_return": 0.8624750971794128, "regret": 0.0012565160868689418, "entropy": 0.07649978250265121, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:01.159457Z", "loop": 15189, "env_steps": 9332735999, "loss": 0.01660110056400299, "avg_return": 0.8629069328308105, "regret": 0.0012565160868689418, "entropy": 0.07935181260108948, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:02.051232Z", "loop": 15190, "env_steps": 9333350399, "loss": 0.016631055623292923, "avg_return": 0.862697184085846, "regret": 0.0012584271607920527, "entropy": 0.0864427387714386, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:02.904135Z", "loop": 15191, "env_steps": 9333964799, "loss": 0.01693442091345787, "avg_return": 0.86175936460495, "regret": 0.0012584271607920527, "entropy": 0.08553051948547363, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:03.758418Z", "loop": 15192, "env_steps": 9334579199, "loss": 0.018215427175164223, "avg_return": 0.8612868189811707, "regret": 0.0012584271607920527, "entropy": 0.08946021646261215, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:04.612977Z", "loop": 15193, "env_steps": 9335193599, "loss": 0.018197037279605865, "avg_return": 0.8613037467002869, "regret": 0.0012584271607920527, "entropy": 0.08993116021156311, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:05.467414Z", "loop": 15194, "env_steps": 9335807999, "loss": 0.01653422974050045, "avg_return": 0.8626229166984558, "regret": 0.0012584271607920527, "entropy": 0.08186496794223785, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:06.320921Z", "loop": 15195, "env_steps": 9336422399, "loss": 0.017806127667427063, "avg_return": 0.8632888793945312, "regret": 0.0012584271607920527, "entropy": 0.08624812960624695, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:07.174867Z", "loop": 15196, "env_steps": 9337036799, "loss": 0.01798052340745926, "avg_return": 0.8620225191116333, "regret": 0.0012584271607920527, "entropy": 0.08825985342264175, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:08.029993Z", "loop": 15197, "env_steps": 9337651199, "loss": 0.01781708188354969, "avg_return": 0.8618263006210327, "regret": 0.0012584271607920527, "entropy": 0.08401688188314438, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:08.884414Z", "loop": 15198, "env_steps": 9338265599, "loss": 0.01876305416226387, "avg_return": 0.8617688417434692, "regret": 0.0012584271607920527, "entropy": 0.09141430258750916, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:09.738091Z", "loop": 15199, "env_steps": 9338879999, "loss": 0.018287861719727516, "avg_return": 0.8629014492034912, "regret": 0.0012584271607920527, "entropy": 0.08978013694286346, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:10.631953Z", "loop": 15200, "env_steps": 9339494399, "loss": 0.019409166648983955, "avg_return": 0.862358033657074, "regret": 0.00103852862957865, "entropy": 0.090495266020298, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:11.485987Z", "loop": 15201, "env_steps": 9340108799, "loss": 0.020525967702269554, "avg_return": 0.8631800413131714, "regret": 0.00103852862957865, "entropy": 0.09681464731693268, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:12.340078Z", "loop": 15202, "env_steps": 9340723199, "loss": 0.02099570818245411, "avg_return": 0.8630828857421875, "regret": 0.00103852862957865, "entropy": 0.09799414128065109, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:13.194164Z", "loop": 15203, "env_steps": 9341337599, "loss": 0.021937312558293343, "avg_return": 0.8617807030677795, "regret": 0.00103852862957865, "entropy": 0.10595265030860901, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:14.047699Z", "loop": 15204, "env_steps": 9341951999, "loss": 0.02110566757619381, "avg_return": 0.8610122799873352, "regret": 0.00103852862957865, "entropy": 0.10380012542009354, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:14.902468Z", "loop": 15205, "env_steps": 9342566399, "loss": 0.020346583798527718, "avg_return": 0.8618760108947754, "regret": 0.00103852862957865, "entropy": 0.09916742146015167, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:15.756726Z", "loop": 15206, "env_steps": 9343180799, "loss": 0.01922193169593811, "avg_return": 0.8619732856750488, "regret": 0.00103852862957865, "entropy": 0.09424944967031479, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:16.611284Z", "loop": 15207, "env_steps": 9343795199, "loss": 0.018449265509843826, "avg_return": 0.8629786372184753, "regret": 0.00103852862957865, "entropy": 0.0872226133942604, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:17.464746Z", "loop": 15208, "env_steps": 9344409599, "loss": 0.01782289519906044, "avg_return": 0.8615222573280334, "regret": 0.00103852862957865, "entropy": 0.0924622118473053, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:18.319301Z", "loop": 15209, "env_steps": 9345023999, "loss": 0.01868308335542679, "avg_return": 0.8607895374298096, "regret": 0.00103852862957865, "entropy": 0.09242042154073715, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:19.213282Z", "loop": 15210, "env_steps": 9345638399, "loss": 0.019173337146639824, "avg_return": 0.8617057204246521, "regret": 0.0019552388694137335, "entropy": 0.09840714931488037, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:20.067769Z", "loop": 15211, "env_steps": 9346252799, "loss": 0.01900416985154152, "avg_return": 0.8620661497116089, "regret": 0.0019552388694137335, "entropy": 0.0934380441904068, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:20.922399Z", "loop": 15212, "env_steps": 9346867199, "loss": 0.018029574304819107, "avg_return": 0.8607764840126038, "regret": 0.0019552388694137335, "entropy": 0.09351345151662827, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:21.775716Z", "loop": 15213, "env_steps": 9347481599, "loss": 0.019653139635920525, "avg_return": 0.861527144908905, "regret": 0.0019552388694137335, "entropy": 0.0969710722565651, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:22.631454Z", "loop": 15214, "env_steps": 9348095999, "loss": 0.018058065325021744, "avg_return": 0.8632810711860657, "regret": 0.0019552388694137335, "entropy": 0.0952979028224945, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:23.486440Z", "loop": 15215, "env_steps": 9348710399, "loss": 0.01830672286450863, "avg_return": 0.8631089329719543, "regret": 0.0019552388694137335, "entropy": 0.08913762867450714, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:24.342114Z", "loop": 15216, "env_steps": 9349324799, "loss": 0.01873757503926754, "avg_return": 0.8628336787223816, "regret": 0.0019552388694137335, "entropy": 0.09279423207044601, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:25.195982Z", "loop": 15217, "env_steps": 9349939199, "loss": 0.018812570720911026, "avg_return": 0.8629388809204102, "regret": 0.0019552388694137335, "entropy": 0.09160789102315903, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:26.049655Z", "loop": 15218, "env_steps": 9350553599, "loss": 0.01864558272063732, "avg_return": 0.8629419207572937, "regret": 0.0019552388694137335, "entropy": 0.09473149478435516, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:26.903424Z", "loop": 15219, "env_steps": 9351167999, "loss": 0.01788627728819847, "avg_return": 0.8634453415870667, "regret": 0.0019552388694137335, "entropy": 0.08897948265075684, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:27.796630Z", "loop": 15220, "env_steps": 9351782399, "loss": 0.018452320247888565, "avg_return": 0.863478422164917, "regret": 0.0005923060816712677, "entropy": 0.09336281567811966, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:28.650218Z", "loop": 15221, "env_steps": 9352396799, "loss": 0.018521448597311974, "avg_return": 0.8626236915588379, "regret": 0.0005923060816712677, "entropy": 0.09184062480926514, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:29.503554Z", "loop": 15222, "env_steps": 9353011199, "loss": 0.018314532935619354, "avg_return": 0.8637807369232178, "regret": 0.0005923060816712677, "entropy": 0.09576026350259781, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:30.357079Z", "loop": 15223, "env_steps": 9353625599, "loss": 0.01795128360390663, "avg_return": 0.8628544211387634, "regret": 0.0005923060816712677, "entropy": 0.09446830302476883, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:31.212758Z", "loop": 15224, "env_steps": 9354239999, "loss": 0.017710069194436073, "avg_return": 0.8635439276695251, "regret": 0.0005923060816712677, "entropy": 0.09462553262710571, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:32.067174Z", "loop": 15225, "env_steps": 9354854399, "loss": 0.018628591671586037, "avg_return": 0.8623173236846924, "regret": 0.0005923060816712677, "entropy": 0.09942080825567245, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:32.919863Z", "loop": 15226, "env_steps": 9355468799, "loss": 0.019444698467850685, "avg_return": 0.8625126481056213, "regret": 0.0005923060816712677, "entropy": 0.09535271674394608, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:33.773079Z", "loop": 15227, "env_steps": 9356083199, "loss": 0.0185489971190691, "avg_return": 0.8628005981445312, "regret": 0.0005923060816712677, "entropy": 0.09404366463422775, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:34.627492Z", "loop": 15228, "env_steps": 9356697599, "loss": 0.018458468839526176, "avg_return": 0.8610357642173767, "regret": 0.0005923060816712677, "entropy": 0.09545896202325821, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:35.482190Z", "loop": 15229, "env_steps": 9357311999, "loss": 0.018568379804491997, "avg_return": 0.8618094325065613, "regret": 0.0005923060816712677, "entropy": 0.09481730312108994, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:36.374532Z", "loop": 15230, "env_steps": 9357926399, "loss": 0.017787134274840355, "avg_return": 0.8614140152931213, "regret": 0.0010319476714357734, "entropy": 0.09369833022356033, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:37.227529Z", "loop": 15231, "env_steps": 9358540799, "loss": 0.018647022545337677, "avg_return": 0.8618818521499634, "regret": 0.0010319476714357734, "entropy": 0.09527062624692917, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:38.082120Z", "loop": 15232, "env_steps": 9359155199, "loss": 0.017340760678052902, "avg_return": 0.8624684810638428, "regret": 0.0010319476714357734, "entropy": 0.09482446312904358, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:38.936790Z", "loop": 15233, "env_steps": 9359769599, "loss": 0.018116192892193794, "avg_return": 0.8633550405502319, "regret": 0.0010319476714357734, "entropy": 0.0906624123454094, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:39.792025Z", "loop": 15234, "env_steps": 9360383999, "loss": 0.01778259500861168, "avg_return": 0.8621343970298767, "regret": 0.0010319476714357734, "entropy": 0.09058631211519241, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:40.644832Z", "loop": 15235, "env_steps": 9360998399, "loss": 0.016687646508216858, "avg_return": 0.8627506494522095, "regret": 0.0010319476714357734, "entropy": 0.09140323847532272, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:41.499796Z", "loop": 15236, "env_steps": 9361612799, "loss": 0.01871464215219021, "avg_return": 0.862715482711792, "regret": 0.0010319476714357734, "entropy": 0.09032121300697327, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:42.353451Z", "loop": 15237, "env_steps": 9362227199, "loss": 0.01833597756922245, "avg_return": 0.8622623682022095, "regret": 0.0010319476714357734, "entropy": 0.09126988053321838, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:43.209017Z", "loop": 15238, "env_steps": 9362841599, "loss": 0.018207896500825882, "avg_return": 0.8626957535743713, "regret": 0.0010319476714357734, "entropy": 0.09532801806926727, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:44.062513Z", "loop": 15239, "env_steps": 9363455999, "loss": 0.01795901730656624, "avg_return": 0.8632262349128723, "regret": 0.0010319476714357734, "entropy": 0.09156576544046402, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:44.959501Z", "loop": 15240, "env_steps": 9364070399, "loss": 0.017941555008292198, "avg_return": 0.8625290989875793, "regret": 0.0008501301053911448, "entropy": 0.09087153524160385, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:45.812355Z", "loop": 15241, "env_steps": 9364684799, "loss": 0.018267249688506126, "avg_return": 0.8622174263000488, "regret": 0.0008501301053911448, "entropy": 0.0946304053068161, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:46.666556Z", "loop": 15242, "env_steps": 9365299199, "loss": 0.01922341249883175, "avg_return": 0.8625466227531433, "regret": 0.0008501301053911448, "entropy": 0.09268757700920105, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:47.520592Z", "loop": 15243, "env_steps": 9365913599, "loss": 0.017756830900907516, "avg_return": 0.863437831401825, "regret": 0.0008501301053911448, "entropy": 0.0905088484287262, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:48.374058Z", "loop": 15244, "env_steps": 9366527999, "loss": 0.01796153001487255, "avg_return": 0.8626800775527954, "regret": 0.0008501301053911448, "entropy": 0.08892379701137543, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:49.227873Z", "loop": 15245, "env_steps": 9367142399, "loss": 0.01830424554646015, "avg_return": 0.862718403339386, "regret": 0.0008501301053911448, "entropy": 0.0915812999010086, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:50.082893Z", "loop": 15246, "env_steps": 9367756799, "loss": 0.01854071207344532, "avg_return": 0.8625470399856567, "regret": 0.0008501301053911448, "entropy": 0.08890276402235031, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:50.938831Z", "loop": 15247, "env_steps": 9368371199, "loss": 0.019226213917136192, "avg_return": 0.8629864454269409, "regret": 0.0008501301053911448, "entropy": 0.09508408606052399, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:51.793595Z", "loop": 15248, "env_steps": 9368985599, "loss": 0.01774945855140686, "avg_return": 0.8626654148101807, "regret": 0.0008501301053911448, "entropy": 0.09177087992429733, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:52.647403Z", "loop": 15249, "env_steps": 9369599999, "loss": 0.017513681203126907, "avg_return": 0.8631753921508789, "regret": 0.0008501301053911448, "entropy": 0.0918637290596962, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:53.542595Z", "loop": 15250, "env_steps": 9370214399, "loss": 0.01936134323477745, "avg_return": 0.862927258014679, "regret": 0.0005641215830110013, "entropy": 0.09846141189336777, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:54.399014Z", "loop": 15251, "env_steps": 9370828799, "loss": 0.01805807277560234, "avg_return": 0.8623547554016113, "regret": 0.0005641215830110013, "entropy": 0.09495891630649567, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:55.253993Z", "loop": 15252, "env_steps": 9371443199, "loss": 0.018762290477752686, "avg_return": 0.8636157512664795, "regret": 0.0005641215830110013, "entropy": 0.09708403795957565, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:56.108899Z", "loop": 15253, "env_steps": 9372057599, "loss": 0.02015933208167553, "avg_return": 0.864826500415802, "regret": 0.0005641215830110013, "entropy": 0.10668283700942993, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:56.963769Z", "loop": 15254, "env_steps": 9372671999, "loss": 0.021859867498278618, "avg_return": 0.8624215126037598, "regret": 0.0005641215830110013, "entropy": 0.11210222542285919, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:57.819349Z", "loop": 15255, "env_steps": 9373286399, "loss": 0.023872170597314835, "avg_return": 0.8624997138977051, "regret": 0.0005641215830110013, "entropy": 0.11741536855697632, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:58.673598Z", "loop": 15256, "env_steps": 9373900799, "loss": 0.023901566863059998, "avg_return": 0.8629831075668335, "regret": 0.0005641215830110013, "entropy": 0.11866224557161331, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:01:59.527248Z", "loop": 15257, "env_steps": 9374515199, "loss": 0.0249002855271101, "avg_return": 0.8636331558227539, "regret": 0.0005641215830110013, "entropy": 0.1207861453294754, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:00.382093Z", "loop": 15258, "env_steps": 9375129599, "loss": 0.02251114323735237, "avg_return": 0.8629074096679688, "regret": 0.0005641215830110013, "entropy": 0.11240973323583603, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:01.236394Z", "loop": 15259, "env_steps": 9375743999, "loss": 0.020947705954313278, "avg_return": 0.8629812598228455, "regret": 0.0005641215830110013, "entropy": 0.10551512241363525, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:02.129900Z", "loop": 15260, "env_steps": 9376358399, "loss": 0.019714919850230217, "avg_return": 0.8629757165908813, "regret": 0.0006566127995029092, "entropy": 0.0993567705154419, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:02.984621Z", "loop": 15261, "env_steps": 9376972799, "loss": 0.017384661361575127, "avg_return": 0.863054633140564, "regret": 0.0006566127995029092, "entropy": 0.09774848073720932, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:03.839685Z", "loop": 15262, "env_steps": 9377587199, "loss": 0.018306134268641472, "avg_return": 0.8615320920944214, "regret": 0.0006566127995029092, "entropy": 0.09987632185220718, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:04.695651Z", "loop": 15263, "env_steps": 9378201599, "loss": 0.019252480939030647, "avg_return": 0.8621537685394287, "regret": 0.0006566127995029092, "entropy": 0.10390892624855042, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:05.549826Z", "loop": 15264, "env_steps": 9378815999, "loss": 0.01919637806713581, "avg_return": 0.8620346188545227, "regret": 0.0006566127995029092, "entropy": 0.1030353307723999, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:06.403774Z", "loop": 15265, "env_steps": 9379430399, "loss": 0.02044270746409893, "avg_return": 0.8631271719932556, "regret": 0.0006566127995029092, "entropy": 0.11205355823040009, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:07.258159Z", "loop": 15266, "env_steps": 9380044799, "loss": 0.021878695115447044, "avg_return": 0.8617238402366638, "regret": 0.0006566127995029092, "entropy": 0.11259802430868149, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:08.112096Z", "loop": 15267, "env_steps": 9380659199, "loss": 0.021103370934724808, "avg_return": 0.8619950413703918, "regret": 0.0006566127995029092, "entropy": 0.11077054589986801, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:08.965672Z", "loop": 15268, "env_steps": 9381273599, "loss": 0.020077146589756012, "avg_return": 0.8625288009643555, "regret": 0.0006566127995029092, "entropy": 0.1089453399181366, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:09.820153Z", "loop": 15269, "env_steps": 9381887999, "loss": 0.020470017567276955, "avg_return": 0.8621907830238342, "regret": 0.0006566127995029092, "entropy": 0.11169801652431488, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:10.713188Z", "loop": 15270, "env_steps": 9382502399, "loss": 0.021504255011677742, "avg_return": 0.8617432117462158, "regret": 0.001292172004468739, "entropy": 0.11197694391012192, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:11.566514Z", "loop": 15271, "env_steps": 9383116799, "loss": 0.020951291546225548, "avg_return": 0.8612713813781738, "regret": 0.001292172004468739, "entropy": 0.10804300010204315, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:12.420862Z", "loop": 15272, "env_steps": 9383731199, "loss": 0.020037738606333733, "avg_return": 0.8631848096847534, "regret": 0.001292172004468739, "entropy": 0.10191921144723892, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:13.275249Z", "loop": 15273, "env_steps": 9384345599, "loss": 0.020671693608164787, "avg_return": 0.8624879121780396, "regret": 0.001292172004468739, "entropy": 0.10486406087875366, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:14.129076Z", "loop": 15274, "env_steps": 9384959999, "loss": 0.019422730430960655, "avg_return": 0.8635417819023132, "regret": 0.001292172004468739, "entropy": 0.09959109127521515, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:14.983659Z", "loop": 15275, "env_steps": 9385574399, "loss": 0.019313612952828407, "avg_return": 0.8624204993247986, "regret": 0.001292172004468739, "entropy": 0.10211101919412613, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:15.836566Z", "loop": 15276, "env_steps": 9386188799, "loss": 0.019763706251978874, "avg_return": 0.8628399968147278, "regret": 0.001292172004468739, "entropy": 0.10094252228736877, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:16.690200Z", "loop": 15277, "env_steps": 9386803199, "loss": 0.01921577751636505, "avg_return": 0.8629714250564575, "regret": 0.001292172004468739, "entropy": 0.09676222503185272, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:17.543776Z", "loop": 15278, "env_steps": 9387417599, "loss": 0.01824832521378994, "avg_return": 0.8635836243629456, "regret": 0.001292172004468739, "entropy": 0.09221141040325165, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:18.397432Z", "loop": 15279, "env_steps": 9388031999, "loss": 0.02033434435725212, "avg_return": 0.8619308471679688, "regret": 0.001292172004468739, "entropy": 0.10142123699188232, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:19.290542Z", "loop": 15280, "env_steps": 9388646399, "loss": 0.01939466968178749, "avg_return": 0.8618853688240051, "regret": 0.0008971220813691616, "entropy": 0.09454283863306046, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:20.144227Z", "loop": 15281, "env_steps": 9389260799, "loss": 0.019358111545443535, "avg_return": 0.8618682026863098, "regret": 0.0008971220813691616, "entropy": 0.09784623980522156, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:20.997225Z", "loop": 15282, "env_steps": 9389875199, "loss": 0.019267499446868896, "avg_return": 0.8632940649986267, "regret": 0.0008971220813691616, "entropy": 0.09455516189336777, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:21.851429Z", "loop": 15283, "env_steps": 9390489599, "loss": 0.01815025508403778, "avg_return": 0.863154411315918, "regret": 0.0008971220813691616, "entropy": 0.08949014544487, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:22.706330Z", "loop": 15284, "env_steps": 9391103999, "loss": 0.018005095422267914, "avg_return": 0.8622235059738159, "regret": 0.0008971220813691616, "entropy": 0.0913509875535965, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:23.559217Z", "loop": 15285, "env_steps": 9391718399, "loss": 0.01856318674981594, "avg_return": 0.862583339214325, "regret": 0.0008971220813691616, "entropy": 0.09244608879089355, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:24.412275Z", "loop": 15286, "env_steps": 9392332799, "loss": 0.018276823684573174, "avg_return": 0.8619161248207092, "regret": 0.0008971220813691616, "entropy": 0.09159588068723679, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:25.266637Z", "loop": 15287, "env_steps": 9392947199, "loss": 0.01847381703555584, "avg_return": 0.8613384366035461, "regret": 0.0008971220813691616, "entropy": 0.09048411250114441, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:26.120183Z", "loop": 15288, "env_steps": 9393561599, "loss": 0.017907598987221718, "avg_return": 0.8627294301986694, "regret": 0.0008971220813691616, "entropy": 0.08490128815174103, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:26.973554Z", "loop": 15289, "env_steps": 9394175999, "loss": 0.015992017462849617, "avg_return": 0.8617976903915405, "regret": 0.0008971220813691616, "entropy": 0.08340993523597717, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:27.866788Z", "loop": 15290, "env_steps": 9394790399, "loss": 0.01607670821249485, "avg_return": 0.8633341789245605, "regret": 0.0009473584359511733, "entropy": 0.08367124199867249, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:28.720127Z", "loop": 15291, "env_steps": 9395404799, "loss": 0.016316844150424004, "avg_return": 0.8636589646339417, "regret": 0.0009473584359511733, "entropy": 0.08247344195842743, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:29.574954Z", "loop": 15292, "env_steps": 9396019199, "loss": 0.016653046011924744, "avg_return": 0.862802267074585, "regret": 0.0009473584359511733, "entropy": 0.08449001610279083, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:30.430230Z", "loop": 15293, "env_steps": 9396633599, "loss": 0.017889639362692833, "avg_return": 0.8631665110588074, "regret": 0.0009473584359511733, "entropy": 0.08801916986703873, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:31.284850Z", "loop": 15294, "env_steps": 9397247999, "loss": 0.01890992745757103, "avg_return": 0.8627176880836487, "regret": 0.0009473584359511733, "entropy": 0.09341496974229813, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:32.138526Z", "loop": 15295, "env_steps": 9397862399, "loss": 0.01979486085474491, "avg_return": 0.8635072112083435, "regret": 0.0009473584359511733, "entropy": 0.09602291136980057, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:32.992288Z", "loop": 15296, "env_steps": 9398476799, "loss": 0.020736845210194588, "avg_return": 0.8629661202430725, "regret": 0.0009473584359511733, "entropy": 0.09842538088560104, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:33.846789Z", "loop": 15297, "env_steps": 9399091199, "loss": 0.02056996338069439, "avg_return": 0.8636538982391357, "regret": 0.0009473584359511733, "entropy": 0.10103357583284378, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:34.701240Z", "loop": 15298, "env_steps": 9399705599, "loss": 0.0193049106746912, "avg_return": 0.8638564348220825, "regret": 0.0009473584359511733, "entropy": 0.09471378475427628, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:35.555415Z", "loop": 15299, "env_steps": 9400319999, "loss": 0.019249051809310913, "avg_return": 0.8638541102409363, "regret": 0.0009473584359511733, "entropy": 0.09618819504976273, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:36.448643Z", "loop": 15300, "env_steps": 9400934399, "loss": 0.01841142773628235, "avg_return": 0.8626152873039246, "regret": 0.0005944106378592551, "entropy": 0.08984021842479706, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:37.302029Z", "loop": 15301, "env_steps": 9401548799, "loss": 0.01901889033615589, "avg_return": 0.8626739978790283, "regret": 0.0005944106378592551, "entropy": 0.09183873236179352, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:38.157310Z", "loop": 15302, "env_steps": 9402163199, "loss": 0.017461633309721947, "avg_return": 0.8633547425270081, "regret": 0.0005944106378592551, "entropy": 0.08786794543266296, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:39.010625Z", "loop": 15303, "env_steps": 9402777599, "loss": 0.018158216029405594, "avg_return": 0.8630822896957397, "regret": 0.0005944106378592551, "entropy": 0.08946414291858673, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:39.864054Z", "loop": 15304, "env_steps": 9403391999, "loss": 0.01716204732656479, "avg_return": 0.863015353679657, "regret": 0.0005944106378592551, "entropy": 0.08449993282556534, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:40.717458Z", "loop": 15305, "env_steps": 9404006399, "loss": 0.01758268103003502, "avg_return": 0.8623740673065186, "regret": 0.0005944106378592551, "entropy": 0.08912160247564316, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:41.571593Z", "loop": 15306, "env_steps": 9404620799, "loss": 0.01656450517475605, "avg_return": 0.8627465963363647, "regret": 0.0005944106378592551, "entropy": 0.0828780010342598, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:42.426637Z", "loop": 15307, "env_steps": 9405235199, "loss": 0.015595090575516224, "avg_return": 0.863237738609314, "regret": 0.0005944106378592551, "entropy": 0.07729103416204453, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:43.282583Z", "loop": 15308, "env_steps": 9405849599, "loss": 0.015730738639831543, "avg_return": 0.8628021478652954, "regret": 0.0005944106378592551, "entropy": 0.07725072652101517, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:44.136431Z", "loop": 15309, "env_steps": 9406463999, "loss": 0.015880221500992775, "avg_return": 0.8633624315261841, "regret": 0.0005944106378592551, "entropy": 0.07457645982503891, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:45.028393Z", "loop": 15310, "env_steps": 9407078399, "loss": 0.014729680493474007, "avg_return": 0.8630470037460327, "regret": 0.0005721429479308426, "entropy": 0.07314607501029968, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:45.883607Z", "loop": 15311, "env_steps": 9407692799, "loss": 0.015248310752213001, "avg_return": 0.8628670573234558, "regret": 0.0005721429479308426, "entropy": 0.07651352137327194, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:46.737698Z", "loop": 15312, "env_steps": 9408307199, "loss": 0.01460095215588808, "avg_return": 0.8631123304367065, "regret": 0.0005721429479308426, "entropy": 0.0729677826166153, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:47.591065Z", "loop": 15313, "env_steps": 9408921599, "loss": 0.015099641866981983, "avg_return": 0.8639169335365295, "regret": 0.0005721429479308426, "entropy": 0.07515616714954376, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:48.445727Z", "loop": 15314, "env_steps": 9409535999, "loss": 0.014663467183709145, "avg_return": 0.862131655216217, "regret": 0.0005721429479308426, "entropy": 0.07388558238744736, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:49.300156Z", "loop": 15315, "env_steps": 9410150399, "loss": 0.013732090592384338, "avg_return": 0.8642740249633789, "regret": 0.0005721429479308426, "entropy": 0.07207479327917099, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:50.154336Z", "loop": 15316, "env_steps": 9410764799, "loss": 0.01504321675747633, "avg_return": 0.8630379438400269, "regret": 0.0005721429479308426, "entropy": 0.07711358368396759, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:51.009161Z", "loop": 15317, "env_steps": 9411379199, "loss": 0.015861565247178078, "avg_return": 0.8629528880119324, "regret": 0.0005721429479308426, "entropy": 0.07790538668632507, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:51.864558Z", "loop": 15318, "env_steps": 9411993599, "loss": 0.014201091602444649, "avg_return": 0.8630550503730774, "regret": 0.0005721429479308426, "entropy": 0.07333970814943314, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:52.718720Z", "loop": 15319, "env_steps": 9412607999, "loss": 0.013827300630509853, "avg_return": 0.862632691860199, "regret": 0.0005721429479308426, "entropy": 0.07074353843927383, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:53.609905Z", "loop": 15320, "env_steps": 9413222399, "loss": 0.015078349970281124, "avg_return": 0.8643084764480591, "regret": 0.00029286000062711537, "entropy": 0.07441765815019608, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:54.463188Z", "loop": 15321, "env_steps": 9413836799, "loss": 0.014113183133304119, "avg_return": 0.865373969078064, "regret": 0.00029286000062711537, "entropy": 0.071723073720932, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:55.317253Z", "loop": 15322, "env_steps": 9414451199, "loss": 0.014490768313407898, "avg_return": 0.8652238249778748, "regret": 0.00029286000062711537, "entropy": 0.0690508559346199, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:56.171100Z", "loop": 15323, "env_steps": 9415065599, "loss": 0.015390855260193348, "avg_return": 0.8631563782691956, "regret": 0.00029286000062711537, "entropy": 0.07633904367685318, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:57.025222Z", "loop": 15324, "env_steps": 9415679999, "loss": 0.014143119566142559, "avg_return": 0.8648455142974854, "regret": 0.00029286000062711537, "entropy": 0.07186012715101242, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:57.879314Z", "loop": 15325, "env_steps": 9416294399, "loss": 0.014275583438575268, "avg_return": 0.8631314039230347, "regret": 0.00029286000062711537, "entropy": 0.07115837931632996, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:58.733652Z", "loop": 15326, "env_steps": 9416908799, "loss": 0.014373495243489742, "avg_return": 0.8644171357154846, "regret": 0.00029286000062711537, "entropy": 0.06941399723291397, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:02:59.588310Z", "loop": 15327, "env_steps": 9417523199, "loss": 0.014446980319917202, "avg_return": 0.8641807436943054, "regret": 0.00029286000062711537, "entropy": 0.07143346965312958, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:00.442267Z", "loop": 15328, "env_steps": 9418137599, "loss": 0.013929048553109169, "avg_return": 0.8650293946266174, "regret": 0.00029286000062711537, "entropy": 0.0728018507361412, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:01.296942Z", "loop": 15329, "env_steps": 9418751999, "loss": 0.014508195221424103, "avg_return": 0.863551676273346, "regret": 0.00029286000062711537, "entropy": 0.07114707678556442, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:02.190900Z", "loop": 15330, "env_steps": 9419366399, "loss": 0.01367892324924469, "avg_return": 0.8627743721008301, "regret": 0.0001062317387550138, "entropy": 0.06952505558729172, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:03.043868Z", "loop": 15331, "env_steps": 9419980799, "loss": 0.014371337369084358, "avg_return": 0.863250732421875, "regret": 0.0001062317387550138, "entropy": 0.07340694218873978, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:03.898429Z", "loop": 15332, "env_steps": 9420595199, "loss": 0.01407867856323719, "avg_return": 0.8631368279457092, "regret": 0.0001062317387550138, "entropy": 0.07172456383705139, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:04.754072Z", "loop": 15333, "env_steps": 9421209599, "loss": 0.014774567447602749, "avg_return": 0.8628666400909424, "regret": 0.0001062317387550138, "entropy": 0.07245343178510666, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:05.608547Z", "loop": 15334, "env_steps": 9421823999, "loss": 0.013403387740254402, "avg_return": 0.8631283640861511, "regret": 0.0001062317387550138, "entropy": 0.0683530867099762, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:06.463499Z", "loop": 15335, "env_steps": 9422438399, "loss": 0.014197123236954212, "avg_return": 0.8632724285125732, "regret": 0.0001062317387550138, "entropy": 0.0732862651348114, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:07.317828Z", "loop": 15336, "env_steps": 9423052799, "loss": 0.013667146675288677, "avg_return": 0.8642633557319641, "regret": 0.0001062317387550138, "entropy": 0.069655641913414, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:08.173106Z", "loop": 15337, "env_steps": 9423667199, "loss": 0.01407346036285162, "avg_return": 0.8626967668533325, "regret": 0.0001062317387550138, "entropy": 0.07009093463420868, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:09.028523Z", "loop": 15338, "env_steps": 9424281599, "loss": 0.013969807885587215, "avg_return": 0.8642624020576477, "regret": 0.0001062317387550138, "entropy": 0.06976684182882309, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:09.883060Z", "loop": 15339, "env_steps": 9424895999, "loss": 0.014042394235730171, "avg_return": 0.8636149168014526, "regret": 0.0001062317387550138, "entropy": 0.07372264564037323, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:10.777595Z", "loop": 15340, "env_steps": 9425510399, "loss": 0.013787236995995045, "avg_return": 0.8639892935752869, "regret": 6.968942034291103e-05, "entropy": 0.06849601119756699, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:11.632110Z", "loop": 15341, "env_steps": 9426124799, "loss": 0.012770704925060272, "avg_return": 0.8642297387123108, "regret": 6.968942034291103e-05, "entropy": 0.06660906970500946, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:12.487061Z", "loop": 15342, "env_steps": 9426739199, "loss": 0.014531194232404232, "avg_return": 0.8634034395217896, "regret": 6.968942034291103e-05, "entropy": 0.07110508531332016, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:13.341260Z", "loop": 15343, "env_steps": 9427353599, "loss": 0.013785782270133495, "avg_return": 0.8631073236465454, "regret": 6.968942034291103e-05, "entropy": 0.07063015550374985, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:14.194582Z", "loop": 15344, "env_steps": 9427967999, "loss": 0.015196489170193672, "avg_return": 0.8628067374229431, "regret": 6.968942034291103e-05, "entropy": 0.07423163950443268, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:15.048542Z", "loop": 15345, "env_steps": 9428582399, "loss": 0.014697154052555561, "avg_return": 0.8634727001190186, "regret": 6.968942034291103e-05, "entropy": 0.07185037434101105, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:15.902388Z", "loop": 15346, "env_steps": 9429196799, "loss": 0.014834466390311718, "avg_return": 0.8644450306892395, "regret": 6.968942034291103e-05, "entropy": 0.07059268653392792, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:16.756074Z", "loop": 15347, "env_steps": 9429811199, "loss": 0.014002057723701, "avg_return": 0.8618473410606384, "regret": 6.968942034291103e-05, "entropy": 0.07353406399488449, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:17.609584Z", "loop": 15348, "env_steps": 9430425599, "loss": 0.014725643210113049, "avg_return": 0.8651623725891113, "regret": 6.968942034291103e-05, "entropy": 0.0739775225520134, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:18.463660Z", "loop": 15349, "env_steps": 9431039999, "loss": 0.014470082707703114, "avg_return": 0.8639330267906189, "regret": 6.968942034291103e-05, "entropy": 0.07329250872135162, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:19.356235Z", "loop": 15350, "env_steps": 9431654399, "loss": 0.014415070414543152, "avg_return": 0.8635537028312683, "regret": 8.811778388917446e-05, "entropy": 0.07388953864574432, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:20.210594Z", "loop": 15351, "env_steps": 9432268799, "loss": 0.01559525728225708, "avg_return": 0.8638354539871216, "regret": 8.811778388917446e-05, "entropy": 0.0754576101899147, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:21.064049Z", "loop": 15352, "env_steps": 9432883199, "loss": 0.015059624798595905, "avg_return": 0.863718569278717, "regret": 8.811778388917446e-05, "entropy": 0.07558617740869522, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:21.918606Z", "loop": 15353, "env_steps": 9433497599, "loss": 0.01536546926945448, "avg_return": 0.8632106781005859, "regret": 8.811778388917446e-05, "entropy": 0.07762790471315384, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:22.772107Z", "loop": 15354, "env_steps": 9434111999, "loss": 0.015351371839642525, "avg_return": 0.8632593750953674, "regret": 8.811778388917446e-05, "entropy": 0.07850809395313263, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:23.626069Z", "loop": 15355, "env_steps": 9434726399, "loss": 0.015384159050881863, "avg_return": 0.8632275462150574, "regret": 8.811778388917446e-05, "entropy": 0.07859163731336594, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:24.480343Z", "loop": 15356, "env_steps": 9435340799, "loss": 0.016244610771536827, "avg_return": 0.8629370331764221, "regret": 8.811778388917446e-05, "entropy": 0.08104325830936432, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:25.335134Z", "loop": 15357, "env_steps": 9435955199, "loss": 0.016827216371893883, "avg_return": 0.8644080758094788, "regret": 8.811778388917446e-05, "entropy": 0.08021650463342667, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:26.189675Z", "loop": 15358, "env_steps": 9436569599, "loss": 0.016972174867987633, "avg_return": 0.8620438575744629, "regret": 8.811778388917446e-05, "entropy": 0.0827803686261177, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:27.043188Z", "loop": 15359, "env_steps": 9437183999, "loss": 0.016187122091650963, "avg_return": 0.8632839322090149, "regret": 8.811778388917446e-05, "entropy": 0.07962542027235031, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:27.936367Z", "loop": 15360, "env_steps": 9437798399, "loss": 0.015990732237696648, "avg_return": 0.8628891110420227, "regret": 0.00022723761503584683, "entropy": 0.08081957697868347, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:28.792714Z", "loop": 15361, "env_steps": 9438412799, "loss": 0.01768576353788376, "avg_return": 0.8637231588363647, "regret": 0.00022723761503584683, "entropy": 0.08668991923332214, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:29.646150Z", "loop": 15362, "env_steps": 9439027199, "loss": 0.01763218827545643, "avg_return": 0.863610029220581, "regret": 0.00022723761503584683, "entropy": 0.08830888569355011, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:30.499397Z", "loop": 15363, "env_steps": 9439641599, "loss": 0.018567735329270363, "avg_return": 0.863185465335846, "regret": 0.00022723761503584683, "entropy": 0.0910642221570015, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:31.354470Z", "loop": 15364, "env_steps": 9440255999, "loss": 0.018775930628180504, "avg_return": 0.8627714514732361, "regret": 0.00022723761503584683, "entropy": 0.0945582464337349, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:32.208965Z", "loop": 15365, "env_steps": 9440870399, "loss": 0.01984686776995659, "avg_return": 0.8619498610496521, "regret": 0.00022723761503584683, "entropy": 0.09872729331254959, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:33.063032Z", "loop": 15366, "env_steps": 9441484799, "loss": 0.020581448450684547, "avg_return": 0.8616170287132263, "regret": 0.00022723761503584683, "entropy": 0.10081116110086441, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:33.916664Z", "loop": 15367, "env_steps": 9442099199, "loss": 0.021594872698187828, "avg_return": 0.862610399723053, "regret": 0.00022723761503584683, "entropy": 0.10442085564136505, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:34.771007Z", "loop": 15368, "env_steps": 9442713599, "loss": 0.020226525142788887, "avg_return": 0.8629046678543091, "regret": 0.00022723761503584683, "entropy": 0.10115934908390045, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:35.625870Z", "loop": 15369, "env_steps": 9443327999, "loss": 0.021061696112155914, "avg_return": 0.863449215888977, "regret": 0.00022723761503584683, "entropy": 0.10294784605503082, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:36.517157Z", "loop": 15370, "env_steps": 9443942399, "loss": 0.020872289314866066, "avg_return": 0.8617708683013916, "regret": 0.0008378592901863158, "entropy": 0.10233370959758759, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:37.370611Z", "loop": 15371, "env_steps": 9444556799, "loss": 0.020478149875998497, "avg_return": 0.8629842400550842, "regret": 0.0008378592901863158, "entropy": 0.10030461102724075, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:38.224634Z", "loop": 15372, "env_steps": 9445171199, "loss": 0.020603623241186142, "avg_return": 0.8623846769332886, "regret": 0.0008378592901863158, "entropy": 0.09886770695447922, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:39.078637Z", "loop": 15373, "env_steps": 9445785599, "loss": 0.021674884483218193, "avg_return": 0.8641502857208252, "regret": 0.0008378592901863158, "entropy": 0.10470487177371979, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:39.932224Z", "loop": 15374, "env_steps": 9446399999, "loss": 0.02061028592288494, "avg_return": 0.8632432222366333, "regret": 0.0008378592901863158, "entropy": 0.09744017571210861, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:40.785164Z", "loop": 15375, "env_steps": 9447014399, "loss": 0.018800189718604088, "avg_return": 0.8628458976745605, "regret": 0.0008378592901863158, "entropy": 0.09428798407316208, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:41.640031Z", "loop": 15376, "env_steps": 9447628799, "loss": 0.019253622740507126, "avg_return": 0.8634207248687744, "regret": 0.0008378592901863158, "entropy": 0.09547808021306992, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:42.496184Z", "loop": 15377, "env_steps": 9448243199, "loss": 0.019167346879839897, "avg_return": 0.8631022572517395, "regret": 0.0008378592901863158, "entropy": 0.0962965115904808, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:43.350145Z", "loop": 15378, "env_steps": 9448857599, "loss": 0.018613364547491074, "avg_return": 0.8641178607940674, "regret": 0.0008378592901863158, "entropy": 0.09253610670566559, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:44.204201Z", "loop": 15379, "env_steps": 9449471999, "loss": 0.018479464575648308, "avg_return": 0.8638556003570557, "regret": 0.0008378592901863158, "entropy": 0.0919179618358612, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:45.096212Z", "loop": 15380, "env_steps": 9450086399, "loss": 0.018001995980739594, "avg_return": 0.8626730442047119, "regret": 0.0004686623578891158, "entropy": 0.09149444848299026, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:45.950463Z", "loop": 15381, "env_steps": 9450700799, "loss": 0.01750248484313488, "avg_return": 0.863368570804596, "regret": 0.0004686623578891158, "entropy": 0.089899443089962, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:46.805877Z", "loop": 15382, "env_steps": 9451315199, "loss": 0.017552468925714493, "avg_return": 0.8635271191596985, "regret": 0.0004686623578891158, "entropy": 0.08960684388875961, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:47.659956Z", "loop": 15383, "env_steps": 9451929599, "loss": 0.01775573566555977, "avg_return": 0.8626967668533325, "regret": 0.0004686623578891158, "entropy": 0.0891437903046608, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:48.514001Z", "loop": 15384, "env_steps": 9452543999, "loss": 0.017214063555002213, "avg_return": 0.863982081413269, "regret": 0.0004686623578891158, "entropy": 0.08665649592876434, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:49.368443Z", "loop": 15385, "env_steps": 9453158399, "loss": 0.016864806413650513, "avg_return": 0.862377941608429, "regret": 0.0004686623578891158, "entropy": 0.08717741817235947, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:50.223377Z", "loop": 15386, "env_steps": 9453772799, "loss": 0.01655491814017296, "avg_return": 0.8626212477684021, "regret": 0.0004686623578891158, "entropy": 0.08508095890283585, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:51.077894Z", "loop": 15387, "env_steps": 9454387199, "loss": 0.016934573650360107, "avg_return": 0.861957848072052, "regret": 0.0004686623578891158, "entropy": 0.08667358011007309, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:51.933068Z", "loop": 15388, "env_steps": 9455001599, "loss": 0.018298612907528877, "avg_return": 0.8627411127090454, "regret": 0.0004686623578891158, "entropy": 0.08854454755783081, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:52.787293Z", "loop": 15389, "env_steps": 9455615999, "loss": 0.018491258844733238, "avg_return": 0.8644047379493713, "regret": 0.0004686623578891158, "entropy": 0.08989954739809036, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:53.680784Z", "loop": 15390, "env_steps": 9456230399, "loss": 0.020119277760386467, "avg_return": 0.8655388355255127, "regret": 0.00037956255255267024, "entropy": 0.09699049592018127, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:54.535326Z", "loop": 15391, "env_steps": 9456844799, "loss": 0.021413085982203484, "avg_return": 0.8640992641448975, "regret": 0.00037956255255267024, "entropy": 0.09858833998441696, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:55.390879Z", "loop": 15392, "env_steps": 9457459199, "loss": 0.01839805394411087, "avg_return": 0.8622589111328125, "regret": 0.00037956255255267024, "entropy": 0.09033980220556259, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:56.245536Z", "loop": 15393, "env_steps": 9458073599, "loss": 0.0177772156894207, "avg_return": 0.8627862930297852, "regret": 0.00037956255255267024, "entropy": 0.0862107127904892, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:57.099841Z", "loop": 15394, "env_steps": 9458687999, "loss": 0.018227774649858475, "avg_return": 0.8634220361709595, "regret": 0.00037956255255267024, "entropy": 0.08819076418876648, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:57.955429Z", "loop": 15395, "env_steps": 9459302399, "loss": 0.015929047018289566, "avg_return": 0.8624196648597717, "regret": 0.00037956255255267024, "entropy": 0.07936970889568329, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:58.810596Z", "loop": 15396, "env_steps": 9459916799, "loss": 0.01574154756963253, "avg_return": 0.8633064031600952, "regret": 0.00037956255255267024, "entropy": 0.07823493331670761, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:03:59.665362Z", "loop": 15397, "env_steps": 9460531199, "loss": 0.01476623397320509, "avg_return": 0.8631214499473572, "regret": 0.00037956255255267024, "entropy": 0.07631755620241165, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:00.518952Z", "loop": 15398, "env_steps": 9461145599, "loss": 0.013433746062219143, "avg_return": 0.8638536930084229, "regret": 0.00037956255255267024, "entropy": 0.07180581986904144, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:01.372325Z", "loop": 15399, "env_steps": 9461759999, "loss": 0.014851718209683895, "avg_return": 0.8637001514434814, "regret": 0.00037956255255267024, "entropy": 0.07745330035686493, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:02.268051Z", "loop": 15400, "env_steps": 9462374399, "loss": 0.013916007243096828, "avg_return": 0.8622987866401672, "regret": 0.00011368770356057212, "entropy": 0.07107096910476685, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:03.122926Z", "loop": 15401, "env_steps": 9462988799, "loss": 0.013990471139550209, "avg_return": 0.8642122745513916, "regret": 0.00011368770356057212, "entropy": 0.07057259976863861, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:03.976895Z", "loop": 15402, "env_steps": 9463603199, "loss": 0.01321896631270647, "avg_return": 0.8635913133621216, "regret": 0.00011368770356057212, "entropy": 0.06616976857185364, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:04.831226Z", "loop": 15403, "env_steps": 9464217599, "loss": 0.012767503969371319, "avg_return": 0.862697958946228, "regret": 0.00011368770356057212, "entropy": 0.06440961360931396, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:05.686335Z", "loop": 15404, "env_steps": 9464831999, "loss": 0.01261766254901886, "avg_return": 0.8630807995796204, "regret": 0.00011368770356057212, "entropy": 0.0702238455414772, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:06.541726Z", "loop": 15405, "env_steps": 9465446399, "loss": 0.012530438601970673, "avg_return": 0.8644896745681763, "regret": 0.00011368770356057212, "entropy": 0.06601288914680481, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:07.396932Z", "loop": 15406, "env_steps": 9466060799, "loss": 0.012580922804772854, "avg_return": 0.8628383874893188, "regret": 0.00011368770356057212, "entropy": 0.06649793684482574, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:08.251210Z", "loop": 15407, "env_steps": 9466675199, "loss": 0.011779573746025562, "avg_return": 0.8646726608276367, "regret": 0.00011368770356057212, "entropy": 0.06334524601697922, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:09.106226Z", "loop": 15408, "env_steps": 9467289599, "loss": 0.012972329743206501, "avg_return": 0.8637372851371765, "regret": 0.00011368770356057212, "entropy": 0.06454567611217499, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:09.960638Z", "loop": 15409, "env_steps": 9467903999, "loss": 0.012194198556244373, "avg_return": 0.8637567162513733, "regret": 0.00011368770356057212, "entropy": 0.059483349323272705, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:10.854524Z", "loop": 15410, "env_steps": 9468518399, "loss": 0.012248756363987923, "avg_return": 0.8640218377113342, "regret": 0.0003665591066237539, "entropy": 0.06182774528861046, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:11.708479Z", "loop": 15411, "env_steps": 9469132799, "loss": 0.01242051925510168, "avg_return": 0.8636258244514465, "regret": 0.0003665591066237539, "entropy": 0.06323639303445816, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:12.564268Z", "loop": 15412, "env_steps": 9469747199, "loss": 0.011651596985757351, "avg_return": 0.864037811756134, "regret": 0.0003665591066237539, "entropy": 0.06295155733823776, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:13.418375Z", "loop": 15413, "env_steps": 9470361599, "loss": 0.01214976143091917, "avg_return": 0.863267719745636, "regret": 0.0003665591066237539, "entropy": 0.06532613188028336, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:14.272392Z", "loop": 15414, "env_steps": 9470975999, "loss": 0.011908764950931072, "avg_return": 0.8632718920707703, "regret": 0.0003665591066237539, "entropy": 0.06456991285085678, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:15.127599Z", "loop": 15415, "env_steps": 9471590399, "loss": 0.012051166966557503, "avg_return": 0.863251268863678, "regret": 0.0003665591066237539, "entropy": 0.06400133669376373, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:15.982903Z", "loop": 15416, "env_steps": 9472204799, "loss": 0.013756397180259228, "avg_return": 0.8607968091964722, "regret": 0.0003665591066237539, "entropy": 0.0674654021859169, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:16.837329Z", "loop": 15417, "env_steps": 9472819199, "loss": 0.011105977930128574, "avg_return": 0.8622632026672363, "regret": 0.0003665591066237539, "entropy": 0.064398854970932, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:17.692063Z", "loop": 15418, "env_steps": 9473433599, "loss": 0.01282994169741869, "avg_return": 0.8621926307678223, "regret": 0.0003665591066237539, "entropy": 0.06548365950584412, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:18.546674Z", "loop": 15419, "env_steps": 9474047999, "loss": 0.012242063879966736, "avg_return": 0.8622536659240723, "regret": 0.0003665591066237539, "entropy": 0.06611437350511551, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:19.444302Z", "loop": 15420, "env_steps": 9474662399, "loss": 0.013125084340572357, "avg_return": 0.8611000776290894, "regret": 0.0011462736874818802, "entropy": 0.07004427164793015, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:20.297776Z", "loop": 15421, "env_steps": 9475276799, "loss": 0.013563957996666431, "avg_return": 0.8604087233543396, "regret": 0.0011462736874818802, "entropy": 0.07028055191040039, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:21.151916Z", "loop": 15422, "env_steps": 9475891199, "loss": 0.013001741841435432, "avg_return": 0.8611252903938293, "regret": 0.0011462736874818802, "entropy": 0.06716703623533249, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:22.006799Z", "loop": 15423, "env_steps": 9476505599, "loss": 0.011255955323576927, "avg_return": 0.862166166305542, "regret": 0.0011462736874818802, "entropy": 0.06108440086245537, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:22.861531Z", "loop": 15424, "env_steps": 9477119999, "loss": 0.012975990772247314, "avg_return": 0.861453652381897, "regret": 0.0011462736874818802, "entropy": 0.0668007880449295, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:23.715565Z", "loop": 15425, "env_steps": 9477734399, "loss": 0.013737454079091549, "avg_return": 0.8626517653465271, "regret": 0.0011462736874818802, "entropy": 0.07000178843736649, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:24.569766Z", "loop": 15426, "env_steps": 9478348799, "loss": 0.013592545874416828, "avg_return": 0.8614170551300049, "regret": 0.0011462736874818802, "entropy": 0.06889241933822632, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:25.424310Z", "loop": 15427, "env_steps": 9478963199, "loss": 0.012991383671760559, "avg_return": 0.8615390062332153, "regret": 0.0011462736874818802, "entropy": 0.0656508132815361, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:26.279305Z", "loop": 15428, "env_steps": 9479577599, "loss": 0.01383789163082838, "avg_return": 0.8628089427947998, "regret": 0.0011462736874818802, "entropy": 0.07167606055736542, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:27.134609Z", "loop": 15429, "env_steps": 9480191999, "loss": 0.013860381208360195, "avg_return": 0.8610041737556458, "regret": 0.0011462736874818802, "entropy": 0.06767165660858154, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:28.028517Z", "loop": 15430, "env_steps": 9480806399, "loss": 0.013501130044460297, "avg_return": 0.8610406517982483, "regret": 0.0024135431740432978, "entropy": 0.07256249338388443, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:28.883384Z", "loop": 15431, "env_steps": 9481420799, "loss": 0.012613586150109768, "avg_return": 0.8610610961914062, "regret": 0.0024135431740432978, "entropy": 0.06634615361690521, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:29.737669Z", "loop": 15432, "env_steps": 9482035199, "loss": 0.01354049053043127, "avg_return": 0.8613805174827576, "regret": 0.0024135431740432978, "entropy": 0.06723839789628983, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:30.591889Z", "loop": 15433, "env_steps": 9482649599, "loss": 0.01304627861827612, "avg_return": 0.8605484962463379, "regret": 0.0024135431740432978, "entropy": 0.0684080496430397, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:31.445141Z", "loop": 15434, "env_steps": 9483263999, "loss": 0.01378506701439619, "avg_return": 0.8605589270591736, "regret": 0.0024135431740432978, "entropy": 0.07139219343662262, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:32.299599Z", "loop": 15435, "env_steps": 9483878399, "loss": 0.013729768805205822, "avg_return": 0.860045313835144, "regret": 0.0024135431740432978, "entropy": 0.07191706448793411, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:33.155410Z", "loop": 15436, "env_steps": 9484492799, "loss": 0.01291153859347105, "avg_return": 0.859890341758728, "regret": 0.0024135431740432978, "entropy": 0.06269581615924835, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:34.010255Z", "loop": 15437, "env_steps": 9485107199, "loss": 0.013680837117135525, "avg_return": 0.8615041375160217, "regret": 0.0024135431740432978, "entropy": 0.06826693564653397, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:34.865792Z", "loop": 15438, "env_steps": 9485721599, "loss": 0.012557734735310078, "avg_return": 0.860988974571228, "regret": 0.0024135431740432978, "entropy": 0.06844846904277802, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:35.719502Z", "loop": 15439, "env_steps": 9486335999, "loss": 0.012309362180531025, "avg_return": 0.8600330948829651, "regret": 0.0024135431740432978, "entropy": 0.0652361512184143, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:36.613115Z", "loop": 15440, "env_steps": 9486950399, "loss": 0.012197359465062618, "avg_return": 0.8602431416511536, "regret": 0.0023302275221794844, "entropy": 0.06488712131977081, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:37.468221Z", "loop": 15441, "env_steps": 9487564799, "loss": 0.01197649072855711, "avg_return": 0.8618620038032532, "regret": 0.0023302275221794844, "entropy": 0.06557398289442062, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:38.322196Z", "loop": 15442, "env_steps": 9488179199, "loss": 0.013550924137234688, "avg_return": 0.8617570996284485, "regret": 0.0023302275221794844, "entropy": 0.06853703409433365, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:39.175905Z", "loop": 15443, "env_steps": 9488793599, "loss": 0.013708633370697498, "avg_return": 0.8616032004356384, "regret": 0.0023302275221794844, "entropy": 0.06970130652189255, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:40.029235Z", "loop": 15444, "env_steps": 9489407999, "loss": 0.014182730577886105, "avg_return": 0.8615961670875549, "regret": 0.0023302275221794844, "entropy": 0.07163851708173752, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:40.883420Z", "loop": 15445, "env_steps": 9490022399, "loss": 0.014633766375482082, "avg_return": 0.8604719042778015, "regret": 0.0023302275221794844, "entropy": 0.07520123571157455, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:41.737979Z", "loop": 15446, "env_steps": 9490636799, "loss": 0.014032169245183468, "avg_return": 0.8621752858161926, "regret": 0.0023302275221794844, "entropy": 0.07050516456365585, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:42.592408Z", "loop": 15447, "env_steps": 9491251199, "loss": 0.013618553057312965, "avg_return": 0.8612289428710938, "regret": 0.0023302275221794844, "entropy": 0.07128988951444626, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:43.445686Z", "loop": 15448, "env_steps": 9491865599, "loss": 0.013612762093544006, "avg_return": 0.8626471161842346, "regret": 0.0023302275221794844, "entropy": 0.07327847927808762, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:44.299259Z", "loop": 15449, "env_steps": 9492479999, "loss": 0.014037124812602997, "avg_return": 0.8623639941215515, "regret": 0.0023302275221794844, "entropy": 0.07154779136180878, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:45.192728Z", "loop": 15450, "env_steps": 9493094399, "loss": 0.012952858582139015, "avg_return": 0.8622156977653503, "regret": 0.001490304246544838, "entropy": 0.06690230220556259, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:46.047629Z", "loop": 15451, "env_steps": 9493708799, "loss": 0.01332178432494402, "avg_return": 0.8635132312774658, "regret": 0.001490304246544838, "entropy": 0.06874386966228485, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:46.902743Z", "loop": 15452, "env_steps": 9494323199, "loss": 0.013856048695743084, "avg_return": 0.862248957157135, "regret": 0.001490304246544838, "entropy": 0.07157324254512787, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:47.756848Z", "loop": 15453, "env_steps": 9494937599, "loss": 0.014394404366612434, "avg_return": 0.8628723621368408, "regret": 0.001490304246544838, "entropy": 0.07608961313962936, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:48.611656Z", "loop": 15454, "env_steps": 9495551999, "loss": 0.014167976565659046, "avg_return": 0.8615725636482239, "regret": 0.001490304246544838, "entropy": 0.07312856614589691, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:49.466439Z", "loop": 15455, "env_steps": 9496166399, "loss": 0.01440933533012867, "avg_return": 0.8623813986778259, "regret": 0.001490304246544838, "entropy": 0.07423282414674759, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:50.320301Z", "loop": 15456, "env_steps": 9496780799, "loss": 0.014493407681584358, "avg_return": 0.8600483536720276, "regret": 0.001490304246544838, "entropy": 0.07345574349164963, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:51.175164Z", "loop": 15457, "env_steps": 9497395199, "loss": 0.014484469778835773, "avg_return": 0.8623965382575989, "regret": 0.001490304246544838, "entropy": 0.07553152740001678, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:52.029798Z", "loop": 15458, "env_steps": 9498009599, "loss": 0.014551358297467232, "avg_return": 0.8625005483627319, "regret": 0.001490304246544838, "entropy": 0.07300510257482529, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:52.885041Z", "loop": 15459, "env_steps": 9498623999, "loss": 0.014319258742034435, "avg_return": 0.8630474209785461, "regret": 0.001490304246544838, "entropy": 0.07064131647348404, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:53.779287Z", "loop": 15460, "env_steps": 9499238399, "loss": 0.013999509625136852, "avg_return": 0.8622077703475952, "regret": 0.001282708952203393, "entropy": 0.07020139694213867, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:54.632881Z", "loop": 15461, "env_steps": 9499852799, "loss": 0.013611296191811562, "avg_return": 0.8616048097610474, "regret": 0.001282708952203393, "entropy": 0.07409367710351944, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:55.487754Z", "loop": 15462, "env_steps": 9500467199, "loss": 0.013268164359033108, "avg_return": 0.8640240430831909, "regret": 0.001282708952203393, "entropy": 0.06838426738977432, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:56.342648Z", "loop": 15463, "env_steps": 9501081599, "loss": 0.014907407574355602, "avg_return": 0.8617403507232666, "regret": 0.001282708952203393, "entropy": 0.07381821423768997, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:57.197291Z", "loop": 15464, "env_steps": 9501695999, "loss": 0.015195131301879883, "avg_return": 0.8633511662483215, "regret": 0.001282708952203393, "entropy": 0.07381498068571091, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:58.051402Z", "loop": 15465, "env_steps": 9502310399, "loss": 0.014332192949950695, "avg_return": 0.8635386228561401, "regret": 0.001282708952203393, "entropy": 0.07498858869075775, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:58.905523Z", "loop": 15466, "env_steps": 9502924799, "loss": 0.01569654792547226, "avg_return": 0.8617290258407593, "regret": 0.001282708952203393, "entropy": 0.07880610227584839, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:04:59.759016Z", "loop": 15467, "env_steps": 9503539199, "loss": 0.016663094982504845, "avg_return": 0.8600488305091858, "regret": 0.001282708952203393, "entropy": 0.08281535655260086, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:00.612885Z", "loop": 15468, "env_steps": 9504153599, "loss": 0.015928251668810844, "avg_return": 0.8580215573310852, "regret": 0.001282708952203393, "entropy": 0.0865054652094841, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:01.467075Z", "loop": 15469, "env_steps": 9504767999, "loss": 0.01749059371650219, "avg_return": 0.8552302122116089, "regret": 0.001282708952203393, "entropy": 0.09439095109701157, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:02.361385Z", "loop": 15470, "env_steps": 9505382399, "loss": 0.01741102524101734, "avg_return": 0.857154130935669, "regret": 0.0071671511977910995, "entropy": 0.09003563970327377, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:03.214793Z", "loop": 15471, "env_steps": 9505996799, "loss": 0.018789192661643028, "avg_return": 0.8572260737419128, "regret": 0.0071671511977910995, "entropy": 0.09531863778829575, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:04.068620Z", "loop": 15472, "env_steps": 9506611199, "loss": 0.016558900475502014, "avg_return": 0.8616472482681274, "regret": 0.0071671511977910995, "entropy": 0.08952643722295761, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:04.922298Z", "loop": 15473, "env_steps": 9507225599, "loss": 0.016512280330061913, "avg_return": 0.8612468838691711, "regret": 0.0071671511977910995, "entropy": 0.08896484971046448, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:05.776897Z", "loop": 15474, "env_steps": 9507839999, "loss": 0.016463976353406906, "avg_return": 0.8614779710769653, "regret": 0.0071671511977910995, "entropy": 0.08677602559328079, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:06.629046Z", "loop": 15475, "env_steps": 9508454399, "loss": 0.01603068597614765, "avg_return": 0.8637741208076477, "regret": 0.0071671511977910995, "entropy": 0.08216378092765808, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:07.480792Z", "loop": 15476, "env_steps": 9509068799, "loss": 0.015525697730481625, "avg_return": 0.8631005883216858, "regret": 0.0071671511977910995, "entropy": 0.08083998411893845, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:08.334581Z", "loop": 15477, "env_steps": 9509683199, "loss": 0.015013537369668484, "avg_return": 0.8648515939712524, "regret": 0.0071671511977910995, "entropy": 0.07829373329877853, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:09.188887Z", "loop": 15478, "env_steps": 9510297599, "loss": 0.012882709503173828, "avg_return": 0.8639011979103088, "regret": 0.0071671511977910995, "entropy": 0.0708722248673439, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:10.042555Z", "loop": 15479, "env_steps": 9510911999, "loss": 0.013976672664284706, "avg_return": 0.8648370504379272, "regret": 0.0071671511977910995, "entropy": 0.07126817107200623, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:10.934151Z", "loop": 15480, "env_steps": 9511526399, "loss": 0.013955208472907543, "avg_return": 0.8641881346702576, "regret": 0.0001929031132021919, "entropy": 0.07082905620336533, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:11.787810Z", "loop": 15481, "env_steps": 9512140799, "loss": 0.013317475095391273, "avg_return": 0.8635825514793396, "regret": 0.0001929031132021919, "entropy": 0.06849787384271622, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:12.642376Z", "loop": 15482, "env_steps": 9512755199, "loss": 0.014729921706020832, "avg_return": 0.8629404902458191, "regret": 0.0001929031132021919, "entropy": 0.0709247961640358, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:13.495760Z", "loop": 15483, "env_steps": 9513369599, "loss": 0.013587872497737408, "avg_return": 0.8627926707267761, "regret": 0.0001929031132021919, "entropy": 0.07174268364906311, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:14.348979Z", "loop": 15484, "env_steps": 9513983999, "loss": 0.014259228482842445, "avg_return": 0.8638290762901306, "regret": 0.0001929031132021919, "entropy": 0.07591991871595383, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:15.203159Z", "loop": 15485, "env_steps": 9514598399, "loss": 0.013931713066995144, "avg_return": 0.863460123538971, "regret": 0.0001929031132021919, "entropy": 0.07435550540685654, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:16.058780Z", "loop": 15486, "env_steps": 9515212799, "loss": 0.014339111745357513, "avg_return": 0.8643199801445007, "regret": 0.0001929031132021919, "entropy": 0.07086660712957382, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:16.913207Z", "loop": 15487, "env_steps": 9515827199, "loss": 0.014412346296012402, "avg_return": 0.8628689050674438, "regret": 0.0001929031132021919, "entropy": 0.0741938129067421, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:17.767771Z", "loop": 15488, "env_steps": 9516441599, "loss": 0.014322059229016304, "avg_return": 0.8642740845680237, "regret": 0.0001929031132021919, "entropy": 0.07154200971126556, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:18.623209Z", "loop": 15489, "env_steps": 9517055999, "loss": 0.014258230105042458, "avg_return": 0.8643406629562378, "regret": 0.0001929031132021919, "entropy": 0.07245439291000366, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:19.516857Z", "loop": 15490, "env_steps": 9517670399, "loss": 0.013849533163011074, "avg_return": 0.8629735708236694, "regret": 0.00012638219050131738, "entropy": 0.07175406068563461, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:20.370778Z", "loop": 15491, "env_steps": 9518284799, "loss": 0.014124231413006783, "avg_return": 0.8638155460357666, "regret": 0.00012638219050131738, "entropy": 0.07128915935754776, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:21.225714Z", "loop": 15492, "env_steps": 9518899199, "loss": 0.014705131761729717, "avg_return": 0.8631376624107361, "regret": 0.00012638219050131738, "entropy": 0.07206537574529648, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:22.079195Z", "loop": 15493, "env_steps": 9519513599, "loss": 0.01461152732372284, "avg_return": 0.8635178804397583, "regret": 0.00012638219050131738, "entropy": 0.07465752214193344, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:22.932647Z", "loop": 15494, "env_steps": 9520127999, "loss": 0.015835179015994072, "avg_return": 0.8644827604293823, "regret": 0.00012638219050131738, "entropy": 0.07887686789035797, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:23.786724Z", "loop": 15495, "env_steps": 9520742399, "loss": 0.015256649814546108, "avg_return": 0.863130509853363, "regret": 0.00012638219050131738, "entropy": 0.07598649710416794, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:24.640417Z", "loop": 15496, "env_steps": 9521356799, "loss": 0.015977777540683746, "avg_return": 0.8643108606338501, "regret": 0.00012638219050131738, "entropy": 0.07958188652992249, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:25.494847Z", "loop": 15497, "env_steps": 9521971199, "loss": 0.01564623974263668, "avg_return": 0.8630822896957397, "regret": 0.00012638219050131738, "entropy": 0.08077652752399445, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:26.350939Z", "loop": 15498, "env_steps": 9522585599, "loss": 0.015856588259339333, "avg_return": 0.8623089790344238, "regret": 0.00012638219050131738, "entropy": 0.07723117619752884, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:27.205876Z", "loop": 15499, "env_steps": 9523199999, "loss": 0.0162864588201046, "avg_return": 0.8626555800437927, "regret": 0.00012638219050131738, "entropy": 0.08239365369081497, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:28.097817Z", "loop": 15500, "env_steps": 9523814399, "loss": 0.01541925873607397, "avg_return": 0.8639630079269409, "regret": 0.00028531200950965285, "entropy": 0.07745610922574997, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:28.952217Z", "loop": 15501, "env_steps": 9524428799, "loss": 0.016339082270860672, "avg_return": 0.8618956804275513, "regret": 0.00028531200950965285, "entropy": 0.08194394409656525, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:29.805698Z", "loop": 15502, "env_steps": 9525043199, "loss": 0.017412830144166946, "avg_return": 0.8620712757110596, "regret": 0.00028531200950965285, "entropy": 0.08432145416736603, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:30.659991Z", "loop": 15503, "env_steps": 9525657599, "loss": 0.017561402171850204, "avg_return": 0.8620402216911316, "regret": 0.00028531200950965285, "entropy": 0.08334080129861832, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:31.514294Z", "loop": 15504, "env_steps": 9526271999, "loss": 0.01845601201057434, "avg_return": 0.8633484840393066, "regret": 0.00028531200950965285, "entropy": 0.08834648132324219, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:32.368694Z", "loop": 15505, "env_steps": 9526886399, "loss": 0.017130805179476738, "avg_return": 0.8634212613105774, "regret": 0.00028531200950965285, "entropy": 0.0862904042005539, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:33.222604Z", "loop": 15506, "env_steps": 9527500799, "loss": 0.017807452008128166, "avg_return": 0.8634663224220276, "regret": 0.00028531200950965285, "entropy": 0.0862915962934494, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:34.076253Z", "loop": 15507, "env_steps": 9528115199, "loss": 0.01795908994972706, "avg_return": 0.8626037836074829, "regret": 0.00028531200950965285, "entropy": 0.08706319332122803, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:34.930232Z", "loop": 15508, "env_steps": 9528729599, "loss": 0.01835543103516102, "avg_return": 0.8634796142578125, "regret": 0.00028531200950965285, "entropy": 0.09029491990804672, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:35.784557Z", "loop": 15509, "env_steps": 9529343999, "loss": 0.01757998950779438, "avg_return": 0.8620569109916687, "regret": 0.00028531200950965285, "entropy": 0.09246456623077393, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:36.676394Z", "loop": 15510, "env_steps": 9529958399, "loss": 0.01720612123608589, "avg_return": 0.8624544739723206, "regret": 0.0007550388691015542, "entropy": 0.08982247859239578, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:37.530420Z", "loop": 15511, "env_steps": 9530572799, "loss": 0.018211103975772858, "avg_return": 0.8632166981697083, "regret": 0.0007550388691015542, "entropy": 0.09108975529670715, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:38.383539Z", "loop": 15512, "env_steps": 9531187199, "loss": 0.01846413128077984, "avg_return": 0.8622556924819946, "regret": 0.0007550388691015542, "entropy": 0.09085217863321304, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:39.239440Z", "loop": 15513, "env_steps": 9531801599, "loss": 0.018394330516457558, "avg_return": 0.8620023727416992, "regret": 0.0007550388691015542, "entropy": 0.09138341248035431, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:40.094467Z", "loop": 15514, "env_steps": 9532415999, "loss": 0.017129411920905113, "avg_return": 0.8629367351531982, "regret": 0.0007550388691015542, "entropy": 0.08315223455429077, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:40.948517Z", "loop": 15515, "env_steps": 9533030399, "loss": 0.016319425776600838, "avg_return": 0.8634584546089172, "regret": 0.0007550388691015542, "entropy": 0.08136270940303802, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:41.802784Z", "loop": 15516, "env_steps": 9533644799, "loss": 0.01664075255393982, "avg_return": 0.8637188673019409, "regret": 0.0007550388691015542, "entropy": 0.08642534166574478, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:42.657619Z", "loop": 15517, "env_steps": 9534259199, "loss": 0.017038743942975998, "avg_return": 0.8636635541915894, "regret": 0.0007550388691015542, "entropy": 0.08402268588542938, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:43.512511Z", "loop": 15518, "env_steps": 9534873599, "loss": 0.01703745685517788, "avg_return": 0.8631805777549744, "regret": 0.0007550388691015542, "entropy": 0.08156657218933105, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:44.367316Z", "loop": 15519, "env_steps": 9535487999, "loss": 0.016138508915901184, "avg_return": 0.864144504070282, "regret": 0.0007550388691015542, "entropy": 0.08118800073862076, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:45.259189Z", "loop": 15520, "env_steps": 9536102399, "loss": 0.01581166684627533, "avg_return": 0.8634517788887024, "regret": 0.0003372090286575258, "entropy": 0.0763583779335022, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:46.114148Z", "loop": 15521, "env_steps": 9536716799, "loss": 0.01616835780441761, "avg_return": 0.8628650903701782, "regret": 0.0003372090286575258, "entropy": 0.07930368930101395, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:46.968634Z", "loop": 15522, "env_steps": 9537331199, "loss": 0.01653590239584446, "avg_return": 0.8627968430519104, "regret": 0.0003372090286575258, "entropy": 0.08115304261445999, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:47.823886Z", "loop": 15523, "env_steps": 9537945599, "loss": 0.015214434824883938, "avg_return": 0.8635060787200928, "regret": 0.0003372090286575258, "entropy": 0.07819029688835144, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:48.677599Z", "loop": 15524, "env_steps": 9538559999, "loss": 0.014456006698310375, "avg_return": 0.8638832569122314, "regret": 0.0003372090286575258, "entropy": 0.07354511320590973, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:49.531628Z", "loop": 15525, "env_steps": 9539174399, "loss": 0.014762694016098976, "avg_return": 0.8637410402297974, "regret": 0.0003372090286575258, "entropy": 0.07406304776668549, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:50.385147Z", "loop": 15526, "env_steps": 9539788799, "loss": 0.01569977216422558, "avg_return": 0.8637188076972961, "regret": 0.0003372090286575258, "entropy": 0.0764700248837471, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:51.238754Z", "loop": 15527, "env_steps": 9540403199, "loss": 0.01482158899307251, "avg_return": 0.8635768890380859, "regret": 0.0003372090286575258, "entropy": 0.07650622725486755, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:52.092943Z", "loop": 15528, "env_steps": 9541017599, "loss": 0.014903879724442959, "avg_return": 0.8620400428771973, "regret": 0.0003372090286575258, "entropy": 0.07745334506034851, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:52.946437Z", "loop": 15529, "env_steps": 9541631999, "loss": 0.015022351406514645, "avg_return": 0.8637779951095581, "regret": 0.0003372090286575258, "entropy": 0.0747564435005188, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:53.839207Z", "loop": 15530, "env_steps": 9542246399, "loss": 0.014083939604461193, "avg_return": 0.8636792302131653, "regret": 0.0003090416139457375, "entropy": 0.07272400707006454, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:54.692474Z", "loop": 15531, "env_steps": 9542860799, "loss": 0.01380632072687149, "avg_return": 0.8625165224075317, "regret": 0.0003090416139457375, "entropy": 0.0705607458949089, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:55.546808Z", "loop": 15532, "env_steps": 9543475199, "loss": 0.012044975534081459, "avg_return": 0.8639536499977112, "regret": 0.0003090416139457375, "entropy": 0.06368658691644669, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:56.400962Z", "loop": 15533, "env_steps": 9544089599, "loss": 0.012621707282960415, "avg_return": 0.8637831807136536, "regret": 0.0003090416139457375, "entropy": 0.06632301956415176, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:05:57.254159Z", "loop": 15534, "env_steps": 9544703999, "loss": 0.01164255291223526, "avg_return": 0.8637688159942627, "regret": 0.0003090416139457375, "entropy": 0.06271030753850937, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:03.426244Z", "loop": 15535, "env_steps": 9545318399, "loss": 0.012641835026443005, "avg_return": 0.8617456555366516, "regret": 0.0003090416139457375, "entropy": 0.06689921766519547, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:04.281546Z", "loop": 15536, "env_steps": 9545932799, "loss": 0.01181394699960947, "avg_return": 0.8623923063278198, "regret": 0.0003090416139457375, "entropy": 0.06422583013772964, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:05.136282Z", "loop": 15537, "env_steps": 9546547199, "loss": 0.013208587653934956, "avg_return": 0.8640018105506897, "regret": 0.0003090416139457375, "entropy": 0.06751982122659683, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:05.990182Z", "loop": 15538, "env_steps": 9547161599, "loss": 0.012202589772641659, "avg_return": 0.8633926510810852, "regret": 0.0003090416139457375, "entropy": 0.06535637378692627, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:06.844636Z", "loop": 15539, "env_steps": 9547775999, "loss": 0.011199837550520897, "avg_return": 0.8639052510261536, "regret": 0.0003090416139457375, "entropy": 0.0572778582572937, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:07.738510Z", "loop": 15540, "env_steps": 9548390399, "loss": 0.012001053430140018, "avg_return": 0.8635062575340271, "regret": 0.00037680158857256174, "entropy": 0.061627838760614395, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:08.593287Z", "loop": 15541, "env_steps": 9549004799, "loss": 0.01147882267832756, "avg_return": 0.8616862297058105, "regret": 0.00037680158857256174, "entropy": 0.062239281833171844, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:09.446544Z", "loop": 15542, "env_steps": 9549619199, "loss": 0.012428030371665955, "avg_return": 0.86334627866745, "regret": 0.00037680158857256174, "entropy": 0.06388960778713226, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:10.299589Z", "loop": 15543, "env_steps": 9550233599, "loss": 0.011759812943637371, "avg_return": 0.8638502955436707, "regret": 0.00037680158857256174, "entropy": 0.06248045712709427, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:11.153700Z", "loop": 15544, "env_steps": 9550847999, "loss": 0.01261516846716404, "avg_return": 0.8637874722480774, "regret": 0.00037680158857256174, "entropy": 0.06499823182821274, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:12.008448Z", "loop": 15545, "env_steps": 9551462399, "loss": 0.012451047077775002, "avg_return": 0.8628610372543335, "regret": 0.00037680158857256174, "entropy": 0.06336318701505661, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:12.862971Z", "loop": 15546, "env_steps": 9552076799, "loss": 0.011581930331885815, "avg_return": 0.8632725477218628, "regret": 0.00037680158857256174, "entropy": 0.06358301639556885, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:13.717495Z", "loop": 15547, "env_steps": 9552691199, "loss": 0.012252752669155598, "avg_return": 0.8627728223800659, "regret": 0.00037680158857256174, "entropy": 0.0635731965303421, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:14.571580Z", "loop": 15548, "env_steps": 9553305599, "loss": 0.012326999567449093, "avg_return": 0.8623858094215393, "regret": 0.00037680158857256174, "entropy": 0.061553385108709335, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:15.425892Z", "loop": 15549, "env_steps": 9553919999, "loss": 0.012394418008625507, "avg_return": 0.86185622215271, "regret": 0.00037680158857256174, "entropy": 0.0671561136841774, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:16.318787Z", "loop": 15550, "env_steps": 9554534399, "loss": 0.01066308282315731, "avg_return": 0.8637447357177734, "regret": 0.0006049062358215451, "entropy": 0.06004587188363075, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:17.172085Z", "loop": 15551, "env_steps": 9555148799, "loss": 0.012634179554879665, "avg_return": 0.863293468952179, "regret": 0.0006049062358215451, "entropy": 0.06339515745639801, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:18.025751Z", "loop": 15552, "env_steps": 9555763199, "loss": 0.011726317927241325, "avg_return": 0.8635321259498596, "regret": 0.0006049062358215451, "entropy": 0.06531167030334473, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:18.879878Z", "loop": 15553, "env_steps": 9556377599, "loss": 0.01313954871147871, "avg_return": 0.8634535670280457, "regret": 0.0006049062358215451, "entropy": 0.06675072014331818, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:19.733681Z", "loop": 15554, "env_steps": 9556991999, "loss": 0.013022854924201965, "avg_return": 0.8640628457069397, "regret": 0.0006049062358215451, "entropy": 0.07134551554918289, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:20.587590Z", "loop": 15555, "env_steps": 9557606399, "loss": 0.012791873887181282, "avg_return": 0.8619224429130554, "regret": 0.0006049062358215451, "entropy": 0.06579968333244324, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:21.442213Z", "loop": 15556, "env_steps": 9558220799, "loss": 0.013362253084778786, "avg_return": 0.8627380728721619, "regret": 0.0006049062358215451, "entropy": 0.07326572388410568, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:22.296589Z", "loop": 15557, "env_steps": 9558835199, "loss": 0.013479244895279408, "avg_return": 0.8630786538124084, "regret": 0.0006049062358215451, "entropy": 0.0715395137667656, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:23.150583Z", "loop": 15558, "env_steps": 9559449599, "loss": 0.014061440713703632, "avg_return": 0.8625189661979675, "regret": 0.0006049062358215451, "entropy": 0.07559581100940704, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:24.005328Z", "loop": 15559, "env_steps": 9560063999, "loss": 0.013644158840179443, "avg_return": 0.860981285572052, "regret": 0.0006049062358215451, "entropy": 0.07362137734889984, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:24.898060Z", "loop": 15560, "env_steps": 9560678399, "loss": 0.013721785508096218, "avg_return": 0.8598055243492126, "regret": 0.0025006968062371016, "entropy": 0.07660439610481262, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:25.751862Z", "loop": 15561, "env_steps": 9561292799, "loss": 0.015085609629750252, "avg_return": 0.8616776466369629, "regret": 0.0025006968062371016, "entropy": 0.07729765772819519, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:26.605374Z", "loop": 15562, "env_steps": 9561907199, "loss": 0.013897130265831947, "avg_return": 0.8604888916015625, "regret": 0.0025006968062371016, "entropy": 0.07572277635335922, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:27.459593Z", "loop": 15563, "env_steps": 9562521599, "loss": 0.015202092006802559, "avg_return": 0.8616525530815125, "regret": 0.0025006968062371016, "entropy": 0.07859179377555847, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:28.313399Z", "loop": 15564, "env_steps": 9563135999, "loss": 0.014747983776032925, "avg_return": 0.861221432685852, "regret": 0.0025006968062371016, "entropy": 0.07720012217760086, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:29.166629Z", "loop": 15565, "env_steps": 9563750399, "loss": 0.014177021570503712, "avg_return": 0.8617517352104187, "regret": 0.0025006968062371016, "entropy": 0.07646840065717697, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:30.020646Z", "loop": 15566, "env_steps": 9564364799, "loss": 0.013890773057937622, "avg_return": 0.8631498217582703, "regret": 0.0025006968062371016, "entropy": 0.07344349473714828, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:30.874449Z", "loop": 15567, "env_steps": 9564979199, "loss": 0.013705446384847164, "avg_return": 0.8624982833862305, "regret": 0.0025006968062371016, "entropy": 0.07091980427503586, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:31.728562Z", "loop": 15568, "env_steps": 9565593599, "loss": 0.013506178744137287, "avg_return": 0.8631852269172668, "regret": 0.0025006968062371016, "entropy": 0.07199165225028992, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:32.581132Z", "loop": 15569, "env_steps": 9566207999, "loss": 0.013605047948658466, "avg_return": 0.8626956343650818, "regret": 0.0025006968062371016, "entropy": 0.07067891955375671, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:33.472295Z", "loop": 15570, "env_steps": 9566822399, "loss": 0.012537190690636635, "avg_return": 0.8634617328643799, "regret": 0.00032668703352101147, "entropy": 0.06973584741353989, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:34.327433Z", "loop": 15571, "env_steps": 9567436799, "loss": 0.012968710623681545, "avg_return": 0.8624855875968933, "regret": 0.00032668703352101147, "entropy": 0.0689343810081482, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:35.181847Z", "loop": 15572, "env_steps": 9568051199, "loss": 0.012964191846549511, "avg_return": 0.861855685710907, "regret": 0.00032668703352101147, "entropy": 0.07174703478813171, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:36.035718Z", "loop": 15573, "env_steps": 9568665599, "loss": 0.014014164917171001, "avg_return": 0.863922119140625, "regret": 0.00032668703352101147, "entropy": 0.07244820892810822, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:36.889326Z", "loop": 15574, "env_steps": 9569279999, "loss": 0.014877267181873322, "avg_return": 0.8634564280509949, "regret": 0.00032668703352101147, "entropy": 0.0728648230433464, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:37.742842Z", "loop": 15575, "env_steps": 9569894399, "loss": 0.013329296372830868, "avg_return": 0.8637941479682922, "regret": 0.00032668703352101147, "entropy": 0.0700463280081749, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:38.598186Z", "loop": 15576, "env_steps": 9570508799, "loss": 0.013996814377605915, "avg_return": 0.86371910572052, "regret": 0.00032668703352101147, "entropy": 0.07265375554561615, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:39.453059Z", "loop": 15577, "env_steps": 9571123199, "loss": 0.012998322024941444, "avg_return": 0.862457275390625, "regret": 0.00032668703352101147, "entropy": 0.06950559467077255, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:40.306568Z", "loop": 15578, "env_steps": 9571737599, "loss": 0.014249828644096851, "avg_return": 0.8640725016593933, "regret": 0.00032668703352101147, "entropy": 0.07625900954008102, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:41.160144Z", "loop": 15579, "env_steps": 9572351999, "loss": 0.013909156434237957, "avg_return": 0.8625093698501587, "regret": 0.00032668703352101147, "entropy": 0.07747293263673782, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:42.053777Z", "loop": 15580, "env_steps": 9572966399, "loss": 0.014776808209717274, "avg_return": 0.8625486493110657, "regret": 0.00102343934122473, "entropy": 0.07719917595386505, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:42.908868Z", "loop": 15581, "env_steps": 9573580799, "loss": 0.01543064322322607, "avg_return": 0.8613037467002869, "regret": 0.00102343934122473, "entropy": 0.08194450289011002, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:43.763100Z", "loop": 15582, "env_steps": 9574195199, "loss": 0.015980752184987068, "avg_return": 0.861574113368988, "regret": 0.00102343934122473, "entropy": 0.08047603070735931, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:44.616455Z", "loop": 15583, "env_steps": 9574809599, "loss": 0.016856255009770393, "avg_return": 0.8634377121925354, "regret": 0.00102343934122473, "entropy": 0.08181644976139069, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:45.470090Z", "loop": 15584, "env_steps": 9575423999, "loss": 0.016277167946100235, "avg_return": 0.8623691201210022, "regret": 0.00102343934122473, "entropy": 0.07821854948997498, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:46.323991Z", "loop": 15585, "env_steps": 9576038399, "loss": 0.015623293817043304, "avg_return": 0.8637110590934753, "regret": 0.00102343934122473, "entropy": 0.07918673008680344, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:47.178096Z", "loop": 15586, "env_steps": 9576652799, "loss": 0.015439278446137905, "avg_return": 0.8639127612113953, "regret": 0.00102343934122473, "entropy": 0.07915057986974716, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:48.031408Z", "loop": 15587, "env_steps": 9577267199, "loss": 0.015126779675483704, "avg_return": 0.8638066053390503, "regret": 0.00102343934122473, "entropy": 0.07686745375394821, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:48.884888Z", "loop": 15588, "env_steps": 9577881599, "loss": 0.014171368442475796, "avg_return": 0.8626520037651062, "regret": 0.00102343934122473, "entropy": 0.07293550670146942, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:49.739794Z", "loop": 15589, "env_steps": 9578495999, "loss": 0.014379613101482391, "avg_return": 0.8625578880310059, "regret": 0.00102343934122473, "entropy": 0.07641465216875076, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:50.632557Z", "loop": 15590, "env_steps": 9579110399, "loss": 0.013712006621062756, "avg_return": 0.8630051612854004, "regret": 0.0005522291758097708, "entropy": 0.07294946163892746, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:51.486972Z", "loop": 15591, "env_steps": 9579724799, "loss": 0.013705591671168804, "avg_return": 0.8632192015647888, "regret": 0.0005522291758097708, "entropy": 0.07340816408395767, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:52.340865Z", "loop": 15592, "env_steps": 9580339199, "loss": 0.014281893149018288, "avg_return": 0.86319899559021, "regret": 0.0005522291758097708, "entropy": 0.07370976358652115, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:53.195259Z", "loop": 15593, "env_steps": 9580953599, "loss": 0.014212675392627716, "avg_return": 0.8634505271911621, "regret": 0.0005522291758097708, "entropy": 0.07447656244039536, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:54.050892Z", "loop": 15594, "env_steps": 9581567999, "loss": 0.013718785718083382, "avg_return": 0.8618075847625732, "regret": 0.0005522291758097708, "entropy": 0.07292504608631134, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:54.905695Z", "loop": 15595, "env_steps": 9582182399, "loss": 0.013528525829315186, "avg_return": 0.8627347946166992, "regret": 0.0005522291758097708, "entropy": 0.06924567371606827, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:55.761316Z", "loop": 15596, "env_steps": 9582796799, "loss": 0.012544097378849983, "avg_return": 0.862342119216919, "regret": 0.0005522291758097708, "entropy": 0.06759580224752426, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:56.615482Z", "loop": 15597, "env_steps": 9583411199, "loss": 0.013411437161266804, "avg_return": 0.8634989857673645, "regret": 0.0005522291758097708, "entropy": 0.06692951917648315, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:57.469956Z", "loop": 15598, "env_steps": 9584025599, "loss": 0.012505625374615192, "avg_return": 0.8636165857315063, "regret": 0.0005522291758097708, "entropy": 0.06693343073129654, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:58.324940Z", "loop": 15599, "env_steps": 9584639999, "loss": 0.012370927259325981, "avg_return": 0.8625512719154358, "regret": 0.0005522291758097708, "entropy": 0.06645923107862473, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:06:59.216509Z", "loop": 15600, "env_steps": 9585254399, "loss": 0.013278419151902199, "avg_return": 0.8641764521598816, "regret": 0.0002591166412457824, "entropy": 0.06724222749471664, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:00.070065Z", "loop": 15601, "env_steps": 9585868799, "loss": 0.012440736405551434, "avg_return": 0.8628910779953003, "regret": 0.0002591166412457824, "entropy": 0.06833275407552719, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:00.923676Z", "loop": 15602, "env_steps": 9586483199, "loss": 0.012820973992347717, "avg_return": 0.8627856373786926, "regret": 0.0002591166412457824, "entropy": 0.06806042045354843, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:01.778359Z", "loop": 15603, "env_steps": 9587097599, "loss": 0.011985129676759243, "avg_return": 0.8636823892593384, "regret": 0.0002591166412457824, "entropy": 0.06352458149194717, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:02.632529Z", "loop": 15604, "env_steps": 9587711999, "loss": 0.012340637855231762, "avg_return": 0.8631870746612549, "regret": 0.0002591166412457824, "entropy": 0.06376757472753525, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:03.486764Z", "loop": 15605, "env_steps": 9588326399, "loss": 0.012562437914311886, "avg_return": 0.8631117939949036, "regret": 0.0002591166412457824, "entropy": 0.0669330358505249, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:04.340280Z", "loop": 15606, "env_steps": 9588940799, "loss": 0.01311214454472065, "avg_return": 0.8622705340385437, "regret": 0.0002591166412457824, "entropy": 0.0677671805024147, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:05.194885Z", "loop": 15607, "env_steps": 9589555199, "loss": 0.012371888384222984, "avg_return": 0.8628220558166504, "regret": 0.0002591166412457824, "entropy": 0.06710998713970184, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:06.049599Z", "loop": 15608, "env_steps": 9590169599, "loss": 0.013281608931720257, "avg_return": 0.8641260266304016, "regret": 0.0002591166412457824, "entropy": 0.07106754183769226, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:06.903175Z", "loop": 15609, "env_steps": 9590783999, "loss": 0.012396848760545254, "avg_return": 0.8630245923995972, "regret": 0.0002591166412457824, "entropy": 0.06343283504247665, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:07.794160Z", "loop": 15610, "env_steps": 9591398399, "loss": 0.012652467004954815, "avg_return": 0.8634037375450134, "regret": 0.0002500339469406754, "entropy": 0.06901056319475174, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:08.648448Z", "loop": 15611, "env_steps": 9592012799, "loss": 0.01219235546886921, "avg_return": 0.8639477491378784, "regret": 0.0002500339469406754, "entropy": 0.06429865211248398, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:09.502682Z", "loop": 15612, "env_steps": 9592627199, "loss": 0.012061585672199726, "avg_return": 0.8631166815757751, "regret": 0.0002500339469406754, "entropy": 0.06142553687095642, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:10.356732Z", "loop": 15613, "env_steps": 9593241599, "loss": 0.013571010902523994, "avg_return": 0.862691342830658, "regret": 0.0002500339469406754, "entropy": 0.06707581877708435, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:11.211730Z", "loop": 15614, "env_steps": 9593855999, "loss": 0.012897237204015255, "avg_return": 0.863741397857666, "regret": 0.0002500339469406754, "entropy": 0.06683855503797531, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:12.066701Z", "loop": 15615, "env_steps": 9594470399, "loss": 0.013636779971420765, "avg_return": 0.8626731634140015, "regret": 0.0002500339469406754, "entropy": 0.07083074003458023, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:12.920226Z", "loop": 15616, "env_steps": 9595084799, "loss": 0.013231699354946613, "avg_return": 0.8625645041465759, "regret": 0.0002500339469406754, "entropy": 0.06581059098243713, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:13.773947Z", "loop": 15617, "env_steps": 9595699199, "loss": 0.01333389338105917, "avg_return": 0.8638116717338562, "regret": 0.0002500339469406754, "entropy": 0.07013197243213654, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:14.628301Z", "loop": 15618, "env_steps": 9596313599, "loss": 0.012911519967019558, "avg_return": 0.8629695773124695, "regret": 0.0002500339469406754, "entropy": 0.06853318214416504, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:15.481086Z", "loop": 15619, "env_steps": 9596927999, "loss": 0.014259730465710163, "avg_return": 0.8628909587860107, "regret": 0.0002500339469406754, "entropy": 0.07320698350667953, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:16.373125Z", "loop": 15620, "env_steps": 9597542399, "loss": 0.013828684575855732, "avg_return": 0.8617110252380371, "regret": 0.0010498068295419216, "entropy": 0.0725526511669159, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:17.227248Z", "loop": 15621, "env_steps": 9598156799, "loss": 0.01433978509157896, "avg_return": 0.8639654517173767, "regret": 0.0010498068295419216, "entropy": 0.07153528183698654, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:18.080977Z", "loop": 15622, "env_steps": 9598771199, "loss": 0.013592964969575405, "avg_return": 0.8606129884719849, "regret": 0.0010498068295419216, "entropy": 0.072630375623703, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:18.935292Z", "loop": 15623, "env_steps": 9599385599, "loss": 0.01513894647359848, "avg_return": 0.8620412349700928, "regret": 0.0010498068295419216, "entropy": 0.07684782892465591, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:19.789359Z", "loop": 15624, "env_steps": 9599999999, "loss": 0.014292641542851925, "avg_return": 0.8623177409172058, "regret": 0.0010498068295419216, "entropy": 0.07575661689043045, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:20.643875Z", "loop": 15625, "env_steps": 9600614399, "loss": 0.014447596855461597, "avg_return": 0.8626954555511475, "regret": 0.0010498068295419216, "entropy": 0.07267993688583374, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:21.498037Z", "loop": 15626, "env_steps": 9601228799, "loss": 0.014607774093747139, "avg_return": 0.8619534373283386, "regret": 0.0010498068295419216, "entropy": 0.07514806091785431, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:22.352434Z", "loop": 15627, "env_steps": 9601843199, "loss": 0.014855170622467995, "avg_return": 0.86307293176651, "regret": 0.0010498068295419216, "entropy": 0.07717461884021759, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:23.206153Z", "loop": 15628, "env_steps": 9602457599, "loss": 0.013394433073699474, "avg_return": 0.86426842212677, "regret": 0.0010498068295419216, "entropy": 0.06913165003061295, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:24.059766Z", "loop": 15629, "env_steps": 9603071999, "loss": 0.01391258742660284, "avg_return": 0.8614414930343628, "regret": 0.0010498068295419216, "entropy": 0.06833480298519135, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:24.953699Z", "loop": 15630, "env_steps": 9603686399, "loss": 0.013653026893734932, "avg_return": 0.8638854026794434, "regret": 0.00023007221170701087, "entropy": 0.06886745989322662, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:25.808673Z", "loop": 15631, "env_steps": 9604300799, "loss": 0.012046757154166698, "avg_return": 0.8634284734725952, "regret": 0.00023007221170701087, "entropy": 0.06433699280023575, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:26.663538Z", "loop": 15632, "env_steps": 9604915199, "loss": 0.0123031847178936, "avg_return": 0.8635584712028503, "regret": 0.00023007221170701087, "entropy": 0.06569621711969376, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:27.517246Z", "loop": 15633, "env_steps": 9605529599, "loss": 0.011677436530590057, "avg_return": 0.8634694814682007, "regret": 0.00023007221170701087, "entropy": 0.06618034839630127, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:28.372211Z", "loop": 15634, "env_steps": 9606143999, "loss": 0.014175571501255035, "avg_return": 0.8631640076637268, "regret": 0.00023007221170701087, "entropy": 0.06833784282207489, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:29.227313Z", "loop": 15635, "env_steps": 9606758399, "loss": 0.013126312755048275, "avg_return": 0.8632009029388428, "regret": 0.00023007221170701087, "entropy": 0.06680133938789368, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:30.082323Z", "loop": 15636, "env_steps": 9607372799, "loss": 0.012975305318832397, "avg_return": 0.8622786402702332, "regret": 0.00023007221170701087, "entropy": 0.06802522391080856, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:30.938909Z", "loop": 15637, "env_steps": 9607987199, "loss": 0.013360599055886269, "avg_return": 0.864404022693634, "regret": 0.00023007221170701087, "entropy": 0.0675383135676384, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:31.793170Z", "loop": 15638, "env_steps": 9608601599, "loss": 0.013651628978550434, "avg_return": 0.8626920580863953, "regret": 0.00023007221170701087, "entropy": 0.06572040915489197, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:32.648186Z", "loop": 15639, "env_steps": 9609215999, "loss": 0.012664166279137135, "avg_return": 0.863234281539917, "regret": 0.00023007221170701087, "entropy": 0.06728868931531906, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:33.542705Z", "loop": 15640, "env_steps": 9609830399, "loss": 0.013163546100258827, "avg_return": 0.8636314868927002, "regret": 0.00023799952759873122, "entropy": 0.06800086051225662, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:34.396054Z", "loop": 15641, "env_steps": 9610444799, "loss": 0.013065814971923828, "avg_return": 0.863974928855896, "regret": 0.00023799952759873122, "entropy": 0.0682937502861023, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:35.251552Z", "loop": 15642, "env_steps": 9611059199, "loss": 0.01249673217535019, "avg_return": 0.8652617335319519, "regret": 0.00023799952759873122, "entropy": 0.06775642931461334, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:36.105673Z", "loop": 15643, "env_steps": 9611673599, "loss": 0.012401738204061985, "avg_return": 0.8622347116470337, "regret": 0.00023799952759873122, "entropy": 0.06451069563627243, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:36.960046Z", "loop": 15644, "env_steps": 9612287999, "loss": 0.013240339234471321, "avg_return": 0.8616706728935242, "regret": 0.00023799952759873122, "entropy": 0.07047756016254425, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:37.814815Z", "loop": 15645, "env_steps": 9612902399, "loss": 0.013266394846141338, "avg_return": 0.8626490235328674, "regret": 0.00023799952759873122, "entropy": 0.07341162860393524, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:38.668841Z", "loop": 15646, "env_steps": 9613516799, "loss": 0.014023876748979092, "avg_return": 0.861866295337677, "regret": 0.00023799952759873122, "entropy": 0.07502425462007523, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:39.522600Z", "loop": 15647, "env_steps": 9614131199, "loss": 0.015050830319523811, "avg_return": 0.8610907196998596, "regret": 0.00023799952759873122, "entropy": 0.08025806397199631, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:40.376091Z", "loop": 15648, "env_steps": 9614745599, "loss": 0.014595918357372284, "avg_return": 0.8602457642555237, "regret": 0.00023799952759873122, "entropy": 0.07713634520769119, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:41.229793Z", "loop": 15649, "env_steps": 9615359999, "loss": 0.014866799116134644, "avg_return": 0.8618011474609375, "regret": 0.00023799952759873122, "entropy": 0.07923169434070587, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:42.124320Z", "loop": 15650, "env_steps": 9615974399, "loss": 0.013095967471599579, "avg_return": 0.8626230955123901, "regret": 0.0008353315643034875, "entropy": 0.07018200308084488, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:42.977637Z", "loop": 15651, "env_steps": 9616588799, "loss": 0.013033481314778328, "avg_return": 0.8625781536102295, "regret": 0.0008353315643034875, "entropy": 0.0661732479929924, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:43.831587Z", "loop": 15652, "env_steps": 9617203199, "loss": 0.013171294704079628, "avg_return": 0.861921489238739, "regret": 0.0008353315643034875, "entropy": 0.06818936765193939, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:44.686077Z", "loop": 15653, "env_steps": 9617817599, "loss": 0.012895869091153145, "avg_return": 0.8632184267044067, "regret": 0.0008353315643034875, "entropy": 0.06751684099435806, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:45.541904Z", "loop": 15654, "env_steps": 9618431999, "loss": 0.014302687719464302, "avg_return": 0.8630019426345825, "regret": 0.0008353315643034875, "entropy": 0.07567135989665985, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:46.396334Z", "loop": 15655, "env_steps": 9619046399, "loss": 0.015376006253063679, "avg_return": 0.8642550706863403, "regret": 0.0008353315643034875, "entropy": 0.07585272938013077, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:47.251491Z", "loop": 15656, "env_steps": 9619660799, "loss": 0.01490072626620531, "avg_return": 0.8628841638565063, "regret": 0.0008353315643034875, "entropy": 0.0757271870970726, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:48.106084Z", "loop": 15657, "env_steps": 9620275199, "loss": 0.01597587577998638, "avg_return": 0.8621454238891602, "regret": 0.0008353315643034875, "entropy": 0.08188457041978836, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:48.960397Z", "loop": 15658, "env_steps": 9620889599, "loss": 0.014953535981476307, "avg_return": 0.8633557558059692, "regret": 0.0008353315643034875, "entropy": 0.07726810872554779, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:49.813880Z", "loop": 15659, "env_steps": 9621503999, "loss": 0.015977120026946068, "avg_return": 0.863419234752655, "regret": 0.0008353315643034875, "entropy": 0.07950209081172943, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:50.708908Z", "loop": 15660, "env_steps": 9622118399, "loss": 0.016307787969708443, "avg_return": 0.8614546656608582, "regret": 0.0010563379619270563, "entropy": 0.08465339988470078, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:51.563090Z", "loop": 15661, "env_steps": 9622732799, "loss": 0.01586144231259823, "avg_return": 0.8625388741493225, "regret": 0.0010563379619270563, "entropy": 0.07930002361536026, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:52.419463Z", "loop": 15662, "env_steps": 9623347199, "loss": 0.018203070387244225, "avg_return": 0.8620918989181519, "regret": 0.0010563379619270563, "entropy": 0.0905260294675827, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:53.273661Z", "loop": 15663, "env_steps": 9623961599, "loss": 0.01930522918701172, "avg_return": 0.8629597425460815, "regret": 0.0010563379619270563, "entropy": 0.09405823796987534, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:54.126754Z", "loop": 15664, "env_steps": 9624575999, "loss": 0.02112646959722042, "avg_return": 0.8616476655006409, "regret": 0.0010563379619270563, "entropy": 0.09743436425924301, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:54.979686Z", "loop": 15665, "env_steps": 9625190399, "loss": 0.020947473123669624, "avg_return": 0.863459587097168, "regret": 0.0010563379619270563, "entropy": 0.09903081506490707, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:55.833941Z", "loop": 15666, "env_steps": 9625804799, "loss": 0.01995679922401905, "avg_return": 0.8626377582550049, "regret": 0.0010563379619270563, "entropy": 0.0998198390007019, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:56.688637Z", "loop": 15667, "env_steps": 9626419199, "loss": 0.020530564710497856, "avg_return": 0.8616109490394592, "regret": 0.0010563379619270563, "entropy": 0.10283424705266953, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:57.542826Z", "loop": 15668, "env_steps": 9627033599, "loss": 0.021870270371437073, "avg_return": 0.8626501560211182, "regret": 0.0010563379619270563, "entropy": 0.10386807471513748, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:58.395776Z", "loop": 15669, "env_steps": 9627647999, "loss": 0.022433528676629066, "avg_return": 0.8624301552772522, "regret": 0.0010563379619270563, "entropy": 0.10540946573019028, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:07:59.288931Z", "loop": 15670, "env_steps": 9628262399, "loss": 0.022831715643405914, "avg_return": 0.8619046211242676, "regret": 0.0010354021796956658, "entropy": 0.10871239751577377, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:00.144065Z", "loop": 15671, "env_steps": 9628876799, "loss": 0.021265430375933647, "avg_return": 0.8634454607963562, "regret": 0.0010354021796956658, "entropy": 0.10184674710035324, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:00.998293Z", "loop": 15672, "env_steps": 9629491199, "loss": 0.020192285999655724, "avg_return": 0.8636472821235657, "regret": 0.0010354021796956658, "entropy": 0.09928366541862488, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:01.852162Z", "loop": 15673, "env_steps": 9630105599, "loss": 0.019460106268525124, "avg_return": 0.8624817132949829, "regret": 0.0010354021796956658, "entropy": 0.0981469452381134, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:02.706520Z", "loop": 15674, "env_steps": 9630719999, "loss": 0.019606813788414, "avg_return": 0.8623521327972412, "regret": 0.0010354021796956658, "entropy": 0.0962824746966362, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:03.560645Z", "loop": 15675, "env_steps": 9631334399, "loss": 0.018916096538305283, "avg_return": 0.8633691668510437, "regret": 0.0010354021796956658, "entropy": 0.09152030944824219, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:04.414952Z", "loop": 15676, "env_steps": 9631948799, "loss": 0.018460264429450035, "avg_return": 0.8627419471740723, "regret": 0.0010354021796956658, "entropy": 0.09327184408903122, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:05.267927Z", "loop": 15677, "env_steps": 9632563199, "loss": 0.0171668641269207, "avg_return": 0.861686646938324, "regret": 0.0010354021796956658, "entropy": 0.08953838795423508, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:06.121409Z", "loop": 15678, "env_steps": 9633177599, "loss": 0.018221288919448853, "avg_return": 0.8634401559829712, "regret": 0.0010354021796956658, "entropy": 0.09133823215961456, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:06.975789Z", "loop": 15679, "env_steps": 9633791999, "loss": 0.019396547228097916, "avg_return": 0.8630582690238953, "regret": 0.0010354021796956658, "entropy": 0.0929129421710968, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:07.871709Z", "loop": 15680, "env_steps": 9634406399, "loss": 0.0186830572783947, "avg_return": 0.8626965284347534, "regret": 0.0008014612249098718, "entropy": 0.09368504583835602, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:08.726092Z", "loop": 15681, "env_steps": 9635020799, "loss": 0.01918838918209076, "avg_return": 0.8624805808067322, "regret": 0.0008014612249098718, "entropy": 0.09703283756971359, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:09.580196Z", "loop": 15682, "env_steps": 9635635199, "loss": 0.01945851929485798, "avg_return": 0.8616904616355896, "regret": 0.0008014612249098718, "entropy": 0.09725096076726913, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:10.433231Z", "loop": 15683, "env_steps": 9636249599, "loss": 0.019270040094852448, "avg_return": 0.8616787791252136, "regret": 0.0008014612249098718, "entropy": 0.1003291979432106, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:11.288995Z", "loop": 15684, "env_steps": 9636863999, "loss": 0.0188083928078413, "avg_return": 0.8642742037773132, "regret": 0.0008014612249098718, "entropy": 0.09640076011419296, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:12.145612Z", "loop": 15685, "env_steps": 9637478399, "loss": 0.019897477701306343, "avg_return": 0.8628641963005066, "regret": 0.0008014612249098718, "entropy": 0.09792952239513397, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:12.999502Z", "loop": 15686, "env_steps": 9638092799, "loss": 0.019581474363803864, "avg_return": 0.8638993501663208, "regret": 0.0008014612249098718, "entropy": 0.09873326867818832, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:13.851955Z", "loop": 15687, "env_steps": 9638707199, "loss": 0.018999332562088966, "avg_return": 0.8619600534439087, "regret": 0.0008014612249098718, "entropy": 0.09901533275842667, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:14.704994Z", "loop": 15688, "env_steps": 9639321599, "loss": 0.02069755271077156, "avg_return": 0.862790048122406, "regret": 0.0008014612249098718, "entropy": 0.10405425727367401, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:15.559996Z", "loop": 15689, "env_steps": 9639935999, "loss": 0.020622020587325096, "avg_return": 0.862769365310669, "regret": 0.0008014612249098718, "entropy": 0.10493604093790054, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:16.454290Z", "loop": 15690, "env_steps": 9640550399, "loss": 0.019690722227096558, "avg_return": 0.8624127507209778, "regret": 0.0005746036185882986, "entropy": 0.10051454603672028, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:17.307531Z", "loop": 15691, "env_steps": 9641164799, "loss": 0.019908668473362923, "avg_return": 0.8625713586807251, "regret": 0.0005746036185882986, "entropy": 0.10142066329717636, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:18.161714Z", "loop": 15692, "env_steps": 9641779199, "loss": 0.020961077883839607, "avg_return": 0.86362224817276, "regret": 0.0005746036185882986, "entropy": 0.10410401225090027, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:19.015907Z", "loop": 15693, "env_steps": 9642393599, "loss": 0.019769420847296715, "avg_return": 0.8627855777740479, "regret": 0.0005746036185882986, "entropy": 0.09638720750808716, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:19.870143Z", "loop": 15694, "env_steps": 9643007999, "loss": 0.02051098830997944, "avg_return": 0.8626397848129272, "regret": 0.0005746036185882986, "entropy": 0.1012905016541481, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:20.724079Z", "loop": 15695, "env_steps": 9643622399, "loss": 0.021566545590758324, "avg_return": 0.8629967570304871, "regret": 0.0005746036185882986, "entropy": 0.10143210738897324, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:21.576678Z", "loop": 15696, "env_steps": 9644236799, "loss": 0.021641086786985397, "avg_return": 0.8643497824668884, "regret": 0.0005746036185882986, "entropy": 0.10266169905662537, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:22.430167Z", "loop": 15697, "env_steps": 9644851199, "loss": 0.020901381969451904, "avg_return": 0.8632091283798218, "regret": 0.0005746036185882986, "entropy": 0.10235860198736191, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:23.285093Z", "loop": 15698, "env_steps": 9645465599, "loss": 0.020540961995720863, "avg_return": 0.863505482673645, "regret": 0.0005746036185882986, "entropy": 0.10241081565618515, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:24.140100Z", "loop": 15699, "env_steps": 9646079999, "loss": 0.019832270219922066, "avg_return": 0.8637576699256897, "regret": 0.0005746036185882986, "entropy": 0.10196665674448013, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:25.035459Z", "loop": 15700, "env_steps": 9646694399, "loss": 0.018455034121870995, "avg_return": 0.8644250631332397, "regret": 0.0005114303203299642, "entropy": 0.0947040319442749, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:25.890431Z", "loop": 15701, "env_steps": 9647308799, "loss": 0.019534163177013397, "avg_return": 0.8633437156677246, "regret": 0.0005114303203299642, "entropy": 0.09571980684995651, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:26.745465Z", "loop": 15702, "env_steps": 9647923199, "loss": 0.020438572391867638, "avg_return": 0.8628005981445312, "regret": 0.0005114303203299642, "entropy": 0.10036429017782211, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:27.599630Z", "loop": 15703, "env_steps": 9648537599, "loss": 0.019047435373067856, "avg_return": 0.8630422353744507, "regret": 0.0005114303203299642, "entropy": 0.09483989328145981, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:28.453318Z", "loop": 15704, "env_steps": 9649151999, "loss": 0.01741885207593441, "avg_return": 0.863243043422699, "regret": 0.0005114303203299642, "entropy": 0.09329301863908768, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:29.307490Z", "loop": 15705, "env_steps": 9649766399, "loss": 0.018032629042863846, "avg_return": 0.8623185157775879, "regret": 0.0005114303203299642, "entropy": 0.09325206279754639, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:30.161516Z", "loop": 15706, "env_steps": 9650380799, "loss": 0.0172857865691185, "avg_return": 0.8631412982940674, "regret": 0.0005114303203299642, "entropy": 0.08688511699438095, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:31.015565Z", "loop": 15707, "env_steps": 9650995199, "loss": 0.018157120794057846, "avg_return": 0.863223671913147, "regret": 0.0005114303203299642, "entropy": 0.09263207018375397, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:31.869200Z", "loop": 15708, "env_steps": 9651609599, "loss": 0.016622167080640793, "avg_return": 0.8628702759742737, "regret": 0.0005114303203299642, "entropy": 0.08538876473903656, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:32.724023Z", "loop": 15709, "env_steps": 9652223999, "loss": 0.017840798944234848, "avg_return": 0.8631300330162048, "regret": 0.0005114303203299642, "entropy": 0.08845147490501404, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:33.616559Z", "loop": 15710, "env_steps": 9652838399, "loss": 0.017278043553233147, "avg_return": 0.8634936809539795, "regret": 0.0006306683062575758, "entropy": 0.08640840649604797, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:34.471195Z", "loop": 15711, "env_steps": 9653452799, "loss": 0.017065241932868958, "avg_return": 0.8624148964881897, "regret": 0.0006306683062575758, "entropy": 0.08863271772861481, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:35.325651Z", "loop": 15712, "env_steps": 9654067199, "loss": 0.016044287011027336, "avg_return": 0.861494779586792, "regret": 0.0006306683062575758, "entropy": 0.08175716549158096, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:36.181014Z", "loop": 15713, "env_steps": 9654681599, "loss": 0.01700003258883953, "avg_return": 0.8610599040985107, "regret": 0.0006306683062575758, "entropy": 0.08700188249349594, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:37.036421Z", "loop": 15714, "env_steps": 9655295999, "loss": 0.015693556517362595, "avg_return": 0.8627249598503113, "regret": 0.0006306683062575758, "entropy": 0.08302238583564758, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:37.890026Z", "loop": 15715, "env_steps": 9655910399, "loss": 0.016389887779951096, "avg_return": 0.8626511693000793, "regret": 0.0006306683062575758, "entropy": 0.08034983277320862, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:38.744458Z", "loop": 15716, "env_steps": 9656524799, "loss": 0.016504544764757156, "avg_return": 0.8618389964103699, "regret": 0.0006306683062575758, "entropy": 0.0786110982298851, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:39.599765Z", "loop": 15717, "env_steps": 9657139199, "loss": 0.015841098502278328, "avg_return": 0.8630121350288391, "regret": 0.0006306683062575758, "entropy": 0.08145356923341751, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:40.454056Z", "loop": 15718, "env_steps": 9657753599, "loss": 0.016329295933246613, "avg_return": 0.8623335957527161, "regret": 0.0006306683062575758, "entropy": 0.0829302966594696, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:41.308866Z", "loop": 15719, "env_steps": 9658367999, "loss": 0.015312603674829006, "avg_return": 0.8622666597366333, "regret": 0.0006306683062575758, "entropy": 0.08031418919563293, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:42.202801Z", "loop": 15720, "env_steps": 9658982399, "loss": 0.014996080659329891, "avg_return": 0.8627549409866333, "regret": 0.0007992653409019113, "entropy": 0.08094947040081024, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:43.057834Z", "loop": 15721, "env_steps": 9659596799, "loss": 0.014725424349308014, "avg_return": 0.862735390663147, "regret": 0.0007992653409019113, "entropy": 0.07848622649908066, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:43.912940Z", "loop": 15722, "env_steps": 9660211199, "loss": 0.016900619491934776, "avg_return": 0.8636208176612854, "regret": 0.0007992653409019113, "entropy": 0.08235020935535431, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:44.766668Z", "loop": 15723, "env_steps": 9660825599, "loss": 0.01606818102300167, "avg_return": 0.8634616136550903, "regret": 0.0007992653409019113, "entropy": 0.08177156001329422, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:45.621346Z", "loop": 15724, "env_steps": 9661439999, "loss": 0.016444457694888115, "avg_return": 0.8635365962982178, "regret": 0.0007992653409019113, "entropy": 0.08432326465845108, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:46.476494Z", "loop": 15725, "env_steps": 9662054399, "loss": 0.01610458269715309, "avg_return": 0.8625810146331787, "regret": 0.0007992653409019113, "entropy": 0.08476985991001129, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:47.331188Z", "loop": 15726, "env_steps": 9662668799, "loss": 0.017351122573018074, "avg_return": 0.8627327680587769, "regret": 0.0007992653409019113, "entropy": 0.08654323220252991, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:48.185346Z", "loop": 15727, "env_steps": 9663283199, "loss": 0.016783708706498146, "avg_return": 0.8607237935066223, "regret": 0.0007992653409019113, "entropy": 0.0850951075553894, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:49.038801Z", "loop": 15728, "env_steps": 9663897599, "loss": 0.015806060284376144, "avg_return": 0.862610399723053, "regret": 0.0007992653409019113, "entropy": 0.08128410577774048, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:49.893518Z", "loop": 15729, "env_steps": 9664511999, "loss": 0.015746554359793663, "avg_return": 0.8632894158363342, "regret": 0.0007992653409019113, "entropy": 0.08148728311061859, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:50.787356Z", "loop": 15730, "env_steps": 9665126399, "loss": 0.016313480213284492, "avg_return": 0.8622097969055176, "regret": 0.0005685215000994503, "entropy": 0.08205333352088928, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:51.641841Z", "loop": 15731, "env_steps": 9665740799, "loss": 0.016119880601763725, "avg_return": 0.8621647357940674, "regret": 0.0005685215000994503, "entropy": 0.08320119231939316, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:52.495656Z", "loop": 15732, "env_steps": 9666355199, "loss": 0.016632338985800743, "avg_return": 0.8632675409317017, "regret": 0.0005685215000994503, "entropy": 0.08244721591472626, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:53.351063Z", "loop": 15733, "env_steps": 9666969599, "loss": 0.0162209402769804, "avg_return": 0.863681972026825, "regret": 0.0005685215000994503, "entropy": 0.08302025496959686, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:54.206612Z", "loop": 15734, "env_steps": 9667583999, "loss": 0.01723385788500309, "avg_return": 0.8633996844291687, "regret": 0.0005685215000994503, "entropy": 0.08327268064022064, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:55.061845Z", "loop": 15735, "env_steps": 9668198399, "loss": 0.017562158405780792, "avg_return": 0.8632732629776001, "regret": 0.0005685215000994503, "entropy": 0.08889530599117279, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:55.917718Z", "loop": 15736, "env_steps": 9668812799, "loss": 0.01781705766916275, "avg_return": 0.8635751605033875, "regret": 0.0005685215000994503, "entropy": 0.08632411062717438, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:56.771847Z", "loop": 15737, "env_steps": 9669427199, "loss": 0.01948816329240799, "avg_return": 0.8623909950256348, "regret": 0.0005685215000994503, "entropy": 0.0961076095700264, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:57.627703Z", "loop": 15738, "env_steps": 9670041599, "loss": 0.02048405632376671, "avg_return": 0.8630897402763367, "regret": 0.0005685215000994503, "entropy": 0.09617558121681213, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:58.482865Z", "loop": 15739, "env_steps": 9670655999, "loss": 0.019941100850701332, "avg_return": 0.8628948330879211, "regret": 0.0005685215000994503, "entropy": 0.09444145113229752, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:08:59.378444Z", "loop": 15740, "env_steps": 9671270399, "loss": 0.020284000784158707, "avg_return": 0.863159716129303, "regret": 0.000162590789841488, "entropy": 0.09675223380327225, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:00.231982Z", "loop": 15741, "env_steps": 9671884799, "loss": 0.020012350752949715, "avg_return": 0.8635638356208801, "regret": 0.000162590789841488, "entropy": 0.09527377039194107, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:01.085955Z", "loop": 15742, "env_steps": 9672499199, "loss": 0.019791780039668083, "avg_return": 0.8632776141166687, "regret": 0.000162590789841488, "entropy": 0.09285528212785721, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:01.940780Z", "loop": 15743, "env_steps": 9673113599, "loss": 0.02005574107170105, "avg_return": 0.864101767539978, "regret": 0.000162590789841488, "entropy": 0.09183766692876816, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:02.795774Z", "loop": 15744, "env_steps": 9673727999, "loss": 0.02108667604625225, "avg_return": 0.863975465297699, "regret": 0.000162590789841488, "entropy": 0.10189862549304962, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:03.649613Z", "loop": 15745, "env_steps": 9674342399, "loss": 0.022178299725055695, "avg_return": 0.8625596165657043, "regret": 0.000162590789841488, "entropy": 0.10333329439163208, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:04.503009Z", "loop": 15746, "env_steps": 9674956799, "loss": 0.021740024909377098, "avg_return": 0.8634224534034729, "regret": 0.000162590789841488, "entropy": 0.10369255393743515, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:05.356658Z", "loop": 15747, "env_steps": 9675571199, "loss": 0.021241141483187675, "avg_return": 0.8623051047325134, "regret": 0.000162590789841488, "entropy": 0.10241512209177017, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:06.211928Z", "loop": 15748, "env_steps": 9676185599, "loss": 0.018504900857806206, "avg_return": 0.8644216060638428, "regret": 0.000162590789841488, "entropy": 0.091371551156044, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:07.066643Z", "loop": 15749, "env_steps": 9676799999, "loss": 0.017694151028990746, "avg_return": 0.864726185798645, "regret": 0.000162590789841488, "entropy": 0.08647296577692032, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:07.959131Z", "loop": 15750, "env_steps": 9677414399, "loss": 0.01808314025402069, "avg_return": 0.862906813621521, "regret": 0.0001103551039705053, "entropy": 0.08772207051515579, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:08.813116Z", "loop": 15751, "env_steps": 9678028799, "loss": 0.017000311985611916, "avg_return": 0.8635754585266113, "regret": 0.0001103551039705053, "entropy": 0.08164855092763901, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:09.667953Z", "loop": 15752, "env_steps": 9678643199, "loss": 0.01757182367146015, "avg_return": 0.8644639253616333, "regret": 0.0001103551039705053, "entropy": 0.08630398660898209, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:10.522988Z", "loop": 15753, "env_steps": 9679257599, "loss": 0.016627125442028046, "avg_return": 0.8638681173324585, "regret": 0.0001103551039705053, "entropy": 0.08115199208259583, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:11.377549Z", "loop": 15754, "env_steps": 9679871999, "loss": 0.016026703640818596, "avg_return": 0.8641699552536011, "regret": 0.0001103551039705053, "entropy": 0.08060140162706375, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:12.231162Z", "loop": 15755, "env_steps": 9680486399, "loss": 0.015205620788037777, "avg_return": 0.8647491931915283, "regret": 0.0001103551039705053, "entropy": 0.07929734885692596, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:13.084539Z", "loop": 15756, "env_steps": 9681100799, "loss": 0.0157353263348341, "avg_return": 0.8635600209236145, "regret": 0.0001103551039705053, "entropy": 0.07706348598003387, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:13.939739Z", "loop": 15757, "env_steps": 9681715199, "loss": 0.015113495290279388, "avg_return": 0.8630906343460083, "regret": 0.0001103551039705053, "entropy": 0.07409120351076126, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:14.794939Z", "loop": 15758, "env_steps": 9682329599, "loss": 0.015304799191653728, "avg_return": 0.8636763691902161, "regret": 0.0001103551039705053, "entropy": 0.07775504142045975, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:15.648516Z", "loop": 15759, "env_steps": 9682943999, "loss": 0.016566019505262375, "avg_return": 0.8630833029747009, "regret": 0.0001103551039705053, "entropy": 0.07739637792110443, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:16.540367Z", "loop": 15760, "env_steps": 9683558399, "loss": 0.015291738323867321, "avg_return": 0.8653519153594971, "regret": 0.00014282962365541607, "entropy": 0.07720701396465302, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:17.395618Z", "loop": 15761, "env_steps": 9684172799, "loss": 0.014421887695789337, "avg_return": 0.8650515675544739, "regret": 0.00014282962365541607, "entropy": 0.07073734700679779, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:18.250413Z", "loop": 15762, "env_steps": 9684787199, "loss": 0.014238174073398113, "avg_return": 0.8633461594581604, "regret": 0.00014282962365541607, "entropy": 0.07370022684335709, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:19.104533Z", "loop": 15763, "env_steps": 9685401599, "loss": 0.013675137422978878, "avg_return": 0.8626036047935486, "regret": 0.00014282962365541607, "entropy": 0.07241272181272507, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:19.958064Z", "loop": 15764, "env_steps": 9686015999, "loss": 0.013836311176419258, "avg_return": 0.8644399046897888, "regret": 0.00014282962365541607, "entropy": 0.06960287690162659, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:20.812858Z", "loop": 15765, "env_steps": 9686630399, "loss": 0.012935205362737179, "avg_return": 0.8630602359771729, "regret": 0.00014282962365541607, "entropy": 0.06870395690202713, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:21.667568Z", "loop": 15766, "env_steps": 9687244799, "loss": 0.013881427235901356, "avg_return": 0.862257719039917, "regret": 0.00014282962365541607, "entropy": 0.06945914030075073, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:22.522258Z", "loop": 15767, "env_steps": 9687859199, "loss": 0.012291236780583858, "avg_return": 0.8647407293319702, "regret": 0.00014282962365541607, "entropy": 0.06487762928009033, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:23.376484Z", "loop": 15768, "env_steps": 9688473599, "loss": 0.011799032799899578, "avg_return": 0.8642311692237854, "regret": 0.00014282962365541607, "entropy": 0.06155678629875183, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:24.230751Z", "loop": 15769, "env_steps": 9689087999, "loss": 0.012397784739732742, "avg_return": 0.8630547523498535, "regret": 0.00014282962365541607, "entropy": 0.0647406056523323, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:25.124671Z", "loop": 15770, "env_steps": 9689702399, "loss": 0.010574695654213428, "avg_return": 0.8630180954933167, "regret": 0.00033039861591532826, "entropy": 0.05773070827126503, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:25.979193Z", "loop": 15771, "env_steps": 9690316799, "loss": 0.011824642308056355, "avg_return": 0.8629285097122192, "regret": 0.00033039861591532826, "entropy": 0.06260276585817337, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:26.834279Z", "loop": 15772, "env_steps": 9690931199, "loss": 0.01173305045813322, "avg_return": 0.8638653755187988, "regret": 0.00033039861591532826, "entropy": 0.059488795697689056, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:27.689358Z", "loop": 15773, "env_steps": 9691545599, "loss": 0.012390147894620895, "avg_return": 0.8636061549186707, "regret": 0.00033039861591532826, "entropy": 0.06356172263622284, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:28.543686Z", "loop": 15774, "env_steps": 9692159999, "loss": 0.011069233529269695, "avg_return": 0.8636161684989929, "regret": 0.00033039861591532826, "entropy": 0.05827939137816429, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:29.398006Z", "loop": 15775, "env_steps": 9692774399, "loss": 0.011085291393101215, "avg_return": 0.8637939691543579, "regret": 0.00033039861591532826, "entropy": 0.05989168956875801, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:30.251781Z", "loop": 15776, "env_steps": 9693388799, "loss": 0.012412692420184612, "avg_return": 0.8628159761428833, "regret": 0.00033039861591532826, "entropy": 0.06497443467378616, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:31.105748Z", "loop": 15777, "env_steps": 9694003199, "loss": 0.011117765679955482, "avg_return": 0.862415611743927, "regret": 0.00033039861591532826, "entropy": 0.060107916593551636, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:31.959600Z", "loop": 15778, "env_steps": 9694617599, "loss": 0.012710923328995705, "avg_return": 0.8621206879615784, "regret": 0.00033039861591532826, "entropy": 0.06834827363491058, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:32.814474Z", "loop": 15779, "env_steps": 9695231999, "loss": 0.012393591925501823, "avg_return": 0.8638630509376526, "regret": 0.00033039861591532826, "entropy": 0.06520724296569824, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:33.707188Z", "loop": 15780, "env_steps": 9695846399, "loss": 0.01243587676435709, "avg_return": 0.8622702360153198, "regret": 0.0006325665162876248, "entropy": 0.06652968376874924, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:34.561458Z", "loop": 15781, "env_steps": 9696460799, "loss": 0.011473435908555984, "avg_return": 0.8625224232673645, "regret": 0.0006325665162876248, "entropy": 0.06339679658412933, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:35.415270Z", "loop": 15782, "env_steps": 9697075199, "loss": 0.012106968089938164, "avg_return": 0.8634243011474609, "regret": 0.0006325665162876248, "entropy": 0.06482759863138199, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:36.269500Z", "loop": 15783, "env_steps": 9697689599, "loss": 0.013033747673034668, "avg_return": 0.8631136417388916, "regret": 0.0006325665162876248, "entropy": 0.06472094357013702, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:37.123468Z", "loop": 15784, "env_steps": 9698303999, "loss": 0.012406607158482075, "avg_return": 0.8637378215789795, "regret": 0.0006325665162876248, "entropy": 0.06653092056512833, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:37.977953Z", "loop": 15785, "env_steps": 9698918399, "loss": 0.011382284574210644, "avg_return": 0.8641502857208252, "regret": 0.0006325665162876248, "entropy": 0.06154781952500343, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:38.831633Z", "loop": 15786, "env_steps": 9699532799, "loss": 0.012056025676429272, "avg_return": 0.8628523945808411, "regret": 0.0006325665162876248, "entropy": 0.05935141071677208, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:39.686597Z", "loop": 15787, "env_steps": 9700147199, "loss": 0.011134102009236813, "avg_return": 0.8620821237564087, "regret": 0.0006325665162876248, "entropy": 0.05946081131696701, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:40.541438Z", "loop": 15788, "env_steps": 9700761599, "loss": 0.011194877326488495, "avg_return": 0.8620835542678833, "regret": 0.0006325665162876248, "entropy": 0.06301930546760559, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:41.395773Z", "loop": 15789, "env_steps": 9701375999, "loss": 0.011437083594501019, "avg_return": 0.8627814054489136, "regret": 0.0006325665162876248, "entropy": 0.06455373764038086, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:42.288415Z", "loop": 15790, "env_steps": 9701990399, "loss": 0.011936313472688198, "avg_return": 0.86163330078125, "regret": 0.0010344048496335745, "entropy": 0.06446165591478348, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:43.141868Z", "loop": 15791, "env_steps": 9702604799, "loss": 0.01262450497597456, "avg_return": 0.8632664084434509, "regret": 0.0010344048496335745, "entropy": 0.06475061178207397, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:43.996127Z", "loop": 15792, "env_steps": 9703219199, "loss": 0.011156836524605751, "avg_return": 0.862115204334259, "regret": 0.0010344048496335745, "entropy": 0.0602697879076004, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:44.849553Z", "loop": 15793, "env_steps": 9703833599, "loss": 0.01153301727026701, "avg_return": 0.8635607361793518, "regret": 0.0010344048496335745, "entropy": 0.06184283271431923, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:45.702970Z", "loop": 15794, "env_steps": 9704447999, "loss": 0.010685849003493786, "avg_return": 0.862343966960907, "regret": 0.0010344048496335745, "entropy": 0.05970289558172226, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:46.555777Z", "loop": 15795, "env_steps": 9705062399, "loss": 0.011850629933178425, "avg_return": 0.8615223169326782, "regret": 0.0010344048496335745, "entropy": 0.06667670607566833, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:47.410066Z", "loop": 15796, "env_steps": 9705676799, "loss": 0.012754273600876331, "avg_return": 0.862581193447113, "regret": 0.0010344048496335745, "entropy": 0.06615157425403595, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:48.265835Z", "loop": 15797, "env_steps": 9706291199, "loss": 0.01315856259316206, "avg_return": 0.8635233640670776, "regret": 0.0010344048496335745, "entropy": 0.06746923923492432, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:49.120227Z", "loop": 15798, "env_steps": 9706905599, "loss": 0.010958186350762844, "avg_return": 0.8627205491065979, "regret": 0.0010344048496335745, "entropy": 0.061574287712574005, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:49.974446Z", "loop": 15799, "env_steps": 9707519999, "loss": 0.012992838397622108, "avg_return": 0.8628473281860352, "regret": 0.0010344048496335745, "entropy": 0.0649878978729248, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:50.865969Z", "loop": 15800, "env_steps": 9708134399, "loss": 0.011894123628735542, "avg_return": 0.8640735149383545, "regret": 0.00032532113255001605, "entropy": 0.06320694088935852, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:51.719713Z", "loop": 15801, "env_steps": 9708748799, "loss": 0.011838201433420181, "avg_return": 0.8622702956199646, "regret": 0.00032532113255001605, "entropy": 0.06314613670110703, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:52.574918Z", "loop": 15802, "env_steps": 9709363199, "loss": 0.013353611342608929, "avg_return": 0.8631612062454224, "regret": 0.00032532113255001605, "entropy": 0.06692483276128769, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:53.429807Z", "loop": 15803, "env_steps": 9709977599, "loss": 0.012508615851402283, "avg_return": 0.8636487126350403, "regret": 0.00032532113255001605, "entropy": 0.06400834769010544, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:54.285468Z", "loop": 15804, "env_steps": 9710591999, "loss": 0.012155297212302685, "avg_return": 0.8638328313827515, "regret": 0.00032532113255001605, "entropy": 0.06379774212837219, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:55.139986Z", "loop": 15805, "env_steps": 9711206399, "loss": 0.014181544072926044, "avg_return": 0.8639773726463318, "regret": 0.00032532113255001605, "entropy": 0.06870521605014801, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:55.994781Z", "loop": 15806, "env_steps": 9711820799, "loss": 0.013895894400775433, "avg_return": 0.8623996376991272, "regret": 0.00032532113255001605, "entropy": 0.07141271978616714, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:56.849978Z", "loop": 15807, "env_steps": 9712435199, "loss": 0.013175100088119507, "avg_return": 0.8616564869880676, "regret": 0.00032532113255001605, "entropy": 0.07113240659236908, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:57.705000Z", "loop": 15808, "env_steps": 9713049599, "loss": 0.01495362725108862, "avg_return": 0.862103283405304, "regret": 0.00032532113255001605, "entropy": 0.07473305612802505, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:58.559536Z", "loop": 15809, "env_steps": 9713663999, "loss": 0.013371169567108154, "avg_return": 0.8638027310371399, "regret": 0.00032532113255001605, "entropy": 0.06989053636789322, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:09:59.452507Z", "loop": 15810, "env_steps": 9714278399, "loss": 0.015121090225875378, "avg_return": 0.8616135716438293, "regret": 0.0005361725925467908, "entropy": 0.0742432177066803, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:00.307618Z", "loop": 15811, "env_steps": 9714892799, "loss": 0.013352684676647186, "avg_return": 0.8611190915107727, "regret": 0.0005361725925467908, "entropy": 0.07499644160270691, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:01.161626Z", "loop": 15812, "env_steps": 9715507199, "loss": 0.014602149836719036, "avg_return": 0.8622650504112244, "regret": 0.0005361725925467908, "entropy": 0.07982877641916275, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:02.016348Z", "loop": 15813, "env_steps": 9716121599, "loss": 0.013883045874536037, "avg_return": 0.8617126941680908, "regret": 0.0005361725925467908, "entropy": 0.07231497019529343, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:02.870669Z", "loop": 15814, "env_steps": 9716735999, "loss": 0.01455545425415039, "avg_return": 0.8620133399963379, "regret": 0.0005361725925467908, "entropy": 0.07602336257696152, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:03.726056Z", "loop": 15815, "env_steps": 9717350399, "loss": 0.013569948263466358, "avg_return": 0.8613794445991516, "regret": 0.0005361725925467908, "entropy": 0.07001219689846039, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:04.580995Z", "loop": 15816, "env_steps": 9717964799, "loss": 0.013819584622979164, "avg_return": 0.86155766248703, "regret": 0.0005361725925467908, "entropy": 0.07353907078504562, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:05.436223Z", "loop": 15817, "env_steps": 9718579199, "loss": 0.013670842163264751, "avg_return": 0.8618375658988953, "regret": 0.0005361725925467908, "entropy": 0.07101881504058838, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:06.290377Z", "loop": 15818, "env_steps": 9719193599, "loss": 0.012585616670548916, "avg_return": 0.8631624579429626, "regret": 0.0005361725925467908, "entropy": 0.06669194251298904, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:07.145728Z", "loop": 15819, "env_steps": 9719807999, "loss": 0.013033782131969929, "avg_return": 0.8629230856895447, "regret": 0.0005361725925467908, "entropy": 0.07109963148832321, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:08.039246Z", "loop": 15820, "env_steps": 9720422399, "loss": 0.012777969241142273, "avg_return": 0.862217128276825, "regret": 0.0012702634558081627, "entropy": 0.06767246127128601, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:08.893202Z", "loop": 15821, "env_steps": 9721036799, "loss": 0.012309190817177296, "avg_return": 0.8610401749610901, "regret": 0.0012702634558081627, "entropy": 0.06549523770809174, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:09.747525Z", "loop": 15822, "env_steps": 9721651199, "loss": 0.013471418991684914, "avg_return": 0.8632989525794983, "regret": 0.0012702634558081627, "entropy": 0.0680762454867363, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:10.602059Z", "loop": 15823, "env_steps": 9722265599, "loss": 0.012903362512588501, "avg_return": 0.8635058999061584, "regret": 0.0012702634558081627, "entropy": 0.06848660111427307, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:11.456619Z", "loop": 15824, "env_steps": 9722879999, "loss": 0.012495600618422031, "avg_return": 0.8613191843032837, "regret": 0.0012702634558081627, "entropy": 0.07038409262895584, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:12.311142Z", "loop": 15825, "env_steps": 9723494399, "loss": 0.013689154759049416, "avg_return": 0.8601076602935791, "regret": 0.0012702634558081627, "entropy": 0.0708451196551323, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:13.165768Z", "loop": 15826, "env_steps": 9724108799, "loss": 0.013189946301281452, "avg_return": 0.862214982509613, "regret": 0.0012702634558081627, "entropy": 0.07000437378883362, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:14.021309Z", "loop": 15827, "env_steps": 9724723199, "loss": 0.013959919102489948, "avg_return": 0.8600918054580688, "regret": 0.0012702634558081627, "entropy": 0.07470569759607315, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:14.874295Z", "loop": 15828, "env_steps": 9725337599, "loss": 0.0127973398193717, "avg_return": 0.8613505363464355, "regret": 0.0012702634558081627, "entropy": 0.07113946974277496, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:15.727932Z", "loop": 15829, "env_steps": 9725951999, "loss": 0.012298592366278172, "avg_return": 0.8612330555915833, "regret": 0.0012702634558081627, "entropy": 0.06966245174407959, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:16.621561Z", "loop": 15830, "env_steps": 9726566399, "loss": 0.013224306516349316, "avg_return": 0.8623725771903992, "regret": 0.0009275380289182067, "entropy": 0.06889846920967102, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:17.475857Z", "loop": 15831, "env_steps": 9727180799, "loss": 0.013055345974862576, "avg_return": 0.8625486493110657, "regret": 0.0009275380289182067, "entropy": 0.06414024531841278, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:18.329175Z", "loop": 15832, "env_steps": 9727795199, "loss": 0.011823555454611778, "avg_return": 0.8628671765327454, "regret": 0.0009275380289182067, "entropy": 0.06615084409713745, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:19.182929Z", "loop": 15833, "env_steps": 9728409599, "loss": 0.012740041129291058, "avg_return": 0.8635095357894897, "regret": 0.0009275380289182067, "entropy": 0.06457739323377609, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:20.037617Z", "loop": 15834, "env_steps": 9729023999, "loss": 0.011481426656246185, "avg_return": 0.8646246790885925, "regret": 0.0009275380289182067, "entropy": 0.060278117656707764, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:20.892428Z", "loop": 15835, "env_steps": 9729638399, "loss": 0.012010197155177593, "avg_return": 0.8621211051940918, "regret": 0.0009275380289182067, "entropy": 0.06239818409085274, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:21.745844Z", "loop": 15836, "env_steps": 9730252799, "loss": 0.01161716878414154, "avg_return": 0.8629335761070251, "regret": 0.0009275380289182067, "entropy": 0.06318256258964539, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:22.600178Z", "loop": 15837, "env_steps": 9730867199, "loss": 0.011809083633124828, "avg_return": 0.8642419576644897, "regret": 0.0009275380289182067, "entropy": 0.06158421188592911, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:23.454398Z", "loop": 15838, "env_steps": 9731481599, "loss": 0.01146021205931902, "avg_return": 0.8623941540718079, "regret": 0.0009275380289182067, "entropy": 0.060849424451589584, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:24.310013Z", "loop": 15839, "env_steps": 9732095999, "loss": 0.013376672752201557, "avg_return": 0.8633787035942078, "regret": 0.0009275380289182067, "entropy": 0.06349312514066696, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:25.204566Z", "loop": 15840, "env_steps": 9732710399, "loss": 0.012929501943290234, "avg_return": 0.8616377711296082, "regret": 0.00011910397734027356, "entropy": 0.06645320355892181, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:26.058616Z", "loop": 15841, "env_steps": 9733324799, "loss": 0.012291889637708664, "avg_return": 0.8652965426445007, "regret": 0.00011910397734027356, "entropy": 0.06436561048030853, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:26.912617Z", "loop": 15842, "env_steps": 9733939199, "loss": 0.012593920342624187, "avg_return": 0.8636434078216553, "regret": 0.00011910397734027356, "entropy": 0.059516385197639465, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:27.768247Z", "loop": 15843, "env_steps": 9734553599, "loss": 0.012402514927089214, "avg_return": 0.8649628758430481, "regret": 0.00011910397734027356, "entropy": 0.06285275518894196, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:28.623608Z", "loop": 15844, "env_steps": 9735167999, "loss": 0.012003530748188496, "avg_return": 0.8621841669082642, "regret": 0.00011910397734027356, "entropy": 0.06327247619628906, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:29.476926Z", "loop": 15845, "env_steps": 9735782399, "loss": 0.012791642919182777, "avg_return": 0.8634546399116516, "regret": 0.00011910397734027356, "entropy": 0.06410463154315948, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:30.330617Z", "loop": 15846, "env_steps": 9736396799, "loss": 0.012898008339107037, "avg_return": 0.8632649779319763, "regret": 0.00011910397734027356, "entropy": 0.06705774366855621, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:31.185474Z", "loop": 15847, "env_steps": 9737011199, "loss": 0.013694767840206623, "avg_return": 0.8627486228942871, "regret": 0.00011910397734027356, "entropy": 0.06947679817676544, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:32.040396Z", "loop": 15848, "env_steps": 9737625599, "loss": 0.013433183543384075, "avg_return": 0.8630548119544983, "regret": 0.00011910397734027356, "entropy": 0.07035063952207565, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:32.894323Z", "loop": 15849, "env_steps": 9738239999, "loss": 0.015212765894830227, "avg_return": 0.863975465297699, "regret": 0.00011910397734027356, "entropy": 0.07309576123952866, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:33.787196Z", "loop": 15850, "env_steps": 9738854399, "loss": 0.015018959529697895, "avg_return": 0.864071786403656, "regret": 0.0003022505552507937, "entropy": 0.07447649538516998, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:34.640980Z", "loop": 15851, "env_steps": 9739468799, "loss": 0.015609889291226864, "avg_return": 0.8630006909370422, "regret": 0.0003022505552507937, "entropy": 0.07698419690132141, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:35.495513Z", "loop": 15852, "env_steps": 9740083199, "loss": 0.015594958327710629, "avg_return": 0.8613108396530151, "regret": 0.0003022505552507937, "entropy": 0.07739973813295364, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:36.349990Z", "loop": 15853, "env_steps": 9740697599, "loss": 0.01593068055808544, "avg_return": 0.8627579212188721, "regret": 0.0003022505552507937, "entropy": 0.08252577483654022, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:37.203771Z", "loop": 15854, "env_steps": 9741311999, "loss": 0.01530458964407444, "avg_return": 0.8624249696731567, "regret": 0.0003022505552507937, "entropy": 0.0822276622056961, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:38.058830Z", "loop": 15855, "env_steps": 9741926399, "loss": 0.017400281503796577, "avg_return": 0.8605592250823975, "regret": 0.0003022505552507937, "entropy": 0.08738057315349579, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:38.914101Z", "loop": 15856, "env_steps": 9742540799, "loss": 0.01609675958752632, "avg_return": 0.8627058267593384, "regret": 0.0003022505552507937, "entropy": 0.08556803315877914, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:39.769293Z", "loop": 15857, "env_steps": 9743155199, "loss": 0.016512401401996613, "avg_return": 0.8602146506309509, "regret": 0.0003022505552507937, "entropy": 0.08546513319015503, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:40.622937Z", "loop": 15858, "env_steps": 9743769599, "loss": 0.01587505452334881, "avg_return": 0.8628244996070862, "regret": 0.0003022505552507937, "entropy": 0.08234022557735443, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:41.475704Z", "loop": 15859, "env_steps": 9744383999, "loss": 0.014995932579040527, "avg_return": 0.8622955679893494, "regret": 0.0003022505552507937, "entropy": 0.07934790849685669, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:42.368115Z", "loop": 15860, "env_steps": 9744998399, "loss": 0.015244744718074799, "avg_return": 0.8622406125068665, "regret": 0.0010754752438515425, "entropy": 0.07972630858421326, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:43.222602Z", "loop": 15861, "env_steps": 9745612799, "loss": 0.015833023935556412, "avg_return": 0.8623257875442505, "regret": 0.0010754752438515425, "entropy": 0.08153016120195389, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:44.077263Z", "loop": 15862, "env_steps": 9746227199, "loss": 0.016214393079280853, "avg_return": 0.8621309399604797, "regret": 0.0010754752438515425, "entropy": 0.08318820595741272, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:44.931230Z", "loop": 15863, "env_steps": 9746841599, "loss": 0.015962563455104828, "avg_return": 0.8631165623664856, "regret": 0.0010754752438515425, "entropy": 0.08347397297620773, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:45.784801Z", "loop": 15864, "env_steps": 9747455999, "loss": 0.01750030182301998, "avg_return": 0.8620255589485168, "regret": 0.0010754752438515425, "entropy": 0.0854455977678299, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:46.640301Z", "loop": 15865, "env_steps": 9748070399, "loss": 0.016672156751155853, "avg_return": 0.8638728857040405, "regret": 0.0010754752438515425, "entropy": 0.0832555890083313, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:47.495293Z", "loop": 15866, "env_steps": 9748684799, "loss": 0.017457660287618637, "avg_return": 0.8621206879615784, "regret": 0.0010754752438515425, "entropy": 0.08677632361650467, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:48.349646Z", "loop": 15867, "env_steps": 9749299199, "loss": 0.019006984308362007, "avg_return": 0.8622644543647766, "regret": 0.0010754752438515425, "entropy": 0.09489157050848007, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:49.202703Z", "loop": 15868, "env_steps": 9749913599, "loss": 0.018792083486914635, "avg_return": 0.8614475727081299, "regret": 0.0010754752438515425, "entropy": 0.0903979018330574, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:50.057254Z", "loop": 15869, "env_steps": 9750527999, "loss": 0.019268564879894257, "avg_return": 0.8610708713531494, "regret": 0.0010754752438515425, "entropy": 0.09289629012346268, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:50.950461Z", "loop": 15870, "env_steps": 9751142399, "loss": 0.017625469714403152, "avg_return": 0.8607451319694519, "regret": 0.0022223088890314102, "entropy": 0.09068585932254791, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:51.803846Z", "loop": 15871, "env_steps": 9751756799, "loss": 0.018002651631832123, "avg_return": 0.8601665496826172, "regret": 0.0022223088890314102, "entropy": 0.08995702117681503, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:52.657499Z", "loop": 15872, "env_steps": 9752371199, "loss": 0.017776772379875183, "avg_return": 0.8618477582931519, "regret": 0.0022223088890314102, "entropy": 0.09071335941553116, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:53.512285Z", "loop": 15873, "env_steps": 9752985599, "loss": 0.01868283934891224, "avg_return": 0.8623868227005005, "regret": 0.0022223088890314102, "entropy": 0.09304005652666092, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:54.366833Z", "loop": 15874, "env_steps": 9753599999, "loss": 0.017951568588614464, "avg_return": 0.8608642816543579, "regret": 0.0022223088890314102, "entropy": 0.0907621756196022, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:55.220124Z", "loop": 15875, "env_steps": 9754214399, "loss": 0.01874569058418274, "avg_return": 0.8599726557731628, "regret": 0.0022223088890314102, "entropy": 0.09276891499757767, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:56.074635Z", "loop": 15876, "env_steps": 9754828799, "loss": 0.020868999883532524, "avg_return": 0.8606329560279846, "regret": 0.0022223088890314102, "entropy": 0.10083159804344177, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:56.928235Z", "loop": 15877, "env_steps": 9755443199, "loss": 0.021004820242524147, "avg_return": 0.8616400361061096, "regret": 0.0022223088890314102, "entropy": 0.10116001963615417, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:57.781779Z", "loop": 15878, "env_steps": 9756057599, "loss": 0.02080356888473034, "avg_return": 0.8607024550437927, "regret": 0.0022223088890314102, "entropy": 0.10207276791334152, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:58.635862Z", "loop": 15879, "env_steps": 9756671999, "loss": 0.01990586891770363, "avg_return": 0.8618324995040894, "regret": 0.0022223088890314102, "entropy": 0.09604405611753464, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:10:59.528020Z", "loop": 15880, "env_steps": 9757286399, "loss": 0.018755130469799042, "avg_return": 0.8625591993331909, "regret": 0.001554688555188477, "entropy": 0.09113189578056335, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:00.382501Z", "loop": 15881, "env_steps": 9757900799, "loss": 0.017730994150042534, "avg_return": 0.8616963624954224, "regret": 0.001554688555188477, "entropy": 0.08599720150232315, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:01.236956Z", "loop": 15882, "env_steps": 9758515199, "loss": 0.016348866745829582, "avg_return": 0.8617173433303833, "regret": 0.001554688555188477, "entropy": 0.08153802901506424, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:02.091379Z", "loop": 15883, "env_steps": 9759129599, "loss": 0.015785057097673416, "avg_return": 0.8619874119758606, "regret": 0.001554688555188477, "entropy": 0.07700978219509125, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:02.945705Z", "loop": 15884, "env_steps": 9759743999, "loss": 0.016773534938693047, "avg_return": 0.8613580465316772, "regret": 0.001554688555188477, "entropy": 0.08350547403097153, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:03.800041Z", "loop": 15885, "env_steps": 9760358399, "loss": 0.016973350197076797, "avg_return": 0.8613702654838562, "regret": 0.001554688555188477, "entropy": 0.08331124484539032, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:04.654848Z", "loop": 15886, "env_steps": 9760972799, "loss": 0.018880439922213554, "avg_return": 0.8615908026695251, "regret": 0.001554688555188477, "entropy": 0.08926049619913101, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:05.509076Z", "loop": 15887, "env_steps": 9761587199, "loss": 0.01858234964311123, "avg_return": 0.8615656495094299, "regret": 0.001554688555188477, "entropy": 0.08723300695419312, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:06.363356Z", "loop": 15888, "env_steps": 9762201599, "loss": 0.017518896609544754, "avg_return": 0.8611869215965271, "regret": 0.001554688555188477, "entropy": 0.08189494162797928, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:07.217572Z", "loop": 15889, "env_steps": 9762815999, "loss": 0.0191446952521801, "avg_return": 0.8617324233055115, "regret": 0.001554688555188477, "entropy": 0.09274578094482422, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:08.111965Z", "loop": 15890, "env_steps": 9763430399, "loss": 0.019668899476528168, "avg_return": 0.8634188175201416, "regret": 0.0014599920250475407, "entropy": 0.09499125927686691, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:08.966281Z", "loop": 15891, "env_steps": 9764044799, "loss": 0.019013721495866776, "avg_return": 0.8626197576522827, "regret": 0.0014599920250475407, "entropy": 0.09190300852060318, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:09.819977Z", "loop": 15892, "env_steps": 9764659199, "loss": 0.019988687708973885, "avg_return": 0.8618620038032532, "regret": 0.0014599920250475407, "entropy": 0.0968758761882782, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:10.673475Z", "loop": 15893, "env_steps": 9765273599, "loss": 0.020987527444958687, "avg_return": 0.8619698286056519, "regret": 0.0014599920250475407, "entropy": 0.10109729319810867, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:11.528453Z", "loop": 15894, "env_steps": 9765887999, "loss": 0.022325875237584114, "avg_return": 0.8614073991775513, "regret": 0.0014599920250475407, "entropy": 0.1099761351943016, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:12.381112Z", "loop": 15895, "env_steps": 9766502399, "loss": 0.02348952367901802, "avg_return": 0.8623959422111511, "regret": 0.0014599920250475407, "entropy": 0.11135740578174591, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:13.233673Z", "loop": 15896, "env_steps": 9767116799, "loss": 0.023967133834958076, "avg_return": 0.8628775477409363, "regret": 0.0014599920250475407, "entropy": 0.11624760925769806, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:14.088008Z", "loop": 15897, "env_steps": 9767731199, "loss": 0.023783762007951736, "avg_return": 0.8617488741874695, "regret": 0.0014599920250475407, "entropy": 0.11671511828899384, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:14.942619Z", "loop": 15898, "env_steps": 9768345599, "loss": 0.02393525093793869, "avg_return": 0.8623249530792236, "regret": 0.0014599920250475407, "entropy": 0.11318650841712952, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:15.796380Z", "loop": 15899, "env_steps": 9768959999, "loss": 0.02372858300805092, "avg_return": 0.8615500926971436, "regret": 0.0014599920250475407, "entropy": 0.11227390915155411, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:16.688252Z", "loop": 15900, "env_steps": 9769574399, "loss": 0.023651590570807457, "avg_return": 0.861530601978302, "regret": 0.0013974640751257539, "entropy": 0.11564827710390091, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:17.541776Z", "loop": 15901, "env_steps": 9770188799, "loss": 0.02267313562333584, "avg_return": 0.8628359436988831, "regret": 0.0013974640751257539, "entropy": 0.11080656945705414, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:18.397162Z", "loop": 15902, "env_steps": 9770803199, "loss": 0.022846369072794914, "avg_return": 0.8632012009620667, "regret": 0.0013974640751257539, "entropy": 0.112409807741642, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:19.251860Z", "loop": 15903, "env_steps": 9771417599, "loss": 0.021393215283751488, "avg_return": 0.8622497916221619, "regret": 0.0013974640751257539, "entropy": 0.11083139479160309, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:20.104549Z", "loop": 15904, "env_steps": 9772031999, "loss": 0.022539624944329262, "avg_return": 0.8627343773841858, "regret": 0.0013974640751257539, "entropy": 0.11466694623231888, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:20.956700Z", "loop": 15905, "env_steps": 9772646399, "loss": 0.024300599470734596, "avg_return": 0.8619880080223083, "regret": 0.0013974640751257539, "entropy": 0.1188289225101471, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:21.812442Z", "loop": 15906, "env_steps": 9773260799, "loss": 0.022230027243494987, "avg_return": 0.862927258014679, "regret": 0.0013974640751257539, "entropy": 0.11299493163824081, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:22.666670Z", "loop": 15907, "env_steps": 9773875199, "loss": 0.022645477205514908, "avg_return": 0.8623318672180176, "regret": 0.0013974640751257539, "entropy": 0.11279302090406418, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:23.519851Z", "loop": 15908, "env_steps": 9774489599, "loss": 0.022674547508358955, "avg_return": 0.8630444407463074, "regret": 0.0013974640751257539, "entropy": 0.10895141959190369, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:24.373207Z", "loop": 15909, "env_steps": 9775103999, "loss": 0.020911021158099174, "avg_return": 0.8620133399963379, "regret": 0.0013974640751257539, "entropy": 0.110578253865242, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:25.266572Z", "loop": 15910, "env_steps": 9775718399, "loss": 0.02094358392059803, "avg_return": 0.8624693155288696, "regret": 0.000994818052276969, "entropy": 0.1031353548169136, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:26.122047Z", "loop": 15911, "env_steps": 9776332799, "loss": 0.01837971620261669, "avg_return": 0.862568199634552, "regret": 0.000994818052276969, "entropy": 0.09750252217054367, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:26.976276Z", "loop": 15912, "env_steps": 9776947199, "loss": 0.019261488690972328, "avg_return": 0.8626718521118164, "regret": 0.000994818052276969, "entropy": 0.09811215847730637, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:27.830320Z", "loop": 15913, "env_steps": 9777561599, "loss": 0.01776902563869953, "avg_return": 0.8624641299247742, "regret": 0.000994818052276969, "entropy": 0.09043491631746292, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:28.685184Z", "loop": 15914, "env_steps": 9778175999, "loss": 0.01654994674026966, "avg_return": 0.8631172776222229, "regret": 0.000994818052276969, "entropy": 0.08415301144123077, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:29.540250Z", "loop": 15915, "env_steps": 9778790399, "loss": 0.015868229791522026, "avg_return": 0.8636694550514221, "regret": 0.000994818052276969, "entropy": 0.08062933385372162, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:30.394495Z", "loop": 15916, "env_steps": 9779404799, "loss": 0.016316255554556847, "avg_return": 0.8618454337120056, "regret": 0.000994818052276969, "entropy": 0.08359865099191666, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:31.248215Z", "loop": 15917, "env_steps": 9780019199, "loss": 0.01639106497168541, "avg_return": 0.863440752029419, "regret": 0.000994818052276969, "entropy": 0.0837324857711792, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:32.102673Z", "loop": 15918, "env_steps": 9780633599, "loss": 0.016963280737400055, "avg_return": 0.8631608486175537, "regret": 0.000994818052276969, "entropy": 0.0808161199092865, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:32.956721Z", "loop": 15919, "env_steps": 9781247999, "loss": 0.018862640485167503, "avg_return": 0.8625306487083435, "regret": 0.000994818052276969, "entropy": 0.09223487228155136, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:33.848838Z", "loop": 15920, "env_steps": 9781862399, "loss": 0.021796224638819695, "avg_return": 0.8627415299415588, "regret": 0.00022758202976547182, "entropy": 0.10099892318248749, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:34.702384Z", "loop": 15921, "env_steps": 9782476799, "loss": 0.022068090736865997, "avg_return": 0.8639697432518005, "regret": 0.00022758202976547182, "entropy": 0.10284522920846939, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:35.556241Z", "loop": 15922, "env_steps": 9783091199, "loss": 0.020915687084197998, "avg_return": 0.8636491298675537, "regret": 0.00022758202976547182, "entropy": 0.09979776293039322, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:36.410613Z", "loop": 15923, "env_steps": 9783705599, "loss": 0.01964406855404377, "avg_return": 0.8625205755233765, "regret": 0.00022758202976547182, "entropy": 0.09391649812459946, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:37.266331Z", "loop": 15924, "env_steps": 9784319999, "loss": 0.021161794662475586, "avg_return": 0.8641381859779358, "regret": 0.00022758202976547182, "entropy": 0.09971869736909866, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:38.121213Z", "loop": 15925, "env_steps": 9784934399, "loss": 0.01907516084611416, "avg_return": 0.8640122413635254, "regret": 0.00022758202976547182, "entropy": 0.09445273876190186, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:38.976776Z", "loop": 15926, "env_steps": 9785548799, "loss": 0.01902802102267742, "avg_return": 0.8641977906227112, "regret": 0.00022758202976547182, "entropy": 0.09098686277866364, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:39.830350Z", "loop": 15927, "env_steps": 9786163199, "loss": 0.01860000006854534, "avg_return": 0.8632097840309143, "regret": 0.00022758202976547182, "entropy": 0.0898566022515297, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:40.683232Z", "loop": 15928, "env_steps": 9786777599, "loss": 0.018201859667897224, "avg_return": 0.8619950413703918, "regret": 0.00022758202976547182, "entropy": 0.08741920441389084, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:41.537949Z", "loop": 15929, "env_steps": 9787391999, "loss": 0.01890433207154274, "avg_return": 0.8632076382637024, "regret": 0.00022758202976547182, "entropy": 0.09026941657066345, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:42.432400Z", "loop": 15930, "env_steps": 9788006399, "loss": 0.01888944022357464, "avg_return": 0.8622211813926697, "regret": 0.00013386353384703398, "entropy": 0.08834125846624374, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:43.287246Z", "loop": 15931, "env_steps": 9788620799, "loss": 0.01761382631957531, "avg_return": 0.8626402020454407, "regret": 0.00013386353384703398, "entropy": 0.08890888839960098, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:44.142264Z", "loop": 15932, "env_steps": 9789235199, "loss": 0.01826607808470726, "avg_return": 0.8635627627372742, "regret": 0.00013386353384703398, "entropy": 0.0880993902683258, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:44.998065Z", "loop": 15933, "env_steps": 9789849599, "loss": 0.018167663365602493, "avg_return": 0.8626888394355774, "regret": 0.00013386353384703398, "entropy": 0.08562277257442474, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:45.854148Z", "loop": 15934, "env_steps": 9790463999, "loss": 0.017296915873885155, "avg_return": 0.8646425604820251, "regret": 0.00013386353384703398, "entropy": 0.08745680004358292, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:46.709371Z", "loop": 15935, "env_steps": 9791078399, "loss": 0.017504019662737846, "avg_return": 0.8639494180679321, "regret": 0.00013386353384703398, "entropy": 0.08741911500692368, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:47.563621Z", "loop": 15936, "env_steps": 9791692799, "loss": 0.017030850052833557, "avg_return": 0.8616892695426941, "regret": 0.00013386353384703398, "entropy": 0.08508285880088806, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:48.417502Z", "loop": 15937, "env_steps": 9792307199, "loss": 0.016235429793596268, "avg_return": 0.864214301109314, "regret": 0.00013386353384703398, "entropy": 0.08093217760324478, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:49.273718Z", "loop": 15938, "env_steps": 9792921599, "loss": 0.015970654785633087, "avg_return": 0.865294337272644, "regret": 0.00013386353384703398, "entropy": 0.07664601504802704, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:50.128879Z", "loop": 15939, "env_steps": 9793535999, "loss": 0.01634315960109234, "avg_return": 0.8630326390266418, "regret": 0.00013386353384703398, "entropy": 0.08150863647460938, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:51.026478Z", "loop": 15940, "env_steps": 9794150399, "loss": 0.016361823305487633, "avg_return": 0.8630854487419128, "regret": 0.00014019633817952126, "entropy": 0.08003579825162888, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:51.879085Z", "loop": 15941, "env_steps": 9794764799, "loss": 0.016265958547592163, "avg_return": 0.8636289834976196, "regret": 0.00014019633817952126, "entropy": 0.07865925133228302, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:52.732925Z", "loop": 15942, "env_steps": 9795379199, "loss": 0.015008359216153622, "avg_return": 0.8639341592788696, "regret": 0.00014019633817952126, "entropy": 0.07487878948450089, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:53.587167Z", "loop": 15943, "env_steps": 9795993599, "loss": 0.015595659613609314, "avg_return": 0.8626832365989685, "regret": 0.00014019633817952126, "entropy": 0.0769992247223854, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:54.440738Z", "loop": 15944, "env_steps": 9796607999, "loss": 0.015584778971970081, "avg_return": 0.8617563247680664, "regret": 0.00014019633817952126, "entropy": 0.07420133054256439, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:55.294217Z", "loop": 15945, "env_steps": 9797222399, "loss": 0.015475179068744183, "avg_return": 0.8631020188331604, "regret": 0.00014019633817952126, "entropy": 0.07612313330173492, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:56.148424Z", "loop": 15946, "env_steps": 9797836799, "loss": 0.01429089903831482, "avg_return": 0.8634334802627563, "regret": 0.00014019633817952126, "entropy": 0.07184263318777084, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:57.002546Z", "loop": 15947, "env_steps": 9798451199, "loss": 0.013869187794625759, "avg_return": 0.8622555732727051, "regret": 0.00014019633817952126, "entropy": 0.06928908079862595, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:57.856324Z", "loop": 15948, "env_steps": 9799065599, "loss": 0.01399556826800108, "avg_return": 0.8629797697067261, "regret": 0.00014019633817952126, "entropy": 0.07122150808572769, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:58.709756Z", "loop": 15949, "env_steps": 9799679999, "loss": 0.01360967755317688, "avg_return": 0.8629952073097229, "regret": 0.00014019633817952126, "entropy": 0.06749601662158966, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:11:59.603893Z", "loop": 15950, "env_steps": 9800294399, "loss": 0.013997378759086132, "avg_return": 0.863985538482666, "regret": 0.00036143901525065303, "entropy": 0.06974176317453384, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:00.459230Z", "loop": 15951, "env_steps": 9800908799, "loss": 0.012160350568592548, "avg_return": 0.8641276359558105, "regret": 0.00036143901525065303, "entropy": 0.06486625224351883, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:01.314145Z", "loop": 15952, "env_steps": 9801523199, "loss": 0.01222569402307272, "avg_return": 0.8634486198425293, "regret": 0.00036143901525065303, "entropy": 0.06490422785282135, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:02.169888Z", "loop": 15953, "env_steps": 9802137599, "loss": 0.012335594743490219, "avg_return": 0.8637513518333435, "regret": 0.00036143901525065303, "entropy": 0.06489772349596024, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:03.025151Z", "loop": 15954, "env_steps": 9802751999, "loss": 0.013138865120708942, "avg_return": 0.864130973815918, "regret": 0.00036143901525065303, "entropy": 0.06744511425495148, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:03.880320Z", "loop": 15955, "env_steps": 9803366399, "loss": 0.012192918919026852, "avg_return": 0.8621553778648376, "regret": 0.00036143901525065303, "entropy": 0.06367920339107513, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:04.734905Z", "loop": 15956, "env_steps": 9803980799, "loss": 0.012608997523784637, "avg_return": 0.8640291690826416, "regret": 0.00036143901525065303, "entropy": 0.06422949582338333, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:05.590250Z", "loop": 15957, "env_steps": 9804595199, "loss": 0.012931719422340393, "avg_return": 0.8620487451553345, "regret": 0.00036143901525065303, "entropy": 0.06663085520267487, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:06.446148Z", "loop": 15958, "env_steps": 9805209599, "loss": 0.013120266608893871, "avg_return": 0.863710343837738, "regret": 0.00036143901525065303, "entropy": 0.07149709761142731, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:07.300117Z", "loop": 15959, "env_steps": 9805823999, "loss": 0.013157553970813751, "avg_return": 0.8644702434539795, "regret": 0.00036143901525065303, "entropy": 0.06732288002967834, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:08.194933Z", "loop": 15960, "env_steps": 9806438399, "loss": 0.01487436331808567, "avg_return": 0.8636078834533691, "regret": 0.00029828562401235104, "entropy": 0.07168349623680115, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:09.048793Z", "loop": 15961, "env_steps": 9807052799, "loss": 0.013787969946861267, "avg_return": 0.8637830018997192, "regret": 0.00029828562401235104, "entropy": 0.07136803865432739, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:09.903962Z", "loop": 15962, "env_steps": 9807667199, "loss": 0.012896129861474037, "avg_return": 0.8638342618942261, "regret": 0.00029828562401235104, "entropy": 0.06865247339010239, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:10.758852Z", "loop": 15963, "env_steps": 9808281599, "loss": 0.014038960449397564, "avg_return": 0.8638395667076111, "regret": 0.00029828562401235104, "entropy": 0.07357621937990189, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:11.613115Z", "loop": 15964, "env_steps": 9808895999, "loss": 0.013983284123241901, "avg_return": 0.8626734614372253, "regret": 0.00029828562401235104, "entropy": 0.07261655479669571, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:12.468288Z", "loop": 15965, "env_steps": 9809510399, "loss": 0.014130835421383381, "avg_return": 0.862886905670166, "regret": 0.00029828562401235104, "entropy": 0.07319686561822891, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:13.323536Z", "loop": 15966, "env_steps": 9810124799, "loss": 0.013263448141515255, "avg_return": 0.8646153211593628, "regret": 0.00029828562401235104, "entropy": 0.0685150995850563, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:14.177689Z", "loop": 15967, "env_steps": 9810739199, "loss": 0.012785269878804684, "avg_return": 0.8632699847221375, "regret": 0.00029828562401235104, "entropy": 0.06693965941667557, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:15.032025Z", "loop": 15968, "env_steps": 9811353599, "loss": 0.013228148221969604, "avg_return": 0.8632013201713562, "regret": 0.00029828562401235104, "entropy": 0.06909646838903427, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:15.885291Z", "loop": 15969, "env_steps": 9811967999, "loss": 0.01451210118830204, "avg_return": 0.8643034100532532, "regret": 0.00029828562401235104, "entropy": 0.0720151737332344, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:16.778412Z", "loop": 15970, "env_steps": 9812582399, "loss": 0.014913725666701794, "avg_return": 0.8636858463287354, "regret": 0.00013337767450138927, "entropy": 0.07628945261240005, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:17.633238Z", "loop": 15971, "env_steps": 9813196799, "loss": 0.013529479503631592, "avg_return": 0.8624676465988159, "regret": 0.00013337767450138927, "entropy": 0.07216937094926834, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:18.486226Z", "loop": 15972, "env_steps": 9813811199, "loss": 0.014329696074128151, "avg_return": 0.8654740452766418, "regret": 0.00013337767450138927, "entropy": 0.07209891080856323, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:19.340069Z", "loop": 15973, "env_steps": 9814425599, "loss": 0.014460526406764984, "avg_return": 0.8647928833961487, "regret": 0.00013337767450138927, "entropy": 0.06704563647508621, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:20.194609Z", "loop": 15974, "env_steps": 9815039999, "loss": 0.014532259665429592, "avg_return": 0.863271176815033, "regret": 0.00013337767450138927, "entropy": 0.07249142229557037, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:21.048381Z", "loop": 15975, "env_steps": 9815654399, "loss": 0.013791198842227459, "avg_return": 0.8637778162956238, "regret": 0.00013337767450138927, "entropy": 0.06960775703191757, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:21.902445Z", "loop": 15976, "env_steps": 9816268799, "loss": 0.014876442961394787, "avg_return": 0.8644974827766418, "regret": 0.00013337767450138927, "entropy": 0.0744241401553154, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:22.756386Z", "loop": 15977, "env_steps": 9816883199, "loss": 0.01605990156531334, "avg_return": 0.8623079657554626, "regret": 0.00013337767450138927, "entropy": 0.0780806764960289, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:23.610191Z", "loop": 15978, "env_steps": 9817497599, "loss": 0.01502970326691866, "avg_return": 0.8629305362701416, "regret": 0.00013337767450138927, "entropy": 0.07624910026788712, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:24.464672Z", "loop": 15979, "env_steps": 9818111999, "loss": 0.015347370877861977, "avg_return": 0.8617937564849854, "regret": 0.00013337767450138927, "entropy": 0.07858411967754364, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:25.358728Z", "loop": 15980, "env_steps": 9818726399, "loss": 0.01597384177148342, "avg_return": 0.8637269139289856, "regret": 0.0001317520800512284, "entropy": 0.08133227378129959, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:26.214072Z", "loop": 15981, "env_steps": 9819340799, "loss": 0.016634482890367508, "avg_return": 0.8644102215766907, "regret": 0.0001317520800512284, "entropy": 0.08096569776535034, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:27.068582Z", "loop": 15982, "env_steps": 9819955199, "loss": 0.016567178070545197, "avg_return": 0.8638451099395752, "regret": 0.0001317520800512284, "entropy": 0.08370243012905121, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:27.922905Z", "loop": 15983, "env_steps": 9820569599, "loss": 0.01727302372455597, "avg_return": 0.8640821576118469, "regret": 0.0001317520800512284, "entropy": 0.08437959849834442, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:28.777157Z", "loop": 15984, "env_steps": 9821183999, "loss": 0.017122304067015648, "avg_return": 0.8635200262069702, "regret": 0.0001317520800512284, "entropy": 0.08904124051332474, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:29.631015Z", "loop": 15985, "env_steps": 9821798399, "loss": 0.017994480207562447, "avg_return": 0.8636299967765808, "regret": 0.0001317520800512284, "entropy": 0.08736184984445572, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:30.485041Z", "loop": 15986, "env_steps": 9822412799, "loss": 0.018477899953722954, "avg_return": 0.8641825318336487, "regret": 0.0001317520800512284, "entropy": 0.09281933307647705, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:31.338976Z", "loop": 15987, "env_steps": 9823027199, "loss": 0.02103584073483944, "avg_return": 0.8629944324493408, "regret": 0.0001317520800512284, "entropy": 0.10402630269527435, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:32.194327Z", "loop": 15988, "env_steps": 9823641599, "loss": 0.02104932814836502, "avg_return": 0.862533688545227, "regret": 0.0001317520800512284, "entropy": 0.1041112020611763, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:33.049533Z", "loop": 15989, "env_steps": 9824255999, "loss": 0.020060351118445396, "avg_return": 0.864734411239624, "regret": 0.0001317520800512284, "entropy": 0.1015022024512291, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:33.944434Z", "loop": 15990, "env_steps": 9824870399, "loss": 0.01869136653840542, "avg_return": 0.8635509610176086, "regret": 0.0005227542715147138, "entropy": 0.09337247163057327, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:34.799536Z", "loop": 15991, "env_steps": 9825484799, "loss": 0.020117219537496567, "avg_return": 0.8636318445205688, "regret": 0.0005227542715147138, "entropy": 0.10008350014686584, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:35.654852Z", "loop": 15992, "env_steps": 9826099199, "loss": 0.016746556386351585, "avg_return": 0.862398087978363, "regret": 0.0005227542715147138, "entropy": 0.08829571306705475, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:36.509486Z", "loop": 15993, "env_steps": 9826713599, "loss": 0.0169119480997324, "avg_return": 0.8623281121253967, "regret": 0.0005227542715147138, "entropy": 0.08759675174951553, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:37.364043Z", "loop": 15994, "env_steps": 9827327999, "loss": 0.01626504212617874, "avg_return": 0.8620012402534485, "regret": 0.0005227542715147138, "entropy": 0.0872662290930748, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:38.216945Z", "loop": 15995, "env_steps": 9827942399, "loss": 0.01635069027543068, "avg_return": 0.8632871508598328, "regret": 0.0005227542715147138, "entropy": 0.08569356799125671, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:39.070819Z", "loop": 15996, "env_steps": 9828556799, "loss": 0.016940314322710037, "avg_return": 0.8629065155982971, "regret": 0.0005227542715147138, "entropy": 0.08585461229085922, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:39.926558Z", "loop": 15997, "env_steps": 9829171199, "loss": 0.01720949076116085, "avg_return": 0.8624851703643799, "regret": 0.0005227542715147138, "entropy": 0.09136533737182617, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:40.780956Z", "loop": 15998, "env_steps": 9829785599, "loss": 0.016314072534441948, "avg_return": 0.8620659708976746, "regret": 0.0005227542715147138, "entropy": 0.08647692948579788, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:41.634965Z", "loop": 15999, "env_steps": 9830399999, "loss": 0.016885878518223763, "avg_return": 0.8626974821090698, "regret": 0.0005227542715147138, "entropy": 0.09384910762310028, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:42.527609Z", "loop": 16000, "env_steps": 9831014399, "loss": 0.016939625144004822, "avg_return": 0.8634778261184692, "regret": 0.0007300915312953293, "entropy": 0.09105828404426575, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:43.382333Z", "loop": 16001, "env_steps": 9831628799, "loss": 0.01667649671435356, "avg_return": 0.8615575432777405, "regret": 0.0007300915312953293, "entropy": 0.09153079241514206, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:44.236040Z", "loop": 16002, "env_steps": 9832243199, "loss": 0.017795216292142868, "avg_return": 0.8635733127593994, "regret": 0.0007300915312953293, "entropy": 0.0934295728802681, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:45.089625Z", "loop": 16003, "env_steps": 9832857599, "loss": 0.017424030229449272, "avg_return": 0.8621185421943665, "regret": 0.0007300915312953293, "entropy": 0.09293891489505768, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:45.943336Z", "loop": 16004, "env_steps": 9833471999, "loss": 0.017969684675335884, "avg_return": 0.8625150918960571, "regret": 0.0007300915312953293, "entropy": 0.09270640462636948, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:46.797852Z", "loop": 16005, "env_steps": 9834086399, "loss": 0.01683739200234413, "avg_return": 0.8617390990257263, "regret": 0.0007300915312953293, "entropy": 0.08668963611125946, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:47.652163Z", "loop": 16006, "env_steps": 9834700799, "loss": 0.018273917958140373, "avg_return": 0.861340343952179, "regret": 0.0007300915312953293, "entropy": 0.09393204748630524, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:48.505987Z", "loop": 16007, "env_steps": 9835315199, "loss": 0.017030512914061546, "avg_return": 0.8639231324195862, "regret": 0.0007300915312953293, "entropy": 0.09051782637834549, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:49.359397Z", "loop": 16008, "env_steps": 9835929599, "loss": 0.01874428614974022, "avg_return": 0.862194836139679, "regret": 0.0007300915312953293, "entropy": 0.09367655962705612, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:50.214104Z", "loop": 16009, "env_steps": 9836543999, "loss": 0.01855512149631977, "avg_return": 0.8621379733085632, "regret": 0.0007300915312953293, "entropy": 0.09078970551490784, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:51.106738Z", "loop": 16010, "env_steps": 9837158399, "loss": 0.018306022509932518, "avg_return": 0.8626548647880554, "regret": 0.0005782231455668807, "entropy": 0.09137112647294998, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:51.960193Z", "loop": 16011, "env_steps": 9837772799, "loss": 0.01870717667043209, "avg_return": 0.8631477952003479, "regret": 0.0005782231455668807, "entropy": 0.09205499291419983, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:52.813713Z", "loop": 16012, "env_steps": 9838387199, "loss": 0.01844829134643078, "avg_return": 0.8636792302131653, "regret": 0.0005782231455668807, "entropy": 0.0961957722902298, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:53.668455Z", "loop": 16013, "env_steps": 9839001599, "loss": 0.02016236074268818, "avg_return": 0.8624527454376221, "regret": 0.0005782231455668807, "entropy": 0.10288278013467789, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:54.522445Z", "loop": 16014, "env_steps": 9839615999, "loss": 0.020808439701795578, "avg_return": 0.8635601997375488, "regret": 0.0005782231455668807, "entropy": 0.10331201553344727, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:55.376756Z", "loop": 16015, "env_steps": 9840230399, "loss": 0.021503059193491936, "avg_return": 0.8634912371635437, "regret": 0.0005782231455668807, "entropy": 0.10355107486248016, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:56.230945Z", "loop": 16016, "env_steps": 9840844799, "loss": 0.020506924018263817, "avg_return": 0.8636353015899658, "regret": 0.0005782231455668807, "entropy": 0.10271866619586945, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:57.086020Z", "loop": 16017, "env_steps": 9841459199, "loss": 0.020826462656259537, "avg_return": 0.8637221455574036, "regret": 0.0005782231455668807, "entropy": 0.09927934408187866, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:57.939357Z", "loop": 16018, "env_steps": 9842073599, "loss": 0.020144786685705185, "avg_return": 0.8640271425247192, "regret": 0.0005782231455668807, "entropy": 0.09818845987319946, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:58.792660Z", "loop": 16019, "env_steps": 9842687999, "loss": 0.020787108689546585, "avg_return": 0.8637022376060486, "regret": 0.0005782231455668807, "entropy": 0.10036328434944153, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:12:59.686691Z", "loop": 16020, "env_steps": 9843302399, "loss": 0.019925067201256752, "avg_return": 0.8623464107513428, "regret": 0.0007171043544076383, "entropy": 0.09883488714694977, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:00.543084Z", "loop": 16021, "env_steps": 9843916799, "loss": 0.01921490579843521, "avg_return": 0.8620095252990723, "regret": 0.0007171043544076383, "entropy": 0.09562485665082932, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:01.398072Z", "loop": 16022, "env_steps": 9844531199, "loss": 0.019145125523209572, "avg_return": 0.8625516891479492, "regret": 0.0007171043544076383, "entropy": 0.0983942523598671, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:02.252699Z", "loop": 16023, "env_steps": 9845145599, "loss": 0.019236018881201744, "avg_return": 0.86252361536026, "regret": 0.0007171043544076383, "entropy": 0.09822650998830795, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:03.107627Z", "loop": 16024, "env_steps": 9845759999, "loss": 0.01950228400528431, "avg_return": 0.8619911074638367, "regret": 0.0007171043544076383, "entropy": 0.101957306265831, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:03.961908Z", "loop": 16025, "env_steps": 9846374399, "loss": 0.018212366849184036, "avg_return": 0.8623958826065063, "regret": 0.0007171043544076383, "entropy": 0.09451375156641006, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:04.816262Z", "loop": 16026, "env_steps": 9846988799, "loss": 0.018198946490883827, "avg_return": 0.8619935512542725, "regret": 0.0007171043544076383, "entropy": 0.0982029139995575, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:05.670467Z", "loop": 16027, "env_steps": 9847603199, "loss": 0.018688203766942024, "avg_return": 0.8616076111793518, "regret": 0.0007171043544076383, "entropy": 0.1014975905418396, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:06.524821Z", "loop": 16028, "env_steps": 9848217599, "loss": 0.019981801509857178, "avg_return": 0.861920177936554, "regret": 0.0007171043544076383, "entropy": 0.09994655847549438, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:07.379871Z", "loop": 16029, "env_steps": 9848831999, "loss": 0.01928882673382759, "avg_return": 0.8622833490371704, "regret": 0.0007171043544076383, "entropy": 0.09662868827581406, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:08.273650Z", "loop": 16030, "env_steps": 9849446399, "loss": 0.018963728100061417, "avg_return": 0.8617147207260132, "regret": 0.001583944307640195, "entropy": 0.09667941927909851, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:09.127669Z", "loop": 16031, "env_steps": 9850060799, "loss": 0.0177293848246336, "avg_return": 0.8633864521980286, "regret": 0.001583944307640195, "entropy": 0.09523573517799377, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:09.980701Z", "loop": 16032, "env_steps": 9850675199, "loss": 0.018349286168813705, "avg_return": 0.863774836063385, "regret": 0.001583944307640195, "entropy": 0.09178128838539124, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:10.836305Z", "loop": 16033, "env_steps": 9851289599, "loss": 0.01722116395831108, "avg_return": 0.8618497848510742, "regret": 0.001583944307640195, "entropy": 0.09189874678850174, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:11.691137Z", "loop": 16034, "env_steps": 9851903999, "loss": 0.01810634694993496, "avg_return": 0.8627482056617737, "regret": 0.001583944307640195, "entropy": 0.09033498913049698, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:12.545604Z", "loop": 16035, "env_steps": 9852518399, "loss": 0.016784315928816795, "avg_return": 0.8628290891647339, "regret": 0.001583944307640195, "entropy": 0.08679264783859253, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:13.401048Z", "loop": 16036, "env_steps": 9853132799, "loss": 0.017310168594121933, "avg_return": 0.8615676164627075, "regret": 0.001583944307640195, "entropy": 0.08679762482643127, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:14.256450Z", "loop": 16037, "env_steps": 9853747199, "loss": 0.017115963622927666, "avg_return": 0.8628953099250793, "regret": 0.001583944307640195, "entropy": 0.08476290851831436, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:15.112040Z", "loop": 16038, "env_steps": 9854361599, "loss": 0.02002040110528469, "avg_return": 0.8614949584007263, "regret": 0.001583944307640195, "entropy": 0.0970439463853836, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:15.967320Z", "loop": 16039, "env_steps": 9854975999, "loss": 0.019666550680994987, "avg_return": 0.8645428419113159, "regret": 0.001583944307640195, "entropy": 0.09833917766809464, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:16.863404Z", "loop": 16040, "env_steps": 9855590399, "loss": 0.02088801935315132, "avg_return": 0.8632284998893738, "regret": 0.0005957952234894037, "entropy": 0.09625829756259918, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:17.718093Z", "loop": 16041, "env_steps": 9856204799, "loss": 0.021625233814120293, "avg_return": 0.8634812831878662, "regret": 0.0005957952234894037, "entropy": 0.10039360821247101, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:18.572742Z", "loop": 16042, "env_steps": 9856819199, "loss": 0.020640753209590912, "avg_return": 0.8621843457221985, "regret": 0.0005957952234894037, "entropy": 0.10144171118736267, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:19.427537Z", "loop": 16043, "env_steps": 9857433599, "loss": 0.020811554044485092, "avg_return": 0.861372709274292, "regret": 0.0005957952234894037, "entropy": 0.10069333016872406, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:20.282592Z", "loop": 16044, "env_steps": 9858047999, "loss": 0.020325863733887672, "avg_return": 0.8638216257095337, "regret": 0.0005957952234894037, "entropy": 0.09827906638383865, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:21.137617Z", "loop": 16045, "env_steps": 9858662399, "loss": 0.017718080431222916, "avg_return": 0.8630456924438477, "regret": 0.0005957952234894037, "entropy": 0.08775504678487778, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:21.991715Z", "loop": 16046, "env_steps": 9859276799, "loss": 0.01626848243176937, "avg_return": 0.863018810749054, "regret": 0.0005957952234894037, "entropy": 0.08218587934970856, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:22.845604Z", "loop": 16047, "env_steps": 9859891199, "loss": 0.016629710793495178, "avg_return": 0.8625065088272095, "regret": 0.0005957952234894037, "entropy": 0.08137956261634827, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:23.699458Z", "loop": 16048, "env_steps": 9860505599, "loss": 0.014608900062739849, "avg_return": 0.8624589443206787, "regret": 0.0005957952234894037, "entropy": 0.0753229409456253, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:24.552934Z", "loop": 16049, "env_steps": 9861119999, "loss": 0.014287697151303291, "avg_return": 0.8628384470939636, "regret": 0.0005957952234894037, "entropy": 0.06988364458084106, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:25.445117Z", "loop": 16050, "env_steps": 9861734399, "loss": 0.012434679083526134, "avg_return": 0.86276775598526, "regret": 0.0007088236161507666, "entropy": 0.06655415892601013, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:26.299559Z", "loop": 16051, "env_steps": 9862348799, "loss": 0.012297553941607475, "avg_return": 0.8622151613235474, "regret": 0.0007088236161507666, "entropy": 0.0671439841389656, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:27.155640Z", "loop": 16052, "env_steps": 9862963199, "loss": 0.012233908288180828, "avg_return": 0.8633710741996765, "regret": 0.0007088236161507666, "entropy": 0.06313514709472656, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:28.011219Z", "loop": 16053, "env_steps": 9863577599, "loss": 0.013028030283749104, "avg_return": 0.8626240491867065, "regret": 0.0007088236161507666, "entropy": 0.06534270942211151, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:28.865495Z", "loop": 16054, "env_steps": 9864191999, "loss": 0.011652280576527119, "avg_return": 0.8626705408096313, "regret": 0.0007088236161507666, "entropy": 0.0655955821275711, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:29.719753Z", "loop": 16055, "env_steps": 9864806399, "loss": 0.011640130542218685, "avg_return": 0.8622495532035828, "regret": 0.0007088236161507666, "entropy": 0.06181130185723305, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:30.576291Z", "loop": 16056, "env_steps": 9865420799, "loss": 0.011703252792358398, "avg_return": 0.8619096279144287, "regret": 0.0007088236161507666, "entropy": 0.06180920451879501, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:31.431716Z", "loop": 16057, "env_steps": 9866035199, "loss": 0.011189337819814682, "avg_return": 0.863856315612793, "regret": 0.0007088236161507666, "entropy": 0.061489131301641464, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:32.286903Z", "loop": 16058, "env_steps": 9866649599, "loss": 0.011758708395063877, "avg_return": 0.8634175658226013, "regret": 0.0007088236161507666, "entropy": 0.061892591416835785, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:33.142202Z", "loop": 16059, "env_steps": 9867263999, "loss": 0.011650021187961102, "avg_return": 0.8632403612136841, "regret": 0.0007088236161507666, "entropy": 0.06188669800758362, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:34.035181Z", "loop": 16060, "env_steps": 9867878399, "loss": 0.011749942786991596, "avg_return": 0.8629283905029297, "regret": 0.001051718951202929, "entropy": 0.062020909041166306, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:34.889205Z", "loop": 16061, "env_steps": 9868492799, "loss": 0.012020397000014782, "avg_return": 0.861903727054596, "regret": 0.001051718951202929, "entropy": 0.064401775598526, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:35.744086Z", "loop": 16062, "env_steps": 9869107199, "loss": 0.011509014293551445, "avg_return": 0.8611124753952026, "regret": 0.001051718951202929, "entropy": 0.06080904230475426, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:36.598837Z", "loop": 16063, "env_steps": 9869721599, "loss": 0.011115020141005516, "avg_return": 0.8609210252761841, "regret": 0.001051718951202929, "entropy": 0.05891616642475128, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:37.454737Z", "loop": 16064, "env_steps": 9870335999, "loss": 0.010730542242527008, "avg_return": 0.8620806932449341, "regret": 0.001051718951202929, "entropy": 0.05897580459713936, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:38.310523Z", "loop": 16065, "env_steps": 9870950399, "loss": 0.010636352002620697, "avg_return": 0.8620825409889221, "regret": 0.001051718951202929, "entropy": 0.060997359454631805, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:39.165567Z", "loop": 16066, "env_steps": 9871564799, "loss": 0.01021901797503233, "avg_return": 0.861616849899292, "regret": 0.001051718951202929, "entropy": 0.05750009045004845, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:40.019457Z", "loop": 16067, "env_steps": 9872179199, "loss": 0.01099409069865942, "avg_return": 0.863186240196228, "regret": 0.001051718951202929, "entropy": 0.05873687565326691, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:40.874302Z", "loop": 16068, "env_steps": 9872793599, "loss": 0.010826824232935905, "avg_return": 0.8624863624572754, "regret": 0.001051718951202929, "entropy": 0.061302755028009415, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:41.729326Z", "loop": 16069, "env_steps": 9873407999, "loss": 0.011523952707648277, "avg_return": 0.8631850481033325, "regret": 0.001051718951202929, "entropy": 0.0625443235039711, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:42.623970Z", "loop": 16070, "env_steps": 9874022399, "loss": 0.011434987187385559, "avg_return": 0.8621693849563599, "regret": 0.0010893932776525617, "entropy": 0.059839364141225815, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:43.479283Z", "loop": 16071, "env_steps": 9874636799, "loss": 0.011743366718292236, "avg_return": 0.8614058494567871, "regret": 0.0010893932776525617, "entropy": 0.059702057391405106, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:44.334170Z", "loop": 16072, "env_steps": 9875251199, "loss": 0.010815580375492573, "avg_return": 0.8626106977462769, "regret": 0.0010893932776525617, "entropy": 0.06020117178559303, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:45.187073Z", "loop": 16073, "env_steps": 9875865599, "loss": 0.010498963296413422, "avg_return": 0.862127423286438, "regret": 0.0010893932776525617, "entropy": 0.05965330824255943, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:46.041554Z", "loop": 16074, "env_steps": 9876479999, "loss": 0.010401328094303608, "avg_return": 0.8622957468032837, "regret": 0.0010893932776525617, "entropy": 0.05688208341598511, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:46.895575Z", "loop": 16075, "env_steps": 9877094399, "loss": 0.010863425210118294, "avg_return": 0.8633679151535034, "regret": 0.0010893932776525617, "entropy": 0.05575805902481079, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:47.750215Z", "loop": 16076, "env_steps": 9877708799, "loss": 0.009807433001697063, "avg_return": 0.8628778457641602, "regret": 0.0010893932776525617, "entropy": 0.05471167340874672, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:48.604934Z", "loop": 16077, "env_steps": 9878323199, "loss": 0.010306219570338726, "avg_return": 0.8638922572135925, "regret": 0.0010893932776525617, "entropy": 0.05645516887307167, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:49.459065Z", "loop": 16078, "env_steps": 9878937599, "loss": 0.010856173001229763, "avg_return": 0.8618587255477905, "regret": 0.0010893932776525617, "entropy": 0.057389236986637115, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:50.313421Z", "loop": 16079, "env_steps": 9879551999, "loss": 0.009984437376260757, "avg_return": 0.8620361685752869, "regret": 0.0010893932776525617, "entropy": 0.05640162155032158, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:51.205224Z", "loop": 16080, "env_steps": 9880166399, "loss": 0.010378214530646801, "avg_return": 0.8641405701637268, "regret": 0.0006801719428040087, "entropy": 0.05359739065170288, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:52.058577Z", "loop": 16081, "env_steps": 9880780799, "loss": 0.011045226827263832, "avg_return": 0.8629024624824524, "regret": 0.0006801719428040087, "entropy": 0.05792652443051338, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:52.912127Z", "loop": 16082, "env_steps": 9881395199, "loss": 0.009726358577609062, "avg_return": 0.8625752925872803, "regret": 0.0006801719428040087, "entropy": 0.05382603406906128, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:53.765634Z", "loop": 16083, "env_steps": 9882009599, "loss": 0.0105323800817132, "avg_return": 0.8624774217605591, "regret": 0.0006801719428040087, "entropy": 0.053454551845788956, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:54.619930Z", "loop": 16084, "env_steps": 9882623999, "loss": 0.01020157989114523, "avg_return": 0.8632233738899231, "regret": 0.0006801719428040087, "entropy": 0.052245061844587326, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:55.473102Z", "loop": 16085, "env_steps": 9883238399, "loss": 0.010947185568511486, "avg_return": 0.8636353015899658, "regret": 0.0006801719428040087, "entropy": 0.05452028289437294, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:56.326269Z", "loop": 16086, "env_steps": 9883852799, "loss": 0.010144567117094994, "avg_return": 0.8624749779701233, "regret": 0.0006801719428040087, "entropy": 0.053618453443050385, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:57.180544Z", "loop": 16087, "env_steps": 9884467199, "loss": 0.009707747027277946, "avg_return": 0.8646252751350403, "regret": 0.0006801719428040087, "entropy": 0.05095858871936798, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:58.034527Z", "loop": 16088, "env_steps": 9885081599, "loss": 0.010621918365359306, "avg_return": 0.8641262054443359, "regret": 0.0006801719428040087, "entropy": 0.05345207452774048, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:58.887991Z", "loop": 16089, "env_steps": 9885695999, "loss": 0.010680444538593292, "avg_return": 0.8632485270500183, "regret": 0.0006801719428040087, "entropy": 0.058975912630558014, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:13:59.779033Z", "loop": 16090, "env_steps": 9886310399, "loss": 0.01041461806744337, "avg_return": 0.8629080653190613, "regret": 0.0003268655273132026, "entropy": 0.05371060594916344, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:00.632640Z", "loop": 16091, "env_steps": 9886924799, "loss": 0.00990456622093916, "avg_return": 0.8621477484703064, "regret": 0.0003268655273132026, "entropy": 0.0527108758687973, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:01.487356Z", "loop": 16092, "env_steps": 9887539199, "loss": 0.01037590205669403, "avg_return": 0.8627263307571411, "regret": 0.0003268655273132026, "entropy": 0.05646737664937973, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:02.341075Z", "loop": 16093, "env_steps": 9888153599, "loss": 0.010721358470618725, "avg_return": 0.8635678291320801, "regret": 0.0003268655273132026, "entropy": 0.056504495441913605, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:03.194687Z", "loop": 16094, "env_steps": 9888767999, "loss": 0.010670332238078117, "avg_return": 0.8636075258255005, "regret": 0.0003268655273132026, "entropy": 0.055706687271595, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:04.048406Z", "loop": 16095, "env_steps": 9889382399, "loss": 0.011293425224721432, "avg_return": 0.8627132177352905, "regret": 0.0003268655273132026, "entropy": 0.05641559138894081, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:04.902751Z", "loop": 16096, "env_steps": 9889996799, "loss": 0.011140109971165657, "avg_return": 0.8634598255157471, "regret": 0.0003268655273132026, "entropy": 0.05800044909119606, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:05.757337Z", "loop": 16097, "env_steps": 9890611199, "loss": 0.012153802439570427, "avg_return": 0.8631188273429871, "regret": 0.0003268655273132026, "entropy": 0.05859322100877762, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:06.611505Z", "loop": 16098, "env_steps": 9891225599, "loss": 0.010999787598848343, "avg_return": 0.8627457618713379, "regret": 0.0003268655273132026, "entropy": 0.060802653431892395, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:07.465321Z", "loop": 16099, "env_steps": 9891839999, "loss": 0.013350330293178558, "avg_return": 0.8620626926422119, "regret": 0.0003268655273132026, "entropy": 0.06341216713190079, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:08.356691Z", "loop": 16100, "env_steps": 9892454399, "loss": 0.012638813816010952, "avg_return": 0.8632591962814331, "regret": 0.00022461829939857125, "entropy": 0.06226950138807297, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:09.211233Z", "loop": 16101, "env_steps": 9893068799, "loss": 0.013652818277478218, "avg_return": 0.8621541261672974, "regret": 0.00022461829939857125, "entropy": 0.06691155582666397, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:10.065383Z", "loop": 16102, "env_steps": 9893683199, "loss": 0.013457453809678555, "avg_return": 0.8628363013267517, "regret": 0.00022461829939857125, "entropy": 0.0669819712638855, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:10.919791Z", "loop": 16103, "env_steps": 9894297599, "loss": 0.012933671474456787, "avg_return": 0.8637264966964722, "regret": 0.00022461829939857125, "entropy": 0.06431662291288376, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:11.773746Z", "loop": 16104, "env_steps": 9894911999, "loss": 0.013173683546483517, "avg_return": 0.8638253211975098, "regret": 0.00022461829939857125, "entropy": 0.06828717142343521, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:12.629606Z", "loop": 16105, "env_steps": 9895526399, "loss": 0.013583964668214321, "avg_return": 0.8636125922203064, "regret": 0.00022461829939857125, "entropy": 0.07017641514539719, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:13.483776Z", "loop": 16106, "env_steps": 9896140799, "loss": 0.013759396970272064, "avg_return": 0.8633262515068054, "regret": 0.00022461829939857125, "entropy": 0.06850661337375641, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:14.338512Z", "loop": 16107, "env_steps": 9896755199, "loss": 0.014620346017181873, "avg_return": 0.8638409376144409, "regret": 0.00022461829939857125, "entropy": 0.06964828819036484, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:15.191039Z", "loop": 16108, "env_steps": 9897369599, "loss": 0.014143607579171658, "avg_return": 0.863784909248352, "regret": 0.00022461829939857125, "entropy": 0.07049307227134705, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:16.044286Z", "loop": 16109, "env_steps": 9897983999, "loss": 0.015234867110848427, "avg_return": 0.8623239398002625, "regret": 0.00022461829939857125, "entropy": 0.07226485759019852, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:16.937033Z", "loop": 16110, "env_steps": 9898598399, "loss": 0.01575174368917942, "avg_return": 0.8626601099967957, "regret": 0.00019181575044058263, "entropy": 0.07446540892124176, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:17.792336Z", "loop": 16111, "env_steps": 9899212799, "loss": 0.015529341995716095, "avg_return": 0.8633832931518555, "regret": 0.00019181575044058263, "entropy": 0.07553361356258392, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:18.647762Z", "loop": 16112, "env_steps": 9899827199, "loss": 0.01505250483751297, "avg_return": 0.8641948699951172, "regret": 0.00019181575044058263, "entropy": 0.07938098162412643, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:19.503504Z", "loop": 16113, "env_steps": 9900441599, "loss": 0.0163787342607975, "avg_return": 0.8633665442466736, "regret": 0.00019181575044058263, "entropy": 0.0797288566827774, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:20.358212Z", "loop": 16114, "env_steps": 9901055999, "loss": 0.015103167854249477, "avg_return": 0.8653731346130371, "regret": 0.00019181575044058263, "entropy": 0.07549701631069183, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:21.212170Z", "loop": 16115, "env_steps": 9901670399, "loss": 0.015500696375966072, "avg_return": 0.8632887005805969, "regret": 0.00019181575044058263, "entropy": 0.07782949507236481, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:22.066701Z", "loop": 16116, "env_steps": 9902284799, "loss": 0.014955912716686726, "avg_return": 0.8635849952697754, "regret": 0.00019181575044058263, "entropy": 0.07435004413127899, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:22.921408Z", "loop": 16117, "env_steps": 9902899199, "loss": 0.015565930865705013, "avg_return": 0.8634122014045715, "regret": 0.00019181575044058263, "entropy": 0.07520440965890884, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:23.775533Z", "loop": 16118, "env_steps": 9903513599, "loss": 0.015174207277595997, "avg_return": 0.8635367155075073, "regret": 0.00019181575044058263, "entropy": 0.07485131919384003, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:24.629741Z", "loop": 16119, "env_steps": 9904127999, "loss": 0.015465125441551208, "avg_return": 0.8629518747329712, "regret": 0.00019181575044058263, "entropy": 0.07409384101629257, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:25.523063Z", "loop": 16120, "env_steps": 9904742399, "loss": 0.015142890624701977, "avg_return": 0.8643288612365723, "regret": 0.00040350083145312965, "entropy": 0.07425303757190704, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:26.377561Z", "loop": 16121, "env_steps": 9905356799, "loss": 0.014721537940204144, "avg_return": 0.862774670124054, "regret": 0.00040350083145312965, "entropy": 0.07683030515909195, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:27.231506Z", "loop": 16122, "env_steps": 9905971199, "loss": 0.015339118428528309, "avg_return": 0.8627516627311707, "regret": 0.00040350083145312965, "entropy": 0.07796679437160492, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:28.085682Z", "loop": 16123, "env_steps": 9906585599, "loss": 0.015298093669116497, "avg_return": 0.862388551235199, "regret": 0.00040350083145312965, "entropy": 0.08208175003528595, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:28.939954Z", "loop": 16124, "env_steps": 9907199999, "loss": 0.01728903502225876, "avg_return": 0.8614969253540039, "regret": 0.00040350083145312965, "entropy": 0.08671324700117111, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:29.794728Z", "loop": 16125, "env_steps": 9907814399, "loss": 0.018898818641901016, "avg_return": 0.8603537082672119, "regret": 0.00040350083145312965, "entropy": 0.09158482402563095, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:30.648602Z", "loop": 16126, "env_steps": 9908428799, "loss": 0.018250392749905586, "avg_return": 0.8592487573623657, "regret": 0.00040350083145312965, "entropy": 0.09717217087745667, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:31.501909Z", "loop": 16127, "env_steps": 9909043199, "loss": 0.018838390707969666, "avg_return": 0.8580930829048157, "regret": 0.00040350083145312965, "entropy": 0.09813031554222107, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:32.356007Z", "loop": 16128, "env_steps": 9909657599, "loss": 0.01837693154811859, "avg_return": 0.8585076332092285, "regret": 0.00040350083145312965, "entropy": 0.09602534770965576, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:33.210506Z", "loop": 16129, "env_steps": 9910271999, "loss": 0.016797449439764023, "avg_return": 0.8583329319953918, "regret": 0.00040350083145312965, "entropy": 0.09087225794792175, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:34.105636Z", "loop": 16130, "env_steps": 9910886399, "loss": 0.017245303839445114, "avg_return": 0.8602890968322754, "regret": 0.003424924798309803, "entropy": 0.09002843499183655, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:34.959812Z", "loop": 16131, "env_steps": 9911500799, "loss": 0.015421378426253796, "avg_return": 0.8612040281295776, "regret": 0.003424924798309803, "entropy": 0.08268126100301743, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:35.813458Z", "loop": 16132, "env_steps": 9912115199, "loss": 0.015797723084688187, "avg_return": 0.8618687987327576, "regret": 0.003424924798309803, "entropy": 0.08168925344944, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:36.668526Z", "loop": 16133, "env_steps": 9912729599, "loss": 0.014206659980118275, "avg_return": 0.8615381121635437, "regret": 0.003424924798309803, "entropy": 0.07551196217536926, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:37.523571Z", "loop": 16134, "env_steps": 9913343999, "loss": 0.01415786799043417, "avg_return": 0.8608964085578918, "regret": 0.003424924798309803, "entropy": 0.077955462038517, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:38.377331Z", "loop": 16135, "env_steps": 9913958399, "loss": 0.015762586146593094, "avg_return": 0.8617463111877441, "regret": 0.003424924798309803, "entropy": 0.08213532716035843, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:39.230621Z", "loop": 16136, "env_steps": 9914572799, "loss": 0.01575101539492607, "avg_return": 0.8620970845222473, "regret": 0.003424924798309803, "entropy": 0.0792570561170578, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:40.085150Z", "loop": 16137, "env_steps": 9915187199, "loss": 0.015006284229457378, "avg_return": 0.8613376021385193, "regret": 0.003424924798309803, "entropy": 0.07976394891738892, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:40.942122Z", "loop": 16138, "env_steps": 9915801599, "loss": 0.01517865527421236, "avg_return": 0.8614461421966553, "regret": 0.003424924798309803, "entropy": 0.07820297032594681, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:41.796184Z", "loop": 16139, "env_steps": 9916415999, "loss": 0.015089246444404125, "avg_return": 0.8630392551422119, "regret": 0.003424924798309803, "entropy": 0.07613425701856613, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:42.692453Z", "loop": 16140, "env_steps": 9917030399, "loss": 0.015829551964998245, "avg_return": 0.8622738122940063, "regret": 0.0013661866541951895, "entropy": 0.08134826272726059, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:43.546658Z", "loop": 16141, "env_steps": 9917644799, "loss": 0.015246664173901081, "avg_return": 0.8615700602531433, "regret": 0.0013661866541951895, "entropy": 0.07806414365768433, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:44.400816Z", "loop": 16142, "env_steps": 9918259199, "loss": 0.014770892448723316, "avg_return": 0.8616988062858582, "regret": 0.0013661866541951895, "entropy": 0.07618458569049835, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:45.254913Z", "loop": 16143, "env_steps": 9918873599, "loss": 0.014372015371918678, "avg_return": 0.8611311316490173, "regret": 0.0013661866541951895, "entropy": 0.07292498648166656, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:46.110048Z", "loop": 16144, "env_steps": 9919487999, "loss": 0.0143536776304245, "avg_return": 0.8610559105873108, "regret": 0.0013661866541951895, "entropy": 0.07496608793735504, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:46.964604Z", "loop": 16145, "env_steps": 9920102399, "loss": 0.014676788821816444, "avg_return": 0.8622620701789856, "regret": 0.0013661866541951895, "entropy": 0.07099497318267822, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:47.820165Z", "loop": 16146, "env_steps": 9920716799, "loss": 0.014533902518451214, "avg_return": 0.8627301454544067, "regret": 0.0013661866541951895, "entropy": 0.07562079280614853, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:48.675289Z", "loop": 16147, "env_steps": 9921331199, "loss": 0.014885323122143745, "avg_return": 0.8626224994659424, "regret": 0.0013661866541951895, "entropy": 0.07770101726055145, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:49.529746Z", "loop": 16148, "env_steps": 9921945599, "loss": 0.01546930056065321, "avg_return": 0.8611515760421753, "regret": 0.0013661866541951895, "entropy": 0.0772300511598587, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:50.383715Z", "loop": 16149, "env_steps": 9922559999, "loss": 0.015710415318608284, "avg_return": 0.8608464002609253, "regret": 0.0013661866541951895, "entropy": 0.07648257166147232, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:51.278012Z", "loop": 16150, "env_steps": 9923174399, "loss": 0.015136375091969967, "avg_return": 0.8629734516143799, "regret": 0.0007773975958116353, "entropy": 0.07673556357622147, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:52.132783Z", "loop": 16151, "env_steps": 9923788799, "loss": 0.014091174118220806, "avg_return": 0.8638142943382263, "regret": 0.0007773975958116353, "entropy": 0.07163389027118683, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:52.987779Z", "loop": 16152, "env_steps": 9924403199, "loss": 0.014547303318977356, "avg_return": 0.8623285293579102, "regret": 0.0007773975958116353, "entropy": 0.07640301436185837, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:53.842077Z", "loop": 16153, "env_steps": 9925017599, "loss": 0.014376642182469368, "avg_return": 0.8634243011474609, "regret": 0.0007773975958116353, "entropy": 0.07326982915401459, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:54.695909Z", "loop": 16154, "env_steps": 9925631999, "loss": 0.013614793308079243, "avg_return": 0.8640609979629517, "regret": 0.0007773975958116353, "entropy": 0.07049176096916199, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:55.549716Z", "loop": 16155, "env_steps": 9926246399, "loss": 0.014064420945942402, "avg_return": 0.8626007437705994, "regret": 0.0007773975958116353, "entropy": 0.07149042189121246, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:56.404083Z", "loop": 16156, "env_steps": 9926860799, "loss": 0.014321024529635906, "avg_return": 0.8634528517723083, "regret": 0.0007773975958116353, "entropy": 0.0724242702126503, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:57.257711Z", "loop": 16157, "env_steps": 9927475199, "loss": 0.013985593803226948, "avg_return": 0.8622090816497803, "regret": 0.0007773975958116353, "entropy": 0.07061373442411423, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:58.110964Z", "loop": 16158, "env_steps": 9928089599, "loss": 0.012755351141095161, "avg_return": 0.8632709980010986, "regret": 0.0007773975958116353, "entropy": 0.06559795141220093, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:58.964228Z", "loop": 16159, "env_steps": 9928703999, "loss": 0.013825635425746441, "avg_return": 0.8648248314857483, "regret": 0.0007773975958116353, "entropy": 0.06996864080429077, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:14:59.860866Z", "loop": 16160, "env_steps": 9929318399, "loss": 0.014359547756612301, "avg_return": 0.86381596326828, "regret": 0.0002542152942623943, "entropy": 0.06860220432281494, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:00.715778Z", "loop": 16161, "env_steps": 9929932799, "loss": 0.013761303387582302, "avg_return": 0.8646084666252136, "regret": 0.0002542152942623943, "entropy": 0.06931304186582565, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:01.570538Z", "loop": 16162, "env_steps": 9930547199, "loss": 0.013503200374543667, "avg_return": 0.8632632493972778, "regret": 0.0002542152942623943, "entropy": 0.0699470043182373, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:02.426851Z", "loop": 16163, "env_steps": 9931161599, "loss": 0.014125892892479897, "avg_return": 0.8643532395362854, "regret": 0.0002542152942623943, "entropy": 0.07169042527675629, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:03.282876Z", "loop": 16164, "env_steps": 9931775999, "loss": 0.014384153299033642, "avg_return": 0.8634178638458252, "regret": 0.0002542152942623943, "entropy": 0.07056029886007309, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:04.138022Z", "loop": 16165, "env_steps": 9932390399, "loss": 0.013385235331952572, "avg_return": 0.8637349605560303, "regret": 0.0002542152942623943, "entropy": 0.06670162081718445, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:04.994160Z", "loop": 16166, "env_steps": 9933004799, "loss": 0.012545394711196423, "avg_return": 0.8640003800392151, "regret": 0.0002542152942623943, "entropy": 0.06354585289955139, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:05.848665Z", "loop": 16167, "env_steps": 9933619199, "loss": 0.01389224361628294, "avg_return": 0.8628805875778198, "regret": 0.0002542152942623943, "entropy": 0.06893344968557358, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:06.703865Z", "loop": 16168, "env_steps": 9934233599, "loss": 0.01294265128672123, "avg_return": 0.8629917502403259, "regret": 0.0002542152942623943, "entropy": 0.06512770056724548, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:07.559270Z", "loop": 16169, "env_steps": 9934847999, "loss": 0.011957352049648762, "avg_return": 0.8639914989471436, "regret": 0.0002542152942623943, "entropy": 0.06158623471856117, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:08.453412Z", "loop": 16170, "env_steps": 9935462399, "loss": 0.011579410172998905, "avg_return": 0.8637487888336182, "regret": 0.00022335592075251043, "entropy": 0.06373795866966248, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:09.307347Z", "loop": 16171, "env_steps": 9936076799, "loss": 0.010918413288891315, "avg_return": 0.8630200624465942, "regret": 0.00022335592075251043, "entropy": 0.059474535286426544, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:10.160766Z", "loop": 16172, "env_steps": 9936691199, "loss": 0.010841654613614082, "avg_return": 0.8634875416755676, "regret": 0.00022335592075251043, "entropy": 0.05621035024523735, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:11.014390Z", "loop": 16173, "env_steps": 9937305599, "loss": 0.010445321910083294, "avg_return": 0.8640183806419373, "regret": 0.00022335592075251043, "entropy": 0.055636294186115265, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:11.868132Z", "loop": 16174, "env_steps": 9937919999, "loss": 0.010241946205496788, "avg_return": 0.8643951416015625, "regret": 0.00022335592075251043, "entropy": 0.05648825317621231, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:12.723298Z", "loop": 16175, "env_steps": 9938534399, "loss": 0.010819101706147194, "avg_return": 0.8625797629356384, "regret": 0.00022335592075251043, "entropy": 0.0559983067214489, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:13.578497Z", "loop": 16176, "env_steps": 9939148799, "loss": 0.010474449954926968, "avg_return": 0.8640592694282532, "regret": 0.00022335592075251043, "entropy": 0.055735621601343155, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:14.432713Z", "loop": 16177, "env_steps": 9939763199, "loss": 0.010724653489887714, "avg_return": 0.8629279732704163, "regret": 0.00022335592075251043, "entropy": 0.05704192444682121, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:15.287080Z", "loop": 16178, "env_steps": 9940377599, "loss": 0.010104152373969555, "avg_return": 0.863623857498169, "regret": 0.00022335592075251043, "entropy": 0.0538942851126194, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:16.141518Z", "loop": 16179, "env_steps": 9940991999, "loss": 0.010763521306216717, "avg_return": 0.862383246421814, "regret": 0.00022335592075251043, "entropy": 0.055737998336553574, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:17.035220Z", "loop": 16180, "env_steps": 9941606399, "loss": 0.01035401877015829, "avg_return": 0.8625866174697876, "regret": 0.00035102420952171087, "entropy": 0.05559476464986801, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:17.889601Z", "loop": 16181, "env_steps": 9942220799, "loss": 0.010722430422902107, "avg_return": 0.8645180463790894, "regret": 0.00035102420952171087, "entropy": 0.05395135655999184, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:18.745236Z", "loop": 16182, "env_steps": 9942835199, "loss": 0.011201709508895874, "avg_return": 0.8629862666130066, "regret": 0.00035102420952171087, "entropy": 0.0574299693107605, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:19.601457Z", "loop": 16183, "env_steps": 9943449599, "loss": 0.009928028099238873, "avg_return": 0.8643170595169067, "regret": 0.00035102420952171087, "entropy": 0.05558183789253235, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:20.456764Z", "loop": 16184, "env_steps": 9944063999, "loss": 0.010811720043420792, "avg_return": 0.863912045955658, "regret": 0.00035102420952171087, "entropy": 0.059821102768182755, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:21.311251Z", "loop": 16185, "env_steps": 9944678399, "loss": 0.01038789376616478, "avg_return": 0.8624284267425537, "regret": 0.00035102420952171087, "entropy": 0.05709502846002579, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:22.165142Z", "loop": 16186, "env_steps": 9945292799, "loss": 0.012098087929189205, "avg_return": 0.8617902994155884, "regret": 0.00035102420952171087, "entropy": 0.06371748447418213, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:23.020642Z", "loop": 16187, "env_steps": 9945907199, "loss": 0.011183823458850384, "avg_return": 0.8605061769485474, "regret": 0.00035102420952171087, "entropy": 0.06121879443526268, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:23.875944Z", "loop": 16188, "env_steps": 9946521599, "loss": 0.011261191219091415, "avg_return": 0.8582016229629517, "regret": 0.00035102420952171087, "entropy": 0.0659247487783432, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:24.730068Z", "loop": 16189, "env_steps": 9947135999, "loss": 0.012269615195691586, "avg_return": 0.8593290448188782, "regret": 0.00035102420952171087, "entropy": 0.06505345553159714, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:25.622512Z", "loop": 16190, "env_steps": 9947750399, "loss": 0.012552541680634022, "avg_return": 0.859131395816803, "regret": 0.00432838499546051, "entropy": 0.06869472563266754, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:26.476157Z", "loop": 16191, "env_steps": 9948364799, "loss": 0.012209123931825161, "avg_return": 0.8588891625404358, "regret": 0.00432838499546051, "entropy": 0.06718189269304276, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:27.330371Z", "loop": 16192, "env_steps": 9948979199, "loss": 0.012349715456366539, "avg_return": 0.859239935874939, "regret": 0.00432838499546051, "entropy": 0.06805801391601562, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:28.183821Z", "loop": 16193, "env_steps": 9949593599, "loss": 0.012257284484803677, "avg_return": 0.8608142137527466, "regret": 0.00432838499546051, "entropy": 0.06835241615772247, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:29.036731Z", "loop": 16194, "env_steps": 9950207999, "loss": 0.012537121772766113, "avg_return": 0.860615074634552, "regret": 0.00432838499546051, "entropy": 0.06592762470245361, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:29.890345Z", "loop": 16195, "env_steps": 9950822399, "loss": 0.012057004496455193, "avg_return": 0.8616206049919128, "regret": 0.00432838499546051, "entropy": 0.06560572236776352, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:30.743515Z", "loop": 16196, "env_steps": 9951436799, "loss": 0.011513417586684227, "avg_return": 0.8622967004776001, "regret": 0.00432838499546051, "entropy": 0.06617744266986847, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:31.597454Z", "loop": 16197, "env_steps": 9952051199, "loss": 0.011910299770534039, "avg_return": 0.8618212938308716, "regret": 0.00432838499546051, "entropy": 0.06644643843173981, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:32.450781Z", "loop": 16198, "env_steps": 9952665599, "loss": 0.011933263391256332, "avg_return": 0.8624186515808105, "regret": 0.00432838499546051, "entropy": 0.06813642382621765, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:33.303955Z", "loop": 16199, "env_steps": 9953279999, "loss": 0.011821621097624302, "avg_return": 0.8626155853271484, "regret": 0.00432838499546051, "entropy": 0.06354808062314987, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:34.197172Z", "loop": 16200, "env_steps": 9953894399, "loss": 0.011684826575219631, "avg_return": 0.8629598021507263, "regret": 0.0006729150773026049, "entropy": 0.0642099604010582, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:35.050940Z", "loop": 16201, "env_steps": 9954508799, "loss": 0.011418882757425308, "avg_return": 0.8636226654052734, "regret": 0.0006729150773026049, "entropy": 0.06444200873374939, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:35.905140Z", "loop": 16202, "env_steps": 9955123199, "loss": 0.012989967130124569, "avg_return": 0.8631690740585327, "regret": 0.0006729150773026049, "entropy": 0.06425297260284424, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:36.757987Z", "loop": 16203, "env_steps": 9955737599, "loss": 0.01153010968118906, "avg_return": 0.8623337745666504, "regret": 0.0006729150773026049, "entropy": 0.06327496469020844, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:37.612029Z", "loop": 16204, "env_steps": 9956351999, "loss": 0.011269668117165565, "avg_return": 0.8625671863555908, "regret": 0.0006729150773026049, "entropy": 0.06313049793243408, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:38.468005Z", "loop": 16205, "env_steps": 9956966399, "loss": 0.011602816171944141, "avg_return": 0.8628000020980835, "regret": 0.0006729150773026049, "entropy": 0.06374992430210114, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:39.323205Z", "loop": 16206, "env_steps": 9957580799, "loss": 0.012235932983458042, "avg_return": 0.8630512952804565, "regret": 0.0006729150773026049, "entropy": 0.06700488924980164, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:40.176945Z", "loop": 16207, "env_steps": 9958195199, "loss": 0.011819517239928246, "avg_return": 0.8636116981506348, "regret": 0.0006729150773026049, "entropy": 0.06750636547803879, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:41.029981Z", "loop": 16208, "env_steps": 9958809599, "loss": 0.011368208564817905, "avg_return": 0.8609108924865723, "regret": 0.0006729150773026049, "entropy": 0.06415674090385437, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:41.884265Z", "loop": 16209, "env_steps": 9959423999, "loss": 0.013393326662480831, "avg_return": 0.8627997040748596, "regret": 0.0006729150773026049, "entropy": 0.07118792831897736, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:42.777158Z", "loop": 16210, "env_steps": 9960038399, "loss": 0.0136712109670043, "avg_return": 0.8627565503120422, "regret": 0.001002253033220768, "entropy": 0.0722178965806961, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:43.630633Z", "loop": 16211, "env_steps": 9960652799, "loss": 0.01302355993539095, "avg_return": 0.8627060055732727, "regret": 0.001002253033220768, "entropy": 0.07280472666025162, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:44.484489Z", "loop": 16212, "env_steps": 9961267199, "loss": 0.013423039577901363, "avg_return": 0.8612831830978394, "regret": 0.001002253033220768, "entropy": 0.07235559076070786, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:45.338713Z", "loop": 16213, "env_steps": 9961881599, "loss": 0.013560405932366848, "avg_return": 0.8611369132995605, "regret": 0.001002253033220768, "entropy": 0.07555019110441208, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:46.194129Z", "loop": 16214, "env_steps": 9962495999, "loss": 0.01320978719741106, "avg_return": 0.8617002367973328, "regret": 0.001002253033220768, "entropy": 0.07341327518224716, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:47.049672Z", "loop": 16215, "env_steps": 9963110399, "loss": 0.013378024101257324, "avg_return": 0.8625636100769043, "regret": 0.001002253033220768, "entropy": 0.07565159350633621, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:47.904053Z", "loop": 16216, "env_steps": 9963724799, "loss": 0.013124711811542511, "avg_return": 0.8632493019104004, "regret": 0.001002253033220768, "entropy": 0.07231845706701279, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:48.757713Z", "loop": 16217, "env_steps": 9964339199, "loss": 0.012125189416110516, "avg_return": 0.8630366325378418, "regret": 0.001002253033220768, "entropy": 0.06698403507471085, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:49.612194Z", "loop": 16218, "env_steps": 9964953599, "loss": 0.011448550038039684, "avg_return": 0.8631268739700317, "regret": 0.001002253033220768, "entropy": 0.06445365399122238, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:50.466400Z", "loop": 16219, "env_steps": 9965567999, "loss": 0.01241296622902155, "avg_return": 0.8624119162559509, "regret": 0.001002253033220768, "entropy": 0.06658945232629776, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:51.358785Z", "loop": 16220, "env_steps": 9966182399, "loss": 0.012434074655175209, "avg_return": 0.8634178638458252, "regret": 0.0003913172986358404, "entropy": 0.06506602466106415, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:52.212468Z", "loop": 16221, "env_steps": 9966796799, "loss": 0.012377250008285046, "avg_return": 0.8635579347610474, "regret": 0.0003913172986358404, "entropy": 0.06528748571872711, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:53.068044Z", "loop": 16222, "env_steps": 9967411199, "loss": 0.011253147386014462, "avg_return": 0.8648016452789307, "regret": 0.0003913172986358404, "entropy": 0.06075204536318779, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:53.922622Z", "loop": 16223, "env_steps": 9968025599, "loss": 0.013393963687121868, "avg_return": 0.8623835444450378, "regret": 0.0003913172986358404, "entropy": 0.06804731488227844, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:54.776719Z", "loop": 16224, "env_steps": 9968639999, "loss": 0.012810167856514454, "avg_return": 0.8639229536056519, "regret": 0.0003913172986358404, "entropy": 0.0652918666601181, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:55.631022Z", "loop": 16225, "env_steps": 9969254399, "loss": 0.013130910694599152, "avg_return": 0.8631212711334229, "regret": 0.0003913172986358404, "entropy": 0.06988576799631119, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:56.485103Z", "loop": 16226, "env_steps": 9969868799, "loss": 0.01374551560729742, "avg_return": 0.8620913028717041, "regret": 0.0003913172986358404, "entropy": 0.06777297705411911, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:57.338551Z", "loop": 16227, "env_steps": 9970483199, "loss": 0.013258515857160091, "avg_return": 0.8623570799827576, "regret": 0.0003913172986358404, "entropy": 0.06743700802326202, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:58.192647Z", "loop": 16228, "env_steps": 9971097599, "loss": 0.014791923575103283, "avg_return": 0.8635367155075073, "regret": 0.0003913172986358404, "entropy": 0.0740635097026825, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:59.046602Z", "loop": 16229, "env_steps": 9971711999, "loss": 0.01420892309397459, "avg_return": 0.863254189491272, "regret": 0.0003913172986358404, "entropy": 0.07460030168294907, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:15:59.942553Z", "loop": 16230, "env_steps": 9972326399, "loss": 0.014880108647048473, "avg_return": 0.8625494837760925, "regret": 8.946408343035728e-05, "entropy": 0.07315102964639664, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:00.796758Z", "loop": 16231, "env_steps": 9972940799, "loss": 0.014844881370663643, "avg_return": 0.8631553053855896, "regret": 8.946408343035728e-05, "entropy": 0.07389052957296371, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:01.650514Z", "loop": 16232, "env_steps": 9973555199, "loss": 0.015130330808460712, "avg_return": 0.8633186221122742, "regret": 8.946408343035728e-05, "entropy": 0.07612822949886322, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:02.504688Z", "loop": 16233, "env_steps": 9974169599, "loss": 0.015320384874939919, "avg_return": 0.8629676699638367, "regret": 8.946408343035728e-05, "entropy": 0.07589049637317657, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:03.359912Z", "loop": 16234, "env_steps": 9974783999, "loss": 0.01555034052580595, "avg_return": 0.8643414378166199, "regret": 8.946408343035728e-05, "entropy": 0.07537968456745148, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:04.213706Z", "loop": 16235, "env_steps": 9975398399, "loss": 0.015422500669956207, "avg_return": 0.8646051287651062, "regret": 8.946408343035728e-05, "entropy": 0.07684213668107986, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:05.066954Z", "loop": 16236, "env_steps": 9976012799, "loss": 0.015532965771853924, "avg_return": 0.863067626953125, "regret": 8.946408343035728e-05, "entropy": 0.079402856528759, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:05.921167Z", "loop": 16237, "env_steps": 9976627199, "loss": 0.01783539354801178, "avg_return": 0.8638999462127686, "regret": 8.946408343035728e-05, "entropy": 0.08304572105407715, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:06.776175Z", "loop": 16238, "env_steps": 9977241599, "loss": 0.016710245981812477, "avg_return": 0.8634346723556519, "regret": 8.946408343035728e-05, "entropy": 0.07923848181962967, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:07.630573Z", "loop": 16239, "env_steps": 9977855999, "loss": 0.01660754904150963, "avg_return": 0.863140881061554, "regret": 8.946408343035728e-05, "entropy": 0.07976164668798447, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:08.523417Z", "loop": 16240, "env_steps": 9978470399, "loss": 0.016659734770655632, "avg_return": 0.8636210560798645, "regret": 9.723291441332549e-05, "entropy": 0.08239535242319107, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:09.376994Z", "loop": 16241, "env_steps": 9979084799, "loss": 0.014980544336140156, "avg_return": 0.8629530072212219, "regret": 9.723291441332549e-05, "entropy": 0.07348017394542694, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:10.232839Z", "loop": 16242, "env_steps": 9979699199, "loss": 0.015687858685851097, "avg_return": 0.8627811670303345, "regret": 9.723291441332549e-05, "entropy": 0.07408309727907181, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:11.087304Z", "loop": 16243, "env_steps": 9980313599, "loss": 0.015255165286362171, "avg_return": 0.8643743991851807, "regret": 9.723291441332549e-05, "entropy": 0.07637922465801239, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:11.941879Z", "loop": 16244, "env_steps": 9980927999, "loss": 0.015038633719086647, "avg_return": 0.8646316528320312, "regret": 9.723291441332549e-05, "entropy": 0.0744323804974556, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:12.795959Z", "loop": 16245, "env_steps": 9981542399, "loss": 0.014498034492135048, "avg_return": 0.8637011647224426, "regret": 9.723291441332549e-05, "entropy": 0.07139118015766144, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:13.650317Z", "loop": 16246, "env_steps": 9982156799, "loss": 0.013543262146413326, "avg_return": 0.8639906048774719, "regret": 9.723291441332549e-05, "entropy": 0.06877820938825607, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:14.504391Z", "loop": 16247, "env_steps": 9982771199, "loss": 0.013852867297828197, "avg_return": 0.8639272451400757, "regret": 9.723291441332549e-05, "entropy": 0.06781215220689774, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:15.358343Z", "loop": 16248, "env_steps": 9983385599, "loss": 0.01228115800768137, "avg_return": 0.8617373108863831, "regret": 9.723291441332549e-05, "entropy": 0.06771879643201828, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:16.212153Z", "loop": 16249, "env_steps": 9983999999, "loss": 0.013589970767498016, "avg_return": 0.8615473508834839, "regret": 9.723291441332549e-05, "entropy": 0.07075025886297226, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:17.106776Z", "loop": 16250, "env_steps": 9984614399, "loss": 0.012886375188827515, "avg_return": 0.8639980554580688, "regret": 8.6916537838988e-05, "entropy": 0.06595365703105927, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:17.961787Z", "loop": 16251, "env_steps": 9985228799, "loss": 0.01311519742012024, "avg_return": 0.863165020942688, "regret": 8.6916537838988e-05, "entropy": 0.06660450994968414, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:18.815680Z", "loop": 16252, "env_steps": 9985843199, "loss": 0.013520230539143085, "avg_return": 0.8647037744522095, "regret": 8.6916537838988e-05, "entropy": 0.0668439269065857, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:19.668992Z", "loop": 16253, "env_steps": 9986457599, "loss": 0.01254697609692812, "avg_return": 0.8629956245422363, "regret": 8.6916537838988e-05, "entropy": 0.06354883313179016, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:20.523472Z", "loop": 16254, "env_steps": 9987071999, "loss": 0.013056903146207333, "avg_return": 0.8644606471061707, "regret": 8.6916537838988e-05, "entropy": 0.06494031101465225, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:21.377816Z", "loop": 16255, "env_steps": 9987686399, "loss": 0.013092152774333954, "avg_return": 0.8633513450622559, "regret": 8.6916537838988e-05, "entropy": 0.06572344899177551, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:22.232685Z", "loop": 16256, "env_steps": 9988300799, "loss": 0.012700765393674374, "avg_return": 0.8629687428474426, "regret": 8.6916537838988e-05, "entropy": 0.06472732126712799, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:23.086101Z", "loop": 16257, "env_steps": 9988915199, "loss": 0.01263835746794939, "avg_return": 0.8638185858726501, "regret": 8.6916537838988e-05, "entropy": 0.062044624239206314, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:23.940692Z", "loop": 16258, "env_steps": 9989529599, "loss": 0.013815809972584248, "avg_return": 0.8631860613822937, "regret": 8.6916537838988e-05, "entropy": 0.06775592267513275, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:24.795206Z", "loop": 16259, "env_steps": 9990143999, "loss": 0.013582891784608364, "avg_return": 0.863508939743042, "regret": 8.6916537838988e-05, "entropy": 0.06901857256889343, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:25.687297Z", "loop": 16260, "env_steps": 9990758399, "loss": 0.014495092444121838, "avg_return": 0.8626847267150879, "regret": 0.0006208818522281945, "entropy": 0.07022937387228012, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:26.542243Z", "loop": 16261, "env_steps": 9991372799, "loss": 0.01449512131512165, "avg_return": 0.8632780909538269, "regret": 0.0006208818522281945, "entropy": 0.07508128136396408, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:27.396222Z", "loop": 16262, "env_steps": 9991987199, "loss": 0.014891671016812325, "avg_return": 0.8636446595191956, "regret": 0.0006208818522281945, "entropy": 0.07090003788471222, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:28.249601Z", "loop": 16263, "env_steps": 9992601599, "loss": 0.01563035324215889, "avg_return": 0.8646589517593384, "regret": 0.0006208818522281945, "entropy": 0.07385698705911636, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:29.103480Z", "loop": 16264, "env_steps": 9993215999, "loss": 0.014982043765485287, "avg_return": 0.8618894815444946, "regret": 0.0006208818522281945, "entropy": 0.07533012330532074, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:29.958673Z", "loop": 16265, "env_steps": 9993830399, "loss": 0.015168065205216408, "avg_return": 0.8622198700904846, "regret": 0.0006208818522281945, "entropy": 0.0731242224574089, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:30.812776Z", "loop": 16266, "env_steps": 9994444799, "loss": 0.014419621787965298, "avg_return": 0.8635165691375732, "regret": 0.0006208818522281945, "entropy": 0.0729149729013443, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:31.666468Z", "loop": 16267, "env_steps": 9995059199, "loss": 0.015334092080593109, "avg_return": 0.8627598285675049, "regret": 0.0006208818522281945, "entropy": 0.07682172954082489, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:32.520075Z", "loop": 16268, "env_steps": 9995673599, "loss": 0.014085185714066029, "avg_return": 0.8639340400695801, "regret": 0.0006208818522281945, "entropy": 0.07279770076274872, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:33.374926Z", "loop": 16269, "env_steps": 9996287999, "loss": 0.015819089487195015, "avg_return": 0.8626033663749695, "regret": 0.0006208818522281945, "entropy": 0.07751349359750748, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:34.267596Z", "loop": 16270, "env_steps": 9996902399, "loss": 0.015822051092982292, "avg_return": 0.8626664280891418, "regret": 0.0014015259221196175, "entropy": 0.0783279612660408, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:35.121541Z", "loop": 16271, "env_steps": 9997516799, "loss": 0.01593763194978237, "avg_return": 0.8616846203804016, "regret": 0.0014015259221196175, "entropy": 0.081810362637043, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:35.975564Z", "loop": 16272, "env_steps": 9998131199, "loss": 0.01614863984286785, "avg_return": 0.8617415428161621, "regret": 0.0014015259221196175, "entropy": 0.08140651136636734, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:36.829798Z", "loop": 16273, "env_steps": 9998745599, "loss": 0.016316039487719536, "avg_return": 0.8612974286079407, "regret": 0.0014015259221196175, "entropy": 0.08520776778459549, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:37.684677Z", "loop": 16274, "env_steps": 9999359999, "loss": 0.017510950565338135, "avg_return": 0.8615146279335022, "regret": 0.0014015259221196175, "entropy": 0.08576234430074692, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} +{"ts": "2026-03-20T21:16:38.537931Z", "loop": 16275, "env_steps": 9999974399, "loss": 0.0168222077190876, "avg_return": 0.8619512915611267, "regret": 0.0014015259221196175, "entropy": 0.08619251847267151, "lr": 5e-05, "discount_rate": 0.98, "num_rollout_steps": 64} diff --git a/control_al_0.6_g_0.98_id_94_seed_9806094/train.log b/control_al_0.6_g_0.98_id_94_seed_9806094/train.log new file mode 100644 index 0000000000000000000000000000000000000000..e7e27787304c031e979a7e83ddfb5fbaf0d0da7b --- /dev/null +++ b/control_al_0.6_g_0.98_id_94_seed_9806094/train.log @@ -0,0 +1,16276 @@ +[2026-03-20T17:23:27.626587Z] Loop 0: Loss: 1.94e-02, Avg Return: 0.116, Regret: 0.7276, Entropy: 1.3858 +[2026-03-20T17:23:28.517920Z] Loop 1: Loss: 1.74e-02, Avg Return: 0.112, Regret: 0.7271, Entropy: 1.3858 +[2026-03-20T17:23:29.404331Z] Loop 2: Loss: 1.82e-02, Avg Return: 0.110, Regret: 0.7265, Entropy: 1.3857 +[2026-03-20T17:23:30.291546Z] Loop 3: Loss: 1.82e-02, Avg Return: 0.113, Regret: 0.7260, Entropy: 1.3857 +[2026-03-20T17:23:31.180488Z] Loop 4: Loss: 1.69e-02, Avg Return: 0.113, Regret: 0.7255, Entropy: 1.3857 +[2026-03-20T17:23:32.068871Z] Loop 5: Loss: 1.67e-02, Avg Return: 0.111, Regret: 0.7249, Entropy: 1.3856 +[2026-03-20T17:23:32.955846Z] Loop 6: Loss: 1.72e-02, Avg Return: 0.112, Regret: 0.7244, Entropy: 1.3856 +[2026-03-20T17:23:33.845196Z] Loop 7: Loss: 1.64e-02, Avg Return: 0.110, Regret: 0.7239, Entropy: 1.3855 +[2026-03-20T17:23:34.732901Z] Loop 8: Loss: 1.81e-02, Avg Return: 0.116, Regret: 0.7233, Entropy: 1.3855 +[2026-03-20T17:23:35.621460Z] Loop 9: Loss: 1.71e-02, Avg Return: 0.114, Regret: 0.7228, Entropy: 1.3854 +[2026-03-20T17:23:36.510049Z] Loop 10: Loss: 1.93e-02, Avg Return: 0.114, Regret: 0.7222, Entropy: 1.3854 +[2026-03-20T17:23:37.398845Z] Loop 11: Loss: 2.02e-02, Avg Return: 0.113, Regret: 0.7217, Entropy: 1.3853 +[2026-03-20T17:23:38.287643Z] Loop 12: Loss: 1.80e-02, Avg Return: 0.113, Regret: 0.7211, Entropy: 1.3853 +[2026-03-20T17:23:39.176036Z] Loop 13: Loss: 1.95e-02, Avg Return: 0.116, Regret: 0.7205, Entropy: 1.3852 +[2026-03-20T17:23:40.063489Z] Loop 14: Loss: 1.97e-02, Avg Return: 0.120, Regret: 0.7199, Entropy: 1.3851 +[2026-03-20T17:23:40.950764Z] Loop 15: Loss: 1.96e-02, Avg Return: 0.113, Regret: 0.7192, Entropy: 1.3850 +[2026-03-20T17:23:41.837303Z] Loop 16: Loss: 1.91e-02, Avg Return: 0.114, Regret: 0.7186, Entropy: 1.3850 +[2026-03-20T17:23:42.724295Z] Loop 17: Loss: 1.90e-02, Avg Return: 0.116, Regret: 0.7179, Entropy: 1.3849 +[2026-03-20T17:23:43.612533Z] Loop 18: Loss: 1.95e-02, Avg Return: 0.117, Regret: 0.7172, Entropy: 1.3848 +[2026-03-20T17:23:44.501202Z] Loop 19: Loss: 1.96e-02, Avg Return: 0.120, Regret: 0.7165, Entropy: 1.3847 +[2026-03-20T17:23:45.390104Z] Loop 20: Loss: 1.74e-02, Avg Return: 0.117, Regret: 0.7157, Entropy: 1.3846 +[2026-03-20T17:23:46.277416Z] Loop 21: Loss: 1.80e-02, Avg Return: 0.119, Regret: 0.7150, Entropy: 1.3845 +[2026-03-20T17:23:47.165962Z] Loop 22: Loss: 1.93e-02, Avg Return: 0.117, Regret: 0.7142, Entropy: 1.3843 +[2026-03-20T17:23:48.053597Z] Loop 23: Loss: 1.97e-02, Avg Return: 0.118, Regret: 0.7133, Entropy: 1.3842 +[2026-03-20T17:23:48.938829Z] Loop 24: Loss: 1.92e-02, Avg Return: 0.123, Regret: 0.7124, Entropy: 1.3841 +[2026-03-20T17:23:49.825429Z] Loop 25: Loss: 1.98e-02, Avg Return: 0.123, Regret: 0.7115, Entropy: 1.3839 +[2026-03-20T17:23:50.712568Z] Loop 26: Loss: 2.08e-02, Avg Return: 0.122, Regret: 0.7106, Entropy: 1.3837 +[2026-03-20T17:23:51.599971Z] Loop 27: Loss: 1.82e-02, Avg Return: 0.120, Regret: 0.7095, Entropy: 1.3836 +[2026-03-20T17:23:52.486679Z] Loop 28: Loss: 2.05e-02, Avg Return: 0.119, Regret: 0.7085, Entropy: 1.3834 +[2026-03-20T17:23:53.376503Z] Loop 29: Loss: 2.06e-02, Avg Return: 0.124, Regret: 0.7074, Entropy: 1.3832 +[2026-03-20T17:23:54.266010Z] Loop 30: Loss: 1.94e-02, Avg Return: 0.122, Regret: 0.7062, Entropy: 1.3829 +[2026-03-20T17:23:55.152447Z] Loop 31: Loss: 1.87e-02, Avg Return: 0.127, Regret: 0.7050, Entropy: 1.3827 +[2026-03-20T17:23:56.040570Z] Loop 32: Loss: 2.19e-02, Avg Return: 0.127, Regret: 0.7037, Entropy: 1.3824 +[2026-03-20T17:23:56.928063Z] Loop 33: Loss: 1.98e-02, Avg Return: 0.129, Regret: 0.7024, Entropy: 1.3821 +[2026-03-20T17:23:57.816253Z] Loop 34: Loss: 2.21e-02, Avg Return: 0.131, Regret: 0.7011, Entropy: 1.3818 +[2026-03-20T17:23:58.704379Z] Loop 35: Loss: 2.28e-02, Avg Return: 0.133, Regret: 0.6996, Entropy: 1.3815 +[2026-03-20T17:23:59.590608Z] Loop 36: Loss: 2.32e-02, Avg Return: 0.130, Regret: 0.6981, Entropy: 1.3811 +[2026-03-20T17:24:00.478046Z] Loop 37: Loss: 2.62e-02, Avg Return: 0.135, Regret: 0.6965, Entropy: 1.3807 +[2026-03-20T17:24:01.365593Z] Loop 38: Loss: 2.28e-02, Avg Return: 0.133, Regret: 0.6947, Entropy: 1.3803 +[2026-03-20T17:24:02.252643Z] Loop 39: Loss: 2.37e-02, Avg Return: 0.136, Regret: 0.6929, Entropy: 1.3798 +[2026-03-20T17:24:03.141061Z] Loop 40: Loss: 2.40e-02, Avg Return: 0.142, Regret: 0.6909, Entropy: 1.3793 +[2026-03-20T17:24:04.029913Z] Loop 41: Loss: 2.46e-02, Avg Return: 0.139, Regret: 0.6888, Entropy: 1.3787 +[2026-03-20T17:24:04.920260Z] Loop 42: Loss: 2.39e-02, Avg Return: 0.147, Regret: 0.6865, Entropy: 1.3780 +[2026-03-20T17:24:05.810037Z] Loop 43: Loss: 2.48e-02, Avg Return: 0.144, Regret: 0.6840, Entropy: 1.3772 +[2026-03-20T17:24:06.699066Z] Loop 44: Loss: 2.41e-02, Avg Return: 0.144, Regret: 0.6814, Entropy: 1.3764 +[2026-03-20T17:24:07.586555Z] Loop 45: Loss: 2.71e-02, Avg Return: 0.146, Regret: 0.6786, Entropy: 1.3754 +[2026-03-20T17:24:08.471700Z] Loop 46: Loss: 2.67e-02, Avg Return: 0.146, Regret: 0.6756, Entropy: 1.3744 +[2026-03-20T17:24:09.358029Z] Loop 47: Loss: 2.79e-02, Avg Return: 0.148, Regret: 0.6725, Entropy: 1.3732 +[2026-03-20T17:24:10.246985Z] Loop 48: Loss: 3.00e-02, Avg Return: 0.159, Regret: 0.6691, Entropy: 1.3719 +[2026-03-20T17:24:11.135079Z] Loop 49: Loss: 2.96e-02, Avg Return: 0.164, Regret: 0.6655, Entropy: 1.3704 +[2026-03-20T17:24:12.021826Z] Loop 50: Loss: 2.99e-02, Avg Return: 0.167, Regret: 0.6618, Entropy: 1.3688 +[2026-03-20T17:24:12.908636Z] Loop 51: Loss: 3.26e-02, Avg Return: 0.170, Regret: 0.6578, Entropy: 1.3669 +[2026-03-20T17:24:13.797219Z] Loop 52: Loss: 3.20e-02, Avg Return: 0.170, Regret: 0.6536, Entropy: 1.3649 +[2026-03-20T17:24:14.685367Z] Loop 53: Loss: 3.25e-02, Avg Return: 0.178, Regret: 0.6491, Entropy: 1.3625 +[2026-03-20T17:24:15.573986Z] Loop 54: Loss: 3.55e-02, Avg Return: 0.181, Regret: 0.6444, Entropy: 1.3598 +[2026-03-20T17:24:16.462484Z] Loop 55: Loss: 3.77e-02, Avg Return: 0.193, Regret: 0.6394, Entropy: 1.3568 +[2026-03-20T17:24:17.350620Z] Loop 56: Loss: 3.65e-02, Avg Return: 0.200, Regret: 0.6341, Entropy: 1.3532 +[2026-03-20T17:24:18.239139Z] Loop 57: Loss: 3.62e-02, Avg Return: 0.205, Regret: 0.6284, Entropy: 1.3491 +[2026-03-20T17:24:19.127440Z] Loop 58: Loss: 4.24e-02, Avg Return: 0.207, Regret: 0.6225, Entropy: 1.3444 +[2026-03-20T17:24:20.015691Z] Loop 59: Loss: 4.35e-02, Avg Return: 0.221, Regret: 0.6164, Entropy: 1.3390 +[2026-03-20T17:24:20.907965Z] Loop 60: Loss: 4.54e-02, Avg Return: 0.224, Regret: 0.6102, Entropy: 1.3328 +[2026-03-20T17:24:21.796270Z] Loop 61: Loss: 4.87e-02, Avg Return: 0.237, Regret: 0.6039, Entropy: 1.3259 +[2026-03-20T17:24:22.683262Z] Loop 62: Loss: 4.69e-02, Avg Return: 0.248, Regret: 0.5975, Entropy: 1.3180 +[2026-03-20T17:24:23.573771Z] Loop 63: Loss: 5.13e-02, Avg Return: 0.252, Regret: 0.5912, Entropy: 1.3088 +[2026-03-20T17:24:24.463604Z] Loop 64: Loss: 4.87e-02, Avg Return: 0.267, Regret: 0.5848, Entropy: 1.2983 +[2026-03-20T17:24:25.352650Z] Loop 65: Loss: 5.29e-02, Avg Return: 0.279, Regret: 0.5784, Entropy: 1.2865 +[2026-03-20T17:24:26.241963Z] Loop 66: Loss: 5.12e-02, Avg Return: 0.282, Regret: 0.5722, Entropy: 1.2729 +[2026-03-20T17:24:27.132527Z] Loop 67: Loss: 4.94e-02, Avg Return: 0.291, Regret: 0.5662, Entropy: 1.2575 +[2026-03-20T17:24:28.022141Z] Loop 68: Loss: 4.89e-02, Avg Return: 0.300, Regret: 0.5604, Entropy: 1.2403 +[2026-03-20T17:24:28.913632Z] Loop 69: Loss: 4.75e-02, Avg Return: 0.302, Regret: 0.5550, Entropy: 1.2213 +[2026-03-20T17:24:29.801917Z] Loop 70: Loss: 4.85e-02, Avg Return: 0.312, Regret: 0.5500, Entropy: 1.2009 +[2026-03-20T17:24:30.692127Z] Loop 71: Loss: 4.51e-02, Avg Return: 0.320, Regret: 0.5454, Entropy: 1.1789 +[2026-03-20T17:24:31.580445Z] Loop 72: Loss: 4.34e-02, Avg Return: 0.324, Regret: 0.5413, Entropy: 1.1551 +[2026-03-20T17:24:32.468537Z] Loop 73: Loss: 3.94e-02, Avg Return: 0.324, Regret: 0.5375, Entropy: 1.1308 +[2026-03-20T17:24:33.358691Z] Loop 74: Loss: 3.75e-02, Avg Return: 0.323, Regret: 0.5342, Entropy: 1.1052 +[2026-03-20T17:24:34.246760Z] Loop 75: Loss: 3.37e-02, Avg Return: 0.330, Regret: 0.5312, Entropy: 1.0789 +[2026-03-20T17:24:35.133774Z] Loop 76: Loss: 3.42e-02, Avg Return: 0.335, Regret: 0.5286, Entropy: 1.0534 +[2026-03-20T17:24:36.020010Z] Loop 77: Loss: 3.33e-02, Avg Return: 0.337, Regret: 0.5264, Entropy: 1.0279 +[2026-03-20T17:24:36.908589Z] Loop 78: Loss: 3.06e-02, Avg Return: 0.337, Regret: 0.5244, Entropy: 1.0028 +[2026-03-20T17:24:37.797245Z] Loop 79: Loss: 2.97e-02, Avg Return: 0.338, Regret: 0.5227, Entropy: 0.9787 +[2026-03-20T17:24:38.688375Z] Loop 80: Loss: 2.81e-02, Avg Return: 0.342, Regret: 0.5212, Entropy: 0.9561 +[2026-03-20T17:24:39.584181Z] Loop 81: Loss: 2.71e-02, Avg Return: 0.342, Regret: 0.5200, Entropy: 0.9343 +[2026-03-20T17:24:40.472495Z] Loop 82: Loss: 2.47e-02, Avg Return: 0.343, Regret: 0.5189, Entropy: 0.9133 +[2026-03-20T17:24:41.362330Z] Loop 83: Loss: 2.67e-02, Avg Return: 0.357, Regret: 0.5180, Entropy: 0.8944 +[2026-03-20T17:24:42.252016Z] Loop 84: Loss: 2.37e-02, Avg Return: 0.347, Regret: 0.5172, Entropy: 0.8776 +[2026-03-20T17:24:43.139905Z] Loop 85: Loss: 2.34e-02, Avg Return: 0.346, Regret: 0.5166, Entropy: 0.8627 +[2026-03-20T17:24:44.027851Z] Loop 86: Loss: 2.27e-02, Avg Return: 0.347, Regret: 0.5161, Entropy: 0.8494 +[2026-03-20T17:24:44.917452Z] Loop 87: Loss: 2.21e-02, Avg Return: 0.343, Regret: 0.5157, Entropy: 0.8372 +[2026-03-20T17:24:45.804916Z] Loop 88: Loss: 2.31e-02, Avg Return: 0.350, Regret: 0.5153, Entropy: 0.8255 +[2026-03-20T17:24:46.693830Z] Loop 89: Loss: 2.23e-02, Avg Return: 0.351, Regret: 0.5150, Entropy: 0.8137 +[2026-03-20T17:24:47.583277Z] Loop 90: Loss: 2.37e-02, Avg Return: 0.357, Regret: 0.5146, Entropy: 0.8033 +[2026-03-20T17:24:48.471579Z] Loop 91: Loss: 2.02e-02, Avg Return: 0.347, Regret: 0.5144, Entropy: 0.7931 +[2026-03-20T17:24:49.361670Z] Loop 92: Loss: 2.05e-02, Avg Return: 0.350, Regret: 0.5141, Entropy: 0.7845 +[2026-03-20T17:24:50.248492Z] Loop 93: Loss: 2.00e-02, Avg Return: 0.351, Regret: 0.5139, Entropy: 0.7767 +[2026-03-20T17:24:51.136480Z] Loop 94: Loss: 2.01e-02, Avg Return: 0.349, Regret: 0.5137, Entropy: 0.7700 +[2026-03-20T17:24:52.023749Z] Loop 95: Loss: 2.00e-02, Avg Return: 0.356, Regret: 0.5136, Entropy: 0.7634 +[2026-03-20T17:24:52.911741Z] Loop 96: Loss: 2.02e-02, Avg Return: 0.344, Regret: 0.5135, Entropy: 0.7575 +[2026-03-20T17:24:53.799441Z] Loop 97: Loss: 1.91e-02, Avg Return: 0.345, Regret: 0.5134, Entropy: 0.7530 +[2026-03-20T17:24:54.688012Z] Loop 98: Loss: 1.99e-02, Avg Return: 0.348, Regret: 0.5134, Entropy: 0.7489 +[2026-03-20T17:24:55.578581Z] Loop 99: Loss: 2.04e-02, Avg Return: 0.344, Regret: 0.5133, Entropy: 0.7454 +[2026-03-20T17:24:56.468764Z] Loop 100: Loss: 1.99e-02, Avg Return: 0.358, Regret: 0.5132, Entropy: 0.7425 +[2026-03-20T17:24:57.357931Z] Loop 101: Loss: 1.93e-02, Avg Return: 0.356, Regret: 0.5132, Entropy: 0.7397 +[2026-03-20T17:24:58.248684Z] Loop 102: Loss: 1.85e-02, Avg Return: 0.352, Regret: 0.5131, Entropy: 0.7373 +[2026-03-20T17:24:59.136738Z] Loop 103: Loss: 1.99e-02, Avg Return: 0.353, Regret: 0.5131, Entropy: 0.7355 +[2026-03-20T17:25:00.026406Z] Loop 104: Loss: 1.85e-02, Avg Return: 0.352, Regret: 0.5131, Entropy: 0.7337 +[2026-03-20T17:25:00.915420Z] Loop 105: Loss: 1.92e-02, Avg Return: 0.345, Regret: 0.5130, Entropy: 0.7320 +[2026-03-20T17:25:01.806534Z] Loop 106: Loss: 1.89e-02, Avg Return: 0.354, Regret: 0.5130, Entropy: 0.7302 +[2026-03-20T17:25:02.695636Z] Loop 107: Loss: 1.86e-02, Avg Return: 0.350, Regret: 0.5130, Entropy: 0.7284 +[2026-03-20T17:25:03.582169Z] Loop 108: Loss: 1.88e-02, Avg Return: 0.350, Regret: 0.5130, Entropy: 0.7266 +[2026-03-20T17:25:04.470981Z] Loop 109: Loss: 1.83e-02, Avg Return: 0.352, Regret: 0.5130, Entropy: 0.7250 +[2026-03-20T17:25:05.359280Z] Loop 110: Loss: 1.86e-02, Avg Return: 0.346, Regret: 0.5129, Entropy: 0.7235 +[2026-03-20T17:25:06.247766Z] Loop 111: Loss: 1.90e-02, Avg Return: 0.354, Regret: 0.5129, Entropy: 0.7223 +[2026-03-20T17:25:07.135338Z] Loop 112: Loss: 1.73e-02, Avg Return: 0.349, Regret: 0.5129, Entropy: 0.7212 +[2026-03-20T17:25:08.023767Z] Loop 113: Loss: 1.75e-02, Avg Return: 0.350, Regret: 0.5129, Entropy: 0.7206 +[2026-03-20T17:25:08.912580Z] Loop 114: Loss: 1.87e-02, Avg Return: 0.352, Regret: 0.5129, Entropy: 0.7199 +[2026-03-20T17:25:09.801781Z] Loop 115: Loss: 1.68e-02, Avg Return: 0.340, Regret: 0.5129, Entropy: 0.7193 +[2026-03-20T17:25:10.689704Z] Loop 116: Loss: 1.76e-02, Avg Return: 0.344, Regret: 0.5129, Entropy: 0.7187 +[2026-03-20T17:25:11.578542Z] Loop 117: Loss: 1.97e-02, Avg Return: 0.355, Regret: 0.5129, Entropy: 0.7179 +[2026-03-20T17:25:12.466020Z] Loop 118: Loss: 1.81e-02, Avg Return: 0.350, Regret: 0.5130, Entropy: 0.7173 +[2026-03-20T17:25:13.353864Z] Loop 119: Loss: 1.92e-02, Avg Return: 0.354, Regret: 0.5131, Entropy: 0.7164 +[2026-03-20T17:25:14.243073Z] Loop 120: Loss: 1.83e-02, Avg Return: 0.353, Regret: 0.5133, Entropy: 0.7153 +[2026-03-20T17:25:15.136644Z] Loop 121: Loss: 1.92e-02, Avg Return: 0.352, Regret: 0.5133, Entropy: 0.7146 +[2026-03-20T17:25:16.024313Z] Loop 122: Loss: 2.03e-02, Avg Return: 0.350, Regret: 0.5133, Entropy: 0.7146 +[2026-03-20T17:25:16.914446Z] Loop 123: Loss: 1.72e-02, Avg Return: 0.345, Regret: 0.5132, Entropy: 0.7148 +[2026-03-20T17:25:17.804044Z] Loop 124: Loss: 1.94e-02, Avg Return: 0.353, Regret: 0.5131, Entropy: 0.7156 +[2026-03-20T17:25:18.693007Z] Loop 125: Loss: 1.86e-02, Avg Return: 0.352, Regret: 0.5130, Entropy: 0.7158 +[2026-03-20T17:25:19.581567Z] Loop 126: Loss: 1.88e-02, Avg Return: 0.353, Regret: 0.5129, Entropy: 0.7160 +[2026-03-20T17:25:20.469898Z] Loop 127: Loss: 1.80e-02, Avg Return: 0.350, Regret: 0.5129, Entropy: 0.7164 +[2026-03-20T17:25:21.359535Z] Loop 128: Loss: 1.93e-02, Avg Return: 0.350, Regret: 0.5128, Entropy: 0.7164 +[2026-03-20T17:25:22.248562Z] Loop 129: Loss: 1.94e-02, Avg Return: 0.349, Regret: 0.5129, Entropy: 0.7161 +[2026-03-20T17:25:23.137688Z] Loop 130: Loss: 1.83e-02, Avg Return: 0.348, Regret: 0.5129, Entropy: 0.7159 +[2026-03-20T17:25:24.026916Z] Loop 131: Loss: 1.82e-02, Avg Return: 0.355, Regret: 0.5129, Entropy: 0.7158 +[2026-03-20T17:25:24.917097Z] Loop 132: Loss: 1.87e-02, Avg Return: 0.346, Regret: 0.5129, Entropy: 0.7156 +[2026-03-20T17:25:25.805484Z] Loop 133: Loss: 1.78e-02, Avg Return: 0.349, Regret: 0.5129, Entropy: 0.7153 +[2026-03-20T17:25:26.693284Z] Loop 134: Loss: 1.87e-02, Avg Return: 0.358, Regret: 0.5129, Entropy: 0.7151 +[2026-03-20T17:25:27.581162Z] Loop 135: Loss: 1.78e-02, Avg Return: 0.347, Regret: 0.5129, Entropy: 0.7149 +[2026-03-20T17:25:28.469200Z] Loop 136: Loss: 1.89e-02, Avg Return: 0.352, Regret: 0.5130, Entropy: 0.7147 +[2026-03-20T17:25:29.358598Z] Loop 137: Loss: 2.02e-02, Avg Return: 0.352, Regret: 0.5130, Entropy: 0.7146 +[2026-03-20T17:25:30.245781Z] Loop 138: Loss: 1.69e-02, Avg Return: 0.349, Regret: 0.5130, Entropy: 0.7145 +[2026-03-20T17:25:31.134722Z] Loop 139: Loss: 1.88e-02, Avg Return: 0.355, Regret: 0.5129, Entropy: 0.7144 +[2026-03-20T17:25:32.022866Z] Loop 140: Loss: 1.86e-02, Avg Return: 0.348, Regret: 0.5129, Entropy: 0.7144 +[2026-03-20T17:25:32.911938Z] Loop 141: Loss: 1.87e-02, Avg Return: 0.354, Regret: 0.5130, Entropy: 0.7143 +[2026-03-20T17:25:33.800827Z] Loop 142: Loss: 1.93e-02, Avg Return: 0.356, Regret: 0.5130, Entropy: 0.7141 +[2026-03-20T17:25:34.690191Z] Loop 143: Loss: 1.77e-02, Avg Return: 0.349, Regret: 0.5129, Entropy: 0.7141 +[2026-03-20T17:25:35.579137Z] Loop 144: Loss: 1.85e-02, Avg Return: 0.356, Regret: 0.5129, Entropy: 0.7141 +[2026-03-20T17:25:36.468499Z] Loop 145: Loss: 1.78e-02, Avg Return: 0.352, Regret: 0.5129, Entropy: 0.7145 +[2026-03-20T17:25:37.358759Z] Loop 146: Loss: 1.79e-02, Avg Return: 0.352, Regret: 0.5129, Entropy: 0.7147 +[2026-03-20T17:25:38.248947Z] Loop 147: Loss: 1.79e-02, Avg Return: 0.349, Regret: 0.5128, Entropy: 0.7148 +[2026-03-20T17:25:39.138295Z] Loop 148: Loss: 1.83e-02, Avg Return: 0.353, Regret: 0.5128, Entropy: 0.7149 +[2026-03-20T17:25:40.029941Z] Loop 149: Loss: 2.02e-02, Avg Return: 0.351, Regret: 0.5128, Entropy: 0.7150 +[2026-03-20T17:25:40.919993Z] Loop 150: Loss: 1.81e-02, Avg Return: 0.351, Regret: 0.5129, Entropy: 0.7148 +[2026-03-20T17:25:41.808999Z] Loop 151: Loss: 1.80e-02, Avg Return: 0.349, Regret: 0.5129, Entropy: 0.7147 +[2026-03-20T17:25:42.697827Z] Loop 152: Loss: 1.88e-02, Avg Return: 0.352, Regret: 0.5129, Entropy: 0.7147 +[2026-03-20T17:25:43.587306Z] Loop 153: Loss: 1.85e-02, Avg Return: 0.350, Regret: 0.5129, Entropy: 0.7145 +[2026-03-20T17:25:44.477778Z] Loop 154: Loss: 1.88e-02, Avg Return: 0.347, Regret: 0.5129, Entropy: 0.7145 +[2026-03-20T17:25:45.367708Z] Loop 155: Loss: 1.94e-02, Avg Return: 0.351, Regret: 0.5128, Entropy: 0.7146 +[2026-03-20T17:25:46.258230Z] Loop 156: Loss: 1.74e-02, Avg Return: 0.346, Regret: 0.5128, Entropy: 0.7146 +[2026-03-20T17:25:47.147816Z] Loop 157: Loss: 1.81e-02, Avg Return: 0.344, Regret: 0.5128, Entropy: 0.7147 +[2026-03-20T17:25:48.036613Z] Loop 158: Loss: 1.95e-02, Avg Return: 0.348, Regret: 0.5128, Entropy: 0.7147 +[2026-03-20T17:25:48.925430Z] Loop 159: Loss: 1.90e-02, Avg Return: 0.344, Regret: 0.5128, Entropy: 0.7146 +[2026-03-20T17:25:49.814410Z] Loop 160: Loss: 1.94e-02, Avg Return: 0.355, Regret: 0.5129, Entropy: 0.7144 +[2026-03-20T17:25:50.703657Z] Loop 161: Loss: 1.76e-02, Avg Return: 0.346, Regret: 0.5129, Entropy: 0.7142 +[2026-03-20T17:25:51.593859Z] Loop 162: Loss: 1.76e-02, Avg Return: 0.346, Regret: 0.5130, Entropy: 0.7139 +[2026-03-20T17:25:52.482755Z] Loop 163: Loss: 1.87e-02, Avg Return: 0.345, Regret: 0.5130, Entropy: 0.7134 +[2026-03-20T17:25:53.369972Z] Loop 164: Loss: 1.99e-02, Avg Return: 0.360, Regret: 0.5131, Entropy: 0.7130 +[2026-03-20T17:25:54.257266Z] Loop 165: Loss: 1.75e-02, Avg Return: 0.355, Regret: 0.5131, Entropy: 0.7129 +[2026-03-20T17:25:55.146105Z] Loop 166: Loss: 1.86e-02, Avg Return: 0.352, Regret: 0.5130, Entropy: 0.7130 +[2026-03-20T17:25:56.034343Z] Loop 167: Loss: 1.81e-02, Avg Return: 0.346, Regret: 0.5130, Entropy: 0.7131 +[2026-03-20T17:25:56.926032Z] Loop 168: Loss: 1.86e-02, Avg Return: 0.351, Regret: 0.5129, Entropy: 0.7134 +[2026-03-20T17:25:57.816025Z] Loop 169: Loss: 1.88e-02, Avg Return: 0.356, Regret: 0.5129, Entropy: 0.7135 +[2026-03-20T17:25:58.705316Z] Loop 170: Loss: 1.90e-02, Avg Return: 0.359, Regret: 0.5128, Entropy: 0.7136 +[2026-03-20T17:25:59.594413Z] Loop 171: Loss: 1.81e-02, Avg Return: 0.348, Regret: 0.5128, Entropy: 0.7135 +[2026-03-20T17:26:00.484033Z] Loop 172: Loss: 1.85e-02, Avg Return: 0.353, Regret: 0.5128, Entropy: 0.7136 +[2026-03-20T17:26:01.374356Z] Loop 173: Loss: 1.88e-02, Avg Return: 0.351, Regret: 0.5128, Entropy: 0.7133 +[2026-03-20T17:26:02.263703Z] Loop 174: Loss: 1.92e-02, Avg Return: 0.354, Regret: 0.5129, Entropy: 0.7129 +[2026-03-20T17:26:03.152859Z] Loop 175: Loss: 1.86e-02, Avg Return: 0.350, Regret: 0.5131, Entropy: 0.7119 +[2026-03-20T17:26:04.041933Z] Loop 176: Loss: 1.85e-02, Avg Return: 0.352, Regret: 0.5134, Entropy: 0.7103 +[2026-03-20T17:26:04.933470Z] Loop 177: Loss: 1.75e-02, Avg Return: 0.344, Regret: 0.5139, Entropy: 0.7078 +[2026-03-20T17:26:05.824615Z] Loop 178: Loss: 1.78e-02, Avg Return: 0.345, Regret: 0.5143, Entropy: 0.7061 +[2026-03-20T17:26:06.714780Z] Loop 179: Loss: 1.86e-02, Avg Return: 0.353, Regret: 0.5145, Entropy: 0.7051 +[2026-03-20T17:26:07.607952Z] Loop 180: Loss: 1.79e-02, Avg Return: 0.353, Regret: 0.5145, Entropy: 0.7048 +[2026-03-20T17:26:08.498648Z] Loop 181: Loss: 1.87e-02, Avg Return: 0.353, Regret: 0.5146, Entropy: 0.7046 +[2026-03-20T17:26:09.388136Z] Loop 182: Loss: 2.02e-02, Avg Return: 0.352, Regret: 0.5143, Entropy: 0.7059 +[2026-03-20T17:26:10.278173Z] Loop 183: Loss: 1.93e-02, Avg Return: 0.350, Regret: 0.5137, Entropy: 0.7085 +[2026-03-20T17:26:11.169501Z] Loop 184: Loss: 1.75e-02, Avg Return: 0.350, Regret: 0.5132, Entropy: 0.7107 +[2026-03-20T17:26:12.058256Z] Loop 185: Loss: 1.78e-02, Avg Return: 0.349, Regret: 0.5129, Entropy: 0.7121 +[2026-03-20T17:26:12.946624Z] Loop 186: Loss: 1.75e-02, Avg Return: 0.344, Regret: 0.5128, Entropy: 0.7128 +[2026-03-20T17:26:13.836855Z] Loop 187: Loss: 1.87e-02, Avg Return: 0.349, Regret: 0.5128, Entropy: 0.7129 +[2026-03-20T17:26:14.728319Z] Loop 188: Loss: 1.83e-02, Avg Return: 0.349, Regret: 0.5129, Entropy: 0.7128 +[2026-03-20T17:26:15.617412Z] Loop 189: Loss: 1.85e-02, Avg Return: 0.350, Regret: 0.5130, Entropy: 0.7123 +[2026-03-20T17:26:16.505644Z] Loop 190: Loss: 1.86e-02, Avg Return: 0.354, Regret: 0.5132, Entropy: 0.7116 +[2026-03-20T17:26:17.394046Z] Loop 191: Loss: 1.85e-02, Avg Return: 0.341, Regret: 0.5133, Entropy: 0.7109 +[2026-03-20T17:26:18.282825Z] Loop 192: Loss: 1.81e-02, Avg Return: 0.348, Regret: 0.5133, Entropy: 0.7106 +[2026-03-20T17:26:19.173118Z] Loop 193: Loss: 1.87e-02, Avg Return: 0.350, Regret: 0.5132, Entropy: 0.7105 +[2026-03-20T17:26:20.064047Z] Loop 194: Loss: 1.86e-02, Avg Return: 0.352, Regret: 0.5131, Entropy: 0.7106 +[2026-03-20T17:26:20.953983Z] Loop 195: Loss: 1.81e-02, Avg Return: 0.347, Regret: 0.5129, Entropy: 0.7110 +[2026-03-20T17:26:21.844495Z] Loop 196: Loss: 1.91e-02, Avg Return: 0.351, Regret: 0.5128, Entropy: 0.7111 +[2026-03-20T17:26:22.734639Z] Loop 197: Loss: 1.91e-02, Avg Return: 0.351, Regret: 0.5128, Entropy: 0.7106 +[2026-03-20T17:26:23.626128Z] Loop 198: Loss: 1.81e-02, Avg Return: 0.352, Regret: 0.5129, Entropy: 0.7096 +[2026-03-20T17:26:24.514972Z] Loop 199: Loss: 1.80e-02, Avg Return: 0.350, Regret: 0.5131, Entropy: 0.7083 +[2026-03-20T17:26:25.403830Z] Loop 200: Loss: 1.85e-02, Avg Return: 0.347, Regret: 0.5133, Entropy: 0.7071 +[2026-03-20T17:26:26.292285Z] Loop 201: Loss: 1.75e-02, Avg Return: 0.350, Regret: 0.5135, Entropy: 0.7056 +[2026-03-20T17:26:27.180480Z] Loop 202: Loss: 1.71e-02, Avg Return: 0.343, Regret: 0.5136, Entropy: 0.7048 +[2026-03-20T17:26:28.071732Z] Loop 203: Loss: 1.81e-02, Avg Return: 0.354, Regret: 0.5137, Entropy: 0.7038 +[2026-03-20T17:26:28.962164Z] Loop 204: Loss: 1.79e-02, Avg Return: 0.357, Regret: 0.5138, Entropy: 0.7034 +[2026-03-20T17:26:29.851532Z] Loop 205: Loss: 1.72e-02, Avg Return: 0.344, Regret: 0.5137, Entropy: 0.7036 +[2026-03-20T17:26:30.742372Z] Loop 206: Loss: 1.75e-02, Avg Return: 0.352, Regret: 0.5135, Entropy: 0.7036 +[2026-03-20T17:26:31.632172Z] Loop 207: Loss: 1.84e-02, Avg Return: 0.352, Regret: 0.5133, Entropy: 0.7044 +[2026-03-20T17:26:32.521817Z] Loop 208: Loss: 1.74e-02, Avg Return: 0.348, Regret: 0.5130, Entropy: 0.7052 +[2026-03-20T17:26:33.412062Z] Loop 209: Loss: 1.90e-02, Avg Return: 0.350, Regret: 0.5128, Entropy: 0.7058 +[2026-03-20T17:26:34.299323Z] Loop 210: Loss: 1.92e-02, Avg Return: 0.359, Regret: 0.5127, Entropy: 0.7060 +[2026-03-20T17:26:35.188478Z] Loop 211: Loss: 1.80e-02, Avg Return: 0.348, Regret: 0.5127, Entropy: 0.7060 +[2026-03-20T17:26:36.078943Z] Loop 212: Loss: 1.55e-02, Avg Return: 0.342, Regret: 0.5127, Entropy: 0.7058 +[2026-03-20T17:26:36.970592Z] Loop 213: Loss: 1.76e-02, Avg Return: 0.352, Regret: 0.5128, Entropy: 0.7055 +[2026-03-20T17:26:37.862202Z] Loop 214: Loss: 1.77e-02, Avg Return: 0.347, Regret: 0.5128, Entropy: 0.7052 +[2026-03-20T17:26:38.753097Z] Loop 215: Loss: 1.85e-02, Avg Return: 0.348, Regret: 0.5128, Entropy: 0.7050 +[2026-03-20T17:26:39.643152Z] Loop 216: Loss: 1.76e-02, Avg Return: 0.345, Regret: 0.5128, Entropy: 0.7049 +[2026-03-20T17:26:40.532673Z] Loop 217: Loss: 1.81e-02, Avg Return: 0.357, Regret: 0.5128, Entropy: 0.7046 +[2026-03-20T17:26:41.422209Z] Loop 218: Loss: 1.74e-02, Avg Return: 0.347, Regret: 0.5127, Entropy: 0.7045 +[2026-03-20T17:26:42.310662Z] Loop 219: Loss: 1.88e-02, Avg Return: 0.356, Regret: 0.5127, Entropy: 0.7043 +[2026-03-20T17:26:43.200642Z] Loop 220: Loss: 1.93e-02, Avg Return: 0.351, Regret: 0.5128, Entropy: 0.7042 +[2026-03-20T17:26:44.090973Z] Loop 221: Loss: 1.83e-02, Avg Return: 0.341, Regret: 0.5128, Entropy: 0.7043 +[2026-03-20T17:26:44.979079Z] Loop 222: Loss: 1.74e-02, Avg Return: 0.350, Regret: 0.5127, Entropy: 0.7044 +[2026-03-20T17:26:45.867639Z] Loop 223: Loss: 1.81e-02, Avg Return: 0.353, Regret: 0.5127, Entropy: 0.7044 +[2026-03-20T17:26:46.755959Z] Loop 224: Loss: 1.81e-02, Avg Return: 0.346, Regret: 0.5127, Entropy: 0.7044 +[2026-03-20T17:26:47.644788Z] Loop 225: Loss: 1.78e-02, Avg Return: 0.354, Regret: 0.5127, Entropy: 0.7044 +[2026-03-20T17:26:48.533256Z] Loop 226: Loss: 1.87e-02, Avg Return: 0.347, Regret: 0.5127, Entropy: 0.7045 +[2026-03-20T17:26:49.422824Z] Loop 227: Loss: 1.67e-02, Avg Return: 0.351, Regret: 0.5127, Entropy: 0.7045 +[2026-03-20T17:26:50.310853Z] Loop 228: Loss: 1.82e-02, Avg Return: 0.351, Regret: 0.5127, Entropy: 0.7044 +[2026-03-20T17:26:51.199974Z] Loop 229: Loss: 1.66e-02, Avg Return: 0.352, Regret: 0.5128, Entropy: 0.7041 +[2026-03-20T17:26:52.088886Z] Loop 230: Loss: 1.84e-02, Avg Return: 0.356, Regret: 0.5129, Entropy: 0.7036 +[2026-03-20T17:26:52.978735Z] Loop 231: Loss: 1.88e-02, Avg Return: 0.351, Regret: 0.5130, Entropy: 0.7029 +[2026-03-20T17:26:53.868621Z] Loop 232: Loss: 1.92e-02, Avg Return: 0.358, Regret: 0.5129, Entropy: 0.7028 +[2026-03-20T17:26:54.760717Z] Loop 233: Loss: 1.77e-02, Avg Return: 0.352, Regret: 0.5129, Entropy: 0.7029 +[2026-03-20T17:26:55.650425Z] Loop 234: Loss: 1.77e-02, Avg Return: 0.346, Regret: 0.5129, Entropy: 0.7029 +[2026-03-20T17:26:56.540262Z] Loop 235: Loss: 1.67e-02, Avg Return: 0.353, Regret: 0.5128, Entropy: 0.7031 +[2026-03-20T17:26:57.430278Z] Loop 236: Loss: 1.85e-02, Avg Return: 0.350, Regret: 0.5127, Entropy: 0.7031 +[2026-03-20T17:26:58.321910Z] Loop 237: Loss: 1.75e-02, Avg Return: 0.350, Regret: 0.5127, Entropy: 0.7030 +[2026-03-20T17:26:59.211386Z] Loop 238: Loss: 1.77e-02, Avg Return: 0.346, Regret: 0.5127, Entropy: 0.7027 +[2026-03-20T17:27:00.100745Z] Loop 239: Loss: 1.68e-02, Avg Return: 0.352, Regret: 0.5127, Entropy: 0.7027 +[2026-03-20T17:27:00.991910Z] Loop 240: Loss: 1.80e-02, Avg Return: 0.349, Regret: 0.5127, Entropy: 0.7027 +[2026-03-20T17:27:01.882316Z] Loop 241: Loss: 1.65e-02, Avg Return: 0.347, Regret: 0.5127, Entropy: 0.7029 +[2026-03-20T17:27:02.771285Z] Loop 242: Loss: 1.79e-02, Avg Return: 0.349, Regret: 0.5127, Entropy: 0.7029 +[2026-03-20T17:27:03.659663Z] Loop 243: Loss: 1.66e-02, Avg Return: 0.351, Regret: 0.5127, Entropy: 0.7031 +[2026-03-20T17:27:04.551606Z] Loop 244: Loss: 1.90e-02, Avg Return: 0.352, Regret: 0.5127, Entropy: 0.7031 +[2026-03-20T17:27:05.443049Z] Loop 245: Loss: 1.82e-02, Avg Return: 0.348, Regret: 0.5127, Entropy: 0.7031 +[2026-03-20T17:27:06.334110Z] Loop 246: Loss: 1.71e-02, Avg Return: 0.349, Regret: 0.5127, Entropy: 0.7030 +[2026-03-20T17:27:07.221949Z] Loop 247: Loss: 1.83e-02, Avg Return: 0.353, Regret: 0.5127, Entropy: 0.7029 +[2026-03-20T17:27:08.110362Z] Loop 248: Loss: 1.83e-02, Avg Return: 0.349, Regret: 0.5127, Entropy: 0.7027 +[2026-03-20T17:27:08.998353Z] Loop 249: Loss: 1.76e-02, Avg Return: 0.355, Regret: 0.5127, Entropy: 0.7025 +[2026-03-20T17:27:09.888062Z] Loop 250: Loss: 1.82e-02, Avg Return: 0.351, Regret: 0.5128, Entropy: 0.7020 +[2026-03-20T17:27:10.740819Z] Loop 251: Loss: 1.84e-02, Avg Return: 0.354, Regret: 0.5128, Entropy: 0.7017 +[2026-03-20T17:27:11.631174Z] Loop 252: Loss: 1.91e-02, Avg Return: 0.358, Regret: 0.5129, Entropy: 0.7014 +[2026-03-20T17:27:12.482574Z] Loop 253: Loss: 1.87e-02, Avg Return: 0.354, Regret: 0.5129, Entropy: 0.7012 +[2026-03-20T17:27:13.370894Z] Loop 254: Loss: 1.82e-02, Avg Return: 0.351, Regret: 0.5128, Entropy: 0.7013 +[2026-03-20T17:27:14.223225Z] Loop 255: Loss: 1.94e-02, Avg Return: 0.357, Regret: 0.5128, Entropy: 0.7012 +[2026-03-20T17:27:15.113412Z] Loop 256: Loss: 1.83e-02, Avg Return: 0.356, Regret: 0.5128, Entropy: 0.7012 +[2026-03-20T17:27:15.965858Z] Loop 257: Loss: 1.80e-02, Avg Return: 0.346, Regret: 0.5128, Entropy: 0.7011 +[2026-03-20T17:27:16.854083Z] Loop 258: Loss: 1.78e-02, Avg Return: 0.345, Regret: 0.5128, Entropy: 0.7010 +[2026-03-20T17:27:17.707747Z] Loop 259: Loss: 1.80e-02, Avg Return: 0.359, Regret: 0.5128, Entropy: 0.7013 +[2026-03-20T17:27:18.599536Z] Loop 260: Loss: 1.72e-02, Avg Return: 0.348, Regret: 0.5127, Entropy: 0.7012 +[2026-03-20T17:27:19.452995Z] Loop 261: Loss: 1.82e-02, Avg Return: 0.354, Regret: 0.5127, Entropy: 0.7011 +[2026-03-20T17:27:20.342253Z] Loop 262: Loss: 1.86e-02, Avg Return: 0.355, Regret: 0.5127, Entropy: 0.7008 +[2026-03-20T17:27:21.195378Z] Loop 263: Loss: 1.88e-02, Avg Return: 0.355, Regret: 0.5127, Entropy: 0.7003 +[2026-03-20T17:27:22.085560Z] Loop 264: Loss: 1.73e-02, Avg Return: 0.350, Regret: 0.5128, Entropy: 0.6999 +[2026-03-20T17:27:22.939271Z] Loop 265: Loss: 1.67e-02, Avg Return: 0.342, Regret: 0.5128, Entropy: 0.6993 +[2026-03-20T17:27:23.828668Z] Loop 266: Loss: 1.84e-02, Avg Return: 0.349, Regret: 0.5130, Entropy: 0.6988 +[2026-03-20T17:27:24.682053Z] Loop 267: Loss: 1.76e-02, Avg Return: 0.351, Regret: 0.5130, Entropy: 0.6988 +[2026-03-20T17:27:25.571786Z] Loop 268: Loss: 1.83e-02, Avg Return: 0.354, Regret: 0.5129, Entropy: 0.6990 +[2026-03-20T17:27:26.423999Z] Loop 269: Loss: 1.82e-02, Avg Return: 0.349, Regret: 0.5129, Entropy: 0.6992 +[2026-03-20T17:27:27.314388Z] Loop 270: Loss: 1.86e-02, Avg Return: 0.358, Regret: 0.5128, Entropy: 0.6992 +[2026-03-20T17:27:28.167229Z] Loop 271: Loss: 1.86e-02, Avg Return: 0.360, Regret: 0.5128, Entropy: 0.6995 +[2026-03-20T17:27:29.056901Z] Loop 272: Loss: 1.88e-02, Avg Return: 0.350, Regret: 0.5127, Entropy: 0.6996 +[2026-03-20T17:27:29.908377Z] Loop 273: Loss: 1.86e-02, Avg Return: 0.349, Regret: 0.5127, Entropy: 0.6996 +[2026-03-20T17:27:30.799223Z] Loop 274: Loss: 1.81e-02, Avg Return: 0.353, Regret: 0.5127, Entropy: 0.6995 +[2026-03-20T17:27:31.652447Z] Loop 275: Loss: 1.81e-02, Avg Return: 0.351, Regret: 0.5127, Entropy: 0.6994 +[2026-03-20T17:27:32.541038Z] Loop 276: Loss: 1.89e-02, Avg Return: 0.358, Regret: 0.5127, Entropy: 0.6994 +[2026-03-20T17:27:33.392182Z] Loop 277: Loss: 1.73e-02, Avg Return: 0.354, Regret: 0.5127, Entropy: 0.6994 +[2026-03-20T17:27:34.281217Z] Loop 278: Loss: 1.77e-02, Avg Return: 0.352, Regret: 0.5127, Entropy: 0.6995 +[2026-03-20T17:27:35.134016Z] Loop 279: Loss: 1.74e-02, Avg Return: 0.349, Regret: 0.5127, Entropy: 0.6997 +[2026-03-20T17:27:36.022667Z] Loop 280: Loss: 1.82e-02, Avg Return: 0.355, Regret: 0.5127, Entropy: 0.6998 +[2026-03-20T17:27:36.874803Z] Loop 281: Loss: 1.77e-02, Avg Return: 0.348, Regret: 0.5127, Entropy: 0.6996 +[2026-03-20T17:27:37.762261Z] Loop 282: Loss: 1.75e-02, Avg Return: 0.344, Regret: 0.5128, Entropy: 0.6992 +[2026-03-20T17:27:38.614241Z] Loop 283: Loss: 1.75e-02, Avg Return: 0.350, Regret: 0.5128, Entropy: 0.6988 +[2026-03-20T17:27:39.505421Z] Loop 284: Loss: 1.75e-02, Avg Return: 0.348, Regret: 0.5129, Entropy: 0.6986 +[2026-03-20T17:27:40.358664Z] Loop 285: Loss: 1.91e-02, Avg Return: 0.348, Regret: 0.5129, Entropy: 0.6987 +[2026-03-20T17:27:41.249499Z] Loop 286: Loss: 1.70e-02, Avg Return: 0.347, Regret: 0.5128, Entropy: 0.6991 +[2026-03-20T17:27:42.101326Z] Loop 287: Loss: 1.84e-02, Avg Return: 0.351, Regret: 0.5128, Entropy: 0.6995 +[2026-03-20T17:27:42.992065Z] Loop 288: Loss: 1.84e-02, Avg Return: 0.352, Regret: 0.5127, Entropy: 0.6996 +[2026-03-20T17:27:43.846138Z] Loop 289: Loss: 1.79e-02, Avg Return: 0.355, Regret: 0.5127, Entropy: 0.6995 +[2026-03-20T17:27:44.736044Z] Loop 290: Loss: 1.77e-02, Avg Return: 0.351, Regret: 0.5128, Entropy: 0.6992 +[2026-03-20T17:27:45.588394Z] Loop 291: Loss: 1.73e-02, Avg Return: 0.349, Regret: 0.5128, Entropy: 0.6987 +[2026-03-20T17:27:46.478685Z] Loop 292: Loss: 1.74e-02, Avg Return: 0.347, Regret: 0.5131, Entropy: 0.6979 +[2026-03-20T17:27:47.332025Z] Loop 293: Loss: 1.74e-02, Avg Return: 0.345, Regret: 0.5131, Entropy: 0.6970 +[2026-03-20T17:27:48.221157Z] Loop 294: Loss: 1.92e-02, Avg Return: 0.349, Regret: 0.5133, Entropy: 0.6972 +[2026-03-20T17:27:49.074617Z] Loop 295: Loss: 1.70e-02, Avg Return: 0.348, Regret: 0.5133, Entropy: 0.6980 +[2026-03-20T17:27:49.963390Z] Loop 296: Loss: 1.74e-02, Avg Return: 0.355, Regret: 0.5129, Entropy: 0.6989 +[2026-03-20T17:27:50.816842Z] Loop 297: Loss: 1.70e-02, Avg Return: 0.343, Regret: 0.5129, Entropy: 0.6995 +[2026-03-20T17:27:51.706593Z] Loop 298: Loss: 1.88e-02, Avg Return: 0.351, Regret: 0.5127, Entropy: 0.6998 +[2026-03-20T17:27:52.558836Z] Loop 299: Loss: 1.84e-02, Avg Return: 0.352, Regret: 0.5127, Entropy: 0.6997 +[2026-03-20T17:27:53.446595Z] Loop 300: Loss: 1.80e-02, Avg Return: 0.351, Regret: 0.5127, Entropy: 0.6995 +[2026-03-20T17:27:54.298572Z] Loop 301: Loss: 1.80e-02, Avg Return: 0.352, Regret: 0.5127, Entropy: 0.6991 +[2026-03-20T17:27:55.187519Z] Loop 302: Loss: 1.82e-02, Avg Return: 0.347, Regret: 0.5129, Entropy: 0.6986 +[2026-03-20T17:27:56.039585Z] Loop 303: Loss: 1.77e-02, Avg Return: 0.351, Regret: 0.5129, Entropy: 0.6982 +[2026-03-20T17:27:56.928482Z] Loop 304: Loss: 1.83e-02, Avg Return: 0.350, Regret: 0.5131, Entropy: 0.6981 +[2026-03-20T17:27:57.781830Z] Loop 305: Loss: 1.85e-02, Avg Return: 0.353, Regret: 0.5131, Entropy: 0.6985 +[2026-03-20T17:27:58.670704Z] Loop 306: Loss: 1.78e-02, Avg Return: 0.353, Regret: 0.5130, Entropy: 0.6989 +[2026-03-20T17:27:59.523028Z] Loop 307: Loss: 2.00e-02, Avg Return: 0.356, Regret: 0.5130, Entropy: 0.6996 +[2026-03-20T17:28:00.412795Z] Loop 308: Loss: 1.80e-02, Avg Return: 0.347, Regret: 0.5127, Entropy: 0.7005 +[2026-03-20T17:28:01.266118Z] Loop 309: Loss: 1.77e-02, Avg Return: 0.350, Regret: 0.5127, Entropy: 0.7009 +[2026-03-20T17:28:02.157920Z] Loop 310: Loss: 1.74e-02, Avg Return: 0.341, Regret: 0.5127, Entropy: 0.7009 +[2026-03-20T17:28:03.010791Z] Loop 311: Loss: 1.74e-02, Avg Return: 0.350, Regret: 0.5127, Entropy: 0.7006 +[2026-03-20T17:28:03.900774Z] Loop 312: Loss: 1.89e-02, Avg Return: 0.355, Regret: 0.5131, Entropy: 0.6996 +[2026-03-20T17:28:04.754449Z] Loop 313: Loss: 1.77e-02, Avg Return: 0.347, Regret: 0.5131, Entropy: 0.6986 +[2026-03-20T17:28:05.646035Z] Loop 314: Loss: 1.78e-02, Avg Return: 0.354, Regret: 0.5136, Entropy: 0.6978 +[2026-03-20T17:28:06.498338Z] Loop 315: Loss: 1.78e-02, Avg Return: 0.353, Regret: 0.5136, Entropy: 0.6982 +[2026-03-20T17:28:07.389024Z] Loop 316: Loss: 1.75e-02, Avg Return: 0.346, Regret: 0.5132, Entropy: 0.6997 +[2026-03-20T17:28:08.243071Z] Loop 317: Loss: 1.81e-02, Avg Return: 0.354, Regret: 0.5132, Entropy: 0.7005 +[2026-03-20T17:28:09.132124Z] Loop 318: Loss: 1.81e-02, Avg Return: 0.352, Regret: 0.5128, Entropy: 0.7013 +[2026-03-20T17:28:09.985263Z] Loop 319: Loss: 1.79e-02, Avg Return: 0.346, Regret: 0.5128, Entropy: 0.7017 +[2026-03-20T17:28:10.875457Z] Loop 320: Loss: 1.65e-02, Avg Return: 0.349, Regret: 0.5127, Entropy: 0.7019 +[2026-03-20T17:28:11.727516Z] Loop 321: Loss: 1.86e-02, Avg Return: 0.348, Regret: 0.5127, Entropy: 0.7018 +[2026-03-20T17:28:12.618627Z] Loop 322: Loss: 1.74e-02, Avg Return: 0.347, Regret: 0.5128, Entropy: 0.7013 +[2026-03-20T17:28:13.471600Z] Loop 323: Loss: 1.72e-02, Avg Return: 0.359, Regret: 0.5128, Entropy: 0.7008 +[2026-03-20T17:28:14.362166Z] Loop 324: Loss: 1.83e-02, Avg Return: 0.349, Regret: 0.5130, Entropy: 0.7005 +[2026-03-20T17:28:15.214701Z] Loop 325: Loss: 1.89e-02, Avg Return: 0.356, Regret: 0.5130, Entropy: 0.6999 +[2026-03-20T17:28:16.104721Z] Loop 326: Loss: 1.87e-02, Avg Return: 0.345, Regret: 0.5134, Entropy: 0.6986 +[2026-03-20T17:28:16.957635Z] Loop 327: Loss: 1.77e-02, Avg Return: 0.352, Regret: 0.5134, Entropy: 0.6967 +[2026-03-20T17:28:17.849430Z] Loop 328: Loss: 1.84e-02, Avg Return: 0.354, Regret: 0.5140, Entropy: 0.6961 +[2026-03-20T17:28:18.701759Z] Loop 329: Loss: 1.68e-02, Avg Return: 0.342, Regret: 0.5140, Entropy: 0.6966 +[2026-03-20T17:28:19.592388Z] Loop 330: Loss: 1.88e-02, Avg Return: 0.351, Regret: 0.5137, Entropy: 0.6980 +[2026-03-20T17:28:20.444434Z] Loop 331: Loss: 1.88e-02, Avg Return: 0.350, Regret: 0.5137, Entropy: 0.6996 +[2026-03-20T17:28:21.336166Z] Loop 332: Loss: 1.88e-02, Avg Return: 0.355, Regret: 0.5130, Entropy: 0.7013 +[2026-03-20T17:28:22.189386Z] Loop 333: Loss: 1.75e-02, Avg Return: 0.349, Regret: 0.5130, Entropy: 0.7026 +[2026-03-20T17:28:23.081624Z] Loop 334: Loss: 1.79e-02, Avg Return: 0.354, Regret: 0.5127, Entropy: 0.7035 +[2026-03-20T17:28:23.934610Z] Loop 335: Loss: 1.84e-02, Avg Return: 0.353, Regret: 0.5127, Entropy: 0.7039 +[2026-03-20T17:28:24.824197Z] Loop 336: Loss: 1.77e-02, Avg Return: 0.349, Regret: 0.5128, Entropy: 0.7035 +[2026-03-20T17:28:25.677698Z] Loop 337: Loss: 1.89e-02, Avg Return: 0.354, Regret: 0.5128, Entropy: 0.7029 +[2026-03-20T17:28:26.568042Z] Loop 338: Loss: 1.84e-02, Avg Return: 0.348, Regret: 0.5133, Entropy: 0.7021 +[2026-03-20T17:28:27.419894Z] Loop 339: Loss: 1.75e-02, Avg Return: 0.348, Regret: 0.5133, Entropy: 0.7018 +[2026-03-20T17:28:28.308507Z] Loop 340: Loss: 1.86e-02, Avg Return: 0.354, Regret: 0.5135, Entropy: 0.7019 +[2026-03-20T17:28:29.161265Z] Loop 341: Loss: 1.87e-02, Avg Return: 0.357, Regret: 0.5135, Entropy: 0.7021 +[2026-03-20T17:28:30.051509Z] Loop 342: Loss: 1.96e-02, Avg Return: 0.350, Regret: 0.5134, Entropy: 0.7027 +[2026-03-20T17:28:30.904638Z] Loop 343: Loss: 2.04e-02, Avg Return: 0.365, Regret: 0.5134, Entropy: 0.7036 +[2026-03-20T17:28:31.792873Z] Loop 344: Loss: 1.81e-02, Avg Return: 0.352, Regret: 0.5131, Entropy: 0.7045 +[2026-03-20T17:28:32.644717Z] Loop 345: Loss: 1.94e-02, Avg Return: 0.348, Regret: 0.5131, Entropy: 0.7057 +[2026-03-20T17:28:33.533498Z] Loop 346: Loss: 1.70e-02, Avg Return: 0.348, Regret: 0.5128, Entropy: 0.7063 +[2026-03-20T17:28:34.386016Z] Loop 347: Loss: 1.85e-02, Avg Return: 0.349, Regret: 0.5128, Entropy: 0.7070 +[2026-03-20T17:28:35.275147Z] Loop 348: Loss: 1.74e-02, Avg Return: 0.342, Regret: 0.5128, Entropy: 0.7073 +[2026-03-20T17:28:36.128458Z] Loop 349: Loss: 1.89e-02, Avg Return: 0.355, Regret: 0.5128, Entropy: 0.7076 +[2026-03-20T17:28:37.018369Z] Loop 350: Loss: 1.77e-02, Avg Return: 0.351, Regret: 0.5127, Entropy: 0.7078 +[2026-03-20T17:28:37.870726Z] Loop 351: Loss: 1.70e-02, Avg Return: 0.352, Regret: 0.5127, Entropy: 0.7078 +[2026-03-20T17:28:38.761101Z] Loop 352: Loss: 1.69e-02, Avg Return: 0.354, Regret: 0.5127, Entropy: 0.7077 +[2026-03-20T17:28:39.614571Z] Loop 353: Loss: 1.77e-02, Avg Return: 0.355, Regret: 0.5127, Entropy: 0.7077 +[2026-03-20T17:28:40.504307Z] Loop 354: Loss: 1.90e-02, Avg Return: 0.352, Regret: 0.5128, Entropy: 0.7077 +[2026-03-20T17:28:41.356978Z] Loop 355: Loss: 1.85e-02, Avg Return: 0.346, Regret: 0.5128, Entropy: 0.7080 +[2026-03-20T17:28:42.247879Z] Loop 356: Loss: 1.90e-02, Avg Return: 0.353, Regret: 0.5128, Entropy: 0.7082 +[2026-03-20T17:28:43.100488Z] Loop 357: Loss: 1.86e-02, Avg Return: 0.351, Regret: 0.5128, Entropy: 0.7082 +[2026-03-20T17:28:43.991793Z] Loop 358: Loss: 1.89e-02, Avg Return: 0.349, Regret: 0.5128, Entropy: 0.7081 +[2026-03-20T17:28:44.843977Z] Loop 359: Loss: 1.96e-02, Avg Return: 0.357, Regret: 0.5128, Entropy: 0.7082 +[2026-03-20T17:28:45.734871Z] Loop 360: Loss: 1.78e-02, Avg Return: 0.349, Regret: 0.5128, Entropy: 0.7081 +[2026-03-20T17:28:46.587763Z] Loop 361: Loss: 1.93e-02, Avg Return: 0.353, Regret: 0.5128, Entropy: 0.7082 +[2026-03-20T17:28:47.478992Z] Loop 362: Loss: 1.98e-02, Avg Return: 0.354, Regret: 0.5127, Entropy: 0.7084 +[2026-03-20T17:28:48.331445Z] Loop 363: Loss: 1.92e-02, Avg Return: 0.356, Regret: 0.5127, Entropy: 0.7082 +[2026-03-20T17:28:49.221033Z] Loop 364: Loss: 1.67e-02, Avg Return: 0.348, Regret: 0.5127, Entropy: 0.7081 +[2026-03-20T17:28:50.073551Z] Loop 365: Loss: 1.83e-02, Avg Return: 0.350, Regret: 0.5127, Entropy: 0.7080 +[2026-03-20T17:28:50.963205Z] Loop 366: Loss: 1.85e-02, Avg Return: 0.354, Regret: 0.5127, Entropy: 0.7077 +[2026-03-20T17:28:51.816578Z] Loop 367: Loss: 1.90e-02, Avg Return: 0.346, Regret: 0.5127, Entropy: 0.7074 +[2026-03-20T17:28:52.707183Z] Loop 368: Loss: 1.79e-02, Avg Return: 0.351, Regret: 0.5128, Entropy: 0.7071 +[2026-03-20T17:28:53.565833Z] Loop 369: Loss: 1.87e-02, Avg Return: 0.348, Regret: 0.5128, Entropy: 0.7067 +[2026-03-20T17:28:54.455279Z] Loop 370: Loss: 1.89e-02, Avg Return: 0.350, Regret: 0.5130, Entropy: 0.7062 +[2026-03-20T17:28:55.307734Z] Loop 371: Loss: 1.84e-02, Avg Return: 0.346, Regret: 0.5130, Entropy: 0.7056 +[2026-03-20T17:28:56.196697Z] Loop 372: Loss: 1.76e-02, Avg Return: 0.351, Regret: 0.5132, Entropy: 0.7050 +[2026-03-20T17:28:57.049449Z] Loop 373: Loss: 1.84e-02, Avg Return: 0.349, Regret: 0.5132, Entropy: 0.7047 +[2026-03-20T17:28:57.938741Z] Loop 374: Loss: 1.83e-02, Avg Return: 0.352, Regret: 0.5131, Entropy: 0.7052 +[2026-03-20T17:28:58.792510Z] Loop 375: Loss: 1.77e-02, Avg Return: 0.346, Regret: 0.5131, Entropy: 0.7056 +[2026-03-20T17:28:59.684813Z] Loop 376: Loss: 1.72e-02, Avg Return: 0.342, Regret: 0.5129, Entropy: 0.7060 +[2026-03-20T17:29:00.538981Z] Loop 377: Loss: 1.89e-02, Avg Return: 0.347, Regret: 0.5129, Entropy: 0.7067 +[2026-03-20T17:29:01.427871Z] Loop 378: Loss: 1.90e-02, Avg Return: 0.351, Regret: 0.5127, Entropy: 0.7072 +[2026-03-20T17:29:02.280760Z] Loop 379: Loss: 1.83e-02, Avg Return: 0.357, Regret: 0.5127, Entropy: 0.7073 +[2026-03-20T17:29:03.172429Z] Loop 380: Loss: 1.91e-02, Avg Return: 0.352, Regret: 0.5127, Entropy: 0.7073 +[2026-03-20T17:29:04.025075Z] Loop 381: Loss: 1.74e-02, Avg Return: 0.347, Regret: 0.5127, Entropy: 0.7068 +[2026-03-20T17:29:04.914957Z] Loop 382: Loss: 1.88e-02, Avg Return: 0.354, Regret: 0.5128, Entropy: 0.7064 +[2026-03-20T17:29:05.768379Z] Loop 383: Loss: 1.81e-02, Avg Return: 0.351, Regret: 0.5128, Entropy: 0.7057 +[2026-03-20T17:29:06.660269Z] Loop 384: Loss: 1.76e-02, Avg Return: 0.347, Regret: 0.5131, Entropy: 0.7052 +[2026-03-20T17:29:07.513232Z] Loop 385: Loss: 1.76e-02, Avg Return: 0.342, Regret: 0.5131, Entropy: 0.7051 +[2026-03-20T17:29:08.403919Z] Loop 386: Loss: 1.76e-02, Avg Return: 0.352, Regret: 0.5131, Entropy: 0.7050 +[2026-03-20T17:29:09.256060Z] Loop 387: Loss: 1.85e-02, Avg Return: 0.352, Regret: 0.5131, Entropy: 0.7053 +[2026-03-20T17:29:10.145149Z] Loop 388: Loss: 1.90e-02, Avg Return: 0.352, Regret: 0.5129, Entropy: 0.7057 +[2026-03-20T17:29:10.997522Z] Loop 389: Loss: 1.84e-02, Avg Return: 0.353, Regret: 0.5129, Entropy: 0.7061 +[2026-03-20T17:29:11.887383Z] Loop 390: Loss: 1.83e-02, Avg Return: 0.355, Regret: 0.5127, Entropy: 0.7066 +[2026-03-20T17:29:12.740405Z] Loop 391: Loss: 1.74e-02, Avg Return: 0.342, Regret: 0.5127, Entropy: 0.7066 +[2026-03-20T17:29:13.630806Z] Loop 392: Loss: 2.05e-02, Avg Return: 0.356, Regret: 0.5127, Entropy: 0.7067 +[2026-03-20T17:29:14.482588Z] Loop 393: Loss: 1.89e-02, Avg Return: 0.360, Regret: 0.5127, Entropy: 0.7071 +[2026-03-20T17:29:15.372431Z] Loop 394: Loss: 1.81e-02, Avg Return: 0.351, Regret: 0.5127, Entropy: 0.7074 +[2026-03-20T17:29:16.226300Z] Loop 395: Loss: 1.69e-02, Avg Return: 0.348, Regret: 0.5127, Entropy: 0.7074 +[2026-03-20T17:29:17.118157Z] Loop 396: Loss: 1.83e-02, Avg Return: 0.340, Regret: 0.5127, Entropy: 0.7074 +[2026-03-20T17:29:17.970224Z] Loop 397: Loss: 1.84e-02, Avg Return: 0.352, Regret: 0.5127, Entropy: 0.7074 +[2026-03-20T17:29:18.857967Z] Loop 398: Loss: 1.92e-02, Avg Return: 0.351, Regret: 0.5127, Entropy: 0.7073 +[2026-03-20T17:29:19.709978Z] Loop 399: Loss: 1.99e-02, Avg Return: 0.350, Regret: 0.5127, Entropy: 0.7071 +[2026-03-20T17:29:20.599443Z] Loop 400: Loss: 1.91e-02, Avg Return: 0.355, Regret: 0.5127, Entropy: 0.7067 +[2026-03-20T17:29:21.452153Z] Loop 401: Loss: 1.69e-02, Avg Return: 0.349, Regret: 0.5127, Entropy: 0.7060 +[2026-03-20T17:29:22.341587Z] Loop 402: Loss: 1.92e-02, Avg Return: 0.350, Regret: 0.5130, Entropy: 0.7051 +[2026-03-20T17:29:23.193643Z] Loop 403: Loss: 1.97e-02, Avg Return: 0.353, Regret: 0.5130, Entropy: 0.7044 +[2026-03-20T17:29:24.083435Z] Loop 404: Loss: 1.84e-02, Avg Return: 0.350, Regret: 0.5132, Entropy: 0.7045 +[2026-03-20T17:29:24.935113Z] Loop 405: Loss: 1.87e-02, Avg Return: 0.354, Regret: 0.5132, Entropy: 0.7050 +[2026-03-20T17:29:25.826506Z] Loop 406: Loss: 1.81e-02, Avg Return: 0.356, Regret: 0.5129, Entropy: 0.7058 +[2026-03-20T17:29:26.678901Z] Loop 407: Loss: 1.88e-02, Avg Return: 0.346, Regret: 0.5129, Entropy: 0.7064 +[2026-03-20T17:29:27.568393Z] Loop 408: Loss: 1.92e-02, Avg Return: 0.349, Regret: 0.5127, Entropy: 0.7068 +[2026-03-20T17:29:28.420395Z] Loop 409: Loss: 1.74e-02, Avg Return: 0.349, Regret: 0.5127, Entropy: 0.7069 +[2026-03-20T17:29:29.310028Z] Loop 410: Loss: 1.69e-02, Avg Return: 0.346, Regret: 0.5127, Entropy: 0.7069 +[2026-03-20T17:29:30.162472Z] Loop 411: Loss: 1.98e-02, Avg Return: 0.353, Regret: 0.5127, Entropy: 0.7065 +[2026-03-20T17:29:31.050228Z] Loop 412: Loss: 1.64e-02, Avg Return: 0.343, Regret: 0.5129, Entropy: 0.7061 +[2026-03-20T17:29:31.902268Z] Loop 413: Loss: 1.74e-02, Avg Return: 0.345, Regret: 0.5129, Entropy: 0.7058 +[2026-03-20T17:29:32.792793Z] Loop 414: Loss: 1.78e-02, Avg Return: 0.343, Regret: 0.5130, Entropy: 0.7058 +[2026-03-20T17:29:33.645472Z] Loop 415: Loss: 1.88e-02, Avg Return: 0.353, Regret: 0.5130, Entropy: 0.7060 +[2026-03-20T17:29:34.533438Z] Loop 416: Loss: 1.92e-02, Avg Return: 0.350, Regret: 0.5129, Entropy: 0.7061 +[2026-03-20T17:29:35.384811Z] Loop 417: Loss: 1.87e-02, Avg Return: 0.355, Regret: 0.5129, Entropy: 0.7062 +[2026-03-20T17:29:36.274224Z] Loop 418: Loss: 1.85e-02, Avg Return: 0.352, Regret: 0.5128, Entropy: 0.7065 +[2026-03-20T17:29:37.126963Z] Loop 419: Loss: 1.85e-02, Avg Return: 0.351, Regret: 0.5128, Entropy: 0.7067 +[2026-03-20T17:29:38.015240Z] Loop 420: Loss: 1.86e-02, Avg Return: 0.345, Regret: 0.5127, Entropy: 0.7069 +[2026-03-20T17:29:38.867526Z] Loop 421: Loss: 1.93e-02, Avg Return: 0.354, Regret: 0.5127, Entropy: 0.7069 +[2026-03-20T17:29:39.757460Z] Loop 422: Loss: 1.69e-02, Avg Return: 0.351, Regret: 0.5127, Entropy: 0.7067 +[2026-03-20T17:29:40.611014Z] Loop 423: Loss: 1.90e-02, Avg Return: 0.353, Regret: 0.5127, Entropy: 0.7067 +[2026-03-20T17:29:41.501678Z] Loop 424: Loss: 1.94e-02, Avg Return: 0.354, Regret: 0.5127, Entropy: 0.7065 +[2026-03-20T17:29:42.354762Z] Loop 425: Loss: 1.85e-02, Avg Return: 0.360, Regret: 0.5127, Entropy: 0.7063 +[2026-03-20T17:29:43.243313Z] Loop 426: Loss: 1.89e-02, Avg Return: 0.346, Regret: 0.5127, Entropy: 0.7063 +[2026-03-20T17:29:44.095115Z] Loop 427: Loss: 1.91e-02, Avg Return: 0.352, Regret: 0.5127, Entropy: 0.7064 +[2026-03-20T17:29:44.984515Z] Loop 428: Loss: 1.82e-02, Avg Return: 0.360, Regret: 0.5126, Entropy: 0.7066 +[2026-03-20T17:29:45.837702Z] Loop 429: Loss: 1.85e-02, Avg Return: 0.349, Regret: 0.5126, Entropy: 0.7068 +[2026-03-20T17:29:46.728315Z] Loop 430: Loss: 2.04e-02, Avg Return: 0.359, Regret: 0.5126, Entropy: 0.7070 +[2026-03-20T17:29:47.580834Z] Loop 431: Loss: 1.87e-02, Avg Return: 0.344, Regret: 0.5126, Entropy: 0.7072 +[2026-03-20T17:29:48.471981Z] Loop 432: Loss: 1.84e-02, Avg Return: 0.352, Regret: 0.5127, Entropy: 0.7073 +[2026-03-20T17:29:49.325512Z] Loop 433: Loss: 1.79e-02, Avg Return: 0.348, Regret: 0.5127, Entropy: 0.7073 +[2026-03-20T17:29:50.217460Z] Loop 434: Loss: 1.75e-02, Avg Return: 0.353, Regret: 0.5127, Entropy: 0.7075 +[2026-03-20T17:29:51.069567Z] Loop 435: Loss: 1.77e-02, Avg Return: 0.347, Regret: 0.5127, Entropy: 0.7075 +[2026-03-20T17:29:51.961474Z] Loop 436: Loss: 1.87e-02, Avg Return: 0.349, Regret: 0.5127, Entropy: 0.7077 +[2026-03-20T17:29:52.814840Z] Loop 437: Loss: 1.86e-02, Avg Return: 0.345, Regret: 0.5127, Entropy: 0.7078 +[2026-03-20T17:29:53.705162Z] Loop 438: Loss: 1.90e-02, Avg Return: 0.356, Regret: 0.5127, Entropy: 0.7080 +[2026-03-20T17:29:54.558443Z] Loop 439: Loss: 1.95e-02, Avg Return: 0.356, Regret: 0.5127, Entropy: 0.7078 +[2026-03-20T17:29:55.447696Z] Loop 440: Loss: 1.88e-02, Avg Return: 0.355, Regret: 0.5127, Entropy: 0.7078 +[2026-03-20T17:29:56.300142Z] Loop 441: Loss: 1.85e-02, Avg Return: 0.348, Regret: 0.5127, Entropy: 0.7077 +[2026-03-20T17:29:57.191112Z] Loop 442: Loss: 1.90e-02, Avg Return: 0.351, Regret: 0.5127, Entropy: 0.7076 +[2026-03-20T17:29:58.046387Z] Loop 443: Loss: 1.99e-02, Avg Return: 0.353, Regret: 0.5127, Entropy: 0.7074 +[2026-03-20T17:29:58.936151Z] Loop 444: Loss: 1.84e-02, Avg Return: 0.353, Regret: 0.5128, Entropy: 0.7071 +[2026-03-20T17:29:59.789833Z] Loop 445: Loss: 1.86e-02, Avg Return: 0.351, Regret: 0.5128, Entropy: 0.7068 +[2026-03-20T17:30:00.679662Z] Loop 446: Loss: 1.83e-02, Avg Return: 0.349, Regret: 0.5129, Entropy: 0.7067 +[2026-03-20T17:30:01.533990Z] Loop 447: Loss: 1.91e-02, Avg Return: 0.352, Regret: 0.5129, Entropy: 0.7065 +[2026-03-20T17:30:02.428313Z] Loop 448: Loss: 1.86e-02, Avg Return: 0.349, Regret: 0.5128, Entropy: 0.7067 +[2026-03-20T17:30:03.283646Z] Loop 449: Loss: 1.76e-02, Avg Return: 0.351, Regret: 0.5128, Entropy: 0.7068 +[2026-03-20T17:30:04.173074Z] Loop 450: Loss: 1.78e-02, Avg Return: 0.353, Regret: 0.5127, Entropy: 0.7069 +[2026-03-20T17:30:05.025263Z] Loop 451: Loss: 1.84e-02, Avg Return: 0.351, Regret: 0.5127, Entropy: 0.7067 +[2026-03-20T17:30:05.914959Z] Loop 452: Loss: 1.79e-02, Avg Return: 0.350, Regret: 0.5126, Entropy: 0.7066 +[2026-03-20T17:30:06.767086Z] Loop 453: Loss: 1.72e-02, Avg Return: 0.351, Regret: 0.5126, Entropy: 0.7065 +[2026-03-20T17:30:07.657695Z] Loop 454: Loss: 1.79e-02, Avg Return: 0.353, Regret: 0.5126, Entropy: 0.7063 +[2026-03-20T17:30:08.510384Z] Loop 455: Loss: 1.79e-02, Avg Return: 0.349, Regret: 0.5126, Entropy: 0.7062 +[2026-03-20T17:30:09.401224Z] Loop 456: Loss: 1.89e-02, Avg Return: 0.353, Regret: 0.5127, Entropy: 0.7063 +[2026-03-20T17:30:10.254395Z] Loop 457: Loss: 1.91e-02, Avg Return: 0.358, Regret: 0.5127, Entropy: 0.7064 +[2026-03-20T17:30:11.144648Z] Loop 458: Loss: 1.78e-02, Avg Return: 0.354, Regret: 0.5126, Entropy: 0.7070 +[2026-03-20T17:30:11.997623Z] Loop 459: Loss: 1.80e-02, Avg Return: 0.355, Regret: 0.5126, Entropy: 0.7073 +[2026-03-20T17:30:12.888133Z] Loop 460: Loss: 1.81e-02, Avg Return: 0.344, Regret: 0.5126, Entropy: 0.7077 +[2026-03-20T17:30:13.742299Z] Loop 461: Loss: 1.83e-02, Avg Return: 0.360, Regret: 0.5126, Entropy: 0.7079 +[2026-03-20T17:30:14.631370Z] Loop 462: Loss: 1.84e-02, Avg Return: 0.349, Regret: 0.5126, Entropy: 0.7081 +[2026-03-20T17:30:15.484268Z] Loop 463: Loss: 1.76e-02, Avg Return: 0.345, Regret: 0.5126, Entropy: 0.7082 +[2026-03-20T17:30:16.374159Z] Loop 464: Loss: 1.88e-02, Avg Return: 0.349, Regret: 0.5126, Entropy: 0.7084 +[2026-03-20T17:30:17.227047Z] Loop 465: Loss: 1.75e-02, Avg Return: 0.349, Regret: 0.5126, Entropy: 0.7084 +[2026-03-20T17:30:18.116825Z] Loop 466: Loss: 1.91e-02, Avg Return: 0.349, Regret: 0.5127, Entropy: 0.7085 +[2026-03-20T17:30:18.970075Z] Loop 467: Loss: 1.73e-02, Avg Return: 0.347, Regret: 0.5127, Entropy: 0.7086 +[2026-03-20T17:30:19.861349Z] Loop 468: Loss: 1.85e-02, Avg Return: 0.352, Regret: 0.5127, Entropy: 0.7087 +[2026-03-20T17:30:20.714242Z] Loop 469: Loss: 1.84e-02, Avg Return: 0.352, Regret: 0.5127, Entropy: 0.7091 +[2026-03-20T17:30:21.605905Z] Loop 470: Loss: 1.84e-02, Avg Return: 0.351, Regret: 0.5127, Entropy: 0.7092 +[2026-03-20T17:30:22.459277Z] Loop 471: Loss: 1.76e-02, Avg Return: 0.353, Regret: 0.5127, Entropy: 0.7093 +[2026-03-20T17:30:23.350263Z] Loop 472: Loss: 1.84e-02, Avg Return: 0.351, Regret: 0.5127, Entropy: 0.7094 +[2026-03-20T17:30:24.202799Z] Loop 473: Loss: 1.79e-02, Avg Return: 0.352, Regret: 0.5127, Entropy: 0.7097 +[2026-03-20T17:30:25.091429Z] Loop 474: Loss: 1.90e-02, Avg Return: 0.355, Regret: 0.5127, Entropy: 0.7099 +[2026-03-20T17:30:25.943661Z] Loop 475: Loss: 1.83e-02, Avg Return: 0.349, Regret: 0.5127, Entropy: 0.7101 +[2026-03-20T17:30:26.834731Z] Loop 476: Loss: 1.85e-02, Avg Return: 0.349, Regret: 0.5127, Entropy: 0.7100 +[2026-03-20T17:30:27.686943Z] Loop 477: Loss: 1.79e-02, Avg Return: 0.345, Regret: 0.5127, Entropy: 0.7099 +[2026-03-20T17:30:28.580208Z] Loop 478: Loss: 1.82e-02, Avg Return: 0.351, Regret: 0.5128, Entropy: 0.7094 +[2026-03-20T17:30:29.432137Z] Loop 479: Loss: 1.80e-02, Avg Return: 0.350, Regret: 0.5128, Entropy: 0.7091 +[2026-03-20T17:30:30.321029Z] Loop 480: Loss: 2.01e-02, Avg Return: 0.351, Regret: 0.5129, Entropy: 0.7091 +[2026-03-20T17:30:31.173536Z] Loop 481: Loss: 1.86e-02, Avg Return: 0.350, Regret: 0.5129, Entropy: 0.7094 +[2026-03-20T17:30:32.063898Z] Loop 482: Loss: 1.93e-02, Avg Return: 0.348, Regret: 0.5127, Entropy: 0.7099 +[2026-03-20T17:30:32.916896Z] Loop 483: Loss: 1.80e-02, Avg Return: 0.349, Regret: 0.5127, Entropy: 0.7100 +[2026-03-20T17:30:33.806488Z] Loop 484: Loss: 1.84e-02, Avg Return: 0.360, Regret: 0.5126, Entropy: 0.7101 +[2026-03-20T17:30:34.658574Z] Loop 485: Loss: 1.80e-02, Avg Return: 0.350, Regret: 0.5126, Entropy: 0.7097 +[2026-03-20T17:30:35.549166Z] Loop 486: Loss: 1.74e-02, Avg Return: 0.347, Regret: 0.5127, Entropy: 0.7093 +[2026-03-20T17:30:36.402407Z] Loop 487: Loss: 1.94e-02, Avg Return: 0.353, Regret: 0.5127, Entropy: 0.7089 +[2026-03-20T17:30:37.292207Z] Loop 488: Loss: 1.83e-02, Avg Return: 0.353, Regret: 0.5126, Entropy: 0.7082 +[2026-03-20T17:30:38.144661Z] Loop 489: Loss: 1.87e-02, Avg Return: 0.352, Regret: 0.5126, Entropy: 0.7076 +[2026-03-20T17:30:39.034889Z] Loop 490: Loss: 1.83e-02, Avg Return: 0.349, Regret: 0.5126, Entropy: 0.7071 +[2026-03-20T17:30:39.888985Z] Loop 491: Loss: 1.86e-02, Avg Return: 0.352, Regret: 0.5126, Entropy: 0.7067 +[2026-03-20T17:30:40.778974Z] Loop 492: Loss: 1.84e-02, Avg Return: 0.347, Regret: 0.5126, Entropy: 0.7065 +[2026-03-20T17:30:41.631964Z] Loop 493: Loss: 1.85e-02, Avg Return: 0.350, Regret: 0.5126, Entropy: 0.7063 +[2026-03-20T17:30:42.522917Z] Loop 494: Loss: 1.60e-02, Avg Return: 0.337, Regret: 0.5126, Entropy: 0.7060 +[2026-03-20T17:30:43.375945Z] Loop 495: Loss: 1.86e-02, Avg Return: 0.349, Regret: 0.5126, Entropy: 0.7056 +[2026-03-20T17:30:44.265356Z] Loop 496: Loss: 1.92e-02, Avg Return: 0.351, Regret: 0.5126, Entropy: 0.7053 +[2026-03-20T17:30:45.118545Z] Loop 497: Loss: 1.76e-02, Avg Return: 0.347, Regret: 0.5126, Entropy: 0.7051 +[2026-03-20T17:30:46.008478Z] Loop 498: Loss: 1.89e-02, Avg Return: 0.352, Regret: 0.5126, Entropy: 0.7048 +[2026-03-20T17:30:46.862279Z] Loop 499: Loss: 1.84e-02, Avg Return: 0.353, Regret: 0.5126, Entropy: 0.7046 +[2026-03-20T17:30:47.752033Z] Loop 500: Loss: 1.77e-02, Avg Return: 0.352, Regret: 0.5126, Entropy: 0.7047 +[2026-03-20T17:30:48.604604Z] Loop 501: Loss: 1.86e-02, Avg Return: 0.353, Regret: 0.5126, Entropy: 0.7047 +[2026-03-20T17:30:49.457723Z] Loop 502: Loss: 1.76e-02, Avg Return: 0.346, Regret: 0.5126, Entropy: 0.7046 +[2026-03-20T17:30:50.310744Z] Loop 503: Loss: 1.77e-02, Avg Return: 0.350, Regret: 0.5126, Entropy: 0.7043 +[2026-03-20T17:30:51.162917Z] Loop 504: Loss: 1.83e-02, Avg Return: 0.349, Regret: 0.5126, Entropy: 0.7040 +[2026-03-20T17:30:52.053395Z] Loop 505: Loss: 1.82e-02, Avg Return: 0.351, Regret: 0.5126, Entropy: 0.7037 +[2026-03-20T17:30:52.906011Z] Loop 506: Loss: 1.72e-02, Avg Return: 0.345, Regret: 0.5126, Entropy: 0.7035 +[2026-03-20T17:30:53.758652Z] Loop 507: Loss: 1.82e-02, Avg Return: 0.358, Regret: 0.5126, Entropy: 0.7034 +[2026-03-20T17:30:54.611735Z] Loop 508: Loss: 1.70e-02, Avg Return: 0.349, Regret: 0.5126, Entropy: 0.7035 +[2026-03-20T17:30:55.465977Z] Loop 509: Loss: 1.88e-02, Avg Return: 0.346, Regret: 0.5126, Entropy: 0.7035 +[2026-03-20T17:30:56.357188Z] Loop 510: Loss: 1.72e-02, Avg Return: 0.347, Regret: 0.5126, Entropy: 0.7038 +[2026-03-20T17:30:57.210088Z] Loop 511: Loss: 1.92e-02, Avg Return: 0.357, Regret: 0.5126, Entropy: 0.7041 +[2026-03-20T17:30:58.063253Z] Loop 512: Loss: 1.87e-02, Avg Return: 0.354, Regret: 0.5126, Entropy: 0.7042 +[2026-03-20T17:30:58.916100Z] Loop 513: Loss: 1.77e-02, Avg Return: 0.345, Regret: 0.5126, Entropy: 0.7042 +[2026-03-20T17:30:59.769180Z] Loop 514: Loss: 1.81e-02, Avg Return: 0.353, Regret: 0.5126, Entropy: 0.7042 +[2026-03-20T17:31:00.657244Z] Loop 515: Loss: 1.79e-02, Avg Return: 0.350, Regret: 0.5126, Entropy: 0.7043 +[2026-03-20T17:31:01.508629Z] Loop 516: Loss: 1.91e-02, Avg Return: 0.354, Regret: 0.5126, Entropy: 0.7043 +[2026-03-20T17:31:02.360010Z] Loop 517: Loss: 1.81e-02, Avg Return: 0.351, Regret: 0.5126, Entropy: 0.7044 +[2026-03-20T17:31:03.213239Z] Loop 518: Loss: 1.88e-02, Avg Return: 0.354, Regret: 0.5126, Entropy: 0.7043 +[2026-03-20T17:31:04.065530Z] Loop 519: Loss: 1.80e-02, Avg Return: 0.349, Regret: 0.5126, Entropy: 0.7042 +[2026-03-20T17:31:04.954566Z] Loop 520: Loss: 1.75e-02, Avg Return: 0.350, Regret: 0.5126, Entropy: 0.7043 +[2026-03-20T17:31:05.807885Z] Loop 521: Loss: 1.85e-02, Avg Return: 0.344, Regret: 0.5126, Entropy: 0.7042 +[2026-03-20T17:31:06.661477Z] Loop 522: Loss: 1.76e-02, Avg Return: 0.351, Regret: 0.5126, Entropy: 0.7041 +[2026-03-20T17:31:07.513905Z] Loop 523: Loss: 1.86e-02, Avg Return: 0.351, Regret: 0.5126, Entropy: 0.7040 +[2026-03-20T17:31:08.367040Z] Loop 524: Loss: 1.91e-02, Avg Return: 0.361, Regret: 0.5126, Entropy: 0.7040 +[2026-03-20T17:31:09.254843Z] Loop 525: Loss: 1.74e-02, Avg Return: 0.348, Regret: 0.5126, Entropy: 0.7038 +[2026-03-20T17:31:10.108571Z] Loop 526: Loss: 1.97e-02, Avg Return: 0.356, Regret: 0.5126, Entropy: 0.7038 +[2026-03-20T17:31:10.960797Z] Loop 527: Loss: 1.85e-02, Avg Return: 0.356, Regret: 0.5126, Entropy: 0.7036 +[2026-03-20T17:31:11.812899Z] Loop 528: Loss: 1.82e-02, Avg Return: 0.350, Regret: 0.5126, Entropy: 0.7035 +[2026-03-20T17:31:12.665614Z] Loop 529: Loss: 1.86e-02, Avg Return: 0.348, Regret: 0.5126, Entropy: 0.7032 +[2026-03-20T17:31:13.556162Z] Loop 530: Loss: 1.86e-02, Avg Return: 0.353, Regret: 0.5126, Entropy: 0.7034 +[2026-03-20T17:31:14.408446Z] Loop 531: Loss: 1.75e-02, Avg Return: 0.354, Regret: 0.5126, Entropy: 0.7035 +[2026-03-20T17:31:15.261487Z] Loop 532: Loss: 1.97e-02, Avg Return: 0.358, Regret: 0.5126, Entropy: 0.7037 +[2026-03-20T17:31:16.114123Z] Loop 533: Loss: 1.76e-02, Avg Return: 0.349, Regret: 0.5126, Entropy: 0.7035 +[2026-03-20T17:31:16.967214Z] Loop 534: Loss: 1.89e-02, Avg Return: 0.358, Regret: 0.5126, Entropy: 0.7031 +[2026-03-20T17:31:17.857781Z] Loop 535: Loss: 2.01e-02, Avg Return: 0.353, Regret: 0.5128, Entropy: 0.7027 +[2026-03-20T17:31:18.710811Z] Loop 536: Loss: 1.89e-02, Avg Return: 0.350, Regret: 0.5128, Entropy: 0.7021 +[2026-03-20T17:31:19.563080Z] Loop 537: Loss: 1.81e-02, Avg Return: 0.351, Regret: 0.5128, Entropy: 0.7018 +[2026-03-20T17:31:20.415544Z] Loop 538: Loss: 1.72e-02, Avg Return: 0.344, Regret: 0.5128, Entropy: 0.7018 +[2026-03-20T17:31:21.268728Z] Loop 539: Loss: 1.83e-02, Avg Return: 0.348, Regret: 0.5128, Entropy: 0.7019 +[2026-03-20T17:31:22.160326Z] Loop 540: Loss: 1.77e-02, Avg Return: 0.343, Regret: 0.5128, Entropy: 0.7023 +[2026-03-20T17:31:23.012766Z] Loop 541: Loss: 1.81e-02, Avg Return: 0.346, Regret: 0.5128, Entropy: 0.7027 +[2026-03-20T17:31:23.865660Z] Loop 542: Loss: 1.73e-02, Avg Return: 0.348, Regret: 0.5128, Entropy: 0.7028 +[2026-03-20T17:31:24.718138Z] Loop 543: Loss: 1.80e-02, Avg Return: 0.352, Regret: 0.5128, Entropy: 0.7029 +[2026-03-20T17:31:25.570892Z] Loop 544: Loss: 1.75e-02, Avg Return: 0.349, Regret: 0.5128, Entropy: 0.7029 +[2026-03-20T17:31:26.460740Z] Loop 545: Loss: 1.73e-02, Avg Return: 0.349, Regret: 0.5126, Entropy: 0.7028 +[2026-03-20T17:31:27.314038Z] Loop 546: Loss: 1.76e-02, Avg Return: 0.359, Regret: 0.5126, Entropy: 0.7029 +[2026-03-20T17:31:28.166433Z] Loop 547: Loss: 1.87e-02, Avg Return: 0.355, Regret: 0.5126, Entropy: 0.7029 +[2026-03-20T17:31:29.018310Z] Loop 548: Loss: 1.72e-02, Avg Return: 0.348, Regret: 0.5126, Entropy: 0.7028 +[2026-03-20T17:31:29.870144Z] Loop 549: Loss: 1.77e-02, Avg Return: 0.351, Regret: 0.5126, Entropy: 0.7029 +[2026-03-20T17:31:30.761774Z] Loop 550: Loss: 1.75e-02, Avg Return: 0.348, Regret: 0.5127, Entropy: 0.7029 +[2026-03-20T17:31:31.615620Z] Loop 551: Loss: 1.82e-02, Avg Return: 0.347, Regret: 0.5127, Entropy: 0.7032 +[2026-03-20T17:31:32.469192Z] Loop 552: Loss: 1.74e-02, Avg Return: 0.348, Regret: 0.5127, Entropy: 0.7034 +[2026-03-20T17:31:33.321890Z] Loop 553: Loss: 1.78e-02, Avg Return: 0.347, Regret: 0.5127, Entropy: 0.7032 +[2026-03-20T17:31:34.173704Z] Loop 554: Loss: 1.83e-02, Avg Return: 0.345, Regret: 0.5127, Entropy: 0.7030 +[2026-03-20T17:31:35.063923Z] Loop 555: Loss: 1.67e-02, Avg Return: 0.350, Regret: 0.5126, Entropy: 0.7031 +[2026-03-20T17:31:35.916390Z] Loop 556: Loss: 1.72e-02, Avg Return: 0.352, Regret: 0.5126, Entropy: 0.7032 +[2026-03-20T17:31:36.767594Z] Loop 557: Loss: 1.86e-02, Avg Return: 0.352, Regret: 0.5126, Entropy: 0.7033 +[2026-03-20T17:31:37.618875Z] Loop 558: Loss: 1.78e-02, Avg Return: 0.355, Regret: 0.5126, Entropy: 0.7033 +[2026-03-20T17:31:38.471745Z] Loop 559: Loss: 1.83e-02, Avg Return: 0.357, Regret: 0.5126, Entropy: 0.7033 +[2026-03-20T17:31:39.362165Z] Loop 560: Loss: 1.84e-02, Avg Return: 0.347, Regret: 0.5125, Entropy: 0.7034 +[2026-03-20T17:31:40.214810Z] Loop 561: Loss: 1.81e-02, Avg Return: 0.346, Regret: 0.5125, Entropy: 0.7035 +[2026-03-20T17:31:41.067383Z] Loop 562: Loss: 1.84e-02, Avg Return: 0.348, Regret: 0.5125, Entropy: 0.7036 +[2026-03-20T17:31:41.919252Z] Loop 563: Loss: 1.77e-02, Avg Return: 0.350, Regret: 0.5125, Entropy: 0.7036 +[2026-03-20T17:31:42.771492Z] Loop 564: Loss: 1.96e-02, Avg Return: 0.352, Regret: 0.5125, Entropy: 0.7037 +[2026-03-20T17:31:43.662019Z] Loop 565: Loss: 1.80e-02, Avg Return: 0.354, Regret: 0.5125, Entropy: 0.7038 +[2026-03-20T17:31:44.513444Z] Loop 566: Loss: 1.82e-02, Avg Return: 0.349, Regret: 0.5125, Entropy: 0.7038 +[2026-03-20T17:31:45.366098Z] Loop 567: Loss: 1.78e-02, Avg Return: 0.348, Regret: 0.5125, Entropy: 0.7039 +[2026-03-20T17:31:46.218596Z] Loop 568: Loss: 1.87e-02, Avg Return: 0.353, Regret: 0.5125, Entropy: 0.7043 +[2026-03-20T17:31:47.071519Z] Loop 569: Loss: 1.90e-02, Avg Return: 0.349, Regret: 0.5125, Entropy: 0.7046 +[2026-03-20T17:31:47.960108Z] Loop 570: Loss: 1.95e-02, Avg Return: 0.353, Regret: 0.5127, Entropy: 0.7047 +[2026-03-20T17:31:48.812188Z] Loop 571: Loss: 1.80e-02, Avg Return: 0.348, Regret: 0.5127, Entropy: 0.7049 +[2026-03-20T17:31:49.664082Z] Loop 572: Loss: 1.89e-02, Avg Return: 0.354, Regret: 0.5127, Entropy: 0.7052 +[2026-03-20T17:31:50.517057Z] Loop 573: Loss: 1.71e-02, Avg Return: 0.350, Regret: 0.5127, Entropy: 0.7054 +[2026-03-20T17:31:51.369358Z] Loop 574: Loss: 1.69e-02, Avg Return: 0.351, Regret: 0.5127, Entropy: 0.7054 +[2026-03-20T17:31:52.261386Z] Loop 575: Loss: 1.80e-02, Avg Return: 0.354, Regret: 0.5125, Entropy: 0.7052 +[2026-03-20T17:31:53.114326Z] Loop 576: Loss: 1.83e-02, Avg Return: 0.348, Regret: 0.5125, Entropy: 0.7047 +[2026-03-20T17:31:53.967488Z] Loop 577: Loss: 1.91e-02, Avg Return: 0.346, Regret: 0.5125, Entropy: 0.7040 +[2026-03-20T17:31:54.820148Z] Loop 578: Loss: 1.86e-02, Avg Return: 0.354, Regret: 0.5125, Entropy: 0.7036 +[2026-03-20T17:31:55.673269Z] Loop 579: Loss: 1.81e-02, Avg Return: 0.354, Regret: 0.5125, Entropy: 0.7030 +[2026-03-20T17:31:56.563215Z] Loop 580: Loss: 1.77e-02, Avg Return: 0.355, Regret: 0.5131, Entropy: 0.7025 +[2026-03-20T17:31:57.415852Z] Loop 581: Loss: 1.88e-02, Avg Return: 0.350, Regret: 0.5131, Entropy: 0.7026 +[2026-03-20T17:31:58.268253Z] Loop 582: Loss: 1.79e-02, Avg Return: 0.344, Regret: 0.5131, Entropy: 0.7030 +[2026-03-20T17:31:59.120691Z] Loop 583: Loss: 1.90e-02, Avg Return: 0.349, Regret: 0.5131, Entropy: 0.7038 +[2026-03-20T17:31:59.972803Z] Loop 584: Loss: 1.86e-02, Avg Return: 0.356, Regret: 0.5131, Entropy: 0.7046 +[2026-03-20T17:32:00.864321Z] Loop 585: Loss: 1.78e-02, Avg Return: 0.346, Regret: 0.5125, Entropy: 0.7052 +[2026-03-20T17:32:01.717364Z] Loop 586: Loss: 1.69e-02, Avg Return: 0.349, Regret: 0.5125, Entropy: 0.7053 +[2026-03-20T17:32:02.571062Z] Loop 587: Loss: 1.82e-02, Avg Return: 0.350, Regret: 0.5125, Entropy: 0.7054 +[2026-03-20T17:32:03.423953Z] Loop 588: Loss: 1.91e-02, Avg Return: 0.359, Regret: 0.5125, Entropy: 0.7056 +[2026-03-20T17:32:04.276037Z] Loop 589: Loss: 1.86e-02, Avg Return: 0.349, Regret: 0.5125, Entropy: 0.7059 +[2026-03-20T17:32:05.166508Z] Loop 590: Loss: 1.82e-02, Avg Return: 0.350, Regret: 0.5125, Entropy: 0.7059 +[2026-03-20T17:32:06.019574Z] Loop 591: Loss: 1.95e-02, Avg Return: 0.360, Regret: 0.5125, Entropy: 0.7060 +[2026-03-20T17:32:06.872794Z] Loop 592: Loss: 1.87e-02, Avg Return: 0.359, Regret: 0.5125, Entropy: 0.7063 +[2026-03-20T17:32:07.724733Z] Loop 593: Loss: 1.89e-02, Avg Return: 0.356, Regret: 0.5125, Entropy: 0.7065 +[2026-03-20T17:32:08.576923Z] Loop 594: Loss: 1.86e-02, Avg Return: 0.351, Regret: 0.5125, Entropy: 0.7069 +[2026-03-20T17:32:09.470139Z] Loop 595: Loss: 1.82e-02, Avg Return: 0.352, Regret: 0.5126, Entropy: 0.7072 +[2026-03-20T17:32:10.323323Z] Loop 596: Loss: 1.91e-02, Avg Return: 0.345, Regret: 0.5126, Entropy: 0.7075 +[2026-03-20T17:32:11.175544Z] Loop 597: Loss: 1.78e-02, Avg Return: 0.342, Regret: 0.5126, Entropy: 0.7079 +[2026-03-20T17:32:12.027692Z] Loop 598: Loss: 1.75e-02, Avg Return: 0.348, Regret: 0.5126, Entropy: 0.7082 +[2026-03-20T17:32:12.879932Z] Loop 599: Loss: 1.80e-02, Avg Return: 0.347, Regret: 0.5126, Entropy: 0.7083 +[2026-03-20T17:32:13.771162Z] Loop 600: Loss: 1.78e-02, Avg Return: 0.352, Regret: 0.5125, Entropy: 0.7082 +[2026-03-20T17:32:14.623391Z] Loop 601: Loss: 1.82e-02, Avg Return: 0.345, Regret: 0.5125, Entropy: 0.7079 +[2026-03-20T17:32:15.475929Z] Loop 602: Loss: 1.86e-02, Avg Return: 0.357, Regret: 0.5125, Entropy: 0.7072 +[2026-03-20T17:32:16.328017Z] Loop 603: Loss: 1.89e-02, Avg Return: 0.353, Regret: 0.5125, Entropy: 0.7067 +[2026-03-20T17:32:17.180301Z] Loop 604: Loss: 1.91e-02, Avg Return: 0.353, Regret: 0.5125, Entropy: 0.7064 +[2026-03-20T17:32:18.070999Z] Loop 605: Loss: 1.76e-02, Avg Return: 0.350, Regret: 0.5131, Entropy: 0.7062 +[2026-03-20T17:32:18.923414Z] Loop 606: Loss: 1.72e-02, Avg Return: 0.352, Regret: 0.5131, Entropy: 0.7062 +[2026-03-20T17:32:19.777073Z] Loop 607: Loss: 2.02e-02, Avg Return: 0.350, Regret: 0.5131, Entropy: 0.7064 +[2026-03-20T17:32:20.629603Z] Loop 608: Loss: 1.82e-02, Avg Return: 0.345, Regret: 0.5131, Entropy: 0.7064 +[2026-03-20T17:32:21.482541Z] Loop 609: Loss: 1.85e-02, Avg Return: 0.354, Regret: 0.5131, Entropy: 0.7072 +[2026-03-20T17:32:22.373645Z] Loop 610: Loss: 1.75e-02, Avg Return: 0.349, Regret: 0.5130, Entropy: 0.7079 +[2026-03-20T17:32:23.227719Z] Loop 611: Loss: 1.77e-02, Avg Return: 0.351, Regret: 0.5130, Entropy: 0.7087 +[2026-03-20T17:32:24.079678Z] Loop 612: Loss: 1.89e-02, Avg Return: 0.355, Regret: 0.5130, Entropy: 0.7097 +[2026-03-20T17:32:24.931411Z] Loop 613: Loss: 1.75e-02, Avg Return: 0.348, Regret: 0.5130, Entropy: 0.7103 +[2026-03-20T17:32:25.784097Z] Loop 614: Loss: 1.85e-02, Avg Return: 0.358, Regret: 0.5130, Entropy: 0.7107 +[2026-03-20T17:32:26.677154Z] Loop 615: Loss: 1.81e-02, Avg Return: 0.351, Regret: 0.5125, Entropy: 0.7111 +[2026-03-20T17:32:27.529644Z] Loop 616: Loss: 1.98e-02, Avg Return: 0.356, Regret: 0.5125, Entropy: 0.7112 +[2026-03-20T17:32:28.383217Z] Loop 617: Loss: 1.75e-02, Avg Return: 0.345, Regret: 0.5125, Entropy: 0.7110 +[2026-03-20T17:32:29.236880Z] Loop 618: Loss: 1.84e-02, Avg Return: 0.352, Regret: 0.5125, Entropy: 0.7103 +[2026-03-20T17:32:30.089834Z] Loop 619: Loss: 1.84e-02, Avg Return: 0.346, Regret: 0.5125, Entropy: 0.7096 +[2026-03-20T17:32:30.984357Z] Loop 620: Loss: 1.94e-02, Avg Return: 0.350, Regret: 0.5129, Entropy: 0.7091 +[2026-03-20T17:32:31.837555Z] Loop 621: Loss: 1.98e-02, Avg Return: 0.347, Regret: 0.5129, Entropy: 0.7091 +[2026-03-20T17:32:32.690402Z] Loop 622: Loss: 1.89e-02, Avg Return: 0.347, Regret: 0.5129, Entropy: 0.7096 +[2026-03-20T17:32:33.542421Z] Loop 623: Loss: 1.75e-02, Avg Return: 0.352, Regret: 0.5129, Entropy: 0.7103 +[2026-03-20T17:32:34.395747Z] Loop 624: Loss: 1.81e-02, Avg Return: 0.351, Regret: 0.5129, Entropy: 0.7107 +[2026-03-20T17:32:35.289271Z] Loop 625: Loss: 1.74e-02, Avg Return: 0.350, Regret: 0.5125, Entropy: 0.7112 +[2026-03-20T17:32:36.141263Z] Loop 626: Loss: 1.88e-02, Avg Return: 0.356, Regret: 0.5125, Entropy: 0.7111 +[2026-03-20T17:32:36.994087Z] Loop 627: Loss: 1.77e-02, Avg Return: 0.348, Regret: 0.5125, Entropy: 0.7110 +[2026-03-20T17:32:37.848019Z] Loop 628: Loss: 1.68e-02, Avg Return: 0.348, Regret: 0.5125, Entropy: 0.7104 +[2026-03-20T17:32:38.700563Z] Loop 629: Loss: 1.79e-02, Avg Return: 0.354, Regret: 0.5125, Entropy: 0.7099 +[2026-03-20T17:32:39.590822Z] Loop 630: Loss: 1.89e-02, Avg Return: 0.351, Regret: 0.5126, Entropy: 0.7093 +[2026-03-20T17:32:40.443086Z] Loop 631: Loss: 1.79e-02, Avg Return: 0.353, Regret: 0.5126, Entropy: 0.7086 +[2026-03-20T17:32:41.296238Z] Loop 632: Loss: 1.81e-02, Avg Return: 0.347, Regret: 0.5126, Entropy: 0.7082 +[2026-03-20T17:32:42.149180Z] Loop 633: Loss: 1.90e-02, Avg Return: 0.354, Regret: 0.5126, Entropy: 0.7079 +[2026-03-20T17:32:43.002495Z] Loop 634: Loss: 1.81e-02, Avg Return: 0.352, Regret: 0.5126, Entropy: 0.7072 +[2026-03-20T17:32:43.895032Z] Loop 635: Loss: 1.83e-02, Avg Return: 0.352, Regret: 0.5126, Entropy: 0.7067 +[2026-03-20T17:32:44.747790Z] Loop 636: Loss: 1.86e-02, Avg Return: 0.352, Regret: 0.5126, Entropy: 0.7061 +[2026-03-20T17:32:45.600865Z] Loop 637: Loss: 1.83e-02, Avg Return: 0.354, Regret: 0.5126, Entropy: 0.7060 +[2026-03-20T17:32:46.453813Z] Loop 638: Loss: 1.79e-02, Avg Return: 0.353, Regret: 0.5126, Entropy: 0.7062 +[2026-03-20T17:32:47.306257Z] Loop 639: Loss: 1.70e-02, Avg Return: 0.346, Regret: 0.5126, Entropy: 0.7064 +[2026-03-20T17:32:48.199785Z] Loop 640: Loss: 1.82e-02, Avg Return: 0.357, Regret: 0.5125, Entropy: 0.7066 +[2026-03-20T17:32:49.053046Z] Loop 641: Loss: 1.95e-02, Avg Return: 0.348, Regret: 0.5125, Entropy: 0.7069 +[2026-03-20T17:32:49.906170Z] Loop 642: Loss: 1.90e-02, Avg Return: 0.358, Regret: 0.5125, Entropy: 0.7071 +[2026-03-20T17:32:50.759375Z] Loop 643: Loss: 1.87e-02, Avg Return: 0.347, Regret: 0.5125, Entropy: 0.7073 +[2026-03-20T17:32:51.612343Z] Loop 644: Loss: 1.80e-02, Avg Return: 0.347, Regret: 0.5125, Entropy: 0.7076 +[2026-03-20T17:32:52.505382Z] Loop 645: Loss: 1.80e-02, Avg Return: 0.351, Regret: 0.5125, Entropy: 0.7079 +[2026-03-20T17:32:53.358911Z] Loop 646: Loss: 1.81e-02, Avg Return: 0.350, Regret: 0.5125, Entropy: 0.7079 +[2026-03-20T17:32:54.211254Z] Loop 647: Loss: 1.85e-02, Avg Return: 0.354, Regret: 0.5125, Entropy: 0.7083 +[2026-03-20T17:32:55.063608Z] Loop 648: Loss: 1.80e-02, Avg Return: 0.349, Regret: 0.5125, Entropy: 0.7086 +[2026-03-20T17:32:55.915615Z] Loop 649: Loss: 1.99e-02, Avg Return: 0.350, Regret: 0.5125, Entropy: 0.7088 +[2026-03-20T17:32:56.809503Z] Loop 650: Loss: 1.86e-02, Avg Return: 0.351, Regret: 0.5125, Entropy: 0.7087 +[2026-03-20T17:32:57.663189Z] Loop 651: Loss: 1.80e-02, Avg Return: 0.354, Regret: 0.5125, Entropy: 0.7087 +[2026-03-20T17:32:58.516507Z] Loop 652: Loss: 1.80e-02, Avg Return: 0.350, Regret: 0.5125, Entropy: 0.7086 +[2026-03-20T17:32:59.367908Z] Loop 653: Loss: 1.88e-02, Avg Return: 0.350, Regret: 0.5125, Entropy: 0.7084 +[2026-03-20T17:33:00.219599Z] Loop 654: Loss: 1.91e-02, Avg Return: 0.353, Regret: 0.5125, Entropy: 0.7079 +[2026-03-20T17:33:01.113682Z] Loop 655: Loss: 1.81e-02, Avg Return: 0.353, Regret: 0.5124, Entropy: 0.7073 +[2026-03-20T17:33:01.966551Z] Loop 656: Loss: 1.87e-02, Avg Return: 0.354, Regret: 0.5124, Entropy: 0.7069 +[2026-03-20T17:33:02.818415Z] Loop 657: Loss: 1.68e-02, Avg Return: 0.354, Regret: 0.5124, Entropy: 0.7067 +[2026-03-20T17:33:03.669771Z] Loop 658: Loss: 1.78e-02, Avg Return: 0.353, Regret: 0.5124, Entropy: 0.7068 +[2026-03-20T17:33:04.521203Z] Loop 659: Loss: 1.81e-02, Avg Return: 0.347, Regret: 0.5124, Entropy: 0.7068 +[2026-03-20T17:33:05.412806Z] Loop 660: Loss: 1.73e-02, Avg Return: 0.352, Regret: 0.5124, Entropy: 0.7067 +[2026-03-20T17:33:06.264545Z] Loop 661: Loss: 1.80e-02, Avg Return: 0.357, Regret: 0.5124, Entropy: 0.7065 +[2026-03-20T17:33:07.116520Z] Loop 662: Loss: 1.84e-02, Avg Return: 0.356, Regret: 0.5124, Entropy: 0.7062 +[2026-03-20T17:33:07.968325Z] Loop 663: Loss: 1.84e-02, Avg Return: 0.352, Regret: 0.5124, Entropy: 0.7058 +[2026-03-20T17:33:08.821206Z] Loop 664: Loss: 1.70e-02, Avg Return: 0.349, Regret: 0.5124, Entropy: 0.7056 +[2026-03-20T17:33:09.713418Z] Loop 665: Loss: 1.85e-02, Avg Return: 0.350, Regret: 0.5124, Entropy: 0.7057 +[2026-03-20T17:33:10.566244Z] Loop 666: Loss: 1.85e-02, Avg Return: 0.352, Regret: 0.5124, Entropy: 0.7056 +[2026-03-20T17:33:11.419854Z] Loop 667: Loss: 1.80e-02, Avg Return: 0.346, Regret: 0.5124, Entropy: 0.7053 +[2026-03-20T17:33:12.274072Z] Loop 668: Loss: 1.77e-02, Avg Return: 0.350, Regret: 0.5124, Entropy: 0.7048 +[2026-03-20T17:33:13.128061Z] Loop 669: Loss: 1.86e-02, Avg Return: 0.350, Regret: 0.5124, Entropy: 0.7042 +[2026-03-20T17:33:14.018357Z] Loop 670: Loss: 1.67e-02, Avg Return: 0.354, Regret: 0.5129, Entropy: 0.7033 +[2026-03-20T17:33:14.871322Z] Loop 671: Loss: 1.79e-02, Avg Return: 0.351, Regret: 0.5129, Entropy: 0.7019 +[2026-03-20T17:33:15.723936Z] Loop 672: Loss: 1.87e-02, Avg Return: 0.359, Regret: 0.5129, Entropy: 0.7010 +[2026-03-20T17:33:16.577155Z] Loop 673: Loss: 1.91e-02, Avg Return: 0.350, Regret: 0.5129, Entropy: 0.7016 +[2026-03-20T17:33:17.429798Z] Loop 674: Loss: 1.68e-02, Avg Return: 0.351, Regret: 0.5129, Entropy: 0.7020 +[2026-03-20T17:33:18.319639Z] Loop 675: Loss: 1.78e-02, Avg Return: 0.350, Regret: 0.5129, Entropy: 0.7032 +[2026-03-20T17:33:19.171537Z] Loop 676: Loss: 1.77e-02, Avg Return: 0.353, Regret: 0.5129, Entropy: 0.7046 +[2026-03-20T17:33:20.023330Z] Loop 677: Loss: 1.83e-02, Avg Return: 0.354, Regret: 0.5129, Entropy: 0.7056 +[2026-03-20T17:33:20.875760Z] Loop 678: Loss: 1.89e-02, Avg Return: 0.348, Regret: 0.5129, Entropy: 0.7051 +[2026-03-20T17:33:21.728201Z] Loop 679: Loss: 1.83e-02, Avg Return: 0.349, Regret: 0.5129, Entropy: 0.7039 +[2026-03-20T17:33:22.618839Z] Loop 680: Loss: 1.79e-02, Avg Return: 0.348, Regret: 0.5129, Entropy: 0.7027 +[2026-03-20T17:33:23.471941Z] Loop 681: Loss: 1.89e-02, Avg Return: 0.351, Regret: 0.5129, Entropy: 0.7016 +[2026-03-20T17:33:24.323904Z] Loop 682: Loss: 1.82e-02, Avg Return: 0.348, Regret: 0.5129, Entropy: 0.7005 +[2026-03-20T17:33:25.176261Z] Loop 683: Loss: 2.00e-02, Avg Return: 0.355, Regret: 0.5129, Entropy: 0.7002 +[2026-03-20T17:33:26.029294Z] Loop 684: Loss: 1.84e-02, Avg Return: 0.351, Regret: 0.5129, Entropy: 0.7005 +[2026-03-20T17:33:26.919305Z] Loop 685: Loss: 1.70e-02, Avg Return: 0.349, Regret: 0.5131, Entropy: 0.7004 +[2026-03-20T17:33:27.771532Z] Loop 686: Loss: 1.89e-02, Avg Return: 0.350, Regret: 0.5131, Entropy: 0.7002 +[2026-03-20T17:33:28.623735Z] Loop 687: Loss: 1.90e-02, Avg Return: 0.354, Regret: 0.5131, Entropy: 0.7000 +[2026-03-20T17:33:29.476365Z] Loop 688: Loss: 1.80e-02, Avg Return: 0.348, Regret: 0.5131, Entropy: 0.7004 +[2026-03-20T17:33:30.329939Z] Loop 689: Loss: 1.78e-02, Avg Return: 0.351, Regret: 0.5131, Entropy: 0.7006 +[2026-03-20T17:33:31.220945Z] Loop 690: Loss: 1.96e-02, Avg Return: 0.354, Regret: 0.5126, Entropy: 0.7011 +[2026-03-20T17:33:32.074075Z] Loop 691: Loss: 1.91e-02, Avg Return: 0.355, Regret: 0.5126, Entropy: 0.7016 +[2026-03-20T17:33:32.927025Z] Loop 692: Loss: 1.95e-02, Avg Return: 0.358, Regret: 0.5126, Entropy: 0.7016 +[2026-03-20T17:33:33.779876Z] Loop 693: Loss: 1.73e-02, Avg Return: 0.346, Regret: 0.5126, Entropy: 0.7017 +[2026-03-20T17:33:34.632438Z] Loop 694: Loss: 1.75e-02, Avg Return: 0.353, Regret: 0.5126, Entropy: 0.7021 +[2026-03-20T17:33:35.524350Z] Loop 695: Loss: 1.83e-02, Avg Return: 0.359, Regret: 0.5123, Entropy: 0.7024 +[2026-03-20T17:33:36.377218Z] Loop 696: Loss: 1.77e-02, Avg Return: 0.351, Regret: 0.5123, Entropy: 0.7023 +[2026-03-20T17:33:37.230185Z] Loop 697: Loss: 1.83e-02, Avg Return: 0.354, Regret: 0.5123, Entropy: 0.7018 +[2026-03-20T17:33:38.083803Z] Loop 698: Loss: 1.83e-02, Avg Return: 0.349, Regret: 0.5123, Entropy: 0.7012 +[2026-03-20T17:33:38.936161Z] Loop 699: Loss: 1.69e-02, Avg Return: 0.351, Regret: 0.5123, Entropy: 0.7007 +[2026-03-20T17:33:39.828381Z] Loop 700: Loss: 1.75e-02, Avg Return: 0.350, Regret: 0.5127, Entropy: 0.7004 +[2026-03-20T17:33:40.681810Z] Loop 701: Loss: 1.68e-02, Avg Return: 0.346, Regret: 0.5127, Entropy: 0.7010 +[2026-03-20T17:33:41.536441Z] Loop 702: Loss: 1.92e-02, Avg Return: 0.347, Regret: 0.5127, Entropy: 0.7014 +[2026-03-20T17:33:42.391313Z] Loop 703: Loss: 1.76e-02, Avg Return: 0.353, Regret: 0.5127, Entropy: 0.7018 +[2026-03-20T17:33:43.244295Z] Loop 704: Loss: 1.77e-02, Avg Return: 0.352, Regret: 0.5127, Entropy: 0.7026 +[2026-03-20T17:33:44.135621Z] Loop 705: Loss: 1.87e-02, Avg Return: 0.353, Regret: 0.5123, Entropy: 0.7030 +[2026-03-20T17:33:44.988657Z] Loop 706: Loss: 1.65e-02, Avg Return: 0.348, Regret: 0.5123, Entropy: 0.7036 +[2026-03-20T17:33:45.842089Z] Loop 707: Loss: 1.81e-02, Avg Return: 0.357, Regret: 0.5123, Entropy: 0.7042 +[2026-03-20T17:33:46.694735Z] Loop 708: Loss: 1.88e-02, Avg Return: 0.346, Regret: 0.5123, Entropy: 0.7049 +[2026-03-20T17:33:47.546876Z] Loop 709: Loss: 1.82e-02, Avg Return: 0.345, Regret: 0.5123, Entropy: 0.7056 +[2026-03-20T17:33:48.441690Z] Loop 710: Loss: 1.81e-02, Avg Return: 0.361, Regret: 0.5123, Entropy: 0.7065 +[2026-03-20T17:33:49.295487Z] Loop 711: Loss: 1.77e-02, Avg Return: 0.353, Regret: 0.5123, Entropy: 0.7072 +[2026-03-20T17:33:50.148885Z] Loop 712: Loss: 1.74e-02, Avg Return: 0.357, Regret: 0.5123, Entropy: 0.7075 +[2026-03-20T17:33:51.001888Z] Loop 713: Loss: 1.82e-02, Avg Return: 0.351, Regret: 0.5123, Entropy: 0.7078 +[2026-03-20T17:33:51.855636Z] Loop 714: Loss: 1.80e-02, Avg Return: 0.353, Regret: 0.5123, Entropy: 0.7080 +[2026-03-20T17:33:52.749924Z] Loop 715: Loss: 1.73e-02, Avg Return: 0.354, Regret: 0.5123, Entropy: 0.7085 +[2026-03-20T17:33:53.603362Z] Loop 716: Loss: 1.76e-02, Avg Return: 0.352, Regret: 0.5123, Entropy: 0.7088 +[2026-03-20T17:33:54.455965Z] Loop 717: Loss: 1.73e-02, Avg Return: 0.347, Regret: 0.5123, Entropy: 0.7093 +[2026-03-20T17:33:55.309899Z] Loop 718: Loss: 1.84e-02, Avg Return: 0.359, Regret: 0.5123, Entropy: 0.7091 +[2026-03-20T17:33:56.163150Z] Loop 719: Loss: 1.87e-02, Avg Return: 0.353, Regret: 0.5123, Entropy: 0.7088 +[2026-03-20T17:33:57.056322Z] Loop 720: Loss: 1.98e-02, Avg Return: 0.350, Regret: 0.5125, Entropy: 0.7082 +[2026-03-20T17:33:57.909624Z] Loop 721: Loss: 1.85e-02, Avg Return: 0.356, Regret: 0.5125, Entropy: 0.7076 +[2026-03-20T17:33:58.763114Z] Loop 722: Loss: 1.94e-02, Avg Return: 0.359, Regret: 0.5125, Entropy: 0.7071 +[2026-03-20T17:33:59.616581Z] Loop 723: Loss: 1.90e-02, Avg Return: 0.352, Regret: 0.5125, Entropy: 0.7073 +[2026-03-20T17:34:00.469687Z] Loop 724: Loss: 1.85e-02, Avg Return: 0.350, Regret: 0.5125, Entropy: 0.7073 +[2026-03-20T17:34:01.361014Z] Loop 725: Loss: 1.77e-02, Avg Return: 0.349, Regret: 0.5127, Entropy: 0.7075 +[2026-03-20T17:34:02.214124Z] Loop 726: Loss: 1.66e-02, Avg Return: 0.342, Regret: 0.5127, Entropy: 0.7076 +[2026-03-20T17:34:03.066289Z] Loop 727: Loss: 1.80e-02, Avg Return: 0.345, Regret: 0.5127, Entropy: 0.7079 +[2026-03-20T17:34:03.919583Z] Loop 728: Loss: 1.91e-02, Avg Return: 0.350, Regret: 0.5127, Entropy: 0.7083 +[2026-03-20T17:34:04.772064Z] Loop 729: Loss: 1.76e-02, Avg Return: 0.346, Regret: 0.5127, Entropy: 0.7089 +[2026-03-20T17:34:05.664384Z] Loop 730: Loss: 1.84e-02, Avg Return: 0.345, Regret: 0.5123, Entropy: 0.7099 +[2026-03-20T17:34:06.517477Z] Loop 731: Loss: 1.99e-02, Avg Return: 0.352, Regret: 0.5123, Entropy: 0.7104 +[2026-03-20T17:34:07.369400Z] Loop 732: Loss: 1.83e-02, Avg Return: 0.350, Regret: 0.5123, Entropy: 0.7105 +[2026-03-20T17:34:08.221505Z] Loop 733: Loss: 1.76e-02, Avg Return: 0.358, Regret: 0.5123, Entropy: 0.7105 +[2026-03-20T17:34:09.074915Z] Loop 734: Loss: 1.89e-02, Avg Return: 0.350, Regret: 0.5123, Entropy: 0.7103 +[2026-03-20T17:34:09.968208Z] Loop 735: Loss: 1.84e-02, Avg Return: 0.351, Regret: 0.5122, Entropy: 0.7099 +[2026-03-20T17:34:10.820221Z] Loop 736: Loss: 1.92e-02, Avg Return: 0.356, Regret: 0.5122, Entropy: 0.7096 +[2026-03-20T17:34:11.673461Z] Loop 737: Loss: 1.75e-02, Avg Return: 0.345, Regret: 0.5122, Entropy: 0.7092 +[2026-03-20T17:34:12.526877Z] Loop 738: Loss: 1.87e-02, Avg Return: 0.361, Regret: 0.5122, Entropy: 0.7090 +[2026-03-20T17:34:13.380019Z] Loop 739: Loss: 1.93e-02, Avg Return: 0.348, Regret: 0.5122, Entropy: 0.7086 +[2026-03-20T17:34:14.272562Z] Loop 740: Loss: 1.69e-02, Avg Return: 0.344, Regret: 0.5122, Entropy: 0.7082 +[2026-03-20T17:34:15.125417Z] Loop 741: Loss: 1.69e-02, Avg Return: 0.349, Regret: 0.5122, Entropy: 0.7074 +[2026-03-20T17:34:15.979059Z] Loop 742: Loss: 1.84e-02, Avg Return: 0.356, Regret: 0.5122, Entropy: 0.7068 +[2026-03-20T17:34:16.832747Z] Loop 743: Loss: 1.95e-02, Avg Return: 0.349, Regret: 0.5122, Entropy: 0.7068 +[2026-03-20T17:34:17.685616Z] Loop 744: Loss: 1.79e-02, Avg Return: 0.355, Regret: 0.5122, Entropy: 0.7068 +[2026-03-20T17:34:18.575782Z] Loop 745: Loss: 1.74e-02, Avg Return: 0.349, Regret: 0.5123, Entropy: 0.7069 +[2026-03-20T17:34:19.429148Z] Loop 746: Loss: 1.94e-02, Avg Return: 0.357, Regret: 0.5123, Entropy: 0.7064 +[2026-03-20T17:34:20.282860Z] Loop 747: Loss: 1.82e-02, Avg Return: 0.347, Regret: 0.5123, Entropy: 0.7060 +[2026-03-20T17:34:21.136870Z] Loop 748: Loss: 1.78e-02, Avg Return: 0.345, Regret: 0.5123, Entropy: 0.7052 +[2026-03-20T17:34:21.989773Z] Loop 749: Loss: 1.82e-02, Avg Return: 0.338, Regret: 0.5123, Entropy: 0.7048 +[2026-03-20T17:34:22.882662Z] Loop 750: Loss: 1.90e-02, Avg Return: 0.358, Regret: 0.5130, Entropy: 0.7048 +[2026-03-20T17:34:23.735564Z] Loop 751: Loss: 1.78e-02, Avg Return: 0.347, Regret: 0.5130, Entropy: 0.7049 +[2026-03-20T17:34:24.588757Z] Loop 752: Loss: 1.83e-02, Avg Return: 0.346, Regret: 0.5130, Entropy: 0.7056 +[2026-03-20T17:34:25.441029Z] Loop 753: Loss: 1.76e-02, Avg Return: 0.349, Regret: 0.5130, Entropy: 0.7061 +[2026-03-20T17:34:26.294043Z] Loop 754: Loss: 1.76e-02, Avg Return: 0.350, Regret: 0.5130, Entropy: 0.7070 +[2026-03-20T17:34:27.185101Z] Loop 755: Loss: 1.99e-02, Avg Return: 0.352, Regret: 0.5125, Entropy: 0.7080 +[2026-03-20T17:34:28.038042Z] Loop 756: Loss: 1.76e-02, Avg Return: 0.354, Regret: 0.5125, Entropy: 0.7089 +[2026-03-20T17:34:28.891267Z] Loop 757: Loss: 1.64e-02, Avg Return: 0.345, Regret: 0.5125, Entropy: 0.7104 +[2026-03-20T17:34:29.744602Z] Loop 758: Loss: 1.84e-02, Avg Return: 0.349, Regret: 0.5125, Entropy: 0.7113 +[2026-03-20T17:34:30.597046Z] Loop 759: Loss: 1.79e-02, Avg Return: 0.354, Regret: 0.5125, Entropy: 0.7118 +[2026-03-20T17:34:31.488237Z] Loop 760: Loss: 1.84e-02, Avg Return: 0.351, Regret: 0.5122, Entropy: 0.7119 +[2026-03-20T17:34:32.341213Z] Loop 761: Loss: 1.83e-02, Avg Return: 0.353, Regret: 0.5122, Entropy: 0.7118 +[2026-03-20T17:34:33.195399Z] Loop 762: Loss: 1.84e-02, Avg Return: 0.343, Regret: 0.5122, Entropy: 0.7115 +[2026-03-20T17:34:34.046845Z] Loop 763: Loss: 1.94e-02, Avg Return: 0.358, Regret: 0.5122, Entropy: 0.7111 +[2026-03-20T17:34:34.898253Z] Loop 764: Loss: 1.92e-02, Avg Return: 0.350, Regret: 0.5122, Entropy: 0.7112 +[2026-03-20T17:34:35.789571Z] Loop 765: Loss: 1.88e-02, Avg Return: 0.349, Regret: 0.5129, Entropy: 0.7120 +[2026-03-20T17:34:36.643453Z] Loop 766: Loss: 1.82e-02, Avg Return: 0.352, Regret: 0.5129, Entropy: 0.7123 +[2026-03-20T17:34:37.496349Z] Loop 767: Loss: 1.64e-02, Avg Return: 0.356, Regret: 0.5129, Entropy: 0.7131 +[2026-03-20T17:34:38.347966Z] Loop 768: Loss: 1.89e-02, Avg Return: 0.355, Regret: 0.5129, Entropy: 0.7138 +[2026-03-20T17:34:39.200447Z] Loop 769: Loss: 1.73e-02, Avg Return: 0.353, Regret: 0.5129, Entropy: 0.7142 +[2026-03-20T17:34:40.092608Z] Loop 770: Loss: 1.83e-02, Avg Return: 0.352, Regret: 0.5121, Entropy: 0.7143 +[2026-03-20T17:34:40.945175Z] Loop 771: Loss: 1.88e-02, Avg Return: 0.355, Regret: 0.5121, Entropy: 0.7144 +[2026-03-20T17:34:41.797895Z] Loop 772: Loss: 1.82e-02, Avg Return: 0.352, Regret: 0.5121, Entropy: 0.7143 +[2026-03-20T17:34:42.650824Z] Loop 773: Loss: 1.96e-02, Avg Return: 0.344, Regret: 0.5121, Entropy: 0.7139 +[2026-03-20T17:34:43.504066Z] Loop 774: Loss: 1.70e-02, Avg Return: 0.345, Regret: 0.5121, Entropy: 0.7131 +[2026-03-20T17:34:44.397481Z] Loop 775: Loss: 1.83e-02, Avg Return: 0.355, Regret: 0.5127, Entropy: 0.7124 +[2026-03-20T17:34:45.250207Z] Loop 776: Loss: 1.81e-02, Avg Return: 0.350, Regret: 0.5127, Entropy: 0.7125 +[2026-03-20T17:34:46.103047Z] Loop 777: Loss: 1.89e-02, Avg Return: 0.350, Regret: 0.5127, Entropy: 0.7132 +[2026-03-20T17:34:46.956219Z] Loop 778: Loss: 1.80e-02, Avg Return: 0.351, Regret: 0.5127, Entropy: 0.7136 +[2026-03-20T17:34:47.809311Z] Loop 779: Loss: 1.89e-02, Avg Return: 0.351, Regret: 0.5127, Entropy: 0.7144 +[2026-03-20T17:34:48.701402Z] Loop 780: Loss: 1.82e-02, Avg Return: 0.347, Regret: 0.5121, Entropy: 0.7146 +[2026-03-20T17:34:49.553878Z] Loop 781: Loss: 1.80e-02, Avg Return: 0.357, Regret: 0.5121, Entropy: 0.7151 +[2026-03-20T17:34:50.407402Z] Loop 782: Loss: 1.83e-02, Avg Return: 0.350, Regret: 0.5121, Entropy: 0.7151 +[2026-03-20T17:34:51.259644Z] Loop 783: Loss: 1.84e-02, Avg Return: 0.354, Regret: 0.5121, Entropy: 0.7141 +[2026-03-20T17:34:52.112143Z] Loop 784: Loss: 1.95e-02, Avg Return: 0.355, Regret: 0.5121, Entropy: 0.7127 +[2026-03-20T17:34:53.000917Z] Loop 785: Loss: 1.85e-02, Avg Return: 0.352, Regret: 0.5126, Entropy: 0.7117 +[2026-03-20T17:34:53.852840Z] Loop 786: Loss: 1.89e-02, Avg Return: 0.349, Regret: 0.5126, Entropy: 0.7112 +[2026-03-20T17:34:54.705096Z] Loop 787: Loss: 1.80e-02, Avg Return: 0.356, Regret: 0.5126, Entropy: 0.7111 +[2026-03-20T17:34:55.557508Z] Loop 788: Loss: 1.82e-02, Avg Return: 0.353, Regret: 0.5126, Entropy: 0.7108 +[2026-03-20T17:34:56.409879Z] Loop 789: Loss: 1.75e-02, Avg Return: 0.352, Regret: 0.5126, Entropy: 0.7106 +[2026-03-20T17:34:57.303418Z] Loop 790: Loss: 1.77e-02, Avg Return: 0.351, Regret: 0.5124, Entropy: 0.7112 +[2026-03-20T17:34:58.155824Z] Loop 791: Loss: 1.80e-02, Avg Return: 0.351, Regret: 0.5124, Entropy: 0.7119 +[2026-03-20T17:34:59.008221Z] Loop 792: Loss: 1.87e-02, Avg Return: 0.356, Regret: 0.5124, Entropy: 0.7123 +[2026-03-20T17:34:59.860842Z] Loop 793: Loss: 1.89e-02, Avg Return: 0.351, Regret: 0.5124, Entropy: 0.7127 +[2026-03-20T17:35:00.714657Z] Loop 794: Loss: 1.86e-02, Avg Return: 0.355, Regret: 0.5124, Entropy: 0.7128 +[2026-03-20T17:35:01.608495Z] Loop 795: Loss: 1.79e-02, Avg Return: 0.350, Regret: 0.5120, Entropy: 0.7125 +[2026-03-20T17:35:02.461748Z] Loop 796: Loss: 1.98e-02, Avg Return: 0.365, Regret: 0.5120, Entropy: 0.7115 +[2026-03-20T17:35:03.314049Z] Loop 797: Loss: 1.82e-02, Avg Return: 0.350, Regret: 0.5120, Entropy: 0.7103 +[2026-03-20T17:35:04.167480Z] Loop 798: Loss: 1.77e-02, Avg Return: 0.350, Regret: 0.5120, Entropy: 0.7088 +[2026-03-20T17:35:05.019739Z] Loop 799: Loss: 1.93e-02, Avg Return: 0.359, Regret: 0.5120, Entropy: 0.7077 +[2026-03-20T17:35:05.909888Z] Loop 800: Loss: 1.71e-02, Avg Return: 0.346, Regret: 0.5127, Entropy: 0.7072 +[2026-03-20T17:35:06.762704Z] Loop 801: Loss: 1.80e-02, Avg Return: 0.351, Regret: 0.5127, Entropy: 0.7067 +[2026-03-20T17:35:07.616360Z] Loop 802: Loss: 1.89e-02, Avg Return: 0.350, Regret: 0.5127, Entropy: 0.7061 +[2026-03-20T17:35:08.469845Z] Loop 803: Loss: 1.97e-02, Avg Return: 0.352, Regret: 0.5127, Entropy: 0.7052 +[2026-03-20T17:35:09.321919Z] Loop 804: Loss: 1.89e-02, Avg Return: 0.347, Regret: 0.5127, Entropy: 0.7053 +[2026-03-20T17:35:10.213258Z] Loop 805: Loss: 1.91e-02, Avg Return: 0.350, Regret: 0.5125, Entropy: 0.7062 +[2026-03-20T17:35:11.067079Z] Loop 806: Loss: 1.83e-02, Avg Return: 0.352, Regret: 0.5125, Entropy: 0.7083 +[2026-03-20T17:35:11.919501Z] Loop 807: Loss: 1.73e-02, Avg Return: 0.353, Regret: 0.5125, Entropy: 0.7096 +[2026-03-20T17:35:12.771907Z] Loop 808: Loss: 1.77e-02, Avg Return: 0.348, Regret: 0.5125, Entropy: 0.7097 +[2026-03-20T17:35:13.623684Z] Loop 809: Loss: 1.80e-02, Avg Return: 0.347, Regret: 0.5125, Entropy: 0.7092 +[2026-03-20T17:35:14.513266Z] Loop 810: Loss: 1.71e-02, Avg Return: 0.347, Regret: 0.5124, Entropy: 0.7079 +[2026-03-20T17:35:15.367184Z] Loop 811: Loss: 1.74e-02, Avg Return: 0.342, Regret: 0.5124, Entropy: 0.7070 +[2026-03-20T17:35:16.219398Z] Loop 812: Loss: 1.98e-02, Avg Return: 0.351, Regret: 0.5124, Entropy: 0.7062 +[2026-03-20T17:35:17.072131Z] Loop 813: Loss: 1.72e-02, Avg Return: 0.345, Regret: 0.5124, Entropy: 0.7058 +[2026-03-20T17:35:17.925295Z] Loop 814: Loss: 1.81e-02, Avg Return: 0.352, Regret: 0.5124, Entropy: 0.7060 +[2026-03-20T17:35:18.818201Z] Loop 815: Loss: 1.72e-02, Avg Return: 0.356, Regret: 0.5129, Entropy: 0.7068 +[2026-03-20T17:35:19.671650Z] Loop 816: Loss: 1.98e-02, Avg Return: 0.359, Regret: 0.5129, Entropy: 0.7085 +[2026-03-20T17:35:20.525359Z] Loop 817: Loss: 1.85e-02, Avg Return: 0.350, Regret: 0.5129, Entropy: 0.7114 +[2026-03-20T17:35:21.378004Z] Loop 818: Loss: 1.83e-02, Avg Return: 0.350, Regret: 0.5129, Entropy: 0.7133 +[2026-03-20T17:35:22.230277Z] Loop 819: Loss: 1.89e-02, Avg Return: 0.357, Regret: 0.5129, Entropy: 0.7138 +[2026-03-20T17:35:23.121985Z] Loop 820: Loss: 1.89e-02, Avg Return: 0.352, Regret: 0.5121, Entropy: 0.7129 +[2026-03-20T17:35:23.975907Z] Loop 821: Loss: 1.85e-02, Avg Return: 0.352, Regret: 0.5121, Entropy: 0.7120 +[2026-03-20T17:35:24.828905Z] Loop 822: Loss: 1.84e-02, Avg Return: 0.351, Regret: 0.5121, Entropy: 0.7115 +[2026-03-20T17:35:25.682439Z] Loop 823: Loss: 1.93e-02, Avg Return: 0.352, Regret: 0.5121, Entropy: 0.7111 +[2026-03-20T17:35:26.535218Z] Loop 824: Loss: 1.71e-02, Avg Return: 0.348, Regret: 0.5121, Entropy: 0.7108 +[2026-03-20T17:35:27.429259Z] Loop 825: Loss: 1.91e-02, Avg Return: 0.343, Regret: 0.5129, Entropy: 0.7111 +[2026-03-20T17:35:28.282497Z] Loop 826: Loss: 1.87e-02, Avg Return: 0.354, Regret: 0.5129, Entropy: 0.7120 +[2026-03-20T17:35:29.136216Z] Loop 827: Loss: 1.96e-02, Avg Return: 0.352, Regret: 0.5129, Entropy: 0.7126 +[2026-03-20T17:35:29.990039Z] Loop 828: Loss: 2.02e-02, Avg Return: 0.357, Regret: 0.5129, Entropy: 0.7131 +[2026-03-20T17:35:30.843011Z] Loop 829: Loss: 1.86e-02, Avg Return: 0.349, Regret: 0.5129, Entropy: 0.7133 +[2026-03-20T17:35:31.737025Z] Loop 830: Loss: 1.77e-02, Avg Return: 0.352, Regret: 0.5121, Entropy: 0.7131 +[2026-03-20T17:35:32.590757Z] Loop 831: Loss: 1.71e-02, Avg Return: 0.348, Regret: 0.5121, Entropy: 0.7132 +[2026-03-20T17:35:33.442964Z] Loop 832: Loss: 1.84e-02, Avg Return: 0.355, Regret: 0.5121, Entropy: 0.7134 +[2026-03-20T17:35:34.295003Z] Loop 833: Loss: 1.85e-02, Avg Return: 0.352, Regret: 0.5121, Entropy: 0.7134 +[2026-03-20T17:35:35.148510Z] Loop 834: Loss: 1.92e-02, Avg Return: 0.351, Regret: 0.5121, Entropy: 0.7133 +[2026-03-20T17:35:36.040781Z] Loop 835: Loss: 1.92e-02, Avg Return: 0.355, Regret: 0.5117, Entropy: 0.7135 +[2026-03-20T17:35:36.894881Z] Loop 836: Loss: 1.73e-02, Avg Return: 0.350, Regret: 0.5117, Entropy: 0.7135 +[2026-03-20T17:35:37.748300Z] Loop 837: Loss: 1.90e-02, Avg Return: 0.356, Regret: 0.5117, Entropy: 0.7130 +[2026-03-20T17:35:38.601636Z] Loop 838: Loss: 1.81e-02, Avg Return: 0.354, Regret: 0.5117, Entropy: 0.7128 +[2026-03-20T17:35:39.454253Z] Loop 839: Loss: 1.97e-02, Avg Return: 0.353, Regret: 0.5117, Entropy: 0.7130 +[2026-03-20T17:35:40.344326Z] Loop 840: Loss: 1.80e-02, Avg Return: 0.350, Regret: 0.5117, Entropy: 0.7129 +[2026-03-20T17:35:41.197373Z] Loop 841: Loss: 1.70e-02, Avg Return: 0.351, Regret: 0.5117, Entropy: 0.7126 +[2026-03-20T17:35:42.050541Z] Loop 842: Loss: 1.93e-02, Avg Return: 0.351, Regret: 0.5117, Entropy: 0.7125 +[2026-03-20T17:35:42.904316Z] Loop 843: Loss: 1.83e-02, Avg Return: 0.351, Regret: 0.5117, Entropy: 0.7128 +[2026-03-20T17:35:43.756896Z] Loop 844: Loss: 1.76e-02, Avg Return: 0.351, Regret: 0.5117, Entropy: 0.7129 +[2026-03-20T17:35:44.648537Z] Loop 845: Loss: 1.76e-02, Avg Return: 0.356, Regret: 0.5116, Entropy: 0.7132 +[2026-03-20T17:35:45.500835Z] Loop 846: Loss: 1.77e-02, Avg Return: 0.346, Regret: 0.5116, Entropy: 0.7134 +[2026-03-20T17:35:46.353876Z] Loop 847: Loss: 1.90e-02, Avg Return: 0.346, Regret: 0.5116, Entropy: 0.7131 +[2026-03-20T17:35:47.206984Z] Loop 848: Loss: 1.70e-02, Avg Return: 0.352, Regret: 0.5116, Entropy: 0.7126 +[2026-03-20T17:35:48.060615Z] Loop 849: Loss: 1.82e-02, Avg Return: 0.350, Regret: 0.5116, Entropy: 0.7126 +[2026-03-20T17:35:48.953420Z] Loop 850: Loss: 1.83e-02, Avg Return: 0.355, Regret: 0.5117, Entropy: 0.7127 +[2026-03-20T17:35:49.806127Z] Loop 851: Loss: 1.72e-02, Avg Return: 0.356, Regret: 0.5117, Entropy: 0.7126 +[2026-03-20T17:35:50.660185Z] Loop 852: Loss: 1.84e-02, Avg Return: 0.352, Regret: 0.5117, Entropy: 0.7123 +[2026-03-20T17:35:51.514260Z] Loop 853: Loss: 1.80e-02, Avg Return: 0.351, Regret: 0.5117, Entropy: 0.7121 +[2026-03-20T17:35:52.367334Z] Loop 854: Loss: 1.80e-02, Avg Return: 0.353, Regret: 0.5117, Entropy: 0.7116 +[2026-03-20T17:35:53.261086Z] Loop 855: Loss: 1.94e-02, Avg Return: 0.350, Regret: 0.5115, Entropy: 0.7109 +[2026-03-20T17:35:54.114670Z] Loop 856: Loss: 1.86e-02, Avg Return: 0.349, Regret: 0.5115, Entropy: 0.7099 +[2026-03-20T17:35:54.968551Z] Loop 857: Loss: 1.75e-02, Avg Return: 0.352, Regret: 0.5115, Entropy: 0.7090 +[2026-03-20T17:35:55.822348Z] Loop 858: Loss: 1.78e-02, Avg Return: 0.353, Regret: 0.5115, Entropy: 0.7084 +[2026-03-20T17:35:56.675212Z] Loop 859: Loss: 1.78e-02, Avg Return: 0.349, Regret: 0.5115, Entropy: 0.7079 +[2026-03-20T17:35:57.569719Z] Loop 860: Loss: 1.79e-02, Avg Return: 0.347, Regret: 0.5115, Entropy: 0.7072 +[2026-03-20T17:35:58.423335Z] Loop 861: Loss: 1.84e-02, Avg Return: 0.354, Regret: 0.5115, Entropy: 0.7064 +[2026-03-20T17:35:59.275894Z] Loop 862: Loss: 1.91e-02, Avg Return: 0.354, Regret: 0.5115, Entropy: 0.7059 +[2026-03-20T17:36:00.127933Z] Loop 863: Loss: 1.82e-02, Avg Return: 0.350, Regret: 0.5115, Entropy: 0.7055 +[2026-03-20T17:36:00.979613Z] Loop 864: Loss: 1.78e-02, Avg Return: 0.353, Regret: 0.5115, Entropy: 0.7050 +[2026-03-20T17:36:01.872854Z] Loop 865: Loss: 1.93e-02, Avg Return: 0.356, Regret: 0.5118, Entropy: 0.7037 +[2026-03-20T17:36:02.725456Z] Loop 866: Loss: 1.87e-02, Avg Return: 0.350, Regret: 0.5118, Entropy: 0.7028 +[2026-03-20T17:36:03.578213Z] Loop 867: Loss: 1.71e-02, Avg Return: 0.350, Regret: 0.5118, Entropy: 0.7029 +[2026-03-20T17:36:04.430589Z] Loop 868: Loss: 1.80e-02, Avg Return: 0.353, Regret: 0.5118, Entropy: 0.7037 +[2026-03-20T17:36:05.283414Z] Loop 869: Loss: 1.77e-02, Avg Return: 0.351, Regret: 0.5118, Entropy: 0.7050 +[2026-03-20T17:36:06.177439Z] Loop 870: Loss: 1.70e-02, Avg Return: 0.347, Regret: 0.5112, Entropy: 0.7059 +[2026-03-20T17:36:07.030828Z] Loop 871: Loss: 1.80e-02, Avg Return: 0.352, Regret: 0.5112, Entropy: 0.7059 +[2026-03-20T17:36:07.884071Z] Loop 872: Loss: 1.80e-02, Avg Return: 0.347, Regret: 0.5112, Entropy: 0.7058 +[2026-03-20T17:36:08.737308Z] Loop 873: Loss: 1.91e-02, Avg Return: 0.352, Regret: 0.5112, Entropy: 0.7054 +[2026-03-20T17:36:09.589673Z] Loop 874: Loss: 1.72e-02, Avg Return: 0.351, Regret: 0.5112, Entropy: 0.7052 +[2026-03-20T17:36:10.483781Z] Loop 875: Loss: 1.79e-02, Avg Return: 0.353, Regret: 0.5112, Entropy: 0.7051 +[2026-03-20T17:36:11.336850Z] Loop 876: Loss: 1.66e-02, Avg Return: 0.342, Regret: 0.5112, Entropy: 0.7050 +[2026-03-20T17:36:12.189381Z] Loop 877: Loss: 1.82e-02, Avg Return: 0.350, Regret: 0.5112, Entropy: 0.7048 +[2026-03-20T17:36:13.040957Z] Loop 878: Loss: 1.79e-02, Avg Return: 0.357, Regret: 0.5112, Entropy: 0.7044 +[2026-03-20T17:36:13.893472Z] Loop 879: Loss: 1.81e-02, Avg Return: 0.350, Regret: 0.5112, Entropy: 0.7037 +[2026-03-20T17:36:14.786932Z] Loop 880: Loss: 1.81e-02, Avg Return: 0.349, Regret: 0.5113, Entropy: 0.7029 +[2026-03-20T17:36:15.640489Z] Loop 881: Loss: 1.89e-02, Avg Return: 0.351, Regret: 0.5113, Entropy: 0.7018 +[2026-03-20T17:36:16.494121Z] Loop 882: Loss: 1.66e-02, Avg Return: 0.356, Regret: 0.5113, Entropy: 0.7012 +[2026-03-20T17:36:17.347194Z] Loop 883: Loss: 1.84e-02, Avg Return: 0.347, Regret: 0.5113, Entropy: 0.7004 +[2026-03-20T17:36:18.200087Z] Loop 884: Loss: 1.82e-02, Avg Return: 0.348, Regret: 0.5113, Entropy: 0.7004 +[2026-03-20T17:36:19.092337Z] Loop 885: Loss: 1.86e-02, Avg Return: 0.350, Regret: 0.5113, Entropy: 0.7015 +[2026-03-20T17:36:19.944471Z] Loop 886: Loss: 1.70e-02, Avg Return: 0.348, Regret: 0.5113, Entropy: 0.7027 +[2026-03-20T17:36:20.796051Z] Loop 887: Loss: 1.83e-02, Avg Return: 0.350, Regret: 0.5113, Entropy: 0.7030 +[2026-03-20T17:36:21.649414Z] Loop 888: Loss: 1.80e-02, Avg Return: 0.352, Regret: 0.5113, Entropy: 0.7032 +[2026-03-20T17:36:22.502328Z] Loop 889: Loss: 1.88e-02, Avg Return: 0.355, Regret: 0.5113, Entropy: 0.7026 +[2026-03-20T17:36:23.393295Z] Loop 890: Loss: 1.82e-02, Avg Return: 0.355, Regret: 0.5114, Entropy: 0.7015 +[2026-03-20T17:36:24.245023Z] Loop 891: Loss: 1.79e-02, Avg Return: 0.351, Regret: 0.5114, Entropy: 0.7001 +[2026-03-20T17:36:25.099102Z] Loop 892: Loss: 1.85e-02, Avg Return: 0.359, Regret: 0.5114, Entropy: 0.6989 +[2026-03-20T17:36:25.952380Z] Loop 893: Loss: 1.78e-02, Avg Return: 0.348, Regret: 0.5114, Entropy: 0.6997 +[2026-03-20T17:36:26.804967Z] Loop 894: Loss: 1.72e-02, Avg Return: 0.347, Regret: 0.5114, Entropy: 0.7005 +[2026-03-20T17:36:27.694675Z] Loop 895: Loss: 1.83e-02, Avg Return: 0.356, Regret: 0.5112, Entropy: 0.7015 +[2026-03-20T17:36:28.546124Z] Loop 896: Loss: 1.83e-02, Avg Return: 0.348, Regret: 0.5112, Entropy: 0.7028 +[2026-03-20T17:36:29.398648Z] Loop 897: Loss: 1.67e-02, Avg Return: 0.351, Regret: 0.5112, Entropy: 0.7031 +[2026-03-20T17:36:30.250713Z] Loop 898: Loss: 1.82e-02, Avg Return: 0.352, Regret: 0.5112, Entropy: 0.7026 +[2026-03-20T17:36:31.103267Z] Loop 899: Loss: 1.80e-02, Avg Return: 0.350, Regret: 0.5112, Entropy: 0.7014 +[2026-03-20T17:36:31.996047Z] Loop 900: Loss: 1.84e-02, Avg Return: 0.357, Regret: 0.5110, Entropy: 0.7005 +[2026-03-20T17:36:32.848620Z] Loop 901: Loss: 1.79e-02, Avg Return: 0.352, Regret: 0.5110, Entropy: 0.7003 +[2026-03-20T17:36:33.701156Z] Loop 902: Loss: 1.88e-02, Avg Return: 0.353, Regret: 0.5110, Entropy: 0.7006 +[2026-03-20T17:36:34.553450Z] Loop 903: Loss: 1.71e-02, Avg Return: 0.353, Regret: 0.5110, Entropy: 0.7012 +[2026-03-20T17:36:35.406249Z] Loop 904: Loss: 1.73e-02, Avg Return: 0.351, Regret: 0.5110, Entropy: 0.7019 +[2026-03-20T17:36:36.297504Z] Loop 905: Loss: 1.72e-02, Avg Return: 0.351, Regret: 0.5105, Entropy: 0.7026 +[2026-03-20T17:36:37.149169Z] Loop 906: Loss: 1.74e-02, Avg Return: 0.353, Regret: 0.5105, Entropy: 0.7029 +[2026-03-20T17:36:38.001456Z] Loop 907: Loss: 1.85e-02, Avg Return: 0.355, Regret: 0.5105, Entropy: 0.7025 +[2026-03-20T17:36:38.854375Z] Loop 908: Loss: 1.89e-02, Avg Return: 0.354, Regret: 0.5105, Entropy: 0.7010 +[2026-03-20T17:36:39.707686Z] Loop 909: Loss: 1.77e-02, Avg Return: 0.352, Regret: 0.5105, Entropy: 0.6981 +[2026-03-20T17:36:40.595770Z] Loop 910: Loss: 1.76e-02, Avg Return: 0.348, Regret: 0.5119, Entropy: 0.6964 +[2026-03-20T17:36:41.448410Z] Loop 911: Loss: 1.69e-02, Avg Return: 0.347, Regret: 0.5119, Entropy: 0.6964 +[2026-03-20T17:36:42.301699Z] Loop 912: Loss: 1.93e-02, Avg Return: 0.356, Regret: 0.5119, Entropy: 0.6972 +[2026-03-20T17:36:43.154963Z] Loop 913: Loss: 1.77e-02, Avg Return: 0.347, Regret: 0.5119, Entropy: 0.6993 +[2026-03-20T17:36:44.007703Z] Loop 914: Loss: 1.70e-02, Avg Return: 0.346, Regret: 0.5119, Entropy: 0.7012 +[2026-03-20T17:36:44.901104Z] Loop 915: Loss: 1.65e-02, Avg Return: 0.346, Regret: 0.5102, Entropy: 0.7021 +[2026-03-20T17:36:45.754329Z] Loop 916: Loss: 1.78e-02, Avg Return: 0.355, Regret: 0.5102, Entropy: 0.7024 +[2026-03-20T17:36:46.608521Z] Loop 917: Loss: 1.71e-02, Avg Return: 0.345, Regret: 0.5102, Entropy: 0.7021 +[2026-03-20T17:36:47.463146Z] Loop 918: Loss: 1.69e-02, Avg Return: 0.350, Regret: 0.5102, Entropy: 0.7014 +[2026-03-20T17:36:48.315914Z] Loop 919: Loss: 1.75e-02, Avg Return: 0.353, Regret: 0.5102, Entropy: 0.7015 +[2026-03-20T17:36:49.208460Z] Loop 920: Loss: 1.74e-02, Avg Return: 0.350, Regret: 0.5105, Entropy: 0.7014 +[2026-03-20T17:36:50.062246Z] Loop 921: Loss: 1.82e-02, Avg Return: 0.358, Regret: 0.5105, Entropy: 0.7018 +[2026-03-20T17:36:50.915120Z] Loop 922: Loss: 1.81e-02, Avg Return: 0.357, Regret: 0.5105, Entropy: 0.7022 +[2026-03-20T17:36:51.767394Z] Loop 923: Loss: 1.69e-02, Avg Return: 0.352, Regret: 0.5105, Entropy: 0.7028 +[2026-03-20T17:36:52.620979Z] Loop 924: Loss: 1.79e-02, Avg Return: 0.357, Regret: 0.5105, Entropy: 0.7031 +[2026-03-20T17:36:53.516395Z] Loop 925: Loss: 1.76e-02, Avg Return: 0.350, Regret: 0.5101, Entropy: 0.7025 +[2026-03-20T17:36:54.370316Z] Loop 926: Loss: 1.90e-02, Avg Return: 0.354, Regret: 0.5101, Entropy: 0.7007 +[2026-03-20T17:36:55.222911Z] Loop 927: Loss: 1.76e-02, Avg Return: 0.355, Regret: 0.5101, Entropy: 0.6993 +[2026-03-20T17:36:56.074335Z] Loop 928: Loss: 1.61e-02, Avg Return: 0.349, Regret: 0.5101, Entropy: 0.6982 +[2026-03-20T17:36:56.926506Z] Loop 929: Loss: 1.60e-02, Avg Return: 0.346, Regret: 0.5101, Entropy: 0.6982 +[2026-03-20T17:36:57.820980Z] Loop 930: Loss: 1.78e-02, Avg Return: 0.359, Regret: 0.5105, Entropy: 0.6990 +[2026-03-20T17:36:58.674653Z] Loop 931: Loss: 1.70e-02, Avg Return: 0.349, Regret: 0.5105, Entropy: 0.7003 +[2026-03-20T17:36:59.527742Z] Loop 932: Loss: 1.76e-02, Avg Return: 0.354, Regret: 0.5105, Entropy: 0.7014 +[2026-03-20T17:37:00.380938Z] Loop 933: Loss: 1.82e-02, Avg Return: 0.355, Regret: 0.5105, Entropy: 0.7021 +[2026-03-20T17:37:01.235470Z] Loop 934: Loss: 1.79e-02, Avg Return: 0.356, Regret: 0.5105, Entropy: 0.7023 +[2026-03-20T17:37:02.131637Z] Loop 935: Loss: 1.66e-02, Avg Return: 0.351, Regret: 0.5095, Entropy: 0.7019 +[2026-03-20T17:37:02.984532Z] Loop 936: Loss: 1.85e-02, Avg Return: 0.356, Regret: 0.5095, Entropy: 0.7012 +[2026-03-20T17:37:03.836959Z] Loop 937: Loss: 1.68e-02, Avg Return: 0.356, Regret: 0.5095, Entropy: 0.7002 +[2026-03-20T17:37:04.691374Z] Loop 938: Loss: 1.76e-02, Avg Return: 0.355, Regret: 0.5095, Entropy: 0.6997 +[2026-03-20T17:37:05.544009Z] Loop 939: Loss: 1.79e-02, Avg Return: 0.358, Regret: 0.5095, Entropy: 0.7002 +[2026-03-20T17:37:06.436581Z] Loop 940: Loss: 1.81e-02, Avg Return: 0.353, Regret: 0.5091, Entropy: 0.7004 +[2026-03-20T17:37:07.289690Z] Loop 941: Loss: 1.87e-02, Avg Return: 0.362, Regret: 0.5091, Entropy: 0.7002 +[2026-03-20T17:37:08.142850Z] Loop 942: Loss: 1.66e-02, Avg Return: 0.349, Regret: 0.5091, Entropy: 0.6999 +[2026-03-20T17:37:08.995941Z] Loop 943: Loss: 1.65e-02, Avg Return: 0.356, Regret: 0.5091, Entropy: 0.6997 +[2026-03-20T17:37:09.849786Z] Loop 944: Loss: 1.75e-02, Avg Return: 0.364, Regret: 0.5091, Entropy: 0.6996 +[2026-03-20T17:37:10.742552Z] Loop 945: Loss: 1.82e-02, Avg Return: 0.357, Regret: 0.5089, Entropy: 0.6991 +[2026-03-20T17:37:11.595211Z] Loop 946: Loss: 1.64e-02, Avg Return: 0.355, Regret: 0.5089, Entropy: 0.6988 +[2026-03-20T17:37:12.448678Z] Loop 947: Loss: 1.86e-02, Avg Return: 0.354, Regret: 0.5089, Entropy: 0.6979 +[2026-03-20T17:37:13.301153Z] Loop 948: Loss: 1.76e-02, Avg Return: 0.355, Regret: 0.5089, Entropy: 0.6975 +[2026-03-20T17:37:14.153862Z] Loop 949: Loss: 1.70e-02, Avg Return: 0.356, Regret: 0.5089, Entropy: 0.6977 +[2026-03-20T17:37:15.044318Z] Loop 950: Loss: 1.76e-02, Avg Return: 0.358, Regret: 0.5089, Entropy: 0.6972 +[2026-03-20T17:37:15.896964Z] Loop 951: Loss: 1.75e-02, Avg Return: 0.363, Regret: 0.5089, Entropy: 0.6983 +[2026-03-20T17:37:16.749096Z] Loop 952: Loss: 1.79e-02, Avg Return: 0.362, Regret: 0.5089, Entropy: 0.6993 +[2026-03-20T17:37:17.601724Z] Loop 953: Loss: 1.84e-02, Avg Return: 0.357, Regret: 0.5089, Entropy: 0.6992 +[2026-03-20T17:37:18.454536Z] Loop 954: Loss: 1.71e-02, Avg Return: 0.353, Regret: 0.5089, Entropy: 0.6981 +[2026-03-20T17:37:19.348467Z] Loop 955: Loss: 1.75e-02, Avg Return: 0.359, Regret: 0.5085, Entropy: 0.6977 +[2026-03-20T17:37:20.200459Z] Loop 956: Loss: 1.75e-02, Avg Return: 0.363, Regret: 0.5085, Entropy: 0.6984 +[2026-03-20T17:37:21.052996Z] Loop 957: Loss: 1.74e-02, Avg Return: 0.350, Regret: 0.5085, Entropy: 0.6994 +[2026-03-20T17:37:21.905590Z] Loop 958: Loss: 1.80e-02, Avg Return: 0.356, Regret: 0.5085, Entropy: 0.6999 +[2026-03-20T17:37:22.759709Z] Loop 959: Loss: 1.80e-02, Avg Return: 0.358, Regret: 0.5085, Entropy: 0.6998 +[2026-03-20T17:37:23.651746Z] Loop 960: Loss: 1.89e-02, Avg Return: 0.359, Regret: 0.5076, Entropy: 0.6999 +[2026-03-20T17:37:24.504526Z] Loop 961: Loss: 1.61e-02, Avg Return: 0.352, Regret: 0.5076, Entropy: 0.6999 +[2026-03-20T17:37:25.357615Z] Loop 962: Loss: 1.64e-02, Avg Return: 0.350, Regret: 0.5076, Entropy: 0.6997 +[2026-03-20T17:37:26.211053Z] Loop 963: Loss: 1.79e-02, Avg Return: 0.356, Regret: 0.5076, Entropy: 0.6990 +[2026-03-20T17:37:27.063793Z] Loop 964: Loss: 1.67e-02, Avg Return: 0.357, Regret: 0.5076, Entropy: 0.6987 +[2026-03-20T17:37:27.956474Z] Loop 965: Loss: 1.75e-02, Avg Return: 0.363, Regret: 0.5073, Entropy: 0.6983 +[2026-03-20T17:37:28.809913Z] Loop 966: Loss: 1.72e-02, Avg Return: 0.353, Regret: 0.5073, Entropy: 0.6984 +[2026-03-20T17:37:29.662559Z] Loop 967: Loss: 1.76e-02, Avg Return: 0.360, Regret: 0.5073, Entropy: 0.6980 +[2026-03-20T17:37:30.515240Z] Loop 968: Loss: 1.73e-02, Avg Return: 0.358, Regret: 0.5073, Entropy: 0.6974 +[2026-03-20T17:37:31.367177Z] Loop 969: Loss: 1.67e-02, Avg Return: 0.353, Regret: 0.5073, Entropy: 0.6969 +[2026-03-20T17:37:32.259771Z] Loop 970: Loss: 1.60e-02, Avg Return: 0.353, Regret: 0.5065, Entropy: 0.6972 +[2026-03-20T17:37:33.113015Z] Loop 971: Loss: 1.69e-02, Avg Return: 0.352, Regret: 0.5065, Entropy: 0.6967 +[2026-03-20T17:37:33.965478Z] Loop 972: Loss: 1.76e-02, Avg Return: 0.357, Regret: 0.5065, Entropy: 0.6963 +[2026-03-20T17:37:34.818967Z] Loop 973: Loss: 1.83e-02, Avg Return: 0.357, Regret: 0.5065, Entropy: 0.6955 +[2026-03-20T17:37:35.671456Z] Loop 974: Loss: 1.63e-02, Avg Return: 0.351, Regret: 0.5065, Entropy: 0.6953 +[2026-03-20T17:37:36.562322Z] Loop 975: Loss: 1.85e-02, Avg Return: 0.363, Regret: 0.5058, Entropy: 0.6948 +[2026-03-20T17:37:37.414316Z] Loop 976: Loss: 1.85e-02, Avg Return: 0.361, Regret: 0.5058, Entropy: 0.6934 +[2026-03-20T17:37:38.266556Z] Loop 977: Loss: 1.73e-02, Avg Return: 0.359, Regret: 0.5058, Entropy: 0.6932 +[2026-03-20T17:37:39.120175Z] Loop 978: Loss: 1.64e-02, Avg Return: 0.355, Regret: 0.5058, Entropy: 0.6932 +[2026-03-20T17:37:39.973205Z] Loop 979: Loss: 1.68e-02, Avg Return: 0.361, Regret: 0.5058, Entropy: 0.6927 +[2026-03-20T17:37:40.866115Z] Loop 980: Loss: 1.80e-02, Avg Return: 0.366, Regret: 0.5051, Entropy: 0.6910 +[2026-03-20T17:37:41.719148Z] Loop 981: Loss: 1.61e-02, Avg Return: 0.355, Regret: 0.5051, Entropy: 0.6871 +[2026-03-20T17:37:42.572758Z] Loop 982: Loss: 1.71e-02, Avg Return: 0.358, Regret: 0.5051, Entropy: 0.6856 +[2026-03-20T17:37:43.425187Z] Loop 983: Loss: 1.71e-02, Avg Return: 0.357, Regret: 0.5051, Entropy: 0.6866 +[2026-03-20T17:37:44.277189Z] Loop 984: Loss: 1.70e-02, Avg Return: 0.357, Regret: 0.5051, Entropy: 0.6895 +[2026-03-20T17:37:45.167990Z] Loop 985: Loss: 1.71e-02, Avg Return: 0.362, Regret: 0.5043, Entropy: 0.6897 +[2026-03-20T17:37:46.021508Z] Loop 986: Loss: 1.64e-02, Avg Return: 0.355, Regret: 0.5043, Entropy: 0.6861 +[2026-03-20T17:37:46.874203Z] Loop 987: Loss: 1.64e-02, Avg Return: 0.368, Regret: 0.5043, Entropy: 0.6827 +[2026-03-20T17:37:47.726662Z] Loop 988: Loss: 1.62e-02, Avg Return: 0.364, Regret: 0.5043, Entropy: 0.6874 +[2026-03-20T17:37:48.579053Z] Loop 989: Loss: 1.63e-02, Avg Return: 0.363, Regret: 0.5043, Entropy: 0.6884 +[2026-03-20T17:37:49.471216Z] Loop 990: Loss: 1.55e-02, Avg Return: 0.354, Regret: 0.5032, Entropy: 0.6879 +[2026-03-20T17:37:50.323675Z] Loop 991: Loss: 1.67e-02, Avg Return: 0.369, Regret: 0.5032, Entropy: 0.6870 +[2026-03-20T17:37:51.174975Z] Loop 992: Loss: 1.80e-02, Avg Return: 0.365, Regret: 0.5032, Entropy: 0.6854 +[2026-03-20T17:37:52.028351Z] Loop 993: Loss: 1.69e-02, Avg Return: 0.360, Regret: 0.5032, Entropy: 0.6810 +[2026-03-20T17:37:52.881194Z] Loop 994: Loss: 1.64e-02, Avg Return: 0.359, Regret: 0.5032, Entropy: 0.6748 +[2026-03-20T17:37:53.771473Z] Loop 995: Loss: 1.70e-02, Avg Return: 0.357, Regret: 0.5055, Entropy: 0.6685 +[2026-03-20T17:37:54.623581Z] Loop 996: Loss: 1.70e-02, Avg Return: 0.360, Regret: 0.5055, Entropy: 0.6734 +[2026-03-20T17:37:55.475924Z] Loop 997: Loss: 1.70e-02, Avg Return: 0.366, Regret: 0.5055, Entropy: 0.6830 +[2026-03-20T17:37:56.328917Z] Loop 998: Loss: 1.64e-02, Avg Return: 0.356, Regret: 0.5055, Entropy: 0.6825 +[2026-03-20T17:37:57.182220Z] Loop 999: Loss: 1.73e-02, Avg Return: 0.362, Regret: 0.5055, Entropy: 0.6735 +[2026-03-20T17:37:58.073149Z] Loop 1000: Loss: 1.84e-02, Avg Return: 0.363, Regret: 0.5050, Entropy: 0.6726 +[2026-03-20T17:37:58.926259Z] Loop 1001: Loss: 1.69e-02, Avg Return: 0.365, Regret: 0.5050, Entropy: 0.6767 +[2026-03-20T17:37:59.778918Z] Loop 1002: Loss: 1.66e-02, Avg Return: 0.371, Regret: 0.5050, Entropy: 0.6823 +[2026-03-20T17:38:00.632008Z] Loop 1003: Loss: 1.46e-02, Avg Return: 0.360, Regret: 0.5050, Entropy: 0.6817 +[2026-03-20T17:38:01.484041Z] Loop 1004: Loss: 1.61e-02, Avg Return: 0.362, Regret: 0.5050, Entropy: 0.6791 +[2026-03-20T17:38:02.374171Z] Loop 1005: Loss: 1.51e-02, Avg Return: 0.364, Regret: 0.5002, Entropy: 0.6786 +[2026-03-20T17:38:03.226080Z] Loop 1006: Loss: 1.58e-02, Avg Return: 0.358, Regret: 0.5002, Entropy: 0.6785 +[2026-03-20T17:38:04.077952Z] Loop 1007: Loss: 1.61e-02, Avg Return: 0.369, Regret: 0.5002, Entropy: 0.6797 +[2026-03-20T17:38:04.931129Z] Loop 1008: Loss: 1.57e-02, Avg Return: 0.364, Regret: 0.5002, Entropy: 0.6795 +[2026-03-20T17:38:05.784267Z] Loop 1009: Loss: 1.59e-02, Avg Return: 0.367, Regret: 0.5002, Entropy: 0.6781 +[2026-03-20T17:38:06.677246Z] Loop 1010: Loss: 1.55e-02, Avg Return: 0.362, Regret: 0.4993, Entropy: 0.6775 +[2026-03-20T17:38:07.530884Z] Loop 1011: Loss: 1.52e-02, Avg Return: 0.368, Regret: 0.4993, Entropy: 0.6750 +[2026-03-20T17:38:08.384871Z] Loop 1012: Loss: 1.42e-02, Avg Return: 0.363, Regret: 0.4993, Entropy: 0.6748 +[2026-03-20T17:38:09.237124Z] Loop 1013: Loss: 1.56e-02, Avg Return: 0.368, Regret: 0.4993, Entropy: 0.6717 +[2026-03-20T17:38:10.090514Z] Loop 1014: Loss: 1.52e-02, Avg Return: 0.360, Regret: 0.4993, Entropy: 0.6721 +[2026-03-20T17:38:10.982114Z] Loop 1015: Loss: 1.42e-02, Avg Return: 0.368, Regret: 0.4975, Entropy: 0.6726 +[2026-03-20T17:38:11.834259Z] Loop 1016: Loss: 1.56e-02, Avg Return: 0.361, Regret: 0.4975, Entropy: 0.6713 +[2026-03-20T17:38:12.687437Z] Loop 1017: Loss: 1.49e-02, Avg Return: 0.365, Regret: 0.4975, Entropy: 0.6661 +[2026-03-20T17:38:13.540577Z] Loop 1018: Loss: 1.62e-02, Avg Return: 0.368, Regret: 0.4975, Entropy: 0.6591 +[2026-03-20T17:38:14.393053Z] Loop 1019: Loss: 1.53e-02, Avg Return: 0.363, Regret: 0.4975, Entropy: 0.6575 +[2026-03-20T17:38:15.284478Z] Loop 1020: Loss: 1.42e-02, Avg Return: 0.363, Regret: 0.4955, Entropy: 0.6614 +[2026-03-20T17:38:16.136682Z] Loop 1021: Loss: 1.57e-02, Avg Return: 0.369, Regret: 0.4955, Entropy: 0.6636 +[2026-03-20T17:38:16.990228Z] Loop 1022: Loss: 1.41e-02, Avg Return: 0.370, Regret: 0.4955, Entropy: 0.6641 +[2026-03-20T17:38:17.843382Z] Loop 1023: Loss: 1.55e-02, Avg Return: 0.372, Regret: 0.4955, Entropy: 0.6626 +[2026-03-20T17:38:18.696423Z] Loop 1024: Loss: 1.51e-02, Avg Return: 0.377, Regret: 0.4955, Entropy: 0.6581 +[2026-03-20T17:38:19.588674Z] Loop 1025: Loss: 1.50e-02, Avg Return: 0.367, Regret: 0.4948, Entropy: 0.6581 +[2026-03-20T17:38:20.441911Z] Loop 1026: Loss: 1.42e-02, Avg Return: 0.366, Regret: 0.4948, Entropy: 0.6578 +[2026-03-20T17:38:21.296012Z] Loop 1027: Loss: 1.45e-02, Avg Return: 0.377, Regret: 0.4948, Entropy: 0.6537 +[2026-03-20T17:38:22.149368Z] Loop 1028: Loss: 1.50e-02, Avg Return: 0.371, Regret: 0.4948, Entropy: 0.6475 +[2026-03-20T17:38:23.001100Z] Loop 1029: Loss: 1.49e-02, Avg Return: 0.363, Regret: 0.4948, Entropy: 0.6372 +[2026-03-20T17:38:23.892070Z] Loop 1030: Loss: 1.45e-02, Avg Return: 0.377, Regret: 0.4941, Entropy: 0.6225 +[2026-03-20T17:38:24.745325Z] Loop 1031: Loss: 1.48e-02, Avg Return: 0.367, Regret: 0.4941, Entropy: 0.6186 +[2026-03-20T17:38:25.599795Z] Loop 1032: Loss: 1.47e-02, Avg Return: 0.369, Regret: 0.4941, Entropy: 0.6243 +[2026-03-20T17:38:26.452346Z] Loop 1033: Loss: 1.40e-02, Avg Return: 0.375, Regret: 0.4941, Entropy: 0.6258 +[2026-03-20T17:38:27.305799Z] Loop 1034: Loss: 1.40e-02, Avg Return: 0.375, Regret: 0.4941, Entropy: 0.6288 +[2026-03-20T17:38:28.199890Z] Loop 1035: Loss: 1.34e-02, Avg Return: 0.373, Regret: 0.4889, Entropy: 0.6315 +[2026-03-20T17:38:29.053275Z] Loop 1036: Loss: 1.46e-02, Avg Return: 0.378, Regret: 0.4889, Entropy: 0.6270 +[2026-03-20T17:38:29.905977Z] Loop 1037: Loss: 1.31e-02, Avg Return: 0.361, Regret: 0.4889, Entropy: 0.6196 +[2026-03-20T17:38:30.756958Z] Loop 1038: Loss: 1.33e-02, Avg Return: 0.366, Regret: 0.4889, Entropy: 0.6138 +[2026-03-20T17:38:31.607537Z] Loop 1039: Loss: 1.32e-02, Avg Return: 0.365, Regret: 0.4889, Entropy: 0.6148 +[2026-03-20T17:38:32.499999Z] Loop 1040: Loss: 1.42e-02, Avg Return: 0.384, Regret: 0.4882, Entropy: 0.6141 +[2026-03-20T17:38:33.353063Z] Loop 1041: Loss: 1.28e-02, Avg Return: 0.377, Regret: 0.4882, Entropy: 0.6065 +[2026-03-20T17:38:34.205204Z] Loop 1042: Loss: 1.32e-02, Avg Return: 0.385, Regret: 0.4882, Entropy: 0.5892 +[2026-03-20T17:38:35.056775Z] Loop 1043: Loss: 1.43e-02, Avg Return: 0.372, Regret: 0.4882, Entropy: 0.5785 +[2026-03-20T17:38:35.908395Z] Loop 1044: Loss: 1.33e-02, Avg Return: 0.383, Regret: 0.4882, Entropy: 0.5823 +[2026-03-20T17:38:36.799716Z] Loop 1045: Loss: 1.22e-02, Avg Return: 0.384, Regret: 0.4827, Entropy: 0.5883 +[2026-03-20T17:38:37.652048Z] Loop 1046: Loss: 1.25e-02, Avg Return: 0.386, Regret: 0.4827, Entropy: 0.5929 +[2026-03-20T17:38:38.504755Z] Loop 1047: Loss: 1.16e-02, Avg Return: 0.374, Regret: 0.4827, Entropy: 0.5915 +[2026-03-20T17:38:39.356724Z] Loop 1048: Loss: 1.26e-02, Avg Return: 0.390, Regret: 0.4827, Entropy: 0.5809 +[2026-03-20T17:38:40.209074Z] Loop 1049: Loss: 1.21e-02, Avg Return: 0.382, Regret: 0.4827, Entropy: 0.5728 +[2026-03-20T17:38:41.101541Z] Loop 1050: Loss: 1.37e-02, Avg Return: 0.387, Regret: 0.4808, Entropy: 0.5534 +[2026-03-20T17:38:41.954213Z] Loop 1051: Loss: 1.38e-02, Avg Return: 0.380, Regret: 0.4808, Entropy: 0.5282 +[2026-03-20T17:38:42.806052Z] Loop 1052: Loss: 1.37e-02, Avg Return: 0.380, Regret: 0.4808, Entropy: 0.5264 +[2026-03-20T17:38:43.658171Z] Loop 1053: Loss: 1.32e-02, Avg Return: 0.384, Regret: 0.4808, Entropy: 0.5233 +[2026-03-20T17:38:44.510922Z] Loop 1054: Loss: 1.22e-02, Avg Return: 0.387, Regret: 0.4808, Entropy: 0.5347 +[2026-03-20T17:38:45.402860Z] Loop 1055: Loss: 1.06e-02, Avg Return: 0.379, Regret: 0.4776, Entropy: 0.5473 +[2026-03-20T17:38:46.255339Z] Loop 1056: Loss: 1.17e-02, Avg Return: 0.387, Regret: 0.4776, Entropy: 0.5531 +[2026-03-20T17:38:47.107510Z] Loop 1057: Loss: 1.11e-02, Avg Return: 0.388, Regret: 0.4776, Entropy: 0.5481 +[2026-03-20T17:38:47.960274Z] Loop 1058: Loss: 1.11e-02, Avg Return: 0.381, Regret: 0.4776, Entropy: 0.5419 +[2026-03-20T17:38:48.812917Z] Loop 1059: Loss: 1.21e-02, Avg Return: 0.388, Regret: 0.4776, Entropy: 0.5394 +[2026-03-20T17:38:49.705567Z] Loop 1060: Loss: 1.16e-02, Avg Return: 0.386, Regret: 0.4848, Entropy: 0.5428 +[2026-03-20T17:38:50.558822Z] Loop 1061: Loss: 1.01e-02, Avg Return: 0.376, Regret: 0.4848, Entropy: 0.5382 +[2026-03-20T17:38:51.410968Z] Loop 1062: Loss: 1.01e-02, Avg Return: 0.386, Regret: 0.4848, Entropy: 0.5269 +[2026-03-20T17:38:52.264060Z] Loop 1063: Loss: 1.05e-02, Avg Return: 0.391, Regret: 0.4848, Entropy: 0.5021 +[2026-03-20T17:38:53.115988Z] Loop 1064: Loss: 1.18e-02, Avg Return: 0.388, Regret: 0.4848, Entropy: 0.4834 +[2026-03-20T17:38:54.008688Z] Loop 1065: Loss: 1.26e-02, Avg Return: 0.387, Regret: 0.4751, Entropy: 0.4698 +[2026-03-20T17:38:54.862224Z] Loop 1066: Loss: 1.12e-02, Avg Return: 0.393, Regret: 0.4751, Entropy: 0.4723 +[2026-03-20T17:38:55.715796Z] Loop 1067: Loss: 1.14e-02, Avg Return: 0.392, Regret: 0.4751, Entropy: 0.4746 +[2026-03-20T17:38:56.568120Z] Loop 1068: Loss: 1.03e-02, Avg Return: 0.399, Regret: 0.4751, Entropy: 0.4902 +[2026-03-20T17:38:57.420855Z] Loop 1069: Loss: 1.06e-02, Avg Return: 0.397, Regret: 0.4751, Entropy: 0.4885 +[2026-03-20T17:38:58.312587Z] Loop 1070: Loss: 1.02e-02, Avg Return: 0.399, Regret: 0.4708, Entropy: 0.4854 +[2026-03-20T17:38:59.165712Z] Loop 1071: Loss: 9.60e-03, Avg Return: 0.390, Regret: 0.4708, Entropy: 0.4775 +[2026-03-20T17:39:00.018050Z] Loop 1072: Loss: 9.44e-03, Avg Return: 0.390, Regret: 0.4708, Entropy: 0.4813 +[2026-03-20T17:39:00.870785Z] Loop 1073: Loss: 9.69e-03, Avg Return: 0.392, Regret: 0.4708, Entropy: 0.4766 +[2026-03-20T17:39:01.722828Z] Loop 1074: Loss: 9.50e-03, Avg Return: 0.390, Regret: 0.4708, Entropy: 0.4672 +[2026-03-20T17:39:02.615443Z] Loop 1075: Loss: 9.67e-03, Avg Return: 0.397, Regret: 0.4664, Entropy: 0.4599 +[2026-03-20T17:39:03.468325Z] Loop 1076: Loss: 1.03e-02, Avg Return: 0.399, Regret: 0.4664, Entropy: 0.4537 +[2026-03-20T17:39:04.321463Z] Loop 1077: Loss: 1.03e-02, Avg Return: 0.398, Regret: 0.4664, Entropy: 0.4329 +[2026-03-20T17:39:05.173850Z] Loop 1078: Loss: 1.13e-02, Avg Return: 0.402, Regret: 0.4664, Entropy: 0.4371 +[2026-03-20T17:39:06.026858Z] Loop 1079: Loss: 9.80e-03, Avg Return: 0.397, Regret: 0.4664, Entropy: 0.4393 +[2026-03-20T17:39:06.918242Z] Loop 1080: Loss: 8.96e-03, Avg Return: 0.397, Regret: 0.4633, Entropy: 0.4401 +[2026-03-20T17:39:07.771200Z] Loop 1081: Loss: 9.73e-03, Avg Return: 0.398, Regret: 0.4633, Entropy: 0.4414 +[2026-03-20T17:39:08.624232Z] Loop 1082: Loss: 1.01e-02, Avg Return: 0.396, Regret: 0.4633, Entropy: 0.4362 +[2026-03-20T17:39:09.477152Z] Loop 1083: Loss: 9.36e-03, Avg Return: 0.405, Regret: 0.4633, Entropy: 0.4293 +[2026-03-20T17:39:10.328729Z] Loop 1084: Loss: 1.05e-02, Avg Return: 0.414, Regret: 0.4633, Entropy: 0.4276 +[2026-03-20T17:39:11.220813Z] Loop 1085: Loss: 9.50e-03, Avg Return: 0.398, Regret: 0.4600, Entropy: 0.4291 +[2026-03-20T17:39:12.073674Z] Loop 1086: Loss: 9.18e-03, Avg Return: 0.411, Regret: 0.4600, Entropy: 0.4264 +[2026-03-20T17:39:12.926827Z] Loop 1087: Loss: 8.92e-03, Avg Return: 0.400, Regret: 0.4600, Entropy: 0.4299 +[2026-03-20T17:39:13.779524Z] Loop 1088: Loss: 9.12e-03, Avg Return: 0.405, Regret: 0.4600, Entropy: 0.4273 +[2026-03-20T17:39:14.632244Z] Loop 1089: Loss: 8.83e-03, Avg Return: 0.401, Regret: 0.4600, Entropy: 0.4258 +[2026-03-20T17:39:15.525518Z] Loop 1090: Loss: 9.23e-03, Avg Return: 0.406, Regret: 0.4580, Entropy: 0.4266 +[2026-03-20T17:39:16.378677Z] Loop 1091: Loss: 9.57e-03, Avg Return: 0.410, Regret: 0.4580, Entropy: 0.4244 +[2026-03-20T17:39:17.231325Z] Loop 1092: Loss: 9.36e-03, Avg Return: 0.407, Regret: 0.4580, Entropy: 0.4119 +[2026-03-20T17:39:18.082697Z] Loop 1093: Loss: 1.04e-02, Avg Return: 0.416, Regret: 0.4580, Entropy: 0.4127 +[2026-03-20T17:39:18.934269Z] Loop 1094: Loss: 1.03e-02, Avg Return: 0.403, Regret: 0.4580, Entropy: 0.4058 +[2026-03-20T17:39:19.828030Z] Loop 1095: Loss: 1.08e-02, Avg Return: 0.403, Regret: 0.4555, Entropy: 0.3995 +[2026-03-20T17:39:20.681639Z] Loop 1096: Loss: 1.16e-02, Avg Return: 0.411, Regret: 0.4555, Entropy: 0.4113 +[2026-03-20T17:39:21.534032Z] Loop 1097: Loss: 9.63e-03, Avg Return: 0.406, Regret: 0.4555, Entropy: 0.4275 +[2026-03-20T17:39:22.386868Z] Loop 1098: Loss: 9.23e-03, Avg Return: 0.411, Regret: 0.4555, Entropy: 0.4453 +[2026-03-20T17:39:23.239671Z] Loop 1099: Loss: 8.72e-03, Avg Return: 0.408, Regret: 0.4555, Entropy: 0.4590 +[2026-03-20T17:39:24.132177Z] Loop 1100: Loss: 9.41e-03, Avg Return: 0.414, Regret: 0.4577, Entropy: 0.4528 +[2026-03-20T17:39:24.984556Z] Loop 1101: Loss: 9.01e-03, Avg Return: 0.403, Regret: 0.4577, Entropy: 0.4421 +[2026-03-20T17:39:25.837332Z] Loop 1102: Loss: 9.51e-03, Avg Return: 0.415, Regret: 0.4577, Entropy: 0.4193 +[2026-03-20T17:39:26.695264Z] Loop 1103: Loss: 1.06e-02, Avg Return: 0.421, Regret: 0.4577, Entropy: 0.4111 +[2026-03-20T17:39:27.548388Z] Loop 1104: Loss: 1.09e-02, Avg Return: 0.414, Regret: 0.4577, Entropy: 0.4013 +[2026-03-20T17:39:28.440785Z] Loop 1105: Loss: 1.11e-02, Avg Return: 0.418, Regret: 0.4501, Entropy: 0.3944 +[2026-03-20T17:39:29.293911Z] Loop 1106: Loss: 1.02e-02, Avg Return: 0.407, Regret: 0.4501, Entropy: 0.3888 +[2026-03-20T17:39:30.146720Z] Loop 1107: Loss: 9.66e-03, Avg Return: 0.410, Regret: 0.4501, Entropy: 0.3960 +[2026-03-20T17:39:30.999347Z] Loop 1108: Loss: 9.92e-03, Avg Return: 0.423, Regret: 0.4501, Entropy: 0.3991 +[2026-03-20T17:39:31.852254Z] Loop 1109: Loss: 1.01e-02, Avg Return: 0.418, Regret: 0.4501, Entropy: 0.4087 +[2026-03-20T17:39:32.743847Z] Loop 1110: Loss: 9.21e-03, Avg Return: 0.425, Regret: 0.4437, Entropy: 0.4108 +[2026-03-20T17:39:33.596987Z] Loop 1111: Loss: 9.39e-03, Avg Return: 0.415, Regret: 0.4437, Entropy: 0.4143 +[2026-03-20T17:39:34.449999Z] Loop 1112: Loss: 9.08e-03, Avg Return: 0.419, Regret: 0.4437, Entropy: 0.4175 +[2026-03-20T17:39:35.302527Z] Loop 1113: Loss: 1.04e-02, Avg Return: 0.435, Regret: 0.4437, Entropy: 0.4088 +[2026-03-20T17:39:36.155473Z] Loop 1114: Loss: 9.49e-03, Avg Return: 0.423, Regret: 0.4437, Entropy: 0.3884 +[2026-03-20T17:39:37.048736Z] Loop 1115: Loss: 1.08e-02, Avg Return: 0.424, Regret: 0.4394, Entropy: 0.3895 +[2026-03-20T17:39:37.900483Z] Loop 1116: Loss: 9.79e-03, Avg Return: 0.429, Regret: 0.4394, Entropy: 0.3900 +[2026-03-20T17:39:38.752001Z] Loop 1117: Loss: 1.08e-02, Avg Return: 0.431, Regret: 0.4394, Entropy: 0.4002 +[2026-03-20T17:39:39.604807Z] Loop 1118: Loss: 9.76e-03, Avg Return: 0.424, Regret: 0.4394, Entropy: 0.4051 +[2026-03-20T17:39:40.457301Z] Loop 1119: Loss: 8.95e-03, Avg Return: 0.419, Regret: 0.4394, Entropy: 0.4247 +[2026-03-20T17:39:41.352329Z] Loop 1120: Loss: 9.19e-03, Avg Return: 0.421, Regret: 0.4386, Entropy: 0.4171 +[2026-03-20T17:39:42.204684Z] Loop 1121: Loss: 9.05e-03, Avg Return: 0.420, Regret: 0.4386, Entropy: 0.4089 +[2026-03-20T17:39:43.057208Z] Loop 1122: Loss: 9.55e-03, Avg Return: 0.430, Regret: 0.4386, Entropy: 0.3790 +[2026-03-20T17:39:43.910595Z] Loop 1123: Loss: 9.70e-03, Avg Return: 0.424, Regret: 0.4386, Entropy: 0.3553 +[2026-03-20T17:39:44.764129Z] Loop 1124: Loss: 1.01e-02, Avg Return: 0.427, Regret: 0.4386, Entropy: 0.3534 +[2026-03-20T17:39:45.657051Z] Loop 1125: Loss: 1.01e-02, Avg Return: 0.439, Regret: 0.4297, Entropy: 0.3647 +[2026-03-20T17:39:46.509265Z] Loop 1126: Loss: 9.46e-03, Avg Return: 0.430, Regret: 0.4297, Entropy: 0.3846 +[2026-03-20T17:39:47.361847Z] Loop 1127: Loss: 1.00e-02, Avg Return: 0.438, Regret: 0.4297, Entropy: 0.3743 +[2026-03-20T17:39:48.215834Z] Loop 1128: Loss: 9.77e-03, Avg Return: 0.440, Regret: 0.4297, Entropy: 0.3684 +[2026-03-20T17:39:49.069242Z] Loop 1129: Loss: 1.01e-02, Avg Return: 0.443, Regret: 0.4297, Entropy: 0.3552 +[2026-03-20T17:39:49.962496Z] Loop 1130: Loss: 9.34e-03, Avg Return: 0.437, Regret: 0.4255, Entropy: 0.3501 +[2026-03-20T17:39:50.814482Z] Loop 1131: Loss: 9.56e-03, Avg Return: 0.438, Regret: 0.4255, Entropy: 0.3406 +[2026-03-20T17:39:51.667590Z] Loop 1132: Loss: 9.22e-03, Avg Return: 0.444, Regret: 0.4255, Entropy: 0.3594 +[2026-03-20T17:39:52.521260Z] Loop 1133: Loss: 8.99e-03, Avg Return: 0.438, Regret: 0.4255, Entropy: 0.3834 +[2026-03-20T17:39:53.373613Z] Loop 1134: Loss: 8.48e-03, Avg Return: 0.435, Regret: 0.4255, Entropy: 0.3921 +[2026-03-20T17:39:54.268473Z] Loop 1135: Loss: 8.73e-03, Avg Return: 0.436, Regret: 0.4230, Entropy: 0.3820 +[2026-03-20T17:39:55.121435Z] Loop 1136: Loss: 8.85e-03, Avg Return: 0.440, Regret: 0.4230, Entropy: 0.3516 +[2026-03-20T17:39:55.974936Z] Loop 1137: Loss: 1.07e-02, Avg Return: 0.445, Regret: 0.4230, Entropy: 0.3270 +[2026-03-20T17:39:56.828463Z] Loop 1138: Loss: 9.90e-03, Avg Return: 0.437, Regret: 0.4230, Entropy: 0.3119 +[2026-03-20T17:39:57.680908Z] Loop 1139: Loss: 9.64e-03, Avg Return: 0.438, Regret: 0.4230, Entropy: 0.3114 +[2026-03-20T17:39:58.573624Z] Loop 1140: Loss: 9.58e-03, Avg Return: 0.444, Regret: 0.4162, Entropy: 0.3298 +[2026-03-20T17:39:59.427275Z] Loop 1141: Loss: 9.84e-03, Avg Return: 0.447, Regret: 0.4162, Entropy: 0.3650 +[2026-03-20T17:40:00.280865Z] Loop 1142: Loss: 8.86e-03, Avg Return: 0.440, Regret: 0.4162, Entropy: 0.3910 +[2026-03-20T17:40:01.134054Z] Loop 1143: Loss: 8.81e-03, Avg Return: 0.441, Regret: 0.4162, Entropy: 0.4012 +[2026-03-20T17:40:01.987733Z] Loop 1144: Loss: 9.59e-03, Avg Return: 0.453, Regret: 0.4162, Entropy: 0.3879 +[2026-03-20T17:40:02.883099Z] Loop 1145: Loss: 8.93e-03, Avg Return: 0.449, Regret: 0.4108, Entropy: 0.3460 +[2026-03-20T17:40:03.740589Z] Loop 1146: Loss: 8.75e-03, Avg Return: 0.446, Regret: 0.4108, Entropy: 0.3122 +[2026-03-20T17:40:04.593698Z] Loop 1147: Loss: 9.24e-03, Avg Return: 0.441, Regret: 0.4108, Entropy: 0.2982 +[2026-03-20T17:40:05.446171Z] Loop 1148: Loss: 9.16e-03, Avg Return: 0.454, Regret: 0.4108, Entropy: 0.3036 +[2026-03-20T17:40:06.300004Z] Loop 1149: Loss: 8.25e-03, Avg Return: 0.459, Regret: 0.4108, Entropy: 0.3334 +[2026-03-20T17:40:07.193478Z] Loop 1150: Loss: 8.23e-03, Avg Return: 0.452, Regret: 0.4078, Entropy: 0.3474 +[2026-03-20T17:40:08.046690Z] Loop 1151: Loss: 8.05e-03, Avg Return: 0.452, Regret: 0.4078, Entropy: 0.3736 +[2026-03-20T17:40:08.899454Z] Loop 1152: Loss: 8.66e-03, Avg Return: 0.450, Regret: 0.4078, Entropy: 0.3756 +[2026-03-20T17:40:09.752525Z] Loop 1153: Loss: 8.76e-03, Avg Return: 0.459, Regret: 0.4078, Entropy: 0.3613 +[2026-03-20T17:40:10.605131Z] Loop 1154: Loss: 8.07e-03, Avg Return: 0.452, Regret: 0.4078, Entropy: 0.3456 +[2026-03-20T17:40:11.497606Z] Loop 1155: Loss: 9.02e-03, Avg Return: 0.458, Regret: 0.4040, Entropy: 0.3116 +[2026-03-20T17:40:12.350639Z] Loop 1156: Loss: 8.66e-03, Avg Return: 0.461, Regret: 0.4040, Entropy: 0.2832 +[2026-03-20T17:40:13.205185Z] Loop 1157: Loss: 8.08e-03, Avg Return: 0.453, Regret: 0.4040, Entropy: 0.2661 +[2026-03-20T17:40:14.058730Z] Loop 1158: Loss: 8.05e-03, Avg Return: 0.454, Regret: 0.4040, Entropy: 0.2741 +[2026-03-20T17:40:14.912101Z] Loop 1159: Loss: 7.66e-03, Avg Return: 0.461, Regret: 0.4040, Entropy: 0.3164 +[2026-03-20T17:40:15.808478Z] Loop 1160: Loss: 8.03e-03, Avg Return: 0.462, Regret: 0.4052, Entropy: 0.3642 +[2026-03-20T17:40:16.662275Z] Loop 1161: Loss: 8.53e-03, Avg Return: 0.448, Regret: 0.4052, Entropy: 0.3796 +[2026-03-20T17:40:17.514383Z] Loop 1162: Loss: 8.60e-03, Avg Return: 0.446, Regret: 0.4052, Entropy: 0.3800 +[2026-03-20T17:40:18.367138Z] Loop 1163: Loss: 8.18e-03, Avg Return: 0.464, Regret: 0.4052, Entropy: 0.3719 +[2026-03-20T17:40:19.220693Z] Loop 1164: Loss: 8.11e-03, Avg Return: 0.465, Regret: 0.4052, Entropy: 0.3398 +[2026-03-20T17:40:20.113929Z] Loop 1165: Loss: 7.12e-03, Avg Return: 0.470, Regret: 0.3993, Entropy: 0.3035 +[2026-03-20T17:40:20.966439Z] Loop 1166: Loss: 7.37e-03, Avg Return: 0.463, Regret: 0.3993, Entropy: 0.2867 +[2026-03-20T17:40:21.820269Z] Loop 1167: Loss: 6.74e-03, Avg Return: 0.461, Regret: 0.3993, Entropy: 0.2674 +[2026-03-20T17:40:22.673650Z] Loop 1168: Loss: 6.74e-03, Avg Return: 0.458, Regret: 0.3993, Entropy: 0.2595 +[2026-03-20T17:40:23.527159Z] Loop 1169: Loss: 6.37e-03, Avg Return: 0.467, Regret: 0.3993, Entropy: 0.2519 +[2026-03-20T17:40:24.420670Z] Loop 1170: Loss: 6.96e-03, Avg Return: 0.458, Regret: 0.4037, Entropy: 0.2563 +[2026-03-20T17:40:25.273725Z] Loop 1171: Loss: 6.03e-03, Avg Return: 0.465, Regret: 0.4037, Entropy: 0.2664 +[2026-03-20T17:40:26.126631Z] Loop 1172: Loss: 6.10e-03, Avg Return: 0.460, Regret: 0.4037, Entropy: 0.2920 +[2026-03-20T17:40:26.980205Z] Loop 1173: Loss: 6.83e-03, Avg Return: 0.464, Regret: 0.4037, Entropy: 0.3039 +[2026-03-20T17:40:27.834667Z] Loop 1174: Loss: 7.66e-03, Avg Return: 0.472, Regret: 0.4037, Entropy: 0.3159 +[2026-03-20T17:40:28.728781Z] Loop 1175: Loss: 7.24e-03, Avg Return: 0.461, Regret: 0.3992, Entropy: 0.3257 +[2026-03-20T17:40:29.581606Z] Loop 1176: Loss: 7.11e-03, Avg Return: 0.461, Regret: 0.3992, Entropy: 0.3189 +[2026-03-20T17:40:30.434272Z] Loop 1177: Loss: 7.29e-03, Avg Return: 0.462, Regret: 0.3992, Entropy: 0.3161 +[2026-03-20T17:40:31.287786Z] Loop 1178: Loss: 6.92e-03, Avg Return: 0.462, Regret: 0.3992, Entropy: 0.3153 +[2026-03-20T17:40:32.141639Z] Loop 1179: Loss: 7.43e-03, Avg Return: 0.472, Regret: 0.3992, Entropy: 0.3097 +[2026-03-20T17:40:33.035017Z] Loop 1180: Loss: 7.59e-03, Avg Return: 0.474, Regret: 0.3937, Entropy: 0.3030 +[2026-03-20T17:40:33.887773Z] Loop 1181: Loss: 8.23e-03, Avg Return: 0.476, Regret: 0.3937, Entropy: 0.3107 +[2026-03-20T17:40:34.740628Z] Loop 1182: Loss: 8.12e-03, Avg Return: 0.472, Regret: 0.3937, Entropy: 0.3068 +[2026-03-20T17:40:35.593110Z] Loop 1183: Loss: 7.39e-03, Avg Return: 0.475, Regret: 0.3937, Entropy: 0.3027 +[2026-03-20T17:40:36.445676Z] Loop 1184: Loss: 7.77e-03, Avg Return: 0.478, Regret: 0.3937, Entropy: 0.2998 +[2026-03-20T17:40:37.336624Z] Loop 1185: Loss: 7.39e-03, Avg Return: 0.476, Regret: 0.3914, Entropy: 0.2994 +[2026-03-20T17:40:38.189658Z] Loop 1186: Loss: 7.69e-03, Avg Return: 0.481, Regret: 0.3914, Entropy: 0.3022 +[2026-03-20T17:40:39.043472Z] Loop 1187: Loss: 7.18e-03, Avg Return: 0.471, Regret: 0.3914, Entropy: 0.2977 +[2026-03-20T17:40:39.895444Z] Loop 1188: Loss: 6.84e-03, Avg Return: 0.464, Regret: 0.3914, Entropy: 0.2902 +[2026-03-20T17:40:40.747324Z] Loop 1189: Loss: 6.98e-03, Avg Return: 0.470, Regret: 0.3914, Entropy: 0.2927 +[2026-03-20T17:40:41.641207Z] Loop 1190: Loss: 7.28e-03, Avg Return: 0.479, Regret: 0.3886, Entropy: 0.2727 +[2026-03-20T17:40:42.495185Z] Loop 1191: Loss: 5.46e-03, Avg Return: 0.472, Regret: 0.3886, Entropy: 0.2458 +[2026-03-20T17:40:43.347861Z] Loop 1192: Loss: 6.11e-03, Avg Return: 0.473, Regret: 0.3886, Entropy: 0.2344 +[2026-03-20T17:40:44.201457Z] Loop 1193: Loss: 6.12e-03, Avg Return: 0.475, Regret: 0.3886, Entropy: 0.2222 +[2026-03-20T17:40:45.055577Z] Loop 1194: Loss: 5.69e-03, Avg Return: 0.471, Regret: 0.3886, Entropy: 0.2097 +[2026-03-20T17:40:45.950023Z] Loop 1195: Loss: 6.12e-03, Avg Return: 0.473, Regret: 0.3931, Entropy: 0.2045 +[2026-03-20T17:40:46.803923Z] Loop 1196: Loss: 5.16e-03, Avg Return: 0.466, Regret: 0.3931, Entropy: 0.2055 +[2026-03-20T17:40:47.658176Z] Loop 1197: Loss: 5.41e-03, Avg Return: 0.474, Regret: 0.3931, Entropy: 0.2171 +[2026-03-20T17:40:48.511375Z] Loop 1198: Loss: 5.48e-03, Avg Return: 0.476, Regret: 0.3931, Entropy: 0.2221 +[2026-03-20T17:40:49.363821Z] Loop 1199: Loss: 5.84e-03, Avg Return: 0.479, Regret: 0.3931, Entropy: 0.2396 +[2026-03-20T17:40:50.256071Z] Loop 1200: Loss: 6.46e-03, Avg Return: 0.479, Regret: 0.3863, Entropy: 0.2616 +[2026-03-20T17:40:51.109367Z] Loop 1201: Loss: 6.83e-03, Avg Return: 0.474, Regret: 0.3863, Entropy: 0.2810 +[2026-03-20T17:40:51.962601Z] Loop 1202: Loss: 7.79e-03, Avg Return: 0.472, Regret: 0.3863, Entropy: 0.2908 +[2026-03-20T17:40:52.814863Z] Loop 1203: Loss: 8.25e-03, Avg Return: 0.463, Regret: 0.3863, Entropy: 0.2926 +[2026-03-20T17:40:53.666691Z] Loop 1204: Loss: 7.82e-03, Avg Return: 0.472, Regret: 0.3863, Entropy: 0.2876 +[2026-03-20T17:40:54.558605Z] Loop 1205: Loss: 7.85e-03, Avg Return: 0.480, Regret: 0.3882, Entropy: 0.2815 +[2026-03-20T17:40:55.410785Z] Loop 1206: Loss: 5.98e-03, Avg Return: 0.471, Regret: 0.3882, Entropy: 0.2664 +[2026-03-20T17:40:56.263605Z] Loop 1207: Loss: 5.42e-03, Avg Return: 0.473, Regret: 0.3882, Entropy: 0.2463 +[2026-03-20T17:40:57.115713Z] Loop 1208: Loss: 5.23e-03, Avg Return: 0.477, Regret: 0.3882, Entropy: 0.2202 +[2026-03-20T17:40:57.968246Z] Loop 1209: Loss: 4.94e-03, Avg Return: 0.472, Regret: 0.3882, Entropy: 0.1918 +[2026-03-20T17:40:58.860754Z] Loop 1210: Loss: 4.77e-03, Avg Return: 0.471, Regret: 0.3971, Entropy: 0.1763 +[2026-03-20T17:40:59.713337Z] Loop 1211: Loss: 4.57e-03, Avg Return: 0.459, Regret: 0.3971, Entropy: 0.1727 +[2026-03-20T17:41:00.566372Z] Loop 1212: Loss: 4.65e-03, Avg Return: 0.471, Regret: 0.3971, Entropy: 0.1750 +[2026-03-20T17:41:01.420042Z] Loop 1213: Loss: 4.01e-03, Avg Return: 0.472, Regret: 0.3971, Entropy: 0.1840 +[2026-03-20T17:41:02.272765Z] Loop 1214: Loss: 4.40e-03, Avg Return: 0.468, Regret: 0.3971, Entropy: 0.1946 +[2026-03-20T17:41:03.164941Z] Loop 1215: Loss: 4.78e-03, Avg Return: 0.472, Regret: 0.3895, Entropy: 0.2080 +[2026-03-20T17:41:04.018707Z] Loop 1216: Loss: 5.16e-03, Avg Return: 0.476, Regret: 0.3895, Entropy: 0.2245 +[2026-03-20T17:41:04.871261Z] Loop 1217: Loss: 4.72e-03, Avg Return: 0.470, Regret: 0.3895, Entropy: 0.2348 +[2026-03-20T17:41:05.724090Z] Loop 1218: Loss: 6.46e-03, Avg Return: 0.480, Regret: 0.3895, Entropy: 0.2395 +[2026-03-20T17:41:06.576424Z] Loop 1219: Loss: 7.17e-03, Avg Return: 0.481, Regret: 0.3895, Entropy: 0.2525 +[2026-03-20T17:41:07.468364Z] Loop 1220: Loss: 6.94e-03, Avg Return: 0.467, Regret: 0.3933, Entropy: 0.2591 +[2026-03-20T17:41:08.321818Z] Loop 1221: Loss: 7.79e-03, Avg Return: 0.478, Regret: 0.3933, Entropy: 0.2551 +[2026-03-20T17:41:09.174247Z] Loop 1222: Loss: 7.45e-03, Avg Return: 0.475, Regret: 0.3933, Entropy: 0.2495 +[2026-03-20T17:41:10.027206Z] Loop 1223: Loss: 7.00e-03, Avg Return: 0.477, Regret: 0.3933, Entropy: 0.2434 +[2026-03-20T17:41:10.879391Z] Loop 1224: Loss: 5.52e-03, Avg Return: 0.481, Regret: 0.3933, Entropy: 0.2236 +[2026-03-20T17:41:11.772791Z] Loop 1225: Loss: 5.41e-03, Avg Return: 0.479, Regret: 0.3833, Entropy: 0.2256 +[2026-03-20T17:41:12.625434Z] Loop 1226: Loss: 4.96e-03, Avg Return: 0.479, Regret: 0.3833, Entropy: 0.2180 +[2026-03-20T17:41:13.478405Z] Loop 1227: Loss: 4.45e-03, Avg Return: 0.476, Regret: 0.3833, Entropy: 0.2192 +[2026-03-20T17:41:14.331529Z] Loop 1228: Loss: 4.66e-03, Avg Return: 0.483, Regret: 0.3833, Entropy: 0.2062 +[2026-03-20T17:41:15.185008Z] Loop 1229: Loss: 5.22e-03, Avg Return: 0.488, Regret: 0.3833, Entropy: 0.2021 +[2026-03-20T17:41:16.078055Z] Loop 1230: Loss: 5.03e-03, Avg Return: 0.475, Regret: 0.3864, Entropy: 0.1899 +[2026-03-20T17:41:16.930139Z] Loop 1231: Loss: 4.88e-03, Avg Return: 0.482, Regret: 0.3864, Entropy: 0.1940 +[2026-03-20T17:41:17.783344Z] Loop 1232: Loss: 4.63e-03, Avg Return: 0.478, Regret: 0.3864, Entropy: 0.1866 +[2026-03-20T17:41:18.636350Z] Loop 1233: Loss: 5.12e-03, Avg Return: 0.475, Regret: 0.3864, Entropy: 0.1953 +[2026-03-20T17:41:19.489292Z] Loop 1234: Loss: 4.56e-03, Avg Return: 0.479, Regret: 0.3864, Entropy: 0.1988 +[2026-03-20T17:41:20.383259Z] Loop 1235: Loss: 4.58e-03, Avg Return: 0.481, Regret: 0.3830, Entropy: 0.1999 +[2026-03-20T17:41:21.235862Z] Loop 1236: Loss: 5.02e-03, Avg Return: 0.478, Regret: 0.3830, Entropy: 0.2061 +[2026-03-20T17:41:22.089153Z] Loop 1237: Loss: 5.12e-03, Avg Return: 0.484, Regret: 0.3830, Entropy: 0.2128 +[2026-03-20T17:41:22.942187Z] Loop 1238: Loss: 4.89e-03, Avg Return: 0.472, Regret: 0.3830, Entropy: 0.2085 +[2026-03-20T17:41:23.795569Z] Loop 1239: Loss: 5.41e-03, Avg Return: 0.482, Regret: 0.3830, Entropy: 0.2122 +[2026-03-20T17:41:24.688057Z] Loop 1240: Loss: 5.58e-03, Avg Return: 0.491, Regret: 0.3826, Entropy: 0.2130 +[2026-03-20T17:41:25.540595Z] Loop 1241: Loss: 5.31e-03, Avg Return: 0.484, Regret: 0.3826, Entropy: 0.2106 +[2026-03-20T17:41:26.393961Z] Loop 1242: Loss: 6.00e-03, Avg Return: 0.482, Regret: 0.3826, Entropy: 0.2186 +[2026-03-20T17:41:27.248292Z] Loop 1243: Loss: 5.46e-03, Avg Return: 0.480, Regret: 0.3826, Entropy: 0.2222 +[2026-03-20T17:41:28.101948Z] Loop 1244: Loss: 5.16e-03, Avg Return: 0.475, Regret: 0.3826, Entropy: 0.2230 +[2026-03-20T17:41:28.995335Z] Loop 1245: Loss: 5.79e-03, Avg Return: 0.482, Regret: 0.3824, Entropy: 0.2141 +[2026-03-20T17:41:29.848982Z] Loop 1246: Loss: 5.26e-03, Avg Return: 0.479, Regret: 0.3824, Entropy: 0.2073 +[2026-03-20T17:41:30.703647Z] Loop 1247: Loss: 5.14e-03, Avg Return: 0.478, Regret: 0.3824, Entropy: 0.2025 +[2026-03-20T17:41:31.558155Z] Loop 1248: Loss: 5.23e-03, Avg Return: 0.482, Regret: 0.3824, Entropy: 0.2062 +[2026-03-20T17:41:32.410877Z] Loop 1249: Loss: 5.08e-03, Avg Return: 0.484, Regret: 0.3824, Entropy: 0.2040 +[2026-03-20T17:41:33.305098Z] Loop 1250: Loss: 5.08e-03, Avg Return: 0.480, Regret: 0.3817, Entropy: 0.2094 +[2026-03-20T17:41:34.158450Z] Loop 1251: Loss: 5.46e-03, Avg Return: 0.482, Regret: 0.3817, Entropy: 0.2091 +[2026-03-20T17:41:35.012781Z] Loop 1252: Loss: 4.86e-03, Avg Return: 0.481, Regret: 0.3817, Entropy: 0.2067 +[2026-03-20T17:41:35.866085Z] Loop 1253: Loss: 5.46e-03, Avg Return: 0.484, Regret: 0.3817, Entropy: 0.2005 +[2026-03-20T17:41:36.719916Z] Loop 1254: Loss: 5.07e-03, Avg Return: 0.480, Regret: 0.3817, Entropy: 0.2044 +[2026-03-20T17:41:37.614645Z] Loop 1255: Loss: 5.81e-03, Avg Return: 0.477, Regret: 0.3812, Entropy: 0.2042 +[2026-03-20T17:41:38.469137Z] Loop 1256: Loss: 5.63e-03, Avg Return: 0.481, Regret: 0.3812, Entropy: 0.2045 +[2026-03-20T17:41:39.323221Z] Loop 1257: Loss: 5.90e-03, Avg Return: 0.479, Regret: 0.3812, Entropy: 0.2041 +[2026-03-20T17:41:40.176643Z] Loop 1258: Loss: 5.72e-03, Avg Return: 0.472, Regret: 0.3812, Entropy: 0.2119 +[2026-03-20T17:41:41.030144Z] Loop 1259: Loss: 6.00e-03, Avg Return: 0.479, Regret: 0.3812, Entropy: 0.2116 +[2026-03-20T17:41:41.923903Z] Loop 1260: Loss: 6.06e-03, Avg Return: 0.482, Regret: 0.3857, Entropy: 0.2010 +[2026-03-20T17:41:42.777334Z] Loop 1261: Loss: 5.94e-03, Avg Return: 0.483, Regret: 0.3857, Entropy: 0.2015 +[2026-03-20T17:41:43.631018Z] Loop 1262: Loss: 5.44e-03, Avg Return: 0.476, Regret: 0.3857, Entropy: 0.1959 +[2026-03-20T17:41:44.483107Z] Loop 1263: Loss: 5.20e-03, Avg Return: 0.483, Regret: 0.3857, Entropy: 0.1955 +[2026-03-20T17:41:45.336205Z] Loop 1264: Loss: 4.49e-03, Avg Return: 0.490, Regret: 0.3857, Entropy: 0.1874 +[2026-03-20T17:41:46.230735Z] Loop 1265: Loss: 4.52e-03, Avg Return: 0.478, Regret: 0.3812, Entropy: 0.1810 +[2026-03-20T17:41:47.083902Z] Loop 1266: Loss: 4.50e-03, Avg Return: 0.486, Regret: 0.3812, Entropy: 0.1885 +[2026-03-20T17:41:47.937735Z] Loop 1267: Loss: 4.10e-03, Avg Return: 0.474, Regret: 0.3812, Entropy: 0.1977 +[2026-03-20T17:41:48.790802Z] Loop 1268: Loss: 3.73e-03, Avg Return: 0.484, Regret: 0.3812, Entropy: 0.1773 +[2026-03-20T17:41:49.644313Z] Loop 1269: Loss: 3.59e-03, Avg Return: 0.479, Regret: 0.3812, Entropy: 0.1555 +[2026-03-20T17:41:50.538280Z] Loop 1270: Loss: 3.74e-03, Avg Return: 0.471, Regret: 0.3935, Entropy: 0.1438 +[2026-03-20T17:41:51.391624Z] Loop 1271: Loss: 4.75e-03, Avg Return: 0.463, Regret: 0.3935, Entropy: 0.1505 +[2026-03-20T17:41:52.246879Z] Loop 1272: Loss: 4.74e-03, Avg Return: 0.453, Regret: 0.3935, Entropy: 0.1480 +[2026-03-20T17:41:53.100034Z] Loop 1273: Loss: 4.57e-03, Avg Return: 0.476, Regret: 0.3935, Entropy: 0.1483 +[2026-03-20T17:41:53.953597Z] Loop 1274: Loss: 3.57e-03, Avg Return: 0.480, Regret: 0.3935, Entropy: 0.1578 +[2026-03-20T17:41:54.847413Z] Loop 1275: Loss: 3.77e-03, Avg Return: 0.489, Regret: 0.3855, Entropy: 0.1691 +[2026-03-20T17:41:55.701487Z] Loop 1276: Loss: 4.04e-03, Avg Return: 0.477, Regret: 0.3855, Entropy: 0.1847 +[2026-03-20T17:41:56.555221Z] Loop 1277: Loss: 4.43e-03, Avg Return: 0.485, Regret: 0.3855, Entropy: 0.1926 +[2026-03-20T17:41:57.408527Z] Loop 1278: Loss: 4.60e-03, Avg Return: 0.484, Regret: 0.3855, Entropy: 0.1826 +[2026-03-20T17:41:58.261805Z] Loop 1279: Loss: 4.57e-03, Avg Return: 0.483, Regret: 0.3855, Entropy: 0.1841 +[2026-03-20T17:41:59.156880Z] Loop 1280: Loss: 5.40e-03, Avg Return: 0.479, Regret: 0.3814, Entropy: 0.1974 +[2026-03-20T17:42:00.009013Z] Loop 1281: Loss: 5.59e-03, Avg Return: 0.474, Regret: 0.3814, Entropy: 0.2064 +[2026-03-20T17:42:00.861450Z] Loop 1282: Loss: 6.62e-03, Avg Return: 0.473, Regret: 0.3814, Entropy: 0.2088 +[2026-03-20T17:42:01.713938Z] Loop 1283: Loss: 5.52e-03, Avg Return: 0.479, Regret: 0.3814, Entropy: 0.2087 +[2026-03-20T17:42:02.568120Z] Loop 1284: Loss: 5.13e-03, Avg Return: 0.481, Regret: 0.3814, Entropy: 0.1997 +[2026-03-20T17:42:03.462080Z] Loop 1285: Loss: 4.96e-03, Avg Return: 0.485, Regret: 0.3808, Entropy: 0.1917 +[2026-03-20T17:42:04.314927Z] Loop 1286: Loss: 5.07e-03, Avg Return: 0.479, Regret: 0.3808, Entropy: 0.1868 +[2026-03-20T17:42:05.168153Z] Loop 1287: Loss: 4.46e-03, Avg Return: 0.474, Regret: 0.3808, Entropy: 0.1811 +[2026-03-20T17:42:06.023176Z] Loop 1288: Loss: 4.60e-03, Avg Return: 0.487, Regret: 0.3808, Entropy: 0.1790 +[2026-03-20T17:42:06.875901Z] Loop 1289: Loss: 4.38e-03, Avg Return: 0.489, Regret: 0.3808, Entropy: 0.1765 +[2026-03-20T17:42:07.770573Z] Loop 1290: Loss: 4.55e-03, Avg Return: 0.491, Regret: 0.3810, Entropy: 0.1796 +[2026-03-20T17:42:08.624591Z] Loop 1291: Loss: 4.00e-03, Avg Return: 0.479, Regret: 0.3810, Entropy: 0.1814 +[2026-03-20T17:42:09.478962Z] Loop 1292: Loss: 3.21e-03, Avg Return: 0.483, Regret: 0.3810, Entropy: 0.1760 +[2026-03-20T17:42:10.332806Z] Loop 1293: Loss: 3.01e-03, Avg Return: 0.475, Regret: 0.3810, Entropy: 0.1464 +[2026-03-20T17:42:11.185267Z] Loop 1294: Loss: 2.88e-03, Avg Return: 0.469, Regret: 0.3810, Entropy: 0.1412 +[2026-03-20T17:42:12.076541Z] Loop 1295: Loss: 3.24e-03, Avg Return: 0.469, Regret: 0.3952, Entropy: 0.1313 +[2026-03-20T17:42:12.930180Z] Loop 1296: Loss: 3.14e-03, Avg Return: 0.474, Regret: 0.3952, Entropy: 0.1323 +[2026-03-20T17:42:13.783309Z] Loop 1297: Loss: 3.29e-03, Avg Return: 0.464, Regret: 0.3952, Entropy: 0.1349 +[2026-03-20T17:42:14.637152Z] Loop 1298: Loss: 2.86e-03, Avg Return: 0.477, Regret: 0.3952, Entropy: 0.1489 +[2026-03-20T17:42:15.490455Z] Loop 1299: Loss: 2.95e-03, Avg Return: 0.479, Regret: 0.3952, Entropy: 0.1641 +[2026-03-20T17:42:16.386165Z] Loop 1300: Loss: 4.06e-03, Avg Return: 0.491, Regret: 0.3807, Entropy: 0.1702 +[2026-03-20T17:42:17.239545Z] Loop 1301: Loss: 4.22e-03, Avg Return: 0.490, Regret: 0.3807, Entropy: 0.1716 +[2026-03-20T17:42:18.092565Z] Loop 1302: Loss: 4.12e-03, Avg Return: 0.484, Regret: 0.3807, Entropy: 0.1610 +[2026-03-20T17:42:18.946897Z] Loop 1303: Loss: 3.76e-03, Avg Return: 0.484, Regret: 0.3807, Entropy: 0.1583 +[2026-03-20T17:42:19.799486Z] Loop 1304: Loss: 4.11e-03, Avg Return: 0.486, Regret: 0.3807, Entropy: 0.1637 +[2026-03-20T17:42:20.694085Z] Loop 1305: Loss: 4.01e-03, Avg Return: 0.478, Regret: 0.3792, Entropy: 0.1576 +[2026-03-20T17:42:21.547715Z] Loop 1306: Loss: 4.07e-03, Avg Return: 0.485, Regret: 0.3792, Entropy: 0.1606 +[2026-03-20T17:42:22.403063Z] Loop 1307: Loss: 3.91e-03, Avg Return: 0.484, Regret: 0.3792, Entropy: 0.1573 +[2026-03-20T17:42:23.256241Z] Loop 1308: Loss: 3.76e-03, Avg Return: 0.474, Regret: 0.3792, Entropy: 0.1595 +[2026-03-20T17:42:24.109019Z] Loop 1309: Loss: 4.01e-03, Avg Return: 0.485, Regret: 0.3792, Entropy: 0.1557 +[2026-03-20T17:42:25.003892Z] Loop 1310: Loss: 4.15e-03, Avg Return: 0.485, Regret: 0.3802, Entropy: 0.1602 +[2026-03-20T17:42:25.858271Z] Loop 1311: Loss: 3.85e-03, Avg Return: 0.486, Regret: 0.3802, Entropy: 0.1585 +[2026-03-20T17:42:26.711535Z] Loop 1312: Loss: 3.87e-03, Avg Return: 0.481, Regret: 0.3802, Entropy: 0.1621 +[2026-03-20T17:42:27.564265Z] Loop 1313: Loss: 3.89e-03, Avg Return: 0.483, Regret: 0.3802, Entropy: 0.1560 +[2026-03-20T17:42:28.417902Z] Loop 1314: Loss: 3.81e-03, Avg Return: 0.489, Regret: 0.3802, Entropy: 0.1540 +[2026-03-20T17:42:29.312793Z] Loop 1315: Loss: 3.95e-03, Avg Return: 0.489, Regret: 0.3793, Entropy: 0.1592 +[2026-03-20T17:42:30.166998Z] Loop 1316: Loss: 3.97e-03, Avg Return: 0.490, Regret: 0.3793, Entropy: 0.1519 +[2026-03-20T17:42:31.020527Z] Loop 1317: Loss: 4.19e-03, Avg Return: 0.483, Regret: 0.3793, Entropy: 0.1605 +[2026-03-20T17:42:31.872642Z] Loop 1318: Loss: 3.96e-03, Avg Return: 0.484, Regret: 0.3793, Entropy: 0.1542 +[2026-03-20T17:42:32.724948Z] Loop 1319: Loss: 4.08e-03, Avg Return: 0.486, Regret: 0.3793, Entropy: 0.1600 +[2026-03-20T17:42:33.618976Z] Loop 1320: Loss: 4.49e-03, Avg Return: 0.490, Regret: 0.3788, Entropy: 0.1609 +[2026-03-20T17:42:34.471807Z] Loop 1321: Loss: 4.48e-03, Avg Return: 0.482, Regret: 0.3788, Entropy: 0.1585 +[2026-03-20T17:42:35.324818Z] Loop 1322: Loss: 4.02e-03, Avg Return: 0.487, Regret: 0.3788, Entropy: 0.1679 +[2026-03-20T17:42:36.176989Z] Loop 1323: Loss: 4.29e-03, Avg Return: 0.473, Regret: 0.3788, Entropy: 0.1683 +[2026-03-20T17:42:37.029782Z] Loop 1324: Loss: 5.03e-03, Avg Return: 0.482, Regret: 0.3788, Entropy: 0.1755 +[2026-03-20T17:42:37.922963Z] Loop 1325: Loss: 5.34e-03, Avg Return: 0.484, Regret: 0.3830, Entropy: 0.1830 +[2026-03-20T17:42:38.776496Z] Loop 1326: Loss: 5.51e-03, Avg Return: 0.475, Regret: 0.3830, Entropy: 0.1839 +[2026-03-20T17:42:39.628316Z] Loop 1327: Loss: 5.92e-03, Avg Return: 0.473, Regret: 0.3830, Entropy: 0.1909 +[2026-03-20T17:42:40.480575Z] Loop 1328: Loss: 5.38e-03, Avg Return: 0.474, Regret: 0.3830, Entropy: 0.1893 +[2026-03-20T17:42:41.333822Z] Loop 1329: Loss: 5.39e-03, Avg Return: 0.480, Regret: 0.3830, Entropy: 0.1845 +[2026-03-20T17:42:42.228840Z] Loop 1330: Loss: 5.71e-03, Avg Return: 0.475, Regret: 0.3831, Entropy: 0.1893 +[2026-03-20T17:42:43.084046Z] Loop 1331: Loss: 4.93e-03, Avg Return: 0.477, Regret: 0.3831, Entropy: 0.1775 +[2026-03-20T17:42:43.938369Z] Loop 1332: Loss: 4.83e-03, Avg Return: 0.490, Regret: 0.3831, Entropy: 0.1770 +[2026-03-20T17:42:44.792148Z] Loop 1333: Loss: 4.68e-03, Avg Return: 0.483, Regret: 0.3831, Entropy: 0.1662 +[2026-03-20T17:42:45.646528Z] Loop 1334: Loss: 4.05e-03, Avg Return: 0.485, Regret: 0.3831, Entropy: 0.1690 +[2026-03-20T17:42:46.540974Z] Loop 1335: Loss: 3.70e-03, Avg Return: 0.479, Regret: 0.3788, Entropy: 0.1654 +[2026-03-20T17:42:47.394450Z] Loop 1336: Loss: 3.66e-03, Avg Return: 0.480, Regret: 0.3788, Entropy: 0.1636 +[2026-03-20T17:42:48.248007Z] Loop 1337: Loss: 4.16e-03, Avg Return: 0.483, Regret: 0.3788, Entropy: 0.1565 +[2026-03-20T17:42:49.102650Z] Loop 1338: Loss: 3.68e-03, Avg Return: 0.477, Regret: 0.3788, Entropy: 0.1567 +[2026-03-20T17:42:49.957621Z] Loop 1339: Loss: 3.70e-03, Avg Return: 0.489, Regret: 0.3788, Entropy: 0.1570 +[2026-03-20T17:42:50.853298Z] Loop 1340: Loss: 3.92e-03, Avg Return: 0.485, Regret: 0.3789, Entropy: 0.1567 +[2026-03-20T17:42:51.705453Z] Loop 1341: Loss: 3.75e-03, Avg Return: 0.479, Regret: 0.3789, Entropy: 0.1641 +[2026-03-20T17:42:52.557246Z] Loop 1342: Loss: 3.85e-03, Avg Return: 0.486, Regret: 0.3789, Entropy: 0.1569 +[2026-03-20T17:42:53.410034Z] Loop 1343: Loss: 3.77e-03, Avg Return: 0.482, Regret: 0.3789, Entropy: 0.1547 +[2026-03-20T17:42:54.262471Z] Loop 1344: Loss: 4.12e-03, Avg Return: 0.484, Regret: 0.3789, Entropy: 0.1558 +[2026-03-20T17:42:55.160299Z] Loop 1345: Loss: 3.69e-03, Avg Return: 0.486, Regret: 0.3806, Entropy: 0.1599 +[2026-03-20T17:42:56.012478Z] Loop 1346: Loss: 3.55e-03, Avg Return: 0.476, Regret: 0.3806, Entropy: 0.1729 +[2026-03-20T17:42:56.865460Z] Loop 1347: Loss: 3.47e-03, Avg Return: 0.479, Regret: 0.3806, Entropy: 0.1709 +[2026-03-20T17:42:57.717710Z] Loop 1348: Loss: 3.54e-03, Avg Return: 0.481, Regret: 0.3806, Entropy: 0.1714 +[2026-03-20T17:42:58.570452Z] Loop 1349: Loss: 3.53e-03, Avg Return: 0.480, Regret: 0.3806, Entropy: 0.1776 +[2026-03-20T17:42:59.462346Z] Loop 1350: Loss: 4.05e-03, Avg Return: 0.481, Regret: 0.3810, Entropy: 0.1750 +[2026-03-20T17:43:00.315646Z] Loop 1351: Loss: 3.85e-03, Avg Return: 0.485, Regret: 0.3810, Entropy: 0.1667 +[2026-03-20T17:43:01.168301Z] Loop 1352: Loss: 3.74e-03, Avg Return: 0.476, Regret: 0.3810, Entropy: 0.1668 +[2026-03-20T17:43:02.021275Z] Loop 1353: Loss: 3.63e-03, Avg Return: 0.483, Regret: 0.3810, Entropy: 0.1721 +[2026-03-20T17:43:02.873891Z] Loop 1354: Loss: 4.08e-03, Avg Return: 0.486, Regret: 0.3810, Entropy: 0.1708 +[2026-03-20T17:43:03.766968Z] Loop 1355: Loss: 3.93e-03, Avg Return: 0.480, Regret: 0.3786, Entropy: 0.1650 +[2026-03-20T17:43:04.618635Z] Loop 1356: Loss: 4.31e-03, Avg Return: 0.484, Regret: 0.3786, Entropy: 0.1689 +[2026-03-20T17:43:05.471491Z] Loop 1357: Loss: 3.98e-03, Avg Return: 0.484, Regret: 0.3786, Entropy: 0.1628 +[2026-03-20T17:43:06.323614Z] Loop 1358: Loss: 4.25e-03, Avg Return: 0.485, Regret: 0.3786, Entropy: 0.1710 +[2026-03-20T17:43:07.176022Z] Loop 1359: Loss: 4.55e-03, Avg Return: 0.490, Regret: 0.3786, Entropy: 0.1713 +[2026-03-20T17:43:08.069552Z] Loop 1360: Loss: 4.16e-03, Avg Return: 0.483, Regret: 0.3779, Entropy: 0.1714 +[2026-03-20T17:43:08.922935Z] Loop 1361: Loss: 4.68e-03, Avg Return: 0.490, Regret: 0.3779, Entropy: 0.1731 +[2026-03-20T17:43:09.776079Z] Loop 1362: Loss: 4.95e-03, Avg Return: 0.486, Regret: 0.3779, Entropy: 0.1771 +[2026-03-20T17:43:10.629181Z] Loop 1363: Loss: 5.06e-03, Avg Return: 0.480, Regret: 0.3779, Entropy: 0.1831 +[2026-03-20T17:43:11.481953Z] Loop 1364: Loss: 4.96e-03, Avg Return: 0.484, Regret: 0.3779, Entropy: 0.1861 +[2026-03-20T17:43:12.375542Z] Loop 1365: Loss: 5.01e-03, Avg Return: 0.479, Regret: 0.3800, Entropy: 0.1785 +[2026-03-20T17:43:13.228156Z] Loop 1366: Loss: 4.67e-03, Avg Return: 0.481, Regret: 0.3800, Entropy: 0.1844 +[2026-03-20T17:43:14.081404Z] Loop 1367: Loss: 4.86e-03, Avg Return: 0.483, Regret: 0.3800, Entropy: 0.1737 +[2026-03-20T17:43:14.934757Z] Loop 1368: Loss: 4.04e-03, Avg Return: 0.485, Regret: 0.3800, Entropy: 0.1756 +[2026-03-20T17:43:15.788477Z] Loop 1369: Loss: 4.21e-03, Avg Return: 0.484, Regret: 0.3800, Entropy: 0.1681 +[2026-03-20T17:43:16.681672Z] Loop 1370: Loss: 3.89e-03, Avg Return: 0.485, Regret: 0.3775, Entropy: 0.1699 +[2026-03-20T17:43:17.534332Z] Loop 1371: Loss: 3.68e-03, Avg Return: 0.486, Regret: 0.3775, Entropy: 0.1656 +[2026-03-20T17:43:18.387983Z] Loop 1372: Loss: 4.02e-03, Avg Return: 0.490, Regret: 0.3775, Entropy: 0.1664 +[2026-03-20T17:43:19.240576Z] Loop 1373: Loss: 3.71e-03, Avg Return: 0.480, Regret: 0.3775, Entropy: 0.1671 +[2026-03-20T17:43:20.092271Z] Loop 1374: Loss: 4.30e-03, Avg Return: 0.482, Regret: 0.3775, Entropy: 0.1640 +[2026-03-20T17:43:20.985883Z] Loop 1375: Loss: 4.13e-03, Avg Return: 0.481, Regret: 0.3781, Entropy: 0.1667 +[2026-03-20T17:43:21.839581Z] Loop 1376: Loss: 4.01e-03, Avg Return: 0.487, Regret: 0.3781, Entropy: 0.1703 +[2026-03-20T17:43:22.691623Z] Loop 1377: Loss: 3.85e-03, Avg Return: 0.484, Regret: 0.3781, Entropy: 0.1663 +[2026-03-20T17:43:23.543097Z] Loop 1378: Loss: 4.26e-03, Avg Return: 0.489, Regret: 0.3781, Entropy: 0.1568 +[2026-03-20T17:43:24.395186Z] Loop 1379: Loss: 3.87e-03, Avg Return: 0.489, Regret: 0.3781, Entropy: 0.1661 +[2026-03-20T17:43:25.289913Z] Loop 1380: Loss: 4.16e-03, Avg Return: 0.484, Regret: 0.3785, Entropy: 0.1563 +[2026-03-20T17:43:26.143198Z] Loop 1381: Loss: 3.87e-03, Avg Return: 0.486, Regret: 0.3785, Entropy: 0.1627 +[2026-03-20T17:43:26.995174Z] Loop 1382: Loss: 3.36e-03, Avg Return: 0.483, Regret: 0.3785, Entropy: 0.1650 +[2026-03-20T17:43:27.848139Z] Loop 1383: Loss: 3.72e-03, Avg Return: 0.489, Regret: 0.3785, Entropy: 0.1680 +[2026-03-20T17:43:28.701745Z] Loop 1384: Loss: 3.84e-03, Avg Return: 0.483, Regret: 0.3785, Entropy: 0.1641 +[2026-03-20T17:43:29.598889Z] Loop 1385: Loss: 3.65e-03, Avg Return: 0.481, Regret: 0.3784, Entropy: 0.1660 +[2026-03-20T17:43:30.452046Z] Loop 1386: Loss: 4.06e-03, Avg Return: 0.486, Regret: 0.3784, Entropy: 0.1605 +[2026-03-20T17:43:31.305132Z] Loop 1387: Loss: 4.10e-03, Avg Return: 0.493, Regret: 0.3784, Entropy: 0.1580 +[2026-03-20T17:43:32.158322Z] Loop 1388: Loss: 3.87e-03, Avg Return: 0.482, Regret: 0.3784, Entropy: 0.1541 +[2026-03-20T17:43:33.012598Z] Loop 1389: Loss: 3.41e-03, Avg Return: 0.480, Regret: 0.3784, Entropy: 0.1586 +[2026-03-20T17:43:33.905950Z] Loop 1390: Loss: 4.27e-03, Avg Return: 0.490, Regret: 0.3774, Entropy: 0.1608 +[2026-03-20T17:43:34.758420Z] Loop 1391: Loss: 4.43e-03, Avg Return: 0.482, Regret: 0.3774, Entropy: 0.1717 +[2026-03-20T17:43:35.611630Z] Loop 1392: Loss: 4.56e-03, Avg Return: 0.486, Regret: 0.3774, Entropy: 0.1688 +[2026-03-20T17:43:36.465061Z] Loop 1393: Loss: 5.09e-03, Avg Return: 0.484, Regret: 0.3774, Entropy: 0.1733 +[2026-03-20T17:43:37.318370Z] Loop 1394: Loss: 5.18e-03, Avg Return: 0.483, Regret: 0.3774, Entropy: 0.1812 +[2026-03-20T17:43:38.211946Z] Loop 1395: Loss: 5.04e-03, Avg Return: 0.482, Regret: 0.3788, Entropy: 0.1753 +[2026-03-20T17:43:39.064598Z] Loop 1396: Loss: 5.24e-03, Avg Return: 0.485, Regret: 0.3788, Entropy: 0.1825 +[2026-03-20T17:43:39.917158Z] Loop 1397: Loss: 6.24e-03, Avg Return: 0.485, Regret: 0.3788, Entropy: 0.1842 +[2026-03-20T17:43:40.770130Z] Loop 1398: Loss: 6.39e-03, Avg Return: 0.486, Regret: 0.3788, Entropy: 0.1962 +[2026-03-20T17:43:41.622790Z] Loop 1399: Loss: 6.48e-03, Avg Return: 0.481, Regret: 0.3788, Entropy: 0.1903 +[2026-03-20T17:43:42.517281Z] Loop 1400: Loss: 6.36e-03, Avg Return: 0.477, Regret: 0.3823, Entropy: 0.1971 +[2026-03-20T17:43:43.368908Z] Loop 1401: Loss: 6.72e-03, Avg Return: 0.479, Regret: 0.3823, Entropy: 0.1915 +[2026-03-20T17:43:44.221150Z] Loop 1402: Loss: 5.97e-03, Avg Return: 0.481, Regret: 0.3823, Entropy: 0.1854 +[2026-03-20T17:43:45.074033Z] Loop 1403: Loss: 5.58e-03, Avg Return: 0.487, Regret: 0.3823, Entropy: 0.1781 +[2026-03-20T17:43:45.927211Z] Loop 1404: Loss: 4.89e-03, Avg Return: 0.486, Regret: 0.3823, Entropy: 0.1757 +[2026-03-20T17:43:46.819217Z] Loop 1405: Loss: 4.29e-03, Avg Return: 0.482, Regret: 0.3776, Entropy: 0.1704 +[2026-03-20T17:43:47.671424Z] Loop 1406: Loss: 4.25e-03, Avg Return: 0.482, Regret: 0.3776, Entropy: 0.1639 +[2026-03-20T17:43:48.523726Z] Loop 1407: Loss: 3.94e-03, Avg Return: 0.490, Regret: 0.3776, Entropy: 0.1613 +[2026-03-20T17:43:49.376390Z] Loop 1408: Loss: 3.83e-03, Avg Return: 0.486, Regret: 0.3776, Entropy: 0.1571 +[2026-03-20T17:43:50.228849Z] Loop 1409: Loss: 3.86e-03, Avg Return: 0.489, Regret: 0.3776, Entropy: 0.1622 +[2026-03-20T17:43:51.122022Z] Loop 1410: Loss: 3.97e-03, Avg Return: 0.489, Regret: 0.3777, Entropy: 0.1599 +[2026-03-20T17:43:51.975841Z] Loop 1411: Loss: 3.56e-03, Avg Return: 0.488, Regret: 0.3777, Entropy: 0.1525 +[2026-03-20T17:43:52.829491Z] Loop 1412: Loss: 3.26e-03, Avg Return: 0.486, Regret: 0.3777, Entropy: 0.1530 +[2026-03-20T17:43:53.683251Z] Loop 1413: Loss: 3.25e-03, Avg Return: 0.488, Regret: 0.3777, Entropy: 0.1472 +[2026-03-20T17:43:54.536150Z] Loop 1414: Loss: 3.07e-03, Avg Return: 0.481, Regret: 0.3777, Entropy: 0.1514 +[2026-03-20T17:43:55.429912Z] Loop 1415: Loss: 3.15e-03, Avg Return: 0.487, Regret: 0.3787, Entropy: 0.1511 +[2026-03-20T17:43:56.283123Z] Loop 1416: Loss: 3.26e-03, Avg Return: 0.490, Regret: 0.3787, Entropy: 0.1495 +[2026-03-20T17:43:57.136246Z] Loop 1417: Loss: 3.13e-03, Avg Return: 0.489, Regret: 0.3787, Entropy: 0.1491 +[2026-03-20T17:43:57.989655Z] Loop 1418: Loss: 3.29e-03, Avg Return: 0.485, Regret: 0.3787, Entropy: 0.1416 +[2026-03-20T17:43:58.843979Z] Loop 1419: Loss: 3.49e-03, Avg Return: 0.487, Regret: 0.3787, Entropy: 0.1425 +[2026-03-20T17:43:59.736449Z] Loop 1420: Loss: 3.65e-03, Avg Return: 0.483, Regret: 0.3778, Entropy: 0.1510 +[2026-03-20T17:44:00.589626Z] Loop 1421: Loss: 3.53e-03, Avg Return: 0.488, Regret: 0.3778, Entropy: 0.1499 +[2026-03-20T17:44:01.442926Z] Loop 1422: Loss: 2.98e-03, Avg Return: 0.483, Regret: 0.3778, Entropy: 0.1517 +[2026-03-20T17:44:02.296926Z] Loop 1423: Loss: 3.68e-03, Avg Return: 0.485, Regret: 0.3778, Entropy: 0.1540 +[2026-03-20T17:44:03.149807Z] Loop 1424: Loss: 4.15e-03, Avg Return: 0.482, Regret: 0.3778, Entropy: 0.1620 +[2026-03-20T17:44:04.044821Z] Loop 1425: Loss: 4.55e-03, Avg Return: 0.488, Regret: 0.3776, Entropy: 0.1629 +[2026-03-20T17:44:04.899110Z] Loop 1426: Loss: 4.54e-03, Avg Return: 0.490, Regret: 0.3776, Entropy: 0.1733 +[2026-03-20T17:44:05.753497Z] Loop 1427: Loss: 4.98e-03, Avg Return: 0.488, Regret: 0.3776, Entropy: 0.1800 +[2026-03-20T17:44:06.606123Z] Loop 1428: Loss: 5.91e-03, Avg Return: 0.478, Regret: 0.3776, Entropy: 0.1805 +[2026-03-20T17:44:07.459572Z] Loop 1429: Loss: 5.67e-03, Avg Return: 0.483, Regret: 0.3776, Entropy: 0.1812 +[2026-03-20T17:44:08.354417Z] Loop 1430: Loss: 6.20e-03, Avg Return: 0.483, Regret: 0.3795, Entropy: 0.1853 +[2026-03-20T17:44:09.209174Z] Loop 1431: Loss: 5.95e-03, Avg Return: 0.482, Regret: 0.3795, Entropy: 0.1863 +[2026-03-20T17:44:10.062903Z] Loop 1432: Loss: 6.61e-03, Avg Return: 0.488, Regret: 0.3795, Entropy: 0.1872 +[2026-03-20T17:44:10.916311Z] Loop 1433: Loss: 5.99e-03, Avg Return: 0.482, Regret: 0.3795, Entropy: 0.1802 +[2026-03-20T17:44:11.770024Z] Loop 1434: Loss: 6.09e-03, Avg Return: 0.484, Regret: 0.3795, Entropy: 0.1814 +[2026-03-20T17:44:12.663324Z] Loop 1435: Loss: 6.35e-03, Avg Return: 0.485, Regret: 0.3788, Entropy: 0.1856 +[2026-03-20T17:44:13.516374Z] Loop 1436: Loss: 5.60e-03, Avg Return: 0.481, Regret: 0.3788, Entropy: 0.1863 +[2026-03-20T17:44:14.369813Z] Loop 1437: Loss: 4.72e-03, Avg Return: 0.485, Regret: 0.3788, Entropy: 0.1646 +[2026-03-20T17:44:15.223209Z] Loop 1438: Loss: 3.71e-03, Avg Return: 0.487, Regret: 0.3788, Entropy: 0.1586 +[2026-03-20T17:44:16.076881Z] Loop 1439: Loss: 3.93e-03, Avg Return: 0.493, Regret: 0.3788, Entropy: 0.1473 +[2026-03-20T17:44:16.968934Z] Loop 1440: Loss: 3.29e-03, Avg Return: 0.488, Regret: 0.3768, Entropy: 0.1428 +[2026-03-20T17:44:17.822290Z] Loop 1441: Loss: 3.17e-03, Avg Return: 0.482, Regret: 0.3768, Entropy: 0.1350 +[2026-03-20T17:44:18.674088Z] Loop 1442: Loss: 3.11e-03, Avg Return: 0.485, Regret: 0.3768, Entropy: 0.1338 +[2026-03-20T17:44:19.526921Z] Loop 1443: Loss: 2.92e-03, Avg Return: 0.491, Regret: 0.3768, Entropy: 0.1365 +[2026-03-20T17:44:20.379827Z] Loop 1444: Loss: 3.32e-03, Avg Return: 0.494, Regret: 0.3768, Entropy: 0.1442 +[2026-03-20T17:44:21.273629Z] Loop 1445: Loss: 3.20e-03, Avg Return: 0.491, Regret: 0.3779, Entropy: 0.1444 +[2026-03-20T17:44:22.126469Z] Loop 1446: Loss: 3.28e-03, Avg Return: 0.487, Regret: 0.3779, Entropy: 0.1510 +[2026-03-20T17:44:22.979144Z] Loop 1447: Loss: 3.61e-03, Avg Return: 0.483, Regret: 0.3779, Entropy: 0.1464 +[2026-03-20T17:44:23.832372Z] Loop 1448: Loss: 3.18e-03, Avg Return: 0.481, Regret: 0.3779, Entropy: 0.1509 +[2026-03-20T17:44:24.685645Z] Loop 1449: Loss: 2.74e-03, Avg Return: 0.482, Regret: 0.3779, Entropy: 0.1369 +[2026-03-20T17:44:25.579806Z] Loop 1450: Loss: 2.59e-03, Avg Return: 0.484, Regret: 0.3821, Entropy: 0.1300 +[2026-03-20T17:44:26.433705Z] Loop 1451: Loss: 2.07e-03, Avg Return: 0.478, Regret: 0.3821, Entropy: 0.1256 +[2026-03-20T17:44:27.287092Z] Loop 1452: Loss: 2.21e-03, Avg Return: 0.479, Regret: 0.3821, Entropy: 0.1179 +[2026-03-20T17:44:28.141344Z] Loop 1453: Loss: 2.20e-03, Avg Return: 0.474, Regret: 0.3821, Entropy: 0.1213 +[2026-03-20T17:44:28.995503Z] Loop 1454: Loss: 2.22e-03, Avg Return: 0.482, Regret: 0.3821, Entropy: 0.1314 +[2026-03-20T17:44:29.889369Z] Loop 1455: Loss: 2.78e-03, Avg Return: 0.481, Regret: 0.3796, Entropy: 0.1459 +[2026-03-20T17:44:30.741526Z] Loop 1456: Loss: 2.75e-03, Avg Return: 0.480, Regret: 0.3796, Entropy: 0.1534 +[2026-03-20T17:44:31.593693Z] Loop 1457: Loss: 3.78e-03, Avg Return: 0.491, Regret: 0.3796, Entropy: 0.1543 +[2026-03-20T17:44:32.447736Z] Loop 1458: Loss: 3.61e-03, Avg Return: 0.487, Regret: 0.3796, Entropy: 0.1559 +[2026-03-20T17:44:33.301072Z] Loop 1459: Loss: 3.51e-03, Avg Return: 0.482, Regret: 0.3796, Entropy: 0.1594 +[2026-03-20T17:44:34.192673Z] Loop 1460: Loss: 3.81e-03, Avg Return: 0.490, Regret: 0.3762, Entropy: 0.1446 +[2026-03-20T17:44:35.045330Z] Loop 1461: Loss: 3.27e-03, Avg Return: 0.489, Regret: 0.3762, Entropy: 0.1451 +[2026-03-20T17:44:35.898875Z] Loop 1462: Loss: 3.40e-03, Avg Return: 0.478, Regret: 0.3762, Entropy: 0.1433 +[2026-03-20T17:44:36.751582Z] Loop 1463: Loss: 3.77e-03, Avg Return: 0.488, Regret: 0.3762, Entropy: 0.1430 +[2026-03-20T17:44:37.603719Z] Loop 1464: Loss: 3.73e-03, Avg Return: 0.489, Regret: 0.3762, Entropy: 0.1492 +[2026-03-20T17:44:38.494507Z] Loop 1465: Loss: 3.66e-03, Avg Return: 0.481, Regret: 0.3772, Entropy: 0.1532 +[2026-03-20T17:44:39.348603Z] Loop 1466: Loss: 4.48e-03, Avg Return: 0.484, Regret: 0.3772, Entropy: 0.1628 +[2026-03-20T17:44:40.201404Z] Loop 1467: Loss: 4.50e-03, Avg Return: 0.483, Regret: 0.3772, Entropy: 0.1694 +[2026-03-20T17:44:41.055070Z] Loop 1468: Loss: 5.20e-03, Avg Return: 0.488, Regret: 0.3772, Entropy: 0.1763 +[2026-03-20T17:44:41.906887Z] Loop 1469: Loss: 6.17e-03, Avg Return: 0.483, Regret: 0.3772, Entropy: 0.1886 +[2026-03-20T17:44:42.800502Z] Loop 1470: Loss: 6.83e-03, Avg Return: 0.485, Regret: 0.3813, Entropy: 0.1873 +[2026-03-20T17:44:43.654023Z] Loop 1471: Loss: 6.86e-03, Avg Return: 0.475, Regret: 0.3813, Entropy: 0.1808 +[2026-03-20T17:44:44.506561Z] Loop 1472: Loss: 6.37e-03, Avg Return: 0.471, Regret: 0.3813, Entropy: 0.1758 +[2026-03-20T17:44:45.359315Z] Loop 1473: Loss: 6.74e-03, Avg Return: 0.482, Regret: 0.3813, Entropy: 0.1768 +[2026-03-20T17:44:46.212424Z] Loop 1474: Loss: 6.44e-03, Avg Return: 0.480, Regret: 0.3813, Entropy: 0.1678 +[2026-03-20T17:44:47.105440Z] Loop 1475: Loss: 6.45e-03, Avg Return: 0.481, Regret: 0.3820, Entropy: 0.1775 +[2026-03-20T17:44:47.958845Z] Loop 1476: Loss: 6.58e-03, Avg Return: 0.482, Regret: 0.3820, Entropy: 0.1660 +[2026-03-20T17:44:48.811642Z] Loop 1477: Loss: 6.37e-03, Avg Return: 0.484, Regret: 0.3820, Entropy: 0.1702 +[2026-03-20T17:44:49.664848Z] Loop 1478: Loss: 5.63e-03, Avg Return: 0.477, Regret: 0.3820, Entropy: 0.1635 +[2026-03-20T17:44:50.518678Z] Loop 1479: Loss: 5.91e-03, Avg Return: 0.482, Regret: 0.3820, Entropy: 0.1720 +[2026-03-20T17:44:51.411127Z] Loop 1480: Loss: 5.88e-03, Avg Return: 0.484, Regret: 0.3780, Entropy: 0.1738 +[2026-03-20T17:44:52.263419Z] Loop 1481: Loss: 5.42e-03, Avg Return: 0.491, Regret: 0.3780, Entropy: 0.1661 +[2026-03-20T17:44:53.117587Z] Loop 1482: Loss: 4.36e-03, Avg Return: 0.487, Regret: 0.3780, Entropy: 0.1594 +[2026-03-20T17:44:53.970420Z] Loop 1483: Loss: 3.61e-03, Avg Return: 0.483, Regret: 0.3780, Entropy: 0.1527 +[2026-03-20T17:44:54.823348Z] Loop 1484: Loss: 3.29e-03, Avg Return: 0.481, Regret: 0.3780, Entropy: 0.1541 +[2026-03-20T17:44:55.715844Z] Loop 1485: Loss: 2.83e-03, Avg Return: 0.479, Regret: 0.3779, Entropy: 0.1575 +[2026-03-20T17:44:56.569468Z] Loop 1486: Loss: 2.97e-03, Avg Return: 0.488, Regret: 0.3779, Entropy: 0.1425 +[2026-03-20T17:44:57.422418Z] Loop 1487: Loss: 2.81e-03, Avg Return: 0.484, Regret: 0.3779, Entropy: 0.1348 +[2026-03-20T17:44:58.274454Z] Loop 1488: Loss: 3.27e-03, Avg Return: 0.487, Regret: 0.3779, Entropy: 0.1423 +[2026-03-20T17:44:59.127211Z] Loop 1489: Loss: 3.41e-03, Avg Return: 0.484, Regret: 0.3779, Entropy: 0.1537 +[2026-03-20T17:45:00.020537Z] Loop 1490: Loss: 3.38e-03, Avg Return: 0.490, Regret: 0.3800, Entropy: 0.1473 +[2026-03-20T17:45:00.872534Z] Loop 1491: Loss: 3.29e-03, Avg Return: 0.478, Regret: 0.3800, Entropy: 0.1540 +[2026-03-20T17:45:01.726668Z] Loop 1492: Loss: 3.77e-03, Avg Return: 0.489, Regret: 0.3800, Entropy: 0.1528 +[2026-03-20T17:45:02.581776Z] Loop 1493: Loss: 3.38e-03, Avg Return: 0.494, Regret: 0.3800, Entropy: 0.1512 +[2026-03-20T17:45:03.435121Z] Loop 1494: Loss: 3.37e-03, Avg Return: 0.486, Regret: 0.3800, Entropy: 0.1495 +[2026-03-20T17:45:04.329334Z] Loop 1495: Loss: 3.37e-03, Avg Return: 0.490, Regret: 0.3809, Entropy: 0.1425 +[2026-03-20T17:45:05.183225Z] Loop 1496: Loss: 2.93e-03, Avg Return: 0.492, Regret: 0.3809, Entropy: 0.1465 +[2026-03-20T17:45:06.037693Z] Loop 1497: Loss: 2.57e-03, Avg Return: 0.485, Regret: 0.3809, Entropy: 0.1412 +[2026-03-20T17:45:06.890238Z] Loop 1498: Loss: 2.27e-03, Avg Return: 0.483, Regret: 0.3809, Entropy: 0.1293 +[2026-03-20T17:45:07.743952Z] Loop 1499: Loss: 2.06e-03, Avg Return: 0.478, Regret: 0.3809, Entropy: 0.1268 +[2026-03-20T17:45:08.636249Z] Loop 1500: Loss: 2.21e-03, Avg Return: 0.478, Regret: 0.3810, Entropy: 0.1255 +[2026-03-20T17:45:09.491582Z] Loop 1501: Loss: 2.15e-03, Avg Return: 0.481, Regret: 0.3810, Entropy: 0.1293 +[2026-03-20T17:45:10.344194Z] Loop 1502: Loss: 2.19e-03, Avg Return: 0.487, Regret: 0.3810, Entropy: 0.1212 +[2026-03-20T17:45:11.197063Z] Loop 1503: Loss: 2.23e-03, Avg Return: 0.479, Regret: 0.3810, Entropy: 0.1219 +[2026-03-20T17:45:12.050184Z] Loop 1504: Loss: 2.20e-03, Avg Return: 0.490, Regret: 0.3810, Entropy: 0.1165 +[2026-03-20T17:45:12.942861Z] Loop 1505: Loss: 2.52e-03, Avg Return: 0.488, Regret: 0.3787, Entropy: 0.1180 +[2026-03-20T17:45:13.795613Z] Loop 1506: Loss: 2.42e-03, Avg Return: 0.486, Regret: 0.3787, Entropy: 0.1255 +[2026-03-20T17:45:14.648255Z] Loop 1507: Loss: 2.72e-03, Avg Return: 0.486, Regret: 0.3787, Entropy: 0.1316 +[2026-03-20T17:45:15.502066Z] Loop 1508: Loss: 2.69e-03, Avg Return: 0.485, Regret: 0.3787, Entropy: 0.1318 +[2026-03-20T17:45:16.355360Z] Loop 1509: Loss: 3.05e-03, Avg Return: 0.488, Regret: 0.3787, Entropy: 0.1398 +[2026-03-20T17:45:17.247475Z] Loop 1510: Loss: 3.13e-03, Avg Return: 0.482, Regret: 0.3767, Entropy: 0.1404 +[2026-03-20T17:45:18.099630Z] Loop 1511: Loss: 3.15e-03, Avg Return: 0.484, Regret: 0.3767, Entropy: 0.1386 +[2026-03-20T17:45:18.952867Z] Loop 1512: Loss: 3.48e-03, Avg Return: 0.491, Regret: 0.3767, Entropy: 0.1417 +[2026-03-20T17:45:19.806104Z] Loop 1513: Loss: 3.63e-03, Avg Return: 0.489, Regret: 0.3767, Entropy: 0.1448 +[2026-03-20T17:45:20.660115Z] Loop 1514: Loss: 3.46e-03, Avg Return: 0.487, Regret: 0.3767, Entropy: 0.1461 +[2026-03-20T17:45:21.552174Z] Loop 1515: Loss: 3.86e-03, Avg Return: 0.494, Regret: 0.3766, Entropy: 0.1461 +[2026-03-20T17:45:22.405005Z] Loop 1516: Loss: 4.17e-03, Avg Return: 0.485, Regret: 0.3766, Entropy: 0.1479 +[2026-03-20T17:45:23.259306Z] Loop 1517: Loss: 4.04e-03, Avg Return: 0.482, Regret: 0.3766, Entropy: 0.1469 +[2026-03-20T17:45:24.113919Z] Loop 1518: Loss: 4.40e-03, Avg Return: 0.487, Regret: 0.3766, Entropy: 0.1497 +[2026-03-20T17:45:24.968363Z] Loop 1519: Loss: 3.77e-03, Avg Return: 0.481, Regret: 0.3766, Entropy: 0.1428 +[2026-03-20T17:45:25.862323Z] Loop 1520: Loss: 3.71e-03, Avg Return: 0.483, Regret: 0.3769, Entropy: 0.1429 +[2026-03-20T17:45:26.715076Z] Loop 1521: Loss: 4.27e-03, Avg Return: 0.484, Regret: 0.3769, Entropy: 0.1487 +[2026-03-20T17:45:27.567892Z] Loop 1522: Loss: 3.84e-03, Avg Return: 0.492, Regret: 0.3769, Entropy: 0.1377 +[2026-03-20T17:45:28.420132Z] Loop 1523: Loss: 3.38e-03, Avg Return: 0.481, Regret: 0.3769, Entropy: 0.1383 +[2026-03-20T17:45:29.272986Z] Loop 1524: Loss: 3.81e-03, Avg Return: 0.489, Regret: 0.3769, Entropy: 0.1373 +[2026-03-20T17:45:30.164865Z] Loop 1525: Loss: 3.22e-03, Avg Return: 0.493, Regret: 0.3769, Entropy: 0.1315 +[2026-03-20T17:45:31.019194Z] Loop 1526: Loss: 3.43e-03, Avg Return: 0.488, Regret: 0.3769, Entropy: 0.1235 +[2026-03-20T17:45:31.873059Z] Loop 1527: Loss: 3.75e-03, Avg Return: 0.491, Regret: 0.3769, Entropy: 0.1313 +[2026-03-20T17:45:32.727079Z] Loop 1528: Loss: 3.74e-03, Avg Return: 0.484, Regret: 0.3769, Entropy: 0.1291 +[2026-03-20T17:45:33.581287Z] Loop 1529: Loss: 3.70e-03, Avg Return: 0.484, Regret: 0.3769, Entropy: 0.1328 +[2026-03-20T17:45:34.474454Z] Loop 1530: Loss: 3.82e-03, Avg Return: 0.485, Regret: 0.3773, Entropy: 0.1390 +[2026-03-20T17:45:35.327648Z] Loop 1531: Loss: 3.65e-03, Avg Return: 0.483, Regret: 0.3773, Entropy: 0.1378 +[2026-03-20T17:45:36.182726Z] Loop 1532: Loss: 3.97e-03, Avg Return: 0.489, Regret: 0.3773, Entropy: 0.1395 +[2026-03-20T17:45:37.036960Z] Loop 1533: Loss: 4.09e-03, Avg Return: 0.491, Regret: 0.3773, Entropy: 0.1467 +[2026-03-20T17:45:37.889921Z] Loop 1534: Loss: 4.37e-03, Avg Return: 0.488, Regret: 0.3773, Entropy: 0.1401 +[2026-03-20T17:45:38.783708Z] Loop 1535: Loss: 3.93e-03, Avg Return: 0.488, Regret: 0.3758, Entropy: 0.1405 +[2026-03-20T17:45:39.638246Z] Loop 1536: Loss: 3.75e-03, Avg Return: 0.483, Regret: 0.3758, Entropy: 0.1431 +[2026-03-20T17:45:40.491881Z] Loop 1537: Loss: 3.79e-03, Avg Return: 0.478, Regret: 0.3758, Entropy: 0.1476 +[2026-03-20T17:45:41.344175Z] Loop 1538: Loss: 4.56e-03, Avg Return: 0.486, Regret: 0.3758, Entropy: 0.1525 +[2026-03-20T17:45:42.197170Z] Loop 1539: Loss: 5.13e-03, Avg Return: 0.488, Regret: 0.3758, Entropy: 0.1641 +[2026-03-20T17:45:43.090616Z] Loop 1540: Loss: 5.59e-03, Avg Return: 0.494, Regret: 0.3763, Entropy: 0.1630 +[2026-03-20T17:45:43.944408Z] Loop 1541: Loss: 5.23e-03, Avg Return: 0.485, Regret: 0.3763, Entropy: 0.1680 +[2026-03-20T17:45:44.797926Z] Loop 1542: Loss: 5.74e-03, Avg Return: 0.482, Regret: 0.3763, Entropy: 0.1685 +[2026-03-20T17:45:45.650849Z] Loop 1543: Loss: 4.40e-03, Avg Return: 0.487, Regret: 0.3763, Entropy: 0.1569 +[2026-03-20T17:45:46.504562Z] Loop 1544: Loss: 4.76e-03, Avg Return: 0.483, Regret: 0.3763, Entropy: 0.1575 +[2026-03-20T17:45:47.397529Z] Loop 1545: Loss: 4.60e-03, Avg Return: 0.484, Regret: 0.3763, Entropy: 0.1575 +[2026-03-20T17:45:48.250267Z] Loop 1546: Loss: 4.49e-03, Avg Return: 0.489, Regret: 0.3763, Entropy: 0.1525 +[2026-03-20T17:45:49.102869Z] Loop 1547: Loss: 4.49e-03, Avg Return: 0.490, Regret: 0.3763, Entropy: 0.1483 +[2026-03-20T17:45:49.956093Z] Loop 1548: Loss: 3.80e-03, Avg Return: 0.486, Regret: 0.3763, Entropy: 0.1394 +[2026-03-20T17:45:50.809207Z] Loop 1549: Loss: 3.55e-03, Avg Return: 0.492, Regret: 0.3763, Entropy: 0.1390 +[2026-03-20T17:45:51.701715Z] Loop 1550: Loss: 3.41e-03, Avg Return: 0.486, Regret: 0.3762, Entropy: 0.1302 +[2026-03-20T17:45:52.555075Z] Loop 1551: Loss: 3.24e-03, Avg Return: 0.491, Regret: 0.3762, Entropy: 0.1257 +[2026-03-20T17:45:53.407780Z] Loop 1552: Loss: 3.33e-03, Avg Return: 0.497, Regret: 0.3762, Entropy: 0.1249 +[2026-03-20T17:45:54.260637Z] Loop 1553: Loss: 3.04e-03, Avg Return: 0.486, Regret: 0.3762, Entropy: 0.1261 +[2026-03-20T17:45:55.113619Z] Loop 1554: Loss: 2.63e-03, Avg Return: 0.489, Regret: 0.3762, Entropy: 0.1256 +[2026-03-20T17:45:56.004818Z] Loop 1555: Loss: 2.62e-03, Avg Return: 0.488, Regret: 0.3765, Entropy: 0.1264 +[2026-03-20T17:45:56.857549Z] Loop 1556: Loss: 2.75e-03, Avg Return: 0.487, Regret: 0.3765, Entropy: 0.1200 +[2026-03-20T17:45:57.709664Z] Loop 1557: Loss: 2.71e-03, Avg Return: 0.488, Regret: 0.3765, Entropy: 0.1173 +[2026-03-20T17:45:58.562509Z] Loop 1558: Loss: 2.57e-03, Avg Return: 0.491, Regret: 0.3765, Entropy: 0.1198 +[2026-03-20T17:45:59.415164Z] Loop 1559: Loss: 2.80e-03, Avg Return: 0.480, Regret: 0.3765, Entropy: 0.1213 +[2026-03-20T17:46:00.307106Z] Loop 1560: Loss: 2.92e-03, Avg Return: 0.484, Regret: 0.3760, Entropy: 0.1182 +[2026-03-20T17:46:01.159703Z] Loop 1561: Loss: 2.85e-03, Avg Return: 0.484, Regret: 0.3760, Entropy: 0.1238 +[2026-03-20T17:46:02.012022Z] Loop 1562: Loss: 3.01e-03, Avg Return: 0.484, Regret: 0.3760, Entropy: 0.1306 +[2026-03-20T17:46:02.865908Z] Loop 1563: Loss: 3.35e-03, Avg Return: 0.491, Regret: 0.3760, Entropy: 0.1338 +[2026-03-20T17:46:03.719321Z] Loop 1564: Loss: 3.47e-03, Avg Return: 0.493, Regret: 0.3760, Entropy: 0.1365 +[2026-03-20T17:46:04.610254Z] Loop 1565: Loss: 3.61e-03, Avg Return: 0.484, Regret: 0.3766, Entropy: 0.1321 +[2026-03-20T17:46:05.462831Z] Loop 1566: Loss: 2.98e-03, Avg Return: 0.491, Regret: 0.3766, Entropy: 0.1257 +[2026-03-20T17:46:06.316343Z] Loop 1567: Loss: 2.61e-03, Avg Return: 0.488, Regret: 0.3766, Entropy: 0.1208 +[2026-03-20T17:46:07.170539Z] Loop 1568: Loss: 2.77e-03, Avg Return: 0.488, Regret: 0.3766, Entropy: 0.1221 +[2026-03-20T17:46:08.023032Z] Loop 1569: Loss: 2.80e-03, Avg Return: 0.478, Regret: 0.3766, Entropy: 0.1229 +[2026-03-20T17:46:08.914862Z] Loop 1570: Loss: 2.77e-03, Avg Return: 0.483, Regret: 0.3768, Entropy: 0.1220 +[2026-03-20T17:46:09.769171Z] Loop 1571: Loss: 2.72e-03, Avg Return: 0.488, Regret: 0.3768, Entropy: 0.1229 +[2026-03-20T17:46:10.622392Z] Loop 1572: Loss: 2.55e-03, Avg Return: 0.485, Regret: 0.3768, Entropy: 0.1223 +[2026-03-20T17:46:11.475032Z] Loop 1573: Loss: 2.38e-03, Avg Return: 0.479, Regret: 0.3768, Entropy: 0.1189 +[2026-03-20T17:46:12.327687Z] Loop 1574: Loss: 2.44e-03, Avg Return: 0.488, Regret: 0.3768, Entropy: 0.1208 +[2026-03-20T17:46:13.219835Z] Loop 1575: Loss: 2.58e-03, Avg Return: 0.492, Regret: 0.3777, Entropy: 0.1139 +[2026-03-20T17:46:14.072651Z] Loop 1576: Loss: 2.77e-03, Avg Return: 0.490, Regret: 0.3777, Entropy: 0.1170 +[2026-03-20T17:46:14.925369Z] Loop 1577: Loss: 2.66e-03, Avg Return: 0.492, Regret: 0.3777, Entropy: 0.1139 +[2026-03-20T17:46:15.778614Z] Loop 1578: Loss: 2.53e-03, Avg Return: 0.489, Regret: 0.3777, Entropy: 0.1196 +[2026-03-20T17:46:16.632021Z] Loop 1579: Loss: 2.53e-03, Avg Return: 0.487, Regret: 0.3777, Entropy: 0.1248 +[2026-03-20T17:46:17.526336Z] Loop 1580: Loss: 2.67e-03, Avg Return: 0.487, Regret: 0.3767, Entropy: 0.1226 +[2026-03-20T17:46:18.379259Z] Loop 1581: Loss: 2.74e-03, Avg Return: 0.495, Regret: 0.3767, Entropy: 0.1222 +[2026-03-20T17:46:19.231389Z] Loop 1582: Loss: 2.74e-03, Avg Return: 0.487, Regret: 0.3767, Entropy: 0.1295 +[2026-03-20T17:46:20.085069Z] Loop 1583: Loss: 2.99e-03, Avg Return: 0.492, Regret: 0.3767, Entropy: 0.1309 +[2026-03-20T17:46:20.936840Z] Loop 1584: Loss: 2.95e-03, Avg Return: 0.488, Regret: 0.3767, Entropy: 0.1308 +[2026-03-20T17:46:21.829013Z] Loop 1585: Loss: 3.30e-03, Avg Return: 0.489, Regret: 0.3761, Entropy: 0.1392 +[2026-03-20T17:46:22.682723Z] Loop 1586: Loss: 3.05e-03, Avg Return: 0.481, Regret: 0.3761, Entropy: 0.1383 +[2026-03-20T17:46:23.536497Z] Loop 1587: Loss: 3.67e-03, Avg Return: 0.494, Regret: 0.3761, Entropy: 0.1410 +[2026-03-20T17:46:24.388907Z] Loop 1588: Loss: 3.83e-03, Avg Return: 0.494, Regret: 0.3761, Entropy: 0.1335 +[2026-03-20T17:46:25.242986Z] Loop 1589: Loss: 3.68e-03, Avg Return: 0.490, Regret: 0.3761, Entropy: 0.1439 +[2026-03-20T17:46:26.136524Z] Loop 1590: Loss: 4.26e-03, Avg Return: 0.484, Regret: 0.3759, Entropy: 0.1349 +[2026-03-20T17:46:26.990626Z] Loop 1591: Loss: 3.88e-03, Avg Return: 0.496, Regret: 0.3759, Entropy: 0.1305 +[2026-03-20T17:46:27.844132Z] Loop 1592: Loss: 3.74e-03, Avg Return: 0.489, Regret: 0.3759, Entropy: 0.1243 +[2026-03-20T17:46:28.696261Z] Loop 1593: Loss: 3.31e-03, Avg Return: 0.483, Regret: 0.3759, Entropy: 0.1235 +[2026-03-20T17:46:29.549193Z] Loop 1594: Loss: 3.50e-03, Avg Return: 0.487, Regret: 0.3759, Entropy: 0.1351 +[2026-03-20T17:46:30.444060Z] Loop 1595: Loss: 3.75e-03, Avg Return: 0.485, Regret: 0.3772, Entropy: 0.1355 +[2026-03-20T17:46:31.297434Z] Loop 1596: Loss: 4.20e-03, Avg Return: 0.488, Regret: 0.3772, Entropy: 0.1382 +[2026-03-20T17:46:32.150359Z] Loop 1597: Loss: 4.38e-03, Avg Return: 0.485, Regret: 0.3772, Entropy: 0.1418 +[2026-03-20T17:46:33.003557Z] Loop 1598: Loss: 4.35e-03, Avg Return: 0.487, Regret: 0.3772, Entropy: 0.1401 +[2026-03-20T17:46:33.857052Z] Loop 1599: Loss: 4.51e-03, Avg Return: 0.481, Regret: 0.3772, Entropy: 0.1423 +[2026-03-20T17:46:34.748856Z] Loop 1600: Loss: 4.78e-03, Avg Return: 0.491, Regret: 0.3778, Entropy: 0.1456 +[2026-03-20T17:46:35.602989Z] Loop 1601: Loss: 4.61e-03, Avg Return: 0.489, Regret: 0.3778, Entropy: 0.1434 +[2026-03-20T17:46:36.456255Z] Loop 1602: Loss: 4.77e-03, Avg Return: 0.490, Regret: 0.3778, Entropy: 0.1414 +[2026-03-20T17:46:37.309511Z] Loop 1603: Loss: 4.13e-03, Avg Return: 0.480, Regret: 0.3778, Entropy: 0.1436 +[2026-03-20T17:46:38.162448Z] Loop 1604: Loss: 4.79e-03, Avg Return: 0.489, Regret: 0.3778, Entropy: 0.1434 +[2026-03-20T17:46:39.054903Z] Loop 1605: Loss: 4.77e-03, Avg Return: 0.485, Regret: 0.3769, Entropy: 0.1483 +[2026-03-20T17:46:39.908403Z] Loop 1606: Loss: 4.31e-03, Avg Return: 0.482, Regret: 0.3769, Entropy: 0.1487 +[2026-03-20T17:46:40.761167Z] Loop 1607: Loss: 5.00e-03, Avg Return: 0.487, Regret: 0.3769, Entropy: 0.1510 +[2026-03-20T17:46:41.613685Z] Loop 1608: Loss: 5.33e-03, Avg Return: 0.494, Regret: 0.3769, Entropy: 0.1582 +[2026-03-20T17:46:42.466526Z] Loop 1609: Loss: 5.90e-03, Avg Return: 0.483, Regret: 0.3769, Entropy: 0.1552 +[2026-03-20T17:46:43.359968Z] Loop 1610: Loss: 5.70e-03, Avg Return: 0.483, Regret: 0.3774, Entropy: 0.1538 +[2026-03-20T17:46:44.212630Z] Loop 1611: Loss: 4.97e-03, Avg Return: 0.480, Regret: 0.3774, Entropy: 0.1579 +[2026-03-20T17:46:45.064493Z] Loop 1612: Loss: 5.72e-03, Avg Return: 0.492, Regret: 0.3774, Entropy: 0.1530 +[2026-03-20T17:46:45.916836Z] Loop 1613: Loss: 5.52e-03, Avg Return: 0.482, Regret: 0.3774, Entropy: 0.1575 +[2026-03-20T17:46:46.769863Z] Loop 1614: Loss: 5.39e-03, Avg Return: 0.486, Regret: 0.3774, Entropy: 0.1553 +[2026-03-20T17:46:47.663652Z] Loop 1615: Loss: 5.41e-03, Avg Return: 0.481, Regret: 0.3774, Entropy: 0.1563 +[2026-03-20T17:46:48.515708Z] Loop 1616: Loss: 5.52e-03, Avg Return: 0.477, Regret: 0.3774, Entropy: 0.1555 +[2026-03-20T17:46:49.367859Z] Loop 1617: Loss: 5.38e-03, Avg Return: 0.485, Regret: 0.3774, Entropy: 0.1580 +[2026-03-20T17:46:50.221657Z] Loop 1618: Loss: 5.58e-03, Avg Return: 0.484, Regret: 0.3774, Entropy: 0.1583 +[2026-03-20T17:46:51.074717Z] Loop 1619: Loss: 5.52e-03, Avg Return: 0.480, Regret: 0.3774, Entropy: 0.1528 +[2026-03-20T17:46:51.966375Z] Loop 1620: Loss: 5.44e-03, Avg Return: 0.486, Regret: 0.3791, Entropy: 0.1523 +[2026-03-20T17:46:52.818139Z] Loop 1621: Loss: 5.93e-03, Avg Return: 0.486, Regret: 0.3791, Entropy: 0.1594 +[2026-03-20T17:46:53.670660Z] Loop 1622: Loss: 6.07e-03, Avg Return: 0.492, Regret: 0.3791, Entropy: 0.1577 +[2026-03-20T17:46:54.523596Z] Loop 1623: Loss: 6.02e-03, Avg Return: 0.491, Regret: 0.3791, Entropy: 0.1618 +[2026-03-20T17:46:55.377078Z] Loop 1624: Loss: 5.19e-03, Avg Return: 0.486, Regret: 0.3791, Entropy: 0.1568 +[2026-03-20T17:46:56.270278Z] Loop 1625: Loss: 4.94e-03, Avg Return: 0.489, Regret: 0.3770, Entropy: 0.1557 +[2026-03-20T17:46:57.124191Z] Loop 1626: Loss: 4.46e-03, Avg Return: 0.487, Regret: 0.3770, Entropy: 0.1506 +[2026-03-20T17:46:57.976903Z] Loop 1627: Loss: 4.39e-03, Avg Return: 0.485, Regret: 0.3770, Entropy: 0.1511 +[2026-03-20T17:46:58.830787Z] Loop 1628: Loss: 3.90e-03, Avg Return: 0.481, Regret: 0.3770, Entropy: 0.1407 +[2026-03-20T17:46:59.683405Z] Loop 1629: Loss: 4.31e-03, Avg Return: 0.491, Regret: 0.3770, Entropy: 0.1373 +[2026-03-20T17:47:00.575906Z] Loop 1630: Loss: 3.90e-03, Avg Return: 0.486, Regret: 0.3766, Entropy: 0.1416 +[2026-03-20T17:47:01.429141Z] Loop 1631: Loss: 4.18e-03, Avg Return: 0.488, Regret: 0.3766, Entropy: 0.1350 +[2026-03-20T17:47:02.282027Z] Loop 1632: Loss: 3.97e-03, Avg Return: 0.489, Regret: 0.3766, Entropy: 0.1385 +[2026-03-20T17:47:03.135110Z] Loop 1633: Loss: 3.77e-03, Avg Return: 0.493, Regret: 0.3766, Entropy: 0.1377 +[2026-03-20T17:47:03.988430Z] Loop 1634: Loss: 2.99e-03, Avg Return: 0.484, Regret: 0.3766, Entropy: 0.1293 +[2026-03-20T17:47:04.880799Z] Loop 1635: Loss: 3.12e-03, Avg Return: 0.488, Regret: 0.3762, Entropy: 0.1315 +[2026-03-20T17:47:05.734219Z] Loop 1636: Loss: 2.85e-03, Avg Return: 0.488, Regret: 0.3762, Entropy: 0.1335 +[2026-03-20T17:47:06.586906Z] Loop 1637: Loss: 3.05e-03, Avg Return: 0.477, Regret: 0.3762, Entropy: 0.1284 +[2026-03-20T17:47:07.440548Z] Loop 1638: Loss: 3.31e-03, Avg Return: 0.489, Regret: 0.3762, Entropy: 0.1327 +[2026-03-20T17:47:08.292671Z] Loop 1639: Loss: 3.55e-03, Avg Return: 0.491, Regret: 0.3762, Entropy: 0.1396 +[2026-03-20T17:47:09.184156Z] Loop 1640: Loss: 3.58e-03, Avg Return: 0.488, Regret: 0.3765, Entropy: 0.1437 +[2026-03-20T17:47:10.036679Z] Loop 1641: Loss: 3.39e-03, Avg Return: 0.492, Regret: 0.3765, Entropy: 0.1470 +[2026-03-20T17:47:10.890037Z] Loop 1642: Loss: 3.84e-03, Avg Return: 0.487, Regret: 0.3765, Entropy: 0.1462 +[2026-03-20T17:47:11.743158Z] Loop 1643: Loss: 3.47e-03, Avg Return: 0.486, Regret: 0.3765, Entropy: 0.1473 +[2026-03-20T17:47:12.595336Z] Loop 1644: Loss: 3.90e-03, Avg Return: 0.498, Regret: 0.3765, Entropy: 0.1471 +[2026-03-20T17:47:13.487008Z] Loop 1645: Loss: 3.61e-03, Avg Return: 0.488, Regret: 0.3760, Entropy: 0.1466 +[2026-03-20T17:47:14.341717Z] Loop 1646: Loss: 3.54e-03, Avg Return: 0.488, Regret: 0.3760, Entropy: 0.1429 +[2026-03-20T17:47:15.194092Z] Loop 1647: Loss: 3.60e-03, Avg Return: 0.480, Regret: 0.3760, Entropy: 0.1494 +[2026-03-20T17:47:16.046017Z] Loop 1648: Loss: 3.80e-03, Avg Return: 0.485, Regret: 0.3760, Entropy: 0.1464 +[2026-03-20T17:47:16.899024Z] Loop 1649: Loss: 3.39e-03, Avg Return: 0.487, Regret: 0.3760, Entropy: 0.1423 +[2026-03-20T17:47:17.793001Z] Loop 1650: Loss: 3.92e-03, Avg Return: 0.492, Regret: 0.3758, Entropy: 0.1443 +[2026-03-20T17:47:18.646413Z] Loop 1651: Loss: 3.45e-03, Avg Return: 0.487, Regret: 0.3758, Entropy: 0.1454 +[2026-03-20T17:47:19.499342Z] Loop 1652: Loss: 3.95e-03, Avg Return: 0.488, Regret: 0.3758, Entropy: 0.1443 +[2026-03-20T17:47:20.351198Z] Loop 1653: Loss: 3.88e-03, Avg Return: 0.484, Regret: 0.3758, Entropy: 0.1413 +[2026-03-20T17:47:21.203855Z] Loop 1654: Loss: 3.80e-03, Avg Return: 0.490, Regret: 0.3758, Entropy: 0.1451 +[2026-03-20T17:47:22.094750Z] Loop 1655: Loss: 3.77e-03, Avg Return: 0.492, Regret: 0.3759, Entropy: 0.1465 +[2026-03-20T17:47:22.947953Z] Loop 1656: Loss: 3.43e-03, Avg Return: 0.485, Regret: 0.3759, Entropy: 0.1433 +[2026-03-20T17:47:23.800651Z] Loop 1657: Loss: 3.21e-03, Avg Return: 0.484, Regret: 0.3759, Entropy: 0.1408 +[2026-03-20T17:47:24.654799Z] Loop 1658: Loss: 2.91e-03, Avg Return: 0.479, Regret: 0.3759, Entropy: 0.1438 +[2026-03-20T17:47:25.507482Z] Loop 1659: Loss: 2.60e-03, Avg Return: 0.484, Regret: 0.3759, Entropy: 0.1269 +[2026-03-20T17:47:26.399649Z] Loop 1660: Loss: 2.84e-03, Avg Return: 0.487, Regret: 0.3767, Entropy: 0.1271 +[2026-03-20T17:47:27.252752Z] Loop 1661: Loss: 2.21e-03, Avg Return: 0.492, Regret: 0.3767, Entropy: 0.1236 +[2026-03-20T17:47:28.105205Z] Loop 1662: Loss: 1.91e-03, Avg Return: 0.481, Regret: 0.3767, Entropy: 0.1219 +[2026-03-20T17:47:28.957437Z] Loop 1663: Loss: 2.02e-03, Avg Return: 0.485, Regret: 0.3767, Entropy: 0.1171 +[2026-03-20T17:47:29.811481Z] Loop 1664: Loss: 2.40e-03, Avg Return: 0.492, Regret: 0.3767, Entropy: 0.1149 +[2026-03-20T17:47:30.703917Z] Loop 1665: Loss: 2.24e-03, Avg Return: 0.492, Regret: 0.3788, Entropy: 0.1190 +[2026-03-20T17:47:31.558047Z] Loop 1666: Loss: 2.03e-03, Avg Return: 0.486, Regret: 0.3788, Entropy: 0.1225 +[2026-03-20T17:47:32.410640Z] Loop 1667: Loss: 2.21e-03, Avg Return: 0.489, Regret: 0.3788, Entropy: 0.1181 +[2026-03-20T17:47:33.263551Z] Loop 1668: Loss: 2.38e-03, Avg Return: 0.489, Regret: 0.3788, Entropy: 0.1204 +[2026-03-20T17:47:34.116890Z] Loop 1669: Loss: 2.59e-03, Avg Return: 0.486, Regret: 0.3788, Entropy: 0.1324 +[2026-03-20T17:47:35.010704Z] Loop 1670: Loss: 3.59e-03, Avg Return: 0.492, Regret: 0.3769, Entropy: 0.1364 +[2026-03-20T17:47:35.863211Z] Loop 1671: Loss: 3.41e-03, Avg Return: 0.484, Regret: 0.3769, Entropy: 0.1368 +[2026-03-20T17:47:36.716376Z] Loop 1672: Loss: 4.28e-03, Avg Return: 0.491, Regret: 0.3769, Entropy: 0.1495 +[2026-03-20T17:47:37.569734Z] Loop 1673: Loss: 4.10e-03, Avg Return: 0.483, Regret: 0.3769, Entropy: 0.1529 +[2026-03-20T17:47:38.423247Z] Loop 1674: Loss: 4.13e-03, Avg Return: 0.484, Regret: 0.3769, Entropy: 0.1535 +[2026-03-20T17:47:39.316461Z] Loop 1675: Loss: 3.77e-03, Avg Return: 0.482, Regret: 0.3771, Entropy: 0.1507 +[2026-03-20T17:47:40.168208Z] Loop 1676: Loss: 4.15e-03, Avg Return: 0.489, Regret: 0.3771, Entropy: 0.1470 +[2026-03-20T17:47:41.020926Z] Loop 1677: Loss: 3.75e-03, Avg Return: 0.485, Regret: 0.3771, Entropy: 0.1477 +[2026-03-20T17:47:41.875548Z] Loop 1678: Loss: 3.82e-03, Avg Return: 0.491, Regret: 0.3771, Entropy: 0.1360 +[2026-03-20T17:47:42.729912Z] Loop 1679: Loss: 3.72e-03, Avg Return: 0.489, Regret: 0.3771, Entropy: 0.1435 +[2026-03-20T17:47:43.622581Z] Loop 1680: Loss: 3.69e-03, Avg Return: 0.490, Regret: 0.3765, Entropy: 0.1415 +[2026-03-20T17:47:44.475320Z] Loop 1681: Loss: 3.48e-03, Avg Return: 0.487, Regret: 0.3765, Entropy: 0.1391 +[2026-03-20T17:47:45.328794Z] Loop 1682: Loss: 3.60e-03, Avg Return: 0.486, Regret: 0.3765, Entropy: 0.1382 +[2026-03-20T17:47:46.182413Z] Loop 1683: Loss: 3.60e-03, Avg Return: 0.485, Regret: 0.3765, Entropy: 0.1372 +[2026-03-20T17:47:47.035859Z] Loop 1684: Loss: 2.82e-03, Avg Return: 0.484, Regret: 0.3765, Entropy: 0.1309 +[2026-03-20T17:47:47.927779Z] Loop 1685: Loss: 2.24e-03, Avg Return: 0.490, Regret: 0.3767, Entropy: 0.1145 +[2026-03-20T17:47:48.780671Z] Loop 1686: Loss: 1.81e-03, Avg Return: 0.480, Regret: 0.3767, Entropy: 0.1109 +[2026-03-20T17:47:49.633237Z] Loop 1687: Loss: 2.11e-03, Avg Return: 0.488, Regret: 0.3767, Entropy: 0.1056 +[2026-03-20T17:47:50.486513Z] Loop 1688: Loss: 2.24e-03, Avg Return: 0.492, Regret: 0.3767, Entropy: 0.1091 +[2026-03-20T17:47:51.339657Z] Loop 1689: Loss: 1.78e-03, Avg Return: 0.478, Regret: 0.3767, Entropy: 0.1026 +[2026-03-20T17:47:52.231821Z] Loop 1690: Loss: 2.08e-03, Avg Return: 0.488, Regret: 0.3808, Entropy: 0.0962 +[2026-03-20T17:47:53.085863Z] Loop 1691: Loss: 2.22e-03, Avg Return: 0.486, Regret: 0.3808, Entropy: 0.1004 +[2026-03-20T17:47:53.939556Z] Loop 1692: Loss: 1.65e-03, Avg Return: 0.479, Regret: 0.3808, Entropy: 0.0996 +[2026-03-20T17:47:54.793985Z] Loop 1693: Loss: 1.72e-03, Avg Return: 0.491, Regret: 0.3808, Entropy: 0.1077 +[2026-03-20T17:47:55.647216Z] Loop 1694: Loss: 1.96e-03, Avg Return: 0.491, Regret: 0.3808, Entropy: 0.1145 +[2026-03-20T17:47:56.540331Z] Loop 1695: Loss: 2.29e-03, Avg Return: 0.481, Regret: 0.3768, Entropy: 0.1165 +[2026-03-20T17:47:57.393510Z] Loop 1696: Loss: 2.37e-03, Avg Return: 0.488, Regret: 0.3768, Entropy: 0.1232 +[2026-03-20T17:47:58.246516Z] Loop 1697: Loss: 2.62e-03, Avg Return: 0.486, Regret: 0.3768, Entropy: 0.1258 +[2026-03-20T17:47:59.099632Z] Loop 1698: Loss: 2.90e-03, Avg Return: 0.487, Regret: 0.3768, Entropy: 0.1220 +[2026-03-20T17:47:59.952431Z] Loop 1699: Loss: 2.74e-03, Avg Return: 0.486, Regret: 0.3768, Entropy: 0.1305 +[2026-03-20T17:48:00.843717Z] Loop 1700: Loss: 2.91e-03, Avg Return: 0.483, Regret: 0.3759, Entropy: 0.1292 +[2026-03-20T17:48:01.696773Z] Loop 1701: Loss: 3.16e-03, Avg Return: 0.496, Regret: 0.3759, Entropy: 0.1323 +[2026-03-20T17:48:02.550593Z] Loop 1702: Loss: 3.31e-03, Avg Return: 0.483, Regret: 0.3759, Entropy: 0.1307 +[2026-03-20T17:48:03.404621Z] Loop 1703: Loss: 3.90e-03, Avg Return: 0.493, Regret: 0.3759, Entropy: 0.1298 +[2026-03-20T17:48:04.256742Z] Loop 1704: Loss: 3.30e-03, Avg Return: 0.485, Regret: 0.3759, Entropy: 0.1272 +[2026-03-20T17:48:05.150863Z] Loop 1705: Loss: 3.16e-03, Avg Return: 0.495, Regret: 0.3755, Entropy: 0.1206 +[2026-03-20T17:48:06.003920Z] Loop 1706: Loss: 3.60e-03, Avg Return: 0.498, Regret: 0.3755, Entropy: 0.1166 +[2026-03-20T17:48:06.857557Z] Loop 1707: Loss: 3.12e-03, Avg Return: 0.489, Regret: 0.3755, Entropy: 0.1215 +[2026-03-20T17:48:07.710506Z] Loop 1708: Loss: 3.36e-03, Avg Return: 0.490, Regret: 0.3755, Entropy: 0.1152 +[2026-03-20T17:48:08.563149Z] Loop 1709: Loss: 3.45e-03, Avg Return: 0.486, Regret: 0.3755, Entropy: 0.1229 +[2026-03-20T17:48:09.455943Z] Loop 1710: Loss: 3.51e-03, Avg Return: 0.494, Regret: 0.3755, Entropy: 0.1250 +[2026-03-20T17:48:10.309329Z] Loop 1711: Loss: 3.25e-03, Avg Return: 0.482, Regret: 0.3755, Entropy: 0.1337 +[2026-03-20T17:48:11.161769Z] Loop 1712: Loss: 3.43e-03, Avg Return: 0.489, Regret: 0.3755, Entropy: 0.1254 +[2026-03-20T17:48:12.015565Z] Loop 1713: Loss: 3.57e-03, Avg Return: 0.492, Regret: 0.3755, Entropy: 0.1269 +[2026-03-20T17:48:12.868701Z] Loop 1714: Loss: 3.59e-03, Avg Return: 0.485, Regret: 0.3755, Entropy: 0.1232 +[2026-03-20T17:48:13.762320Z] Loop 1715: Loss: 3.91e-03, Avg Return: 0.501, Regret: 0.3755, Entropy: 0.1353 +[2026-03-20T17:48:14.614872Z] Loop 1716: Loss: 3.65e-03, Avg Return: 0.489, Regret: 0.3755, Entropy: 0.1306 +[2026-03-20T17:48:15.466759Z] Loop 1717: Loss: 3.38e-03, Avg Return: 0.487, Regret: 0.3755, Entropy: 0.1350 +[2026-03-20T17:48:16.319195Z] Loop 1718: Loss: 3.88e-03, Avg Return: 0.492, Regret: 0.3755, Entropy: 0.1376 +[2026-03-20T17:48:17.173583Z] Loop 1719: Loss: 3.48e-03, Avg Return: 0.490, Regret: 0.3755, Entropy: 0.1286 +[2026-03-20T17:48:18.066747Z] Loop 1720: Loss: 3.48e-03, Avg Return: 0.490, Regret: 0.3755, Entropy: 0.1283 +[2026-03-20T17:48:18.918818Z] Loop 1721: Loss: 3.57e-03, Avg Return: 0.491, Regret: 0.3755, Entropy: 0.1242 +[2026-03-20T17:48:19.771447Z] Loop 1722: Loss: 3.19e-03, Avg Return: 0.494, Regret: 0.3755, Entropy: 0.1201 +[2026-03-20T17:48:20.625014Z] Loop 1723: Loss: 3.03e-03, Avg Return: 0.483, Regret: 0.3755, Entropy: 0.1191 +[2026-03-20T17:48:21.478756Z] Loop 1724: Loss: 3.22e-03, Avg Return: 0.476, Regret: 0.3755, Entropy: 0.1198 +[2026-03-20T17:48:22.371253Z] Loop 1725: Loss: 3.52e-03, Avg Return: 0.494, Regret: 0.3769, Entropy: 0.1258 +[2026-03-20T17:48:23.223546Z] Loop 1726: Loss: 4.45e-03, Avg Return: 0.491, Regret: 0.3769, Entropy: 0.1359 +[2026-03-20T17:48:24.079373Z] Loop 1727: Loss: 4.24e-03, Avg Return: 0.485, Regret: 0.3769, Entropy: 0.1318 +[2026-03-20T17:48:24.932114Z] Loop 1728: Loss: 4.59e-03, Avg Return: 0.484, Regret: 0.3769, Entropy: 0.1389 +[2026-03-20T17:48:25.785187Z] Loop 1729: Loss: 5.05e-03, Avg Return: 0.482, Regret: 0.3769, Entropy: 0.1437 +[2026-03-20T17:48:26.678913Z] Loop 1730: Loss: 5.12e-03, Avg Return: 0.488, Regret: 0.3785, Entropy: 0.1398 +[2026-03-20T17:48:27.531575Z] Loop 1731: Loss: 5.09e-03, Avg Return: 0.476, Regret: 0.3785, Entropy: 0.1449 +[2026-03-20T17:48:28.384483Z] Loop 1732: Loss: 4.82e-03, Avg Return: 0.477, Regret: 0.3785, Entropy: 0.1428 +[2026-03-20T17:48:29.237675Z] Loop 1733: Loss: 5.47e-03, Avg Return: 0.493, Regret: 0.3785, Entropy: 0.1478 +[2026-03-20T17:48:30.089563Z] Loop 1734: Loss: 4.14e-03, Avg Return: 0.484, Regret: 0.3785, Entropy: 0.1381 +[2026-03-20T17:48:30.982946Z] Loop 1735: Loss: 4.11e-03, Avg Return: 0.478, Regret: 0.3758, Entropy: 0.1310 +[2026-03-20T17:48:31.835872Z] Loop 1736: Loss: 3.70e-03, Avg Return: 0.493, Regret: 0.3758, Entropy: 0.1260 +[2026-03-20T17:48:32.689540Z] Loop 1737: Loss: 3.33e-03, Avg Return: 0.486, Regret: 0.3758, Entropy: 0.1242 +[2026-03-20T17:48:33.542265Z] Loop 1738: Loss: 3.14e-03, Avg Return: 0.491, Regret: 0.3758, Entropy: 0.1179 +[2026-03-20T17:48:34.395465Z] Loop 1739: Loss: 3.26e-03, Avg Return: 0.490, Regret: 0.3758, Entropy: 0.1241 +[2026-03-20T17:48:35.285913Z] Loop 1740: Loss: 2.89e-03, Avg Return: 0.488, Regret: 0.3757, Entropy: 0.1219 +[2026-03-20T17:48:36.137857Z] Loop 1741: Loss: 3.14e-03, Avg Return: 0.488, Regret: 0.3757, Entropy: 0.1194 +[2026-03-20T17:48:36.991278Z] Loop 1742: Loss: 3.28e-03, Avg Return: 0.490, Regret: 0.3757, Entropy: 0.1153 +[2026-03-20T17:48:37.844640Z] Loop 1743: Loss: 3.01e-03, Avg Return: 0.487, Regret: 0.3757, Entropy: 0.1225 +[2026-03-20T17:48:38.697694Z] Loop 1744: Loss: 3.31e-03, Avg Return: 0.484, Regret: 0.3757, Entropy: 0.1221 +[2026-03-20T17:48:39.591219Z] Loop 1745: Loss: 3.25e-03, Avg Return: 0.487, Regret: 0.3759, Entropy: 0.1211 +[2026-03-20T17:48:40.443683Z] Loop 1746: Loss: 3.32e-03, Avg Return: 0.484, Regret: 0.3759, Entropy: 0.1292 +[2026-03-20T17:48:41.296922Z] Loop 1747: Loss: 3.67e-03, Avg Return: 0.487, Regret: 0.3759, Entropy: 0.1250 +[2026-03-20T17:48:42.149374Z] Loop 1748: Loss: 3.45e-03, Avg Return: 0.491, Regret: 0.3759, Entropy: 0.1239 +[2026-03-20T17:48:43.001638Z] Loop 1749: Loss: 3.90e-03, Avg Return: 0.482, Regret: 0.3759, Entropy: 0.1336 +[2026-03-20T17:48:43.892490Z] Loop 1750: Loss: 4.21e-03, Avg Return: 0.488, Regret: 0.3761, Entropy: 0.1344 +[2026-03-20T17:48:44.746345Z] Loop 1751: Loss: 4.22e-03, Avg Return: 0.483, Regret: 0.3761, Entropy: 0.1367 +[2026-03-20T17:48:45.599905Z] Loop 1752: Loss: 4.48e-03, Avg Return: 0.488, Regret: 0.3761, Entropy: 0.1361 +[2026-03-20T17:48:46.452186Z] Loop 1753: Loss: 5.42e-03, Avg Return: 0.482, Regret: 0.3761, Entropy: 0.1502 +[2026-03-20T17:48:47.304616Z] Loop 1754: Loss: 4.94e-03, Avg Return: 0.493, Regret: 0.3761, Entropy: 0.1308 +[2026-03-20T17:48:48.199142Z] Loop 1755: Loss: 4.92e-03, Avg Return: 0.481, Regret: 0.3771, Entropy: 0.1359 +[2026-03-20T17:48:49.052181Z] Loop 1756: Loss: 4.45e-03, Avg Return: 0.493, Regret: 0.3771, Entropy: 0.1302 +[2026-03-20T17:48:49.905482Z] Loop 1757: Loss: 4.99e-03, Avg Return: 0.483, Regret: 0.3771, Entropy: 0.1343 +[2026-03-20T17:48:50.758210Z] Loop 1758: Loss: 4.93e-03, Avg Return: 0.485, Regret: 0.3771, Entropy: 0.1314 +[2026-03-20T17:48:51.611449Z] Loop 1759: Loss: 4.93e-03, Avg Return: 0.486, Regret: 0.3771, Entropy: 0.1327 +[2026-03-20T17:48:52.505109Z] Loop 1760: Loss: 4.91e-03, Avg Return: 0.496, Regret: 0.3767, Entropy: 0.1388 +[2026-03-20T17:48:53.357643Z] Loop 1761: Loss: 4.13e-03, Avg Return: 0.482, Regret: 0.3767, Entropy: 0.1270 +[2026-03-20T17:48:54.210591Z] Loop 1762: Loss: 4.23e-03, Avg Return: 0.485, Regret: 0.3767, Entropy: 0.1269 +[2026-03-20T17:48:55.063813Z] Loop 1763: Loss: 3.94e-03, Avg Return: 0.488, Regret: 0.3767, Entropy: 0.1177 +[2026-03-20T17:48:55.916320Z] Loop 1764: Loss: 3.96e-03, Avg Return: 0.482, Regret: 0.3767, Entropy: 0.1072 +[2026-03-20T17:48:56.810597Z] Loop 1765: Loss: 4.14e-03, Avg Return: 0.474, Regret: 0.3807, Entropy: 0.1086 +[2026-03-20T17:48:57.664797Z] Loop 1766: Loss: 4.50e-03, Avg Return: 0.487, Regret: 0.3807, Entropy: 0.1115 +[2026-03-20T17:48:58.518533Z] Loop 1767: Loss: 4.51e-03, Avg Return: 0.485, Regret: 0.3807, Entropy: 0.1048 +[2026-03-20T17:48:59.371448Z] Loop 1768: Loss: 4.19e-03, Avg Return: 0.487, Regret: 0.3807, Entropy: 0.1063 +[2026-03-20T17:49:00.223822Z] Loop 1769: Loss: 4.31e-03, Avg Return: 0.481, Regret: 0.3807, Entropy: 0.1079 +[2026-03-20T17:49:01.115312Z] Loop 1770: Loss: 4.12e-03, Avg Return: 0.480, Regret: 0.3789, Entropy: 0.1077 +[2026-03-20T17:49:01.969471Z] Loop 1771: Loss: 4.56e-03, Avg Return: 0.487, Regret: 0.3789, Entropy: 0.1161 +[2026-03-20T17:49:02.822837Z] Loop 1772: Loss: 3.79e-03, Avg Return: 0.488, Regret: 0.3789, Entropy: 0.1168 +[2026-03-20T17:49:03.674523Z] Loop 1773: Loss: 4.41e-03, Avg Return: 0.479, Regret: 0.3789, Entropy: 0.1255 +[2026-03-20T17:49:04.527313Z] Loop 1774: Loss: 5.03e-03, Avg Return: 0.483, Regret: 0.3789, Entropy: 0.1427 +[2026-03-20T17:49:05.421427Z] Loop 1775: Loss: 5.08e-03, Avg Return: 0.490, Regret: 0.3756, Entropy: 0.1539 +[2026-03-20T17:49:06.275693Z] Loop 1776: Loss: 4.32e-03, Avg Return: 0.491, Regret: 0.3756, Entropy: 0.1323 +[2026-03-20T17:49:07.128669Z] Loop 1777: Loss: 2.96e-03, Avg Return: 0.490, Regret: 0.3756, Entropy: 0.1234 +[2026-03-20T17:49:07.980838Z] Loop 1778: Loss: 2.57e-03, Avg Return: 0.489, Regret: 0.3756, Entropy: 0.1119 +[2026-03-20T17:49:08.833810Z] Loop 1779: Loss: 2.36e-03, Avg Return: 0.486, Regret: 0.3756, Entropy: 0.1022 +[2026-03-20T17:49:09.727011Z] Loop 1780: Loss: 2.30e-03, Avg Return: 0.486, Regret: 0.3755, Entropy: 0.0996 +[2026-03-20T17:49:10.581197Z] Loop 1781: Loss: 2.24e-03, Avg Return: 0.481, Regret: 0.3755, Entropy: 0.0994 +[2026-03-20T17:49:11.434071Z] Loop 1782: Loss: 2.59e-03, Avg Return: 0.484, Regret: 0.3755, Entropy: 0.1031 +[2026-03-20T17:49:12.288407Z] Loop 1783: Loss: 2.64e-03, Avg Return: 0.486, Regret: 0.3755, Entropy: 0.1047 +[2026-03-20T17:49:13.142029Z] Loop 1784: Loss: 3.04e-03, Avg Return: 0.484, Regret: 0.3755, Entropy: 0.1193 +[2026-03-20T17:49:14.035832Z] Loop 1785: Loss: 3.08e-03, Avg Return: 0.485, Regret: 0.3777, Entropy: 0.1221 +[2026-03-20T17:49:14.889580Z] Loop 1786: Loss: 2.55e-03, Avg Return: 0.484, Regret: 0.3777, Entropy: 0.1167 +[2026-03-20T17:49:15.742557Z] Loop 1787: Loss: 2.12e-03, Avg Return: 0.479, Regret: 0.3777, Entropy: 0.1077 +[2026-03-20T17:49:16.594753Z] Loop 1788: Loss: 1.65e-03, Avg Return: 0.480, Regret: 0.3777, Entropy: 0.0920 +[2026-03-20T17:49:17.446746Z] Loop 1789: Loss: 1.85e-03, Avg Return: 0.483, Regret: 0.3777, Entropy: 0.0887 +[2026-03-20T17:49:18.340623Z] Loop 1790: Loss: 1.66e-03, Avg Return: 0.482, Regret: 0.3818, Entropy: 0.0811 +[2026-03-20T17:49:19.193900Z] Loop 1791: Loss: 1.43e-03, Avg Return: 0.477, Regret: 0.3818, Entropy: 0.0853 +[2026-03-20T17:49:20.046726Z] Loop 1792: Loss: 1.62e-03, Avg Return: 0.476, Regret: 0.3818, Entropy: 0.0851 +[2026-03-20T17:49:20.899156Z] Loop 1793: Loss: 1.81e-03, Avg Return: 0.481, Regret: 0.3818, Entropy: 0.0906 +[2026-03-20T17:49:21.751859Z] Loop 1794: Loss: 1.64e-03, Avg Return: 0.488, Regret: 0.3818, Entropy: 0.0940 +[2026-03-20T17:49:22.644013Z] Loop 1795: Loss: 1.85e-03, Avg Return: 0.487, Regret: 0.3789, Entropy: 0.0930 +[2026-03-20T17:49:23.498671Z] Loop 1796: Loss: 2.14e-03, Avg Return: 0.488, Regret: 0.3789, Entropy: 0.0985 +[2026-03-20T17:49:24.351528Z] Loop 1797: Loss: 2.08e-03, Avg Return: 0.484, Regret: 0.3789, Entropy: 0.1031 +[2026-03-20T17:49:25.205019Z] Loop 1798: Loss: 2.54e-03, Avg Return: 0.488, Regret: 0.3789, Entropy: 0.1046 +[2026-03-20T17:49:26.057367Z] Loop 1799: Loss: 2.92e-03, Avg Return: 0.490, Regret: 0.3789, Entropy: 0.1152 +[2026-03-20T17:49:26.950006Z] Loop 1800: Loss: 3.00e-03, Avg Return: 0.488, Regret: 0.3759, Entropy: 0.1130 +[2026-03-20T17:49:27.803751Z] Loop 1801: Loss: 2.89e-03, Avg Return: 0.490, Regret: 0.3759, Entropy: 0.1215 +[2026-03-20T17:49:28.657835Z] Loop 1802: Loss: 3.55e-03, Avg Return: 0.493, Regret: 0.3759, Entropy: 0.1201 +[2026-03-20T17:49:29.510958Z] Loop 1803: Loss: 3.02e-03, Avg Return: 0.485, Regret: 0.3759, Entropy: 0.1153 +[2026-03-20T17:49:30.364409Z] Loop 1804: Loss: 3.28e-03, Avg Return: 0.485, Regret: 0.3759, Entropy: 0.1163 +[2026-03-20T17:49:31.257898Z] Loop 1805: Loss: 2.71e-03, Avg Return: 0.485, Regret: 0.3755, Entropy: 0.1079 +[2026-03-20T17:49:32.111826Z] Loop 1806: Loss: 2.09e-03, Avg Return: 0.486, Regret: 0.3755, Entropy: 0.1036 +[2026-03-20T17:49:32.965513Z] Loop 1807: Loss: 2.70e-03, Avg Return: 0.494, Regret: 0.3755, Entropy: 0.1013 +[2026-03-20T17:49:33.819993Z] Loop 1808: Loss: 2.31e-03, Avg Return: 0.488, Regret: 0.3755, Entropy: 0.0914 +[2026-03-20T17:49:34.673071Z] Loop 1809: Loss: 2.27e-03, Avg Return: 0.485, Regret: 0.3755, Entropy: 0.0993 +[2026-03-20T17:49:35.567396Z] Loop 1810: Loss: 2.59e-03, Avg Return: 0.481, Regret: 0.3756, Entropy: 0.1038 +[2026-03-20T17:49:36.420078Z] Loop 1811: Loss: 2.84e-03, Avg Return: 0.495, Regret: 0.3756, Entropy: 0.1036 +[2026-03-20T17:49:37.273900Z] Loop 1812: Loss: 2.45e-03, Avg Return: 0.496, Regret: 0.3756, Entropy: 0.1119 +[2026-03-20T17:49:38.126410Z] Loop 1813: Loss: 2.91e-03, Avg Return: 0.491, Regret: 0.3756, Entropy: 0.1075 +[2026-03-20T17:49:38.979473Z] Loop 1814: Loss: 3.16e-03, Avg Return: 0.489, Regret: 0.3756, Entropy: 0.1164 +[2026-03-20T17:49:39.875485Z] Loop 1815: Loss: 3.87e-03, Avg Return: 0.492, Regret: 0.3760, Entropy: 0.1229 +[2026-03-20T17:49:40.730070Z] Loop 1816: Loss: 3.59e-03, Avg Return: 0.486, Regret: 0.3760, Entropy: 0.1287 +[2026-03-20T17:49:41.584825Z] Loop 1817: Loss: 4.82e-03, Avg Return: 0.487, Regret: 0.3760, Entropy: 0.1359 +[2026-03-20T17:49:42.438563Z] Loop 1818: Loss: 5.11e-03, Avg Return: 0.485, Regret: 0.3760, Entropy: 0.1484 +[2026-03-20T17:49:43.292221Z] Loop 1819: Loss: 5.60e-03, Avg Return: 0.494, Regret: 0.3760, Entropy: 0.1521 +[2026-03-20T17:49:44.188431Z] Loop 1820: Loss: 5.53e-03, Avg Return: 0.486, Regret: 0.3773, Entropy: 0.1466 +[2026-03-20T17:49:45.042347Z] Loop 1821: Loss: 5.43e-03, Avg Return: 0.479, Regret: 0.3773, Entropy: 0.1423 +[2026-03-20T17:49:45.896561Z] Loop 1822: Loss: 4.75e-03, Avg Return: 0.484, Regret: 0.3773, Entropy: 0.1274 +[2026-03-20T17:49:46.749386Z] Loop 1823: Loss: 4.46e-03, Avg Return: 0.483, Regret: 0.3773, Entropy: 0.1212 +[2026-03-20T17:49:47.602676Z] Loop 1824: Loss: 4.13e-03, Avg Return: 0.482, Regret: 0.3773, Entropy: 0.1200 +[2026-03-20T17:49:48.499102Z] Loop 1825: Loss: 4.29e-03, Avg Return: 0.486, Regret: 0.3787, Entropy: 0.1131 +[2026-03-20T17:49:49.353829Z] Loop 1826: Loss: 5.44e-03, Avg Return: 0.481, Regret: 0.3787, Entropy: 0.1173 +[2026-03-20T17:49:50.207536Z] Loop 1827: Loss: 5.05e-03, Avg Return: 0.482, Regret: 0.3787, Entropy: 0.1162 +[2026-03-20T17:49:51.061625Z] Loop 1828: Loss: 4.37e-03, Avg Return: 0.478, Regret: 0.3787, Entropy: 0.1100 +[2026-03-20T17:49:51.915681Z] Loop 1829: Loss: 3.90e-03, Avg Return: 0.490, Regret: 0.3787, Entropy: 0.1058 +[2026-03-20T17:49:52.811272Z] Loop 1830: Loss: 3.97e-03, Avg Return: 0.489, Regret: 0.3769, Entropy: 0.1045 +[2026-03-20T17:49:53.664280Z] Loop 1831: Loss: 4.15e-03, Avg Return: 0.491, Regret: 0.3769, Entropy: 0.1087 +[2026-03-20T17:49:54.517007Z] Loop 1832: Loss: 3.58e-03, Avg Return: 0.476, Regret: 0.3769, Entropy: 0.1069 +[2026-03-20T17:49:55.369527Z] Loop 1833: Loss: 3.76e-03, Avg Return: 0.493, Regret: 0.3769, Entropy: 0.1123 +[2026-03-20T17:49:56.222712Z] Loop 1834: Loss: 4.12e-03, Avg Return: 0.490, Regret: 0.3769, Entropy: 0.1185 +[2026-03-20T17:49:57.116233Z] Loop 1835: Loss: 4.49e-03, Avg Return: 0.491, Regret: 0.3758, Entropy: 0.1282 +[2026-03-20T17:49:57.969498Z] Loop 1836: Loss: 5.05e-03, Avg Return: 0.495, Regret: 0.3758, Entropy: 0.1405 +[2026-03-20T17:49:58.822526Z] Loop 1837: Loss: 4.51e-03, Avg Return: 0.490, Regret: 0.3758, Entropy: 0.1447 +[2026-03-20T17:49:59.675698Z] Loop 1838: Loss: 3.55e-03, Avg Return: 0.495, Regret: 0.3758, Entropy: 0.1232 +[2026-03-20T17:50:00.528698Z] Loop 1839: Loss: 2.84e-03, Avg Return: 0.484, Regret: 0.3758, Entropy: 0.1273 +[2026-03-20T17:50:01.421307Z] Loop 1840: Loss: 2.42e-03, Avg Return: 0.484, Regret: 0.3773, Entropy: 0.1136 +[2026-03-20T17:50:02.275040Z] Loop 1841: Loss: 2.40e-03, Avg Return: 0.482, Regret: 0.3773, Entropy: 0.1223 +[2026-03-20T17:50:03.129306Z] Loop 1842: Loss: 2.14e-03, Avg Return: 0.492, Regret: 0.3773, Entropy: 0.1072 +[2026-03-20T17:50:03.981609Z] Loop 1843: Loss: 2.12e-03, Avg Return: 0.484, Regret: 0.3773, Entropy: 0.1038 +[2026-03-20T17:50:04.834404Z] Loop 1844: Loss: 1.94e-03, Avg Return: 0.480, Regret: 0.3773, Entropy: 0.1094 +[2026-03-20T17:50:05.726474Z] Loop 1845: Loss: 1.92e-03, Avg Return: 0.483, Regret: 0.3785, Entropy: 0.0954 +[2026-03-20T17:50:06.578682Z] Loop 1846: Loss: 2.19e-03, Avg Return: 0.486, Regret: 0.3785, Entropy: 0.0944 +[2026-03-20T17:50:07.431392Z] Loop 1847: Loss: 2.21e-03, Avg Return: 0.483, Regret: 0.3785, Entropy: 0.0965 +[2026-03-20T17:50:08.284683Z] Loop 1848: Loss: 2.12e-03, Avg Return: 0.487, Regret: 0.3785, Entropy: 0.0989 +[2026-03-20T17:50:09.138268Z] Loop 1849: Loss: 2.16e-03, Avg Return: 0.482, Regret: 0.3785, Entropy: 0.1023 +[2026-03-20T17:50:10.030573Z] Loop 1850: Loss: 1.95e-03, Avg Return: 0.487, Regret: 0.3781, Entropy: 0.0983 +[2026-03-20T17:50:10.884267Z] Loop 1851: Loss: 2.01e-03, Avg Return: 0.484, Regret: 0.3781, Entropy: 0.0930 +[2026-03-20T17:50:11.737490Z] Loop 1852: Loss: 2.29e-03, Avg Return: 0.484, Regret: 0.3781, Entropy: 0.1030 +[2026-03-20T17:50:12.590104Z] Loop 1853: Loss: 2.50e-03, Avg Return: 0.493, Regret: 0.3781, Entropy: 0.1040 +[2026-03-20T17:50:13.443894Z] Loop 1854: Loss: 2.36e-03, Avg Return: 0.486, Regret: 0.3781, Entropy: 0.1042 +[2026-03-20T17:50:14.340205Z] Loop 1855: Loss: 2.50e-03, Avg Return: 0.486, Regret: 0.3774, Entropy: 0.1079 +[2026-03-20T17:50:15.194885Z] Loop 1856: Loss: 2.72e-03, Avg Return: 0.487, Regret: 0.3774, Entropy: 0.1120 +[2026-03-20T17:50:16.049571Z] Loop 1857: Loss: 2.81e-03, Avg Return: 0.493, Regret: 0.3774, Entropy: 0.1203 +[2026-03-20T17:50:16.903674Z] Loop 1858: Loss: 2.83e-03, Avg Return: 0.478, Regret: 0.3774, Entropy: 0.1214 +[2026-03-20T17:50:17.756455Z] Loop 1859: Loss: 3.08e-03, Avg Return: 0.493, Regret: 0.3774, Entropy: 0.1158 +[2026-03-20T17:50:18.649358Z] Loop 1860: Loss: 2.88e-03, Avg Return: 0.486, Regret: 0.3774, Entropy: 0.1217 +[2026-03-20T17:50:19.502981Z] Loop 1861: Loss: 2.70e-03, Avg Return: 0.490, Regret: 0.3774, Entropy: 0.1189 +[2026-03-20T17:50:20.356035Z] Loop 1862: Loss: 2.82e-03, Avg Return: 0.485, Regret: 0.3774, Entropy: 0.1213 +[2026-03-20T17:50:21.208685Z] Loop 1863: Loss: 3.16e-03, Avg Return: 0.491, Regret: 0.3774, Entropy: 0.1212 +[2026-03-20T17:50:22.062354Z] Loop 1864: Loss: 3.18e-03, Avg Return: 0.487, Regret: 0.3774, Entropy: 0.1170 +[2026-03-20T17:50:22.955249Z] Loop 1865: Loss: 2.95e-03, Avg Return: 0.488, Regret: 0.3762, Entropy: 0.1168 +[2026-03-20T17:50:23.807828Z] Loop 1866: Loss: 2.87e-03, Avg Return: 0.493, Regret: 0.3762, Entropy: 0.1206 +[2026-03-20T17:50:24.661822Z] Loop 1867: Loss: 3.00e-03, Avg Return: 0.489, Regret: 0.3762, Entropy: 0.1207 +[2026-03-20T17:50:25.514607Z] Loop 1868: Loss: 2.98e-03, Avg Return: 0.492, Regret: 0.3762, Entropy: 0.1166 +[2026-03-20T17:50:26.367913Z] Loop 1869: Loss: 2.89e-03, Avg Return: 0.485, Regret: 0.3762, Entropy: 0.1146 +[2026-03-20T17:50:27.260518Z] Loop 1870: Loss: 2.94e-03, Avg Return: 0.484, Regret: 0.3760, Entropy: 0.1228 +[2026-03-20T17:50:28.113898Z] Loop 1871: Loss: 3.10e-03, Avg Return: 0.489, Regret: 0.3760, Entropy: 0.1152 +[2026-03-20T17:50:28.967836Z] Loop 1872: Loss: 3.13e-03, Avg Return: 0.483, Regret: 0.3760, Entropy: 0.1277 +[2026-03-20T17:50:29.821266Z] Loop 1873: Loss: 3.13e-03, Avg Return: 0.486, Regret: 0.3760, Entropy: 0.1179 +[2026-03-20T17:50:30.674397Z] Loop 1874: Loss: 3.15e-03, Avg Return: 0.491, Regret: 0.3760, Entropy: 0.1187 +[2026-03-20T17:50:31.567298Z] Loop 1875: Loss: 2.80e-03, Avg Return: 0.500, Regret: 0.3758, Entropy: 0.1217 +[2026-03-20T17:50:32.420870Z] Loop 1876: Loss: 3.41e-03, Avg Return: 0.488, Regret: 0.3758, Entropy: 0.1237 +[2026-03-20T17:50:33.273589Z] Loop 1877: Loss: 2.87e-03, Avg Return: 0.484, Regret: 0.3758, Entropy: 0.1136 +[2026-03-20T17:50:34.126164Z] Loop 1878: Loss: 3.07e-03, Avg Return: 0.489, Regret: 0.3758, Entropy: 0.1166 +[2026-03-20T17:50:34.979432Z] Loop 1879: Loss: 2.64e-03, Avg Return: 0.486, Regret: 0.3758, Entropy: 0.1101 +[2026-03-20T17:50:35.874406Z] Loop 1880: Loss: 2.89e-03, Avg Return: 0.489, Regret: 0.3758, Entropy: 0.1185 +[2026-03-20T17:50:36.727250Z] Loop 1881: Loss: 2.88e-03, Avg Return: 0.496, Regret: 0.3758, Entropy: 0.1099 +[2026-03-20T17:50:37.579873Z] Loop 1882: Loss: 2.67e-03, Avg Return: 0.488, Regret: 0.3758, Entropy: 0.1079 +[2026-03-20T17:50:38.432683Z] Loop 1883: Loss: 2.56e-03, Avg Return: 0.489, Regret: 0.3758, Entropy: 0.1053 +[2026-03-20T17:50:39.286246Z] Loop 1884: Loss: 2.28e-03, Avg Return: 0.487, Regret: 0.3758, Entropy: 0.1040 +[2026-03-20T17:50:40.179643Z] Loop 1885: Loss: 2.65e-03, Avg Return: 0.491, Regret: 0.3761, Entropy: 0.0980 +[2026-03-20T17:50:41.032613Z] Loop 1886: Loss: 2.30e-03, Avg Return: 0.490, Regret: 0.3761, Entropy: 0.1002 +[2026-03-20T17:50:41.885001Z] Loop 1887: Loss: 2.26e-03, Avg Return: 0.484, Regret: 0.3761, Entropy: 0.0969 +[2026-03-20T17:50:42.736812Z] Loop 1888: Loss: 1.99e-03, Avg Return: 0.480, Regret: 0.3761, Entropy: 0.1009 +[2026-03-20T17:50:43.589741Z] Loop 1889: Loss: 1.92e-03, Avg Return: 0.476, Regret: 0.3761, Entropy: 0.0977 +[2026-03-20T17:50:44.482035Z] Loop 1890: Loss: 2.07e-03, Avg Return: 0.482, Regret: 0.3756, Entropy: 0.1019 +[2026-03-20T17:50:45.335176Z] Loop 1891: Loss: 2.21e-03, Avg Return: 0.486, Regret: 0.3756, Entropy: 0.1023 +[2026-03-20T17:50:46.187746Z] Loop 1892: Loss: 1.94e-03, Avg Return: 0.480, Regret: 0.3756, Entropy: 0.0976 +[2026-03-20T17:50:47.041083Z] Loop 1893: Loss: 2.23e-03, Avg Return: 0.480, Regret: 0.3756, Entropy: 0.1069 +[2026-03-20T17:50:47.894996Z] Loop 1894: Loss: 2.66e-03, Avg Return: 0.491, Regret: 0.3756, Entropy: 0.1091 +[2026-03-20T17:50:48.787426Z] Loop 1895: Loss: 2.68e-03, Avg Return: 0.484, Regret: 0.3757, Entropy: 0.1135 +[2026-03-20T17:50:49.640690Z] Loop 1896: Loss: 2.99e-03, Avg Return: 0.493, Regret: 0.3757, Entropy: 0.1179 +[2026-03-20T17:50:50.494344Z] Loop 1897: Loss: 2.99e-03, Avg Return: 0.494, Regret: 0.3757, Entropy: 0.1154 +[2026-03-20T17:50:51.347966Z] Loop 1898: Loss: 3.11e-03, Avg Return: 0.490, Regret: 0.3757, Entropy: 0.1201 +[2026-03-20T17:50:52.202321Z] Loop 1899: Loss: 3.10e-03, Avg Return: 0.488, Regret: 0.3757, Entropy: 0.1197 +[2026-03-20T17:50:53.092801Z] Loop 1900: Loss: 2.78e-03, Avg Return: 0.490, Regret: 0.3759, Entropy: 0.1167 +[2026-03-20T17:50:53.945600Z] Loop 1901: Loss: 3.08e-03, Avg Return: 0.492, Regret: 0.3759, Entropy: 0.1136 +[2026-03-20T17:50:54.797577Z] Loop 1902: Loss: 3.14e-03, Avg Return: 0.488, Regret: 0.3759, Entropy: 0.1202 +[2026-03-20T17:50:55.650867Z] Loop 1903: Loss: 3.12e-03, Avg Return: 0.489, Regret: 0.3759, Entropy: 0.1129 +[2026-03-20T17:50:56.504681Z] Loop 1904: Loss: 2.81e-03, Avg Return: 0.484, Regret: 0.3759, Entropy: 0.1189 +[2026-03-20T17:50:57.397967Z] Loop 1905: Loss: 2.97e-03, Avg Return: 0.487, Regret: 0.3760, Entropy: 0.1204 +[2026-03-20T17:50:58.251910Z] Loop 1906: Loss: 3.38e-03, Avg Return: 0.492, Regret: 0.3760, Entropy: 0.1124 +[2026-03-20T17:50:59.105826Z] Loop 1907: Loss: 3.28e-03, Avg Return: 0.489, Regret: 0.3760, Entropy: 0.1063 +[2026-03-20T17:50:59.959295Z] Loop 1908: Loss: 2.42e-03, Avg Return: 0.492, Regret: 0.3760, Entropy: 0.1029 +[2026-03-20T17:51:00.813307Z] Loop 1909: Loss: 2.29e-03, Avg Return: 0.495, Regret: 0.3760, Entropy: 0.1045 +[2026-03-20T17:51:01.706642Z] Loop 1910: Loss: 2.34e-03, Avg Return: 0.484, Regret: 0.3763, Entropy: 0.1009 +[2026-03-20T17:51:02.560189Z] Loop 1911: Loss: 2.33e-03, Avg Return: 0.482, Regret: 0.3763, Entropy: 0.1017 +[2026-03-20T17:51:03.413524Z] Loop 1912: Loss: 2.37e-03, Avg Return: 0.496, Regret: 0.3763, Entropy: 0.0955 +[2026-03-20T17:51:04.267143Z] Loop 1913: Loss: 2.54e-03, Avg Return: 0.492, Regret: 0.3763, Entropy: 0.1020 +[2026-03-20T17:51:05.119377Z] Loop 1914: Loss: 2.43e-03, Avg Return: 0.484, Regret: 0.3763, Entropy: 0.0985 +[2026-03-20T17:51:06.011261Z] Loop 1915: Loss: 3.04e-03, Avg Return: 0.485, Regret: 0.3760, Entropy: 0.1038 +[2026-03-20T17:51:06.865040Z] Loop 1916: Loss: 2.92e-03, Avg Return: 0.492, Regret: 0.3760, Entropy: 0.1127 +[2026-03-20T17:51:07.718406Z] Loop 1917: Loss: 3.47e-03, Avg Return: 0.493, Regret: 0.3760, Entropy: 0.1158 +[2026-03-20T17:51:08.572385Z] Loop 1918: Loss: 2.98e-03, Avg Return: 0.487, Regret: 0.3760, Entropy: 0.1193 +[2026-03-20T17:51:09.425624Z] Loop 1919: Loss: 3.16e-03, Avg Return: 0.488, Regret: 0.3760, Entropy: 0.1215 +[2026-03-20T17:51:10.319279Z] Loop 1920: Loss: 3.22e-03, Avg Return: 0.492, Regret: 0.3755, Entropy: 0.1176 +[2026-03-20T17:51:11.172792Z] Loop 1921: Loss: 3.15e-03, Avg Return: 0.480, Regret: 0.3755, Entropy: 0.1228 +[2026-03-20T17:51:12.026884Z] Loop 1922: Loss: 3.18e-03, Avg Return: 0.499, Regret: 0.3755, Entropy: 0.1202 +[2026-03-20T17:51:12.879963Z] Loop 1923: Loss: 3.45e-03, Avg Return: 0.493, Regret: 0.3755, Entropy: 0.1232 +[2026-03-20T17:51:13.733028Z] Loop 1924: Loss: 3.30e-03, Avg Return: 0.490, Regret: 0.3755, Entropy: 0.1275 +[2026-03-20T17:51:14.628621Z] Loop 1925: Loss: 2.99e-03, Avg Return: 0.485, Regret: 0.3754, Entropy: 0.1219 +[2026-03-20T17:51:15.482445Z] Loop 1926: Loss: 3.08e-03, Avg Return: 0.488, Regret: 0.3754, Entropy: 0.1192 +[2026-03-20T17:51:16.335902Z] Loop 1927: Loss: 2.74e-03, Avg Return: 0.484, Regret: 0.3754, Entropy: 0.1175 +[2026-03-20T17:51:17.189096Z] Loop 1928: Loss: 2.91e-03, Avg Return: 0.488, Regret: 0.3754, Entropy: 0.1208 +[2026-03-20T17:51:18.042514Z] Loop 1929: Loss: 3.06e-03, Avg Return: 0.484, Regret: 0.3754, Entropy: 0.1184 +[2026-03-20T17:51:18.933474Z] Loop 1930: Loss: 2.76e-03, Avg Return: 0.494, Regret: 0.3755, Entropy: 0.1197 +[2026-03-20T17:51:19.786788Z] Loop 1931: Loss: 2.47e-03, Avg Return: 0.488, Regret: 0.3755, Entropy: 0.1213 +[2026-03-20T17:51:20.640302Z] Loop 1932: Loss: 2.39e-03, Avg Return: 0.489, Regret: 0.3755, Entropy: 0.1184 +[2026-03-20T17:51:21.493623Z] Loop 1933: Loss: 2.30e-03, Avg Return: 0.485, Regret: 0.3755, Entropy: 0.1188 +[2026-03-20T17:51:22.345939Z] Loop 1934: Loss: 2.12e-03, Avg Return: 0.486, Regret: 0.3755, Entropy: 0.1176 +[2026-03-20T17:51:23.241196Z] Loop 1935: Loss: 2.74e-03, Avg Return: 0.485, Regret: 0.3756, Entropy: 0.1187 +[2026-03-20T17:51:24.094995Z] Loop 1936: Loss: 2.52e-03, Avg Return: 0.492, Regret: 0.3756, Entropy: 0.1236 +[2026-03-20T17:51:24.949079Z] Loop 1937: Loss: 3.13e-03, Avg Return: 0.492, Regret: 0.3756, Entropy: 0.1207 +[2026-03-20T17:51:25.802780Z] Loop 1938: Loss: 3.10e-03, Avg Return: 0.488, Regret: 0.3756, Entropy: 0.1327 +[2026-03-20T17:51:26.656814Z] Loop 1939: Loss: 3.66e-03, Avg Return: 0.494, Regret: 0.3756, Entropy: 0.1394 +[2026-03-20T17:51:27.551126Z] Loop 1940: Loss: 3.90e-03, Avg Return: 0.491, Regret: 0.3755, Entropy: 0.1423 +[2026-03-20T17:51:28.405966Z] Loop 1941: Loss: 3.71e-03, Avg Return: 0.485, Regret: 0.3755, Entropy: 0.1458 +[2026-03-20T17:51:29.259003Z] Loop 1942: Loss: 3.88e-03, Avg Return: 0.493, Regret: 0.3755, Entropy: 0.1401 +[2026-03-20T17:51:30.112786Z] Loop 1943: Loss: 3.38e-03, Avg Return: 0.497, Regret: 0.3755, Entropy: 0.1385 +[2026-03-20T17:51:30.966746Z] Loop 1944: Loss: 3.54e-03, Avg Return: 0.490, Regret: 0.3755, Entropy: 0.1334 +[2026-03-20T17:51:31.860780Z] Loop 1945: Loss: 3.44e-03, Avg Return: 0.487, Regret: 0.3755, Entropy: 0.1259 +[2026-03-20T17:51:32.713680Z] Loop 1946: Loss: 3.09e-03, Avg Return: 0.482, Regret: 0.3755, Entropy: 0.1297 +[2026-03-20T17:51:33.566116Z] Loop 1947: Loss: 2.81e-03, Avg Return: 0.493, Regret: 0.3755, Entropy: 0.1351 +[2026-03-20T17:51:34.418714Z] Loop 1948: Loss: 3.04e-03, Avg Return: 0.481, Regret: 0.3755, Entropy: 0.1329 +[2026-03-20T17:51:35.272494Z] Loop 1949: Loss: 3.33e-03, Avg Return: 0.487, Regret: 0.3755, Entropy: 0.1357 +[2026-03-20T17:51:36.164557Z] Loop 1950: Loss: 3.26e-03, Avg Return: 0.490, Regret: 0.3756, Entropy: 0.1373 +[2026-03-20T17:51:37.017574Z] Loop 1951: Loss: 3.59e-03, Avg Return: 0.495, Regret: 0.3756, Entropy: 0.1383 +[2026-03-20T17:51:37.870176Z] Loop 1952: Loss: 4.09e-03, Avg Return: 0.480, Regret: 0.3756, Entropy: 0.1426 +[2026-03-20T17:51:38.723990Z] Loop 1953: Loss: 4.21e-03, Avg Return: 0.478, Regret: 0.3756, Entropy: 0.1433 +[2026-03-20T17:51:39.577545Z] Loop 1954: Loss: 4.06e-03, Avg Return: 0.486, Regret: 0.3756, Entropy: 0.1348 +[2026-03-20T17:51:40.469867Z] Loop 1955: Loss: 3.93e-03, Avg Return: 0.496, Regret: 0.3756, Entropy: 0.1419 +[2026-03-20T17:51:41.321377Z] Loop 1956: Loss: 3.75e-03, Avg Return: 0.484, Regret: 0.3756, Entropy: 0.1376 +[2026-03-20T17:51:42.173439Z] Loop 1957: Loss: 3.98e-03, Avg Return: 0.483, Regret: 0.3756, Entropy: 0.1377 +[2026-03-20T17:51:43.026524Z] Loop 1958: Loss: 4.39e-03, Avg Return: 0.491, Regret: 0.3756, Entropy: 0.1380 +[2026-03-20T17:51:43.879343Z] Loop 1959: Loss: 4.15e-03, Avg Return: 0.480, Regret: 0.3756, Entropy: 0.1443 +[2026-03-20T17:51:44.771548Z] Loop 1960: Loss: 4.62e-03, Avg Return: 0.486, Regret: 0.3756, Entropy: 0.1395 +[2026-03-20T17:51:45.624881Z] Loop 1961: Loss: 4.31e-03, Avg Return: 0.487, Regret: 0.3756, Entropy: 0.1464 +[2026-03-20T17:51:46.478251Z] Loop 1962: Loss: 4.19e-03, Avg Return: 0.486, Regret: 0.3756, Entropy: 0.1408 +[2026-03-20T17:51:47.330606Z] Loop 1963: Loss: 4.05e-03, Avg Return: 0.494, Regret: 0.3756, Entropy: 0.1386 +[2026-03-20T17:51:48.183315Z] Loop 1964: Loss: 3.59e-03, Avg Return: 0.492, Regret: 0.3756, Entropy: 0.1354 +[2026-03-20T17:51:49.074645Z] Loop 1965: Loss: 3.82e-03, Avg Return: 0.486, Regret: 0.3755, Entropy: 0.1274 +[2026-03-20T17:51:49.927633Z] Loop 1966: Loss: 3.16e-03, Avg Return: 0.487, Regret: 0.3755, Entropy: 0.1314 +[2026-03-20T17:51:50.780464Z] Loop 1967: Loss: 3.44e-03, Avg Return: 0.485, Regret: 0.3755, Entropy: 0.1265 +[2026-03-20T17:51:51.633742Z] Loop 1968: Loss: 3.46e-03, Avg Return: 0.493, Regret: 0.3755, Entropy: 0.1226 +[2026-03-20T17:51:52.487051Z] Loop 1969: Loss: 2.86e-03, Avg Return: 0.489, Regret: 0.3755, Entropy: 0.1240 +[2026-03-20T17:51:53.380284Z] Loop 1970: Loss: 3.10e-03, Avg Return: 0.487, Regret: 0.3754, Entropy: 0.1255 +[2026-03-20T17:51:54.233069Z] Loop 1971: Loss: 2.99e-03, Avg Return: 0.489, Regret: 0.3754, Entropy: 0.1288 +[2026-03-20T17:51:55.086074Z] Loop 1972: Loss: 3.48e-03, Avg Return: 0.483, Regret: 0.3754, Entropy: 0.1266 +[2026-03-20T17:51:55.939836Z] Loop 1973: Loss: 4.23e-03, Avg Return: 0.492, Regret: 0.3754, Entropy: 0.1404 +[2026-03-20T17:51:56.792185Z] Loop 1974: Loss: 4.65e-03, Avg Return: 0.487, Regret: 0.3754, Entropy: 0.1497 +[2026-03-20T17:51:57.683757Z] Loop 1975: Loss: 5.15e-03, Avg Return: 0.491, Regret: 0.3755, Entropy: 0.1523 +[2026-03-20T17:51:58.536744Z] Loop 1976: Loss: 5.34e-03, Avg Return: 0.484, Regret: 0.3755, Entropy: 0.1492 +[2026-03-20T17:51:59.391099Z] Loop 1977: Loss: 5.82e-03, Avg Return: 0.489, Regret: 0.3755, Entropy: 0.1498 +[2026-03-20T17:52:00.244560Z] Loop 1978: Loss: 5.12e-03, Avg Return: 0.481, Regret: 0.3755, Entropy: 0.1528 +[2026-03-20T17:52:01.097143Z] Loop 1979: Loss: 5.24e-03, Avg Return: 0.494, Regret: 0.3755, Entropy: 0.1520 +[2026-03-20T17:52:01.990546Z] Loop 1980: Loss: 5.34e-03, Avg Return: 0.494, Regret: 0.3757, Entropy: 0.1468 +[2026-03-20T17:52:02.844839Z] Loop 1981: Loss: 4.75e-03, Avg Return: 0.486, Regret: 0.3757, Entropy: 0.1406 +[2026-03-20T17:52:03.698328Z] Loop 1982: Loss: 4.93e-03, Avg Return: 0.483, Regret: 0.3757, Entropy: 0.1261 +[2026-03-20T17:52:04.550537Z] Loop 1983: Loss: 4.59e-03, Avg Return: 0.493, Regret: 0.3757, Entropy: 0.1174 +[2026-03-20T17:52:05.403661Z] Loop 1984: Loss: 4.25e-03, Avg Return: 0.486, Regret: 0.3757, Entropy: 0.1124 +[2026-03-20T17:52:06.296926Z] Loop 1985: Loss: 4.62e-03, Avg Return: 0.487, Regret: 0.3776, Entropy: 0.1125 +[2026-03-20T17:52:07.149953Z] Loop 1986: Loss: 3.95e-03, Avg Return: 0.485, Regret: 0.3776, Entropy: 0.1116 +[2026-03-20T17:52:08.004355Z] Loop 1987: Loss: 4.41e-03, Avg Return: 0.498, Regret: 0.3776, Entropy: 0.1093 +[2026-03-20T17:52:08.856721Z] Loop 1988: Loss: 4.49e-03, Avg Return: 0.485, Regret: 0.3776, Entropy: 0.1034 +[2026-03-20T17:52:09.710716Z] Loop 1989: Loss: 4.60e-03, Avg Return: 0.486, Regret: 0.3776, Entropy: 0.1098 +[2026-03-20T17:52:10.604744Z] Loop 1990: Loss: 4.40e-03, Avg Return: 0.487, Regret: 0.3789, Entropy: 0.1085 +[2026-03-20T17:52:11.457960Z] Loop 1991: Loss: 4.34e-03, Avg Return: 0.478, Regret: 0.3789, Entropy: 0.1036 +[2026-03-20T17:52:12.311531Z] Loop 1992: Loss: 4.63e-03, Avg Return: 0.491, Regret: 0.3789, Entropy: 0.1093 +[2026-03-20T17:52:13.166185Z] Loop 1993: Loss: 3.98e-03, Avg Return: 0.487, Regret: 0.3789, Entropy: 0.1032 +[2026-03-20T17:52:14.020349Z] Loop 1994: Loss: 4.50e-03, Avg Return: 0.489, Regret: 0.3789, Entropy: 0.1044 +[2026-03-20T17:52:14.913774Z] Loop 1995: Loss: 4.17e-03, Avg Return: 0.485, Regret: 0.3772, Entropy: 0.1070 +[2026-03-20T17:52:15.767106Z] Loop 1996: Loss: 4.04e-03, Avg Return: 0.482, Regret: 0.3772, Entropy: 0.1081 +[2026-03-20T17:52:16.621738Z] Loop 1997: Loss: 4.38e-03, Avg Return: 0.490, Regret: 0.3772, Entropy: 0.1105 +[2026-03-20T17:52:17.475268Z] Loop 1998: Loss: 3.80e-03, Avg Return: 0.491, Regret: 0.3772, Entropy: 0.1070 +[2026-03-20T17:52:18.328932Z] Loop 1999: Loss: 4.09e-03, Avg Return: 0.486, Regret: 0.3772, Entropy: 0.1177 +[2026-03-20T17:52:19.223271Z] Loop 2000: Loss: 4.07e-03, Avg Return: 0.490, Regret: 0.3760, Entropy: 0.1134 +[2026-03-20T17:52:20.077667Z] Loop 2001: Loss: 4.05e-03, Avg Return: 0.489, Regret: 0.3760, Entropy: 0.1240 +[2026-03-20T17:52:20.931617Z] Loop 2002: Loss: 4.05e-03, Avg Return: 0.497, Regret: 0.3760, Entropy: 0.1202 +[2026-03-20T17:52:21.785956Z] Loop 2003: Loss: 4.20e-03, Avg Return: 0.493, Regret: 0.3760, Entropy: 0.1209 +[2026-03-20T17:52:22.640946Z] Loop 2004: Loss: 4.51e-03, Avg Return: 0.488, Regret: 0.3760, Entropy: 0.1263 +[2026-03-20T17:52:23.495586Z] Loop 2005: Loss: 3.87e-03, Avg Return: 0.483, Regret: 0.3760, Entropy: 0.1244 +[2026-03-20T17:52:24.348426Z] Loop 2006: Loss: 4.99e-03, Avg Return: 0.492, Regret: 0.3760, Entropy: 0.1390 +[2026-03-20T17:52:25.201278Z] Loop 2007: Loss: 4.55e-03, Avg Return: 0.486, Regret: 0.3760, Entropy: 0.1349 +[2026-03-20T17:52:26.053991Z] Loop 2008: Loss: 4.04e-03, Avg Return: 0.486, Regret: 0.3760, Entropy: 0.1412 +[2026-03-20T17:52:26.907205Z] Loop 2009: Loss: 4.14e-03, Avg Return: 0.487, Regret: 0.3760, Entropy: 0.1367 +[2026-03-20T17:52:27.798767Z] Loop 2010: Loss: 4.16e-03, Avg Return: 0.489, Regret: 0.3753, Entropy: 0.1303 +[2026-03-20T17:52:28.650349Z] Loop 2011: Loss: 3.93e-03, Avg Return: 0.494, Regret: 0.3753, Entropy: 0.1241 +[2026-03-20T17:52:29.502359Z] Loop 2012: Loss: 3.74e-03, Avg Return: 0.485, Regret: 0.3753, Entropy: 0.1284 +[2026-03-20T17:52:30.355562Z] Loop 2013: Loss: 3.51e-03, Avg Return: 0.479, Regret: 0.3753, Entropy: 0.1266 +[2026-03-20T17:52:31.209180Z] Loop 2014: Loss: 3.72e-03, Avg Return: 0.480, Regret: 0.3753, Entropy: 0.1304 +[2026-03-20T17:52:32.061249Z] Loop 2015: Loss: 4.33e-03, Avg Return: 0.493, Regret: 0.3753, Entropy: 0.1382 +[2026-03-20T17:52:32.912848Z] Loop 2016: Loss: 4.49e-03, Avg Return: 0.494, Regret: 0.3753, Entropy: 0.1354 +[2026-03-20T17:52:33.765209Z] Loop 2017: Loss: 4.47e-03, Avg Return: 0.490, Regret: 0.3753, Entropy: 0.1329 +[2026-03-20T17:52:34.619251Z] Loop 2018: Loss: 4.20e-03, Avg Return: 0.487, Regret: 0.3753, Entropy: 0.1345 +[2026-03-20T17:52:35.472409Z] Loop 2019: Loss: 4.12e-03, Avg Return: 0.485, Regret: 0.3753, Entropy: 0.1297 +[2026-03-20T17:52:36.364355Z] Loop 2020: Loss: 4.42e-03, Avg Return: 0.483, Regret: 0.3755, Entropy: 0.1295 +[2026-03-20T17:52:37.217057Z] Loop 2021: Loss: 4.24e-03, Avg Return: 0.484, Regret: 0.3755, Entropy: 0.1260 +[2026-03-20T17:52:38.070177Z] Loop 2022: Loss: 3.97e-03, Avg Return: 0.490, Regret: 0.3755, Entropy: 0.1266 +[2026-03-20T17:52:38.923563Z] Loop 2023: Loss: 4.71e-03, Avg Return: 0.487, Regret: 0.3755, Entropy: 0.1239 +[2026-03-20T17:52:39.776186Z] Loop 2024: Loss: 4.43e-03, Avg Return: 0.496, Regret: 0.3755, Entropy: 0.1271 +[2026-03-20T17:52:40.629366Z] Loop 2025: Loss: 3.89e-03, Avg Return: 0.486, Regret: 0.3755, Entropy: 0.1215 +[2026-03-20T17:52:41.482472Z] Loop 2026: Loss: 3.28e-03, Avg Return: 0.488, Regret: 0.3755, Entropy: 0.1179 +[2026-03-20T17:52:42.335091Z] Loop 2027: Loss: 2.65e-03, Avg Return: 0.484, Regret: 0.3755, Entropy: 0.1054 +[2026-03-20T17:52:43.187355Z] Loop 2028: Loss: 2.13e-03, Avg Return: 0.485, Regret: 0.3755, Entropy: 0.0940 +[2026-03-20T17:52:44.039011Z] Loop 2029: Loss: 2.16e-03, Avg Return: 0.493, Regret: 0.3755, Entropy: 0.0839 +[2026-03-20T17:52:44.932428Z] Loop 2030: Loss: 1.87e-03, Avg Return: 0.490, Regret: 0.3754, Entropy: 0.0841 +[2026-03-20T17:52:45.786745Z] Loop 2031: Loss: 1.93e-03, Avg Return: 0.486, Regret: 0.3754, Entropy: 0.0883 +[2026-03-20T17:52:46.640656Z] Loop 2032: Loss: 1.88e-03, Avg Return: 0.488, Regret: 0.3754, Entropy: 0.0895 +[2026-03-20T17:52:47.493684Z] Loop 2033: Loss: 1.92e-03, Avg Return: 0.479, Regret: 0.3754, Entropy: 0.0886 +[2026-03-20T17:52:48.347723Z] Loop 2034: Loss: 1.78e-03, Avg Return: 0.489, Regret: 0.3754, Entropy: 0.0896 +[2026-03-20T17:52:49.201586Z] Loop 2035: Loss: 1.72e-03, Avg Return: 0.493, Regret: 0.3754, Entropy: 0.0852 +[2026-03-20T17:52:50.055409Z] Loop 2036: Loss: 1.94e-03, Avg Return: 0.489, Regret: 0.3754, Entropy: 0.0915 +[2026-03-20T17:52:50.908301Z] Loop 2037: Loss: 1.92e-03, Avg Return: 0.488, Regret: 0.3754, Entropy: 0.0843 +[2026-03-20T17:52:51.761613Z] Loop 2038: Loss: 1.89e-03, Avg Return: 0.485, Regret: 0.3754, Entropy: 0.0912 +[2026-03-20T17:52:52.614129Z] Loop 2039: Loss: 1.81e-03, Avg Return: 0.485, Regret: 0.3754, Entropy: 0.0875 +[2026-03-20T17:52:53.506107Z] Loop 2040: Loss: 1.63e-03, Avg Return: 0.489, Regret: 0.3755, Entropy: 0.0872 +[2026-03-20T17:52:54.359631Z] Loop 2041: Loss: 1.70e-03, Avg Return: 0.488, Regret: 0.3755, Entropy: 0.0904 +[2026-03-20T17:52:55.213851Z] Loop 2042: Loss: 1.68e-03, Avg Return: 0.485, Regret: 0.3755, Entropy: 0.0904 +[2026-03-20T17:52:56.067193Z] Loop 2043: Loss: 1.75e-03, Avg Return: 0.491, Regret: 0.3755, Entropy: 0.0931 +[2026-03-20T17:52:56.920830Z] Loop 2044: Loss: 1.88e-03, Avg Return: 0.497, Regret: 0.3755, Entropy: 0.0915 +[2026-03-20T17:52:57.775304Z] Loop 2045: Loss: 2.00e-03, Avg Return: 0.495, Regret: 0.3755, Entropy: 0.0959 +[2026-03-20T17:52:58.628494Z] Loop 2046: Loss: 1.96e-03, Avg Return: 0.491, Regret: 0.3755, Entropy: 0.0978 +[2026-03-20T17:52:59.481039Z] Loop 2047: Loss: 1.91e-03, Avg Return: 0.492, Regret: 0.3755, Entropy: 0.1001 +[2026-03-20T17:53:00.333249Z] Loop 2048: Loss: 1.88e-03, Avg Return: 0.486, Regret: 0.3755, Entropy: 0.0955 +[2026-03-20T17:53:01.185844Z] Loop 2049: Loss: 2.45e-03, Avg Return: 0.492, Regret: 0.3755, Entropy: 0.1008 +[2026-03-20T17:53:02.077136Z] Loop 2050: Loss: 1.93e-03, Avg Return: 0.482, Regret: 0.3757, Entropy: 0.0988 +[2026-03-20T17:53:02.930973Z] Loop 2051: Loss: 1.91e-03, Avg Return: 0.492, Regret: 0.3757, Entropy: 0.0971 +[2026-03-20T17:53:03.784228Z] Loop 2052: Loss: 1.65e-03, Avg Return: 0.491, Regret: 0.3757, Entropy: 0.0952 +[2026-03-20T17:53:04.637626Z] Loop 2053: Loss: 1.80e-03, Avg Return: 0.483, Regret: 0.3757, Entropy: 0.0937 +[2026-03-20T17:53:05.491396Z] Loop 2054: Loss: 1.84e-03, Avg Return: 0.493, Regret: 0.3757, Entropy: 0.0937 +[2026-03-20T17:53:06.344621Z] Loop 2055: Loss: 1.74e-03, Avg Return: 0.485, Regret: 0.3757, Entropy: 0.0915 +[2026-03-20T17:53:07.197259Z] Loop 2056: Loss: 1.69e-03, Avg Return: 0.491, Regret: 0.3757, Entropy: 0.0917 +[2026-03-20T17:53:08.049973Z] Loop 2057: Loss: 1.96e-03, Avg Return: 0.488, Regret: 0.3757, Entropy: 0.0921 +[2026-03-20T17:53:08.903137Z] Loop 2058: Loss: 2.03e-03, Avg Return: 0.479, Regret: 0.3757, Entropy: 0.0921 +[2026-03-20T17:53:09.755837Z] Loop 2059: Loss: 1.86e-03, Avg Return: 0.486, Regret: 0.3757, Entropy: 0.0907 +[2026-03-20T17:53:10.647779Z] Loop 2060: Loss: 2.21e-03, Avg Return: 0.490, Regret: 0.3759, Entropy: 0.0957 +[2026-03-20T17:53:11.501166Z] Loop 2061: Loss: 1.89e-03, Avg Return: 0.483, Regret: 0.3759, Entropy: 0.0899 +[2026-03-20T17:53:12.354541Z] Loop 2062: Loss: 1.93e-03, Avg Return: 0.496, Regret: 0.3759, Entropy: 0.0895 +[2026-03-20T17:53:13.207159Z] Loop 2063: Loss: 1.89e-03, Avg Return: 0.480, Regret: 0.3759, Entropy: 0.0990 +[2026-03-20T17:53:14.060703Z] Loop 2064: Loss: 1.85e-03, Avg Return: 0.488, Regret: 0.3759, Entropy: 0.0981 +[2026-03-20T17:53:14.913090Z] Loop 2065: Loss: 1.92e-03, Avg Return: 0.494, Regret: 0.3759, Entropy: 0.1033 +[2026-03-20T17:53:15.765876Z] Loop 2066: Loss: 2.09e-03, Avg Return: 0.482, Regret: 0.3759, Entropy: 0.1016 +[2026-03-20T17:53:16.619278Z] Loop 2067: Loss: 2.49e-03, Avg Return: 0.481, Regret: 0.3759, Entropy: 0.1088 +[2026-03-20T17:53:17.472750Z] Loop 2068: Loss: 2.38e-03, Avg Return: 0.480, Regret: 0.3759, Entropy: 0.1131 +[2026-03-20T17:53:18.325105Z] Loop 2069: Loss: 2.64e-03, Avg Return: 0.486, Regret: 0.3759, Entropy: 0.1113 +[2026-03-20T17:53:19.216288Z] Loop 2070: Loss: 2.26e-03, Avg Return: 0.489, Regret: 0.3754, Entropy: 0.1155 +[2026-03-20T17:53:20.069003Z] Loop 2071: Loss: 2.14e-03, Avg Return: 0.492, Regret: 0.3754, Entropy: 0.1049 +[2026-03-20T17:53:20.923174Z] Loop 2072: Loss: 2.06e-03, Avg Return: 0.484, Regret: 0.3754, Entropy: 0.0993 +[2026-03-20T17:53:21.775593Z] Loop 2073: Loss: 1.91e-03, Avg Return: 0.489, Regret: 0.3754, Entropy: 0.1040 +[2026-03-20T17:53:22.627742Z] Loop 2074: Loss: 1.95e-03, Avg Return: 0.480, Regret: 0.3754, Entropy: 0.1043 +[2026-03-20T17:53:23.480021Z] Loop 2075: Loss: 1.83e-03, Avg Return: 0.490, Regret: 0.3754, Entropy: 0.1062 +[2026-03-20T17:53:24.333808Z] Loop 2076: Loss: 1.98e-03, Avg Return: 0.486, Regret: 0.3754, Entropy: 0.0954 +[2026-03-20T17:53:25.186586Z] Loop 2077: Loss: 2.15e-03, Avg Return: 0.491, Regret: 0.3754, Entropy: 0.1009 +[2026-03-20T17:53:26.039517Z] Loop 2078: Loss: 1.99e-03, Avg Return: 0.486, Regret: 0.3754, Entropy: 0.1010 +[2026-03-20T17:53:26.892145Z] Loop 2079: Loss: 1.84e-03, Avg Return: 0.488, Regret: 0.3754, Entropy: 0.1005 +[2026-03-20T17:53:27.784674Z] Loop 2080: Loss: 1.45e-03, Avg Return: 0.491, Regret: 0.3753, Entropy: 0.0929 +[2026-03-20T17:53:28.638293Z] Loop 2081: Loss: 1.64e-03, Avg Return: 0.482, Regret: 0.3753, Entropy: 0.0975 +[2026-03-20T17:53:29.492209Z] Loop 2082: Loss: 1.79e-03, Avg Return: 0.487, Regret: 0.3753, Entropy: 0.0863 +[2026-03-20T17:53:30.344689Z] Loop 2083: Loss: 1.95e-03, Avg Return: 0.493, Regret: 0.3753, Entropy: 0.0931 +[2026-03-20T17:53:31.198210Z] Loop 2084: Loss: 2.19e-03, Avg Return: 0.490, Regret: 0.3753, Entropy: 0.0919 +[2026-03-20T17:53:32.051997Z] Loop 2085: Loss: 2.26e-03, Avg Return: 0.493, Regret: 0.3753, Entropy: 0.0906 +[2026-03-20T17:53:32.905116Z] Loop 2086: Loss: 2.16e-03, Avg Return: 0.489, Regret: 0.3753, Entropy: 0.0905 +[2026-03-20T17:53:33.758011Z] Loop 2087: Loss: 2.23e-03, Avg Return: 0.482, Regret: 0.3753, Entropy: 0.0968 +[2026-03-20T17:53:34.611094Z] Loop 2088: Loss: 2.08e-03, Avg Return: 0.488, Regret: 0.3753, Entropy: 0.0932 +[2026-03-20T17:53:35.463687Z] Loop 2089: Loss: 2.38e-03, Avg Return: 0.488, Regret: 0.3753, Entropy: 0.0869 +[2026-03-20T17:53:36.356004Z] Loop 2090: Loss: 2.00e-03, Avg Return: 0.485, Regret: 0.3754, Entropy: 0.0894 +[2026-03-20T17:53:37.210193Z] Loop 2091: Loss: 1.86e-03, Avg Return: 0.476, Regret: 0.3754, Entropy: 0.0932 +[2026-03-20T17:53:38.063928Z] Loop 2092: Loss: 2.02e-03, Avg Return: 0.487, Regret: 0.3754, Entropy: 0.0980 +[2026-03-20T17:53:38.916740Z] Loop 2093: Loss: 1.93e-03, Avg Return: 0.486, Regret: 0.3754, Entropy: 0.0875 +[2026-03-20T17:53:39.770190Z] Loop 2094: Loss: 2.11e-03, Avg Return: 0.495, Regret: 0.3754, Entropy: 0.0857 +[2026-03-20T17:53:40.623932Z] Loop 2095: Loss: 1.64e-03, Avg Return: 0.500, Regret: 0.3754, Entropy: 0.0904 +[2026-03-20T17:53:41.478369Z] Loop 2096: Loss: 1.89e-03, Avg Return: 0.497, Regret: 0.3754, Entropy: 0.0869 +[2026-03-20T17:53:42.331651Z] Loop 2097: Loss: 2.02e-03, Avg Return: 0.482, Regret: 0.3754, Entropy: 0.0988 +[2026-03-20T17:53:43.185113Z] Loop 2098: Loss: 2.47e-03, Avg Return: 0.488, Regret: 0.3754, Entropy: 0.1104 +[2026-03-20T17:53:44.038559Z] Loop 2099: Loss: 3.11e-03, Avg Return: 0.495, Regret: 0.3754, Entropy: 0.1235 +[2026-03-20T17:53:44.930237Z] Loop 2100: Loss: 4.04e-03, Avg Return: 0.489, Regret: 0.3754, Entropy: 0.1217 +[2026-03-20T17:53:45.783884Z] Loop 2101: Loss: 5.08e-03, Avg Return: 0.493, Regret: 0.3754, Entropy: 0.1291 +[2026-03-20T17:53:46.636946Z] Loop 2102: Loss: 3.73e-03, Avg Return: 0.480, Regret: 0.3754, Entropy: 0.1218 +[2026-03-20T17:53:47.491395Z] Loop 2103: Loss: 3.46e-03, Avg Return: 0.487, Regret: 0.3754, Entropy: 0.1018 +[2026-03-20T17:53:48.346252Z] Loop 2104: Loss: 3.12e-03, Avg Return: 0.492, Regret: 0.3754, Entropy: 0.0944 +[2026-03-20T17:53:49.200439Z] Loop 2105: Loss: 3.01e-03, Avg Return: 0.488, Regret: 0.3754, Entropy: 0.0869 +[2026-03-20T17:53:50.055357Z] Loop 2106: Loss: 3.23e-03, Avg Return: 0.487, Regret: 0.3754, Entropy: 0.0885 +[2026-03-20T17:53:50.908279Z] Loop 2107: Loss: 3.69e-03, Avg Return: 0.487, Regret: 0.3754, Entropy: 0.0891 +[2026-03-20T17:53:51.761320Z] Loop 2108: Loss: 3.66e-03, Avg Return: 0.486, Regret: 0.3754, Entropy: 0.0955 +[2026-03-20T17:53:52.614593Z] Loop 2109: Loss: 3.76e-03, Avg Return: 0.489, Regret: 0.3754, Entropy: 0.0925 +[2026-03-20T17:53:53.505772Z] Loop 2110: Loss: 3.84e-03, Avg Return: 0.486, Regret: 0.3793, Entropy: 0.0896 +[2026-03-20T17:53:54.359247Z] Loop 2111: Loss: 3.26e-03, Avg Return: 0.488, Regret: 0.3793, Entropy: 0.0868 +[2026-03-20T17:53:55.212076Z] Loop 2112: Loss: 3.18e-03, Avg Return: 0.487, Regret: 0.3793, Entropy: 0.0891 +[2026-03-20T17:53:56.065265Z] Loop 2113: Loss: 3.26e-03, Avg Return: 0.486, Regret: 0.3793, Entropy: 0.0965 +[2026-03-20T17:53:56.918252Z] Loop 2114: Loss: 3.73e-03, Avg Return: 0.489, Regret: 0.3793, Entropy: 0.1061 +[2026-03-20T17:53:57.771492Z] Loop 2115: Loss: 3.83e-03, Avg Return: 0.483, Regret: 0.3793, Entropy: 0.1002 +[2026-03-20T17:53:58.625071Z] Loop 2116: Loss: 2.92e-03, Avg Return: 0.488, Regret: 0.3793, Entropy: 0.0994 +[2026-03-20T17:53:59.479191Z] Loop 2117: Loss: 3.41e-03, Avg Return: 0.482, Regret: 0.3793, Entropy: 0.1051 +[2026-03-20T17:54:00.332990Z] Loop 2118: Loss: 3.40e-03, Avg Return: 0.480, Regret: 0.3793, Entropy: 0.1029 +[2026-03-20T17:54:01.185811Z] Loop 2119: Loss: 3.84e-03, Avg Return: 0.498, Regret: 0.3793, Entropy: 0.1073 +[2026-03-20T17:54:02.079743Z] Loop 2120: Loss: 3.83e-03, Avg Return: 0.486, Regret: 0.3756, Entropy: 0.1113 +[2026-03-20T17:54:02.934087Z] Loop 2121: Loss: 3.46e-03, Avg Return: 0.492, Regret: 0.3756, Entropy: 0.1037 +[2026-03-20T17:54:03.787089Z] Loop 2122: Loss: 3.77e-03, Avg Return: 0.494, Regret: 0.3756, Entropy: 0.1121 +[2026-03-20T17:54:04.640033Z] Loop 2123: Loss: 3.72e-03, Avg Return: 0.492, Regret: 0.3756, Entropy: 0.1110 +[2026-03-20T17:54:05.493862Z] Loop 2124: Loss: 4.03e-03, Avg Return: 0.485, Regret: 0.3756, Entropy: 0.1139 +[2026-03-20T17:54:06.348005Z] Loop 2125: Loss: 3.75e-03, Avg Return: 0.488, Regret: 0.3756, Entropy: 0.1169 +[2026-03-20T17:54:07.202256Z] Loop 2126: Loss: 3.83e-03, Avg Return: 0.492, Regret: 0.3756, Entropy: 0.1152 +[2026-03-20T17:54:08.054786Z] Loop 2127: Loss: 3.26e-03, Avg Return: 0.487, Regret: 0.3756, Entropy: 0.1124 +[2026-03-20T17:54:08.907785Z] Loop 2128: Loss: 3.42e-03, Avg Return: 0.483, Regret: 0.3756, Entropy: 0.1122 +[2026-03-20T17:54:09.761860Z] Loop 2129: Loss: 3.59e-03, Avg Return: 0.486, Regret: 0.3756, Entropy: 0.1140 +[2026-03-20T17:54:10.657315Z] Loop 2130: Loss: 3.22e-03, Avg Return: 0.483, Regret: 0.3754, Entropy: 0.1147 +[2026-03-20T17:54:11.510582Z] Loop 2131: Loss: 3.78e-03, Avg Return: 0.487, Regret: 0.3754, Entropy: 0.1116 +[2026-03-20T17:54:12.364782Z] Loop 2132: Loss: 3.59e-03, Avg Return: 0.491, Regret: 0.3754, Entropy: 0.1112 +[2026-03-20T17:54:13.218625Z] Loop 2133: Loss: 3.68e-03, Avg Return: 0.483, Regret: 0.3754, Entropy: 0.1127 +[2026-03-20T17:54:14.071525Z] Loop 2134: Loss: 3.38e-03, Avg Return: 0.487, Regret: 0.3754, Entropy: 0.1048 +[2026-03-20T17:54:14.923788Z] Loop 2135: Loss: 3.05e-03, Avg Return: 0.488, Regret: 0.3754, Entropy: 0.1048 +[2026-03-20T17:54:15.776651Z] Loop 2136: Loss: 2.98e-03, Avg Return: 0.492, Regret: 0.3754, Entropy: 0.0935 +[2026-03-20T17:54:16.630397Z] Loop 2137: Loss: 2.50e-03, Avg Return: 0.491, Regret: 0.3754, Entropy: 0.0837 +[2026-03-20T17:54:17.483439Z] Loop 2138: Loss: 2.84e-03, Avg Return: 0.481, Regret: 0.3754, Entropy: 0.0861 +[2026-03-20T17:54:18.336859Z] Loop 2139: Loss: 3.11e-03, Avg Return: 0.494, Regret: 0.3754, Entropy: 0.0825 +[2026-03-20T17:54:19.230286Z] Loop 2140: Loss: 3.27e-03, Avg Return: 0.484, Regret: 0.3776, Entropy: 0.0845 +[2026-03-20T17:54:20.084831Z] Loop 2141: Loss: 3.54e-03, Avg Return: 0.484, Regret: 0.3776, Entropy: 0.0855 +[2026-03-20T17:54:20.938729Z] Loop 2142: Loss: 3.51e-03, Avg Return: 0.487, Regret: 0.3776, Entropy: 0.0884 +[2026-03-20T17:54:21.791711Z] Loop 2143: Loss: 3.95e-03, Avg Return: 0.480, Regret: 0.3776, Entropy: 0.0841 +[2026-03-20T17:54:22.645587Z] Loop 2144: Loss: 3.62e-03, Avg Return: 0.480, Regret: 0.3776, Entropy: 0.0873 +[2026-03-20T17:54:23.499404Z] Loop 2145: Loss: 3.31e-03, Avg Return: 0.483, Regret: 0.3776, Entropy: 0.0861 +[2026-03-20T17:54:24.354655Z] Loop 2146: Loss: 2.95e-03, Avg Return: 0.493, Regret: 0.3776, Entropy: 0.0821 +[2026-03-20T17:54:25.207578Z] Loop 2147: Loss: 2.73e-03, Avg Return: 0.486, Regret: 0.3776, Entropy: 0.0820 +[2026-03-20T17:54:26.060204Z] Loop 2148: Loss: 2.72e-03, Avg Return: 0.491, Regret: 0.3776, Entropy: 0.0852 +[2026-03-20T17:54:26.913941Z] Loop 2149: Loss: 3.24e-03, Avg Return: 0.489, Regret: 0.3776, Entropy: 0.0922 +[2026-03-20T17:54:27.807120Z] Loop 2150: Loss: 3.20e-03, Avg Return: 0.486, Regret: 0.3756, Entropy: 0.0970 +[2026-03-20T17:54:28.660639Z] Loop 2151: Loss: 2.99e-03, Avg Return: 0.483, Regret: 0.3756, Entropy: 0.1028 +[2026-03-20T17:54:29.514485Z] Loop 2152: Loss: 3.53e-03, Avg Return: 0.493, Regret: 0.3756, Entropy: 0.1012 +[2026-03-20T17:54:30.368486Z] Loop 2153: Loss: 3.28e-03, Avg Return: 0.492, Regret: 0.3756, Entropy: 0.1105 +[2026-03-20T17:54:31.222587Z] Loop 2154: Loss: 3.36e-03, Avg Return: 0.488, Regret: 0.3756, Entropy: 0.1073 +[2026-03-20T17:54:32.074830Z] Loop 2155: Loss: 3.33e-03, Avg Return: 0.487, Regret: 0.3756, Entropy: 0.1072 +[2026-03-20T17:54:32.926796Z] Loop 2156: Loss: 3.22e-03, Avg Return: 0.488, Regret: 0.3756, Entropy: 0.1069 +[2026-03-20T17:54:33.779650Z] Loop 2157: Loss: 2.66e-03, Avg Return: 0.482, Regret: 0.3756, Entropy: 0.0908 +[2026-03-20T17:54:34.633198Z] Loop 2158: Loss: 2.40e-03, Avg Return: 0.482, Regret: 0.3756, Entropy: 0.0837 +[2026-03-20T17:54:35.486646Z] Loop 2159: Loss: 2.60e-03, Avg Return: 0.484, Regret: 0.3756, Entropy: 0.0811 +[2026-03-20T17:54:36.379050Z] Loop 2160: Loss: 2.94e-03, Avg Return: 0.490, Regret: 0.3762, Entropy: 0.0773 +[2026-03-20T17:54:37.232912Z] Loop 2161: Loss: 3.68e-03, Avg Return: 0.490, Regret: 0.3762, Entropy: 0.0835 +[2026-03-20T17:54:38.087881Z] Loop 2162: Loss: 3.42e-03, Avg Return: 0.488, Regret: 0.3762, Entropy: 0.0848 +[2026-03-20T17:54:38.942102Z] Loop 2163: Loss: 3.12e-03, Avg Return: 0.487, Regret: 0.3762, Entropy: 0.0773 +[2026-03-20T17:54:39.796044Z] Loop 2164: Loss: 3.43e-03, Avg Return: 0.486, Regret: 0.3762, Entropy: 0.0852 +[2026-03-20T17:54:40.649666Z] Loop 2165: Loss: 3.47e-03, Avg Return: 0.497, Regret: 0.3762, Entropy: 0.0823 +[2026-03-20T17:54:41.504288Z] Loop 2166: Loss: 4.08e-03, Avg Return: 0.491, Regret: 0.3762, Entropy: 0.0874 +[2026-03-20T17:54:42.358594Z] Loop 2167: Loss: 3.75e-03, Avg Return: 0.487, Regret: 0.3762, Entropy: 0.0830 +[2026-03-20T17:54:43.212333Z] Loop 2168: Loss: 3.94e-03, Avg Return: 0.484, Regret: 0.3762, Entropy: 0.0877 +[2026-03-20T17:54:44.067619Z] Loop 2169: Loss: 3.69e-03, Avg Return: 0.481, Regret: 0.3762, Entropy: 0.0840 +[2026-03-20T17:54:44.960676Z] Loop 2170: Loss: 4.04e-03, Avg Return: 0.487, Regret: 0.3772, Entropy: 0.0885 +[2026-03-20T17:54:45.814885Z] Loop 2171: Loss: 3.65e-03, Avg Return: 0.487, Regret: 0.3772, Entropy: 0.0859 +[2026-03-20T17:54:46.669312Z] Loop 2172: Loss: 3.94e-03, Avg Return: 0.488, Regret: 0.3772, Entropy: 0.0901 +[2026-03-20T17:54:47.524041Z] Loop 2173: Loss: 3.29e-03, Avg Return: 0.492, Regret: 0.3772, Entropy: 0.0849 +[2026-03-20T17:54:48.379132Z] Loop 2174: Loss: 2.63e-03, Avg Return: 0.491, Regret: 0.3772, Entropy: 0.0814 +[2026-03-20T17:54:49.232457Z] Loop 2175: Loss: 2.61e-03, Avg Return: 0.493, Regret: 0.3772, Entropy: 0.0941 +[2026-03-20T17:54:50.086103Z] Loop 2176: Loss: 3.42e-03, Avg Return: 0.487, Regret: 0.3772, Entropy: 0.1045 +[2026-03-20T17:54:50.939083Z] Loop 2177: Loss: 3.22e-03, Avg Return: 0.489, Regret: 0.3772, Entropy: 0.1074 +[2026-03-20T17:54:51.792546Z] Loop 2178: Loss: 3.51e-03, Avg Return: 0.486, Regret: 0.3772, Entropy: 0.1137 +[2026-03-20T17:54:52.645797Z] Loop 2179: Loss: 3.88e-03, Avg Return: 0.492, Regret: 0.3772, Entropy: 0.1174 +[2026-03-20T17:54:53.539087Z] Loop 2180: Loss: 4.02e-03, Avg Return: 0.483, Regret: 0.3753, Entropy: 0.1278 +[2026-03-20T17:54:54.392138Z] Loop 2181: Loss: 4.34e-03, Avg Return: 0.490, Regret: 0.3753, Entropy: 0.1314 +[2026-03-20T17:54:55.244738Z] Loop 2182: Loss: 4.00e-03, Avg Return: 0.486, Regret: 0.3753, Entropy: 0.1241 +[2026-03-20T17:54:56.097599Z] Loop 2183: Loss: 3.10e-03, Avg Return: 0.495, Regret: 0.3753, Entropy: 0.1161 +[2026-03-20T17:54:56.951829Z] Loop 2184: Loss: 3.19e-03, Avg Return: 0.483, Regret: 0.3753, Entropy: 0.1162 +[2026-03-20T17:54:57.806144Z] Loop 2185: Loss: 2.77e-03, Avg Return: 0.489, Regret: 0.3753, Entropy: 0.0984 +[2026-03-20T17:54:58.659387Z] Loop 2186: Loss: 2.06e-03, Avg Return: 0.501, Regret: 0.3753, Entropy: 0.0896 +[2026-03-20T17:54:59.511503Z] Loop 2187: Loss: 1.99e-03, Avg Return: 0.490, Regret: 0.3753, Entropy: 0.0887 +[2026-03-20T17:55:00.364282Z] Loop 2188: Loss: 1.83e-03, Avg Return: 0.485, Regret: 0.3753, Entropy: 0.0854 +[2026-03-20T17:55:01.218838Z] Loop 2189: Loss: 1.60e-03, Avg Return: 0.486, Regret: 0.3753, Entropy: 0.0866 +[2026-03-20T17:55:02.116614Z] Loop 2190: Loss: 1.67e-03, Avg Return: 0.487, Regret: 0.3754, Entropy: 0.0861 +[2026-03-20T17:55:02.970961Z] Loop 2191: Loss: 1.80e-03, Avg Return: 0.482, Regret: 0.3754, Entropy: 0.0864 +[2026-03-20T17:55:03.824063Z] Loop 2192: Loss: 1.57e-03, Avg Return: 0.484, Regret: 0.3754, Entropy: 0.0835 +[2026-03-20T17:55:04.677673Z] Loop 2193: Loss: 1.59e-03, Avg Return: 0.485, Regret: 0.3754, Entropy: 0.0858 +[2026-03-20T17:55:05.531444Z] Loop 2194: Loss: 1.59e-03, Avg Return: 0.488, Regret: 0.3754, Entropy: 0.0808 +[2026-03-20T17:55:06.384330Z] Loop 2195: Loss: 1.61e-03, Avg Return: 0.499, Regret: 0.3754, Entropy: 0.0848 +[2026-03-20T17:55:07.237273Z] Loop 2196: Loss: 1.85e-03, Avg Return: 0.483, Regret: 0.3754, Entropy: 0.0913 +[2026-03-20T17:55:08.090268Z] Loop 2197: Loss: 2.26e-03, Avg Return: 0.495, Regret: 0.3754, Entropy: 0.0984 +[2026-03-20T17:55:08.944109Z] Loop 2198: Loss: 2.04e-03, Avg Return: 0.492, Regret: 0.3754, Entropy: 0.0983 +[2026-03-20T17:55:09.797159Z] Loop 2199: Loss: 2.01e-03, Avg Return: 0.486, Regret: 0.3754, Entropy: 0.0978 +[2026-03-20T17:55:10.689692Z] Loop 2200: Loss: 1.84e-03, Avg Return: 0.488, Regret: 0.3760, Entropy: 0.0963 +[2026-03-20T17:55:11.544347Z] Loop 2201: Loss: 1.90e-03, Avg Return: 0.494, Regret: 0.3760, Entropy: 0.1031 +[2026-03-20T17:55:12.398668Z] Loop 2202: Loss: 2.35e-03, Avg Return: 0.492, Regret: 0.3760, Entropy: 0.1081 +[2026-03-20T17:55:13.251391Z] Loop 2203: Loss: 2.62e-03, Avg Return: 0.487, Regret: 0.3760, Entropy: 0.1084 +[2026-03-20T17:55:14.104744Z] Loop 2204: Loss: 2.80e-03, Avg Return: 0.495, Regret: 0.3760, Entropy: 0.1065 +[2026-03-20T17:55:14.957618Z] Loop 2205: Loss: 2.70e-03, Avg Return: 0.490, Regret: 0.3760, Entropy: 0.1162 +[2026-03-20T17:55:15.811727Z] Loop 2206: Loss: 2.68e-03, Avg Return: 0.483, Regret: 0.3760, Entropy: 0.1122 +[2026-03-20T17:55:16.665409Z] Loop 2207: Loss: 2.82e-03, Avg Return: 0.484, Regret: 0.3760, Entropy: 0.1132 +[2026-03-20T17:55:17.519097Z] Loop 2208: Loss: 2.59e-03, Avg Return: 0.485, Regret: 0.3760, Entropy: 0.1116 +[2026-03-20T17:55:18.371217Z] Loop 2209: Loss: 2.73e-03, Avg Return: 0.482, Regret: 0.3760, Entropy: 0.1134 +[2026-03-20T17:55:19.263279Z] Loop 2210: Loss: 2.91e-03, Avg Return: 0.480, Regret: 0.3770, Entropy: 0.1109 +[2026-03-20T17:55:20.117036Z] Loop 2211: Loss: 2.97e-03, Avg Return: 0.482, Regret: 0.3770, Entropy: 0.1143 +[2026-03-20T17:55:20.970648Z] Loop 2212: Loss: 3.03e-03, Avg Return: 0.491, Regret: 0.3770, Entropy: 0.1122 +[2026-03-20T17:55:21.824438Z] Loop 2213: Loss: 2.97e-03, Avg Return: 0.485, Regret: 0.3770, Entropy: 0.1097 +[2026-03-20T17:55:22.678478Z] Loop 2214: Loss: 2.92e-03, Avg Return: 0.486, Regret: 0.3770, Entropy: 0.1090 +[2026-03-20T17:55:23.530622Z] Loop 2215: Loss: 2.51e-03, Avg Return: 0.488, Regret: 0.3770, Entropy: 0.1094 +[2026-03-20T17:55:24.384117Z] Loop 2216: Loss: 2.30e-03, Avg Return: 0.486, Regret: 0.3770, Entropy: 0.1041 +[2026-03-20T17:55:25.237384Z] Loop 2217: Loss: 2.41e-03, Avg Return: 0.485, Regret: 0.3770, Entropy: 0.1004 +[2026-03-20T17:55:26.090756Z] Loop 2218: Loss: 2.34e-03, Avg Return: 0.484, Regret: 0.3770, Entropy: 0.1026 +[2026-03-20T17:55:26.943434Z] Loop 2219: Loss: 2.69e-03, Avg Return: 0.491, Regret: 0.3770, Entropy: 0.0967 +[2026-03-20T17:55:27.834937Z] Loop 2220: Loss: 2.84e-03, Avg Return: 0.484, Regret: 0.3773, Entropy: 0.1090 +[2026-03-20T17:55:28.689147Z] Loop 2221: Loss: 2.88e-03, Avg Return: 0.486, Regret: 0.3773, Entropy: 0.1052 +[2026-03-20T17:55:29.542845Z] Loop 2222: Loss: 2.75e-03, Avg Return: 0.486, Regret: 0.3773, Entropy: 0.1074 +[2026-03-20T17:55:30.395854Z] Loop 2223: Loss: 2.54e-03, Avg Return: 0.482, Regret: 0.3773, Entropy: 0.1107 +[2026-03-20T17:55:31.247815Z] Loop 2224: Loss: 2.70e-03, Avg Return: 0.491, Regret: 0.3773, Entropy: 0.1080 +[2026-03-20T17:55:32.100716Z] Loop 2225: Loss: 2.40e-03, Avg Return: 0.499, Regret: 0.3773, Entropy: 0.1104 +[2026-03-20T17:55:32.953638Z] Loop 2226: Loss: 2.04e-03, Avg Return: 0.486, Regret: 0.3773, Entropy: 0.1096 +[2026-03-20T17:55:33.808068Z] Loop 2227: Loss: 1.90e-03, Avg Return: 0.496, Regret: 0.3773, Entropy: 0.0975 +[2026-03-20T17:55:34.661642Z] Loop 2228: Loss: 1.93e-03, Avg Return: 0.488, Regret: 0.3773, Entropy: 0.0969 +[2026-03-20T17:55:35.514681Z] Loop 2229: Loss: 1.83e-03, Avg Return: 0.477, Regret: 0.3773, Entropy: 0.1031 +[2026-03-20T17:55:36.409282Z] Loop 2230: Loss: 1.89e-03, Avg Return: 0.491, Regret: 0.3755, Entropy: 0.1020 +[2026-03-20T17:55:37.263438Z] Loop 2231: Loss: 1.64e-03, Avg Return: 0.490, Regret: 0.3755, Entropy: 0.0961 +[2026-03-20T17:55:38.115639Z] Loop 2232: Loss: 1.86e-03, Avg Return: 0.483, Regret: 0.3755, Entropy: 0.0902 +[2026-03-20T17:55:38.968480Z] Loop 2233: Loss: 2.03e-03, Avg Return: 0.483, Regret: 0.3755, Entropy: 0.0942 +[2026-03-20T17:55:39.822255Z] Loop 2234: Loss: 2.18e-03, Avg Return: 0.487, Regret: 0.3755, Entropy: 0.0956 +[2026-03-20T17:55:40.675996Z] Loop 2235: Loss: 2.16e-03, Avg Return: 0.487, Regret: 0.3755, Entropy: 0.0943 +[2026-03-20T17:55:41.529201Z] Loop 2236: Loss: 1.94e-03, Avg Return: 0.485, Regret: 0.3755, Entropy: 0.0952 +[2026-03-20T17:55:42.382135Z] Loop 2237: Loss: 1.70e-03, Avg Return: 0.488, Regret: 0.3755, Entropy: 0.0918 +[2026-03-20T17:55:43.236565Z] Loop 2238: Loss: 1.71e-03, Avg Return: 0.483, Regret: 0.3755, Entropy: 0.0919 +[2026-03-20T17:55:44.090440Z] Loop 2239: Loss: 1.77e-03, Avg Return: 0.483, Regret: 0.3755, Entropy: 0.0927 +[2026-03-20T17:55:44.983051Z] Loop 2240: Loss: 1.70e-03, Avg Return: 0.492, Regret: 0.3752, Entropy: 0.0981 +[2026-03-20T17:55:45.835473Z] Loop 2241: Loss: 1.67e-03, Avg Return: 0.489, Regret: 0.3752, Entropy: 0.0954 +[2026-03-20T17:55:46.687861Z] Loop 2242: Loss: 1.97e-03, Avg Return: 0.478, Regret: 0.3752, Entropy: 0.0994 +[2026-03-20T17:55:47.542886Z] Loop 2243: Loss: 1.99e-03, Avg Return: 0.496, Regret: 0.3752, Entropy: 0.0978 +[2026-03-20T17:55:48.396579Z] Loop 2244: Loss: 1.69e-03, Avg Return: 0.482, Regret: 0.3752, Entropy: 0.0941 +[2026-03-20T17:55:49.249456Z] Loop 2245: Loss: 1.78e-03, Avg Return: 0.489, Regret: 0.3752, Entropy: 0.0942 +[2026-03-20T17:55:50.102329Z] Loop 2246: Loss: 1.93e-03, Avg Return: 0.488, Regret: 0.3752, Entropy: 0.0999 +[2026-03-20T17:55:50.955795Z] Loop 2247: Loss: 1.91e-03, Avg Return: 0.483, Regret: 0.3752, Entropy: 0.1017 +[2026-03-20T17:55:51.809738Z] Loop 2248: Loss: 1.82e-03, Avg Return: 0.489, Regret: 0.3752, Entropy: 0.1042 +[2026-03-20T17:55:52.662843Z] Loop 2249: Loss: 1.79e-03, Avg Return: 0.483, Regret: 0.3752, Entropy: 0.0982 +[2026-03-20T17:55:53.553248Z] Loop 2250: Loss: 1.91e-03, Avg Return: 0.484, Regret: 0.3754, Entropy: 0.1083 +[2026-03-20T17:55:54.408187Z] Loop 2251: Loss: 2.13e-03, Avg Return: 0.493, Regret: 0.3754, Entropy: 0.1097 +[2026-03-20T17:55:55.262779Z] Loop 2252: Loss: 2.02e-03, Avg Return: 0.479, Regret: 0.3754, Entropy: 0.1102 +[2026-03-20T17:55:56.118112Z] Loop 2253: Loss: 2.41e-03, Avg Return: 0.489, Regret: 0.3754, Entropy: 0.1064 +[2026-03-20T17:55:56.972933Z] Loop 2254: Loss: 2.15e-03, Avg Return: 0.483, Regret: 0.3754, Entropy: 0.1070 +[2026-03-20T17:55:57.828166Z] Loop 2255: Loss: 2.20e-03, Avg Return: 0.490, Regret: 0.3754, Entropy: 0.1075 +[2026-03-20T17:55:58.683450Z] Loop 2256: Loss: 2.29e-03, Avg Return: 0.496, Regret: 0.3754, Entropy: 0.1050 +[2026-03-20T17:55:59.536207Z] Loop 2257: Loss: 2.03e-03, Avg Return: 0.487, Regret: 0.3754, Entropy: 0.1067 +[2026-03-20T17:56:00.390243Z] Loop 2258: Loss: 2.07e-03, Avg Return: 0.486, Regret: 0.3754, Entropy: 0.1118 +[2026-03-20T17:56:01.243759Z] Loop 2259: Loss: 2.17e-03, Avg Return: 0.487, Regret: 0.3754, Entropy: 0.1051 +[2026-03-20T17:56:02.137852Z] Loop 2260: Loss: 1.84e-03, Avg Return: 0.479, Regret: 0.3756, Entropy: 0.1059 +[2026-03-20T17:56:02.992351Z] Loop 2261: Loss: 2.15e-03, Avg Return: 0.493, Regret: 0.3756, Entropy: 0.1094 +[2026-03-20T17:56:03.847464Z] Loop 2262: Loss: 2.11e-03, Avg Return: 0.494, Regret: 0.3756, Entropy: 0.1108 +[2026-03-20T17:56:04.703081Z] Loop 2263: Loss: 2.07e-03, Avg Return: 0.487, Regret: 0.3756, Entropy: 0.1153 +[2026-03-20T17:56:05.556226Z] Loop 2264: Loss: 1.70e-03, Avg Return: 0.488, Regret: 0.3756, Entropy: 0.1075 +[2026-03-20T17:56:06.408934Z] Loop 2265: Loss: 2.22e-03, Avg Return: 0.490, Regret: 0.3756, Entropy: 0.1049 +[2026-03-20T17:56:07.262712Z] Loop 2266: Loss: 1.94e-03, Avg Return: 0.480, Regret: 0.3756, Entropy: 0.1090 +[2026-03-20T17:56:08.116350Z] Loop 2267: Loss: 1.84e-03, Avg Return: 0.495, Regret: 0.3756, Entropy: 0.1098 +[2026-03-20T17:56:08.968802Z] Loop 2268: Loss: 2.28e-03, Avg Return: 0.491, Regret: 0.3756, Entropy: 0.1126 +[2026-03-20T17:56:09.821147Z] Loop 2269: Loss: 1.89e-03, Avg Return: 0.489, Regret: 0.3756, Entropy: 0.1150 +[2026-03-20T17:56:10.712804Z] Loop 2270: Loss: 1.97e-03, Avg Return: 0.491, Regret: 0.3758, Entropy: 0.1152 +[2026-03-20T17:56:11.566835Z] Loop 2271: Loss: 1.90e-03, Avg Return: 0.478, Regret: 0.3758, Entropy: 0.1180 +[2026-03-20T17:56:12.420275Z] Loop 2272: Loss: 1.96e-03, Avg Return: 0.479, Regret: 0.3758, Entropy: 0.1188 +[2026-03-20T17:56:13.273407Z] Loop 2273: Loss: 2.02e-03, Avg Return: 0.483, Regret: 0.3758, Entropy: 0.1186 +[2026-03-20T17:56:14.126657Z] Loop 2274: Loss: 2.00e-03, Avg Return: 0.488, Regret: 0.3758, Entropy: 0.1152 +[2026-03-20T17:56:14.981281Z] Loop 2275: Loss: 1.94e-03, Avg Return: 0.493, Regret: 0.3758, Entropy: 0.1052 +[2026-03-20T17:56:15.834831Z] Loop 2276: Loss: 2.05e-03, Avg Return: 0.489, Regret: 0.3758, Entropy: 0.1114 +[2026-03-20T17:56:16.687831Z] Loop 2277: Loss: 2.12e-03, Avg Return: 0.489, Regret: 0.3758, Entropy: 0.1066 +[2026-03-20T17:56:17.541083Z] Loop 2278: Loss: 1.88e-03, Avg Return: 0.481, Regret: 0.3758, Entropy: 0.1090 +[2026-03-20T17:56:18.395169Z] Loop 2279: Loss: 2.06e-03, Avg Return: 0.480, Regret: 0.3758, Entropy: 0.1120 +[2026-03-20T17:56:19.288585Z] Loop 2280: Loss: 2.11e-03, Avg Return: 0.483, Regret: 0.3759, Entropy: 0.1104 +[2026-03-20T17:56:20.141597Z] Loop 2281: Loss: 2.22e-03, Avg Return: 0.487, Regret: 0.3759, Entropy: 0.1075 +[2026-03-20T17:56:20.994704Z] Loop 2282: Loss: 2.24e-03, Avg Return: 0.495, Regret: 0.3759, Entropy: 0.1111 +[2026-03-20T17:56:21.848445Z] Loop 2283: Loss: 2.16e-03, Avg Return: 0.486, Regret: 0.3759, Entropy: 0.1102 +[2026-03-20T17:56:22.701747Z] Loop 2284: Loss: 2.14e-03, Avg Return: 0.489, Regret: 0.3759, Entropy: 0.1061 +[2026-03-20T17:56:23.554809Z] Loop 2285: Loss: 2.22e-03, Avg Return: 0.491, Regret: 0.3759, Entropy: 0.1066 +[2026-03-20T17:56:24.407493Z] Loop 2286: Loss: 2.21e-03, Avg Return: 0.485, Regret: 0.3759, Entropy: 0.1110 +[2026-03-20T17:56:25.261200Z] Loop 2287: Loss: 1.96e-03, Avg Return: 0.488, Regret: 0.3759, Entropy: 0.1108 +[2026-03-20T17:56:26.115454Z] Loop 2288: Loss: 2.17e-03, Avg Return: 0.475, Regret: 0.3759, Entropy: 0.1097 +[2026-03-20T17:56:26.970166Z] Loop 2289: Loss: 1.85e-03, Avg Return: 0.487, Regret: 0.3759, Entropy: 0.1081 +[2026-03-20T17:56:27.861747Z] Loop 2290: Loss: 2.25e-03, Avg Return: 0.488, Regret: 0.3760, Entropy: 0.1038 +[2026-03-20T17:56:28.716174Z] Loop 2291: Loss: 2.24e-03, Avg Return: 0.491, Regret: 0.3760, Entropy: 0.1152 +[2026-03-20T17:56:29.569680Z] Loop 2292: Loss: 2.12e-03, Avg Return: 0.488, Regret: 0.3760, Entropy: 0.1105 +[2026-03-20T17:56:30.423539Z] Loop 2293: Loss: 2.14e-03, Avg Return: 0.483, Regret: 0.3760, Entropy: 0.1080 +[2026-03-20T17:56:31.277088Z] Loop 2294: Loss: 2.16e-03, Avg Return: 0.489, Regret: 0.3760, Entropy: 0.1065 +[2026-03-20T17:56:32.130347Z] Loop 2295: Loss: 2.62e-03, Avg Return: 0.487, Regret: 0.3760, Entropy: 0.1068 +[2026-03-20T17:56:32.983713Z] Loop 2296: Loss: 2.34e-03, Avg Return: 0.494, Regret: 0.3760, Entropy: 0.1087 +[2026-03-20T17:56:33.836958Z] Loop 2297: Loss: 1.92e-03, Avg Return: 0.482, Regret: 0.3760, Entropy: 0.1093 +[2026-03-20T17:56:34.690387Z] Loop 2298: Loss: 2.05e-03, Avg Return: 0.487, Regret: 0.3760, Entropy: 0.1111 +[2026-03-20T17:56:35.543562Z] Loop 2299: Loss: 2.12e-03, Avg Return: 0.491, Regret: 0.3760, Entropy: 0.1067 +[2026-03-20T17:56:36.437741Z] Loop 2300: Loss: 2.09e-03, Avg Return: 0.491, Regret: 0.3759, Entropy: 0.1079 +[2026-03-20T17:56:37.290216Z] Loop 2301: Loss: 1.88e-03, Avg Return: 0.488, Regret: 0.3759, Entropy: 0.1089 +[2026-03-20T17:56:38.144226Z] Loop 2302: Loss: 2.01e-03, Avg Return: 0.486, Regret: 0.3759, Entropy: 0.1052 +[2026-03-20T17:56:38.998060Z] Loop 2303: Loss: 2.09e-03, Avg Return: 0.484, Regret: 0.3759, Entropy: 0.1154 +[2026-03-20T17:56:39.852423Z] Loop 2304: Loss: 2.44e-03, Avg Return: 0.480, Regret: 0.3759, Entropy: 0.1206 +[2026-03-20T17:56:40.706306Z] Loop 2305: Loss: 2.45e-03, Avg Return: 0.483, Regret: 0.3759, Entropy: 0.1220 +[2026-03-20T17:56:41.559899Z] Loop 2306: Loss: 2.18e-03, Avg Return: 0.480, Regret: 0.3759, Entropy: 0.1191 +[2026-03-20T17:56:42.414593Z] Loop 2307: Loss: 2.44e-03, Avg Return: 0.492, Regret: 0.3759, Entropy: 0.1137 +[2026-03-20T17:56:43.268609Z] Loop 2308: Loss: 2.22e-03, Avg Return: 0.477, Regret: 0.3759, Entropy: 0.1191 +[2026-03-20T17:56:44.122094Z] Loop 2309: Loss: 1.92e-03, Avg Return: 0.486, Regret: 0.3759, Entropy: 0.1147 +[2026-03-20T17:56:45.016221Z] Loop 2310: Loss: 2.12e-03, Avg Return: 0.485, Regret: 0.3767, Entropy: 0.1190 +[2026-03-20T17:56:45.869869Z] Loop 2311: Loss: 2.08e-03, Avg Return: 0.489, Regret: 0.3767, Entropy: 0.1131 +[2026-03-20T17:56:46.724321Z] Loop 2312: Loss: 1.82e-03, Avg Return: 0.495, Regret: 0.3767, Entropy: 0.1111 +[2026-03-20T17:56:47.578886Z] Loop 2313: Loss: 1.73e-03, Avg Return: 0.487, Regret: 0.3767, Entropy: 0.1028 +[2026-03-20T17:56:48.432939Z] Loop 2314: Loss: 1.62e-03, Avg Return: 0.494, Regret: 0.3767, Entropy: 0.0987 +[2026-03-20T17:56:49.286949Z] Loop 2315: Loss: 1.66e-03, Avg Return: 0.485, Regret: 0.3767, Entropy: 0.1001 +[2026-03-20T17:56:50.141688Z] Loop 2316: Loss: 1.69e-03, Avg Return: 0.496, Regret: 0.3767, Entropy: 0.1004 +[2026-03-20T17:56:50.996744Z] Loop 2317: Loss: 1.67e-03, Avg Return: 0.494, Regret: 0.3767, Entropy: 0.1046 +[2026-03-20T17:56:51.849571Z] Loop 2318: Loss: 1.56e-03, Avg Return: 0.488, Regret: 0.3767, Entropy: 0.1021 +[2026-03-20T17:56:52.702970Z] Loop 2319: Loss: 1.81e-03, Avg Return: 0.479, Regret: 0.3767, Entropy: 0.1002 +[2026-03-20T17:56:53.598237Z] Loop 2320: Loss: 1.66e-03, Avg Return: 0.489, Regret: 0.3757, Entropy: 0.0968 +[2026-03-20T17:56:54.452114Z] Loop 2321: Loss: 1.66e-03, Avg Return: 0.493, Regret: 0.3757, Entropy: 0.0998 +[2026-03-20T17:56:55.305610Z] Loop 2322: Loss: 1.85e-03, Avg Return: 0.485, Regret: 0.3757, Entropy: 0.0962 +[2026-03-20T17:56:56.158682Z] Loop 2323: Loss: 1.80e-03, Avg Return: 0.487, Regret: 0.3757, Entropy: 0.1056 +[2026-03-20T17:56:57.013024Z] Loop 2324: Loss: 1.68e-03, Avg Return: 0.488, Regret: 0.3757, Entropy: 0.1016 +[2026-03-20T17:56:57.866194Z] Loop 2325: Loss: 1.96e-03, Avg Return: 0.488, Regret: 0.3757, Entropy: 0.1086 +[2026-03-20T17:56:58.719785Z] Loop 2326: Loss: 2.14e-03, Avg Return: 0.488, Regret: 0.3757, Entropy: 0.1108 +[2026-03-20T17:56:59.573490Z] Loop 2327: Loss: 2.73e-03, Avg Return: 0.487, Regret: 0.3757, Entropy: 0.1103 +[2026-03-20T17:57:00.426799Z] Loop 2328: Loss: 2.78e-03, Avg Return: 0.484, Regret: 0.3757, Entropy: 0.1112 +[2026-03-20T17:57:01.279825Z] Loop 2329: Loss: 2.65e-03, Avg Return: 0.490, Regret: 0.3757, Entropy: 0.1029 +[2026-03-20T17:57:02.173470Z] Loop 2330: Loss: 2.28e-03, Avg Return: 0.487, Regret: 0.3787, Entropy: 0.0946 +[2026-03-20T17:57:03.026756Z] Loop 2331: Loss: 1.62e-03, Avg Return: 0.484, Regret: 0.3787, Entropy: 0.0778 +[2026-03-20T17:57:03.881165Z] Loop 2332: Loss: 1.44e-03, Avg Return: 0.481, Regret: 0.3787, Entropy: 0.0632 +[2026-03-20T17:57:04.734812Z] Loop 2333: Loss: 1.22e-03, Avg Return: 0.487, Regret: 0.3787, Entropy: 0.0628 +[2026-03-20T17:57:05.588111Z] Loop 2334: Loss: 1.19e-03, Avg Return: 0.483, Regret: 0.3787, Entropy: 0.0612 +[2026-03-20T17:57:06.441288Z] Loop 2335: Loss: 9.72e-04, Avg Return: 0.471, Regret: 0.3787, Entropy: 0.0548 +[2026-03-20T17:57:07.295940Z] Loop 2336: Loss: 8.69e-04, Avg Return: 0.475, Regret: 0.3787, Entropy: 0.0555 +[2026-03-20T17:57:08.149233Z] Loop 2337: Loss: 9.11e-04, Avg Return: 0.474, Regret: 0.3787, Entropy: 0.0540 +[2026-03-20T17:57:09.002637Z] Loop 2338: Loss: 1.14e-03, Avg Return: 0.471, Regret: 0.3787, Entropy: 0.0533 +[2026-03-20T17:57:09.855884Z] Loop 2339: Loss: 1.17e-03, Avg Return: 0.482, Regret: 0.3787, Entropy: 0.0541 +[2026-03-20T17:57:10.749880Z] Loop 2340: Loss: 1.11e-03, Avg Return: 0.485, Regret: 0.3793, Entropy: 0.0604 +[2026-03-20T17:57:11.603623Z] Loop 2341: Loss: 1.18e-03, Avg Return: 0.478, Regret: 0.3793, Entropy: 0.0716 +[2026-03-20T17:57:12.456772Z] Loop 2342: Loss: 1.50e-03, Avg Return: 0.496, Regret: 0.3793, Entropy: 0.0677 +[2026-03-20T17:57:13.309883Z] Loop 2343: Loss: 1.50e-03, Avg Return: 0.489, Regret: 0.3793, Entropy: 0.0711 +[2026-03-20T17:57:14.164185Z] Loop 2344: Loss: 1.56e-03, Avg Return: 0.486, Regret: 0.3793, Entropy: 0.0755 +[2026-03-20T17:57:15.016867Z] Loop 2345: Loss: 1.92e-03, Avg Return: 0.490, Regret: 0.3793, Entropy: 0.0821 +[2026-03-20T17:57:15.869938Z] Loop 2346: Loss: 1.91e-03, Avg Return: 0.486, Regret: 0.3793, Entropy: 0.0843 +[2026-03-20T17:57:16.722994Z] Loop 2347: Loss: 1.91e-03, Avg Return: 0.494, Regret: 0.3793, Entropy: 0.0851 +[2026-03-20T17:57:17.576247Z] Loop 2348: Loss: 2.29e-03, Avg Return: 0.490, Regret: 0.3793, Entropy: 0.0925 +[2026-03-20T17:57:18.429175Z] Loop 2349: Loss: 2.44e-03, Avg Return: 0.487, Regret: 0.3793, Entropy: 0.1046 +[2026-03-20T17:57:19.320750Z] Loop 2350: Loss: 2.83e-03, Avg Return: 0.483, Regret: 0.3761, Entropy: 0.1156 +[2026-03-20T17:57:20.174936Z] Loop 2351: Loss: 2.92e-03, Avg Return: 0.495, Regret: 0.3761, Entropy: 0.1106 +[2026-03-20T17:57:21.029415Z] Loop 2352: Loss: 3.23e-03, Avg Return: 0.496, Regret: 0.3761, Entropy: 0.1084 +[2026-03-20T17:57:21.883728Z] Loop 2353: Loss: 2.63e-03, Avg Return: 0.487, Regret: 0.3761, Entropy: 0.1054 +[2026-03-20T17:57:22.735666Z] Loop 2354: Loss: 2.60e-03, Avg Return: 0.494, Regret: 0.3761, Entropy: 0.0944 +[2026-03-20T17:57:23.587156Z] Loop 2355: Loss: 1.88e-03, Avg Return: 0.491, Regret: 0.3761, Entropy: 0.0971 +[2026-03-20T17:57:24.440132Z] Loop 2356: Loss: 2.07e-03, Avg Return: 0.488, Regret: 0.3761, Entropy: 0.0952 +[2026-03-20T17:57:25.293082Z] Loop 2357: Loss: 2.06e-03, Avg Return: 0.486, Regret: 0.3761, Entropy: 0.0938 +[2026-03-20T17:57:26.146512Z] Loop 2358: Loss: 2.35e-03, Avg Return: 0.489, Regret: 0.3761, Entropy: 0.0909 +[2026-03-20T17:57:27.000008Z] Loop 2359: Loss: 2.32e-03, Avg Return: 0.487, Regret: 0.3761, Entropy: 0.0875 +[2026-03-20T17:57:27.894445Z] Loop 2360: Loss: 1.65e-03, Avg Return: 0.486, Regret: 0.3756, Entropy: 0.0815 +[2026-03-20T17:57:28.748670Z] Loop 2361: Loss: 1.54e-03, Avg Return: 0.492, Regret: 0.3756, Entropy: 0.0721 +[2026-03-20T17:57:29.602065Z] Loop 2362: Loss: 1.28e-03, Avg Return: 0.488, Regret: 0.3756, Entropy: 0.0778 +[2026-03-20T17:57:30.454777Z] Loop 2363: Loss: 1.77e-03, Avg Return: 0.489, Regret: 0.3756, Entropy: 0.0860 +[2026-03-20T17:57:31.306958Z] Loop 2364: Loss: 2.04e-03, Avg Return: 0.491, Regret: 0.3756, Entropy: 0.0902 +[2026-03-20T17:57:32.159621Z] Loop 2365: Loss: 2.35e-03, Avg Return: 0.485, Regret: 0.3756, Entropy: 0.0957 +[2026-03-20T17:57:33.012842Z] Loop 2366: Loss: 2.60e-03, Avg Return: 0.486, Regret: 0.3756, Entropy: 0.1019 +[2026-03-20T17:57:33.865906Z] Loop 2367: Loss: 3.64e-03, Avg Return: 0.487, Regret: 0.3756, Entropy: 0.1134 +[2026-03-20T17:57:34.718708Z] Loop 2368: Loss: 3.93e-03, Avg Return: 0.491, Regret: 0.3756, Entropy: 0.1183 +[2026-03-20T17:57:35.571540Z] Loop 2369: Loss: 3.99e-03, Avg Return: 0.485, Regret: 0.3756, Entropy: 0.1207 +[2026-03-20T17:57:36.463732Z] Loop 2370: Loss: 4.10e-03, Avg Return: 0.490, Regret: 0.3755, Entropy: 0.1253 +[2026-03-20T17:57:37.318117Z] Loop 2371: Loss: 4.29e-03, Avg Return: 0.484, Regret: 0.3755, Entropy: 0.1217 +[2026-03-20T17:57:38.170768Z] Loop 2372: Loss: 3.86e-03, Avg Return: 0.477, Regret: 0.3755, Entropy: 0.1212 +[2026-03-20T17:57:39.023945Z] Loop 2373: Loss: 4.23e-03, Avg Return: 0.490, Regret: 0.3755, Entropy: 0.1225 +[2026-03-20T17:57:39.877072Z] Loop 2374: Loss: 4.51e-03, Avg Return: 0.487, Regret: 0.3755, Entropy: 0.1230 +[2026-03-20T17:57:40.731183Z] Loop 2375: Loss: 4.12e-03, Avg Return: 0.489, Regret: 0.3755, Entropy: 0.1181 +[2026-03-20T17:57:41.584310Z] Loop 2376: Loss: 4.07e-03, Avg Return: 0.482, Regret: 0.3755, Entropy: 0.1190 +[2026-03-20T17:57:42.438508Z] Loop 2377: Loss: 4.51e-03, Avg Return: 0.491, Regret: 0.3755, Entropy: 0.1222 +[2026-03-20T17:57:43.291776Z] Loop 2378: Loss: 4.53e-03, Avg Return: 0.485, Regret: 0.3755, Entropy: 0.1130 +[2026-03-20T17:57:44.145229Z] Loop 2379: Loss: 4.32e-03, Avg Return: 0.486, Regret: 0.3755, Entropy: 0.1183 +[2026-03-20T17:57:45.039491Z] Loop 2380: Loss: 4.25e-03, Avg Return: 0.489, Regret: 0.3756, Entropy: 0.1189 +[2026-03-20T17:57:45.892703Z] Loop 2381: Loss: 3.61e-03, Avg Return: 0.489, Regret: 0.3756, Entropy: 0.1088 +[2026-03-20T17:57:46.745770Z] Loop 2382: Loss: 3.51e-03, Avg Return: 0.492, Regret: 0.3756, Entropy: 0.0997 +[2026-03-20T17:57:47.599965Z] Loop 2383: Loss: 2.76e-03, Avg Return: 0.480, Regret: 0.3756, Entropy: 0.0862 +[2026-03-20T17:57:48.453993Z] Loop 2384: Loss: 2.21e-03, Avg Return: 0.493, Regret: 0.3756, Entropy: 0.0794 +[2026-03-20T17:57:49.307955Z] Loop 2385: Loss: 2.03e-03, Avg Return: 0.490, Regret: 0.3756, Entropy: 0.0693 +[2026-03-20T17:57:50.160003Z] Loop 2386: Loss: 2.10e-03, Avg Return: 0.488, Regret: 0.3756, Entropy: 0.0730 +[2026-03-20T17:57:51.012681Z] Loop 2387: Loss: 2.31e-03, Avg Return: 0.489, Regret: 0.3756, Entropy: 0.0701 +[2026-03-20T17:57:51.866288Z] Loop 2388: Loss: 2.30e-03, Avg Return: 0.492, Regret: 0.3756, Entropy: 0.0681 +[2026-03-20T17:57:52.720211Z] Loop 2389: Loss: 2.90e-03, Avg Return: 0.489, Regret: 0.3756, Entropy: 0.0759 +[2026-03-20T17:57:53.612663Z] Loop 2390: Loss: 3.75e-03, Avg Return: 0.488, Regret: 0.3802, Entropy: 0.0852 +[2026-03-20T17:57:54.465658Z] Loop 2391: Loss: 4.26e-03, Avg Return: 0.483, Regret: 0.3802, Entropy: 0.0928 +[2026-03-20T17:57:55.319323Z] Loop 2392: Loss: 4.06e-03, Avg Return: 0.479, Regret: 0.3802, Entropy: 0.0899 +[2026-03-20T17:57:56.173850Z] Loop 2393: Loss: 3.38e-03, Avg Return: 0.481, Regret: 0.3802, Entropy: 0.0807 +[2026-03-20T17:57:57.026835Z] Loop 2394: Loss: 3.22e-03, Avg Return: 0.482, Regret: 0.3802, Entropy: 0.0743 +[2026-03-20T17:57:57.880264Z] Loop 2395: Loss: 2.65e-03, Avg Return: 0.490, Regret: 0.3802, Entropy: 0.0709 +[2026-03-20T17:57:58.733313Z] Loop 2396: Loss: 2.38e-03, Avg Return: 0.481, Regret: 0.3802, Entropy: 0.0658 +[2026-03-20T17:57:59.587269Z] Loop 2397: Loss: 2.45e-03, Avg Return: 0.486, Regret: 0.3802, Entropy: 0.0646 +[2026-03-20T17:58:00.440447Z] Loop 2398: Loss: 2.20e-03, Avg Return: 0.489, Regret: 0.3802, Entropy: 0.0658 +[2026-03-20T17:58:01.292518Z] Loop 2399: Loss: 2.08e-03, Avg Return: 0.493, Regret: 0.3802, Entropy: 0.0656 +[2026-03-20T17:58:02.184123Z] Loop 2400: Loss: 1.87e-03, Avg Return: 0.491, Regret: 0.3759, Entropy: 0.0663 +[2026-03-20T17:58:03.038238Z] Loop 2401: Loss: 2.19e-03, Avg Return: 0.489, Regret: 0.3759, Entropy: 0.0707 +[2026-03-20T17:58:03.892309Z] Loop 2402: Loss: 1.94e-03, Avg Return: 0.480, Regret: 0.3759, Entropy: 0.0686 +[2026-03-20T17:58:04.745622Z] Loop 2403: Loss: 2.09e-03, Avg Return: 0.499, Regret: 0.3759, Entropy: 0.0700 +[2026-03-20T17:58:05.598886Z] Loop 2404: Loss: 1.68e-03, Avg Return: 0.487, Regret: 0.3759, Entropy: 0.0691 +[2026-03-20T17:58:06.453041Z] Loop 2405: Loss: 2.24e-03, Avg Return: 0.485, Regret: 0.3759, Entropy: 0.0748 +[2026-03-20T17:58:07.306937Z] Loop 2406: Loss: 2.06e-03, Avg Return: 0.486, Regret: 0.3759, Entropy: 0.0774 +[2026-03-20T17:58:08.160170Z] Loop 2407: Loss: 2.58e-03, Avg Return: 0.489, Regret: 0.3759, Entropy: 0.0815 +[2026-03-20T17:58:09.012846Z] Loop 2408: Loss: 2.85e-03, Avg Return: 0.494, Regret: 0.3759, Entropy: 0.0816 +[2026-03-20T17:58:09.866436Z] Loop 2409: Loss: 3.05e-03, Avg Return: 0.487, Regret: 0.3759, Entropy: 0.0890 +[2026-03-20T17:58:10.759606Z] Loop 2410: Loss: 3.01e-03, Avg Return: 0.492, Regret: 0.3755, Entropy: 0.0880 +[2026-03-20T17:58:11.614511Z] Loop 2411: Loss: 2.92e-03, Avg Return: 0.490, Regret: 0.3755, Entropy: 0.0887 +[2026-03-20T17:58:12.467700Z] Loop 2412: Loss: 2.58e-03, Avg Return: 0.488, Regret: 0.3755, Entropy: 0.0913 +[2026-03-20T17:58:13.320807Z] Loop 2413: Loss: 2.84e-03, Avg Return: 0.488, Regret: 0.3755, Entropy: 0.0904 +[2026-03-20T17:58:14.173563Z] Loop 2414: Loss: 3.17e-03, Avg Return: 0.493, Regret: 0.3755, Entropy: 0.0935 +[2026-03-20T17:58:15.027031Z] Loop 2415: Loss: 2.85e-03, Avg Return: 0.479, Regret: 0.3755, Entropy: 0.0929 +[2026-03-20T17:58:15.880346Z] Loop 2416: Loss: 2.56e-03, Avg Return: 0.486, Regret: 0.3755, Entropy: 0.0865 +[2026-03-20T17:58:16.733253Z] Loop 2417: Loss: 2.53e-03, Avg Return: 0.485, Regret: 0.3755, Entropy: 0.0889 +[2026-03-20T17:58:17.590282Z] Loop 2418: Loss: 2.69e-03, Avg Return: 0.493, Regret: 0.3755, Entropy: 0.0858 +[2026-03-20T17:58:18.443174Z] Loop 2419: Loss: 2.48e-03, Avg Return: 0.485, Regret: 0.3755, Entropy: 0.0878 +[2026-03-20T17:58:19.335269Z] Loop 2420: Loss: 2.10e-03, Avg Return: 0.489, Regret: 0.3755, Entropy: 0.0790 +[2026-03-20T17:58:20.188767Z] Loop 2421: Loss: 1.96e-03, Avg Return: 0.492, Regret: 0.3755, Entropy: 0.0687 +[2026-03-20T17:58:21.041095Z] Loop 2422: Loss: 2.06e-03, Avg Return: 0.491, Regret: 0.3755, Entropy: 0.0679 +[2026-03-20T17:58:21.893646Z] Loop 2423: Loss: 1.96e-03, Avg Return: 0.484, Regret: 0.3755, Entropy: 0.0651 +[2026-03-20T17:58:22.746274Z] Loop 2424: Loss: 2.12e-03, Avg Return: 0.486, Regret: 0.3755, Entropy: 0.0682 +[2026-03-20T17:58:23.600600Z] Loop 2425: Loss: 2.02e-03, Avg Return: 0.492, Regret: 0.3755, Entropy: 0.0635 +[2026-03-20T17:58:24.453641Z] Loop 2426: Loss: 2.01e-03, Avg Return: 0.487, Regret: 0.3755, Entropy: 0.0693 +[2026-03-20T17:58:25.306661Z] Loop 2427: Loss: 1.98e-03, Avg Return: 0.486, Regret: 0.3755, Entropy: 0.0691 +[2026-03-20T17:58:26.162284Z] Loop 2428: Loss: 2.01e-03, Avg Return: 0.490, Regret: 0.3755, Entropy: 0.0741 +[2026-03-20T17:58:27.016817Z] Loop 2429: Loss: 2.20e-03, Avg Return: 0.479, Regret: 0.3755, Entropy: 0.0733 +[2026-03-20T17:58:27.911500Z] Loop 2430: Loss: 2.60e-03, Avg Return: 0.490, Regret: 0.3754, Entropy: 0.0817 +[2026-03-20T17:58:28.763720Z] Loop 2431: Loss: 2.45e-03, Avg Return: 0.496, Regret: 0.3754, Entropy: 0.0829 +[2026-03-20T17:58:29.616753Z] Loop 2432: Loss: 2.59e-03, Avg Return: 0.491, Regret: 0.3754, Entropy: 0.0868 +[2026-03-20T17:58:30.471158Z] Loop 2433: Loss: 2.41e-03, Avg Return: 0.491, Regret: 0.3754, Entropy: 0.0805 +[2026-03-20T17:58:31.325367Z] Loop 2434: Loss: 2.33e-03, Avg Return: 0.490, Regret: 0.3754, Entropy: 0.0787 +[2026-03-20T17:58:32.179401Z] Loop 2435: Loss: 2.03e-03, Avg Return: 0.486, Regret: 0.3754, Entropy: 0.0779 +[2026-03-20T17:58:33.032489Z] Loop 2436: Loss: 1.97e-03, Avg Return: 0.482, Regret: 0.3754, Entropy: 0.0706 +[2026-03-20T17:58:33.885652Z] Loop 2437: Loss: 1.62e-03, Avg Return: 0.489, Regret: 0.3754, Entropy: 0.0708 +[2026-03-20T17:58:34.740085Z] Loop 2438: Loss: 1.99e-03, Avg Return: 0.491, Regret: 0.3754, Entropy: 0.0653 +[2026-03-20T17:58:35.592415Z] Loop 2439: Loss: 2.25e-03, Avg Return: 0.486, Regret: 0.3754, Entropy: 0.0700 +[2026-03-20T17:58:36.482800Z] Loop 2440: Loss: 2.15e-03, Avg Return: 0.491, Regret: 0.3757, Entropy: 0.0656 +[2026-03-20T17:58:37.335756Z] Loop 2441: Loss: 2.19e-03, Avg Return: 0.481, Regret: 0.3757, Entropy: 0.0697 +[2026-03-20T17:58:38.190188Z] Loop 2442: Loss: 2.26e-03, Avg Return: 0.488, Regret: 0.3757, Entropy: 0.0704 +[2026-03-20T17:58:39.044009Z] Loop 2443: Loss: 2.40e-03, Avg Return: 0.485, Regret: 0.3757, Entropy: 0.0701 +[2026-03-20T17:58:39.897348Z] Loop 2444: Loss: 2.20e-03, Avg Return: 0.490, Regret: 0.3757, Entropy: 0.0679 +[2026-03-20T17:58:40.750803Z] Loop 2445: Loss: 1.83e-03, Avg Return: 0.494, Regret: 0.3757, Entropy: 0.0640 +[2026-03-20T17:58:41.605758Z] Loop 2446: Loss: 1.74e-03, Avg Return: 0.496, Regret: 0.3757, Entropy: 0.0624 +[2026-03-20T17:58:42.460163Z] Loop 2447: Loss: 1.63e-03, Avg Return: 0.479, Regret: 0.3757, Entropy: 0.0663 +[2026-03-20T17:58:43.314791Z] Loop 2448: Loss: 1.77e-03, Avg Return: 0.486, Regret: 0.3757, Entropy: 0.0661 +[2026-03-20T17:58:44.168067Z] Loop 2449: Loss: 1.82e-03, Avg Return: 0.483, Regret: 0.3757, Entropy: 0.0665 +[2026-03-20T17:58:45.062326Z] Loop 2450: Loss: 1.78e-03, Avg Return: 0.485, Regret: 0.3754, Entropy: 0.0742 +[2026-03-20T17:58:45.916310Z] Loop 2451: Loss: 2.27e-03, Avg Return: 0.493, Regret: 0.3754, Entropy: 0.0776 +[2026-03-20T17:58:46.769608Z] Loop 2452: Loss: 2.49e-03, Avg Return: 0.489, Regret: 0.3754, Entropy: 0.0840 +[2026-03-20T17:58:47.623738Z] Loop 2453: Loss: 2.76e-03, Avg Return: 0.487, Regret: 0.3754, Entropy: 0.0908 +[2026-03-20T17:58:48.478797Z] Loop 2454: Loss: 2.92e-03, Avg Return: 0.490, Regret: 0.3754, Entropy: 0.0953 +[2026-03-20T17:58:49.333585Z] Loop 2455: Loss: 3.16e-03, Avg Return: 0.490, Regret: 0.3754, Entropy: 0.1019 +[2026-03-20T17:58:50.187901Z] Loop 2456: Loss: 2.94e-03, Avg Return: 0.483, Regret: 0.3754, Entropy: 0.1017 +[2026-03-20T17:58:51.042611Z] Loop 2457: Loss: 3.39e-03, Avg Return: 0.491, Regret: 0.3754, Entropy: 0.1042 +[2026-03-20T17:58:51.896409Z] Loop 2458: Loss: 3.25e-03, Avg Return: 0.490, Regret: 0.3754, Entropy: 0.1037 +[2026-03-20T17:58:52.750557Z] Loop 2459: Loss: 2.89e-03, Avg Return: 0.489, Regret: 0.3754, Entropy: 0.1040 +[2026-03-20T17:58:53.644296Z] Loop 2460: Loss: 3.04e-03, Avg Return: 0.491, Regret: 0.3752, Entropy: 0.0969 +[2026-03-20T17:58:54.498511Z] Loop 2461: Loss: 2.75e-03, Avg Return: 0.485, Regret: 0.3752, Entropy: 0.0957 +[2026-03-20T17:58:55.353811Z] Loop 2462: Loss: 2.69e-03, Avg Return: 0.487, Regret: 0.3752, Entropy: 0.0928 +[2026-03-20T17:58:56.208213Z] Loop 2463: Loss: 2.58e-03, Avg Return: 0.481, Regret: 0.3752, Entropy: 0.0890 +[2026-03-20T17:58:57.061389Z] Loop 2464: Loss: 2.28e-03, Avg Return: 0.488, Regret: 0.3752, Entropy: 0.0811 +[2026-03-20T17:58:57.914929Z] Loop 2465: Loss: 2.13e-03, Avg Return: 0.485, Regret: 0.3752, Entropy: 0.0772 +[2026-03-20T17:58:58.769863Z] Loop 2466: Loss: 1.62e-03, Avg Return: 0.483, Regret: 0.3752, Entropy: 0.0716 +[2026-03-20T17:58:59.625378Z] Loop 2467: Loss: 1.54e-03, Avg Return: 0.480, Regret: 0.3752, Entropy: 0.0632 +[2026-03-20T17:59:00.478172Z] Loop 2468: Loss: 1.56e-03, Avg Return: 0.485, Regret: 0.3752, Entropy: 0.0569 +[2026-03-20T17:59:01.331600Z] Loop 2469: Loss: 2.00e-03, Avg Return: 0.482, Regret: 0.3752, Entropy: 0.0615 +[2026-03-20T17:59:02.224949Z] Loop 2470: Loss: 2.36e-03, Avg Return: 0.482, Regret: 0.3768, Entropy: 0.0639 +[2026-03-20T17:59:03.079078Z] Loop 2471: Loss: 2.71e-03, Avg Return: 0.492, Regret: 0.3768, Entropy: 0.0665 +[2026-03-20T17:59:03.931235Z] Loop 2472: Loss: 2.67e-03, Avg Return: 0.482, Regret: 0.3768, Entropy: 0.0657 +[2026-03-20T17:59:04.783303Z] Loop 2473: Loss: 2.78e-03, Avg Return: 0.488, Regret: 0.3768, Entropy: 0.0675 +[2026-03-20T17:59:05.637362Z] Loop 2474: Loss: 2.58e-03, Avg Return: 0.478, Regret: 0.3768, Entropy: 0.0662 +[2026-03-20T17:59:06.492032Z] Loop 2475: Loss: 2.76e-03, Avg Return: 0.485, Regret: 0.3768, Entropy: 0.0695 +[2026-03-20T17:59:07.344285Z] Loop 2476: Loss: 2.99e-03, Avg Return: 0.486, Regret: 0.3768, Entropy: 0.0722 +[2026-03-20T17:59:08.196447Z] Loop 2477: Loss: 3.68e-03, Avg Return: 0.491, Regret: 0.3768, Entropy: 0.0791 +[2026-03-20T17:59:09.050989Z] Loop 2478: Loss: 4.28e-03, Avg Return: 0.482, Regret: 0.3768, Entropy: 0.0865 +[2026-03-20T17:59:09.904868Z] Loop 2479: Loss: 3.46e-03, Avg Return: 0.487, Regret: 0.3768, Entropy: 0.0802 +[2026-03-20T17:59:10.797763Z] Loop 2480: Loss: 3.02e-03, Avg Return: 0.485, Regret: 0.3762, Entropy: 0.0754 +[2026-03-20T17:59:11.650257Z] Loop 2481: Loss: 3.28e-03, Avg Return: 0.482, Regret: 0.3762, Entropy: 0.0773 +[2026-03-20T17:59:12.503227Z] Loop 2482: Loss: 3.75e-03, Avg Return: 0.487, Regret: 0.3762, Entropy: 0.0788 +[2026-03-20T17:59:13.357022Z] Loop 2483: Loss: 3.32e-03, Avg Return: 0.491, Regret: 0.3762, Entropy: 0.0792 +[2026-03-20T17:59:14.210762Z] Loop 2484: Loss: 3.42e-03, Avg Return: 0.483, Regret: 0.3762, Entropy: 0.0786 +[2026-03-20T17:59:15.063176Z] Loop 2485: Loss: 3.92e-03, Avg Return: 0.475, Regret: 0.3762, Entropy: 0.0836 +[2026-03-20T17:59:15.915691Z] Loop 2486: Loss: 3.87e-03, Avg Return: 0.488, Regret: 0.3762, Entropy: 0.0818 +[2026-03-20T17:59:16.769535Z] Loop 2487: Loss: 3.61e-03, Avg Return: 0.488, Regret: 0.3762, Entropy: 0.0789 +[2026-03-20T17:59:17.622828Z] Loop 2488: Loss: 3.47e-03, Avg Return: 0.487, Regret: 0.3762, Entropy: 0.0825 +[2026-03-20T17:59:18.476232Z] Loop 2489: Loss: 3.88e-03, Avg Return: 0.484, Regret: 0.3762, Entropy: 0.0813 +[2026-03-20T17:59:19.366872Z] Loop 2490: Loss: 3.54e-03, Avg Return: 0.482, Regret: 0.3803, Entropy: 0.0808 +[2026-03-20T17:59:20.221145Z] Loop 2491: Loss: 3.74e-03, Avg Return: 0.476, Regret: 0.3803, Entropy: 0.0821 +[2026-03-20T17:59:21.075098Z] Loop 2492: Loss: 3.80e-03, Avg Return: 0.480, Regret: 0.3803, Entropy: 0.0807 +[2026-03-20T17:59:21.929416Z] Loop 2493: Loss: 4.19e-03, Avg Return: 0.482, Regret: 0.3803, Entropy: 0.0833 +[2026-03-20T17:59:22.781778Z] Loop 2494: Loss: 3.80e-03, Avg Return: 0.482, Regret: 0.3803, Entropy: 0.0820 +[2026-03-20T17:59:23.634639Z] Loop 2495: Loss: 3.60e-03, Avg Return: 0.484, Regret: 0.3803, Entropy: 0.0784 +[2026-03-20T17:59:24.487299Z] Loop 2496: Loss: 3.39e-03, Avg Return: 0.485, Regret: 0.3803, Entropy: 0.0826 +[2026-03-20T17:59:25.340865Z] Loop 2497: Loss: 3.48e-03, Avg Return: 0.486, Regret: 0.3803, Entropy: 0.0775 +[2026-03-20T17:59:26.194156Z] Loop 2498: Loss: 3.79e-03, Avg Return: 0.489, Regret: 0.3803, Entropy: 0.0804 +[2026-03-20T17:59:27.047467Z] Loop 2499: Loss: 3.41e-03, Avg Return: 0.480, Regret: 0.3803, Entropy: 0.0752 +[2026-03-20T17:59:27.938584Z] Loop 2500: Loss: 3.16e-03, Avg Return: 0.486, Regret: 0.3770, Entropy: 0.0696 +[2026-03-20T17:59:28.791977Z] Loop 2501: Loss: 2.86e-03, Avg Return: 0.487, Regret: 0.3770, Entropy: 0.0645 +[2026-03-20T17:59:29.645453Z] Loop 2502: Loss: 2.94e-03, Avg Return: 0.482, Regret: 0.3770, Entropy: 0.0653 +[2026-03-20T17:59:30.498597Z] Loop 2503: Loss: 3.11e-03, Avg Return: 0.480, Regret: 0.3770, Entropy: 0.0677 +[2026-03-20T17:59:31.351389Z] Loop 2504: Loss: 2.81e-03, Avg Return: 0.486, Regret: 0.3770, Entropy: 0.0652 +[2026-03-20T17:59:32.205248Z] Loop 2505: Loss: 2.52e-03, Avg Return: 0.495, Regret: 0.3770, Entropy: 0.0599 +[2026-03-20T17:59:33.059053Z] Loop 2506: Loss: 2.44e-03, Avg Return: 0.478, Regret: 0.3770, Entropy: 0.0599 +[2026-03-20T17:59:33.912574Z] Loop 2507: Loss: 2.96e-03, Avg Return: 0.487, Regret: 0.3770, Entropy: 0.0665 +[2026-03-20T17:59:34.764709Z] Loop 2508: Loss: 3.53e-03, Avg Return: 0.486, Regret: 0.3770, Entropy: 0.0802 +[2026-03-20T17:59:35.617058Z] Loop 2509: Loss: 3.52e-03, Avg Return: 0.489, Regret: 0.3770, Entropy: 0.0827 +[2026-03-20T17:59:36.508969Z] Loop 2510: Loss: 2.31e-03, Avg Return: 0.481, Regret: 0.3753, Entropy: 0.0744 +[2026-03-20T17:59:37.362752Z] Loop 2511: Loss: 1.84e-03, Avg Return: 0.485, Regret: 0.3753, Entropy: 0.0679 +[2026-03-20T17:59:38.215688Z] Loop 2512: Loss: 1.46e-03, Avg Return: 0.484, Regret: 0.3753, Entropy: 0.0638 +[2026-03-20T17:59:39.069226Z] Loop 2513: Loss: 1.75e-03, Avg Return: 0.487, Regret: 0.3753, Entropy: 0.0735 +[2026-03-20T17:59:39.922997Z] Loop 2514: Loss: 1.98e-03, Avg Return: 0.487, Regret: 0.3753, Entropy: 0.0826 +[2026-03-20T17:59:40.777315Z] Loop 2515: Loss: 2.48e-03, Avg Return: 0.485, Regret: 0.3753, Entropy: 0.0935 +[2026-03-20T17:59:41.630418Z] Loop 2516: Loss: 3.00e-03, Avg Return: 0.483, Regret: 0.3753, Entropy: 0.1122 +[2026-03-20T17:59:42.482604Z] Loop 2517: Loss: 3.84e-03, Avg Return: 0.497, Regret: 0.3753, Entropy: 0.1119 +[2026-03-20T17:59:43.335894Z] Loop 2518: Loss: 3.30e-03, Avg Return: 0.481, Regret: 0.3753, Entropy: 0.1097 +[2026-03-20T17:59:44.189963Z] Loop 2519: Loss: 2.80e-03, Avg Return: 0.486, Regret: 0.3753, Entropy: 0.0998 +[2026-03-20T17:59:45.082802Z] Loop 2520: Loss: 2.44e-03, Avg Return: 0.494, Regret: 0.3752, Entropy: 0.0824 +[2026-03-20T17:59:45.936607Z] Loop 2521: Loss: 2.31e-03, Avg Return: 0.493, Regret: 0.3752, Entropy: 0.0793 +[2026-03-20T17:59:46.790441Z] Loop 2522: Loss: 1.82e-03, Avg Return: 0.494, Regret: 0.3752, Entropy: 0.0800 +[2026-03-20T17:59:47.645356Z] Loop 2523: Loss: 1.52e-03, Avg Return: 0.488, Regret: 0.3752, Entropy: 0.0750 +[2026-03-20T17:59:48.499300Z] Loop 2524: Loss: 1.35e-03, Avg Return: 0.491, Regret: 0.3752, Entropy: 0.0724 +[2026-03-20T17:59:49.351599Z] Loop 2525: Loss: 1.39e-03, Avg Return: 0.486, Regret: 0.3752, Entropy: 0.0684 +[2026-03-20T17:59:50.203098Z] Loop 2526: Loss: 1.53e-03, Avg Return: 0.486, Regret: 0.3752, Entropy: 0.0704 +[2026-03-20T17:59:51.055528Z] Loop 2527: Loss: 1.52e-03, Avg Return: 0.482, Regret: 0.3752, Entropy: 0.0760 +[2026-03-20T17:59:51.909055Z] Loop 2528: Loss: 1.24e-03, Avg Return: 0.489, Regret: 0.3752, Entropy: 0.0713 +[2026-03-20T17:59:52.764861Z] Loop 2529: Loss: 1.14e-03, Avg Return: 0.496, Regret: 0.3752, Entropy: 0.0720 +[2026-03-20T17:59:53.659987Z] Loop 2530: Loss: 1.68e-03, Avg Return: 0.487, Regret: 0.3758, Entropy: 0.0715 +[2026-03-20T17:59:54.513686Z] Loop 2531: Loss: 1.95e-03, Avg Return: 0.478, Regret: 0.3758, Entropy: 0.0740 +[2026-03-20T17:59:55.368513Z] Loop 2532: Loss: 1.96e-03, Avg Return: 0.487, Regret: 0.3758, Entropy: 0.0792 +[2026-03-20T17:59:56.222853Z] Loop 2533: Loss: 1.82e-03, Avg Return: 0.493, Regret: 0.3758, Entropy: 0.0669 +[2026-03-20T17:59:57.077405Z] Loop 2534: Loss: 1.74e-03, Avg Return: 0.494, Regret: 0.3758, Entropy: 0.0636 +[2026-03-20T17:59:57.931774Z] Loop 2535: Loss: 1.73e-03, Avg Return: 0.479, Regret: 0.3758, Entropy: 0.0660 +[2026-03-20T17:59:58.786117Z] Loop 2536: Loss: 1.55e-03, Avg Return: 0.480, Regret: 0.3758, Entropy: 0.0620 +[2026-03-20T17:59:59.639766Z] Loop 2537: Loss: 1.74e-03, Avg Return: 0.486, Regret: 0.3758, Entropy: 0.0657 +[2026-03-20T18:00:00.494031Z] Loop 2538: Loss: 1.66e-03, Avg Return: 0.483, Regret: 0.3758, Entropy: 0.0669 +[2026-03-20T18:00:01.347466Z] Loop 2539: Loss: 1.78e-03, Avg Return: 0.487, Regret: 0.3758, Entropy: 0.0720 +[2026-03-20T18:00:02.243409Z] Loop 2540: Loss: 1.67e-03, Avg Return: 0.484, Regret: 0.3771, Entropy: 0.0675 +[2026-03-20T18:00:03.097689Z] Loop 2541: Loss: 1.83e-03, Avg Return: 0.484, Regret: 0.3771, Entropy: 0.0678 +[2026-03-20T18:00:03.953491Z] Loop 2542: Loss: 1.92e-03, Avg Return: 0.486, Regret: 0.3771, Entropy: 0.0702 +[2026-03-20T18:00:04.809810Z] Loop 2543: Loss: 2.02e-03, Avg Return: 0.487, Regret: 0.3771, Entropy: 0.0772 +[2026-03-20T18:00:05.664361Z] Loop 2544: Loss: 2.03e-03, Avg Return: 0.488, Regret: 0.3771, Entropy: 0.0780 +[2026-03-20T18:00:06.519082Z] Loop 2545: Loss: 1.87e-03, Avg Return: 0.479, Regret: 0.3771, Entropy: 0.0755 +[2026-03-20T18:00:07.373850Z] Loop 2546: Loss: 2.17e-03, Avg Return: 0.488, Regret: 0.3771, Entropy: 0.0783 +[2026-03-20T18:00:08.228350Z] Loop 2547: Loss: 2.14e-03, Avg Return: 0.495, Regret: 0.3771, Entropy: 0.0788 +[2026-03-20T18:00:09.082670Z] Loop 2548: Loss: 1.71e-03, Avg Return: 0.490, Regret: 0.3771, Entropy: 0.0723 +[2026-03-20T18:00:09.937121Z] Loop 2549: Loss: 1.16e-03, Avg Return: 0.477, Regret: 0.3771, Entropy: 0.0572 +[2026-03-20T18:00:10.831462Z] Loop 2550: Loss: 1.14e-03, Avg Return: 0.493, Regret: 0.3784, Entropy: 0.0522 +[2026-03-20T18:00:11.685349Z] Loop 2551: Loss: 9.35e-04, Avg Return: 0.491, Regret: 0.3784, Entropy: 0.0482 +[2026-03-20T18:00:12.539356Z] Loop 2552: Loss: 1.11e-03, Avg Return: 0.483, Regret: 0.3784, Entropy: 0.0454 +[2026-03-20T18:00:13.393070Z] Loop 2553: Loss: 9.41e-04, Avg Return: 0.473, Regret: 0.3784, Entropy: 0.0446 +[2026-03-20T18:00:14.246504Z] Loop 2554: Loss: 7.52e-04, Avg Return: 0.476, Regret: 0.3784, Entropy: 0.0478 +[2026-03-20T18:00:15.100829Z] Loop 2555: Loss: 1.12e-03, Avg Return: 0.484, Regret: 0.3784, Entropy: 0.0478 +[2026-03-20T18:00:15.954591Z] Loop 2556: Loss: 8.98e-04, Avg Return: 0.491, Regret: 0.3784, Entropy: 0.0468 +[2026-03-20T18:00:16.807115Z] Loop 2557: Loss: 1.00e-03, Avg Return: 0.479, Regret: 0.3784, Entropy: 0.0480 +[2026-03-20T18:00:17.660652Z] Loop 2558: Loss: 9.44e-04, Avg Return: 0.482, Regret: 0.3784, Entropy: 0.0560 +[2026-03-20T18:00:18.514755Z] Loop 2559: Loss: 1.44e-03, Avg Return: 0.490, Regret: 0.3784, Entropy: 0.0659 +[2026-03-20T18:00:19.408457Z] Loop 2560: Loss: 2.11e-03, Avg Return: 0.489, Regret: 0.3760, Entropy: 0.0786 +[2026-03-20T18:00:20.261323Z] Loop 2561: Loss: 2.48e-03, Avg Return: 0.481, Regret: 0.3760, Entropy: 0.0909 +[2026-03-20T18:00:21.114277Z] Loop 2562: Loss: 3.17e-03, Avg Return: 0.490, Regret: 0.3760, Entropy: 0.0992 +[2026-03-20T18:00:21.968210Z] Loop 2563: Loss: 2.54e-03, Avg Return: 0.484, Regret: 0.3760, Entropy: 0.0999 +[2026-03-20T18:00:22.824416Z] Loop 2564: Loss: 2.59e-03, Avg Return: 0.499, Regret: 0.3760, Entropy: 0.0942 +[2026-03-20T18:00:23.677729Z] Loop 2565: Loss: 2.27e-03, Avg Return: 0.485, Regret: 0.3760, Entropy: 0.0925 +[2026-03-20T18:00:24.531380Z] Loop 2566: Loss: 2.61e-03, Avg Return: 0.486, Regret: 0.3760, Entropy: 0.0897 +[2026-03-20T18:00:25.386859Z] Loop 2567: Loss: 2.41e-03, Avg Return: 0.482, Regret: 0.3760, Entropy: 0.0906 +[2026-03-20T18:00:26.240131Z] Loop 2568: Loss: 2.27e-03, Avg Return: 0.480, Regret: 0.3760, Entropy: 0.0945 +[2026-03-20T18:00:27.092970Z] Loop 2569: Loss: 2.31e-03, Avg Return: 0.489, Regret: 0.3760, Entropy: 0.0871 +[2026-03-20T18:00:27.987742Z] Loop 2570: Loss: 2.18e-03, Avg Return: 0.488, Regret: 0.3765, Entropy: 0.0859 +[2026-03-20T18:00:28.841682Z] Loop 2571: Loss: 2.51e-03, Avg Return: 0.489, Regret: 0.3765, Entropy: 0.0934 +[2026-03-20T18:00:29.696765Z] Loop 2572: Loss: 2.51e-03, Avg Return: 0.487, Regret: 0.3765, Entropy: 0.0932 +[2026-03-20T18:00:30.550141Z] Loop 2573: Loss: 2.26e-03, Avg Return: 0.492, Regret: 0.3765, Entropy: 0.0920 +[2026-03-20T18:00:31.403405Z] Loop 2574: Loss: 2.57e-03, Avg Return: 0.486, Regret: 0.3765, Entropy: 0.0943 +[2026-03-20T18:00:32.256051Z] Loop 2575: Loss: 2.39e-03, Avg Return: 0.484, Regret: 0.3765, Entropy: 0.0936 +[2026-03-20T18:00:33.108690Z] Loop 2576: Loss: 2.72e-03, Avg Return: 0.491, Regret: 0.3765, Entropy: 0.0996 +[2026-03-20T18:00:33.962745Z] Loop 2577: Loss: 2.57e-03, Avg Return: 0.481, Regret: 0.3765, Entropy: 0.0944 +[2026-03-20T18:00:34.816401Z] Loop 2578: Loss: 2.71e-03, Avg Return: 0.487, Regret: 0.3765, Entropy: 0.0968 +[2026-03-20T18:00:35.670634Z] Loop 2579: Loss: 2.82e-03, Avg Return: 0.495, Regret: 0.3765, Entropy: 0.0992 +[2026-03-20T18:00:36.564120Z] Loop 2580: Loss: 2.57e-03, Avg Return: 0.479, Regret: 0.3765, Entropy: 0.0955 +[2026-03-20T18:00:37.418114Z] Loop 2581: Loss: 2.64e-03, Avg Return: 0.478, Regret: 0.3765, Entropy: 0.0922 +[2026-03-20T18:00:38.272665Z] Loop 2582: Loss: 2.57e-03, Avg Return: 0.480, Regret: 0.3765, Entropy: 0.0952 +[2026-03-20T18:00:39.127389Z] Loop 2583: Loss: 2.32e-03, Avg Return: 0.490, Regret: 0.3765, Entropy: 0.0889 +[2026-03-20T18:00:39.981546Z] Loop 2584: Loss: 2.22e-03, Avg Return: 0.489, Regret: 0.3765, Entropy: 0.0797 +[2026-03-20T18:00:40.834980Z] Loop 2585: Loss: 1.73e-03, Avg Return: 0.485, Regret: 0.3765, Entropy: 0.0736 +[2026-03-20T18:00:41.689011Z] Loop 2586: Loss: 1.35e-03, Avg Return: 0.485, Regret: 0.3765, Entropy: 0.0671 +[2026-03-20T18:00:42.543499Z] Loop 2587: Loss: 1.45e-03, Avg Return: 0.485, Regret: 0.3765, Entropy: 0.0650 +[2026-03-20T18:00:43.398613Z] Loop 2588: Loss: 1.37e-03, Avg Return: 0.486, Regret: 0.3765, Entropy: 0.0656 +[2026-03-20T18:00:44.251894Z] Loop 2589: Loss: 1.26e-03, Avg Return: 0.492, Regret: 0.3765, Entropy: 0.0621 +[2026-03-20T18:00:45.144391Z] Loop 2590: Loss: 1.15e-03, Avg Return: 0.492, Regret: 0.3760, Entropy: 0.0620 +[2026-03-20T18:00:45.997364Z] Loop 2591: Loss: 1.11e-03, Avg Return: 0.490, Regret: 0.3760, Entropy: 0.0626 +[2026-03-20T18:00:46.851813Z] Loop 2592: Loss: 1.05e-03, Avg Return: 0.484, Regret: 0.3760, Entropy: 0.0627 +[2026-03-20T18:00:47.704988Z] Loop 2593: Loss: 1.08e-03, Avg Return: 0.490, Regret: 0.3760, Entropy: 0.0539 +[2026-03-20T18:00:48.557430Z] Loop 2594: Loss: 9.54e-04, Avg Return: 0.485, Regret: 0.3760, Entropy: 0.0556 +[2026-03-20T18:00:49.410288Z] Loop 2595: Loss: 1.14e-03, Avg Return: 0.495, Regret: 0.3760, Entropy: 0.0549 +[2026-03-20T18:00:50.264297Z] Loop 2596: Loss: 9.31e-04, Avg Return: 0.491, Regret: 0.3760, Entropy: 0.0554 +[2026-03-20T18:00:51.118225Z] Loop 2597: Loss: 8.63e-04, Avg Return: 0.485, Regret: 0.3760, Entropy: 0.0516 +[2026-03-20T18:00:51.970932Z] Loop 2598: Loss: 1.01e-03, Avg Return: 0.482, Regret: 0.3760, Entropy: 0.0523 +[2026-03-20T18:00:52.823735Z] Loop 2599: Loss: 1.04e-03, Avg Return: 0.489, Regret: 0.3760, Entropy: 0.0559 +[2026-03-20T18:00:53.716417Z] Loop 2600: Loss: 8.39e-04, Avg Return: 0.483, Regret: 0.3772, Entropy: 0.0498 +[2026-03-20T18:00:54.570925Z] Loop 2601: Loss: 8.90e-04, Avg Return: 0.486, Regret: 0.3772, Entropy: 0.0471 +[2026-03-20T18:00:55.424891Z] Loop 2602: Loss: 9.33e-04, Avg Return: 0.484, Regret: 0.3772, Entropy: 0.0460 +[2026-03-20T18:00:56.278134Z] Loop 2603: Loss: 9.16e-04, Avg Return: 0.487, Regret: 0.3772, Entropy: 0.0475 +[2026-03-20T18:00:57.131700Z] Loop 2604: Loss: 8.48e-04, Avg Return: 0.490, Regret: 0.3772, Entropy: 0.0488 +[2026-03-20T18:00:57.985614Z] Loop 2605: Loss: 8.92e-04, Avg Return: 0.477, Regret: 0.3772, Entropy: 0.0495 +[2026-03-20T18:00:58.838927Z] Loop 2606: Loss: 7.93e-04, Avg Return: 0.480, Regret: 0.3772, Entropy: 0.0467 +[2026-03-20T18:00:59.691976Z] Loop 2607: Loss: 9.67e-04, Avg Return: 0.491, Regret: 0.3772, Entropy: 0.0492 +[2026-03-20T18:01:00.545640Z] Loop 2608: Loss: 9.71e-04, Avg Return: 0.492, Regret: 0.3772, Entropy: 0.0539 +[2026-03-20T18:01:01.400300Z] Loop 2609: Loss: 1.16e-03, Avg Return: 0.498, Regret: 0.3772, Entropy: 0.0493 +[2026-03-20T18:01:02.294771Z] Loop 2610: Loss: 1.03e-03, Avg Return: 0.489, Regret: 0.3765, Entropy: 0.0569 +[2026-03-20T18:01:03.148480Z] Loop 2611: Loss: 1.00e-03, Avg Return: 0.493, Regret: 0.3765, Entropy: 0.0514 +[2026-03-20T18:01:04.003098Z] Loop 2612: Loss: 1.05e-03, Avg Return: 0.493, Regret: 0.3765, Entropy: 0.0518 +[2026-03-20T18:01:04.855796Z] Loop 2613: Loss: 9.96e-04, Avg Return: 0.484, Regret: 0.3765, Entropy: 0.0517 +[2026-03-20T18:01:05.709511Z] Loop 2614: Loss: 1.06e-03, Avg Return: 0.490, Regret: 0.3765, Entropy: 0.0553 +[2026-03-20T18:01:06.562561Z] Loop 2615: Loss: 8.73e-04, Avg Return: 0.487, Regret: 0.3765, Entropy: 0.0549 +[2026-03-20T18:01:07.416231Z] Loop 2616: Loss: 9.00e-04, Avg Return: 0.480, Regret: 0.3765, Entropy: 0.0564 +[2026-03-20T18:01:08.269661Z] Loop 2617: Loss: 1.06e-03, Avg Return: 0.483, Regret: 0.3765, Entropy: 0.0621 +[2026-03-20T18:01:09.122807Z] Loop 2618: Loss: 1.22e-03, Avg Return: 0.493, Regret: 0.3765, Entropy: 0.0659 +[2026-03-20T18:01:09.975595Z] Loop 2619: Loss: 1.15e-03, Avg Return: 0.481, Regret: 0.3765, Entropy: 0.0706 +[2026-03-20T18:01:10.868006Z] Loop 2620: Loss: 1.63e-03, Avg Return: 0.488, Regret: 0.3759, Entropy: 0.0755 +[2026-03-20T18:01:11.721639Z] Loop 2621: Loss: 1.71e-03, Avg Return: 0.490, Regret: 0.3759, Entropy: 0.0797 +[2026-03-20T18:01:12.575276Z] Loop 2622: Loss: 1.94e-03, Avg Return: 0.482, Regret: 0.3759, Entropy: 0.0837 +[2026-03-20T18:01:13.429715Z] Loop 2623: Loss: 1.80e-03, Avg Return: 0.484, Regret: 0.3759, Entropy: 0.0866 +[2026-03-20T18:01:14.282966Z] Loop 2624: Loss: 2.05e-03, Avg Return: 0.483, Regret: 0.3759, Entropy: 0.0801 +[2026-03-20T18:01:15.137216Z] Loop 2625: Loss: 1.77e-03, Avg Return: 0.488, Regret: 0.3759, Entropy: 0.0822 +[2026-03-20T18:01:15.990628Z] Loop 2626: Loss: 1.43e-03, Avg Return: 0.486, Regret: 0.3759, Entropy: 0.0796 +[2026-03-20T18:01:16.844553Z] Loop 2627: Loss: 1.55e-03, Avg Return: 0.492, Regret: 0.3759, Entropy: 0.0698 +[2026-03-20T18:01:17.697798Z] Loop 2628: Loss: 1.22e-03, Avg Return: 0.479, Regret: 0.3759, Entropy: 0.0671 +[2026-03-20T18:01:18.550464Z] Loop 2629: Loss: 1.19e-03, Avg Return: 0.487, Regret: 0.3759, Entropy: 0.0615 +[2026-03-20T18:01:19.444418Z] Loop 2630: Loss: 1.37e-03, Avg Return: 0.489, Regret: 0.3759, Entropy: 0.0631 +[2026-03-20T18:01:20.298501Z] Loop 2631: Loss: 9.44e-04, Avg Return: 0.495, Regret: 0.3759, Entropy: 0.0508 +[2026-03-20T18:01:21.152775Z] Loop 2632: Loss: 8.32e-04, Avg Return: 0.495, Regret: 0.3759, Entropy: 0.0511 +[2026-03-20T18:01:22.005784Z] Loop 2633: Loss: 6.79e-04, Avg Return: 0.492, Regret: 0.3759, Entropy: 0.0411 +[2026-03-20T18:01:22.858770Z] Loop 2634: Loss: 4.45e-04, Avg Return: 0.481, Regret: 0.3759, Entropy: 0.0405 +[2026-03-20T18:01:23.711800Z] Loop 2635: Loss: 5.66e-04, Avg Return: 0.485, Regret: 0.3759, Entropy: 0.0417 +[2026-03-20T18:01:24.565911Z] Loop 2636: Loss: 6.12e-04, Avg Return: 0.481, Regret: 0.3759, Entropy: 0.0403 +[2026-03-20T18:01:25.419138Z] Loop 2637: Loss: 5.97e-04, Avg Return: 0.483, Regret: 0.3759, Entropy: 0.0392 +[2026-03-20T18:01:26.272635Z] Loop 2638: Loss: 5.13e-04, Avg Return: 0.484, Regret: 0.3759, Entropy: 0.0354 +[2026-03-20T18:01:27.124783Z] Loop 2639: Loss: 6.36e-04, Avg Return: 0.483, Regret: 0.3759, Entropy: 0.0394 +[2026-03-20T18:01:28.016777Z] Loop 2640: Loss: 4.65e-04, Avg Return: 0.479, Regret: 0.3777, Entropy: 0.0440 +[2026-03-20T18:01:28.870981Z] Loop 2641: Loss: 7.25e-04, Avg Return: 0.493, Regret: 0.3777, Entropy: 0.0432 +[2026-03-20T18:01:29.724814Z] Loop 2642: Loss: 6.07e-04, Avg Return: 0.482, Regret: 0.3777, Entropy: 0.0480 +[2026-03-20T18:01:30.579122Z] Loop 2643: Loss: 9.32e-04, Avg Return: 0.487, Regret: 0.3777, Entropy: 0.0575 +[2026-03-20T18:01:31.432254Z] Loop 2644: Loss: 9.64e-04, Avg Return: 0.491, Regret: 0.3777, Entropy: 0.0632 +[2026-03-20T18:01:32.286500Z] Loop 2645: Loss: 1.32e-03, Avg Return: 0.488, Regret: 0.3777, Entropy: 0.0663 +[2026-03-20T18:01:33.141238Z] Loop 2646: Loss: 1.38e-03, Avg Return: 0.489, Regret: 0.3777, Entropy: 0.0721 +[2026-03-20T18:01:33.995733Z] Loop 2647: Loss: 1.56e-03, Avg Return: 0.490, Regret: 0.3777, Entropy: 0.0784 +[2026-03-20T18:01:34.848222Z] Loop 2648: Loss: 1.42e-03, Avg Return: 0.481, Regret: 0.3777, Entropy: 0.0769 +[2026-03-20T18:01:35.701626Z] Loop 2649: Loss: 1.54e-03, Avg Return: 0.488, Regret: 0.3777, Entropy: 0.0840 +[2026-03-20T18:01:36.595284Z] Loop 2650: Loss: 1.83e-03, Avg Return: 0.493, Regret: 0.3757, Entropy: 0.0853 +[2026-03-20T18:01:37.449816Z] Loop 2651: Loss: 1.87e-03, Avg Return: 0.492, Regret: 0.3757, Entropy: 0.0882 +[2026-03-20T18:01:38.304209Z] Loop 2652: Loss: 2.06e-03, Avg Return: 0.489, Regret: 0.3757, Entropy: 0.0841 +[2026-03-20T18:01:39.159541Z] Loop 2653: Loss: 2.11e-03, Avg Return: 0.486, Regret: 0.3757, Entropy: 0.0858 +[2026-03-20T18:01:40.015173Z] Loop 2654: Loss: 2.04e-03, Avg Return: 0.484, Regret: 0.3757, Entropy: 0.0871 +[2026-03-20T18:01:40.869719Z] Loop 2655: Loss: 2.37e-03, Avg Return: 0.488, Regret: 0.3757, Entropy: 0.0940 +[2026-03-20T18:01:41.724163Z] Loop 2656: Loss: 2.57e-03, Avg Return: 0.487, Regret: 0.3757, Entropy: 0.0951 +[2026-03-20T18:01:42.578546Z] Loop 2657: Loss: 2.62e-03, Avg Return: 0.478, Regret: 0.3757, Entropy: 0.0933 +[2026-03-20T18:01:43.431232Z] Loop 2658: Loss: 2.94e-03, Avg Return: 0.490, Regret: 0.3757, Entropy: 0.0945 +[2026-03-20T18:01:44.284290Z] Loop 2659: Loss: 1.91e-03, Avg Return: 0.483, Regret: 0.3757, Entropy: 0.0810 +[2026-03-20T18:01:45.176973Z] Loop 2660: Loss: 1.81e-03, Avg Return: 0.488, Regret: 0.3775, Entropy: 0.0709 +[2026-03-20T18:01:46.031372Z] Loop 2661: Loss: 2.05e-03, Avg Return: 0.493, Regret: 0.3775, Entropy: 0.0732 +[2026-03-20T18:01:46.884106Z] Loop 2662: Loss: 2.02e-03, Avg Return: 0.486, Regret: 0.3775, Entropy: 0.0735 +[2026-03-20T18:01:47.737039Z] Loop 2663: Loss: 2.08e-03, Avg Return: 0.487, Regret: 0.3775, Entropy: 0.0716 +[2026-03-20T18:01:48.590071Z] Loop 2664: Loss: 1.88e-03, Avg Return: 0.481, Regret: 0.3775, Entropy: 0.0805 +[2026-03-20T18:01:49.444377Z] Loop 2665: Loss: 1.61e-03, Avg Return: 0.496, Regret: 0.3775, Entropy: 0.0711 +[2026-03-20T18:01:50.297746Z] Loop 2666: Loss: 1.59e-03, Avg Return: 0.496, Regret: 0.3775, Entropy: 0.0744 +[2026-03-20T18:01:51.150305Z] Loop 2667: Loss: 1.72e-03, Avg Return: 0.489, Regret: 0.3775, Entropy: 0.0718 +[2026-03-20T18:01:52.004018Z] Loop 2668: Loss: 1.68e-03, Avg Return: 0.487, Regret: 0.3775, Entropy: 0.0672 +[2026-03-20T18:01:52.859227Z] Loop 2669: Loss: 1.65e-03, Avg Return: 0.485, Regret: 0.3775, Entropy: 0.0695 +[2026-03-20T18:01:53.752307Z] Loop 2670: Loss: 1.47e-03, Avg Return: 0.484, Regret: 0.3752, Entropy: 0.0684 +[2026-03-20T18:01:54.605469Z] Loop 2671: Loss: 1.52e-03, Avg Return: 0.491, Regret: 0.3752, Entropy: 0.0735 +[2026-03-20T18:01:55.459023Z] Loop 2672: Loss: 1.46e-03, Avg Return: 0.490, Regret: 0.3752, Entropy: 0.0694 +[2026-03-20T18:01:56.314643Z] Loop 2673: Loss: 1.59e-03, Avg Return: 0.489, Regret: 0.3752, Entropy: 0.0688 +[2026-03-20T18:01:57.169018Z] Loop 2674: Loss: 1.46e-03, Avg Return: 0.496, Regret: 0.3752, Entropy: 0.0672 +[2026-03-20T18:01:58.021628Z] Loop 2675: Loss: 1.45e-03, Avg Return: 0.487, Regret: 0.3752, Entropy: 0.0730 +[2026-03-20T18:01:58.873932Z] Loop 2676: Loss: 1.60e-03, Avg Return: 0.488, Regret: 0.3752, Entropy: 0.0710 +[2026-03-20T18:01:59.727925Z] Loop 2677: Loss: 1.53e-03, Avg Return: 0.489, Regret: 0.3752, Entropy: 0.0674 +[2026-03-20T18:02:00.582364Z] Loop 2678: Loss: 1.51e-03, Avg Return: 0.486, Regret: 0.3752, Entropy: 0.0753 +[2026-03-20T18:02:01.435626Z] Loop 2679: Loss: 1.48e-03, Avg Return: 0.490, Regret: 0.3752, Entropy: 0.0696 +[2026-03-20T18:02:02.327338Z] Loop 2680: Loss: 1.74e-03, Avg Return: 0.493, Regret: 0.3750, Entropy: 0.0678 +[2026-03-20T18:02:03.181565Z] Loop 2681: Loss: 1.78e-03, Avg Return: 0.490, Regret: 0.3750, Entropy: 0.0721 +[2026-03-20T18:02:04.035970Z] Loop 2682: Loss: 1.82e-03, Avg Return: 0.497, Regret: 0.3750, Entropy: 0.0768 +[2026-03-20T18:02:04.889825Z] Loop 2683: Loss: 2.16e-03, Avg Return: 0.486, Regret: 0.3750, Entropy: 0.0766 +[2026-03-20T18:02:05.742724Z] Loop 2684: Loss: 2.11e-03, Avg Return: 0.483, Regret: 0.3750, Entropy: 0.0787 +[2026-03-20T18:02:06.596682Z] Loop 2685: Loss: 1.79e-03, Avg Return: 0.488, Regret: 0.3750, Entropy: 0.0806 +[2026-03-20T18:02:07.450445Z] Loop 2686: Loss: 2.05e-03, Avg Return: 0.487, Regret: 0.3750, Entropy: 0.0850 +[2026-03-20T18:02:08.304683Z] Loop 2687: Loss: 1.81e-03, Avg Return: 0.489, Regret: 0.3750, Entropy: 0.0837 +[2026-03-20T18:02:09.158117Z] Loop 2688: Loss: 1.46e-03, Avg Return: 0.486, Regret: 0.3750, Entropy: 0.0859 +[2026-03-20T18:02:10.010784Z] Loop 2689: Loss: 1.58e-03, Avg Return: 0.493, Regret: 0.3750, Entropy: 0.0751 +[2026-03-20T18:02:10.902620Z] Loop 2690: Loss: 1.78e-03, Avg Return: 0.493, Regret: 0.3750, Entropy: 0.0818 +[2026-03-20T18:02:11.756692Z] Loop 2691: Loss: 1.61e-03, Avg Return: 0.492, Regret: 0.3750, Entropy: 0.0907 +[2026-03-20T18:02:12.610304Z] Loop 2692: Loss: 1.46e-03, Avg Return: 0.488, Regret: 0.3750, Entropy: 0.0758 +[2026-03-20T18:02:13.462939Z] Loop 2693: Loss: 1.86e-03, Avg Return: 0.485, Regret: 0.3750, Entropy: 0.0840 +[2026-03-20T18:02:14.316760Z] Loop 2694: Loss: 1.70e-03, Avg Return: 0.486, Regret: 0.3750, Entropy: 0.0816 +[2026-03-20T18:02:15.170378Z] Loop 2695: Loss: 1.67e-03, Avg Return: 0.491, Regret: 0.3750, Entropy: 0.0838 +[2026-03-20T18:02:16.024775Z] Loop 2696: Loss: 1.50e-03, Avg Return: 0.489, Regret: 0.3750, Entropy: 0.0836 +[2026-03-20T18:02:16.878635Z] Loop 2697: Loss: 1.84e-03, Avg Return: 0.495, Regret: 0.3750, Entropy: 0.0793 +[2026-03-20T18:02:17.733052Z] Loop 2698: Loss: 1.82e-03, Avg Return: 0.497, Regret: 0.3750, Entropy: 0.0812 +[2026-03-20T18:02:18.586018Z] Loop 2699: Loss: 1.86e-03, Avg Return: 0.487, Regret: 0.3750, Entropy: 0.0862 +[2026-03-20T18:02:19.478897Z] Loop 2700: Loss: 2.55e-03, Avg Return: 0.498, Regret: 0.3752, Entropy: 0.0914 +[2026-03-20T18:02:20.331383Z] Loop 2701: Loss: 2.93e-03, Avg Return: 0.485, Regret: 0.3752, Entropy: 0.1002 +[2026-03-20T18:02:21.185299Z] Loop 2702: Loss: 3.58e-03, Avg Return: 0.491, Regret: 0.3752, Entropy: 0.1057 +[2026-03-20T18:02:22.038399Z] Loop 2703: Loss: 3.88e-03, Avg Return: 0.492, Regret: 0.3752, Entropy: 0.1114 +[2026-03-20T18:02:22.892116Z] Loop 2704: Loss: 3.88e-03, Avg Return: 0.483, Regret: 0.3752, Entropy: 0.1160 +[2026-03-20T18:02:23.746515Z] Loop 2705: Loss: 4.48e-03, Avg Return: 0.484, Regret: 0.3752, Entropy: 0.1215 +[2026-03-20T18:02:24.601529Z] Loop 2706: Loss: 4.75e-03, Avg Return: 0.491, Regret: 0.3752, Entropy: 0.1267 +[2026-03-20T18:02:25.454492Z] Loop 2707: Loss: 4.46e-03, Avg Return: 0.489, Regret: 0.3752, Entropy: 0.1177 +[2026-03-20T18:02:26.307327Z] Loop 2708: Loss: 3.86e-03, Avg Return: 0.492, Regret: 0.3752, Entropy: 0.1075 +[2026-03-20T18:02:27.161719Z] Loop 2709: Loss: 4.04e-03, Avg Return: 0.491, Regret: 0.3752, Entropy: 0.1066 +[2026-03-20T18:02:28.056135Z] Loop 2710: Loss: 3.54e-03, Avg Return: 0.482, Regret: 0.3759, Entropy: 0.1035 +[2026-03-20T18:02:28.909603Z] Loop 2711: Loss: 3.56e-03, Avg Return: 0.490, Regret: 0.3759, Entropy: 0.1012 +[2026-03-20T18:02:29.764866Z] Loop 2712: Loss: 3.90e-03, Avg Return: 0.491, Regret: 0.3759, Entropy: 0.0981 +[2026-03-20T18:02:30.619112Z] Loop 2713: Loss: 3.58e-03, Avg Return: 0.480, Regret: 0.3759, Entropy: 0.1010 +[2026-03-20T18:02:31.473762Z] Loop 2714: Loss: 3.32e-03, Avg Return: 0.485, Regret: 0.3759, Entropy: 0.0897 +[2026-03-20T18:02:32.328656Z] Loop 2715: Loss: 3.26e-03, Avg Return: 0.486, Regret: 0.3759, Entropy: 0.0856 +[2026-03-20T18:02:33.182396Z] Loop 2716: Loss: 2.84e-03, Avg Return: 0.481, Regret: 0.3759, Entropy: 0.0753 +[2026-03-20T18:02:34.036205Z] Loop 2717: Loss: 2.60e-03, Avg Return: 0.483, Regret: 0.3759, Entropy: 0.0724 +[2026-03-20T18:02:34.891012Z] Loop 2718: Loss: 2.56e-03, Avg Return: 0.494, Regret: 0.3759, Entropy: 0.0647 +[2026-03-20T18:02:35.745044Z] Loop 2719: Loss: 2.14e-03, Avg Return: 0.478, Regret: 0.3759, Entropy: 0.0630 +[2026-03-20T18:02:36.639659Z] Loop 2720: Loss: 2.73e-03, Avg Return: 0.491, Regret: 0.3790, Entropy: 0.0666 +[2026-03-20T18:02:37.493724Z] Loop 2721: Loss: 3.02e-03, Avg Return: 0.477, Regret: 0.3790, Entropy: 0.0734 +[2026-03-20T18:02:38.348838Z] Loop 2722: Loss: 2.85e-03, Avg Return: 0.487, Regret: 0.3790, Entropy: 0.0686 +[2026-03-20T18:02:39.202793Z] Loop 2723: Loss: 2.50e-03, Avg Return: 0.491, Regret: 0.3790, Entropy: 0.0660 +[2026-03-20T18:02:40.056878Z] Loop 2724: Loss: 2.58e-03, Avg Return: 0.476, Regret: 0.3790, Entropy: 0.0671 +[2026-03-20T18:02:40.909536Z] Loop 2725: Loss: 2.21e-03, Avg Return: 0.477, Regret: 0.3790, Entropy: 0.0626 +[2026-03-20T18:02:41.762367Z] Loop 2726: Loss: 1.91e-03, Avg Return: 0.480, Regret: 0.3790, Entropy: 0.0591 +[2026-03-20T18:02:42.616397Z] Loop 2727: Loss: 1.95e-03, Avg Return: 0.491, Regret: 0.3790, Entropy: 0.0592 +[2026-03-20T18:02:43.469705Z] Loop 2728: Loss: 2.01e-03, Avg Return: 0.482, Regret: 0.3790, Entropy: 0.0595 +[2026-03-20T18:02:44.322734Z] Loop 2729: Loss: 2.28e-03, Avg Return: 0.483, Regret: 0.3790, Entropy: 0.0630 +[2026-03-20T18:02:45.217868Z] Loop 2730: Loss: 2.31e-03, Avg Return: 0.489, Regret: 0.3770, Entropy: 0.0623 +[2026-03-20T18:02:46.072365Z] Loop 2731: Loss: 2.31e-03, Avg Return: 0.487, Regret: 0.3770, Entropy: 0.0670 +[2026-03-20T18:02:46.926185Z] Loop 2732: Loss: 1.97e-03, Avg Return: 0.485, Regret: 0.3770, Entropy: 0.0669 +[2026-03-20T18:02:47.779636Z] Loop 2733: Loss: 2.52e-03, Avg Return: 0.486, Regret: 0.3770, Entropy: 0.0654 +[2026-03-20T18:02:48.631959Z] Loop 2734: Loss: 2.03e-03, Avg Return: 0.480, Regret: 0.3770, Entropy: 0.0587 +[2026-03-20T18:02:49.484865Z] Loop 2735: Loss: 2.00e-03, Avg Return: 0.499, Regret: 0.3770, Entropy: 0.0567 +[2026-03-20T18:02:50.339099Z] Loop 2736: Loss: 1.81e-03, Avg Return: 0.489, Regret: 0.3770, Entropy: 0.0586 +[2026-03-20T18:02:51.193158Z] Loop 2737: Loss: 1.76e-03, Avg Return: 0.484, Regret: 0.3770, Entropy: 0.0581 +[2026-03-20T18:02:52.046905Z] Loop 2738: Loss: 1.71e-03, Avg Return: 0.484, Regret: 0.3770, Entropy: 0.0587 +[2026-03-20T18:02:52.901143Z] Loop 2739: Loss: 1.77e-03, Avg Return: 0.486, Regret: 0.3770, Entropy: 0.0584 +[2026-03-20T18:02:53.792343Z] Loop 2740: Loss: 1.60e-03, Avg Return: 0.481, Regret: 0.3757, Entropy: 0.0593 +[2026-03-20T18:02:54.646813Z] Loop 2741: Loss: 1.64e-03, Avg Return: 0.484, Regret: 0.3757, Entropy: 0.0592 +[2026-03-20T18:02:55.500444Z] Loop 2742: Loss: 1.69e-03, Avg Return: 0.483, Regret: 0.3757, Entropy: 0.0550 +[2026-03-20T18:02:56.353815Z] Loop 2743: Loss: 1.63e-03, Avg Return: 0.493, Regret: 0.3757, Entropy: 0.0583 +[2026-03-20T18:02:57.207442Z] Loop 2744: Loss: 2.08e-03, Avg Return: 0.495, Regret: 0.3757, Entropy: 0.0634 +[2026-03-20T18:02:58.061768Z] Loop 2745: Loss: 2.20e-03, Avg Return: 0.488, Regret: 0.3757, Entropy: 0.0675 +[2026-03-20T18:02:58.916083Z] Loop 2746: Loss: 2.37e-03, Avg Return: 0.492, Regret: 0.3757, Entropy: 0.0728 +[2026-03-20T18:02:59.770720Z] Loop 2747: Loss: 2.54e-03, Avg Return: 0.486, Regret: 0.3757, Entropy: 0.0717 +[2026-03-20T18:03:00.624514Z] Loop 2748: Loss: 2.99e-03, Avg Return: 0.490, Regret: 0.3757, Entropy: 0.0859 +[2026-03-20T18:03:01.478108Z] Loop 2749: Loss: 3.38e-03, Avg Return: 0.490, Regret: 0.3757, Entropy: 0.0882 +[2026-03-20T18:03:02.368992Z] Loop 2750: Loss: 3.31e-03, Avg Return: 0.499, Regret: 0.3753, Entropy: 0.0898 +[2026-03-20T18:03:03.223511Z] Loop 2751: Loss: 2.90e-03, Avg Return: 0.490, Regret: 0.3753, Entropy: 0.0888 +[2026-03-20T18:03:04.076946Z] Loop 2752: Loss: 2.99e-03, Avg Return: 0.488, Regret: 0.3753, Entropy: 0.0870 +[2026-03-20T18:03:04.928729Z] Loop 2753: Loss: 3.23e-03, Avg Return: 0.491, Regret: 0.3753, Entropy: 0.0914 +[2026-03-20T18:03:05.782233Z] Loop 2754: Loss: 3.02e-03, Avg Return: 0.497, Regret: 0.3753, Entropy: 0.0927 +[2026-03-20T18:03:06.635331Z] Loop 2755: Loss: 3.55e-03, Avg Return: 0.490, Regret: 0.3753, Entropy: 0.0897 +[2026-03-20T18:03:07.488414Z] Loop 2756: Loss: 3.10e-03, Avg Return: 0.495, Regret: 0.3753, Entropy: 0.0876 +[2026-03-20T18:03:08.341134Z] Loop 2757: Loss: 2.66e-03, Avg Return: 0.486, Regret: 0.3753, Entropy: 0.0870 +[2026-03-20T18:03:09.195457Z] Loop 2758: Loss: 2.58e-03, Avg Return: 0.492, Regret: 0.3753, Entropy: 0.0752 +[2026-03-20T18:03:10.049557Z] Loop 2759: Loss: 1.82e-03, Avg Return: 0.489, Regret: 0.3753, Entropy: 0.0629 +[2026-03-20T18:03:10.940525Z] Loop 2760: Loss: 1.58e-03, Avg Return: 0.488, Regret: 0.3755, Entropy: 0.0556 +[2026-03-20T18:03:11.793654Z] Loop 2761: Loss: 1.93e-03, Avg Return: 0.482, Regret: 0.3755, Entropy: 0.0593 +[2026-03-20T18:03:12.645610Z] Loop 2762: Loss: 3.23e-03, Avg Return: 0.485, Regret: 0.3755, Entropy: 0.0714 +[2026-03-20T18:03:13.499919Z] Loop 2763: Loss: 3.92e-03, Avg Return: 0.489, Regret: 0.3755, Entropy: 0.0790 +[2026-03-20T18:03:14.353014Z] Loop 2764: Loss: 3.33e-03, Avg Return: 0.484, Regret: 0.3755, Entropy: 0.0686 +[2026-03-20T18:03:15.206251Z] Loop 2765: Loss: 2.74e-03, Avg Return: 0.483, Regret: 0.3755, Entropy: 0.0614 +[2026-03-20T18:03:16.059119Z] Loop 2766: Loss: 2.28e-03, Avg Return: 0.486, Regret: 0.3755, Entropy: 0.0557 +[2026-03-20T18:03:16.913155Z] Loop 2767: Loss: 2.31e-03, Avg Return: 0.483, Regret: 0.3755, Entropy: 0.0519 +[2026-03-20T18:03:17.766369Z] Loop 2768: Loss: 2.36e-03, Avg Return: 0.489, Regret: 0.3755, Entropy: 0.0551 +[2026-03-20T18:03:18.620200Z] Loop 2769: Loss: 2.76e-03, Avg Return: 0.485, Regret: 0.3755, Entropy: 0.0618 +[2026-03-20T18:03:19.510155Z] Loop 2770: Loss: 2.75e-03, Avg Return: 0.479, Regret: 0.3772, Entropy: 0.0635 +[2026-03-20T18:03:20.363776Z] Loop 2771: Loss: 3.60e-03, Avg Return: 0.488, Regret: 0.3772, Entropy: 0.0751 +[2026-03-20T18:03:21.216802Z] Loop 2772: Loss: 3.70e-03, Avg Return: 0.489, Regret: 0.3772, Entropy: 0.0770 +[2026-03-20T18:03:22.069802Z] Loop 2773: Loss: 3.37e-03, Avg Return: 0.488, Regret: 0.3772, Entropy: 0.0785 +[2026-03-20T18:03:22.923755Z] Loop 2774: Loss: 2.72e-03, Avg Return: 0.483, Regret: 0.3772, Entropy: 0.0696 +[2026-03-20T18:03:23.777415Z] Loop 2775: Loss: 2.15e-03, Avg Return: 0.490, Regret: 0.3772, Entropy: 0.0640 +[2026-03-20T18:03:24.630881Z] Loop 2776: Loss: 1.66e-03, Avg Return: 0.491, Regret: 0.3772, Entropy: 0.0599 +[2026-03-20T18:03:25.483145Z] Loop 2777: Loss: 1.94e-03, Avg Return: 0.489, Regret: 0.3772, Entropy: 0.0648 +[2026-03-20T18:03:26.336583Z] Loop 2778: Loss: 2.29e-03, Avg Return: 0.490, Regret: 0.3772, Entropy: 0.0766 +[2026-03-20T18:03:27.190021Z] Loop 2779: Loss: 2.37e-03, Avg Return: 0.482, Regret: 0.3772, Entropy: 0.0853 +[2026-03-20T18:03:28.080235Z] Loop 2780: Loss: 2.38e-03, Avg Return: 0.487, Regret: 0.3752, Entropy: 0.0911 +[2026-03-20T18:03:28.933444Z] Loop 2781: Loss: 3.53e-03, Avg Return: 0.480, Regret: 0.3752, Entropy: 0.0999 +[2026-03-20T18:03:29.787536Z] Loop 2782: Loss: 4.42e-03, Avg Return: 0.497, Regret: 0.3752, Entropy: 0.1142 +[2026-03-20T18:03:30.641276Z] Loop 2783: Loss: 3.97e-03, Avg Return: 0.485, Regret: 0.3752, Entropy: 0.1091 +[2026-03-20T18:03:31.495064Z] Loop 2784: Loss: 3.03e-03, Avg Return: 0.485, Regret: 0.3752, Entropy: 0.0982 +[2026-03-20T18:03:32.349375Z] Loop 2785: Loss: 2.55e-03, Avg Return: 0.487, Regret: 0.3752, Entropy: 0.0904 +[2026-03-20T18:03:33.202024Z] Loop 2786: Loss: 2.00e-03, Avg Return: 0.490, Regret: 0.3752, Entropy: 0.0853 +[2026-03-20T18:03:34.055677Z] Loop 2787: Loss: 1.63e-03, Avg Return: 0.492, Regret: 0.3752, Entropy: 0.0783 +[2026-03-20T18:03:34.908464Z] Loop 2788: Loss: 1.54e-03, Avg Return: 0.494, Regret: 0.3752, Entropy: 0.0752 +[2026-03-20T18:03:35.760821Z] Loop 2789: Loss: 1.10e-03, Avg Return: 0.490, Regret: 0.3752, Entropy: 0.0693 +[2026-03-20T18:03:36.652749Z] Loop 2790: Loss: 1.22e-03, Avg Return: 0.483, Regret: 0.3753, Entropy: 0.0613 +[2026-03-20T18:03:37.505734Z] Loop 2791: Loss: 1.09e-03, Avg Return: 0.484, Regret: 0.3753, Entropy: 0.0630 +[2026-03-20T18:03:38.359158Z] Loop 2792: Loss: 1.44e-03, Avg Return: 0.486, Regret: 0.3753, Entropy: 0.0601 +[2026-03-20T18:03:39.212391Z] Loop 2793: Loss: 1.53e-03, Avg Return: 0.487, Regret: 0.3753, Entropy: 0.0665 +[2026-03-20T18:03:40.065271Z] Loop 2794: Loss: 1.28e-03, Avg Return: 0.483, Regret: 0.3753, Entropy: 0.0672 +[2026-03-20T18:03:40.917942Z] Loop 2795: Loss: 1.56e-03, Avg Return: 0.487, Regret: 0.3753, Entropy: 0.0690 +[2026-03-20T18:03:41.772804Z] Loop 2796: Loss: 1.90e-03, Avg Return: 0.496, Regret: 0.3753, Entropy: 0.0675 +[2026-03-20T18:03:42.625903Z] Loop 2797: Loss: 1.81e-03, Avg Return: 0.483, Regret: 0.3753, Entropy: 0.0738 +[2026-03-20T18:03:43.478558Z] Loop 2798: Loss: 1.67e-03, Avg Return: 0.500, Regret: 0.3753, Entropy: 0.0720 +[2026-03-20T18:03:44.332326Z] Loop 2799: Loss: 1.65e-03, Avg Return: 0.488, Regret: 0.3753, Entropy: 0.0736 +[2026-03-20T18:03:45.225389Z] Loop 2800: Loss: 1.45e-03, Avg Return: 0.490, Regret: 0.3772, Entropy: 0.0693 +[2026-03-20T18:03:46.080060Z] Loop 2801: Loss: 1.40e-03, Avg Return: 0.485, Regret: 0.3772, Entropy: 0.0697 +[2026-03-20T18:03:46.933383Z] Loop 2802: Loss: 1.56e-03, Avg Return: 0.486, Regret: 0.3772, Entropy: 0.0746 +[2026-03-20T18:03:47.786905Z] Loop 2803: Loss: 1.39e-03, Avg Return: 0.481, Regret: 0.3772, Entropy: 0.0761 +[2026-03-20T18:03:48.641527Z] Loop 2804: Loss: 1.67e-03, Avg Return: 0.484, Regret: 0.3772, Entropy: 0.0749 +[2026-03-20T18:03:49.494932Z] Loop 2805: Loss: 2.20e-03, Avg Return: 0.486, Regret: 0.3772, Entropy: 0.0882 +[2026-03-20T18:03:50.347777Z] Loop 2806: Loss: 2.42e-03, Avg Return: 0.485, Regret: 0.3772, Entropy: 0.0956 +[2026-03-20T18:03:51.201235Z] Loop 2807: Loss: 2.48e-03, Avg Return: 0.488, Regret: 0.3772, Entropy: 0.1002 +[2026-03-20T18:03:52.056199Z] Loop 2808: Loss: 2.22e-03, Avg Return: 0.484, Regret: 0.3772, Entropy: 0.1005 +[2026-03-20T18:03:52.909601Z] Loop 2809: Loss: 2.37e-03, Avg Return: 0.481, Regret: 0.3772, Entropy: 0.1027 +[2026-03-20T18:03:53.800564Z] Loop 2810: Loss: 2.36e-03, Avg Return: 0.484, Regret: 0.3805, Entropy: 0.0930 +[2026-03-20T18:03:54.654542Z] Loop 2811: Loss: 2.09e-03, Avg Return: 0.483, Regret: 0.3805, Entropy: 0.0922 +[2026-03-20T18:03:55.508724Z] Loop 2812: Loss: 1.87e-03, Avg Return: 0.486, Regret: 0.3805, Entropy: 0.0859 +[2026-03-20T18:03:56.361712Z] Loop 2813: Loss: 1.92e-03, Avg Return: 0.488, Regret: 0.3805, Entropy: 0.0901 +[2026-03-20T18:03:57.214233Z] Loop 2814: Loss: 1.94e-03, Avg Return: 0.482, Regret: 0.3805, Entropy: 0.0878 +[2026-03-20T18:03:58.066962Z] Loop 2815: Loss: 1.88e-03, Avg Return: 0.481, Regret: 0.3805, Entropy: 0.0918 +[2026-03-20T18:03:58.920933Z] Loop 2816: Loss: 2.21e-03, Avg Return: 0.489, Regret: 0.3805, Entropy: 0.0938 +[2026-03-20T18:03:59.774483Z] Loop 2817: Loss: 2.17e-03, Avg Return: 0.481, Regret: 0.3805, Entropy: 0.1053 +[2026-03-20T18:04:00.627145Z] Loop 2818: Loss: 2.32e-03, Avg Return: 0.495, Regret: 0.3805, Entropy: 0.0970 +[2026-03-20T18:04:01.479279Z] Loop 2819: Loss: 2.47e-03, Avg Return: 0.489, Regret: 0.3805, Entropy: 0.0995 +[2026-03-20T18:04:02.370931Z] Loop 2820: Loss: 2.31e-03, Avg Return: 0.496, Regret: 0.3772, Entropy: 0.1007 +[2026-03-20T18:04:03.224446Z] Loop 2821: Loss: 1.95e-03, Avg Return: 0.487, Regret: 0.3772, Entropy: 0.0926 +[2026-03-20T18:04:04.077491Z] Loop 2822: Loss: 1.64e-03, Avg Return: 0.490, Regret: 0.3772, Entropy: 0.0891 +[2026-03-20T18:04:04.930665Z] Loop 2823: Loss: 1.68e-03, Avg Return: 0.487, Regret: 0.3772, Entropy: 0.0806 +[2026-03-20T18:04:05.784278Z] Loop 2824: Loss: 1.24e-03, Avg Return: 0.483, Regret: 0.3772, Entropy: 0.0764 +[2026-03-20T18:04:06.638030Z] Loop 2825: Loss: 1.08e-03, Avg Return: 0.487, Regret: 0.3772, Entropy: 0.0642 +[2026-03-20T18:04:07.491369Z] Loop 2826: Loss: 9.79e-04, Avg Return: 0.482, Regret: 0.3772, Entropy: 0.0568 +[2026-03-20T18:04:08.344099Z] Loop 2827: Loss: 7.57e-04, Avg Return: 0.485, Regret: 0.3772, Entropy: 0.0565 +[2026-03-20T18:04:09.197191Z] Loop 2828: Loss: 8.11e-04, Avg Return: 0.483, Regret: 0.3772, Entropy: 0.0500 +[2026-03-20T18:04:10.050052Z] Loop 2829: Loss: 7.41e-04, Avg Return: 0.485, Regret: 0.3772, Entropy: 0.0520 +[2026-03-20T18:04:10.941174Z] Loop 2830: Loss: 7.14e-04, Avg Return: 0.477, Regret: 0.3775, Entropy: 0.0512 +[2026-03-20T18:04:11.795958Z] Loop 2831: Loss: 7.39e-04, Avg Return: 0.484, Regret: 0.3775, Entropy: 0.0452 +[2026-03-20T18:04:12.650558Z] Loop 2832: Loss: 1.03e-03, Avg Return: 0.487, Regret: 0.3775, Entropy: 0.0569 +[2026-03-20T18:04:13.505037Z] Loop 2833: Loss: 8.45e-04, Avg Return: 0.485, Regret: 0.3775, Entropy: 0.0564 +[2026-03-20T18:04:14.359270Z] Loop 2834: Loss: 1.21e-03, Avg Return: 0.492, Regret: 0.3775, Entropy: 0.0615 +[2026-03-20T18:04:15.212928Z] Loop 2835: Loss: 9.86e-04, Avg Return: 0.491, Regret: 0.3775, Entropy: 0.0664 +[2026-03-20T18:04:16.066235Z] Loop 2836: Loss: 1.22e-03, Avg Return: 0.484, Regret: 0.3775, Entropy: 0.0682 +[2026-03-20T18:04:16.919465Z] Loop 2837: Loss: 1.24e-03, Avg Return: 0.486, Regret: 0.3775, Entropy: 0.0717 +[2026-03-20T18:04:17.774212Z] Loop 2838: Loss: 1.62e-03, Avg Return: 0.488, Regret: 0.3775, Entropy: 0.0765 +[2026-03-20T18:04:18.628196Z] Loop 2839: Loss: 1.54e-03, Avg Return: 0.487, Regret: 0.3775, Entropy: 0.0827 +[2026-03-20T18:04:19.518856Z] Loop 2840: Loss: 2.07e-03, Avg Return: 0.488, Regret: 0.3757, Entropy: 0.0861 +[2026-03-20T18:04:20.371339Z] Loop 2841: Loss: 2.10e-03, Avg Return: 0.490, Regret: 0.3757, Entropy: 0.0911 +[2026-03-20T18:04:21.224174Z] Loop 2842: Loss: 2.41e-03, Avg Return: 0.498, Regret: 0.3757, Entropy: 0.0903 +[2026-03-20T18:04:22.079201Z] Loop 2843: Loss: 2.30e-03, Avg Return: 0.482, Regret: 0.3757, Entropy: 0.0952 +[2026-03-20T18:04:22.933127Z] Loop 2844: Loss: 2.92e-03, Avg Return: 0.492, Regret: 0.3757, Entropy: 0.0936 +[2026-03-20T18:04:23.785697Z] Loop 2845: Loss: 2.52e-03, Avg Return: 0.485, Regret: 0.3757, Entropy: 0.0930 +[2026-03-20T18:04:24.638763Z] Loop 2846: Loss: 1.92e-03, Avg Return: 0.488, Regret: 0.3757, Entropy: 0.0843 +[2026-03-20T18:04:25.491589Z] Loop 2847: Loss: 1.92e-03, Avg Return: 0.494, Regret: 0.3757, Entropy: 0.0827 +[2026-03-20T18:04:26.346081Z] Loop 2848: Loss: 1.86e-03, Avg Return: 0.483, Regret: 0.3757, Entropy: 0.0804 +[2026-03-20T18:04:27.199738Z] Loop 2849: Loss: 2.24e-03, Avg Return: 0.490, Regret: 0.3757, Entropy: 0.0791 +[2026-03-20T18:04:28.090314Z] Loop 2850: Loss: 1.89e-03, Avg Return: 0.491, Regret: 0.3750, Entropy: 0.0777 +[2026-03-20T18:04:28.944360Z] Loop 2851: Loss: 1.81e-03, Avg Return: 0.488, Regret: 0.3750, Entropy: 0.0730 +[2026-03-20T18:04:29.799875Z] Loop 2852: Loss: 1.64e-03, Avg Return: 0.490, Regret: 0.3750, Entropy: 0.0610 +[2026-03-20T18:04:30.654614Z] Loop 2853: Loss: 1.28e-03, Avg Return: 0.494, Regret: 0.3750, Entropy: 0.0576 +[2026-03-20T18:04:31.507373Z] Loop 2854: Loss: 1.13e-03, Avg Return: 0.494, Regret: 0.3750, Entropy: 0.0541 +[2026-03-20T18:04:32.360834Z] Loop 2855: Loss: 1.22e-03, Avg Return: 0.492, Regret: 0.3750, Entropy: 0.0601 +[2026-03-20T18:04:33.215179Z] Loop 2856: Loss: 1.12e-03, Avg Return: 0.486, Regret: 0.3750, Entropy: 0.0563 +[2026-03-20T18:04:34.068718Z] Loop 2857: Loss: 1.20e-03, Avg Return: 0.485, Regret: 0.3750, Entropy: 0.0643 +[2026-03-20T18:04:34.922552Z] Loop 2858: Loss: 1.21e-03, Avg Return: 0.489, Regret: 0.3750, Entropy: 0.0666 +[2026-03-20T18:04:35.774634Z] Loop 2859: Loss: 1.20e-03, Avg Return: 0.490, Regret: 0.3750, Entropy: 0.0698 +[2026-03-20T18:04:36.664999Z] Loop 2860: Loss: 1.19e-03, Avg Return: 0.492, Regret: 0.3750, Entropy: 0.0677 +[2026-03-20T18:04:37.519072Z] Loop 2861: Loss: 1.26e-03, Avg Return: 0.488, Regret: 0.3750, Entropy: 0.0616 +[2026-03-20T18:04:38.373536Z] Loop 2862: Loss: 1.18e-03, Avg Return: 0.488, Regret: 0.3750, Entropy: 0.0679 +[2026-03-20T18:04:39.228327Z] Loop 2863: Loss: 1.28e-03, Avg Return: 0.498, Regret: 0.3750, Entropy: 0.0636 +[2026-03-20T18:04:40.082804Z] Loop 2864: Loss: 1.33e-03, Avg Return: 0.492, Regret: 0.3750, Entropy: 0.0674 +[2026-03-20T18:04:40.937570Z] Loop 2865: Loss: 1.40e-03, Avg Return: 0.490, Regret: 0.3750, Entropy: 0.0706 +[2026-03-20T18:04:41.790902Z] Loop 2866: Loss: 1.29e-03, Avg Return: 0.486, Regret: 0.3750, Entropy: 0.0726 +[2026-03-20T18:04:42.643676Z] Loop 2867: Loss: 1.12e-03, Avg Return: 0.487, Regret: 0.3750, Entropy: 0.0772 +[2026-03-20T18:04:43.496465Z] Loop 2868: Loss: 1.32e-03, Avg Return: 0.489, Regret: 0.3750, Entropy: 0.0714 +[2026-03-20T18:04:44.349232Z] Loop 2869: Loss: 1.43e-03, Avg Return: 0.487, Regret: 0.3750, Entropy: 0.0673 +[2026-03-20T18:04:45.243741Z] Loop 2870: Loss: 1.33e-03, Avg Return: 0.495, Regret: 0.3750, Entropy: 0.0737 +[2026-03-20T18:04:46.097430Z] Loop 2871: Loss: 1.22e-03, Avg Return: 0.491, Regret: 0.3750, Entropy: 0.0656 +[2026-03-20T18:04:46.951920Z] Loop 2872: Loss: 1.03e-03, Avg Return: 0.478, Regret: 0.3750, Entropy: 0.0675 +[2026-03-20T18:04:47.806326Z] Loop 2873: Loss: 1.26e-03, Avg Return: 0.486, Regret: 0.3750, Entropy: 0.0773 +[2026-03-20T18:04:48.661081Z] Loop 2874: Loss: 9.10e-04, Avg Return: 0.480, Regret: 0.3750, Entropy: 0.0723 +[2026-03-20T18:04:49.515125Z] Loop 2875: Loss: 1.30e-03, Avg Return: 0.494, Regret: 0.3750, Entropy: 0.0743 +[2026-03-20T18:04:50.368787Z] Loop 2876: Loss: 1.37e-03, Avg Return: 0.490, Regret: 0.3750, Entropy: 0.0730 +[2026-03-20T18:04:51.221928Z] Loop 2877: Loss: 1.21e-03, Avg Return: 0.490, Regret: 0.3750, Entropy: 0.0743 +[2026-03-20T18:04:52.075421Z] Loop 2878: Loss: 1.21e-03, Avg Return: 0.496, Regret: 0.3750, Entropy: 0.0705 +[2026-03-20T18:04:52.928551Z] Loop 2879: Loss: 1.32e-03, Avg Return: 0.482, Regret: 0.3750, Entropy: 0.0775 +[2026-03-20T18:04:53.819707Z] Loop 2880: Loss: 1.29e-03, Avg Return: 0.490, Regret: 0.3750, Entropy: 0.0746 +[2026-03-20T18:04:54.673775Z] Loop 2881: Loss: 1.41e-03, Avg Return: 0.485, Regret: 0.3750, Entropy: 0.0840 +[2026-03-20T18:04:55.527266Z] Loop 2882: Loss: 1.33e-03, Avg Return: 0.494, Regret: 0.3750, Entropy: 0.0777 +[2026-03-20T18:04:56.380829Z] Loop 2883: Loss: 1.24e-03, Avg Return: 0.490, Regret: 0.3750, Entropy: 0.0728 +[2026-03-20T18:04:57.233872Z] Loop 2884: Loss: 1.26e-03, Avg Return: 0.492, Regret: 0.3750, Entropy: 0.0820 +[2026-03-20T18:04:58.088267Z] Loop 2885: Loss: 1.38e-03, Avg Return: 0.491, Regret: 0.3750, Entropy: 0.0755 +[2026-03-20T18:04:58.939939Z] Loop 2886: Loss: 1.33e-03, Avg Return: 0.495, Regret: 0.3750, Entropy: 0.0735 +[2026-03-20T18:04:59.792294Z] Loop 2887: Loss: 1.71e-03, Avg Return: 0.490, Regret: 0.3750, Entropy: 0.0778 +[2026-03-20T18:05:00.645884Z] Loop 2888: Loss: 1.32e-03, Avg Return: 0.491, Regret: 0.3750, Entropy: 0.0776 +[2026-03-20T18:05:01.499713Z] Loop 2889: Loss: 1.49e-03, Avg Return: 0.494, Regret: 0.3750, Entropy: 0.0754 +[2026-03-20T18:05:02.391541Z] Loop 2890: Loss: 1.43e-03, Avg Return: 0.486, Regret: 0.3750, Entropy: 0.0768 +[2026-03-20T18:05:03.244329Z] Loop 2891: Loss: 1.14e-03, Avg Return: 0.483, Regret: 0.3750, Entropy: 0.0788 +[2026-03-20T18:05:04.098817Z] Loop 2892: Loss: 1.48e-03, Avg Return: 0.492, Regret: 0.3750, Entropy: 0.0715 +[2026-03-20T18:05:04.952657Z] Loop 2893: Loss: 1.16e-03, Avg Return: 0.486, Regret: 0.3750, Entropy: 0.0699 +[2026-03-20T18:05:05.806546Z] Loop 2894: Loss: 1.36e-03, Avg Return: 0.487, Regret: 0.3750, Entropy: 0.0703 +[2026-03-20T18:05:06.659309Z] Loop 2895: Loss: 1.51e-03, Avg Return: 0.483, Regret: 0.3750, Entropy: 0.0724 +[2026-03-20T18:05:07.511914Z] Loop 2896: Loss: 2.00e-03, Avg Return: 0.492, Regret: 0.3750, Entropy: 0.0751 +[2026-03-20T18:05:08.366807Z] Loop 2897: Loss: 2.20e-03, Avg Return: 0.489, Regret: 0.3750, Entropy: 0.0793 +[2026-03-20T18:05:09.220046Z] Loop 2898: Loss: 2.19e-03, Avg Return: 0.488, Regret: 0.3750, Entropy: 0.0814 +[2026-03-20T18:05:10.072800Z] Loop 2899: Loss: 2.27e-03, Avg Return: 0.487, Regret: 0.3750, Entropy: 0.0825 +[2026-03-20T18:05:10.963353Z] Loop 2900: Loss: 1.93e-03, Avg Return: 0.486, Regret: 0.3751, Entropy: 0.0758 +[2026-03-20T18:05:11.817269Z] Loop 2901: Loss: 2.04e-03, Avg Return: 0.494, Regret: 0.3751, Entropy: 0.0802 +[2026-03-20T18:05:12.671230Z] Loop 2902: Loss: 1.56e-03, Avg Return: 0.487, Regret: 0.3751, Entropy: 0.0837 +[2026-03-20T18:05:13.524277Z] Loop 2903: Loss: 2.01e-03, Avg Return: 0.491, Regret: 0.3751, Entropy: 0.0751 +[2026-03-20T18:05:14.376499Z] Loop 2904: Loss: 1.62e-03, Avg Return: 0.477, Regret: 0.3751, Entropy: 0.0832 +[2026-03-20T18:05:15.229524Z] Loop 2905: Loss: 1.63e-03, Avg Return: 0.493, Regret: 0.3751, Entropy: 0.0833 +[2026-03-20T18:05:16.083251Z] Loop 2906: Loss: 2.04e-03, Avg Return: 0.490, Regret: 0.3751, Entropy: 0.0814 +[2026-03-20T18:05:16.937286Z] Loop 2907: Loss: 1.93e-03, Avg Return: 0.487, Regret: 0.3751, Entropy: 0.0864 +[2026-03-20T18:05:17.791011Z] Loop 2908: Loss: 1.85e-03, Avg Return: 0.489, Regret: 0.3751, Entropy: 0.0794 +[2026-03-20T18:05:18.645161Z] Loop 2909: Loss: 1.90e-03, Avg Return: 0.488, Regret: 0.3751, Entropy: 0.0835 +[2026-03-20T18:05:19.536979Z] Loop 2910: Loss: 1.81e-03, Avg Return: 0.490, Regret: 0.3752, Entropy: 0.0913 +[2026-03-20T18:05:20.389884Z] Loop 2911: Loss: 1.89e-03, Avg Return: 0.480, Regret: 0.3752, Entropy: 0.0886 +[2026-03-20T18:05:21.242874Z] Loop 2912: Loss: 1.95e-03, Avg Return: 0.482, Regret: 0.3752, Entropy: 0.0926 +[2026-03-20T18:05:22.095957Z] Loop 2913: Loss: 2.36e-03, Avg Return: 0.489, Regret: 0.3752, Entropy: 0.0954 +[2026-03-20T18:05:22.950200Z] Loop 2914: Loss: 2.43e-03, Avg Return: 0.489, Regret: 0.3752, Entropy: 0.0969 +[2026-03-20T18:05:23.804166Z] Loop 2915: Loss: 2.34e-03, Avg Return: 0.484, Regret: 0.3752, Entropy: 0.0985 +[2026-03-20T18:05:24.658433Z] Loop 2916: Loss: 2.71e-03, Avg Return: 0.494, Regret: 0.3752, Entropy: 0.1009 +[2026-03-20T18:05:25.511760Z] Loop 2917: Loss: 2.52e-03, Avg Return: 0.491, Regret: 0.3752, Entropy: 0.0938 +[2026-03-20T18:05:26.365277Z] Loop 2918: Loss: 2.48e-03, Avg Return: 0.484, Regret: 0.3752, Entropy: 0.0998 +[2026-03-20T18:05:27.219114Z] Loop 2919: Loss: 2.60e-03, Avg Return: 0.489, Regret: 0.3752, Entropy: 0.1060 +[2026-03-20T18:05:28.110933Z] Loop 2920: Loss: 2.73e-03, Avg Return: 0.490, Regret: 0.3756, Entropy: 0.1096 +[2026-03-20T18:05:28.964458Z] Loop 2921: Loss: 2.80e-03, Avg Return: 0.488, Regret: 0.3756, Entropy: 0.1132 +[2026-03-20T18:05:29.817804Z] Loop 2922: Loss: 2.64e-03, Avg Return: 0.491, Regret: 0.3756, Entropy: 0.1087 +[2026-03-20T18:05:30.670736Z] Loop 2923: Loss: 2.76e-03, Avg Return: 0.486, Regret: 0.3756, Entropy: 0.1011 +[2026-03-20T18:05:31.523603Z] Loop 2924: Loss: 2.29e-03, Avg Return: 0.488, Regret: 0.3756, Entropy: 0.0990 +[2026-03-20T18:05:32.377103Z] Loop 2925: Loss: 2.19e-03, Avg Return: 0.487, Regret: 0.3756, Entropy: 0.0956 +[2026-03-20T18:05:33.231055Z] Loop 2926: Loss: 1.98e-03, Avg Return: 0.485, Regret: 0.3756, Entropy: 0.0929 +[2026-03-20T18:05:34.084863Z] Loop 2927: Loss: 1.92e-03, Avg Return: 0.484, Regret: 0.3756, Entropy: 0.0998 +[2026-03-20T18:05:34.938052Z] Loop 2928: Loss: 2.08e-03, Avg Return: 0.480, Regret: 0.3756, Entropy: 0.1027 +[2026-03-20T18:05:35.790694Z] Loop 2929: Loss: 2.57e-03, Avg Return: 0.489, Regret: 0.3756, Entropy: 0.1068 +[2026-03-20T18:05:36.685626Z] Loop 2930: Loss: 2.90e-03, Avg Return: 0.494, Regret: 0.3759, Entropy: 0.1130 +[2026-03-20T18:05:37.539151Z] Loop 2931: Loss: 2.68e-03, Avg Return: 0.482, Regret: 0.3759, Entropy: 0.1088 +[2026-03-20T18:05:38.393789Z] Loop 2932: Loss: 2.80e-03, Avg Return: 0.481, Regret: 0.3759, Entropy: 0.1103 +[2026-03-20T18:05:39.247590Z] Loop 2933: Loss: 2.53e-03, Avg Return: 0.477, Regret: 0.3759, Entropy: 0.1158 +[2026-03-20T18:05:40.101960Z] Loop 2934: Loss: 2.85e-03, Avg Return: 0.492, Regret: 0.3759, Entropy: 0.1085 +[2026-03-20T18:05:40.956317Z] Loop 2935: Loss: 2.58e-03, Avg Return: 0.480, Regret: 0.3759, Entropy: 0.1022 +[2026-03-20T18:05:41.809930Z] Loop 2936: Loss: 2.40e-03, Avg Return: 0.487, Regret: 0.3759, Entropy: 0.1046 +[2026-03-20T18:05:42.662686Z] Loop 2937: Loss: 2.89e-03, Avg Return: 0.486, Regret: 0.3759, Entropy: 0.1086 +[2026-03-20T18:05:43.516717Z] Loop 2938: Loss: 2.80e-03, Avg Return: 0.482, Regret: 0.3759, Entropy: 0.1081 +[2026-03-20T18:05:44.370920Z] Loop 2939: Loss: 2.59e-03, Avg Return: 0.485, Regret: 0.3759, Entropy: 0.1035 +[2026-03-20T18:05:45.262253Z] Loop 2940: Loss: 2.71e-03, Avg Return: 0.487, Regret: 0.3752, Entropy: 0.1053 +[2026-03-20T18:05:46.115254Z] Loop 2941: Loss: 2.78e-03, Avg Return: 0.481, Regret: 0.3752, Entropy: 0.1134 +[2026-03-20T18:05:46.969881Z] Loop 2942: Loss: 3.17e-03, Avg Return: 0.487, Regret: 0.3752, Entropy: 0.1123 +[2026-03-20T18:05:47.823796Z] Loop 2943: Loss: 3.02e-03, Avg Return: 0.483, Regret: 0.3752, Entropy: 0.1224 +[2026-03-20T18:05:48.676927Z] Loop 2944: Loss: 3.06e-03, Avg Return: 0.489, Regret: 0.3752, Entropy: 0.1220 +[2026-03-20T18:05:49.531200Z] Loop 2945: Loss: 3.38e-03, Avg Return: 0.496, Regret: 0.3752, Entropy: 0.1236 +[2026-03-20T18:05:50.386497Z] Loop 2946: Loss: 3.17e-03, Avg Return: 0.488, Regret: 0.3752, Entropy: 0.1293 +[2026-03-20T18:05:51.239673Z] Loop 2947: Loss: 3.14e-03, Avg Return: 0.489, Regret: 0.3752, Entropy: 0.1241 +[2026-03-20T18:05:52.092556Z] Loop 2948: Loss: 3.06e-03, Avg Return: 0.491, Regret: 0.3752, Entropy: 0.1288 +[2026-03-20T18:05:52.945114Z] Loop 2949: Loss: 3.29e-03, Avg Return: 0.495, Regret: 0.3752, Entropy: 0.1342 +[2026-03-20T18:05:53.838614Z] Loop 2950: Loss: 3.07e-03, Avg Return: 0.487, Regret: 0.3753, Entropy: 0.1360 +[2026-03-20T18:05:54.692347Z] Loop 2951: Loss: 3.20e-03, Avg Return: 0.489, Regret: 0.3753, Entropy: 0.1280 +[2026-03-20T18:05:55.546215Z] Loop 2952: Loss: 3.10e-03, Avg Return: 0.493, Regret: 0.3753, Entropy: 0.1204 +[2026-03-20T18:05:56.399140Z] Loop 2953: Loss: 3.25e-03, Avg Return: 0.487, Regret: 0.3753, Entropy: 0.1232 +[2026-03-20T18:05:57.252565Z] Loop 2954: Loss: 3.00e-03, Avg Return: 0.491, Regret: 0.3753, Entropy: 0.1192 +[2026-03-20T18:05:58.105867Z] Loop 2955: Loss: 2.83e-03, Avg Return: 0.493, Regret: 0.3753, Entropy: 0.1125 +[2026-03-20T18:05:58.959042Z] Loop 2956: Loss: 2.99e-03, Avg Return: 0.498, Regret: 0.3753, Entropy: 0.1138 +[2026-03-20T18:05:59.812126Z] Loop 2957: Loss: 2.85e-03, Avg Return: 0.491, Regret: 0.3753, Entropy: 0.1168 +[2026-03-20T18:06:00.666388Z] Loop 2958: Loss: 2.74e-03, Avg Return: 0.484, Regret: 0.3753, Entropy: 0.1223 +[2026-03-20T18:06:01.519040Z] Loop 2959: Loss: 2.73e-03, Avg Return: 0.485, Regret: 0.3753, Entropy: 0.1091 +[2026-03-20T18:06:02.409661Z] Loop 2960: Loss: 2.92e-03, Avg Return: 0.493, Regret: 0.3749, Entropy: 0.1122 +[2026-03-20T18:06:03.263491Z] Loop 2961: Loss: 2.75e-03, Avg Return: 0.491, Regret: 0.3749, Entropy: 0.1094 +[2026-03-20T18:06:04.117790Z] Loop 2962: Loss: 2.73e-03, Avg Return: 0.485, Regret: 0.3749, Entropy: 0.1140 +[2026-03-20T18:06:04.970335Z] Loop 2963: Loss: 3.39e-03, Avg Return: 0.496, Regret: 0.3749, Entropy: 0.1177 +[2026-03-20T18:06:05.823413Z] Loop 2964: Loss: 3.23e-03, Avg Return: 0.491, Regret: 0.3749, Entropy: 0.1214 +[2026-03-20T18:06:06.676586Z] Loop 2965: Loss: 3.18e-03, Avg Return: 0.486, Regret: 0.3749, Entropy: 0.1238 +[2026-03-20T18:06:07.530822Z] Loop 2966: Loss: 3.19e-03, Avg Return: 0.488, Regret: 0.3749, Entropy: 0.1272 +[2026-03-20T18:06:08.382949Z] Loop 2967: Loss: 3.24e-03, Avg Return: 0.482, Regret: 0.3749, Entropy: 0.1261 +[2026-03-20T18:06:09.235251Z] Loop 2968: Loss: 3.24e-03, Avg Return: 0.484, Regret: 0.3749, Entropy: 0.1195 +[2026-03-20T18:06:10.088299Z] Loop 2969: Loss: 2.77e-03, Avg Return: 0.490, Regret: 0.3749, Entropy: 0.1231 +[2026-03-20T18:06:10.979899Z] Loop 2970: Loss: 3.27e-03, Avg Return: 0.482, Regret: 0.3749, Entropy: 0.1245 +[2026-03-20T18:06:11.833268Z] Loop 2971: Loss: 2.74e-03, Avg Return: 0.493, Regret: 0.3749, Entropy: 0.1283 +[2026-03-20T18:06:12.686761Z] Loop 2972: Loss: 3.35e-03, Avg Return: 0.489, Regret: 0.3749, Entropy: 0.1260 +[2026-03-20T18:06:13.539885Z] Loop 2973: Loss: 3.12e-03, Avg Return: 0.483, Regret: 0.3749, Entropy: 0.1300 +[2026-03-20T18:06:14.393340Z] Loop 2974: Loss: 2.98e-03, Avg Return: 0.494, Regret: 0.3749, Entropy: 0.1348 +[2026-03-20T18:06:15.246273Z] Loop 2975: Loss: 3.22e-03, Avg Return: 0.483, Regret: 0.3749, Entropy: 0.1243 +[2026-03-20T18:06:16.099329Z] Loop 2976: Loss: 3.40e-03, Avg Return: 0.489, Regret: 0.3749, Entropy: 0.1344 +[2026-03-20T18:06:16.951853Z] Loop 2977: Loss: 3.35e-03, Avg Return: 0.485, Regret: 0.3749, Entropy: 0.1337 +[2026-03-20T18:06:17.805192Z] Loop 2978: Loss: 3.14e-03, Avg Return: 0.492, Regret: 0.3749, Entropy: 0.1320 +[2026-03-20T18:06:18.658413Z] Loop 2979: Loss: 3.33e-03, Avg Return: 0.485, Regret: 0.3749, Entropy: 0.1332 +[2026-03-20T18:06:19.548885Z] Loop 2980: Loss: 3.29e-03, Avg Return: 0.496, Regret: 0.3751, Entropy: 0.1324 +[2026-03-20T18:06:20.402253Z] Loop 2981: Loss: 2.93e-03, Avg Return: 0.487, Regret: 0.3751, Entropy: 0.1269 +[2026-03-20T18:06:21.256664Z] Loop 2982: Loss: 2.55e-03, Avg Return: 0.488, Regret: 0.3751, Entropy: 0.1164 +[2026-03-20T18:06:22.110489Z] Loop 2983: Loss: 2.30e-03, Avg Return: 0.490, Regret: 0.3751, Entropy: 0.1053 +[2026-03-20T18:06:22.963175Z] Loop 2984: Loss: 1.70e-03, Avg Return: 0.489, Regret: 0.3751, Entropy: 0.1016 +[2026-03-20T18:06:23.815698Z] Loop 2985: Loss: 1.77e-03, Avg Return: 0.482, Regret: 0.3751, Entropy: 0.1058 +[2026-03-20T18:06:24.669395Z] Loop 2986: Loss: 1.95e-03, Avg Return: 0.491, Regret: 0.3751, Entropy: 0.1023 +[2026-03-20T18:06:25.522981Z] Loop 2987: Loss: 1.52e-03, Avg Return: 0.495, Regret: 0.3751, Entropy: 0.1021 +[2026-03-20T18:06:26.376749Z] Loop 2988: Loss: 1.85e-03, Avg Return: 0.486, Regret: 0.3751, Entropy: 0.1024 +[2026-03-20T18:06:27.229680Z] Loop 2989: Loss: 1.85e-03, Avg Return: 0.483, Regret: 0.3751, Entropy: 0.1098 +[2026-03-20T18:06:28.122876Z] Loop 2990: Loss: 2.47e-03, Avg Return: 0.487, Regret: 0.3745, Entropy: 0.1153 +[2026-03-20T18:06:28.976338Z] Loop 2991: Loss: 2.20e-03, Avg Return: 0.492, Regret: 0.3745, Entropy: 0.1175 +[2026-03-20T18:06:29.831681Z] Loop 2992: Loss: 2.59e-03, Avg Return: 0.486, Regret: 0.3745, Entropy: 0.1209 +[2026-03-20T18:06:30.684600Z] Loop 2993: Loss: 2.80e-03, Avg Return: 0.492, Regret: 0.3745, Entropy: 0.1293 +[2026-03-20T18:06:31.537500Z] Loop 2994: Loss: 2.72e-03, Avg Return: 0.490, Regret: 0.3745, Entropy: 0.1469 +[2026-03-20T18:06:32.391369Z] Loop 2995: Loss: 2.86e-03, Avg Return: 0.490, Regret: 0.3745, Entropy: 0.1401 +[2026-03-20T18:06:33.245985Z] Loop 2996: Loss: 3.39e-03, Avg Return: 0.489, Regret: 0.3745, Entropy: 0.1507 +[2026-03-20T18:06:34.099073Z] Loop 2997: Loss: 3.41e-03, Avg Return: 0.488, Regret: 0.3745, Entropy: 0.1739 +[2026-03-20T18:06:34.951572Z] Loop 2998: Loss: 3.90e-03, Avg Return: 0.488, Regret: 0.3745, Entropy: 0.1764 +[2026-03-20T18:06:35.804379Z] Loop 2999: Loss: 4.39e-03, Avg Return: 0.493, Regret: 0.3745, Entropy: 0.1877 +[2026-03-20T18:06:36.698971Z] Loop 3000: Loss: 4.47e-03, Avg Return: 0.497, Regret: 0.3726, Entropy: 0.1896 +[2026-03-20T18:06:37.552698Z] Loop 3001: Loss: 4.52e-03, Avg Return: 0.482, Regret: 0.3726, Entropy: 0.2132 +[2026-03-20T18:06:38.407091Z] Loop 3002: Loss: 4.99e-03, Avg Return: 0.493, Regret: 0.3726, Entropy: 0.2297 +[2026-03-20T18:06:39.259923Z] Loop 3003: Loss: 5.98e-03, Avg Return: 0.496, Regret: 0.3726, Entropy: 0.2366 +[2026-03-20T18:06:40.112907Z] Loop 3004: Loss: 6.01e-03, Avg Return: 0.491, Regret: 0.3726, Entropy: 0.2490 +[2026-03-20T18:06:40.966128Z] Loop 3005: Loss: 6.52e-03, Avg Return: 0.503, Regret: 0.3726, Entropy: 0.2666 +[2026-03-20T18:06:41.819497Z] Loop 3006: Loss: 6.94e-03, Avg Return: 0.495, Regret: 0.3726, Entropy: 0.2853 +[2026-03-20T18:06:42.672245Z] Loop 3007: Loss: 7.40e-03, Avg Return: 0.497, Regret: 0.3726, Entropy: 0.2924 +[2026-03-20T18:06:43.525557Z] Loop 3008: Loss: 7.74e-03, Avg Return: 0.498, Regret: 0.3726, Entropy: 0.3168 +[2026-03-20T18:06:44.378084Z] Loop 3009: Loss: 8.53e-03, Avg Return: 0.501, Regret: 0.3726, Entropy: 0.3357 +[2026-03-20T18:06:45.272354Z] Loop 3010: Loss: 9.24e-03, Avg Return: 0.495, Regret: 0.3670, Entropy: 0.3564 +[2026-03-20T18:06:46.126548Z] Loop 3011: Loss: 1.05e-02, Avg Return: 0.496, Regret: 0.3670, Entropy: 0.3774 +[2026-03-20T18:06:46.981310Z] Loop 3012: Loss: 1.16e-02, Avg Return: 0.498, Regret: 0.3670, Entropy: 0.3966 +[2026-03-20T18:06:47.835604Z] Loop 3013: Loss: 1.40e-02, Avg Return: 0.498, Regret: 0.3670, Entropy: 0.4255 +[2026-03-20T18:06:48.689325Z] Loop 3014: Loss: 1.40e-02, Avg Return: 0.503, Regret: 0.3670, Entropy: 0.4491 +[2026-03-20T18:06:49.542864Z] Loop 3015: Loss: 1.57e-02, Avg Return: 0.494, Regret: 0.3670, Entropy: 0.4613 +[2026-03-20T18:06:50.395724Z] Loop 3016: Loss: 1.67e-02, Avg Return: 0.499, Regret: 0.3670, Entropy: 0.4814 +[2026-03-20T18:06:51.248158Z] Loop 3017: Loss: 1.74e-02, Avg Return: 0.502, Regret: 0.3670, Entropy: 0.4859 +[2026-03-20T18:06:52.101050Z] Loop 3018: Loss: 1.76e-02, Avg Return: 0.495, Regret: 0.3670, Entropy: 0.4860 +[2026-03-20T18:06:52.954961Z] Loop 3019: Loss: 1.77e-02, Avg Return: 0.499, Regret: 0.3670, Entropy: 0.4692 +[2026-03-20T18:06:53.851040Z] Loop 3020: Loss: 1.53e-02, Avg Return: 0.498, Regret: 0.3636, Entropy: 0.4684 +[2026-03-20T18:06:54.705433Z] Loop 3021: Loss: 1.66e-02, Avg Return: 0.506, Regret: 0.3636, Entropy: 0.4655 +[2026-03-20T18:06:55.559071Z] Loop 3022: Loss: 1.63e-02, Avg Return: 0.501, Regret: 0.3636, Entropy: 0.4499 +[2026-03-20T18:06:56.412408Z] Loop 3023: Loss: 1.59e-02, Avg Return: 0.494, Regret: 0.3636, Entropy: 0.4530 +[2026-03-20T18:06:57.265448Z] Loop 3024: Loss: 1.65e-02, Avg Return: 0.505, Regret: 0.3636, Entropy: 0.4499 +[2026-03-20T18:06:58.118909Z] Loop 3025: Loss: 1.70e-02, Avg Return: 0.506, Regret: 0.3636, Entropy: 0.4472 +[2026-03-20T18:06:58.971139Z] Loop 3026: Loss: 1.70e-02, Avg Return: 0.507, Regret: 0.3636, Entropy: 0.4441 +[2026-03-20T18:06:59.823776Z] Loop 3027: Loss: 1.59e-02, Avg Return: 0.503, Regret: 0.3636, Entropy: 0.4504 +[2026-03-20T18:07:00.676999Z] Loop 3028: Loss: 1.56e-02, Avg Return: 0.505, Regret: 0.3636, Entropy: 0.4441 +[2026-03-20T18:07:01.530645Z] Loop 3029: Loss: 1.57e-02, Avg Return: 0.504, Regret: 0.3636, Entropy: 0.4493 +[2026-03-20T18:07:02.425162Z] Loop 3030: Loss: 1.55e-02, Avg Return: 0.506, Regret: 0.3597, Entropy: 0.4560 +[2026-03-20T18:07:03.280467Z] Loop 3031: Loss: 1.85e-02, Avg Return: 0.501, Regret: 0.3597, Entropy: 0.4612 +[2026-03-20T18:07:04.140053Z] Loop 3032: Loss: 1.77e-02, Avg Return: 0.497, Regret: 0.3597, Entropy: 0.4659 +[2026-03-20T18:07:05.000538Z] Loop 3033: Loss: 1.82e-02, Avg Return: 0.504, Regret: 0.3597, Entropy: 0.4736 +[2026-03-20T18:07:05.853985Z] Loop 3034: Loss: 2.01e-02, Avg Return: 0.505, Regret: 0.3597, Entropy: 0.4796 +[2026-03-20T18:07:06.707049Z] Loop 3035: Loss: 1.91e-02, Avg Return: 0.505, Regret: 0.3597, Entropy: 0.4788 +[2026-03-20T18:07:07.560297Z] Loop 3036: Loss: 1.91e-02, Avg Return: 0.507, Regret: 0.3597, Entropy: 0.4843 +[2026-03-20T18:07:08.413729Z] Loop 3037: Loss: 1.90e-02, Avg Return: 0.507, Regret: 0.3597, Entropy: 0.4717 +[2026-03-20T18:07:09.266416Z] Loop 3038: Loss: 1.90e-02, Avg Return: 0.510, Regret: 0.3597, Entropy: 0.4795 +[2026-03-20T18:07:10.119181Z] Loop 3039: Loss: 1.89e-02, Avg Return: 0.511, Regret: 0.3597, Entropy: 0.4632 +[2026-03-20T18:07:11.015366Z] Loop 3040: Loss: 1.84e-02, Avg Return: 0.502, Regret: 0.3573, Entropy: 0.4593 +[2026-03-20T18:07:11.868803Z] Loop 3041: Loss: 1.83e-02, Avg Return: 0.510, Regret: 0.3573, Entropy: 0.4551 +[2026-03-20T18:07:12.722272Z] Loop 3042: Loss: 1.92e-02, Avg Return: 0.506, Regret: 0.3573, Entropy: 0.4676 +[2026-03-20T18:07:13.576224Z] Loop 3043: Loss: 1.91e-02, Avg Return: 0.504, Regret: 0.3573, Entropy: 0.4653 +[2026-03-20T18:07:14.429443Z] Loop 3044: Loss: 1.88e-02, Avg Return: 0.507, Regret: 0.3573, Entropy: 0.4542 +[2026-03-20T18:07:15.282644Z] Loop 3045: Loss: 1.88e-02, Avg Return: 0.507, Regret: 0.3573, Entropy: 0.4605 +[2026-03-20T18:07:16.136496Z] Loop 3046: Loss: 2.00e-02, Avg Return: 0.506, Regret: 0.3573, Entropy: 0.4617 +[2026-03-20T18:07:16.989638Z] Loop 3047: Loss: 1.87e-02, Avg Return: 0.497, Regret: 0.3573, Entropy: 0.4540 +[2026-03-20T18:07:17.842649Z] Loop 3048: Loss: 1.96e-02, Avg Return: 0.510, Regret: 0.3573, Entropy: 0.4647 +[2026-03-20T18:07:18.696716Z] Loop 3049: Loss: 1.95e-02, Avg Return: 0.505, Regret: 0.3573, Entropy: 0.4624 +[2026-03-20T18:07:19.592420Z] Loop 3050: Loss: 1.83e-02, Avg Return: 0.509, Regret: 0.3556, Entropy: 0.4484 +[2026-03-20T18:07:20.445716Z] Loop 3051: Loss: 1.72e-02, Avg Return: 0.508, Regret: 0.3556, Entropy: 0.4445 +[2026-03-20T18:07:21.299923Z] Loop 3052: Loss: 1.64e-02, Avg Return: 0.497, Regret: 0.3556, Entropy: 0.4245 +[2026-03-20T18:07:22.152919Z] Loop 3053: Loss: 1.88e-02, Avg Return: 0.511, Regret: 0.3556, Entropy: 0.4214 +[2026-03-20T18:07:23.007331Z] Loop 3054: Loss: 1.74e-02, Avg Return: 0.509, Regret: 0.3556, Entropy: 0.4232 +[2026-03-20T18:07:23.861125Z] Loop 3055: Loss: 1.88e-02, Avg Return: 0.508, Regret: 0.3556, Entropy: 0.4172 +[2026-03-20T18:07:24.714354Z] Loop 3056: Loss: 1.72e-02, Avg Return: 0.510, Regret: 0.3556, Entropy: 0.4124 +[2026-03-20T18:07:25.567590Z] Loop 3057: Loss: 1.81e-02, Avg Return: 0.504, Regret: 0.3556, Entropy: 0.4209 +[2026-03-20T18:07:26.420027Z] Loop 3058: Loss: 1.98e-02, Avg Return: 0.509, Regret: 0.3556, Entropy: 0.4103 +[2026-03-20T18:07:27.274749Z] Loop 3059: Loss: 1.83e-02, Avg Return: 0.507, Regret: 0.3556, Entropy: 0.4124 +[2026-03-20T18:07:28.171907Z] Loop 3060: Loss: 1.70e-02, Avg Return: 0.507, Regret: 0.3545, Entropy: 0.3995 +[2026-03-20T18:07:29.034711Z] Loop 3061: Loss: 1.69e-02, Avg Return: 0.511, Regret: 0.3545, Entropy: 0.3971 +[2026-03-20T18:07:29.886977Z] Loop 3062: Loss: 1.64e-02, Avg Return: 0.512, Regret: 0.3545, Entropy: 0.3892 +[2026-03-20T18:07:30.739391Z] Loop 3063: Loss: 1.54e-02, Avg Return: 0.508, Regret: 0.3545, Entropy: 0.3889 +[2026-03-20T18:07:31.593957Z] Loop 3064: Loss: 1.57e-02, Avg Return: 0.515, Regret: 0.3545, Entropy: 0.3784 +[2026-03-20T18:07:32.448699Z] Loop 3065: Loss: 1.65e-02, Avg Return: 0.506, Regret: 0.3545, Entropy: 0.3863 +[2026-03-20T18:07:33.302339Z] Loop 3066: Loss: 1.73e-02, Avg Return: 0.504, Regret: 0.3545, Entropy: 0.4115 +[2026-03-20T18:07:34.155187Z] Loop 3067: Loss: 1.88e-02, Avg Return: 0.501, Regret: 0.3545, Entropy: 0.4395 +[2026-03-20T18:07:35.009154Z] Loop 3068: Loss: 1.83e-02, Avg Return: 0.500, Regret: 0.3545, Entropy: 0.4384 +[2026-03-20T18:07:35.863731Z] Loop 3069: Loss: 1.68e-02, Avg Return: 0.510, Regret: 0.3545, Entropy: 0.4190 +[2026-03-20T18:07:36.759958Z] Loop 3070: Loss: 1.69e-02, Avg Return: 0.508, Regret: 0.3493, Entropy: 0.4049 +[2026-03-20T18:07:37.612654Z] Loop 3071: Loss: 1.74e-02, Avg Return: 0.516, Regret: 0.3493, Entropy: 0.4132 +[2026-03-20T18:07:38.466045Z] Loop 3072: Loss: 1.60e-02, Avg Return: 0.514, Regret: 0.3493, Entropy: 0.4250 +[2026-03-20T18:07:39.319450Z] Loop 3073: Loss: 1.87e-02, Avg Return: 0.513, Regret: 0.3493, Entropy: 0.4325 +[2026-03-20T18:07:40.173083Z] Loop 3074: Loss: 1.87e-02, Avg Return: 0.509, Regret: 0.3493, Entropy: 0.4362 +[2026-03-20T18:07:41.026614Z] Loop 3075: Loss: 1.86e-02, Avg Return: 0.518, Regret: 0.3493, Entropy: 0.4387 +[2026-03-20T18:07:41.880648Z] Loop 3076: Loss: 2.07e-02, Avg Return: 0.521, Regret: 0.3493, Entropy: 0.4395 +[2026-03-20T18:07:42.733819Z] Loop 3077: Loss: 1.90e-02, Avg Return: 0.514, Regret: 0.3493, Entropy: 0.4409 +[2026-03-20T18:07:43.587467Z] Loop 3078: Loss: 1.87e-02, Avg Return: 0.518, Regret: 0.3493, Entropy: 0.4447 +[2026-03-20T18:07:44.442381Z] Loop 3079: Loss: 1.98e-02, Avg Return: 0.512, Regret: 0.3493, Entropy: 0.4465 +[2026-03-20T18:07:45.339818Z] Loop 3080: Loss: 2.00e-02, Avg Return: 0.515, Regret: 0.3492, Entropy: 0.4494 +[2026-03-20T18:07:46.192371Z] Loop 3081: Loss: 1.88e-02, Avg Return: 0.513, Regret: 0.3492, Entropy: 0.4319 +[2026-03-20T18:07:47.045783Z] Loop 3082: Loss: 1.89e-02, Avg Return: 0.511, Regret: 0.3492, Entropy: 0.4396 +[2026-03-20T18:07:47.900230Z] Loop 3083: Loss: 1.72e-02, Avg Return: 0.512, Regret: 0.3492, Entropy: 0.4339 +[2026-03-20T18:07:48.754776Z] Loop 3084: Loss: 1.60e-02, Avg Return: 0.518, Regret: 0.3492, Entropy: 0.4261 +[2026-03-20T18:07:49.606476Z] Loop 3085: Loss: 1.73e-02, Avg Return: 0.511, Regret: 0.3492, Entropy: 0.4203 +[2026-03-20T18:07:50.458926Z] Loop 3086: Loss: 1.79e-02, Avg Return: 0.516, Regret: 0.3492, Entropy: 0.4263 +[2026-03-20T18:07:51.312821Z] Loop 3087: Loss: 1.84e-02, Avg Return: 0.523, Regret: 0.3492, Entropy: 0.4218 +[2026-03-20T18:07:52.167021Z] Loop 3088: Loss: 1.74e-02, Avg Return: 0.516, Regret: 0.3492, Entropy: 0.4230 +[2026-03-20T18:07:53.019871Z] Loop 3089: Loss: 1.75e-02, Avg Return: 0.519, Regret: 0.3492, Entropy: 0.4185 +[2026-03-20T18:07:53.912642Z] Loop 3090: Loss: 1.59e-02, Avg Return: 0.519, Regret: 0.3437, Entropy: 0.3962 +[2026-03-20T18:07:54.767203Z] Loop 3091: Loss: 1.51e-02, Avg Return: 0.520, Regret: 0.3437, Entropy: 0.3790 +[2026-03-20T18:07:55.620904Z] Loop 3092: Loss: 1.37e-02, Avg Return: 0.516, Regret: 0.3437, Entropy: 0.3641 +[2026-03-20T18:07:56.473561Z] Loop 3093: Loss: 1.38e-02, Avg Return: 0.512, Regret: 0.3437, Entropy: 0.3683 +[2026-03-20T18:07:57.325834Z] Loop 3094: Loss: 1.32e-02, Avg Return: 0.514, Regret: 0.3437, Entropy: 0.3739 +[2026-03-20T18:07:58.179558Z] Loop 3095: Loss: 1.49e-02, Avg Return: 0.521, Regret: 0.3437, Entropy: 0.3707 +[2026-03-20T18:07:59.033372Z] Loop 3096: Loss: 1.51e-02, Avg Return: 0.518, Regret: 0.3437, Entropy: 0.3879 +[2026-03-20T18:07:59.886168Z] Loop 3097: Loss: 1.71e-02, Avg Return: 0.530, Regret: 0.3437, Entropy: 0.3810 +[2026-03-20T18:08:00.737836Z] Loop 3098: Loss: 1.67e-02, Avg Return: 0.525, Regret: 0.3437, Entropy: 0.3877 +[2026-03-20T18:08:01.590385Z] Loop 3099: Loss: 1.82e-02, Avg Return: 0.524, Regret: 0.3437, Entropy: 0.3955 +[2026-03-20T18:08:02.486012Z] Loop 3100: Loss: 1.80e-02, Avg Return: 0.523, Regret: 0.3377, Entropy: 0.3996 +[2026-03-20T18:08:03.339169Z] Loop 3101: Loss: 1.82e-02, Avg Return: 0.528, Regret: 0.3377, Entropy: 0.3958 +[2026-03-20T18:08:04.192192Z] Loop 3102: Loss: 1.81e-02, Avg Return: 0.529, Regret: 0.3377, Entropy: 0.3905 +[2026-03-20T18:08:05.045494Z] Loop 3103: Loss: 1.75e-02, Avg Return: 0.522, Regret: 0.3377, Entropy: 0.3887 +[2026-03-20T18:08:05.898670Z] Loop 3104: Loss: 1.69e-02, Avg Return: 0.521, Regret: 0.3377, Entropy: 0.3875 +[2026-03-20T18:08:06.752304Z] Loop 3105: Loss: 1.73e-02, Avg Return: 0.533, Regret: 0.3377, Entropy: 0.3780 +[2026-03-20T18:08:07.605263Z] Loop 3106: Loss: 1.72e-02, Avg Return: 0.529, Regret: 0.3377, Entropy: 0.3766 +[2026-03-20T18:08:08.458451Z] Loop 3107: Loss: 1.63e-02, Avg Return: 0.525, Regret: 0.3377, Entropy: 0.3865 +[2026-03-20T18:08:09.310383Z] Loop 3108: Loss: 1.76e-02, Avg Return: 0.525, Regret: 0.3377, Entropy: 0.4006 +[2026-03-20T18:08:10.163177Z] Loop 3109: Loss: 1.68e-02, Avg Return: 0.531, Regret: 0.3377, Entropy: 0.3998 +[2026-03-20T18:08:11.058331Z] Loop 3110: Loss: 1.94e-02, Avg Return: 0.526, Regret: 0.3336, Entropy: 0.4226 +[2026-03-20T18:08:11.911849Z] Loop 3111: Loss: 1.84e-02, Avg Return: 0.531, Regret: 0.3336, Entropy: 0.4424 +[2026-03-20T18:08:12.764801Z] Loop 3112: Loss: 2.12e-02, Avg Return: 0.530, Regret: 0.3336, Entropy: 0.4452 +[2026-03-20T18:08:13.618668Z] Loop 3113: Loss: 2.07e-02, Avg Return: 0.534, Regret: 0.3336, Entropy: 0.4457 +[2026-03-20T18:08:14.472484Z] Loop 3114: Loss: 2.24e-02, Avg Return: 0.537, Regret: 0.3336, Entropy: 0.4574 +[2026-03-20T18:08:15.326401Z] Loop 3115: Loss: 2.24e-02, Avg Return: 0.536, Regret: 0.3336, Entropy: 0.4480 +[2026-03-20T18:08:16.179937Z] Loop 3116: Loss: 2.27e-02, Avg Return: 0.548, Regret: 0.3336, Entropy: 0.4475 +[2026-03-20T18:08:17.033620Z] Loop 3117: Loss: 2.38e-02, Avg Return: 0.547, Regret: 0.3336, Entropy: 0.4485 +[2026-03-20T18:08:17.887987Z] Loop 3118: Loss: 2.25e-02, Avg Return: 0.551, Regret: 0.3336, Entropy: 0.4526 +[2026-03-20T18:08:18.742876Z] Loop 3119: Loss: 2.65e-02, Avg Return: 0.550, Regret: 0.3336, Entropy: 0.4676 +[2026-03-20T18:08:19.639871Z] Loop 3120: Loss: 2.53e-02, Avg Return: 0.556, Regret: 0.3035, Entropy: 0.4795 +[2026-03-20T18:08:20.493346Z] Loop 3121: Loss: 2.83e-02, Avg Return: 0.556, Regret: 0.3035, Entropy: 0.5055 +[2026-03-20T18:08:21.346616Z] Loop 3122: Loss: 2.71e-02, Avg Return: 0.562, Regret: 0.3035, Entropy: 0.5006 +[2026-03-20T18:08:22.201687Z] Loop 3123: Loss: 3.07e-02, Avg Return: 0.563, Regret: 0.3035, Entropy: 0.5164 +[2026-03-20T18:08:23.055823Z] Loop 3124: Loss: 3.12e-02, Avg Return: 0.572, Regret: 0.3035, Entropy: 0.5306 +[2026-03-20T18:08:23.909871Z] Loop 3125: Loss: 3.20e-02, Avg Return: 0.577, Regret: 0.3035, Entropy: 0.5235 +[2026-03-20T18:08:24.763134Z] Loop 3126: Loss: 3.03e-02, Avg Return: 0.577, Regret: 0.3035, Entropy: 0.5257 +[2026-03-20T18:08:25.618269Z] Loop 3127: Loss: 3.37e-02, Avg Return: 0.578, Regret: 0.3035, Entropy: 0.5275 +[2026-03-20T18:08:26.472469Z] Loop 3128: Loss: 3.52e-02, Avg Return: 0.585, Regret: 0.3035, Entropy: 0.5298 +[2026-03-20T18:08:27.325320Z] Loop 3129: Loss: 3.70e-02, Avg Return: 0.590, Regret: 0.3035, Entropy: 0.5416 +[2026-03-20T18:08:28.218580Z] Loop 3130: Loss: 3.53e-02, Avg Return: 0.582, Regret: 0.2744, Entropy: 0.5301 +[2026-03-20T18:08:29.071057Z] Loop 3131: Loss: 3.64e-02, Avg Return: 0.581, Regret: 0.2744, Entropy: 0.5233 +[2026-03-20T18:08:29.924599Z] Loop 3132: Loss: 3.77e-02, Avg Return: 0.594, Regret: 0.2744, Entropy: 0.5380 +[2026-03-20T18:08:30.777495Z] Loop 3133: Loss: 3.86e-02, Avg Return: 0.593, Regret: 0.2744, Entropy: 0.5634 +[2026-03-20T18:08:31.631535Z] Loop 3134: Loss: 4.19e-02, Avg Return: 0.590, Regret: 0.2744, Entropy: 0.5893 +[2026-03-20T18:08:32.486508Z] Loop 3135: Loss: 4.56e-02, Avg Return: 0.598, Regret: 0.2744, Entropy: 0.6044 +[2026-03-20T18:08:33.340233Z] Loop 3136: Loss: 3.94e-02, Avg Return: 0.595, Regret: 0.2744, Entropy: 0.6087 +[2026-03-20T18:08:34.193311Z] Loop 3137: Loss: 4.42e-02, Avg Return: 0.602, Regret: 0.2744, Entropy: 0.5973 +[2026-03-20T18:08:35.046737Z] Loop 3138: Loss: 4.54e-02, Avg Return: 0.609, Regret: 0.2744, Entropy: 0.5847 +[2026-03-20T18:08:35.899295Z] Loop 3139: Loss: 4.35e-02, Avg Return: 0.611, Regret: 0.2744, Entropy: 0.5865 +[2026-03-20T18:08:36.798013Z] Loop 3140: Loss: 4.10e-02, Avg Return: 0.607, Regret: 0.2499, Entropy: 0.5740 +[2026-03-20T18:08:37.650541Z] Loop 3141: Loss: 4.26e-02, Avg Return: 0.618, Regret: 0.2499, Entropy: 0.5646 +[2026-03-20T18:08:38.504010Z] Loop 3142: Loss: 4.23e-02, Avg Return: 0.609, Regret: 0.2499, Entropy: 0.5808 +[2026-03-20T18:08:39.358034Z] Loop 3143: Loss: 4.98e-02, Avg Return: 0.618, Regret: 0.2499, Entropy: 0.5852 +[2026-03-20T18:08:40.211227Z] Loop 3144: Loss: 4.75e-02, Avg Return: 0.614, Regret: 0.2499, Entropy: 0.6040 +[2026-03-20T18:08:41.065387Z] Loop 3145: Loss: 5.09e-02, Avg Return: 0.615, Regret: 0.2499, Entropy: 0.6109 +[2026-03-20T18:08:41.919734Z] Loop 3146: Loss: 4.63e-02, Avg Return: 0.618, Regret: 0.2499, Entropy: 0.5836 +[2026-03-20T18:08:42.774140Z] Loop 3147: Loss: 4.54e-02, Avg Return: 0.621, Regret: 0.2499, Entropy: 0.5684 +[2026-03-20T18:08:43.627732Z] Loop 3148: Loss: 4.43e-02, Avg Return: 0.622, Regret: 0.2499, Entropy: 0.5752 +[2026-03-20T18:08:44.481246Z] Loop 3149: Loss: 4.01e-02, Avg Return: 0.617, Regret: 0.2499, Entropy: 0.5806 +[2026-03-20T18:08:45.380876Z] Loop 3150: Loss: 4.54e-02, Avg Return: 0.624, Regret: 0.2377, Entropy: 0.5883 +[2026-03-20T18:08:46.234714Z] Loop 3151: Loss: 4.53e-02, Avg Return: 0.627, Regret: 0.2377, Entropy: 0.6075 +[2026-03-20T18:08:47.086821Z] Loop 3152: Loss: 4.75e-02, Avg Return: 0.630, Regret: 0.2377, Entropy: 0.6192 +[2026-03-20T18:08:47.939722Z] Loop 3153: Loss: 5.23e-02, Avg Return: 0.630, Regret: 0.2377, Entropy: 0.6198 +[2026-03-20T18:08:48.793088Z] Loop 3154: Loss: 5.06e-02, Avg Return: 0.632, Regret: 0.2377, Entropy: 0.5980 +[2026-03-20T18:08:49.645741Z] Loop 3155: Loss: 5.25e-02, Avg Return: 0.634, Regret: 0.2377, Entropy: 0.5864 +[2026-03-20T18:08:50.499393Z] Loop 3156: Loss: 5.15e-02, Avg Return: 0.631, Regret: 0.2377, Entropy: 0.5610 +[2026-03-20T18:08:51.351719Z] Loop 3157: Loss: 5.06e-02, Avg Return: 0.636, Regret: 0.2377, Entropy: 0.5481 +[2026-03-20T18:08:52.204782Z] Loop 3158: Loss: 5.15e-02, Avg Return: 0.632, Regret: 0.2377, Entropy: 0.5478 +[2026-03-20T18:08:53.058172Z] Loop 3159: Loss: 5.47e-02, Avg Return: 0.646, Regret: 0.2377, Entropy: 0.5597 +[2026-03-20T18:08:53.953766Z] Loop 3160: Loss: 5.28e-02, Avg Return: 0.647, Regret: 0.2133, Entropy: 0.5883 +[2026-03-20T18:08:54.807232Z] Loop 3161: Loss: 5.63e-02, Avg Return: 0.651, Regret: 0.2133, Entropy: 0.6010 +[2026-03-20T18:08:55.660499Z] Loop 3162: Loss: 5.81e-02, Avg Return: 0.655, Regret: 0.2133, Entropy: 0.6073 +[2026-03-20T18:08:56.514391Z] Loop 3163: Loss: 5.43e-02, Avg Return: 0.650, Regret: 0.2133, Entropy: 0.5996 +[2026-03-20T18:08:57.368321Z] Loop 3164: Loss: 5.69e-02, Avg Return: 0.657, Regret: 0.2133, Entropy: 0.5963 +[2026-03-20T18:08:58.222648Z] Loop 3165: Loss: 5.88e-02, Avg Return: 0.656, Regret: 0.2133, Entropy: 0.5803 +[2026-03-20T18:08:59.075873Z] Loop 3166: Loss: 6.46e-02, Avg Return: 0.655, Regret: 0.2133, Entropy: 0.5627 +[2026-03-20T18:08:59.928204Z] Loop 3167: Loss: 6.39e-02, Avg Return: 0.654, Regret: 0.2133, Entropy: 0.5686 +[2026-03-20T18:09:00.781395Z] Loop 3168: Loss: 6.43e-02, Avg Return: 0.667, Regret: 0.2133, Entropy: 0.5647 +[2026-03-20T18:09:01.635702Z] Loop 3169: Loss: 5.97e-02, Avg Return: 0.659, Regret: 0.2133, Entropy: 0.5692 +[2026-03-20T18:09:02.532491Z] Loop 3170: Loss: 5.79e-02, Avg Return: 0.666, Regret: 0.1944, Entropy: 0.5828 +[2026-03-20T18:09:03.384590Z] Loop 3171: Loss: 5.41e-02, Avg Return: 0.662, Regret: 0.1944, Entropy: 0.5725 +[2026-03-20T18:09:04.238456Z] Loop 3172: Loss: 6.34e-02, Avg Return: 0.673, Regret: 0.1944, Entropy: 0.5749 +[2026-03-20T18:09:05.092277Z] Loop 3173: Loss: 6.11e-02, Avg Return: 0.678, Regret: 0.1944, Entropy: 0.5584 +[2026-03-20T18:09:05.946155Z] Loop 3174: Loss: 6.61e-02, Avg Return: 0.672, Regret: 0.1944, Entropy: 0.5652 +[2026-03-20T18:09:06.799529Z] Loop 3175: Loss: 6.10e-02, Avg Return: 0.678, Regret: 0.1944, Entropy: 0.5370 +[2026-03-20T18:09:07.652184Z] Loop 3176: Loss: 6.18e-02, Avg Return: 0.678, Regret: 0.1944, Entropy: 0.5366 +[2026-03-20T18:09:08.506602Z] Loop 3177: Loss: 6.07e-02, Avg Return: 0.684, Regret: 0.1944, Entropy: 0.5448 +[2026-03-20T18:09:09.360010Z] Loop 3178: Loss: 6.49e-02, Avg Return: 0.690, Regret: 0.1944, Entropy: 0.5457 +[2026-03-20T18:09:10.213141Z] Loop 3179: Loss: 6.20e-02, Avg Return: 0.689, Regret: 0.1944, Entropy: 0.5618 +[2026-03-20T18:09:11.109176Z] Loop 3180: Loss: 6.38e-02, Avg Return: 0.694, Regret: 0.1666, Entropy: 0.5562 +[2026-03-20T18:09:11.962436Z] Loop 3181: Loss: 6.40e-02, Avg Return: 0.697, Regret: 0.1666, Entropy: 0.5318 +[2026-03-20T18:09:12.816307Z] Loop 3182: Loss: 6.42e-02, Avg Return: 0.698, Regret: 0.1666, Entropy: 0.5246 +[2026-03-20T18:09:13.669264Z] Loop 3183: Loss: 6.21e-02, Avg Return: 0.700, Regret: 0.1666, Entropy: 0.5265 +[2026-03-20T18:09:14.521048Z] Loop 3184: Loss: 6.68e-02, Avg Return: 0.708, Regret: 0.1666, Entropy: 0.5274 +[2026-03-20T18:09:15.373287Z] Loop 3185: Loss: 6.44e-02, Avg Return: 0.701, Regret: 0.1666, Entropy: 0.5373 +[2026-03-20T18:09:16.226517Z] Loop 3186: Loss: 6.93e-02, Avg Return: 0.706, Regret: 0.1666, Entropy: 0.5396 +[2026-03-20T18:09:17.079728Z] Loop 3187: Loss: 6.37e-02, Avg Return: 0.710, Regret: 0.1666, Entropy: 0.5151 +[2026-03-20T18:09:17.932360Z] Loop 3188: Loss: 6.51e-02, Avg Return: 0.706, Regret: 0.1666, Entropy: 0.5147 +[2026-03-20T18:09:18.784614Z] Loop 3189: Loss: 6.29e-02, Avg Return: 0.708, Regret: 0.1666, Entropy: 0.5379 +[2026-03-20T18:09:19.679710Z] Loop 3190: Loss: 7.10e-02, Avg Return: 0.714, Regret: 0.1457, Entropy: 0.5570 +[2026-03-20T18:09:20.534079Z] Loop 3191: Loss: 7.32e-02, Avg Return: 0.713, Regret: 0.1457, Entropy: 0.5428 +[2026-03-20T18:09:21.387592Z] Loop 3192: Loss: 7.10e-02, Avg Return: 0.713, Regret: 0.1457, Entropy: 0.5394 +[2026-03-20T18:09:22.240430Z] Loop 3193: Loss: 7.08e-02, Avg Return: 0.710, Regret: 0.1457, Entropy: 0.5238 +[2026-03-20T18:09:23.093543Z] Loop 3194: Loss: 7.13e-02, Avg Return: 0.715, Regret: 0.1457, Entropy: 0.5195 +[2026-03-20T18:09:23.945680Z] Loop 3195: Loss: 6.90e-02, Avg Return: 0.720, Regret: 0.1457, Entropy: 0.5275 +[2026-03-20T18:09:24.799216Z] Loop 3196: Loss: 6.75e-02, Avg Return: 0.717, Regret: 0.1457, Entropy: 0.5475 +[2026-03-20T18:09:25.652886Z] Loop 3197: Loss: 7.25e-02, Avg Return: 0.721, Regret: 0.1457, Entropy: 0.5605 +[2026-03-20T18:09:26.504808Z] Loop 3198: Loss: 7.32e-02, Avg Return: 0.723, Regret: 0.1457, Entropy: 0.5497 +[2026-03-20T18:09:27.358172Z] Loop 3199: Loss: 7.43e-02, Avg Return: 0.727, Regret: 0.1457, Entropy: 0.5494 +[2026-03-20T18:09:28.255736Z] Loop 3200: Loss: 7.59e-02, Avg Return: 0.725, Regret: 0.1318, Entropy: 0.5321 +[2026-03-20T18:09:29.109117Z] Loop 3201: Loss: 7.37e-02, Avg Return: 0.720, Regret: 0.1318, Entropy: 0.5156 +[2026-03-20T18:09:29.963501Z] Loop 3202: Loss: 7.31e-02, Avg Return: 0.727, Regret: 0.1318, Entropy: 0.5284 +[2026-03-20T18:09:30.816499Z] Loop 3203: Loss: 7.89e-02, Avg Return: 0.738, Regret: 0.1318, Entropy: 0.5302 +[2026-03-20T18:09:31.672153Z] Loop 3204: Loss: 7.60e-02, Avg Return: 0.732, Regret: 0.1318, Entropy: 0.5350 +[2026-03-20T18:09:32.525456Z] Loop 3205: Loss: 7.29e-02, Avg Return: 0.730, Regret: 0.1318, Entropy: 0.5478 +[2026-03-20T18:09:33.378576Z] Loop 3206: Loss: 7.43e-02, Avg Return: 0.738, Regret: 0.1318, Entropy: 0.5247 +[2026-03-20T18:09:34.232384Z] Loop 3207: Loss: 6.93e-02, Avg Return: 0.740, Regret: 0.1318, Entropy: 0.5023 +[2026-03-20T18:09:35.086114Z] Loop 3208: Loss: 7.20e-02, Avg Return: 0.740, Regret: 0.1318, Entropy: 0.4898 +[2026-03-20T18:09:35.940607Z] Loop 3209: Loss: 6.99e-02, Avg Return: 0.741, Regret: 0.1318, Entropy: 0.4936 +[2026-03-20T18:09:36.838277Z] Loop 3210: Loss: 7.18e-02, Avg Return: 0.738, Regret: 0.1204, Entropy: 0.4919 +[2026-03-20T18:09:37.691187Z] Loop 3211: Loss: 6.74e-02, Avg Return: 0.742, Regret: 0.1204, Entropy: 0.4907 +[2026-03-20T18:09:38.547130Z] Loop 3212: Loss: 6.94e-02, Avg Return: 0.742, Regret: 0.1204, Entropy: 0.5020 +[2026-03-20T18:09:39.401817Z] Loop 3213: Loss: 6.54e-02, Avg Return: 0.747, Regret: 0.1204, Entropy: 0.4856 +[2026-03-20T18:09:40.255737Z] Loop 3214: Loss: 6.88e-02, Avg Return: 0.746, Regret: 0.1204, Entropy: 0.4774 +[2026-03-20T18:09:41.109505Z] Loop 3215: Loss: 6.67e-02, Avg Return: 0.748, Regret: 0.1204, Entropy: 0.4780 +[2026-03-20T18:09:41.963667Z] Loop 3216: Loss: 6.86e-02, Avg Return: 0.746, Regret: 0.1204, Entropy: 0.4636 +[2026-03-20T18:09:42.816816Z] Loop 3217: Loss: 6.88e-02, Avg Return: 0.755, Regret: 0.1204, Entropy: 0.4648 +[2026-03-20T18:09:43.669942Z] Loop 3218: Loss: 6.97e-02, Avg Return: 0.748, Regret: 0.1204, Entropy: 0.4652 +[2026-03-20T18:09:44.522918Z] Loop 3219: Loss: 7.05e-02, Avg Return: 0.757, Regret: 0.1204, Entropy: 0.4550 +[2026-03-20T18:09:45.421814Z] Loop 3220: Loss: 6.64e-02, Avg Return: 0.758, Regret: 0.1047, Entropy: 0.4574 +[2026-03-20T18:09:46.274391Z] Loop 3221: Loss: 6.73e-02, Avg Return: 0.755, Regret: 0.1047, Entropy: 0.4385 +[2026-03-20T18:09:47.127786Z] Loop 3222: Loss: 7.08e-02, Avg Return: 0.756, Regret: 0.1047, Entropy: 0.4661 +[2026-03-20T18:09:47.981605Z] Loop 3223: Loss: 7.09e-02, Avg Return: 0.758, Regret: 0.1047, Entropy: 0.4657 +[2026-03-20T18:09:48.836802Z] Loop 3224: Loss: 7.25e-02, Avg Return: 0.762, Regret: 0.1047, Entropy: 0.4644 +[2026-03-20T18:09:49.690309Z] Loop 3225: Loss: 6.91e-02, Avg Return: 0.758, Regret: 0.1047, Entropy: 0.4647 +[2026-03-20T18:09:50.543590Z] Loop 3226: Loss: 6.90e-02, Avg Return: 0.763, Regret: 0.1047, Entropy: 0.4631 +[2026-03-20T18:09:51.397669Z] Loop 3227: Loss: 6.71e-02, Avg Return: 0.759, Regret: 0.1047, Entropy: 0.4678 +[2026-03-20T18:09:52.251315Z] Loop 3228: Loss: 6.42e-02, Avg Return: 0.758, Regret: 0.1047, Entropy: 0.4670 +[2026-03-20T18:09:53.103726Z] Loop 3229: Loss: 6.76e-02, Avg Return: 0.760, Regret: 0.1047, Entropy: 0.4632 +[2026-03-20T18:09:53.999328Z] Loop 3230: Loss: 7.22e-02, Avg Return: 0.763, Regret: 0.0979, Entropy: 0.4610 +[2026-03-20T18:09:54.853877Z] Loop 3231: Loss: 7.17e-02, Avg Return: 0.764, Regret: 0.0979, Entropy: 0.4548 +[2026-03-20T18:09:55.707709Z] Loop 3232: Loss: 7.02e-02, Avg Return: 0.757, Regret: 0.0979, Entropy: 0.4547 +[2026-03-20T18:09:56.560879Z] Loop 3233: Loss: 7.09e-02, Avg Return: 0.758, Regret: 0.0979, Entropy: 0.4561 +[2026-03-20T18:09:57.413313Z] Loop 3234: Loss: 7.05e-02, Avg Return: 0.761, Regret: 0.0979, Entropy: 0.4450 +[2026-03-20T18:09:58.267447Z] Loop 3235: Loss: 6.74e-02, Avg Return: 0.763, Regret: 0.0979, Entropy: 0.4448 +[2026-03-20T18:09:59.121487Z] Loop 3236: Loss: 6.83e-02, Avg Return: 0.769, Regret: 0.0979, Entropy: 0.4537 +[2026-03-20T18:09:59.974294Z] Loop 3237: Loss: 6.99e-02, Avg Return: 0.769, Regret: 0.0979, Entropy: 0.4480 +[2026-03-20T18:10:00.827577Z] Loop 3238: Loss: 7.02e-02, Avg Return: 0.771, Regret: 0.0979, Entropy: 0.4418 +[2026-03-20T18:10:01.680980Z] Loop 3239: Loss: 6.88e-02, Avg Return: 0.769, Regret: 0.0979, Entropy: 0.4394 +[2026-03-20T18:10:02.578673Z] Loop 3240: Loss: 7.32e-02, Avg Return: 0.763, Regret: 0.0992, Entropy: 0.4443 +[2026-03-20T18:10:03.434206Z] Loop 3241: Loss: 7.49e-02, Avg Return: 0.752, Regret: 0.0992, Entropy: 0.4641 +[2026-03-20T18:10:04.289349Z] Loop 3242: Loss: 7.25e-02, Avg Return: 0.761, Regret: 0.0992, Entropy: 0.4611 +[2026-03-20T18:10:05.142635Z] Loop 3243: Loss: 6.70e-02, Avg Return: 0.760, Regret: 0.0992, Entropy: 0.4332 +[2026-03-20T18:10:05.995301Z] Loop 3244: Loss: 6.94e-02, Avg Return: 0.763, Regret: 0.0992, Entropy: 0.4489 +[2026-03-20T18:10:06.848565Z] Loop 3245: Loss: 6.63e-02, Avg Return: 0.761, Regret: 0.0992, Entropy: 0.4473 +[2026-03-20T18:10:07.702693Z] Loop 3246: Loss: 6.52e-02, Avg Return: 0.768, Regret: 0.0992, Entropy: 0.4514 +[2026-03-20T18:10:08.557447Z] Loop 3247: Loss: 6.99e-02, Avg Return: 0.774, Regret: 0.0992, Entropy: 0.4415 +[2026-03-20T18:10:09.410798Z] Loop 3248: Loss: 6.35e-02, Avg Return: 0.777, Regret: 0.0992, Entropy: 0.4125 +[2026-03-20T18:10:10.265212Z] Loop 3249: Loss: 6.18e-02, Avg Return: 0.774, Regret: 0.0992, Entropy: 0.3894 +[2026-03-20T18:10:11.161972Z] Loop 3250: Loss: 6.40e-02, Avg Return: 0.773, Regret: 0.0893, Entropy: 0.3994 +[2026-03-20T18:10:12.016155Z] Loop 3251: Loss: 6.50e-02, Avg Return: 0.775, Regret: 0.0893, Entropy: 0.4157 +[2026-03-20T18:10:12.869404Z] Loop 3252: Loss: 6.78e-02, Avg Return: 0.762, Regret: 0.0893, Entropy: 0.4368 +[2026-03-20T18:10:13.721735Z] Loop 3253: Loss: 6.86e-02, Avg Return: 0.765, Regret: 0.0893, Entropy: 0.4474 +[2026-03-20T18:10:14.574736Z] Loop 3254: Loss: 6.31e-02, Avg Return: 0.777, Regret: 0.0893, Entropy: 0.4180 +[2026-03-20T18:10:15.427739Z] Loop 3255: Loss: 6.59e-02, Avg Return: 0.777, Regret: 0.0893, Entropy: 0.4215 +[2026-03-20T18:10:16.280590Z] Loop 3256: Loss: 6.68e-02, Avg Return: 0.777, Regret: 0.0893, Entropy: 0.4118 +[2026-03-20T18:10:17.133106Z] Loop 3257: Loss: 6.28e-02, Avg Return: 0.781, Regret: 0.0893, Entropy: 0.4093 +[2026-03-20T18:10:17.986001Z] Loop 3258: Loss: 6.65e-02, Avg Return: 0.777, Regret: 0.0893, Entropy: 0.4197 +[2026-03-20T18:10:18.838669Z] Loop 3259: Loss: 6.67e-02, Avg Return: 0.778, Regret: 0.0893, Entropy: 0.4240 +[2026-03-20T18:10:19.734127Z] Loop 3260: Loss: 6.93e-02, Avg Return: 0.780, Regret: 0.0846, Entropy: 0.4164 +[2026-03-20T18:10:20.587132Z] Loop 3261: Loss: 6.80e-02, Avg Return: 0.781, Regret: 0.0846, Entropy: 0.4237 +[2026-03-20T18:10:21.440415Z] Loop 3262: Loss: 6.83e-02, Avg Return: 0.776, Regret: 0.0846, Entropy: 0.4159 +[2026-03-20T18:10:22.293592Z] Loop 3263: Loss: 6.65e-02, Avg Return: 0.777, Regret: 0.0846, Entropy: 0.4132 +[2026-03-20T18:10:23.147000Z] Loop 3264: Loss: 6.46e-02, Avg Return: 0.779, Regret: 0.0846, Entropy: 0.4133 +[2026-03-20T18:10:23.999970Z] Loop 3265: Loss: 6.14e-02, Avg Return: 0.780, Regret: 0.0846, Entropy: 0.4111 +[2026-03-20T18:10:24.853286Z] Loop 3266: Loss: 5.85e-02, Avg Return: 0.781, Regret: 0.0846, Entropy: 0.3953 +[2026-03-20T18:10:25.705750Z] Loop 3267: Loss: 5.61e-02, Avg Return: 0.778, Regret: 0.0846, Entropy: 0.3771 +[2026-03-20T18:10:26.558794Z] Loop 3268: Loss: 6.04e-02, Avg Return: 0.783, Regret: 0.0846, Entropy: 0.3925 +[2026-03-20T18:10:27.411353Z] Loop 3269: Loss: 5.76e-02, Avg Return: 0.781, Regret: 0.0846, Entropy: 0.3957 +[2026-03-20T18:10:28.305956Z] Loop 3270: Loss: 6.03e-02, Avg Return: 0.780, Regret: 0.0789, Entropy: 0.3874 +[2026-03-20T18:10:29.159296Z] Loop 3271: Loss: 6.05e-02, Avg Return: 0.784, Regret: 0.0789, Entropy: 0.3795 +[2026-03-20T18:10:30.011952Z] Loop 3272: Loss: 6.23e-02, Avg Return: 0.778, Regret: 0.0789, Entropy: 0.3817 +[2026-03-20T18:10:30.864984Z] Loop 3273: Loss: 5.94e-02, Avg Return: 0.779, Regret: 0.0789, Entropy: 0.3888 +[2026-03-20T18:10:31.718826Z] Loop 3274: Loss: 6.08e-02, Avg Return: 0.779, Regret: 0.0789, Entropy: 0.3889 +[2026-03-20T18:10:32.571233Z] Loop 3275: Loss: 6.53e-02, Avg Return: 0.776, Regret: 0.0789, Entropy: 0.4064 +[2026-03-20T18:10:33.424154Z] Loop 3276: Loss: 6.32e-02, Avg Return: 0.783, Regret: 0.0789, Entropy: 0.4166 +[2026-03-20T18:10:34.277014Z] Loop 3277: Loss: 6.54e-02, Avg Return: 0.784, Regret: 0.0789, Entropy: 0.4198 +[2026-03-20T18:10:35.130697Z] Loop 3278: Loss: 6.44e-02, Avg Return: 0.787, Regret: 0.0789, Entropy: 0.4191 +[2026-03-20T18:10:35.983324Z] Loop 3279: Loss: 6.69e-02, Avg Return: 0.790, Regret: 0.0789, Entropy: 0.4079 +[2026-03-20T18:10:36.878202Z] Loop 3280: Loss: 6.27e-02, Avg Return: 0.793, Regret: 0.0706, Entropy: 0.3979 +[2026-03-20T18:10:37.731732Z] Loop 3281: Loss: 6.81e-02, Avg Return: 0.793, Regret: 0.0706, Entropy: 0.3991 +[2026-03-20T18:10:38.585604Z] Loop 3282: Loss: 6.80e-02, Avg Return: 0.786, Regret: 0.0706, Entropy: 0.4098 +[2026-03-20T18:10:39.438987Z] Loop 3283: Loss: 6.64e-02, Avg Return: 0.786, Regret: 0.0706, Entropy: 0.4048 +[2026-03-20T18:10:40.291963Z] Loop 3284: Loss: 6.62e-02, Avg Return: 0.793, Regret: 0.0706, Entropy: 0.4087 +[2026-03-20T18:10:41.144362Z] Loop 3285: Loss: 6.32e-02, Avg Return: 0.788, Regret: 0.0706, Entropy: 0.3830 +[2026-03-20T18:10:41.998318Z] Loop 3286: Loss: 6.42e-02, Avg Return: 0.783, Regret: 0.0706, Entropy: 0.3939 +[2026-03-20T18:10:42.851614Z] Loop 3287: Loss: 6.20e-02, Avg Return: 0.777, Regret: 0.0706, Entropy: 0.3956 +[2026-03-20T18:10:43.704276Z] Loop 3288: Loss: 6.09e-02, Avg Return: 0.784, Regret: 0.0706, Entropy: 0.3940 +[2026-03-20T18:10:44.557401Z] Loop 3289: Loss: 6.25e-02, Avg Return: 0.790, Regret: 0.0706, Entropy: 0.3889 +[2026-03-20T18:10:45.454693Z] Loop 3290: Loss: 6.05e-02, Avg Return: 0.794, Regret: 0.0668, Entropy: 0.3815 +[2026-03-20T18:10:46.308558Z] Loop 3291: Loss: 6.11e-02, Avg Return: 0.799, Regret: 0.0668, Entropy: 0.3549 +[2026-03-20T18:10:47.162731Z] Loop 3292: Loss: 6.14e-02, Avg Return: 0.798, Regret: 0.0668, Entropy: 0.3569 +[2026-03-20T18:10:48.015933Z] Loop 3293: Loss: 6.06e-02, Avg Return: 0.797, Regret: 0.0668, Entropy: 0.3479 +[2026-03-20T18:10:48.869953Z] Loop 3294: Loss: 6.02e-02, Avg Return: 0.797, Regret: 0.0668, Entropy: 0.3522 +[2026-03-20T18:10:49.725056Z] Loop 3295: Loss: 6.05e-02, Avg Return: 0.798, Regret: 0.0668, Entropy: 0.3603 +[2026-03-20T18:10:50.578902Z] Loop 3296: Loss: 6.07e-02, Avg Return: 0.800, Regret: 0.0668, Entropy: 0.3651 +[2026-03-20T18:10:51.431884Z] Loop 3297: Loss: 6.08e-02, Avg Return: 0.800, Regret: 0.0668, Entropy: 0.3690 +[2026-03-20T18:10:52.286023Z] Loop 3298: Loss: 5.87e-02, Avg Return: 0.800, Regret: 0.0668, Entropy: 0.3599 +[2026-03-20T18:10:53.140570Z] Loop 3299: Loss: 5.72e-02, Avg Return: 0.803, Regret: 0.0668, Entropy: 0.3424 +[2026-03-20T18:10:54.036870Z] Loop 3300: Loss: 6.25e-02, Avg Return: 0.801, Regret: 0.0617, Entropy: 0.3614 +[2026-03-20T18:10:54.890619Z] Loop 3301: Loss: 5.75e-02, Avg Return: 0.801, Regret: 0.0617, Entropy: 0.3460 +[2026-03-20T18:10:55.743430Z] Loop 3302: Loss: 5.91e-02, Avg Return: 0.801, Regret: 0.0617, Entropy: 0.3476 +[2026-03-20T18:10:56.597325Z] Loop 3303: Loss: 5.99e-02, Avg Return: 0.801, Regret: 0.0617, Entropy: 0.3516 +[2026-03-20T18:10:57.451550Z] Loop 3304: Loss: 6.34e-02, Avg Return: 0.800, Regret: 0.0617, Entropy: 0.3683 +[2026-03-20T18:10:58.305430Z] Loop 3305: Loss: 5.90e-02, Avg Return: 0.797, Regret: 0.0617, Entropy: 0.3589 +[2026-03-20T18:10:59.159014Z] Loop 3306: Loss: 5.95e-02, Avg Return: 0.802, Regret: 0.0617, Entropy: 0.3583 +[2026-03-20T18:11:00.012329Z] Loop 3307: Loss: 6.02e-02, Avg Return: 0.805, Regret: 0.0617, Entropy: 0.3370 +[2026-03-20T18:11:00.865298Z] Loop 3308: Loss: 5.73e-02, Avg Return: 0.798, Regret: 0.0617, Entropy: 0.3445 +[2026-03-20T18:11:01.719608Z] Loop 3309: Loss: 5.95e-02, Avg Return: 0.799, Regret: 0.0617, Entropy: 0.3480 +[2026-03-20T18:11:02.615726Z] Loop 3310: Loss: 6.05e-02, Avg Return: 0.805, Regret: 0.0563, Entropy: 0.3575 +[2026-03-20T18:11:03.468191Z] Loop 3311: Loss: 6.24e-02, Avg Return: 0.802, Regret: 0.0563, Entropy: 0.3792 +[2026-03-20T18:11:04.320826Z] Loop 3312: Loss: 5.73e-02, Avg Return: 0.795, Regret: 0.0563, Entropy: 0.3786 +[2026-03-20T18:11:05.175534Z] Loop 3313: Loss: 6.25e-02, Avg Return: 0.803, Regret: 0.0563, Entropy: 0.3763 +[2026-03-20T18:11:06.029248Z] Loop 3314: Loss: 6.44e-02, Avg Return: 0.811, Regret: 0.0563, Entropy: 0.3624 +[2026-03-20T18:11:06.883428Z] Loop 3315: Loss: 6.18e-02, Avg Return: 0.806, Regret: 0.0563, Entropy: 0.3452 +[2026-03-20T18:11:07.737948Z] Loop 3316: Loss: 5.99e-02, Avg Return: 0.804, Regret: 0.0563, Entropy: 0.3438 +[2026-03-20T18:11:08.593575Z] Loop 3317: Loss: 6.00e-02, Avg Return: 0.805, Regret: 0.0563, Entropy: 0.3459 +[2026-03-20T18:11:09.448120Z] Loop 3318: Loss: 5.97e-02, Avg Return: 0.802, Regret: 0.0563, Entropy: 0.3488 +[2026-03-20T18:11:10.302121Z] Loop 3319: Loss: 6.08e-02, Avg Return: 0.801, Regret: 0.0563, Entropy: 0.3464 +[2026-03-20T18:11:11.199426Z] Loop 3320: Loss: 6.01e-02, Avg Return: 0.808, Regret: 0.0552, Entropy: 0.3565 +[2026-03-20T18:11:12.053501Z] Loop 3321: Loss: 5.91e-02, Avg Return: 0.808, Regret: 0.0552, Entropy: 0.3500 +[2026-03-20T18:11:12.907124Z] Loop 3322: Loss: 5.73e-02, Avg Return: 0.804, Regret: 0.0552, Entropy: 0.3485 +[2026-03-20T18:11:13.760369Z] Loop 3323: Loss: 5.77e-02, Avg Return: 0.804, Regret: 0.0552, Entropy: 0.3564 +[2026-03-20T18:11:14.613560Z] Loop 3324: Loss: 5.79e-02, Avg Return: 0.794, Regret: 0.0552, Entropy: 0.3634 +[2026-03-20T18:11:15.466701Z] Loop 3325: Loss: 5.65e-02, Avg Return: 0.801, Regret: 0.0552, Entropy: 0.3517 +[2026-03-20T18:11:16.319726Z] Loop 3326: Loss: 5.90e-02, Avg Return: 0.811, Regret: 0.0552, Entropy: 0.3514 +[2026-03-20T18:11:17.172609Z] Loop 3327: Loss: 5.84e-02, Avg Return: 0.813, Regret: 0.0552, Entropy: 0.3393 +[2026-03-20T18:11:18.025447Z] Loop 3328: Loss: 6.05e-02, Avg Return: 0.809, Regret: 0.0552, Entropy: 0.3407 +[2026-03-20T18:11:18.879014Z] Loop 3329: Loss: 5.96e-02, Avg Return: 0.809, Regret: 0.0552, Entropy: 0.3409 +[2026-03-20T18:11:19.774555Z] Loop 3330: Loss: 5.89e-02, Avg Return: 0.806, Regret: 0.0559, Entropy: 0.3424 +[2026-03-20T18:11:20.628095Z] Loop 3331: Loss: 6.27e-02, Avg Return: 0.808, Regret: 0.0559, Entropy: 0.3541 +[2026-03-20T18:11:21.483002Z] Loop 3332: Loss: 6.25e-02, Avg Return: 0.809, Regret: 0.0559, Entropy: 0.3560 +[2026-03-20T18:11:22.336764Z] Loop 3333: Loss: 6.47e-02, Avg Return: 0.817, Regret: 0.0559, Entropy: 0.3637 +[2026-03-20T18:11:23.189985Z] Loop 3334: Loss: 6.00e-02, Avg Return: 0.811, Regret: 0.0559, Entropy: 0.3560 +[2026-03-20T18:11:24.044189Z] Loop 3335: Loss: 6.02e-02, Avg Return: 0.810, Regret: 0.0559, Entropy: 0.3654 +[2026-03-20T18:11:24.900015Z] Loop 3336: Loss: 5.81e-02, Avg Return: 0.808, Regret: 0.0559, Entropy: 0.3570 +[2026-03-20T18:11:25.753664Z] Loop 3337: Loss: 6.02e-02, Avg Return: 0.809, Regret: 0.0559, Entropy: 0.3595 +[2026-03-20T18:11:26.606722Z] Loop 3338: Loss: 6.24e-02, Avg Return: 0.814, Regret: 0.0559, Entropy: 0.3603 +[2026-03-20T18:11:27.460474Z] Loop 3339: Loss: 6.33e-02, Avg Return: 0.817, Regret: 0.0559, Entropy: 0.3642 +[2026-03-20T18:11:28.356767Z] Loop 3340: Loss: 6.32e-02, Avg Return: 0.812, Regret: 0.0490, Entropy: 0.3607 +[2026-03-20T18:11:29.209615Z] Loop 3341: Loss: 6.06e-02, Avg Return: 0.811, Regret: 0.0490, Entropy: 0.3509 +[2026-03-20T18:11:30.062730Z] Loop 3342: Loss: 6.12e-02, Avg Return: 0.812, Regret: 0.0490, Entropy: 0.3379 +[2026-03-20T18:11:30.916612Z] Loop 3343: Loss: 5.83e-02, Avg Return: 0.810, Regret: 0.0490, Entropy: 0.3255 +[2026-03-20T18:11:31.770725Z] Loop 3344: Loss: 5.72e-02, Avg Return: 0.814, Regret: 0.0490, Entropy: 0.3209 +[2026-03-20T18:11:32.623572Z] Loop 3345: Loss: 5.76e-02, Avg Return: 0.815, Regret: 0.0490, Entropy: 0.3260 +[2026-03-20T18:11:33.476846Z] Loop 3346: Loss: 5.61e-02, Avg Return: 0.815, Regret: 0.0490, Entropy: 0.3287 +[2026-03-20T18:11:34.329430Z] Loop 3347: Loss: 5.78e-02, Avg Return: 0.817, Regret: 0.0490, Entropy: 0.3403 +[2026-03-20T18:11:35.183198Z] Loop 3348: Loss: 5.72e-02, Avg Return: 0.815, Regret: 0.0490, Entropy: 0.3396 +[2026-03-20T18:11:36.036104Z] Loop 3349: Loss: 5.59e-02, Avg Return: 0.817, Regret: 0.0490, Entropy: 0.3290 +[2026-03-20T18:11:36.929796Z] Loop 3350: Loss: 5.71e-02, Avg Return: 0.817, Regret: 0.0439, Entropy: 0.3253 +[2026-03-20T18:11:37.782974Z] Loop 3351: Loss: 5.36e-02, Avg Return: 0.820, Regret: 0.0439, Entropy: 0.3157 +[2026-03-20T18:11:38.637022Z] Loop 3352: Loss: 5.52e-02, Avg Return: 0.820, Regret: 0.0439, Entropy: 0.3085 +[2026-03-20T18:11:39.491302Z] Loop 3353: Loss: 5.72e-02, Avg Return: 0.821, Regret: 0.0439, Entropy: 0.3097 +[2026-03-20T18:11:40.346833Z] Loop 3354: Loss: 5.66e-02, Avg Return: 0.819, Regret: 0.0439, Entropy: 0.3163 +[2026-03-20T18:11:41.202105Z] Loop 3355: Loss: 5.24e-02, Avg Return: 0.818, Regret: 0.0439, Entropy: 0.3055 +[2026-03-20T18:11:42.055059Z] Loop 3356: Loss: 5.61e-02, Avg Return: 0.820, Regret: 0.0439, Entropy: 0.3238 +[2026-03-20T18:11:42.907152Z] Loop 3357: Loss: 5.41e-02, Avg Return: 0.822, Regret: 0.0439, Entropy: 0.3102 +[2026-03-20T18:11:43.760224Z] Loop 3358: Loss: 5.48e-02, Avg Return: 0.820, Regret: 0.0439, Entropy: 0.3248 +[2026-03-20T18:11:44.614091Z] Loop 3359: Loss: 5.82e-02, Avg Return: 0.820, Regret: 0.0439, Entropy: 0.3259 +[2026-03-20T18:11:45.510787Z] Loop 3360: Loss: 5.64e-02, Avg Return: 0.821, Regret: 0.0422, Entropy: 0.3317 +[2026-03-20T18:11:46.363279Z] Loop 3361: Loss: 5.59e-02, Avg Return: 0.820, Regret: 0.0422, Entropy: 0.3115 +[2026-03-20T18:11:47.216160Z] Loop 3362: Loss: 5.67e-02, Avg Return: 0.820, Regret: 0.0422, Entropy: 0.3217 +[2026-03-20T18:11:48.070057Z] Loop 3363: Loss: 5.82e-02, Avg Return: 0.820, Regret: 0.0422, Entropy: 0.3297 +[2026-03-20T18:11:48.923292Z] Loop 3364: Loss: 5.72e-02, Avg Return: 0.820, Regret: 0.0422, Entropy: 0.3300 +[2026-03-20T18:11:49.775906Z] Loop 3365: Loss: 5.85e-02, Avg Return: 0.822, Regret: 0.0422, Entropy: 0.3354 +[2026-03-20T18:11:50.628772Z] Loop 3366: Loss: 5.69e-02, Avg Return: 0.823, Regret: 0.0422, Entropy: 0.3239 +[2026-03-20T18:11:51.482541Z] Loop 3367: Loss: 5.64e-02, Avg Return: 0.821, Regret: 0.0422, Entropy: 0.3221 +[2026-03-20T18:11:52.335742Z] Loop 3368: Loss: 5.92e-02, Avg Return: 0.821, Regret: 0.0422, Entropy: 0.3305 +[2026-03-20T18:11:53.188342Z] Loop 3369: Loss: 5.96e-02, Avg Return: 0.820, Regret: 0.0422, Entropy: 0.3277 +[2026-03-20T18:11:54.082415Z] Loop 3370: Loss: 5.57e-02, Avg Return: 0.822, Regret: 0.0413, Entropy: 0.3134 +[2026-03-20T18:11:54.936459Z] Loop 3371: Loss: 5.68e-02, Avg Return: 0.823, Regret: 0.0413, Entropy: 0.3141 +[2026-03-20T18:11:55.790456Z] Loop 3372: Loss: 5.63e-02, Avg Return: 0.824, Regret: 0.0413, Entropy: 0.3279 +[2026-03-20T18:11:56.643641Z] Loop 3373: Loss: 5.80e-02, Avg Return: 0.824, Regret: 0.0413, Entropy: 0.3341 +[2026-03-20T18:11:57.498102Z] Loop 3374: Loss: 5.39e-02, Avg Return: 0.820, Regret: 0.0413, Entropy: 0.3260 +[2026-03-20T18:11:58.352112Z] Loop 3375: Loss: 5.72e-02, Avg Return: 0.819, Regret: 0.0413, Entropy: 0.3374 +[2026-03-20T18:11:59.205645Z] Loop 3376: Loss: 5.38e-02, Avg Return: 0.821, Regret: 0.0413, Entropy: 0.3216 +[2026-03-20T18:12:00.059270Z] Loop 3377: Loss: 5.29e-02, Avg Return: 0.827, Regret: 0.0413, Entropy: 0.3084 +[2026-03-20T18:12:00.912978Z] Loop 3378: Loss: 5.26e-02, Avg Return: 0.828, Regret: 0.0413, Entropy: 0.3003 +[2026-03-20T18:12:01.767879Z] Loop 3379: Loss: 5.11e-02, Avg Return: 0.825, Regret: 0.0413, Entropy: 0.2882 +[2026-03-20T18:12:02.663807Z] Loop 3380: Loss: 5.26e-02, Avg Return: 0.826, Regret: 0.0395, Entropy: 0.2928 +[2026-03-20T18:12:03.518605Z] Loop 3381: Loss: 5.42e-02, Avg Return: 0.826, Regret: 0.0395, Entropy: 0.3084 +[2026-03-20T18:12:04.373477Z] Loop 3382: Loss: 5.24e-02, Avg Return: 0.827, Regret: 0.0395, Entropy: 0.2952 +[2026-03-20T18:12:05.227989Z] Loop 3383: Loss: 5.18e-02, Avg Return: 0.824, Regret: 0.0395, Entropy: 0.3089 +[2026-03-20T18:12:06.082071Z] Loop 3384: Loss: 5.22e-02, Avg Return: 0.824, Regret: 0.0395, Entropy: 0.3063 +[2026-03-20T18:12:06.937201Z] Loop 3385: Loss: 5.36e-02, Avg Return: 0.822, Regret: 0.0395, Entropy: 0.3036 +[2026-03-20T18:12:07.792338Z] Loop 3386: Loss: 5.20e-02, Avg Return: 0.823, Regret: 0.0395, Entropy: 0.3045 +[2026-03-20T18:12:08.646345Z] Loop 3387: Loss: 5.33e-02, Avg Return: 0.827, Regret: 0.0395, Entropy: 0.3046 +[2026-03-20T18:12:09.499527Z] Loop 3388: Loss: 5.27e-02, Avg Return: 0.826, Regret: 0.0395, Entropy: 0.2987 +[2026-03-20T18:12:10.352624Z] Loop 3389: Loss: 5.23e-02, Avg Return: 0.829, Regret: 0.0395, Entropy: 0.2969 +[2026-03-20T18:12:11.249404Z] Loop 3390: Loss: 5.40e-02, Avg Return: 0.829, Regret: 0.0362, Entropy: 0.3086 +[2026-03-20T18:12:12.103519Z] Loop 3391: Loss: 5.13e-02, Avg Return: 0.829, Regret: 0.0362, Entropy: 0.2876 +[2026-03-20T18:12:12.957262Z] Loop 3392: Loss: 5.43e-02, Avg Return: 0.826, Regret: 0.0362, Entropy: 0.2980 +[2026-03-20T18:12:13.810925Z] Loop 3393: Loss: 5.27e-02, Avg Return: 0.826, Regret: 0.0362, Entropy: 0.3005 +[2026-03-20T18:12:14.664995Z] Loop 3394: Loss: 5.31e-02, Avg Return: 0.825, Regret: 0.0362, Entropy: 0.2978 +[2026-03-20T18:12:15.519069Z] Loop 3395: Loss: 5.25e-02, Avg Return: 0.825, Regret: 0.0362, Entropy: 0.3091 +[2026-03-20T18:12:16.372272Z] Loop 3396: Loss: 5.37e-02, Avg Return: 0.825, Regret: 0.0362, Entropy: 0.3043 +[2026-03-20T18:12:17.224855Z] Loop 3397: Loss: 5.33e-02, Avg Return: 0.826, Regret: 0.0362, Entropy: 0.3125 +[2026-03-20T18:12:18.077981Z] Loop 3398: Loss: 5.26e-02, Avg Return: 0.828, Regret: 0.0362, Entropy: 0.3011 +[2026-03-20T18:12:18.931913Z] Loop 3399: Loss: 5.14e-02, Avg Return: 0.827, Regret: 0.0362, Entropy: 0.2889 +[2026-03-20T18:12:19.825969Z] Loop 3400: Loss: 4.85e-02, Avg Return: 0.824, Regret: 0.0390, Entropy: 0.2853 +[2026-03-20T18:12:20.678847Z] Loop 3401: Loss: 5.30e-02, Avg Return: 0.825, Regret: 0.0390, Entropy: 0.2918 +[2026-03-20T18:12:21.532572Z] Loop 3402: Loss: 4.96e-02, Avg Return: 0.830, Regret: 0.0390, Entropy: 0.2868 +[2026-03-20T18:12:22.387516Z] Loop 3403: Loss: 5.66e-02, Avg Return: 0.827, Regret: 0.0390, Entropy: 0.3212 +[2026-03-20T18:12:23.242747Z] Loop 3404: Loss: 5.28e-02, Avg Return: 0.825, Regret: 0.0390, Entropy: 0.3095 +[2026-03-20T18:12:24.096728Z] Loop 3405: Loss: 5.51e-02, Avg Return: 0.829, Regret: 0.0390, Entropy: 0.3159 +[2026-03-20T18:12:24.950501Z] Loop 3406: Loss: 5.51e-02, Avg Return: 0.829, Regret: 0.0390, Entropy: 0.3095 +[2026-03-20T18:12:25.805067Z] Loop 3407: Loss: 5.20e-02, Avg Return: 0.830, Regret: 0.0390, Entropy: 0.2964 +[2026-03-20T18:12:26.660365Z] Loop 3408: Loss: 5.17e-02, Avg Return: 0.824, Regret: 0.0390, Entropy: 0.2918 +[2026-03-20T18:12:27.513199Z] Loop 3409: Loss: 5.24e-02, Avg Return: 0.823, Regret: 0.0390, Entropy: 0.2945 +[2026-03-20T18:12:28.407798Z] Loop 3410: Loss: 5.21e-02, Avg Return: 0.821, Regret: 0.0391, Entropy: 0.2974 +[2026-03-20T18:12:29.261715Z] Loop 3411: Loss: 5.21e-02, Avg Return: 0.826, Regret: 0.0391, Entropy: 0.2986 +[2026-03-20T18:12:30.115833Z] Loop 3412: Loss: 5.13e-02, Avg Return: 0.830, Regret: 0.0391, Entropy: 0.2916 +[2026-03-20T18:12:30.969505Z] Loop 3413: Loss: 5.11e-02, Avg Return: 0.830, Regret: 0.0391, Entropy: 0.2968 +[2026-03-20T18:12:31.824058Z] Loop 3414: Loss: 5.50e-02, Avg Return: 0.826, Regret: 0.0391, Entropy: 0.3022 +[2026-03-20T18:12:32.677609Z] Loop 3415: Loss: 5.39e-02, Avg Return: 0.822, Regret: 0.0391, Entropy: 0.3112 +[2026-03-20T18:12:33.530720Z] Loop 3416: Loss: 5.43e-02, Avg Return: 0.817, Regret: 0.0391, Entropy: 0.3043 +[2026-03-20T18:12:34.385412Z] Loop 3417: Loss: 5.43e-02, Avg Return: 0.819, Regret: 0.0391, Entropy: 0.2954 +[2026-03-20T18:12:35.240284Z] Loop 3418: Loss: 5.45e-02, Avg Return: 0.827, Regret: 0.0391, Entropy: 0.2997 +[2026-03-20T18:12:36.094220Z] Loop 3419: Loss: 5.34e-02, Avg Return: 0.830, Regret: 0.0391, Entropy: 0.2935 +[2026-03-20T18:12:36.988358Z] Loop 3420: Loss: 4.95e-02, Avg Return: 0.831, Regret: 0.0310, Entropy: 0.2813 +[2026-03-20T18:12:37.843161Z] Loop 3421: Loss: 4.88e-02, Avg Return: 0.828, Regret: 0.0310, Entropy: 0.2791 +[2026-03-20T18:12:38.697570Z] Loop 3422: Loss: 5.29e-02, Avg Return: 0.818, Regret: 0.0310, Entropy: 0.3006 +[2026-03-20T18:12:39.552515Z] Loop 3423: Loss: 5.03e-02, Avg Return: 0.815, Regret: 0.0310, Entropy: 0.2956 +[2026-03-20T18:12:40.406271Z] Loop 3424: Loss: 4.97e-02, Avg Return: 0.820, Regret: 0.0310, Entropy: 0.2832 +[2026-03-20T18:12:41.259914Z] Loop 3425: Loss: 5.02e-02, Avg Return: 0.829, Regret: 0.0310, Entropy: 0.2898 +[2026-03-20T18:12:42.114699Z] Loop 3426: Loss: 5.08e-02, Avg Return: 0.834, Regret: 0.0310, Entropy: 0.2884 +[2026-03-20T18:12:42.968435Z] Loop 3427: Loss: 5.19e-02, Avg Return: 0.834, Regret: 0.0310, Entropy: 0.2910 +[2026-03-20T18:12:43.822814Z] Loop 3428: Loss: 5.17e-02, Avg Return: 0.833, Regret: 0.0310, Entropy: 0.2770 +[2026-03-20T18:12:44.677023Z] Loop 3429: Loss: 5.23e-02, Avg Return: 0.828, Regret: 0.0310, Entropy: 0.2817 +[2026-03-20T18:12:45.573454Z] Loop 3430: Loss: 5.04e-02, Avg Return: 0.827, Regret: 0.0372, Entropy: 0.2754 +[2026-03-20T18:12:46.427278Z] Loop 3431: Loss: 4.90e-02, Avg Return: 0.824, Regret: 0.0372, Entropy: 0.2824 +[2026-03-20T18:12:47.281745Z] Loop 3432: Loss: 5.05e-02, Avg Return: 0.829, Regret: 0.0372, Entropy: 0.2781 +[2026-03-20T18:12:48.134407Z] Loop 3433: Loss: 5.19e-02, Avg Return: 0.831, Regret: 0.0372, Entropy: 0.2884 +[2026-03-20T18:12:48.987717Z] Loop 3434: Loss: 4.99e-02, Avg Return: 0.832, Regret: 0.0372, Entropy: 0.2787 +[2026-03-20T18:12:49.841141Z] Loop 3435: Loss: 5.05e-02, Avg Return: 0.834, Regret: 0.0372, Entropy: 0.2820 +[2026-03-20T18:12:50.694846Z] Loop 3436: Loss: 5.02e-02, Avg Return: 0.833, Regret: 0.0372, Entropy: 0.2898 +[2026-03-20T18:12:51.549412Z] Loop 3437: Loss: 5.06e-02, Avg Return: 0.832, Regret: 0.0372, Entropy: 0.2837 +[2026-03-20T18:12:52.403937Z] Loop 3438: Loss: 5.08e-02, Avg Return: 0.834, Regret: 0.0372, Entropy: 0.2882 +[2026-03-20T18:12:53.259709Z] Loop 3439: Loss: 5.03e-02, Avg Return: 0.835, Regret: 0.0372, Entropy: 0.2778 +[2026-03-20T18:12:54.158507Z] Loop 3440: Loss: 4.93e-02, Avg Return: 0.836, Regret: 0.0264, Entropy: 0.2809 +[2026-03-20T18:12:55.013020Z] Loop 3441: Loss: 4.82e-02, Avg Return: 0.838, Regret: 0.0264, Entropy: 0.2708 +[2026-03-20T18:12:55.867335Z] Loop 3442: Loss: 4.73e-02, Avg Return: 0.831, Regret: 0.0264, Entropy: 0.2693 +[2026-03-20T18:12:56.721846Z] Loop 3443: Loss: 4.80e-02, Avg Return: 0.830, Regret: 0.0264, Entropy: 0.2675 +[2026-03-20T18:12:57.575224Z] Loop 3444: Loss: 4.67e-02, Avg Return: 0.837, Regret: 0.0264, Entropy: 0.2661 +[2026-03-20T18:12:58.429172Z] Loop 3445: Loss: 4.76e-02, Avg Return: 0.837, Regret: 0.0264, Entropy: 0.2664 +[2026-03-20T18:12:59.282754Z] Loop 3446: Loss: 4.37e-02, Avg Return: 0.836, Regret: 0.0264, Entropy: 0.2624 +[2026-03-20T18:13:00.135602Z] Loop 3447: Loss: 4.78e-02, Avg Return: 0.836, Regret: 0.0264, Entropy: 0.2722 +[2026-03-20T18:13:00.988297Z] Loop 3448: Loss: 4.71e-02, Avg Return: 0.833, Regret: 0.0264, Entropy: 0.2667 +[2026-03-20T18:13:01.842369Z] Loop 3449: Loss: 4.45e-02, Avg Return: 0.835, Regret: 0.0264, Entropy: 0.2594 +[2026-03-20T18:13:02.736951Z] Loop 3450: Loss: 4.64e-02, Avg Return: 0.837, Regret: 0.0278, Entropy: 0.2640 +[2026-03-20T18:13:03.591456Z] Loop 3451: Loss: 4.67e-02, Avg Return: 0.836, Regret: 0.0278, Entropy: 0.2680 +[2026-03-20T18:13:04.445383Z] Loop 3452: Loss: 4.45e-02, Avg Return: 0.836, Regret: 0.0278, Entropy: 0.2583 +[2026-03-20T18:13:05.300712Z] Loop 3453: Loss: 4.80e-02, Avg Return: 0.835, Regret: 0.0278, Entropy: 0.2684 +[2026-03-20T18:13:06.155147Z] Loop 3454: Loss: 4.59e-02, Avg Return: 0.835, Regret: 0.0278, Entropy: 0.2646 +[2026-03-20T18:13:07.009153Z] Loop 3455: Loss: 4.87e-02, Avg Return: 0.837, Regret: 0.0278, Entropy: 0.2786 +[2026-03-20T18:13:07.863367Z] Loop 3456: Loss: 4.72e-02, Avg Return: 0.835, Regret: 0.0278, Entropy: 0.2715 +[2026-03-20T18:13:08.718246Z] Loop 3457: Loss: 4.70e-02, Avg Return: 0.835, Regret: 0.0278, Entropy: 0.2668 +[2026-03-20T18:13:09.572407Z] Loop 3458: Loss: 4.75e-02, Avg Return: 0.837, Regret: 0.0278, Entropy: 0.2754 +[2026-03-20T18:13:10.427280Z] Loop 3459: Loss: 4.77e-02, Avg Return: 0.838, Regret: 0.0278, Entropy: 0.2688 +[2026-03-20T18:13:11.323416Z] Loop 3460: Loss: 4.55e-02, Avg Return: 0.839, Regret: 0.0247, Entropy: 0.2570 +[2026-03-20T18:13:12.178081Z] Loop 3461: Loss: 4.65e-02, Avg Return: 0.838, Regret: 0.0247, Entropy: 0.2539 +[2026-03-20T18:13:13.032983Z] Loop 3462: Loss: 4.44e-02, Avg Return: 0.833, Regret: 0.0247, Entropy: 0.2492 +[2026-03-20T18:13:13.886103Z] Loop 3463: Loss: 4.69e-02, Avg Return: 0.830, Regret: 0.0247, Entropy: 0.2565 +[2026-03-20T18:13:14.739162Z] Loop 3464: Loss: 4.92e-02, Avg Return: 0.832, Regret: 0.0247, Entropy: 0.2623 +[2026-03-20T18:13:15.592295Z] Loop 3465: Loss: 4.56e-02, Avg Return: 0.837, Regret: 0.0247, Entropy: 0.2524 +[2026-03-20T18:13:16.445281Z] Loop 3466: Loss: 4.57e-02, Avg Return: 0.838, Regret: 0.0247, Entropy: 0.2672 +[2026-03-20T18:13:17.299299Z] Loop 3467: Loss: 4.68e-02, Avg Return: 0.836, Regret: 0.0247, Entropy: 0.2674 +[2026-03-20T18:13:18.153119Z] Loop 3468: Loss: 4.69e-02, Avg Return: 0.834, Regret: 0.0247, Entropy: 0.2767 +[2026-03-20T18:13:19.006660Z] Loop 3469: Loss: 5.02e-02, Avg Return: 0.834, Regret: 0.0247, Entropy: 0.2830 +[2026-03-20T18:13:19.901170Z] Loop 3470: Loss: 4.65e-02, Avg Return: 0.835, Regret: 0.0289, Entropy: 0.2736 +[2026-03-20T18:13:20.755152Z] Loop 3471: Loss: 4.89e-02, Avg Return: 0.836, Regret: 0.0289, Entropy: 0.2666 +[2026-03-20T18:13:21.609210Z] Loop 3472: Loss: 4.38e-02, Avg Return: 0.836, Regret: 0.0289, Entropy: 0.2469 +[2026-03-20T18:13:22.463201Z] Loop 3473: Loss: 4.85e-02, Avg Return: 0.836, Regret: 0.0289, Entropy: 0.2518 +[2026-03-20T18:13:23.316236Z] Loop 3474: Loss: 4.58e-02, Avg Return: 0.832, Regret: 0.0289, Entropy: 0.2574 +[2026-03-20T18:13:24.169009Z] Loop 3475: Loss: 4.77e-02, Avg Return: 0.834, Regret: 0.0289, Entropy: 0.2583 +[2026-03-20T18:13:25.023002Z] Loop 3476: Loss: 4.57e-02, Avg Return: 0.835, Regret: 0.0289, Entropy: 0.2580 +[2026-03-20T18:13:25.876301Z] Loop 3477: Loss: 4.65e-02, Avg Return: 0.836, Regret: 0.0289, Entropy: 0.2698 +[2026-03-20T18:13:26.728674Z] Loop 3478: Loss: 4.62e-02, Avg Return: 0.833, Regret: 0.0289, Entropy: 0.2723 +[2026-03-20T18:13:27.582434Z] Loop 3479: Loss: 4.86e-02, Avg Return: 0.834, Regret: 0.0289, Entropy: 0.2784 +[2026-03-20T18:13:28.476512Z] Loop 3480: Loss: 4.62e-02, Avg Return: 0.837, Regret: 0.0256, Entropy: 0.2585 +[2026-03-20T18:13:29.330141Z] Loop 3481: Loss: 4.48e-02, Avg Return: 0.840, Regret: 0.0256, Entropy: 0.2513 +[2026-03-20T18:13:30.184326Z] Loop 3482: Loss: 4.44e-02, Avg Return: 0.838, Regret: 0.0256, Entropy: 0.2370 +[2026-03-20T18:13:31.037871Z] Loop 3483: Loss: 4.39e-02, Avg Return: 0.834, Regret: 0.0256, Entropy: 0.2301 +[2026-03-20T18:13:31.891185Z] Loop 3484: Loss: 4.35e-02, Avg Return: 0.830, Regret: 0.0256, Entropy: 0.2363 +[2026-03-20T18:13:32.745322Z] Loop 3485: Loss: 4.67e-02, Avg Return: 0.834, Regret: 0.0256, Entropy: 0.2386 +[2026-03-20T18:13:33.598834Z] Loop 3486: Loss: 4.28e-02, Avg Return: 0.840, Regret: 0.0256, Entropy: 0.2329 +[2026-03-20T18:13:34.453149Z] Loop 3487: Loss: 4.33e-02, Avg Return: 0.842, Regret: 0.0256, Entropy: 0.2532 +[2026-03-20T18:13:35.307480Z] Loop 3488: Loss: 4.64e-02, Avg Return: 0.840, Regret: 0.0256, Entropy: 0.2612 +[2026-03-20T18:13:36.161707Z] Loop 3489: Loss: 4.65e-02, Avg Return: 0.834, Regret: 0.0256, Entropy: 0.2706 +[2026-03-20T18:13:37.056626Z] Loop 3490: Loss: 4.56e-02, Avg Return: 0.835, Regret: 0.0279, Entropy: 0.2680 +[2026-03-20T18:13:37.910285Z] Loop 3491: Loss: 4.66e-02, Avg Return: 0.841, Regret: 0.0279, Entropy: 0.2599 +[2026-03-20T18:13:38.764229Z] Loop 3492: Loss: 4.46e-02, Avg Return: 0.840, Regret: 0.0279, Entropy: 0.2456 +[2026-03-20T18:13:39.617095Z] Loop 3493: Loss: 4.68e-02, Avg Return: 0.836, Regret: 0.0279, Entropy: 0.2476 +[2026-03-20T18:13:40.471230Z] Loop 3494: Loss: 4.83e-02, Avg Return: 0.833, Regret: 0.0279, Entropy: 0.2479 +[2026-03-20T18:13:41.324571Z] Loop 3495: Loss: 4.70e-02, Avg Return: 0.831, Regret: 0.0279, Entropy: 0.2439 +[2026-03-20T18:13:42.178562Z] Loop 3496: Loss: 4.50e-02, Avg Return: 0.833, Regret: 0.0279, Entropy: 0.2419 +[2026-03-20T18:13:43.032364Z] Loop 3497: Loss: 4.30e-02, Avg Return: 0.834, Regret: 0.0279, Entropy: 0.2397 +[2026-03-20T18:13:43.886501Z] Loop 3498: Loss: 4.81e-02, Avg Return: 0.830, Regret: 0.0279, Entropy: 0.2740 +[2026-03-20T18:13:44.739816Z] Loop 3499: Loss: 4.74e-02, Avg Return: 0.827, Regret: 0.0279, Entropy: 0.2800 +[2026-03-20T18:13:45.634529Z] Loop 3500: Loss: 4.80e-02, Avg Return: 0.832, Regret: 0.0305, Entropy: 0.2756 +[2026-03-20T18:13:46.487256Z] Loop 3501: Loss: 4.63e-02, Avg Return: 0.836, Regret: 0.0305, Entropy: 0.2720 +[2026-03-20T18:13:47.340650Z] Loop 3502: Loss: 4.51e-02, Avg Return: 0.837, Regret: 0.0305, Entropy: 0.2603 +[2026-03-20T18:13:48.194613Z] Loop 3503: Loss: 4.47e-02, Avg Return: 0.836, Regret: 0.0305, Entropy: 0.2501 +[2026-03-20T18:13:49.049196Z] Loop 3504: Loss: 4.67e-02, Avg Return: 0.833, Regret: 0.0305, Entropy: 0.2563 +[2026-03-20T18:13:49.903599Z] Loop 3505: Loss: 4.58e-02, Avg Return: 0.831, Regret: 0.0305, Entropy: 0.2508 +[2026-03-20T18:13:50.758115Z] Loop 3506: Loss: 4.38e-02, Avg Return: 0.827, Regret: 0.0305, Entropy: 0.2460 +[2026-03-20T18:13:51.612244Z] Loop 3507: Loss: 4.67e-02, Avg Return: 0.829, Regret: 0.0305, Entropy: 0.2553 +[2026-03-20T18:13:52.466457Z] Loop 3508: Loss: 4.49e-02, Avg Return: 0.834, Regret: 0.0305, Entropy: 0.2536 +[2026-03-20T18:13:53.319704Z] Loop 3509: Loss: 4.52e-02, Avg Return: 0.837, Regret: 0.0305, Entropy: 0.2558 +[2026-03-20T18:13:54.211888Z] Loop 3510: Loss: 4.58e-02, Avg Return: 0.841, Regret: 0.0229, Entropy: 0.2571 +[2026-03-20T18:13:55.064917Z] Loop 3511: Loss: 4.72e-02, Avg Return: 0.841, Regret: 0.0229, Entropy: 0.2626 +[2026-03-20T18:13:55.918358Z] Loop 3512: Loss: 4.56e-02, Avg Return: 0.840, Regret: 0.0229, Entropy: 0.2561 +[2026-03-20T18:13:56.772692Z] Loop 3513: Loss: 4.86e-02, Avg Return: 0.838, Regret: 0.0229, Entropy: 0.2647 +[2026-03-20T18:13:57.626798Z] Loop 3514: Loss: 4.90e-02, Avg Return: 0.834, Regret: 0.0229, Entropy: 0.2735 +[2026-03-20T18:13:58.479316Z] Loop 3515: Loss: 4.97e-02, Avg Return: 0.833, Regret: 0.0229, Entropy: 0.2737 +[2026-03-20T18:13:59.331967Z] Loop 3516: Loss: 4.82e-02, Avg Return: 0.832, Regret: 0.0229, Entropy: 0.2738 +[2026-03-20T18:14:00.184692Z] Loop 3517: Loss: 4.67e-02, Avg Return: 0.833, Regret: 0.0229, Entropy: 0.2619 +[2026-03-20T18:14:01.038714Z] Loop 3518: Loss: 4.52e-02, Avg Return: 0.838, Regret: 0.0229, Entropy: 0.2478 +[2026-03-20T18:14:01.892463Z] Loop 3519: Loss: 4.66e-02, Avg Return: 0.841, Regret: 0.0229, Entropy: 0.2560 +[2026-03-20T18:14:02.787476Z] Loop 3520: Loss: 4.54e-02, Avg Return: 0.842, Regret: 0.0216, Entropy: 0.2467 +[2026-03-20T18:14:03.641226Z] Loop 3521: Loss: 4.15e-02, Avg Return: 0.842, Regret: 0.0216, Entropy: 0.2335 +[2026-03-20T18:14:04.496162Z] Loop 3522: Loss: 4.42e-02, Avg Return: 0.843, Regret: 0.0216, Entropy: 0.2465 +[2026-03-20T18:14:05.350365Z] Loop 3523: Loss: 4.55e-02, Avg Return: 0.842, Regret: 0.0216, Entropy: 0.2454 +[2026-03-20T18:14:06.203393Z] Loop 3524: Loss: 4.33e-02, Avg Return: 0.844, Regret: 0.0216, Entropy: 0.2372 +[2026-03-20T18:14:07.056784Z] Loop 3525: Loss: 4.43e-02, Avg Return: 0.844, Regret: 0.0216, Entropy: 0.2477 +[2026-03-20T18:14:07.910929Z] Loop 3526: Loss: 4.05e-02, Avg Return: 0.844, Regret: 0.0216, Entropy: 0.2312 +[2026-03-20T18:14:08.765017Z] Loop 3527: Loss: 4.28e-02, Avg Return: 0.844, Regret: 0.0216, Entropy: 0.2367 +[2026-03-20T18:14:09.617686Z] Loop 3528: Loss: 3.81e-02, Avg Return: 0.844, Regret: 0.0216, Entropy: 0.2229 +[2026-03-20T18:14:10.471019Z] Loop 3529: Loss: 4.24e-02, Avg Return: 0.844, Regret: 0.0216, Entropy: 0.2372 +[2026-03-20T18:14:11.366318Z] Loop 3530: Loss: 4.06e-02, Avg Return: 0.844, Regret: 0.0200, Entropy: 0.2338 +[2026-03-20T18:14:12.220342Z] Loop 3531: Loss: 3.96e-02, Avg Return: 0.842, Regret: 0.0200, Entropy: 0.2302 +[2026-03-20T18:14:13.074729Z] Loop 3532: Loss: 3.95e-02, Avg Return: 0.840, Regret: 0.0200, Entropy: 0.2332 +[2026-03-20T18:14:13.928854Z] Loop 3533: Loss: 3.87e-02, Avg Return: 0.842, Regret: 0.0200, Entropy: 0.2294 +[2026-03-20T18:14:14.782991Z] Loop 3534: Loss: 3.98e-02, Avg Return: 0.841, Regret: 0.0200, Entropy: 0.2355 +[2026-03-20T18:14:15.636979Z] Loop 3535: Loss: 4.16e-02, Avg Return: 0.842, Regret: 0.0200, Entropy: 0.2340 +[2026-03-20T18:14:16.489955Z] Loop 3536: Loss: 4.05e-02, Avg Return: 0.843, Regret: 0.0200, Entropy: 0.2340 +[2026-03-20T18:14:17.343256Z] Loop 3537: Loss: 4.00e-02, Avg Return: 0.841, Regret: 0.0200, Entropy: 0.2301 +[2026-03-20T18:14:18.194990Z] Loop 3538: Loss: 4.04e-02, Avg Return: 0.840, Regret: 0.0200, Entropy: 0.2294 +[2026-03-20T18:14:19.048023Z] Loop 3539: Loss: 4.37e-02, Avg Return: 0.842, Regret: 0.0200, Entropy: 0.2367 +[2026-03-20T18:14:19.942901Z] Loop 3540: Loss: 4.27e-02, Avg Return: 0.841, Regret: 0.0217, Entropy: 0.2320 +[2026-03-20T18:14:20.796342Z] Loop 3541: Loss: 4.31e-02, Avg Return: 0.843, Regret: 0.0217, Entropy: 0.2387 +[2026-03-20T18:14:21.648837Z] Loop 3542: Loss: 4.55e-02, Avg Return: 0.845, Regret: 0.0217, Entropy: 0.2463 +[2026-03-20T18:14:22.502380Z] Loop 3543: Loss: 4.55e-02, Avg Return: 0.845, Regret: 0.0217, Entropy: 0.2481 +[2026-03-20T18:14:23.355762Z] Loop 3544: Loss: 4.41e-02, Avg Return: 0.846, Regret: 0.0217, Entropy: 0.2547 +[2026-03-20T18:14:24.209367Z] Loop 3545: Loss: 4.62e-02, Avg Return: 0.845, Regret: 0.0217, Entropy: 0.2616 +[2026-03-20T18:14:25.062533Z] Loop 3546: Loss: 4.52e-02, Avg Return: 0.844, Regret: 0.0217, Entropy: 0.2609 +[2026-03-20T18:14:25.915921Z] Loop 3547: Loss: 4.65e-02, Avg Return: 0.845, Regret: 0.0217, Entropy: 0.2664 +[2026-03-20T18:14:26.768970Z] Loop 3548: Loss: 4.75e-02, Avg Return: 0.844, Regret: 0.0217, Entropy: 0.2629 +[2026-03-20T18:14:27.622930Z] Loop 3549: Loss: 4.90e-02, Avg Return: 0.842, Regret: 0.0217, Entropy: 0.2701 +[2026-03-20T18:14:28.516725Z] Loop 3550: Loss: 4.81e-02, Avg Return: 0.841, Regret: 0.0216, Entropy: 0.2721 +[2026-03-20T18:14:29.370349Z] Loop 3551: Loss: 4.87e-02, Avg Return: 0.839, Regret: 0.0216, Entropy: 0.2699 +[2026-03-20T18:14:30.224216Z] Loop 3552: Loss: 4.68e-02, Avg Return: 0.841, Regret: 0.0216, Entropy: 0.2604 +[2026-03-20T18:14:31.078657Z] Loop 3553: Loss: 4.74e-02, Avg Return: 0.840, Regret: 0.0216, Entropy: 0.2624 +[2026-03-20T18:14:31.931784Z] Loop 3554: Loss: 4.35e-02, Avg Return: 0.842, Regret: 0.0216, Entropy: 0.2386 +[2026-03-20T18:14:32.785862Z] Loop 3555: Loss: 4.39e-02, Avg Return: 0.842, Regret: 0.0216, Entropy: 0.2420 +[2026-03-20T18:14:33.639934Z] Loop 3556: Loss: 4.13e-02, Avg Return: 0.845, Regret: 0.0216, Entropy: 0.2322 +[2026-03-20T18:14:34.494825Z] Loop 3557: Loss: 3.98e-02, Avg Return: 0.845, Regret: 0.0216, Entropy: 0.2253 +[2026-03-20T18:14:35.349390Z] Loop 3558: Loss: 3.94e-02, Avg Return: 0.846, Regret: 0.0216, Entropy: 0.2244 +[2026-03-20T18:14:36.203496Z] Loop 3559: Loss: 3.95e-02, Avg Return: 0.847, Regret: 0.0216, Entropy: 0.2196 +[2026-03-20T18:14:37.100525Z] Loop 3560: Loss: 4.20e-02, Avg Return: 0.843, Regret: 0.0205, Entropy: 0.2372 +[2026-03-20T18:14:37.953097Z] Loop 3561: Loss: 3.94e-02, Avg Return: 0.842, Regret: 0.0205, Entropy: 0.2327 +[2026-03-20T18:14:38.806608Z] Loop 3562: Loss: 4.11e-02, Avg Return: 0.840, Regret: 0.0205, Entropy: 0.2334 +[2026-03-20T18:14:39.660745Z] Loop 3563: Loss: 3.98e-02, Avg Return: 0.841, Regret: 0.0205, Entropy: 0.2325 +[2026-03-20T18:14:40.515155Z] Loop 3564: Loss: 3.78e-02, Avg Return: 0.843, Regret: 0.0205, Entropy: 0.2123 +[2026-03-20T18:14:41.368201Z] Loop 3565: Loss: 3.78e-02, Avg Return: 0.845, Regret: 0.0205, Entropy: 0.2152 +[2026-03-20T18:14:42.221438Z] Loop 3566: Loss: 3.67e-02, Avg Return: 0.846, Regret: 0.0205, Entropy: 0.2096 +[2026-03-20T18:14:43.074233Z] Loop 3567: Loss: 3.72e-02, Avg Return: 0.847, Regret: 0.0205, Entropy: 0.2162 +[2026-03-20T18:14:43.926942Z] Loop 3568: Loss: 3.91e-02, Avg Return: 0.846, Regret: 0.0205, Entropy: 0.2178 +[2026-03-20T18:14:44.779402Z] Loop 3569: Loss: 3.97e-02, Avg Return: 0.845, Regret: 0.0205, Entropy: 0.2257 +[2026-03-20T18:14:45.673909Z] Loop 3570: Loss: 3.85e-02, Avg Return: 0.847, Regret: 0.0177, Entropy: 0.2255 +[2026-03-20T18:14:46.526828Z] Loop 3571: Loss: 3.87e-02, Avg Return: 0.848, Regret: 0.0177, Entropy: 0.2292 +[2026-03-20T18:14:47.381248Z] Loop 3572: Loss: 4.10e-02, Avg Return: 0.848, Regret: 0.0177, Entropy: 0.2332 +[2026-03-20T18:14:48.234544Z] Loop 3573: Loss: 3.98e-02, Avg Return: 0.847, Regret: 0.0177, Entropy: 0.2308 +[2026-03-20T18:14:49.088849Z] Loop 3574: Loss: 4.12e-02, Avg Return: 0.846, Regret: 0.0177, Entropy: 0.2401 +[2026-03-20T18:14:49.942436Z] Loop 3575: Loss: 4.29e-02, Avg Return: 0.843, Regret: 0.0177, Entropy: 0.2415 +[2026-03-20T18:14:50.796001Z] Loop 3576: Loss: 4.23e-02, Avg Return: 0.846, Regret: 0.0177, Entropy: 0.2396 +[2026-03-20T18:14:51.649134Z] Loop 3577: Loss: 4.14e-02, Avg Return: 0.847, Regret: 0.0177, Entropy: 0.2302 +[2026-03-20T18:14:52.501955Z] Loop 3578: Loss: 3.94e-02, Avg Return: 0.848, Regret: 0.0177, Entropy: 0.2203 +[2026-03-20T18:14:53.354654Z] Loop 3579: Loss: 3.92e-02, Avg Return: 0.847, Regret: 0.0177, Entropy: 0.2293 +[2026-03-20T18:14:54.249150Z] Loop 3580: Loss: 3.93e-02, Avg Return: 0.846, Regret: 0.0157, Entropy: 0.2263 +[2026-03-20T18:14:55.101700Z] Loop 3581: Loss: 3.87e-02, Avg Return: 0.847, Regret: 0.0157, Entropy: 0.2252 +[2026-03-20T18:14:55.955846Z] Loop 3582: Loss: 4.04e-02, Avg Return: 0.848, Regret: 0.0157, Entropy: 0.2248 +[2026-03-20T18:14:56.809199Z] Loop 3583: Loss: 3.89e-02, Avg Return: 0.844, Regret: 0.0157, Entropy: 0.2299 +[2026-03-20T18:14:57.663532Z] Loop 3584: Loss: 4.20e-02, Avg Return: 0.844, Regret: 0.0157, Entropy: 0.2329 +[2026-03-20T18:14:58.517957Z] Loop 3585: Loss: 4.21e-02, Avg Return: 0.843, Regret: 0.0157, Entropy: 0.2262 +[2026-03-20T18:14:59.371738Z] Loop 3586: Loss: 4.25e-02, Avg Return: 0.844, Regret: 0.0157, Entropy: 0.2365 +[2026-03-20T18:15:00.223458Z] Loop 3587: Loss: 4.09e-02, Avg Return: 0.846, Regret: 0.0157, Entropy: 0.2296 +[2026-03-20T18:15:01.075454Z] Loop 3588: Loss: 4.05e-02, Avg Return: 0.848, Regret: 0.0157, Entropy: 0.2313 +[2026-03-20T18:15:01.929824Z] Loop 3589: Loss: 4.08e-02, Avg Return: 0.848, Regret: 0.0157, Entropy: 0.2327 +[2026-03-20T18:15:02.825838Z] Loop 3590: Loss: 4.06e-02, Avg Return: 0.844, Regret: 0.0171, Entropy: 0.2285 +[2026-03-20T18:15:03.678672Z] Loop 3591: Loss: 4.02e-02, Avg Return: 0.844, Regret: 0.0171, Entropy: 0.2285 +[2026-03-20T18:15:04.531963Z] Loop 3592: Loss: 4.12e-02, Avg Return: 0.842, Regret: 0.0171, Entropy: 0.2273 +[2026-03-20T18:15:05.384843Z] Loop 3593: Loss: 3.95e-02, Avg Return: 0.845, Regret: 0.0171, Entropy: 0.2230 +[2026-03-20T18:15:06.238645Z] Loop 3594: Loss: 4.04e-02, Avg Return: 0.845, Regret: 0.0171, Entropy: 0.2292 +[2026-03-20T18:15:07.091530Z] Loop 3595: Loss: 3.94e-02, Avg Return: 0.846, Regret: 0.0171, Entropy: 0.2253 +[2026-03-20T18:15:07.943906Z] Loop 3596: Loss: 4.14e-02, Avg Return: 0.847, Regret: 0.0171, Entropy: 0.2355 +[2026-03-20T18:15:08.796193Z] Loop 3597: Loss: 3.89e-02, Avg Return: 0.848, Regret: 0.0171, Entropy: 0.2262 +[2026-03-20T18:15:09.649554Z] Loop 3598: Loss: 3.93e-02, Avg Return: 0.849, Regret: 0.0171, Entropy: 0.2249 +[2026-03-20T18:15:10.502159Z] Loop 3599: Loss: 3.82e-02, Avg Return: 0.849, Regret: 0.0171, Entropy: 0.2220 +[2026-03-20T18:15:11.396651Z] Loop 3600: Loss: 3.70e-02, Avg Return: 0.848, Regret: 0.0150, Entropy: 0.2139 +[2026-03-20T18:15:12.251897Z] Loop 3601: Loss: 4.11e-02, Avg Return: 0.846, Regret: 0.0150, Entropy: 0.2289 +[2026-03-20T18:15:13.105453Z] Loop 3602: Loss: 4.05e-02, Avg Return: 0.844, Regret: 0.0150, Entropy: 0.2229 +[2026-03-20T18:15:13.958465Z] Loop 3603: Loss: 4.18e-02, Avg Return: 0.846, Regret: 0.0150, Entropy: 0.2262 +[2026-03-20T18:15:14.813080Z] Loop 3604: Loss: 3.92e-02, Avg Return: 0.846, Regret: 0.0150, Entropy: 0.2224 +[2026-03-20T18:15:15.667407Z] Loop 3605: Loss: 3.89e-02, Avg Return: 0.849, Regret: 0.0150, Entropy: 0.2222 +[2026-03-20T18:15:16.521272Z] Loop 3606: Loss: 3.94e-02, Avg Return: 0.848, Regret: 0.0150, Entropy: 0.2256 +[2026-03-20T18:15:17.375165Z] Loop 3607: Loss: 4.09e-02, Avg Return: 0.848, Regret: 0.0150, Entropy: 0.2305 +[2026-03-20T18:15:18.229550Z] Loop 3608: Loss: 4.27e-02, Avg Return: 0.844, Regret: 0.0150, Entropy: 0.2321 +[2026-03-20T18:15:19.083795Z] Loop 3609: Loss: 3.89e-02, Avg Return: 0.847, Regret: 0.0150, Entropy: 0.2253 +[2026-03-20T18:15:19.978726Z] Loop 3610: Loss: 3.91e-02, Avg Return: 0.850, Regret: 0.0144, Entropy: 0.2245 +[2026-03-20T18:15:20.831558Z] Loop 3611: Loss: 3.86e-02, Avg Return: 0.848, Regret: 0.0144, Entropy: 0.2164 +[2026-03-20T18:15:21.685361Z] Loop 3612: Loss: 3.94e-02, Avg Return: 0.849, Regret: 0.0144, Entropy: 0.2140 +[2026-03-20T18:15:22.540007Z] Loop 3613: Loss: 3.76e-02, Avg Return: 0.849, Regret: 0.0144, Entropy: 0.2127 +[2026-03-20T18:15:23.392725Z] Loop 3614: Loss: 3.75e-02, Avg Return: 0.849, Regret: 0.0144, Entropy: 0.2112 +[2026-03-20T18:15:24.246037Z] Loop 3615: Loss: 3.97e-02, Avg Return: 0.850, Regret: 0.0144, Entropy: 0.2161 +[2026-03-20T18:15:25.099978Z] Loop 3616: Loss: 3.63e-02, Avg Return: 0.849, Regret: 0.0144, Entropy: 0.2043 +[2026-03-20T18:15:25.954996Z] Loop 3617: Loss: 4.11e-02, Avg Return: 0.849, Regret: 0.0144, Entropy: 0.2155 +[2026-03-20T18:15:26.808838Z] Loop 3618: Loss: 3.78e-02, Avg Return: 0.848, Regret: 0.0144, Entropy: 0.2084 +[2026-03-20T18:15:27.662260Z] Loop 3619: Loss: 3.81e-02, Avg Return: 0.849, Regret: 0.0144, Entropy: 0.2043 +[2026-03-20T18:15:28.557246Z] Loop 3620: Loss: 3.59e-02, Avg Return: 0.848, Regret: 0.0149, Entropy: 0.2012 +[2026-03-20T18:15:29.411996Z] Loop 3621: Loss: 3.72e-02, Avg Return: 0.848, Regret: 0.0149, Entropy: 0.2083 +[2026-03-20T18:15:30.265675Z] Loop 3622: Loss: 3.79e-02, Avg Return: 0.849, Regret: 0.0149, Entropy: 0.2151 +[2026-03-20T18:15:31.119653Z] Loop 3623: Loss: 3.71e-02, Avg Return: 0.849, Regret: 0.0149, Entropy: 0.2168 +[2026-03-20T18:15:31.973448Z] Loop 3624: Loss: 3.74e-02, Avg Return: 0.849, Regret: 0.0149, Entropy: 0.2132 +[2026-03-20T18:15:32.827258Z] Loop 3625: Loss: 3.77e-02, Avg Return: 0.851, Regret: 0.0149, Entropy: 0.2103 +[2026-03-20T18:15:33.681003Z] Loop 3626: Loss: 3.69e-02, Avg Return: 0.850, Regret: 0.0149, Entropy: 0.1987 +[2026-03-20T18:15:34.534182Z] Loop 3627: Loss: 3.50e-02, Avg Return: 0.849, Regret: 0.0149, Entropy: 0.2093 +[2026-03-20T18:15:35.386181Z] Loop 3628: Loss: 3.74e-02, Avg Return: 0.850, Regret: 0.0149, Entropy: 0.2040 +[2026-03-20T18:15:36.238836Z] Loop 3629: Loss: 3.52e-02, Avg Return: 0.850, Regret: 0.0149, Entropy: 0.1988 +[2026-03-20T18:15:37.132931Z] Loop 3630: Loss: 3.71e-02, Avg Return: 0.849, Regret: 0.0148, Entropy: 0.2039 +[2026-03-20T18:15:37.985959Z] Loop 3631: Loss: 3.80e-02, Avg Return: 0.851, Regret: 0.0148, Entropy: 0.2106 +[2026-03-20T18:15:38.838879Z] Loop 3632: Loss: 3.51e-02, Avg Return: 0.851, Regret: 0.0148, Entropy: 0.1979 +[2026-03-20T18:15:39.692086Z] Loop 3633: Loss: 3.69e-02, Avg Return: 0.849, Regret: 0.0148, Entropy: 0.2018 +[2026-03-20T18:15:40.544722Z] Loop 3634: Loss: 3.50e-02, Avg Return: 0.850, Regret: 0.0148, Entropy: 0.1971 +[2026-03-20T18:15:41.398578Z] Loop 3635: Loss: 3.66e-02, Avg Return: 0.850, Regret: 0.0148, Entropy: 0.2049 +[2026-03-20T18:15:42.252702Z] Loop 3636: Loss: 3.49e-02, Avg Return: 0.852, Regret: 0.0148, Entropy: 0.1946 +[2026-03-20T18:15:43.106649Z] Loop 3637: Loss: 3.52e-02, Avg Return: 0.853, Regret: 0.0148, Entropy: 0.1971 +[2026-03-20T18:15:43.961626Z] Loop 3638: Loss: 3.49e-02, Avg Return: 0.851, Regret: 0.0148, Entropy: 0.2021 +[2026-03-20T18:15:44.815542Z] Loop 3639: Loss: 3.44e-02, Avg Return: 0.852, Regret: 0.0148, Entropy: 0.1932 +[2026-03-20T18:15:45.714043Z] Loop 3640: Loss: 3.50e-02, Avg Return: 0.852, Regret: 0.0126, Entropy: 0.1961 +[2026-03-20T18:15:46.568141Z] Loop 3641: Loss: 3.62e-02, Avg Return: 0.850, Regret: 0.0126, Entropy: 0.1961 +[2026-03-20T18:15:47.422274Z] Loop 3642: Loss: 3.62e-02, Avg Return: 0.851, Regret: 0.0126, Entropy: 0.2089 +[2026-03-20T18:15:48.275931Z] Loop 3643: Loss: 3.46e-02, Avg Return: 0.851, Regret: 0.0126, Entropy: 0.2032 +[2026-03-20T18:15:49.129984Z] Loop 3644: Loss: 3.60e-02, Avg Return: 0.850, Regret: 0.0126, Entropy: 0.2070 +[2026-03-20T18:15:49.984095Z] Loop 3645: Loss: 3.57e-02, Avg Return: 0.852, Regret: 0.0126, Entropy: 0.2030 +[2026-03-20T18:15:50.837035Z] Loop 3646: Loss: 3.83e-02, Avg Return: 0.852, Regret: 0.0126, Entropy: 0.2137 +[2026-03-20T18:15:51.690307Z] Loop 3647: Loss: 3.86e-02, Avg Return: 0.850, Regret: 0.0126, Entropy: 0.2169 +[2026-03-20T18:15:52.543982Z] Loop 3648: Loss: 3.87e-02, Avg Return: 0.849, Regret: 0.0126, Entropy: 0.2166 +[2026-03-20T18:15:53.398380Z] Loop 3649: Loss: 3.94e-02, Avg Return: 0.849, Regret: 0.0126, Entropy: 0.2168 +[2026-03-20T18:15:54.293043Z] Loop 3650: Loss: 3.88e-02, Avg Return: 0.849, Regret: 0.0148, Entropy: 0.2199 +[2026-03-20T18:15:55.146349Z] Loop 3651: Loss: 3.81e-02, Avg Return: 0.849, Regret: 0.0148, Entropy: 0.2084 +[2026-03-20T18:15:56.000739Z] Loop 3652: Loss: 3.78e-02, Avg Return: 0.849, Regret: 0.0148, Entropy: 0.2129 +[2026-03-20T18:15:56.855837Z] Loop 3653: Loss: 3.69e-02, Avg Return: 0.848, Regret: 0.0148, Entropy: 0.2056 +[2026-03-20T18:15:57.709353Z] Loop 3654: Loss: 3.80e-02, Avg Return: 0.846, Regret: 0.0148, Entropy: 0.2114 +[2026-03-20T18:15:58.561980Z] Loop 3655: Loss: 3.96e-02, Avg Return: 0.847, Regret: 0.0148, Entropy: 0.2137 +[2026-03-20T18:15:59.414772Z] Loop 3656: Loss: 3.77e-02, Avg Return: 0.846, Regret: 0.0148, Entropy: 0.2173 +[2026-03-20T18:16:00.268768Z] Loop 3657: Loss: 3.49e-02, Avg Return: 0.848, Regret: 0.0148, Entropy: 0.1957 +[2026-03-20T18:16:01.121797Z] Loop 3658: Loss: 3.81e-02, Avg Return: 0.851, Regret: 0.0148, Entropy: 0.2074 +[2026-03-20T18:16:01.974629Z] Loop 3659: Loss: 3.49e-02, Avg Return: 0.850, Regret: 0.0148, Entropy: 0.2056 +[2026-03-20T18:16:02.870936Z] Loop 3660: Loss: 3.45e-02, Avg Return: 0.852, Regret: 0.0126, Entropy: 0.1983 +[2026-03-20T18:16:03.724579Z] Loop 3661: Loss: 3.50e-02, Avg Return: 0.852, Regret: 0.0126, Entropy: 0.1957 +[2026-03-20T18:16:04.579455Z] Loop 3662: Loss: 3.34e-02, Avg Return: 0.853, Regret: 0.0126, Entropy: 0.1938 +[2026-03-20T18:16:05.433127Z] Loop 3663: Loss: 3.39e-02, Avg Return: 0.851, Regret: 0.0126, Entropy: 0.1924 +[2026-03-20T18:16:06.286344Z] Loop 3664: Loss: 3.35e-02, Avg Return: 0.851, Regret: 0.0126, Entropy: 0.1917 +[2026-03-20T18:16:07.140395Z] Loop 3665: Loss: 3.54e-02, Avg Return: 0.852, Regret: 0.0126, Entropy: 0.1979 +[2026-03-20T18:16:07.995047Z] Loop 3666: Loss: 3.31e-02, Avg Return: 0.849, Regret: 0.0126, Entropy: 0.1874 +[2026-03-20T18:16:08.849051Z] Loop 3667: Loss: 3.31e-02, Avg Return: 0.849, Regret: 0.0126, Entropy: 0.1919 +[2026-03-20T18:16:09.702465Z] Loop 3668: Loss: 3.31e-02, Avg Return: 0.850, Regret: 0.0126, Entropy: 0.1873 +[2026-03-20T18:16:10.557462Z] Loop 3669: Loss: 3.49e-02, Avg Return: 0.851, Regret: 0.0126, Entropy: 0.1891 +[2026-03-20T18:16:11.450986Z] Loop 3670: Loss: 3.29e-02, Avg Return: 0.852, Regret: 0.0117, Entropy: 0.1889 +[2026-03-20T18:16:12.305607Z] Loop 3671: Loss: 3.28e-02, Avg Return: 0.854, Regret: 0.0117, Entropy: 0.1835 +[2026-03-20T18:16:13.160286Z] Loop 3672: Loss: 3.67e-02, Avg Return: 0.852, Regret: 0.0117, Entropy: 0.1979 +[2026-03-20T18:16:14.014133Z] Loop 3673: Loss: 3.39e-02, Avg Return: 0.849, Regret: 0.0117, Entropy: 0.1912 +[2026-03-20T18:16:14.868098Z] Loop 3674: Loss: 3.49e-02, Avg Return: 0.848, Regret: 0.0117, Entropy: 0.1978 +[2026-03-20T18:16:15.721928Z] Loop 3675: Loss: 3.81e-02, Avg Return: 0.847, Regret: 0.0117, Entropy: 0.2085 +[2026-03-20T18:16:16.575629Z] Loop 3676: Loss: 3.68e-02, Avg Return: 0.845, Regret: 0.0117, Entropy: 0.2103 +[2026-03-20T18:16:17.430341Z] Loop 3677: Loss: 3.64e-02, Avg Return: 0.845, Regret: 0.0117, Entropy: 0.2019 +[2026-03-20T18:16:18.283690Z] Loop 3678: Loss: 3.57e-02, Avg Return: 0.846, Regret: 0.0117, Entropy: 0.1996 +[2026-03-20T18:16:19.138003Z] Loop 3679: Loss: 3.56e-02, Avg Return: 0.850, Regret: 0.0117, Entropy: 0.1945 +[2026-03-20T18:16:20.031065Z] Loop 3680: Loss: 3.36e-02, Avg Return: 0.853, Regret: 0.0118, Entropy: 0.1890 +[2026-03-20T18:16:20.885168Z] Loop 3681: Loss: 3.34e-02, Avg Return: 0.853, Regret: 0.0118, Entropy: 0.1933 +[2026-03-20T18:16:21.738021Z] Loop 3682: Loss: 3.35e-02, Avg Return: 0.851, Regret: 0.0118, Entropy: 0.1938 +[2026-03-20T18:16:22.591146Z] Loop 3683: Loss: 3.82e-02, Avg Return: 0.846, Regret: 0.0118, Entropy: 0.2071 +[2026-03-20T18:16:23.445493Z] Loop 3684: Loss: 3.77e-02, Avg Return: 0.847, Regret: 0.0118, Entropy: 0.2165 +[2026-03-20T18:16:24.298812Z] Loop 3685: Loss: 3.44e-02, Avg Return: 0.848, Regret: 0.0118, Entropy: 0.2000 +[2026-03-20T18:16:25.151582Z] Loop 3686: Loss: 3.39e-02, Avg Return: 0.853, Regret: 0.0118, Entropy: 0.1925 +[2026-03-20T18:16:26.005008Z] Loop 3687: Loss: 3.50e-02, Avg Return: 0.852, Regret: 0.0118, Entropy: 0.1987 +[2026-03-20T18:16:26.858472Z] Loop 3688: Loss: 3.36e-02, Avg Return: 0.853, Regret: 0.0118, Entropy: 0.1909 +[2026-03-20T18:16:27.712039Z] Loop 3689: Loss: 3.42e-02, Avg Return: 0.851, Regret: 0.0118, Entropy: 0.1897 +[2026-03-20T18:16:28.605717Z] Loop 3690: Loss: 3.28e-02, Avg Return: 0.851, Regret: 0.0120, Entropy: 0.1876 +[2026-03-20T18:16:29.457691Z] Loop 3691: Loss: 3.34e-02, Avg Return: 0.852, Regret: 0.0120, Entropy: 0.1950 +[2026-03-20T18:16:30.309881Z] Loop 3692: Loss: 3.60e-02, Avg Return: 0.852, Regret: 0.0120, Entropy: 0.1976 +[2026-03-20T18:16:31.163692Z] Loop 3693: Loss: 3.41e-02, Avg Return: 0.853, Regret: 0.0120, Entropy: 0.1944 +[2026-03-20T18:16:32.017481Z] Loop 3694: Loss: 3.53e-02, Avg Return: 0.854, Regret: 0.0120, Entropy: 0.1970 +[2026-03-20T18:16:32.871130Z] Loop 3695: Loss: 3.55e-02, Avg Return: 0.852, Regret: 0.0120, Entropy: 0.2012 +[2026-03-20T18:16:33.724951Z] Loop 3696: Loss: 3.94e-02, Avg Return: 0.849, Regret: 0.0120, Entropy: 0.2189 +[2026-03-20T18:16:34.579472Z] Loop 3697: Loss: 3.70e-02, Avg Return: 0.850, Regret: 0.0120, Entropy: 0.2064 +[2026-03-20T18:16:35.433289Z] Loop 3698: Loss: 3.66e-02, Avg Return: 0.853, Regret: 0.0120, Entropy: 0.2011 +[2026-03-20T18:16:36.287689Z] Loop 3699: Loss: 3.47e-02, Avg Return: 0.853, Regret: 0.0120, Entropy: 0.1966 +[2026-03-20T18:16:37.181209Z] Loop 3700: Loss: 3.22e-02, Avg Return: 0.853, Regret: 0.0101, Entropy: 0.1869 +[2026-03-20T18:16:38.034703Z] Loop 3701: Loss: 3.29e-02, Avg Return: 0.852, Regret: 0.0101, Entropy: 0.1828 +[2026-03-20T18:16:38.888411Z] Loop 3702: Loss: 3.24e-02, Avg Return: 0.849, Regret: 0.0101, Entropy: 0.1784 +[2026-03-20T18:16:39.742996Z] Loop 3703: Loss: 3.24e-02, Avg Return: 0.849, Regret: 0.0101, Entropy: 0.1808 +[2026-03-20T18:16:40.597241Z] Loop 3704: Loss: 3.36e-02, Avg Return: 0.852, Regret: 0.0101, Entropy: 0.1809 +[2026-03-20T18:16:41.450502Z] Loop 3705: Loss: 3.19e-02, Avg Return: 0.854, Regret: 0.0101, Entropy: 0.1838 +[2026-03-20T18:16:42.303761Z] Loop 3706: Loss: 3.40e-02, Avg Return: 0.853, Regret: 0.0101, Entropy: 0.1998 +[2026-03-20T18:16:43.156921Z] Loop 3707: Loss: 3.51e-02, Avg Return: 0.848, Regret: 0.0101, Entropy: 0.2011 +[2026-03-20T18:16:44.010761Z] Loop 3708: Loss: 3.40e-02, Avg Return: 0.852, Regret: 0.0101, Entropy: 0.1917 +[2026-03-20T18:16:44.863491Z] Loop 3709: Loss: 3.37e-02, Avg Return: 0.854, Regret: 0.0101, Entropy: 0.1912 +[2026-03-20T18:16:45.756160Z] Loop 3710: Loss: 3.27e-02, Avg Return: 0.853, Regret: 0.0114, Entropy: 0.1854 +[2026-03-20T18:16:46.609923Z] Loop 3711: Loss: 3.29e-02, Avg Return: 0.849, Regret: 0.0114, Entropy: 0.1834 +[2026-03-20T18:16:47.464420Z] Loop 3712: Loss: 3.33e-02, Avg Return: 0.850, Regret: 0.0114, Entropy: 0.1833 +[2026-03-20T18:16:48.318753Z] Loop 3713: Loss: 3.21e-02, Avg Return: 0.852, Regret: 0.0114, Entropy: 0.1762 +[2026-03-20T18:16:49.171711Z] Loop 3714: Loss: 3.14e-02, Avg Return: 0.853, Regret: 0.0114, Entropy: 0.1793 +[2026-03-20T18:16:50.024713Z] Loop 3715: Loss: 3.18e-02, Avg Return: 0.854, Regret: 0.0114, Entropy: 0.1869 +[2026-03-20T18:16:50.878635Z] Loop 3716: Loss: 3.29e-02, Avg Return: 0.855, Regret: 0.0114, Entropy: 0.1888 +[2026-03-20T18:16:51.732677Z] Loop 3717: Loss: 3.45e-02, Avg Return: 0.853, Regret: 0.0114, Entropy: 0.1989 +[2026-03-20T18:16:52.586117Z] Loop 3718: Loss: 3.54e-02, Avg Return: 0.853, Regret: 0.0114, Entropy: 0.1980 +[2026-03-20T18:16:53.439263Z] Loop 3719: Loss: 3.48e-02, Avg Return: 0.854, Regret: 0.0114, Entropy: 0.1975 +[2026-03-20T18:16:54.335680Z] Loop 3720: Loss: 3.43e-02, Avg Return: 0.853, Regret: 0.0106, Entropy: 0.1965 +[2026-03-20T18:16:55.188892Z] Loop 3721: Loss: 3.61e-02, Avg Return: 0.853, Regret: 0.0106, Entropy: 0.2008 +[2026-03-20T18:16:56.041613Z] Loop 3722: Loss: 3.44e-02, Avg Return: 0.854, Regret: 0.0106, Entropy: 0.1983 +[2026-03-20T18:16:56.895186Z] Loop 3723: Loss: 3.16e-02, Avg Return: 0.853, Regret: 0.0106, Entropy: 0.1895 +[2026-03-20T18:16:57.749444Z] Loop 3724: Loss: 3.20e-02, Avg Return: 0.852, Regret: 0.0106, Entropy: 0.1859 +[2026-03-20T18:16:58.603195Z] Loop 3725: Loss: 3.08e-02, Avg Return: 0.853, Regret: 0.0106, Entropy: 0.1819 +[2026-03-20T18:16:59.456707Z] Loop 3726: Loss: 3.04e-02, Avg Return: 0.852, Regret: 0.0106, Entropy: 0.1746 +[2026-03-20T18:17:00.309511Z] Loop 3727: Loss: 3.22e-02, Avg Return: 0.855, Regret: 0.0106, Entropy: 0.1859 +[2026-03-20T18:17:01.163339Z] Loop 3728: Loss: 2.91e-02, Avg Return: 0.852, Regret: 0.0106, Entropy: 0.1650 +[2026-03-20T18:17:02.016545Z] Loop 3729: Loss: 3.12e-02, Avg Return: 0.855, Regret: 0.0106, Entropy: 0.1766 +[2026-03-20T18:17:02.909854Z] Loop 3730: Loss: 3.12e-02, Avg Return: 0.855, Regret: 0.0100, Entropy: 0.1784 +[2026-03-20T18:17:03.763491Z] Loop 3731: Loss: 3.07e-02, Avg Return: 0.853, Regret: 0.0100, Entropy: 0.1776 +[2026-03-20T18:17:04.617277Z] Loop 3732: Loss: 3.32e-02, Avg Return: 0.852, Regret: 0.0100, Entropy: 0.1864 +[2026-03-20T18:17:05.471008Z] Loop 3733: Loss: 3.29e-02, Avg Return: 0.851, Regret: 0.0100, Entropy: 0.1868 +[2026-03-20T18:17:06.324280Z] Loop 3734: Loss: 3.40e-02, Avg Return: 0.851, Regret: 0.0100, Entropy: 0.1851 +[2026-03-20T18:17:07.177258Z] Loop 3735: Loss: 3.17e-02, Avg Return: 0.853, Regret: 0.0100, Entropy: 0.1812 +[2026-03-20T18:17:08.030393Z] Loop 3736: Loss: 3.05e-02, Avg Return: 0.854, Regret: 0.0100, Entropy: 0.1775 +[2026-03-20T18:17:08.883297Z] Loop 3737: Loss: 3.18e-02, Avg Return: 0.855, Regret: 0.0100, Entropy: 0.1775 +[2026-03-20T18:17:09.737331Z] Loop 3738: Loss: 2.96e-02, Avg Return: 0.853, Regret: 0.0100, Entropy: 0.1736 +[2026-03-20T18:17:10.592323Z] Loop 3739: Loss: 3.08e-02, Avg Return: 0.853, Regret: 0.0100, Entropy: 0.1740 +[2026-03-20T18:17:11.488803Z] Loop 3740: Loss: 3.21e-02, Avg Return: 0.854, Regret: 0.0110, Entropy: 0.1795 +[2026-03-20T18:17:12.341288Z] Loop 3741: Loss: 3.19e-02, Avg Return: 0.852, Regret: 0.0110, Entropy: 0.1814 +[2026-03-20T18:17:13.193770Z] Loop 3742: Loss: 3.25e-02, Avg Return: 0.852, Regret: 0.0110, Entropy: 0.1777 +[2026-03-20T18:17:14.047368Z] Loop 3743: Loss: 3.27e-02, Avg Return: 0.852, Regret: 0.0110, Entropy: 0.1791 +[2026-03-20T18:17:14.900962Z] Loop 3744: Loss: 3.23e-02, Avg Return: 0.851, Regret: 0.0110, Entropy: 0.1747 +[2026-03-20T18:17:15.753933Z] Loop 3745: Loss: 3.18e-02, Avg Return: 0.853, Regret: 0.0110, Entropy: 0.1853 +[2026-03-20T18:17:16.606639Z] Loop 3746: Loss: 3.04e-02, Avg Return: 0.852, Regret: 0.0110, Entropy: 0.1760 +[2026-03-20T18:17:17.459933Z] Loop 3747: Loss: 3.26e-02, Avg Return: 0.851, Regret: 0.0110, Entropy: 0.1881 +[2026-03-20T18:17:18.313823Z] Loop 3748: Loss: 3.34e-02, Avg Return: 0.849, Regret: 0.0110, Entropy: 0.1906 +[2026-03-20T18:17:19.166722Z] Loop 3749: Loss: 3.38e-02, Avg Return: 0.849, Regret: 0.0110, Entropy: 0.1900 +[2026-03-20T18:17:20.060513Z] Loop 3750: Loss: 3.64e-02, Avg Return: 0.847, Regret: 0.0154, Entropy: 0.1941 +[2026-03-20T18:17:20.913634Z] Loop 3751: Loss: 3.30e-02, Avg Return: 0.850, Regret: 0.0154, Entropy: 0.1928 +[2026-03-20T18:17:21.768991Z] Loop 3752: Loss: 3.28e-02, Avg Return: 0.851, Regret: 0.0154, Entropy: 0.1853 +[2026-03-20T18:17:22.622757Z] Loop 3753: Loss: 3.07e-02, Avg Return: 0.853, Regret: 0.0154, Entropy: 0.1779 +[2026-03-20T18:17:23.475806Z] Loop 3754: Loss: 3.06e-02, Avg Return: 0.853, Regret: 0.0154, Entropy: 0.1763 +[2026-03-20T18:17:24.328870Z] Loop 3755: Loss: 3.11e-02, Avg Return: 0.851, Regret: 0.0154, Entropy: 0.1689 +[2026-03-20T18:17:25.182774Z] Loop 3756: Loss: 3.01e-02, Avg Return: 0.852, Regret: 0.0154, Entropy: 0.1618 +[2026-03-20T18:17:26.036167Z] Loop 3757: Loss: 3.05e-02, Avg Return: 0.846, Regret: 0.0154, Entropy: 0.1691 +[2026-03-20T18:17:26.888852Z] Loop 3758: Loss: 3.14e-02, Avg Return: 0.845, Regret: 0.0154, Entropy: 0.1793 +[2026-03-20T18:17:27.741303Z] Loop 3759: Loss: 3.22e-02, Avg Return: 0.847, Regret: 0.0154, Entropy: 0.1811 +[2026-03-20T18:17:28.636676Z] Loop 3760: Loss: 3.32e-02, Avg Return: 0.849, Regret: 0.0142, Entropy: 0.1922 +[2026-03-20T18:17:29.491170Z] Loop 3761: Loss: 3.48e-02, Avg Return: 0.847, Regret: 0.0142, Entropy: 0.2022 +[2026-03-20T18:17:30.345785Z] Loop 3762: Loss: 3.66e-02, Avg Return: 0.843, Regret: 0.0142, Entropy: 0.2105 +[2026-03-20T18:17:31.199045Z] Loop 3763: Loss: 3.41e-02, Avg Return: 0.849, Regret: 0.0142, Entropy: 0.1969 +[2026-03-20T18:17:32.053427Z] Loop 3764: Loss: 3.17e-02, Avg Return: 0.855, Regret: 0.0142, Entropy: 0.1808 +[2026-03-20T18:17:32.908059Z] Loop 3765: Loss: 3.14e-02, Avg Return: 0.856, Regret: 0.0142, Entropy: 0.1730 +[2026-03-20T18:17:33.760888Z] Loop 3766: Loss: 3.06e-02, Avg Return: 0.855, Regret: 0.0142, Entropy: 0.1736 +[2026-03-20T18:17:34.613974Z] Loop 3767: Loss: 3.30e-02, Avg Return: 0.852, Regret: 0.0142, Entropy: 0.1798 +[2026-03-20T18:17:35.467072Z] Loop 3768: Loss: 3.17e-02, Avg Return: 0.849, Regret: 0.0142, Entropy: 0.1872 +[2026-03-20T18:17:36.320324Z] Loop 3769: Loss: 3.31e-02, Avg Return: 0.850, Regret: 0.0142, Entropy: 0.1855 +[2026-03-20T18:17:37.213828Z] Loop 3770: Loss: 3.20e-02, Avg Return: 0.851, Regret: 0.0134, Entropy: 0.1788 +[2026-03-20T18:17:38.068328Z] Loop 3771: Loss: 3.22e-02, Avg Return: 0.850, Regret: 0.0134, Entropy: 0.1802 +[2026-03-20T18:17:38.923412Z] Loop 3772: Loss: 3.33e-02, Avg Return: 0.850, Regret: 0.0134, Entropy: 0.1827 +[2026-03-20T18:17:39.778239Z] Loop 3773: Loss: 3.24e-02, Avg Return: 0.851, Regret: 0.0134, Entropy: 0.1802 +[2026-03-20T18:17:40.632562Z] Loop 3774: Loss: 3.19e-02, Avg Return: 0.854, Regret: 0.0134, Entropy: 0.1774 +[2026-03-20T18:17:41.485953Z] Loop 3775: Loss: 2.94e-02, Avg Return: 0.855, Regret: 0.0134, Entropy: 0.1712 +[2026-03-20T18:17:42.339409Z] Loop 3776: Loss: 3.05e-02, Avg Return: 0.854, Regret: 0.0134, Entropy: 0.1707 +[2026-03-20T18:17:43.192082Z] Loop 3777: Loss: 3.07e-02, Avg Return: 0.855, Regret: 0.0134, Entropy: 0.1761 +[2026-03-20T18:17:44.044587Z] Loop 3778: Loss: 3.04e-02, Avg Return: 0.854, Regret: 0.0134, Entropy: 0.1785 +[2026-03-20T18:17:44.898812Z] Loop 3779: Loss: 3.08e-02, Avg Return: 0.853, Regret: 0.0134, Entropy: 0.1777 +[2026-03-20T18:17:45.792879Z] Loop 3780: Loss: 3.14e-02, Avg Return: 0.851, Regret: 0.0116, Entropy: 0.1807 +[2026-03-20T18:17:46.647462Z] Loop 3781: Loss: 3.13e-02, Avg Return: 0.851, Regret: 0.0116, Entropy: 0.1819 +[2026-03-20T18:17:47.500992Z] Loop 3782: Loss: 3.31e-02, Avg Return: 0.851, Regret: 0.0116, Entropy: 0.1864 +[2026-03-20T18:17:48.355342Z] Loop 3783: Loss: 3.28e-02, Avg Return: 0.850, Regret: 0.0116, Entropy: 0.1790 +[2026-03-20T18:17:49.208902Z] Loop 3784: Loss: 3.13e-02, Avg Return: 0.853, Regret: 0.0116, Entropy: 0.1816 +[2026-03-20T18:17:50.061814Z] Loop 3785: Loss: 3.12e-02, Avg Return: 0.853, Regret: 0.0116, Entropy: 0.1869 +[2026-03-20T18:17:50.915160Z] Loop 3786: Loss: 3.08e-02, Avg Return: 0.853, Regret: 0.0116, Entropy: 0.1850 +[2026-03-20T18:17:51.769596Z] Loop 3787: Loss: 3.35e-02, Avg Return: 0.851, Regret: 0.0116, Entropy: 0.1911 +[2026-03-20T18:17:52.624515Z] Loop 3788: Loss: 3.21e-02, Avg Return: 0.853, Regret: 0.0116, Entropy: 0.1790 +[2026-03-20T18:17:53.478245Z] Loop 3789: Loss: 3.14e-02, Avg Return: 0.853, Regret: 0.0116, Entropy: 0.1843 +[2026-03-20T18:17:54.371305Z] Loop 3790: Loss: 3.08e-02, Avg Return: 0.855, Regret: 0.0090, Entropy: 0.1776 +[2026-03-20T18:17:55.225704Z] Loop 3791: Loss: 3.04e-02, Avg Return: 0.855, Regret: 0.0090, Entropy: 0.1734 +[2026-03-20T18:17:56.079885Z] Loop 3792: Loss: 2.84e-02, Avg Return: 0.854, Regret: 0.0090, Entropy: 0.1697 +[2026-03-20T18:17:56.933510Z] Loop 3793: Loss: 2.99e-02, Avg Return: 0.854, Regret: 0.0090, Entropy: 0.1668 +[2026-03-20T18:17:57.786922Z] Loop 3794: Loss: 3.17e-02, Avg Return: 0.852, Regret: 0.0090, Entropy: 0.1716 +[2026-03-20T18:17:58.640897Z] Loop 3795: Loss: 2.93e-02, Avg Return: 0.853, Regret: 0.0090, Entropy: 0.1686 +[2026-03-20T18:17:59.494254Z] Loop 3796: Loss: 2.90e-02, Avg Return: 0.854, Regret: 0.0090, Entropy: 0.1636 +[2026-03-20T18:18:00.348303Z] Loop 3797: Loss: 2.92e-02, Avg Return: 0.855, Regret: 0.0090, Entropy: 0.1610 +[2026-03-20T18:18:01.201384Z] Loop 3798: Loss: 2.74e-02, Avg Return: 0.856, Regret: 0.0090, Entropy: 0.1606 +[2026-03-20T18:18:02.055320Z] Loop 3799: Loss: 2.86e-02, Avg Return: 0.856, Regret: 0.0090, Entropy: 0.1738 +[2026-03-20T18:18:02.949147Z] Loop 3800: Loss: 3.07e-02, Avg Return: 0.855, Regret: 0.0085, Entropy: 0.1748 +[2026-03-20T18:18:03.803416Z] Loop 3801: Loss: 3.24e-02, Avg Return: 0.856, Regret: 0.0085, Entropy: 0.1794 +[2026-03-20T18:18:04.657907Z] Loop 3802: Loss: 3.08e-02, Avg Return: 0.855, Regret: 0.0085, Entropy: 0.1707 +[2026-03-20T18:18:05.512848Z] Loop 3803: Loss: 2.95e-02, Avg Return: 0.855, Regret: 0.0085, Entropy: 0.1683 +[2026-03-20T18:18:06.365234Z] Loop 3804: Loss: 2.94e-02, Avg Return: 0.855, Regret: 0.0085, Entropy: 0.1666 +[2026-03-20T18:18:07.217742Z] Loop 3805: Loss: 2.89e-02, Avg Return: 0.856, Regret: 0.0085, Entropy: 0.1599 +[2026-03-20T18:18:08.071099Z] Loop 3806: Loss: 2.83e-02, Avg Return: 0.857, Regret: 0.0085, Entropy: 0.1622 +[2026-03-20T18:18:08.925489Z] Loop 3807: Loss: 2.97e-02, Avg Return: 0.856, Regret: 0.0085, Entropy: 0.1681 +[2026-03-20T18:18:09.778653Z] Loop 3808: Loss: 2.92e-02, Avg Return: 0.855, Regret: 0.0085, Entropy: 0.1661 +[2026-03-20T18:18:10.631321Z] Loop 3809: Loss: 2.67e-02, Avg Return: 0.856, Regret: 0.0085, Entropy: 0.1573 +[2026-03-20T18:18:11.524653Z] Loop 3810: Loss: 2.86e-02, Avg Return: 0.856, Regret: 0.0074, Entropy: 0.1579 +[2026-03-20T18:18:12.379101Z] Loop 3811: Loss: 2.69e-02, Avg Return: 0.855, Regret: 0.0074, Entropy: 0.1594 +[2026-03-20T18:18:13.233989Z] Loop 3812: Loss: 2.91e-02, Avg Return: 0.855, Regret: 0.0074, Entropy: 0.1586 +[2026-03-20T18:18:14.086899Z] Loop 3813: Loss: 2.59e-02, Avg Return: 0.855, Regret: 0.0074, Entropy: 0.1512 +[2026-03-20T18:18:14.940131Z] Loop 3814: Loss: 2.80e-02, Avg Return: 0.853, Regret: 0.0074, Entropy: 0.1564 +[2026-03-20T18:18:15.794478Z] Loop 3815: Loss: 2.69e-02, Avg Return: 0.854, Regret: 0.0074, Entropy: 0.1490 +[2026-03-20T18:18:16.647751Z] Loop 3816: Loss: 2.84e-02, Avg Return: 0.854, Regret: 0.0074, Entropy: 0.1548 +[2026-03-20T18:18:17.501036Z] Loop 3817: Loss: 2.81e-02, Avg Return: 0.854, Regret: 0.0074, Entropy: 0.1591 +[2026-03-20T18:18:18.353598Z] Loop 3818: Loss: 3.00e-02, Avg Return: 0.851, Regret: 0.0074, Entropy: 0.1630 +[2026-03-20T18:18:19.207170Z] Loop 3819: Loss: 2.90e-02, Avg Return: 0.851, Regret: 0.0074, Entropy: 0.1644 +[2026-03-20T18:18:20.100312Z] Loop 3820: Loss: 2.78e-02, Avg Return: 0.853, Regret: 0.0113, Entropy: 0.1643 +[2026-03-20T18:18:20.953669Z] Loop 3821: Loss: 3.07e-02, Avg Return: 0.854, Regret: 0.0113, Entropy: 0.1705 +[2026-03-20T18:18:21.806078Z] Loop 3822: Loss: 2.86e-02, Avg Return: 0.854, Regret: 0.0113, Entropy: 0.1621 +[2026-03-20T18:18:22.659702Z] Loop 3823: Loss: 2.81e-02, Avg Return: 0.855, Regret: 0.0113, Entropy: 0.1637 +[2026-03-20T18:18:23.513229Z] Loop 3824: Loss: 2.95e-02, Avg Return: 0.853, Regret: 0.0113, Entropy: 0.1647 +[2026-03-20T18:18:24.366937Z] Loop 3825: Loss: 2.77e-02, Avg Return: 0.857, Regret: 0.0113, Entropy: 0.1584 +[2026-03-20T18:18:25.220767Z] Loop 3826: Loss: 2.73e-02, Avg Return: 0.855, Regret: 0.0113, Entropy: 0.1559 +[2026-03-20T18:18:26.075130Z] Loop 3827: Loss: 2.56e-02, Avg Return: 0.856, Regret: 0.0113, Entropy: 0.1555 +[2026-03-20T18:18:26.928878Z] Loop 3828: Loss: 2.86e-02, Avg Return: 0.856, Regret: 0.0113, Entropy: 0.1647 +[2026-03-20T18:18:27.782441Z] Loop 3829: Loss: 2.74e-02, Avg Return: 0.855, Regret: 0.0113, Entropy: 0.1612 +[2026-03-20T18:18:28.674769Z] Loop 3830: Loss: 2.97e-02, Avg Return: 0.854, Regret: 0.0108, Entropy: 0.1707 +[2026-03-20T18:18:29.528153Z] Loop 3831: Loss: 3.04e-02, Avg Return: 0.851, Regret: 0.0108, Entropy: 0.1743 +[2026-03-20T18:18:30.381577Z] Loop 3832: Loss: 3.13e-02, Avg Return: 0.851, Regret: 0.0108, Entropy: 0.1790 +[2026-03-20T18:18:31.234755Z] Loop 3833: Loss: 3.48e-02, Avg Return: 0.848, Regret: 0.0108, Entropy: 0.1881 +[2026-03-20T18:18:32.088363Z] Loop 3834: Loss: 3.20e-02, Avg Return: 0.850, Regret: 0.0108, Entropy: 0.1755 +[2026-03-20T18:18:32.942611Z] Loop 3835: Loss: 3.05e-02, Avg Return: 0.853, Regret: 0.0108, Entropy: 0.1738 +[2026-03-20T18:18:33.796733Z] Loop 3836: Loss: 3.00e-02, Avg Return: 0.856, Regret: 0.0108, Entropy: 0.1703 +[2026-03-20T18:18:34.650092Z] Loop 3837: Loss: 2.86e-02, Avg Return: 0.856, Regret: 0.0108, Entropy: 0.1628 +[2026-03-20T18:18:35.503846Z] Loop 3838: Loss: 2.91e-02, Avg Return: 0.855, Regret: 0.0108, Entropy: 0.1764 +[2026-03-20T18:18:36.357263Z] Loop 3839: Loss: 3.30e-02, Avg Return: 0.853, Regret: 0.0108, Entropy: 0.1894 +[2026-03-20T18:18:37.253990Z] Loop 3840: Loss: 3.18e-02, Avg Return: 0.853, Regret: 0.0103, Entropy: 0.1836 +[2026-03-20T18:18:38.106698Z] Loop 3841: Loss: 3.18e-02, Avg Return: 0.853, Regret: 0.0103, Entropy: 0.1783 +[2026-03-20T18:18:38.961039Z] Loop 3842: Loss: 3.15e-02, Avg Return: 0.853, Regret: 0.0103, Entropy: 0.1823 +[2026-03-20T18:18:39.815692Z] Loop 3843: Loss: 2.99e-02, Avg Return: 0.853, Regret: 0.0103, Entropy: 0.1792 +[2026-03-20T18:18:40.668854Z] Loop 3844: Loss: 3.21e-02, Avg Return: 0.852, Regret: 0.0103, Entropy: 0.1843 +[2026-03-20T18:18:41.521771Z] Loop 3845: Loss: 3.11e-02, Avg Return: 0.851, Regret: 0.0103, Entropy: 0.1788 +[2026-03-20T18:18:42.375430Z] Loop 3846: Loss: 3.07e-02, Avg Return: 0.854, Regret: 0.0103, Entropy: 0.1793 +[2026-03-20T18:18:43.229193Z] Loop 3847: Loss: 2.93e-02, Avg Return: 0.856, Regret: 0.0103, Entropy: 0.1681 +[2026-03-20T18:18:44.083267Z] Loop 3848: Loss: 2.87e-02, Avg Return: 0.855, Regret: 0.0103, Entropy: 0.1640 +[2026-03-20T18:18:44.935346Z] Loop 3849: Loss: 2.84e-02, Avg Return: 0.855, Regret: 0.0103, Entropy: 0.1645 +[2026-03-20T18:18:45.828313Z] Loop 3850: Loss: 2.89e-02, Avg Return: 0.855, Regret: 0.0080, Entropy: 0.1660 +[2026-03-20T18:18:46.681583Z] Loop 3851: Loss: 2.90e-02, Avg Return: 0.856, Regret: 0.0080, Entropy: 0.1627 +[2026-03-20T18:18:47.535188Z] Loop 3852: Loss: 2.71e-02, Avg Return: 0.856, Regret: 0.0080, Entropy: 0.1561 +[2026-03-20T18:18:48.388644Z] Loop 3853: Loss: 2.87e-02, Avg Return: 0.856, Regret: 0.0080, Entropy: 0.1649 +[2026-03-20T18:18:49.242278Z] Loop 3854: Loss: 2.94e-02, Avg Return: 0.856, Regret: 0.0080, Entropy: 0.1624 +[2026-03-20T18:18:50.095648Z] Loop 3855: Loss: 2.84e-02, Avg Return: 0.855, Regret: 0.0080, Entropy: 0.1574 +[2026-03-20T18:18:50.949331Z] Loop 3856: Loss: 2.81e-02, Avg Return: 0.857, Regret: 0.0080, Entropy: 0.1596 +[2026-03-20T18:18:51.802519Z] Loop 3857: Loss: 2.71e-02, Avg Return: 0.856, Regret: 0.0080, Entropy: 0.1586 +[2026-03-20T18:18:52.656065Z] Loop 3858: Loss: 2.89e-02, Avg Return: 0.856, Regret: 0.0080, Entropy: 0.1565 +[2026-03-20T18:18:53.508621Z] Loop 3859: Loss: 2.93e-02, Avg Return: 0.856, Regret: 0.0080, Entropy: 0.1607 +[2026-03-20T18:18:54.402395Z] Loop 3860: Loss: 3.03e-02, Avg Return: 0.855, Regret: 0.0078, Entropy: 0.1702 +[2026-03-20T18:18:55.257444Z] Loop 3861: Loss: 2.90e-02, Avg Return: 0.855, Regret: 0.0078, Entropy: 0.1648 +[2026-03-20T18:18:56.111753Z] Loop 3862: Loss: 2.92e-02, Avg Return: 0.857, Regret: 0.0078, Entropy: 0.1661 +[2026-03-20T18:18:56.965160Z] Loop 3863: Loss: 2.83e-02, Avg Return: 0.854, Regret: 0.0078, Entropy: 0.1679 +[2026-03-20T18:18:57.818843Z] Loop 3864: Loss: 3.02e-02, Avg Return: 0.852, Regret: 0.0078, Entropy: 0.1713 +[2026-03-20T18:18:58.672314Z] Loop 3865: Loss: 3.07e-02, Avg Return: 0.855, Regret: 0.0078, Entropy: 0.1686 +[2026-03-20T18:18:59.526540Z] Loop 3866: Loss: 2.99e-02, Avg Return: 0.857, Regret: 0.0078, Entropy: 0.1737 +[2026-03-20T18:19:00.379861Z] Loop 3867: Loss: 2.97e-02, Avg Return: 0.855, Regret: 0.0078, Entropy: 0.1731 +[2026-03-20T18:19:01.232528Z] Loop 3868: Loss: 2.88e-02, Avg Return: 0.855, Regret: 0.0078, Entropy: 0.1743 +[2026-03-20T18:19:02.085939Z] Loop 3869: Loss: 3.05e-02, Avg Return: 0.855, Regret: 0.0078, Entropy: 0.1765 +[2026-03-20T18:19:02.980697Z] Loop 3870: Loss: 3.02e-02, Avg Return: 0.853, Regret: 0.0102, Entropy: 0.1755 +[2026-03-20T18:19:03.834534Z] Loop 3871: Loss: 3.10e-02, Avg Return: 0.852, Regret: 0.0102, Entropy: 0.1769 +[2026-03-20T18:19:04.686300Z] Loop 3872: Loss: 3.13e-02, Avg Return: 0.850, Regret: 0.0102, Entropy: 0.1734 +[2026-03-20T18:19:05.538602Z] Loop 3873: Loss: 3.33e-02, Avg Return: 0.851, Regret: 0.0102, Entropy: 0.1809 +[2026-03-20T18:19:06.392193Z] Loop 3874: Loss: 3.38e-02, Avg Return: 0.851, Regret: 0.0102, Entropy: 0.1778 +[2026-03-20T18:19:07.246308Z] Loop 3875: Loss: 3.33e-02, Avg Return: 0.852, Regret: 0.0102, Entropy: 0.1809 +[2026-03-20T18:19:08.099144Z] Loop 3876: Loss: 3.15e-02, Avg Return: 0.853, Regret: 0.0102, Entropy: 0.1761 +[2026-03-20T18:19:08.951423Z] Loop 3877: Loss: 3.13e-02, Avg Return: 0.855, Regret: 0.0102, Entropy: 0.1736 +[2026-03-20T18:19:09.804396Z] Loop 3878: Loss: 3.17e-02, Avg Return: 0.855, Regret: 0.0102, Entropy: 0.1809 +[2026-03-20T18:19:10.658259Z] Loop 3879: Loss: 3.09e-02, Avg Return: 0.854, Regret: 0.0102, Entropy: 0.1771 +[2026-03-20T18:19:11.552365Z] Loop 3880: Loss: 3.34e-02, Avg Return: 0.853, Regret: 0.0108, Entropy: 0.1807 +[2026-03-20T18:19:12.405121Z] Loop 3881: Loss: 2.89e-02, Avg Return: 0.854, Regret: 0.0108, Entropy: 0.1673 +[2026-03-20T18:19:13.257725Z] Loop 3882: Loss: 2.90e-02, Avg Return: 0.857, Regret: 0.0108, Entropy: 0.1619 +[2026-03-20T18:19:14.110926Z] Loop 3883: Loss: 2.68e-02, Avg Return: 0.858, Regret: 0.0108, Entropy: 0.1543 +[2026-03-20T18:19:14.964926Z] Loop 3884: Loss: 2.85e-02, Avg Return: 0.855, Regret: 0.0108, Entropy: 0.1652 +[2026-03-20T18:19:15.818246Z] Loop 3885: Loss: 3.08e-02, Avg Return: 0.851, Regret: 0.0108, Entropy: 0.1664 +[2026-03-20T18:19:16.671573Z] Loop 3886: Loss: 3.01e-02, Avg Return: 0.850, Regret: 0.0108, Entropy: 0.1634 +[2026-03-20T18:19:17.524667Z] Loop 3887: Loss: 3.05e-02, Avg Return: 0.851, Regret: 0.0108, Entropy: 0.1615 +[2026-03-20T18:19:18.378262Z] Loop 3888: Loss: 3.17e-02, Avg Return: 0.851, Regret: 0.0108, Entropy: 0.1668 +[2026-03-20T18:19:19.231630Z] Loop 3889: Loss: 2.83e-02, Avg Return: 0.855, Regret: 0.0108, Entropy: 0.1563 +[2026-03-20T18:19:20.125214Z] Loop 3890: Loss: 2.90e-02, Avg Return: 0.856, Regret: 0.0077, Entropy: 0.1606 +[2026-03-20T18:19:20.979986Z] Loop 3891: Loss: 2.97e-02, Avg Return: 0.855, Regret: 0.0077, Entropy: 0.1678 +[2026-03-20T18:19:21.834099Z] Loop 3892: Loss: 3.02e-02, Avg Return: 0.855, Regret: 0.0077, Entropy: 0.1751 +[2026-03-20T18:19:22.688237Z] Loop 3893: Loss: 3.39e-02, Avg Return: 0.854, Regret: 0.0077, Entropy: 0.1874 +[2026-03-20T18:19:23.540951Z] Loop 3894: Loss: 3.22e-02, Avg Return: 0.854, Regret: 0.0077, Entropy: 0.1777 +[2026-03-20T18:19:24.395670Z] Loop 3895: Loss: 2.98e-02, Avg Return: 0.855, Regret: 0.0077, Entropy: 0.1656 +[2026-03-20T18:19:25.249199Z] Loop 3896: Loss: 2.97e-02, Avg Return: 0.857, Regret: 0.0077, Entropy: 0.1664 +[2026-03-20T18:19:26.102986Z] Loop 3897: Loss: 2.82e-02, Avg Return: 0.857, Regret: 0.0077, Entropy: 0.1578 +[2026-03-20T18:19:26.956274Z] Loop 3898: Loss: 2.76e-02, Avg Return: 0.857, Regret: 0.0077, Entropy: 0.1539 +[2026-03-20T18:19:27.809268Z] Loop 3899: Loss: 2.58e-02, Avg Return: 0.856, Regret: 0.0077, Entropy: 0.1515 +[2026-03-20T18:19:28.703760Z] Loop 3900: Loss: 2.58e-02, Avg Return: 0.855, Regret: 0.0068, Entropy: 0.1451 +[2026-03-20T18:19:29.557185Z] Loop 3901: Loss: 2.54e-02, Avg Return: 0.855, Regret: 0.0068, Entropy: 0.1407 +[2026-03-20T18:19:30.410374Z] Loop 3902: Loss: 2.57e-02, Avg Return: 0.856, Regret: 0.0068, Entropy: 0.1471 +[2026-03-20T18:19:31.263210Z] Loop 3903: Loss: 2.65e-02, Avg Return: 0.855, Regret: 0.0068, Entropy: 0.1469 +[2026-03-20T18:19:32.117809Z] Loop 3904: Loss: 2.53e-02, Avg Return: 0.854, Regret: 0.0068, Entropy: 0.1433 +[2026-03-20T18:19:32.971901Z] Loop 3905: Loss: 2.73e-02, Avg Return: 0.857, Regret: 0.0068, Entropy: 0.1522 +[2026-03-20T18:19:33.825763Z] Loop 3906: Loss: 2.84e-02, Avg Return: 0.854, Regret: 0.0068, Entropy: 0.1567 +[2026-03-20T18:19:34.678637Z] Loop 3907: Loss: 2.73e-02, Avg Return: 0.853, Regret: 0.0068, Entropy: 0.1538 +[2026-03-20T18:19:35.533117Z] Loop 3908: Loss: 2.94e-02, Avg Return: 0.850, Regret: 0.0068, Entropy: 0.1604 +[2026-03-20T18:19:36.386466Z] Loop 3909: Loss: 3.09e-02, Avg Return: 0.850, Regret: 0.0068, Entropy: 0.1661 +[2026-03-20T18:19:37.280499Z] Loop 3910: Loss: 3.07e-02, Avg Return: 0.849, Regret: 0.0135, Entropy: 0.1628 +[2026-03-20T18:19:38.134161Z] Loop 3911: Loss: 3.08e-02, Avg Return: 0.851, Regret: 0.0135, Entropy: 0.1649 +[2026-03-20T18:19:38.988444Z] Loop 3912: Loss: 2.81e-02, Avg Return: 0.853, Regret: 0.0135, Entropy: 0.1534 +[2026-03-20T18:19:39.841720Z] Loop 3913: Loss: 2.83e-02, Avg Return: 0.855, Regret: 0.0135, Entropy: 0.1561 +[2026-03-20T18:19:40.694857Z] Loop 3914: Loss: 2.68e-02, Avg Return: 0.856, Regret: 0.0135, Entropy: 0.1530 +[2026-03-20T18:19:41.548087Z] Loop 3915: Loss: 2.64e-02, Avg Return: 0.857, Regret: 0.0135, Entropy: 0.1505 +[2026-03-20T18:19:42.402242Z] Loop 3916: Loss: 2.75e-02, Avg Return: 0.856, Regret: 0.0135, Entropy: 0.1525 +[2026-03-20T18:19:43.254538Z] Loop 3917: Loss: 2.69e-02, Avg Return: 0.856, Regret: 0.0135, Entropy: 0.1560 +[2026-03-20T18:19:44.106893Z] Loop 3918: Loss: 2.78e-02, Avg Return: 0.854, Regret: 0.0135, Entropy: 0.1582 +[2026-03-20T18:19:44.960471Z] Loop 3919: Loss: 2.90e-02, Avg Return: 0.852, Regret: 0.0135, Entropy: 0.1654 +[2026-03-20T18:19:45.854609Z] Loop 3920: Loss: 2.94e-02, Avg Return: 0.850, Regret: 0.0133, Entropy: 0.1659 +[2026-03-20T18:19:46.708576Z] Loop 3921: Loss: 3.11e-02, Avg Return: 0.851, Regret: 0.0133, Entropy: 0.1730 +[2026-03-20T18:19:47.562866Z] Loop 3922: Loss: 2.79e-02, Avg Return: 0.854, Regret: 0.0133, Entropy: 0.1593 +[2026-03-20T18:19:48.417309Z] Loop 3923: Loss: 2.78e-02, Avg Return: 0.855, Regret: 0.0133, Entropy: 0.1547 +[2026-03-20T18:19:49.271049Z] Loop 3924: Loss: 2.75e-02, Avg Return: 0.857, Regret: 0.0133, Entropy: 0.1503 +[2026-03-20T18:19:50.125303Z] Loop 3925: Loss: 2.72e-02, Avg Return: 0.856, Regret: 0.0133, Entropy: 0.1483 +[2026-03-20T18:19:50.978846Z] Loop 3926: Loss: 2.77e-02, Avg Return: 0.855, Regret: 0.0133, Entropy: 0.1530 +[2026-03-20T18:19:51.832983Z] Loop 3927: Loss: 3.11e-02, Avg Return: 0.854, Regret: 0.0133, Entropy: 0.1618 +[2026-03-20T18:19:52.686722Z] Loop 3928: Loss: 3.00e-02, Avg Return: 0.853, Regret: 0.0133, Entropy: 0.1678 +[2026-03-20T18:19:53.540100Z] Loop 3929: Loss: 3.02e-02, Avg Return: 0.849, Regret: 0.0133, Entropy: 0.1633 +[2026-03-20T18:19:54.434691Z] Loop 3930: Loss: 3.47e-02, Avg Return: 0.847, Regret: 0.0155, Entropy: 0.1767 +[2026-03-20T18:19:55.288047Z] Loop 3931: Loss: 3.43e-02, Avg Return: 0.848, Regret: 0.0155, Entropy: 0.1832 +[2026-03-20T18:19:56.142353Z] Loop 3932: Loss: 3.26e-02, Avg Return: 0.849, Regret: 0.0155, Entropy: 0.1759 +[2026-03-20T18:19:56.995767Z] Loop 3933: Loss: 3.18e-02, Avg Return: 0.852, Regret: 0.0155, Entropy: 0.1681 +[2026-03-20T18:19:57.849120Z] Loop 3934: Loss: 2.89e-02, Avg Return: 0.853, Regret: 0.0155, Entropy: 0.1635 +[2026-03-20T18:19:58.703057Z] Loop 3935: Loss: 2.89e-02, Avg Return: 0.855, Regret: 0.0155, Entropy: 0.1610 +[2026-03-20T18:19:59.557068Z] Loop 3936: Loss: 2.86e-02, Avg Return: 0.856, Regret: 0.0155, Entropy: 0.1588 +[2026-03-20T18:20:00.410870Z] Loop 3937: Loss: 2.88e-02, Avg Return: 0.855, Regret: 0.0155, Entropy: 0.1611 +[2026-03-20T18:20:01.264140Z] Loop 3938: Loss: 2.72e-02, Avg Return: 0.857, Regret: 0.0155, Entropy: 0.1553 +[2026-03-20T18:20:02.117752Z] Loop 3939: Loss: 2.43e-02, Avg Return: 0.858, Regret: 0.0155, Entropy: 0.1451 +[2026-03-20T18:20:03.014399Z] Loop 3940: Loss: 2.65e-02, Avg Return: 0.857, Regret: 0.0065, Entropy: 0.1512 +[2026-03-20T18:20:03.870362Z] Loop 3941: Loss: 2.72e-02, Avg Return: 0.855, Regret: 0.0065, Entropy: 0.1538 +[2026-03-20T18:20:04.724750Z] Loop 3942: Loss: 2.55e-02, Avg Return: 0.856, Regret: 0.0065, Entropy: 0.1504 +[2026-03-20T18:20:05.579654Z] Loop 3943: Loss: 2.67e-02, Avg Return: 0.857, Regret: 0.0065, Entropy: 0.1503 +[2026-03-20T18:20:06.433883Z] Loop 3944: Loss: 2.60e-02, Avg Return: 0.858, Regret: 0.0065, Entropy: 0.1469 +[2026-03-20T18:20:07.289032Z] Loop 3945: Loss: 2.45e-02, Avg Return: 0.858, Regret: 0.0065, Entropy: 0.1435 +[2026-03-20T18:20:08.144097Z] Loop 3946: Loss: 2.52e-02, Avg Return: 0.859, Regret: 0.0065, Entropy: 0.1439 +[2026-03-20T18:20:08.997808Z] Loop 3947: Loss: 2.68e-02, Avg Return: 0.857, Regret: 0.0065, Entropy: 0.1512 +[2026-03-20T18:20:09.850487Z] Loop 3948: Loss: 2.72e-02, Avg Return: 0.855, Regret: 0.0065, Entropy: 0.1587 +[2026-03-20T18:20:10.704245Z] Loop 3949: Loss: 2.85e-02, Avg Return: 0.854, Regret: 0.0065, Entropy: 0.1603 +[2026-03-20T18:20:11.599861Z] Loop 3950: Loss: 2.95e-02, Avg Return: 0.853, Regret: 0.0099, Entropy: 0.1622 +[2026-03-20T18:20:12.453862Z] Loop 3951: Loss: 2.68e-02, Avg Return: 0.855, Regret: 0.0099, Entropy: 0.1603 +[2026-03-20T18:20:13.308413Z] Loop 3952: Loss: 2.86e-02, Avg Return: 0.856, Regret: 0.0099, Entropy: 0.1596 +[2026-03-20T18:20:14.162097Z] Loop 3953: Loss: 2.64e-02, Avg Return: 0.857, Regret: 0.0099, Entropy: 0.1537 +[2026-03-20T18:20:15.016198Z] Loop 3954: Loss: 2.49e-02, Avg Return: 0.857, Regret: 0.0099, Entropy: 0.1453 +[2026-03-20T18:20:15.869749Z] Loop 3955: Loss: 2.50e-02, Avg Return: 0.859, Regret: 0.0099, Entropy: 0.1477 +[2026-03-20T18:20:16.724430Z] Loop 3956: Loss: 2.63e-02, Avg Return: 0.856, Regret: 0.0099, Entropy: 0.1460 +[2026-03-20T18:20:17.578489Z] Loop 3957: Loss: 2.52e-02, Avg Return: 0.858, Regret: 0.0099, Entropy: 0.1463 +[2026-03-20T18:20:18.431607Z] Loop 3958: Loss: 2.62e-02, Avg Return: 0.857, Regret: 0.0099, Entropy: 0.1469 +[2026-03-20T18:20:19.286148Z] Loop 3959: Loss: 2.62e-02, Avg Return: 0.856, Regret: 0.0099, Entropy: 0.1474 +[2026-03-20T18:20:20.179299Z] Loop 3960: Loss: 2.54e-02, Avg Return: 0.855, Regret: 0.0073, Entropy: 0.1451 +[2026-03-20T18:20:21.033525Z] Loop 3961: Loss: 2.75e-02, Avg Return: 0.855, Regret: 0.0073, Entropy: 0.1503 +[2026-03-20T18:20:21.886310Z] Loop 3962: Loss: 2.73e-02, Avg Return: 0.855, Regret: 0.0073, Entropy: 0.1547 +[2026-03-20T18:20:22.738409Z] Loop 3963: Loss: 2.67e-02, Avg Return: 0.857, Regret: 0.0073, Entropy: 0.1532 +[2026-03-20T18:20:23.592864Z] Loop 3964: Loss: 2.77e-02, Avg Return: 0.858, Regret: 0.0073, Entropy: 0.1570 +[2026-03-20T18:20:24.447608Z] Loop 3965: Loss: 2.55e-02, Avg Return: 0.855, Regret: 0.0073, Entropy: 0.1517 +[2026-03-20T18:20:25.300773Z] Loop 3966: Loss: 2.66e-02, Avg Return: 0.855, Regret: 0.0073, Entropy: 0.1579 +[2026-03-20T18:20:26.153447Z] Loop 3967: Loss: 2.79e-02, Avg Return: 0.857, Regret: 0.0073, Entropy: 0.1596 +[2026-03-20T18:20:27.006131Z] Loop 3968: Loss: 2.51e-02, Avg Return: 0.859, Regret: 0.0073, Entropy: 0.1490 +[2026-03-20T18:20:27.860664Z] Loop 3969: Loss: 2.74e-02, Avg Return: 0.858, Regret: 0.0073, Entropy: 0.1567 +[2026-03-20T18:20:28.755550Z] Loop 3970: Loss: 2.60e-02, Avg Return: 0.858, Regret: 0.0069, Entropy: 0.1469 +[2026-03-20T18:20:29.608852Z] Loop 3971: Loss: 2.67e-02, Avg Return: 0.855, Regret: 0.0069, Entropy: 0.1492 +[2026-03-20T18:20:30.462953Z] Loop 3972: Loss: 2.66e-02, Avg Return: 0.855, Regret: 0.0069, Entropy: 0.1430 +[2026-03-20T18:20:31.317188Z] Loop 3973: Loss: 2.70e-02, Avg Return: 0.854, Regret: 0.0069, Entropy: 0.1536 +[2026-03-20T18:20:32.172377Z] Loop 3974: Loss: 2.71e-02, Avg Return: 0.854, Regret: 0.0069, Entropy: 0.1495 +[2026-03-20T18:20:33.027391Z] Loop 3975: Loss: 2.90e-02, Avg Return: 0.855, Regret: 0.0069, Entropy: 0.1535 +[2026-03-20T18:20:33.880789Z] Loop 3976: Loss: 2.66e-02, Avg Return: 0.855, Regret: 0.0069, Entropy: 0.1447 +[2026-03-20T18:20:34.735415Z] Loop 3977: Loss: 2.65e-02, Avg Return: 0.855, Regret: 0.0069, Entropy: 0.1468 +[2026-03-20T18:20:35.590740Z] Loop 3978: Loss: 2.66e-02, Avg Return: 0.856, Regret: 0.0069, Entropy: 0.1537 +[2026-03-20T18:20:36.446996Z] Loop 3979: Loss: 2.77e-02, Avg Return: 0.856, Regret: 0.0069, Entropy: 0.1570 +[2026-03-20T18:20:37.343173Z] Loop 3980: Loss: 3.01e-02, Avg Return: 0.855, Regret: 0.0089, Entropy: 0.1702 +[2026-03-20T18:20:38.198537Z] Loop 3981: Loss: 3.06e-02, Avg Return: 0.850, Regret: 0.0089, Entropy: 0.1728 +[2026-03-20T18:20:39.053623Z] Loop 3982: Loss: 3.12e-02, Avg Return: 0.847, Regret: 0.0089, Entropy: 0.1773 +[2026-03-20T18:20:39.908468Z] Loop 3983: Loss: 2.84e-02, Avg Return: 0.850, Regret: 0.0089, Entropy: 0.1652 +[2026-03-20T18:20:40.763960Z] Loop 3984: Loss: 2.70e-02, Avg Return: 0.854, Regret: 0.0089, Entropy: 0.1585 +[2026-03-20T18:20:41.618343Z] Loop 3985: Loss: 2.50e-02, Avg Return: 0.856, Regret: 0.0089, Entropy: 0.1427 +[2026-03-20T18:20:42.472151Z] Loop 3986: Loss: 2.61e-02, Avg Return: 0.858, Regret: 0.0089, Entropy: 0.1410 +[2026-03-20T18:20:43.325940Z] Loop 3987: Loss: 2.55e-02, Avg Return: 0.855, Regret: 0.0089, Entropy: 0.1416 +[2026-03-20T18:20:44.179231Z] Loop 3988: Loss: 2.47e-02, Avg Return: 0.855, Regret: 0.0089, Entropy: 0.1399 +[2026-03-20T18:20:45.032944Z] Loop 3989: Loss: 2.47e-02, Avg Return: 0.857, Regret: 0.0089, Entropy: 0.1372 +[2026-03-20T18:20:45.926672Z] Loop 3990: Loss: 2.67e-02, Avg Return: 0.856, Regret: 0.0076, Entropy: 0.1431 +[2026-03-20T18:20:46.781162Z] Loop 3991: Loss: 2.82e-02, Avg Return: 0.855, Regret: 0.0076, Entropy: 0.1525 +[2026-03-20T18:20:47.635746Z] Loop 3992: Loss: 2.94e-02, Avg Return: 0.853, Regret: 0.0076, Entropy: 0.1616 +[2026-03-20T18:20:48.490985Z] Loop 3993: Loss: 3.06e-02, Avg Return: 0.850, Regret: 0.0076, Entropy: 0.1707 +[2026-03-20T18:20:49.344652Z] Loop 3994: Loss: 3.34e-02, Avg Return: 0.846, Regret: 0.0076, Entropy: 0.1749 +[2026-03-20T18:20:50.198686Z] Loop 3995: Loss: 3.20e-02, Avg Return: 0.845, Regret: 0.0076, Entropy: 0.1768 +[2026-03-20T18:20:51.052961Z] Loop 3996: Loss: 3.39e-02, Avg Return: 0.845, Regret: 0.0076, Entropy: 0.1861 +[2026-03-20T18:20:51.906937Z] Loop 3997: Loss: 3.04e-02, Avg Return: 0.846, Regret: 0.0076, Entropy: 0.1726 +[2026-03-20T18:20:52.760517Z] Loop 3998: Loss: 3.06e-02, Avg Return: 0.849, Regret: 0.0076, Entropy: 0.1670 +[2026-03-20T18:20:53.614792Z] Loop 3999: Loss: 3.06e-02, Avg Return: 0.849, Regret: 0.0076, Entropy: 0.1700 +[2026-03-20T18:20:54.507514Z] Loop 4000: Loss: 3.01e-02, Avg Return: 0.853, Regret: 0.0113, Entropy: 0.1632 +[2026-03-20T18:20:55.362652Z] Loop 4001: Loss: 2.90e-02, Avg Return: 0.853, Regret: 0.0113, Entropy: 0.1559 +[2026-03-20T18:20:56.216251Z] Loop 4002: Loss: 2.92e-02, Avg Return: 0.856, Regret: 0.0113, Entropy: 0.1653 +[2026-03-20T18:20:57.069431Z] Loop 4003: Loss: 2.62e-02, Avg Return: 0.856, Regret: 0.0113, Entropy: 0.1503 +[2026-03-20T18:20:57.922016Z] Loop 4004: Loss: 2.71e-02, Avg Return: 0.857, Regret: 0.0113, Entropy: 0.1504 +[2026-03-20T18:20:58.776576Z] Loop 4005: Loss: 2.49e-02, Avg Return: 0.858, Regret: 0.0113, Entropy: 0.1421 +[2026-03-20T18:20:59.629217Z] Loop 4006: Loss: 2.41e-02, Avg Return: 0.858, Regret: 0.0113, Entropy: 0.1399 +[2026-03-20T18:21:00.482535Z] Loop 4007: Loss: 2.49e-02, Avg Return: 0.858, Regret: 0.0113, Entropy: 0.1397 +[2026-03-20T18:21:01.336433Z] Loop 4008: Loss: 2.50e-02, Avg Return: 0.857, Regret: 0.0113, Entropy: 0.1500 +[2026-03-20T18:21:02.190159Z] Loop 4009: Loss: 2.61e-02, Avg Return: 0.857, Regret: 0.0113, Entropy: 0.1489 +[2026-03-20T18:21:03.083429Z] Loop 4010: Loss: 2.75e-02, Avg Return: 0.855, Regret: 0.0096, Entropy: 0.1563 +[2026-03-20T18:21:03.938062Z] Loop 4011: Loss: 3.00e-02, Avg Return: 0.853, Regret: 0.0096, Entropy: 0.1635 +[2026-03-20T18:21:04.790926Z] Loop 4012: Loss: 2.69e-02, Avg Return: 0.855, Regret: 0.0096, Entropy: 0.1519 +[2026-03-20T18:21:05.644516Z] Loop 4013: Loss: 2.51e-02, Avg Return: 0.856, Regret: 0.0096, Entropy: 0.1416 +[2026-03-20T18:21:06.498805Z] Loop 4014: Loss: 2.50e-02, Avg Return: 0.858, Regret: 0.0096, Entropy: 0.1397 +[2026-03-20T18:21:07.352696Z] Loop 4015: Loss: 2.48e-02, Avg Return: 0.860, Regret: 0.0096, Entropy: 0.1391 +[2026-03-20T18:21:08.206758Z] Loop 4016: Loss: 2.28e-02, Avg Return: 0.858, Regret: 0.0096, Entropy: 0.1356 +[2026-03-20T18:21:09.060707Z] Loop 4017: Loss: 2.41e-02, Avg Return: 0.859, Regret: 0.0096, Entropy: 0.1371 +[2026-03-20T18:21:09.915510Z] Loop 4018: Loss: 2.47e-02, Avg Return: 0.858, Regret: 0.0096, Entropy: 0.1374 +[2026-03-20T18:21:10.768831Z] Loop 4019: Loss: 2.36e-02, Avg Return: 0.858, Regret: 0.0096, Entropy: 0.1318 +[2026-03-20T18:21:11.661610Z] Loop 4020: Loss: 2.43e-02, Avg Return: 0.858, Regret: 0.0063, Entropy: 0.1382 +[2026-03-20T18:21:12.513882Z] Loop 4021: Loss: 2.46e-02, Avg Return: 0.859, Regret: 0.0063, Entropy: 0.1416 +[2026-03-20T18:21:13.367478Z] Loop 4022: Loss: 2.39e-02, Avg Return: 0.859, Regret: 0.0063, Entropy: 0.1395 +[2026-03-20T18:21:14.221698Z] Loop 4023: Loss: 2.46e-02, Avg Return: 0.857, Regret: 0.0063, Entropy: 0.1411 +[2026-03-20T18:21:15.075580Z] Loop 4024: Loss: 2.68e-02, Avg Return: 0.855, Regret: 0.0063, Entropy: 0.1427 +[2026-03-20T18:21:15.928997Z] Loop 4025: Loss: 2.49e-02, Avg Return: 0.859, Regret: 0.0063, Entropy: 0.1411 +[2026-03-20T18:21:16.784054Z] Loop 4026: Loss: 2.63e-02, Avg Return: 0.857, Regret: 0.0063, Entropy: 0.1451 +[2026-03-20T18:21:17.638135Z] Loop 4027: Loss: 2.43e-02, Avg Return: 0.858, Regret: 0.0063, Entropy: 0.1377 +[2026-03-20T18:21:18.491715Z] Loop 4028: Loss: 2.42e-02, Avg Return: 0.857, Regret: 0.0063, Entropy: 0.1405 +[2026-03-20T18:21:19.345670Z] Loop 4029: Loss: 2.54e-02, Avg Return: 0.856, Regret: 0.0063, Entropy: 0.1448 +[2026-03-20T18:21:20.239521Z] Loop 4030: Loss: 2.57e-02, Avg Return: 0.856, Regret: 0.0076, Entropy: 0.1417 +[2026-03-20T18:21:21.092789Z] Loop 4031: Loss: 2.73e-02, Avg Return: 0.856, Regret: 0.0076, Entropy: 0.1510 +[2026-03-20T18:21:21.945535Z] Loop 4032: Loss: 2.77e-02, Avg Return: 0.857, Regret: 0.0076, Entropy: 0.1524 +[2026-03-20T18:21:22.799249Z] Loop 4033: Loss: 2.64e-02, Avg Return: 0.857, Regret: 0.0076, Entropy: 0.1496 +[2026-03-20T18:21:23.654033Z] Loop 4034: Loss: 2.66e-02, Avg Return: 0.857, Regret: 0.0076, Entropy: 0.1508 +[2026-03-20T18:21:24.507757Z] Loop 4035: Loss: 2.44e-02, Avg Return: 0.858, Regret: 0.0076, Entropy: 0.1446 +[2026-03-20T18:21:25.361074Z] Loop 4036: Loss: 2.59e-02, Avg Return: 0.858, Regret: 0.0076, Entropy: 0.1455 +[2026-03-20T18:21:26.215374Z] Loop 4037: Loss: 2.56e-02, Avg Return: 0.858, Regret: 0.0076, Entropy: 0.1457 +[2026-03-20T18:21:27.070548Z] Loop 4038: Loss: 2.50e-02, Avg Return: 0.857, Regret: 0.0076, Entropy: 0.1432 +[2026-03-20T18:21:27.924383Z] Loop 4039: Loss: 2.42e-02, Avg Return: 0.858, Regret: 0.0076, Entropy: 0.1381 +[2026-03-20T18:21:28.817775Z] Loop 4040: Loss: 2.34e-02, Avg Return: 0.858, Regret: 0.0054, Entropy: 0.1294 +[2026-03-20T18:21:29.672553Z] Loop 4041: Loss: 2.34e-02, Avg Return: 0.857, Regret: 0.0054, Entropy: 0.1350 +[2026-03-20T18:21:30.527715Z] Loop 4042: Loss: 2.36e-02, Avg Return: 0.857, Regret: 0.0054, Entropy: 0.1342 +[2026-03-20T18:21:31.382335Z] Loop 4043: Loss: 2.56e-02, Avg Return: 0.856, Regret: 0.0054, Entropy: 0.1373 +[2026-03-20T18:21:32.235094Z] Loop 4044: Loss: 2.42e-02, Avg Return: 0.855, Regret: 0.0054, Entropy: 0.1330 +[2026-03-20T18:21:33.088226Z] Loop 4045: Loss: 2.46e-02, Avg Return: 0.858, Regret: 0.0054, Entropy: 0.1345 +[2026-03-20T18:21:33.941876Z] Loop 4046: Loss: 2.24e-02, Avg Return: 0.857, Regret: 0.0054, Entropy: 0.1283 +[2026-03-20T18:21:34.796429Z] Loop 4047: Loss: 2.31e-02, Avg Return: 0.857, Regret: 0.0054, Entropy: 0.1293 +[2026-03-20T18:21:35.650135Z] Loop 4048: Loss: 2.23e-02, Avg Return: 0.856, Regret: 0.0054, Entropy: 0.1292 +[2026-03-20T18:21:36.503520Z] Loop 4049: Loss: 2.38e-02, Avg Return: 0.858, Regret: 0.0054, Entropy: 0.1319 +[2026-03-20T18:21:37.399318Z] Loop 4050: Loss: 2.28e-02, Avg Return: 0.857, Regret: 0.0064, Entropy: 0.1284 +[2026-03-20T18:21:38.253353Z] Loop 4051: Loss: 2.35e-02, Avg Return: 0.859, Regret: 0.0064, Entropy: 0.1304 +[2026-03-20T18:21:39.107113Z] Loop 4052: Loss: 2.30e-02, Avg Return: 0.858, Regret: 0.0064, Entropy: 0.1287 +[2026-03-20T18:21:39.961611Z] Loop 4053: Loss: 2.37e-02, Avg Return: 0.859, Regret: 0.0064, Entropy: 0.1329 +[2026-03-20T18:21:40.815243Z] Loop 4054: Loss: 2.28e-02, Avg Return: 0.859, Regret: 0.0064, Entropy: 0.1307 +[2026-03-20T18:21:41.670025Z] Loop 4055: Loss: 2.26e-02, Avg Return: 0.858, Regret: 0.0064, Entropy: 0.1338 +[2026-03-20T18:21:42.524103Z] Loop 4056: Loss: 2.22e-02, Avg Return: 0.858, Regret: 0.0064, Entropy: 0.1315 +[2026-03-20T18:21:43.376926Z] Loop 4057: Loss: 2.31e-02, Avg Return: 0.858, Regret: 0.0064, Entropy: 0.1293 +[2026-03-20T18:21:44.229591Z] Loop 4058: Loss: 2.26e-02, Avg Return: 0.858, Regret: 0.0064, Entropy: 0.1272 +[2026-03-20T18:21:45.083572Z] Loop 4059: Loss: 2.44e-02, Avg Return: 0.858, Regret: 0.0064, Entropy: 0.1333 +[2026-03-20T18:21:45.977782Z] Loop 4060: Loss: 2.42e-02, Avg Return: 0.858, Regret: 0.0055, Entropy: 0.1360 +[2026-03-20T18:21:46.831498Z] Loop 4061: Loss: 2.49e-02, Avg Return: 0.857, Regret: 0.0055, Entropy: 0.1369 +[2026-03-20T18:21:47.684599Z] Loop 4062: Loss: 2.35e-02, Avg Return: 0.859, Regret: 0.0055, Entropy: 0.1308 +[2026-03-20T18:21:48.537707Z] Loop 4063: Loss: 2.33e-02, Avg Return: 0.858, Regret: 0.0055, Entropy: 0.1320 +[2026-03-20T18:21:49.392075Z] Loop 4064: Loss: 2.42e-02, Avg Return: 0.858, Regret: 0.0055, Entropy: 0.1339 +[2026-03-20T18:21:50.246466Z] Loop 4065: Loss: 2.50e-02, Avg Return: 0.859, Regret: 0.0055, Entropy: 0.1386 +[2026-03-20T18:21:51.100519Z] Loop 4066: Loss: 2.27e-02, Avg Return: 0.858, Regret: 0.0055, Entropy: 0.1325 +[2026-03-20T18:21:51.953491Z] Loop 4067: Loss: 2.33e-02, Avg Return: 0.858, Regret: 0.0055, Entropy: 0.1360 +[2026-03-20T18:21:52.807424Z] Loop 4068: Loss: 2.30e-02, Avg Return: 0.860, Regret: 0.0055, Entropy: 0.1324 +[2026-03-20T18:21:53.661197Z] Loop 4069: Loss: 2.32e-02, Avg Return: 0.858, Regret: 0.0055, Entropy: 0.1320 +[2026-03-20T18:21:54.554232Z] Loop 4070: Loss: 2.33e-02, Avg Return: 0.858, Regret: 0.0050, Entropy: 0.1311 +[2026-03-20T18:21:55.406875Z] Loop 4071: Loss: 2.28e-02, Avg Return: 0.857, Regret: 0.0050, Entropy: 0.1297 +[2026-03-20T18:21:56.259807Z] Loop 4072: Loss: 2.33e-02, Avg Return: 0.857, Regret: 0.0050, Entropy: 0.1333 +[2026-03-20T18:21:57.114776Z] Loop 4073: Loss: 2.36e-02, Avg Return: 0.856, Regret: 0.0050, Entropy: 0.1346 +[2026-03-20T18:21:57.968001Z] Loop 4074: Loss: 2.56e-02, Avg Return: 0.855, Regret: 0.0050, Entropy: 0.1425 +[2026-03-20T18:21:58.822433Z] Loop 4075: Loss: 2.48e-02, Avg Return: 0.855, Regret: 0.0050, Entropy: 0.1418 +[2026-03-20T18:21:59.676050Z] Loop 4076: Loss: 2.50e-02, Avg Return: 0.855, Regret: 0.0050, Entropy: 0.1438 +[2026-03-20T18:22:00.530704Z] Loop 4077: Loss: 2.62e-02, Avg Return: 0.855, Regret: 0.0050, Entropy: 0.1460 +[2026-03-20T18:22:01.385441Z] Loop 4078: Loss: 2.31e-02, Avg Return: 0.857, Regret: 0.0050, Entropy: 0.1370 +[2026-03-20T18:22:02.240037Z] Loop 4079: Loss: 2.52e-02, Avg Return: 0.856, Regret: 0.0050, Entropy: 0.1419 +[2026-03-20T18:22:03.134195Z] Loop 4080: Loss: 2.34e-02, Avg Return: 0.859, Regret: 0.0057, Entropy: 0.1379 +[2026-03-20T18:22:03.988320Z] Loop 4081: Loss: 2.38e-02, Avg Return: 0.859, Regret: 0.0057, Entropy: 0.1379 +[2026-03-20T18:22:04.842950Z] Loop 4082: Loss: 2.44e-02, Avg Return: 0.859, Regret: 0.0057, Entropy: 0.1427 +[2026-03-20T18:22:05.697054Z] Loop 4083: Loss: 2.39e-02, Avg Return: 0.859, Regret: 0.0057, Entropy: 0.1350 +[2026-03-20T18:22:06.550672Z] Loop 4084: Loss: 2.59e-02, Avg Return: 0.857, Regret: 0.0057, Entropy: 0.1474 +[2026-03-20T18:22:07.405011Z] Loop 4085: Loss: 2.67e-02, Avg Return: 0.855, Regret: 0.0057, Entropy: 0.1439 +[2026-03-20T18:22:08.258949Z] Loop 4086: Loss: 2.88e-02, Avg Return: 0.854, Regret: 0.0057, Entropy: 0.1514 +[2026-03-20T18:22:09.112613Z] Loop 4087: Loss: 2.62e-02, Avg Return: 0.854, Regret: 0.0057, Entropy: 0.1494 +[2026-03-20T18:22:09.965901Z] Loop 4088: Loss: 2.72e-02, Avg Return: 0.854, Regret: 0.0057, Entropy: 0.1457 +[2026-03-20T18:22:10.819380Z] Loop 4089: Loss: 2.69e-02, Avg Return: 0.856, Regret: 0.0057, Entropy: 0.1490 +[2026-03-20T18:22:11.712277Z] Loop 4090: Loss: 2.79e-02, Avg Return: 0.855, Regret: 0.0072, Entropy: 0.1609 +[2026-03-20T18:22:12.566592Z] Loop 4091: Loss: 3.30e-02, Avg Return: 0.853, Regret: 0.0072, Entropy: 0.1887 +[2026-03-20T18:22:13.422324Z] Loop 4092: Loss: 3.37e-02, Avg Return: 0.852, Regret: 0.0072, Entropy: 0.1933 +[2026-03-20T18:22:14.278569Z] Loop 4093: Loss: 3.22e-02, Avg Return: 0.851, Regret: 0.0072, Entropy: 0.1848 +[2026-03-20T18:22:15.132190Z] Loop 4094: Loss: 3.11e-02, Avg Return: 0.853, Regret: 0.0072, Entropy: 0.1722 +[2026-03-20T18:22:15.986502Z] Loop 4095: Loss: 2.69e-02, Avg Return: 0.855, Regret: 0.0072, Entropy: 0.1533 +[2026-03-20T18:22:16.839867Z] Loop 4096: Loss: 2.82e-02, Avg Return: 0.856, Regret: 0.0072, Entropy: 0.1552 +[2026-03-20T18:22:17.695417Z] Loop 4097: Loss: 2.83e-02, Avg Return: 0.853, Regret: 0.0072, Entropy: 0.1495 +[2026-03-20T18:22:18.549271Z] Loop 4098: Loss: 2.82e-02, Avg Return: 0.852, Regret: 0.0072, Entropy: 0.1469 +[2026-03-20T18:22:19.402168Z] Loop 4099: Loss: 2.84e-02, Avg Return: 0.850, Regret: 0.0072, Entropy: 0.1467 +[2026-03-20T18:22:20.295120Z] Loop 4100: Loss: 2.97e-02, Avg Return: 0.849, Regret: 0.0136, Entropy: 0.1499 +[2026-03-20T18:22:21.150686Z] Loop 4101: Loss: 2.63e-02, Avg Return: 0.852, Regret: 0.0136, Entropy: 0.1433 +[2026-03-20T18:22:22.005089Z] Loop 4102: Loss: 2.49e-02, Avg Return: 0.854, Regret: 0.0136, Entropy: 0.1309 +[2026-03-20T18:22:22.858435Z] Loop 4103: Loss: 2.24e-02, Avg Return: 0.855, Regret: 0.0136, Entropy: 0.1280 +[2026-03-20T18:22:23.711195Z] Loop 4104: Loss: 2.32e-02, Avg Return: 0.856, Regret: 0.0136, Entropy: 0.1259 +[2026-03-20T18:22:24.565327Z] Loop 4105: Loss: 2.24e-02, Avg Return: 0.857, Regret: 0.0136, Entropy: 0.1242 +[2026-03-20T18:22:25.418951Z] Loop 4106: Loss: 2.17e-02, Avg Return: 0.859, Regret: 0.0136, Entropy: 0.1246 +[2026-03-20T18:22:26.271729Z] Loop 4107: Loss: 2.14e-02, Avg Return: 0.856, Regret: 0.0136, Entropy: 0.1233 +[2026-03-20T18:22:27.124352Z] Loop 4108: Loss: 2.54e-02, Avg Return: 0.858, Regret: 0.0136, Entropy: 0.1426 +[2026-03-20T18:22:27.977949Z] Loop 4109: Loss: 2.40e-02, Avg Return: 0.856, Regret: 0.0136, Entropy: 0.1366 +[2026-03-20T18:22:28.872422Z] Loop 4110: Loss: 2.63e-02, Avg Return: 0.854, Regret: 0.0092, Entropy: 0.1432 +[2026-03-20T18:22:29.726991Z] Loop 4111: Loss: 2.62e-02, Avg Return: 0.855, Regret: 0.0092, Entropy: 0.1425 +[2026-03-20T18:22:30.580561Z] Loop 4112: Loss: 2.48e-02, Avg Return: 0.855, Regret: 0.0092, Entropy: 0.1351 +[2026-03-20T18:22:31.435212Z] Loop 4113: Loss: 2.21e-02, Avg Return: 0.856, Regret: 0.0092, Entropy: 0.1327 +[2026-03-20T18:22:32.288991Z] Loop 4114: Loss: 2.51e-02, Avg Return: 0.855, Regret: 0.0092, Entropy: 0.1411 +[2026-03-20T18:22:33.143116Z] Loop 4115: Loss: 2.67e-02, Avg Return: 0.855, Regret: 0.0092, Entropy: 0.1376 +[2026-03-20T18:22:33.996524Z] Loop 4116: Loss: 2.74e-02, Avg Return: 0.848, Regret: 0.0092, Entropy: 0.1461 +[2026-03-20T18:22:34.850337Z] Loop 4117: Loss: 2.74e-02, Avg Return: 0.847, Regret: 0.0092, Entropy: 0.1477 +[2026-03-20T18:22:35.703829Z] Loop 4118: Loss: 2.74e-02, Avg Return: 0.849, Regret: 0.0092, Entropy: 0.1427 +[2026-03-20T18:22:36.557099Z] Loop 4119: Loss: 2.61e-02, Avg Return: 0.851, Regret: 0.0092, Entropy: 0.1399 +[2026-03-20T18:22:37.452643Z] Loop 4120: Loss: 2.54e-02, Avg Return: 0.855, Regret: 0.0085, Entropy: 0.1407 +[2026-03-20T18:22:38.307238Z] Loop 4121: Loss: 2.50e-02, Avg Return: 0.858, Regret: 0.0085, Entropy: 0.1403 +[2026-03-20T18:22:39.161510Z] Loop 4122: Loss: 2.52e-02, Avg Return: 0.856, Regret: 0.0085, Entropy: 0.1446 +[2026-03-20T18:22:40.016070Z] Loop 4123: Loss: 2.73e-02, Avg Return: 0.857, Regret: 0.0085, Entropy: 0.1565 +[2026-03-20T18:22:40.869878Z] Loop 4124: Loss: 2.82e-02, Avg Return: 0.855, Regret: 0.0085, Entropy: 0.1683 +[2026-03-20T18:22:41.723353Z] Loop 4125: Loss: 3.10e-02, Avg Return: 0.854, Regret: 0.0085, Entropy: 0.1785 +[2026-03-20T18:22:42.576618Z] Loop 4126: Loss: 2.96e-02, Avg Return: 0.854, Regret: 0.0085, Entropy: 0.1733 +[2026-03-20T18:22:43.430313Z] Loop 4127: Loss: 2.71e-02, Avg Return: 0.856, Regret: 0.0085, Entropy: 0.1578 +[2026-03-20T18:22:44.284247Z] Loop 4128: Loss: 2.64e-02, Avg Return: 0.857, Regret: 0.0085, Entropy: 0.1460 +[2026-03-20T18:22:45.138524Z] Loop 4129: Loss: 2.46e-02, Avg Return: 0.857, Regret: 0.0085, Entropy: 0.1364 +[2026-03-20T18:22:46.030721Z] Loop 4130: Loss: 2.24e-02, Avg Return: 0.859, Regret: 0.0048, Entropy: 0.1309 +[2026-03-20T18:22:46.885884Z] Loop 4131: Loss: 2.13e-02, Avg Return: 0.860, Regret: 0.0048, Entropy: 0.1253 +[2026-03-20T18:22:47.740786Z] Loop 4132: Loss: 2.37e-02, Avg Return: 0.860, Regret: 0.0048, Entropy: 0.1391 +[2026-03-20T18:22:48.595099Z] Loop 4133: Loss: 2.37e-02, Avg Return: 0.859, Regret: 0.0048, Entropy: 0.1344 +[2026-03-20T18:22:49.447371Z] Loop 4134: Loss: 2.29e-02, Avg Return: 0.858, Regret: 0.0048, Entropy: 0.1333 +[2026-03-20T18:22:50.300218Z] Loop 4135: Loss: 2.56e-02, Avg Return: 0.855, Regret: 0.0048, Entropy: 0.1438 +[2026-03-20T18:22:51.153995Z] Loop 4136: Loss: 2.61e-02, Avg Return: 0.853, Regret: 0.0048, Entropy: 0.1426 +[2026-03-20T18:22:52.007968Z] Loop 4137: Loss: 2.64e-02, Avg Return: 0.855, Regret: 0.0048, Entropy: 0.1456 +[2026-03-20T18:22:52.861145Z] Loop 4138: Loss: 2.69e-02, Avg Return: 0.856, Regret: 0.0048, Entropy: 0.1518 +[2026-03-20T18:22:53.714406Z] Loop 4139: Loss: 2.64e-02, Avg Return: 0.856, Regret: 0.0048, Entropy: 0.1475 +[2026-03-20T18:22:54.607949Z] Loop 4140: Loss: 2.40e-02, Avg Return: 0.856, Regret: 0.0064, Entropy: 0.1365 +[2026-03-20T18:22:55.462705Z] Loop 4141: Loss: 2.30e-02, Avg Return: 0.858, Regret: 0.0064, Entropy: 0.1360 +[2026-03-20T18:22:56.317411Z] Loop 4142: Loss: 2.42e-02, Avg Return: 0.857, Regret: 0.0064, Entropy: 0.1328 +[2026-03-20T18:22:57.170401Z] Loop 4143: Loss: 2.33e-02, Avg Return: 0.856, Regret: 0.0064, Entropy: 0.1309 +[2026-03-20T18:22:58.024329Z] Loop 4144: Loss: 2.58e-02, Avg Return: 0.855, Regret: 0.0064, Entropy: 0.1362 +[2026-03-20T18:22:58.877100Z] Loop 4145: Loss: 2.53e-02, Avg Return: 0.854, Regret: 0.0064, Entropy: 0.1364 +[2026-03-20T18:22:59.731173Z] Loop 4146: Loss: 2.47e-02, Avg Return: 0.855, Regret: 0.0064, Entropy: 0.1350 +[2026-03-20T18:23:00.584636Z] Loop 4147: Loss: 2.44e-02, Avg Return: 0.857, Regret: 0.0064, Entropy: 0.1342 +[2026-03-20T18:23:01.437936Z] Loop 4148: Loss: 2.34e-02, Avg Return: 0.858, Regret: 0.0064, Entropy: 0.1309 +[2026-03-20T18:23:02.291721Z] Loop 4149: Loss: 2.31e-02, Avg Return: 0.860, Regret: 0.0064, Entropy: 0.1312 +[2026-03-20T18:23:03.186654Z] Loop 4150: Loss: 2.28e-02, Avg Return: 0.859, Regret: 0.0044, Entropy: 0.1314 +[2026-03-20T18:23:04.041261Z] Loop 4151: Loss: 2.48e-02, Avg Return: 0.856, Regret: 0.0044, Entropy: 0.1448 +[2026-03-20T18:23:04.896033Z] Loop 4152: Loss: 2.58e-02, Avg Return: 0.858, Regret: 0.0044, Entropy: 0.1471 +[2026-03-20T18:23:05.749850Z] Loop 4153: Loss: 2.68e-02, Avg Return: 0.857, Regret: 0.0044, Entropy: 0.1538 +[2026-03-20T18:23:06.604820Z] Loop 4154: Loss: 2.96e-02, Avg Return: 0.854, Regret: 0.0044, Entropy: 0.1588 +[2026-03-20T18:23:07.459256Z] Loop 4155: Loss: 3.02e-02, Avg Return: 0.854, Regret: 0.0044, Entropy: 0.1668 +[2026-03-20T18:23:08.314069Z] Loop 4156: Loss: 2.73e-02, Avg Return: 0.853, Regret: 0.0044, Entropy: 0.1579 +[2026-03-20T18:23:09.167832Z] Loop 4157: Loss: 2.82e-02, Avg Return: 0.856, Regret: 0.0044, Entropy: 0.1582 +[2026-03-20T18:23:10.022113Z] Loop 4158: Loss: 2.76e-02, Avg Return: 0.858, Regret: 0.0044, Entropy: 0.1534 +[2026-03-20T18:23:10.875501Z] Loop 4159: Loss: 2.36e-02, Avg Return: 0.858, Regret: 0.0044, Entropy: 0.1386 +[2026-03-20T18:23:11.768497Z] Loop 4160: Loss: 2.53e-02, Avg Return: 0.858, Regret: 0.0051, Entropy: 0.1504 +[2026-03-20T18:23:12.622415Z] Loop 4161: Loss: 2.51e-02, Avg Return: 0.859, Regret: 0.0051, Entropy: 0.1407 +[2026-03-20T18:23:13.475481Z] Loop 4162: Loss: 2.43e-02, Avg Return: 0.858, Regret: 0.0051, Entropy: 0.1430 +[2026-03-20T18:23:14.328848Z] Loop 4163: Loss: 2.57e-02, Avg Return: 0.857, Regret: 0.0051, Entropy: 0.1410 +[2026-03-20T18:23:15.182416Z] Loop 4164: Loss: 2.34e-02, Avg Return: 0.855, Regret: 0.0051, Entropy: 0.1299 +[2026-03-20T18:23:16.036523Z] Loop 4165: Loss: 2.41e-02, Avg Return: 0.857, Regret: 0.0051, Entropy: 0.1376 +[2026-03-20T18:23:16.889890Z] Loop 4166: Loss: 2.59e-02, Avg Return: 0.856, Regret: 0.0051, Entropy: 0.1435 +[2026-03-20T18:23:17.742927Z] Loop 4167: Loss: 2.36e-02, Avg Return: 0.857, Regret: 0.0051, Entropy: 0.1387 +[2026-03-20T18:23:18.596627Z] Loop 4168: Loss: 2.50e-02, Avg Return: 0.857, Regret: 0.0051, Entropy: 0.1406 +[2026-03-20T18:23:19.450433Z] Loop 4169: Loss: 2.40e-02, Avg Return: 0.856, Regret: 0.0051, Entropy: 0.1409 +[2026-03-20T18:23:20.345351Z] Loop 4170: Loss: 2.58e-02, Avg Return: 0.859, Regret: 0.0062, Entropy: 0.1400 +[2026-03-20T18:23:21.198634Z] Loop 4171: Loss: 2.47e-02, Avg Return: 0.858, Regret: 0.0062, Entropy: 0.1429 +[2026-03-20T18:23:22.053219Z] Loop 4172: Loss: 2.32e-02, Avg Return: 0.857, Regret: 0.0062, Entropy: 0.1384 +[2026-03-20T18:23:22.907934Z] Loop 4173: Loss: 2.58e-02, Avg Return: 0.858, Regret: 0.0062, Entropy: 0.1431 +[2026-03-20T18:23:23.761559Z] Loop 4174: Loss: 2.36e-02, Avg Return: 0.857, Regret: 0.0062, Entropy: 0.1363 +[2026-03-20T18:23:24.613757Z] Loop 4175: Loss: 2.54e-02, Avg Return: 0.857, Regret: 0.0062, Entropy: 0.1386 +[2026-03-20T18:23:25.465507Z] Loop 4176: Loss: 2.28e-02, Avg Return: 0.859, Regret: 0.0062, Entropy: 0.1347 +[2026-03-20T18:23:26.320169Z] Loop 4177: Loss: 2.42e-02, Avg Return: 0.858, Regret: 0.0062, Entropy: 0.1413 +[2026-03-20T18:23:27.173499Z] Loop 4178: Loss: 2.39e-02, Avg Return: 0.858, Regret: 0.0062, Entropy: 0.1403 +[2026-03-20T18:23:28.026697Z] Loop 4179: Loss: 2.40e-02, Avg Return: 0.858, Regret: 0.0062, Entropy: 0.1324 +[2026-03-20T18:23:28.918941Z] Loop 4180: Loss: 2.32e-02, Avg Return: 0.858, Regret: 0.0050, Entropy: 0.1330 +[2026-03-20T18:23:29.773766Z] Loop 4181: Loss: 2.56e-02, Avg Return: 0.859, Regret: 0.0050, Entropy: 0.1372 +[2026-03-20T18:23:30.628169Z] Loop 4182: Loss: 2.44e-02, Avg Return: 0.859, Regret: 0.0050, Entropy: 0.1350 +[2026-03-20T18:23:31.482265Z] Loop 4183: Loss: 2.18e-02, Avg Return: 0.858, Regret: 0.0050, Entropy: 0.1248 +[2026-03-20T18:23:32.335847Z] Loop 4184: Loss: 2.54e-02, Avg Return: 0.859, Regret: 0.0050, Entropy: 0.1376 +[2026-03-20T18:23:33.189886Z] Loop 4185: Loss: 2.48e-02, Avg Return: 0.858, Regret: 0.0050, Entropy: 0.1359 +[2026-03-20T18:23:34.044158Z] Loop 4186: Loss: 2.32e-02, Avg Return: 0.857, Regret: 0.0050, Entropy: 0.1372 +[2026-03-20T18:23:34.898195Z] Loop 4187: Loss: 2.37e-02, Avg Return: 0.858, Regret: 0.0050, Entropy: 0.1354 +[2026-03-20T18:23:35.751730Z] Loop 4188: Loss: 2.34e-02, Avg Return: 0.858, Regret: 0.0050, Entropy: 0.1428 +[2026-03-20T18:23:36.606359Z] Loop 4189: Loss: 2.47e-02, Avg Return: 0.856, Regret: 0.0050, Entropy: 0.1400 +[2026-03-20T18:23:37.499582Z] Loop 4190: Loss: 2.58e-02, Avg Return: 0.856, Regret: 0.0086, Entropy: 0.1521 +[2026-03-20T18:23:38.353131Z] Loop 4191: Loss: 2.71e-02, Avg Return: 0.854, Regret: 0.0086, Entropy: 0.1619 +[2026-03-20T18:23:39.207811Z] Loop 4192: Loss: 2.73e-02, Avg Return: 0.854, Regret: 0.0086, Entropy: 0.1545 +[2026-03-20T18:23:40.061801Z] Loop 4193: Loss: 2.64e-02, Avg Return: 0.855, Regret: 0.0086, Entropy: 0.1536 +[2026-03-20T18:23:40.915194Z] Loop 4194: Loss: 2.56e-02, Avg Return: 0.857, Regret: 0.0086, Entropy: 0.1479 +[2026-03-20T18:23:41.769289Z] Loop 4195: Loss: 2.42e-02, Avg Return: 0.857, Regret: 0.0086, Entropy: 0.1389 +[2026-03-20T18:23:42.623645Z] Loop 4196: Loss: 2.45e-02, Avg Return: 0.856, Regret: 0.0086, Entropy: 0.1449 +[2026-03-20T18:23:43.478206Z] Loop 4197: Loss: 2.34e-02, Avg Return: 0.857, Regret: 0.0086, Entropy: 0.1408 +[2026-03-20T18:23:44.332347Z] Loop 4198: Loss: 2.50e-02, Avg Return: 0.856, Regret: 0.0086, Entropy: 0.1444 +[2026-03-20T18:23:45.186713Z] Loop 4199: Loss: 2.64e-02, Avg Return: 0.856, Regret: 0.0086, Entropy: 0.1529 +[2026-03-20T18:23:46.081872Z] Loop 4200: Loss: 2.63e-02, Avg Return: 0.857, Regret: 0.0082, Entropy: 0.1550 +[2026-03-20T18:23:46.935570Z] Loop 4201: Loss: 2.70e-02, Avg Return: 0.856, Regret: 0.0082, Entropy: 0.1573 +[2026-03-20T18:23:47.790167Z] Loop 4202: Loss: 2.78e-02, Avg Return: 0.855, Regret: 0.0082, Entropy: 0.1646 +[2026-03-20T18:23:48.644878Z] Loop 4203: Loss: 2.83e-02, Avg Return: 0.853, Regret: 0.0082, Entropy: 0.1673 +[2026-03-20T18:23:49.500043Z] Loop 4204: Loss: 2.84e-02, Avg Return: 0.855, Regret: 0.0082, Entropy: 0.1658 +[2026-03-20T18:23:50.355515Z] Loop 4205: Loss: 2.79e-02, Avg Return: 0.855, Regret: 0.0082, Entropy: 0.1654 +[2026-03-20T18:23:51.210286Z] Loop 4206: Loss: 2.63e-02, Avg Return: 0.855, Regret: 0.0082, Entropy: 0.1551 +[2026-03-20T18:23:52.065209Z] Loop 4207: Loss: 2.67e-02, Avg Return: 0.856, Regret: 0.0082, Entropy: 0.1526 +[2026-03-20T18:23:52.920986Z] Loop 4208: Loss: 2.62e-02, Avg Return: 0.857, Regret: 0.0082, Entropy: 0.1527 +[2026-03-20T18:23:53.774921Z] Loop 4209: Loss: 2.72e-02, Avg Return: 0.854, Regret: 0.0082, Entropy: 0.1535 +[2026-03-20T18:23:54.671676Z] Loop 4210: Loss: 2.64e-02, Avg Return: 0.855, Regret: 0.0093, Entropy: 0.1479 +[2026-03-20T18:23:55.525553Z] Loop 4211: Loss: 2.64e-02, Avg Return: 0.853, Regret: 0.0093, Entropy: 0.1445 +[2026-03-20T18:23:56.378448Z] Loop 4212: Loss: 2.61e-02, Avg Return: 0.854, Regret: 0.0093, Entropy: 0.1466 +[2026-03-20T18:23:57.232213Z] Loop 4213: Loss: 2.67e-02, Avg Return: 0.855, Regret: 0.0093, Entropy: 0.1508 +[2026-03-20T18:23:58.087920Z] Loop 4214: Loss: 2.62e-02, Avg Return: 0.852, Regret: 0.0093, Entropy: 0.1481 +[2026-03-20T18:23:58.942837Z] Loop 4215: Loss: 2.80e-02, Avg Return: 0.850, Regret: 0.0093, Entropy: 0.1540 +[2026-03-20T18:23:59.796342Z] Loop 4216: Loss: 2.71e-02, Avg Return: 0.851, Regret: 0.0093, Entropy: 0.1535 +[2026-03-20T18:24:00.650578Z] Loop 4217: Loss: 2.41e-02, Avg Return: 0.853, Regret: 0.0093, Entropy: 0.1390 +[2026-03-20T18:24:01.505193Z] Loop 4218: Loss: 2.30e-02, Avg Return: 0.856, Regret: 0.0093, Entropy: 0.1305 +[2026-03-20T18:24:02.360236Z] Loop 4219: Loss: 2.36e-02, Avg Return: 0.857, Regret: 0.0093, Entropy: 0.1301 +[2026-03-20T18:24:03.254506Z] Loop 4220: Loss: 2.18e-02, Avg Return: 0.857, Regret: 0.0050, Entropy: 0.1273 +[2026-03-20T18:24:04.108347Z] Loop 4221: Loss: 2.27e-02, Avg Return: 0.858, Regret: 0.0050, Entropy: 0.1283 +[2026-03-20T18:24:04.964461Z] Loop 4222: Loss: 2.24e-02, Avg Return: 0.859, Regret: 0.0050, Entropy: 0.1298 +[2026-03-20T18:24:05.818780Z] Loop 4223: Loss: 2.25e-02, Avg Return: 0.860, Regret: 0.0050, Entropy: 0.1251 +[2026-03-20T18:24:06.672860Z] Loop 4224: Loss: 2.27e-02, Avg Return: 0.861, Regret: 0.0050, Entropy: 0.1297 +[2026-03-20T18:24:07.526443Z] Loop 4225: Loss: 2.18e-02, Avg Return: 0.860, Regret: 0.0050, Entropy: 0.1262 +[2026-03-20T18:24:08.381520Z] Loop 4226: Loss: 2.34e-02, Avg Return: 0.859, Regret: 0.0050, Entropy: 0.1328 +[2026-03-20T18:24:09.235553Z] Loop 4227: Loss: 2.30e-02, Avg Return: 0.860, Regret: 0.0050, Entropy: 0.1232 +[2026-03-20T18:24:10.089491Z] Loop 4228: Loss: 2.30e-02, Avg Return: 0.860, Regret: 0.0050, Entropy: 0.1233 +[2026-03-20T18:24:10.942836Z] Loop 4229: Loss: 2.24e-02, Avg Return: 0.858, Regret: 0.0050, Entropy: 0.1276 +[2026-03-20T18:24:11.838467Z] Loop 4230: Loss: 2.25e-02, Avg Return: 0.860, Regret: 0.0051, Entropy: 0.1248 +[2026-03-20T18:24:12.692342Z] Loop 4231: Loss: 2.14e-02, Avg Return: 0.857, Regret: 0.0051, Entropy: 0.1220 +[2026-03-20T18:24:13.546356Z] Loop 4232: Loss: 2.21e-02, Avg Return: 0.858, Regret: 0.0051, Entropy: 0.1277 +[2026-03-20T18:24:14.401098Z] Loop 4233: Loss: 2.28e-02, Avg Return: 0.859, Regret: 0.0051, Entropy: 0.1226 +[2026-03-20T18:24:15.256084Z] Loop 4234: Loss: 2.15e-02, Avg Return: 0.859, Regret: 0.0051, Entropy: 0.1216 +[2026-03-20T18:24:16.112884Z] Loop 4235: Loss: 2.26e-02, Avg Return: 0.858, Regret: 0.0051, Entropy: 0.1261 +[2026-03-20T18:24:16.968030Z] Loop 4236: Loss: 2.42e-02, Avg Return: 0.856, Regret: 0.0051, Entropy: 0.1351 +[2026-03-20T18:24:17.821170Z] Loop 4237: Loss: 2.60e-02, Avg Return: 0.854, Regret: 0.0051, Entropy: 0.1373 +[2026-03-20T18:24:18.675327Z] Loop 4238: Loss: 2.39e-02, Avg Return: 0.855, Regret: 0.0051, Entropy: 0.1304 +[2026-03-20T18:24:19.529253Z] Loop 4239: Loss: 2.36e-02, Avg Return: 0.858, Regret: 0.0051, Entropy: 0.1279 +[2026-03-20T18:24:20.425676Z] Loop 4240: Loss: 2.23e-02, Avg Return: 0.858, Regret: 0.0062, Entropy: 0.1207 +[2026-03-20T18:24:21.279903Z] Loop 4241: Loss: 2.23e-02, Avg Return: 0.856, Regret: 0.0062, Entropy: 0.1222 +[2026-03-20T18:24:22.136320Z] Loop 4242: Loss: 2.43e-02, Avg Return: 0.857, Regret: 0.0062, Entropy: 0.1306 +[2026-03-20T18:24:22.991553Z] Loop 4243: Loss: 2.44e-02, Avg Return: 0.857, Regret: 0.0062, Entropy: 0.1327 +[2026-03-20T18:24:23.845805Z] Loop 4244: Loss: 2.31e-02, Avg Return: 0.855, Regret: 0.0062, Entropy: 0.1276 +[2026-03-20T18:24:24.701040Z] Loop 4245: Loss: 2.38e-02, Avg Return: 0.857, Regret: 0.0062, Entropy: 0.1307 +[2026-03-20T18:24:25.555537Z] Loop 4246: Loss: 2.28e-02, Avg Return: 0.859, Regret: 0.0062, Entropy: 0.1295 +[2026-03-20T18:24:26.409184Z] Loop 4247: Loss: 2.14e-02, Avg Return: 0.859, Regret: 0.0062, Entropy: 0.1273 +[2026-03-20T18:24:27.262380Z] Loop 4248: Loss: 2.09e-02, Avg Return: 0.858, Regret: 0.0062, Entropy: 0.1244 +[2026-03-20T18:24:28.117341Z] Loop 4249: Loss: 2.32e-02, Avg Return: 0.858, Regret: 0.0062, Entropy: 0.1268 +[2026-03-20T18:24:29.013886Z] Loop 4250: Loss: 2.30e-02, Avg Return: 0.858, Regret: 0.0059, Entropy: 0.1292 +[2026-03-20T18:24:29.867331Z] Loop 4251: Loss: 2.27e-02, Avg Return: 0.856, Regret: 0.0059, Entropy: 0.1276 +[2026-03-20T18:24:30.721988Z] Loop 4252: Loss: 2.31e-02, Avg Return: 0.857, Regret: 0.0059, Entropy: 0.1337 +[2026-03-20T18:24:31.576518Z] Loop 4253: Loss: 2.28e-02, Avg Return: 0.859, Regret: 0.0059, Entropy: 0.1281 +[2026-03-20T18:24:32.431996Z] Loop 4254: Loss: 2.37e-02, Avg Return: 0.859, Regret: 0.0059, Entropy: 0.1340 +[2026-03-20T18:24:33.287444Z] Loop 4255: Loss: 2.23e-02, Avg Return: 0.861, Regret: 0.0059, Entropy: 0.1308 +[2026-03-20T18:24:34.141578Z] Loop 4256: Loss: 2.39e-02, Avg Return: 0.860, Regret: 0.0059, Entropy: 0.1337 +[2026-03-20T18:24:34.996077Z] Loop 4257: Loss: 2.30e-02, Avg Return: 0.859, Regret: 0.0059, Entropy: 0.1297 +[2026-03-20T18:24:35.850626Z] Loop 4258: Loss: 2.15e-02, Avg Return: 0.858, Regret: 0.0059, Entropy: 0.1254 +[2026-03-20T18:24:36.707172Z] Loop 4259: Loss: 2.20e-02, Avg Return: 0.858, Regret: 0.0059, Entropy: 0.1276 +[2026-03-20T18:24:37.603714Z] Loop 4260: Loss: 2.10e-02, Avg Return: 0.858, Regret: 0.0054, Entropy: 0.1239 +[2026-03-20T18:24:38.457763Z] Loop 4261: Loss: 2.25e-02, Avg Return: 0.858, Regret: 0.0054, Entropy: 0.1268 +[2026-03-20T18:24:39.312866Z] Loop 4262: Loss: 2.31e-02, Avg Return: 0.854, Regret: 0.0054, Entropy: 0.1269 +[2026-03-20T18:24:40.167794Z] Loop 4263: Loss: 2.32e-02, Avg Return: 0.855, Regret: 0.0054, Entropy: 0.1273 +[2026-03-20T18:24:41.022214Z] Loop 4264: Loss: 2.31e-02, Avg Return: 0.852, Regret: 0.0054, Entropy: 0.1216 +[2026-03-20T18:24:41.875915Z] Loop 4265: Loss: 2.30e-02, Avg Return: 0.855, Regret: 0.0054, Entropy: 0.1238 +[2026-03-20T18:24:42.729580Z] Loop 4266: Loss: 2.35e-02, Avg Return: 0.852, Regret: 0.0054, Entropy: 0.1262 +[2026-03-20T18:24:43.583242Z] Loop 4267: Loss: 2.16e-02, Avg Return: 0.855, Regret: 0.0054, Entropy: 0.1249 +[2026-03-20T18:24:44.436943Z] Loop 4268: Loss: 2.18e-02, Avg Return: 0.857, Regret: 0.0054, Entropy: 0.1219 +[2026-03-20T18:24:45.291497Z] Loop 4269: Loss: 2.17e-02, Avg Return: 0.859, Regret: 0.0054, Entropy: 0.1218 +[2026-03-20T18:24:46.184196Z] Loop 4270: Loss: 2.10e-02, Avg Return: 0.859, Regret: 0.0049, Entropy: 0.1188 +[2026-03-20T18:24:47.038200Z] Loop 4271: Loss: 2.18e-02, Avg Return: 0.857, Regret: 0.0049, Entropy: 0.1249 +[2026-03-20T18:24:47.892173Z] Loop 4272: Loss: 2.29e-02, Avg Return: 0.858, Regret: 0.0049, Entropy: 0.1254 +[2026-03-20T18:24:48.746612Z] Loop 4273: Loss: 2.42e-02, Avg Return: 0.856, Regret: 0.0049, Entropy: 0.1353 +[2026-03-20T18:24:49.601117Z] Loop 4274: Loss: 2.58e-02, Avg Return: 0.854, Regret: 0.0049, Entropy: 0.1410 +[2026-03-20T18:24:50.454063Z] Loop 4275: Loss: 2.48e-02, Avg Return: 0.857, Regret: 0.0049, Entropy: 0.1335 +[2026-03-20T18:24:51.307943Z] Loop 4276: Loss: 2.30e-02, Avg Return: 0.857, Regret: 0.0049, Entropy: 0.1260 +[2026-03-20T18:24:52.162360Z] Loop 4277: Loss: 2.13e-02, Avg Return: 0.859, Regret: 0.0049, Entropy: 0.1199 +[2026-03-20T18:24:53.016225Z] Loop 4278: Loss: 1.99e-02, Avg Return: 0.859, Regret: 0.0049, Entropy: 0.1165 +[2026-03-20T18:24:53.869872Z] Loop 4279: Loss: 2.13e-02, Avg Return: 0.860, Regret: 0.0049, Entropy: 0.1160 +[2026-03-20T18:24:54.765063Z] Loop 4280: Loss: 2.02e-02, Avg Return: 0.858, Regret: 0.0047, Entropy: 0.1168 +[2026-03-20T18:24:55.619383Z] Loop 4281: Loss: 2.11e-02, Avg Return: 0.858, Regret: 0.0047, Entropy: 0.1212 +[2026-03-20T18:24:56.473799Z] Loop 4282: Loss: 2.07e-02, Avg Return: 0.858, Regret: 0.0047, Entropy: 0.1229 +[2026-03-20T18:24:57.327500Z] Loop 4283: Loss: 2.20e-02, Avg Return: 0.858, Regret: 0.0047, Entropy: 0.1216 +[2026-03-20T18:24:58.181969Z] Loop 4284: Loss: 2.22e-02, Avg Return: 0.859, Regret: 0.0047, Entropy: 0.1288 +[2026-03-20T18:24:59.035422Z] Loop 4285: Loss: 2.19e-02, Avg Return: 0.858, Regret: 0.0047, Entropy: 0.1252 +[2026-03-20T18:24:59.889091Z] Loop 4286: Loss: 2.42e-02, Avg Return: 0.854, Regret: 0.0047, Entropy: 0.1368 +[2026-03-20T18:25:00.743107Z] Loop 4287: Loss: 2.51e-02, Avg Return: 0.853, Regret: 0.0047, Entropy: 0.1334 +[2026-03-20T18:25:01.597669Z] Loop 4288: Loss: 2.55e-02, Avg Return: 0.857, Regret: 0.0047, Entropy: 0.1400 +[2026-03-20T18:25:02.452035Z] Loop 4289: Loss: 2.27e-02, Avg Return: 0.859, Regret: 0.0047, Entropy: 0.1282 +[2026-03-20T18:25:03.347501Z] Loop 4290: Loss: 2.18e-02, Avg Return: 0.859, Regret: 0.0037, Entropy: 0.1240 +[2026-03-20T18:25:04.201925Z] Loop 4291: Loss: 2.12e-02, Avg Return: 0.860, Regret: 0.0037, Entropy: 0.1177 +[2026-03-20T18:25:05.055625Z] Loop 4292: Loss: 2.17e-02, Avg Return: 0.858, Regret: 0.0037, Entropy: 0.1215 +[2026-03-20T18:25:05.909066Z] Loop 4293: Loss: 2.32e-02, Avg Return: 0.858, Regret: 0.0037, Entropy: 0.1276 +[2026-03-20T18:25:06.763786Z] Loop 4294: Loss: 2.06e-02, Avg Return: 0.856, Regret: 0.0037, Entropy: 0.1163 +[2026-03-20T18:25:07.619051Z] Loop 4295: Loss: 2.11e-02, Avg Return: 0.858, Regret: 0.0037, Entropy: 0.1220 +[2026-03-20T18:25:08.473286Z] Loop 4296: Loss: 2.13e-02, Avg Return: 0.859, Regret: 0.0037, Entropy: 0.1169 +[2026-03-20T18:25:09.327480Z] Loop 4297: Loss: 1.98e-02, Avg Return: 0.859, Regret: 0.0037, Entropy: 0.1180 +[2026-03-20T18:25:10.181338Z] Loop 4298: Loss: 2.10e-02, Avg Return: 0.861, Regret: 0.0037, Entropy: 0.1209 +[2026-03-20T18:25:11.036224Z] Loop 4299: Loss: 2.17e-02, Avg Return: 0.861, Regret: 0.0037, Entropy: 0.1225 +[2026-03-20T18:25:11.930090Z] Loop 4300: Loss: 2.18e-02, Avg Return: 0.861, Regret: 0.0037, Entropy: 0.1217 +[2026-03-20T18:25:12.785734Z] Loop 4301: Loss: 2.15e-02, Avg Return: 0.860, Regret: 0.0037, Entropy: 0.1229 +[2026-03-20T18:25:13.639804Z] Loop 4302: Loss: 2.28e-02, Avg Return: 0.859, Regret: 0.0037, Entropy: 0.1280 +[2026-03-20T18:25:14.494233Z] Loop 4303: Loss: 2.42e-02, Avg Return: 0.857, Regret: 0.0037, Entropy: 0.1385 +[2026-03-20T18:25:15.349458Z] Loop 4304: Loss: 2.49e-02, Avg Return: 0.857, Regret: 0.0037, Entropy: 0.1365 +[2026-03-20T18:25:16.203857Z] Loop 4305: Loss: 2.51e-02, Avg Return: 0.857, Regret: 0.0037, Entropy: 0.1302 +[2026-03-20T18:25:17.059055Z] Loop 4306: Loss: 2.29e-02, Avg Return: 0.859, Regret: 0.0037, Entropy: 0.1265 +[2026-03-20T18:25:17.913804Z] Loop 4307: Loss: 2.11e-02, Avg Return: 0.861, Regret: 0.0037, Entropy: 0.1194 +[2026-03-20T18:25:18.769066Z] Loop 4308: Loss: 2.14e-02, Avg Return: 0.860, Regret: 0.0037, Entropy: 0.1210 +[2026-03-20T18:25:19.623457Z] Loop 4309: Loss: 1.83e-02, Avg Return: 0.860, Regret: 0.0037, Entropy: 0.1113 +[2026-03-20T18:25:20.518328Z] Loop 4310: Loss: 1.93e-02, Avg Return: 0.860, Regret: 0.0037, Entropy: 0.1175 +[2026-03-20T18:25:21.371353Z] Loop 4311: Loss: 1.87e-02, Avg Return: 0.859, Regret: 0.0037, Entropy: 0.1084 +[2026-03-20T18:25:22.223750Z] Loop 4312: Loss: 2.07e-02, Avg Return: 0.859, Regret: 0.0037, Entropy: 0.1149 +[2026-03-20T18:25:23.077891Z] Loop 4313: Loss: 1.99e-02, Avg Return: 0.859, Regret: 0.0037, Entropy: 0.1122 +[2026-03-20T18:25:23.932206Z] Loop 4314: Loss: 2.03e-02, Avg Return: 0.860, Regret: 0.0037, Entropy: 0.1136 +[2026-03-20T18:25:24.786332Z] Loop 4315: Loss: 2.04e-02, Avg Return: 0.860, Regret: 0.0037, Entropy: 0.1128 +[2026-03-20T18:25:25.639710Z] Loop 4316: Loss: 2.11e-02, Avg Return: 0.860, Regret: 0.0037, Entropy: 0.1164 +[2026-03-20T18:25:26.493488Z] Loop 4317: Loss: 2.25e-02, Avg Return: 0.860, Regret: 0.0037, Entropy: 0.1261 +[2026-03-20T18:25:27.347569Z] Loop 4318: Loss: 2.04e-02, Avg Return: 0.860, Regret: 0.0037, Entropy: 0.1216 +[2026-03-20T18:25:28.200880Z] Loop 4319: Loss: 2.20e-02, Avg Return: 0.860, Regret: 0.0037, Entropy: 0.1246 +[2026-03-20T18:25:29.093963Z] Loop 4320: Loss: 2.20e-02, Avg Return: 0.858, Regret: 0.0043, Entropy: 0.1326 +[2026-03-20T18:25:29.947211Z] Loop 4321: Loss: 2.38e-02, Avg Return: 0.857, Regret: 0.0043, Entropy: 0.1337 +[2026-03-20T18:25:30.801961Z] Loop 4322: Loss: 2.51e-02, Avg Return: 0.856, Regret: 0.0043, Entropy: 0.1443 +[2026-03-20T18:25:31.656614Z] Loop 4323: Loss: 2.35e-02, Avg Return: 0.857, Regret: 0.0043, Entropy: 0.1394 +[2026-03-20T18:25:32.509856Z] Loop 4324: Loss: 2.33e-02, Avg Return: 0.860, Regret: 0.0043, Entropy: 0.1332 +[2026-03-20T18:25:33.363754Z] Loop 4325: Loss: 2.27e-02, Avg Return: 0.859, Regret: 0.0043, Entropy: 0.1253 +[2026-03-20T18:25:34.219692Z] Loop 4326: Loss: 2.18e-02, Avg Return: 0.860, Regret: 0.0043, Entropy: 0.1246 +[2026-03-20T18:25:35.073567Z] Loop 4327: Loss: 2.12e-02, Avg Return: 0.860, Regret: 0.0043, Entropy: 0.1145 +[2026-03-20T18:25:35.927873Z] Loop 4328: Loss: 2.11e-02, Avg Return: 0.858, Regret: 0.0043, Entropy: 0.1196 +[2026-03-20T18:25:36.782273Z] Loop 4329: Loss: 2.21e-02, Avg Return: 0.858, Regret: 0.0043, Entropy: 0.1241 +[2026-03-20T18:25:37.677960Z] Loop 4330: Loss: 2.06e-02, Avg Return: 0.858, Regret: 0.0063, Entropy: 0.1160 +[2026-03-20T18:25:38.532210Z] Loop 4331: Loss: 2.34e-02, Avg Return: 0.857, Regret: 0.0063, Entropy: 0.1259 +[2026-03-20T18:25:39.388214Z] Loop 4332: Loss: 2.09e-02, Avg Return: 0.859, Regret: 0.0063, Entropy: 0.1130 +[2026-03-20T18:25:40.242781Z] Loop 4333: Loss: 2.16e-02, Avg Return: 0.860, Regret: 0.0063, Entropy: 0.1225 +[2026-03-20T18:25:41.097596Z] Loop 4334: Loss: 1.87e-02, Avg Return: 0.859, Regret: 0.0063, Entropy: 0.1082 +[2026-03-20T18:25:41.951055Z] Loop 4335: Loss: 1.99e-02, Avg Return: 0.859, Regret: 0.0063, Entropy: 0.1134 +[2026-03-20T18:25:42.804390Z] Loop 4336: Loss: 2.03e-02, Avg Return: 0.860, Regret: 0.0063, Entropy: 0.1166 +[2026-03-20T18:25:43.657873Z] Loop 4337: Loss: 2.00e-02, Avg Return: 0.861, Regret: 0.0063, Entropy: 0.1164 +[2026-03-20T18:25:44.511852Z] Loop 4338: Loss: 2.30e-02, Avg Return: 0.859, Regret: 0.0063, Entropy: 0.1218 +[2026-03-20T18:25:45.365266Z] Loop 4339: Loss: 2.16e-02, Avg Return: 0.859, Regret: 0.0063, Entropy: 0.1226 +[2026-03-20T18:25:46.259627Z] Loop 4340: Loss: 2.19e-02, Avg Return: 0.858, Regret: 0.0052, Entropy: 0.1241 +[2026-03-20T18:25:47.113388Z] Loop 4341: Loss: 2.38e-02, Avg Return: 0.857, Regret: 0.0052, Entropy: 0.1273 +[2026-03-20T18:25:47.967182Z] Loop 4342: Loss: 2.26e-02, Avg Return: 0.858, Regret: 0.0052, Entropy: 0.1231 +[2026-03-20T18:25:48.820527Z] Loop 4343: Loss: 2.09e-02, Avg Return: 0.858, Regret: 0.0052, Entropy: 0.1177 +[2026-03-20T18:25:49.675301Z] Loop 4344: Loss: 1.99e-02, Avg Return: 0.859, Regret: 0.0052, Entropy: 0.1161 +[2026-03-20T18:25:50.528469Z] Loop 4345: Loss: 2.03e-02, Avg Return: 0.860, Regret: 0.0052, Entropy: 0.1131 +[2026-03-20T18:25:51.382411Z] Loop 4346: Loss: 2.01e-02, Avg Return: 0.862, Regret: 0.0052, Entropy: 0.1185 +[2026-03-20T18:25:52.236315Z] Loop 4347: Loss: 2.02e-02, Avg Return: 0.860, Regret: 0.0052, Entropy: 0.1144 +[2026-03-20T18:25:53.090814Z] Loop 4348: Loss: 2.01e-02, Avg Return: 0.860, Regret: 0.0052, Entropy: 0.1159 +[2026-03-20T18:25:53.944941Z] Loop 4349: Loss: 2.02e-02, Avg Return: 0.859, Regret: 0.0052, Entropy: 0.1127 +[2026-03-20T18:25:54.843687Z] Loop 4350: Loss: 2.02e-02, Avg Return: 0.863, Regret: 0.0035, Entropy: 0.1209 +[2026-03-20T18:25:55.697007Z] Loop 4351: Loss: 2.06e-02, Avg Return: 0.861, Regret: 0.0035, Entropy: 0.1195 +[2026-03-20T18:25:56.551703Z] Loop 4352: Loss: 2.06e-02, Avg Return: 0.860, Regret: 0.0035, Entropy: 0.1150 +[2026-03-20T18:25:57.405350Z] Loop 4353: Loss: 1.99e-02, Avg Return: 0.861, Regret: 0.0035, Entropy: 0.1123 +[2026-03-20T18:25:58.260262Z] Loop 4354: Loss: 2.11e-02, Avg Return: 0.857, Regret: 0.0035, Entropy: 0.1166 +[2026-03-20T18:25:59.114805Z] Loop 4355: Loss: 2.16e-02, Avg Return: 0.858, Regret: 0.0035, Entropy: 0.1196 +[2026-03-20T18:25:59.968230Z] Loop 4356: Loss: 2.18e-02, Avg Return: 0.858, Regret: 0.0035, Entropy: 0.1160 +[2026-03-20T18:26:00.822365Z] Loop 4357: Loss: 2.14e-02, Avg Return: 0.858, Regret: 0.0035, Entropy: 0.1165 +[2026-03-20T18:26:01.676698Z] Loop 4358: Loss: 2.17e-02, Avg Return: 0.855, Regret: 0.0035, Entropy: 0.1193 +[2026-03-20T18:26:02.530981Z] Loop 4359: Loss: 2.20e-02, Avg Return: 0.856, Regret: 0.0035, Entropy: 0.1160 +[2026-03-20T18:26:03.426056Z] Loop 4360: Loss: 2.10e-02, Avg Return: 0.855, Regret: 0.0090, Entropy: 0.1160 +[2026-03-20T18:26:04.279372Z] Loop 4361: Loss: 2.08e-02, Avg Return: 0.854, Regret: 0.0090, Entropy: 0.1156 +[2026-03-20T18:26:05.133256Z] Loop 4362: Loss: 2.06e-02, Avg Return: 0.853, Regret: 0.0090, Entropy: 0.1110 +[2026-03-20T18:26:05.987409Z] Loop 4363: Loss: 2.12e-02, Avg Return: 0.852, Regret: 0.0090, Entropy: 0.1134 +[2026-03-20T18:26:06.841748Z] Loop 4364: Loss: 1.92e-02, Avg Return: 0.854, Regret: 0.0090, Entropy: 0.1101 +[2026-03-20T18:26:07.694899Z] Loop 4365: Loss: 1.95e-02, Avg Return: 0.858, Regret: 0.0090, Entropy: 0.1066 +[2026-03-20T18:26:08.547867Z] Loop 4366: Loss: 1.81e-02, Avg Return: 0.859, Regret: 0.0090, Entropy: 0.1034 +[2026-03-20T18:26:09.401685Z] Loop 4367: Loss: 2.11e-02, Avg Return: 0.860, Regret: 0.0090, Entropy: 0.1147 +[2026-03-20T18:26:10.257049Z] Loop 4368: Loss: 2.08e-02, Avg Return: 0.861, Regret: 0.0090, Entropy: 0.1139 +[2026-03-20T18:26:11.110442Z] Loop 4369: Loss: 2.14e-02, Avg Return: 0.859, Regret: 0.0090, Entropy: 0.1178 +[2026-03-20T18:26:12.003386Z] Loop 4370: Loss: 2.11e-02, Avg Return: 0.860, Regret: 0.0054, Entropy: 0.1159 +[2026-03-20T18:26:12.856273Z] Loop 4371: Loss: 2.25e-02, Avg Return: 0.858, Regret: 0.0054, Entropy: 0.1224 +[2026-03-20T18:26:13.711513Z] Loop 4372: Loss: 2.23e-02, Avg Return: 0.859, Regret: 0.0054, Entropy: 0.1213 +[2026-03-20T18:26:14.565383Z] Loop 4373: Loss: 2.06e-02, Avg Return: 0.860, Regret: 0.0054, Entropy: 0.1175 +[2026-03-20T18:26:15.418702Z] Loop 4374: Loss: 1.96e-02, Avg Return: 0.859, Regret: 0.0054, Entropy: 0.1140 +[2026-03-20T18:26:16.272796Z] Loop 4375: Loss: 1.93e-02, Avg Return: 0.859, Regret: 0.0054, Entropy: 0.1151 +[2026-03-20T18:26:17.128305Z] Loop 4376: Loss: 2.10e-02, Avg Return: 0.859, Regret: 0.0054, Entropy: 0.1150 +[2026-03-20T18:26:17.982524Z] Loop 4377: Loss: 2.12e-02, Avg Return: 0.860, Regret: 0.0054, Entropy: 0.1168 +[2026-03-20T18:26:18.836507Z] Loop 4378: Loss: 2.02e-02, Avg Return: 0.859, Regret: 0.0054, Entropy: 0.1166 +[2026-03-20T18:26:19.689417Z] Loop 4379: Loss: 2.09e-02, Avg Return: 0.860, Regret: 0.0054, Entropy: 0.1166 +[2026-03-20T18:26:20.584634Z] Loop 4380: Loss: 2.11e-02, Avg Return: 0.859, Regret: 0.0047, Entropy: 0.1232 +[2026-03-20T18:26:21.438496Z] Loop 4381: Loss: 2.14e-02, Avg Return: 0.859, Regret: 0.0047, Entropy: 0.1212 +[2026-03-20T18:26:22.293125Z] Loop 4382: Loss: 2.28e-02, Avg Return: 0.858, Regret: 0.0047, Entropy: 0.1266 +[2026-03-20T18:26:23.147046Z] Loop 4383: Loss: 2.25e-02, Avg Return: 0.858, Regret: 0.0047, Entropy: 0.1248 +[2026-03-20T18:26:24.001153Z] Loop 4384: Loss: 2.27e-02, Avg Return: 0.858, Regret: 0.0047, Entropy: 0.1245 +[2026-03-20T18:26:24.855138Z] Loop 4385: Loss: 2.37e-02, Avg Return: 0.856, Regret: 0.0047, Entropy: 0.1277 +[2026-03-20T18:26:25.709616Z] Loop 4386: Loss: 2.36e-02, Avg Return: 0.856, Regret: 0.0047, Entropy: 0.1288 +[2026-03-20T18:26:26.565027Z] Loop 4387: Loss: 2.31e-02, Avg Return: 0.859, Regret: 0.0047, Entropy: 0.1292 +[2026-03-20T18:26:27.417744Z] Loop 4388: Loss: 2.20e-02, Avg Return: 0.857, Regret: 0.0047, Entropy: 0.1218 +[2026-03-20T18:26:28.271167Z] Loop 4389: Loss: 2.16e-02, Avg Return: 0.860, Regret: 0.0047, Entropy: 0.1225 +[2026-03-20T18:26:29.166267Z] Loop 4390: Loss: 2.06e-02, Avg Return: 0.860, Regret: 0.0040, Entropy: 0.1192 +[2026-03-20T18:26:30.020459Z] Loop 4391: Loss: 2.03e-02, Avg Return: 0.860, Regret: 0.0040, Entropy: 0.1179 +[2026-03-20T18:26:30.874550Z] Loop 4392: Loss: 2.04e-02, Avg Return: 0.860, Regret: 0.0040, Entropy: 0.1118 +[2026-03-20T18:26:31.729176Z] Loop 4393: Loss: 2.15e-02, Avg Return: 0.860, Regret: 0.0040, Entropy: 0.1170 +[2026-03-20T18:26:32.583842Z] Loop 4394: Loss: 2.04e-02, Avg Return: 0.859, Regret: 0.0040, Entropy: 0.1142 +[2026-03-20T18:26:33.438236Z] Loop 4395: Loss: 2.05e-02, Avg Return: 0.860, Regret: 0.0040, Entropy: 0.1153 +[2026-03-20T18:26:34.291676Z] Loop 4396: Loss: 2.22e-02, Avg Return: 0.861, Regret: 0.0040, Entropy: 0.1211 +[2026-03-20T18:26:35.145505Z] Loop 4397: Loss: 2.14e-02, Avg Return: 0.859, Regret: 0.0040, Entropy: 0.1127 +[2026-03-20T18:26:35.998846Z] Loop 4398: Loss: 2.09e-02, Avg Return: 0.860, Regret: 0.0040, Entropy: 0.1186 +[2026-03-20T18:26:36.853042Z] Loop 4399: Loss: 2.27e-02, Avg Return: 0.860, Regret: 0.0040, Entropy: 0.1254 +[2026-03-20T18:26:37.748913Z] Loop 4400: Loss: 2.21e-02, Avg Return: 0.857, Regret: 0.0054, Entropy: 0.1177 +[2026-03-20T18:26:38.603131Z] Loop 4401: Loss: 2.28e-02, Avg Return: 0.856, Regret: 0.0054, Entropy: 0.1217 +[2026-03-20T18:26:39.457665Z] Loop 4402: Loss: 2.22e-02, Avg Return: 0.856, Regret: 0.0054, Entropy: 0.1218 +[2026-03-20T18:26:40.312571Z] Loop 4403: Loss: 2.27e-02, Avg Return: 0.858, Regret: 0.0054, Entropy: 0.1277 +[2026-03-20T18:26:41.166824Z] Loop 4404: Loss: 2.41e-02, Avg Return: 0.860, Regret: 0.0054, Entropy: 0.1328 +[2026-03-20T18:26:42.021370Z] Loop 4405: Loss: 2.31e-02, Avg Return: 0.858, Regret: 0.0054, Entropy: 0.1343 +[2026-03-20T18:26:42.875125Z] Loop 4406: Loss: 2.42e-02, Avg Return: 0.859, Regret: 0.0054, Entropy: 0.1366 +[2026-03-20T18:26:43.729220Z] Loop 4407: Loss: 2.47e-02, Avg Return: 0.858, Regret: 0.0054, Entropy: 0.1414 +[2026-03-20T18:26:44.584049Z] Loop 4408: Loss: 2.32e-02, Avg Return: 0.859, Regret: 0.0054, Entropy: 0.1371 +[2026-03-20T18:26:45.438742Z] Loop 4409: Loss: 2.51e-02, Avg Return: 0.858, Regret: 0.0054, Entropy: 0.1398 +[2026-03-20T18:26:46.334687Z] Loop 4410: Loss: 2.58e-02, Avg Return: 0.857, Regret: 0.0052, Entropy: 0.1396 +[2026-03-20T18:26:47.188327Z] Loop 4411: Loss: 2.55e-02, Avg Return: 0.857, Regret: 0.0052, Entropy: 0.1425 +[2026-03-20T18:26:48.042072Z] Loop 4412: Loss: 2.35e-02, Avg Return: 0.858, Regret: 0.0052, Entropy: 0.1363 +[2026-03-20T18:26:48.896266Z] Loop 4413: Loss: 2.28e-02, Avg Return: 0.857, Regret: 0.0052, Entropy: 0.1280 +[2026-03-20T18:26:49.751413Z] Loop 4414: Loss: 2.47e-02, Avg Return: 0.859, Regret: 0.0052, Entropy: 0.1339 +[2026-03-20T18:26:50.604907Z] Loop 4415: Loss: 2.15e-02, Avg Return: 0.860, Regret: 0.0052, Entropy: 0.1215 +[2026-03-20T18:26:51.457565Z] Loop 4416: Loss: 2.11e-02, Avg Return: 0.861, Regret: 0.0052, Entropy: 0.1203 +[2026-03-20T18:26:52.311122Z] Loop 4417: Loss: 1.94e-02, Avg Return: 0.861, Regret: 0.0052, Entropy: 0.1147 +[2026-03-20T18:26:53.166471Z] Loop 4418: Loss: 1.99e-02, Avg Return: 0.862, Regret: 0.0052, Entropy: 0.1126 +[2026-03-20T18:26:54.021720Z] Loop 4419: Loss: 1.94e-02, Avg Return: 0.861, Regret: 0.0052, Entropy: 0.1093 +[2026-03-20T18:26:54.915865Z] Loop 4420: Loss: 1.97e-02, Avg Return: 0.860, Regret: 0.0032, Entropy: 0.1114 +[2026-03-20T18:26:55.770675Z] Loop 4421: Loss: 2.07e-02, Avg Return: 0.860, Regret: 0.0032, Entropy: 0.1149 +[2026-03-20T18:26:56.625661Z] Loop 4422: Loss: 2.01e-02, Avg Return: 0.858, Regret: 0.0032, Entropy: 0.1111 +[2026-03-20T18:26:57.479495Z] Loop 4423: Loss: 1.88e-02, Avg Return: 0.858, Regret: 0.0032, Entropy: 0.1093 +[2026-03-20T18:26:58.331775Z] Loop 4424: Loss: 2.13e-02, Avg Return: 0.856, Regret: 0.0032, Entropy: 0.1168 +[2026-03-20T18:26:59.184462Z] Loop 4425: Loss: 2.14e-02, Avg Return: 0.856, Regret: 0.0032, Entropy: 0.1196 +[2026-03-20T18:27:00.038513Z] Loop 4426: Loss: 2.24e-02, Avg Return: 0.857, Regret: 0.0032, Entropy: 0.1145 +[2026-03-20T18:27:00.891645Z] Loop 4427: Loss: 1.99e-02, Avg Return: 0.858, Regret: 0.0032, Entropy: 0.1132 +[2026-03-20T18:27:01.744585Z] Loop 4428: Loss: 2.11e-02, Avg Return: 0.859, Regret: 0.0032, Entropy: 0.1161 +[2026-03-20T18:27:02.598727Z] Loop 4429: Loss: 2.10e-02, Avg Return: 0.859, Regret: 0.0032, Entropy: 0.1126 +[2026-03-20T18:27:03.496490Z] Loop 4430: Loss: 1.81e-02, Avg Return: 0.859, Regret: 0.0039, Entropy: 0.1093 +[2026-03-20T18:27:04.351527Z] Loop 4431: Loss: 2.02e-02, Avg Return: 0.860, Regret: 0.0039, Entropy: 0.1112 +[2026-03-20T18:27:05.207328Z] Loop 4432: Loss: 1.91e-02, Avg Return: 0.859, Regret: 0.0039, Entropy: 0.1145 +[2026-03-20T18:27:06.061150Z] Loop 4433: Loss: 2.17e-02, Avg Return: 0.858, Regret: 0.0039, Entropy: 0.1191 +[2026-03-20T18:27:06.915889Z] Loop 4434: Loss: 2.06e-02, Avg Return: 0.859, Regret: 0.0039, Entropy: 0.1164 +[2026-03-20T18:27:07.769758Z] Loop 4435: Loss: 2.26e-02, Avg Return: 0.856, Regret: 0.0039, Entropy: 0.1235 +[2026-03-20T18:27:08.625078Z] Loop 4436: Loss: 2.20e-02, Avg Return: 0.858, Regret: 0.0039, Entropy: 0.1243 +[2026-03-20T18:27:09.478936Z] Loop 4437: Loss: 2.22e-02, Avg Return: 0.858, Regret: 0.0039, Entropy: 0.1226 +[2026-03-20T18:27:10.333685Z] Loop 4438: Loss: 2.15e-02, Avg Return: 0.858, Regret: 0.0039, Entropy: 0.1244 +[2026-03-20T18:27:11.187596Z] Loop 4439: Loss: 2.15e-02, Avg Return: 0.857, Regret: 0.0039, Entropy: 0.1247 +[2026-03-20T18:27:12.082830Z] Loop 4440: Loss: 2.28e-02, Avg Return: 0.859, Regret: 0.0052, Entropy: 0.1257 +[2026-03-20T18:27:12.936622Z] Loop 4441: Loss: 2.02e-02, Avg Return: 0.859, Regret: 0.0052, Entropy: 0.1152 +[2026-03-20T18:27:13.791949Z] Loop 4442: Loss: 2.24e-02, Avg Return: 0.858, Regret: 0.0052, Entropy: 0.1255 +[2026-03-20T18:27:14.646520Z] Loop 4443: Loss: 2.25e-02, Avg Return: 0.859, Regret: 0.0052, Entropy: 0.1252 +[2026-03-20T18:27:15.501562Z] Loop 4444: Loss: 2.05e-02, Avg Return: 0.858, Regret: 0.0052, Entropy: 0.1178 +[2026-03-20T18:27:16.357677Z] Loop 4445: Loss: 2.09e-02, Avg Return: 0.859, Regret: 0.0052, Entropy: 0.1164 +[2026-03-20T18:27:17.212911Z] Loop 4446: Loss: 1.96e-02, Avg Return: 0.861, Regret: 0.0052, Entropy: 0.1161 +[2026-03-20T18:27:18.067197Z] Loop 4447: Loss: 2.17e-02, Avg Return: 0.859, Regret: 0.0052, Entropy: 0.1219 +[2026-03-20T18:27:18.922286Z] Loop 4448: Loss: 2.00e-02, Avg Return: 0.859, Regret: 0.0052, Entropy: 0.1200 +[2026-03-20T18:27:19.777269Z] Loop 4449: Loss: 2.23e-02, Avg Return: 0.858, Regret: 0.0052, Entropy: 0.1280 +[2026-03-20T18:27:20.674662Z] Loop 4450: Loss: 2.29e-02, Avg Return: 0.858, Regret: 0.0071, Entropy: 0.1295 +[2026-03-20T18:27:21.529529Z] Loop 4451: Loss: 2.20e-02, Avg Return: 0.859, Regret: 0.0071, Entropy: 0.1246 +[2026-03-20T18:27:22.384005Z] Loop 4452: Loss: 2.18e-02, Avg Return: 0.861, Regret: 0.0071, Entropy: 0.1272 +[2026-03-20T18:27:23.238921Z] Loop 4453: Loss: 1.99e-02, Avg Return: 0.857, Regret: 0.0071, Entropy: 0.1167 +[2026-03-20T18:27:24.093483Z] Loop 4454: Loss: 2.09e-02, Avg Return: 0.859, Regret: 0.0071, Entropy: 0.1169 +[2026-03-20T18:27:24.947458Z] Loop 4455: Loss: 2.07e-02, Avg Return: 0.858, Regret: 0.0071, Entropy: 0.1164 +[2026-03-20T18:27:25.800728Z] Loop 4456: Loss: 2.03e-02, Avg Return: 0.857, Regret: 0.0071, Entropy: 0.1144 +[2026-03-20T18:27:26.653817Z] Loop 4457: Loss: 2.13e-02, Avg Return: 0.859, Regret: 0.0071, Entropy: 0.1136 +[2026-03-20T18:27:27.508289Z] Loop 4458: Loss: 2.00e-02, Avg Return: 0.859, Regret: 0.0071, Entropy: 0.1132 +[2026-03-20T18:27:28.361823Z] Loop 4459: Loss: 1.97e-02, Avg Return: 0.860, Regret: 0.0071, Entropy: 0.1131 +[2026-03-20T18:27:29.256454Z] Loop 4460: Loss: 2.08e-02, Avg Return: 0.860, Regret: 0.0037, Entropy: 0.1195 +[2026-03-20T18:27:30.110684Z] Loop 4461: Loss: 1.92e-02, Avg Return: 0.861, Regret: 0.0037, Entropy: 0.1156 +[2026-03-20T18:27:30.965234Z] Loop 4462: Loss: 2.12e-02, Avg Return: 0.859, Regret: 0.0037, Entropy: 0.1195 +[2026-03-20T18:27:31.818794Z] Loop 4463: Loss: 1.97e-02, Avg Return: 0.858, Regret: 0.0037, Entropy: 0.1168 +[2026-03-20T18:27:32.672303Z] Loop 4464: Loss: 2.08e-02, Avg Return: 0.859, Regret: 0.0037, Entropy: 0.1145 +[2026-03-20T18:27:33.525580Z] Loop 4465: Loss: 2.20e-02, Avg Return: 0.861, Regret: 0.0037, Entropy: 0.1182 +[2026-03-20T18:27:34.379405Z] Loop 4466: Loss: 1.96e-02, Avg Return: 0.860, Regret: 0.0037, Entropy: 0.1122 +[2026-03-20T18:27:35.233273Z] Loop 4467: Loss: 1.95e-02, Avg Return: 0.860, Regret: 0.0037, Entropy: 0.1088 +[2026-03-20T18:27:36.087015Z] Loop 4468: Loss: 1.86e-02, Avg Return: 0.859, Regret: 0.0037, Entropy: 0.1103 +[2026-03-20T18:27:36.940735Z] Loop 4469: Loss: 1.95e-02, Avg Return: 0.859, Regret: 0.0037, Entropy: 0.1097 +[2026-03-20T18:27:37.835687Z] Loop 4470: Loss: 2.03e-02, Avg Return: 0.860, Regret: 0.0041, Entropy: 0.1095 +[2026-03-20T18:27:38.689334Z] Loop 4471: Loss: 1.94e-02, Avg Return: 0.860, Regret: 0.0041, Entropy: 0.1093 +[2026-03-20T18:27:39.543537Z] Loop 4472: Loss: 2.08e-02, Avg Return: 0.859, Regret: 0.0041, Entropy: 0.1161 +[2026-03-20T18:27:40.398107Z] Loop 4473: Loss: 2.20e-02, Avg Return: 0.858, Regret: 0.0041, Entropy: 0.1180 +[2026-03-20T18:27:41.252047Z] Loop 4474: Loss: 2.04e-02, Avg Return: 0.857, Regret: 0.0041, Entropy: 0.1121 +[2026-03-20T18:27:42.105760Z] Loop 4475: Loss: 2.24e-02, Avg Return: 0.857, Regret: 0.0041, Entropy: 0.1211 +[2026-03-20T18:27:42.960278Z] Loop 4476: Loss: 2.18e-02, Avg Return: 0.858, Regret: 0.0041, Entropy: 0.1211 +[2026-03-20T18:27:43.814386Z] Loop 4477: Loss: 2.09e-02, Avg Return: 0.857, Regret: 0.0041, Entropy: 0.1154 +[2026-03-20T18:27:44.668480Z] Loop 4478: Loss: 2.20e-02, Avg Return: 0.857, Regret: 0.0041, Entropy: 0.1190 +[2026-03-20T18:27:45.522383Z] Loop 4479: Loss: 2.18e-02, Avg Return: 0.858, Regret: 0.0041, Entropy: 0.1182 +[2026-03-20T18:27:46.416718Z] Loop 4480: Loss: 1.97e-02, Avg Return: 0.859, Regret: 0.0044, Entropy: 0.1165 +[2026-03-20T18:27:47.270318Z] Loop 4481: Loss: 2.07e-02, Avg Return: 0.860, Regret: 0.0044, Entropy: 0.1137 +[2026-03-20T18:27:48.124975Z] Loop 4482: Loss: 2.20e-02, Avg Return: 0.859, Regret: 0.0044, Entropy: 0.1191 +[2026-03-20T18:27:48.978340Z] Loop 4483: Loss: 1.99e-02, Avg Return: 0.859, Regret: 0.0044, Entropy: 0.1127 +[2026-03-20T18:27:49.832011Z] Loop 4484: Loss: 2.25e-02, Avg Return: 0.859, Regret: 0.0044, Entropy: 0.1220 +[2026-03-20T18:27:50.685699Z] Loop 4485: Loss: 2.20e-02, Avg Return: 0.860, Regret: 0.0044, Entropy: 0.1183 +[2026-03-20T18:27:51.539788Z] Loop 4486: Loss: 2.17e-02, Avg Return: 0.860, Regret: 0.0044, Entropy: 0.1214 +[2026-03-20T18:27:52.392692Z] Loop 4487: Loss: 2.22e-02, Avg Return: 0.858, Regret: 0.0044, Entropy: 0.1213 +[2026-03-20T18:27:53.246501Z] Loop 4488: Loss: 2.12e-02, Avg Return: 0.858, Regret: 0.0044, Entropy: 0.1206 +[2026-03-20T18:27:54.100194Z] Loop 4489: Loss: 2.14e-02, Avg Return: 0.860, Regret: 0.0044, Entropy: 0.1191 +[2026-03-20T18:27:54.994547Z] Loop 4490: Loss: 2.10e-02, Avg Return: 0.860, Regret: 0.0036, Entropy: 0.1163 +[2026-03-20T18:27:55.848840Z] Loop 4491: Loss: 2.01e-02, Avg Return: 0.860, Regret: 0.0036, Entropy: 0.1170 +[2026-03-20T18:27:56.702344Z] Loop 4492: Loss: 2.00e-02, Avg Return: 0.860, Regret: 0.0036, Entropy: 0.1156 +[2026-03-20T18:27:57.556276Z] Loop 4493: Loss: 2.00e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.1162 +[2026-03-20T18:27:58.410513Z] Loop 4494: Loss: 2.09e-02, Avg Return: 0.860, Regret: 0.0036, Entropy: 0.1181 +[2026-03-20T18:27:59.264749Z] Loop 4495: Loss: 2.10e-02, Avg Return: 0.860, Regret: 0.0036, Entropy: 0.1168 +[2026-03-20T18:28:00.117787Z] Loop 4496: Loss: 2.26e-02, Avg Return: 0.860, Regret: 0.0036, Entropy: 0.1205 +[2026-03-20T18:28:00.970877Z] Loop 4497: Loss: 2.08e-02, Avg Return: 0.860, Regret: 0.0036, Entropy: 0.1147 +[2026-03-20T18:28:01.824560Z] Loop 4498: Loss: 2.04e-02, Avg Return: 0.860, Regret: 0.0036, Entropy: 0.1154 +[2026-03-20T18:28:02.677973Z] Loop 4499: Loss: 1.79e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.1049 +[2026-03-20T18:28:03.571086Z] Loop 4500: Loss: 1.93e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.1049 +[2026-03-20T18:28:04.424095Z] Loop 4501: Loss: 1.94e-02, Avg Return: 0.860, Regret: 0.0028, Entropy: 0.1072 +[2026-03-20T18:28:05.278047Z] Loop 4502: Loss: 1.75e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.0993 +[2026-03-20T18:28:06.133289Z] Loop 4503: Loss: 1.91e-02, Avg Return: 0.860, Regret: 0.0028, Entropy: 0.1080 +[2026-03-20T18:28:06.988202Z] Loop 4504: Loss: 1.76e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.1007 +[2026-03-20T18:28:07.842140Z] Loop 4505: Loss: 1.92e-02, Avg Return: 0.860, Regret: 0.0028, Entropy: 0.1035 +[2026-03-20T18:28:08.697103Z] Loop 4506: Loss: 1.89e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.1056 +[2026-03-20T18:28:09.552174Z] Loop 4507: Loss: 2.01e-02, Avg Return: 0.860, Regret: 0.0028, Entropy: 0.1094 +[2026-03-20T18:28:10.407127Z] Loop 4508: Loss: 1.80e-02, Avg Return: 0.860, Regret: 0.0028, Entropy: 0.1037 +[2026-03-20T18:28:11.262557Z] Loop 4509: Loss: 1.78e-02, Avg Return: 0.860, Regret: 0.0028, Entropy: 0.1022 +[2026-03-20T18:28:12.160539Z] Loop 4510: Loss: 1.83e-02, Avg Return: 0.860, Regret: 0.0038, Entropy: 0.1047 +[2026-03-20T18:28:13.013141Z] Loop 4511: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0038, Entropy: 0.1011 +[2026-03-20T18:28:13.867380Z] Loop 4512: Loss: 1.83e-02, Avg Return: 0.862, Regret: 0.0038, Entropy: 0.0974 +[2026-03-20T18:28:14.722448Z] Loop 4513: Loss: 1.82e-02, Avg Return: 0.861, Regret: 0.0038, Entropy: 0.1023 +[2026-03-20T18:28:15.575894Z] Loop 4514: Loss: 1.81e-02, Avg Return: 0.863, Regret: 0.0038, Entropy: 0.1012 +[2026-03-20T18:28:16.429117Z] Loop 4515: Loss: 1.93e-02, Avg Return: 0.862, Regret: 0.0038, Entropy: 0.1087 +[2026-03-20T18:28:17.283082Z] Loop 4516: Loss: 1.98e-02, Avg Return: 0.860, Regret: 0.0038, Entropy: 0.1068 +[2026-03-20T18:28:18.137157Z] Loop 4517: Loss: 1.75e-02, Avg Return: 0.859, Regret: 0.0038, Entropy: 0.1025 +[2026-03-20T18:28:18.990836Z] Loop 4518: Loss: 1.93e-02, Avg Return: 0.861, Regret: 0.0038, Entropy: 0.1104 +[2026-03-20T18:28:19.843397Z] Loop 4519: Loss: 1.93e-02, Avg Return: 0.861, Regret: 0.0038, Entropy: 0.1055 +[2026-03-20T18:28:20.737096Z] Loop 4520: Loss: 1.86e-02, Avg Return: 0.861, Regret: 0.0031, Entropy: 0.1080 +[2026-03-20T18:28:21.591847Z] Loop 4521: Loss: 1.82e-02, Avg Return: 0.859, Regret: 0.0031, Entropy: 0.1014 +[2026-03-20T18:28:22.446063Z] Loop 4522: Loss: 1.87e-02, Avg Return: 0.859, Regret: 0.0031, Entropy: 0.1077 +[2026-03-20T18:28:23.300492Z] Loop 4523: Loss: 2.00e-02, Avg Return: 0.858, Regret: 0.0031, Entropy: 0.1092 +[2026-03-20T18:28:24.153166Z] Loop 4524: Loss: 2.00e-02, Avg Return: 0.857, Regret: 0.0031, Entropy: 0.1054 +[2026-03-20T18:28:25.007120Z] Loop 4525: Loss: 2.01e-02, Avg Return: 0.854, Regret: 0.0031, Entropy: 0.1062 +[2026-03-20T18:28:25.861763Z] Loop 4526: Loss: 1.97e-02, Avg Return: 0.854, Regret: 0.0031, Entropy: 0.1066 +[2026-03-20T18:28:26.716356Z] Loop 4527: Loss: 1.90e-02, Avg Return: 0.857, Regret: 0.0031, Entropy: 0.1015 +[2026-03-20T18:28:27.569275Z] Loop 4528: Loss: 1.94e-02, Avg Return: 0.859, Regret: 0.0031, Entropy: 0.1035 +[2026-03-20T18:28:28.422787Z] Loop 4529: Loss: 1.99e-02, Avg Return: 0.862, Regret: 0.0031, Entropy: 0.1042 +[2026-03-20T18:28:29.317744Z] Loop 4530: Loss: 1.77e-02, Avg Return: 0.861, Regret: 0.0030, Entropy: 0.0975 +[2026-03-20T18:28:30.173201Z] Loop 4531: Loss: 1.72e-02, Avg Return: 0.860, Regret: 0.0030, Entropy: 0.0975 +[2026-03-20T18:28:31.026951Z] Loop 4532: Loss: 1.83e-02, Avg Return: 0.859, Regret: 0.0030, Entropy: 0.1059 +[2026-03-20T18:28:31.881129Z] Loop 4533: Loss: 2.03e-02, Avg Return: 0.858, Regret: 0.0030, Entropy: 0.1113 +[2026-03-20T18:28:32.735676Z] Loop 4534: Loss: 1.96e-02, Avg Return: 0.857, Regret: 0.0030, Entropy: 0.1132 +[2026-03-20T18:28:33.590197Z] Loop 4535: Loss: 2.09e-02, Avg Return: 0.858, Regret: 0.0030, Entropy: 0.1117 +[2026-03-20T18:28:34.443483Z] Loop 4536: Loss: 1.91e-02, Avg Return: 0.857, Regret: 0.0030, Entropy: 0.1044 +[2026-03-20T18:28:35.297889Z] Loop 4537: Loss: 1.98e-02, Avg Return: 0.857, Regret: 0.0030, Entropy: 0.1125 +[2026-03-20T18:28:36.151875Z] Loop 4538: Loss: 2.10e-02, Avg Return: 0.859, Regret: 0.0030, Entropy: 0.1103 +[2026-03-20T18:28:37.007370Z] Loop 4539: Loss: 1.91e-02, Avg Return: 0.859, Regret: 0.0030, Entropy: 0.1069 +[2026-03-20T18:28:37.903658Z] Loop 4540: Loss: 1.84e-02, Avg Return: 0.860, Regret: 0.0040, Entropy: 0.1055 +[2026-03-20T18:28:38.758580Z] Loop 4541: Loss: 1.93e-02, Avg Return: 0.858, Regret: 0.0040, Entropy: 0.1108 +[2026-03-20T18:28:39.613461Z] Loop 4542: Loss: 1.90e-02, Avg Return: 0.859, Regret: 0.0040, Entropy: 0.1074 +[2026-03-20T18:28:40.466560Z] Loop 4543: Loss: 2.04e-02, Avg Return: 0.861, Regret: 0.0040, Entropy: 0.1109 +[2026-03-20T18:28:41.321218Z] Loop 4544: Loss: 2.01e-02, Avg Return: 0.859, Regret: 0.0040, Entropy: 0.1122 +[2026-03-20T18:28:42.175525Z] Loop 4545: Loss: 2.08e-02, Avg Return: 0.858, Regret: 0.0040, Entropy: 0.1137 +[2026-03-20T18:28:43.030066Z] Loop 4546: Loss: 2.09e-02, Avg Return: 0.858, Regret: 0.0040, Entropy: 0.1194 +[2026-03-20T18:28:43.884656Z] Loop 4547: Loss: 2.11e-02, Avg Return: 0.858, Regret: 0.0040, Entropy: 0.1168 +[2026-03-20T18:28:44.739742Z] Loop 4548: Loss: 2.13e-02, Avg Return: 0.858, Regret: 0.0040, Entropy: 0.1200 +[2026-03-20T18:28:45.594816Z] Loop 4549: Loss: 2.14e-02, Avg Return: 0.858, Regret: 0.0040, Entropy: 0.1195 +[2026-03-20T18:28:46.492719Z] Loop 4550: Loss: 2.00e-02, Avg Return: 0.859, Regret: 0.0045, Entropy: 0.1110 +[2026-03-20T18:28:47.346375Z] Loop 4551: Loss: 1.91e-02, Avg Return: 0.858, Regret: 0.0045, Entropy: 0.1071 +[2026-03-20T18:28:48.199477Z] Loop 4552: Loss: 1.98e-02, Avg Return: 0.859, Regret: 0.0045, Entropy: 0.1081 +[2026-03-20T18:28:49.054759Z] Loop 4553: Loss: 2.01e-02, Avg Return: 0.859, Regret: 0.0045, Entropy: 0.1144 +[2026-03-20T18:28:49.909251Z] Loop 4554: Loss: 1.96e-02, Avg Return: 0.860, Regret: 0.0045, Entropy: 0.1127 +[2026-03-20T18:28:50.762890Z] Loop 4555: Loss: 1.88e-02, Avg Return: 0.860, Regret: 0.0045, Entropy: 0.1079 +[2026-03-20T18:28:51.616540Z] Loop 4556: Loss: 1.89e-02, Avg Return: 0.862, Regret: 0.0045, Entropy: 0.1095 +[2026-03-20T18:28:52.470650Z] Loop 4557: Loss: 1.82e-02, Avg Return: 0.861, Regret: 0.0045, Entropy: 0.1083 +[2026-03-20T18:28:53.324341Z] Loop 4558: Loss: 1.97e-02, Avg Return: 0.860, Regret: 0.0045, Entropy: 0.1109 +[2026-03-20T18:28:54.178646Z] Loop 4559: Loss: 2.08e-02, Avg Return: 0.861, Regret: 0.0045, Entropy: 0.1174 +[2026-03-20T18:28:55.075807Z] Loop 4560: Loss: 2.16e-02, Avg Return: 0.860, Regret: 0.0028, Entropy: 0.1186 +[2026-03-20T18:28:55.929755Z] Loop 4561: Loss: 2.35e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.1244 +[2026-03-20T18:28:56.783171Z] Loop 4562: Loss: 2.12e-02, Avg Return: 0.860, Regret: 0.0028, Entropy: 0.1207 +[2026-03-20T18:28:57.636720Z] Loop 4563: Loss: 2.19e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.1239 +[2026-03-20T18:28:58.490994Z] Loop 4564: Loss: 2.29e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.1243 +[2026-03-20T18:28:59.345440Z] Loop 4565: Loss: 2.25e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.1269 +[2026-03-20T18:29:00.199651Z] Loop 4566: Loss: 2.37e-02, Avg Return: 0.860, Regret: 0.0028, Entropy: 0.1338 +[2026-03-20T18:29:01.055019Z] Loop 4567: Loss: 2.32e-02, Avg Return: 0.860, Regret: 0.0028, Entropy: 0.1316 +[2026-03-20T18:29:01.910645Z] Loop 4568: Loss: 2.09e-02, Avg Return: 0.860, Regret: 0.0028, Entropy: 0.1228 +[2026-03-20T18:29:02.764839Z] Loop 4569: Loss: 2.17e-02, Avg Return: 0.860, Regret: 0.0028, Entropy: 0.1177 +[2026-03-20T18:29:03.660075Z] Loop 4570: Loss: 2.05e-02, Avg Return: 0.860, Regret: 0.0034, Entropy: 0.1221 +[2026-03-20T18:29:04.513982Z] Loop 4571: Loss: 2.09e-02, Avg Return: 0.859, Regret: 0.0034, Entropy: 0.1176 +[2026-03-20T18:29:05.369011Z] Loop 4572: Loss: 2.24e-02, Avg Return: 0.859, Regret: 0.0034, Entropy: 0.1193 +[2026-03-20T18:29:06.223748Z] Loop 4573: Loss: 2.28e-02, Avg Return: 0.859, Regret: 0.0034, Entropy: 0.1224 +[2026-03-20T18:29:07.077375Z] Loop 4574: Loss: 2.13e-02, Avg Return: 0.855, Regret: 0.0034, Entropy: 0.1193 +[2026-03-20T18:29:07.931410Z] Loop 4575: Loss: 2.21e-02, Avg Return: 0.858, Regret: 0.0034, Entropy: 0.1254 +[2026-03-20T18:29:08.785331Z] Loop 4576: Loss: 2.06e-02, Avg Return: 0.857, Regret: 0.0034, Entropy: 0.1180 +[2026-03-20T18:29:09.639486Z] Loop 4577: Loss: 2.01e-02, Avg Return: 0.858, Regret: 0.0034, Entropy: 0.1084 +[2026-03-20T18:29:10.494040Z] Loop 4578: Loss: 2.15e-02, Avg Return: 0.858, Regret: 0.0034, Entropy: 0.1211 +[2026-03-20T18:29:11.347170Z] Loop 4579: Loss: 2.13e-02, Avg Return: 0.857, Regret: 0.0034, Entropy: 0.1158 +[2026-03-20T18:29:12.241474Z] Loop 4580: Loss: 2.17e-02, Avg Return: 0.858, Regret: 0.0057, Entropy: 0.1198 +[2026-03-20T18:29:13.095289Z] Loop 4581: Loss: 1.98e-02, Avg Return: 0.860, Regret: 0.0057, Entropy: 0.1136 +[2026-03-20T18:29:13.949850Z] Loop 4582: Loss: 2.00e-02, Avg Return: 0.860, Regret: 0.0057, Entropy: 0.1112 +[2026-03-20T18:29:14.803399Z] Loop 4583: Loss: 2.03e-02, Avg Return: 0.861, Regret: 0.0057, Entropy: 0.1111 +[2026-03-20T18:29:15.657394Z] Loop 4584: Loss: 1.78e-02, Avg Return: 0.860, Regret: 0.0057, Entropy: 0.1035 +[2026-03-20T18:29:16.512420Z] Loop 4585: Loss: 1.85e-02, Avg Return: 0.860, Regret: 0.0057, Entropy: 0.1044 +[2026-03-20T18:29:17.367712Z] Loop 4586: Loss: 1.95e-02, Avg Return: 0.862, Regret: 0.0057, Entropy: 0.1061 +[2026-03-20T18:29:18.221330Z] Loop 4587: Loss: 1.81e-02, Avg Return: 0.860, Regret: 0.0057, Entropy: 0.1007 +[2026-03-20T18:29:19.078560Z] Loop 4588: Loss: 2.01e-02, Avg Return: 0.861, Regret: 0.0057, Entropy: 0.1087 +[2026-03-20T18:29:19.934230Z] Loop 4589: Loss: 1.76e-02, Avg Return: 0.859, Regret: 0.0057, Entropy: 0.1025 +[2026-03-20T18:29:20.830230Z] Loop 4590: Loss: 2.03e-02, Avg Return: 0.861, Regret: 0.0038, Entropy: 0.1100 +[2026-03-20T18:29:21.684645Z] Loop 4591: Loss: 1.90e-02, Avg Return: 0.859, Regret: 0.0038, Entropy: 0.1066 +[2026-03-20T18:29:22.539513Z] Loop 4592: Loss: 1.93e-02, Avg Return: 0.860, Regret: 0.0038, Entropy: 0.1112 +[2026-03-20T18:29:23.394344Z] Loop 4593: Loss: 2.02e-02, Avg Return: 0.862, Regret: 0.0038, Entropy: 0.1094 +[2026-03-20T18:29:24.248471Z] Loop 4594: Loss: 2.08e-02, Avg Return: 0.862, Regret: 0.0038, Entropy: 0.1124 +[2026-03-20T18:29:25.102653Z] Loop 4595: Loss: 1.99e-02, Avg Return: 0.861, Regret: 0.0038, Entropy: 0.1101 +[2026-03-20T18:29:25.956292Z] Loop 4596: Loss: 1.79e-02, Avg Return: 0.861, Regret: 0.0038, Entropy: 0.1042 +[2026-03-20T18:29:26.810020Z] Loop 4597: Loss: 1.97e-02, Avg Return: 0.862, Regret: 0.0038, Entropy: 0.1125 +[2026-03-20T18:29:27.665207Z] Loop 4598: Loss: 2.05e-02, Avg Return: 0.861, Regret: 0.0038, Entropy: 0.1132 +[2026-03-20T18:29:28.519476Z] Loop 4599: Loss: 1.89e-02, Avg Return: 0.861, Regret: 0.0038, Entropy: 0.1119 +[2026-03-20T18:29:29.414891Z] Loop 4600: Loss: 2.12e-02, Avg Return: 0.859, Regret: 0.0043, Entropy: 0.1177 +[2026-03-20T18:29:30.268103Z] Loop 4601: Loss: 2.20e-02, Avg Return: 0.858, Regret: 0.0043, Entropy: 0.1215 +[2026-03-20T18:29:31.121920Z] Loop 4602: Loss: 2.10e-02, Avg Return: 0.858, Regret: 0.0043, Entropy: 0.1178 +[2026-03-20T18:29:31.976644Z] Loop 4603: Loss: 1.88e-02, Avg Return: 0.859, Regret: 0.0043, Entropy: 0.1119 +[2026-03-20T18:29:32.831046Z] Loop 4604: Loss: 2.20e-02, Avg Return: 0.858, Regret: 0.0043, Entropy: 0.1191 +[2026-03-20T18:29:33.684664Z] Loop 4605: Loss: 1.88e-02, Avg Return: 0.859, Regret: 0.0043, Entropy: 0.1087 +[2026-03-20T18:29:34.539568Z] Loop 4606: Loss: 1.89e-02, Avg Return: 0.860, Regret: 0.0043, Entropy: 0.1109 +[2026-03-20T18:29:35.393404Z] Loop 4607: Loss: 2.13e-02, Avg Return: 0.859, Regret: 0.0043, Entropy: 0.1152 +[2026-03-20T18:29:36.248281Z] Loop 4608: Loss: 2.03e-02, Avg Return: 0.859, Regret: 0.0043, Entropy: 0.1111 +[2026-03-20T18:29:37.103242Z] Loop 4609: Loss: 1.84e-02, Avg Return: 0.860, Regret: 0.0043, Entropy: 0.1087 +[2026-03-20T18:29:37.997617Z] Loop 4610: Loss: 1.88e-02, Avg Return: 0.860, Regret: 0.0038, Entropy: 0.1057 +[2026-03-20T18:29:38.850510Z] Loop 4611: Loss: 1.92e-02, Avg Return: 0.860, Regret: 0.0038, Entropy: 0.1052 +[2026-03-20T18:29:39.706500Z] Loop 4612: Loss: 1.82e-02, Avg Return: 0.861, Regret: 0.0038, Entropy: 0.1091 +[2026-03-20T18:29:40.561228Z] Loop 4613: Loss: 1.96e-02, Avg Return: 0.861, Regret: 0.0038, Entropy: 0.1067 +[2026-03-20T18:29:41.415825Z] Loop 4614: Loss: 1.73e-02, Avg Return: 0.861, Regret: 0.0038, Entropy: 0.1026 +[2026-03-20T18:29:42.270890Z] Loop 4615: Loss: 1.95e-02, Avg Return: 0.861, Regret: 0.0038, Entropy: 0.1026 +[2026-03-20T18:29:43.126879Z] Loop 4616: Loss: 1.82e-02, Avg Return: 0.861, Regret: 0.0038, Entropy: 0.1053 +[2026-03-20T18:29:43.982244Z] Loop 4617: Loss: 1.80e-02, Avg Return: 0.859, Regret: 0.0038, Entropy: 0.1019 +[2026-03-20T18:29:44.836799Z] Loop 4618: Loss: 1.96e-02, Avg Return: 0.859, Regret: 0.0038, Entropy: 0.1086 +[2026-03-20T18:29:45.690267Z] Loop 4619: Loss: 1.93e-02, Avg Return: 0.860, Regret: 0.0038, Entropy: 0.1119 +[2026-03-20T18:29:46.582858Z] Loop 4620: Loss: 1.88e-02, Avg Return: 0.859, Regret: 0.0044, Entropy: 0.1025 +[2026-03-20T18:29:47.435779Z] Loop 4621: Loss: 1.86e-02, Avg Return: 0.861, Regret: 0.0044, Entropy: 0.0997 +[2026-03-20T18:29:48.290219Z] Loop 4622: Loss: 1.77e-02, Avg Return: 0.861, Regret: 0.0044, Entropy: 0.1032 +[2026-03-20T18:29:49.144043Z] Loop 4623: Loss: 1.80e-02, Avg Return: 0.860, Regret: 0.0044, Entropy: 0.1007 +[2026-03-20T18:29:49.998425Z] Loop 4624: Loss: 1.81e-02, Avg Return: 0.860, Regret: 0.0044, Entropy: 0.1021 +[2026-03-20T18:29:50.852689Z] Loop 4625: Loss: 1.90e-02, Avg Return: 0.860, Regret: 0.0044, Entropy: 0.1014 +[2026-03-20T18:29:51.707256Z] Loop 4626: Loss: 1.98e-02, Avg Return: 0.861, Regret: 0.0044, Entropy: 0.1057 +[2026-03-20T18:29:52.561939Z] Loop 4627: Loss: 1.92e-02, Avg Return: 0.861, Regret: 0.0044, Entropy: 0.1039 +[2026-03-20T18:29:53.416239Z] Loop 4628: Loss: 2.04e-02, Avg Return: 0.860, Regret: 0.0044, Entropy: 0.1058 +[2026-03-20T18:29:54.270882Z] Loop 4629: Loss: 2.07e-02, Avg Return: 0.857, Regret: 0.0044, Entropy: 0.1110 +[2026-03-20T18:29:55.164858Z] Loop 4630: Loss: 1.98e-02, Avg Return: 0.857, Regret: 0.0064, Entropy: 0.1115 +[2026-03-20T18:29:56.018306Z] Loop 4631: Loss: 2.18e-02, Avg Return: 0.857, Regret: 0.0064, Entropy: 0.1174 +[2026-03-20T18:29:56.871588Z] Loop 4632: Loss: 1.97e-02, Avg Return: 0.858, Regret: 0.0064, Entropy: 0.1082 +[2026-03-20T18:29:57.725477Z] Loop 4633: Loss: 1.92e-02, Avg Return: 0.859, Regret: 0.0064, Entropy: 0.1076 +[2026-03-20T18:29:58.578248Z] Loop 4634: Loss: 1.98e-02, Avg Return: 0.861, Regret: 0.0064, Entropy: 0.1100 +[2026-03-20T18:29:59.431858Z] Loop 4635: Loss: 1.78e-02, Avg Return: 0.861, Regret: 0.0064, Entropy: 0.1003 +[2026-03-20T18:30:00.285771Z] Loop 4636: Loss: 1.81e-02, Avg Return: 0.860, Regret: 0.0064, Entropy: 0.0980 +[2026-03-20T18:30:01.138652Z] Loop 4637: Loss: 1.81e-02, Avg Return: 0.861, Regret: 0.0064, Entropy: 0.1063 +[2026-03-20T18:30:01.992835Z] Loop 4638: Loss: 2.07e-02, Avg Return: 0.861, Regret: 0.0064, Entropy: 0.1107 +[2026-03-20T18:30:02.848727Z] Loop 4639: Loss: 2.02e-02, Avg Return: 0.860, Regret: 0.0064, Entropy: 0.1125 +[2026-03-20T18:30:03.743684Z] Loop 4640: Loss: 2.19e-02, Avg Return: 0.857, Regret: 0.0043, Entropy: 0.1210 +[2026-03-20T18:30:04.596939Z] Loop 4641: Loss: 2.10e-02, Avg Return: 0.859, Regret: 0.0043, Entropy: 0.1165 +[2026-03-20T18:30:05.450247Z] Loop 4642: Loss: 2.37e-02, Avg Return: 0.857, Regret: 0.0043, Entropy: 0.1298 +[2026-03-20T18:30:06.304978Z] Loop 4643: Loss: 2.60e-02, Avg Return: 0.854, Regret: 0.0043, Entropy: 0.1378 +[2026-03-20T18:30:07.160032Z] Loop 4644: Loss: 2.39e-02, Avg Return: 0.855, Regret: 0.0043, Entropy: 0.1317 +[2026-03-20T18:30:08.015881Z] Loop 4645: Loss: 2.46e-02, Avg Return: 0.857, Regret: 0.0043, Entropy: 0.1313 +[2026-03-20T18:30:08.870933Z] Loop 4646: Loss: 2.20e-02, Avg Return: 0.859, Regret: 0.0043, Entropy: 0.1236 +[2026-03-20T18:30:09.726136Z] Loop 4647: Loss: 2.25e-02, Avg Return: 0.858, Regret: 0.0043, Entropy: 0.1262 +[2026-03-20T18:30:10.580066Z] Loop 4648: Loss: 2.04e-02, Avg Return: 0.860, Regret: 0.0043, Entropy: 0.1154 +[2026-03-20T18:30:11.433829Z] Loop 4649: Loss: 2.05e-02, Avg Return: 0.860, Regret: 0.0043, Entropy: 0.1156 +[2026-03-20T18:30:12.327772Z] Loop 4650: Loss: 2.03e-02, Avg Return: 0.859, Regret: 0.0036, Entropy: 0.1119 +[2026-03-20T18:30:13.180253Z] Loop 4651: Loss: 2.08e-02, Avg Return: 0.859, Regret: 0.0036, Entropy: 0.1124 +[2026-03-20T18:30:14.034382Z] Loop 4652: Loss: 2.14e-02, Avg Return: 0.855, Regret: 0.0036, Entropy: 0.1197 +[2026-03-20T18:30:14.889697Z] Loop 4653: Loss: 2.05e-02, Avg Return: 0.853, Regret: 0.0036, Entropy: 0.1082 +[2026-03-20T18:30:15.745515Z] Loop 4654: Loss: 2.21e-02, Avg Return: 0.854, Regret: 0.0036, Entropy: 0.1156 +[2026-03-20T18:30:16.600273Z] Loop 4655: Loss: 2.21e-02, Avg Return: 0.858, Regret: 0.0036, Entropy: 0.1165 +[2026-03-20T18:30:17.454610Z] Loop 4656: Loss: 2.04e-02, Avg Return: 0.859, Regret: 0.0036, Entropy: 0.1099 +[2026-03-20T18:30:18.310940Z] Loop 4657: Loss: 2.03e-02, Avg Return: 0.860, Regret: 0.0036, Entropy: 0.1124 +[2026-03-20T18:30:19.166555Z] Loop 4658: Loss: 2.00e-02, Avg Return: 0.861, Regret: 0.0036, Entropy: 0.1072 +[2026-03-20T18:30:20.021932Z] Loop 4659: Loss: 1.90e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.1039 +[2026-03-20T18:30:20.915598Z] Loop 4660: Loss: 2.02e-02, Avg Return: 0.861, Regret: 0.0031, Entropy: 0.1136 +[2026-03-20T18:30:21.769456Z] Loop 4661: Loss: 2.08e-02, Avg Return: 0.859, Regret: 0.0031, Entropy: 0.1125 +[2026-03-20T18:30:22.624378Z] Loop 4662: Loss: 1.96e-02, Avg Return: 0.859, Regret: 0.0031, Entropy: 0.1133 +[2026-03-20T18:30:23.478170Z] Loop 4663: Loss: 2.11e-02, Avg Return: 0.859, Regret: 0.0031, Entropy: 0.1186 +[2026-03-20T18:30:24.331909Z] Loop 4664: Loss: 2.20e-02, Avg Return: 0.859, Regret: 0.0031, Entropy: 0.1220 +[2026-03-20T18:30:25.185931Z] Loop 4665: Loss: 2.26e-02, Avg Return: 0.859, Regret: 0.0031, Entropy: 0.1184 +[2026-03-20T18:30:26.039665Z] Loop 4666: Loss: 2.10e-02, Avg Return: 0.859, Regret: 0.0031, Entropy: 0.1195 +[2026-03-20T18:30:26.894142Z] Loop 4667: Loss: 2.08e-02, Avg Return: 0.860, Regret: 0.0031, Entropy: 0.1158 +[2026-03-20T18:30:27.747670Z] Loop 4668: Loss: 1.90e-02, Avg Return: 0.862, Regret: 0.0031, Entropy: 0.1091 +[2026-03-20T18:30:28.601364Z] Loop 4669: Loss: 1.75e-02, Avg Return: 0.861, Regret: 0.0031, Entropy: 0.1039 +[2026-03-20T18:30:29.496179Z] Loop 4670: Loss: 1.92e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.1102 +[2026-03-20T18:30:30.351323Z] Loop 4671: Loss: 1.95e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.1094 +[2026-03-20T18:30:31.206670Z] Loop 4672: Loss: 2.02e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.1098 +[2026-03-20T18:30:32.061617Z] Loop 4673: Loss: 1.87e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.1075 +[2026-03-20T18:30:32.915288Z] Loop 4674: Loss: 1.88e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.1049 +[2026-03-20T18:30:33.769374Z] Loop 4675: Loss: 2.02e-02, Avg Return: 0.860, Regret: 0.0020, Entropy: 0.1105 +[2026-03-20T18:30:34.623012Z] Loop 4676: Loss: 1.95e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.1075 +[2026-03-20T18:30:35.476693Z] Loop 4677: Loss: 1.90e-02, Avg Return: 0.860, Regret: 0.0020, Entropy: 0.1086 +[2026-03-20T18:30:36.329441Z] Loop 4678: Loss: 2.04e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.1173 +[2026-03-20T18:30:37.182852Z] Loop 4679: Loss: 2.08e-02, Avg Return: 0.860, Regret: 0.0020, Entropy: 0.1161 +[2026-03-20T18:30:38.077531Z] Loop 4680: Loss: 2.25e-02, Avg Return: 0.861, Regret: 0.0036, Entropy: 0.1235 +[2026-03-20T18:30:38.931574Z] Loop 4681: Loss: 2.22e-02, Avg Return: 0.856, Regret: 0.0036, Entropy: 0.1291 +[2026-03-20T18:30:39.786231Z] Loop 4682: Loss: 2.44e-02, Avg Return: 0.854, Regret: 0.0036, Entropy: 0.1380 +[2026-03-20T18:30:40.641126Z] Loop 4683: Loss: 2.24e-02, Avg Return: 0.858, Regret: 0.0036, Entropy: 0.1285 +[2026-03-20T18:30:41.496351Z] Loop 4684: Loss: 2.20e-02, Avg Return: 0.859, Regret: 0.0036, Entropy: 0.1239 +[2026-03-20T18:30:42.351471Z] Loop 4685: Loss: 2.30e-02, Avg Return: 0.860, Regret: 0.0036, Entropy: 0.1268 +[2026-03-20T18:30:43.206013Z] Loop 4686: Loss: 2.25e-02, Avg Return: 0.861, Regret: 0.0036, Entropy: 0.1246 +[2026-03-20T18:30:44.058997Z] Loop 4687: Loss: 2.05e-02, Avg Return: 0.859, Regret: 0.0036, Entropy: 0.1222 +[2026-03-20T18:30:44.911973Z] Loop 4688: Loss: 2.19e-02, Avg Return: 0.859, Regret: 0.0036, Entropy: 0.1221 +[2026-03-20T18:30:45.766291Z] Loop 4689: Loss: 2.18e-02, Avg Return: 0.860, Regret: 0.0036, Entropy: 0.1176 +[2026-03-20T18:30:46.660625Z] Loop 4690: Loss: 2.08e-02, Avg Return: 0.861, Regret: 0.0031, Entropy: 0.1145 +[2026-03-20T18:30:47.514631Z] Loop 4691: Loss: 1.78e-02, Avg Return: 0.860, Regret: 0.0031, Entropy: 0.1073 +[2026-03-20T18:30:48.369557Z] Loop 4692: Loss: 2.05e-02, Avg Return: 0.860, Regret: 0.0031, Entropy: 0.1162 +[2026-03-20T18:30:49.225262Z] Loop 4693: Loss: 2.06e-02, Avg Return: 0.862, Regret: 0.0031, Entropy: 0.1107 +[2026-03-20T18:30:50.079714Z] Loop 4694: Loss: 1.85e-02, Avg Return: 0.861, Regret: 0.0031, Entropy: 0.1070 +[2026-03-20T18:30:50.934179Z] Loop 4695: Loss: 2.09e-02, Avg Return: 0.861, Regret: 0.0031, Entropy: 0.1116 +[2026-03-20T18:30:51.787755Z] Loop 4696: Loss: 2.16e-02, Avg Return: 0.857, Regret: 0.0031, Entropy: 0.1215 +[2026-03-20T18:30:52.641852Z] Loop 4697: Loss: 2.40e-02, Avg Return: 0.858, Regret: 0.0031, Entropy: 0.1329 +[2026-03-20T18:30:53.496936Z] Loop 4698: Loss: 1.97e-02, Avg Return: 0.860, Regret: 0.0031, Entropy: 0.1171 +[2026-03-20T18:30:54.352242Z] Loop 4699: Loss: 1.96e-02, Avg Return: 0.861, Regret: 0.0031, Entropy: 0.1120 +[2026-03-20T18:30:55.248357Z] Loop 4700: Loss: 2.11e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.1141 +[2026-03-20T18:30:56.102587Z] Loop 4701: Loss: 2.12e-02, Avg Return: 0.859, Regret: 0.0024, Entropy: 0.1122 +[2026-03-20T18:30:56.957378Z] Loop 4702: Loss: 2.29e-02, Avg Return: 0.858, Regret: 0.0024, Entropy: 0.1224 +[2026-03-20T18:30:57.812452Z] Loop 4703: Loss: 2.39e-02, Avg Return: 0.854, Regret: 0.0024, Entropy: 0.1213 +[2026-03-20T18:30:58.667040Z] Loop 4704: Loss: 2.36e-02, Avg Return: 0.853, Regret: 0.0024, Entropy: 0.1270 +[2026-03-20T18:30:59.521624Z] Loop 4705: Loss: 2.39e-02, Avg Return: 0.852, Regret: 0.0024, Entropy: 0.1268 +[2026-03-20T18:31:00.375655Z] Loop 4706: Loss: 2.40e-02, Avg Return: 0.858, Regret: 0.0024, Entropy: 0.1313 +[2026-03-20T18:31:01.229561Z] Loop 4707: Loss: 2.20e-02, Avg Return: 0.858, Regret: 0.0024, Entropy: 0.1230 +[2026-03-20T18:31:02.083198Z] Loop 4708: Loss: 2.15e-02, Avg Return: 0.860, Regret: 0.0024, Entropy: 0.1229 +[2026-03-20T18:31:02.936876Z] Loop 4709: Loss: 2.13e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.1215 +[2026-03-20T18:31:03.832676Z] Loop 4710: Loss: 2.40e-02, Avg Return: 0.861, Regret: 0.0045, Entropy: 0.1354 +[2026-03-20T18:31:04.686925Z] Loop 4711: Loss: 2.36e-02, Avg Return: 0.859, Regret: 0.0045, Entropy: 0.1354 +[2026-03-20T18:31:05.542300Z] Loop 4712: Loss: 2.28e-02, Avg Return: 0.859, Regret: 0.0045, Entropy: 0.1329 +[2026-03-20T18:31:06.397155Z] Loop 4713: Loss: 2.45e-02, Avg Return: 0.859, Regret: 0.0045, Entropy: 0.1371 +[2026-03-20T18:31:07.251995Z] Loop 4714: Loss: 2.52e-02, Avg Return: 0.858, Regret: 0.0045, Entropy: 0.1354 +[2026-03-20T18:31:08.106121Z] Loop 4715: Loss: 2.31e-02, Avg Return: 0.860, Regret: 0.0045, Entropy: 0.1307 +[2026-03-20T18:31:08.960962Z] Loop 4716: Loss: 2.24e-02, Avg Return: 0.860, Regret: 0.0045, Entropy: 0.1288 +[2026-03-20T18:31:09.816227Z] Loop 4717: Loss: 2.20e-02, Avg Return: 0.860, Regret: 0.0045, Entropy: 0.1277 +[2026-03-20T18:31:10.671361Z] Loop 4718: Loss: 2.11e-02, Avg Return: 0.860, Regret: 0.0045, Entropy: 0.1254 +[2026-03-20T18:31:11.525298Z] Loop 4719: Loss: 2.19e-02, Avg Return: 0.859, Regret: 0.0045, Entropy: 0.1283 +[2026-03-20T18:31:12.420691Z] Loop 4720: Loss: 2.16e-02, Avg Return: 0.860, Regret: 0.0048, Entropy: 0.1246 +[2026-03-20T18:31:13.275442Z] Loop 4721: Loss: 2.34e-02, Avg Return: 0.859, Regret: 0.0048, Entropy: 0.1311 +[2026-03-20T18:31:14.130670Z] Loop 4722: Loss: 2.22e-02, Avg Return: 0.859, Regret: 0.0048, Entropy: 0.1278 +[2026-03-20T18:31:14.984269Z] Loop 4723: Loss: 2.08e-02, Avg Return: 0.859, Regret: 0.0048, Entropy: 0.1225 +[2026-03-20T18:31:15.838136Z] Loop 4724: Loss: 2.31e-02, Avg Return: 0.859, Regret: 0.0048, Entropy: 0.1299 +[2026-03-20T18:31:16.692662Z] Loop 4725: Loss: 2.04e-02, Avg Return: 0.861, Regret: 0.0048, Entropy: 0.1189 +[2026-03-20T18:31:17.547131Z] Loop 4726: Loss: 2.13e-02, Avg Return: 0.859, Regret: 0.0048, Entropy: 0.1169 +[2026-03-20T18:31:18.401478Z] Loop 4727: Loss: 2.08e-02, Avg Return: 0.860, Regret: 0.0048, Entropy: 0.1157 +[2026-03-20T18:31:19.254915Z] Loop 4728: Loss: 1.97e-02, Avg Return: 0.862, Regret: 0.0048, Entropy: 0.1147 +[2026-03-20T18:31:20.108314Z] Loop 4729: Loss: 1.95e-02, Avg Return: 0.861, Regret: 0.0048, Entropy: 0.1105 +[2026-03-20T18:31:21.004192Z] Loop 4730: Loss: 1.94e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.1129 +[2026-03-20T18:31:21.858249Z] Loop 4731: Loss: 2.02e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.1139 +[2026-03-20T18:31:22.712276Z] Loop 4732: Loss: 2.14e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.1157 +[2026-03-20T18:31:23.566763Z] Loop 4733: Loss: 1.96e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.1158 +[2026-03-20T18:31:24.421541Z] Loop 4734: Loss: 2.04e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.1115 +[2026-03-20T18:31:25.275843Z] Loop 4735: Loss: 2.05e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.1155 +[2026-03-20T18:31:26.130663Z] Loop 4736: Loss: 2.08e-02, Avg Return: 0.858, Regret: 0.0022, Entropy: 0.1156 +[2026-03-20T18:31:26.983589Z] Loop 4737: Loss: 2.16e-02, Avg Return: 0.858, Regret: 0.0022, Entropy: 0.1197 +[2026-03-20T18:31:27.836233Z] Loop 4738: Loss: 2.22e-02, Avg Return: 0.858, Regret: 0.0022, Entropy: 0.1224 +[2026-03-20T18:31:28.690376Z] Loop 4739: Loss: 2.05e-02, Avg Return: 0.858, Regret: 0.0022, Entropy: 0.1161 +[2026-03-20T18:31:29.583653Z] Loop 4740: Loss: 2.17e-02, Avg Return: 0.857, Regret: 0.0058, Entropy: 0.1220 +[2026-03-20T18:31:30.437354Z] Loop 4741: Loss: 2.13e-02, Avg Return: 0.859, Regret: 0.0058, Entropy: 0.1231 +[2026-03-20T18:31:31.291461Z] Loop 4742: Loss: 2.17e-02, Avg Return: 0.859, Regret: 0.0058, Entropy: 0.1199 +[2026-03-20T18:31:32.146565Z] Loop 4743: Loss: 2.27e-02, Avg Return: 0.860, Regret: 0.0058, Entropy: 0.1249 +[2026-03-20T18:31:33.000411Z] Loop 4744: Loss: 2.12e-02, Avg Return: 0.861, Regret: 0.0058, Entropy: 0.1218 +[2026-03-20T18:31:33.854816Z] Loop 4745: Loss: 2.05e-02, Avg Return: 0.860, Regret: 0.0058, Entropy: 0.1224 +[2026-03-20T18:31:34.708695Z] Loop 4746: Loss: 2.10e-02, Avg Return: 0.861, Regret: 0.0058, Entropy: 0.1221 +[2026-03-20T18:31:35.563842Z] Loop 4747: Loss: 1.97e-02, Avg Return: 0.861, Regret: 0.0058, Entropy: 0.1148 +[2026-03-20T18:31:36.417920Z] Loop 4748: Loss: 2.12e-02, Avg Return: 0.862, Regret: 0.0058, Entropy: 0.1207 +[2026-03-20T18:31:37.272004Z] Loop 4749: Loss: 1.96e-02, Avg Return: 0.862, Regret: 0.0058, Entropy: 0.1104 +[2026-03-20T18:31:38.169299Z] Loop 4750: Loss: 2.06e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1142 +[2026-03-20T18:31:39.022801Z] Loop 4751: Loss: 1.96e-02, Avg Return: 0.863, Regret: 0.0019, Entropy: 0.1093 +[2026-03-20T18:31:39.878959Z] Loop 4752: Loss: 1.87e-02, Avg Return: 0.863, Regret: 0.0019, Entropy: 0.1087 +[2026-03-20T18:31:40.735356Z] Loop 4753: Loss: 1.87e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1047 +[2026-03-20T18:31:41.591811Z] Loop 4754: Loss: 1.98e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.1102 +[2026-03-20T18:31:42.448044Z] Loop 4755: Loss: 2.01e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1128 +[2026-03-20T18:31:43.303488Z] Loop 4756: Loss: 1.87e-02, Avg Return: 0.860, Regret: 0.0019, Entropy: 0.1086 +[2026-03-20T18:31:44.159383Z] Loop 4757: Loss: 1.97e-02, Avg Return: 0.860, Regret: 0.0019, Entropy: 0.1112 +[2026-03-20T18:31:45.015025Z] Loop 4758: Loss: 1.99e-02, Avg Return: 0.860, Regret: 0.0019, Entropy: 0.1117 +[2026-03-20T18:31:45.871076Z] Loop 4759: Loss: 2.03e-02, Avg Return: 0.858, Regret: 0.0019, Entropy: 0.1111 +[2026-03-20T18:31:46.768594Z] Loop 4760: Loss: 1.94e-02, Avg Return: 0.860, Regret: 0.0034, Entropy: 0.1107 +[2026-03-20T18:31:47.623265Z] Loop 4761: Loss: 1.98e-02, Avg Return: 0.861, Regret: 0.0034, Entropy: 0.1096 +[2026-03-20T18:31:48.477942Z] Loop 4762: Loss: 2.01e-02, Avg Return: 0.861, Regret: 0.0034, Entropy: 0.1119 +[2026-03-20T18:31:49.331566Z] Loop 4763: Loss: 1.96e-02, Avg Return: 0.861, Regret: 0.0034, Entropy: 0.1094 +[2026-03-20T18:31:50.185162Z] Loop 4764: Loss: 1.97e-02, Avg Return: 0.861, Regret: 0.0034, Entropy: 0.1145 +[2026-03-20T18:31:51.038762Z] Loop 4765: Loss: 2.01e-02, Avg Return: 0.861, Regret: 0.0034, Entropy: 0.1140 +[2026-03-20T18:31:51.892128Z] Loop 4766: Loss: 2.09e-02, Avg Return: 0.861, Regret: 0.0034, Entropy: 0.1182 +[2026-03-20T18:31:52.745587Z] Loop 4767: Loss: 1.97e-02, Avg Return: 0.862, Regret: 0.0034, Entropy: 0.1136 +[2026-03-20T18:31:53.599202Z] Loop 4768: Loss: 1.99e-02, Avg Return: 0.860, Regret: 0.0034, Entropy: 0.1127 +[2026-03-20T18:31:54.452512Z] Loop 4769: Loss: 2.12e-02, Avg Return: 0.859, Regret: 0.0034, Entropy: 0.1187 +[2026-03-20T18:31:55.346532Z] Loop 4770: Loss: 2.10e-02, Avg Return: 0.860, Regret: 0.0032, Entropy: 0.1179 +[2026-03-20T18:31:56.200423Z] Loop 4771: Loss: 2.00e-02, Avg Return: 0.860, Regret: 0.0032, Entropy: 0.1184 +[2026-03-20T18:31:57.054258Z] Loop 4772: Loss: 2.12e-02, Avg Return: 0.860, Regret: 0.0032, Entropy: 0.1220 +[2026-03-20T18:31:57.907991Z] Loop 4773: Loss: 2.09e-02, Avg Return: 0.858, Regret: 0.0032, Entropy: 0.1176 +[2026-03-20T18:31:58.762171Z] Loop 4774: Loss: 2.13e-02, Avg Return: 0.859, Regret: 0.0032, Entropy: 0.1269 +[2026-03-20T18:31:59.617091Z] Loop 4775: Loss: 2.19e-02, Avg Return: 0.857, Regret: 0.0032, Entropy: 0.1274 +[2026-03-20T18:32:00.471413Z] Loop 4776: Loss: 2.25e-02, Avg Return: 0.857, Regret: 0.0032, Entropy: 0.1241 +[2026-03-20T18:32:01.325106Z] Loop 4777: Loss: 2.28e-02, Avg Return: 0.860, Regret: 0.0032, Entropy: 0.1289 +[2026-03-20T18:32:02.178187Z] Loop 4778: Loss: 2.11e-02, Avg Return: 0.860, Regret: 0.0032, Entropy: 0.1216 +[2026-03-20T18:32:03.031837Z] Loop 4779: Loss: 2.10e-02, Avg Return: 0.861, Regret: 0.0032, Entropy: 0.1210 +[2026-03-20T18:32:03.927689Z] Loop 4780: Loss: 2.05e-02, Avg Return: 0.860, Regret: 0.0029, Entropy: 0.1146 +[2026-03-20T18:32:04.781034Z] Loop 4781: Loss: 2.00e-02, Avg Return: 0.860, Regret: 0.0029, Entropy: 0.1146 +[2026-03-20T18:32:05.634257Z] Loop 4782: Loss: 1.90e-02, Avg Return: 0.861, Regret: 0.0029, Entropy: 0.1082 +[2026-03-20T18:32:06.488067Z] Loop 4783: Loss: 2.06e-02, Avg Return: 0.860, Regret: 0.0029, Entropy: 0.1164 +[2026-03-20T18:32:07.342472Z] Loop 4784: Loss: 2.11e-02, Avg Return: 0.860, Regret: 0.0029, Entropy: 0.1177 +[2026-03-20T18:32:08.197419Z] Loop 4785: Loss: 2.01e-02, Avg Return: 0.860, Regret: 0.0029, Entropy: 0.1179 +[2026-03-20T18:32:09.050992Z] Loop 4786: Loss: 2.05e-02, Avg Return: 0.859, Regret: 0.0029, Entropy: 0.1184 +[2026-03-20T18:32:09.903755Z] Loop 4787: Loss: 2.13e-02, Avg Return: 0.859, Regret: 0.0029, Entropy: 0.1164 +[2026-03-20T18:32:10.757484Z] Loop 4788: Loss: 1.87e-02, Avg Return: 0.861, Regret: 0.0029, Entropy: 0.1060 +[2026-03-20T18:32:11.612015Z] Loop 4789: Loss: 1.90e-02, Avg Return: 0.861, Regret: 0.0029, Entropy: 0.1071 +[2026-03-20T18:32:12.506129Z] Loop 4790: Loss: 1.90e-02, Avg Return: 0.861, Regret: 0.0023, Entropy: 0.1069 +[2026-03-20T18:32:13.359602Z] Loop 4791: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.1000 +[2026-03-20T18:32:14.213491Z] Loop 4792: Loss: 1.96e-02, Avg Return: 0.863, Regret: 0.0023, Entropy: 0.1064 +[2026-03-20T18:32:15.067614Z] Loop 4793: Loss: 1.94e-02, Avg Return: 0.861, Regret: 0.0023, Entropy: 0.1073 +[2026-03-20T18:32:15.920997Z] Loop 4794: Loss: 1.96e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.1067 +[2026-03-20T18:32:16.774814Z] Loop 4795: Loss: 1.80e-02, Avg Return: 0.861, Regret: 0.0023, Entropy: 0.1047 +[2026-03-20T18:32:17.628085Z] Loop 4796: Loss: 1.80e-02, Avg Return: 0.859, Regret: 0.0023, Entropy: 0.1026 +[2026-03-20T18:32:18.481283Z] Loop 4797: Loss: 2.10e-02, Avg Return: 0.860, Regret: 0.0023, Entropy: 0.1132 +[2026-03-20T18:32:19.335312Z] Loop 4798: Loss: 1.95e-02, Avg Return: 0.859, Regret: 0.0023, Entropy: 0.1127 +[2026-03-20T18:32:20.188769Z] Loop 4799: Loss: 2.01e-02, Avg Return: 0.860, Regret: 0.0023, Entropy: 0.1097 +[2026-03-20T18:32:21.084041Z] Loop 4800: Loss: 2.10e-02, Avg Return: 0.859, Regret: 0.0052, Entropy: 0.1163 +[2026-03-20T18:32:21.938428Z] Loop 4801: Loss: 2.04e-02, Avg Return: 0.859, Regret: 0.0052, Entropy: 0.1160 +[2026-03-20T18:32:22.794388Z] Loop 4802: Loss: 2.18e-02, Avg Return: 0.857, Regret: 0.0052, Entropy: 0.1212 +[2026-03-20T18:32:23.648992Z] Loop 4803: Loss: 2.09e-02, Avg Return: 0.860, Regret: 0.0052, Entropy: 0.1156 +[2026-03-20T18:32:24.504978Z] Loop 4804: Loss: 2.02e-02, Avg Return: 0.858, Regret: 0.0052, Entropy: 0.1138 +[2026-03-20T18:32:25.359506Z] Loop 4805: Loss: 1.91e-02, Avg Return: 0.859, Regret: 0.0052, Entropy: 0.1095 +[2026-03-20T18:32:26.215820Z] Loop 4806: Loss: 2.03e-02, Avg Return: 0.861, Regret: 0.0052, Entropy: 0.1128 +[2026-03-20T18:32:27.072314Z] Loop 4807: Loss: 2.01e-02, Avg Return: 0.861, Regret: 0.0052, Entropy: 0.1088 +[2026-03-20T18:32:27.928491Z] Loop 4808: Loss: 1.89e-02, Avg Return: 0.860, Regret: 0.0052, Entropy: 0.1028 +[2026-03-20T18:32:28.783856Z] Loop 4809: Loss: 1.87e-02, Avg Return: 0.859, Regret: 0.0052, Entropy: 0.1061 +[2026-03-20T18:32:29.679455Z] Loop 4810: Loss: 1.94e-02, Avg Return: 0.861, Regret: 0.0038, Entropy: 0.1078 +[2026-03-20T18:32:30.533501Z] Loop 4811: Loss: 1.86e-02, Avg Return: 0.860, Regret: 0.0038, Entropy: 0.1065 +[2026-03-20T18:32:31.388047Z] Loop 4812: Loss: 2.06e-02, Avg Return: 0.860, Regret: 0.0038, Entropy: 0.1114 +[2026-03-20T18:32:32.241865Z] Loop 4813: Loss: 1.93e-02, Avg Return: 0.861, Regret: 0.0038, Entropy: 0.1025 +[2026-03-20T18:32:33.095305Z] Loop 4814: Loss: 1.91e-02, Avg Return: 0.860, Regret: 0.0038, Entropy: 0.1046 +[2026-03-20T18:32:33.949141Z] Loop 4815: Loss: 1.95e-02, Avg Return: 0.861, Regret: 0.0038, Entropy: 0.1052 +[2026-03-20T18:32:34.803379Z] Loop 4816: Loss: 1.73e-02, Avg Return: 0.862, Regret: 0.0038, Entropy: 0.0973 +[2026-03-20T18:32:35.658033Z] Loop 4817: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0038, Entropy: 0.0969 +[2026-03-20T18:32:36.511438Z] Loop 4818: Loss: 1.63e-02, Avg Return: 0.862, Regret: 0.0038, Entropy: 0.0956 +[2026-03-20T18:32:37.365451Z] Loop 4819: Loss: 1.81e-02, Avg Return: 0.861, Regret: 0.0038, Entropy: 0.1010 +[2026-03-20T18:32:38.260255Z] Loop 4820: Loss: 1.80e-02, Avg Return: 0.861, Regret: 0.0017, Entropy: 0.1028 +[2026-03-20T18:32:39.115016Z] Loop 4821: Loss: 1.97e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.1122 +[2026-03-20T18:32:39.970791Z] Loop 4822: Loss: 2.00e-02, Avg Return: 0.861, Regret: 0.0017, Entropy: 0.1103 +[2026-03-20T18:32:40.825096Z] Loop 4823: Loss: 2.15e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.1198 +[2026-03-20T18:32:41.679572Z] Loop 4824: Loss: 2.21e-02, Avg Return: 0.861, Regret: 0.0017, Entropy: 0.1235 +[2026-03-20T18:32:42.534328Z] Loop 4825: Loss: 2.27e-02, Avg Return: 0.861, Regret: 0.0017, Entropy: 0.1271 +[2026-03-20T18:32:43.389752Z] Loop 4826: Loss: 2.20e-02, Avg Return: 0.860, Regret: 0.0017, Entropy: 0.1218 +[2026-03-20T18:32:44.244302Z] Loop 4827: Loss: 2.30e-02, Avg Return: 0.860, Regret: 0.0017, Entropy: 0.1241 +[2026-03-20T18:32:45.097915Z] Loop 4828: Loss: 2.20e-02, Avg Return: 0.861, Regret: 0.0017, Entropy: 0.1233 +[2026-03-20T18:32:45.952202Z] Loop 4829: Loss: 2.12e-02, Avg Return: 0.860, Regret: 0.0017, Entropy: 0.1254 +[2026-03-20T18:32:46.847260Z] Loop 4830: Loss: 2.03e-02, Avg Return: 0.860, Regret: 0.0028, Entropy: 0.1158 +[2026-03-20T18:32:47.702177Z] Loop 4831: Loss: 2.12e-02, Avg Return: 0.860, Regret: 0.0028, Entropy: 0.1164 +[2026-03-20T18:32:48.556515Z] Loop 4832: Loss: 1.95e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.1123 +[2026-03-20T18:32:49.410606Z] Loop 4833: Loss: 2.01e-02, Avg Return: 0.860, Regret: 0.0028, Entropy: 0.1114 +[2026-03-20T18:32:50.265980Z] Loop 4834: Loss: 2.01e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.1150 +[2026-03-20T18:32:51.121847Z] Loop 4835: Loss: 1.92e-02, Avg Return: 0.859, Regret: 0.0028, Entropy: 0.1064 +[2026-03-20T18:32:51.975899Z] Loop 4836: Loss: 2.02e-02, Avg Return: 0.860, Regret: 0.0028, Entropy: 0.1133 +[2026-03-20T18:32:52.829011Z] Loop 4837: Loss: 2.04e-02, Avg Return: 0.860, Regret: 0.0028, Entropy: 0.1097 +[2026-03-20T18:32:53.682422Z] Loop 4838: Loss: 1.96e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.1097 +[2026-03-20T18:32:54.536553Z] Loop 4839: Loss: 2.01e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.1142 +[2026-03-20T18:32:55.430900Z] Loop 4840: Loss: 1.93e-02, Avg Return: 0.860, Regret: 0.0035, Entropy: 0.1090 +[2026-03-20T18:32:56.283987Z] Loop 4841: Loss: 1.91e-02, Avg Return: 0.860, Regret: 0.0035, Entropy: 0.1091 +[2026-03-20T18:32:57.136814Z] Loop 4842: Loss: 2.09e-02, Avg Return: 0.860, Regret: 0.0035, Entropy: 0.1157 +[2026-03-20T18:32:57.991106Z] Loop 4843: Loss: 1.96e-02, Avg Return: 0.860, Regret: 0.0035, Entropy: 0.1116 +[2026-03-20T18:32:58.846029Z] Loop 4844: Loss: 1.89e-02, Avg Return: 0.860, Regret: 0.0035, Entropy: 0.1102 +[2026-03-20T18:32:59.699570Z] Loop 4845: Loss: 1.99e-02, Avg Return: 0.860, Regret: 0.0035, Entropy: 0.1094 +[2026-03-20T18:33:00.552349Z] Loop 4846: Loss: 2.03e-02, Avg Return: 0.862, Regret: 0.0035, Entropy: 0.1153 +[2026-03-20T18:33:01.406195Z] Loop 4847: Loss: 1.92e-02, Avg Return: 0.861, Regret: 0.0035, Entropy: 0.1072 +[2026-03-20T18:33:02.261026Z] Loop 4848: Loss: 1.87e-02, Avg Return: 0.863, Regret: 0.0035, Entropy: 0.1063 +[2026-03-20T18:33:03.115044Z] Loop 4849: Loss: 1.95e-02, Avg Return: 0.861, Regret: 0.0035, Entropy: 0.1128 +[2026-03-20T18:33:04.007653Z] Loop 4850: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.1091 +[2026-03-20T18:33:04.862562Z] Loop 4851: Loss: 1.84e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.1077 +[2026-03-20T18:33:05.717969Z] Loop 4852: Loss: 2.06e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.1135 +[2026-03-20T18:33:06.572946Z] Loop 4853: Loss: 2.05e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.1151 +[2026-03-20T18:33:07.427273Z] Loop 4854: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.1098 +[2026-03-20T18:33:08.282171Z] Loop 4855: Loss: 1.99e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.1117 +[2026-03-20T18:33:09.136401Z] Loop 4856: Loss: 1.92e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.1056 +[2026-03-20T18:33:09.990131Z] Loop 4857: Loss: 2.09e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.1157 +[2026-03-20T18:33:10.844246Z] Loop 4858: Loss: 2.02e-02, Avg Return: 0.863, Regret: 0.0022, Entropy: 0.1146 +[2026-03-20T18:33:11.699545Z] Loop 4859: Loss: 1.96e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.1123 +[2026-03-20T18:33:12.596175Z] Loop 4860: Loss: 1.94e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.1109 +[2026-03-20T18:33:13.451548Z] Loop 4861: Loss: 1.96e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.1155 +[2026-03-20T18:33:14.306147Z] Loop 4862: Loss: 2.07e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.1132 +[2026-03-20T18:33:15.161308Z] Loop 4863: Loss: 1.95e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.1112 +[2026-03-20T18:33:16.014900Z] Loop 4864: Loss: 1.92e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.1090 +[2026-03-20T18:33:16.868849Z] Loop 4865: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0026, Entropy: 0.1066 +[2026-03-20T18:33:17.723322Z] Loop 4866: Loss: 1.85e-02, Avg Return: 0.863, Regret: 0.0026, Entropy: 0.1014 +[2026-03-20T18:33:18.578510Z] Loop 4867: Loss: 2.00e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.1104 +[2026-03-20T18:33:19.432039Z] Loop 4868: Loss: 2.04e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.1066 +[2026-03-20T18:33:20.286478Z] Loop 4869: Loss: 2.04e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.1130 +[2026-03-20T18:33:21.181984Z] Loop 4870: Loss: 1.81e-02, Avg Return: 0.859, Regret: 0.0046, Entropy: 0.0987 +[2026-03-20T18:33:22.036044Z] Loop 4871: Loss: 1.91e-02, Avg Return: 0.859, Regret: 0.0046, Entropy: 0.1041 +[2026-03-20T18:33:22.891098Z] Loop 4872: Loss: 1.98e-02, Avg Return: 0.859, Regret: 0.0046, Entropy: 0.1080 +[2026-03-20T18:33:23.744568Z] Loop 4873: Loss: 2.00e-02, Avg Return: 0.859, Regret: 0.0046, Entropy: 0.1050 +[2026-03-20T18:33:24.598104Z] Loop 4874: Loss: 2.14e-02, Avg Return: 0.860, Regret: 0.0046, Entropy: 0.1133 +[2026-03-20T18:33:25.453416Z] Loop 4875: Loss: 1.95e-02, Avg Return: 0.861, Regret: 0.0046, Entropy: 0.1045 +[2026-03-20T18:33:26.308323Z] Loop 4876: Loss: 2.01e-02, Avg Return: 0.861, Regret: 0.0046, Entropy: 0.1117 +[2026-03-20T18:33:27.162222Z] Loop 4877: Loss: 2.02e-02, Avg Return: 0.861, Regret: 0.0046, Entropy: 0.1106 +[2026-03-20T18:33:28.016978Z] Loop 4878: Loss: 1.97e-02, Avg Return: 0.862, Regret: 0.0046, Entropy: 0.1126 +[2026-03-20T18:33:28.872479Z] Loop 4879: Loss: 1.81e-02, Avg Return: 0.861, Regret: 0.0046, Entropy: 0.1045 +[2026-03-20T18:33:29.769309Z] Loop 4880: Loss: 2.15e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.1191 +[2026-03-20T18:33:30.624525Z] Loop 4881: Loss: 2.06e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.1221 +[2026-03-20T18:33:31.479087Z] Loop 4882: Loss: 2.24e-02, Avg Return: 0.858, Regret: 0.0024, Entropy: 0.1252 +[2026-03-20T18:33:32.334258Z] Loop 4883: Loss: 2.37e-02, Avg Return: 0.857, Regret: 0.0024, Entropy: 0.1364 +[2026-03-20T18:33:33.189813Z] Loop 4884: Loss: 2.46e-02, Avg Return: 0.854, Regret: 0.0024, Entropy: 0.1392 +[2026-03-20T18:33:34.045560Z] Loop 4885: Loss: 2.31e-02, Avg Return: 0.856, Regret: 0.0024, Entropy: 0.1377 +[2026-03-20T18:33:34.900170Z] Loop 4886: Loss: 2.28e-02, Avg Return: 0.859, Regret: 0.0024, Entropy: 0.1328 +[2026-03-20T18:33:35.755244Z] Loop 4887: Loss: 2.11e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.1220 +[2026-03-20T18:33:36.611561Z] Loop 4888: Loss: 2.02e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.1141 +[2026-03-20T18:33:37.466525Z] Loop 4889: Loss: 1.97e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.1069 +[2026-03-20T18:33:38.361786Z] Loop 4890: Loss: 1.97e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.1087 +[2026-03-20T18:33:39.215810Z] Loop 4891: Loss: 1.80e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.1027 +[2026-03-20T18:33:40.069399Z] Loop 4892: Loss: 1.90e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.1084 +[2026-03-20T18:33:40.924332Z] Loop 4893: Loss: 1.84e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.1074 +[2026-03-20T18:33:41.779763Z] Loop 4894: Loss: 2.04e-02, Avg Return: 0.860, Regret: 0.0016, Entropy: 0.1084 +[2026-03-20T18:33:42.636121Z] Loop 4895: Loss: 1.82e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.1062 +[2026-03-20T18:33:43.489232Z] Loop 4896: Loss: 1.84e-02, Avg Return: 0.860, Regret: 0.0016, Entropy: 0.1068 +[2026-03-20T18:33:44.342798Z] Loop 4897: Loss: 1.76e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.1035 +[2026-03-20T18:33:45.198469Z] Loop 4898: Loss: 1.96e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.1099 +[2026-03-20T18:33:46.052024Z] Loop 4899: Loss: 1.79e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.1020 +[2026-03-20T18:33:46.945637Z] Loop 4900: Loss: 1.92e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.1065 +[2026-03-20T18:33:47.799429Z] Loop 4901: Loss: 1.93e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.1037 +[2026-03-20T18:33:48.655171Z] Loop 4902: Loss: 1.85e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.1051 +[2026-03-20T18:33:49.510641Z] Loop 4903: Loss: 1.82e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.1062 +[2026-03-20T18:33:50.364549Z] Loop 4904: Loss: 1.91e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.1081 +[2026-03-20T18:33:51.217129Z] Loop 4905: Loss: 1.86e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.0992 +[2026-03-20T18:33:52.070685Z] Loop 4906: Loss: 1.91e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.1063 +[2026-03-20T18:33:52.926346Z] Loop 4907: Loss: 1.94e-02, Avg Return: 0.859, Regret: 0.0022, Entropy: 0.1074 +[2026-03-20T18:33:53.780353Z] Loop 4908: Loss: 1.94e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.1046 +[2026-03-20T18:33:54.633363Z] Loop 4909: Loss: 1.83e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.1027 +[2026-03-20T18:33:55.529767Z] Loop 4910: Loss: 1.93e-02, Avg Return: 0.860, Regret: 0.0037, Entropy: 0.1080 +[2026-03-20T18:33:56.383831Z] Loop 4911: Loss: 1.92e-02, Avg Return: 0.859, Regret: 0.0037, Entropy: 0.1118 +[2026-03-20T18:33:57.236813Z] Loop 4912: Loss: 1.83e-02, Avg Return: 0.860, Regret: 0.0037, Entropy: 0.1044 +[2026-03-20T18:33:58.090208Z] Loop 4913: Loss: 1.95e-02, Avg Return: 0.861, Regret: 0.0037, Entropy: 0.1110 +[2026-03-20T18:33:58.944660Z] Loop 4914: Loss: 1.80e-02, Avg Return: 0.859, Regret: 0.0037, Entropy: 0.1026 +[2026-03-20T18:33:59.798079Z] Loop 4915: Loss: 2.04e-02, Avg Return: 0.862, Regret: 0.0037, Entropy: 0.1081 +[2026-03-20T18:34:00.651578Z] Loop 4916: Loss: 1.71e-02, Avg Return: 0.861, Regret: 0.0037, Entropy: 0.1001 +[2026-03-20T18:34:01.504473Z] Loop 4917: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0037, Entropy: 0.1036 +[2026-03-20T18:34:02.358795Z] Loop 4918: Loss: 1.82e-02, Avg Return: 0.860, Regret: 0.0037, Entropy: 0.1028 +[2026-03-20T18:34:03.213428Z] Loop 4919: Loss: 1.80e-02, Avg Return: 0.861, Regret: 0.0037, Entropy: 0.1032 +[2026-03-20T18:34:04.108012Z] Loop 4920: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0026, Entropy: 0.1014 +[2026-03-20T18:34:04.961463Z] Loop 4921: Loss: 1.67e-02, Avg Return: 0.859, Regret: 0.0026, Entropy: 0.0965 +[2026-03-20T18:34:05.815588Z] Loop 4922: Loss: 1.78e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.0985 +[2026-03-20T18:34:06.668464Z] Loop 4923: Loss: 1.88e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.1058 +[2026-03-20T18:34:07.521307Z] Loop 4924: Loss: 1.91e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.1057 +[2026-03-20T18:34:08.375633Z] Loop 4925: Loss: 1.96e-02, Avg Return: 0.859, Regret: 0.0026, Entropy: 0.1050 +[2026-03-20T18:34:09.230118Z] Loop 4926: Loss: 1.90e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.1080 +[2026-03-20T18:34:10.084278Z] Loop 4927: Loss: 1.99e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.1082 +[2026-03-20T18:34:10.938582Z] Loop 4928: Loss: 1.76e-02, Avg Return: 0.859, Regret: 0.0026, Entropy: 0.1036 +[2026-03-20T18:34:11.793646Z] Loop 4929: Loss: 1.94e-02, Avg Return: 0.859, Regret: 0.0026, Entropy: 0.1072 +[2026-03-20T18:34:12.689514Z] Loop 4930: Loss: 1.89e-02, Avg Return: 0.860, Regret: 0.0036, Entropy: 0.1072 +[2026-03-20T18:34:13.543846Z] Loop 4931: Loss: 2.02e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.1086 +[2026-03-20T18:34:14.397814Z] Loop 4932: Loss: 1.91e-02, Avg Return: 0.861, Regret: 0.0036, Entropy: 0.1071 +[2026-03-20T18:34:15.252577Z] Loop 4933: Loss: 1.96e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.1068 +[2026-03-20T18:34:16.107572Z] Loop 4934: Loss: 1.72e-02, Avg Return: 0.861, Regret: 0.0036, Entropy: 0.0985 +[2026-03-20T18:34:16.964114Z] Loop 4935: Loss: 1.83e-02, Avg Return: 0.861, Regret: 0.0036, Entropy: 0.1017 +[2026-03-20T18:34:17.819105Z] Loop 4936: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.1018 +[2026-03-20T18:34:18.674469Z] Loop 4937: Loss: 1.94e-02, Avg Return: 0.861, Regret: 0.0036, Entropy: 0.1049 +[2026-03-20T18:34:19.529063Z] Loop 4938: Loss: 1.83e-02, Avg Return: 0.860, Regret: 0.0036, Entropy: 0.1002 +[2026-03-20T18:34:20.384117Z] Loop 4939: Loss: 1.73e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.0999 +[2026-03-20T18:34:21.278472Z] Loop 4940: Loss: 1.82e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.1020 +[2026-03-20T18:34:22.131339Z] Loop 4941: Loss: 1.98e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.1049 +[2026-03-20T18:34:22.987120Z] Loop 4942: Loss: 1.72e-02, Avg Return: 0.859, Regret: 0.0026, Entropy: 0.0974 +[2026-03-20T18:34:23.841391Z] Loop 4943: Loss: 1.89e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.1050 +[2026-03-20T18:34:24.695088Z] Loop 4944: Loss: 1.82e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.1068 +[2026-03-20T18:34:25.548723Z] Loop 4945: Loss: 1.91e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.1110 +[2026-03-20T18:34:26.402107Z] Loop 4946: Loss: 2.01e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.1116 +[2026-03-20T18:34:27.255956Z] Loop 4947: Loss: 1.80e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.1050 +[2026-03-20T18:34:28.109617Z] Loop 4948: Loss: 2.00e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.1119 +[2026-03-20T18:34:28.964589Z] Loop 4949: Loss: 1.90e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.1083 +[2026-03-20T18:34:29.861430Z] Loop 4950: Loss: 1.91e-02, Avg Return: 0.859, Regret: 0.0049, Entropy: 0.1076 +[2026-03-20T18:34:30.715118Z] Loop 4951: Loss: 2.12e-02, Avg Return: 0.858, Regret: 0.0049, Entropy: 0.1136 +[2026-03-20T18:34:31.569456Z] Loop 4952: Loss: 1.98e-02, Avg Return: 0.857, Regret: 0.0049, Entropy: 0.1101 +[2026-03-20T18:34:32.423822Z] Loop 4953: Loss: 1.94e-02, Avg Return: 0.860, Regret: 0.0049, Entropy: 0.1059 +[2026-03-20T18:34:33.278164Z] Loop 4954: Loss: 1.98e-02, Avg Return: 0.860, Regret: 0.0049, Entropy: 0.1108 +[2026-03-20T18:34:34.132021Z] Loop 4955: Loss: 1.87e-02, Avg Return: 0.861, Regret: 0.0049, Entropy: 0.1030 +[2026-03-20T18:34:34.987049Z] Loop 4956: Loss: 1.95e-02, Avg Return: 0.860, Regret: 0.0049, Entropy: 0.1080 +[2026-03-20T18:34:35.842119Z] Loop 4957: Loss: 1.98e-02, Avg Return: 0.860, Regret: 0.0049, Entropy: 0.1112 +[2026-03-20T18:34:36.697036Z] Loop 4958: Loss: 1.94e-02, Avg Return: 0.859, Regret: 0.0049, Entropy: 0.1140 +[2026-03-20T18:34:37.550763Z] Loop 4959: Loss: 1.89e-02, Avg Return: 0.861, Regret: 0.0049, Entropy: 0.1074 +[2026-03-20T18:34:38.445729Z] Loop 4960: Loss: 1.89e-02, Avg Return: 0.860, Regret: 0.0036, Entropy: 0.1099 +[2026-03-20T18:34:39.300093Z] Loop 4961: Loss: 2.12e-02, Avg Return: 0.859, Regret: 0.0036, Entropy: 0.1199 +[2026-03-20T18:34:40.155230Z] Loop 4962: Loss: 2.16e-02, Avg Return: 0.860, Regret: 0.0036, Entropy: 0.1160 +[2026-03-20T18:34:41.009107Z] Loop 4963: Loss: 2.11e-02, Avg Return: 0.861, Regret: 0.0036, Entropy: 0.1146 +[2026-03-20T18:34:41.862288Z] Loop 4964: Loss: 2.07e-02, Avg Return: 0.860, Regret: 0.0036, Entropy: 0.1183 +[2026-03-20T18:34:42.715973Z] Loop 4965: Loss: 2.10e-02, Avg Return: 0.861, Regret: 0.0036, Entropy: 0.1132 +[2026-03-20T18:34:43.571240Z] Loop 4966: Loss: 2.13e-02, Avg Return: 0.861, Regret: 0.0036, Entropy: 0.1176 +[2026-03-20T18:34:44.425379Z] Loop 4967: Loss: 2.10e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.1149 +[2026-03-20T18:34:45.279095Z] Loop 4968: Loss: 2.05e-02, Avg Return: 0.863, Regret: 0.0036, Entropy: 0.1096 +[2026-03-20T18:34:46.133122Z] Loop 4969: Loss: 2.00e-02, Avg Return: 0.861, Regret: 0.0036, Entropy: 0.1068 +[2026-03-20T18:34:47.028764Z] Loop 4970: Loss: 1.90e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.1071 +[2026-03-20T18:34:47.883342Z] Loop 4971: Loss: 1.83e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.1052 +[2026-03-20T18:34:48.737547Z] Loop 4972: Loss: 2.02e-02, Avg Return: 0.860, Regret: 0.0020, Entropy: 0.1058 +[2026-03-20T18:34:49.591609Z] Loop 4973: Loss: 2.01e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.1103 +[2026-03-20T18:34:50.445754Z] Loop 4974: Loss: 1.80e-02, Avg Return: 0.860, Regret: 0.0020, Entropy: 0.1001 +[2026-03-20T18:34:51.300632Z] Loop 4975: Loss: 1.84e-02, Avg Return: 0.859, Regret: 0.0020, Entropy: 0.1042 +[2026-03-20T18:34:52.155469Z] Loop 4976: Loss: 1.74e-02, Avg Return: 0.859, Regret: 0.0020, Entropy: 0.1012 +[2026-03-20T18:34:53.009978Z] Loop 4977: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0993 +[2026-03-20T18:34:53.864032Z] Loop 4978: Loss: 1.91e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.1039 +[2026-03-20T18:34:54.718483Z] Loop 4979: Loss: 1.69e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0951 +[2026-03-20T18:34:55.612826Z] Loop 4980: Loss: 1.78e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.0962 +[2026-03-20T18:34:56.467503Z] Loop 4981: Loss: 1.79e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.1009 +[2026-03-20T18:34:57.320951Z] Loop 4982: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0021, Entropy: 0.0988 +[2026-03-20T18:34:58.174881Z] Loop 4983: Loss: 1.83e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.0993 +[2026-03-20T18:34:59.028361Z] Loop 4984: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.0996 +[2026-03-20T18:34:59.883446Z] Loop 4985: Loss: 1.84e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.1011 +[2026-03-20T18:35:00.737765Z] Loop 4986: Loss: 1.76e-02, Avg Return: 0.860, Regret: 0.0021, Entropy: 0.1007 +[2026-03-20T18:35:01.593983Z] Loop 4987: Loss: 1.77e-02, Avg Return: 0.860, Regret: 0.0021, Entropy: 0.1006 +[2026-03-20T18:35:02.448156Z] Loop 4988: Loss: 1.88e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.1044 +[2026-03-20T18:35:03.303635Z] Loop 4989: Loss: 1.84e-02, Avg Return: 0.860, Regret: 0.0021, Entropy: 0.1023 +[2026-03-20T18:35:04.198451Z] Loop 4990: Loss: 1.93e-02, Avg Return: 0.861, Regret: 0.0031, Entropy: 0.1020 +[2026-03-20T18:35:05.051835Z] Loop 4991: Loss: 1.91e-02, Avg Return: 0.861, Regret: 0.0031, Entropy: 0.1042 +[2026-03-20T18:35:05.905122Z] Loop 4992: Loss: 1.98e-02, Avg Return: 0.859, Regret: 0.0031, Entropy: 0.1072 +[2026-03-20T18:35:06.760267Z] Loop 4993: Loss: 2.02e-02, Avg Return: 0.859, Regret: 0.0031, Entropy: 0.1166 +[2026-03-20T18:35:07.614769Z] Loop 4994: Loss: 2.00e-02, Avg Return: 0.859, Regret: 0.0031, Entropy: 0.1127 +[2026-03-20T18:35:08.468160Z] Loop 4995: Loss: 2.10e-02, Avg Return: 0.859, Regret: 0.0031, Entropy: 0.1159 +[2026-03-20T18:35:09.323464Z] Loop 4996: Loss: 2.10e-02, Avg Return: 0.857, Regret: 0.0031, Entropy: 0.1117 +[2026-03-20T18:35:10.179314Z] Loop 4997: Loss: 2.08e-02, Avg Return: 0.857, Regret: 0.0031, Entropy: 0.1171 +[2026-03-20T18:35:11.034189Z] Loop 4998: Loss: 2.15e-02, Avg Return: 0.858, Regret: 0.0031, Entropy: 0.1156 +[2026-03-20T18:35:11.889428Z] Loop 4999: Loss: 1.93e-02, Avg Return: 0.859, Regret: 0.0031, Entropy: 0.1101 +[2026-03-20T18:35:12.787194Z] Loop 5000: Loss: 1.99e-02, Avg Return: 0.858, Regret: 0.0043, Entropy: 0.1087 +[2026-03-20T18:35:13.642159Z] Loop 5001: Loss: 1.99e-02, Avg Return: 0.860, Regret: 0.0043, Entropy: 0.1102 +[2026-03-20T18:35:14.496500Z] Loop 5002: Loss: 1.98e-02, Avg Return: 0.861, Regret: 0.0043, Entropy: 0.1151 +[2026-03-20T18:35:15.351495Z] Loop 5003: Loss: 2.13e-02, Avg Return: 0.860, Regret: 0.0043, Entropy: 0.1148 +[2026-03-20T18:35:16.206208Z] Loop 5004: Loss: 2.09e-02, Avg Return: 0.860, Regret: 0.0043, Entropy: 0.1168 +[2026-03-20T18:35:17.061355Z] Loop 5005: Loss: 2.13e-02, Avg Return: 0.859, Regret: 0.0043, Entropy: 0.1179 +[2026-03-20T18:35:17.916553Z] Loop 5006: Loss: 2.30e-02, Avg Return: 0.858, Regret: 0.0043, Entropy: 0.1267 +[2026-03-20T18:35:18.771517Z] Loop 5007: Loss: 2.29e-02, Avg Return: 0.859, Regret: 0.0043, Entropy: 0.1270 +[2026-03-20T18:35:19.626996Z] Loop 5008: Loss: 2.35e-02, Avg Return: 0.858, Regret: 0.0043, Entropy: 0.1259 +[2026-03-20T18:35:20.481191Z] Loop 5009: Loss: 2.43e-02, Avg Return: 0.857, Regret: 0.0043, Entropy: 0.1326 +[2026-03-20T18:35:21.374324Z] Loop 5010: Loss: 2.48e-02, Avg Return: 0.857, Regret: 0.0061, Entropy: 0.1324 +[2026-03-20T18:35:22.227674Z] Loop 5011: Loss: 2.36e-02, Avg Return: 0.858, Regret: 0.0061, Entropy: 0.1328 +[2026-03-20T18:35:23.082261Z] Loop 5012: Loss: 2.32e-02, Avg Return: 0.860, Regret: 0.0061, Entropy: 0.1351 +[2026-03-20T18:35:23.936578Z] Loop 5013: Loss: 2.50e-02, Avg Return: 0.859, Regret: 0.0061, Entropy: 0.1439 +[2026-03-20T18:35:24.789882Z] Loop 5014: Loss: 2.51e-02, Avg Return: 0.859, Regret: 0.0061, Entropy: 0.1417 +[2026-03-20T18:35:25.643554Z] Loop 5015: Loss: 2.80e-02, Avg Return: 0.855, Regret: 0.0061, Entropy: 0.1612 +[2026-03-20T18:35:26.499973Z] Loop 5016: Loss: 3.11e-02, Avg Return: 0.851, Regret: 0.0061, Entropy: 0.1712 +[2026-03-20T18:35:27.354221Z] Loop 5017: Loss: 3.09e-02, Avg Return: 0.851, Regret: 0.0061, Entropy: 0.1731 +[2026-03-20T18:35:28.207548Z] Loop 5018: Loss: 3.07e-02, Avg Return: 0.854, Regret: 0.0061, Entropy: 0.1710 +[2026-03-20T18:35:29.060725Z] Loop 5019: Loss: 2.90e-02, Avg Return: 0.858, Regret: 0.0061, Entropy: 0.1573 +[2026-03-20T18:35:29.955358Z] Loop 5020: Loss: 2.49e-02, Avg Return: 0.858, Regret: 0.0043, Entropy: 0.1411 +[2026-03-20T18:35:30.809426Z] Loop 5021: Loss: 2.34e-02, Avg Return: 0.860, Regret: 0.0043, Entropy: 0.1319 +[2026-03-20T18:35:31.662920Z] Loop 5022: Loss: 2.35e-02, Avg Return: 0.860, Regret: 0.0043, Entropy: 0.1235 +[2026-03-20T18:35:32.516287Z] Loop 5023: Loss: 2.18e-02, Avg Return: 0.862, Regret: 0.0043, Entropy: 0.1215 +[2026-03-20T18:35:33.369826Z] Loop 5024: Loss: 2.08e-02, Avg Return: 0.861, Regret: 0.0043, Entropy: 0.1140 +[2026-03-20T18:35:34.224295Z] Loop 5025: Loss: 1.96e-02, Avg Return: 0.863, Regret: 0.0043, Entropy: 0.1029 +[2026-03-20T18:35:35.078052Z] Loop 5026: Loss: 1.87e-02, Avg Return: 0.862, Regret: 0.0043, Entropy: 0.1034 +[2026-03-20T18:35:35.931363Z] Loop 5027: Loss: 1.92e-02, Avg Return: 0.861, Regret: 0.0043, Entropy: 0.1043 +[2026-03-20T18:35:36.786089Z] Loop 5028: Loss: 1.89e-02, Avg Return: 0.862, Regret: 0.0043, Entropy: 0.0981 +[2026-03-20T18:35:37.640692Z] Loop 5029: Loss: 1.82e-02, Avg Return: 0.860, Regret: 0.0043, Entropy: 0.1033 +[2026-03-20T18:35:38.536415Z] Loop 5030: Loss: 1.72e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.0996 +[2026-03-20T18:35:39.390885Z] Loop 5031: Loss: 1.71e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.0982 +[2026-03-20T18:35:40.245279Z] Loop 5032: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.0982 +[2026-03-20T18:35:41.100014Z] Loop 5033: Loss: 1.93e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.1058 +[2026-03-20T18:35:41.954764Z] Loop 5034: Loss: 1.96e-02, Avg Return: 0.860, Regret: 0.0021, Entropy: 0.1090 +[2026-03-20T18:35:42.809322Z] Loop 5035: Loss: 2.08e-02, Avg Return: 0.858, Regret: 0.0021, Entropy: 0.1145 +[2026-03-20T18:35:43.664046Z] Loop 5036: Loss: 2.04e-02, Avg Return: 0.858, Regret: 0.0021, Entropy: 0.1094 +[2026-03-20T18:35:44.519010Z] Loop 5037: Loss: 2.05e-02, Avg Return: 0.857, Regret: 0.0021, Entropy: 0.1104 +[2026-03-20T18:35:45.374059Z] Loop 5038: Loss: 1.88e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.1082 +[2026-03-20T18:35:46.227719Z] Loop 5039: Loss: 1.82e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.1014 +[2026-03-20T18:35:47.120730Z] Loop 5040: Loss: 1.73e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.1003 +[2026-03-20T18:35:47.974239Z] Loop 5041: Loss: 1.82e-02, Avg Return: 0.859, Regret: 0.0022, Entropy: 0.1024 +[2026-03-20T18:35:48.827714Z] Loop 5042: Loss: 1.85e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.1001 +[2026-03-20T18:35:49.682535Z] Loop 5043: Loss: 1.88e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.1042 +[2026-03-20T18:35:50.537914Z] Loop 5044: Loss: 2.06e-02, Avg Return: 0.858, Regret: 0.0022, Entropy: 0.1125 +[2026-03-20T18:35:51.392703Z] Loop 5045: Loss: 2.08e-02, Avg Return: 0.855, Regret: 0.0022, Entropy: 0.1093 +[2026-03-20T18:35:52.246309Z] Loop 5046: Loss: 2.00e-02, Avg Return: 0.856, Regret: 0.0022, Entropy: 0.1090 +[2026-03-20T18:35:53.100849Z] Loop 5047: Loss: 2.02e-02, Avg Return: 0.859, Regret: 0.0022, Entropy: 0.1080 +[2026-03-20T18:35:53.955661Z] Loop 5048: Loss: 1.92e-02, Avg Return: 0.859, Regret: 0.0022, Entropy: 0.1047 +[2026-03-20T18:35:54.809807Z] Loop 5049: Loss: 1.93e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.1069 +[2026-03-20T18:35:55.705780Z] Loop 5050: Loss: 2.02e-02, Avg Return: 0.860, Regret: 0.0032, Entropy: 0.1107 +[2026-03-20T18:35:56.558638Z] Loop 5051: Loss: 1.98e-02, Avg Return: 0.861, Regret: 0.0032, Entropy: 0.1107 +[2026-03-20T18:35:57.412983Z] Loop 5052: Loss: 1.93e-02, Avg Return: 0.861, Regret: 0.0032, Entropy: 0.1093 +[2026-03-20T18:35:58.267135Z] Loop 5053: Loss: 1.98e-02, Avg Return: 0.860, Regret: 0.0032, Entropy: 0.1110 +[2026-03-20T18:35:59.121525Z] Loop 5054: Loss: 1.90e-02, Avg Return: 0.861, Regret: 0.0032, Entropy: 0.1074 +[2026-03-20T18:35:59.976291Z] Loop 5055: Loss: 2.03e-02, Avg Return: 0.862, Regret: 0.0032, Entropy: 0.1137 +[2026-03-20T18:36:00.832004Z] Loop 5056: Loss: 2.04e-02, Avg Return: 0.860, Regret: 0.0032, Entropy: 0.1133 +[2026-03-20T18:36:01.686100Z] Loop 5057: Loss: 2.03e-02, Avg Return: 0.862, Regret: 0.0032, Entropy: 0.1122 +[2026-03-20T18:36:02.540833Z] Loop 5058: Loss: 2.02e-02, Avg Return: 0.861, Regret: 0.0032, Entropy: 0.1137 +[2026-03-20T18:36:03.394795Z] Loop 5059: Loss: 2.04e-02, Avg Return: 0.860, Regret: 0.0032, Entropy: 0.1124 +[2026-03-20T18:36:04.287956Z] Loop 5060: Loss: 2.00e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.1113 +[2026-03-20T18:36:05.141618Z] Loop 5061: Loss: 1.83e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.1085 +[2026-03-20T18:36:05.997056Z] Loop 5062: Loss: 1.98e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.1163 +[2026-03-20T18:36:06.852333Z] Loop 5063: Loss: 2.01e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.1111 +[2026-03-20T18:36:07.707461Z] Loop 5064: Loss: 1.85e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.1063 +[2026-03-20T18:36:08.563776Z] Loop 5065: Loss: 1.86e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.1052 +[2026-03-20T18:36:09.419057Z] Loop 5066: Loss: 2.01e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.1133 +[2026-03-20T18:36:10.275193Z] Loop 5067: Loss: 1.95e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.1081 +[2026-03-20T18:36:11.129374Z] Loop 5068: Loss: 2.00e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.1098 +[2026-03-20T18:36:11.983132Z] Loop 5069: Loss: 2.03e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.1128 +[2026-03-20T18:36:12.878036Z] Loop 5070: Loss: 2.02e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.1106 +[2026-03-20T18:36:13.732858Z] Loop 5071: Loss: 1.88e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.1074 +[2026-03-20T18:36:14.586398Z] Loop 5072: Loss: 2.06e-02, Avg Return: 0.860, Regret: 0.0024, Entropy: 0.1097 +[2026-03-20T18:36:15.439227Z] Loop 5073: Loss: 1.97e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.1092 +[2026-03-20T18:36:16.292241Z] Loop 5074: Loss: 1.99e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.1070 +[2026-03-20T18:36:17.147172Z] Loop 5075: Loss: 1.89e-02, Avg Return: 0.860, Regret: 0.0024, Entropy: 0.1075 +[2026-03-20T18:36:18.001218Z] Loop 5076: Loss: 2.02e-02, Avg Return: 0.863, Regret: 0.0024, Entropy: 0.1100 +[2026-03-20T18:36:18.854360Z] Loop 5077: Loss: 1.96e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.1100 +[2026-03-20T18:36:19.707684Z] Loop 5078: Loss: 2.13e-02, Avg Return: 0.859, Regret: 0.0024, Entropy: 0.1134 +[2026-03-20T18:36:20.561683Z] Loop 5079: Loss: 2.00e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.1083 +[2026-03-20T18:36:21.456223Z] Loop 5080: Loss: 2.02e-02, Avg Return: 0.859, Regret: 0.0044, Entropy: 0.1069 +[2026-03-20T18:36:22.308963Z] Loop 5081: Loss: 2.28e-02, Avg Return: 0.860, Regret: 0.0044, Entropy: 0.1175 +[2026-03-20T18:36:23.161100Z] Loop 5082: Loss: 1.95e-02, Avg Return: 0.860, Regret: 0.0044, Entropy: 0.1120 +[2026-03-20T18:36:24.013808Z] Loop 5083: Loss: 1.90e-02, Avg Return: 0.861, Regret: 0.0044, Entropy: 0.1099 +[2026-03-20T18:36:24.867507Z] Loop 5084: Loss: 1.88e-02, Avg Return: 0.862, Regret: 0.0044, Entropy: 0.1109 +[2026-03-20T18:36:25.720840Z] Loop 5085: Loss: 2.08e-02, Avg Return: 0.862, Regret: 0.0044, Entropy: 0.1187 +[2026-03-20T18:36:26.574180Z] Loop 5086: Loss: 1.98e-02, Avg Return: 0.861, Regret: 0.0044, Entropy: 0.1176 +[2026-03-20T18:36:27.429478Z] Loop 5087: Loss: 2.40e-02, Avg Return: 0.860, Regret: 0.0044, Entropy: 0.1294 +[2026-03-20T18:36:28.282998Z] Loop 5088: Loss: 2.28e-02, Avg Return: 0.860, Regret: 0.0044, Entropy: 0.1302 +[2026-03-20T18:36:29.137042Z] Loop 5089: Loss: 2.37e-02, Avg Return: 0.857, Regret: 0.0044, Entropy: 0.1327 +[2026-03-20T18:36:30.030623Z] Loop 5090: Loss: 2.37e-02, Avg Return: 0.858, Regret: 0.0073, Entropy: 0.1357 +[2026-03-20T18:36:30.883727Z] Loop 5091: Loss: 2.28e-02, Avg Return: 0.859, Regret: 0.0073, Entropy: 0.1322 +[2026-03-20T18:36:31.737513Z] Loop 5092: Loss: 2.41e-02, Avg Return: 0.860, Regret: 0.0073, Entropy: 0.1324 +[2026-03-20T18:36:32.591359Z] Loop 5093: Loss: 2.30e-02, Avg Return: 0.860, Regret: 0.0073, Entropy: 0.1291 +[2026-03-20T18:36:33.445604Z] Loop 5094: Loss: 2.10e-02, Avg Return: 0.861, Regret: 0.0073, Entropy: 0.1234 +[2026-03-20T18:36:34.298833Z] Loop 5095: Loss: 2.00e-02, Avg Return: 0.861, Regret: 0.0073, Entropy: 0.1137 +[2026-03-20T18:36:35.151450Z] Loop 5096: Loss: 2.05e-02, Avg Return: 0.860, Regret: 0.0073, Entropy: 0.1165 +[2026-03-20T18:36:36.005227Z] Loop 5097: Loss: 1.96e-02, Avg Return: 0.859, Regret: 0.0073, Entropy: 0.1111 +[2026-03-20T18:36:36.859345Z] Loop 5098: Loss: 2.05e-02, Avg Return: 0.859, Regret: 0.0073, Entropy: 0.1104 +[2026-03-20T18:36:37.713394Z] Loop 5099: Loss: 2.20e-02, Avg Return: 0.859, Regret: 0.0073, Entropy: 0.1132 +[2026-03-20T18:36:38.605987Z] Loop 5100: Loss: 1.93e-02, Avg Return: 0.860, Regret: 0.0040, Entropy: 0.1086 +[2026-03-20T18:36:39.458796Z] Loop 5101: Loss: 1.99e-02, Avg Return: 0.859, Regret: 0.0040, Entropy: 0.1101 +[2026-03-20T18:36:40.315194Z] Loop 5102: Loss: 1.92e-02, Avg Return: 0.861, Regret: 0.0040, Entropy: 0.1037 +[2026-03-20T18:36:41.169498Z] Loop 5103: Loss: 1.83e-02, Avg Return: 0.860, Regret: 0.0040, Entropy: 0.1023 +[2026-03-20T18:36:42.024390Z] Loop 5104: Loss: 2.00e-02, Avg Return: 0.861, Regret: 0.0040, Entropy: 0.1081 +[2026-03-20T18:36:42.879518Z] Loop 5105: Loss: 2.00e-02, Avg Return: 0.861, Regret: 0.0040, Entropy: 0.1101 +[2026-03-20T18:36:43.734640Z] Loop 5106: Loss: 1.95e-02, Avg Return: 0.861, Regret: 0.0040, Entropy: 0.1060 +[2026-03-20T18:36:44.588603Z] Loop 5107: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0040, Entropy: 0.1033 +[2026-03-20T18:36:45.442845Z] Loop 5108: Loss: 2.06e-02, Avg Return: 0.860, Regret: 0.0040, Entropy: 0.1099 +[2026-03-20T18:36:46.297638Z] Loop 5109: Loss: 1.99e-02, Avg Return: 0.859, Regret: 0.0040, Entropy: 0.1118 +[2026-03-20T18:36:47.193397Z] Loop 5110: Loss: 2.07e-02, Avg Return: 0.858, Regret: 0.0058, Entropy: 0.1143 +[2026-03-20T18:36:48.048491Z] Loop 5111: Loss: 2.29e-02, Avg Return: 0.853, Regret: 0.0058, Entropy: 0.1243 +[2026-03-20T18:36:48.903640Z] Loop 5112: Loss: 2.27e-02, Avg Return: 0.854, Regret: 0.0058, Entropy: 0.1221 +[2026-03-20T18:36:49.758729Z] Loop 5113: Loss: 2.25e-02, Avg Return: 0.857, Regret: 0.0058, Entropy: 0.1211 +[2026-03-20T18:36:50.614685Z] Loop 5114: Loss: 1.87e-02, Avg Return: 0.860, Regret: 0.0058, Entropy: 0.1130 +[2026-03-20T18:36:51.470155Z] Loop 5115: Loss: 1.96e-02, Avg Return: 0.861, Regret: 0.0058, Entropy: 0.1125 +[2026-03-20T18:36:52.324944Z] Loop 5116: Loss: 1.82e-02, Avg Return: 0.862, Regret: 0.0058, Entropy: 0.1033 +[2026-03-20T18:36:53.179498Z] Loop 5117: Loss: 1.94e-02, Avg Return: 0.861, Regret: 0.0058, Entropy: 0.1020 +[2026-03-20T18:36:54.035115Z] Loop 5118: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0058, Entropy: 0.0981 +[2026-03-20T18:36:54.888631Z] Loop 5119: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0058, Entropy: 0.1084 +[2026-03-20T18:36:55.782521Z] Loop 5120: Loss: 1.93e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1031 +[2026-03-20T18:36:56.636262Z] Loop 5121: Loss: 1.82e-02, Avg Return: 0.860, Regret: 0.0019, Entropy: 0.1063 +[2026-03-20T18:36:57.491425Z] Loop 5122: Loss: 1.86e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1066 +[2026-03-20T18:36:58.345044Z] Loop 5123: Loss: 2.00e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.1071 +[2026-03-20T18:36:59.199669Z] Loop 5124: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.1044 +[2026-03-20T18:37:00.053921Z] Loop 5125: Loss: 1.99e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.1064 +[2026-03-20T18:37:00.908712Z] Loop 5126: Loss: 1.85e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.1010 +[2026-03-20T18:37:01.761532Z] Loop 5127: Loss: 1.99e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.1070 +[2026-03-20T18:37:02.615315Z] Loop 5128: Loss: 2.06e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.1110 +[2026-03-20T18:37:03.469892Z] Loop 5129: Loss: 1.91e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1082 +[2026-03-20T18:37:04.365277Z] Loop 5130: Loss: 2.00e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.1086 +[2026-03-20T18:37:05.219252Z] Loop 5131: Loss: 2.05e-02, Avg Return: 0.859, Regret: 0.0024, Entropy: 0.1075 +[2026-03-20T18:37:06.072979Z] Loop 5132: Loss: 2.11e-02, Avg Return: 0.860, Regret: 0.0024, Entropy: 0.1139 +[2026-03-20T18:37:06.927057Z] Loop 5133: Loss: 2.08e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.1109 +[2026-03-20T18:37:07.781739Z] Loop 5134: Loss: 1.96e-02, Avg Return: 0.860, Regret: 0.0024, Entropy: 0.1149 +[2026-03-20T18:37:08.637022Z] Loop 5135: Loss: 2.04e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.1142 +[2026-03-20T18:37:09.490838Z] Loop 5136: Loss: 2.08e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.1107 +[2026-03-20T18:37:10.344256Z] Loop 5137: Loss: 1.86e-02, Avg Return: 0.860, Regret: 0.0024, Entropy: 0.1030 +[2026-03-20T18:37:11.198738Z] Loop 5138: Loss: 1.99e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.1115 +[2026-03-20T18:37:12.052948Z] Loop 5139: Loss: 2.08e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.1145 +[2026-03-20T18:37:12.948141Z] Loop 5140: Loss: 2.08e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.1138 +[2026-03-20T18:37:13.801882Z] Loop 5141: Loss: 1.91e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.1091 +[2026-03-20T18:37:14.656275Z] Loop 5142: Loss: 1.97e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.1112 +[2026-03-20T18:37:15.511354Z] Loop 5143: Loss: 2.03e-02, Avg Return: 0.860, Regret: 0.0024, Entropy: 0.1093 +[2026-03-20T18:37:16.364927Z] Loop 5144: Loss: 1.96e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.1088 +[2026-03-20T18:37:17.218931Z] Loop 5145: Loss: 1.87e-02, Avg Return: 0.863, Regret: 0.0024, Entropy: 0.1109 +[2026-03-20T18:37:18.072407Z] Loop 5146: Loss: 2.08e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.1141 +[2026-03-20T18:37:18.925482Z] Loop 5147: Loss: 1.79e-02, Avg Return: 0.863, Regret: 0.0024, Entropy: 0.1047 +[2026-03-20T18:37:19.779426Z] Loop 5148: Loss: 1.90e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.1076 +[2026-03-20T18:37:20.633148Z] Loop 5149: Loss: 1.85e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.1057 +[2026-03-20T18:37:21.526512Z] Loop 5150: Loss: 1.89e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.1109 +[2026-03-20T18:37:22.381868Z] Loop 5151: Loss: 2.06e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.1075 +[2026-03-20T18:37:23.236030Z] Loop 5152: Loss: 1.98e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.1096 +[2026-03-20T18:37:24.091655Z] Loop 5153: Loss: 1.98e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.1130 +[2026-03-20T18:37:24.945316Z] Loop 5154: Loss: 2.18e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.1205 +[2026-03-20T18:37:25.798362Z] Loop 5155: Loss: 2.13e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.1177 +[2026-03-20T18:37:26.651607Z] Loop 5156: Loss: 2.28e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.1294 +[2026-03-20T18:37:27.506456Z] Loop 5157: Loss: 2.35e-02, Avg Return: 0.860, Regret: 0.0015, Entropy: 0.1365 +[2026-03-20T18:37:28.360768Z] Loop 5158: Loss: 2.69e-02, Avg Return: 0.858, Regret: 0.0015, Entropy: 0.1463 +[2026-03-20T18:37:29.213775Z] Loop 5159: Loss: 2.72e-02, Avg Return: 0.857, Regret: 0.0015, Entropy: 0.1491 +[2026-03-20T18:37:30.108195Z] Loop 5160: Loss: 2.52e-02, Avg Return: 0.856, Regret: 0.0068, Entropy: 0.1433 +[2026-03-20T18:37:30.963349Z] Loop 5161: Loss: 2.52e-02, Avg Return: 0.857, Regret: 0.0068, Entropy: 0.1451 +[2026-03-20T18:37:31.816239Z] Loop 5162: Loss: 2.29e-02, Avg Return: 0.860, Regret: 0.0068, Entropy: 0.1332 +[2026-03-20T18:37:32.669593Z] Loop 5163: Loss: 2.41e-02, Avg Return: 0.860, Regret: 0.0068, Entropy: 0.1276 +[2026-03-20T18:37:33.523751Z] Loop 5164: Loss: 2.20e-02, Avg Return: 0.861, Regret: 0.0068, Entropy: 0.1243 +[2026-03-20T18:37:34.378310Z] Loop 5165: Loss: 2.00e-02, Avg Return: 0.861, Regret: 0.0068, Entropy: 0.1173 +[2026-03-20T18:37:35.232448Z] Loop 5166: Loss: 1.99e-02, Avg Return: 0.862, Regret: 0.0068, Entropy: 0.1093 +[2026-03-20T18:37:36.086673Z] Loop 5167: Loss: 2.00e-02, Avg Return: 0.861, Regret: 0.0068, Entropy: 0.1087 +[2026-03-20T18:37:36.941556Z] Loop 5168: Loss: 1.87e-02, Avg Return: 0.861, Regret: 0.0068, Entropy: 0.1050 +[2026-03-20T18:37:37.795555Z] Loop 5169: Loss: 1.97e-02, Avg Return: 0.862, Regret: 0.0068, Entropy: 0.1050 +[2026-03-20T18:37:38.690013Z] Loop 5170: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.1002 +[2026-03-20T18:37:39.544046Z] Loop 5171: Loss: 1.93e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.1063 +[2026-03-20T18:37:40.398774Z] Loop 5172: Loss: 1.89e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.1033 +[2026-03-20T18:37:41.253066Z] Loop 5173: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.1015 +[2026-03-20T18:37:42.107880Z] Loop 5174: Loss: 1.79e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0991 +[2026-03-20T18:37:42.961743Z] Loop 5175: Loss: 1.92e-02, Avg Return: 0.860, Regret: 0.0016, Entropy: 0.1070 +[2026-03-20T18:37:43.816302Z] Loop 5176: Loss: 2.02e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.1118 +[2026-03-20T18:37:44.668781Z] Loop 5177: Loss: 1.86e-02, Avg Return: 0.860, Regret: 0.0016, Entropy: 0.1031 +[2026-03-20T18:37:45.522173Z] Loop 5178: Loss: 1.96e-02, Avg Return: 0.860, Regret: 0.0016, Entropy: 0.1109 +[2026-03-20T18:37:46.376388Z] Loop 5179: Loss: 1.96e-02, Avg Return: 0.860, Regret: 0.0016, Entropy: 0.1096 +[2026-03-20T18:37:47.270375Z] Loop 5180: Loss: 1.88e-02, Avg Return: 0.859, Regret: 0.0031, Entropy: 0.1067 +[2026-03-20T18:37:48.123235Z] Loop 5181: Loss: 1.91e-02, Avg Return: 0.860, Regret: 0.0031, Entropy: 0.1046 +[2026-03-20T18:37:48.976795Z] Loop 5182: Loss: 2.01e-02, Avg Return: 0.860, Regret: 0.0031, Entropy: 0.1120 +[2026-03-20T18:37:49.830769Z] Loop 5183: Loss: 1.91e-02, Avg Return: 0.860, Regret: 0.0031, Entropy: 0.1090 +[2026-03-20T18:37:50.684920Z] Loop 5184: Loss: 1.83e-02, Avg Return: 0.860, Regret: 0.0031, Entropy: 0.1051 +[2026-03-20T18:37:51.538702Z] Loop 5185: Loss: 1.93e-02, Avg Return: 0.860, Regret: 0.0031, Entropy: 0.1046 +[2026-03-20T18:37:52.391422Z] Loop 5186: Loss: 1.71e-02, Avg Return: 0.860, Regret: 0.0031, Entropy: 0.1021 +[2026-03-20T18:37:53.244446Z] Loop 5187: Loss: 1.89e-02, Avg Return: 0.860, Regret: 0.0031, Entropy: 0.0978 +[2026-03-20T18:37:54.098292Z] Loop 5188: Loss: 2.09e-02, Avg Return: 0.859, Regret: 0.0031, Entropy: 0.1094 +[2026-03-20T18:37:54.951945Z] Loop 5189: Loss: 1.75e-02, Avg Return: 0.860, Regret: 0.0031, Entropy: 0.1011 +[2026-03-20T18:37:55.845438Z] Loop 5190: Loss: 1.84e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.1060 +[2026-03-20T18:37:56.699450Z] Loop 5191: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.1048 +[2026-03-20T18:37:57.553929Z] Loop 5192: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0023, Entropy: 0.1027 +[2026-03-20T18:37:58.407868Z] Loop 5193: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.1083 +[2026-03-20T18:37:59.261874Z] Loop 5194: Loss: 1.85e-02, Avg Return: 0.861, Regret: 0.0023, Entropy: 0.1005 +[2026-03-20T18:38:00.115601Z] Loop 5195: Loss: 1.73e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.0997 +[2026-03-20T18:38:00.968465Z] Loop 5196: Loss: 1.82e-02, Avg Return: 0.860, Regret: 0.0023, Entropy: 0.1030 +[2026-03-20T18:38:01.821767Z] Loop 5197: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0023, Entropy: 0.0999 +[2026-03-20T18:38:02.674948Z] Loop 5198: Loss: 2.02e-02, Avg Return: 0.863, Regret: 0.0023, Entropy: 0.1077 +[2026-03-20T18:38:03.529459Z] Loop 5199: Loss: 2.01e-02, Avg Return: 0.861, Regret: 0.0023, Entropy: 0.1086 +[2026-03-20T18:38:04.423781Z] Loop 5200: Loss: 1.87e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.1061 +[2026-03-20T18:38:05.278331Z] Loop 5201: Loss: 1.83e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.1032 +[2026-03-20T18:38:06.133766Z] Loop 5202: Loss: 1.97e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.1063 +[2026-03-20T18:38:06.990253Z] Loop 5203: Loss: 1.86e-02, Avg Return: 0.860, Regret: 0.0018, Entropy: 0.1047 +[2026-03-20T18:38:07.849303Z] Loop 5204: Loss: 1.89e-02, Avg Return: 0.860, Regret: 0.0018, Entropy: 0.1020 +[2026-03-20T18:38:08.703226Z] Loop 5205: Loss: 2.05e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.1137 +[2026-03-20T18:38:09.557670Z] Loop 5206: Loss: 2.21e-02, Avg Return: 0.858, Regret: 0.0018, Entropy: 0.1141 +[2026-03-20T18:38:10.411253Z] Loop 5207: Loss: 2.26e-02, Avg Return: 0.859, Regret: 0.0018, Entropy: 0.1212 +[2026-03-20T18:38:11.265884Z] Loop 5208: Loss: 2.17e-02, Avg Return: 0.860, Regret: 0.0018, Entropy: 0.1186 +[2026-03-20T18:38:12.120903Z] Loop 5209: Loss: 2.14e-02, Avg Return: 0.858, Regret: 0.0018, Entropy: 0.1181 +[2026-03-20T18:38:13.016917Z] Loop 5210: Loss: 2.05e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.1117 +[2026-03-20T18:38:13.872402Z] Loop 5211: Loss: 1.87e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.1041 +[2026-03-20T18:38:14.726447Z] Loop 5212: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0027, Entropy: 0.1044 +[2026-03-20T18:38:15.579825Z] Loop 5213: Loss: 1.88e-02, Avg Return: 0.862, Regret: 0.0027, Entropy: 0.1041 +[2026-03-20T18:38:16.433572Z] Loop 5214: Loss: 1.90e-02, Avg Return: 0.863, Regret: 0.0027, Entropy: 0.1074 +[2026-03-20T18:38:17.287901Z] Loop 5215: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0027, Entropy: 0.1063 +[2026-03-20T18:38:18.142195Z] Loop 5216: Loss: 1.96e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.1130 +[2026-03-20T18:38:18.998691Z] Loop 5217: Loss: 1.91e-02, Avg Return: 0.862, Regret: 0.0027, Entropy: 0.1087 +[2026-03-20T18:38:19.852181Z] Loop 5218: Loss: 2.06e-02, Avg Return: 0.863, Regret: 0.0027, Entropy: 0.1108 +[2026-03-20T18:38:20.706393Z] Loop 5219: Loss: 1.96e-02, Avg Return: 0.862, Regret: 0.0027, Entropy: 0.1120 +[2026-03-20T18:38:21.601443Z] Loop 5220: Loss: 1.79e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.1059 +[2026-03-20T18:38:22.456751Z] Loop 5221: Loss: 1.87e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.1040 +[2026-03-20T18:38:23.310695Z] Loop 5222: Loss: 1.83e-02, Avg Return: 0.863, Regret: 0.0019, Entropy: 0.1037 +[2026-03-20T18:38:24.165303Z] Loop 5223: Loss: 1.82e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1014 +[2026-03-20T18:38:25.019179Z] Loop 5224: Loss: 1.95e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.1063 +[2026-03-20T18:38:25.873937Z] Loop 5225: Loss: 1.81e-02, Avg Return: 0.860, Regret: 0.0019, Entropy: 0.1011 +[2026-03-20T18:38:26.727747Z] Loop 5226: Loss: 1.82e-02, Avg Return: 0.859, Regret: 0.0019, Entropy: 0.1048 +[2026-03-20T18:38:27.583460Z] Loop 5227: Loss: 1.99e-02, Avg Return: 0.858, Regret: 0.0019, Entropy: 0.1043 +[2026-03-20T18:38:28.438049Z] Loop 5228: Loss: 2.05e-02, Avg Return: 0.859, Regret: 0.0019, Entropy: 0.1053 +[2026-03-20T18:38:29.291569Z] Loop 5229: Loss: 2.06e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1069 +[2026-03-20T18:38:30.186465Z] Loop 5230: Loss: 2.00e-02, Avg Return: 0.860, Regret: 0.0034, Entropy: 0.1123 +[2026-03-20T18:38:31.041022Z] Loop 5231: Loss: 1.78e-02, Avg Return: 0.860, Regret: 0.0034, Entropy: 0.1011 +[2026-03-20T18:38:31.894594Z] Loop 5232: Loss: 2.04e-02, Avg Return: 0.861, Regret: 0.0034, Entropy: 0.1068 +[2026-03-20T18:38:32.748070Z] Loop 5233: Loss: 1.78e-02, Avg Return: 0.861, Regret: 0.0034, Entropy: 0.0998 +[2026-03-20T18:38:33.602224Z] Loop 5234: Loss: 1.83e-02, Avg Return: 0.863, Regret: 0.0034, Entropy: 0.1011 +[2026-03-20T18:38:34.457114Z] Loop 5235: Loss: 1.85e-02, Avg Return: 0.861, Regret: 0.0034, Entropy: 0.1043 +[2026-03-20T18:38:35.310545Z] Loop 5236: Loss: 1.74e-02, Avg Return: 0.862, Regret: 0.0034, Entropy: 0.1005 +[2026-03-20T18:38:36.164157Z] Loop 5237: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0034, Entropy: 0.1049 +[2026-03-20T18:38:37.018571Z] Loop 5238: Loss: 2.00e-02, Avg Return: 0.861, Regret: 0.0034, Entropy: 0.1102 +[2026-03-20T18:38:37.873539Z] Loop 5239: Loss: 1.90e-02, Avg Return: 0.861, Regret: 0.0034, Entropy: 0.1112 +[2026-03-20T18:38:38.767703Z] Loop 5240: Loss: 2.07e-02, Avg Return: 0.860, Regret: 0.0034, Entropy: 0.1175 +[2026-03-20T18:38:39.621325Z] Loop 5241: Loss: 2.22e-02, Avg Return: 0.858, Regret: 0.0034, Entropy: 0.1227 +[2026-03-20T18:38:40.475745Z] Loop 5242: Loss: 2.38e-02, Avg Return: 0.860, Regret: 0.0034, Entropy: 0.1279 +[2026-03-20T18:38:41.330846Z] Loop 5243: Loss: 2.17e-02, Avg Return: 0.859, Regret: 0.0034, Entropy: 0.1207 +[2026-03-20T18:38:42.185474Z] Loop 5244: Loss: 2.11e-02, Avg Return: 0.860, Regret: 0.0034, Entropy: 0.1185 +[2026-03-20T18:38:43.039448Z] Loop 5245: Loss: 2.01e-02, Avg Return: 0.861, Regret: 0.0034, Entropy: 0.1115 +[2026-03-20T18:38:43.893176Z] Loop 5246: Loss: 1.89e-02, Avg Return: 0.861, Regret: 0.0034, Entropy: 0.1088 +[2026-03-20T18:38:44.748161Z] Loop 5247: Loss: 1.99e-02, Avg Return: 0.862, Regret: 0.0034, Entropy: 0.1109 +[2026-03-20T18:38:45.601044Z] Loop 5248: Loss: 1.88e-02, Avg Return: 0.861, Regret: 0.0034, Entropy: 0.1073 +[2026-03-20T18:38:46.453876Z] Loop 5249: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0034, Entropy: 0.1071 +[2026-03-20T18:38:47.348268Z] Loop 5250: Loss: 2.11e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.1147 +[2026-03-20T18:38:48.204112Z] Loop 5251: Loss: 2.04e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.1139 +[2026-03-20T18:38:49.058354Z] Loop 5252: Loss: 1.98e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.1124 +[2026-03-20T18:38:49.913034Z] Loop 5253: Loss: 2.11e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.1157 +[2026-03-20T18:38:50.766401Z] Loop 5254: Loss: 1.99e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.1106 +[2026-03-20T18:38:51.619776Z] Loop 5255: Loss: 1.99e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.1121 +[2026-03-20T18:38:52.474569Z] Loop 5256: Loss: 2.18e-02, Avg Return: 0.858, Regret: 0.0022, Entropy: 0.1156 +[2026-03-20T18:38:53.328476Z] Loop 5257: Loss: 2.31e-02, Avg Return: 0.858, Regret: 0.0022, Entropy: 0.1217 +[2026-03-20T18:38:54.182149Z] Loop 5258: Loss: 2.09e-02, Avg Return: 0.858, Regret: 0.0022, Entropy: 0.1180 +[2026-03-20T18:38:55.036010Z] Loop 5259: Loss: 2.02e-02, Avg Return: 0.859, Regret: 0.0022, Entropy: 0.1110 +[2026-03-20T18:38:55.931277Z] Loop 5260: Loss: 2.01e-02, Avg Return: 0.861, Regret: 0.0037, Entropy: 0.1124 +[2026-03-20T18:38:56.785402Z] Loop 5261: Loss: 1.94e-02, Avg Return: 0.861, Regret: 0.0037, Entropy: 0.1088 +[2026-03-20T18:38:57.639498Z] Loop 5262: Loss: 1.88e-02, Avg Return: 0.862, Regret: 0.0037, Entropy: 0.1067 +[2026-03-20T18:38:58.492602Z] Loop 5263: Loss: 1.85e-02, Avg Return: 0.861, Regret: 0.0037, Entropy: 0.1031 +[2026-03-20T18:38:59.345725Z] Loop 5264: Loss: 1.86e-02, Avg Return: 0.861, Regret: 0.0037, Entropy: 0.1044 +[2026-03-20T18:39:00.200441Z] Loop 5265: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0037, Entropy: 0.0986 +[2026-03-20T18:39:01.055263Z] Loop 5266: Loss: 1.83e-02, Avg Return: 0.862, Regret: 0.0037, Entropy: 0.0997 +[2026-03-20T18:39:01.908827Z] Loop 5267: Loss: 1.82e-02, Avg Return: 0.862, Regret: 0.0037, Entropy: 0.1034 +[2026-03-20T18:39:02.763136Z] Loop 5268: Loss: 1.94e-02, Avg Return: 0.861, Regret: 0.0037, Entropy: 0.1083 +[2026-03-20T18:39:03.617329Z] Loop 5269: Loss: 2.06e-02, Avg Return: 0.860, Regret: 0.0037, Entropy: 0.1149 +[2026-03-20T18:39:04.512809Z] Loop 5270: Loss: 2.20e-02, Avg Return: 0.859, Regret: 0.0040, Entropy: 0.1210 +[2026-03-20T18:39:05.366857Z] Loop 5271: Loss: 2.14e-02, Avg Return: 0.858, Regret: 0.0040, Entropy: 0.1123 +[2026-03-20T18:39:06.219462Z] Loop 5272: Loss: 2.06e-02, Avg Return: 0.860, Regret: 0.0040, Entropy: 0.1114 +[2026-03-20T18:39:07.072362Z] Loop 5273: Loss: 1.99e-02, Avg Return: 0.861, Regret: 0.0040, Entropy: 0.1087 +[2026-03-20T18:39:07.927166Z] Loop 5274: Loss: 1.79e-02, Avg Return: 0.860, Regret: 0.0040, Entropy: 0.1030 +[2026-03-20T18:39:08.781434Z] Loop 5275: Loss: 1.83e-02, Avg Return: 0.862, Regret: 0.0040, Entropy: 0.1020 +[2026-03-20T18:39:09.635363Z] Loop 5276: Loss: 1.90e-02, Avg Return: 0.861, Regret: 0.0040, Entropy: 0.1014 +[2026-03-20T18:39:10.488949Z] Loop 5277: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0040, Entropy: 0.1038 +[2026-03-20T18:39:11.343543Z] Loop 5278: Loss: 1.92e-02, Avg Return: 0.861, Regret: 0.0040, Entropy: 0.1081 +[2026-03-20T18:39:12.197103Z] Loop 5279: Loss: 1.71e-02, Avg Return: 0.861, Regret: 0.0040, Entropy: 0.1024 +[2026-03-20T18:39:13.089941Z] Loop 5280: Loss: 1.66e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.0984 +[2026-03-20T18:39:13.944202Z] Loop 5281: Loss: 1.84e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.1003 +[2026-03-20T18:39:14.798757Z] Loop 5282: Loss: 1.80e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0994 +[2026-03-20T18:39:15.653438Z] Loop 5283: Loss: 1.79e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.0981 +[2026-03-20T18:39:16.508443Z] Loop 5284: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0988 +[2026-03-20T18:39:17.363668Z] Loop 5285: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0981 +[2026-03-20T18:39:18.218894Z] Loop 5286: Loss: 1.84e-02, Avg Return: 0.863, Regret: 0.0025, Entropy: 0.1035 +[2026-03-20T18:39:19.073508Z] Loop 5287: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.1000 +[2026-03-20T18:39:19.927869Z] Loop 5288: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.1001 +[2026-03-20T18:39:20.781843Z] Loop 5289: Loss: 1.99e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.1066 +[2026-03-20T18:39:21.675617Z] Loop 5290: Loss: 1.87e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.1043 +[2026-03-20T18:39:22.530511Z] Loop 5291: Loss: 1.88e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.1004 +[2026-03-20T18:39:23.385234Z] Loop 5292: Loss: 1.87e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.1033 +[2026-03-20T18:39:24.239249Z] Loop 5293: Loss: 1.78e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.1047 +[2026-03-20T18:39:25.093073Z] Loop 5294: Loss: 1.98e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.1088 +[2026-03-20T18:39:25.947144Z] Loop 5295: Loss: 1.98e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.1098 +[2026-03-20T18:39:26.802431Z] Loop 5296: Loss: 2.02e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.1131 +[2026-03-20T18:39:27.656900Z] Loop 5297: Loss: 2.11e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.1150 +[2026-03-20T18:39:28.511563Z] Loop 5298: Loss: 2.16e-02, Avg Return: 0.860, Regret: 0.0014, Entropy: 0.1179 +[2026-03-20T18:39:29.365050Z] Loop 5299: Loss: 2.20e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.1205 +[2026-03-20T18:39:30.258190Z] Loop 5300: Loss: 1.93e-02, Avg Return: 0.860, Regret: 0.0031, Entropy: 0.1154 +[2026-03-20T18:39:31.112010Z] Loop 5301: Loss: 2.12e-02, Avg Return: 0.861, Regret: 0.0031, Entropy: 0.1178 +[2026-03-20T18:39:31.966770Z] Loop 5302: Loss: 2.09e-02, Avg Return: 0.861, Regret: 0.0031, Entropy: 0.1171 +[2026-03-20T18:39:32.820493Z] Loop 5303: Loss: 2.01e-02, Avg Return: 0.858, Regret: 0.0031, Entropy: 0.1165 +[2026-03-20T18:39:33.673192Z] Loop 5304: Loss: 2.06e-02, Avg Return: 0.859, Regret: 0.0031, Entropy: 0.1157 +[2026-03-20T18:39:34.526146Z] Loop 5305: Loss: 2.00e-02, Avg Return: 0.858, Regret: 0.0031, Entropy: 0.1150 +[2026-03-20T18:39:35.380665Z] Loop 5306: Loss: 2.00e-02, Avg Return: 0.860, Regret: 0.0031, Entropy: 0.1148 +[2026-03-20T18:39:36.235872Z] Loop 5307: Loss: 1.83e-02, Avg Return: 0.862, Regret: 0.0031, Entropy: 0.1058 +[2026-03-20T18:39:37.088702Z] Loop 5308: Loss: 2.01e-02, Avg Return: 0.861, Regret: 0.0031, Entropy: 0.1092 +[2026-03-20T18:39:37.941915Z] Loop 5309: Loss: 1.79e-02, Avg Return: 0.862, Regret: 0.0031, Entropy: 0.1031 +[2026-03-20T18:39:38.837743Z] Loop 5310: Loss: 1.89e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.1046 +[2026-03-20T18:39:39.691547Z] Loop 5311: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.1025 +[2026-03-20T18:39:40.545502Z] Loop 5312: Loss: 1.84e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0966 +[2026-03-20T18:39:41.399191Z] Loop 5313: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0972 +[2026-03-20T18:39:42.252834Z] Loop 5314: Loss: 1.73e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0969 +[2026-03-20T18:39:43.107127Z] Loop 5315: Loss: 1.96e-02, Avg Return: 0.860, Regret: 0.0016, Entropy: 0.1092 +[2026-03-20T18:39:43.961553Z] Loop 5316: Loss: 2.04e-02, Avg Return: 0.856, Regret: 0.0016, Entropy: 0.1098 +[2026-03-20T18:39:44.816104Z] Loop 5317: Loss: 2.26e-02, Avg Return: 0.854, Regret: 0.0016, Entropy: 0.1150 +[2026-03-20T18:39:45.669490Z] Loop 5318: Loss: 2.48e-02, Avg Return: 0.851, Regret: 0.0016, Entropy: 0.1271 +[2026-03-20T18:39:46.523158Z] Loop 5319: Loss: 2.32e-02, Avg Return: 0.852, Regret: 0.0016, Entropy: 0.1239 +[2026-03-20T18:39:47.417758Z] Loop 5320: Loss: 2.26e-02, Avg Return: 0.855, Regret: 0.0094, Entropy: 0.1180 +[2026-03-20T18:39:48.272244Z] Loop 5321: Loss: 2.11e-02, Avg Return: 0.855, Regret: 0.0094, Entropy: 0.1108 +[2026-03-20T18:39:49.126135Z] Loop 5322: Loss: 2.02e-02, Avg Return: 0.859, Regret: 0.0094, Entropy: 0.1046 +[2026-03-20T18:39:49.979028Z] Loop 5323: Loss: 1.82e-02, Avg Return: 0.861, Regret: 0.0094, Entropy: 0.0995 +[2026-03-20T18:39:50.832833Z] Loop 5324: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0094, Entropy: 0.0958 +[2026-03-20T18:39:51.686861Z] Loop 5325: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0094, Entropy: 0.0987 +[2026-03-20T18:39:52.540051Z] Loop 5326: Loss: 1.88e-02, Avg Return: 0.862, Regret: 0.0094, Entropy: 0.1016 +[2026-03-20T18:39:53.393512Z] Loop 5327: Loss: 1.90e-02, Avg Return: 0.860, Regret: 0.0094, Entropy: 0.1058 +[2026-03-20T18:39:54.247223Z] Loop 5328: Loss: 1.99e-02, Avg Return: 0.859, Regret: 0.0094, Entropy: 0.1096 +[2026-03-20T18:39:55.103180Z] Loop 5329: Loss: 1.96e-02, Avg Return: 0.858, Regret: 0.0094, Entropy: 0.1169 +[2026-03-20T18:39:55.999894Z] Loop 5330: Loss: 2.10e-02, Avg Return: 0.857, Regret: 0.0060, Entropy: 0.1151 +[2026-03-20T18:39:56.853340Z] Loop 5331: Loss: 2.02e-02, Avg Return: 0.857, Regret: 0.0060, Entropy: 0.1170 +[2026-03-20T18:39:57.706817Z] Loop 5332: Loss: 2.04e-02, Avg Return: 0.858, Regret: 0.0060, Entropy: 0.1149 +[2026-03-20T18:39:58.561243Z] Loop 5333: Loss: 2.13e-02, Avg Return: 0.859, Regret: 0.0060, Entropy: 0.1190 +[2026-03-20T18:39:59.415459Z] Loop 5334: Loss: 2.06e-02, Avg Return: 0.858, Regret: 0.0060, Entropy: 0.1138 +[2026-03-20T18:40:00.269353Z] Loop 5335: Loss: 1.94e-02, Avg Return: 0.858, Regret: 0.0060, Entropy: 0.1109 +[2026-03-20T18:40:01.123430Z] Loop 5336: Loss: 2.09e-02, Avg Return: 0.858, Regret: 0.0060, Entropy: 0.1101 +[2026-03-20T18:40:01.977865Z] Loop 5337: Loss: 2.15e-02, Avg Return: 0.855, Regret: 0.0060, Entropy: 0.1132 +[2026-03-20T18:40:02.832513Z] Loop 5338: Loss: 2.00e-02, Avg Return: 0.857, Regret: 0.0060, Entropy: 0.1096 +[2026-03-20T18:40:03.687667Z] Loop 5339: Loss: 2.07e-02, Avg Return: 0.860, Regret: 0.0060, Entropy: 0.1110 +[2026-03-20T18:40:04.582574Z] Loop 5340: Loss: 1.83e-02, Avg Return: 0.861, Regret: 0.0032, Entropy: 0.1053 +[2026-03-20T18:40:05.437037Z] Loop 5341: Loss: 1.88e-02, Avg Return: 0.862, Regret: 0.0032, Entropy: 0.1070 +[2026-03-20T18:40:06.292272Z] Loop 5342: Loss: 1.90e-02, Avg Return: 0.861, Regret: 0.0032, Entropy: 0.1030 +[2026-03-20T18:40:07.146229Z] Loop 5343: Loss: 1.99e-02, Avg Return: 0.860, Regret: 0.0032, Entropy: 0.1099 +[2026-03-20T18:40:08.000136Z] Loop 5344: Loss: 1.90e-02, Avg Return: 0.862, Regret: 0.0032, Entropy: 0.1090 +[2026-03-20T18:40:08.854972Z] Loop 5345: Loss: 1.99e-02, Avg Return: 0.862, Regret: 0.0032, Entropy: 0.1106 +[2026-03-20T18:40:09.709896Z] Loop 5346: Loss: 1.92e-02, Avg Return: 0.860, Regret: 0.0032, Entropy: 0.1122 +[2026-03-20T18:40:10.564404Z] Loop 5347: Loss: 1.83e-02, Avg Return: 0.863, Regret: 0.0032, Entropy: 0.1080 +[2026-03-20T18:40:11.420323Z] Loop 5348: Loss: 1.96e-02, Avg Return: 0.861, Regret: 0.0032, Entropy: 0.1134 +[2026-03-20T18:40:12.273922Z] Loop 5349: Loss: 1.98e-02, Avg Return: 0.862, Regret: 0.0032, Entropy: 0.1150 +[2026-03-20T18:40:13.170270Z] Loop 5350: Loss: 2.01e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.1151 +[2026-03-20T18:40:14.024993Z] Loop 5351: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.1126 +[2026-03-20T18:40:14.881012Z] Loop 5352: Loss: 2.08e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.1123 +[2026-03-20T18:40:15.736239Z] Loop 5353: Loss: 2.06e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.1150 +[2026-03-20T18:40:16.591282Z] Loop 5354: Loss: 1.99e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.1125 +[2026-03-20T18:40:17.446046Z] Loop 5355: Loss: 1.99e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.1134 +[2026-03-20T18:40:18.299892Z] Loop 5356: Loss: 2.13e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.1152 +[2026-03-20T18:40:19.154548Z] Loop 5357: Loss: 2.04e-02, Avg Return: 0.860, Regret: 0.0024, Entropy: 0.1107 +[2026-03-20T18:40:20.008207Z] Loop 5358: Loss: 1.97e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.1080 +[2026-03-20T18:40:20.861577Z] Loop 5359: Loss: 2.01e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.1090 +[2026-03-20T18:40:21.757752Z] Loop 5360: Loss: 1.85e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0992 +[2026-03-20T18:40:22.612378Z] Loop 5361: Loss: 1.95e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1098 +[2026-03-20T18:40:23.466756Z] Loop 5362: Loss: 1.99e-02, Avg Return: 0.860, Regret: 0.0019, Entropy: 0.1124 +[2026-03-20T18:40:24.321670Z] Loop 5363: Loss: 1.89e-02, Avg Return: 0.859, Regret: 0.0019, Entropy: 0.1061 +[2026-03-20T18:40:25.176394Z] Loop 5364: Loss: 1.99e-02, Avg Return: 0.860, Regret: 0.0019, Entropy: 0.1113 +[2026-03-20T18:40:26.032731Z] Loop 5365: Loss: 1.87e-02, Avg Return: 0.859, Regret: 0.0019, Entropy: 0.1125 +[2026-03-20T18:40:26.888050Z] Loop 5366: Loss: 2.09e-02, Avg Return: 0.859, Regret: 0.0019, Entropy: 0.1143 +[2026-03-20T18:40:27.743530Z] Loop 5367: Loss: 2.20e-02, Avg Return: 0.860, Regret: 0.0019, Entropy: 0.1200 +[2026-03-20T18:40:28.597551Z] Loop 5368: Loss: 1.90e-02, Avg Return: 0.858, Regret: 0.0019, Entropy: 0.1114 +[2026-03-20T18:40:29.452800Z] Loop 5369: Loss: 2.12e-02, Avg Return: 0.859, Regret: 0.0019, Entropy: 0.1185 +[2026-03-20T18:40:30.348287Z] Loop 5370: Loss: 1.99e-02, Avg Return: 0.860, Regret: 0.0040, Entropy: 0.1114 +[2026-03-20T18:40:31.201194Z] Loop 5371: Loss: 2.02e-02, Avg Return: 0.860, Regret: 0.0040, Entropy: 0.1148 +[2026-03-20T18:40:32.053966Z] Loop 5372: Loss: 2.17e-02, Avg Return: 0.859, Regret: 0.0040, Entropy: 0.1150 +[2026-03-20T18:40:32.907840Z] Loop 5373: Loss: 2.07e-02, Avg Return: 0.861, Regret: 0.0040, Entropy: 0.1173 +[2026-03-20T18:40:33.762484Z] Loop 5374: Loss: 1.85e-02, Avg Return: 0.860, Regret: 0.0040, Entropy: 0.1062 +[2026-03-20T18:40:34.616936Z] Loop 5375: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0040, Entropy: 0.1032 +[2026-03-20T18:40:35.470076Z] Loop 5376: Loss: 1.85e-02, Avg Return: 0.862, Regret: 0.0040, Entropy: 0.1015 +[2026-03-20T18:40:36.323995Z] Loop 5377: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0040, Entropy: 0.0986 +[2026-03-20T18:40:37.177994Z] Loop 5378: Loss: 1.88e-02, Avg Return: 0.861, Regret: 0.0040, Entropy: 0.1031 +[2026-03-20T18:40:38.032474Z] Loop 5379: Loss: 1.79e-02, Avg Return: 0.863, Regret: 0.0040, Entropy: 0.0978 +[2026-03-20T18:40:38.925608Z] Loop 5380: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0993 +[2026-03-20T18:40:39.778584Z] Loop 5381: Loss: 1.90e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.1002 +[2026-03-20T18:40:40.632282Z] Loop 5382: Loss: 1.77e-02, Avg Return: 0.864, Regret: 0.0015, Entropy: 0.1001 +[2026-03-20T18:40:41.486256Z] Loop 5383: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.1007 +[2026-03-20T18:40:42.340195Z] Loop 5384: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.1052 +[2026-03-20T18:40:43.193518Z] Loop 5385: Loss: 1.68e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.0935 +[2026-03-20T18:40:44.046862Z] Loop 5386: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.1017 +[2026-03-20T18:40:44.900268Z] Loop 5387: Loss: 1.83e-02, Avg Return: 0.864, Regret: 0.0015, Entropy: 0.0973 +[2026-03-20T18:40:45.753834Z] Loop 5388: Loss: 1.68e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0970 +[2026-03-20T18:40:46.607906Z] Loop 5389: Loss: 1.76e-02, Avg Return: 0.864, Regret: 0.0015, Entropy: 0.0962 +[2026-03-20T18:40:47.502165Z] Loop 5390: Loss: 1.78e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0965 +[2026-03-20T18:40:48.355286Z] Loop 5391: Loss: 1.82e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0986 +[2026-03-20T18:40:49.209464Z] Loop 5392: Loss: 1.84e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.1016 +[2026-03-20T18:40:50.063940Z] Loop 5393: Loss: 1.71e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0958 +[2026-03-20T18:40:50.918689Z] Loop 5394: Loss: 1.82e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.1009 +[2026-03-20T18:40:51.772680Z] Loop 5395: Loss: 1.89e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.1045 +[2026-03-20T18:40:52.626860Z] Loop 5396: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.1040 +[2026-03-20T18:40:53.481283Z] Loop 5397: Loss: 1.85e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.1007 +[2026-03-20T18:40:54.334885Z] Loop 5398: Loss: 1.83e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.1005 +[2026-03-20T18:40:55.188112Z] Loop 5399: Loss: 1.83e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.1067 +[2026-03-20T18:40:56.082858Z] Loop 5400: Loss: 1.91e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.1068 +[2026-03-20T18:40:56.937698Z] Loop 5401: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.1016 +[2026-03-20T18:40:57.791979Z] Loop 5402: Loss: 1.91e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.1081 +[2026-03-20T18:40:58.646781Z] Loop 5403: Loss: 2.09e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.1115 +[2026-03-20T18:40:59.501665Z] Loop 5404: Loss: 1.92e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.1055 +[2026-03-20T18:41:00.355888Z] Loop 5405: Loss: 1.90e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.1068 +[2026-03-20T18:41:01.208833Z] Loop 5406: Loss: 1.93e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.1075 +[2026-03-20T18:41:02.062054Z] Loop 5407: Loss: 1.96e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.1092 +[2026-03-20T18:41:02.915880Z] Loop 5408: Loss: 1.96e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.1086 +[2026-03-20T18:41:03.770073Z] Loop 5409: Loss: 1.81e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.1032 +[2026-03-20T18:41:04.664621Z] Loop 5410: Loss: 1.79e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.1030 +[2026-03-20T18:41:05.519545Z] Loop 5411: Loss: 1.99e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1078 +[2026-03-20T18:41:06.374511Z] Loop 5412: Loss: 1.91e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1061 +[2026-03-20T18:41:07.230240Z] Loop 5413: Loss: 1.89e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.1082 +[2026-03-20T18:41:08.086079Z] Loop 5414: Loss: 1.86e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1042 +[2026-03-20T18:41:08.941487Z] Loop 5415: Loss: 1.83e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1034 +[2026-03-20T18:41:09.796283Z] Loop 5416: Loss: 1.95e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1091 +[2026-03-20T18:41:10.650225Z] Loop 5417: Loss: 1.89e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1042 +[2026-03-20T18:41:11.504559Z] Loop 5418: Loss: 2.07e-02, Avg Return: 0.858, Regret: 0.0019, Entropy: 0.1140 +[2026-03-20T18:41:12.359149Z] Loop 5419: Loss: 2.07e-02, Avg Return: 0.858, Regret: 0.0019, Entropy: 0.1140 +[2026-03-20T18:41:13.254058Z] Loop 5420: Loss: 2.24e-02, Avg Return: 0.856, Regret: 0.0068, Entropy: 0.1237 +[2026-03-20T18:41:14.108703Z] Loop 5421: Loss: 2.26e-02, Avg Return: 0.855, Regret: 0.0068, Entropy: 0.1230 +[2026-03-20T18:41:14.962916Z] Loop 5422: Loss: 2.43e-02, Avg Return: 0.855, Regret: 0.0068, Entropy: 0.1304 +[2026-03-20T18:41:15.816836Z] Loop 5423: Loss: 2.40e-02, Avg Return: 0.856, Regret: 0.0068, Entropy: 0.1281 +[2026-03-20T18:41:16.673250Z] Loop 5424: Loss: 2.17e-02, Avg Return: 0.855, Regret: 0.0068, Entropy: 0.1199 +[2026-03-20T18:41:17.528685Z] Loop 5425: Loss: 2.29e-02, Avg Return: 0.856, Regret: 0.0068, Entropy: 0.1224 +[2026-03-20T18:41:18.381815Z] Loop 5426: Loss: 2.31e-02, Avg Return: 0.856, Regret: 0.0068, Entropy: 0.1230 +[2026-03-20T18:41:19.234989Z] Loop 5427: Loss: 2.21e-02, Avg Return: 0.858, Regret: 0.0068, Entropy: 0.1225 +[2026-03-20T18:41:20.089624Z] Loop 5428: Loss: 2.01e-02, Avg Return: 0.858, Regret: 0.0068, Entropy: 0.1161 +[2026-03-20T18:41:20.944281Z] Loop 5429: Loss: 2.04e-02, Avg Return: 0.858, Regret: 0.0068, Entropy: 0.1149 +[2026-03-20T18:41:21.837792Z] Loop 5430: Loss: 1.95e-02, Avg Return: 0.861, Regret: 0.0036, Entropy: 0.1078 +[2026-03-20T18:41:22.690971Z] Loop 5431: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.1066 +[2026-03-20T18:41:23.544315Z] Loop 5432: Loss: 1.87e-02, Avg Return: 0.861, Regret: 0.0036, Entropy: 0.1023 +[2026-03-20T18:41:24.398547Z] Loop 5433: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.1030 +[2026-03-20T18:41:25.252023Z] Loop 5434: Loss: 1.84e-02, Avg Return: 0.861, Regret: 0.0036, Entropy: 0.1024 +[2026-03-20T18:41:26.105761Z] Loop 5435: Loss: 1.82e-02, Avg Return: 0.861, Regret: 0.0036, Entropy: 0.1015 +[2026-03-20T18:41:26.959685Z] Loop 5436: Loss: 1.82e-02, Avg Return: 0.863, Regret: 0.0036, Entropy: 0.1018 +[2026-03-20T18:41:27.813011Z] Loop 5437: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0036, Entropy: 0.0976 +[2026-03-20T18:41:28.667620Z] Loop 5438: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.0992 +[2026-03-20T18:41:29.521482Z] Loop 5439: Loss: 1.87e-02, Avg Return: 0.863, Regret: 0.0036, Entropy: 0.1037 +[2026-03-20T18:41:30.415943Z] Loop 5440: Loss: 1.71e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0963 +[2026-03-20T18:41:31.269761Z] Loop 5441: Loss: 1.96e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.1051 +[2026-03-20T18:41:32.123968Z] Loop 5442: Loss: 1.78e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.1004 +[2026-03-20T18:41:32.978315Z] Loop 5443: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.1024 +[2026-03-20T18:41:33.831719Z] Loop 5444: Loss: 1.82e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.1031 +[2026-03-20T18:41:34.685529Z] Loop 5445: Loss: 1.73e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.1008 +[2026-03-20T18:41:35.540168Z] Loop 5446: Loss: 1.87e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.1033 +[2026-03-20T18:41:36.394488Z] Loop 5447: Loss: 1.90e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.1077 +[2026-03-20T18:41:37.248770Z] Loop 5448: Loss: 1.76e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.1005 +[2026-03-20T18:41:38.102275Z] Loop 5449: Loss: 1.78e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.1003 +[2026-03-20T18:41:38.996099Z] Loop 5450: Loss: 1.94e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.1044 +[2026-03-20T18:41:39.850828Z] Loop 5451: Loss: 1.76e-02, Avg Return: 0.860, Regret: 0.0020, Entropy: 0.0966 +[2026-03-20T18:41:40.704877Z] Loop 5452: Loss: 1.82e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.1018 +[2026-03-20T18:41:41.561265Z] Loop 5453: Loss: 1.91e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.1047 +[2026-03-20T18:41:42.414297Z] Loop 5454: Loss: 1.89e-02, Avg Return: 0.860, Regret: 0.0020, Entropy: 0.1030 +[2026-03-20T18:41:43.267714Z] Loop 5455: Loss: 1.87e-02, Avg Return: 0.860, Regret: 0.0020, Entropy: 0.1065 +[2026-03-20T18:41:44.122223Z] Loop 5456: Loss: 1.91e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.1076 +[2026-03-20T18:41:44.976184Z] Loop 5457: Loss: 1.86e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.1058 +[2026-03-20T18:41:45.829508Z] Loop 5458: Loss: 2.02e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.1132 +[2026-03-20T18:41:46.682390Z] Loop 5459: Loss: 2.07e-02, Avg Return: 0.860, Regret: 0.0020, Entropy: 0.1164 +[2026-03-20T18:41:47.578002Z] Loop 5460: Loss: 1.97e-02, Avg Return: 0.860, Regret: 0.0040, Entropy: 0.1144 +[2026-03-20T18:41:48.432639Z] Loop 5461: Loss: 2.09e-02, Avg Return: 0.861, Regret: 0.0040, Entropy: 0.1235 +[2026-03-20T18:41:49.287074Z] Loop 5462: Loss: 2.18e-02, Avg Return: 0.859, Regret: 0.0040, Entropy: 0.1235 +[2026-03-20T18:41:50.141074Z] Loop 5463: Loss: 2.15e-02, Avg Return: 0.859, Regret: 0.0040, Entropy: 0.1219 +[2026-03-20T18:41:50.996125Z] Loop 5464: Loss: 2.24e-02, Avg Return: 0.860, Regret: 0.0040, Entropy: 0.1258 +[2026-03-20T18:41:51.850456Z] Loop 5465: Loss: 2.04e-02, Avg Return: 0.860, Regret: 0.0040, Entropy: 0.1180 +[2026-03-20T18:41:52.704964Z] Loop 5466: Loss: 2.03e-02, Avg Return: 0.860, Regret: 0.0040, Entropy: 0.1158 +[2026-03-20T18:41:53.559122Z] Loop 5467: Loss: 2.04e-02, Avg Return: 0.862, Regret: 0.0040, Entropy: 0.1141 +[2026-03-20T18:41:54.413518Z] Loop 5468: Loss: 1.96e-02, Avg Return: 0.862, Regret: 0.0040, Entropy: 0.1076 +[2026-03-20T18:41:55.267413Z] Loop 5469: Loss: 1.96e-02, Avg Return: 0.863, Regret: 0.0040, Entropy: 0.1109 +[2026-03-20T18:41:56.161070Z] Loop 5470: Loss: 1.88e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.1114 +[2026-03-20T18:41:57.015562Z] Loop 5471: Loss: 1.87e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.1109 +[2026-03-20T18:41:57.869494Z] Loop 5472: Loss: 1.98e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.1091 +[2026-03-20T18:41:58.724386Z] Loop 5473: Loss: 1.90e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.1089 +[2026-03-20T18:41:59.578357Z] Loop 5474: Loss: 1.97e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.1109 +[2026-03-20T18:42:00.432236Z] Loop 5475: Loss: 2.15e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.1136 +[2026-03-20T18:42:01.285082Z] Loop 5476: Loss: 1.83e-02, Avg Return: 0.862, Regret: 0.0026, Entropy: 0.1055 +[2026-03-20T18:42:02.138379Z] Loop 5477: Loss: 1.89e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.1048 +[2026-03-20T18:42:02.992128Z] Loop 5478: Loss: 1.89e-02, Avg Return: 0.863, Regret: 0.0026, Entropy: 0.1073 +[2026-03-20T18:42:03.846521Z] Loop 5479: Loss: 1.89e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.1034 +[2026-03-20T18:42:04.742222Z] Loop 5480: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0998 +[2026-03-20T18:42:05.596463Z] Loop 5481: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0993 +[2026-03-20T18:42:06.451401Z] Loop 5482: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.1040 +[2026-03-20T18:42:07.307456Z] Loop 5483: Loss: 1.92e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.1058 +[2026-03-20T18:42:08.161923Z] Loop 5484: Loss: 1.81e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.1078 +[2026-03-20T18:42:09.015758Z] Loop 5485: Loss: 1.99e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.1123 +[2026-03-20T18:42:09.868884Z] Loop 5486: Loss: 2.01e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.1169 +[2026-03-20T18:42:10.723064Z] Loop 5487: Loss: 2.11e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.1188 +[2026-03-20T18:42:11.577070Z] Loop 5488: Loss: 1.98e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.1189 +[2026-03-20T18:42:12.430485Z] Loop 5489: Loss: 2.07e-02, Avg Return: 0.860, Regret: 0.0016, Entropy: 0.1208 +[2026-03-20T18:42:13.325266Z] Loop 5490: Loss: 2.21e-02, Avg Return: 0.860, Regret: 0.0036, Entropy: 0.1239 +[2026-03-20T18:42:14.179482Z] Loop 5491: Loss: 2.09e-02, Avg Return: 0.860, Regret: 0.0036, Entropy: 0.1156 +[2026-03-20T18:42:15.034229Z] Loop 5492: Loss: 2.10e-02, Avg Return: 0.861, Regret: 0.0036, Entropy: 0.1171 +[2026-03-20T18:42:15.889870Z] Loop 5493: Loss: 2.05e-02, Avg Return: 0.861, Regret: 0.0036, Entropy: 0.1135 +[2026-03-20T18:42:16.742369Z] Loop 5494: Loss: 2.04e-02, Avg Return: 0.861, Regret: 0.0036, Entropy: 0.1150 +[2026-03-20T18:42:17.596107Z] Loop 5495: Loss: 1.99e-02, Avg Return: 0.861, Regret: 0.0036, Entropy: 0.1121 +[2026-03-20T18:42:18.450542Z] Loop 5496: Loss: 1.77e-02, Avg Return: 0.861, Regret: 0.0036, Entropy: 0.1056 +[2026-03-20T18:42:19.305904Z] Loop 5497: Loss: 2.08e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.1121 +[2026-03-20T18:42:20.159816Z] Loop 5498: Loss: 2.07e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.1149 +[2026-03-20T18:42:21.014153Z] Loop 5499: Loss: 2.05e-02, Avg Return: 0.861, Regret: 0.0036, Entropy: 0.1099 +[2026-03-20T18:42:21.908893Z] Loop 5500: Loss: 1.93e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.1112 +[2026-03-20T18:42:22.762966Z] Loop 5501: Loss: 1.81e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.1007 +[2026-03-20T18:42:23.616783Z] Loop 5502: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.1024 +[2026-03-20T18:42:24.470823Z] Loop 5503: Loss: 1.82e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.1020 +[2026-03-20T18:42:25.323957Z] Loop 5504: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.1059 +[2026-03-20T18:42:26.177408Z] Loop 5505: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.1001 +[2026-03-20T18:42:27.031479Z] Loop 5506: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0996 +[2026-03-20T18:42:27.886804Z] Loop 5507: Loss: 1.75e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0991 +[2026-03-20T18:42:28.740151Z] Loop 5508: Loss: 1.80e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0988 +[2026-03-20T18:42:29.593522Z] Loop 5509: Loss: 1.73e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.1041 +[2026-03-20T18:42:30.487465Z] Loop 5510: Loss: 1.90e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.1063 +[2026-03-20T18:42:31.341762Z] Loop 5511: Loss: 1.90e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.1078 +[2026-03-20T18:42:32.195757Z] Loop 5512: Loss: 1.90e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.1087 +[2026-03-20T18:42:33.049517Z] Loop 5513: Loss: 1.87e-02, Avg Return: 0.863, Regret: 0.0021, Entropy: 0.1043 +[2026-03-20T18:42:33.904047Z] Loop 5514: Loss: 2.05e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.1113 +[2026-03-20T18:42:34.758545Z] Loop 5515: Loss: 2.02e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.1147 +[2026-03-20T18:42:35.612060Z] Loop 5516: Loss: 2.12e-02, Avg Return: 0.859, Regret: 0.0021, Entropy: 0.1161 +[2026-03-20T18:42:36.465538Z] Loop 5517: Loss: 1.97e-02, Avg Return: 0.859, Regret: 0.0021, Entropy: 0.1111 +[2026-03-20T18:42:37.319770Z] Loop 5518: Loss: 2.13e-02, Avg Return: 0.860, Regret: 0.0021, Entropy: 0.1150 +[2026-03-20T18:42:38.173775Z] Loop 5519: Loss: 1.95e-02, Avg Return: 0.860, Regret: 0.0021, Entropy: 0.1160 +[2026-03-20T18:42:39.066935Z] Loop 5520: Loss: 1.83e-02, Avg Return: 0.860, Regret: 0.0029, Entropy: 0.1077 +[2026-03-20T18:42:39.921199Z] Loop 5521: Loss: 1.90e-02, Avg Return: 0.862, Regret: 0.0029, Entropy: 0.1057 +[2026-03-20T18:42:40.776092Z] Loop 5522: Loss: 1.71e-02, Avg Return: 0.861, Regret: 0.0029, Entropy: 0.0967 +[2026-03-20T18:42:41.630326Z] Loop 5523: Loss: 1.78e-02, Avg Return: 0.861, Regret: 0.0029, Entropy: 0.0994 +[2026-03-20T18:42:42.484085Z] Loop 5524: Loss: 1.78e-02, Avg Return: 0.861, Regret: 0.0029, Entropy: 0.0992 +[2026-03-20T18:42:43.337508Z] Loop 5525: Loss: 1.81e-02, Avg Return: 0.861, Regret: 0.0029, Entropy: 0.1012 +[2026-03-20T18:42:44.191794Z] Loop 5526: Loss: 1.97e-02, Avg Return: 0.861, Regret: 0.0029, Entropy: 0.1050 +[2026-03-20T18:42:45.046160Z] Loop 5527: Loss: 1.92e-02, Avg Return: 0.860, Regret: 0.0029, Entropy: 0.1074 +[2026-03-20T18:42:45.900111Z] Loop 5528: Loss: 2.02e-02, Avg Return: 0.860, Regret: 0.0029, Entropy: 0.1063 +[2026-03-20T18:42:46.754727Z] Loop 5529: Loss: 1.92e-02, Avg Return: 0.860, Regret: 0.0029, Entropy: 0.1077 +[2026-03-20T18:42:47.650409Z] Loop 5530: Loss: 1.87e-02, Avg Return: 0.860, Regret: 0.0036, Entropy: 0.1053 +[2026-03-20T18:42:48.504061Z] Loop 5531: Loss: 1.85e-02, Avg Return: 0.860, Regret: 0.0036, Entropy: 0.1042 +[2026-03-20T18:42:49.358198Z] Loop 5532: Loss: 1.86e-02, Avg Return: 0.860, Regret: 0.0036, Entropy: 0.1043 +[2026-03-20T18:42:50.212554Z] Loop 5533: Loss: 1.76e-02, Avg Return: 0.860, Regret: 0.0036, Entropy: 0.0989 +[2026-03-20T18:42:51.066957Z] Loop 5534: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.1001 +[2026-03-20T18:42:51.919360Z] Loop 5535: Loss: 1.67e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.0938 +[2026-03-20T18:42:52.771999Z] Loop 5536: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.0948 +[2026-03-20T18:42:53.626054Z] Loop 5537: Loss: 1.83e-02, Avg Return: 0.861, Regret: 0.0036, Entropy: 0.0994 +[2026-03-20T18:42:54.479328Z] Loop 5538: Loss: 1.82e-02, Avg Return: 0.863, Regret: 0.0036, Entropy: 0.1013 +[2026-03-20T18:42:55.331994Z] Loop 5539: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.0990 +[2026-03-20T18:42:56.225976Z] Loop 5540: Loss: 1.73e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0960 +[2026-03-20T18:42:57.079727Z] Loop 5541: Loss: 1.59e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0922 +[2026-03-20T18:42:57.933395Z] Loop 5542: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0951 +[2026-03-20T18:42:58.787681Z] Loop 5543: Loss: 1.83e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0986 +[2026-03-20T18:42:59.640171Z] Loop 5544: Loss: 1.74e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0991 +[2026-03-20T18:43:00.493004Z] Loop 5545: Loss: 1.79e-02, Avg Return: 0.860, Regret: 0.0011, Entropy: 0.1031 +[2026-03-20T18:43:01.347567Z] Loop 5546: Loss: 1.85e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.1025 +[2026-03-20T18:43:02.203401Z] Loop 5547: Loss: 2.02e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.1084 +[2026-03-20T18:43:03.057557Z] Loop 5548: Loss: 1.78e-02, Avg Return: 0.860, Regret: 0.0011, Entropy: 0.0998 +[2026-03-20T18:43:03.911238Z] Loop 5549: Loss: 1.91e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.1060 +[2026-03-20T18:43:04.807280Z] Loop 5550: Loss: 1.98e-02, Avg Return: 0.860, Regret: 0.0019, Entropy: 0.1076 +[2026-03-20T18:43:05.661285Z] Loop 5551: Loss: 1.89e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1075 +[2026-03-20T18:43:06.515902Z] Loop 5552: Loss: 1.87e-02, Avg Return: 0.863, Regret: 0.0019, Entropy: 0.1086 +[2026-03-20T18:43:07.369177Z] Loop 5553: Loss: 1.80e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.1046 +[2026-03-20T18:43:08.225108Z] Loop 5554: Loss: 2.06e-02, Avg Return: 0.860, Regret: 0.0019, Entropy: 0.1112 +[2026-03-20T18:43:09.079816Z] Loop 5555: Loss: 1.81e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1077 +[2026-03-20T18:43:09.933770Z] Loop 5556: Loss: 1.87e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1033 +[2026-03-20T18:43:10.787755Z] Loop 5557: Loss: 2.01e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.1110 +[2026-03-20T18:43:11.643770Z] Loop 5558: Loss: 1.84e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1043 +[2026-03-20T18:43:12.498998Z] Loop 5559: Loss: 2.03e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1084 +[2026-03-20T18:43:13.396374Z] Loop 5560: Loss: 1.86e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1039 +[2026-03-20T18:43:14.250576Z] Loop 5561: Loss: 1.90e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.1071 +[2026-03-20T18:43:15.104920Z] Loop 5562: Loss: 1.91e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.1072 +[2026-03-20T18:43:15.958357Z] Loop 5563: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0993 +[2026-03-20T18:43:16.811685Z] Loop 5564: Loss: 1.83e-02, Avg Return: 0.863, Regret: 0.0019, Entropy: 0.1018 +[2026-03-20T18:43:17.665306Z] Loop 5565: Loss: 1.70e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0970 +[2026-03-20T18:43:18.519860Z] Loop 5566: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0974 +[2026-03-20T18:43:19.373943Z] Loop 5567: Loss: 1.75e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0984 +[2026-03-20T18:43:20.227037Z] Loop 5568: Loss: 1.68e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0973 +[2026-03-20T18:43:21.080551Z] Loop 5569: Loss: 1.77e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0981 +[2026-03-20T18:43:21.976333Z] Loop 5570: Loss: 1.88e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.1030 +[2026-03-20T18:43:22.830041Z] Loop 5571: Loss: 1.99e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.1064 +[2026-03-20T18:43:23.683445Z] Loop 5572: Loss: 1.74e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.0999 +[2026-03-20T18:43:24.537561Z] Loop 5573: Loss: 1.75e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.0951 +[2026-03-20T18:43:25.392494Z] Loop 5574: Loss: 1.81e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.1017 +[2026-03-20T18:43:26.246087Z] Loop 5575: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.1022 +[2026-03-20T18:43:27.099797Z] Loop 5576: Loss: 1.71e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.1018 +[2026-03-20T18:43:27.953350Z] Loop 5577: Loss: 1.96e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.1076 +[2026-03-20T18:43:28.808017Z] Loop 5578: Loss: 2.14e-02, Avg Return: 0.859, Regret: 0.0020, Entropy: 0.1181 +[2026-03-20T18:43:29.662007Z] Loop 5579: Loss: 2.50e-02, Avg Return: 0.854, Regret: 0.0020, Entropy: 0.1326 +[2026-03-20T18:43:30.555594Z] Loop 5580: Loss: 2.75e-02, Avg Return: 0.850, Regret: 0.0149, Entropy: 0.1454 +[2026-03-20T18:43:31.409724Z] Loop 5581: Loss: 2.28e-02, Avg Return: 0.856, Regret: 0.0149, Entropy: 0.1271 +[2026-03-20T18:43:32.265487Z] Loop 5582: Loss: 1.98e-02, Avg Return: 0.862, Regret: 0.0149, Entropy: 0.1132 +[2026-03-20T18:43:33.119851Z] Loop 5583: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0149, Entropy: 0.1012 +[2026-03-20T18:43:33.973521Z] Loop 5584: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0149, Entropy: 0.1004 +[2026-03-20T18:43:34.827405Z] Loop 5585: Loss: 1.77e-02, Avg Return: 0.863, Regret: 0.0149, Entropy: 0.1011 +[2026-03-20T18:43:35.682452Z] Loop 5586: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0149, Entropy: 0.1078 +[2026-03-20T18:43:36.537675Z] Loop 5587: Loss: 1.94e-02, Avg Return: 0.862, Regret: 0.0149, Entropy: 0.1095 +[2026-03-20T18:43:37.392040Z] Loop 5588: Loss: 2.04e-02, Avg Return: 0.859, Regret: 0.0149, Entropy: 0.1122 +[2026-03-20T18:43:38.246445Z] Loop 5589: Loss: 2.19e-02, Avg Return: 0.859, Regret: 0.0149, Entropy: 0.1131 +[2026-03-20T18:43:39.141818Z] Loop 5590: Loss: 2.27e-02, Avg Return: 0.856, Regret: 0.0077, Entropy: 0.1204 +[2026-03-20T18:43:39.998141Z] Loop 5591: Loss: 2.20e-02, Avg Return: 0.856, Regret: 0.0077, Entropy: 0.1173 +[2026-03-20T18:43:40.851870Z] Loop 5592: Loss: 2.05e-02, Avg Return: 0.855, Regret: 0.0077, Entropy: 0.1118 +[2026-03-20T18:43:41.705311Z] Loop 5593: Loss: 2.14e-02, Avg Return: 0.857, Regret: 0.0077, Entropy: 0.1189 +[2026-03-20T18:43:42.559144Z] Loop 5594: Loss: 2.10e-02, Avg Return: 0.859, Regret: 0.0077, Entropy: 0.1191 +[2026-03-20T18:43:43.412063Z] Loop 5595: Loss: 2.11e-02, Avg Return: 0.861, Regret: 0.0077, Entropy: 0.1180 +[2026-03-20T18:43:44.267246Z] Loop 5596: Loss: 2.18e-02, Avg Return: 0.861, Regret: 0.0077, Entropy: 0.1240 +[2026-03-20T18:43:45.120961Z] Loop 5597: Loss: 2.04e-02, Avg Return: 0.862, Regret: 0.0077, Entropy: 0.1173 +[2026-03-20T18:43:45.974159Z] Loop 5598: Loss: 2.03e-02, Avg Return: 0.862, Regret: 0.0077, Entropy: 0.1160 +[2026-03-20T18:43:46.827602Z] Loop 5599: Loss: 2.20e-02, Avg Return: 0.860, Regret: 0.0077, Entropy: 0.1250 +[2026-03-20T18:43:47.721067Z] Loop 5600: Loss: 2.09e-02, Avg Return: 0.861, Regret: 0.0032, Entropy: 0.1203 +[2026-03-20T18:43:48.574680Z] Loop 5601: Loss: 2.27e-02, Avg Return: 0.860, Regret: 0.0032, Entropy: 0.1206 +[2026-03-20T18:43:49.429631Z] Loop 5602: Loss: 2.18e-02, Avg Return: 0.860, Regret: 0.0032, Entropy: 0.1216 +[2026-03-20T18:43:50.283102Z] Loop 5603: Loss: 2.16e-02, Avg Return: 0.861, Regret: 0.0032, Entropy: 0.1221 +[2026-03-20T18:43:51.136400Z] Loop 5604: Loss: 1.97e-02, Avg Return: 0.860, Regret: 0.0032, Entropy: 0.1146 +[2026-03-20T18:43:51.989941Z] Loop 5605: Loss: 2.15e-02, Avg Return: 0.862, Regret: 0.0032, Entropy: 0.1230 +[2026-03-20T18:43:52.843247Z] Loop 5606: Loss: 2.12e-02, Avg Return: 0.860, Regret: 0.0032, Entropy: 0.1213 +[2026-03-20T18:43:53.696874Z] Loop 5607: Loss: 2.23e-02, Avg Return: 0.860, Regret: 0.0032, Entropy: 0.1259 +[2026-03-20T18:43:54.551581Z] Loop 5608: Loss: 2.19e-02, Avg Return: 0.861, Regret: 0.0032, Entropy: 0.1258 +[2026-03-20T18:43:55.405424Z] Loop 5609: Loss: 2.21e-02, Avg Return: 0.860, Regret: 0.0032, Entropy: 0.1242 +[2026-03-20T18:43:56.299941Z] Loop 5610: Loss: 2.27e-02, Avg Return: 0.860, Regret: 0.0042, Entropy: 0.1283 +[2026-03-20T18:43:57.154007Z] Loop 5611: Loss: 2.28e-02, Avg Return: 0.859, Regret: 0.0042, Entropy: 0.1328 +[2026-03-20T18:43:58.008179Z] Loop 5612: Loss: 2.28e-02, Avg Return: 0.857, Regret: 0.0042, Entropy: 0.1333 +[2026-03-20T18:43:58.863308Z] Loop 5613: Loss: 2.37e-02, Avg Return: 0.858, Regret: 0.0042, Entropy: 0.1361 +[2026-03-20T18:43:59.719098Z] Loop 5614: Loss: 2.19e-02, Avg Return: 0.858, Regret: 0.0042, Entropy: 0.1278 +[2026-03-20T18:44:00.574878Z] Loop 5615: Loss: 2.13e-02, Avg Return: 0.859, Regret: 0.0042, Entropy: 0.1236 +[2026-03-20T18:44:01.430629Z] Loop 5616: Loss: 2.21e-02, Avg Return: 0.860, Regret: 0.0042, Entropy: 0.1199 +[2026-03-20T18:44:02.287058Z] Loop 5617: Loss: 2.08e-02, Avg Return: 0.861, Regret: 0.0042, Entropy: 0.1177 +[2026-03-20T18:44:03.143002Z] Loop 5618: Loss: 2.09e-02, Avg Return: 0.862, Regret: 0.0042, Entropy: 0.1183 +[2026-03-20T18:44:03.998398Z] Loop 5619: Loss: 1.84e-02, Avg Return: 0.862, Regret: 0.0042, Entropy: 0.1048 +[2026-03-20T18:44:04.894052Z] Loop 5620: Loss: 2.01e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.1100 +[2026-03-20T18:44:05.746969Z] Loop 5621: Loss: 1.92e-02, Avg Return: 0.860, Regret: 0.0019, Entropy: 0.1098 +[2026-03-20T18:44:06.599826Z] Loop 5622: Loss: 2.08e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1103 +[2026-03-20T18:44:07.454214Z] Loop 5623: Loss: 2.12e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1180 +[2026-03-20T18:44:08.308627Z] Loop 5624: Loss: 1.93e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1114 +[2026-03-20T18:44:09.163344Z] Loop 5625: Loss: 2.17e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1200 +[2026-03-20T18:44:10.016886Z] Loop 5626: Loss: 2.11e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1122 +[2026-03-20T18:44:10.871045Z] Loop 5627: Loss: 2.09e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1157 +[2026-03-20T18:44:11.725834Z] Loop 5628: Loss: 2.16e-02, Avg Return: 0.860, Regret: 0.0019, Entropy: 0.1208 +[2026-03-20T18:44:12.580323Z] Loop 5629: Loss: 2.10e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1180 +[2026-03-20T18:44:13.474763Z] Loop 5630: Loss: 2.05e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.1153 +[2026-03-20T18:44:14.328682Z] Loop 5631: Loss: 2.11e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.1185 +[2026-03-20T18:44:15.183387Z] Loop 5632: Loss: 1.97e-02, Avg Return: 0.862, Regret: 0.0026, Entropy: 0.1086 +[2026-03-20T18:44:16.038409Z] Loop 5633: Loss: 2.02e-02, Avg Return: 0.862, Regret: 0.0026, Entropy: 0.1106 +[2026-03-20T18:44:16.892494Z] Loop 5634: Loss: 1.85e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.1096 +[2026-03-20T18:44:17.746292Z] Loop 5635: Loss: 1.89e-02, Avg Return: 0.862, Regret: 0.0026, Entropy: 0.1083 +[2026-03-20T18:44:18.600904Z] Loop 5636: Loss: 1.84e-02, Avg Return: 0.862, Regret: 0.0026, Entropy: 0.1083 +[2026-03-20T18:44:19.455799Z] Loop 5637: Loss: 1.97e-02, Avg Return: 0.864, Regret: 0.0026, Entropy: 0.1084 +[2026-03-20T18:44:20.310223Z] Loop 5638: Loss: 1.90e-02, Avg Return: 0.862, Regret: 0.0026, Entropy: 0.1008 +[2026-03-20T18:44:21.163306Z] Loop 5639: Loss: 1.92e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.1067 +[2026-03-20T18:44:22.057656Z] Loop 5640: Loss: 1.93e-02, Avg Return: 0.863, Regret: 0.0017, Entropy: 0.1098 +[2026-03-20T18:44:22.911954Z] Loop 5641: Loss: 1.97e-02, Avg Return: 0.860, Regret: 0.0017, Entropy: 0.1095 +[2026-03-20T18:44:23.765971Z] Loop 5642: Loss: 1.92e-02, Avg Return: 0.863, Regret: 0.0017, Entropy: 0.1073 +[2026-03-20T18:44:24.619876Z] Loop 5643: Loss: 1.96e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.1092 +[2026-03-20T18:44:25.473911Z] Loop 5644: Loss: 2.00e-02, Avg Return: 0.861, Regret: 0.0017, Entropy: 0.1136 +[2026-03-20T18:44:26.328316Z] Loop 5645: Loss: 1.79e-02, Avg Return: 0.860, Regret: 0.0017, Entropy: 0.1049 +[2026-03-20T18:44:27.182977Z] Loop 5646: Loss: 1.83e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.1055 +[2026-03-20T18:44:28.037027Z] Loop 5647: Loss: 1.90e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.1065 +[2026-03-20T18:44:28.891116Z] Loop 5648: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0017, Entropy: 0.1010 +[2026-03-20T18:44:29.744614Z] Loop 5649: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0932 +[2026-03-20T18:44:30.639287Z] Loop 5650: Loss: 1.67e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0909 +[2026-03-20T18:44:31.494944Z] Loop 5651: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0903 +[2026-03-20T18:44:32.349687Z] Loop 5652: Loss: 1.64e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0921 +[2026-03-20T18:44:33.203504Z] Loop 5653: Loss: 1.62e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0922 +[2026-03-20T18:44:34.056938Z] Loop 5654: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0905 +[2026-03-20T18:44:34.913755Z] Loop 5655: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0935 +[2026-03-20T18:44:35.767869Z] Loop 5656: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0931 +[2026-03-20T18:44:36.622306Z] Loop 5657: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0913 +[2026-03-20T18:44:37.476564Z] Loop 5658: Loss: 1.63e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0930 +[2026-03-20T18:44:38.331782Z] Loop 5659: Loss: 1.64e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0916 +[2026-03-20T18:44:39.226616Z] Loop 5660: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0956 +[2026-03-20T18:44:40.081337Z] Loop 5661: Loss: 1.70e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0913 +[2026-03-20T18:44:40.933776Z] Loop 5662: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0971 +[2026-03-20T18:44:41.786791Z] Loop 5663: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0951 +[2026-03-20T18:44:42.641562Z] Loop 5664: Loss: 1.76e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0950 +[2026-03-20T18:44:43.495427Z] Loop 5665: Loss: 1.62e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0939 +[2026-03-20T18:44:44.348975Z] Loop 5666: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0943 +[2026-03-20T18:44:45.203117Z] Loop 5667: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0917 +[2026-03-20T18:44:46.056994Z] Loop 5668: Loss: 1.75e-02, Avg Return: 0.864, Regret: 0.0013, Entropy: 0.0950 +[2026-03-20T18:44:46.910982Z] Loop 5669: Loss: 1.81e-02, Avg Return: 0.864, Regret: 0.0013, Entropy: 0.0972 +[2026-03-20T18:44:47.804710Z] Loop 5670: Loss: 1.72e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0947 +[2026-03-20T18:44:48.659353Z] Loop 5671: Loss: 1.76e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0987 +[2026-03-20T18:44:49.514775Z] Loop 5672: Loss: 1.68e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0946 +[2026-03-20T18:44:50.369354Z] Loop 5673: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0950 +[2026-03-20T18:44:51.224811Z] Loop 5674: Loss: 1.73e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.1004 +[2026-03-20T18:44:52.080722Z] Loop 5675: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0986 +[2026-03-20T18:44:52.934819Z] Loop 5676: Loss: 1.79e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.1001 +[2026-03-20T18:44:53.789158Z] Loop 5677: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0997 +[2026-03-20T18:44:54.644760Z] Loop 5678: Loss: 1.82e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.1021 +[2026-03-20T18:44:55.500077Z] Loop 5679: Loss: 1.75e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0982 +[2026-03-20T18:44:56.393956Z] Loop 5680: Loss: 1.72e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.1004 +[2026-03-20T18:44:57.247252Z] Loop 5681: Loss: 2.02e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.1126 +[2026-03-20T18:44:58.102356Z] Loop 5682: Loss: 1.95e-02, Avg Return: 0.860, Regret: 0.0015, Entropy: 0.1104 +[2026-03-20T18:44:58.958399Z] Loop 5683: Loss: 1.89e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.1114 +[2026-03-20T18:44:59.814188Z] Loop 5684: Loss: 2.02e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.1125 +[2026-03-20T18:45:00.668865Z] Loop 5685: Loss: 1.86e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.1091 +[2026-03-20T18:45:01.524713Z] Loop 5686: Loss: 1.92e-02, Avg Return: 0.860, Regret: 0.0015, Entropy: 0.1135 +[2026-03-20T18:45:02.382406Z] Loop 5687: Loss: 2.00e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.1150 +[2026-03-20T18:45:03.238720Z] Loop 5688: Loss: 1.90e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.1087 +[2026-03-20T18:45:04.093649Z] Loop 5689: Loss: 1.93e-02, Avg Return: 0.860, Regret: 0.0015, Entropy: 0.1106 +[2026-03-20T18:45:04.990110Z] Loop 5690: Loss: 1.93e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.1073 +[2026-03-20T18:45:05.844506Z] Loop 5691: Loss: 1.97e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.1127 +[2026-03-20T18:45:06.699393Z] Loop 5692: Loss: 1.90e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.1133 +[2026-03-20T18:45:07.554212Z] Loop 5693: Loss: 2.03e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.1116 +[2026-03-20T18:45:08.408727Z] Loop 5694: Loss: 1.84e-02, Avg Return: 0.860, Regret: 0.0028, Entropy: 0.1073 +[2026-03-20T18:45:09.263389Z] Loop 5695: Loss: 1.85e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.1042 +[2026-03-20T18:45:10.117897Z] Loop 5696: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0028, Entropy: 0.1002 +[2026-03-20T18:45:10.971943Z] Loop 5697: Loss: 1.93e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.1059 +[2026-03-20T18:45:11.825230Z] Loop 5698: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0028, Entropy: 0.0994 +[2026-03-20T18:45:12.681228Z] Loop 5699: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0028, Entropy: 0.0980 +[2026-03-20T18:45:13.579056Z] Loop 5700: Loss: 1.72e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0977 +[2026-03-20T18:45:14.433796Z] Loop 5701: Loss: 1.81e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.1006 +[2026-03-20T18:45:15.289246Z] Loop 5702: Loss: 1.68e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0954 +[2026-03-20T18:45:16.143851Z] Loop 5703: Loss: 1.73e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0949 +[2026-03-20T18:45:16.997756Z] Loop 5704: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0928 +[2026-03-20T18:45:17.852492Z] Loop 5705: Loss: 1.64e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0911 +[2026-03-20T18:45:18.707028Z] Loop 5706: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0939 +[2026-03-20T18:45:19.561727Z] Loop 5707: Loss: 1.84e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0992 +[2026-03-20T18:45:20.416285Z] Loop 5708: Loss: 1.70e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0983 +[2026-03-20T18:45:21.270583Z] Loop 5709: Loss: 1.87e-02, Avg Return: 0.860, Regret: 0.0010, Entropy: 0.1056 +[2026-03-20T18:45:22.164819Z] Loop 5710: Loss: 2.03e-02, Avg Return: 0.860, Regret: 0.0042, Entropy: 0.1093 +[2026-03-20T18:45:23.018966Z] Loop 5711: Loss: 1.96e-02, Avg Return: 0.858, Regret: 0.0042, Entropy: 0.1101 +[2026-03-20T18:45:23.871575Z] Loop 5712: Loss: 1.98e-02, Avg Return: 0.858, Regret: 0.0042, Entropy: 0.1089 +[2026-03-20T18:45:24.724838Z] Loop 5713: Loss: 2.05e-02, Avg Return: 0.858, Regret: 0.0042, Entropy: 0.1124 +[2026-03-20T18:45:25.579113Z] Loop 5714: Loss: 1.82e-02, Avg Return: 0.861, Regret: 0.0042, Entropy: 0.1054 +[2026-03-20T18:45:26.434062Z] Loop 5715: Loss: 1.89e-02, Avg Return: 0.861, Regret: 0.0042, Entropy: 0.1060 +[2026-03-20T18:45:27.288235Z] Loop 5716: Loss: 1.68e-02, Avg Return: 0.862, Regret: 0.0042, Entropy: 0.0952 +[2026-03-20T18:45:28.142248Z] Loop 5717: Loss: 1.58e-02, Avg Return: 0.861, Regret: 0.0042, Entropy: 0.0888 +[2026-03-20T18:45:28.996407Z] Loop 5718: Loss: 1.74e-02, Avg Return: 0.862, Regret: 0.0042, Entropy: 0.0962 +[2026-03-20T18:45:29.850061Z] Loop 5719: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0042, Entropy: 0.0931 +[2026-03-20T18:45:30.744645Z] Loop 5720: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0927 +[2026-03-20T18:45:31.597513Z] Loop 5721: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0942 +[2026-03-20T18:45:32.450933Z] Loop 5722: Loss: 1.81e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.0986 +[2026-03-20T18:45:33.305635Z] Loop 5723: Loss: 1.69e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.0918 +[2026-03-20T18:45:34.160534Z] Loop 5724: Loss: 1.83e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.0990 +[2026-03-20T18:45:35.014174Z] Loop 5725: Loss: 1.68e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.0956 +[2026-03-20T18:45:35.868838Z] Loop 5726: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0959 +[2026-03-20T18:45:36.723680Z] Loop 5727: Loss: 1.69e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.0931 +[2026-03-20T18:45:37.578585Z] Loop 5728: Loss: 1.59e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.0900 +[2026-03-20T18:45:38.433080Z] Loop 5729: Loss: 1.80e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0962 +[2026-03-20T18:45:39.326430Z] Loop 5730: Loss: 2.02e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.1022 +[2026-03-20T18:45:40.189043Z] Loop 5731: Loss: 1.93e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.1070 +[2026-03-20T18:45:41.043380Z] Loop 5732: Loss: 1.80e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.0973 +[2026-03-20T18:45:41.898530Z] Loop 5733: Loss: 1.73e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.0944 +[2026-03-20T18:45:42.751981Z] Loop 5734: Loss: 1.69e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0975 +[2026-03-20T18:45:43.605974Z] Loop 5735: Loss: 1.84e-02, Avg Return: 0.863, Regret: 0.0022, Entropy: 0.1006 +[2026-03-20T18:45:44.459923Z] Loop 5736: Loss: 1.87e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0993 +[2026-03-20T18:45:45.313656Z] Loop 5737: Loss: 1.74e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.1019 +[2026-03-20T18:45:46.167323Z] Loop 5738: Loss: 1.83e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.1039 +[2026-03-20T18:45:47.021282Z] Loop 5739: Loss: 1.88e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.1061 +[2026-03-20T18:45:47.915379Z] Loop 5740: Loss: 1.86e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.1070 +[2026-03-20T18:45:48.769179Z] Loop 5741: Loss: 1.95e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.1061 +[2026-03-20T18:45:49.622703Z] Loop 5742: Loss: 1.94e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.1078 +[2026-03-20T18:45:50.477739Z] Loop 5743: Loss: 1.82e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.1052 +[2026-03-20T18:45:51.330955Z] Loop 5744: Loss: 1.85e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.1033 +[2026-03-20T18:45:52.183887Z] Loop 5745: Loss: 1.83e-02, Avg Return: 0.862, Regret: 0.0026, Entropy: 0.1074 +[2026-03-20T18:45:53.038087Z] Loop 5746: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0026, Entropy: 0.1028 +[2026-03-20T18:45:53.893357Z] Loop 5747: Loss: 1.84e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.1034 +[2026-03-20T18:45:54.747333Z] Loop 5748: Loss: 1.82e-02, Avg Return: 0.862, Regret: 0.0026, Entropy: 0.1015 +[2026-03-20T18:45:55.600365Z] Loop 5749: Loss: 1.81e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.0994 +[2026-03-20T18:45:56.493957Z] Loop 5750: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0990 +[2026-03-20T18:45:57.347753Z] Loop 5751: Loss: 1.82e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0996 +[2026-03-20T18:45:58.201723Z] Loop 5752: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0962 +[2026-03-20T18:45:59.055055Z] Loop 5753: Loss: 1.98e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.1039 +[2026-03-20T18:45:59.909000Z] Loop 5754: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0966 +[2026-03-20T18:46:00.763536Z] Loop 5755: Loss: 1.75e-02, Avg Return: 0.864, Regret: 0.0016, Entropy: 0.1011 +[2026-03-20T18:46:01.617992Z] Loop 5756: Loss: 1.82e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.1021 +[2026-03-20T18:46:02.470533Z] Loop 5757: Loss: 1.85e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.1028 +[2026-03-20T18:46:03.325036Z] Loop 5758: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.1007 +[2026-03-20T18:46:04.179051Z] Loop 5759: Loss: 2.09e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.1132 +[2026-03-20T18:46:05.075539Z] Loop 5760: Loss: 2.00e-02, Avg Return: 0.860, Regret: 0.0019, Entropy: 0.1141 +[2026-03-20T18:46:05.930070Z] Loop 5761: Loss: 2.30e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.1255 +[2026-03-20T18:46:06.784730Z] Loop 5762: Loss: 2.23e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1285 +[2026-03-20T18:46:07.638623Z] Loop 5763: Loss: 2.27e-02, Avg Return: 0.858, Regret: 0.0019, Entropy: 0.1322 +[2026-03-20T18:46:08.492996Z] Loop 5764: Loss: 2.28e-02, Avg Return: 0.860, Regret: 0.0019, Entropy: 0.1328 +[2026-03-20T18:46:09.348141Z] Loop 5765: Loss: 2.18e-02, Avg Return: 0.859, Regret: 0.0019, Entropy: 0.1225 +[2026-03-20T18:46:10.202946Z] Loop 5766: Loss: 2.12e-02, Avg Return: 0.860, Regret: 0.0019, Entropy: 0.1254 +[2026-03-20T18:46:11.057833Z] Loop 5767: Loss: 2.00e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1135 +[2026-03-20T18:46:11.912029Z] Loop 5768: Loss: 2.02e-02, Avg Return: 0.863, Regret: 0.0019, Entropy: 0.1160 +[2026-03-20T18:46:12.767318Z] Loop 5769: Loss: 1.82e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.1079 +[2026-03-20T18:46:13.663498Z] Loop 5770: Loss: 1.92e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.1089 +[2026-03-20T18:46:14.517775Z] Loop 5771: Loss: 1.89e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.1060 +[2026-03-20T18:46:15.372913Z] Loop 5772: Loss: 1.83e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.1055 +[2026-03-20T18:46:16.228702Z] Loop 5773: Loss: 1.93e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.1084 +[2026-03-20T18:46:17.084098Z] Loop 5774: Loss: 1.89e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.1081 +[2026-03-20T18:46:17.938298Z] Loop 5775: Loss: 2.00e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.1110 +[2026-03-20T18:46:18.792493Z] Loop 5776: Loss: 1.93e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.1095 +[2026-03-20T18:46:19.647397Z] Loop 5777: Loss: 1.90e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.1098 +[2026-03-20T18:46:20.502212Z] Loop 5778: Loss: 1.94e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.1102 +[2026-03-20T18:46:21.356457Z] Loop 5779: Loss: 2.28e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.1193 +[2026-03-20T18:46:22.250698Z] Loop 5780: Loss: 2.09e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.1186 +[2026-03-20T18:46:23.103992Z] Loop 5781: Loss: 2.14e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.1169 +[2026-03-20T18:46:23.958052Z] Loop 5782: Loss: 2.32e-02, Avg Return: 0.858, Regret: 0.0020, Entropy: 0.1257 +[2026-03-20T18:46:24.812473Z] Loop 5783: Loss: 2.51e-02, Avg Return: 0.859, Regret: 0.0020, Entropy: 0.1321 +[2026-03-20T18:46:25.666493Z] Loop 5784: Loss: 2.34e-02, Avg Return: 0.855, Regret: 0.0020, Entropy: 0.1279 +[2026-03-20T18:46:26.520295Z] Loop 5785: Loss: 2.58e-02, Avg Return: 0.855, Regret: 0.0020, Entropy: 0.1297 +[2026-03-20T18:46:27.375377Z] Loop 5786: Loss: 2.53e-02, Avg Return: 0.855, Regret: 0.0020, Entropy: 0.1317 +[2026-03-20T18:46:28.230769Z] Loop 5787: Loss: 2.43e-02, Avg Return: 0.857, Regret: 0.0020, Entropy: 0.1374 +[2026-03-20T18:46:29.086089Z] Loop 5788: Loss: 2.33e-02, Avg Return: 0.860, Regret: 0.0020, Entropy: 0.1271 +[2026-03-20T18:46:29.940279Z] Loop 5789: Loss: 2.34e-02, Avg Return: 0.859, Regret: 0.0020, Entropy: 0.1324 +[2026-03-20T18:46:30.837429Z] Loop 5790: Loss: 2.43e-02, Avg Return: 0.860, Regret: 0.0034, Entropy: 0.1301 +[2026-03-20T18:46:31.691423Z] Loop 5791: Loss: 2.23e-02, Avg Return: 0.861, Regret: 0.0034, Entropy: 0.1250 +[2026-03-20T18:46:32.545722Z] Loop 5792: Loss: 2.22e-02, Avg Return: 0.861, Regret: 0.0034, Entropy: 0.1236 +[2026-03-20T18:46:33.399674Z] Loop 5793: Loss: 2.20e-02, Avg Return: 0.861, Regret: 0.0034, Entropy: 0.1222 +[2026-03-20T18:46:34.254230Z] Loop 5794: Loss: 2.11e-02, Avg Return: 0.862, Regret: 0.0034, Entropy: 0.1211 +[2026-03-20T18:46:35.108000Z] Loop 5795: Loss: 2.12e-02, Avg Return: 0.862, Regret: 0.0034, Entropy: 0.1165 +[2026-03-20T18:46:35.962524Z] Loop 5796: Loss: 1.97e-02, Avg Return: 0.863, Regret: 0.0034, Entropy: 0.1117 +[2026-03-20T18:46:36.818127Z] Loop 5797: Loss: 1.92e-02, Avg Return: 0.863, Regret: 0.0034, Entropy: 0.1087 +[2026-03-20T18:46:37.672155Z] Loop 5798: Loss: 1.84e-02, Avg Return: 0.862, Regret: 0.0034, Entropy: 0.1032 +[2026-03-20T18:46:38.525732Z] Loop 5799: Loss: 2.01e-02, Avg Return: 0.862, Regret: 0.0034, Entropy: 0.1112 +[2026-03-20T18:46:39.420161Z] Loop 5800: Loss: 1.94e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.1062 +[2026-03-20T18:46:40.275092Z] Loop 5801: Loss: 1.93e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.1054 +[2026-03-20T18:46:41.129239Z] Loop 5802: Loss: 1.88e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.1019 +[2026-03-20T18:46:41.981453Z] Loop 5803: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0996 +[2026-03-20T18:46:42.834135Z] Loop 5804: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0979 +[2026-03-20T18:46:43.689152Z] Loop 5805: Loss: 1.90e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.1058 +[2026-03-20T18:46:44.542994Z] Loop 5806: Loss: 1.80e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.1019 +[2026-03-20T18:46:45.396118Z] Loop 5807: Loss: 1.89e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.1012 +[2026-03-20T18:46:46.249543Z] Loop 5808: Loss: 1.63e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0897 +[2026-03-20T18:46:47.104063Z] Loop 5809: Loss: 1.72e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0963 +[2026-03-20T18:46:47.998986Z] Loop 5810: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0961 +[2026-03-20T18:46:48.853541Z] Loop 5811: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0917 +[2026-03-20T18:46:49.707555Z] Loop 5812: Loss: 1.71e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0961 +[2026-03-20T18:46:50.562505Z] Loop 5813: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0935 +[2026-03-20T18:46:51.417305Z] Loop 5814: Loss: 1.77e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.1007 +[2026-03-20T18:46:52.271451Z] Loop 5815: Loss: 1.92e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.1049 +[2026-03-20T18:46:53.125521Z] Loop 5816: Loss: 1.83e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.1029 +[2026-03-20T18:46:53.980555Z] Loop 5817: Loss: 1.98e-02, Avg Return: 0.858, Regret: 0.0010, Entropy: 0.1103 +[2026-03-20T18:46:54.835631Z] Loop 5818: Loss: 2.13e-02, Avg Return: 0.858, Regret: 0.0010, Entropy: 0.1135 +[2026-03-20T18:46:55.691028Z] Loop 5819: Loss: 2.10e-02, Avg Return: 0.856, Regret: 0.0010, Entropy: 0.1125 +[2026-03-20T18:46:56.586555Z] Loop 5820: Loss: 2.18e-02, Avg Return: 0.856, Regret: 0.0062, Entropy: 0.1134 +[2026-03-20T18:46:57.440017Z] Loop 5821: Loss: 1.95e-02, Avg Return: 0.859, Regret: 0.0062, Entropy: 0.1075 +[2026-03-20T18:46:58.292926Z] Loop 5822: Loss: 2.04e-02, Avg Return: 0.859, Regret: 0.0062, Entropy: 0.1087 +[2026-03-20T18:46:59.147374Z] Loop 5823: Loss: 1.94e-02, Avg Return: 0.861, Regret: 0.0062, Entropy: 0.1032 +[2026-03-20T18:47:00.001737Z] Loop 5824: Loss: 1.73e-02, Avg Return: 0.861, Regret: 0.0062, Entropy: 0.0977 +[2026-03-20T18:47:00.855544Z] Loop 5825: Loss: 1.72e-02, Avg Return: 0.860, Regret: 0.0062, Entropy: 0.0953 +[2026-03-20T18:47:01.709491Z] Loop 5826: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0062, Entropy: 0.0975 +[2026-03-20T18:47:02.564113Z] Loop 5827: Loss: 1.74e-02, Avg Return: 0.864, Regret: 0.0062, Entropy: 0.0945 +[2026-03-20T18:47:03.418761Z] Loop 5828: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0062, Entropy: 0.0905 +[2026-03-20T18:47:04.273106Z] Loop 5829: Loss: 1.81e-02, Avg Return: 0.863, Regret: 0.0062, Entropy: 0.0978 +[2026-03-20T18:47:05.166307Z] Loop 5830: Loss: 1.74e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0963 +[2026-03-20T18:47:06.019916Z] Loop 5831: Loss: 1.74e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0953 +[2026-03-20T18:47:06.874648Z] Loop 5832: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0963 +[2026-03-20T18:47:07.730777Z] Loop 5833: Loss: 1.67e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0969 +[2026-03-20T18:47:08.585778Z] Loop 5834: Loss: 1.89e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.1015 +[2026-03-20T18:47:09.440781Z] Loop 5835: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0997 +[2026-03-20T18:47:10.296610Z] Loop 5836: Loss: 1.85e-02, Avg Return: 0.860, Regret: 0.0010, Entropy: 0.1041 +[2026-03-20T18:47:11.151821Z] Loop 5837: Loss: 1.79e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.1003 +[2026-03-20T18:47:12.008074Z] Loop 5838: Loss: 1.79e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0998 +[2026-03-20T18:47:12.863132Z] Loop 5839: Loss: 1.84e-02, Avg Return: 0.860, Regret: 0.0010, Entropy: 0.1058 +[2026-03-20T18:47:13.758204Z] Loop 5840: Loss: 1.81e-02, Avg Return: 0.860, Regret: 0.0020, Entropy: 0.1003 +[2026-03-20T18:47:14.615455Z] Loop 5841: Loss: 1.84e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.1043 +[2026-03-20T18:47:15.472187Z] Loop 5842: Loss: 1.69e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.0960 +[2026-03-20T18:47:16.327386Z] Loop 5843: Loss: 1.73e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.0917 +[2026-03-20T18:47:17.183626Z] Loop 5844: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0923 +[2026-03-20T18:47:18.039515Z] Loop 5845: Loss: 1.68e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0934 +[2026-03-20T18:47:18.895555Z] Loop 5846: Loss: 1.88e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0973 +[2026-03-20T18:47:19.751174Z] Loop 5847: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.0978 +[2026-03-20T18:47:20.605890Z] Loop 5848: Loss: 1.72e-02, Avg Return: 0.860, Regret: 0.0020, Entropy: 0.0952 +[2026-03-20T18:47:21.460748Z] Loop 5849: Loss: 1.72e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.0953 +[2026-03-20T18:47:22.356888Z] Loop 5850: Loss: 1.79e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.0970 +[2026-03-20T18:47:23.212102Z] Loop 5851: Loss: 1.67e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.0933 +[2026-03-20T18:47:24.069244Z] Loop 5852: Loss: 1.66e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.0942 +[2026-03-20T18:47:24.925769Z] Loop 5853: Loss: 1.80e-02, Avg Return: 0.859, Regret: 0.0026, Entropy: 0.0989 +[2026-03-20T18:47:25.782301Z] Loop 5854: Loss: 1.80e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.1025 +[2026-03-20T18:47:26.639477Z] Loop 5855: Loss: 1.59e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.0883 +[2026-03-20T18:47:27.497032Z] Loop 5856: Loss: 1.70e-02, Avg Return: 0.862, Regret: 0.0026, Entropy: 0.0970 +[2026-03-20T18:47:28.355461Z] Loop 5857: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0026, Entropy: 0.0938 +[2026-03-20T18:47:29.211270Z] Loop 5858: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0026, Entropy: 0.0911 +[2026-03-20T18:47:30.068008Z] Loop 5859: Loss: 1.57e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.0900 +[2026-03-20T18:47:30.966500Z] Loop 5860: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0911 +[2026-03-20T18:47:31.823796Z] Loop 5861: Loss: 1.60e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0881 +[2026-03-20T18:47:32.679415Z] Loop 5862: Loss: 1.70e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0931 +[2026-03-20T18:47:33.535167Z] Loop 5863: Loss: 1.63e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0929 +[2026-03-20T18:47:34.391363Z] Loop 5864: Loss: 1.63e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0908 +[2026-03-20T18:47:35.246515Z] Loop 5865: Loss: 1.68e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0885 +[2026-03-20T18:47:36.102479Z] Loop 5866: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0019, Entropy: 0.0900 +[2026-03-20T18:47:36.957731Z] Loop 5867: Loss: 1.71e-02, Avg Return: 0.864, Regret: 0.0019, Entropy: 0.0957 +[2026-03-20T18:47:37.813134Z] Loop 5868: Loss: 1.54e-02, Avg Return: 0.864, Regret: 0.0019, Entropy: 0.0876 +[2026-03-20T18:47:38.668487Z] Loop 5869: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0019, Entropy: 0.0864 +[2026-03-20T18:47:39.565055Z] Loop 5870: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0865 +[2026-03-20T18:47:40.420923Z] Loop 5871: Loss: 1.76e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0965 +[2026-03-20T18:47:41.276897Z] Loop 5872: Loss: 1.63e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0875 +[2026-03-20T18:47:42.132666Z] Loop 5873: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0880 +[2026-03-20T18:47:42.988897Z] Loop 5874: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0917 +[2026-03-20T18:47:43.844848Z] Loop 5875: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0914 +[2026-03-20T18:47:44.700422Z] Loop 5876: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0901 +[2026-03-20T18:47:45.556272Z] Loop 5877: Loss: 1.72e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0939 +[2026-03-20T18:47:46.412185Z] Loop 5878: Loss: 1.75e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0935 +[2026-03-20T18:47:47.268678Z] Loop 5879: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0952 +[2026-03-20T18:47:48.164871Z] Loop 5880: Loss: 1.73e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0945 +[2026-03-20T18:47:49.020461Z] Loop 5881: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0937 +[2026-03-20T18:47:49.875203Z] Loop 5882: Loss: 1.70e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0950 +[2026-03-20T18:47:50.731013Z] Loop 5883: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0930 +[2026-03-20T18:47:51.585582Z] Loop 5884: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0955 +[2026-03-20T18:47:52.440203Z] Loop 5885: Loss: 1.64e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.0918 +[2026-03-20T18:47:53.296161Z] Loop 5886: Loss: 1.70e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0955 +[2026-03-20T18:47:54.151804Z] Loop 5887: Loss: 1.73e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0948 +[2026-03-20T18:47:55.007224Z] Loop 5888: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0923 +[2026-03-20T18:47:55.862403Z] Loop 5889: Loss: 1.78e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0940 +[2026-03-20T18:47:56.757333Z] Loop 5890: Loss: 1.73e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0943 +[2026-03-20T18:47:57.613568Z] Loop 5891: Loss: 1.78e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0971 +[2026-03-20T18:47:58.469121Z] Loop 5892: Loss: 1.79e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.1001 +[2026-03-20T18:47:59.324392Z] Loop 5893: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.1023 +[2026-03-20T18:48:00.178408Z] Loop 5894: Loss: 1.72e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0975 +[2026-03-20T18:48:01.033960Z] Loop 5895: Loss: 1.89e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.1050 +[2026-03-20T18:48:01.889681Z] Loop 5896: Loss: 1.78e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.1021 +[2026-03-20T18:48:02.744735Z] Loop 5897: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0988 +[2026-03-20T18:48:03.599252Z] Loop 5898: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0955 +[2026-03-20T18:48:04.454341Z] Loop 5899: Loss: 1.79e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.1001 +[2026-03-20T18:48:05.351086Z] Loop 5900: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0999 +[2026-03-20T18:48:06.205733Z] Loop 5901: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.1004 +[2026-03-20T18:48:07.061575Z] Loop 5902: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0955 +[2026-03-20T18:48:07.917308Z] Loop 5903: Loss: 1.67e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0975 +[2026-03-20T18:48:08.772481Z] Loop 5904: Loss: 1.74e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0989 +[2026-03-20T18:48:09.627823Z] Loop 5905: Loss: 1.79e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0996 +[2026-03-20T18:48:10.483069Z] Loop 5906: Loss: 1.74e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.1009 +[2026-03-20T18:48:11.339261Z] Loop 5907: Loss: 1.97e-02, Avg Return: 0.860, Regret: 0.0012, Entropy: 0.1070 +[2026-03-20T18:48:12.194423Z] Loop 5908: Loss: 1.95e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.1074 +[2026-03-20T18:48:13.051504Z] Loop 5909: Loss: 1.82e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.1025 +[2026-03-20T18:48:13.948811Z] Loop 5910: Loss: 1.90e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.1051 +[2026-03-20T18:48:14.806173Z] Loop 5911: Loss: 1.83e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.0993 +[2026-03-20T18:48:15.661220Z] Loop 5912: Loss: 1.85e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.1015 +[2026-03-20T18:48:16.516045Z] Loop 5913: Loss: 1.79e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.0997 +[2026-03-20T18:48:17.372216Z] Loop 5914: Loss: 1.81e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.0999 +[2026-03-20T18:48:18.229174Z] Loop 5915: Loss: 1.77e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.1004 +[2026-03-20T18:48:19.084055Z] Loop 5916: Loss: 1.94e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.1055 +[2026-03-20T18:48:19.938879Z] Loop 5917: Loss: 1.78e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.1033 +[2026-03-20T18:48:20.794737Z] Loop 5918: Loss: 1.98e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.1074 +[2026-03-20T18:48:21.649114Z] Loop 5919: Loss: 1.83e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.1019 +[2026-03-20T18:48:22.546002Z] Loop 5920: Loss: 1.88e-02, Avg Return: 0.860, Regret: 0.0027, Entropy: 0.1061 +[2026-03-20T18:48:23.400040Z] Loop 5921: Loss: 1.84e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.1063 +[2026-03-20T18:48:24.255827Z] Loop 5922: Loss: 1.81e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.1035 +[2026-03-20T18:48:25.112099Z] Loop 5923: Loss: 1.90e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.1044 +[2026-03-20T18:48:25.968030Z] Loop 5924: Loss: 1.70e-02, Avg Return: 0.860, Regret: 0.0027, Entropy: 0.0961 +[2026-03-20T18:48:26.825143Z] Loop 5925: Loss: 1.87e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.1057 +[2026-03-20T18:48:27.681416Z] Loop 5926: Loss: 1.98e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.1120 +[2026-03-20T18:48:28.537020Z] Loop 5927: Loss: 1.86e-02, Avg Return: 0.859, Regret: 0.0027, Entropy: 0.1066 +[2026-03-20T18:48:29.393679Z] Loop 5928: Loss: 1.85e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.1064 +[2026-03-20T18:48:30.250077Z] Loop 5929: Loss: 1.84e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.1048 +[2026-03-20T18:48:31.151883Z] Loop 5930: Loss: 1.88e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.1047 +[2026-03-20T18:48:32.006715Z] Loop 5931: Loss: 1.86e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.1046 +[2026-03-20T18:48:32.863136Z] Loop 5932: Loss: 1.94e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.1112 +[2026-03-20T18:48:33.719227Z] Loop 5933: Loss: 1.90e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.1081 +[2026-03-20T18:48:34.575474Z] Loop 5934: Loss: 1.74e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.1048 +[2026-03-20T18:48:35.429695Z] Loop 5935: Loss: 1.91e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.1109 +[2026-03-20T18:48:36.283842Z] Loop 5936: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.1054 +[2026-03-20T18:48:37.139090Z] Loop 5937: Loss: 1.87e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.1071 +[2026-03-20T18:48:37.994694Z] Loop 5938: Loss: 1.82e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.1042 +[2026-03-20T18:48:38.850092Z] Loop 5939: Loss: 1.81e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.1047 +[2026-03-20T18:48:39.747598Z] Loop 5940: Loss: 1.93e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.1104 +[2026-03-20T18:48:40.603827Z] Loop 5941: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.1015 +[2026-03-20T18:48:41.459234Z] Loop 5942: Loss: 1.87e-02, Avg Return: 0.861, Regret: 0.0017, Entropy: 0.1057 +[2026-03-20T18:48:42.315975Z] Loop 5943: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.1012 +[2026-03-20T18:48:43.171699Z] Loop 5944: Loss: 1.82e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.1071 +[2026-03-20T18:48:44.027523Z] Loop 5945: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.1017 +[2026-03-20T18:48:44.883171Z] Loop 5946: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.1041 +[2026-03-20T18:48:45.738747Z] Loop 5947: Loss: 1.95e-02, Avg Return: 0.861, Regret: 0.0017, Entropy: 0.1065 +[2026-03-20T18:48:46.593675Z] Loop 5948: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.1033 +[2026-03-20T18:48:47.449611Z] Loop 5949: Loss: 1.96e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.1056 +[2026-03-20T18:48:48.344998Z] Loop 5950: Loss: 1.93e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.1051 +[2026-03-20T18:48:49.200547Z] Loop 5951: Loss: 1.81e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.1018 +[2026-03-20T18:48:50.057483Z] Loop 5952: Loss: 1.87e-02, Avg Return: 0.860, Regret: 0.0024, Entropy: 0.1074 +[2026-03-20T18:48:50.913316Z] Loop 5953: Loss: 1.94e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.1057 +[2026-03-20T18:48:51.769720Z] Loop 5954: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.1022 +[2026-03-20T18:48:52.626324Z] Loop 5955: Loss: 1.73e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.1008 +[2026-03-20T18:48:53.483185Z] Loop 5956: Loss: 1.76e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.1006 +[2026-03-20T18:48:54.341336Z] Loop 5957: Loss: 1.80e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.1034 +[2026-03-20T18:48:55.197064Z] Loop 5958: Loss: 2.02e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.1121 +[2026-03-20T18:48:56.054114Z] Loop 5959: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.1025 +[2026-03-20T18:48:56.952660Z] Loop 5960: Loss: 1.71e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.1011 +[2026-03-20T18:48:57.807938Z] Loop 5961: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.1044 +[2026-03-20T18:48:58.663188Z] Loop 5962: Loss: 1.85e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.1036 +[2026-03-20T18:48:59.518022Z] Loop 5963: Loss: 1.68e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.1050 +[2026-03-20T18:49:00.375212Z] Loop 5964: Loss: 1.71e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0999 +[2026-03-20T18:49:01.231235Z] Loop 5965: Loss: 1.79e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.1042 +[2026-03-20T18:49:02.086666Z] Loop 5966: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.1043 +[2026-03-20T18:49:02.940911Z] Loop 5967: Loss: 1.85e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.1055 +[2026-03-20T18:49:03.795736Z] Loop 5968: Loss: 1.79e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.1039 +[2026-03-20T18:49:04.651261Z] Loop 5969: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.1003 +[2026-03-20T18:49:05.547075Z] Loop 5970: Loss: 1.68e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.1019 +[2026-03-20T18:49:06.402634Z] Loop 5971: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.1034 +[2026-03-20T18:49:07.258961Z] Loop 5972: Loss: 1.76e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.1021 +[2026-03-20T18:49:08.115313Z] Loop 5973: Loss: 1.72e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0993 +[2026-03-20T18:49:08.970258Z] Loop 5974: Loss: 1.79e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.1054 +[2026-03-20T18:49:09.826285Z] Loop 5975: Loss: 1.82e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.1038 +[2026-03-20T18:49:10.682017Z] Loop 5976: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.1081 +[2026-03-20T18:49:11.536501Z] Loop 5977: Loss: 1.83e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.1032 +[2026-03-20T18:49:12.391564Z] Loop 5978: Loss: 1.78e-02, Avg Return: 0.860, Regret: 0.0015, Entropy: 0.1068 +[2026-03-20T18:49:13.246756Z] Loop 5979: Loss: 1.93e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.1111 +[2026-03-20T18:49:14.143250Z] Loop 5980: Loss: 2.16e-02, Avg Return: 0.858, Regret: 0.0046, Entropy: 0.1188 +[2026-03-20T18:49:14.998291Z] Loop 5981: Loss: 2.22e-02, Avg Return: 0.858, Regret: 0.0046, Entropy: 0.1237 +[2026-03-20T18:49:15.853039Z] Loop 5982: Loss: 2.37e-02, Avg Return: 0.855, Regret: 0.0046, Entropy: 0.1265 +[2026-03-20T18:49:16.708934Z] Loop 5983: Loss: 2.15e-02, Avg Return: 0.856, Regret: 0.0046, Entropy: 0.1198 +[2026-03-20T18:49:17.566398Z] Loop 5984: Loss: 2.22e-02, Avg Return: 0.857, Regret: 0.0046, Entropy: 0.1244 +[2026-03-20T18:49:18.421762Z] Loop 5985: Loss: 1.92e-02, Avg Return: 0.859, Regret: 0.0046, Entropy: 0.1096 +[2026-03-20T18:49:19.276826Z] Loop 5986: Loss: 2.00e-02, Avg Return: 0.860, Regret: 0.0046, Entropy: 0.1117 +[2026-03-20T18:49:20.132543Z] Loop 5987: Loss: 1.89e-02, Avg Return: 0.860, Regret: 0.0046, Entropy: 0.1072 +[2026-03-20T18:49:20.989368Z] Loop 5988: Loss: 1.85e-02, Avg Return: 0.860, Regret: 0.0046, Entropy: 0.1048 +[2026-03-20T18:49:21.844614Z] Loop 5989: Loss: 1.87e-02, Avg Return: 0.860, Regret: 0.0046, Entropy: 0.1067 +[2026-03-20T18:49:22.738740Z] Loop 5990: Loss: 1.88e-02, Avg Return: 0.860, Regret: 0.0036, Entropy: 0.0996 +[2026-03-20T18:49:23.593239Z] Loop 5991: Loss: 1.81e-02, Avg Return: 0.860, Regret: 0.0036, Entropy: 0.0983 +[2026-03-20T18:49:24.448623Z] Loop 5992: Loss: 1.89e-02, Avg Return: 0.861, Regret: 0.0036, Entropy: 0.1083 +[2026-03-20T18:49:25.303354Z] Loop 5993: Loss: 1.87e-02, Avg Return: 0.860, Regret: 0.0036, Entropy: 0.1038 +[2026-03-20T18:49:26.157386Z] Loop 5994: Loss: 1.82e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.1021 +[2026-03-20T18:49:27.012472Z] Loop 5995: Loss: 1.70e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.0934 +[2026-03-20T18:49:27.868641Z] Loop 5996: Loss: 1.66e-02, Avg Return: 0.861, Regret: 0.0036, Entropy: 0.0953 +[2026-03-20T18:49:28.724212Z] Loop 5997: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.0972 +[2026-03-20T18:49:29.579181Z] Loop 5998: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.0937 +[2026-03-20T18:49:30.433477Z] Loop 5999: Loss: 1.79e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.0986 +[2026-03-20T18:49:31.328114Z] Loop 6000: Loss: 1.73e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0971 +[2026-03-20T18:49:32.184699Z] Loop 6001: Loss: 1.80e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.1057 +[2026-03-20T18:49:33.040372Z] Loop 6002: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.1030 +[2026-03-20T18:49:33.897311Z] Loop 6003: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0958 +[2026-03-20T18:49:34.754696Z] Loop 6004: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.1063 +[2026-03-20T18:49:35.610589Z] Loop 6005: Loss: 1.79e-02, Avg Return: 0.860, Regret: 0.0014, Entropy: 0.0999 +[2026-03-20T18:49:36.466628Z] Loop 6006: Loss: 1.88e-02, Avg Return: 0.860, Regret: 0.0014, Entropy: 0.1021 +[2026-03-20T18:49:37.322505Z] Loop 6007: Loss: 1.93e-02, Avg Return: 0.859, Regret: 0.0014, Entropy: 0.1028 +[2026-03-20T18:49:38.178291Z] Loop 6008: Loss: 2.04e-02, Avg Return: 0.859, Regret: 0.0014, Entropy: 0.1093 +[2026-03-20T18:49:39.033873Z] Loop 6009: Loss: 1.71e-02, Avg Return: 0.860, Regret: 0.0014, Entropy: 0.1005 +[2026-03-20T18:49:39.931572Z] Loop 6010: Loss: 1.80e-02, Avg Return: 0.860, Regret: 0.0035, Entropy: 0.1011 +[2026-03-20T18:49:40.787800Z] Loop 6011: Loss: 1.76e-02, Avg Return: 0.859, Regret: 0.0035, Entropy: 0.1002 +[2026-03-20T18:49:41.643894Z] Loop 6012: Loss: 1.67e-02, Avg Return: 0.861, Regret: 0.0035, Entropy: 0.0957 +[2026-03-20T18:49:42.500513Z] Loop 6013: Loss: 1.71e-02, Avg Return: 0.859, Regret: 0.0035, Entropy: 0.0988 +[2026-03-20T18:49:43.356929Z] Loop 6014: Loss: 1.69e-02, Avg Return: 0.860, Regret: 0.0035, Entropy: 0.0981 +[2026-03-20T18:49:44.212677Z] Loop 6015: Loss: 1.81e-02, Avg Return: 0.860, Regret: 0.0035, Entropy: 0.0980 +[2026-03-20T18:49:45.069201Z] Loop 6016: Loss: 1.99e-02, Avg Return: 0.859, Regret: 0.0035, Entropy: 0.1052 +[2026-03-20T18:49:45.925076Z] Loop 6017: Loss: 1.89e-02, Avg Return: 0.861, Regret: 0.0035, Entropy: 0.1015 +[2026-03-20T18:49:46.781179Z] Loop 6018: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0035, Entropy: 0.0970 +[2026-03-20T18:49:47.637655Z] Loop 6019: Loss: 1.84e-02, Avg Return: 0.862, Regret: 0.0035, Entropy: 0.0949 +[2026-03-20T18:49:48.535549Z] Loop 6020: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0921 +[2026-03-20T18:49:49.390991Z] Loop 6021: Loss: 1.71e-02, Avg Return: 0.864, Regret: 0.0013, Entropy: 0.0917 +[2026-03-20T18:49:50.245707Z] Loop 6022: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0903 +[2026-03-20T18:49:51.100295Z] Loop 6023: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0899 +[2026-03-20T18:49:51.955668Z] Loop 6024: Loss: 1.85e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0960 +[2026-03-20T18:49:52.810691Z] Loop 6025: Loss: 1.57e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0897 +[2026-03-20T18:49:53.665107Z] Loop 6026: Loss: 1.77e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0976 +[2026-03-20T18:49:54.519009Z] Loop 6027: Loss: 1.86e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.1009 +[2026-03-20T18:49:55.374127Z] Loop 6028: Loss: 1.79e-02, Avg Return: 0.860, Regret: 0.0013, Entropy: 0.1020 +[2026-03-20T18:49:56.229405Z] Loop 6029: Loss: 1.84e-02, Avg Return: 0.859, Regret: 0.0013, Entropy: 0.1028 +[2026-03-20T18:49:57.123523Z] Loop 6030: Loss: 1.81e-02, Avg Return: 0.859, Regret: 0.0036, Entropy: 0.0995 +[2026-03-20T18:49:57.977604Z] Loop 6031: Loss: 1.83e-02, Avg Return: 0.861, Regret: 0.0036, Entropy: 0.0996 +[2026-03-20T18:49:58.832945Z] Loop 6032: Loss: 1.76e-02, Avg Return: 0.859, Regret: 0.0036, Entropy: 0.0966 +[2026-03-20T18:49:59.688221Z] Loop 6033: Loss: 1.69e-02, Avg Return: 0.860, Regret: 0.0036, Entropy: 0.0977 +[2026-03-20T18:50:00.542918Z] Loop 6034: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.0956 +[2026-03-20T18:50:01.399538Z] Loop 6035: Loss: 1.79e-02, Avg Return: 0.860, Regret: 0.0036, Entropy: 0.0978 +[2026-03-20T18:50:02.256728Z] Loop 6036: Loss: 1.84e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.1004 +[2026-03-20T18:50:03.113993Z] Loop 6037: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.0975 +[2026-03-20T18:50:03.974695Z] Loop 6038: Loss: 1.81e-02, Avg Return: 0.859, Regret: 0.0036, Entropy: 0.0974 +[2026-03-20T18:50:04.832650Z] Loop 6039: Loss: 1.89e-02, Avg Return: 0.859, Regret: 0.0036, Entropy: 0.1010 +[2026-03-20T18:50:05.728437Z] Loop 6040: Loss: 1.98e-02, Avg Return: 0.861, Regret: 0.0043, Entropy: 0.1044 +[2026-03-20T18:50:06.583341Z] Loop 6041: Loss: 1.92e-02, Avg Return: 0.858, Regret: 0.0043, Entropy: 0.1033 +[2026-03-20T18:50:07.439137Z] Loop 6042: Loss: 2.03e-02, Avg Return: 0.858, Regret: 0.0043, Entropy: 0.1085 +[2026-03-20T18:50:08.293907Z] Loop 6043: Loss: 1.94e-02, Avg Return: 0.860, Regret: 0.0043, Entropy: 0.1011 +[2026-03-20T18:50:09.149090Z] Loop 6044: Loss: 1.91e-02, Avg Return: 0.861, Regret: 0.0043, Entropy: 0.1032 +[2026-03-20T18:50:10.003914Z] Loop 6045: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0043, Entropy: 0.0971 +[2026-03-20T18:50:10.858868Z] Loop 6046: Loss: 1.61e-02, Avg Return: 0.861, Regret: 0.0043, Entropy: 0.0903 +[2026-03-20T18:50:11.714812Z] Loop 6047: Loss: 1.69e-02, Avg Return: 0.861, Regret: 0.0043, Entropy: 0.0914 +[2026-03-20T18:50:12.570399Z] Loop 6048: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0043, Entropy: 0.0957 +[2026-03-20T18:50:13.424992Z] Loop 6049: Loss: 1.76e-02, Avg Return: 0.861, Regret: 0.0043, Entropy: 0.0940 +[2026-03-20T18:50:14.320656Z] Loop 6050: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0880 +[2026-03-20T18:50:15.175844Z] Loop 6051: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0883 +[2026-03-20T18:50:16.032343Z] Loop 6052: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0925 +[2026-03-20T18:50:16.887949Z] Loop 6053: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0899 +[2026-03-20T18:50:17.743128Z] Loop 6054: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0920 +[2026-03-20T18:50:18.598782Z] Loop 6055: Loss: 1.71e-02, Avg Return: 0.864, Regret: 0.0013, Entropy: 0.0936 +[2026-03-20T18:50:19.454761Z] Loop 6056: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0903 +[2026-03-20T18:50:20.310701Z] Loop 6057: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0901 +[2026-03-20T18:50:21.166066Z] Loop 6058: Loss: 1.64e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0906 +[2026-03-20T18:50:22.021256Z] Loop 6059: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0969 +[2026-03-20T18:50:22.917574Z] Loop 6060: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0896 +[2026-03-20T18:50:23.773577Z] Loop 6061: Loss: 1.77e-02, Avg Return: 0.863, Regret: 0.0019, Entropy: 0.0981 +[2026-03-20T18:50:24.629159Z] Loop 6062: Loss: 1.73e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0967 +[2026-03-20T18:50:25.485305Z] Loop 6063: Loss: 1.62e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0913 +[2026-03-20T18:50:26.344760Z] Loop 6064: Loss: 1.67e-02, Avg Return: 0.860, Regret: 0.0019, Entropy: 0.0964 +[2026-03-20T18:50:27.200188Z] Loop 6065: Loss: 1.83e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0992 +[2026-03-20T18:50:28.055308Z] Loop 6066: Loss: 1.74e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0962 +[2026-03-20T18:50:28.912450Z] Loop 6067: Loss: 1.67e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0933 +[2026-03-20T18:50:29.768187Z] Loop 6068: Loss: 1.60e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0925 +[2026-03-20T18:50:30.623307Z] Loop 6069: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0884 +[2026-03-20T18:50:31.519313Z] Loop 6070: Loss: 1.72e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0931 +[2026-03-20T18:50:32.374374Z] Loop 6071: Loss: 1.75e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0923 +[2026-03-20T18:50:33.229005Z] Loop 6072: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0899 +[2026-03-20T18:50:34.084110Z] Loop 6073: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0899 +[2026-03-20T18:50:34.939960Z] Loop 6074: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0892 +[2026-03-20T18:50:35.795504Z] Loop 6075: Loss: 1.63e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0946 +[2026-03-20T18:50:36.649589Z] Loop 6076: Loss: 1.76e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0942 +[2026-03-20T18:50:37.504534Z] Loop 6077: Loss: 1.79e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0922 +[2026-03-20T18:50:38.359757Z] Loop 6078: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0950 +[2026-03-20T18:50:39.215864Z] Loop 6079: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0909 +[2026-03-20T18:50:40.113104Z] Loop 6080: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0917 +[2026-03-20T18:50:40.967952Z] Loop 6081: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0926 +[2026-03-20T18:50:41.823714Z] Loop 6082: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0893 +[2026-03-20T18:50:42.680931Z] Loop 6083: Loss: 1.70e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0946 +[2026-03-20T18:50:43.537026Z] Loop 6084: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0948 +[2026-03-20T18:50:44.392748Z] Loop 6085: Loss: 1.61e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0909 +[2026-03-20T18:50:45.248900Z] Loop 6086: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0982 +[2026-03-20T18:50:46.104435Z] Loop 6087: Loss: 1.63e-02, Avg Return: 0.860, Regret: 0.0010, Entropy: 0.0926 +[2026-03-20T18:50:46.960186Z] Loop 6088: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0973 +[2026-03-20T18:50:47.815519Z] Loop 6089: Loss: 1.62e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0942 +[2026-03-20T18:50:48.710278Z] Loop 6090: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0881 +[2026-03-20T18:50:49.565537Z] Loop 6091: Loss: 1.77e-02, Avg Return: 0.860, Regret: 0.0015, Entropy: 0.0980 +[2026-03-20T18:50:50.422872Z] Loop 6092: Loss: 1.75e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0986 +[2026-03-20T18:50:51.280307Z] Loop 6093: Loss: 1.67e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0947 +[2026-03-20T18:50:52.138305Z] Loop 6094: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0944 +[2026-03-20T18:50:52.994360Z] Loop 6095: Loss: 1.64e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0934 +[2026-03-20T18:50:53.850990Z] Loop 6096: Loss: 1.75e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0952 +[2026-03-20T18:50:54.707203Z] Loop 6097: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0960 +[2026-03-20T18:50:55.563843Z] Loop 6098: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0906 +[2026-03-20T18:50:56.420467Z] Loop 6099: Loss: 1.71e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.0959 +[2026-03-20T18:50:57.316261Z] Loop 6100: Loss: 1.65e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.0912 +[2026-03-20T18:50:58.172626Z] Loop 6101: Loss: 1.72e-02, Avg Return: 0.859, Regret: 0.0026, Entropy: 0.0926 +[2026-03-20T18:50:59.029363Z] Loop 6102: Loss: 1.74e-02, Avg Return: 0.862, Regret: 0.0026, Entropy: 0.0975 +[2026-03-20T18:50:59.884192Z] Loop 6103: Loss: 1.60e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.0889 +[2026-03-20T18:51:00.738934Z] Loop 6104: Loss: 1.64e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.0919 +[2026-03-20T18:51:01.593698Z] Loop 6105: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0026, Entropy: 0.0944 +[2026-03-20T18:51:02.449947Z] Loop 6106: Loss: 1.78e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.0988 +[2026-03-20T18:51:03.305327Z] Loop 6107: Loss: 1.70e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.0974 +[2026-03-20T18:51:04.160033Z] Loop 6108: Loss: 1.74e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.0963 +[2026-03-20T18:51:05.013966Z] Loop 6109: Loss: 1.83e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.0988 +[2026-03-20T18:51:05.910276Z] Loop 6110: Loss: 1.78e-02, Avg Return: 0.859, Regret: 0.0027, Entropy: 0.0983 +[2026-03-20T18:51:06.765879Z] Loop 6111: Loss: 1.82e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.1001 +[2026-03-20T18:51:07.620995Z] Loop 6112: Loss: 1.75e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.0942 +[2026-03-20T18:51:08.475837Z] Loop 6113: Loss: 1.62e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.0937 +[2026-03-20T18:51:09.330964Z] Loop 6114: Loss: 1.65e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.0942 +[2026-03-20T18:51:10.186921Z] Loop 6115: Loss: 1.81e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.1006 +[2026-03-20T18:51:11.043138Z] Loop 6116: Loss: 1.77e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.0996 +[2026-03-20T18:51:11.898349Z] Loop 6117: Loss: 1.74e-02, Avg Return: 0.860, Regret: 0.0027, Entropy: 0.0969 +[2026-03-20T18:51:12.754173Z] Loop 6118: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0027, Entropy: 0.0962 +[2026-03-20T18:51:13.609705Z] Loop 6119: Loss: 1.62e-02, Avg Return: 0.862, Regret: 0.0027, Entropy: 0.0919 +[2026-03-20T18:51:14.505072Z] Loop 6120: Loss: 1.54e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0866 +[2026-03-20T18:51:15.361396Z] Loop 6121: Loss: 1.65e-02, Avg Return: 0.864, Regret: 0.0014, Entropy: 0.0922 +[2026-03-20T18:51:16.216553Z] Loop 6122: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0915 +[2026-03-20T18:51:17.071288Z] Loop 6123: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0921 +[2026-03-20T18:51:17.927424Z] Loop 6124: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0973 +[2026-03-20T18:51:18.782077Z] Loop 6125: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0940 +[2026-03-20T18:51:19.637760Z] Loop 6126: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0937 +[2026-03-20T18:51:20.493928Z] Loop 6127: Loss: 1.72e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0930 +[2026-03-20T18:51:21.349377Z] Loop 6128: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0990 +[2026-03-20T18:51:22.203905Z] Loop 6129: Loss: 1.74e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0966 +[2026-03-20T18:51:23.098940Z] Loop 6130: Loss: 1.83e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0985 +[2026-03-20T18:51:23.954143Z] Loop 6131: Loss: 1.72e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0967 +[2026-03-20T18:51:24.808962Z] Loop 6132: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0967 +[2026-03-20T18:51:25.664816Z] Loop 6133: Loss: 1.69e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0956 +[2026-03-20T18:51:26.520889Z] Loop 6134: Loss: 1.71e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0954 +[2026-03-20T18:51:27.375587Z] Loop 6135: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0968 +[2026-03-20T18:51:28.230540Z] Loop 6136: Loss: 1.78e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0955 +[2026-03-20T18:51:29.085815Z] Loop 6137: Loss: 1.67e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0969 +[2026-03-20T18:51:29.941210Z] Loop 6138: Loss: 1.80e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0994 +[2026-03-20T18:51:30.797048Z] Loop 6139: Loss: 1.69e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0962 +[2026-03-20T18:51:31.692621Z] Loop 6140: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.1012 +[2026-03-20T18:51:32.549064Z] Loop 6141: Loss: 1.78e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.1023 +[2026-03-20T18:51:33.404421Z] Loop 6142: Loss: 1.89e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.1086 +[2026-03-20T18:51:34.259957Z] Loop 6143: Loss: 1.90e-02, Avg Return: 0.858, Regret: 0.0015, Entropy: 0.1078 +[2026-03-20T18:51:35.115760Z] Loop 6144: Loss: 2.04e-02, Avg Return: 0.860, Regret: 0.0015, Entropy: 0.1163 +[2026-03-20T18:51:35.972289Z] Loop 6145: Loss: 2.02e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.1162 +[2026-03-20T18:51:36.828664Z] Loop 6146: Loss: 2.06e-02, Avg Return: 0.859, Regret: 0.0015, Entropy: 0.1150 +[2026-03-20T18:51:37.684962Z] Loop 6147: Loss: 2.19e-02, Avg Return: 0.859, Regret: 0.0015, Entropy: 0.1235 +[2026-03-20T18:51:38.540663Z] Loop 6148: Loss: 2.30e-02, Avg Return: 0.859, Regret: 0.0015, Entropy: 0.1297 +[2026-03-20T18:51:39.396475Z] Loop 6149: Loss: 2.37e-02, Avg Return: 0.858, Regret: 0.0015, Entropy: 0.1317 +[2026-03-20T18:51:40.291679Z] Loop 6150: Loss: 2.26e-02, Avg Return: 0.859, Regret: 0.0048, Entropy: 0.1318 +[2026-03-20T18:51:41.146674Z] Loop 6151: Loss: 2.23e-02, Avg Return: 0.859, Regret: 0.0048, Entropy: 0.1274 +[2026-03-20T18:51:42.002528Z] Loop 6152: Loss: 2.37e-02, Avg Return: 0.858, Regret: 0.0048, Entropy: 0.1305 +[2026-03-20T18:51:42.858251Z] Loop 6153: Loss: 2.35e-02, Avg Return: 0.858, Regret: 0.0048, Entropy: 0.1282 +[2026-03-20T18:51:43.712022Z] Loop 6154: Loss: 2.32e-02, Avg Return: 0.857, Regret: 0.0048, Entropy: 0.1287 +[2026-03-20T18:51:44.566625Z] Loop 6155: Loss: 2.53e-02, Avg Return: 0.858, Regret: 0.0048, Entropy: 0.1335 +[2026-03-20T18:51:45.422285Z] Loop 6156: Loss: 2.39e-02, Avg Return: 0.857, Regret: 0.0048, Entropy: 0.1321 +[2026-03-20T18:51:46.277125Z] Loop 6157: Loss: 2.51e-02, Avg Return: 0.856, Regret: 0.0048, Entropy: 0.1277 +[2026-03-20T18:51:47.132474Z] Loop 6158: Loss: 2.39e-02, Avg Return: 0.856, Regret: 0.0048, Entropy: 0.1289 +[2026-03-20T18:51:47.988293Z] Loop 6159: Loss: 2.54e-02, Avg Return: 0.857, Regret: 0.0048, Entropy: 0.1353 +[2026-03-20T18:51:48.886595Z] Loop 6160: Loss: 2.65e-02, Avg Return: 0.854, Regret: 0.0077, Entropy: 0.1328 +[2026-03-20T18:51:49.742278Z] Loop 6161: Loss: 2.58e-02, Avg Return: 0.856, Regret: 0.0077, Entropy: 0.1382 +[2026-03-20T18:51:50.597026Z] Loop 6162: Loss: 2.70e-02, Avg Return: 0.858, Regret: 0.0077, Entropy: 0.1392 +[2026-03-20T18:51:51.451127Z] Loop 6163: Loss: 2.73e-02, Avg Return: 0.857, Regret: 0.0077, Entropy: 0.1438 +[2026-03-20T18:51:52.306352Z] Loop 6164: Loss: 2.70e-02, Avg Return: 0.858, Regret: 0.0077, Entropy: 0.1464 +[2026-03-20T18:51:53.161362Z] Loop 6165: Loss: 2.92e-02, Avg Return: 0.858, Regret: 0.0077, Entropy: 0.1512 +[2026-03-20T18:51:54.015443Z] Loop 6166: Loss: 2.84e-02, Avg Return: 0.858, Regret: 0.0077, Entropy: 0.1526 +[2026-03-20T18:51:54.869904Z] Loop 6167: Loss: 2.93e-02, Avg Return: 0.860, Regret: 0.0077, Entropy: 0.1490 +[2026-03-20T18:51:55.725399Z] Loop 6168: Loss: 2.87e-02, Avg Return: 0.859, Regret: 0.0077, Entropy: 0.1508 +[2026-03-20T18:51:56.581331Z] Loop 6169: Loss: 2.60e-02, Avg Return: 0.861, Regret: 0.0077, Entropy: 0.1386 +[2026-03-20T18:51:57.478796Z] Loop 6170: Loss: 2.43e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.1303 +[2026-03-20T18:51:58.333855Z] Loop 6171: Loss: 2.32e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.1239 +[2026-03-20T18:51:59.189183Z] Loop 6172: Loss: 2.01e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.1130 +[2026-03-20T18:52:00.044396Z] Loop 6173: Loss: 2.16e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.1151 +[2026-03-20T18:52:00.899094Z] Loop 6174: Loss: 1.99e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.1159 +[2026-03-20T18:52:01.754246Z] Loop 6175: Loss: 2.03e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.1167 +[2026-03-20T18:52:02.609638Z] Loop 6176: Loss: 2.18e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.1186 +[2026-03-20T18:52:03.463756Z] Loop 6177: Loss: 2.11e-02, Avg Return: 0.863, Regret: 0.0024, Entropy: 0.1152 +[2026-03-20T18:52:04.318916Z] Loop 6178: Loss: 2.04e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.1104 +[2026-03-20T18:52:05.174391Z] Loop 6179: Loss: 2.13e-02, Avg Return: 0.860, Regret: 0.0024, Entropy: 0.1158 +[2026-03-20T18:52:06.070767Z] Loop 6180: Loss: 2.19e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.1206 +[2026-03-20T18:52:06.925431Z] Loop 6181: Loss: 2.06e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.1118 +[2026-03-20T18:52:07.780294Z] Loop 6182: Loss: 1.88e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.1118 +[2026-03-20T18:52:08.637277Z] Loop 6183: Loss: 1.80e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.1016 +[2026-03-20T18:52:09.494377Z] Loop 6184: Loss: 1.84e-02, Avg Return: 0.863, Regret: 0.0022, Entropy: 0.1011 +[2026-03-20T18:52:10.349507Z] Loop 6185: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0982 +[2026-03-20T18:52:11.204265Z] Loop 6186: Loss: 1.73e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0958 +[2026-03-20T18:52:12.060381Z] Loop 6187: Loss: 1.67e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0920 +[2026-03-20T18:52:12.915605Z] Loop 6188: Loss: 1.85e-02, Avg Return: 0.863, Regret: 0.0022, Entropy: 0.1005 +[2026-03-20T18:52:13.770602Z] Loop 6189: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0927 +[2026-03-20T18:52:14.666116Z] Loop 6190: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0859 +[2026-03-20T18:52:15.522191Z] Loop 6191: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0869 +[2026-03-20T18:52:16.377371Z] Loop 6192: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0858 +[2026-03-20T18:52:17.232801Z] Loop 6193: Loss: 1.52e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0892 +[2026-03-20T18:52:18.087536Z] Loop 6194: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0898 +[2026-03-20T18:52:18.943050Z] Loop 6195: Loss: 1.59e-02, Avg Return: 0.860, Regret: 0.0011, Entropy: 0.0894 +[2026-03-20T18:52:19.798613Z] Loop 6196: Loss: 1.61e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0880 +[2026-03-20T18:52:20.654303Z] Loop 6197: Loss: 1.71e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0930 +[2026-03-20T18:52:21.509463Z] Loop 6198: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0919 +[2026-03-20T18:52:22.365551Z] Loop 6199: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0964 +[2026-03-20T18:52:23.263194Z] Loop 6200: Loss: 1.74e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.0949 +[2026-03-20T18:52:24.119758Z] Loop 6201: Loss: 1.64e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.0907 +[2026-03-20T18:52:24.974878Z] Loop 6202: Loss: 1.68e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.0904 +[2026-03-20T18:52:25.830589Z] Loop 6203: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0868 +[2026-03-20T18:52:26.685015Z] Loop 6204: Loss: 1.73e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0908 +[2026-03-20T18:52:27.539863Z] Loop 6205: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0877 +[2026-03-20T18:52:28.394817Z] Loop 6206: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0025, Entropy: 0.0924 +[2026-03-20T18:52:29.250090Z] Loop 6207: Loss: 1.57e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.0894 +[2026-03-20T18:52:30.105590Z] Loop 6208: Loss: 1.53e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.0881 +[2026-03-20T18:52:30.961735Z] Loop 6209: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0883 +[2026-03-20T18:52:31.857930Z] Loop 6210: Loss: 1.63e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.0898 +[2026-03-20T18:52:32.714188Z] Loop 6211: Loss: 1.57e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.0875 +[2026-03-20T18:52:33.570076Z] Loop 6212: Loss: 1.71e-02, Avg Return: 0.860, Regret: 0.0020, Entropy: 0.0963 +[2026-03-20T18:52:34.425758Z] Loop 6213: Loss: 1.79e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.1019 +[2026-03-20T18:52:35.282577Z] Loop 6214: Loss: 1.83e-02, Avg Return: 0.858, Regret: 0.0020, Entropy: 0.0965 +[2026-03-20T18:52:36.139527Z] Loop 6215: Loss: 1.71e-02, Avg Return: 0.859, Regret: 0.0020, Entropy: 0.0948 +[2026-03-20T18:52:36.995215Z] Loop 6216: Loss: 1.76e-02, Avg Return: 0.857, Regret: 0.0020, Entropy: 0.0964 +[2026-03-20T18:52:37.850230Z] Loop 6217: Loss: 1.77e-02, Avg Return: 0.859, Regret: 0.0020, Entropy: 0.0973 +[2026-03-20T18:52:38.705493Z] Loop 6218: Loss: 1.79e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0998 +[2026-03-20T18:52:39.561676Z] Loop 6219: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0914 +[2026-03-20T18:52:40.456325Z] Loop 6220: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0022, Entropy: 0.0871 +[2026-03-20T18:52:41.312473Z] Loop 6221: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0841 +[2026-03-20T18:52:42.166884Z] Loop 6222: Loss: 1.39e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0813 +[2026-03-20T18:52:43.021973Z] Loop 6223: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0022, Entropy: 0.0880 +[2026-03-20T18:52:43.877439Z] Loop 6224: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0870 +[2026-03-20T18:52:44.732608Z] Loop 6225: Loss: 1.74e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0899 +[2026-03-20T18:52:45.587930Z] Loop 6226: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0878 +[2026-03-20T18:52:46.443925Z] Loop 6227: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0881 +[2026-03-20T18:52:47.299618Z] Loop 6228: Loss: 1.70e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.0961 +[2026-03-20T18:52:48.155672Z] Loop 6229: Loss: 1.76e-02, Avg Return: 0.859, Regret: 0.0022, Entropy: 0.0992 +[2026-03-20T18:52:49.051916Z] Loop 6230: Loss: 1.78e-02, Avg Return: 0.858, Regret: 0.0049, Entropy: 0.0945 +[2026-03-20T18:52:49.907979Z] Loop 6231: Loss: 1.79e-02, Avg Return: 0.858, Regret: 0.0049, Entropy: 0.0983 +[2026-03-20T18:52:50.763440Z] Loop 6232: Loss: 1.79e-02, Avg Return: 0.857, Regret: 0.0049, Entropy: 0.1030 +[2026-03-20T18:52:51.619748Z] Loop 6233: Loss: 1.89e-02, Avg Return: 0.858, Regret: 0.0049, Entropy: 0.1049 +[2026-03-20T18:52:52.476066Z] Loop 6234: Loss: 1.82e-02, Avg Return: 0.858, Regret: 0.0049, Entropy: 0.0982 +[2026-03-20T18:52:53.331405Z] Loop 6235: Loss: 1.73e-02, Avg Return: 0.859, Regret: 0.0049, Entropy: 0.0968 +[2026-03-20T18:52:54.185335Z] Loop 6236: Loss: 1.81e-02, Avg Return: 0.860, Regret: 0.0049, Entropy: 0.0980 +[2026-03-20T18:52:55.039237Z] Loop 6237: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0049, Entropy: 0.0924 +[2026-03-20T18:52:55.895392Z] Loop 6238: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0049, Entropy: 0.0916 +[2026-03-20T18:52:56.751006Z] Loop 6239: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0049, Entropy: 0.0892 +[2026-03-20T18:52:57.646167Z] Loop 6240: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0856 +[2026-03-20T18:52:58.501353Z] Loop 6241: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0862 +[2026-03-20T18:52:59.357207Z] Loop 6242: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0888 +[2026-03-20T18:53:00.213161Z] Loop 6243: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0904 +[2026-03-20T18:53:01.068797Z] Loop 6244: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0931 +[2026-03-20T18:53:01.923838Z] Loop 6245: Loss: 1.72e-02, Avg Return: 0.860, Regret: 0.0012, Entropy: 0.0951 +[2026-03-20T18:53:02.779458Z] Loop 6246: Loss: 1.83e-02, Avg Return: 0.860, Regret: 0.0012, Entropy: 0.1030 +[2026-03-20T18:53:03.635053Z] Loop 6247: Loss: 1.77e-02, Avg Return: 0.859, Regret: 0.0012, Entropy: 0.1024 +[2026-03-20T18:53:04.489656Z] Loop 6248: Loss: 2.24e-02, Avg Return: 0.859, Regret: 0.0012, Entropy: 0.1176 +[2026-03-20T18:53:05.343844Z] Loop 6249: Loss: 2.03e-02, Avg Return: 0.857, Regret: 0.0012, Entropy: 0.1112 +[2026-03-20T18:53:06.241112Z] Loop 6250: Loss: 2.21e-02, Avg Return: 0.854, Regret: 0.0091, Entropy: 0.1175 +[2026-03-20T18:53:07.095286Z] Loop 6251: Loss: 2.25e-02, Avg Return: 0.850, Regret: 0.0091, Entropy: 0.1172 +[2026-03-20T18:53:07.950256Z] Loop 6252: Loss: 2.35e-02, Avg Return: 0.847, Regret: 0.0091, Entropy: 0.1233 +[2026-03-20T18:53:08.805664Z] Loop 6253: Loss: 2.39e-02, Avg Return: 0.851, Regret: 0.0091, Entropy: 0.1233 +[2026-03-20T18:53:09.660277Z] Loop 6254: Loss: 2.57e-02, Avg Return: 0.851, Regret: 0.0091, Entropy: 0.1361 +[2026-03-20T18:53:10.514519Z] Loop 6255: Loss: 2.46e-02, Avg Return: 0.854, Regret: 0.0091, Entropy: 0.1360 +[2026-03-20T18:53:11.369082Z] Loop 6256: Loss: 2.66e-02, Avg Return: 0.853, Regret: 0.0091, Entropy: 0.1425 +[2026-03-20T18:53:12.224323Z] Loop 6257: Loss: 2.79e-02, Avg Return: 0.853, Regret: 0.0091, Entropy: 0.1493 +[2026-03-20T18:53:13.079625Z] Loop 6258: Loss: 2.71e-02, Avg Return: 0.850, Regret: 0.0091, Entropy: 0.1465 +[2026-03-20T18:53:13.934904Z] Loop 6259: Loss: 2.96e-02, Avg Return: 0.850, Regret: 0.0091, Entropy: 0.1605 +[2026-03-20T18:53:14.833183Z] Loop 6260: Loss: 2.91e-02, Avg Return: 0.852, Regret: 0.0127, Entropy: 0.1580 +[2026-03-20T18:53:15.688806Z] Loop 6261: Loss: 2.78e-02, Avg Return: 0.852, Regret: 0.0127, Entropy: 0.1560 +[2026-03-20T18:53:16.545080Z] Loop 6262: Loss: 2.71e-02, Avg Return: 0.855, Regret: 0.0127, Entropy: 0.1466 +[2026-03-20T18:53:17.400756Z] Loop 6263: Loss: 2.46e-02, Avg Return: 0.857, Regret: 0.0127, Entropy: 0.1387 +[2026-03-20T18:53:18.255156Z] Loop 6264: Loss: 2.39e-02, Avg Return: 0.856, Regret: 0.0127, Entropy: 0.1296 +[2026-03-20T18:53:19.109812Z] Loop 6265: Loss: 2.36e-02, Avg Return: 0.856, Regret: 0.0127, Entropy: 0.1269 +[2026-03-20T18:53:19.964812Z] Loop 6266: Loss: 2.40e-02, Avg Return: 0.860, Regret: 0.0127, Entropy: 0.1248 +[2026-03-20T18:53:20.820579Z] Loop 6267: Loss: 2.29e-02, Avg Return: 0.860, Regret: 0.0127, Entropy: 0.1225 +[2026-03-20T18:53:21.675580Z] Loop 6268: Loss: 2.28e-02, Avg Return: 0.861, Regret: 0.0127, Entropy: 0.1217 +[2026-03-20T18:53:22.530824Z] Loop 6269: Loss: 2.15e-02, Avg Return: 0.861, Regret: 0.0127, Entropy: 0.1129 +[2026-03-20T18:53:23.427878Z] Loop 6270: Loss: 2.06e-02, Avg Return: 0.863, Regret: 0.0021, Entropy: 0.1126 +[2026-03-20T18:53:24.283455Z] Loop 6271: Loss: 2.02e-02, Avg Return: 0.863, Regret: 0.0021, Entropy: 0.1051 +[2026-03-20T18:53:25.137738Z] Loop 6272: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0021, Entropy: 0.0986 +[2026-03-20T18:53:25.993448Z] Loop 6273: Loss: 1.86e-02, Avg Return: 0.863, Regret: 0.0021, Entropy: 0.0998 +[2026-03-20T18:53:26.849388Z] Loop 6274: Loss: 1.87e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.0998 +[2026-03-20T18:53:27.704341Z] Loop 6275: Loss: 1.85e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.1015 +[2026-03-20T18:53:28.559353Z] Loop 6276: Loss: 1.85e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.0995 +[2026-03-20T18:53:29.414343Z] Loop 6277: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.1016 +[2026-03-20T18:53:30.270543Z] Loop 6278: Loss: 1.80e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.0997 +[2026-03-20T18:53:31.126538Z] Loop 6279: Loss: 1.71e-02, Avg Return: 0.860, Regret: 0.0021, Entropy: 0.0980 +[2026-03-20T18:53:32.021847Z] Loop 6280: Loss: 1.63e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.0940 +[2026-03-20T18:53:32.877559Z] Loop 6281: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0025, Entropy: 0.0905 +[2026-03-20T18:53:33.732845Z] Loop 6282: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0927 +[2026-03-20T18:53:34.588082Z] Loop 6283: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0936 +[2026-03-20T18:53:35.444240Z] Loop 6284: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0870 +[2026-03-20T18:53:36.299532Z] Loop 6285: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0025, Entropy: 0.0876 +[2026-03-20T18:53:37.154468Z] Loop 6286: Loss: 1.62e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0855 +[2026-03-20T18:53:38.009807Z] Loop 6287: Loss: 1.45e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0839 +[2026-03-20T18:53:38.864441Z] Loop 6288: Loss: 1.45e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0795 +[2026-03-20T18:53:39.719361Z] Loop 6289: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0025, Entropy: 0.0842 +[2026-03-20T18:53:40.615213Z] Loop 6290: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0828 +[2026-03-20T18:53:41.469667Z] Loop 6291: Loss: 1.51e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.0889 +[2026-03-20T18:53:42.324352Z] Loop 6292: Loss: 1.72e-02, Avg Return: 0.860, Regret: 0.0020, Entropy: 0.0918 +[2026-03-20T18:53:43.180882Z] Loop 6293: Loss: 1.66e-02, Avg Return: 0.859, Regret: 0.0020, Entropy: 0.0888 +[2026-03-20T18:53:44.036394Z] Loop 6294: Loss: 1.76e-02, Avg Return: 0.858, Regret: 0.0020, Entropy: 0.0961 +[2026-03-20T18:53:44.891027Z] Loop 6295: Loss: 1.74e-02, Avg Return: 0.858, Regret: 0.0020, Entropy: 0.0967 +[2026-03-20T18:53:45.745776Z] Loop 6296: Loss: 1.60e-02, Avg Return: 0.858, Regret: 0.0020, Entropy: 0.0874 +[2026-03-20T18:53:46.601591Z] Loop 6297: Loss: 1.84e-02, Avg Return: 0.860, Regret: 0.0020, Entropy: 0.0965 +[2026-03-20T18:53:47.456558Z] Loop 6298: Loss: 1.81e-02, Avg Return: 0.860, Regret: 0.0020, Entropy: 0.0977 +[2026-03-20T18:53:48.311654Z] Loop 6299: Loss: 1.55e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.0919 +[2026-03-20T18:53:49.205872Z] Loop 6300: Loss: 1.77e-02, Avg Return: 0.860, Regret: 0.0035, Entropy: 0.0926 +[2026-03-20T18:53:50.061320Z] Loop 6301: Loss: 1.76e-02, Avg Return: 0.859, Regret: 0.0035, Entropy: 0.0954 +[2026-03-20T18:53:50.918032Z] Loop 6302: Loss: 1.85e-02, Avg Return: 0.862, Regret: 0.0035, Entropy: 0.0948 +[2026-03-20T18:53:51.773352Z] Loop 6303: Loss: 1.80e-02, Avg Return: 0.861, Regret: 0.0035, Entropy: 0.0979 +[2026-03-20T18:53:52.629116Z] Loop 6304: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0035, Entropy: 0.0889 +[2026-03-20T18:53:53.485224Z] Loop 6305: Loss: 1.60e-02, Avg Return: 0.861, Regret: 0.0035, Entropy: 0.0862 +[2026-03-20T18:53:54.341734Z] Loop 6306: Loss: 1.66e-02, Avg Return: 0.861, Regret: 0.0035, Entropy: 0.0894 +[2026-03-20T18:53:55.198632Z] Loop 6307: Loss: 1.54e-02, Avg Return: 0.862, Regret: 0.0035, Entropy: 0.0893 +[2026-03-20T18:53:56.054882Z] Loop 6308: Loss: 1.67e-02, Avg Return: 0.862, Regret: 0.0035, Entropy: 0.0906 +[2026-03-20T18:53:56.910579Z] Loop 6309: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0035, Entropy: 0.0940 +[2026-03-20T18:53:57.807633Z] Loop 6310: Loss: 1.70e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.0949 +[2026-03-20T18:53:58.663305Z] Loop 6311: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0908 +[2026-03-20T18:53:59.518210Z] Loop 6312: Loss: 1.72e-02, Avg Return: 0.860, Regret: 0.0020, Entropy: 0.0968 +[2026-03-20T18:54:00.374035Z] Loop 6313: Loss: 1.63e-02, Avg Return: 0.860, Regret: 0.0020, Entropy: 0.0932 +[2026-03-20T18:54:01.229317Z] Loop 6314: Loss: 1.70e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.0944 +[2026-03-20T18:54:02.086058Z] Loop 6315: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0927 +[2026-03-20T18:54:02.942339Z] Loop 6316: Loss: 1.68e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.0963 +[2026-03-20T18:54:03.797579Z] Loop 6317: Loss: 1.69e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.0997 +[2026-03-20T18:54:04.652270Z] Loop 6318: Loss: 1.71e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.1002 +[2026-03-20T18:54:05.506702Z] Loop 6319: Loss: 1.84e-02, Avg Return: 0.858, Regret: 0.0020, Entropy: 0.1073 +[2026-03-20T18:54:06.403583Z] Loop 6320: Loss: 1.88e-02, Avg Return: 0.858, Regret: 0.0045, Entropy: 0.1043 +[2026-03-20T18:54:07.259140Z] Loop 6321: Loss: 1.90e-02, Avg Return: 0.860, Regret: 0.0045, Entropy: 0.1081 +[2026-03-20T18:54:08.114243Z] Loop 6322: Loss: 1.77e-02, Avg Return: 0.860, Regret: 0.0045, Entropy: 0.1035 +[2026-03-20T18:54:08.968892Z] Loop 6323: Loss: 1.74e-02, Avg Return: 0.860, Regret: 0.0045, Entropy: 0.0998 +[2026-03-20T18:54:09.824767Z] Loop 6324: Loss: 1.84e-02, Avg Return: 0.860, Regret: 0.0045, Entropy: 0.1070 +[2026-03-20T18:54:10.679332Z] Loop 6325: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0045, Entropy: 0.0983 +[2026-03-20T18:54:11.534349Z] Loop 6326: Loss: 1.89e-02, Avg Return: 0.860, Regret: 0.0045, Entropy: 0.1054 +[2026-03-20T18:54:12.389279Z] Loop 6327: Loss: 1.61e-02, Avg Return: 0.861, Regret: 0.0045, Entropy: 0.0980 +[2026-03-20T18:54:13.244697Z] Loop 6328: Loss: 1.75e-02, Avg Return: 0.863, Regret: 0.0045, Entropy: 0.1013 +[2026-03-20T18:54:14.099422Z] Loop 6329: Loss: 1.85e-02, Avg Return: 0.862, Regret: 0.0045, Entropy: 0.1021 +[2026-03-20T18:54:14.993694Z] Loop 6330: Loss: 1.79e-02, Avg Return: 0.860, Regret: 0.0019, Entropy: 0.0992 +[2026-03-20T18:54:15.848686Z] Loop 6331: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0990 +[2026-03-20T18:54:16.704480Z] Loop 6332: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.1041 +[2026-03-20T18:54:17.560335Z] Loop 6333: Loss: 1.84e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0997 +[2026-03-20T18:54:18.415503Z] Loop 6334: Loss: 1.78e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1030 +[2026-03-20T18:54:19.270699Z] Loop 6335: Loss: 1.89e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1013 +[2026-03-20T18:54:20.126251Z] Loop 6336: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0993 +[2026-03-20T18:54:20.981020Z] Loop 6337: Loss: 1.79e-02, Avg Return: 0.863, Regret: 0.0019, Entropy: 0.1007 +[2026-03-20T18:54:21.837502Z] Loop 6338: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.1037 +[2026-03-20T18:54:22.693716Z] Loop 6339: Loss: 1.99e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.1094 +[2026-03-20T18:54:23.588776Z] Loop 6340: Loss: 1.78e-02, Avg Return: 0.863, Regret: 0.0023, Entropy: 0.1032 +[2026-03-20T18:54:24.443632Z] Loop 6341: Loss: 1.87e-02, Avg Return: 0.860, Regret: 0.0023, Entropy: 0.1057 +[2026-03-20T18:54:25.298765Z] Loop 6342: Loss: 1.87e-02, Avg Return: 0.860, Regret: 0.0023, Entropy: 0.1032 +[2026-03-20T18:54:26.155069Z] Loop 6343: Loss: 1.75e-02, Avg Return: 0.861, Regret: 0.0023, Entropy: 0.1012 +[2026-03-20T18:54:27.012895Z] Loop 6344: Loss: 1.87e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.1062 +[2026-03-20T18:54:27.867751Z] Loop 6345: Loss: 1.81e-02, Avg Return: 0.861, Regret: 0.0023, Entropy: 0.1054 +[2026-03-20T18:54:28.722503Z] Loop 6346: Loss: 1.95e-02, Avg Return: 0.861, Regret: 0.0023, Entropy: 0.1072 +[2026-03-20T18:54:29.578504Z] Loop 6347: Loss: 1.90e-02, Avg Return: 0.863, Regret: 0.0023, Entropy: 0.1027 +[2026-03-20T18:54:30.435226Z] Loop 6348: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.1046 +[2026-03-20T18:54:31.289393Z] Loop 6349: Loss: 1.84e-02, Avg Return: 0.860, Regret: 0.0023, Entropy: 0.1010 +[2026-03-20T18:54:32.184059Z] Loop 6350: Loss: 1.79e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.1014 +[2026-03-20T18:54:33.039569Z] Loop 6351: Loss: 1.70e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.1030 +[2026-03-20T18:54:33.895266Z] Loop 6352: Loss: 1.85e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.1038 +[2026-03-20T18:54:34.750313Z] Loop 6353: Loss: 1.77e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.1039 +[2026-03-20T18:54:35.605237Z] Loop 6354: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.1071 +[2026-03-20T18:54:36.460660Z] Loop 6355: Loss: 1.85e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.1051 +[2026-03-20T18:54:37.317408Z] Loop 6356: Loss: 1.78e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.1051 +[2026-03-20T18:54:38.173243Z] Loop 6357: Loss: 1.80e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.1074 +[2026-03-20T18:54:39.028135Z] Loop 6358: Loss: 1.88e-02, Avg Return: 0.860, Regret: 0.0020, Entropy: 0.1036 +[2026-03-20T18:54:39.883123Z] Loop 6359: Loss: 1.79e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.1008 +[2026-03-20T18:54:40.779667Z] Loop 6360: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0994 +[2026-03-20T18:54:41.636599Z] Loop 6361: Loss: 1.73e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.1003 +[2026-03-20T18:54:42.492296Z] Loop 6362: Loss: 1.76e-02, Avg Return: 0.860, Regret: 0.0018, Entropy: 0.0961 +[2026-03-20T18:54:43.347840Z] Loop 6363: Loss: 1.79e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0991 +[2026-03-20T18:54:44.203914Z] Loop 6364: Loss: 1.84e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0997 +[2026-03-20T18:54:45.059203Z] Loop 6365: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0959 +[2026-03-20T18:54:45.914329Z] Loop 6366: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0879 +[2026-03-20T18:54:46.770144Z] Loop 6367: Loss: 1.62e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0914 +[2026-03-20T18:54:47.625117Z] Loop 6368: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0877 +[2026-03-20T18:54:48.479733Z] Loop 6369: Loss: 1.73e-02, Avg Return: 0.865, Regret: 0.0018, Entropy: 0.0886 +[2026-03-20T18:54:49.375911Z] Loop 6370: Loss: 1.47e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0838 +[2026-03-20T18:54:50.233331Z] Loop 6371: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0880 +[2026-03-20T18:54:51.089231Z] Loop 6372: Loss: 1.36e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0745 +[2026-03-20T18:54:51.944716Z] Loop 6373: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0838 +[2026-03-20T18:54:52.800898Z] Loop 6374: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0808 +[2026-03-20T18:54:53.658010Z] Loop 6375: Loss: 1.52e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0825 +[2026-03-20T18:54:54.514393Z] Loop 6376: Loss: 1.44e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0801 +[2026-03-20T18:54:55.369201Z] Loop 6377: Loss: 1.54e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0833 +[2026-03-20T18:54:56.224225Z] Loop 6378: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0838 +[2026-03-20T18:54:57.079852Z] Loop 6379: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0855 +[2026-03-20T18:54:57.976084Z] Loop 6380: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0849 +[2026-03-20T18:54:58.831498Z] Loop 6381: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0840 +[2026-03-20T18:54:59.685311Z] Loop 6382: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0883 +[2026-03-20T18:55:00.540611Z] Loop 6383: Loss: 1.60e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0864 +[2026-03-20T18:55:01.397567Z] Loop 6384: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0845 +[2026-03-20T18:55:02.253479Z] Loop 6385: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0869 +[2026-03-20T18:55:03.109564Z] Loop 6386: Loss: 1.50e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0854 +[2026-03-20T18:55:03.965129Z] Loop 6387: Loss: 1.66e-02, Avg Return: 0.859, Regret: 0.0010, Entropy: 0.0880 +[2026-03-20T18:55:04.819885Z] Loop 6388: Loss: 1.66e-02, Avg Return: 0.859, Regret: 0.0010, Entropy: 0.0879 +[2026-03-20T18:55:05.675418Z] Loop 6389: Loss: 1.60e-02, Avg Return: 0.859, Regret: 0.0010, Entropy: 0.0857 +[2026-03-20T18:55:06.570743Z] Loop 6390: Loss: 1.45e-02, Avg Return: 0.861, Regret: 0.0030, Entropy: 0.0846 +[2026-03-20T18:55:07.425690Z] Loop 6391: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0030, Entropy: 0.0867 +[2026-03-20T18:55:08.280745Z] Loop 6392: Loss: 1.51e-02, Avg Return: 0.864, Regret: 0.0030, Entropy: 0.0859 +[2026-03-20T18:55:09.136290Z] Loop 6393: Loss: 1.66e-02, Avg Return: 0.864, Regret: 0.0030, Entropy: 0.0858 +[2026-03-20T18:55:09.991947Z] Loop 6394: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0030, Entropy: 0.0856 +[2026-03-20T18:55:10.847019Z] Loop 6395: Loss: 1.82e-02, Avg Return: 0.861, Regret: 0.0030, Entropy: 0.0947 +[2026-03-20T18:55:11.702182Z] Loop 6396: Loss: 1.68e-02, Avg Return: 0.860, Regret: 0.0030, Entropy: 0.0938 +[2026-03-20T18:55:12.558531Z] Loop 6397: Loss: 1.81e-02, Avg Return: 0.859, Regret: 0.0030, Entropy: 0.0942 +[2026-03-20T18:55:13.415150Z] Loop 6398: Loss: 1.75e-02, Avg Return: 0.860, Regret: 0.0030, Entropy: 0.0976 +[2026-03-20T18:55:14.271516Z] Loop 6399: Loss: 1.67e-02, Avg Return: 0.861, Regret: 0.0030, Entropy: 0.0941 +[2026-03-20T18:55:15.166243Z] Loop 6400: Loss: 1.68e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.0912 +[2026-03-20T18:55:16.021784Z] Loop 6401: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0902 +[2026-03-20T18:55:16.877415Z] Loop 6402: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0886 +[2026-03-20T18:55:17.733251Z] Loop 6403: Loss: 1.63e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0882 +[2026-03-20T18:55:18.588825Z] Loop 6404: Loss: 1.50e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0817 +[2026-03-20T18:55:19.444532Z] Loop 6405: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0826 +[2026-03-20T18:55:20.300934Z] Loop 6406: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0022, Entropy: 0.0807 +[2026-03-20T18:55:21.156366Z] Loop 6407: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0022, Entropy: 0.0846 +[2026-03-20T18:55:22.011409Z] Loop 6408: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0022, Entropy: 0.0865 +[2026-03-20T18:55:22.866132Z] Loop 6409: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0022, Entropy: 0.0821 +[2026-03-20T18:55:23.761604Z] Loop 6410: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0858 +[2026-03-20T18:55:24.617035Z] Loop 6411: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0830 +[2026-03-20T18:55:25.472522Z] Loop 6412: Loss: 1.54e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0884 +[2026-03-20T18:55:26.327668Z] Loop 6413: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0856 +[2026-03-20T18:55:27.183606Z] Loop 6414: Loss: 1.73e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0889 +[2026-03-20T18:55:28.038979Z] Loop 6415: Loss: 1.57e-02, Avg Return: 0.860, Regret: 0.0013, Entropy: 0.0888 +[2026-03-20T18:55:28.894155Z] Loop 6416: Loss: 1.70e-02, Avg Return: 0.859, Regret: 0.0013, Entropy: 0.0897 +[2026-03-20T18:55:29.749627Z] Loop 6417: Loss: 1.61e-02, Avg Return: 0.860, Regret: 0.0013, Entropy: 0.0923 +[2026-03-20T18:55:30.604679Z] Loop 6418: Loss: 1.68e-02, Avg Return: 0.860, Regret: 0.0013, Entropy: 0.0931 +[2026-03-20T18:55:31.459536Z] Loop 6419: Loss: 1.66e-02, Avg Return: 0.860, Regret: 0.0013, Entropy: 0.0924 +[2026-03-20T18:55:32.354714Z] Loop 6420: Loss: 1.69e-02, Avg Return: 0.860, Regret: 0.0034, Entropy: 0.0932 +[2026-03-20T18:55:33.210183Z] Loop 6421: Loss: 1.65e-02, Avg Return: 0.859, Regret: 0.0034, Entropy: 0.0923 +[2026-03-20T18:55:34.065781Z] Loop 6422: Loss: 1.70e-02, Avg Return: 0.860, Regret: 0.0034, Entropy: 0.0920 +[2026-03-20T18:55:34.920760Z] Loop 6423: Loss: 1.68e-02, Avg Return: 0.859, Regret: 0.0034, Entropy: 0.0938 +[2026-03-20T18:55:35.775508Z] Loop 6424: Loss: 1.61e-02, Avg Return: 0.860, Regret: 0.0034, Entropy: 0.0882 +[2026-03-20T18:55:36.632181Z] Loop 6425: Loss: 1.58e-02, Avg Return: 0.859, Regret: 0.0034, Entropy: 0.0886 +[2026-03-20T18:55:37.488552Z] Loop 6426: Loss: 1.52e-02, Avg Return: 0.860, Regret: 0.0034, Entropy: 0.0865 +[2026-03-20T18:55:38.342320Z] Loop 6427: Loss: 1.66e-02, Avg Return: 0.860, Regret: 0.0034, Entropy: 0.0901 +[2026-03-20T18:55:39.196736Z] Loop 6428: Loss: 1.70e-02, Avg Return: 0.862, Regret: 0.0034, Entropy: 0.0880 +[2026-03-20T18:55:40.053509Z] Loop 6429: Loss: 1.59e-02, Avg Return: 0.859, Regret: 0.0034, Entropy: 0.0846 +[2026-03-20T18:55:40.951980Z] Loop 6430: Loss: 1.56e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.0845 +[2026-03-20T18:55:41.808255Z] Loop 6431: Loss: 1.64e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.0884 +[2026-03-20T18:55:42.663426Z] Loop 6432: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.0883 +[2026-03-20T18:55:43.519224Z] Loop 6433: Loss: 1.52e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.0834 +[2026-03-20T18:55:44.375411Z] Loop 6434: Loss: 1.46e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.0815 +[2026-03-20T18:55:45.231683Z] Loop 6435: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0021, Entropy: 0.0867 +[2026-03-20T18:55:46.087067Z] Loop 6436: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.0830 +[2026-03-20T18:55:46.943769Z] Loop 6437: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0021, Entropy: 0.0888 +[2026-03-20T18:55:47.799548Z] Loop 6438: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0021, Entropy: 0.0861 +[2026-03-20T18:55:48.655784Z] Loop 6439: Loss: 1.62e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.0927 +[2026-03-20T18:55:49.553065Z] Loop 6440: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0019, Entropy: 0.0893 +[2026-03-20T18:55:50.408753Z] Loop 6441: Loss: 1.65e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0907 +[2026-03-20T18:55:51.264526Z] Loop 6442: Loss: 1.54e-02, Avg Return: 0.860, Regret: 0.0019, Entropy: 0.0891 +[2026-03-20T18:55:52.120032Z] Loop 6443: Loss: 1.64e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0922 +[2026-03-20T18:55:52.975782Z] Loop 6444: Loss: 1.69e-02, Avg Return: 0.860, Regret: 0.0019, Entropy: 0.0936 +[2026-03-20T18:55:53.831778Z] Loop 6445: Loss: 1.69e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0927 +[2026-03-20T18:55:54.686748Z] Loop 6446: Loss: 1.64e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0904 +[2026-03-20T18:55:55.541295Z] Loop 6447: Loss: 1.63e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0923 +[2026-03-20T18:55:56.396660Z] Loop 6448: Loss: 1.79e-02, Avg Return: 0.859, Regret: 0.0019, Entropy: 0.0995 +[2026-03-20T18:55:57.253050Z] Loop 6449: Loss: 1.79e-02, Avg Return: 0.860, Regret: 0.0019, Entropy: 0.0992 +[2026-03-20T18:55:58.151089Z] Loop 6450: Loss: 1.79e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.0970 +[2026-03-20T18:55:59.005437Z] Loop 6451: Loss: 1.72e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.0970 +[2026-03-20T18:55:59.860237Z] Loop 6452: Loss: 1.83e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.1009 +[2026-03-20T18:56:00.716827Z] Loop 6453: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0027, Entropy: 0.0998 +[2026-03-20T18:56:01.571818Z] Loop 6454: Loss: 1.80e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.1004 +[2026-03-20T18:56:02.426105Z] Loop 6455: Loss: 2.01e-02, Avg Return: 0.860, Regret: 0.0027, Entropy: 0.1132 +[2026-03-20T18:56:03.280940Z] Loop 6456: Loss: 2.07e-02, Avg Return: 0.860, Regret: 0.0027, Entropy: 0.1170 +[2026-03-20T18:56:04.137473Z] Loop 6457: Loss: 2.19e-02, Avg Return: 0.859, Regret: 0.0027, Entropy: 0.1236 +[2026-03-20T18:56:04.992559Z] Loop 6458: Loss: 2.18e-02, Avg Return: 0.853, Regret: 0.0027, Entropy: 0.1264 +[2026-03-20T18:56:05.848964Z] Loop 6459: Loss: 2.33e-02, Avg Return: 0.854, Regret: 0.0027, Entropy: 0.1336 +[2026-03-20T18:56:06.746956Z] Loop 6460: Loss: 2.26e-02, Avg Return: 0.855, Regret: 0.0083, Entropy: 0.1278 +[2026-03-20T18:56:07.603748Z] Loop 6461: Loss: 2.25e-02, Avg Return: 0.859, Regret: 0.0083, Entropy: 0.1271 +[2026-03-20T18:56:08.459770Z] Loop 6462: Loss: 2.10e-02, Avg Return: 0.860, Regret: 0.0083, Entropy: 0.1253 +[2026-03-20T18:56:09.315532Z] Loop 6463: Loss: 2.12e-02, Avg Return: 0.860, Regret: 0.0083, Entropy: 0.1199 +[2026-03-20T18:56:10.171431Z] Loop 6464: Loss: 2.10e-02, Avg Return: 0.859, Regret: 0.0083, Entropy: 0.1162 +[2026-03-20T18:56:11.027943Z] Loop 6465: Loss: 2.08e-02, Avg Return: 0.860, Regret: 0.0083, Entropy: 0.1113 +[2026-03-20T18:56:11.883843Z] Loop 6466: Loss: 1.89e-02, Avg Return: 0.859, Regret: 0.0083, Entropy: 0.1072 +[2026-03-20T18:56:12.738332Z] Loop 6467: Loss: 2.01e-02, Avg Return: 0.857, Regret: 0.0083, Entropy: 0.1076 +[2026-03-20T18:56:13.593030Z] Loop 6468: Loss: 1.87e-02, Avg Return: 0.857, Regret: 0.0083, Entropy: 0.1026 +[2026-03-20T18:56:14.449727Z] Loop 6469: Loss: 2.08e-02, Avg Return: 0.856, Regret: 0.0083, Entropy: 0.1111 +[2026-03-20T18:56:15.345929Z] Loop 6470: Loss: 2.14e-02, Avg Return: 0.857, Regret: 0.0074, Entropy: 0.1082 +[2026-03-20T18:56:16.200858Z] Loop 6471: Loss: 2.08e-02, Avg Return: 0.855, Regret: 0.0074, Entropy: 0.1117 +[2026-03-20T18:56:17.056916Z] Loop 6472: Loss: 2.07e-02, Avg Return: 0.855, Regret: 0.0074, Entropy: 0.1088 +[2026-03-20T18:56:17.911210Z] Loop 6473: Loss: 2.12e-02, Avg Return: 0.856, Regret: 0.0074, Entropy: 0.1103 +[2026-03-20T18:56:18.765870Z] Loop 6474: Loss: 2.14e-02, Avg Return: 0.856, Regret: 0.0074, Entropy: 0.1115 +[2026-03-20T18:56:19.620653Z] Loop 6475: Loss: 2.27e-02, Avg Return: 0.857, Regret: 0.0074, Entropy: 0.1166 +[2026-03-20T18:56:20.475658Z] Loop 6476: Loss: 2.18e-02, Avg Return: 0.858, Regret: 0.0074, Entropy: 0.1177 +[2026-03-20T18:56:21.331028Z] Loop 6477: Loss: 2.30e-02, Avg Return: 0.860, Regret: 0.0074, Entropy: 0.1193 +[2026-03-20T18:56:22.186383Z] Loop 6478: Loss: 2.27e-02, Avg Return: 0.859, Regret: 0.0074, Entropy: 0.1233 +[2026-03-20T18:56:23.042507Z] Loop 6479: Loss: 2.24e-02, Avg Return: 0.861, Regret: 0.0074, Entropy: 0.1188 +[2026-03-20T18:56:23.938238Z] Loop 6480: Loss: 2.24e-02, Avg Return: 0.860, Regret: 0.0032, Entropy: 0.1196 +[2026-03-20T18:56:24.794302Z] Loop 6481: Loss: 2.24e-02, Avg Return: 0.861, Regret: 0.0032, Entropy: 0.1184 +[2026-03-20T18:56:25.648581Z] Loop 6482: Loss: 2.16e-02, Avg Return: 0.861, Regret: 0.0032, Entropy: 0.1145 +[2026-03-20T18:56:26.502379Z] Loop 6483: Loss: 2.06e-02, Avg Return: 0.862, Regret: 0.0032, Entropy: 0.1164 +[2026-03-20T18:56:27.358005Z] Loop 6484: Loss: 1.94e-02, Avg Return: 0.862, Regret: 0.0032, Entropy: 0.1076 +[2026-03-20T18:56:28.213009Z] Loop 6485: Loss: 1.84e-02, Avg Return: 0.860, Regret: 0.0032, Entropy: 0.1042 +[2026-03-20T18:56:29.067727Z] Loop 6486: Loss: 1.89e-02, Avg Return: 0.862, Regret: 0.0032, Entropy: 0.1048 +[2026-03-20T18:56:29.922144Z] Loop 6487: Loss: 2.15e-02, Avg Return: 0.861, Regret: 0.0032, Entropy: 0.1128 +[2026-03-20T18:56:30.778635Z] Loop 6488: Loss: 1.93e-02, Avg Return: 0.862, Regret: 0.0032, Entropy: 0.1056 +[2026-03-20T18:56:31.634371Z] Loop 6489: Loss: 1.85e-02, Avg Return: 0.861, Regret: 0.0032, Entropy: 0.1024 +[2026-03-20T18:56:32.529608Z] Loop 6490: Loss: 2.02e-02, Avg Return: 0.861, Regret: 0.0023, Entropy: 0.1096 +[2026-03-20T18:56:33.384616Z] Loop 6491: Loss: 2.05e-02, Avg Return: 0.860, Regret: 0.0023, Entropy: 0.1145 +[2026-03-20T18:56:34.240526Z] Loop 6492: Loss: 2.11e-02, Avg Return: 0.860, Regret: 0.0023, Entropy: 0.1174 +[2026-03-20T18:56:35.096251Z] Loop 6493: Loss: 2.06e-02, Avg Return: 0.861, Regret: 0.0023, Entropy: 0.1152 +[2026-03-20T18:56:35.952321Z] Loop 6494: Loss: 2.15e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.1158 +[2026-03-20T18:56:36.807639Z] Loop 6495: Loss: 1.99e-02, Avg Return: 0.861, Regret: 0.0023, Entropy: 0.1079 +[2026-03-20T18:56:37.662761Z] Loop 6496: Loss: 2.04e-02, Avg Return: 0.861, Regret: 0.0023, Entropy: 0.1079 +[2026-03-20T18:56:38.518034Z] Loop 6497: Loss: 1.87e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.1060 +[2026-03-20T18:56:39.373836Z] Loop 6498: Loss: 1.83e-02, Avg Return: 0.863, Regret: 0.0023, Entropy: 0.1011 +[2026-03-20T18:56:40.230005Z] Loop 6499: Loss: 1.80e-02, Avg Return: 0.860, Regret: 0.0023, Entropy: 0.0989 +[2026-03-20T18:56:41.125692Z] Loop 6500: Loss: 1.82e-02, Avg Return: 0.860, Regret: 0.0024, Entropy: 0.0990 +[2026-03-20T18:56:41.980862Z] Loop 6501: Loss: 1.86e-02, Avg Return: 0.860, Regret: 0.0024, Entropy: 0.1014 +[2026-03-20T18:56:42.836767Z] Loop 6502: Loss: 1.89e-02, Avg Return: 0.860, Regret: 0.0024, Entropy: 0.1025 +[2026-03-20T18:56:43.692568Z] Loop 6503: Loss: 1.77e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.0972 +[2026-03-20T18:56:44.547413Z] Loop 6504: Loss: 1.90e-02, Avg Return: 0.858, Regret: 0.0024, Entropy: 0.1006 +[2026-03-20T18:56:45.402703Z] Loop 6505: Loss: 1.79e-02, Avg Return: 0.858, Regret: 0.0024, Entropy: 0.0983 +[2026-03-20T18:56:46.257660Z] Loop 6506: Loss: 1.87e-02, Avg Return: 0.858, Regret: 0.0024, Entropy: 0.0962 +[2026-03-20T18:56:47.113959Z] Loop 6507: Loss: 1.92e-02, Avg Return: 0.855, Regret: 0.0024, Entropy: 0.1016 +[2026-03-20T18:56:47.969432Z] Loop 6508: Loss: 1.87e-02, Avg Return: 0.857, Regret: 0.0024, Entropy: 0.1010 +[2026-03-20T18:56:48.825268Z] Loop 6509: Loss: 1.89e-02, Avg Return: 0.856, Regret: 0.0024, Entropy: 0.0988 +[2026-03-20T18:56:49.721556Z] Loop 6510: Loss: 1.86e-02, Avg Return: 0.858, Regret: 0.0054, Entropy: 0.1017 +[2026-03-20T18:56:50.576901Z] Loop 6511: Loss: 1.79e-02, Avg Return: 0.860, Regret: 0.0054, Entropy: 0.0965 +[2026-03-20T18:56:51.432394Z] Loop 6512: Loss: 1.73e-02, Avg Return: 0.861, Regret: 0.0054, Entropy: 0.0947 +[2026-03-20T18:56:52.288519Z] Loop 6513: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0054, Entropy: 0.0909 +[2026-03-20T18:56:53.142939Z] Loop 6514: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0054, Entropy: 0.0913 +[2026-03-20T18:56:53.998124Z] Loop 6515: Loss: 1.62e-02, Avg Return: 0.862, Regret: 0.0054, Entropy: 0.0884 +[2026-03-20T18:56:54.854121Z] Loop 6516: Loss: 1.50e-02, Avg Return: 0.862, Regret: 0.0054, Entropy: 0.0857 +[2026-03-20T18:56:55.708810Z] Loop 6517: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0054, Entropy: 0.0891 +[2026-03-20T18:56:56.563889Z] Loop 6518: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0054, Entropy: 0.0893 +[2026-03-20T18:56:57.420832Z] Loop 6519: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0054, Entropy: 0.0919 +[2026-03-20T18:56:58.316852Z] Loop 6520: Loss: 1.86e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0977 +[2026-03-20T18:56:59.172368Z] Loop 6521: Loss: 1.85e-02, Avg Return: 0.860, Regret: 0.0016, Entropy: 0.1020 +[2026-03-20T18:57:00.028712Z] Loop 6522: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.1010 +[2026-03-20T18:57:00.885123Z] Loop 6523: Loss: 2.00e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.1076 +[2026-03-20T18:57:01.740481Z] Loop 6524: Loss: 1.87e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.1005 +[2026-03-20T18:57:02.596425Z] Loop 6525: Loss: 1.95e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.1061 +[2026-03-20T18:57:03.452050Z] Loop 6526: Loss: 1.95e-02, Avg Return: 0.860, Regret: 0.0016, Entropy: 0.1080 +[2026-03-20T18:57:04.307538Z] Loop 6527: Loss: 2.11e-02, Avg Return: 0.860, Regret: 0.0016, Entropy: 0.1193 +[2026-03-20T18:57:05.162412Z] Loop 6528: Loss: 2.11e-02, Avg Return: 0.858, Regret: 0.0016, Entropy: 0.1135 +[2026-03-20T18:57:06.018640Z] Loop 6529: Loss: 2.06e-02, Avg Return: 0.859, Regret: 0.0016, Entropy: 0.1104 +[2026-03-20T18:57:06.915915Z] Loop 6530: Loss: 1.94e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.1014 +[2026-03-20T18:57:07.772874Z] Loop 6531: Loss: 1.76e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.1020 +[2026-03-20T18:57:08.627556Z] Loop 6532: Loss: 1.82e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.1024 +[2026-03-20T18:57:09.483023Z] Loop 6533: Loss: 1.71e-02, Avg Return: 0.862, Regret: 0.0026, Entropy: 0.0985 +[2026-03-20T18:57:10.339819Z] Loop 6534: Loss: 1.76e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.0943 +[2026-03-20T18:57:11.197355Z] Loop 6535: Loss: 1.88e-02, Avg Return: 0.859, Regret: 0.0026, Entropy: 0.1011 +[2026-03-20T18:57:12.053496Z] Loop 6536: Loss: 1.97e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.1063 +[2026-03-20T18:57:12.908565Z] Loop 6537: Loss: 2.02e-02, Avg Return: 0.859, Regret: 0.0026, Entropy: 0.1059 +[2026-03-20T18:57:13.764254Z] Loop 6538: Loss: 1.99e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.1057 +[2026-03-20T18:57:14.620790Z] Loop 6539: Loss: 1.65e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.0932 +[2026-03-20T18:57:15.517657Z] Loop 6540: Loss: 1.61e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.0916 +[2026-03-20T18:57:16.373260Z] Loop 6541: Loss: 1.73e-02, Avg Return: 0.863, Regret: 0.0022, Entropy: 0.0950 +[2026-03-20T18:57:17.229101Z] Loop 6542: Loss: 1.50e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0863 +[2026-03-20T18:57:18.085597Z] Loop 6543: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0897 +[2026-03-20T18:57:18.941716Z] Loop 6544: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0876 +[2026-03-20T18:57:19.798582Z] Loop 6545: Loss: 1.64e-02, Avg Return: 0.863, Regret: 0.0022, Entropy: 0.0921 +[2026-03-20T18:57:20.655199Z] Loop 6546: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0022, Entropy: 0.0835 +[2026-03-20T18:57:21.511264Z] Loop 6547: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0022, Entropy: 0.0845 +[2026-03-20T18:57:22.366831Z] Loop 6548: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0916 +[2026-03-20T18:57:23.222354Z] Loop 6549: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0885 +[2026-03-20T18:57:24.123421Z] Loop 6550: Loss: 1.46e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0834 +[2026-03-20T18:57:24.979065Z] Loop 6551: Loss: 1.60e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0887 +[2026-03-20T18:57:25.834244Z] Loop 6552: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0945 +[2026-03-20T18:57:26.688834Z] Loop 6553: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0886 +[2026-03-20T18:57:27.544173Z] Loop 6554: Loss: 1.59e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0932 +[2026-03-20T18:57:28.399113Z] Loop 6555: Loss: 1.68e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0975 +[2026-03-20T18:57:29.253636Z] Loop 6556: Loss: 1.84e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0969 +[2026-03-20T18:57:30.109001Z] Loop 6557: Loss: 1.72e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0970 +[2026-03-20T18:57:30.964811Z] Loop 6558: Loss: 1.70e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0971 +[2026-03-20T18:57:31.820546Z] Loop 6559: Loss: 1.70e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1007 +[2026-03-20T18:57:32.716377Z] Loop 6560: Loss: 1.89e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.1080 +[2026-03-20T18:57:33.572096Z] Loop 6561: Loss: 2.04e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.1143 +[2026-03-20T18:57:34.430485Z] Loop 6562: Loss: 1.97e-02, Avg Return: 0.860, Regret: 0.0020, Entropy: 0.1130 +[2026-03-20T18:57:35.287893Z] Loop 6563: Loss: 2.14e-02, Avg Return: 0.860, Regret: 0.0020, Entropy: 0.1210 +[2026-03-20T18:57:36.143684Z] Loop 6564: Loss: 2.36e-02, Avg Return: 0.860, Regret: 0.0020, Entropy: 0.1340 +[2026-03-20T18:57:36.999269Z] Loop 6565: Loss: 2.56e-02, Avg Return: 0.858, Regret: 0.0020, Entropy: 0.1408 +[2026-03-20T18:57:37.855866Z] Loop 6566: Loss: 2.79e-02, Avg Return: 0.857, Regret: 0.0020, Entropy: 0.1520 +[2026-03-20T18:57:38.711509Z] Loop 6567: Loss: 3.07e-02, Avg Return: 0.854, Regret: 0.0020, Entropy: 0.1667 +[2026-03-20T18:57:39.566620Z] Loop 6568: Loss: 3.18e-02, Avg Return: 0.853, Regret: 0.0020, Entropy: 0.1737 +[2026-03-20T18:57:40.421279Z] Loop 6569: Loss: 3.07e-02, Avg Return: 0.855, Regret: 0.0020, Entropy: 0.1680 +[2026-03-20T18:57:41.317950Z] Loop 6570: Loss: 2.89e-02, Avg Return: 0.856, Regret: 0.0076, Entropy: 0.1538 +[2026-03-20T18:57:42.174220Z] Loop 6571: Loss: 2.64e-02, Avg Return: 0.858, Regret: 0.0076, Entropy: 0.1427 +[2026-03-20T18:57:43.031037Z] Loop 6572: Loss: 2.50e-02, Avg Return: 0.860, Regret: 0.0076, Entropy: 0.1315 +[2026-03-20T18:57:43.886830Z] Loop 6573: Loss: 2.23e-02, Avg Return: 0.859, Regret: 0.0076, Entropy: 0.1210 +[2026-03-20T18:57:44.742531Z] Loop 6574: Loss: 2.17e-02, Avg Return: 0.860, Regret: 0.0076, Entropy: 0.1151 +[2026-03-20T18:57:45.597938Z] Loop 6575: Loss: 2.00e-02, Avg Return: 0.863, Regret: 0.0076, Entropy: 0.1095 +[2026-03-20T18:57:46.453385Z] Loop 6576: Loss: 1.77e-02, Avg Return: 0.863, Regret: 0.0076, Entropy: 0.1015 +[2026-03-20T18:57:47.309062Z] Loop 6577: Loss: 1.77e-02, Avg Return: 0.863, Regret: 0.0076, Entropy: 0.0987 +[2026-03-20T18:57:48.164617Z] Loop 6578: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0076, Entropy: 0.0922 +[2026-03-20T18:57:49.019524Z] Loop 6579: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0076, Entropy: 0.0841 +[2026-03-20T18:57:49.915595Z] Loop 6580: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0835 +[2026-03-20T18:57:50.770208Z] Loop 6581: Loss: 1.59e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0901 +[2026-03-20T18:57:51.627097Z] Loop 6582: Loss: 1.43e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0802 +[2026-03-20T18:57:52.481988Z] Loop 6583: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0870 +[2026-03-20T18:57:53.336949Z] Loop 6584: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0850 +[2026-03-20T18:57:54.192238Z] Loop 6585: Loss: 1.66e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0876 +[2026-03-20T18:57:55.048820Z] Loop 6586: Loss: 1.63e-02, Avg Return: 0.860, Regret: 0.0011, Entropy: 0.0906 +[2026-03-20T18:57:55.904150Z] Loop 6587: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0869 +[2026-03-20T18:57:56.759362Z] Loop 6588: Loss: 1.60e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0846 +[2026-03-20T18:57:57.614668Z] Loop 6589: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0864 +[2026-03-20T18:57:58.512360Z] Loop 6590: Loss: 1.52e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0835 +[2026-03-20T18:57:59.368129Z] Loop 6591: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0819 +[2026-03-20T18:58:00.223474Z] Loop 6592: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0810 +[2026-03-20T18:58:01.078915Z] Loop 6593: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0812 +[2026-03-20T18:58:01.934911Z] Loop 6594: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0774 +[2026-03-20T18:58:02.790326Z] Loop 6595: Loss: 1.42e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0781 +[2026-03-20T18:58:03.644770Z] Loop 6596: Loss: 1.59e-02, Avg Return: 0.864, Regret: 0.0014, Entropy: 0.0822 +[2026-03-20T18:58:04.498899Z] Loop 6597: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0792 +[2026-03-20T18:58:05.354056Z] Loop 6598: Loss: 1.42e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0821 +[2026-03-20T18:58:06.209440Z] Loop 6599: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0821 +[2026-03-20T18:58:07.105796Z] Loop 6600: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0882 +[2026-03-20T18:58:07.960740Z] Loop 6601: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0915 +[2026-03-20T18:58:08.816710Z] Loop 6602: Loss: 1.64e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0854 +[2026-03-20T18:58:09.673367Z] Loop 6603: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0912 +[2026-03-20T18:58:10.529067Z] Loop 6604: Loss: 1.58e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0876 +[2026-03-20T18:58:11.384531Z] Loop 6605: Loss: 1.60e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0910 +[2026-03-20T18:58:12.240198Z] Loop 6606: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0896 +[2026-03-20T18:58:13.095974Z] Loop 6607: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0908 +[2026-03-20T18:58:13.952153Z] Loop 6608: Loss: 1.62e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0915 +[2026-03-20T18:58:14.806924Z] Loop 6609: Loss: 1.74e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0948 +[2026-03-20T18:58:15.703566Z] Loop 6610: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0852 +[2026-03-20T18:58:16.558832Z] Loop 6611: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0856 +[2026-03-20T18:58:17.414395Z] Loop 6612: Loss: 1.51e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0841 +[2026-03-20T18:58:18.269770Z] Loop 6613: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0817 +[2026-03-20T18:58:19.125853Z] Loop 6614: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0863 +[2026-03-20T18:58:19.981202Z] Loop 6615: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0824 +[2026-03-20T18:58:20.836635Z] Loop 6616: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0806 +[2026-03-20T18:58:21.691331Z] Loop 6617: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0847 +[2026-03-20T18:58:22.547302Z] Loop 6618: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0836 +[2026-03-20T18:58:23.401522Z] Loop 6619: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0877 +[2026-03-20T18:58:24.295997Z] Loop 6620: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0831 +[2026-03-20T18:58:25.151634Z] Loop 6621: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0887 +[2026-03-20T18:58:26.007922Z] Loop 6622: Loss: 1.46e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0826 +[2026-03-20T18:58:26.863454Z] Loop 6623: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0840 +[2026-03-20T18:58:27.718728Z] Loop 6624: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0845 +[2026-03-20T18:58:28.574091Z] Loop 6625: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0807 +[2026-03-20T18:58:29.430591Z] Loop 6626: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0834 +[2026-03-20T18:58:30.287174Z] Loop 6627: Loss: 1.44e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0796 +[2026-03-20T18:58:31.143382Z] Loop 6628: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0839 +[2026-03-20T18:58:31.998821Z] Loop 6629: Loss: 1.49e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0839 +[2026-03-20T18:58:32.897600Z] Loop 6630: Loss: 1.54e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.0852 +[2026-03-20T18:58:33.753643Z] Loop 6631: Loss: 1.72e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.0916 +[2026-03-20T18:58:34.609861Z] Loop 6632: Loss: 1.85e-02, Avg Return: 0.858, Regret: 0.0026, Entropy: 0.0969 +[2026-03-20T18:58:35.464475Z] Loop 6633: Loss: 2.00e-02, Avg Return: 0.858, Regret: 0.0026, Entropy: 0.1018 +[2026-03-20T18:58:36.319034Z] Loop 6634: Loss: 1.89e-02, Avg Return: 0.858, Regret: 0.0026, Entropy: 0.0984 +[2026-03-20T18:58:37.175354Z] Loop 6635: Loss: 1.83e-02, Avg Return: 0.857, Regret: 0.0026, Entropy: 0.0941 +[2026-03-20T18:58:38.032583Z] Loop 6636: Loss: 1.98e-02, Avg Return: 0.856, Regret: 0.0026, Entropy: 0.1005 +[2026-03-20T18:58:38.887330Z] Loop 6637: Loss: 1.82e-02, Avg Return: 0.857, Regret: 0.0026, Entropy: 0.0954 +[2026-03-20T18:58:39.743064Z] Loop 6638: Loss: 1.82e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.0969 +[2026-03-20T18:58:40.598754Z] Loop 6639: Loss: 1.63e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.0926 +[2026-03-20T18:58:41.496986Z] Loop 6640: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0026, Entropy: 0.0864 +[2026-03-20T18:58:42.353369Z] Loop 6641: Loss: 1.52e-02, Avg Return: 0.862, Regret: 0.0026, Entropy: 0.0860 +[2026-03-20T18:58:43.208153Z] Loop 6642: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0026, Entropy: 0.0779 +[2026-03-20T18:58:44.062952Z] Loop 6643: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0026, Entropy: 0.0755 +[2026-03-20T18:58:44.918408Z] Loop 6644: Loss: 1.33e-02, Avg Return: 0.863, Regret: 0.0026, Entropy: 0.0748 +[2026-03-20T18:58:45.773171Z] Loop 6645: Loss: 1.44e-02, Avg Return: 0.862, Regret: 0.0026, Entropy: 0.0795 +[2026-03-20T18:58:46.629435Z] Loop 6646: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0026, Entropy: 0.0828 +[2026-03-20T18:58:47.485194Z] Loop 6647: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0026, Entropy: 0.0783 +[2026-03-20T18:58:48.341333Z] Loop 6648: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0026, Entropy: 0.0810 +[2026-03-20T18:58:49.198203Z] Loop 6649: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0026, Entropy: 0.0816 +[2026-03-20T18:58:50.095468Z] Loop 6650: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0848 +[2026-03-20T18:58:50.952344Z] Loop 6651: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0869 +[2026-03-20T18:58:51.807925Z] Loop 6652: Loss: 1.70e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0923 +[2026-03-20T18:58:52.665692Z] Loop 6653: Loss: 1.69e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0925 +[2026-03-20T18:58:53.521686Z] Loop 6654: Loss: 1.87e-02, Avg Return: 0.860, Regret: 0.0009, Entropy: 0.1009 +[2026-03-20T18:58:54.376582Z] Loop 6655: Loss: 2.01e-02, Avg Return: 0.857, Regret: 0.0009, Entropy: 0.1057 +[2026-03-20T18:58:55.231424Z] Loop 6656: Loss: 1.87e-02, Avg Return: 0.859, Regret: 0.0009, Entropy: 0.1003 +[2026-03-20T18:58:56.087101Z] Loop 6657: Loss: 1.88e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.1000 +[2026-03-20T18:58:56.942257Z] Loop 6658: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0967 +[2026-03-20T18:58:57.797489Z] Loop 6659: Loss: 1.62e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0927 +[2026-03-20T18:58:58.692329Z] Loop 6660: Loss: 1.68e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0939 +[2026-03-20T18:58:59.548242Z] Loop 6661: Loss: 1.65e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0894 +[2026-03-20T18:59:00.403917Z] Loop 6662: Loss: 1.74e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0946 +[2026-03-20T18:59:01.260784Z] Loop 6663: Loss: 1.58e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0912 +[2026-03-20T18:59:02.116377Z] Loop 6664: Loss: 1.71e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0913 +[2026-03-20T18:59:02.973163Z] Loop 6665: Loss: 1.86e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0993 +[2026-03-20T18:59:03.828734Z] Loop 6666: Loss: 1.71e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0922 +[2026-03-20T18:59:04.684671Z] Loop 6667: Loss: 1.95e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0977 +[2026-03-20T18:59:05.540539Z] Loop 6668: Loss: 1.95e-02, Avg Return: 0.859, Regret: 0.0009, Entropy: 0.1029 +[2026-03-20T18:59:06.396385Z] Loop 6669: Loss: 1.94e-02, Avg Return: 0.854, Regret: 0.0009, Entropy: 0.1019 +[2026-03-20T18:59:07.292876Z] Loop 6670: Loss: 2.05e-02, Avg Return: 0.855, Regret: 0.0092, Entropy: 0.1089 +[2026-03-20T18:59:08.148629Z] Loop 6671: Loss: 2.26e-02, Avg Return: 0.856, Regret: 0.0092, Entropy: 0.1094 +[2026-03-20T18:59:09.004915Z] Loop 6672: Loss: 1.93e-02, Avg Return: 0.857, Regret: 0.0092, Entropy: 0.1041 +[2026-03-20T18:59:09.861272Z] Loop 6673: Loss: 1.91e-02, Avg Return: 0.859, Regret: 0.0092, Entropy: 0.1011 +[2026-03-20T18:59:10.716871Z] Loop 6674: Loss: 1.82e-02, Avg Return: 0.860, Regret: 0.0092, Entropy: 0.0952 +[2026-03-20T18:59:11.574513Z] Loop 6675: Loss: 1.64e-02, Avg Return: 0.861, Regret: 0.0092, Entropy: 0.0895 +[2026-03-20T18:59:12.432421Z] Loop 6676: Loss: 1.56e-02, Avg Return: 0.861, Regret: 0.0092, Entropy: 0.0861 +[2026-03-20T18:59:13.288364Z] Loop 6677: Loss: 1.60e-02, Avg Return: 0.861, Regret: 0.0092, Entropy: 0.0841 +[2026-03-20T18:59:14.143346Z] Loop 6678: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0092, Entropy: 0.0809 +[2026-03-20T18:59:14.997710Z] Loop 6679: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0092, Entropy: 0.0813 +[2026-03-20T18:59:15.891984Z] Loop 6680: Loss: 1.42e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.0792 +[2026-03-20T18:59:16.748524Z] Loop 6681: Loss: 1.40e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.0789 +[2026-03-20T18:59:17.603764Z] Loop 6682: Loss: 1.35e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0792 +[2026-03-20T18:59:18.458797Z] Loop 6683: Loss: 1.44e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.0811 +[2026-03-20T18:59:19.315092Z] Loop 6684: Loss: 1.54e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.0814 +[2026-03-20T18:59:20.170705Z] Loop 6685: Loss: 1.57e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.0820 +[2026-03-20T18:59:21.025305Z] Loop 6686: Loss: 1.54e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.0834 +[2026-03-20T18:59:21.880169Z] Loop 6687: Loss: 1.45e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.0797 +[2026-03-20T18:59:22.735914Z] Loop 6688: Loss: 1.46e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.0777 +[2026-03-20T18:59:23.593260Z] Loop 6689: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0751 +[2026-03-20T18:59:24.490585Z] Loop 6690: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0819 +[2026-03-20T18:59:25.346661Z] Loop 6691: Loss: 1.34e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0780 +[2026-03-20T18:59:26.202186Z] Loop 6692: Loss: 1.40e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0781 +[2026-03-20T18:59:27.057298Z] Loop 6693: Loss: 1.43e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0792 +[2026-03-20T18:59:27.912825Z] Loop 6694: Loss: 1.35e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0758 +[2026-03-20T18:59:28.768410Z] Loop 6695: Loss: 1.51e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0836 +[2026-03-20T18:59:29.624253Z] Loop 6696: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0819 +[2026-03-20T18:59:30.480180Z] Loop 6697: Loss: 1.43e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0783 +[2026-03-20T18:59:31.335468Z] Loop 6698: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0847 +[2026-03-20T18:59:32.190530Z] Loop 6699: Loss: 1.50e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0814 +[2026-03-20T18:59:33.086018Z] Loop 6700: Loss: 1.49e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0802 +[2026-03-20T18:59:33.939809Z] Loop 6701: Loss: 1.44e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0807 +[2026-03-20T18:59:34.793573Z] Loop 6702: Loss: 1.50e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0829 +[2026-03-20T18:59:35.648504Z] Loop 6703: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0823 +[2026-03-20T18:59:36.504564Z] Loop 6704: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0787 +[2026-03-20T18:59:37.360286Z] Loop 6705: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0815 +[2026-03-20T18:59:38.216262Z] Loop 6706: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0822 +[2026-03-20T18:59:39.071945Z] Loop 6707: Loss: 1.50e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0802 +[2026-03-20T18:59:39.927414Z] Loop 6708: Loss: 1.40e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0777 +[2026-03-20T18:59:40.782962Z] Loop 6709: Loss: 1.33e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0771 +[2026-03-20T18:59:41.677377Z] Loop 6710: Loss: 1.44e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0815 +[2026-03-20T18:59:42.531529Z] Loop 6711: Loss: 1.37e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.0769 +[2026-03-20T18:59:43.387241Z] Loop 6712: Loss: 1.56e-02, Avg Return: 0.860, Regret: 0.0015, Entropy: 0.0823 +[2026-03-20T18:59:44.243419Z] Loop 6713: Loss: 1.45e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.0802 +[2026-03-20T18:59:45.098633Z] Loop 6714: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0839 +[2026-03-20T18:59:45.953207Z] Loop 6715: Loss: 1.63e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.0851 +[2026-03-20T18:59:46.808875Z] Loop 6716: Loss: 1.43e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.0810 +[2026-03-20T18:59:47.664374Z] Loop 6717: Loss: 1.46e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.0837 +[2026-03-20T18:59:48.519826Z] Loop 6718: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0801 +[2026-03-20T18:59:49.375125Z] Loop 6719: Loss: 1.42e-02, Avg Return: 0.860, Regret: 0.0015, Entropy: 0.0814 +[2026-03-20T18:59:50.270942Z] Loop 6720: Loss: 1.48e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0839 +[2026-03-20T18:59:51.127876Z] Loop 6721: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0783 +[2026-03-20T18:59:51.983230Z] Loop 6722: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0876 +[2026-03-20T18:59:52.839350Z] Loop 6723: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0790 +[2026-03-20T18:59:53.695376Z] Loop 6724: Loss: 1.50e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0823 +[2026-03-20T18:59:54.549891Z] Loop 6725: Loss: 1.36e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0796 +[2026-03-20T18:59:55.406824Z] Loop 6726: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0815 +[2026-03-20T18:59:56.263072Z] Loop 6727: Loss: 1.37e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0771 +[2026-03-20T18:59:57.118120Z] Loop 6728: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0791 +[2026-03-20T18:59:57.973419Z] Loop 6729: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0804 +[2026-03-20T18:59:58.871279Z] Loop 6730: Loss: 1.35e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0764 +[2026-03-20T18:59:59.726511Z] Loop 6731: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0817 +[2026-03-20T19:00:00.583135Z] Loop 6732: Loss: 1.47e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0821 +[2026-03-20T19:00:01.436293Z] Loop 6733: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0812 +[2026-03-20T19:00:02.291970Z] Loop 6734: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0838 +[2026-03-20T19:00:03.148425Z] Loop 6735: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0840 +[2026-03-20T19:00:04.004153Z] Loop 6736: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0804 +[2026-03-20T19:00:04.859809Z] Loop 6737: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0796 +[2026-03-20T19:00:05.715115Z] Loop 6738: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0827 +[2026-03-20T19:00:06.570409Z] Loop 6739: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0804 +[2026-03-20T19:00:07.466753Z] Loop 6740: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0850 +[2026-03-20T19:00:08.322680Z] Loop 6741: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0870 +[2026-03-20T19:00:09.177744Z] Loop 6742: Loss: 1.44e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0795 +[2026-03-20T19:00:10.033246Z] Loop 6743: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0803 +[2026-03-20T19:00:10.889306Z] Loop 6744: Loss: 1.56e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0853 +[2026-03-20T19:00:11.746335Z] Loop 6745: Loss: 1.54e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0819 +[2026-03-20T19:00:12.602479Z] Loop 6746: Loss: 1.57e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0819 +[2026-03-20T19:00:13.457176Z] Loop 6747: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0845 +[2026-03-20T19:00:14.313054Z] Loop 6748: Loss: 1.56e-02, Avg Return: 0.865, Regret: 0.0008, Entropy: 0.0870 +[2026-03-20T19:00:15.168818Z] Loop 6749: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0816 +[2026-03-20T19:00:16.064632Z] Loop 6750: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0861 +[2026-03-20T19:00:16.920503Z] Loop 6751: Loss: 1.62e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0865 +[2026-03-20T19:00:17.777426Z] Loop 6752: Loss: 1.63e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0906 +[2026-03-20T19:00:18.633363Z] Loop 6753: Loss: 1.68e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0897 +[2026-03-20T19:00:19.489794Z] Loop 6754: Loss: 1.73e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0940 +[2026-03-20T19:00:20.345411Z] Loop 6755: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0937 +[2026-03-20T19:00:21.201364Z] Loop 6756: Loss: 1.62e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0901 +[2026-03-20T19:00:22.056822Z] Loop 6757: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0967 +[2026-03-20T19:00:22.913310Z] Loop 6758: Loss: 1.85e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0971 +[2026-03-20T19:00:23.770776Z] Loop 6759: Loss: 1.60e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0930 +[2026-03-20T19:00:24.667114Z] Loop 6760: Loss: 1.71e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0941 +[2026-03-20T19:00:25.522567Z] Loop 6761: Loss: 1.79e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0947 +[2026-03-20T19:00:26.377743Z] Loop 6762: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0896 +[2026-03-20T19:00:27.233568Z] Loop 6763: Loss: 1.68e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.0938 +[2026-03-20T19:00:28.090200Z] Loop 6764: Loss: 1.60e-02, Avg Return: 0.864, Regret: 0.0015, Entropy: 0.0883 +[2026-03-20T19:00:28.944809Z] Loop 6765: Loss: 1.79e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0967 +[2026-03-20T19:00:29.799464Z] Loop 6766: Loss: 1.86e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.1018 +[2026-03-20T19:00:30.655285Z] Loop 6767: Loss: 1.84e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.1032 +[2026-03-20T19:00:31.511978Z] Loop 6768: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.1063 +[2026-03-20T19:00:32.367817Z] Loop 6769: Loss: 2.01e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.1061 +[2026-03-20T19:00:33.265822Z] Loop 6770: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1014 +[2026-03-20T19:00:34.121548Z] Loop 6771: Loss: 1.78e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.1012 +[2026-03-20T19:00:34.977903Z] Loop 6772: Loss: 1.92e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.1060 +[2026-03-20T19:00:35.834936Z] Loop 6773: Loss: 1.85e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1022 +[2026-03-20T19:00:36.690447Z] Loop 6774: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1016 +[2026-03-20T19:00:37.546078Z] Loop 6775: Loss: 1.91e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1016 +[2026-03-20T19:00:38.401519Z] Loop 6776: Loss: 1.69e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0969 +[2026-03-20T19:00:39.257637Z] Loop 6777: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0939 +[2026-03-20T19:00:40.113575Z] Loop 6778: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0947 +[2026-03-20T19:00:40.969282Z] Loop 6779: Loss: 1.74e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0949 +[2026-03-20T19:00:41.867310Z] Loop 6780: Loss: 1.57e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0880 +[2026-03-20T19:00:42.722291Z] Loop 6781: Loss: 1.71e-02, Avg Return: 0.864, Regret: 0.0016, Entropy: 0.0923 +[2026-03-20T19:00:43.578726Z] Loop 6782: Loss: 1.63e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0930 +[2026-03-20T19:00:44.434838Z] Loop 6783: Loss: 1.61e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0878 +[2026-03-20T19:00:45.289049Z] Loop 6784: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0888 +[2026-03-20T19:00:46.143911Z] Loop 6785: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0880 +[2026-03-20T19:00:47.000346Z] Loop 6786: Loss: 1.54e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0880 +[2026-03-20T19:00:47.855810Z] Loop 6787: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0925 +[2026-03-20T19:00:48.710847Z] Loop 6788: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0948 +[2026-03-20T19:00:49.566208Z] Loop 6789: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0865 +[2026-03-20T19:00:50.461989Z] Loop 6790: Loss: 1.73e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0939 +[2026-03-20T19:00:51.317694Z] Loop 6791: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0895 +[2026-03-20T19:00:52.172317Z] Loop 6792: Loss: 1.68e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0891 +[2026-03-20T19:00:53.026839Z] Loop 6793: Loss: 1.63e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0914 +[2026-03-20T19:00:53.882143Z] Loop 6794: Loss: 1.70e-02, Avg Return: 0.860, Regret: 0.0016, Entropy: 0.0947 +[2026-03-20T19:00:54.738152Z] Loop 6795: Loss: 1.79e-02, Avg Return: 0.859, Regret: 0.0016, Entropy: 0.0912 +[2026-03-20T19:00:55.592953Z] Loop 6796: Loss: 1.77e-02, Avg Return: 0.859, Regret: 0.0016, Entropy: 0.0964 +[2026-03-20T19:00:56.447538Z] Loop 6797: Loss: 1.98e-02, Avg Return: 0.859, Regret: 0.0016, Entropy: 0.1057 +[2026-03-20T19:00:57.302570Z] Loop 6798: Loss: 2.01e-02, Avg Return: 0.858, Regret: 0.0016, Entropy: 0.1035 +[2026-03-20T19:00:58.158028Z] Loop 6799: Loss: 1.98e-02, Avg Return: 0.858, Regret: 0.0016, Entropy: 0.1051 +[2026-03-20T19:00:59.053055Z] Loop 6800: Loss: 1.97e-02, Avg Return: 0.857, Regret: 0.0052, Entropy: 0.1082 +[2026-03-20T19:00:59.908529Z] Loop 6801: Loss: 1.79e-02, Avg Return: 0.861, Regret: 0.0052, Entropy: 0.1017 +[2026-03-20T19:01:00.763369Z] Loop 6802: Loss: 1.80e-02, Avg Return: 0.860, Regret: 0.0052, Entropy: 0.1022 +[2026-03-20T19:01:01.618926Z] Loop 6803: Loss: 1.92e-02, Avg Return: 0.860, Regret: 0.0052, Entropy: 0.1063 +[2026-03-20T19:01:02.473826Z] Loop 6804: Loss: 1.90e-02, Avg Return: 0.860, Regret: 0.0052, Entropy: 0.1037 +[2026-03-20T19:01:03.329051Z] Loop 6805: Loss: 1.88e-02, Avg Return: 0.859, Regret: 0.0052, Entropy: 0.1083 +[2026-03-20T19:01:04.184740Z] Loop 6806: Loss: 1.89e-02, Avg Return: 0.859, Regret: 0.0052, Entropy: 0.1063 +[2026-03-20T19:01:05.040074Z] Loop 6807: Loss: 2.07e-02, Avg Return: 0.859, Regret: 0.0052, Entropy: 0.1137 +[2026-03-20T19:01:05.896771Z] Loop 6808: Loss: 2.25e-02, Avg Return: 0.857, Regret: 0.0052, Entropy: 0.1234 +[2026-03-20T19:01:06.752279Z] Loop 6809: Loss: 2.24e-02, Avg Return: 0.857, Regret: 0.0052, Entropy: 0.1260 +[2026-03-20T19:01:07.647753Z] Loop 6810: Loss: 2.27e-02, Avg Return: 0.857, Regret: 0.0071, Entropy: 0.1245 +[2026-03-20T19:01:08.502115Z] Loop 6811: Loss: 2.27e-02, Avg Return: 0.856, Regret: 0.0071, Entropy: 0.1236 +[2026-03-20T19:01:09.357690Z] Loop 6812: Loss: 2.29e-02, Avg Return: 0.857, Regret: 0.0071, Entropy: 0.1268 +[2026-03-20T19:01:10.212651Z] Loop 6813: Loss: 2.26e-02, Avg Return: 0.857, Regret: 0.0071, Entropy: 0.1231 +[2026-03-20T19:01:11.067831Z] Loop 6814: Loss: 2.19e-02, Avg Return: 0.857, Regret: 0.0071, Entropy: 0.1212 +[2026-03-20T19:01:11.922758Z] Loop 6815: Loss: 2.24e-02, Avg Return: 0.855, Regret: 0.0071, Entropy: 0.1231 +[2026-03-20T19:01:12.777118Z] Loop 6816: Loss: 2.26e-02, Avg Return: 0.855, Regret: 0.0071, Entropy: 0.1171 +[2026-03-20T19:01:13.632306Z] Loop 6817: Loss: 2.11e-02, Avg Return: 0.851, Regret: 0.0071, Entropy: 0.1133 +[2026-03-20T19:01:14.486980Z] Loop 6818: Loss: 2.17e-02, Avg Return: 0.850, Regret: 0.0071, Entropy: 0.1155 +[2026-03-20T19:01:15.342280Z] Loop 6819: Loss: 2.25e-02, Avg Return: 0.852, Regret: 0.0071, Entropy: 0.1133 +[2026-03-20T19:01:16.236664Z] Loop 6820: Loss: 2.13e-02, Avg Return: 0.852, Regret: 0.0099, Entropy: 0.1144 +[2026-03-20T19:01:17.091891Z] Loop 6821: Loss: 2.07e-02, Avg Return: 0.856, Regret: 0.0099, Entropy: 0.1116 +[2026-03-20T19:01:17.946833Z] Loop 6822: Loss: 2.08e-02, Avg Return: 0.857, Regret: 0.0099, Entropy: 0.1122 +[2026-03-20T19:01:18.802765Z] Loop 6823: Loss: 2.07e-02, Avg Return: 0.856, Regret: 0.0099, Entropy: 0.1083 +[2026-03-20T19:01:19.658591Z] Loop 6824: Loss: 1.93e-02, Avg Return: 0.860, Regret: 0.0099, Entropy: 0.1023 +[2026-03-20T19:01:20.513462Z] Loop 6825: Loss: 1.81e-02, Avg Return: 0.860, Regret: 0.0099, Entropy: 0.1037 +[2026-03-20T19:01:21.368524Z] Loop 6826: Loss: 1.85e-02, Avg Return: 0.861, Regret: 0.0099, Entropy: 0.0995 +[2026-03-20T19:01:22.224210Z] Loop 6827: Loss: 1.82e-02, Avg Return: 0.862, Regret: 0.0099, Entropy: 0.0931 +[2026-03-20T19:01:23.079194Z] Loop 6828: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0099, Entropy: 0.0921 +[2026-03-20T19:01:23.933318Z] Loop 6829: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0099, Entropy: 0.0911 +[2026-03-20T19:01:24.828934Z] Loop 6830: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0910 +[2026-03-20T19:01:25.684903Z] Loop 6831: Loss: 1.65e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0911 +[2026-03-20T19:01:26.540039Z] Loop 6832: Loss: 1.77e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0978 +[2026-03-20T19:01:27.394261Z] Loop 6833: Loss: 1.80e-02, Avg Return: 0.858, Regret: 0.0008, Entropy: 0.0989 +[2026-03-20T19:01:28.248674Z] Loop 6834: Loss: 1.70e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0919 +[2026-03-20T19:01:29.103302Z] Loop 6835: Loss: 1.59e-02, Avg Return: 0.860, Regret: 0.0008, Entropy: 0.0871 +[2026-03-20T19:01:29.958484Z] Loop 6836: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0906 +[2026-03-20T19:01:30.813880Z] Loop 6837: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0844 +[2026-03-20T19:01:31.669334Z] Loop 6838: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0853 +[2026-03-20T19:01:32.524818Z] Loop 6839: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0843 +[2026-03-20T19:01:33.420442Z] Loop 6840: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0841 +[2026-03-20T19:01:34.276537Z] Loop 6841: Loss: 1.54e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0821 +[2026-03-20T19:01:35.134064Z] Loop 6842: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0829 +[2026-03-20T19:01:35.990299Z] Loop 6843: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0814 +[2026-03-20T19:01:36.845674Z] Loop 6844: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0859 +[2026-03-20T19:01:37.701384Z] Loop 6845: Loss: 1.49e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0857 +[2026-03-20T19:01:38.556843Z] Loop 6846: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0891 +[2026-03-20T19:01:39.411575Z] Loop 6847: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0877 +[2026-03-20T19:01:40.266189Z] Loop 6848: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0827 +[2026-03-20T19:01:41.121484Z] Loop 6849: Loss: 1.64e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0901 +[2026-03-20T19:01:42.018320Z] Loop 6850: Loss: 1.50e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0850 +[2026-03-20T19:01:42.874221Z] Loop 6851: Loss: 1.54e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0860 +[2026-03-20T19:01:43.731465Z] Loop 6852: Loss: 1.45e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0832 +[2026-03-20T19:01:44.588308Z] Loop 6853: Loss: 1.63e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0890 +[2026-03-20T19:01:45.445319Z] Loop 6854: Loss: 1.46e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0812 +[2026-03-20T19:01:46.300854Z] Loop 6855: Loss: 1.41e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0802 +[2026-03-20T19:01:47.155050Z] Loop 6856: Loss: 1.59e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0844 +[2026-03-20T19:01:48.009051Z] Loop 6857: Loss: 1.46e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0823 +[2026-03-20T19:01:48.865464Z] Loop 6858: Loss: 1.50e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0856 +[2026-03-20T19:01:49.720851Z] Loop 6859: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0856 +[2026-03-20T19:01:50.615705Z] Loop 6860: Loss: 1.53e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0821 +[2026-03-20T19:01:51.471422Z] Loop 6861: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0809 +[2026-03-20T19:01:52.326374Z] Loop 6862: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0835 +[2026-03-20T19:01:53.180885Z] Loop 6863: Loss: 1.60e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0864 +[2026-03-20T19:01:54.036480Z] Loop 6864: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0850 +[2026-03-20T19:01:54.893613Z] Loop 6865: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0879 +[2026-03-20T19:01:55.749661Z] Loop 6866: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0839 +[2026-03-20T19:01:56.605327Z] Loop 6867: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0817 +[2026-03-20T19:01:57.460442Z] Loop 6868: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0843 +[2026-03-20T19:01:58.315486Z] Loop 6869: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0892 +[2026-03-20T19:01:59.212885Z] Loop 6870: Loss: 1.50e-02, Avg Return: 0.861, Regret: 0.0017, Entropy: 0.0838 +[2026-03-20T19:02:00.067783Z] Loop 6871: Loss: 1.66e-02, Avg Return: 0.864, Regret: 0.0017, Entropy: 0.0907 +[2026-03-20T19:02:00.923479Z] Loop 6872: Loss: 1.63e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0883 +[2026-03-20T19:02:01.779555Z] Loop 6873: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0894 +[2026-03-20T19:02:02.634061Z] Loop 6874: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0017, Entropy: 0.0884 +[2026-03-20T19:02:03.488492Z] Loop 6875: Loss: 1.50e-02, Avg Return: 0.864, Regret: 0.0017, Entropy: 0.0837 +[2026-03-20T19:02:04.343924Z] Loop 6876: Loss: 1.46e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0810 +[2026-03-20T19:02:05.199883Z] Loop 6877: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0810 +[2026-03-20T19:02:06.054806Z] Loop 6878: Loss: 1.47e-02, Avg Return: 0.861, Regret: 0.0017, Entropy: 0.0822 +[2026-03-20T19:02:06.909815Z] Loop 6879: Loss: 1.58e-02, Avg Return: 0.861, Regret: 0.0017, Entropy: 0.0866 +[2026-03-20T19:02:07.803715Z] Loop 6880: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0810 +[2026-03-20T19:02:08.661045Z] Loop 6881: Loss: 1.44e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0806 +[2026-03-20T19:02:09.517216Z] Loop 6882: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0801 +[2026-03-20T19:02:10.372363Z] Loop 6883: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0800 +[2026-03-20T19:02:11.228353Z] Loop 6884: Loss: 1.50e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0821 +[2026-03-20T19:02:12.085734Z] Loop 6885: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0827 +[2026-03-20T19:02:12.943414Z] Loop 6886: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0848 +[2026-03-20T19:02:13.799873Z] Loop 6887: Loss: 1.45e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0823 +[2026-03-20T19:02:14.654809Z] Loop 6888: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0815 +[2026-03-20T19:02:15.511252Z] Loop 6889: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0866 +[2026-03-20T19:02:16.410459Z] Loop 6890: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0770 +[2026-03-20T19:02:17.266528Z] Loop 6891: Loss: 1.34e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0772 +[2026-03-20T19:02:18.122237Z] Loop 6892: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0818 +[2026-03-20T19:02:18.978544Z] Loop 6893: Loss: 1.50e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0822 +[2026-03-20T19:02:19.835341Z] Loop 6894: Loss: 1.44e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0809 +[2026-03-20T19:02:20.691290Z] Loop 6895: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0779 +[2026-03-20T19:02:21.546986Z] Loop 6896: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0850 +[2026-03-20T19:02:22.403235Z] Loop 6897: Loss: 1.40e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0821 +[2026-03-20T19:02:23.258537Z] Loop 6898: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0807 +[2026-03-20T19:02:24.113606Z] Loop 6899: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0795 +[2026-03-20T19:02:25.010640Z] Loop 6900: Loss: 1.46e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0811 +[2026-03-20T19:02:25.867058Z] Loop 6901: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0805 +[2026-03-20T19:02:26.721380Z] Loop 6902: Loss: 1.45e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0798 +[2026-03-20T19:02:27.575722Z] Loop 6903: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0806 +[2026-03-20T19:02:28.431212Z] Loop 6904: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0791 +[2026-03-20T19:02:29.288264Z] Loop 6905: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0808 +[2026-03-20T19:02:30.143369Z] Loop 6906: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0789 +[2026-03-20T19:02:30.998586Z] Loop 6907: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0860 +[2026-03-20T19:02:31.853752Z] Loop 6908: Loss: 1.46e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0799 +[2026-03-20T19:02:32.709311Z] Loop 6909: Loss: 1.50e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0796 +[2026-03-20T19:02:33.604963Z] Loop 6910: Loss: 1.44e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0787 +[2026-03-20T19:02:34.460175Z] Loop 6911: Loss: 1.40e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0805 +[2026-03-20T19:02:35.315322Z] Loop 6912: Loss: 1.51e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0834 +[2026-03-20T19:02:36.171280Z] Loop 6913: Loss: 1.40e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0792 +[2026-03-20T19:02:37.027107Z] Loop 6914: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0776 +[2026-03-20T19:02:37.881536Z] Loop 6915: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0800 +[2026-03-20T19:02:38.736542Z] Loop 6916: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0824 +[2026-03-20T19:02:39.592028Z] Loop 6917: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0810 +[2026-03-20T19:02:40.447780Z] Loop 6918: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0845 +[2026-03-20T19:02:41.303482Z] Loop 6919: Loss: 1.50e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0838 +[2026-03-20T19:02:42.198341Z] Loop 6920: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0846 +[2026-03-20T19:02:43.053596Z] Loop 6921: Loss: 1.42e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0820 +[2026-03-20T19:02:43.909533Z] Loop 6922: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0847 +[2026-03-20T19:02:44.764498Z] Loop 6923: Loss: 1.50e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0874 +[2026-03-20T19:02:45.619280Z] Loop 6924: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0802 +[2026-03-20T19:02:46.475481Z] Loop 6925: Loss: 1.54e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0867 +[2026-03-20T19:02:47.331325Z] Loop 6926: Loss: 1.50e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0861 +[2026-03-20T19:02:48.186927Z] Loop 6927: Loss: 1.61e-02, Avg Return: 0.860, Regret: 0.0008, Entropy: 0.0882 +[2026-03-20T19:02:49.042798Z] Loop 6928: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0897 +[2026-03-20T19:02:49.897578Z] Loop 6929: Loss: 1.73e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0907 +[2026-03-20T19:02:50.792630Z] Loop 6930: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.0856 +[2026-03-20T19:02:51.647745Z] Loop 6931: Loss: 1.69e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.0939 +[2026-03-20T19:02:52.503295Z] Loop 6932: Loss: 1.53e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.0883 +[2026-03-20T19:02:53.359266Z] Loop 6933: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.0887 +[2026-03-20T19:02:54.214801Z] Loop 6934: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.0823 +[2026-03-20T19:02:55.071218Z] Loop 6935: Loss: 1.42e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.0787 +[2026-03-20T19:02:55.927574Z] Loop 6936: Loss: 1.50e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.0819 +[2026-03-20T19:02:56.784845Z] Loop 6937: Loss: 1.54e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.0840 +[2026-03-20T19:02:57.640158Z] Loop 6938: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.0844 +[2026-03-20T19:02:58.495430Z] Loop 6939: Loss: 1.62e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.0854 +[2026-03-20T19:02:59.391347Z] Loop 6940: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.0853 +[2026-03-20T19:03:00.248247Z] Loop 6941: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0858 +[2026-03-20T19:03:01.103873Z] Loop 6942: Loss: 1.54e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0855 +[2026-03-20T19:03:01.959561Z] Loop 6943: Loss: 1.57e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.0881 +[2026-03-20T19:03:02.816043Z] Loop 6944: Loss: 1.71e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0931 +[2026-03-20T19:03:03.671399Z] Loop 6945: Loss: 1.76e-02, Avg Return: 0.860, Regret: 0.0020, Entropy: 0.0975 +[2026-03-20T19:03:04.526630Z] Loop 6946: Loss: 1.67e-02, Avg Return: 0.860, Regret: 0.0020, Entropy: 0.0972 +[2026-03-20T19:03:05.381335Z] Loop 6947: Loss: 1.81e-02, Avg Return: 0.859, Regret: 0.0020, Entropy: 0.0988 +[2026-03-20T19:03:06.235959Z] Loop 6948: Loss: 1.73e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.0958 +[2026-03-20T19:03:07.091053Z] Loop 6949: Loss: 1.61e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.0938 +[2026-03-20T19:03:07.987959Z] Loop 6950: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0915 +[2026-03-20T19:03:08.842943Z] Loop 6951: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0903 +[2026-03-20T19:03:09.698620Z] Loop 6952: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0869 +[2026-03-20T19:03:10.554703Z] Loop 6953: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0809 +[2026-03-20T19:03:11.410320Z] Loop 6954: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0859 +[2026-03-20T19:03:12.266556Z] Loop 6955: Loss: 1.55e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0869 +[2026-03-20T19:03:13.123168Z] Loop 6956: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0804 +[2026-03-20T19:03:13.978571Z] Loop 6957: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0795 +[2026-03-20T19:03:14.835773Z] Loop 6958: Loss: 1.43e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0807 +[2026-03-20T19:03:15.692204Z] Loop 6959: Loss: 1.49e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0821 +[2026-03-20T19:03:16.588770Z] Loop 6960: Loss: 1.46e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0813 +[2026-03-20T19:03:17.443255Z] Loop 6961: Loss: 1.55e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0865 +[2026-03-20T19:03:18.296997Z] Loop 6962: Loss: 1.57e-02, Avg Return: 0.860, Regret: 0.0019, Entropy: 0.0866 +[2026-03-20T19:03:19.153129Z] Loop 6963: Loss: 1.67e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0911 +[2026-03-20T19:03:20.009627Z] Loop 6964: Loss: 1.62e-02, Avg Return: 0.860, Regret: 0.0019, Entropy: 0.0893 +[2026-03-20T19:03:20.865536Z] Loop 6965: Loss: 1.50e-02, Avg Return: 0.860, Regret: 0.0019, Entropy: 0.0811 +[2026-03-20T19:03:21.722346Z] Loop 6966: Loss: 1.48e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0837 +[2026-03-20T19:03:22.577224Z] Loop 6967: Loss: 1.55e-02, Avg Return: 0.858, Regret: 0.0019, Entropy: 0.0844 +[2026-03-20T19:03:23.433248Z] Loop 6968: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0857 +[2026-03-20T19:03:24.288919Z] Loop 6969: Loss: 1.38e-02, Avg Return: 0.860, Regret: 0.0019, Entropy: 0.0799 +[2026-03-20T19:03:25.183940Z] Loop 6970: Loss: 1.59e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.0850 +[2026-03-20T19:03:26.039513Z] Loop 6971: Loss: 1.46e-02, Avg Return: 0.862, Regret: 0.0026, Entropy: 0.0787 +[2026-03-20T19:03:26.896029Z] Loop 6972: Loss: 1.44e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.0792 +[2026-03-20T19:03:27.752499Z] Loop 6973: Loss: 1.38e-02, Avg Return: 0.862, Regret: 0.0026, Entropy: 0.0787 +[2026-03-20T19:03:28.609300Z] Loop 6974: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0026, Entropy: 0.0818 +[2026-03-20T19:03:29.466050Z] Loop 6975: Loss: 1.52e-02, Avg Return: 0.862, Regret: 0.0026, Entropy: 0.0839 +[2026-03-20T19:03:30.320755Z] Loop 6976: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0026, Entropy: 0.0796 +[2026-03-20T19:03:31.176486Z] Loop 6977: Loss: 1.43e-02, Avg Return: 0.864, Regret: 0.0026, Entropy: 0.0800 +[2026-03-20T19:03:32.032134Z] Loop 6978: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0026, Entropy: 0.0807 +[2026-03-20T19:03:32.887095Z] Loop 6979: Loss: 1.40e-02, Avg Return: 0.864, Regret: 0.0026, Entropy: 0.0770 +[2026-03-20T19:03:33.783651Z] Loop 6980: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0840 +[2026-03-20T19:03:34.639197Z] Loop 6981: Loss: 1.41e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0823 +[2026-03-20T19:03:35.495838Z] Loop 6982: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0817 +[2026-03-20T19:03:36.351392Z] Loop 6983: Loss: 1.45e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0819 +[2026-03-20T19:03:37.206865Z] Loop 6984: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0824 +[2026-03-20T19:03:38.063443Z] Loop 6985: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0843 +[2026-03-20T19:03:38.919339Z] Loop 6986: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0822 +[2026-03-20T19:03:39.775101Z] Loop 6987: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0814 +[2026-03-20T19:03:40.630515Z] Loop 6988: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0802 +[2026-03-20T19:03:41.485761Z] Loop 6989: Loss: 1.52e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0834 +[2026-03-20T19:03:42.383987Z] Loop 6990: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0795 +[2026-03-20T19:03:43.239337Z] Loop 6991: Loss: 1.36e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0781 +[2026-03-20T19:03:44.095146Z] Loop 6992: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0821 +[2026-03-20T19:03:44.949937Z] Loop 6993: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0881 +[2026-03-20T19:03:45.805139Z] Loop 6994: Loss: 1.50e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0831 +[2026-03-20T19:03:46.660896Z] Loop 6995: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0856 +[2026-03-20T19:03:47.517081Z] Loop 6996: Loss: 1.45e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0783 +[2026-03-20T19:03:48.372169Z] Loop 6997: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0818 +[2026-03-20T19:03:49.228490Z] Loop 6998: Loss: 1.54e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0847 +[2026-03-20T19:03:50.084692Z] Loop 6999: Loss: 1.43e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0768 +[2026-03-20T19:03:50.981614Z] Loop 7000: Loss: 1.51e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.0827 +[2026-03-20T19:03:51.837841Z] Loop 7001: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0815 +[2026-03-20T19:03:52.692773Z] Loop 7002: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0828 +[2026-03-20T19:03:53.547735Z] Loop 7003: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0833 +[2026-03-20T19:03:54.403270Z] Loop 7004: Loss: 1.43e-02, Avg Return: 0.864, Regret: 0.0015, Entropy: 0.0783 +[2026-03-20T19:03:55.258355Z] Loop 7005: Loss: 1.50e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0808 +[2026-03-20T19:03:56.112919Z] Loop 7006: Loss: 1.34e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.0777 +[2026-03-20T19:03:56.968413Z] Loop 7007: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0781 +[2026-03-20T19:03:57.824613Z] Loop 7008: Loss: 1.46e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.0832 +[2026-03-20T19:03:58.680202Z] Loop 7009: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0788 +[2026-03-20T19:03:59.575650Z] Loop 7010: Loss: 1.46e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0798 +[2026-03-20T19:04:00.431120Z] Loop 7011: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0797 +[2026-03-20T19:04:01.285775Z] Loop 7012: Loss: 1.39e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0746 +[2026-03-20T19:04:02.141202Z] Loop 7013: Loss: 1.43e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0783 +[2026-03-20T19:04:02.996887Z] Loop 7014: Loss: 1.44e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0838 +[2026-03-20T19:04:03.852069Z] Loop 7015: Loss: 1.50e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0845 +[2026-03-20T19:04:04.706479Z] Loop 7016: Loss: 1.40e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0811 +[2026-03-20T19:04:05.561261Z] Loop 7017: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0857 +[2026-03-20T19:04:06.415660Z] Loop 7018: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0816 +[2026-03-20T19:04:07.271417Z] Loop 7019: Loss: 1.52e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0836 +[2026-03-20T19:04:08.166751Z] Loop 7020: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0818 +[2026-03-20T19:04:09.022064Z] Loop 7021: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0845 +[2026-03-20T19:04:09.877439Z] Loop 7022: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0844 +[2026-03-20T19:04:10.733665Z] Loop 7023: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0858 +[2026-03-20T19:04:11.589046Z] Loop 7024: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0830 +[2026-03-20T19:04:12.444080Z] Loop 7025: Loss: 1.50e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0857 +[2026-03-20T19:04:13.298834Z] Loop 7026: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0922 +[2026-03-20T19:04:14.155250Z] Loop 7027: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0938 +[2026-03-20T19:04:15.011712Z] Loop 7028: Loss: 1.71e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0959 +[2026-03-20T19:04:15.866185Z] Loop 7029: Loss: 1.79e-02, Avg Return: 0.860, Regret: 0.0013, Entropy: 0.0978 +[2026-03-20T19:04:16.760800Z] Loop 7030: Loss: 1.92e-02, Avg Return: 0.861, Regret: 0.0032, Entropy: 0.1057 +[2026-03-20T19:04:17.616742Z] Loop 7031: Loss: 1.82e-02, Avg Return: 0.860, Regret: 0.0032, Entropy: 0.1061 +[2026-03-20T19:04:18.472576Z] Loop 7032: Loss: 1.89e-02, Avg Return: 0.860, Regret: 0.0032, Entropy: 0.1073 +[2026-03-20T19:04:19.328961Z] Loop 7033: Loss: 1.75e-02, Avg Return: 0.861, Regret: 0.0032, Entropy: 0.1026 +[2026-03-20T19:04:20.183220Z] Loop 7034: Loss: 1.74e-02, Avg Return: 0.861, Regret: 0.0032, Entropy: 0.1010 +[2026-03-20T19:04:21.038046Z] Loop 7035: Loss: 1.74e-02, Avg Return: 0.862, Regret: 0.0032, Entropy: 0.0994 +[2026-03-20T19:04:21.893641Z] Loop 7036: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0032, Entropy: 0.0921 +[2026-03-20T19:04:22.748345Z] Loop 7037: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0032, Entropy: 0.0914 +[2026-03-20T19:04:23.603346Z] Loop 7038: Loss: 1.64e-02, Avg Return: 0.861, Regret: 0.0032, Entropy: 0.0960 +[2026-03-20T19:04:24.460152Z] Loop 7039: Loss: 1.71e-02, Avg Return: 0.861, Regret: 0.0032, Entropy: 0.0932 +[2026-03-20T19:04:25.355395Z] Loop 7040: Loss: 1.83e-02, Avg Return: 0.863, Regret: 0.0019, Entropy: 0.0985 +[2026-03-20T19:04:26.211377Z] Loop 7041: Loss: 1.65e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0900 +[2026-03-20T19:04:27.068648Z] Loop 7042: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0973 +[2026-03-20T19:04:27.925266Z] Loop 7043: Loss: 1.72e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0950 +[2026-03-20T19:04:28.781496Z] Loop 7044: Loss: 1.69e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0959 +[2026-03-20T19:04:29.636454Z] Loop 7045: Loss: 1.67e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0931 +[2026-03-20T19:04:30.491271Z] Loop 7046: Loss: 1.58e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0908 +[2026-03-20T19:04:31.346967Z] Loop 7047: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0019, Entropy: 0.0910 +[2026-03-20T19:04:32.202754Z] Loop 7048: Loss: 1.56e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0912 +[2026-03-20T19:04:33.059693Z] Loop 7049: Loss: 1.70e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0960 +[2026-03-20T19:04:33.956992Z] Loop 7050: Loss: 1.70e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0977 +[2026-03-20T19:04:34.813437Z] Loop 7051: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0919 +[2026-03-20T19:04:35.668516Z] Loop 7052: Loss: 1.79e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0991 +[2026-03-20T19:04:36.523209Z] Loop 7053: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0941 +[2026-03-20T19:04:37.378234Z] Loop 7054: Loss: 1.74e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0995 +[2026-03-20T19:04:38.234594Z] Loop 7055: Loss: 1.79e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0913 +[2026-03-20T19:04:39.088935Z] Loop 7056: Loss: 1.87e-02, Avg Return: 0.859, Regret: 0.0018, Entropy: 0.0985 +[2026-03-20T19:04:39.943512Z] Loop 7057: Loss: 1.79e-02, Avg Return: 0.859, Regret: 0.0018, Entropy: 0.0946 +[2026-03-20T19:04:40.798380Z] Loop 7058: Loss: 1.92e-02, Avg Return: 0.858, Regret: 0.0018, Entropy: 0.1002 +[2026-03-20T19:04:41.653972Z] Loop 7059: Loss: 1.86e-02, Avg Return: 0.859, Regret: 0.0018, Entropy: 0.0997 +[2026-03-20T19:04:42.549652Z] Loop 7060: Loss: 1.90e-02, Avg Return: 0.859, Regret: 0.0051, Entropy: 0.1010 +[2026-03-20T19:04:43.404457Z] Loop 7061: Loss: 1.79e-02, Avg Return: 0.860, Regret: 0.0051, Entropy: 0.0967 +[2026-03-20T19:04:44.258706Z] Loop 7062: Loss: 1.64e-02, Avg Return: 0.861, Regret: 0.0051, Entropy: 0.0868 +[2026-03-20T19:04:45.114018Z] Loop 7063: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0051, Entropy: 0.0855 +[2026-03-20T19:04:45.969961Z] Loop 7064: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0051, Entropy: 0.0843 +[2026-03-20T19:04:46.825718Z] Loop 7065: Loss: 1.47e-02, Avg Return: 0.863, Regret: 0.0051, Entropy: 0.0791 +[2026-03-20T19:04:47.681938Z] Loop 7066: Loss: 1.45e-02, Avg Return: 0.862, Regret: 0.0051, Entropy: 0.0820 +[2026-03-20T19:04:48.536998Z] Loop 7067: Loss: 1.46e-02, Avg Return: 0.862, Regret: 0.0051, Entropy: 0.0827 +[2026-03-20T19:04:49.392776Z] Loop 7068: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0051, Entropy: 0.0820 +[2026-03-20T19:04:50.247922Z] Loop 7069: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0051, Entropy: 0.0792 +[2026-03-20T19:04:51.144451Z] Loop 7070: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0794 +[2026-03-20T19:04:52.000097Z] Loop 7071: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0747 +[2026-03-20T19:04:52.856115Z] Loop 7072: Loss: 1.54e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0831 +[2026-03-20T19:04:53.712303Z] Loop 7073: Loss: 1.46e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0774 +[2026-03-20T19:04:54.567612Z] Loop 7074: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0013, Entropy: 0.0755 +[2026-03-20T19:04:55.422679Z] Loop 7075: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0780 +[2026-03-20T19:04:56.277947Z] Loop 7076: Loss: 1.39e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0778 +[2026-03-20T19:04:57.134566Z] Loop 7077: Loss: 1.34e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0781 +[2026-03-20T19:04:57.991164Z] Loop 7078: Loss: 1.54e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0881 +[2026-03-20T19:04:58.846732Z] Loop 7079: Loss: 1.47e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0839 +[2026-03-20T19:04:59.743403Z] Loop 7080: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.0816 +[2026-03-20T19:05:00.599747Z] Loop 7081: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0808 +[2026-03-20T19:05:01.456220Z] Loop 7082: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.0804 +[2026-03-20T19:05:02.313353Z] Loop 7083: Loss: 1.46e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0752 +[2026-03-20T19:05:03.167957Z] Loop 7084: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.0824 +[2026-03-20T19:05:04.022362Z] Loop 7085: Loss: 1.32e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.0753 +[2026-03-20T19:05:04.878520Z] Loop 7086: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.0740 +[2026-03-20T19:05:05.733666Z] Loop 7087: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.0780 +[2026-03-20T19:05:06.588619Z] Loop 7088: Loss: 1.32e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0734 +[2026-03-20T19:05:07.443247Z] Loop 7089: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.0840 +[2026-03-20T19:05:08.340637Z] Loop 7090: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0798 +[2026-03-20T19:05:09.197186Z] Loop 7091: Loss: 1.33e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0788 +[2026-03-20T19:05:10.053883Z] Loop 7092: Loss: 1.47e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0806 +[2026-03-20T19:05:10.909368Z] Loop 7093: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0774 +[2026-03-20T19:05:11.765044Z] Loop 7094: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0824 +[2026-03-20T19:05:12.620271Z] Loop 7095: Loss: 1.42e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0782 +[2026-03-20T19:05:13.476617Z] Loop 7096: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0859 +[2026-03-20T19:05:14.333131Z] Loop 7097: Loss: 1.45e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0798 +[2026-03-20T19:05:15.187866Z] Loop 7098: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0799 +[2026-03-20T19:05:16.043215Z] Loop 7099: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0770 +[2026-03-20T19:05:16.937891Z] Loop 7100: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0773 +[2026-03-20T19:05:17.793399Z] Loop 7101: Loss: 1.49e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0793 +[2026-03-20T19:05:18.649111Z] Loop 7102: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0777 +[2026-03-20T19:05:19.505463Z] Loop 7103: Loss: 1.40e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0775 +[2026-03-20T19:05:20.361953Z] Loop 7104: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0770 +[2026-03-20T19:05:21.218536Z] Loop 7105: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0846 +[2026-03-20T19:05:22.074045Z] Loop 7106: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0844 +[2026-03-20T19:05:22.930297Z] Loop 7107: Loss: 1.34e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0779 +[2026-03-20T19:05:23.786455Z] Loop 7108: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0763 +[2026-03-20T19:05:24.642668Z] Loop 7109: Loss: 1.64e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0883 +[2026-03-20T19:05:25.542540Z] Loop 7110: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0831 +[2026-03-20T19:05:26.398222Z] Loop 7111: Loss: 1.44e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0814 +[2026-03-20T19:05:27.254422Z] Loop 7112: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0774 +[2026-03-20T19:05:28.110652Z] Loop 7113: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0800 +[2026-03-20T19:05:28.967309Z] Loop 7114: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0817 +[2026-03-20T19:05:29.823971Z] Loop 7115: Loss: 1.42e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0789 +[2026-03-20T19:05:30.680336Z] Loop 7116: Loss: 1.36e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0764 +[2026-03-20T19:05:31.536597Z] Loop 7117: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0782 +[2026-03-20T19:05:32.394574Z] Loop 7118: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0770 +[2026-03-20T19:05:33.251024Z] Loop 7119: Loss: 1.43e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0820 +[2026-03-20T19:05:34.149230Z] Loop 7120: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0776 +[2026-03-20T19:05:35.004388Z] Loop 7121: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0814 +[2026-03-20T19:05:35.860538Z] Loop 7122: Loss: 1.49e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0816 +[2026-03-20T19:05:36.715445Z] Loop 7123: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0768 +[2026-03-20T19:05:37.570764Z] Loop 7124: Loss: 1.45e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0784 +[2026-03-20T19:05:38.425446Z] Loop 7125: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0750 +[2026-03-20T19:05:39.281906Z] Loop 7126: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0787 +[2026-03-20T19:05:40.138577Z] Loop 7127: Loss: 1.52e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0842 +[2026-03-20T19:05:40.995043Z] Loop 7128: Loss: 1.46e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0826 +[2026-03-20T19:05:41.851112Z] Loop 7129: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0777 +[2026-03-20T19:05:42.747130Z] Loop 7130: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0814 +[2026-03-20T19:05:43.602675Z] Loop 7131: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0839 +[2026-03-20T19:05:44.458692Z] Loop 7132: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0828 +[2026-03-20T19:05:45.314458Z] Loop 7133: Loss: 1.45e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0808 +[2026-03-20T19:05:46.169087Z] Loop 7134: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0797 +[2026-03-20T19:05:47.023737Z] Loop 7135: Loss: 1.52e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0849 +[2026-03-20T19:05:47.879395Z] Loop 7136: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0812 +[2026-03-20T19:05:48.735277Z] Loop 7137: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0768 +[2026-03-20T19:05:49.590161Z] Loop 7138: Loss: 1.46e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0811 +[2026-03-20T19:05:50.445660Z] Loop 7139: Loss: 1.52e-02, Avg Return: 0.865, Regret: 0.0009, Entropy: 0.0814 +[2026-03-20T19:05:51.342287Z] Loop 7140: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0862 +[2026-03-20T19:05:52.198386Z] Loop 7141: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0838 +[2026-03-20T19:05:53.054176Z] Loop 7142: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0835 +[2026-03-20T19:05:53.909531Z] Loop 7143: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0862 +[2026-03-20T19:05:54.765246Z] Loop 7144: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0888 +[2026-03-20T19:05:55.622228Z] Loop 7145: Loss: 1.50e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0852 +[2026-03-20T19:05:56.477908Z] Loop 7146: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0947 +[2026-03-20T19:05:57.332876Z] Loop 7147: Loss: 1.70e-02, Avg Return: 0.860, Regret: 0.0009, Entropy: 0.0950 +[2026-03-20T19:05:58.187298Z] Loop 7148: Loss: 1.70e-02, Avg Return: 0.860, Regret: 0.0009, Entropy: 0.0957 +[2026-03-20T19:05:59.042527Z] Loop 7149: Loss: 1.80e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0978 +[2026-03-20T19:05:59.938740Z] Loop 7150: Loss: 1.64e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.0915 +[2026-03-20T19:06:00.794480Z] Loop 7151: Loss: 1.64e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.0883 +[2026-03-20T19:06:01.649019Z] Loop 7152: Loss: 1.41e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.0818 +[2026-03-20T19:06:02.504968Z] Loop 7153: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0024, Entropy: 0.0849 +[2026-03-20T19:06:03.360956Z] Loop 7154: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0024, Entropy: 0.0742 +[2026-03-20T19:06:04.216291Z] Loop 7155: Loss: 1.44e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.0781 +[2026-03-20T19:06:05.073518Z] Loop 7156: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0024, Entropy: 0.0772 +[2026-03-20T19:06:05.929207Z] Loop 7157: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0024, Entropy: 0.0797 +[2026-03-20T19:06:06.785442Z] Loop 7158: Loss: 1.39e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.0753 +[2026-03-20T19:06:07.641767Z] Loop 7159: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0024, Entropy: 0.0847 +[2026-03-20T19:06:08.538437Z] Loop 7160: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0789 +[2026-03-20T19:06:09.394054Z] Loop 7161: Loss: 1.41e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0799 +[2026-03-20T19:06:10.248840Z] Loop 7162: Loss: 1.50e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0830 +[2026-03-20T19:06:11.104256Z] Loop 7163: Loss: 1.65e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0866 +[2026-03-20T19:06:11.959671Z] Loop 7164: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0861 +[2026-03-20T19:06:12.815502Z] Loop 7165: Loss: 1.57e-02, Avg Return: 0.860, Regret: 0.0012, Entropy: 0.0874 +[2026-03-20T19:06:13.670642Z] Loop 7166: Loss: 1.48e-02, Avg Return: 0.860, Regret: 0.0012, Entropy: 0.0817 +[2026-03-20T19:06:14.526860Z] Loop 7167: Loss: 1.40e-02, Avg Return: 0.860, Regret: 0.0012, Entropy: 0.0801 +[2026-03-20T19:06:15.381657Z] Loop 7168: Loss: 1.58e-02, Avg Return: 0.860, Regret: 0.0012, Entropy: 0.0828 +[2026-03-20T19:06:16.237645Z] Loop 7169: Loss: 1.49e-02, Avg Return: 0.860, Regret: 0.0012, Entropy: 0.0871 +[2026-03-20T19:06:17.132950Z] Loop 7170: Loss: 1.45e-02, Avg Return: 0.860, Regret: 0.0032, Entropy: 0.0835 +[2026-03-20T19:06:17.988020Z] Loop 7171: Loss: 1.63e-02, Avg Return: 0.862, Regret: 0.0032, Entropy: 0.0886 +[2026-03-20T19:06:18.844188Z] Loop 7172: Loss: 1.62e-02, Avg Return: 0.861, Regret: 0.0032, Entropy: 0.0911 +[2026-03-20T19:06:19.699804Z] Loop 7173: Loss: 1.43e-02, Avg Return: 0.861, Regret: 0.0032, Entropy: 0.0837 +[2026-03-20T19:06:20.555714Z] Loop 7174: Loss: 1.51e-02, Avg Return: 0.861, Regret: 0.0032, Entropy: 0.0856 +[2026-03-20T19:06:21.411530Z] Loop 7175: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0032, Entropy: 0.0808 +[2026-03-20T19:06:22.267468Z] Loop 7176: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0032, Entropy: 0.0791 +[2026-03-20T19:06:23.124156Z] Loop 7177: Loss: 1.42e-02, Avg Return: 0.862, Regret: 0.0032, Entropy: 0.0853 +[2026-03-20T19:06:23.981469Z] Loop 7178: Loss: 1.46e-02, Avg Return: 0.861, Regret: 0.0032, Entropy: 0.0788 +[2026-03-20T19:06:24.836922Z] Loop 7179: Loss: 1.49e-02, Avg Return: 0.860, Regret: 0.0032, Entropy: 0.0818 +[2026-03-20T19:06:25.731530Z] Loop 7180: Loss: 1.44e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0768 +[2026-03-20T19:06:26.586906Z] Loop 7181: Loss: 1.43e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.0811 +[2026-03-20T19:06:27.443492Z] Loop 7182: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0808 +[2026-03-20T19:06:28.298995Z] Loop 7183: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0858 +[2026-03-20T19:06:29.154261Z] Loop 7184: Loss: 1.60e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.0849 +[2026-03-20T19:06:30.010235Z] Loop 7185: Loss: 1.58e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.0913 +[2026-03-20T19:06:30.867463Z] Loop 7186: Loss: 1.74e-02, Avg Return: 0.859, Regret: 0.0020, Entropy: 0.0947 +[2026-03-20T19:06:31.722381Z] Loop 7187: Loss: 2.02e-02, Avg Return: 0.856, Regret: 0.0020, Entropy: 0.1051 +[2026-03-20T19:06:32.577975Z] Loop 7188: Loss: 2.15e-02, Avg Return: 0.853, Regret: 0.0020, Entropy: 0.1139 +[2026-03-20T19:06:33.432481Z] Loop 7189: Loss: 2.28e-02, Avg Return: 0.853, Regret: 0.0020, Entropy: 0.1178 +[2026-03-20T19:06:34.328312Z] Loop 7190: Loss: 2.02e-02, Avg Return: 0.856, Regret: 0.0089, Entropy: 0.1091 +[2026-03-20T19:06:35.182632Z] Loop 7191: Loss: 1.86e-02, Avg Return: 0.857, Regret: 0.0089, Entropy: 0.1017 +[2026-03-20T19:06:36.037865Z] Loop 7192: Loss: 1.74e-02, Avg Return: 0.861, Regret: 0.0089, Entropy: 0.0906 +[2026-03-20T19:06:36.893009Z] Loop 7193: Loss: 1.56e-02, Avg Return: 0.861, Regret: 0.0089, Entropy: 0.0856 +[2026-03-20T19:06:37.749764Z] Loop 7194: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0089, Entropy: 0.0899 +[2026-03-20T19:06:38.605367Z] Loop 7195: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0089, Entropy: 0.0855 +[2026-03-20T19:06:39.460384Z] Loop 7196: Loss: 1.33e-02, Avg Return: 0.862, Regret: 0.0089, Entropy: 0.0787 +[2026-03-20T19:06:40.315060Z] Loop 7197: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0089, Entropy: 0.0841 +[2026-03-20T19:06:41.170088Z] Loop 7198: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0089, Entropy: 0.0851 +[2026-03-20T19:06:42.025281Z] Loop 7199: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0089, Entropy: 0.0860 +[2026-03-20T19:06:42.921159Z] Loop 7200: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0898 +[2026-03-20T19:06:43.777161Z] Loop 7201: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0858 +[2026-03-20T19:06:44.633731Z] Loop 7202: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0852 +[2026-03-20T19:06:45.489080Z] Loop 7203: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0863 +[2026-03-20T19:06:46.344144Z] Loop 7204: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0915 +[2026-03-20T19:06:47.199749Z] Loop 7205: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0889 +[2026-03-20T19:06:48.056061Z] Loop 7206: Loss: 1.69e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0948 +[2026-03-20T19:06:48.910791Z] Loop 7207: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0848 +[2026-03-20T19:06:49.764869Z] Loop 7208: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0882 +[2026-03-20T19:06:50.621123Z] Loop 7209: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0869 +[2026-03-20T19:06:51.516981Z] Loop 7210: Loss: 1.46e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0828 +[2026-03-20T19:06:52.373259Z] Loop 7211: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0891 +[2026-03-20T19:06:53.228962Z] Loop 7212: Loss: 1.45e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0852 +[2026-03-20T19:06:54.083861Z] Loop 7213: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0818 +[2026-03-20T19:06:54.941482Z] Loop 7214: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0855 +[2026-03-20T19:06:55.798301Z] Loop 7215: Loss: 1.59e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0853 +[2026-03-20T19:06:56.653996Z] Loop 7216: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0897 +[2026-03-20T19:06:57.510797Z] Loop 7217: Loss: 1.58e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0863 +[2026-03-20T19:06:58.368709Z] Loop 7218: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0886 +[2026-03-20T19:06:59.226116Z] Loop 7219: Loss: 1.63e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0858 +[2026-03-20T19:07:00.123309Z] Loop 7220: Loss: 1.56e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.0872 +[2026-03-20T19:07:00.979933Z] Loop 7221: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.0832 +[2026-03-20T19:07:01.835214Z] Loop 7222: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.0848 +[2026-03-20T19:07:02.689931Z] Loop 7223: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.0891 +[2026-03-20T19:07:03.545022Z] Loop 7224: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.0846 +[2026-03-20T19:07:04.401153Z] Loop 7225: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.0919 +[2026-03-20T19:07:05.256415Z] Loop 7226: Loss: 1.62e-02, Avg Return: 0.859, Regret: 0.0028, Entropy: 0.0913 +[2026-03-20T19:07:06.113019Z] Loop 7227: Loss: 1.62e-02, Avg Return: 0.859, Regret: 0.0028, Entropy: 0.0898 +[2026-03-20T19:07:06.968447Z] Loop 7228: Loss: 1.68e-02, Avg Return: 0.858, Regret: 0.0028, Entropy: 0.0916 +[2026-03-20T19:07:07.825593Z] Loop 7229: Loss: 1.57e-02, Avg Return: 0.856, Regret: 0.0028, Entropy: 0.0941 +[2026-03-20T19:07:08.722250Z] Loop 7230: Loss: 1.57e-02, Avg Return: 0.857, Regret: 0.0064, Entropy: 0.0943 +[2026-03-20T19:07:09.576952Z] Loop 7231: Loss: 1.63e-02, Avg Return: 0.858, Regret: 0.0064, Entropy: 0.0948 +[2026-03-20T19:07:10.432742Z] Loop 7232: Loss: 1.55e-02, Avg Return: 0.859, Regret: 0.0064, Entropy: 0.0869 +[2026-03-20T19:07:11.290169Z] Loop 7233: Loss: 1.72e-02, Avg Return: 0.859, Regret: 0.0064, Entropy: 0.0980 +[2026-03-20T19:07:12.145116Z] Loop 7234: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0064, Entropy: 0.0886 +[2026-03-20T19:07:12.999679Z] Loop 7235: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0064, Entropy: 0.0886 +[2026-03-20T19:07:13.854224Z] Loop 7236: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0064, Entropy: 0.0904 +[2026-03-20T19:07:14.709534Z] Loop 7237: Loss: 1.56e-02, Avg Return: 0.861, Regret: 0.0064, Entropy: 0.0876 +[2026-03-20T19:07:15.565670Z] Loop 7238: Loss: 1.67e-02, Avg Return: 0.862, Regret: 0.0064, Entropy: 0.0921 +[2026-03-20T19:07:16.420281Z] Loop 7239: Loss: 1.70e-02, Avg Return: 0.862, Regret: 0.0064, Entropy: 0.0917 +[2026-03-20T19:07:17.316269Z] Loop 7240: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0917 +[2026-03-20T19:07:18.172298Z] Loop 7241: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0911 +[2026-03-20T19:07:19.027613Z] Loop 7242: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0932 +[2026-03-20T19:07:19.882961Z] Loop 7243: Loss: 1.63e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0940 +[2026-03-20T19:07:20.738205Z] Loop 7244: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0951 +[2026-03-20T19:07:21.593142Z] Loop 7245: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0935 +[2026-03-20T19:07:22.448997Z] Loop 7246: Loss: 1.66e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0953 +[2026-03-20T19:07:23.304404Z] Loop 7247: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0910 +[2026-03-20T19:07:24.159532Z] Loop 7248: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0969 +[2026-03-20T19:07:25.016486Z] Loop 7249: Loss: 1.52e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0869 +[2026-03-20T19:07:25.912184Z] Loop 7250: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0866 +[2026-03-20T19:07:26.767566Z] Loop 7251: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0892 +[2026-03-20T19:07:27.623206Z] Loop 7252: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0856 +[2026-03-20T19:07:28.477746Z] Loop 7253: Loss: 1.42e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0843 +[2026-03-20T19:07:29.333326Z] Loop 7254: Loss: 1.53e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0849 +[2026-03-20T19:07:30.189695Z] Loop 7255: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0913 +[2026-03-20T19:07:31.044382Z] Loop 7256: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0871 +[2026-03-20T19:07:31.899613Z] Loop 7257: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0849 +[2026-03-20T19:07:32.755833Z] Loop 7258: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0840 +[2026-03-20T19:07:33.611371Z] Loop 7259: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0849 +[2026-03-20T19:07:34.507546Z] Loop 7260: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0845 +[2026-03-20T19:07:35.362747Z] Loop 7261: Loss: 1.46e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0813 +[2026-03-20T19:07:36.217988Z] Loop 7262: Loss: 1.47e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0833 +[2026-03-20T19:07:37.072910Z] Loop 7263: Loss: 1.61e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0882 +[2026-03-20T19:07:37.928357Z] Loop 7264: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0796 +[2026-03-20T19:07:38.783826Z] Loop 7265: Loss: 1.49e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0833 +[2026-03-20T19:07:39.639390Z] Loop 7266: Loss: 1.49e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0810 +[2026-03-20T19:07:40.494534Z] Loop 7267: Loss: 1.45e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0847 +[2026-03-20T19:07:41.351471Z] Loop 7268: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0791 +[2026-03-20T19:07:42.208113Z] Loop 7269: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0802 +[2026-03-20T19:07:43.105021Z] Loop 7270: Loss: 1.52e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0824 +[2026-03-20T19:07:43.959661Z] Loop 7271: Loss: 1.40e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0803 +[2026-03-20T19:07:44.814435Z] Loop 7272: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0771 +[2026-03-20T19:07:45.670844Z] Loop 7273: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0813 +[2026-03-20T19:07:46.526962Z] Loop 7274: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0800 +[2026-03-20T19:07:47.381533Z] Loop 7275: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0768 +[2026-03-20T19:07:48.235526Z] Loop 7276: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0825 +[2026-03-20T19:07:49.090678Z] Loop 7277: Loss: 1.56e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0812 +[2026-03-20T19:07:49.945942Z] Loop 7278: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0771 +[2026-03-20T19:07:50.800971Z] Loop 7279: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0831 +[2026-03-20T19:07:51.695947Z] Loop 7280: Loss: 1.44e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0789 +[2026-03-20T19:07:52.552204Z] Loop 7281: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0787 +[2026-03-20T19:07:53.407214Z] Loop 7282: Loss: 1.39e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0759 +[2026-03-20T19:07:54.262962Z] Loop 7283: Loss: 1.28e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0751 +[2026-03-20T19:07:55.118203Z] Loop 7284: Loss: 1.39e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0751 +[2026-03-20T19:07:55.972607Z] Loop 7285: Loss: 1.54e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0798 +[2026-03-20T19:07:56.827398Z] Loop 7286: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0810 +[2026-03-20T19:07:57.683662Z] Loop 7287: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0797 +[2026-03-20T19:07:58.539200Z] Loop 7288: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0820 +[2026-03-20T19:07:59.393699Z] Loop 7289: Loss: 1.48e-02, Avg Return: 0.860, Regret: 0.0013, Entropy: 0.0835 +[2026-03-20T19:08:00.289980Z] Loop 7290: Loss: 1.52e-02, Avg Return: 0.862, Regret: 0.0029, Entropy: 0.0829 +[2026-03-20T19:08:01.145778Z] Loop 7291: Loss: 1.51e-02, Avg Return: 0.859, Regret: 0.0029, Entropy: 0.0840 +[2026-03-20T19:08:02.002026Z] Loop 7292: Loss: 1.58e-02, Avg Return: 0.860, Regret: 0.0029, Entropy: 0.0849 +[2026-03-20T19:08:02.857548Z] Loop 7293: Loss: 1.46e-02, Avg Return: 0.859, Regret: 0.0029, Entropy: 0.0780 +[2026-03-20T19:08:03.711460Z] Loop 7294: Loss: 1.43e-02, Avg Return: 0.862, Regret: 0.0029, Entropy: 0.0802 +[2026-03-20T19:08:04.565406Z] Loop 7295: Loss: 1.44e-02, Avg Return: 0.861, Regret: 0.0029, Entropy: 0.0779 +[2026-03-20T19:08:05.421209Z] Loop 7296: Loss: 1.50e-02, Avg Return: 0.862, Regret: 0.0029, Entropy: 0.0802 +[2026-03-20T19:08:06.276519Z] Loop 7297: Loss: 1.43e-02, Avg Return: 0.861, Regret: 0.0029, Entropy: 0.0773 +[2026-03-20T19:08:07.131147Z] Loop 7298: Loss: 1.44e-02, Avg Return: 0.860, Regret: 0.0029, Entropy: 0.0808 +[2026-03-20T19:08:07.986423Z] Loop 7299: Loss: 1.48e-02, Avg Return: 0.861, Regret: 0.0029, Entropy: 0.0804 +[2026-03-20T19:08:08.880970Z] Loop 7300: Loss: 1.63e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.0839 +[2026-03-20T19:08:09.736622Z] Loop 7301: Loss: 1.51e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.0825 +[2026-03-20T19:08:10.592353Z] Loop 7302: Loss: 1.47e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.0827 +[2026-03-20T19:08:11.447528Z] Loop 7303: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.0765 +[2026-03-20T19:08:12.302724Z] Loop 7304: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.0743 +[2026-03-20T19:08:13.158838Z] Loop 7305: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.0780 +[2026-03-20T19:08:14.014434Z] Loop 7306: Loss: 1.32e-02, Avg Return: 0.864, Regret: 0.0020, Entropy: 0.0747 +[2026-03-20T19:08:14.869876Z] Loop 7307: Loss: 1.35e-02, Avg Return: 0.864, Regret: 0.0020, Entropy: 0.0748 +[2026-03-20T19:08:15.725503Z] Loop 7308: Loss: 1.38e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.0740 +[2026-03-20T19:08:16.580941Z] Loop 7309: Loss: 1.40e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.0784 +[2026-03-20T19:08:17.476619Z] Loop 7310: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0811 +[2026-03-20T19:08:18.332854Z] Loop 7311: Loss: 1.50e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0802 +[2026-03-20T19:08:19.188521Z] Loop 7312: Loss: 1.64e-02, Avg Return: 0.860, Regret: 0.0011, Entropy: 0.0837 +[2026-03-20T19:08:20.043762Z] Loop 7313: Loss: 1.61e-02, Avg Return: 0.857, Regret: 0.0011, Entropy: 0.0823 +[2026-03-20T19:08:20.898973Z] Loop 7314: Loss: 1.50e-02, Avg Return: 0.856, Regret: 0.0011, Entropy: 0.0829 +[2026-03-20T19:08:21.755405Z] Loop 7315: Loss: 1.58e-02, Avg Return: 0.856, Regret: 0.0011, Entropy: 0.0861 +[2026-03-20T19:08:22.610219Z] Loop 7316: Loss: 1.57e-02, Avg Return: 0.857, Regret: 0.0011, Entropy: 0.0801 +[2026-03-20T19:08:23.465131Z] Loop 7317: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0781 +[2026-03-20T19:08:24.321163Z] Loop 7318: Loss: 1.43e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0791 +[2026-03-20T19:08:25.177480Z] Loop 7319: Loss: 1.35e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0778 +[2026-03-20T19:08:26.073604Z] Loop 7320: Loss: 1.38e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0739 +[2026-03-20T19:08:26.928095Z] Loop 7321: Loss: 1.40e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0758 +[2026-03-20T19:08:27.782732Z] Loop 7322: Loss: 1.33e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0741 +[2026-03-20T19:08:28.638188Z] Loop 7323: Loss: 1.42e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0765 +[2026-03-20T19:08:29.494928Z] Loop 7324: Loss: 1.32e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0721 +[2026-03-20T19:08:30.350393Z] Loop 7325: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0733 +[2026-03-20T19:08:31.204795Z] Loop 7326: Loss: 1.36e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0740 +[2026-03-20T19:08:32.060217Z] Loop 7327: Loss: 1.45e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0773 +[2026-03-20T19:08:32.915810Z] Loop 7328: Loss: 1.47e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0815 +[2026-03-20T19:08:33.770774Z] Loop 7329: Loss: 1.43e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0789 +[2026-03-20T19:08:34.666278Z] Loop 7330: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0800 +[2026-03-20T19:08:35.522755Z] Loop 7331: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0832 +[2026-03-20T19:08:36.379104Z] Loop 7332: Loss: 1.42e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0830 +[2026-03-20T19:08:37.235337Z] Loop 7333: Loss: 1.45e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0834 +[2026-03-20T19:08:38.090869Z] Loop 7334: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0853 +[2026-03-20T19:08:38.948255Z] Loop 7335: Loss: 1.34e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0798 +[2026-03-20T19:08:39.804011Z] Loop 7336: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0819 +[2026-03-20T19:08:40.660627Z] Loop 7337: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0780 +[2026-03-20T19:08:41.516416Z] Loop 7338: Loss: 1.43e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0796 +[2026-03-20T19:08:42.372387Z] Loop 7339: Loss: 1.36e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0760 +[2026-03-20T19:08:43.268829Z] Loop 7340: Loss: 1.47e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0820 +[2026-03-20T19:08:44.123868Z] Loop 7341: Loss: 1.46e-02, Avg Return: 0.865, Regret: 0.0005, Entropy: 0.0766 +[2026-03-20T19:08:44.979959Z] Loop 7342: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0744 +[2026-03-20T19:08:45.836652Z] Loop 7343: Loss: 1.49e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0802 +[2026-03-20T19:08:46.691525Z] Loop 7344: Loss: 1.50e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0820 +[2026-03-20T19:08:47.546872Z] Loop 7345: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0812 +[2026-03-20T19:08:48.402783Z] Loop 7346: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0823 +[2026-03-20T19:08:49.259084Z] Loop 7347: Loss: 1.47e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0816 +[2026-03-20T19:08:50.114922Z] Loop 7348: Loss: 1.52e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0818 +[2026-03-20T19:08:50.970033Z] Loop 7349: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0872 +[2026-03-20T19:08:51.864965Z] Loop 7350: Loss: 1.68e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0866 +[2026-03-20T19:08:52.721588Z] Loop 7351: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0866 +[2026-03-20T19:08:53.577398Z] Loop 7352: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0872 +[2026-03-20T19:08:54.431965Z] Loop 7353: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0855 +[2026-03-20T19:08:55.287000Z] Loop 7354: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0833 +[2026-03-20T19:08:56.142266Z] Loop 7355: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0812 +[2026-03-20T19:08:56.997581Z] Loop 7356: Loss: 1.42e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0776 +[2026-03-20T19:08:57.853846Z] Loop 7357: Loss: 1.36e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0753 +[2026-03-20T19:08:58.709258Z] Loop 7358: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0799 +[2026-03-20T19:08:59.563849Z] Loop 7359: Loss: 1.40e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0776 +[2026-03-20T19:09:00.459943Z] Loop 7360: Loss: 1.41e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0779 +[2026-03-20T19:09:01.314693Z] Loop 7361: Loss: 1.45e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0795 +[2026-03-20T19:09:02.170855Z] Loop 7362: Loss: 1.37e-02, Avg Return: 0.860, Regret: 0.0018, Entropy: 0.0718 +[2026-03-20T19:09:03.026130Z] Loop 7363: Loss: 1.44e-02, Avg Return: 0.860, Regret: 0.0018, Entropy: 0.0780 +[2026-03-20T19:09:03.880692Z] Loop 7364: Loss: 1.34e-02, Avg Return: 0.860, Regret: 0.0018, Entropy: 0.0759 +[2026-03-20T19:09:04.736164Z] Loop 7365: Loss: 1.39e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0763 +[2026-03-20T19:09:05.591963Z] Loop 7366: Loss: 1.39e-02, Avg Return: 0.860, Regret: 0.0018, Entropy: 0.0748 +[2026-03-20T19:09:06.446320Z] Loop 7367: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0783 +[2026-03-20T19:09:07.302309Z] Loop 7368: Loss: 1.34e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0729 +[2026-03-20T19:09:08.160244Z] Loop 7369: Loss: 1.40e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0725 +[2026-03-20T19:09:09.057970Z] Loop 7370: Loss: 1.31e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0736 +[2026-03-20T19:09:09.914469Z] Loop 7371: Loss: 1.41e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0776 +[2026-03-20T19:09:10.770689Z] Loop 7372: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0741 +[2026-03-20T19:09:11.625875Z] Loop 7373: Loss: 1.33e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0711 +[2026-03-20T19:09:12.481067Z] Loop 7374: Loss: 1.32e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0725 +[2026-03-20T19:09:13.335768Z] Loop 7375: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0726 +[2026-03-20T19:09:14.189967Z] Loop 7376: Loss: 1.40e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0730 +[2026-03-20T19:09:15.044998Z] Loop 7377: Loss: 1.30e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0718 +[2026-03-20T19:09:15.900925Z] Loop 7378: Loss: 1.41e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0728 +[2026-03-20T19:09:16.756302Z] Loop 7379: Loss: 1.23e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0695 +[2026-03-20T19:09:17.653458Z] Loop 7380: Loss: 1.27e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0677 +[2026-03-20T19:09:18.508729Z] Loop 7381: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0719 +[2026-03-20T19:09:19.364756Z] Loop 7382: Loss: 1.29e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0710 +[2026-03-20T19:09:20.219489Z] Loop 7383: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0707 +[2026-03-20T19:09:21.074774Z] Loop 7384: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0730 +[2026-03-20T19:09:21.929955Z] Loop 7385: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0709 +[2026-03-20T19:09:22.785551Z] Loop 7386: Loss: 1.37e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0748 +[2026-03-20T19:09:23.641035Z] Loop 7387: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0771 +[2026-03-20T19:09:24.495986Z] Loop 7388: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0774 +[2026-03-20T19:09:25.351299Z] Loop 7389: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0794 +[2026-03-20T19:09:26.247026Z] Loop 7390: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0800 +[2026-03-20T19:09:27.102813Z] Loop 7391: Loss: 1.57e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0856 +[2026-03-20T19:09:27.958076Z] Loop 7392: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0862 +[2026-03-20T19:09:28.813926Z] Loop 7393: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0874 +[2026-03-20T19:09:29.669170Z] Loop 7394: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0943 +[2026-03-20T19:09:30.523456Z] Loop 7395: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0924 +[2026-03-20T19:09:31.378924Z] Loop 7396: Loss: 1.79e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0950 +[2026-03-20T19:09:32.235351Z] Loop 7397: Loss: 1.79e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0994 +[2026-03-20T19:09:33.091324Z] Loop 7398: Loss: 1.70e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0940 +[2026-03-20T19:09:33.946656Z] Loop 7399: Loss: 1.69e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0949 +[2026-03-20T19:09:34.842140Z] Loop 7400: Loss: 1.75e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.0989 +[2026-03-20T19:09:35.698230Z] Loop 7401: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0945 +[2026-03-20T19:09:36.553740Z] Loop 7402: Loss: 1.70e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0937 +[2026-03-20T19:09:37.408612Z] Loop 7403: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0932 +[2026-03-20T19:09:38.262900Z] Loop 7404: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.0899 +[2026-03-20T19:09:39.118732Z] Loop 7405: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0908 +[2026-03-20T19:09:39.975245Z] Loop 7406: Loss: 1.58e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.0906 +[2026-03-20T19:09:40.830085Z] Loop 7407: Loss: 1.52e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0853 +[2026-03-20T19:09:41.685200Z] Loop 7408: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0871 +[2026-03-20T19:09:42.541335Z] Loop 7409: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0991 +[2026-03-20T19:09:43.437453Z] Loop 7410: Loss: 1.70e-02, Avg Return: 0.860, Regret: 0.0021, Entropy: 0.0905 +[2026-03-20T19:09:44.292969Z] Loop 7411: Loss: 1.75e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.0965 +[2026-03-20T19:09:45.147960Z] Loop 7412: Loss: 1.65e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.0906 +[2026-03-20T19:09:46.003895Z] Loop 7413: Loss: 1.64e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.0907 +[2026-03-20T19:09:46.859440Z] Loop 7414: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.0925 +[2026-03-20T19:09:47.714663Z] Loop 7415: Loss: 1.59e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.0905 +[2026-03-20T19:09:48.569840Z] Loop 7416: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.0872 +[2026-03-20T19:09:49.424667Z] Loop 7417: Loss: 1.50e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.0865 +[2026-03-20T19:09:50.279541Z] Loop 7418: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.0871 +[2026-03-20T19:09:51.135773Z] Loop 7419: Loss: 1.66e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.0922 +[2026-03-20T19:09:52.032661Z] Loop 7420: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0864 +[2026-03-20T19:09:52.889083Z] Loop 7421: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0849 +[2026-03-20T19:09:53.744693Z] Loop 7422: Loss: 1.54e-02, Avg Return: 0.865, Regret: 0.0010, Entropy: 0.0817 +[2026-03-20T19:09:54.600463Z] Loop 7423: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0821 +[2026-03-20T19:09:55.456133Z] Loop 7424: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0798 +[2026-03-20T19:09:56.311197Z] Loop 7425: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0808 +[2026-03-20T19:09:57.166267Z] Loop 7426: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0828 +[2026-03-20T19:09:58.021949Z] Loop 7427: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0819 +[2026-03-20T19:09:58.878431Z] Loop 7428: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0892 +[2026-03-20T19:09:59.733518Z] Loop 7429: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0862 +[2026-03-20T19:10:00.630454Z] Loop 7430: Loss: 1.52e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0851 +[2026-03-20T19:10:01.485628Z] Loop 7431: Loss: 1.59e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0862 +[2026-03-20T19:10:02.344681Z] Loop 7432: Loss: 1.63e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0917 +[2026-03-20T19:10:03.200275Z] Loop 7433: Loss: 1.62e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0916 +[2026-03-20T19:10:04.056460Z] Loop 7434: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0889 +[2026-03-20T19:10:04.912036Z] Loop 7435: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0886 +[2026-03-20T19:10:05.768111Z] Loop 7436: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0843 +[2026-03-20T19:10:06.623390Z] Loop 7437: Loss: 1.55e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0856 +[2026-03-20T19:10:07.480242Z] Loop 7438: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0805 +[2026-03-20T19:10:08.335501Z] Loop 7439: Loss: 1.40e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0794 +[2026-03-20T19:10:09.233208Z] Loop 7440: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0827 +[2026-03-20T19:10:10.088305Z] Loop 7441: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0826 +[2026-03-20T19:10:10.943791Z] Loop 7442: Loss: 1.42e-02, Avg Return: 0.864, Regret: 0.0013, Entropy: 0.0790 +[2026-03-20T19:10:11.799881Z] Loop 7443: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0841 +[2026-03-20T19:10:12.656337Z] Loop 7444: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0777 +[2026-03-20T19:10:13.512275Z] Loop 7445: Loss: 1.62e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0895 +[2026-03-20T19:10:14.368649Z] Loop 7446: Loss: 1.56e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0907 +[2026-03-20T19:10:15.224948Z] Loop 7447: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0909 +[2026-03-20T19:10:16.082046Z] Loop 7448: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0911 +[2026-03-20T19:10:16.937694Z] Loop 7449: Loss: 1.43e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0801 +[2026-03-20T19:10:17.833786Z] Loop 7450: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0836 +[2026-03-20T19:10:18.690647Z] Loop 7451: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0825 +[2026-03-20T19:10:19.546590Z] Loop 7452: Loss: 1.51e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0844 +[2026-03-20T19:10:20.401330Z] Loop 7453: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0858 +[2026-03-20T19:10:21.256840Z] Loop 7454: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0833 +[2026-03-20T19:10:22.113961Z] Loop 7455: Loss: 1.60e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0879 +[2026-03-20T19:10:22.970975Z] Loop 7456: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0906 +[2026-03-20T19:10:23.827408Z] Loop 7457: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0895 +[2026-03-20T19:10:24.682710Z] Loop 7458: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0829 +[2026-03-20T19:10:25.538916Z] Loop 7459: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0753 +[2026-03-20T19:10:26.437045Z] Loop 7460: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0784 +[2026-03-20T19:10:27.293076Z] Loop 7461: Loss: 1.43e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0821 +[2026-03-20T19:10:28.148416Z] Loop 7462: Loss: 1.36e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0781 +[2026-03-20T19:10:29.004138Z] Loop 7463: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0788 +[2026-03-20T19:10:29.861786Z] Loop 7464: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0796 +[2026-03-20T19:10:30.717370Z] Loop 7465: Loss: 1.34e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0771 +[2026-03-20T19:10:31.574953Z] Loop 7466: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0767 +[2026-03-20T19:10:32.430865Z] Loop 7467: Loss: 1.52e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0828 +[2026-03-20T19:10:33.287225Z] Loop 7468: Loss: 1.46e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0834 +[2026-03-20T19:10:34.142902Z] Loop 7469: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0805 +[2026-03-20T19:10:35.042074Z] Loop 7470: Loss: 1.49e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0809 +[2026-03-20T19:10:35.897461Z] Loop 7471: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0786 +[2026-03-20T19:10:36.753487Z] Loop 7472: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0778 +[2026-03-20T19:10:37.609269Z] Loop 7473: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0747 +[2026-03-20T19:10:38.465687Z] Loop 7474: Loss: 1.43e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0784 +[2026-03-20T19:10:39.321834Z] Loop 7475: Loss: 1.32e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0752 +[2026-03-20T19:10:40.177580Z] Loop 7476: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0807 +[2026-03-20T19:10:41.032321Z] Loop 7477: Loss: 1.33e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0750 +[2026-03-20T19:10:41.887911Z] Loop 7478: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0798 +[2026-03-20T19:10:42.743409Z] Loop 7479: Loss: 1.50e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0816 +[2026-03-20T19:10:43.638211Z] Loop 7480: Loss: 1.47e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0801 +[2026-03-20T19:10:44.493300Z] Loop 7481: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0886 +[2026-03-20T19:10:45.348948Z] Loop 7482: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0881 +[2026-03-20T19:10:46.205382Z] Loop 7483: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0912 +[2026-03-20T19:10:47.062452Z] Loop 7484: Loss: 1.81e-02, Avg Return: 0.860, Regret: 0.0010, Entropy: 0.0971 +[2026-03-20T19:10:47.918259Z] Loop 7485: Loss: 1.84e-02, Avg Return: 0.859, Regret: 0.0010, Entropy: 0.1022 +[2026-03-20T19:10:48.772747Z] Loop 7486: Loss: 1.79e-02, Avg Return: 0.859, Regret: 0.0010, Entropy: 0.0982 +[2026-03-20T19:10:49.628385Z] Loop 7487: Loss: 1.68e-02, Avg Return: 0.859, Regret: 0.0010, Entropy: 0.0966 +[2026-03-20T19:10:50.484566Z] Loop 7488: Loss: 1.75e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0995 +[2026-03-20T19:10:51.339819Z] Loop 7489: Loss: 1.49e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0911 +[2026-03-20T19:10:52.234607Z] Loop 7490: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0929 +[2026-03-20T19:10:53.091411Z] Loop 7491: Loss: 1.46e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0830 +[2026-03-20T19:10:53.947515Z] Loop 7492: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0841 +[2026-03-20T19:10:54.802498Z] Loop 7493: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0822 +[2026-03-20T19:10:55.657812Z] Loop 7494: Loss: 1.50e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0851 +[2026-03-20T19:10:56.513102Z] Loop 7495: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0864 +[2026-03-20T19:10:57.369121Z] Loop 7496: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0867 +[2026-03-20T19:10:58.224829Z] Loop 7497: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0874 +[2026-03-20T19:10:59.081429Z] Loop 7498: Loss: 1.60e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0900 +[2026-03-20T19:10:59.937282Z] Loop 7499: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0879 +[2026-03-20T19:11:00.834375Z] Loop 7500: Loss: 1.58e-02, Avg Return: 0.864, Regret: 0.0015, Entropy: 0.0868 +[2026-03-20T19:11:01.691095Z] Loop 7501: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0870 +[2026-03-20T19:11:02.546840Z] Loop 7502: Loss: 1.60e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.0899 +[2026-03-20T19:11:03.403491Z] Loop 7503: Loss: 1.53e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.0883 +[2026-03-20T19:11:04.260185Z] Loop 7504: Loss: 1.61e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.0928 +[2026-03-20T19:11:05.115371Z] Loop 7505: Loss: 1.90e-02, Avg Return: 0.860, Regret: 0.0015, Entropy: 0.1056 +[2026-03-20T19:11:05.970877Z] Loop 7506: Loss: 2.33e-02, Avg Return: 0.857, Regret: 0.0015, Entropy: 0.1187 +[2026-03-20T19:11:06.826227Z] Loop 7507: Loss: 2.35e-02, Avg Return: 0.855, Regret: 0.0015, Entropy: 0.1214 +[2026-03-20T19:11:07.680641Z] Loop 7508: Loss: 2.02e-02, Avg Return: 0.860, Regret: 0.0015, Entropy: 0.1092 +[2026-03-20T19:11:08.535964Z] Loop 7509: Loss: 1.86e-02, Avg Return: 0.859, Regret: 0.0015, Entropy: 0.1009 +[2026-03-20T19:11:09.432067Z] Loop 7510: Loss: 1.68e-02, Avg Return: 0.861, Regret: 0.0030, Entropy: 0.0957 +[2026-03-20T19:11:10.288126Z] Loop 7511: Loss: 1.79e-02, Avg Return: 0.861, Regret: 0.0030, Entropy: 0.1004 +[2026-03-20T19:11:11.143489Z] Loop 7512: Loss: 1.63e-02, Avg Return: 0.861, Regret: 0.0030, Entropy: 0.0961 +[2026-03-20T19:11:11.998506Z] Loop 7513: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0030, Entropy: 0.0945 +[2026-03-20T19:11:12.853762Z] Loop 7514: Loss: 1.57e-02, Avg Return: 0.861, Regret: 0.0030, Entropy: 0.0930 +[2026-03-20T19:11:13.710078Z] Loop 7515: Loss: 1.62e-02, Avg Return: 0.860, Regret: 0.0030, Entropy: 0.0918 +[2026-03-20T19:11:14.565049Z] Loop 7516: Loss: 1.52e-02, Avg Return: 0.862, Regret: 0.0030, Entropy: 0.0891 +[2026-03-20T19:11:15.419685Z] Loop 7517: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0030, Entropy: 0.0863 +[2026-03-20T19:11:16.275057Z] Loop 7518: Loss: 1.38e-02, Avg Return: 0.862, Regret: 0.0030, Entropy: 0.0815 +[2026-03-20T19:11:17.130602Z] Loop 7519: Loss: 1.48e-02, Avg Return: 0.861, Regret: 0.0030, Entropy: 0.0834 +[2026-03-20T19:11:18.027261Z] Loop 7520: Loss: 1.52e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0870 +[2026-03-20T19:11:18.882419Z] Loop 7521: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0840 +[2026-03-20T19:11:19.736677Z] Loop 7522: Loss: 1.54e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0843 +[2026-03-20T19:11:20.591122Z] Loop 7523: Loss: 1.53e-02, Avg Return: 0.860, Regret: 0.0016, Entropy: 0.0827 +[2026-03-20T19:11:21.446790Z] Loop 7524: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0858 +[2026-03-20T19:11:22.301935Z] Loop 7525: Loss: 1.51e-02, Avg Return: 0.860, Regret: 0.0016, Entropy: 0.0846 +[2026-03-20T19:11:23.156668Z] Loop 7526: Loss: 1.55e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0830 +[2026-03-20T19:11:24.012535Z] Loop 7527: Loss: 1.47e-02, Avg Return: 0.860, Regret: 0.0016, Entropy: 0.0811 +[2026-03-20T19:11:24.868095Z] Loop 7528: Loss: 1.55e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0870 +[2026-03-20T19:11:25.724069Z] Loop 7529: Loss: 1.54e-02, Avg Return: 0.860, Regret: 0.0016, Entropy: 0.0862 +[2026-03-20T19:11:26.620075Z] Loop 7530: Loss: 1.44e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0809 +[2026-03-20T19:11:27.475493Z] Loop 7531: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0851 +[2026-03-20T19:11:28.330554Z] Loop 7532: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0824 +[2026-03-20T19:11:29.186137Z] Loop 7533: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0840 +[2026-03-20T19:11:30.041866Z] Loop 7534: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0816 +[2026-03-20T19:11:30.898356Z] Loop 7535: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0813 +[2026-03-20T19:11:31.753419Z] Loop 7536: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0842 +[2026-03-20T19:11:32.608399Z] Loop 7537: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0813 +[2026-03-20T19:11:33.463529Z] Loop 7538: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0850 +[2026-03-20T19:11:34.320034Z] Loop 7539: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0824 +[2026-03-20T19:11:35.216253Z] Loop 7540: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0828 +[2026-03-20T19:11:36.071144Z] Loop 7541: Loss: 1.50e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0827 +[2026-03-20T19:11:36.926302Z] Loop 7542: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0862 +[2026-03-20T19:11:37.782893Z] Loop 7543: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0884 +[2026-03-20T19:11:38.638769Z] Loop 7544: Loss: 1.45e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0827 +[2026-03-20T19:11:39.494619Z] Loop 7545: Loss: 1.42e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0816 +[2026-03-20T19:11:40.350774Z] Loop 7546: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0846 +[2026-03-20T19:11:41.208486Z] Loop 7547: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0817 +[2026-03-20T19:11:42.065629Z] Loop 7548: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0871 +[2026-03-20T19:11:42.920355Z] Loop 7549: Loss: 1.46e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0850 +[2026-03-20T19:11:43.816346Z] Loop 7550: Loss: 1.59e-02, Avg Return: 0.861, Regret: 0.0023, Entropy: 0.0891 +[2026-03-20T19:11:44.672962Z] Loop 7551: Loss: 1.61e-02, Avg Return: 0.860, Regret: 0.0023, Entropy: 0.0929 +[2026-03-20T19:11:45.529657Z] Loop 7552: Loss: 2.01e-02, Avg Return: 0.856, Regret: 0.0023, Entropy: 0.1117 +[2026-03-20T19:11:46.385704Z] Loop 7553: Loss: 1.87e-02, Avg Return: 0.856, Regret: 0.0023, Entropy: 0.1041 +[2026-03-20T19:11:47.241558Z] Loop 7554: Loss: 1.85e-02, Avg Return: 0.858, Regret: 0.0023, Entropy: 0.1038 +[2026-03-20T19:11:48.097563Z] Loop 7555: Loss: 1.69e-02, Avg Return: 0.860, Regret: 0.0023, Entropy: 0.0920 +[2026-03-20T19:11:48.954284Z] Loop 7556: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0023, Entropy: 0.0883 +[2026-03-20T19:11:49.811092Z] Loop 7557: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0023, Entropy: 0.0831 +[2026-03-20T19:11:50.668051Z] Loop 7558: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0023, Entropy: 0.0797 +[2026-03-20T19:11:51.523608Z] Loop 7559: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0023, Entropy: 0.0833 +[2026-03-20T19:11:52.421998Z] Loop 7560: Loss: 1.49e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0801 +[2026-03-20T19:11:53.278512Z] Loop 7561: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0806 +[2026-03-20T19:11:54.135475Z] Loop 7562: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0906 +[2026-03-20T19:11:54.991980Z] Loop 7563: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0881 +[2026-03-20T19:11:55.848258Z] Loop 7564: Loss: 1.63e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0879 +[2026-03-20T19:11:56.704409Z] Loop 7565: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0868 +[2026-03-20T19:11:57.561068Z] Loop 7566: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0911 +[2026-03-20T19:11:58.416057Z] Loop 7567: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0947 +[2026-03-20T19:11:59.271218Z] Loop 7568: Loss: 1.67e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0941 +[2026-03-20T19:12:00.126997Z] Loop 7569: Loss: 1.58e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0913 +[2026-03-20T19:12:01.025526Z] Loop 7570: Loss: 1.64e-02, Avg Return: 0.863, Regret: 0.0023, Entropy: 0.0931 +[2026-03-20T19:12:01.883412Z] Loop 7571: Loss: 1.72e-02, Avg Return: 0.860, Regret: 0.0023, Entropy: 0.0973 +[2026-03-20T19:12:02.738600Z] Loop 7572: Loss: 1.57e-02, Avg Return: 0.861, Regret: 0.0023, Entropy: 0.0939 +[2026-03-20T19:12:03.593498Z] Loop 7573: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.0880 +[2026-03-20T19:12:04.449379Z] Loop 7574: Loss: 1.54e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.0885 +[2026-03-20T19:12:05.304928Z] Loop 7575: Loss: 1.51e-02, Avg Return: 0.860, Regret: 0.0023, Entropy: 0.0917 +[2026-03-20T19:12:06.160098Z] Loop 7576: Loss: 1.46e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.0871 +[2026-03-20T19:12:07.016212Z] Loop 7577: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.0879 +[2026-03-20T19:12:07.872133Z] Loop 7578: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.0840 +[2026-03-20T19:12:08.727189Z] Loop 7579: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.0874 +[2026-03-20T19:12:09.623567Z] Loop 7580: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0831 +[2026-03-20T19:12:10.478761Z] Loop 7581: Loss: 1.45e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0805 +[2026-03-20T19:12:11.334198Z] Loop 7582: Loss: 1.50e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0804 +[2026-03-20T19:12:12.189449Z] Loop 7583: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0794 +[2026-03-20T19:12:13.045702Z] Loop 7584: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0784 +[2026-03-20T19:12:13.901677Z] Loop 7585: Loss: 1.46e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0787 +[2026-03-20T19:12:14.756060Z] Loop 7586: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0796 +[2026-03-20T19:12:15.610670Z] Loop 7587: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0795 +[2026-03-20T19:12:16.467176Z] Loop 7588: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0794 +[2026-03-20T19:12:17.322617Z] Loop 7589: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0767 +[2026-03-20T19:12:18.218234Z] Loop 7590: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0809 +[2026-03-20T19:12:19.073179Z] Loop 7591: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0726 +[2026-03-20T19:12:19.928100Z] Loop 7592: Loss: 1.46e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0821 +[2026-03-20T19:12:20.784189Z] Loop 7593: Loss: 1.54e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0819 +[2026-03-20T19:12:21.639586Z] Loop 7594: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0752 +[2026-03-20T19:12:22.493935Z] Loop 7595: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0807 +[2026-03-20T19:12:23.349329Z] Loop 7596: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0820 +[2026-03-20T19:12:24.205584Z] Loop 7597: Loss: 1.46e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0824 +[2026-03-20T19:12:25.061138Z] Loop 7598: Loss: 1.46e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0814 +[2026-03-20T19:12:25.916755Z] Loop 7599: Loss: 1.52e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0828 +[2026-03-20T19:12:26.813435Z] Loop 7600: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0845 +[2026-03-20T19:12:27.670106Z] Loop 7601: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0827 +[2026-03-20T19:12:28.525908Z] Loop 7602: Loss: 1.42e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0823 +[2026-03-20T19:12:29.382559Z] Loop 7603: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0807 +[2026-03-20T19:12:30.238138Z] Loop 7604: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0841 +[2026-03-20T19:12:31.093197Z] Loop 7605: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0851 +[2026-03-20T19:12:31.949587Z] Loop 7606: Loss: 1.71e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0922 +[2026-03-20T19:12:32.805811Z] Loop 7607: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0958 +[2026-03-20T19:12:33.661836Z] Loop 7608: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.1003 +[2026-03-20T19:12:34.518424Z] Loop 7609: Loss: 1.90e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.1019 +[2026-03-20T19:12:35.413854Z] Loop 7610: Loss: 1.83e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.1033 +[2026-03-20T19:12:36.270110Z] Loop 7611: Loss: 1.96e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.1073 +[2026-03-20T19:12:37.125501Z] Loop 7612: Loss: 1.94e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.1106 +[2026-03-20T19:12:37.980901Z] Loop 7613: Loss: 1.90e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.1076 +[2026-03-20T19:12:38.835322Z] Loop 7614: Loss: 1.86e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.1050 +[2026-03-20T19:12:39.689794Z] Loop 7615: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.1027 +[2026-03-20T19:12:40.545108Z] Loop 7616: Loss: 1.89e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.1104 +[2026-03-20T19:12:41.401038Z] Loop 7617: Loss: 1.94e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.1069 +[2026-03-20T19:12:42.255486Z] Loop 7618: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.1014 +[2026-03-20T19:12:43.110912Z] Loop 7619: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0997 +[2026-03-20T19:12:44.005913Z] Loop 7620: Loss: 1.72e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0943 +[2026-03-20T19:12:44.861703Z] Loop 7621: Loss: 1.59e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0871 +[2026-03-20T19:12:45.717400Z] Loop 7622: Loss: 1.63e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0868 +[2026-03-20T19:12:46.571845Z] Loop 7623: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0879 +[2026-03-20T19:12:47.427452Z] Loop 7624: Loss: 1.50e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0832 +[2026-03-20T19:12:48.284160Z] Loop 7625: Loss: 1.47e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0787 +[2026-03-20T19:12:49.139265Z] Loop 7626: Loss: 1.64e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0858 +[2026-03-20T19:12:49.994474Z] Loop 7627: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0810 +[2026-03-20T19:12:50.849688Z] Loop 7628: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0821 +[2026-03-20T19:12:51.705302Z] Loop 7629: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0769 +[2026-03-20T19:12:52.600301Z] Loop 7630: Loss: 1.40e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0803 +[2026-03-20T19:12:53.455327Z] Loop 7631: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0880 +[2026-03-20T19:12:54.310380Z] Loop 7632: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0798 +[2026-03-20T19:12:55.166695Z] Loop 7633: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0854 +[2026-03-20T19:12:56.022328Z] Loop 7634: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0837 +[2026-03-20T19:12:56.878756Z] Loop 7635: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0847 +[2026-03-20T19:12:57.733582Z] Loop 7636: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0824 +[2026-03-20T19:12:58.589376Z] Loop 7637: Loss: 1.54e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0838 +[2026-03-20T19:12:59.446035Z] Loop 7638: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0857 +[2026-03-20T19:13:00.302124Z] Loop 7639: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0848 +[2026-03-20T19:13:01.198958Z] Loop 7640: Loss: 1.42e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0830 +[2026-03-20T19:13:02.054935Z] Loop 7641: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0823 +[2026-03-20T19:13:02.911173Z] Loop 7642: Loss: 1.44e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0764 +[2026-03-20T19:13:03.766765Z] Loop 7643: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0792 +[2026-03-20T19:13:04.622405Z] Loop 7644: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0919 +[2026-03-20T19:13:05.478326Z] Loop 7645: Loss: 1.54e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0871 +[2026-03-20T19:13:06.334871Z] Loop 7646: Loss: 1.56e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0927 +[2026-03-20T19:13:07.192459Z] Loop 7647: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0933 +[2026-03-20T19:13:08.049246Z] Loop 7648: Loss: 1.81e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.1044 +[2026-03-20T19:13:08.905571Z] Loop 7649: Loss: 1.89e-02, Avg Return: 0.860, Regret: 0.0012, Entropy: 0.1063 +[2026-03-20T19:13:09.802613Z] Loop 7650: Loss: 1.81e-02, Avg Return: 0.860, Regret: 0.0036, Entropy: 0.1030 +[2026-03-20T19:13:10.658743Z] Loop 7651: Loss: 1.75e-02, Avg Return: 0.861, Regret: 0.0036, Entropy: 0.1011 +[2026-03-20T19:13:11.514423Z] Loop 7652: Loss: 1.70e-02, Avg Return: 0.859, Regret: 0.0036, Entropy: 0.0993 +[2026-03-20T19:13:12.370040Z] Loop 7653: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.0927 +[2026-03-20T19:13:13.224683Z] Loop 7654: Loss: 1.62e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.0906 +[2026-03-20T19:13:14.079450Z] Loop 7655: Loss: 1.62e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.0850 +[2026-03-20T19:13:14.935424Z] Loop 7656: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0036, Entropy: 0.0877 +[2026-03-20T19:13:15.791414Z] Loop 7657: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.0917 +[2026-03-20T19:13:16.646263Z] Loop 7658: Loss: 1.70e-02, Avg Return: 0.864, Regret: 0.0036, Entropy: 0.0912 +[2026-03-20T19:13:17.501488Z] Loop 7659: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0036, Entropy: 0.0844 +[2026-03-20T19:13:18.398669Z] Loop 7660: Loss: 1.55e-02, Avg Return: 0.865, Regret: 0.0008, Entropy: 0.0846 +[2026-03-20T19:13:19.254847Z] Loop 7661: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0865 +[2026-03-20T19:13:20.110393Z] Loop 7662: Loss: 1.43e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0801 +[2026-03-20T19:13:20.965203Z] Loop 7663: Loss: 1.47e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0792 +[2026-03-20T19:13:21.821000Z] Loop 7664: Loss: 1.45e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0809 +[2026-03-20T19:13:22.676830Z] Loop 7665: Loss: 1.42e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0815 +[2026-03-20T19:13:23.532848Z] Loop 7666: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0795 +[2026-03-20T19:13:24.388232Z] Loop 7667: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0804 +[2026-03-20T19:13:25.243205Z] Loop 7668: Loss: 1.45e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0762 +[2026-03-20T19:13:26.099024Z] Loop 7669: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0756 +[2026-03-20T19:13:26.994562Z] Loop 7670: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0797 +[2026-03-20T19:13:27.851349Z] Loop 7671: Loss: 1.29e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0761 +[2026-03-20T19:13:28.706621Z] Loop 7672: Loss: 1.33e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0759 +[2026-03-20T19:13:29.561852Z] Loop 7673: Loss: 1.33e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0751 +[2026-03-20T19:13:30.417512Z] Loop 7674: Loss: 1.47e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0778 +[2026-03-20T19:13:31.273169Z] Loop 7675: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0760 +[2026-03-20T19:13:32.128669Z] Loop 7676: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0781 +[2026-03-20T19:13:32.983737Z] Loop 7677: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0772 +[2026-03-20T19:13:33.841084Z] Loop 7678: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0800 +[2026-03-20T19:13:34.698686Z] Loop 7679: Loss: 1.40e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0787 +[2026-03-20T19:13:35.596554Z] Loop 7680: Loss: 1.46e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0764 +[2026-03-20T19:13:36.453699Z] Loop 7681: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0734 +[2026-03-20T19:13:37.309914Z] Loop 7682: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0784 +[2026-03-20T19:13:38.167095Z] Loop 7683: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0772 +[2026-03-20T19:13:39.023596Z] Loop 7684: Loss: 1.45e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0802 +[2026-03-20T19:13:39.880491Z] Loop 7685: Loss: 1.42e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0797 +[2026-03-20T19:13:40.736921Z] Loop 7686: Loss: 1.51e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0819 +[2026-03-20T19:13:41.593410Z] Loop 7687: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0799 +[2026-03-20T19:13:42.449937Z] Loop 7688: Loss: 1.45e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0806 +[2026-03-20T19:13:43.306186Z] Loop 7689: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0845 +[2026-03-20T19:13:44.202987Z] Loop 7690: Loss: 1.41e-02, Avg Return: 0.860, Regret: 0.0029, Entropy: 0.0794 +[2026-03-20T19:13:45.059998Z] Loop 7691: Loss: 1.69e-02, Avg Return: 0.859, Regret: 0.0029, Entropy: 0.0877 +[2026-03-20T19:13:45.915023Z] Loop 7692: Loss: 1.48e-02, Avg Return: 0.860, Regret: 0.0029, Entropy: 0.0813 +[2026-03-20T19:13:46.770617Z] Loop 7693: Loss: 1.40e-02, Avg Return: 0.861, Regret: 0.0029, Entropy: 0.0785 +[2026-03-20T19:13:47.626473Z] Loop 7694: Loss: 1.52e-02, Avg Return: 0.861, Regret: 0.0029, Entropy: 0.0826 +[2026-03-20T19:13:48.482570Z] Loop 7695: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0029, Entropy: 0.0803 +[2026-03-20T19:13:49.338361Z] Loop 7696: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0029, Entropy: 0.0796 +[2026-03-20T19:13:50.194711Z] Loop 7697: Loss: 1.31e-02, Avg Return: 0.862, Regret: 0.0029, Entropy: 0.0776 +[2026-03-20T19:13:51.050215Z] Loop 7698: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0029, Entropy: 0.0759 +[2026-03-20T19:13:51.906734Z] Loop 7699: Loss: 1.35e-02, Avg Return: 0.862, Regret: 0.0029, Entropy: 0.0736 +[2026-03-20T19:13:52.799759Z] Loop 7700: Loss: 1.33e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0768 +[2026-03-20T19:13:53.655755Z] Loop 7701: Loss: 1.31e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0773 +[2026-03-20T19:13:54.512682Z] Loop 7702: Loss: 1.45e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0744 +[2026-03-20T19:13:55.369257Z] Loop 7703: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0732 +[2026-03-20T19:13:56.224280Z] Loop 7704: Loss: 1.36e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0748 +[2026-03-20T19:13:57.079577Z] Loop 7705: Loss: 1.38e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0745 +[2026-03-20T19:13:57.935461Z] Loop 7706: Loss: 1.31e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0733 +[2026-03-20T19:13:58.792573Z] Loop 7707: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0726 +[2026-03-20T19:13:59.648506Z] Loop 7708: Loss: 1.42e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0754 +[2026-03-20T19:14:00.503334Z] Loop 7709: Loss: 1.40e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0778 +[2026-03-20T19:14:01.399196Z] Loop 7710: Loss: 1.40e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0760 +[2026-03-20T19:14:02.256948Z] Loop 7711: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0763 +[2026-03-20T19:14:03.112705Z] Loop 7712: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0725 +[2026-03-20T19:14:03.969001Z] Loop 7713: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0757 +[2026-03-20T19:14:04.825163Z] Loop 7714: Loss: 1.45e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0752 +[2026-03-20T19:14:05.681625Z] Loop 7715: Loss: 1.39e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0759 +[2026-03-20T19:14:06.537633Z] Loop 7716: Loss: 1.35e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0740 +[2026-03-20T19:14:07.393218Z] Loop 7717: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0741 +[2026-03-20T19:14:08.248953Z] Loop 7718: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0783 +[2026-03-20T19:14:09.104162Z] Loop 7719: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0779 +[2026-03-20T19:14:10.001734Z] Loop 7720: Loss: 1.47e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0783 +[2026-03-20T19:14:10.857449Z] Loop 7721: Loss: 1.44e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0805 +[2026-03-20T19:14:11.713920Z] Loop 7722: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0827 +[2026-03-20T19:14:12.570278Z] Loop 7723: Loss: 1.55e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0851 +[2026-03-20T19:14:13.425670Z] Loop 7724: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0852 +[2026-03-20T19:14:14.281439Z] Loop 7725: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0914 +[2026-03-20T19:14:15.138084Z] Loop 7726: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0929 +[2026-03-20T19:14:15.992489Z] Loop 7727: Loss: 1.82e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0962 +[2026-03-20T19:14:16.846989Z] Loop 7728: Loss: 1.74e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0955 +[2026-03-20T19:14:17.703305Z] Loop 7729: Loss: 1.81e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.1048 +[2026-03-20T19:14:18.600920Z] Loop 7730: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.1031 +[2026-03-20T19:14:19.456268Z] Loop 7731: Loss: 1.89e-02, Avg Return: 0.859, Regret: 0.0022, Entropy: 0.1045 +[2026-03-20T19:14:20.310602Z] Loop 7732: Loss: 1.92e-02, Avg Return: 0.857, Regret: 0.0022, Entropy: 0.1042 +[2026-03-20T19:14:21.165079Z] Loop 7733: Loss: 2.11e-02, Avg Return: 0.856, Regret: 0.0022, Entropy: 0.1113 +[2026-03-20T19:14:22.021459Z] Loop 7734: Loss: 2.28e-02, Avg Return: 0.853, Regret: 0.0022, Entropy: 0.1202 +[2026-03-20T19:14:22.877578Z] Loop 7735: Loss: 2.28e-02, Avg Return: 0.849, Regret: 0.0022, Entropy: 0.1144 +[2026-03-20T19:14:23.732960Z] Loop 7736: Loss: 2.13e-02, Avg Return: 0.847, Regret: 0.0022, Entropy: 0.1119 +[2026-03-20T19:14:24.588727Z] Loop 7737: Loss: 2.10e-02, Avg Return: 0.848, Regret: 0.0022, Entropy: 0.1150 +[2026-03-20T19:14:25.444652Z] Loop 7738: Loss: 2.15e-02, Avg Return: 0.850, Regret: 0.0022, Entropy: 0.1117 +[2026-03-20T19:14:26.301168Z] Loop 7739: Loss: 2.11e-02, Avg Return: 0.850, Regret: 0.0022, Entropy: 0.1106 +[2026-03-20T19:14:27.199477Z] Loop 7740: Loss: 2.09e-02, Avg Return: 0.854, Regret: 0.0096, Entropy: 0.1108 +[2026-03-20T19:14:28.054899Z] Loop 7741: Loss: 2.00e-02, Avg Return: 0.856, Regret: 0.0096, Entropy: 0.1097 +[2026-03-20T19:14:28.911310Z] Loop 7742: Loss: 2.03e-02, Avg Return: 0.858, Regret: 0.0096, Entropy: 0.1108 +[2026-03-20T19:14:29.767738Z] Loop 7743: Loss: 2.01e-02, Avg Return: 0.859, Regret: 0.0096, Entropy: 0.1068 +[2026-03-20T19:14:30.624485Z] Loop 7744: Loss: 2.01e-02, Avg Return: 0.857, Regret: 0.0096, Entropy: 0.1124 +[2026-03-20T19:14:31.481422Z] Loop 7745: Loss: 2.08e-02, Avg Return: 0.860, Regret: 0.0096, Entropy: 0.1110 +[2026-03-20T19:14:32.336952Z] Loop 7746: Loss: 2.18e-02, Avg Return: 0.859, Regret: 0.0096, Entropy: 0.1157 +[2026-03-20T19:14:33.193596Z] Loop 7747: Loss: 2.34e-02, Avg Return: 0.861, Regret: 0.0096, Entropy: 0.1222 +[2026-03-20T19:14:34.049649Z] Loop 7748: Loss: 2.27e-02, Avg Return: 0.862, Regret: 0.0096, Entropy: 0.1147 +[2026-03-20T19:14:34.905277Z] Loop 7749: Loss: 2.10e-02, Avg Return: 0.863, Regret: 0.0096, Entropy: 0.1092 +[2026-03-20T19:14:35.801849Z] Loop 7750: Loss: 2.03e-02, Avg Return: 0.864, Regret: 0.0013, Entropy: 0.1081 +[2026-03-20T19:14:36.656560Z] Loop 7751: Loss: 2.05e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1057 +[2026-03-20T19:14:37.512656Z] Loop 7752: Loss: 2.12e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.1108 +[2026-03-20T19:14:38.368817Z] Loop 7753: Loss: 2.09e-02, Avg Return: 0.864, Regret: 0.0013, Entropy: 0.1043 +[2026-03-20T19:14:39.224304Z] Loop 7754: Loss: 1.97e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1038 +[2026-03-20T19:14:40.080149Z] Loop 7755: Loss: 2.08e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1068 +[2026-03-20T19:14:40.936020Z] Loop 7756: Loss: 1.93e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1026 +[2026-03-20T19:14:41.791581Z] Loop 7757: Loss: 2.01e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1012 +[2026-03-20T19:14:42.647588Z] Loop 7758: Loss: 1.97e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0990 +[2026-03-20T19:14:43.502295Z] Loop 7759: Loss: 1.93e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1023 +[2026-03-20T19:14:44.397460Z] Loop 7760: Loss: 2.13e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.1070 +[2026-03-20T19:14:45.252086Z] Loop 7761: Loss: 2.04e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.1032 +[2026-03-20T19:14:46.107433Z] Loop 7762: Loss: 2.08e-02, Avg Return: 0.860, Regret: 0.0025, Entropy: 0.1036 +[2026-03-20T19:14:46.962199Z] Loop 7763: Loss: 1.99e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.1032 +[2026-03-20T19:14:47.818405Z] Loop 7764: Loss: 2.21e-02, Avg Return: 0.860, Regret: 0.0025, Entropy: 0.1103 +[2026-03-20T19:14:48.672929Z] Loop 7765: Loss: 2.17e-02, Avg Return: 0.859, Regret: 0.0025, Entropy: 0.1084 +[2026-03-20T19:14:49.528057Z] Loop 7766: Loss: 2.00e-02, Avg Return: 0.859, Regret: 0.0025, Entropy: 0.1051 +[2026-03-20T19:14:50.383831Z] Loop 7767: Loss: 2.04e-02, Avg Return: 0.860, Regret: 0.0025, Entropy: 0.1039 +[2026-03-20T19:14:51.239504Z] Loop 7768: Loss: 2.04e-02, Avg Return: 0.860, Regret: 0.0025, Entropy: 0.1026 +[2026-03-20T19:14:52.095397Z] Loop 7769: Loss: 2.05e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.1036 +[2026-03-20T19:14:52.989661Z] Loop 7770: Loss: 1.97e-02, Avg Return: 0.860, Regret: 0.0024, Entropy: 0.1022 +[2026-03-20T19:14:53.845641Z] Loop 7771: Loss: 1.91e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.1021 +[2026-03-20T19:14:54.703552Z] Loop 7772: Loss: 1.99e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.1025 +[2026-03-20T19:14:55.558593Z] Loop 7773: Loss: 2.03e-02, Avg Return: 0.863, Regret: 0.0024, Entropy: 0.1033 +[2026-03-20T19:14:56.414270Z] Loop 7774: Loss: 1.93e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.1014 +[2026-03-20T19:14:57.271073Z] Loop 7775: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.0970 +[2026-03-20T19:14:58.127287Z] Loop 7776: Loss: 1.71e-02, Avg Return: 0.864, Regret: 0.0024, Entropy: 0.0927 +[2026-03-20T19:14:58.982830Z] Loop 7777: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0024, Entropy: 0.0875 +[2026-03-20T19:14:59.838186Z] Loop 7778: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0024, Entropy: 0.0877 +[2026-03-20T19:15:00.694366Z] Loop 7779: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.0889 +[2026-03-20T19:15:01.594388Z] Loop 7780: Loss: 1.77e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0924 +[2026-03-20T19:15:02.451707Z] Loop 7781: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0890 +[2026-03-20T19:15:03.309866Z] Loop 7782: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0923 +[2026-03-20T19:15:04.165005Z] Loop 7783: Loss: 1.71e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0908 +[2026-03-20T19:15:05.021871Z] Loop 7784: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0867 +[2026-03-20T19:15:05.876927Z] Loop 7785: Loss: 1.62e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0929 +[2026-03-20T19:15:06.732215Z] Loop 7786: Loss: 1.69e-02, Avg Return: 0.860, Regret: 0.0007, Entropy: 0.0945 +[2026-03-20T19:15:07.587371Z] Loop 7787: Loss: 1.65e-02, Avg Return: 0.860, Regret: 0.0007, Entropy: 0.0899 +[2026-03-20T19:15:08.444552Z] Loop 7788: Loss: 1.56e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0886 +[2026-03-20T19:15:09.300233Z] Loop 7789: Loss: 1.49e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0865 +[2026-03-20T19:15:10.194538Z] Loop 7790: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0818 +[2026-03-20T19:15:11.049126Z] Loop 7791: Loss: 1.44e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0829 +[2026-03-20T19:15:11.903880Z] Loop 7792: Loss: 1.43e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0775 +[2026-03-20T19:15:12.759185Z] Loop 7793: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0776 +[2026-03-20T19:15:13.615456Z] Loop 7794: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0771 +[2026-03-20T19:15:14.470173Z] Loop 7795: Loss: 1.46e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.0774 +[2026-03-20T19:15:15.326390Z] Loop 7796: Loss: 1.56e-02, Avg Return: 0.864, Regret: 0.0014, Entropy: 0.0828 +[2026-03-20T19:15:16.182592Z] Loop 7797: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0806 +[2026-03-20T19:15:17.037975Z] Loop 7798: Loss: 1.45e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.0794 +[2026-03-20T19:15:17.894251Z] Loop 7799: Loss: 1.49e-02, Avg Return: 0.860, Regret: 0.0014, Entropy: 0.0800 +[2026-03-20T19:15:18.788850Z] Loop 7800: Loss: 1.55e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.0856 +[2026-03-20T19:15:19.643378Z] Loop 7801: Loss: 1.42e-02, Avg Return: 0.860, Regret: 0.0025, Entropy: 0.0799 +[2026-03-20T19:15:20.498018Z] Loop 7802: Loss: 1.50e-02, Avg Return: 0.860, Regret: 0.0025, Entropy: 0.0830 +[2026-03-20T19:15:21.353605Z] Loop 7803: Loss: 1.62e-02, Avg Return: 0.858, Regret: 0.0025, Entropy: 0.0865 +[2026-03-20T19:15:22.208841Z] Loop 7804: Loss: 1.75e-02, Avg Return: 0.860, Regret: 0.0025, Entropy: 0.0922 +[2026-03-20T19:15:23.063816Z] Loop 7805: Loss: 1.86e-02, Avg Return: 0.860, Regret: 0.0025, Entropy: 0.0955 +[2026-03-20T19:15:23.918112Z] Loop 7806: Loss: 1.80e-02, Avg Return: 0.860, Regret: 0.0025, Entropy: 0.0950 +[2026-03-20T19:15:24.773720Z] Loop 7807: Loss: 1.74e-02, Avg Return: 0.859, Regret: 0.0025, Entropy: 0.0946 +[2026-03-20T19:15:25.629172Z] Loop 7808: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0928 +[2026-03-20T19:15:26.483853Z] Loop 7809: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0943 +[2026-03-20T19:15:27.379304Z] Loop 7810: Loss: 1.90e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.1003 +[2026-03-20T19:15:28.235514Z] Loop 7811: Loss: 1.80e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0973 +[2026-03-20T19:15:29.091719Z] Loop 7812: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0952 +[2026-03-20T19:15:29.946607Z] Loop 7813: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0917 +[2026-03-20T19:15:30.801012Z] Loop 7814: Loss: 1.93e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0984 +[2026-03-20T19:15:31.656007Z] Loop 7815: Loss: 1.94e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0969 +[2026-03-20T19:15:32.511865Z] Loop 7816: Loss: 1.93e-02, Avg Return: 0.860, Regret: 0.0018, Entropy: 0.0992 +[2026-03-20T19:15:33.367764Z] Loop 7817: Loss: 2.15e-02, Avg Return: 0.859, Regret: 0.0018, Entropy: 0.1113 +[2026-03-20T19:15:34.222927Z] Loop 7818: Loss: 1.96e-02, Avg Return: 0.860, Regret: 0.0018, Entropy: 0.1070 +[2026-03-20T19:15:35.079179Z] Loop 7819: Loss: 2.01e-02, Avg Return: 0.858, Regret: 0.0018, Entropy: 0.1094 +[2026-03-20T19:15:35.974261Z] Loop 7820: Loss: 1.97e-02, Avg Return: 0.858, Regret: 0.0043, Entropy: 0.1037 +[2026-03-20T19:15:36.829539Z] Loop 7821: Loss: 1.95e-02, Avg Return: 0.857, Regret: 0.0043, Entropy: 0.1044 +[2026-03-20T19:15:37.685184Z] Loop 7822: Loss: 2.11e-02, Avg Return: 0.859, Regret: 0.0043, Entropy: 0.1062 +[2026-03-20T19:15:38.540994Z] Loop 7823: Loss: 1.89e-02, Avg Return: 0.860, Regret: 0.0043, Entropy: 0.1025 +[2026-03-20T19:15:39.396448Z] Loop 7824: Loss: 1.80e-02, Avg Return: 0.859, Regret: 0.0043, Entropy: 0.0979 +[2026-03-20T19:15:40.252211Z] Loop 7825: Loss: 1.85e-02, Avg Return: 0.858, Regret: 0.0043, Entropy: 0.0983 +[2026-03-20T19:15:41.107078Z] Loop 7826: Loss: 1.81e-02, Avg Return: 0.860, Regret: 0.0043, Entropy: 0.0986 +[2026-03-20T19:15:41.962873Z] Loop 7827: Loss: 1.93e-02, Avg Return: 0.860, Regret: 0.0043, Entropy: 0.1014 +[2026-03-20T19:15:42.818506Z] Loop 7828: Loss: 1.86e-02, Avg Return: 0.860, Regret: 0.0043, Entropy: 0.1026 +[2026-03-20T19:15:43.674602Z] Loop 7829: Loss: 1.76e-02, Avg Return: 0.860, Regret: 0.0043, Entropy: 0.0964 +[2026-03-20T19:15:44.571011Z] Loop 7830: Loss: 1.97e-02, Avg Return: 0.860, Regret: 0.0037, Entropy: 0.1048 +[2026-03-20T19:15:45.427155Z] Loop 7831: Loss: 1.94e-02, Avg Return: 0.860, Regret: 0.0037, Entropy: 0.1046 +[2026-03-20T19:15:46.282064Z] Loop 7832: Loss: 1.95e-02, Avg Return: 0.859, Regret: 0.0037, Entropy: 0.1065 +[2026-03-20T19:15:47.136954Z] Loop 7833: Loss: 1.95e-02, Avg Return: 0.859, Regret: 0.0037, Entropy: 0.1037 +[2026-03-20T19:15:47.992019Z] Loop 7834: Loss: 1.77e-02, Avg Return: 0.860, Regret: 0.0037, Entropy: 0.0975 +[2026-03-20T19:15:48.847757Z] Loop 7835: Loss: 1.83e-02, Avg Return: 0.860, Regret: 0.0037, Entropy: 0.0984 +[2026-03-20T19:15:49.702836Z] Loop 7836: Loss: 1.70e-02, Avg Return: 0.861, Regret: 0.0037, Entropy: 0.0919 +[2026-03-20T19:15:50.558527Z] Loop 7837: Loss: 1.72e-02, Avg Return: 0.861, Regret: 0.0037, Entropy: 0.0938 +[2026-03-20T19:15:51.416054Z] Loop 7838: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0037, Entropy: 0.0938 +[2026-03-20T19:15:52.272538Z] Loop 7839: Loss: 1.83e-02, Avg Return: 0.862, Regret: 0.0037, Entropy: 0.0947 +[2026-03-20T19:15:53.168958Z] Loop 7840: Loss: 1.68e-02, Avg Return: 0.861, Regret: 0.0029, Entropy: 0.0933 +[2026-03-20T19:15:54.023595Z] Loop 7841: Loss: 1.74e-02, Avg Return: 0.859, Regret: 0.0029, Entropy: 0.0902 +[2026-03-20T19:15:54.879844Z] Loop 7842: Loss: 1.94e-02, Avg Return: 0.860, Regret: 0.0029, Entropy: 0.1001 +[2026-03-20T19:15:55.736170Z] Loop 7843: Loss: 1.98e-02, Avg Return: 0.861, Regret: 0.0029, Entropy: 0.0986 +[2026-03-20T19:15:56.593095Z] Loop 7844: Loss: 1.88e-02, Avg Return: 0.861, Regret: 0.0029, Entropy: 0.0973 +[2026-03-20T19:15:57.448751Z] Loop 7845: Loss: 1.84e-02, Avg Return: 0.862, Regret: 0.0029, Entropy: 0.0956 +[2026-03-20T19:15:58.305021Z] Loop 7846: Loss: 1.77e-02, Avg Return: 0.860, Regret: 0.0029, Entropy: 0.0921 +[2026-03-20T19:15:59.160843Z] Loop 7847: Loss: 1.79e-02, Avg Return: 0.860, Regret: 0.0029, Entropy: 0.0945 +[2026-03-20T19:16:00.017539Z] Loop 7848: Loss: 1.63e-02, Avg Return: 0.861, Regret: 0.0029, Entropy: 0.0902 +[2026-03-20T19:16:00.873799Z] Loop 7849: Loss: 1.79e-02, Avg Return: 0.860, Regret: 0.0029, Entropy: 0.0942 +[2026-03-20T19:16:01.770165Z] Loop 7850: Loss: 1.71e-02, Avg Return: 0.861, Regret: 0.0034, Entropy: 0.0908 +[2026-03-20T19:16:02.625497Z] Loop 7851: Loss: 1.71e-02, Avg Return: 0.860, Regret: 0.0034, Entropy: 0.0911 +[2026-03-20T19:16:03.481115Z] Loop 7852: Loss: 1.70e-02, Avg Return: 0.862, Regret: 0.0034, Entropy: 0.0920 +[2026-03-20T19:16:04.336716Z] Loop 7853: Loss: 1.88e-02, Avg Return: 0.861, Regret: 0.0034, Entropy: 0.0965 +[2026-03-20T19:16:05.191852Z] Loop 7854: Loss: 1.87e-02, Avg Return: 0.862, Regret: 0.0034, Entropy: 0.0998 +[2026-03-20T19:16:06.046584Z] Loop 7855: Loss: 1.96e-02, Avg Return: 0.862, Regret: 0.0034, Entropy: 0.1001 +[2026-03-20T19:16:06.901272Z] Loop 7856: Loss: 1.93e-02, Avg Return: 0.861, Regret: 0.0034, Entropy: 0.1067 +[2026-03-20T19:16:07.756361Z] Loop 7857: Loss: 2.14e-02, Avg Return: 0.857, Regret: 0.0034, Entropy: 0.1103 +[2026-03-20T19:16:08.611941Z] Loop 7858: Loss: 1.92e-02, Avg Return: 0.855, Regret: 0.0034, Entropy: 0.1043 +[2026-03-20T19:16:09.466987Z] Loop 7859: Loss: 2.10e-02, Avg Return: 0.858, Regret: 0.0034, Entropy: 0.1062 +[2026-03-20T19:16:10.362665Z] Loop 7860: Loss: 1.82e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.0970 +[2026-03-20T19:16:11.219716Z] Loop 7861: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.0965 +[2026-03-20T19:16:12.075564Z] Loop 7862: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.0857 +[2026-03-20T19:16:12.931785Z] Loop 7863: Loss: 1.69e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.0888 +[2026-03-20T19:16:13.787876Z] Loop 7864: Loss: 1.85e-02, Avg Return: 0.860, Regret: 0.0028, Entropy: 0.0962 +[2026-03-20T19:16:14.643780Z] Loop 7865: Loss: 1.93e-02, Avg Return: 0.859, Regret: 0.0028, Entropy: 0.1011 +[2026-03-20T19:16:15.499941Z] Loop 7866: Loss: 2.09e-02, Avg Return: 0.855, Regret: 0.0028, Entropy: 0.1077 +[2026-03-20T19:16:16.355675Z] Loop 7867: Loss: 2.52e-02, Avg Return: 0.850, Regret: 0.0028, Entropy: 0.1235 +[2026-03-20T19:16:17.211401Z] Loop 7868: Loss: 2.64e-02, Avg Return: 0.846, Regret: 0.0028, Entropy: 0.1332 +[2026-03-20T19:16:18.068561Z] Loop 7869: Loss: 2.83e-02, Avg Return: 0.847, Regret: 0.0028, Entropy: 0.1397 +[2026-03-20T19:16:18.964642Z] Loop 7870: Loss: 2.81e-02, Avg Return: 0.851, Regret: 0.0112, Entropy: 0.1339 +[2026-03-20T19:16:19.820361Z] Loop 7871: Loss: 2.72e-02, Avg Return: 0.857, Regret: 0.0112, Entropy: 0.1307 +[2026-03-20T19:16:20.676543Z] Loop 7872: Loss: 2.61e-02, Avg Return: 0.859, Regret: 0.0112, Entropy: 0.1280 +[2026-03-20T19:16:21.532195Z] Loop 7873: Loss: 2.43e-02, Avg Return: 0.859, Regret: 0.0112, Entropy: 0.1259 +[2026-03-20T19:16:22.387715Z] Loop 7874: Loss: 2.56e-02, Avg Return: 0.859, Regret: 0.0112, Entropy: 0.1276 +[2026-03-20T19:16:23.242790Z] Loop 7875: Loss: 2.55e-02, Avg Return: 0.858, Regret: 0.0112, Entropy: 0.1330 +[2026-03-20T19:16:24.098268Z] Loop 7876: Loss: 2.52e-02, Avg Return: 0.856, Regret: 0.0112, Entropy: 0.1346 +[2026-03-20T19:16:24.954995Z] Loop 7877: Loss: 2.57e-02, Avg Return: 0.855, Regret: 0.0112, Entropy: 0.1370 +[2026-03-20T19:16:25.810714Z] Loop 7878: Loss: 2.43e-02, Avg Return: 0.855, Regret: 0.0112, Entropy: 0.1297 +[2026-03-20T19:16:26.665358Z] Loop 7879: Loss: 2.44e-02, Avg Return: 0.859, Regret: 0.0112, Entropy: 0.1261 +[2026-03-20T19:16:27.561575Z] Loop 7880: Loss: 2.37e-02, Avg Return: 0.860, Regret: 0.0036, Entropy: 0.1240 +[2026-03-20T19:16:28.417134Z] Loop 7881: Loss: 2.24e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.1180 +[2026-03-20T19:16:29.273771Z] Loop 7882: Loss: 2.30e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.1234 +[2026-03-20T19:16:30.128336Z] Loop 7883: Loss: 2.47e-02, Avg Return: 0.861, Regret: 0.0036, Entropy: 0.1270 +[2026-03-20T19:16:30.983738Z] Loop 7884: Loss: 2.77e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.1392 +[2026-03-20T19:16:31.840310Z] Loop 7885: Loss: 2.35e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.1190 +[2026-03-20T19:16:32.695748Z] Loop 7886: Loss: 2.08e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.1044 +[2026-03-20T19:16:33.550759Z] Loop 7887: Loss: 1.73e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.0967 +[2026-03-20T19:16:34.406160Z] Loop 7888: Loss: 1.67e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.0908 +[2026-03-20T19:16:35.261917Z] Loop 7889: Loss: 1.66e-02, Avg Return: 0.864, Regret: 0.0036, Entropy: 0.0895 +[2026-03-20T19:16:36.156646Z] Loop 7890: Loss: 1.70e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0923 +[2026-03-20T19:16:37.012395Z] Loop 7891: Loss: 1.76e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0902 +[2026-03-20T19:16:37.867766Z] Loop 7892: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0936 +[2026-03-20T19:16:38.723518Z] Loop 7893: Loss: 2.09e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1052 +[2026-03-20T19:16:39.579632Z] Loop 7894: Loss: 1.93e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.1025 +[2026-03-20T19:16:40.434703Z] Loop 7895: Loss: 1.90e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.1009 +[2026-03-20T19:16:41.288974Z] Loop 7896: Loss: 1.90e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0985 +[2026-03-20T19:16:42.145416Z] Loop 7897: Loss: 1.73e-02, Avg Return: 0.860, Regret: 0.0013, Entropy: 0.0939 +[2026-03-20T19:16:43.000861Z] Loop 7898: Loss: 1.90e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0977 +[2026-03-20T19:16:43.855997Z] Loop 7899: Loss: 1.77e-02, Avg Return: 0.860, Regret: 0.0013, Entropy: 0.0970 +[2026-03-20T19:16:44.752910Z] Loop 7900: Loss: 1.70e-02, Avg Return: 0.862, Regret: 0.0032, Entropy: 0.0951 +[2026-03-20T19:16:45.609572Z] Loop 7901: Loss: 1.85e-02, Avg Return: 0.862, Regret: 0.0032, Entropy: 0.0962 +[2026-03-20T19:16:46.466097Z] Loop 7902: Loss: 1.85e-02, Avg Return: 0.862, Regret: 0.0032, Entropy: 0.0974 +[2026-03-20T19:16:47.321307Z] Loop 7903: Loss: 1.79e-02, Avg Return: 0.862, Regret: 0.0032, Entropy: 0.0988 +[2026-03-20T19:16:48.177848Z] Loop 7904: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0032, Entropy: 0.0921 +[2026-03-20T19:16:49.033930Z] Loop 7905: Loss: 1.72e-02, Avg Return: 0.863, Regret: 0.0032, Entropy: 0.0912 +[2026-03-20T19:16:49.889326Z] Loop 7906: Loss: 1.75e-02, Avg Return: 0.860, Regret: 0.0032, Entropy: 0.0925 +[2026-03-20T19:16:50.745283Z] Loop 7907: Loss: 1.84e-02, Avg Return: 0.862, Regret: 0.0032, Entropy: 0.0932 +[2026-03-20T19:16:51.600961Z] Loop 7908: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0032, Entropy: 0.0914 +[2026-03-20T19:16:52.457208Z] Loop 7909: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0032, Entropy: 0.0909 +[2026-03-20T19:16:53.353491Z] Loop 7910: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0909 +[2026-03-20T19:16:54.208814Z] Loop 7911: Loss: 1.87e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0935 +[2026-03-20T19:16:55.063574Z] Loop 7912: Loss: 1.88e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.1001 +[2026-03-20T19:16:55.920358Z] Loop 7913: Loss: 1.76e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.0915 +[2026-03-20T19:16:56.775370Z] Loop 7914: Loss: 1.74e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.0919 +[2026-03-20T19:16:57.630159Z] Loop 7915: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0911 +[2026-03-20T19:16:58.485656Z] Loop 7916: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0876 +[2026-03-20T19:16:59.341939Z] Loop 7917: Loss: 1.75e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.0938 +[2026-03-20T19:17:00.197301Z] Loop 7918: Loss: 1.69e-02, Avg Return: 0.859, Regret: 0.0014, Entropy: 0.0895 +[2026-03-20T19:17:01.052051Z] Loop 7919: Loss: 1.56e-02, Avg Return: 0.860, Regret: 0.0014, Entropy: 0.0845 +[2026-03-20T19:17:01.945992Z] Loop 7920: Loss: 1.52e-02, Avg Return: 0.856, Regret: 0.0046, Entropy: 0.0806 +[2026-03-20T19:17:02.801660Z] Loop 7921: Loss: 1.54e-02, Avg Return: 0.859, Regret: 0.0046, Entropy: 0.0854 +[2026-03-20T19:17:03.656706Z] Loop 7922: Loss: 1.59e-02, Avg Return: 0.858, Regret: 0.0046, Entropy: 0.0869 +[2026-03-20T19:17:04.510562Z] Loop 7923: Loss: 1.53e-02, Avg Return: 0.858, Regret: 0.0046, Entropy: 0.0832 +[2026-03-20T19:17:05.365087Z] Loop 7924: Loss: 1.45e-02, Avg Return: 0.858, Regret: 0.0046, Entropy: 0.0807 +[2026-03-20T19:17:06.221175Z] Loop 7925: Loss: 1.44e-02, Avg Return: 0.859, Regret: 0.0046, Entropy: 0.0802 +[2026-03-20T19:17:07.077591Z] Loop 7926: Loss: 1.58e-02, Avg Return: 0.860, Regret: 0.0046, Entropy: 0.0811 +[2026-03-20T19:17:07.933875Z] Loop 7927: Loss: 1.63e-02, Avg Return: 0.861, Regret: 0.0046, Entropy: 0.0855 +[2026-03-20T19:17:08.789427Z] Loop 7928: Loss: 1.43e-02, Avg Return: 0.862, Regret: 0.0046, Entropy: 0.0775 +[2026-03-20T19:17:09.643272Z] Loop 7929: Loss: 1.47e-02, Avg Return: 0.860, Regret: 0.0046, Entropy: 0.0820 +[2026-03-20T19:17:10.537061Z] Loop 7930: Loss: 1.47e-02, Avg Return: 0.863, Regret: 0.0019, Entropy: 0.0812 +[2026-03-20T19:17:11.392126Z] Loop 7931: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0837 +[2026-03-20T19:17:12.247216Z] Loop 7932: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0019, Entropy: 0.0833 +[2026-03-20T19:17:13.102670Z] Loop 7933: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0937 +[2026-03-20T19:17:13.958393Z] Loop 7934: Loss: 1.73e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0939 +[2026-03-20T19:17:14.813678Z] Loop 7935: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0897 +[2026-03-20T19:17:15.668667Z] Loop 7936: Loss: 1.71e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0894 +[2026-03-20T19:17:16.523338Z] Loop 7937: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0019, Entropy: 0.0868 +[2026-03-20T19:17:17.377973Z] Loop 7938: Loss: 1.73e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0927 +[2026-03-20T19:17:18.233079Z] Loop 7939: Loss: 1.75e-02, Avg Return: 0.863, Regret: 0.0019, Entropy: 0.0921 +[2026-03-20T19:17:19.127824Z] Loop 7940: Loss: 1.80e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0953 +[2026-03-20T19:17:19.984070Z] Loop 7941: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0944 +[2026-03-20T19:17:20.839012Z] Loop 7942: Loss: 1.82e-02, Avg Return: 0.864, Regret: 0.0013, Entropy: 0.0948 +[2026-03-20T19:17:21.695925Z] Loop 7943: Loss: 1.92e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0952 +[2026-03-20T19:17:22.552292Z] Loop 7944: Loss: 1.96e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0972 +[2026-03-20T19:17:23.408481Z] Loop 7945: Loss: 1.91e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0984 +[2026-03-20T19:17:24.263310Z] Loop 7946: Loss: 1.85e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0966 +[2026-03-20T19:17:25.117930Z] Loop 7947: Loss: 1.88e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0972 +[2026-03-20T19:17:25.973036Z] Loop 7948: Loss: 1.93e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0997 +[2026-03-20T19:17:26.828867Z] Loop 7949: Loss: 1.99e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.1026 +[2026-03-20T19:17:27.724893Z] Loop 7950: Loss: 2.24e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.1115 +[2026-03-20T19:17:28.579969Z] Loop 7951: Loss: 2.10e-02, Avg Return: 0.863, Regret: 0.0025, Entropy: 0.1076 +[2026-03-20T19:17:29.435662Z] Loop 7952: Loss: 2.09e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.1114 +[2026-03-20T19:17:30.292373Z] Loop 7953: Loss: 2.49e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.1258 +[2026-03-20T19:17:31.148786Z] Loop 7954: Loss: 2.44e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.1235 +[2026-03-20T19:17:32.003295Z] Loop 7955: Loss: 2.52e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.1249 +[2026-03-20T19:17:32.857934Z] Loop 7956: Loss: 2.45e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.1296 +[2026-03-20T19:17:33.713954Z] Loop 7957: Loss: 2.49e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.1266 +[2026-03-20T19:17:34.569586Z] Loop 7958: Loss: 2.56e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.1291 +[2026-03-20T19:17:35.424159Z] Loop 7959: Loss: 2.62e-02, Avg Return: 0.859, Regret: 0.0025, Entropy: 0.1303 +[2026-03-20T19:17:36.318260Z] Loop 7960: Loss: 2.61e-02, Avg Return: 0.860, Regret: 0.0041, Entropy: 0.1344 +[2026-03-20T19:17:37.175129Z] Loop 7961: Loss: 2.68e-02, Avg Return: 0.858, Regret: 0.0041, Entropy: 0.1350 +[2026-03-20T19:17:38.032308Z] Loop 7962: Loss: 2.48e-02, Avg Return: 0.860, Regret: 0.0041, Entropy: 0.1272 +[2026-03-20T19:17:38.888793Z] Loop 7963: Loss: 2.48e-02, Avg Return: 0.860, Regret: 0.0041, Entropy: 0.1270 +[2026-03-20T19:17:39.743326Z] Loop 7964: Loss: 2.50e-02, Avg Return: 0.861, Regret: 0.0041, Entropy: 0.1272 +[2026-03-20T19:17:40.599384Z] Loop 7965: Loss: 2.43e-02, Avg Return: 0.860, Regret: 0.0041, Entropy: 0.1222 +[2026-03-20T19:17:41.455400Z] Loop 7966: Loss: 2.41e-02, Avg Return: 0.862, Regret: 0.0041, Entropy: 0.1207 +[2026-03-20T19:17:42.311957Z] Loop 7967: Loss: 2.14e-02, Avg Return: 0.860, Regret: 0.0041, Entropy: 0.1082 +[2026-03-20T19:17:43.168831Z] Loop 7968: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0041, Entropy: 0.0981 +[2026-03-20T19:17:44.025665Z] Loop 7969: Loss: 2.00e-02, Avg Return: 0.863, Regret: 0.0041, Entropy: 0.1017 +[2026-03-20T19:17:44.923672Z] Loop 7970: Loss: 2.08e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.1027 +[2026-03-20T19:17:45.780042Z] Loop 7971: Loss: 2.01e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0992 +[2026-03-20T19:17:46.636402Z] Loop 7972: Loss: 2.10e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.1022 +[2026-03-20T19:17:47.493834Z] Loop 7973: Loss: 1.99e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.1019 +[2026-03-20T19:17:48.350097Z] Loop 7974: Loss: 2.03e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0999 +[2026-03-20T19:17:49.207341Z] Loop 7975: Loss: 1.98e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.1021 +[2026-03-20T19:17:50.063381Z] Loop 7976: Loss: 1.91e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0978 +[2026-03-20T19:17:50.920599Z] Loop 7977: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0950 +[2026-03-20T19:17:51.776037Z] Loop 7978: Loss: 1.78e-02, Avg Return: 0.860, Regret: 0.0016, Entropy: 0.0919 +[2026-03-20T19:17:52.631697Z] Loop 7979: Loss: 1.75e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0894 +[2026-03-20T19:17:53.529927Z] Loop 7980: Loss: 1.64e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.0886 +[2026-03-20T19:17:54.386111Z] Loop 7981: Loss: 1.69e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.0891 +[2026-03-20T19:17:55.241456Z] Loop 7982: Loss: 1.50e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.0840 +[2026-03-20T19:17:56.095835Z] Loop 7983: Loss: 1.52e-02, Avg Return: 0.862, Regret: 0.0026, Entropy: 0.0822 +[2026-03-20T19:17:56.950472Z] Loop 7984: Loss: 1.64e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.0907 +[2026-03-20T19:17:57.807018Z] Loop 7985: Loss: 1.53e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.0842 +[2026-03-20T19:17:58.662182Z] Loop 7986: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0026, Entropy: 0.0857 +[2026-03-20T19:17:59.516642Z] Loop 7987: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0026, Entropy: 0.0870 +[2026-03-20T19:18:00.371117Z] Loop 7988: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0026, Entropy: 0.0841 +[2026-03-20T19:18:01.227200Z] Loop 7989: Loss: 1.64e-02, Avg Return: 0.863, Regret: 0.0026, Entropy: 0.0873 +[2026-03-20T19:18:02.122862Z] Loop 7990: Loss: 1.59e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0858 +[2026-03-20T19:18:02.978611Z] Loop 7991: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0860 +[2026-03-20T19:18:03.833455Z] Loop 7992: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0873 +[2026-03-20T19:18:04.689368Z] Loop 7993: Loss: 1.62e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0884 +[2026-03-20T19:18:05.545699Z] Loop 7994: Loss: 1.75e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0944 +[2026-03-20T19:18:06.401439Z] Loop 7995: Loss: 1.73e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0923 +[2026-03-20T19:18:07.256062Z] Loop 7996: Loss: 1.68e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0896 +[2026-03-20T19:18:08.112492Z] Loop 7997: Loss: 1.76e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0941 +[2026-03-20T19:18:08.968235Z] Loop 7998: Loss: 1.61e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0905 +[2026-03-20T19:18:09.823718Z] Loop 7999: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0916 +[2026-03-20T19:18:10.718714Z] Loop 8000: Loss: 1.74e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.0959 +[2026-03-20T19:18:11.573976Z] Loop 8001: Loss: 1.83e-02, Avg Return: 0.860, Regret: 0.0028, Entropy: 0.0982 +[2026-03-20T19:18:12.429229Z] Loop 8002: Loss: 1.85e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.0987 +[2026-03-20T19:18:13.285462Z] Loop 8003: Loss: 1.61e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.0861 +[2026-03-20T19:18:14.141493Z] Loop 8004: Loss: 1.67e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.0879 +[2026-03-20T19:18:14.997522Z] Loop 8005: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.0890 +[2026-03-20T19:18:15.852822Z] Loop 8006: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0028, Entropy: 0.0849 +[2026-03-20T19:18:16.707918Z] Loop 8007: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0028, Entropy: 0.0846 +[2026-03-20T19:18:17.563455Z] Loop 8008: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.0889 +[2026-03-20T19:18:18.419089Z] Loop 8009: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.0901 +[2026-03-20T19:18:19.313722Z] Loop 8010: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0923 +[2026-03-20T19:18:20.168973Z] Loop 8011: Loss: 1.93e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0989 +[2026-03-20T19:18:21.024777Z] Loop 8012: Loss: 2.01e-02, Avg Return: 0.860, Regret: 0.0014, Entropy: 0.1034 +[2026-03-20T19:18:21.881415Z] Loop 8013: Loss: 2.08e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.1063 +[2026-03-20T19:18:22.736472Z] Loop 8014: Loss: 1.92e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.0985 +[2026-03-20T19:18:23.591447Z] Loop 8015: Loss: 1.88e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.0984 +[2026-03-20T19:18:24.446652Z] Loop 8016: Loss: 1.96e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.0997 +[2026-03-20T19:18:25.301887Z] Loop 8017: Loss: 2.10e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.1038 +[2026-03-20T19:18:26.157153Z] Loop 8018: Loss: 2.16e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.1077 +[2026-03-20T19:18:27.011189Z] Loop 8019: Loss: 1.80e-02, Avg Return: 0.860, Regret: 0.0014, Entropy: 0.0986 +[2026-03-20T19:18:27.907223Z] Loop 8020: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.0930 +[2026-03-20T19:18:28.763058Z] Loop 8021: Loss: 1.69e-02, Avg Return: 0.860, Regret: 0.0023, Entropy: 0.0922 +[2026-03-20T19:18:29.619437Z] Loop 8022: Loss: 1.72e-02, Avg Return: 0.861, Regret: 0.0023, Entropy: 0.0891 +[2026-03-20T19:18:30.475514Z] Loop 8023: Loss: 1.72e-02, Avg Return: 0.859, Regret: 0.0023, Entropy: 0.0948 +[2026-03-20T19:18:31.330112Z] Loop 8024: Loss: 1.84e-02, Avg Return: 0.859, Regret: 0.0023, Entropy: 0.0967 +[2026-03-20T19:18:32.186359Z] Loop 8025: Loss: 1.97e-02, Avg Return: 0.857, Regret: 0.0023, Entropy: 0.1015 +[2026-03-20T19:18:33.041883Z] Loop 8026: Loss: 2.11e-02, Avg Return: 0.857, Regret: 0.0023, Entropy: 0.1103 +[2026-03-20T19:18:33.897092Z] Loop 8027: Loss: 2.01e-02, Avg Return: 0.858, Regret: 0.0023, Entropy: 0.1070 +[2026-03-20T19:18:34.752192Z] Loop 8028: Loss: 2.05e-02, Avg Return: 0.858, Regret: 0.0023, Entropy: 0.1033 +[2026-03-20T19:18:35.607541Z] Loop 8029: Loss: 2.31e-02, Avg Return: 0.857, Regret: 0.0023, Entropy: 0.1185 +[2026-03-20T19:18:36.502418Z] Loop 8030: Loss: 2.47e-02, Avg Return: 0.857, Regret: 0.0068, Entropy: 0.1282 +[2026-03-20T19:18:37.357864Z] Loop 8031: Loss: 2.33e-02, Avg Return: 0.857, Regret: 0.0068, Entropy: 0.1186 +[2026-03-20T19:18:38.212079Z] Loop 8032: Loss: 2.06e-02, Avg Return: 0.857, Regret: 0.0068, Entropy: 0.1082 +[2026-03-20T19:18:39.066544Z] Loop 8033: Loss: 2.00e-02, Avg Return: 0.856, Regret: 0.0068, Entropy: 0.1036 +[2026-03-20T19:18:39.921477Z] Loop 8034: Loss: 2.24e-02, Avg Return: 0.857, Regret: 0.0068, Entropy: 0.1104 +[2026-03-20T19:18:40.776596Z] Loop 8035: Loss: 2.23e-02, Avg Return: 0.857, Regret: 0.0068, Entropy: 0.1164 +[2026-03-20T19:18:41.631480Z] Loop 8036: Loss: 2.19e-02, Avg Return: 0.859, Regret: 0.0068, Entropy: 0.1163 +[2026-03-20T19:18:42.486375Z] Loop 8037: Loss: 2.12e-02, Avg Return: 0.860, Regret: 0.0068, Entropy: 0.1143 +[2026-03-20T19:18:43.341255Z] Loop 8038: Loss: 2.14e-02, Avg Return: 0.859, Regret: 0.0068, Entropy: 0.1170 +[2026-03-20T19:18:44.197042Z] Loop 8039: Loss: 2.28e-02, Avg Return: 0.860, Regret: 0.0068, Entropy: 0.1212 +[2026-03-20T19:18:45.095236Z] Loop 8040: Loss: 2.24e-02, Avg Return: 0.861, Regret: 0.0032, Entropy: 0.1156 +[2026-03-20T19:18:45.951549Z] Loop 8041: Loss: 2.35e-02, Avg Return: 0.860, Regret: 0.0032, Entropy: 0.1275 +[2026-03-20T19:18:46.805420Z] Loop 8042: Loss: 2.51e-02, Avg Return: 0.860, Regret: 0.0032, Entropy: 0.1272 +[2026-03-20T19:18:47.660318Z] Loop 8043: Loss: 2.44e-02, Avg Return: 0.859, Regret: 0.0032, Entropy: 0.1289 +[2026-03-20T19:18:48.516726Z] Loop 8044: Loss: 2.56e-02, Avg Return: 0.861, Regret: 0.0032, Entropy: 0.1337 +[2026-03-20T19:18:49.371392Z] Loop 8045: Loss: 2.80e-02, Avg Return: 0.861, Regret: 0.0032, Entropy: 0.1455 +[2026-03-20T19:18:50.226166Z] Loop 8046: Loss: 3.04e-02, Avg Return: 0.859, Regret: 0.0032, Entropy: 0.1468 +[2026-03-20T19:18:51.080525Z] Loop 8047: Loss: 3.01e-02, Avg Return: 0.860, Regret: 0.0032, Entropy: 0.1486 +[2026-03-20T19:18:51.936900Z] Loop 8048: Loss: 2.88e-02, Avg Return: 0.860, Regret: 0.0032, Entropy: 0.1462 +[2026-03-20T19:18:52.792382Z] Loop 8049: Loss: 2.66e-02, Avg Return: 0.858, Regret: 0.0032, Entropy: 0.1338 +[2026-03-20T19:18:53.686734Z] Loop 8050: Loss: 2.37e-02, Avg Return: 0.856, Regret: 0.0077, Entropy: 0.1225 +[2026-03-20T19:18:54.540883Z] Loop 8051: Loss: 2.23e-02, Avg Return: 0.853, Regret: 0.0077, Entropy: 0.1216 +[2026-03-20T19:18:55.396369Z] Loop 8052: Loss: 1.95e-02, Avg Return: 0.857, Regret: 0.0077, Entropy: 0.1104 +[2026-03-20T19:18:56.251129Z] Loop 8053: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0077, Entropy: 0.0980 +[2026-03-20T19:18:57.106242Z] Loop 8054: Loss: 1.80e-02, Avg Return: 0.864, Regret: 0.0077, Entropy: 0.0934 +[2026-03-20T19:18:57.961312Z] Loop 8055: Loss: 1.56e-02, Avg Return: 0.864, Regret: 0.0077, Entropy: 0.0841 +[2026-03-20T19:18:58.817682Z] Loop 8056: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0077, Entropy: 0.0843 +[2026-03-20T19:18:59.673281Z] Loop 8057: Loss: 1.73e-02, Avg Return: 0.861, Regret: 0.0077, Entropy: 0.0908 +[2026-03-20T19:19:00.528379Z] Loop 8058: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0077, Entropy: 0.0898 +[2026-03-20T19:19:01.384302Z] Loop 8059: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0077, Entropy: 0.0924 +[2026-03-20T19:19:02.277826Z] Loop 8060: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0949 +[2026-03-20T19:19:03.132456Z] Loop 8061: Loss: 1.68e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0908 +[2026-03-20T19:19:03.987348Z] Loop 8062: Loss: 1.82e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0928 +[2026-03-20T19:19:04.841938Z] Loop 8063: Loss: 1.79e-02, Avg Return: 0.860, Regret: 0.0013, Entropy: 0.0952 +[2026-03-20T19:19:05.696544Z] Loop 8064: Loss: 1.87e-02, Avg Return: 0.860, Regret: 0.0013, Entropy: 0.0990 +[2026-03-20T19:19:06.549908Z] Loop 8065: Loss: 1.96e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.1058 +[2026-03-20T19:19:07.402786Z] Loop 8066: Loss: 2.09e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.1052 +[2026-03-20T19:19:08.256468Z] Loop 8067: Loss: 2.10e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.1066 +[2026-03-20T19:19:09.110836Z] Loop 8068: Loss: 1.99e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.1014 +[2026-03-20T19:19:09.964113Z] Loop 8069: Loss: 2.11e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.1020 +[2026-03-20T19:19:10.857185Z] Loop 8070: Loss: 1.97e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.1024 +[2026-03-20T19:19:11.710800Z] Loop 8071: Loss: 2.04e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.1049 +[2026-03-20T19:19:12.565243Z] Loop 8072: Loss: 2.16e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.1058 +[2026-03-20T19:19:13.418882Z] Loop 8073: Loss: 2.15e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.1097 +[2026-03-20T19:19:14.271698Z] Loop 8074: Loss: 1.99e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.1017 +[2026-03-20T19:19:15.126261Z] Loop 8075: Loss: 1.97e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.1013 +[2026-03-20T19:19:15.979950Z] Loop 8076: Loss: 2.02e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.0999 +[2026-03-20T19:19:16.835233Z] Loop 8077: Loss: 1.88e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.0977 +[2026-03-20T19:19:17.688192Z] Loop 8078: Loss: 2.07e-02, Avg Return: 0.863, Regret: 0.0021, Entropy: 0.1018 +[2026-03-20T19:19:18.541783Z] Loop 8079: Loss: 1.87e-02, Avg Return: 0.863, Regret: 0.0021, Entropy: 0.0936 +[2026-03-20T19:19:19.438479Z] Loop 8080: Loss: 1.74e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0899 +[2026-03-20T19:19:20.292582Z] Loop 8081: Loss: 1.60e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0843 +[2026-03-20T19:19:21.146343Z] Loop 8082: Loss: 1.70e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0860 +[2026-03-20T19:19:21.999941Z] Loop 8083: Loss: 1.76e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0942 +[2026-03-20T19:19:22.853999Z] Loop 8084: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0943 +[2026-03-20T19:19:23.707914Z] Loop 8085: Loss: 1.79e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0926 +[2026-03-20T19:19:24.561982Z] Loop 8086: Loss: 2.10e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.1042 +[2026-03-20T19:19:25.415317Z] Loop 8087: Loss: 2.19e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.1073 +[2026-03-20T19:19:26.269358Z] Loop 8088: Loss: 2.14e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.1125 +[2026-03-20T19:19:27.123276Z] Loop 8089: Loss: 2.28e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.1149 +[2026-03-20T19:19:28.016681Z] Loop 8090: Loss: 2.46e-02, Avg Return: 0.859, Regret: 0.0033, Entropy: 0.1230 +[2026-03-20T19:19:28.870369Z] Loop 8091: Loss: 2.66e-02, Avg Return: 0.860, Regret: 0.0033, Entropy: 0.1274 +[2026-03-20T19:19:29.723414Z] Loop 8092: Loss: 2.65e-02, Avg Return: 0.859, Regret: 0.0033, Entropy: 0.1303 +[2026-03-20T19:19:30.577111Z] Loop 8093: Loss: 2.62e-02, Avg Return: 0.860, Regret: 0.0033, Entropy: 0.1293 +[2026-03-20T19:19:31.431341Z] Loop 8094: Loss: 2.56e-02, Avg Return: 0.860, Regret: 0.0033, Entropy: 0.1261 +[2026-03-20T19:19:32.285157Z] Loop 8095: Loss: 2.46e-02, Avg Return: 0.860, Regret: 0.0033, Entropy: 0.1226 +[2026-03-20T19:19:33.138159Z] Loop 8096: Loss: 2.38e-02, Avg Return: 0.860, Regret: 0.0033, Entropy: 0.1197 +[2026-03-20T19:19:33.991185Z] Loop 8097: Loss: 2.27e-02, Avg Return: 0.861, Regret: 0.0033, Entropy: 0.1144 +[2026-03-20T19:19:34.845548Z] Loop 8098: Loss: 2.14e-02, Avg Return: 0.861, Regret: 0.0033, Entropy: 0.1108 +[2026-03-20T19:19:35.700591Z] Loop 8099: Loss: 2.14e-02, Avg Return: 0.861, Regret: 0.0033, Entropy: 0.1090 +[2026-03-20T19:19:36.594660Z] Loop 8100: Loss: 2.10e-02, Avg Return: 0.859, Regret: 0.0028, Entropy: 0.1091 +[2026-03-20T19:19:37.447988Z] Loop 8101: Loss: 2.05e-02, Avg Return: 0.860, Regret: 0.0028, Entropy: 0.1077 +[2026-03-20T19:19:38.302104Z] Loop 8102: Loss: 2.08e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.1077 +[2026-03-20T19:19:39.158027Z] Loop 8103: Loss: 2.13e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.1097 +[2026-03-20T19:19:40.011765Z] Loop 8104: Loss: 2.22e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.1156 +[2026-03-20T19:19:40.864714Z] Loop 8105: Loss: 2.06e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.1072 +[2026-03-20T19:19:41.718611Z] Loop 8106: Loss: 2.07e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.1101 +[2026-03-20T19:19:42.574424Z] Loop 8107: Loss: 2.21e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.1131 +[2026-03-20T19:19:43.428556Z] Loop 8108: Loss: 2.06e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.1087 +[2026-03-20T19:19:44.283047Z] Loop 8109: Loss: 2.17e-02, Avg Return: 0.863, Regret: 0.0028, Entropy: 0.1118 +[2026-03-20T19:19:45.177694Z] Loop 8110: Loss: 2.28e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1134 +[2026-03-20T19:19:46.033407Z] Loop 8111: Loss: 2.15e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1141 +[2026-03-20T19:19:46.888388Z] Loop 8112: Loss: 2.21e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1166 +[2026-03-20T19:19:47.742292Z] Loop 8113: Loss: 2.26e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1130 +[2026-03-20T19:19:48.595716Z] Loop 8114: Loss: 2.22e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1130 +[2026-03-20T19:19:49.450086Z] Loop 8115: Loss: 2.19e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1157 +[2026-03-20T19:19:50.304616Z] Loop 8116: Loss: 2.19e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1132 +[2026-03-20T19:19:51.159838Z] Loop 8117: Loss: 2.22e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.1169 +[2026-03-20T19:19:52.013846Z] Loop 8118: Loss: 2.22e-02, Avg Return: 0.860, Regret: 0.0013, Entropy: 0.1153 +[2026-03-20T19:19:52.868438Z] Loop 8119: Loss: 2.23e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1184 +[2026-03-20T19:19:53.762088Z] Loop 8120: Loss: 2.31e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.1212 +[2026-03-20T19:19:54.615751Z] Loop 8121: Loss: 2.50e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.1293 +[2026-03-20T19:19:55.469778Z] Loop 8122: Loss: 2.58e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.1391 +[2026-03-20T19:19:56.325086Z] Loop 8123: Loss: 2.94e-02, Avg Return: 0.859, Regret: 0.0027, Entropy: 0.1490 +[2026-03-20T19:19:57.179261Z] Loop 8124: Loss: 2.68e-02, Avg Return: 0.860, Regret: 0.0027, Entropy: 0.1431 +[2026-03-20T19:19:58.034139Z] Loop 8125: Loss: 2.77e-02, Avg Return: 0.860, Regret: 0.0027, Entropy: 0.1446 +[2026-03-20T19:19:58.889353Z] Loop 8126: Loss: 2.62e-02, Avg Return: 0.860, Regret: 0.0027, Entropy: 0.1385 +[2026-03-20T19:19:59.743852Z] Loop 8127: Loss: 2.59e-02, Avg Return: 0.859, Regret: 0.0027, Entropy: 0.1386 +[2026-03-20T19:20:00.597045Z] Loop 8128: Loss: 2.47e-02, Avg Return: 0.860, Regret: 0.0027, Entropy: 0.1328 +[2026-03-20T19:20:01.449731Z] Loop 8129: Loss: 2.38e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.1268 +[2026-03-20T19:20:02.344711Z] Loop 8130: Loss: 2.25e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.1192 +[2026-03-20T19:20:03.199776Z] Loop 8131: Loss: 2.12e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.1117 +[2026-03-20T19:20:04.053007Z] Loop 8132: Loss: 2.05e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.1090 +[2026-03-20T19:20:04.907000Z] Loop 8133: Loss: 2.20e-02, Avg Return: 0.863, Regret: 0.0025, Entropy: 0.1089 +[2026-03-20T19:20:05.760875Z] Loop 8134: Loss: 2.20e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.1105 +[2026-03-20T19:20:06.614537Z] Loop 8135: Loss: 2.22e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.1126 +[2026-03-20T19:20:07.468293Z] Loop 8136: Loss: 2.33e-02, Avg Return: 0.864, Regret: 0.0025, Entropy: 0.1130 +[2026-03-20T19:20:08.321238Z] Loop 8137: Loss: 2.49e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.1209 +[2026-03-20T19:20:09.173829Z] Loop 8138: Loss: 2.40e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.1166 +[2026-03-20T19:20:10.027887Z] Loop 8139: Loss: 2.40e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.1191 +[2026-03-20T19:20:10.921325Z] Loop 8140: Loss: 2.41e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1207 +[2026-03-20T19:20:11.775195Z] Loop 8141: Loss: 2.54e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.1227 +[2026-03-20T19:20:12.629376Z] Loop 8142: Loss: 2.27e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.1126 +[2026-03-20T19:20:13.482502Z] Loop 8143: Loss: 1.86e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0949 +[2026-03-20T19:20:14.335933Z] Loop 8144: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0917 +[2026-03-20T19:20:15.189917Z] Loop 8145: Loss: 1.91e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0979 +[2026-03-20T19:20:16.044306Z] Loop 8146: Loss: 2.03e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.1013 +[2026-03-20T19:20:16.898374Z] Loop 8147: Loss: 1.91e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.1018 +[2026-03-20T19:20:17.752459Z] Loop 8148: Loss: 1.84e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0979 +[2026-03-20T19:20:18.605768Z] Loop 8149: Loss: 1.78e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0877 +[2026-03-20T19:20:19.503996Z] Loop 8150: Loss: 1.92e-02, Avg Return: 0.860, Regret: 0.0048, Entropy: 0.1022 +[2026-03-20T19:20:20.356419Z] Loop 8151: Loss: 2.07e-02, Avg Return: 0.859, Regret: 0.0048, Entropy: 0.1030 +[2026-03-20T19:20:21.210034Z] Loop 8152: Loss: 1.93e-02, Avg Return: 0.859, Regret: 0.0048, Entropy: 0.0999 +[2026-03-20T19:20:22.064047Z] Loop 8153: Loss: 1.88e-02, Avg Return: 0.857, Regret: 0.0048, Entropy: 0.0991 +[2026-03-20T19:20:22.918444Z] Loop 8154: Loss: 1.83e-02, Avg Return: 0.858, Regret: 0.0048, Entropy: 0.0956 +[2026-03-20T19:20:23.771620Z] Loop 8155: Loss: 1.75e-02, Avg Return: 0.859, Regret: 0.0048, Entropy: 0.0921 +[2026-03-20T19:20:24.624573Z] Loop 8156: Loss: 1.75e-02, Avg Return: 0.861, Regret: 0.0048, Entropy: 0.0919 +[2026-03-20T19:20:25.479130Z] Loop 8157: Loss: 1.78e-02, Avg Return: 0.859, Regret: 0.0048, Entropy: 0.0943 +[2026-03-20T19:20:26.333238Z] Loop 8158: Loss: 1.82e-02, Avg Return: 0.861, Regret: 0.0048, Entropy: 0.0952 +[2026-03-20T19:20:27.186348Z] Loop 8159: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0048, Entropy: 0.0902 +[2026-03-20T19:20:28.079047Z] Loop 8160: Loss: 1.74e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0873 +[2026-03-20T19:20:28.932737Z] Loop 8161: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0924 +[2026-03-20T19:20:29.786453Z] Loop 8162: Loss: 1.77e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0945 +[2026-03-20T19:20:30.640362Z] Loop 8163: Loss: 1.90e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0978 +[2026-03-20T19:20:31.493929Z] Loop 8164: Loss: 1.91e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0988 +[2026-03-20T19:20:32.347589Z] Loop 8165: Loss: 1.90e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0972 +[2026-03-20T19:20:33.202953Z] Loop 8166: Loss: 1.77e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0923 +[2026-03-20T19:20:34.058075Z] Loop 8167: Loss: 1.72e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0960 +[2026-03-20T19:20:34.914047Z] Loop 8168: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0879 +[2026-03-20T19:20:35.768383Z] Loop 8169: Loss: 1.88e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0972 +[2026-03-20T19:20:36.664227Z] Loop 8170: Loss: 1.90e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.1009 +[2026-03-20T19:20:37.518849Z] Loop 8171: Loss: 2.07e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.1047 +[2026-03-20T19:20:38.373254Z] Loop 8172: Loss: 2.06e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.1085 +[2026-03-20T19:20:39.226413Z] Loop 8173: Loss: 2.16e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.1062 +[2026-03-20T19:20:40.081235Z] Loop 8174: Loss: 2.28e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.1126 +[2026-03-20T19:20:40.934528Z] Loop 8175: Loss: 2.37e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.1197 +[2026-03-20T19:20:41.789799Z] Loop 8176: Loss: 2.43e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.1242 +[2026-03-20T19:20:42.643629Z] Loop 8177: Loss: 2.49e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.1244 +[2026-03-20T19:20:43.497644Z] Loop 8178: Loss: 2.47e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.1233 +[2026-03-20T19:20:44.351106Z] Loop 8179: Loss: 2.51e-02, Avg Return: 0.860, Regret: 0.0014, Entropy: 0.1249 +[2026-03-20T19:20:45.244697Z] Loop 8180: Loss: 2.49e-02, Avg Return: 0.861, Regret: 0.0023, Entropy: 0.1236 +[2026-03-20T19:20:46.099404Z] Loop 8181: Loss: 2.43e-02, Avg Return: 0.861, Regret: 0.0023, Entropy: 0.1217 +[2026-03-20T19:20:46.953508Z] Loop 8182: Loss: 2.45e-02, Avg Return: 0.860, Regret: 0.0023, Entropy: 0.1223 +[2026-03-20T19:20:47.806960Z] Loop 8183: Loss: 2.34e-02, Avg Return: 0.861, Regret: 0.0023, Entropy: 0.1177 +[2026-03-20T19:20:48.660960Z] Loop 8184: Loss: 2.58e-02, Avg Return: 0.861, Regret: 0.0023, Entropy: 0.1243 +[2026-03-20T19:20:49.516618Z] Loop 8185: Loss: 2.47e-02, Avg Return: 0.861, Regret: 0.0023, Entropy: 0.1264 +[2026-03-20T19:20:50.370363Z] Loop 8186: Loss: 2.56e-02, Avg Return: 0.860, Regret: 0.0023, Entropy: 0.1214 +[2026-03-20T19:20:51.223440Z] Loop 8187: Loss: 2.39e-02, Avg Return: 0.861, Regret: 0.0023, Entropy: 0.1207 +[2026-03-20T19:20:52.076963Z] Loop 8188: Loss: 2.41e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.1228 +[2026-03-20T19:20:52.932058Z] Loop 8189: Loss: 2.46e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.1224 +[2026-03-20T19:20:53.826664Z] Loop 8190: Loss: 2.32e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.1193 +[2026-03-20T19:20:54.680896Z] Loop 8191: Loss: 2.13e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.1071 +[2026-03-20T19:20:55.535328Z] Loop 8192: Loss: 1.99e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.1050 +[2026-03-20T19:20:56.390131Z] Loop 8193: Loss: 2.06e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.1041 +[2026-03-20T19:20:57.244354Z] Loop 8194: Loss: 2.20e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.1107 +[2026-03-20T19:20:58.098163Z] Loop 8195: Loss: 2.24e-02, Avg Return: 0.859, Regret: 0.0020, Entropy: 0.1179 +[2026-03-20T19:20:58.951781Z] Loop 8196: Loss: 2.28e-02, Avg Return: 0.860, Regret: 0.0020, Entropy: 0.1200 +[2026-03-20T19:20:59.806835Z] Loop 8197: Loss: 2.33e-02, Avg Return: 0.859, Regret: 0.0020, Entropy: 0.1234 +[2026-03-20T19:21:00.661586Z] Loop 8198: Loss: 2.82e-02, Avg Return: 0.858, Regret: 0.0020, Entropy: 0.1414 +[2026-03-20T19:21:01.516030Z] Loop 8199: Loss: 3.02e-02, Avg Return: 0.859, Regret: 0.0020, Entropy: 0.1505 +[2026-03-20T19:21:02.410845Z] Loop 8200: Loss: 2.81e-02, Avg Return: 0.861, Regret: 0.0040, Entropy: 0.1412 +[2026-03-20T19:21:03.266402Z] Loop 8201: Loss: 2.51e-02, Avg Return: 0.862, Regret: 0.0040, Entropy: 0.1288 +[2026-03-20T19:21:04.122068Z] Loop 8202: Loss: 2.27e-02, Avg Return: 0.862, Regret: 0.0040, Entropy: 0.1155 +[2026-03-20T19:21:04.976936Z] Loop 8203: Loss: 1.99e-02, Avg Return: 0.863, Regret: 0.0040, Entropy: 0.1069 +[2026-03-20T19:21:05.831667Z] Loop 8204: Loss: 1.97e-02, Avg Return: 0.861, Regret: 0.0040, Entropy: 0.1072 +[2026-03-20T19:21:06.685394Z] Loop 8205: Loss: 2.23e-02, Avg Return: 0.860, Regret: 0.0040, Entropy: 0.1132 +[2026-03-20T19:21:07.539128Z] Loop 8206: Loss: 2.09e-02, Avg Return: 0.862, Regret: 0.0040, Entropy: 0.1097 +[2026-03-20T19:21:08.392661Z] Loop 8207: Loss: 2.15e-02, Avg Return: 0.862, Regret: 0.0040, Entropy: 0.1085 +[2026-03-20T19:21:09.246499Z] Loop 8208: Loss: 2.05e-02, Avg Return: 0.861, Regret: 0.0040, Entropy: 0.1067 +[2026-03-20T19:21:10.100366Z] Loop 8209: Loss: 2.17e-02, Avg Return: 0.862, Regret: 0.0040, Entropy: 0.1079 +[2026-03-20T19:21:10.993788Z] Loop 8210: Loss: 2.09e-02, Avg Return: 0.860, Regret: 0.0014, Entropy: 0.1086 +[2026-03-20T19:21:11.848726Z] Loop 8211: Loss: 2.12e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.1065 +[2026-03-20T19:21:12.704022Z] Loop 8212: Loss: 2.05e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.1037 +[2026-03-20T19:21:13.558232Z] Loop 8213: Loss: 2.09e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.1054 +[2026-03-20T19:21:14.411967Z] Loop 8214: Loss: 1.98e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.1059 +[2026-03-20T19:21:15.266252Z] Loop 8215: Loss: 2.15e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.1090 +[2026-03-20T19:21:16.121690Z] Loop 8216: Loss: 2.20e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.1100 +[2026-03-20T19:21:16.976922Z] Loop 8217: Loss: 2.13e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.1104 +[2026-03-20T19:21:17.832063Z] Loop 8218: Loss: 2.02e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.1068 +[2026-03-20T19:21:18.686512Z] Loop 8219: Loss: 1.86e-02, Avg Return: 0.860, Regret: 0.0014, Entropy: 0.0949 +[2026-03-20T19:21:19.584025Z] Loop 8220: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0911 +[2026-03-20T19:21:20.438657Z] Loop 8221: Loss: 1.67e-02, Avg Return: 0.860, Regret: 0.0025, Entropy: 0.0939 +[2026-03-20T19:21:21.293234Z] Loop 8222: Loss: 1.91e-02, Avg Return: 0.859, Regret: 0.0025, Entropy: 0.1027 +[2026-03-20T19:21:22.147042Z] Loop 8223: Loss: 2.02e-02, Avg Return: 0.859, Regret: 0.0025, Entropy: 0.1058 +[2026-03-20T19:21:23.000992Z] Loop 8224: Loss: 2.01e-02, Avg Return: 0.860, Regret: 0.0025, Entropy: 0.1044 +[2026-03-20T19:21:23.856420Z] Loop 8225: Loss: 1.90e-02, Avg Return: 0.860, Regret: 0.0025, Entropy: 0.1022 +[2026-03-20T19:21:24.711805Z] Loop 8226: Loss: 1.92e-02, Avg Return: 0.860, Regret: 0.0025, Entropy: 0.0983 +[2026-03-20T19:21:25.566195Z] Loop 8227: Loss: 1.92e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.1006 +[2026-03-20T19:21:26.421776Z] Loop 8228: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.1031 +[2026-03-20T19:21:27.277387Z] Loop 8229: Loss: 1.88e-02, Avg Return: 0.859, Regret: 0.0025, Entropy: 0.0970 +[2026-03-20T19:21:28.172566Z] Loop 8230: Loss: 1.96e-02, Avg Return: 0.860, Regret: 0.0028, Entropy: 0.1005 +[2026-03-20T19:21:29.027001Z] Loop 8231: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.1006 +[2026-03-20T19:21:29.881147Z] Loop 8232: Loss: 1.71e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.0936 +[2026-03-20T19:21:30.733907Z] Loop 8233: Loss: 1.82e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.0959 +[2026-03-20T19:21:31.587994Z] Loop 8234: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.0892 +[2026-03-20T19:21:32.442344Z] Loop 8235: Loss: 1.79e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.0970 +[2026-03-20T19:21:33.297741Z] Loop 8236: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.0976 +[2026-03-20T19:21:34.151659Z] Loop 8237: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0028, Entropy: 0.0930 +[2026-03-20T19:21:35.005396Z] Loop 8238: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0028, Entropy: 0.0951 +[2026-03-20T19:21:35.859228Z] Loop 8239: Loss: 1.78e-02, Avg Return: 0.863, Regret: 0.0028, Entropy: 0.0917 +[2026-03-20T19:21:36.751987Z] Loop 8240: Loss: 1.75e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0928 +[2026-03-20T19:21:37.604984Z] Loop 8241: Loss: 1.79e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0939 +[2026-03-20T19:21:38.459411Z] Loop 8242: Loss: 1.82e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0936 +[2026-03-20T19:21:39.313827Z] Loop 8243: Loss: 1.87e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0984 +[2026-03-20T19:21:40.169287Z] Loop 8244: Loss: 2.03e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.1031 +[2026-03-20T19:21:41.022773Z] Loop 8245: Loss: 1.97e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.1016 +[2026-03-20T19:21:41.875491Z] Loop 8246: Loss: 2.08e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.1024 +[2026-03-20T19:21:42.729046Z] Loop 8247: Loss: 2.06e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.1116 +[2026-03-20T19:21:43.582865Z] Loop 8248: Loss: 2.00e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.1085 +[2026-03-20T19:21:44.436717Z] Loop 8249: Loss: 2.27e-02, Avg Return: 0.858, Regret: 0.0009, Entropy: 0.1188 +[2026-03-20T19:21:45.330829Z] Loop 8250: Loss: 2.38e-02, Avg Return: 0.859, Regret: 0.0045, Entropy: 0.1249 +[2026-03-20T19:21:46.185234Z] Loop 8251: Loss: 2.44e-02, Avg Return: 0.860, Regret: 0.0045, Entropy: 0.1243 +[2026-03-20T19:21:47.039458Z] Loop 8252: Loss: 2.32e-02, Avg Return: 0.862, Regret: 0.0045, Entropy: 0.1141 +[2026-03-20T19:21:47.893672Z] Loop 8253: Loss: 2.32e-02, Avg Return: 0.862, Regret: 0.0045, Entropy: 0.1132 +[2026-03-20T19:21:48.747782Z] Loop 8254: Loss: 2.26e-02, Avg Return: 0.862, Regret: 0.0045, Entropy: 0.1138 +[2026-03-20T19:21:49.601152Z] Loop 8255: Loss: 2.40e-02, Avg Return: 0.863, Regret: 0.0045, Entropy: 0.1141 +[2026-03-20T19:21:50.454466Z] Loop 8256: Loss: 2.34e-02, Avg Return: 0.863, Regret: 0.0045, Entropy: 0.1162 +[2026-03-20T19:21:51.308158Z] Loop 8257: Loss: 2.32e-02, Avg Return: 0.862, Regret: 0.0045, Entropy: 0.1101 +[2026-03-20T19:21:52.162992Z] Loop 8258: Loss: 2.28e-02, Avg Return: 0.862, Regret: 0.0045, Entropy: 0.1128 +[2026-03-20T19:21:53.017423Z] Loop 8259: Loss: 2.07e-02, Avg Return: 0.862, Regret: 0.0045, Entropy: 0.1002 +[2026-03-20T19:21:53.911999Z] Loop 8260: Loss: 1.85e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0896 +[2026-03-20T19:21:54.766141Z] Loop 8261: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0842 +[2026-03-20T19:21:55.620674Z] Loop 8262: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0832 +[2026-03-20T19:21:56.475203Z] Loop 8263: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0805 +[2026-03-20T19:21:57.328444Z] Loop 8264: Loss: 1.64e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0824 +[2026-03-20T19:21:58.182900Z] Loop 8265: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0818 +[2026-03-20T19:21:59.037410Z] Loop 8266: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0794 +[2026-03-20T19:21:59.891637Z] Loop 8267: Loss: 1.62e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0852 +[2026-03-20T19:22:00.745163Z] Loop 8268: Loss: 1.65e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0885 +[2026-03-20T19:22:01.599437Z] Loop 8269: Loss: 1.87e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0983 +[2026-03-20T19:22:02.493158Z] Loop 8270: Loss: 2.06e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.1011 +[2026-03-20T19:22:03.347407Z] Loop 8271: Loss: 2.09e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.1014 +[2026-03-20T19:22:04.201693Z] Loop 8272: Loss: 1.96e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.1006 +[2026-03-20T19:22:05.054994Z] Loop 8273: Loss: 2.04e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.1014 +[2026-03-20T19:22:05.907891Z] Loop 8274: Loss: 2.03e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0988 +[2026-03-20T19:22:06.763098Z] Loop 8275: Loss: 2.03e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0989 +[2026-03-20T19:22:07.617650Z] Loop 8276: Loss: 1.97e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0961 +[2026-03-20T19:22:08.471840Z] Loop 8277: Loss: 1.84e-02, Avg Return: 0.864, Regret: 0.0014, Entropy: 0.0930 +[2026-03-20T19:22:09.325128Z] Loop 8278: Loss: 1.86e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0922 +[2026-03-20T19:22:10.179166Z] Loop 8279: Loss: 1.90e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0942 +[2026-03-20T19:22:11.074277Z] Loop 8280: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0877 +[2026-03-20T19:22:11.928166Z] Loop 8281: Loss: 1.65e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.0853 +[2026-03-20T19:22:12.781749Z] Loop 8282: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0815 +[2026-03-20T19:22:13.635622Z] Loop 8283: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0782 +[2026-03-20T19:22:14.489461Z] Loop 8284: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0819 +[2026-03-20T19:22:15.343561Z] Loop 8285: Loss: 1.71e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.0894 +[2026-03-20T19:22:16.197159Z] Loop 8286: Loss: 2.01e-02, Avg Return: 0.859, Regret: 0.0006, Entropy: 0.1004 +[2026-03-20T19:22:17.051453Z] Loop 8287: Loss: 2.11e-02, Avg Return: 0.855, Regret: 0.0006, Entropy: 0.1027 +[2026-03-20T19:22:17.905439Z] Loop 8288: Loss: 2.23e-02, Avg Return: 0.855, Regret: 0.0006, Entropy: 0.1102 +[2026-03-20T19:22:18.759018Z] Loop 8289: Loss: 2.10e-02, Avg Return: 0.852, Regret: 0.0006, Entropy: 0.1099 +[2026-03-20T19:22:19.652436Z] Loop 8290: Loss: 2.21e-02, Avg Return: 0.855, Regret: 0.0074, Entropy: 0.1098 +[2026-03-20T19:22:20.505898Z] Loop 8291: Loss: 2.16e-02, Avg Return: 0.858, Regret: 0.0074, Entropy: 0.1067 +[2026-03-20T19:22:21.359213Z] Loop 8292: Loss: 1.97e-02, Avg Return: 0.861, Regret: 0.0074, Entropy: 0.1008 +[2026-03-20T19:22:22.212675Z] Loop 8293: Loss: 2.06e-02, Avg Return: 0.859, Regret: 0.0074, Entropy: 0.0986 +[2026-03-20T19:22:23.066432Z] Loop 8294: Loss: 2.00e-02, Avg Return: 0.860, Regret: 0.0074, Entropy: 0.1014 +[2026-03-20T19:22:23.921061Z] Loop 8295: Loss: 1.91e-02, Avg Return: 0.861, Regret: 0.0074, Entropy: 0.0991 +[2026-03-20T19:22:24.774037Z] Loop 8296: Loss: 2.10e-02, Avg Return: 0.862, Regret: 0.0074, Entropy: 0.0998 +[2026-03-20T19:22:25.628253Z] Loop 8297: Loss: 1.83e-02, Avg Return: 0.862, Regret: 0.0074, Entropy: 0.0901 +[2026-03-20T19:22:26.481752Z] Loop 8298: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0074, Entropy: 0.0873 +[2026-03-20T19:22:27.335909Z] Loop 8299: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0074, Entropy: 0.0840 +[2026-03-20T19:22:28.228835Z] Loop 8300: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0853 +[2026-03-20T19:22:29.082144Z] Loop 8301: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0827 +[2026-03-20T19:22:29.936820Z] Loop 8302: Loss: 1.52e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0803 +[2026-03-20T19:22:30.791848Z] Loop 8303: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0807 +[2026-03-20T19:22:31.645769Z] Loop 8304: Loss: 1.67e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0860 +[2026-03-20T19:22:32.499313Z] Loop 8305: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0885 +[2026-03-20T19:22:33.353772Z] Loop 8306: Loss: 1.90e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0950 +[2026-03-20T19:22:34.207915Z] Loop 8307: Loss: 1.99e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0999 +[2026-03-20T19:22:35.062057Z] Loop 8308: Loss: 2.06e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.1030 +[2026-03-20T19:22:35.915335Z] Loop 8309: Loss: 2.08e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.1040 +[2026-03-20T19:22:36.811698Z] Loop 8310: Loss: 2.10e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.1053 +[2026-03-20T19:22:37.665144Z] Loop 8311: Loss: 2.17e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.1046 +[2026-03-20T19:22:38.518868Z] Loop 8312: Loss: 2.26e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.1085 +[2026-03-20T19:22:39.372648Z] Loop 8313: Loss: 2.28e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.1121 +[2026-03-20T19:22:40.227149Z] Loop 8314: Loss: 2.26e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.1156 +[2026-03-20T19:22:41.080628Z] Loop 8315: Loss: 2.42e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.1207 +[2026-03-20T19:22:41.934261Z] Loop 8316: Loss: 2.15e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.1112 +[2026-03-20T19:22:42.788382Z] Loop 8317: Loss: 2.24e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.1105 +[2026-03-20T19:22:43.642130Z] Loop 8318: Loss: 2.09e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.1068 +[2026-03-20T19:22:44.495355Z] Loop 8319: Loss: 2.01e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0997 +[2026-03-20T19:22:45.388492Z] Loop 8320: Loss: 1.90e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0970 +[2026-03-20T19:22:46.242888Z] Loop 8321: Loss: 1.79e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0916 +[2026-03-20T19:22:47.097973Z] Loop 8322: Loss: 1.79e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0917 +[2026-03-20T19:22:47.951871Z] Loop 8323: Loss: 1.76e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0893 +[2026-03-20T19:22:48.806373Z] Loop 8324: Loss: 1.83e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0929 +[2026-03-20T19:22:49.660503Z] Loop 8325: Loss: 1.81e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0925 +[2026-03-20T19:22:50.515322Z] Loop 8326: Loss: 1.80e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0922 +[2026-03-20T19:22:51.368641Z] Loop 8327: Loss: 1.79e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0912 +[2026-03-20T19:22:52.222406Z] Loop 8328: Loss: 1.87e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0963 +[2026-03-20T19:22:53.077059Z] Loop 8329: Loss: 1.89e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0944 +[2026-03-20T19:22:53.971928Z] Loop 8330: Loss: 1.78e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0894 +[2026-03-20T19:22:54.826714Z] Loop 8331: Loss: 1.79e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0880 +[2026-03-20T19:22:55.680859Z] Loop 8332: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0866 +[2026-03-20T19:22:56.533580Z] Loop 8333: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0840 +[2026-03-20T19:22:57.387578Z] Loop 8334: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0842 +[2026-03-20T19:22:58.241202Z] Loop 8335: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0815 +[2026-03-20T19:22:59.094275Z] Loop 8336: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0810 +[2026-03-20T19:22:59.947302Z] Loop 8337: Loss: 1.56e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0794 +[2026-03-20T19:23:00.801868Z] Loop 8338: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0765 +[2026-03-20T19:23:01.656588Z] Loop 8339: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0829 +[2026-03-20T19:23:02.550129Z] Loop 8340: Loss: 1.43e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0758 +[2026-03-20T19:23:03.403421Z] Loop 8341: Loss: 1.43e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0786 +[2026-03-20T19:23:04.257395Z] Loop 8342: Loss: 1.57e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0835 +[2026-03-20T19:23:05.111313Z] Loop 8343: Loss: 1.46e-02, Avg Return: 0.860, Regret: 0.0011, Entropy: 0.0797 +[2026-03-20T19:23:05.965279Z] Loop 8344: Loss: 1.59e-02, Avg Return: 0.859, Regret: 0.0011, Entropy: 0.0808 +[2026-03-20T19:23:06.817315Z] Loop 8345: Loss: 1.63e-02, Avg Return: 0.860, Regret: 0.0011, Entropy: 0.0819 +[2026-03-20T19:23:07.670024Z] Loop 8346: Loss: 1.48e-02, Avg Return: 0.858, Regret: 0.0011, Entropy: 0.0769 +[2026-03-20T19:23:08.523806Z] Loop 8347: Loss: 1.51e-02, Avg Return: 0.859, Regret: 0.0011, Entropy: 0.0825 +[2026-03-20T19:23:09.378014Z] Loop 8348: Loss: 1.47e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0772 +[2026-03-20T19:23:10.231986Z] Loop 8349: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0852 +[2026-03-20T19:23:11.124739Z] Loop 8350: Loss: 1.54e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0821 +[2026-03-20T19:23:11.979011Z] Loop 8351: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0792 +[2026-03-20T19:23:12.833855Z] Loop 8352: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0819 +[2026-03-20T19:23:13.687635Z] Loop 8353: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0867 +[2026-03-20T19:23:14.542143Z] Loop 8354: Loss: 1.51e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0821 +[2026-03-20T19:23:15.396179Z] Loop 8355: Loss: 1.64e-02, Avg Return: 0.865, Regret: 0.0012, Entropy: 0.0876 +[2026-03-20T19:23:16.249937Z] Loop 8356: Loss: 1.63e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0853 +[2026-03-20T19:23:17.104935Z] Loop 8357: Loss: 1.65e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0865 +[2026-03-20T19:23:17.960362Z] Loop 8358: Loss: 1.79e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0899 +[2026-03-20T19:23:18.814074Z] Loop 8359: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0926 +[2026-03-20T19:23:19.708056Z] Loop 8360: Loss: 1.94e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0934 +[2026-03-20T19:23:20.562385Z] Loop 8361: Loss: 1.78e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0949 +[2026-03-20T19:23:21.417469Z] Loop 8362: Loss: 1.86e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0941 +[2026-03-20T19:23:22.271473Z] Loop 8363: Loss: 1.97e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0957 +[2026-03-20T19:23:23.125266Z] Loop 8364: Loss: 1.86e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0921 +[2026-03-20T19:23:23.980460Z] Loop 8365: Loss: 1.82e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0967 +[2026-03-20T19:23:24.837371Z] Loop 8366: Loss: 1.85e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0997 +[2026-03-20T19:23:25.691054Z] Loop 8367: Loss: 2.07e-02, Avg Return: 0.861, Regret: 0.0004, Entropy: 0.1060 +[2026-03-20T19:23:26.544487Z] Loop 8368: Loss: 1.91e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0964 +[2026-03-20T19:23:27.397953Z] Loop 8369: Loss: 2.06e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.1034 +[2026-03-20T19:23:28.292144Z] Loop 8370: Loss: 1.91e-02, Avg Return: 0.860, Regret: 0.0014, Entropy: 0.0992 +[2026-03-20T19:23:29.146129Z] Loop 8371: Loss: 1.93e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.1000 +[2026-03-20T19:23:29.999949Z] Loop 8372: Loss: 2.05e-02, Avg Return: 0.860, Regret: 0.0014, Entropy: 0.1042 +[2026-03-20T19:23:30.853169Z] Loop 8373: Loss: 2.06e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.1042 +[2026-03-20T19:23:31.707546Z] Loop 8374: Loss: 2.02e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.1021 +[2026-03-20T19:23:32.561166Z] Loop 8375: Loss: 2.02e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.1021 +[2026-03-20T19:23:33.414559Z] Loop 8376: Loss: 1.94e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0943 +[2026-03-20T19:23:34.268198Z] Loop 8377: Loss: 1.77e-02, Avg Return: 0.864, Regret: 0.0014, Entropy: 0.0925 +[2026-03-20T19:23:35.121163Z] Loop 8378: Loss: 1.69e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0923 +[2026-03-20T19:23:35.974759Z] Loop 8379: Loss: 1.81e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0951 +[2026-03-20T19:23:36.869651Z] Loop 8380: Loss: 1.72e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0902 +[2026-03-20T19:23:37.723196Z] Loop 8381: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0928 +[2026-03-20T19:23:38.577008Z] Loop 8382: Loss: 1.71e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0912 +[2026-03-20T19:23:39.432007Z] Loop 8383: Loss: 1.94e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0995 +[2026-03-20T19:23:40.285454Z] Loop 8384: Loss: 1.88e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.1016 +[2026-03-20T19:23:41.139933Z] Loop 8385: Loss: 2.17e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.1075 +[2026-03-20T19:23:41.993449Z] Loop 8386: Loss: 2.05e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.1048 +[2026-03-20T19:23:42.847332Z] Loop 8387: Loss: 2.15e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.1113 +[2026-03-20T19:23:43.702561Z] Loop 8388: Loss: 2.33e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.1154 +[2026-03-20T19:23:44.556762Z] Loop 8389: Loss: 2.27e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.1114 +[2026-03-20T19:23:45.451108Z] Loop 8390: Loss: 2.47e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.1189 +[2026-03-20T19:23:46.305718Z] Loop 8391: Loss: 2.29e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.1172 +[2026-03-20T19:23:47.160824Z] Loop 8392: Loss: 2.27e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.1113 +[2026-03-20T19:23:48.017318Z] Loop 8393: Loss: 2.04e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.1064 +[2026-03-20T19:23:48.873545Z] Loop 8394: Loss: 1.82e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0968 +[2026-03-20T19:23:49.728308Z] Loop 8395: Loss: 1.75e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0929 +[2026-03-20T19:23:50.582724Z] Loop 8396: Loss: 1.67e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0894 +[2026-03-20T19:23:51.438526Z] Loop 8397: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0880 +[2026-03-20T19:23:52.293746Z] Loop 8398: Loss: 1.57e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0784 +[2026-03-20T19:23:53.147433Z] Loop 8399: Loss: 1.47e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0777 +[2026-03-20T19:23:54.041487Z] Loop 8400: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0833 +[2026-03-20T19:23:54.895916Z] Loop 8401: Loss: 1.64e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0847 +[2026-03-20T19:23:55.749304Z] Loop 8402: Loss: 1.56e-02, Avg Return: 0.861, Regret: 0.0004, Entropy: 0.0850 +[2026-03-20T19:23:56.603624Z] Loop 8403: Loss: 1.53e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0823 +[2026-03-20T19:23:57.457790Z] Loop 8404: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0837 +[2026-03-20T19:23:58.311963Z] Loop 8405: Loss: 1.73e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0854 +[2026-03-20T19:23:59.166404Z] Loop 8406: Loss: 1.63e-02, Avg Return: 0.865, Regret: 0.0004, Entropy: 0.0856 +[2026-03-20T19:24:00.021410Z] Loop 8407: Loss: 1.73e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0914 +[2026-03-20T19:24:00.876295Z] Loop 8408: Loss: 1.75e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0913 +[2026-03-20T19:24:01.731751Z] Loop 8409: Loss: 1.84e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0924 +[2026-03-20T19:24:02.626284Z] Loop 8410: Loss: 1.96e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0990 +[2026-03-20T19:24:03.479984Z] Loop 8411: Loss: 2.15e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.1057 +[2026-03-20T19:24:04.334540Z] Loop 8412: Loss: 2.00e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.1022 +[2026-03-20T19:24:05.188207Z] Loop 8413: Loss: 1.98e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.1043 +[2026-03-20T19:24:06.041201Z] Loop 8414: Loss: 2.10e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.1031 +[2026-03-20T19:24:06.894883Z] Loop 8415: Loss: 2.15e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.1082 +[2026-03-20T19:24:07.748837Z] Loop 8416: Loss: 2.13e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.1068 +[2026-03-20T19:24:08.603121Z] Loop 8417: Loss: 1.99e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.1034 +[2026-03-20T19:24:09.457282Z] Loop 8418: Loss: 1.98e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.1018 +[2026-03-20T19:24:10.310891Z] Loop 8419: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0954 +[2026-03-20T19:24:11.205934Z] Loop 8420: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0909 +[2026-03-20T19:24:12.060411Z] Loop 8421: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0904 +[2026-03-20T19:24:12.914223Z] Loop 8422: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0962 +[2026-03-20T19:24:13.768191Z] Loop 8423: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0953 +[2026-03-20T19:24:14.623651Z] Loop 8424: Loss: 1.72e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0960 +[2026-03-20T19:24:15.479198Z] Loop 8425: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0963 +[2026-03-20T19:24:16.334082Z] Loop 8426: Loss: 1.87e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0967 +[2026-03-20T19:24:17.189341Z] Loop 8427: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0884 +[2026-03-20T19:24:18.044591Z] Loop 8428: Loss: 1.73e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0944 +[2026-03-20T19:24:18.900154Z] Loop 8429: Loss: 1.73e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0924 +[2026-03-20T19:24:19.795954Z] Loop 8430: Loss: 1.78e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0932 +[2026-03-20T19:24:20.649932Z] Loop 8431: Loss: 1.73e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0877 +[2026-03-20T19:24:21.506739Z] Loop 8432: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0900 +[2026-03-20T19:24:22.361326Z] Loop 8433: Loss: 1.65e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0876 +[2026-03-20T19:24:23.215558Z] Loop 8434: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0894 +[2026-03-20T19:24:24.069197Z] Loop 8435: Loss: 1.64e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0891 +[2026-03-20T19:24:24.923293Z] Loop 8436: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0835 +[2026-03-20T19:24:25.778258Z] Loop 8437: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0851 +[2026-03-20T19:24:26.632581Z] Loop 8438: Loss: 1.50e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0801 +[2026-03-20T19:24:27.486725Z] Loop 8439: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0845 +[2026-03-20T19:24:28.381931Z] Loop 8440: Loss: 1.44e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0811 +[2026-03-20T19:24:29.235109Z] Loop 8441: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0786 +[2026-03-20T19:24:30.089730Z] Loop 8442: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0804 +[2026-03-20T19:24:30.944522Z] Loop 8443: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0816 +[2026-03-20T19:24:31.800020Z] Loop 8444: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0809 +[2026-03-20T19:24:32.653767Z] Loop 8445: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0761 +[2026-03-20T19:24:33.507038Z] Loop 8446: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0828 +[2026-03-20T19:24:34.362378Z] Loop 8447: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0785 +[2026-03-20T19:24:35.216705Z] Loop 8448: Loss: 1.45e-02, Avg Return: 0.861, Regret: 0.0005, Entropy: 0.0769 +[2026-03-20T19:24:36.070142Z] Loop 8449: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0807 +[2026-03-20T19:24:36.965295Z] Loop 8450: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0857 +[2026-03-20T19:24:37.821308Z] Loop 8451: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0837 +[2026-03-20T19:24:38.675253Z] Loop 8452: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0803 +[2026-03-20T19:24:39.529582Z] Loop 8453: Loss: 1.54e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0796 +[2026-03-20T19:24:40.383283Z] Loop 8454: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0786 +[2026-03-20T19:24:41.237199Z] Loop 8455: Loss: 1.41e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0789 +[2026-03-20T19:24:42.091153Z] Loop 8456: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0795 +[2026-03-20T19:24:42.945798Z] Loop 8457: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0806 +[2026-03-20T19:24:43.799555Z] Loop 8458: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0807 +[2026-03-20T19:24:44.654859Z] Loop 8459: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0791 +[2026-03-20T19:24:45.549919Z] Loop 8460: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0764 +[2026-03-20T19:24:46.403956Z] Loop 8461: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0782 +[2026-03-20T19:24:47.258749Z] Loop 8462: Loss: 1.46e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0796 +[2026-03-20T19:24:48.114042Z] Loop 8463: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0777 +[2026-03-20T19:24:48.967532Z] Loop 8464: Loss: 1.44e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0789 +[2026-03-20T19:24:49.821454Z] Loop 8465: Loss: 1.34e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0748 +[2026-03-20T19:24:50.675779Z] Loop 8466: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0817 +[2026-03-20T19:24:51.531377Z] Loop 8467: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0823 +[2026-03-20T19:24:52.385457Z] Loop 8468: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0845 +[2026-03-20T19:24:53.238615Z] Loop 8469: Loss: 1.59e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0865 +[2026-03-20T19:24:54.131516Z] Loop 8470: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0854 +[2026-03-20T19:24:54.986801Z] Loop 8471: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0852 +[2026-03-20T19:24:55.840732Z] Loop 8472: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0910 +[2026-03-20T19:24:56.694871Z] Loop 8473: Loss: 1.87e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0964 +[2026-03-20T19:24:57.549722Z] Loop 8474: Loss: 1.76e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0909 +[2026-03-20T19:24:58.404629Z] Loop 8475: Loss: 1.80e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0929 +[2026-03-20T19:24:59.258980Z] Loop 8476: Loss: 1.83e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0924 +[2026-03-20T19:25:00.113816Z] Loop 8477: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0905 +[2026-03-20T19:25:00.968521Z] Loop 8478: Loss: 1.98e-02, Avg Return: 0.860, Regret: 0.0012, Entropy: 0.1001 +[2026-03-20T19:25:01.823123Z] Loop 8479: Loss: 1.83e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0946 +[2026-03-20T19:25:02.718912Z] Loop 8480: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0930 +[2026-03-20T19:25:03.573095Z] Loop 8481: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0894 +[2026-03-20T19:25:04.427522Z] Loop 8482: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0864 +[2026-03-20T19:25:05.282126Z] Loop 8483: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0884 +[2026-03-20T19:25:06.136930Z] Loop 8484: Loss: 1.45e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.0843 +[2026-03-20T19:25:06.990399Z] Loop 8485: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0853 +[2026-03-20T19:25:07.844144Z] Loop 8486: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0846 +[2026-03-20T19:25:08.698157Z] Loop 8487: Loss: 1.60e-02, Avg Return: 0.864, Regret: 0.0014, Entropy: 0.0859 +[2026-03-20T19:25:09.552730Z] Loop 8488: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0868 +[2026-03-20T19:25:10.406704Z] Loop 8489: Loss: 1.64e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0864 +[2026-03-20T19:25:11.301521Z] Loop 8490: Loss: 1.83e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0896 +[2026-03-20T19:25:12.158244Z] Loop 8491: Loss: 1.76e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0907 +[2026-03-20T19:25:13.012890Z] Loop 8492: Loss: 1.84e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0944 +[2026-03-20T19:25:13.866679Z] Loop 8493: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0926 +[2026-03-20T19:25:14.720539Z] Loop 8494: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0901 +[2026-03-20T19:25:15.574384Z] Loop 8495: Loss: 1.76e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0920 +[2026-03-20T19:25:16.428548Z] Loop 8496: Loss: 1.83e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0904 +[2026-03-20T19:25:17.283519Z] Loop 8497: Loss: 1.81e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0893 +[2026-03-20T19:25:18.138150Z] Loop 8498: Loss: 1.82e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0934 +[2026-03-20T19:25:18.992404Z] Loop 8499: Loss: 1.84e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0951 +[2026-03-20T19:25:19.885397Z] Loop 8500: Loss: 1.89e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0953 +[2026-03-20T19:25:20.740753Z] Loop 8501: Loss: 1.91e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0975 +[2026-03-20T19:25:21.595256Z] Loop 8502: Loss: 1.89e-02, Avg Return: 0.866, Regret: 0.0003, Entropy: 0.0932 +[2026-03-20T19:25:22.450757Z] Loop 8503: Loss: 1.99e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0981 +[2026-03-20T19:25:23.306043Z] Loop 8504: Loss: 1.99e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0972 +[2026-03-20T19:25:24.161299Z] Loop 8505: Loss: 1.90e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0970 +[2026-03-20T19:25:25.016436Z] Loop 8506: Loss: 1.95e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0978 +[2026-03-20T19:25:25.873470Z] Loop 8507: Loss: 2.04e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.1034 +[2026-03-20T19:25:26.728841Z] Loop 8508: Loss: 1.89e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0961 +[2026-03-20T19:25:27.583953Z] Loop 8509: Loss: 2.03e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.1008 +[2026-03-20T19:25:28.479503Z] Loop 8510: Loss: 1.95e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0972 +[2026-03-20T19:25:29.335390Z] Loop 8511: Loss: 1.90e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0970 +[2026-03-20T19:25:30.190331Z] Loop 8512: Loss: 2.00e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.1002 +[2026-03-20T19:25:31.044180Z] Loop 8513: Loss: 1.89e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0951 +[2026-03-20T19:25:31.897505Z] Loop 8514: Loss: 1.86e-02, Avg Return: 0.865, Regret: 0.0004, Entropy: 0.0938 +[2026-03-20T19:25:32.752072Z] Loop 8515: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0887 +[2026-03-20T19:25:33.606500Z] Loop 8516: Loss: 1.84e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0897 +[2026-03-20T19:25:34.460802Z] Loop 8517: Loss: 1.82e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0921 +[2026-03-20T19:25:35.314144Z] Loop 8518: Loss: 1.83e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0957 +[2026-03-20T19:25:36.168729Z] Loop 8519: Loss: 1.73e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0888 +[2026-03-20T19:25:37.062962Z] Loop 8520: Loss: 1.80e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0934 +[2026-03-20T19:25:37.917367Z] Loop 8521: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0891 +[2026-03-20T19:25:38.771440Z] Loop 8522: Loss: 1.79e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0901 +[2026-03-20T19:25:39.626551Z] Loop 8523: Loss: 1.80e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0927 +[2026-03-20T19:25:40.481435Z] Loop 8524: Loss: 1.89e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0920 +[2026-03-20T19:25:41.336522Z] Loop 8525: Loss: 1.90e-02, Avg Return: 0.861, Regret: 0.0004, Entropy: 0.0945 +[2026-03-20T19:25:42.191825Z] Loop 8526: Loss: 1.81e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0958 +[2026-03-20T19:25:43.046060Z] Loop 8527: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0962 +[2026-03-20T19:25:43.899601Z] Loop 8528: Loss: 1.74e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0940 +[2026-03-20T19:25:44.753131Z] Loop 8529: Loss: 1.69e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0890 +[2026-03-20T19:25:45.646449Z] Loop 8530: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0962 +[2026-03-20T19:25:46.500661Z] Loop 8531: Loss: 1.81e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0918 +[2026-03-20T19:25:47.354827Z] Loop 8532: Loss: 1.78e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0949 +[2026-03-20T19:25:48.209873Z] Loop 8533: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0889 +[2026-03-20T19:25:49.064467Z] Loop 8534: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0890 +[2026-03-20T19:25:49.918826Z] Loop 8535: Loss: 1.69e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0910 +[2026-03-20T19:25:50.772212Z] Loop 8536: Loss: 1.73e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0926 +[2026-03-20T19:25:51.625616Z] Loop 8537: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0917 +[2026-03-20T19:25:52.480037Z] Loop 8538: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0875 +[2026-03-20T19:25:53.335154Z] Loop 8539: Loss: 1.69e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0873 +[2026-03-20T19:25:54.230612Z] Loop 8540: Loss: 1.82e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0924 +[2026-03-20T19:25:55.084209Z] Loop 8541: Loss: 1.92e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0936 +[2026-03-20T19:25:55.938921Z] Loop 8542: Loss: 1.82e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0934 +[2026-03-20T19:25:56.793620Z] Loop 8543: Loss: 1.78e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0918 +[2026-03-20T19:25:57.648811Z] Loop 8544: Loss: 1.68e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0906 +[2026-03-20T19:25:58.502974Z] Loop 8545: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0967 +[2026-03-20T19:25:59.358036Z] Loop 8546: Loss: 1.86e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0921 +[2026-03-20T19:26:00.213614Z] Loop 8547: Loss: 1.81e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0939 +[2026-03-20T19:26:01.068531Z] Loop 8548: Loss: 1.94e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0961 +[2026-03-20T19:26:01.922385Z] Loop 8549: Loss: 1.94e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0992 +[2026-03-20T19:26:02.816110Z] Loop 8550: Loss: 1.89e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0980 +[2026-03-20T19:26:03.670964Z] Loop 8551: Loss: 1.86e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0955 +[2026-03-20T19:26:04.525618Z] Loop 8552: Loss: 1.84e-02, Avg Return: 0.860, Regret: 0.0009, Entropy: 0.1031 +[2026-03-20T19:26:05.380417Z] Loop 8553: Loss: 1.98e-02, Avg Return: 0.860, Regret: 0.0009, Entropy: 0.1089 +[2026-03-20T19:26:06.234537Z] Loop 8554: Loss: 1.88e-02, Avg Return: 0.859, Regret: 0.0009, Entropy: 0.1068 +[2026-03-20T19:26:07.089413Z] Loop 8555: Loss: 2.02e-02, Avg Return: 0.858, Regret: 0.0009, Entropy: 0.1077 +[2026-03-20T19:26:07.944426Z] Loop 8556: Loss: 1.64e-02, Avg Return: 0.860, Regret: 0.0009, Entropy: 0.0935 +[2026-03-20T19:26:08.798639Z] Loop 8557: Loss: 1.76e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0988 +[2026-03-20T19:26:09.652574Z] Loop 8558: Loss: 1.56e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0868 +[2026-03-20T19:26:10.506554Z] Loop 8559: Loss: 1.57e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0866 +[2026-03-20T19:26:11.400123Z] Loop 8560: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0869 +[2026-03-20T19:26:12.254990Z] Loop 8561: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0786 +[2026-03-20T19:26:13.110320Z] Loop 8562: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0833 +[2026-03-20T19:26:13.963378Z] Loop 8563: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0816 +[2026-03-20T19:26:14.817601Z] Loop 8564: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0799 +[2026-03-20T19:26:15.671703Z] Loop 8565: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0812 +[2026-03-20T19:26:16.525398Z] Loop 8566: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0770 +[2026-03-20T19:26:17.379346Z] Loop 8567: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0817 +[2026-03-20T19:26:18.234656Z] Loop 8568: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0798 +[2026-03-20T19:26:19.089382Z] Loop 8569: Loss: 1.51e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.0803 +[2026-03-20T19:26:19.983915Z] Loop 8570: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0823 +[2026-03-20T19:26:20.838420Z] Loop 8571: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0784 +[2026-03-20T19:26:21.693113Z] Loop 8572: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0847 +[2026-03-20T19:26:22.547015Z] Loop 8573: Loss: 1.50e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0815 +[2026-03-20T19:26:23.402016Z] Loop 8574: Loss: 1.44e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0807 +[2026-03-20T19:26:24.257886Z] Loop 8575: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0852 +[2026-03-20T19:26:25.113200Z] Loop 8576: Loss: 1.55e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0887 +[2026-03-20T19:26:25.967547Z] Loop 8577: Loss: 1.72e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0866 +[2026-03-20T19:26:26.820966Z] Loop 8578: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0834 +[2026-03-20T19:26:27.676180Z] Loop 8579: Loss: 1.74e-02, Avg Return: 0.860, Regret: 0.0009, Entropy: 0.0916 +[2026-03-20T19:26:28.572271Z] Loop 8580: Loss: 1.65e-02, Avg Return: 0.859, Regret: 0.0032, Entropy: 0.0896 +[2026-03-20T19:26:29.425343Z] Loop 8581: Loss: 1.70e-02, Avg Return: 0.860, Regret: 0.0032, Entropy: 0.0914 +[2026-03-20T19:26:30.279599Z] Loop 8582: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0032, Entropy: 0.0883 +[2026-03-20T19:26:31.133699Z] Loop 8583: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0032, Entropy: 0.0897 +[2026-03-20T19:26:31.988886Z] Loop 8584: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0032, Entropy: 0.0899 +[2026-03-20T19:26:32.842657Z] Loop 8585: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0032, Entropy: 0.0861 +[2026-03-20T19:26:33.695343Z] Loop 8586: Loss: 1.79e-02, Avg Return: 0.862, Regret: 0.0032, Entropy: 0.0877 +[2026-03-20T19:26:34.547979Z] Loop 8587: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0032, Entropy: 0.0881 +[2026-03-20T19:26:35.402782Z] Loop 8588: Loss: 1.69e-02, Avg Return: 0.864, Regret: 0.0032, Entropy: 0.0875 +[2026-03-20T19:26:36.256619Z] Loop 8589: Loss: 1.96e-02, Avg Return: 0.864, Regret: 0.0032, Entropy: 0.0955 +[2026-03-20T19:26:37.149801Z] Loop 8590: Loss: 1.63e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0888 +[2026-03-20T19:26:38.003798Z] Loop 8591: Loss: 1.73e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0933 +[2026-03-20T19:26:38.858955Z] Loop 8592: Loss: 1.82e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0937 +[2026-03-20T19:26:39.714196Z] Loop 8593: Loss: 1.78e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0919 +[2026-03-20T19:26:40.568423Z] Loop 8594: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0955 +[2026-03-20T19:26:41.422507Z] Loop 8595: Loss: 1.80e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0927 +[2026-03-20T19:26:42.277108Z] Loop 8596: Loss: 1.84e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0921 +[2026-03-20T19:26:43.131833Z] Loop 8597: Loss: 1.78e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0937 +[2026-03-20T19:26:43.986107Z] Loop 8598: Loss: 1.72e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0900 +[2026-03-20T19:26:44.840523Z] Loop 8599: Loss: 1.82e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0954 +[2026-03-20T19:26:45.736698Z] Loop 8600: Loss: 1.70e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0898 +[2026-03-20T19:26:46.591841Z] Loop 8601: Loss: 1.87e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0951 +[2026-03-20T19:26:47.446594Z] Loop 8602: Loss: 1.85e-02, Avg Return: 0.865, Regret: 0.0004, Entropy: 0.0906 +[2026-03-20T19:26:48.300918Z] Loop 8603: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0913 +[2026-03-20T19:26:49.155171Z] Loop 8604: Loss: 1.93e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.1000 +[2026-03-20T19:26:50.008804Z] Loop 8605: Loss: 1.83e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0974 +[2026-03-20T19:26:50.862439Z] Loop 8606: Loss: 1.75e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0951 +[2026-03-20T19:26:51.716548Z] Loop 8607: Loss: 1.86e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0953 +[2026-03-20T19:26:52.570057Z] Loop 8608: Loss: 1.70e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0921 +[2026-03-20T19:26:53.423999Z] Loop 8609: Loss: 1.76e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0937 +[2026-03-20T19:26:54.318330Z] Loop 8610: Loss: 1.68e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0922 +[2026-03-20T19:26:55.172435Z] Loop 8611: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0932 +[2026-03-20T19:26:56.027918Z] Loop 8612: Loss: 1.82e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0955 +[2026-03-20T19:26:56.882618Z] Loop 8613: Loss: 1.97e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0996 +[2026-03-20T19:26:57.737215Z] Loop 8614: Loss: 1.99e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.1020 +[2026-03-20T19:26:58.591932Z] Loop 8615: Loss: 1.96e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.1037 +[2026-03-20T19:26:59.446925Z] Loop 8616: Loss: 2.10e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.1072 +[2026-03-20T19:27:00.300632Z] Loop 8617: Loss: 2.00e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.1060 +[2026-03-20T19:27:01.154314Z] Loop 8618: Loss: 2.08e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.1061 +[2026-03-20T19:27:02.010760Z] Loop 8619: Loss: 2.12e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.1090 +[2026-03-20T19:27:02.905700Z] Loop 8620: Loss: 2.00e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0997 +[2026-03-20T19:27:03.760097Z] Loop 8621: Loss: 2.08e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.1093 +[2026-03-20T19:27:04.613407Z] Loop 8622: Loss: 2.01e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.1079 +[2026-03-20T19:27:05.466904Z] Loop 8623: Loss: 2.11e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.1106 +[2026-03-20T19:27:06.321051Z] Loop 8624: Loss: 2.06e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.1106 +[2026-03-20T19:27:07.175092Z] Loop 8625: Loss: 2.20e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.1144 +[2026-03-20T19:27:08.029756Z] Loop 8626: Loss: 2.31e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.1229 +[2026-03-20T19:27:08.885322Z] Loop 8627: Loss: 2.22e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.1148 +[2026-03-20T19:27:09.740867Z] Loop 8628: Loss: 2.17e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.1121 +[2026-03-20T19:27:10.596250Z] Loop 8629: Loss: 2.21e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.1152 +[2026-03-20T19:27:11.492072Z] Loop 8630: Loss: 1.99e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.1056 +[2026-03-20T19:27:12.347274Z] Loop 8631: Loss: 1.96e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.1100 +[2026-03-20T19:27:13.201796Z] Loop 8632: Loss: 2.19e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.1085 +[2026-03-20T19:27:14.056649Z] Loop 8633: Loss: 2.11e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.1078 +[2026-03-20T19:27:14.912550Z] Loop 8634: Loss: 1.93e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.1103 +[2026-03-20T19:27:15.768573Z] Loop 8635: Loss: 2.11e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.1109 +[2026-03-20T19:27:16.622340Z] Loop 8636: Loss: 2.09e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.1108 +[2026-03-20T19:27:17.476897Z] Loop 8637: Loss: 2.17e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.1122 +[2026-03-20T19:27:18.332353Z] Loop 8638: Loss: 2.01e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.1094 +[2026-03-20T19:27:19.188628Z] Loop 8639: Loss: 2.16e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.1101 +[2026-03-20T19:27:20.084278Z] Loop 8640: Loss: 2.11e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1120 +[2026-03-20T19:27:20.938487Z] Loop 8641: Loss: 2.01e-02, Avg Return: 0.864, Regret: 0.0013, Entropy: 0.1078 +[2026-03-20T19:27:21.792577Z] Loop 8642: Loss: 2.08e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.1094 +[2026-03-20T19:27:22.648292Z] Loop 8643: Loss: 2.03e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1063 +[2026-03-20T19:27:23.502084Z] Loop 8644: Loss: 1.99e-02, Avg Return: 0.864, Regret: 0.0013, Entropy: 0.1015 +[2026-03-20T19:27:24.355348Z] Loop 8645: Loss: 1.98e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1024 +[2026-03-20T19:27:25.208146Z] Loop 8646: Loss: 1.94e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.1016 +[2026-03-20T19:27:26.061891Z] Loop 8647: Loss: 2.14e-02, Avg Return: 0.864, Regret: 0.0013, Entropy: 0.1059 +[2026-03-20T19:27:26.915931Z] Loop 8648: Loss: 2.06e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1051 +[2026-03-20T19:27:27.769329Z] Loop 8649: Loss: 1.83e-02, Avg Return: 0.864, Regret: 0.0013, Entropy: 0.0975 +[2026-03-20T19:27:28.663147Z] Loop 8650: Loss: 1.94e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.1019 +[2026-03-20T19:27:29.518210Z] Loop 8651: Loss: 1.81e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0981 +[2026-03-20T19:27:30.373004Z] Loop 8652: Loss: 1.93e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0988 +[2026-03-20T19:27:31.227186Z] Loop 8653: Loss: 1.84e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0962 +[2026-03-20T19:27:32.080615Z] Loop 8654: Loss: 1.89e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0962 +[2026-03-20T19:27:32.934658Z] Loop 8655: Loss: 1.93e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0998 +[2026-03-20T19:27:33.789703Z] Loop 8656: Loss: 1.87e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0968 +[2026-03-20T19:27:34.644307Z] Loop 8657: Loss: 1.85e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0968 +[2026-03-20T19:27:35.498653Z] Loop 8658: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0962 +[2026-03-20T19:27:36.353220Z] Loop 8659: Loss: 1.86e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0953 +[2026-03-20T19:27:37.246975Z] Loop 8660: Loss: 1.86e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0952 +[2026-03-20T19:27:38.101076Z] Loop 8661: Loss: 1.76e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0967 +[2026-03-20T19:27:38.956079Z] Loop 8662: Loss: 1.79e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0930 +[2026-03-20T19:27:39.810066Z] Loop 8663: Loss: 1.93e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0929 +[2026-03-20T19:27:40.663303Z] Loop 8664: Loss: 2.10e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.1032 +[2026-03-20T19:27:41.517592Z] Loop 8665: Loss: 1.95e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0969 +[2026-03-20T19:27:42.371982Z] Loop 8666: Loss: 1.85e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0939 +[2026-03-20T19:27:43.226437Z] Loop 8667: Loss: 1.83e-02, Avg Return: 0.865, Regret: 0.0002, Entropy: 0.0953 +[2026-03-20T19:27:44.081096Z] Loop 8668: Loss: 1.85e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0950 +[2026-03-20T19:27:44.936618Z] Loop 8669: Loss: 1.67e-02, Avg Return: 0.866, Regret: 0.0002, Entropy: 0.0874 +[2026-03-20T19:27:45.832133Z] Loop 8670: Loss: 1.86e-02, Avg Return: 0.865, Regret: 0.0003, Entropy: 0.0930 +[2026-03-20T19:27:46.687000Z] Loop 8671: Loss: 1.71e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0937 +[2026-03-20T19:27:47.541272Z] Loop 8672: Loss: 1.77e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0866 +[2026-03-20T19:27:48.395250Z] Loop 8673: Loss: 1.81e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0903 +[2026-03-20T19:27:49.249706Z] Loop 8674: Loss: 1.79e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0922 +[2026-03-20T19:27:50.103955Z] Loop 8675: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0914 +[2026-03-20T19:27:50.957498Z] Loop 8676: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0908 +[2026-03-20T19:27:51.811658Z] Loop 8677: Loss: 1.85e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0913 +[2026-03-20T19:27:52.666795Z] Loop 8678: Loss: 1.88e-02, Avg Return: 0.866, Regret: 0.0003, Entropy: 0.0976 +[2026-03-20T19:27:53.520764Z] Loop 8679: Loss: 1.78e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0916 +[2026-03-20T19:27:54.415545Z] Loop 8680: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0865 +[2026-03-20T19:27:55.269298Z] Loop 8681: Loss: 1.75e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0900 +[2026-03-20T19:27:56.123189Z] Loop 8682: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0882 +[2026-03-20T19:27:56.977405Z] Loop 8683: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0909 +[2026-03-20T19:27:57.831839Z] Loop 8684: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0876 +[2026-03-20T19:27:58.685858Z] Loop 8685: Loss: 1.85e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0935 +[2026-03-20T19:27:59.540960Z] Loop 8686: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0893 +[2026-03-20T19:28:00.396192Z] Loop 8687: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0949 +[2026-03-20T19:28:01.251840Z] Loop 8688: Loss: 1.77e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0968 +[2026-03-20T19:28:02.107180Z] Loop 8689: Loss: 2.01e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.1029 +[2026-03-20T19:28:02.999864Z] Loop 8690: Loss: 1.96e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0975 +[2026-03-20T19:28:03.853227Z] Loop 8691: Loss: 1.90e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0988 +[2026-03-20T19:28:04.706252Z] Loop 8692: Loss: 1.87e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0993 +[2026-03-20T19:28:05.560765Z] Loop 8693: Loss: 1.85e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0973 +[2026-03-20T19:28:06.415071Z] Loop 8694: Loss: 1.94e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.0996 +[2026-03-20T19:28:07.268376Z] Loop 8695: Loss: 1.87e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0972 +[2026-03-20T19:28:08.121400Z] Loop 8696: Loss: 1.85e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0962 +[2026-03-20T19:28:08.975152Z] Loop 8697: Loss: 1.90e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0968 +[2026-03-20T19:28:09.829075Z] Loop 8698: Loss: 2.07e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.1053 +[2026-03-20T19:28:10.681751Z] Loop 8699: Loss: 1.93e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.1006 +[2026-03-20T19:28:11.574046Z] Loop 8700: Loss: 1.94e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0988 +[2026-03-20T19:28:12.428164Z] Loop 8701: Loss: 1.99e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.1012 +[2026-03-20T19:28:13.282469Z] Loop 8702: Loss: 1.85e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0940 +[2026-03-20T19:28:14.136361Z] Loop 8703: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0986 +[2026-03-20T19:28:14.989273Z] Loop 8704: Loss: 1.89e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0960 +[2026-03-20T19:28:15.843035Z] Loop 8705: Loss: 2.01e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0997 +[2026-03-20T19:28:16.698015Z] Loop 8706: Loss: 2.01e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0989 +[2026-03-20T19:28:17.551911Z] Loop 8707: Loss: 1.87e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0994 +[2026-03-20T19:28:18.404892Z] Loop 8708: Loss: 1.89e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0959 +[2026-03-20T19:28:19.258303Z] Loop 8709: Loss: 1.80e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0959 +[2026-03-20T19:28:20.152759Z] Loop 8710: Loss: 1.98e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0991 +[2026-03-20T19:28:21.008114Z] Loop 8711: Loss: 1.96e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0994 +[2026-03-20T19:28:21.863600Z] Loop 8712: Loss: 1.85e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0944 +[2026-03-20T19:28:22.717849Z] Loop 8713: Loss: 1.87e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0943 +[2026-03-20T19:28:23.572846Z] Loop 8714: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0880 +[2026-03-20T19:28:24.428885Z] Loop 8715: Loss: 1.79e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0908 +[2026-03-20T19:28:25.284197Z] Loop 8716: Loss: 1.76e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0900 +[2026-03-20T19:28:26.139605Z] Loop 8717: Loss: 1.73e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0907 +[2026-03-20T19:28:26.993898Z] Loop 8718: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0875 +[2026-03-20T19:28:27.848040Z] Loop 8719: Loss: 1.79e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0919 +[2026-03-20T19:28:28.741397Z] Loop 8720: Loss: 1.80e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0894 +[2026-03-20T19:28:29.594794Z] Loop 8721: Loss: 1.75e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0918 +[2026-03-20T19:28:30.447958Z] Loop 8722: Loss: 1.78e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0930 +[2026-03-20T19:28:31.302045Z] Loop 8723: Loss: 1.82e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0951 +[2026-03-20T19:28:32.155889Z] Loop 8724: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0891 +[2026-03-20T19:28:33.009411Z] Loop 8725: Loss: 1.91e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0966 +[2026-03-20T19:28:33.863255Z] Loop 8726: Loss: 1.98e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.1020 +[2026-03-20T19:28:34.717491Z] Loop 8727: Loss: 1.79e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0914 +[2026-03-20T19:28:35.571517Z] Loop 8728: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0947 +[2026-03-20T19:28:36.425139Z] Loop 8729: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0896 +[2026-03-20T19:28:37.318197Z] Loop 8730: Loss: 1.78e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0906 +[2026-03-20T19:28:38.172318Z] Loop 8731: Loss: 1.77e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0907 +[2026-03-20T19:28:39.026920Z] Loop 8732: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0879 +[2026-03-20T19:28:39.882763Z] Loop 8733: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0850 +[2026-03-20T19:28:40.737796Z] Loop 8734: Loss: 1.64e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0880 +[2026-03-20T19:28:41.592770Z] Loop 8735: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0845 +[2026-03-20T19:28:42.446759Z] Loop 8736: Loss: 1.73e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0939 +[2026-03-20T19:28:43.302336Z] Loop 8737: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0928 +[2026-03-20T19:28:44.156842Z] Loop 8738: Loss: 1.91e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0955 +[2026-03-20T19:28:45.011629Z] Loop 8739: Loss: 1.97e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.1010 +[2026-03-20T19:28:45.906994Z] Loop 8740: Loss: 1.90e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0956 +[2026-03-20T19:28:46.760991Z] Loop 8741: Loss: 1.84e-02, Avg Return: 0.865, Regret: 0.0004, Entropy: 0.0934 +[2026-03-20T19:28:47.616174Z] Loop 8742: Loss: 1.75e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0899 +[2026-03-20T19:28:48.471348Z] Loop 8743: Loss: 1.71e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0904 +[2026-03-20T19:28:49.325354Z] Loop 8744: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0887 +[2026-03-20T19:28:50.178919Z] Loop 8745: Loss: 1.79e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0898 +[2026-03-20T19:28:51.034154Z] Loop 8746: Loss: 1.72e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0902 +[2026-03-20T19:28:51.888572Z] Loop 8747: Loss: 1.81e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0898 +[2026-03-20T19:28:52.742254Z] Loop 8748: Loss: 1.89e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0978 +[2026-03-20T19:28:53.595091Z] Loop 8749: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0894 +[2026-03-20T19:28:54.489243Z] Loop 8750: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0921 +[2026-03-20T19:28:55.343692Z] Loop 8751: Loss: 1.81e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0950 +[2026-03-20T19:28:56.198741Z] Loop 8752: Loss: 1.98e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0982 +[2026-03-20T19:28:57.052858Z] Loop 8753: Loss: 1.87e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0951 +[2026-03-20T19:28:57.907276Z] Loop 8754: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0966 +[2026-03-20T19:28:58.763257Z] Loop 8755: Loss: 1.83e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0961 +[2026-03-20T19:28:59.617090Z] Loop 8756: Loss: 1.80e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0914 +[2026-03-20T19:29:00.472051Z] Loop 8757: Loss: 1.90e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0965 +[2026-03-20T19:29:01.325548Z] Loop 8758: Loss: 1.75e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0911 +[2026-03-20T19:29:02.178473Z] Loop 8759: Loss: 1.73e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0908 +[2026-03-20T19:29:03.071986Z] Loop 8760: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0873 +[2026-03-20T19:29:03.926531Z] Loop 8761: Loss: 1.83e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0913 +[2026-03-20T19:29:04.780235Z] Loop 8762: Loss: 1.70e-02, Avg Return: 0.860, Regret: 0.0008, Entropy: 0.0911 +[2026-03-20T19:29:05.633213Z] Loop 8763: Loss: 1.72e-02, Avg Return: 0.858, Regret: 0.0008, Entropy: 0.0909 +[2026-03-20T19:29:06.486173Z] Loop 8764: Loss: 1.83e-02, Avg Return: 0.859, Regret: 0.0008, Entropy: 0.0941 +[2026-03-20T19:29:07.340728Z] Loop 8765: Loss: 1.82e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0931 +[2026-03-20T19:29:08.195478Z] Loop 8766: Loss: 1.74e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0912 +[2026-03-20T19:29:09.048514Z] Loop 8767: Loss: 1.80e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0915 +[2026-03-20T19:29:09.901441Z] Loop 8768: Loss: 1.73e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0896 +[2026-03-20T19:29:10.755789Z] Loop 8769: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0871 +[2026-03-20T19:29:11.651638Z] Loop 8770: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0017, Entropy: 0.0824 +[2026-03-20T19:29:12.506726Z] Loop 8771: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0017, Entropy: 0.0870 +[2026-03-20T19:29:13.360738Z] Loop 8772: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0017, Entropy: 0.0884 +[2026-03-20T19:29:14.216088Z] Loop 8773: Loss: 1.71e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0917 +[2026-03-20T19:29:15.071986Z] Loop 8774: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0017, Entropy: 0.0865 +[2026-03-20T19:29:15.927240Z] Loop 8775: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0817 +[2026-03-20T19:29:16.781490Z] Loop 8776: Loss: 1.67e-02, Avg Return: 0.864, Regret: 0.0017, Entropy: 0.0861 +[2026-03-20T19:29:17.636970Z] Loop 8777: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0017, Entropy: 0.0829 +[2026-03-20T19:29:18.492168Z] Loop 8778: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0854 +[2026-03-20T19:29:19.347729Z] Loop 8779: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0017, Entropy: 0.0822 +[2026-03-20T19:29:20.241457Z] Loop 8780: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0900 +[2026-03-20T19:29:21.097709Z] Loop 8781: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0863 +[2026-03-20T19:29:21.952805Z] Loop 8782: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0874 +[2026-03-20T19:29:22.808361Z] Loop 8783: Loss: 1.74e-02, Avg Return: 0.865, Regret: 0.0007, Entropy: 0.0882 +[2026-03-20T19:29:23.663699Z] Loop 8784: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0907 +[2026-03-20T19:29:24.519763Z] Loop 8785: Loss: 1.74e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0918 +[2026-03-20T19:29:25.375414Z] Loop 8786: Loss: 1.78e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0883 +[2026-03-20T19:29:26.230452Z] Loop 8787: Loss: 1.87e-02, Avg Return: 0.860, Regret: 0.0007, Entropy: 0.0952 +[2026-03-20T19:29:27.085592Z] Loop 8788: Loss: 1.75e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0912 +[2026-03-20T19:29:27.940281Z] Loop 8789: Loss: 1.72e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0902 +[2026-03-20T19:29:28.836714Z] Loop 8790: Loss: 1.69e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0896 +[2026-03-20T19:29:29.691322Z] Loop 8791: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0873 +[2026-03-20T19:29:30.547092Z] Loop 8792: Loss: 1.83e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0921 +[2026-03-20T19:29:31.402193Z] Loop 8793: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0902 +[2026-03-20T19:29:32.256388Z] Loop 8794: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0896 +[2026-03-20T19:29:33.110697Z] Loop 8795: Loss: 1.81e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0905 +[2026-03-20T19:29:33.965848Z] Loop 8796: Loss: 1.77e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0892 +[2026-03-20T19:29:34.821164Z] Loop 8797: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0828 +[2026-03-20T19:29:35.675469Z] Loop 8798: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0809 +[2026-03-20T19:29:36.530011Z] Loop 8799: Loss: 1.67e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0848 +[2026-03-20T19:29:37.426162Z] Loop 8800: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0879 +[2026-03-20T19:29:38.280791Z] Loop 8801: Loss: 1.57e-02, Avg Return: 0.861, Regret: 0.0017, Entropy: 0.0830 +[2026-03-20T19:29:39.136456Z] Loop 8802: Loss: 1.69e-02, Avg Return: 0.861, Regret: 0.0017, Entropy: 0.0888 +[2026-03-20T19:29:39.991552Z] Loop 8803: Loss: 1.63e-02, Avg Return: 0.861, Regret: 0.0017, Entropy: 0.0862 +[2026-03-20T19:29:40.845812Z] Loop 8804: Loss: 1.65e-02, Avg Return: 0.861, Regret: 0.0017, Entropy: 0.0862 +[2026-03-20T19:29:41.700202Z] Loop 8805: Loss: 1.68e-02, Avg Return: 0.860, Regret: 0.0017, Entropy: 0.0861 +[2026-03-20T19:29:42.555155Z] Loop 8806: Loss: 1.64e-02, Avg Return: 0.860, Regret: 0.0017, Entropy: 0.0877 +[2026-03-20T19:29:43.409825Z] Loop 8807: Loss: 1.77e-02, Avg Return: 0.860, Regret: 0.0017, Entropy: 0.0920 +[2026-03-20T19:29:44.263727Z] Loop 8808: Loss: 1.80e-02, Avg Return: 0.860, Regret: 0.0017, Entropy: 0.0911 +[2026-03-20T19:29:45.117671Z] Loop 8809: Loss: 1.54e-02, Avg Return: 0.861, Regret: 0.0017, Entropy: 0.0852 +[2026-03-20T19:29:46.011366Z] Loop 8810: Loss: 1.51e-02, Avg Return: 0.859, Regret: 0.0039, Entropy: 0.0821 +[2026-03-20T19:29:46.865672Z] Loop 8811: Loss: 1.46e-02, Avg Return: 0.858, Regret: 0.0039, Entropy: 0.0827 +[2026-03-20T19:29:47.719500Z] Loop 8812: Loss: 1.58e-02, Avg Return: 0.861, Regret: 0.0039, Entropy: 0.0849 +[2026-03-20T19:29:48.572515Z] Loop 8813: Loss: 1.40e-02, Avg Return: 0.860, Regret: 0.0039, Entropy: 0.0795 +[2026-03-20T19:29:49.425986Z] Loop 8814: Loss: 1.50e-02, Avg Return: 0.861, Regret: 0.0039, Entropy: 0.0837 +[2026-03-20T19:29:50.279964Z] Loop 8815: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0039, Entropy: 0.0811 +[2026-03-20T19:29:51.134196Z] Loop 8816: Loss: 1.42e-02, Avg Return: 0.862, Regret: 0.0039, Entropy: 0.0777 +[2026-03-20T19:29:51.988448Z] Loop 8817: Loss: 1.46e-02, Avg Return: 0.861, Regret: 0.0039, Entropy: 0.0779 +[2026-03-20T19:29:52.842076Z] Loop 8818: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0039, Entropy: 0.0757 +[2026-03-20T19:29:53.695905Z] Loop 8819: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0039, Entropy: 0.0790 +[2026-03-20T19:29:54.591835Z] Loop 8820: Loss: 1.40e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0779 +[2026-03-20T19:29:55.446932Z] Loop 8821: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0748 +[2026-03-20T19:29:56.299949Z] Loop 8822: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0823 +[2026-03-20T19:29:57.152922Z] Loop 8823: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0871 +[2026-03-20T19:29:58.007820Z] Loop 8824: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0842 +[2026-03-20T19:29:58.862964Z] Loop 8825: Loss: 1.55e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0819 +[2026-03-20T19:29:59.716154Z] Loop 8826: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0882 +[2026-03-20T19:30:00.569234Z] Loop 8827: Loss: 1.68e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0867 +[2026-03-20T19:30:01.424170Z] Loop 8828: Loss: 1.64e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0854 +[2026-03-20T19:30:02.279841Z] Loop 8829: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0886 +[2026-03-20T19:30:03.174506Z] Loop 8830: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0847 +[2026-03-20T19:30:04.027590Z] Loop 8831: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0870 +[2026-03-20T19:30:04.881497Z] Loop 8832: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0858 +[2026-03-20T19:30:05.736810Z] Loop 8833: Loss: 1.68e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0876 +[2026-03-20T19:30:06.591235Z] Loop 8834: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0865 +[2026-03-20T19:30:07.446017Z] Loop 8835: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0867 +[2026-03-20T19:30:08.300647Z] Loop 8836: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0881 +[2026-03-20T19:30:09.154826Z] Loop 8837: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0859 +[2026-03-20T19:30:10.009568Z] Loop 8838: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0846 +[2026-03-20T19:30:10.862978Z] Loop 8839: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0829 +[2026-03-20T19:30:11.758156Z] Loop 8840: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0869 +[2026-03-20T19:30:12.611084Z] Loop 8841: Loss: 1.66e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0857 +[2026-03-20T19:30:13.465362Z] Loop 8842: Loss: 1.62e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0844 +[2026-03-20T19:30:14.318967Z] Loop 8843: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0873 +[2026-03-20T19:30:15.173202Z] Loop 8844: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0873 +[2026-03-20T19:30:16.028202Z] Loop 8845: Loss: 1.78e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0879 +[2026-03-20T19:30:16.882948Z] Loop 8846: Loss: 1.66e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0884 +[2026-03-20T19:30:17.737108Z] Loop 8847: Loss: 1.67e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0890 +[2026-03-20T19:30:18.591612Z] Loop 8848: Loss: 1.72e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0881 +[2026-03-20T19:30:19.444470Z] Loop 8849: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0847 +[2026-03-20T19:30:20.339296Z] Loop 8850: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0890 +[2026-03-20T19:30:21.194248Z] Loop 8851: Loss: 1.73e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0885 +[2026-03-20T19:30:22.048617Z] Loop 8852: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0901 +[2026-03-20T19:30:22.902712Z] Loop 8853: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0930 +[2026-03-20T19:30:23.756657Z] Loop 8854: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0925 +[2026-03-20T19:30:24.611734Z] Loop 8855: Loss: 1.92e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0948 +[2026-03-20T19:30:25.465322Z] Loop 8856: Loss: 1.96e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.0976 +[2026-03-20T19:30:26.319550Z] Loop 8857: Loss: 1.89e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0926 +[2026-03-20T19:30:27.172979Z] Loop 8858: Loss: 1.83e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0966 +[2026-03-20T19:30:28.027972Z] Loop 8859: Loss: 1.89e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0981 +[2026-03-20T19:30:28.922793Z] Loop 8860: Loss: 1.87e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0937 +[2026-03-20T19:30:29.777224Z] Loop 8861: Loss: 1.85e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0951 +[2026-03-20T19:30:30.631801Z] Loop 8862: Loss: 1.90e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0964 +[2026-03-20T19:30:31.485480Z] Loop 8863: Loss: 1.94e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0982 +[2026-03-20T19:30:32.339664Z] Loop 8864: Loss: 1.93e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0971 +[2026-03-20T19:30:33.194050Z] Loop 8865: Loss: 1.95e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0997 +[2026-03-20T19:30:34.048683Z] Loop 8866: Loss: 1.78e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0967 +[2026-03-20T19:30:34.902207Z] Loop 8867: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0966 +[2026-03-20T19:30:35.756174Z] Loop 8868: Loss: 1.84e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0946 +[2026-03-20T19:30:36.610233Z] Loop 8869: Loss: 1.97e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0965 +[2026-03-20T19:30:37.504514Z] Loop 8870: Loss: 1.80e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0961 +[2026-03-20T19:30:38.358694Z] Loop 8871: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0920 +[2026-03-20T19:30:39.214207Z] Loop 8872: Loss: 1.79e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0914 +[2026-03-20T19:30:40.068814Z] Loop 8873: Loss: 1.90e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0942 +[2026-03-20T19:30:40.923661Z] Loop 8874: Loss: 1.84e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0941 +[2026-03-20T19:30:41.779003Z] Loop 8875: Loss: 1.76e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0942 +[2026-03-20T19:30:42.633943Z] Loop 8876: Loss: 1.86e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0949 +[2026-03-20T19:30:43.488717Z] Loop 8877: Loss: 1.80e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0954 +[2026-03-20T19:30:44.344359Z] Loop 8878: Loss: 1.94e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0979 +[2026-03-20T19:30:45.199595Z] Loop 8879: Loss: 2.03e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0989 +[2026-03-20T19:30:46.095834Z] Loop 8880: Loss: 1.77e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0914 +[2026-03-20T19:30:46.950954Z] Loop 8881: Loss: 1.79e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0919 +[2026-03-20T19:30:47.804684Z] Loop 8882: Loss: 1.73e-02, Avg Return: 0.865, Regret: 0.0004, Entropy: 0.0907 +[2026-03-20T19:30:48.658668Z] Loop 8883: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0905 +[2026-03-20T19:30:49.513782Z] Loop 8884: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0888 +[2026-03-20T19:30:50.367039Z] Loop 8885: Loss: 1.69e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0891 +[2026-03-20T19:30:51.220188Z] Loop 8886: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0877 +[2026-03-20T19:30:52.074937Z] Loop 8887: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0860 +[2026-03-20T19:30:52.929214Z] Loop 8888: Loss: 1.54e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0837 +[2026-03-20T19:30:53.783587Z] Loop 8889: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0826 +[2026-03-20T19:30:54.676811Z] Loop 8890: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0780 +[2026-03-20T19:30:55.529997Z] Loop 8891: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0753 +[2026-03-20T19:30:56.384310Z] Loop 8892: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0780 +[2026-03-20T19:30:57.238603Z] Loop 8893: Loss: 1.46e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0750 +[2026-03-20T19:30:58.093159Z] Loop 8894: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0738 +[2026-03-20T19:30:58.946880Z] Loop 8895: Loss: 1.30e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0725 +[2026-03-20T19:30:59.801719Z] Loop 8896: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0742 +[2026-03-20T19:31:00.655854Z] Loop 8897: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0734 +[2026-03-20T19:31:01.510107Z] Loop 8898: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0782 +[2026-03-20T19:31:02.364354Z] Loop 8899: Loss: 1.45e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0789 +[2026-03-20T19:31:03.257557Z] Loop 8900: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0743 +[2026-03-20T19:31:04.111078Z] Loop 8901: Loss: 1.43e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0739 +[2026-03-20T19:31:04.965983Z] Loop 8902: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0814 +[2026-03-20T19:31:05.819939Z] Loop 8903: Loss: 1.46e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0788 +[2026-03-20T19:31:06.674418Z] Loop 8904: Loss: 1.41e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0797 +[2026-03-20T19:31:07.528225Z] Loop 8905: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0836 +[2026-03-20T19:31:08.382467Z] Loop 8906: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0824 +[2026-03-20T19:31:09.236569Z] Loop 8907: Loss: 1.59e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0810 +[2026-03-20T19:31:10.089676Z] Loop 8908: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0833 +[2026-03-20T19:31:10.943206Z] Loop 8909: Loss: 1.49e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0832 +[2026-03-20T19:31:11.839922Z] Loop 8910: Loss: 1.35e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0754 +[2026-03-20T19:31:12.694709Z] Loop 8911: Loss: 1.42e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0792 +[2026-03-20T19:31:13.548390Z] Loop 8912: Loss: 1.46e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0793 +[2026-03-20T19:31:14.403181Z] Loop 8913: Loss: 1.52e-02, Avg Return: 0.864, Regret: 0.0018, Entropy: 0.0822 +[2026-03-20T19:31:15.257527Z] Loop 8914: Loss: 1.40e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0748 +[2026-03-20T19:31:16.112735Z] Loop 8915: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0805 +[2026-03-20T19:31:16.967093Z] Loop 8916: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0811 +[2026-03-20T19:31:17.820750Z] Loop 8917: Loss: 1.33e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0739 +[2026-03-20T19:31:18.674366Z] Loop 8918: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0769 +[2026-03-20T19:31:19.528636Z] Loop 8919: Loss: 1.33e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0742 +[2026-03-20T19:31:20.422633Z] Loop 8920: Loss: 1.41e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0758 +[2026-03-20T19:31:21.276477Z] Loop 8921: Loss: 1.31e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0742 +[2026-03-20T19:31:22.130007Z] Loop 8922: Loss: 1.40e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0710 +[2026-03-20T19:31:22.984489Z] Loop 8923: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0719 +[2026-03-20T19:31:23.838830Z] Loop 8924: Loss: 1.30e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0712 +[2026-03-20T19:31:24.693417Z] Loop 8925: Loss: 1.29e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0712 +[2026-03-20T19:31:25.547014Z] Loop 8926: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0680 +[2026-03-20T19:31:26.400497Z] Loop 8927: Loss: 1.22e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0665 +[2026-03-20T19:31:27.254357Z] Loop 8928: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0745 +[2026-03-20T19:31:28.107773Z] Loop 8929: Loss: 1.27e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0712 +[2026-03-20T19:31:29.003063Z] Loop 8930: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0704 +[2026-03-20T19:31:29.859048Z] Loop 8931: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0734 +[2026-03-20T19:31:30.713367Z] Loop 8932: Loss: 1.34e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0720 +[2026-03-20T19:31:31.568633Z] Loop 8933: Loss: 1.27e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0698 +[2026-03-20T19:31:32.424224Z] Loop 8934: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0718 +[2026-03-20T19:31:33.279033Z] Loop 8935: Loss: 1.30e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0759 +[2026-03-20T19:31:34.133709Z] Loop 8936: Loss: 1.33e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0706 +[2026-03-20T19:31:34.988975Z] Loop 8937: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0756 +[2026-03-20T19:31:35.845493Z] Loop 8938: Loss: 1.27e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0694 +[2026-03-20T19:31:36.699714Z] Loop 8939: Loss: 1.32e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0693 +[2026-03-20T19:31:37.592980Z] Loop 8940: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0681 +[2026-03-20T19:31:38.447995Z] Loop 8941: Loss: 1.31e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0729 +[2026-03-20T19:31:39.302354Z] Loop 8942: Loss: 1.24e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0709 +[2026-03-20T19:31:40.156361Z] Loop 8943: Loss: 1.27e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0683 +[2026-03-20T19:31:41.010884Z] Loop 8944: Loss: 1.33e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0714 +[2026-03-20T19:31:41.864965Z] Loop 8945: Loss: 1.33e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0730 +[2026-03-20T19:31:42.719447Z] Loop 8946: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0692 +[2026-03-20T19:31:43.573736Z] Loop 8947: Loss: 1.29e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0755 +[2026-03-20T19:31:44.428508Z] Loop 8948: Loss: 1.20e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0705 +[2026-03-20T19:31:45.282305Z] Loop 8949: Loss: 1.27e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0692 +[2026-03-20T19:31:46.177752Z] Loop 8950: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0723 +[2026-03-20T19:31:47.032144Z] Loop 8951: Loss: 1.50e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0764 +[2026-03-20T19:31:47.886429Z] Loop 8952: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0773 +[2026-03-20T19:31:48.740743Z] Loop 8953: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0811 +[2026-03-20T19:31:49.595751Z] Loop 8954: Loss: 1.64e-02, Avg Return: 0.860, Regret: 0.0009, Entropy: 0.0833 +[2026-03-20T19:31:50.450167Z] Loop 8955: Loss: 1.46e-02, Avg Return: 0.859, Regret: 0.0009, Entropy: 0.0812 +[2026-03-20T19:31:51.304479Z] Loop 8956: Loss: 1.63e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0864 +[2026-03-20T19:31:52.158907Z] Loop 8957: Loss: 1.57e-02, Avg Return: 0.860, Regret: 0.0009, Entropy: 0.0806 +[2026-03-20T19:31:53.014081Z] Loop 8958: Loss: 1.40e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0774 +[2026-03-20T19:31:53.867590Z] Loop 8959: Loss: 1.32e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0743 +[2026-03-20T19:31:54.763303Z] Loop 8960: Loss: 1.26e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0711 +[2026-03-20T19:31:55.616865Z] Loop 8961: Loss: 1.22e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0651 +[2026-03-20T19:31:56.471641Z] Loop 8962: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0746 +[2026-03-20T19:31:57.325697Z] Loop 8963: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0017, Entropy: 0.0704 +[2026-03-20T19:31:58.179889Z] Loop 8964: Loss: 1.33e-02, Avg Return: 0.861, Regret: 0.0017, Entropy: 0.0695 +[2026-03-20T19:31:59.033139Z] Loop 8965: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0017, Entropy: 0.0708 +[2026-03-20T19:31:59.887856Z] Loop 8966: Loss: 1.17e-02, Avg Return: 0.863, Regret: 0.0017, Entropy: 0.0655 +[2026-03-20T19:32:00.740478Z] Loop 8967: Loss: 1.25e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0691 +[2026-03-20T19:32:01.594037Z] Loop 8968: Loss: 1.33e-02, Avg Return: 0.864, Regret: 0.0017, Entropy: 0.0715 +[2026-03-20T19:32:02.448462Z] Loop 8969: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0017, Entropy: 0.0708 +[2026-03-20T19:32:03.342957Z] Loop 8970: Loss: 1.26e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0705 +[2026-03-20T19:32:04.196297Z] Loop 8971: Loss: 1.23e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0658 +[2026-03-20T19:32:05.051815Z] Loop 8972: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0727 +[2026-03-20T19:32:05.905927Z] Loop 8973: Loss: 1.37e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0719 +[2026-03-20T19:32:06.760856Z] Loop 8974: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0744 +[2026-03-20T19:32:07.614960Z] Loop 8975: Loss: 1.45e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0719 +[2026-03-20T19:32:08.468233Z] Loop 8976: Loss: 1.27e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0718 +[2026-03-20T19:32:09.321834Z] Loop 8977: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0717 +[2026-03-20T19:32:10.176498Z] Loop 8978: Loss: 1.29e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0708 +[2026-03-20T19:32:11.031276Z] Loop 8979: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0761 +[2026-03-20T19:32:11.925513Z] Loop 8980: Loss: 1.25e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0681 +[2026-03-20T19:32:12.781057Z] Loop 8981: Loss: 1.32e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0713 +[2026-03-20T19:32:13.636370Z] Loop 8982: Loss: 1.30e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0715 +[2026-03-20T19:32:14.491400Z] Loop 8983: Loss: 1.44e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0732 +[2026-03-20T19:32:15.345776Z] Loop 8984: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0707 +[2026-03-20T19:32:16.199803Z] Loop 8985: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0682 +[2026-03-20T19:32:17.053550Z] Loop 8986: Loss: 1.18e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0686 +[2026-03-20T19:32:17.907356Z] Loop 8987: Loss: 1.22e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0672 +[2026-03-20T19:32:18.761147Z] Loop 8988: Loss: 1.24e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0667 +[2026-03-20T19:32:19.615465Z] Loop 8989: Loss: 1.25e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0685 +[2026-03-20T19:32:20.509654Z] Loop 8990: Loss: 1.35e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0743 +[2026-03-20T19:32:21.363326Z] Loop 8991: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0773 +[2026-03-20T19:32:22.218409Z] Loop 8992: Loss: 1.36e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0733 +[2026-03-20T19:32:23.072968Z] Loop 8993: Loss: 1.27e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0706 +[2026-03-20T19:32:23.925845Z] Loop 8994: Loss: 1.33e-02, Avg Return: 0.864, Regret: 0.0019, Entropy: 0.0730 +[2026-03-20T19:32:24.778568Z] Loop 8995: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0019, Entropy: 0.0700 +[2026-03-20T19:32:25.632053Z] Loop 8996: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0019, Entropy: 0.0689 +[2026-03-20T19:32:26.486418Z] Loop 8997: Loss: 1.34e-02, Avg Return: 0.865, Regret: 0.0019, Entropy: 0.0734 +[2026-03-20T19:32:27.340164Z] Loop 8998: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0019, Entropy: 0.0725 +[2026-03-20T19:32:28.193082Z] Loop 8999: Loss: 1.30e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0723 +[2026-03-20T19:32:29.089968Z] Loop 9000: Loss: 1.29e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0726 +[2026-03-20T19:32:29.944589Z] Loop 9001: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0726 +[2026-03-20T19:32:30.798870Z] Loop 9002: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0779 +[2026-03-20T19:32:31.652985Z] Loop 9003: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0784 +[2026-03-20T19:32:32.506539Z] Loop 9004: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0765 +[2026-03-20T19:32:33.361140Z] Loop 9005: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0757 +[2026-03-20T19:32:34.216265Z] Loop 9006: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0806 +[2026-03-20T19:32:35.071286Z] Loop 9007: Loss: 1.45e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0785 +[2026-03-20T19:32:35.924594Z] Loop 9008: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0805 +[2026-03-20T19:32:36.778187Z] Loop 9009: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0780 +[2026-03-20T19:32:37.674561Z] Loop 9010: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0783 +[2026-03-20T19:32:38.527903Z] Loop 9011: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0871 +[2026-03-20T19:32:39.381910Z] Loop 9012: Loss: 1.62e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0842 +[2026-03-20T19:32:40.237259Z] Loop 9013: Loss: 1.80e-02, Avg Return: 0.860, Regret: 0.0010, Entropy: 0.0909 +[2026-03-20T19:32:41.091100Z] Loop 9014: Loss: 1.64e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0843 +[2026-03-20T19:32:41.945392Z] Loop 9015: Loss: 1.64e-02, Avg Return: 0.860, Regret: 0.0010, Entropy: 0.0845 +[2026-03-20T19:32:42.798649Z] Loop 9016: Loss: 1.66e-02, Avg Return: 0.860, Regret: 0.0010, Entropy: 0.0857 +[2026-03-20T19:32:43.652754Z] Loop 9017: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0863 +[2026-03-20T19:32:44.507651Z] Loop 9018: Loss: 1.68e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0844 +[2026-03-20T19:32:45.361999Z] Loop 9019: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0828 +[2026-03-20T19:32:46.256212Z] Loop 9020: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0844 +[2026-03-20T19:32:47.111178Z] Loop 9021: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0833 +[2026-03-20T19:32:47.966268Z] Loop 9022: Loss: 1.53e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0809 +[2026-03-20T19:32:48.822462Z] Loop 9023: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0840 +[2026-03-20T19:32:49.678000Z] Loop 9024: Loss: 1.77e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0891 +[2026-03-20T19:32:50.532950Z] Loop 9025: Loss: 1.62e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0848 +[2026-03-20T19:32:51.388277Z] Loop 9026: Loss: 1.75e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.0905 +[2026-03-20T19:32:52.243302Z] Loop 9027: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0906 +[2026-03-20T19:32:53.098354Z] Loop 9028: Loss: 1.76e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.0928 +[2026-03-20T19:32:53.953847Z] Loop 9029: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0937 +[2026-03-20T19:32:54.851085Z] Loop 9030: Loss: 1.97e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.0983 +[2026-03-20T19:32:55.705589Z] Loop 9031: Loss: 1.75e-02, Avg Return: 0.860, Regret: 0.0015, Entropy: 0.0897 +[2026-03-20T19:32:56.560228Z] Loop 9032: Loss: 1.95e-02, Avg Return: 0.859, Regret: 0.0015, Entropy: 0.0984 +[2026-03-20T19:32:57.413927Z] Loop 9033: Loss: 2.07e-02, Avg Return: 0.854, Regret: 0.0015, Entropy: 0.1050 +[2026-03-20T19:32:58.268416Z] Loop 9034: Loss: 2.01e-02, Avg Return: 0.856, Regret: 0.0015, Entropy: 0.1038 +[2026-03-20T19:32:59.121592Z] Loop 9035: Loss: 2.15e-02, Avg Return: 0.856, Regret: 0.0015, Entropy: 0.1039 +[2026-03-20T19:32:59.975052Z] Loop 9036: Loss: 2.15e-02, Avg Return: 0.858, Regret: 0.0015, Entropy: 0.1059 +[2026-03-20T19:33:00.829583Z] Loop 9037: Loss: 2.04e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.1009 +[2026-03-20T19:33:01.684233Z] Loop 9038: Loss: 1.87e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0995 +[2026-03-20T19:33:02.537940Z] Loop 9039: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0930 +[2026-03-20T19:33:03.433064Z] Loop 9040: Loss: 1.87e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0985 +[2026-03-20T19:33:04.286848Z] Loop 9041: Loss: 1.95e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0979 +[2026-03-20T19:33:05.141876Z] Loop 9042: Loss: 2.01e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.1045 +[2026-03-20T19:33:05.997734Z] Loop 9043: Loss: 2.06e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.1071 +[2026-03-20T19:33:06.850700Z] Loop 9044: Loss: 2.12e-02, Avg Return: 0.858, Regret: 0.0012, Entropy: 0.1050 +[2026-03-20T19:33:07.702993Z] Loop 9045: Loss: 2.13e-02, Avg Return: 0.859, Regret: 0.0012, Entropy: 0.1091 +[2026-03-20T19:33:08.557472Z] Loop 9046: Loss: 2.05e-02, Avg Return: 0.858, Regret: 0.0012, Entropy: 0.1015 +[2026-03-20T19:33:09.411565Z] Loop 9047: Loss: 1.80e-02, Avg Return: 0.860, Regret: 0.0012, Entropy: 0.0947 +[2026-03-20T19:33:10.265127Z] Loop 9048: Loss: 1.91e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0940 +[2026-03-20T19:33:11.119235Z] Loop 9049: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0873 +[2026-03-20T19:33:12.013936Z] Loop 9050: Loss: 1.65e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0857 +[2026-03-20T19:33:12.869289Z] Loop 9051: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0868 +[2026-03-20T19:33:13.723881Z] Loop 9052: Loss: 1.56e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0850 +[2026-03-20T19:33:14.577611Z] Loop 9053: Loss: 1.53e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0832 +[2026-03-20T19:33:15.431999Z] Loop 9054: Loss: 1.60e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0868 +[2026-03-20T19:33:16.286321Z] Loop 9055: Loss: 1.56e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0834 +[2026-03-20T19:33:17.140270Z] Loop 9056: Loss: 1.48e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0824 +[2026-03-20T19:33:17.994415Z] Loop 9057: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0839 +[2026-03-20T19:33:18.848351Z] Loop 9058: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0849 +[2026-03-20T19:33:19.701692Z] Loop 9059: Loss: 1.61e-02, Avg Return: 0.861, Regret: 0.0004, Entropy: 0.0862 +[2026-03-20T19:33:20.595146Z] Loop 9060: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0866 +[2026-03-20T19:33:21.450070Z] Loop 9061: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0947 +[2026-03-20T19:33:22.304162Z] Loop 9062: Loss: 1.69e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.0864 +[2026-03-20T19:33:23.157646Z] Loop 9063: Loss: 1.78e-02, Avg Return: 0.860, Regret: 0.0014, Entropy: 0.0904 +[2026-03-20T19:33:24.012610Z] Loop 9064: Loss: 1.59e-02, Avg Return: 0.860, Regret: 0.0014, Entropy: 0.0847 +[2026-03-20T19:33:24.867203Z] Loop 9065: Loss: 1.78e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.0935 +[2026-03-20T19:33:25.720971Z] Loop 9066: Loss: 1.76e-02, Avg Return: 0.859, Regret: 0.0014, Entropy: 0.0942 +[2026-03-20T19:33:26.573634Z] Loop 9067: Loss: 1.82e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.0960 +[2026-03-20T19:33:27.426544Z] Loop 9068: Loss: 2.00e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.0975 +[2026-03-20T19:33:28.280805Z] Loop 9069: Loss: 2.05e-02, Avg Return: 0.860, Regret: 0.0014, Entropy: 0.1043 +[2026-03-20T19:33:29.174798Z] Loop 9070: Loss: 1.92e-02, Avg Return: 0.860, Regret: 0.0044, Entropy: 0.0963 +[2026-03-20T19:33:30.029185Z] Loop 9071: Loss: 2.01e-02, Avg Return: 0.860, Regret: 0.0044, Entropy: 0.0989 +[2026-03-20T19:33:30.883218Z] Loop 9072: Loss: 2.07e-02, Avg Return: 0.859, Regret: 0.0044, Entropy: 0.1045 +[2026-03-20T19:33:31.737772Z] Loop 9073: Loss: 1.94e-02, Avg Return: 0.860, Regret: 0.0044, Entropy: 0.0998 +[2026-03-20T19:33:32.591727Z] Loop 9074: Loss: 1.89e-02, Avg Return: 0.861, Regret: 0.0044, Entropy: 0.0963 +[2026-03-20T19:33:33.445391Z] Loop 9075: Loss: 1.99e-02, Avg Return: 0.860, Regret: 0.0044, Entropy: 0.1002 +[2026-03-20T19:33:34.299456Z] Loop 9076: Loss: 1.86e-02, Avg Return: 0.861, Regret: 0.0044, Entropy: 0.0963 +[2026-03-20T19:33:35.153440Z] Loop 9077: Loss: 1.95e-02, Avg Return: 0.861, Regret: 0.0044, Entropy: 0.1002 +[2026-03-20T19:33:36.008246Z] Loop 9078: Loss: 1.92e-02, Avg Return: 0.860, Regret: 0.0044, Entropy: 0.0929 +[2026-03-20T19:33:36.862012Z] Loop 9079: Loss: 2.04e-02, Avg Return: 0.859, Regret: 0.0044, Entropy: 0.0973 +[2026-03-20T19:33:37.764586Z] Loop 9080: Loss: 1.90e-02, Avg Return: 0.861, Regret: 0.0033, Entropy: 0.0977 +[2026-03-20T19:33:38.619798Z] Loop 9081: Loss: 2.05e-02, Avg Return: 0.860, Regret: 0.0033, Entropy: 0.1033 +[2026-03-20T19:33:39.473650Z] Loop 9082: Loss: 2.04e-02, Avg Return: 0.861, Regret: 0.0033, Entropy: 0.1018 +[2026-03-20T19:33:40.329139Z] Loop 9083: Loss: 2.02e-02, Avg Return: 0.860, Regret: 0.0033, Entropy: 0.0983 +[2026-03-20T19:33:41.184325Z] Loop 9084: Loss: 1.95e-02, Avg Return: 0.858, Regret: 0.0033, Entropy: 0.0959 +[2026-03-20T19:33:42.038112Z] Loop 9085: Loss: 2.06e-02, Avg Return: 0.860, Regret: 0.0033, Entropy: 0.1025 +[2026-03-20T19:33:42.892967Z] Loop 9086: Loss: 1.94e-02, Avg Return: 0.861, Regret: 0.0033, Entropy: 0.0969 +[2026-03-20T19:33:43.746767Z] Loop 9087: Loss: 2.08e-02, Avg Return: 0.861, Regret: 0.0033, Entropy: 0.1012 +[2026-03-20T19:33:44.601414Z] Loop 9088: Loss: 1.94e-02, Avg Return: 0.861, Regret: 0.0033, Entropy: 0.0975 +[2026-03-20T19:33:45.454212Z] Loop 9089: Loss: 1.89e-02, Avg Return: 0.863, Regret: 0.0033, Entropy: 0.0946 +[2026-03-20T19:33:46.349100Z] Loop 9090: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0978 +[2026-03-20T19:33:47.204908Z] Loop 9091: Loss: 1.82e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0932 +[2026-03-20T19:33:48.059496Z] Loop 9092: Loss: 1.80e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0916 +[2026-03-20T19:33:48.912602Z] Loop 9093: Loss: 1.91e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0948 +[2026-03-20T19:33:49.766869Z] Loop 9094: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0875 +[2026-03-20T19:33:50.622375Z] Loop 9095: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0910 +[2026-03-20T19:33:51.478108Z] Loop 9096: Loss: 1.87e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0951 +[2026-03-20T19:33:52.331956Z] Loop 9097: Loss: 1.93e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0961 +[2026-03-20T19:33:53.185214Z] Loop 9098: Loss: 1.98e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0993 +[2026-03-20T19:33:54.038903Z] Loop 9099: Loss: 1.82e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0918 +[2026-03-20T19:33:54.933606Z] Loop 9100: Loss: 1.87e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0938 +[2026-03-20T19:33:55.788921Z] Loop 9101: Loss: 1.83e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0976 +[2026-03-20T19:33:56.643746Z] Loop 9102: Loss: 1.88e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0964 +[2026-03-20T19:33:57.498155Z] Loop 9103: Loss: 2.09e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.1047 +[2026-03-20T19:33:58.353779Z] Loop 9104: Loss: 1.99e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.1039 +[2026-03-20T19:33:59.208465Z] Loop 9105: Loss: 2.08e-02, Avg Return: 0.860, Regret: 0.0008, Entropy: 0.1099 +[2026-03-20T19:34:00.063407Z] Loop 9106: Loss: 2.03e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.1072 +[2026-03-20T19:34:00.918728Z] Loop 9107: Loss: 2.01e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.1048 +[2026-03-20T19:34:01.774243Z] Loop 9108: Loss: 2.12e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.1127 +[2026-03-20T19:34:02.628156Z] Loop 9109: Loss: 2.12e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.1111 +[2026-03-20T19:34:03.522510Z] Loop 9110: Loss: 1.95e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.1042 +[2026-03-20T19:34:04.377503Z] Loop 9111: Loss: 2.01e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.1048 +[2026-03-20T19:34:05.231168Z] Loop 9112: Loss: 2.02e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.1031 +[2026-03-20T19:34:06.085377Z] Loop 9113: Loss: 2.04e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.1049 +[2026-03-20T19:34:06.939303Z] Loop 9114: Loss: 1.97e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.1002 +[2026-03-20T19:34:07.794216Z] Loop 9115: Loss: 1.87e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0961 +[2026-03-20T19:34:08.647700Z] Loop 9116: Loss: 1.83e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0949 +[2026-03-20T19:34:09.501200Z] Loop 9117: Loss: 1.80e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0955 +[2026-03-20T19:34:10.355098Z] Loop 9118: Loss: 1.81e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0929 +[2026-03-20T19:34:11.209494Z] Loop 9119: Loss: 1.80e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0919 +[2026-03-20T19:34:12.103688Z] Loop 9120: Loss: 1.92e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0989 +[2026-03-20T19:34:12.957105Z] Loop 9121: Loss: 1.95e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.1008 +[2026-03-20T19:34:13.812067Z] Loop 9122: Loss: 2.00e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.1001 +[2026-03-20T19:34:14.666273Z] Loop 9123: Loss: 2.01e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0999 +[2026-03-20T19:34:15.519850Z] Loop 9124: Loss: 1.90e-02, Avg Return: 0.860, Regret: 0.0011, Entropy: 0.0960 +[2026-03-20T19:34:16.373385Z] Loop 9125: Loss: 1.95e-02, Avg Return: 0.860, Regret: 0.0011, Entropy: 0.0999 +[2026-03-20T19:34:17.227040Z] Loop 9126: Loss: 1.93e-02, Avg Return: 0.860, Regret: 0.0011, Entropy: 0.1014 +[2026-03-20T19:34:18.080719Z] Loop 9127: Loss: 1.97e-02, Avg Return: 0.860, Regret: 0.0011, Entropy: 0.1010 +[2026-03-20T19:34:18.934318Z] Loop 9128: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0983 +[2026-03-20T19:34:19.788169Z] Loop 9129: Loss: 1.87e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0945 +[2026-03-20T19:34:20.684066Z] Loop 9130: Loss: 1.79e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0949 +[2026-03-20T19:34:21.539077Z] Loop 9131: Loss: 1.87e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0921 +[2026-03-20T19:34:22.393335Z] Loop 9132: Loss: 1.74e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0880 +[2026-03-20T19:34:23.247874Z] Loop 9133: Loss: 1.68e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0854 +[2026-03-20T19:34:24.100646Z] Loop 9134: Loss: 1.79e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0902 +[2026-03-20T19:34:24.954082Z] Loop 9135: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0890 +[2026-03-20T19:34:25.808161Z] Loop 9136: Loss: 1.96e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0980 +[2026-03-20T19:34:26.663721Z] Loop 9137: Loss: 1.91e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0930 +[2026-03-20T19:34:27.517419Z] Loop 9138: Loss: 2.01e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0968 +[2026-03-20T19:34:28.372982Z] Loop 9139: Loss: 1.93e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0969 +[2026-03-20T19:34:29.269097Z] Loop 9140: Loss: 1.90e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0954 +[2026-03-20T19:34:30.123867Z] Loop 9141: Loss: 2.06e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.1006 +[2026-03-20T19:34:30.978007Z] Loop 9142: Loss: 1.93e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0996 +[2026-03-20T19:34:31.832386Z] Loop 9143: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0930 +[2026-03-20T19:34:32.685685Z] Loop 9144: Loss: 1.84e-02, Avg Return: 0.865, Regret: 0.0006, Entropy: 0.0966 +[2026-03-20T19:34:33.539987Z] Loop 9145: Loss: 1.95e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.1010 +[2026-03-20T19:34:34.394694Z] Loop 9146: Loss: 1.88e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0945 +[2026-03-20T19:34:35.248826Z] Loop 9147: Loss: 1.72e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0923 +[2026-03-20T19:34:36.102747Z] Loop 9148: Loss: 1.74e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0909 +[2026-03-20T19:34:36.956227Z] Loop 9149: Loss: 1.88e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0968 +[2026-03-20T19:34:37.852002Z] Loop 9150: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0908 +[2026-03-20T19:34:38.705776Z] Loop 9151: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0887 +[2026-03-20T19:34:39.558948Z] Loop 9152: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0871 +[2026-03-20T19:34:40.412824Z] Loop 9153: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0883 +[2026-03-20T19:34:41.267766Z] Loop 9154: Loss: 1.86e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0909 +[2026-03-20T19:34:42.122440Z] Loop 9155: Loss: 1.89e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0918 +[2026-03-20T19:34:42.976271Z] Loop 9156: Loss: 1.88e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0924 +[2026-03-20T19:34:43.830139Z] Loop 9157: Loss: 1.82e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0964 +[2026-03-20T19:34:44.684354Z] Loop 9158: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0974 +[2026-03-20T19:34:45.538157Z] Loop 9159: Loss: 1.88e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0936 +[2026-03-20T19:34:46.434020Z] Loop 9160: Loss: 1.71e-02, Avg Return: 0.860, Regret: 0.0027, Entropy: 0.0951 +[2026-03-20T19:34:47.287840Z] Loop 9161: Loss: 1.58e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.0894 +[2026-03-20T19:34:48.141925Z] Loop 9162: Loss: 1.83e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.0971 +[2026-03-20T19:34:48.995364Z] Loop 9163: Loss: 1.87e-02, Avg Return: 0.860, Regret: 0.0027, Entropy: 0.0983 +[2026-03-20T19:34:49.849830Z] Loop 9164: Loss: 2.00e-02, Avg Return: 0.858, Regret: 0.0027, Entropy: 0.1027 +[2026-03-20T19:34:50.703812Z] Loop 9165: Loss: 2.04e-02, Avg Return: 0.858, Regret: 0.0027, Entropy: 0.1060 +[2026-03-20T19:34:51.557258Z] Loop 9166: Loss: 2.08e-02, Avg Return: 0.859, Regret: 0.0027, Entropy: 0.1072 +[2026-03-20T19:34:52.410853Z] Loop 9167: Loss: 2.00e-02, Avg Return: 0.860, Regret: 0.0027, Entropy: 0.1044 +[2026-03-20T19:34:53.264814Z] Loop 9168: Loss: 1.77e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.0957 +[2026-03-20T19:34:54.118897Z] Loop 9169: Loss: 1.75e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.0939 +[2026-03-20T19:34:55.014229Z] Loop 9170: Loss: 1.74e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0879 +[2026-03-20T19:34:55.868785Z] Loop 9171: Loss: 1.74e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0924 +[2026-03-20T19:34:56.723562Z] Loop 9172: Loss: 1.88e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0943 +[2026-03-20T19:34:57.578745Z] Loop 9173: Loss: 1.88e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0934 +[2026-03-20T19:34:58.434213Z] Loop 9174: Loss: 1.94e-02, Avg Return: 0.864, Regret: 0.0013, Entropy: 0.0969 +[2026-03-20T19:34:59.289839Z] Loop 9175: Loss: 1.89e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0978 +[2026-03-20T19:35:00.145018Z] Loop 9176: Loss: 1.88e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0961 +[2026-03-20T19:35:01.000148Z] Loop 9177: Loss: 1.80e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0918 +[2026-03-20T19:35:01.856432Z] Loop 9178: Loss: 1.84e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0957 +[2026-03-20T19:35:02.711094Z] Loop 9179: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0914 +[2026-03-20T19:35:03.605237Z] Loop 9180: Loss: 1.70e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0931 +[2026-03-20T19:35:04.459692Z] Loop 9181: Loss: 1.77e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0956 +[2026-03-20T19:35:05.315107Z] Loop 9182: Loss: 1.85e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0985 +[2026-03-20T19:35:06.168905Z] Loop 9183: Loss: 2.00e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.1042 +[2026-03-20T19:35:07.023360Z] Loop 9184: Loss: 2.33e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.1179 +[2026-03-20T19:35:07.876878Z] Loop 9185: Loss: 2.89e-02, Avg Return: 0.858, Regret: 0.0011, Entropy: 0.1477 +[2026-03-20T19:35:08.731290Z] Loop 9186: Loss: 3.26e-02, Avg Return: 0.859, Regret: 0.0011, Entropy: 0.1685 +[2026-03-20T19:35:09.584808Z] Loop 9187: Loss: 3.17e-02, Avg Return: 0.857, Regret: 0.0011, Entropy: 0.1650 +[2026-03-20T19:35:10.438859Z] Loop 9188: Loss: 3.55e-02, Avg Return: 0.858, Regret: 0.0011, Entropy: 0.1744 +[2026-03-20T19:35:11.293432Z] Loop 9189: Loss: 3.15e-02, Avg Return: 0.859, Regret: 0.0011, Entropy: 0.1565 +[2026-03-20T19:35:12.188189Z] Loop 9190: Loss: 2.90e-02, Avg Return: 0.860, Regret: 0.0028, Entropy: 0.1449 +[2026-03-20T19:35:13.042824Z] Loop 9191: Loss: 2.65e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.1354 +[2026-03-20T19:35:13.897109Z] Loop 9192: Loss: 2.50e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.1319 +[2026-03-20T19:35:14.750713Z] Loop 9193: Loss: 2.68e-02, Avg Return: 0.863, Regret: 0.0028, Entropy: 0.1310 +[2026-03-20T19:35:15.605645Z] Loop 9194: Loss: 2.69e-02, Avg Return: 0.863, Regret: 0.0028, Entropy: 0.1290 +[2026-03-20T19:35:16.460760Z] Loop 9195: Loss: 2.50e-02, Avg Return: 0.863, Regret: 0.0028, Entropy: 0.1259 +[2026-03-20T19:35:17.314607Z] Loop 9196: Loss: 2.63e-02, Avg Return: 0.863, Regret: 0.0028, Entropy: 0.1303 +[2026-03-20T19:35:18.168209Z] Loop 9197: Loss: 2.45e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.1233 +[2026-03-20T19:35:19.022706Z] Loop 9198: Loss: 2.60e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.1300 +[2026-03-20T19:35:19.876559Z] Loop 9199: Loss: 2.50e-02, Avg Return: 0.863, Regret: 0.0028, Entropy: 0.1241 +[2026-03-20T19:35:20.770590Z] Loop 9200: Loss: 2.42e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.1180 +[2026-03-20T19:35:21.624789Z] Loop 9201: Loss: 2.21e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.1125 +[2026-03-20T19:35:22.478287Z] Loop 9202: Loss: 2.15e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.1087 +[2026-03-20T19:35:23.331317Z] Loop 9203: Loss: 2.26e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.1096 +[2026-03-20T19:35:24.185501Z] Loop 9204: Loss: 2.23e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.1100 +[2026-03-20T19:35:25.039710Z] Loop 9205: Loss: 2.05e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.1056 +[2026-03-20T19:35:25.894270Z] Loop 9206: Loss: 2.15e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.1113 +[2026-03-20T19:35:26.747831Z] Loop 9207: Loss: 2.10e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.1059 +[2026-03-20T19:35:27.601662Z] Loop 9208: Loss: 2.18e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.1093 +[2026-03-20T19:35:28.457032Z] Loop 9209: Loss: 2.10e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.1099 +[2026-03-20T19:35:29.351834Z] Loop 9210: Loss: 2.17e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.1056 +[2026-03-20T19:35:30.204880Z] Loop 9211: Loss: 2.02e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.1070 +[2026-03-20T19:35:31.058895Z] Loop 9212: Loss: 1.98e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.1033 +[2026-03-20T19:35:31.912674Z] Loop 9213: Loss: 2.00e-02, Avg Return: 0.862, Regret: 0.0027, Entropy: 0.1051 +[2026-03-20T19:35:32.766959Z] Loop 9214: Loss: 2.15e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.1075 +[2026-03-20T19:35:33.620653Z] Loop 9215: Loss: 2.00e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.1082 +[2026-03-20T19:35:34.474649Z] Loop 9216: Loss: 2.05e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.1069 +[2026-03-20T19:35:35.329445Z] Loop 9217: Loss: 2.04e-02, Avg Return: 0.862, Regret: 0.0027, Entropy: 0.1040 +[2026-03-20T19:35:36.183330Z] Loop 9218: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0027, Entropy: 0.1004 +[2026-03-20T19:35:37.038145Z] Loop 9219: Loss: 1.95e-02, Avg Return: 0.863, Regret: 0.0027, Entropy: 0.0995 +[2026-03-20T19:35:37.932275Z] Loop 9220: Loss: 1.85e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0977 +[2026-03-20T19:35:38.785922Z] Loop 9221: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0994 +[2026-03-20T19:35:39.639806Z] Loop 9222: Loss: 1.99e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0997 +[2026-03-20T19:35:40.494384Z] Loop 9223: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1023 +[2026-03-20T19:35:41.348910Z] Loop 9224: Loss: 1.95e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.1014 +[2026-03-20T19:35:42.202099Z] Loop 9225: Loss: 1.94e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.1039 +[2026-03-20T19:35:43.055061Z] Loop 9226: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0997 +[2026-03-20T19:35:43.908495Z] Loop 9227: Loss: 2.04e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1090 +[2026-03-20T19:35:44.763273Z] Loop 9228: Loss: 2.24e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.1130 +[2026-03-20T19:35:45.617008Z] Loop 9229: Loss: 2.38e-02, Avg Return: 0.860, Regret: 0.0013, Entropy: 0.1213 +[2026-03-20T19:35:46.511668Z] Loop 9230: Loss: 2.56e-02, Avg Return: 0.858, Regret: 0.0054, Entropy: 0.1317 +[2026-03-20T19:35:47.365226Z] Loop 9231: Loss: 2.60e-02, Avg Return: 0.858, Regret: 0.0054, Entropy: 0.1329 +[2026-03-20T19:35:48.219145Z] Loop 9232: Loss: 2.42e-02, Avg Return: 0.860, Regret: 0.0054, Entropy: 0.1253 +[2026-03-20T19:35:49.072321Z] Loop 9233: Loss: 2.28e-02, Avg Return: 0.860, Regret: 0.0054, Entropy: 0.1168 +[2026-03-20T19:35:49.925718Z] Loop 9234: Loss: 2.21e-02, Avg Return: 0.861, Regret: 0.0054, Entropy: 0.1143 +[2026-03-20T19:35:50.778870Z] Loop 9235: Loss: 2.24e-02, Avg Return: 0.862, Regret: 0.0054, Entropy: 0.1138 +[2026-03-20T19:35:51.633120Z] Loop 9236: Loss: 2.21e-02, Avg Return: 0.863, Regret: 0.0054, Entropy: 0.1153 +[2026-03-20T19:35:52.487085Z] Loop 9237: Loss: 2.27e-02, Avg Return: 0.863, Regret: 0.0054, Entropy: 0.1101 +[2026-03-20T19:35:53.340216Z] Loop 9238: Loss: 2.26e-02, Avg Return: 0.863, Regret: 0.0054, Entropy: 0.1130 +[2026-03-20T19:35:54.193487Z] Loop 9239: Loss: 2.28e-02, Avg Return: 0.863, Regret: 0.0054, Entropy: 0.1113 +[2026-03-20T19:35:55.088081Z] Loop 9240: Loss: 2.31e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.1116 +[2026-03-20T19:35:55.941921Z] Loop 9241: Loss: 2.15e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.1070 +[2026-03-20T19:35:56.796085Z] Loop 9242: Loss: 2.07e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.1006 +[2026-03-20T19:35:57.650642Z] Loop 9243: Loss: 1.98e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0956 +[2026-03-20T19:35:58.505286Z] Loop 9244: Loss: 1.88e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0951 +[2026-03-20T19:35:59.359802Z] Loop 9245: Loss: 1.89e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0950 +[2026-03-20T19:36:00.213872Z] Loop 9246: Loss: 1.90e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0966 +[2026-03-20T19:36:01.067824Z] Loop 9247: Loss: 1.93e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0943 +[2026-03-20T19:36:01.925299Z] Loop 9248: Loss: 1.97e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0964 +[2026-03-20T19:36:02.779837Z] Loop 9249: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0942 +[2026-03-20T19:36:03.682914Z] Loop 9250: Loss: 1.87e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0929 +[2026-03-20T19:36:04.540943Z] Loop 9251: Loss: 1.89e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0928 +[2026-03-20T19:36:05.395970Z] Loop 9252: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0922 +[2026-03-20T19:36:06.251151Z] Loop 9253: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0912 +[2026-03-20T19:36:07.105775Z] Loop 9254: Loss: 1.78e-02, Avg Return: 0.864, Regret: 0.0016, Entropy: 0.0884 +[2026-03-20T19:36:07.959486Z] Loop 9255: Loss: 1.55e-02, Avg Return: 0.865, Regret: 0.0016, Entropy: 0.0799 +[2026-03-20T19:36:08.813898Z] Loop 9256: Loss: 1.62e-02, Avg Return: 0.864, Regret: 0.0016, Entropy: 0.0798 +[2026-03-20T19:36:09.667414Z] Loop 9257: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0761 +[2026-03-20T19:36:10.521271Z] Loop 9258: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0765 +[2026-03-20T19:36:11.374770Z] Loop 9259: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0874 +[2026-03-20T19:36:12.268736Z] Loop 9260: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0838 +[2026-03-20T19:36:13.122719Z] Loop 9261: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0775 +[2026-03-20T19:36:13.977012Z] Loop 9262: Loss: 1.54e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0793 +[2026-03-20T19:36:14.832768Z] Loop 9263: Loss: 1.74e-02, Avg Return: 0.859, Regret: 0.0007, Entropy: 0.0913 +[2026-03-20T19:36:15.688498Z] Loop 9264: Loss: 1.81e-02, Avg Return: 0.857, Regret: 0.0007, Entropy: 0.0932 +[2026-03-20T19:36:16.543142Z] Loop 9265: Loss: 1.89e-02, Avg Return: 0.857, Regret: 0.0007, Entropy: 0.0966 +[2026-03-20T19:36:17.397542Z] Loop 9266: Loss: 1.80e-02, Avg Return: 0.857, Regret: 0.0007, Entropy: 0.0933 +[2026-03-20T19:36:18.252945Z] Loop 9267: Loss: 1.75e-02, Avg Return: 0.859, Regret: 0.0007, Entropy: 0.0929 +[2026-03-20T19:36:19.107862Z] Loop 9268: Loss: 1.77e-02, Avg Return: 0.860, Regret: 0.0007, Entropy: 0.0885 +[2026-03-20T19:36:19.961170Z] Loop 9269: Loss: 1.73e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0911 +[2026-03-20T19:36:20.855414Z] Loop 9270: Loss: 1.68e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0886 +[2026-03-20T19:36:21.709053Z] Loop 9271: Loss: 1.67e-02, Avg Return: 0.860, Regret: 0.0019, Entropy: 0.0861 +[2026-03-20T19:36:22.562901Z] Loop 9272: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0019, Entropy: 0.0841 +[2026-03-20T19:36:23.416719Z] Loop 9273: Loss: 1.69e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0864 +[2026-03-20T19:36:24.270750Z] Loop 9274: Loss: 1.63e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0829 +[2026-03-20T19:36:25.124858Z] Loop 9275: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0019, Entropy: 0.0839 +[2026-03-20T19:36:25.978524Z] Loop 9276: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0019, Entropy: 0.0827 +[2026-03-20T19:36:26.832147Z] Loop 9277: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0792 +[2026-03-20T19:36:27.687220Z] Loop 9278: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0794 +[2026-03-20T19:36:28.540859Z] Loop 9279: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0019, Entropy: 0.0810 +[2026-03-20T19:36:29.434549Z] Loop 9280: Loss: 1.53e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0793 +[2026-03-20T19:36:30.289011Z] Loop 9281: Loss: 1.70e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0877 +[2026-03-20T19:36:31.143911Z] Loop 9282: Loss: 1.69e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0917 +[2026-03-20T19:36:31.998972Z] Loop 9283: Loss: 1.75e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0911 +[2026-03-20T19:36:32.852833Z] Loop 9284: Loss: 1.70e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0903 +[2026-03-20T19:36:33.707837Z] Loop 9285: Loss: 1.90e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0980 +[2026-03-20T19:36:34.561873Z] Loop 9286: Loss: 1.94e-02, Avg Return: 0.858, Regret: 0.0011, Entropy: 0.0992 +[2026-03-20T19:36:35.415847Z] Loop 9287: Loss: 2.05e-02, Avg Return: 0.856, Regret: 0.0011, Entropy: 0.1039 +[2026-03-20T19:36:36.268678Z] Loop 9288: Loss: 2.27e-02, Avg Return: 0.853, Regret: 0.0011, Entropy: 0.1160 +[2026-03-20T19:36:37.121590Z] Loop 9289: Loss: 1.84e-02, Avg Return: 0.856, Regret: 0.0011, Entropy: 0.1034 +[2026-03-20T19:36:38.015065Z] Loop 9290: Loss: 1.97e-02, Avg Return: 0.858, Regret: 0.0054, Entropy: 0.1045 +[2026-03-20T19:36:38.869538Z] Loop 9291: Loss: 1.74e-02, Avg Return: 0.859, Regret: 0.0054, Entropy: 0.0930 +[2026-03-20T19:36:39.723946Z] Loop 9292: Loss: 1.81e-02, Avg Return: 0.860, Regret: 0.0054, Entropy: 0.0896 +[2026-03-20T19:36:40.577553Z] Loop 9293: Loss: 1.75e-02, Avg Return: 0.861, Regret: 0.0054, Entropy: 0.0934 +[2026-03-20T19:36:41.431220Z] Loop 9294: Loss: 1.70e-02, Avg Return: 0.860, Regret: 0.0054, Entropy: 0.0906 +[2026-03-20T19:36:42.286033Z] Loop 9295: Loss: 1.80e-02, Avg Return: 0.862, Regret: 0.0054, Entropy: 0.0903 +[2026-03-20T19:36:43.140722Z] Loop 9296: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0054, Entropy: 0.0901 +[2026-03-20T19:36:43.995018Z] Loop 9297: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0054, Entropy: 0.0932 +[2026-03-20T19:36:44.848868Z] Loop 9298: Loss: 1.84e-02, Avg Return: 0.863, Regret: 0.0054, Entropy: 0.0897 +[2026-03-20T19:36:45.704233Z] Loop 9299: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0054, Entropy: 0.0889 +[2026-03-20T19:36:46.598850Z] Loop 9300: Loss: 1.77e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0853 +[2026-03-20T19:36:47.452640Z] Loop 9301: Loss: 1.77e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0871 +[2026-03-20T19:36:48.307130Z] Loop 9302: Loss: 1.67e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0842 +[2026-03-20T19:36:49.161578Z] Loop 9303: Loss: 1.60e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0852 +[2026-03-20T19:36:50.015972Z] Loop 9304: Loss: 1.69e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0847 +[2026-03-20T19:36:50.869319Z] Loop 9305: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0828 +[2026-03-20T19:36:51.722533Z] Loop 9306: Loss: 1.75e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0848 +[2026-03-20T19:36:52.576905Z] Loop 9307: Loss: 1.67e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0852 +[2026-03-20T19:36:53.430803Z] Loop 9308: Loss: 1.72e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0860 +[2026-03-20T19:36:54.284591Z] Loop 9309: Loss: 1.73e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0857 +[2026-03-20T19:36:55.178177Z] Loop 9310: Loss: 1.77e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0874 +[2026-03-20T19:36:56.031774Z] Loop 9311: Loss: 1.77e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0902 +[2026-03-20T19:36:56.886706Z] Loop 9312: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0900 +[2026-03-20T19:36:57.741074Z] Loop 9313: Loss: 1.74e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0901 +[2026-03-20T19:36:58.595099Z] Loop 9314: Loss: 1.84e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0913 +[2026-03-20T19:36:59.448794Z] Loop 9315: Loss: 1.88e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0907 +[2026-03-20T19:37:00.301925Z] Loop 9316: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0884 +[2026-03-20T19:37:01.157057Z] Loop 9317: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0884 +[2026-03-20T19:37:02.012174Z] Loop 9318: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0896 +[2026-03-20T19:37:02.866616Z] Loop 9319: Loss: 1.81e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0879 +[2026-03-20T19:37:03.760742Z] Loop 9320: Loss: 1.83e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0932 +[2026-03-20T19:37:04.614110Z] Loop 9321: Loss: 1.89e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0927 +[2026-03-20T19:37:05.470174Z] Loop 9322: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0962 +[2026-03-20T19:37:06.324761Z] Loop 9323: Loss: 1.95e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0974 +[2026-03-20T19:37:07.179518Z] Loop 9324: Loss: 2.03e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.1013 +[2026-03-20T19:37:08.034376Z] Loop 9325: Loss: 1.89e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.1002 +[2026-03-20T19:37:08.889366Z] Loop 9326: Loss: 1.94e-02, Avg Return: 0.860, Regret: 0.0006, Entropy: 0.1009 +[2026-03-20T19:37:09.744309Z] Loop 9327: Loss: 1.89e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.0958 +[2026-03-20T19:37:10.598418Z] Loop 9328: Loss: 1.82e-02, Avg Return: 0.859, Regret: 0.0006, Entropy: 0.0951 +[2026-03-20T19:37:11.451795Z] Loop 9329: Loss: 1.74e-02, Avg Return: 0.858, Regret: 0.0006, Entropy: 0.0914 +[2026-03-20T19:37:12.348352Z] Loop 9330: Loss: 1.70e-02, Avg Return: 0.859, Regret: 0.0050, Entropy: 0.0879 +[2026-03-20T19:37:13.202178Z] Loop 9331: Loss: 1.68e-02, Avg Return: 0.858, Regret: 0.0050, Entropy: 0.0908 +[2026-03-20T19:37:14.056634Z] Loop 9332: Loss: 1.67e-02, Avg Return: 0.857, Regret: 0.0050, Entropy: 0.0895 +[2026-03-20T19:37:14.910923Z] Loop 9333: Loss: 1.67e-02, Avg Return: 0.857, Regret: 0.0050, Entropy: 0.0900 +[2026-03-20T19:37:15.766168Z] Loop 9334: Loss: 1.68e-02, Avg Return: 0.858, Regret: 0.0050, Entropy: 0.0902 +[2026-03-20T19:37:16.620324Z] Loop 9335: Loss: 1.49e-02, Avg Return: 0.860, Regret: 0.0050, Entropy: 0.0833 +[2026-03-20T19:37:17.473746Z] Loop 9336: Loss: 1.39e-02, Avg Return: 0.861, Regret: 0.0050, Entropy: 0.0778 +[2026-03-20T19:37:18.327748Z] Loop 9337: Loss: 1.33e-02, Avg Return: 0.861, Regret: 0.0050, Entropy: 0.0742 +[2026-03-20T19:37:19.182096Z] Loop 9338: Loss: 1.41e-02, Avg Return: 0.861, Regret: 0.0050, Entropy: 0.0757 +[2026-03-20T19:37:20.035592Z] Loop 9339: Loss: 1.33e-02, Avg Return: 0.861, Regret: 0.0050, Entropy: 0.0705 +[2026-03-20T19:37:20.929237Z] Loop 9340: Loss: 1.35e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0728 +[2026-03-20T19:37:21.785014Z] Loop 9341: Loss: 1.30e-02, Avg Return: 0.864, Regret: 0.0018, Entropy: 0.0694 +[2026-03-20T19:37:22.640693Z] Loop 9342: Loss: 1.34e-02, Avg Return: 0.864, Regret: 0.0018, Entropy: 0.0708 +[2026-03-20T19:37:23.494988Z] Loop 9343: Loss: 1.23e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0700 +[2026-03-20T19:37:24.350442Z] Loop 9344: Loss: 1.31e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0729 +[2026-03-20T19:37:25.204958Z] Loop 9345: Loss: 1.30e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0703 +[2026-03-20T19:37:26.060973Z] Loop 9346: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0724 +[2026-03-20T19:37:26.915331Z] Loop 9347: Loss: 1.36e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0738 +[2026-03-20T19:37:27.769950Z] Loop 9348: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0715 +[2026-03-20T19:37:28.624724Z] Loop 9349: Loss: 1.31e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0723 +[2026-03-20T19:37:29.519942Z] Loop 9350: Loss: 1.30e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0705 +[2026-03-20T19:37:30.373643Z] Loop 9351: Loss: 1.33e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0715 +[2026-03-20T19:37:31.226506Z] Loop 9352: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0710 +[2026-03-20T19:37:32.080279Z] Loop 9353: Loss: 1.30e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0710 +[2026-03-20T19:37:32.934559Z] Loop 9354: Loss: 1.35e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0728 +[2026-03-20T19:37:33.789096Z] Loop 9355: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0752 +[2026-03-20T19:37:34.642278Z] Loop 9356: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0736 +[2026-03-20T19:37:35.496115Z] Loop 9357: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0720 +[2026-03-20T19:37:36.349715Z] Loop 9358: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0749 +[2026-03-20T19:37:37.204343Z] Loop 9359: Loss: 1.40e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0727 +[2026-03-20T19:37:38.097342Z] Loop 9360: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0758 +[2026-03-20T19:37:38.950631Z] Loop 9361: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0729 +[2026-03-20T19:37:39.804508Z] Loop 9362: Loss: 1.42e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0772 +[2026-03-20T19:37:40.658946Z] Loop 9363: Loss: 1.43e-02, Avg Return: 0.860, Regret: 0.0008, Entropy: 0.0793 +[2026-03-20T19:37:41.513719Z] Loop 9364: Loss: 1.54e-02, Avg Return: 0.860, Regret: 0.0008, Entropy: 0.0848 +[2026-03-20T19:37:42.367523Z] Loop 9365: Loss: 1.61e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0842 +[2026-03-20T19:37:43.222116Z] Loop 9366: Loss: 1.21e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0702 +[2026-03-20T19:37:44.076137Z] Loop 9367: Loss: 1.31e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0717 +[2026-03-20T19:37:44.930551Z] Loop 9368: Loss: 1.36e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0728 +[2026-03-20T19:37:45.784517Z] Loop 9369: Loss: 1.32e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0703 +[2026-03-20T19:37:46.678225Z] Loop 9370: Loss: 1.29e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0706 +[2026-03-20T19:37:47.531818Z] Loop 9371: Loss: 1.22e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0685 +[2026-03-20T19:37:48.386060Z] Loop 9372: Loss: 1.32e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0702 +[2026-03-20T19:37:49.239777Z] Loop 9373: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0699 +[2026-03-20T19:37:50.092644Z] Loop 9374: Loss: 1.22e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0716 +[2026-03-20T19:37:50.945478Z] Loop 9375: Loss: 1.34e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0765 +[2026-03-20T19:37:51.799201Z] Loop 9376: Loss: 1.35e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0759 +[2026-03-20T19:37:52.653241Z] Loop 9377: Loss: 1.31e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0682 +[2026-03-20T19:37:53.507516Z] Loop 9378: Loss: 1.32e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0715 +[2026-03-20T19:37:54.360274Z] Loop 9379: Loss: 1.24e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0695 +[2026-03-20T19:37:55.252548Z] Loop 9380: Loss: 1.28e-02, Avg Return: 0.860, Regret: 0.0020, Entropy: 0.0710 +[2026-03-20T19:37:56.107083Z] Loop 9381: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.0721 +[2026-03-20T19:37:56.961710Z] Loop 9382: Loss: 1.16e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.0634 +[2026-03-20T19:37:57.815402Z] Loop 9383: Loss: 1.24e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.0689 +[2026-03-20T19:37:58.669661Z] Loop 9384: Loss: 1.22e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0656 +[2026-03-20T19:37:59.524342Z] Loop 9385: Loss: 1.40e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.0720 +[2026-03-20T19:38:00.381678Z] Loop 9386: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.0746 +[2026-03-20T19:38:01.235810Z] Loop 9387: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.0760 +[2026-03-20T19:38:02.089623Z] Loop 9388: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.0775 +[2026-03-20T19:38:02.942677Z] Loop 9389: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0777 +[2026-03-20T19:38:03.837800Z] Loop 9390: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0811 +[2026-03-20T19:38:04.692902Z] Loop 9391: Loss: 1.46e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0804 +[2026-03-20T19:38:05.547925Z] Loop 9392: Loss: 1.62e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0863 +[2026-03-20T19:38:06.403508Z] Loop 9393: Loss: 1.54e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0867 +[2026-03-20T19:38:07.259003Z] Loop 9394: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0861 +[2026-03-20T19:38:08.113719Z] Loop 9395: Loss: 1.78e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0893 +[2026-03-20T19:38:08.968319Z] Loop 9396: Loss: 1.77e-02, Avg Return: 0.865, Regret: 0.0004, Entropy: 0.0943 +[2026-03-20T19:38:09.822718Z] Loop 9397: Loss: 1.98e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.1008 +[2026-03-20T19:38:10.677421Z] Loop 9398: Loss: 2.00e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0985 +[2026-03-20T19:38:11.531455Z] Loop 9399: Loss: 1.96e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0965 +[2026-03-20T19:38:12.424658Z] Loop 9400: Loss: 1.87e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0946 +[2026-03-20T19:38:13.279840Z] Loop 9401: Loss: 1.85e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0916 +[2026-03-20T19:38:14.134081Z] Loop 9402: Loss: 1.78e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0896 +[2026-03-20T19:38:14.988657Z] Loop 9403: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0882 +[2026-03-20T19:38:15.843392Z] Loop 9404: Loss: 1.77e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0908 +[2026-03-20T19:38:16.698089Z] Loop 9405: Loss: 1.70e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0892 +[2026-03-20T19:38:17.551517Z] Loop 9406: Loss: 1.81e-02, Avg Return: 0.861, Regret: 0.0005, Entropy: 0.0925 +[2026-03-20T19:38:18.404709Z] Loop 9407: Loss: 1.77e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0916 +[2026-03-20T19:38:19.258539Z] Loop 9408: Loss: 1.94e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0979 +[2026-03-20T19:38:20.112859Z] Loop 9409: Loss: 1.86e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0940 +[2026-03-20T19:38:21.008032Z] Loop 9410: Loss: 1.94e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0978 +[2026-03-20T19:38:21.860988Z] Loop 9411: Loss: 1.87e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0943 +[2026-03-20T19:38:22.714169Z] Loop 9412: Loss: 1.87e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0949 +[2026-03-20T19:38:23.568508Z] Loop 9413: Loss: 1.91e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0958 +[2026-03-20T19:38:24.423846Z] Loop 9414: Loss: 1.90e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0991 +[2026-03-20T19:38:25.277829Z] Loop 9415: Loss: 1.93e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0955 +[2026-03-20T19:38:26.131614Z] Loop 9416: Loss: 1.84e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0980 +[2026-03-20T19:38:26.986089Z] Loop 9417: Loss: 1.94e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0990 +[2026-03-20T19:38:27.839985Z] Loop 9418: Loss: 1.89e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0975 +[2026-03-20T19:38:28.694236Z] Loop 9419: Loss: 1.92e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0960 +[2026-03-20T19:38:29.589362Z] Loop 9420: Loss: 1.89e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0976 +[2026-03-20T19:38:30.443405Z] Loop 9421: Loss: 1.87e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0982 +[2026-03-20T19:38:31.297966Z] Loop 9422: Loss: 1.91e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0958 +[2026-03-20T19:38:32.152244Z] Loop 9423: Loss: 1.93e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0964 +[2026-03-20T19:38:33.006803Z] Loop 9424: Loss: 1.88e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0931 +[2026-03-20T19:38:33.861534Z] Loop 9425: Loss: 1.78e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0930 +[2026-03-20T19:38:34.715817Z] Loop 9426: Loss: 1.87e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0944 +[2026-03-20T19:38:35.570846Z] Loop 9427: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0876 +[2026-03-20T19:38:36.426476Z] Loop 9428: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0862 +[2026-03-20T19:38:37.282161Z] Loop 9429: Loss: 1.83e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0898 +[2026-03-20T19:38:38.176513Z] Loop 9430: Loss: 1.79e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0894 +[2026-03-20T19:38:39.031283Z] Loop 9431: Loss: 1.90e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0929 +[2026-03-20T19:38:39.885950Z] Loop 9432: Loss: 1.75e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0922 +[2026-03-20T19:38:40.739500Z] Loop 9433: Loss: 1.98e-02, Avg Return: 0.860, Regret: 0.0018, Entropy: 0.0958 +[2026-03-20T19:38:41.593075Z] Loop 9434: Loss: 1.94e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0931 +[2026-03-20T19:38:42.447231Z] Loop 9435: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0892 +[2026-03-20T19:38:43.302195Z] Loop 9436: Loss: 1.90e-02, Avg Return: 0.864, Regret: 0.0018, Entropy: 0.0918 +[2026-03-20T19:38:44.156365Z] Loop 9437: Loss: 1.82e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0898 +[2026-03-20T19:38:45.009211Z] Loop 9438: Loss: 1.94e-02, Avg Return: 0.865, Regret: 0.0018, Entropy: 0.0959 +[2026-03-20T19:38:45.862852Z] Loop 9439: Loss: 1.89e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0949 +[2026-03-20T19:38:46.757102Z] Loop 9440: Loss: 1.69e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0888 +[2026-03-20T19:38:47.611213Z] Loop 9441: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0866 +[2026-03-20T19:38:48.465040Z] Loop 9442: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0878 +[2026-03-20T19:38:49.319298Z] Loop 9443: Loss: 1.77e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0892 +[2026-03-20T19:38:50.174074Z] Loop 9444: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0863 +[2026-03-20T19:38:51.028901Z] Loop 9445: Loss: 1.89e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0913 +[2026-03-20T19:38:51.882935Z] Loop 9446: Loss: 1.88e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0938 +[2026-03-20T19:38:52.736126Z] Loop 9447: Loss: 1.89e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0921 +[2026-03-20T19:38:53.589770Z] Loop 9448: Loss: 1.91e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0907 +[2026-03-20T19:38:54.444931Z] Loop 9449: Loss: 1.81e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0906 +[2026-03-20T19:38:55.339684Z] Loop 9450: Loss: 1.85e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0930 +[2026-03-20T19:38:56.193358Z] Loop 9451: Loss: 1.79e-02, Avg Return: 0.865, Regret: 0.0002, Entropy: 0.0884 +[2026-03-20T19:38:57.048038Z] Loop 9452: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0889 +[2026-03-20T19:38:57.904102Z] Loop 9453: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0856 +[2026-03-20T19:38:58.758403Z] Loop 9454: Loss: 1.68e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0875 +[2026-03-20T19:38:59.612471Z] Loop 9455: Loss: 1.68e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0878 +[2026-03-20T19:39:00.467280Z] Loop 9456: Loss: 1.69e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0831 +[2026-03-20T19:39:01.322087Z] Loop 9457: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0848 +[2026-03-20T19:39:02.176765Z] Loop 9458: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0897 +[2026-03-20T19:39:03.032078Z] Loop 9459: Loss: 1.64e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0884 +[2026-03-20T19:39:03.927771Z] Loop 9460: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0882 +[2026-03-20T19:39:04.781961Z] Loop 9461: Loss: 1.73e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0892 +[2026-03-20T19:39:05.636732Z] Loop 9462: Loss: 1.71e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0862 +[2026-03-20T19:39:06.491302Z] Loop 9463: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0870 +[2026-03-20T19:39:07.346410Z] Loop 9464: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0863 +[2026-03-20T19:39:08.200786Z] Loop 9465: Loss: 1.81e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0902 +[2026-03-20T19:39:09.054805Z] Loop 9466: Loss: 1.77e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0870 +[2026-03-20T19:39:09.909364Z] Loop 9467: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0914 +[2026-03-20T19:39:10.764094Z] Loop 9468: Loss: 1.89e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0923 +[2026-03-20T19:39:11.618675Z] Loop 9469: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0885 +[2026-03-20T19:39:12.513822Z] Loop 9470: Loss: 1.76e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0870 +[2026-03-20T19:39:13.367787Z] Loop 9471: Loss: 1.79e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0898 +[2026-03-20T19:39:14.222519Z] Loop 9472: Loss: 1.71e-02, Avg Return: 0.865, Regret: 0.0004, Entropy: 0.0853 +[2026-03-20T19:39:15.077326Z] Loop 9473: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0894 +[2026-03-20T19:39:15.931443Z] Loop 9474: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0890 +[2026-03-20T19:39:16.785098Z] Loop 9475: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0907 +[2026-03-20T19:39:17.640300Z] Loop 9476: Loss: 1.77e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0885 +[2026-03-20T19:39:18.495590Z] Loop 9477: Loss: 1.65e-02, Avg Return: 0.861, Regret: 0.0004, Entropy: 0.0863 +[2026-03-20T19:39:19.349998Z] Loop 9478: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0815 +[2026-03-20T19:39:20.204963Z] Loop 9479: Loss: 1.70e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0886 +[2026-03-20T19:39:21.099526Z] Loop 9480: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0850 +[2026-03-20T19:39:21.954389Z] Loop 9481: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0869 +[2026-03-20T19:39:22.809104Z] Loop 9482: Loss: 1.71e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0832 +[2026-03-20T19:39:23.662325Z] Loop 9483: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0846 +[2026-03-20T19:39:24.516520Z] Loop 9484: Loss: 1.45e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0798 +[2026-03-20T19:39:25.370189Z] Loop 9485: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0809 +[2026-03-20T19:39:26.226636Z] Loop 9486: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0845 +[2026-03-20T19:39:27.080889Z] Loop 9487: Loss: 1.52e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0823 +[2026-03-20T19:39:27.933889Z] Loop 9488: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0821 +[2026-03-20T19:39:28.788216Z] Loop 9489: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0814 +[2026-03-20T19:39:29.683856Z] Loop 9490: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0777 +[2026-03-20T19:39:30.537277Z] Loop 9491: Loss: 1.40e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0735 +[2026-03-20T19:39:31.391718Z] Loop 9492: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0716 +[2026-03-20T19:39:32.245548Z] Loop 9493: Loss: 1.32e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0706 +[2026-03-20T19:39:33.099505Z] Loop 9494: Loss: 1.22e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0667 +[2026-03-20T19:39:33.953843Z] Loop 9495: Loss: 1.25e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0672 +[2026-03-20T19:39:34.809632Z] Loop 9496: Loss: 1.12e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0657 +[2026-03-20T19:39:35.663921Z] Loop 9497: Loss: 1.25e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0709 +[2026-03-20T19:39:36.517798Z] Loop 9498: Loss: 1.28e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0677 +[2026-03-20T19:39:37.373019Z] Loop 9499: Loss: 1.14e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0642 +[2026-03-20T19:39:38.267019Z] Loop 9500: Loss: 1.23e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0678 +[2026-03-20T19:39:39.119753Z] Loop 9501: Loss: 1.24e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0706 +[2026-03-20T19:39:39.973730Z] Loop 9502: Loss: 1.30e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0695 +[2026-03-20T19:39:40.829386Z] Loop 9503: Loss: 1.22e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0674 +[2026-03-20T19:39:41.683726Z] Loop 9504: Loss: 1.17e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0649 +[2026-03-20T19:39:42.537234Z] Loop 9505: Loss: 1.11e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0636 +[2026-03-20T19:39:43.390206Z] Loop 9506: Loss: 1.31e-02, Avg Return: 0.864, Regret: 0.0013, Entropy: 0.0672 +[2026-03-20T19:39:44.244374Z] Loop 9507: Loss: 1.27e-02, Avg Return: 0.864, Regret: 0.0013, Entropy: 0.0670 +[2026-03-20T19:39:45.099095Z] Loop 9508: Loss: 1.25e-02, Avg Return: 0.865, Regret: 0.0013, Entropy: 0.0663 +[2026-03-20T19:39:45.954131Z] Loop 9509: Loss: 1.20e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0667 +[2026-03-20T19:39:46.849805Z] Loop 9510: Loss: 1.33e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0695 +[2026-03-20T19:39:47.704584Z] Loop 9511: Loss: 1.29e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0702 +[2026-03-20T19:39:48.560280Z] Loop 9512: Loss: 1.31e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0696 +[2026-03-20T19:39:49.415336Z] Loop 9513: Loss: 1.40e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0743 +[2026-03-20T19:39:50.270124Z] Loop 9514: Loss: 1.47e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0751 +[2026-03-20T19:39:51.124643Z] Loop 9515: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0747 +[2026-03-20T19:39:51.979167Z] Loop 9516: Loss: 1.35e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0749 +[2026-03-20T19:39:52.834890Z] Loop 9517: Loss: 1.33e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0716 +[2026-03-20T19:39:53.688460Z] Loop 9518: Loss: 1.39e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0750 +[2026-03-20T19:39:54.542456Z] Loop 9519: Loss: 1.30e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0720 +[2026-03-20T19:39:55.437660Z] Loop 9520: Loss: 1.29e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0666 +[2026-03-20T19:39:56.291031Z] Loop 9521: Loss: 1.25e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0663 +[2026-03-20T19:39:57.144915Z] Loop 9522: Loss: 1.18e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0653 +[2026-03-20T19:39:58.000280Z] Loop 9523: Loss: 1.31e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0673 +[2026-03-20T19:39:58.853443Z] Loop 9524: Loss: 1.26e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0681 +[2026-03-20T19:39:59.706614Z] Loop 9525: Loss: 1.22e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0667 +[2026-03-20T19:40:00.560511Z] Loop 9526: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0644 +[2026-03-20T19:40:01.416165Z] Loop 9527: Loss: 1.23e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0662 +[2026-03-20T19:40:02.271787Z] Loop 9528: Loss: 1.20e-02, Avg Return: 0.861, Regret: 0.0004, Entropy: 0.0679 +[2026-03-20T19:40:03.125393Z] Loop 9529: Loss: 1.31e-02, Avg Return: 0.861, Regret: 0.0004, Entropy: 0.0706 +[2026-03-20T19:40:04.019762Z] Loop 9530: Loss: 1.28e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0707 +[2026-03-20T19:40:04.874354Z] Loop 9531: Loss: 1.30e-02, Avg Return: 0.861, Regret: 0.0017, Entropy: 0.0718 +[2026-03-20T19:40:05.728347Z] Loop 9532: Loss: 1.34e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0738 +[2026-03-20T19:40:06.581351Z] Loop 9533: Loss: 1.33e-02, Avg Return: 0.861, Regret: 0.0017, Entropy: 0.0725 +[2026-03-20T19:40:07.434749Z] Loop 9534: Loss: 1.28e-02, Avg Return: 0.860, Regret: 0.0017, Entropy: 0.0695 +[2026-03-20T19:40:08.288674Z] Loop 9535: Loss: 1.42e-02, Avg Return: 0.859, Regret: 0.0017, Entropy: 0.0742 +[2026-03-20T19:40:09.142009Z] Loop 9536: Loss: 1.25e-02, Avg Return: 0.859, Regret: 0.0017, Entropy: 0.0693 +[2026-03-20T19:40:09.995725Z] Loop 9537: Loss: 1.23e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0683 +[2026-03-20T19:40:10.850869Z] Loop 9538: Loss: 1.24e-02, Avg Return: 0.861, Regret: 0.0017, Entropy: 0.0689 +[2026-03-20T19:40:11.706823Z] Loop 9539: Loss: 1.24e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0655 +[2026-03-20T19:40:12.601119Z] Loop 9540: Loss: 1.24e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0660 +[2026-03-20T19:40:13.455616Z] Loop 9541: Loss: 1.20e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0679 +[2026-03-20T19:40:14.310181Z] Loop 9542: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0695 +[2026-03-20T19:40:15.165502Z] Loop 9543: Loss: 1.21e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0671 +[2026-03-20T19:40:16.018903Z] Loop 9544: Loss: 1.26e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0681 +[2026-03-20T19:40:16.872750Z] Loop 9545: Loss: 1.23e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0701 +[2026-03-20T19:40:17.726715Z] Loop 9546: Loss: 1.31e-02, Avg Return: 0.864, Regret: 0.0018, Entropy: 0.0692 +[2026-03-20T19:40:18.580381Z] Loop 9547: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0717 +[2026-03-20T19:40:19.435162Z] Loop 9548: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0808 +[2026-03-20T19:40:20.289677Z] Loop 9549: Loss: 1.63e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0826 +[2026-03-20T19:40:21.185230Z] Loop 9550: Loss: 1.52e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0823 +[2026-03-20T19:40:22.039693Z] Loop 9551: Loss: 1.66e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0889 +[2026-03-20T19:40:22.894011Z] Loop 9552: Loss: 1.73e-02, Avg Return: 0.860, Regret: 0.0016, Entropy: 0.0924 +[2026-03-20T19:40:23.748289Z] Loop 9553: Loss: 1.96e-02, Avg Return: 0.858, Regret: 0.0016, Entropy: 0.0971 +[2026-03-20T19:40:24.603054Z] Loop 9554: Loss: 2.09e-02, Avg Return: 0.856, Regret: 0.0016, Entropy: 0.1017 +[2026-03-20T19:40:25.457742Z] Loop 9555: Loss: 2.35e-02, Avg Return: 0.855, Regret: 0.0016, Entropy: 0.1113 +[2026-03-20T19:40:26.310962Z] Loop 9556: Loss: 2.25e-02, Avg Return: 0.856, Regret: 0.0016, Entropy: 0.1106 +[2026-03-20T19:40:27.164394Z] Loop 9557: Loss: 2.22e-02, Avg Return: 0.856, Regret: 0.0016, Entropy: 0.1081 +[2026-03-20T19:40:28.020067Z] Loop 9558: Loss: 2.09e-02, Avg Return: 0.857, Regret: 0.0016, Entropy: 0.1006 +[2026-03-20T19:40:28.875303Z] Loop 9559: Loss: 2.07e-02, Avg Return: 0.859, Regret: 0.0016, Entropy: 0.0995 +[2026-03-20T19:40:29.770460Z] Loop 9560: Loss: 1.92e-02, Avg Return: 0.859, Regret: 0.0039, Entropy: 0.0966 +[2026-03-20T19:40:30.624572Z] Loop 9561: Loss: 1.88e-02, Avg Return: 0.861, Regret: 0.0039, Entropy: 0.0929 +[2026-03-20T19:40:31.479265Z] Loop 9562: Loss: 1.87e-02, Avg Return: 0.860, Regret: 0.0039, Entropy: 0.0966 +[2026-03-20T19:40:32.333047Z] Loop 9563: Loss: 1.97e-02, Avg Return: 0.861, Regret: 0.0039, Entropy: 0.1022 +[2026-03-20T19:40:33.186372Z] Loop 9564: Loss: 2.07e-02, Avg Return: 0.862, Regret: 0.0039, Entropy: 0.1053 +[2026-03-20T19:40:34.039555Z] Loop 9565: Loss: 1.80e-02, Avg Return: 0.861, Regret: 0.0039, Entropy: 0.0951 +[2026-03-20T19:40:34.893941Z] Loop 9566: Loss: 1.85e-02, Avg Return: 0.861, Regret: 0.0039, Entropy: 0.0900 +[2026-03-20T19:40:35.748031Z] Loop 9567: Loss: 1.82e-02, Avg Return: 0.862, Regret: 0.0039, Entropy: 0.0934 +[2026-03-20T19:40:36.601861Z] Loop 9568: Loss: 1.82e-02, Avg Return: 0.862, Regret: 0.0039, Entropy: 0.0943 +[2026-03-20T19:40:37.456321Z] Loop 9569: Loss: 1.98e-02, Avg Return: 0.863, Regret: 0.0039, Entropy: 0.1034 +[2026-03-20T19:40:38.351353Z] Loop 9570: Loss: 2.08e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.1061 +[2026-03-20T19:40:39.204798Z] Loop 9571: Loss: 2.25e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.1102 +[2026-03-20T19:40:40.059258Z] Loop 9572: Loss: 2.45e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.1210 +[2026-03-20T19:40:40.913006Z] Loop 9573: Loss: 2.59e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.1314 +[2026-03-20T19:40:41.766691Z] Loop 9574: Loss: 2.85e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.1413 +[2026-03-20T19:40:42.619855Z] Loop 9575: Loss: 2.89e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.1447 +[2026-03-20T19:40:43.473944Z] Loop 9576: Loss: 2.82e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.1443 +[2026-03-20T19:40:44.327407Z] Loop 9577: Loss: 2.85e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.1423 +[2026-03-20T19:40:45.181572Z] Loop 9578: Loss: 2.92e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.1440 +[2026-03-20T19:40:46.035179Z] Loop 9579: Loss: 3.01e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.1468 +[2026-03-20T19:40:46.929607Z] Loop 9580: Loss: 2.90e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.1434 +[2026-03-20T19:40:47.783004Z] Loop 9581: Loss: 2.81e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.1438 +[2026-03-20T19:40:48.637695Z] Loop 9582: Loss: 2.64e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.1381 +[2026-03-20T19:40:49.490946Z] Loop 9583: Loss: 2.71e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.1381 +[2026-03-20T19:40:50.344541Z] Loop 9584: Loss: 2.79e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.1418 +[2026-03-20T19:40:51.198950Z] Loop 9585: Loss: 2.75e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.1403 +[2026-03-20T19:40:52.052685Z] Loop 9586: Loss: 2.74e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.1424 +[2026-03-20T19:40:52.907295Z] Loop 9587: Loss: 2.80e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.1456 +[2026-03-20T19:40:53.761129Z] Loop 9588: Loss: 2.62e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.1366 +[2026-03-20T19:40:54.615478Z] Loop 9589: Loss: 2.35e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.1279 +[2026-03-20T19:40:55.510834Z] Loop 9590: Loss: 2.47e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.1236 +[2026-03-20T19:40:56.364844Z] Loop 9591: Loss: 2.22e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.1192 +[2026-03-20T19:40:57.217920Z] Loop 9592: Loss: 2.19e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.1108 +[2026-03-20T19:40:58.071250Z] Loop 9593: Loss: 2.18e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.1122 +[2026-03-20T19:40:58.925607Z] Loop 9594: Loss: 2.06e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.1092 +[2026-03-20T19:40:59.779599Z] Loop 9595: Loss: 2.04e-02, Avg Return: 0.859, Regret: 0.0026, Entropy: 0.1092 +[2026-03-20T19:41:00.633204Z] Loop 9596: Loss: 2.11e-02, Avg Return: 0.858, Regret: 0.0026, Entropy: 0.1078 +[2026-03-20T19:41:01.487860Z] Loop 9597: Loss: 2.14e-02, Avg Return: 0.856, Regret: 0.0026, Entropy: 0.1071 +[2026-03-20T19:41:02.341849Z] Loop 9598: Loss: 2.17e-02, Avg Return: 0.854, Regret: 0.0026, Entropy: 0.1125 +[2026-03-20T19:41:03.195963Z] Loop 9599: Loss: 2.22e-02, Avg Return: 0.856, Regret: 0.0026, Entropy: 0.1145 +[2026-03-20T19:41:04.089305Z] Loop 9600: Loss: 2.34e-02, Avg Return: 0.857, Regret: 0.0070, Entropy: 0.1177 +[2026-03-20T19:41:04.942734Z] Loop 9601: Loss: 2.41e-02, Avg Return: 0.858, Regret: 0.0070, Entropy: 0.1184 +[2026-03-20T19:41:05.796730Z] Loop 9602: Loss: 2.46e-02, Avg Return: 0.859, Regret: 0.0070, Entropy: 0.1215 +[2026-03-20T19:41:06.650754Z] Loop 9603: Loss: 2.56e-02, Avg Return: 0.861, Regret: 0.0070, Entropy: 0.1283 +[2026-03-20T19:41:07.504113Z] Loop 9604: Loss: 2.46e-02, Avg Return: 0.862, Regret: 0.0070, Entropy: 0.1190 +[2026-03-20T19:41:08.358093Z] Loop 9605: Loss: 2.04e-02, Avg Return: 0.864, Regret: 0.0070, Entropy: 0.1029 +[2026-03-20T19:41:09.211094Z] Loop 9606: Loss: 1.70e-02, Avg Return: 0.865, Regret: 0.0070, Entropy: 0.0913 +[2026-03-20T19:41:10.065792Z] Loop 9607: Loss: 1.59e-02, Avg Return: 0.864, Regret: 0.0070, Entropy: 0.0817 +[2026-03-20T19:41:10.919845Z] Loop 9608: Loss: 1.70e-02, Avg Return: 0.862, Regret: 0.0070, Entropy: 0.0870 +[2026-03-20T19:41:11.774266Z] Loop 9609: Loss: 1.82e-02, Avg Return: 0.863, Regret: 0.0070, Entropy: 0.0905 +[2026-03-20T19:41:12.667182Z] Loop 9610: Loss: 1.84e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0902 +[2026-03-20T19:41:13.520522Z] Loop 9611: Loss: 1.73e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0857 +[2026-03-20T19:41:14.375003Z] Loop 9612: Loss: 1.78e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0860 +[2026-03-20T19:41:15.230129Z] Loop 9613: Loss: 1.70e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0847 +[2026-03-20T19:41:16.084039Z] Loop 9614: Loss: 1.80e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0902 +[2026-03-20T19:41:16.938343Z] Loop 9615: Loss: 1.67e-02, Avg Return: 0.861, Regret: 0.0003, Entropy: 0.0887 +[2026-03-20T19:41:17.792326Z] Loop 9616: Loss: 1.57e-02, Avg Return: 0.861, Regret: 0.0003, Entropy: 0.0831 +[2026-03-20T19:41:18.647634Z] Loop 9617: Loss: 1.82e-02, Avg Return: 0.860, Regret: 0.0003, Entropy: 0.0897 +[2026-03-20T19:41:19.502678Z] Loop 9618: Loss: 1.79e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0887 +[2026-03-20T19:41:20.355622Z] Loop 9619: Loss: 1.63e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0862 +[2026-03-20T19:41:21.247716Z] Loop 9620: Loss: 1.69e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0855 +[2026-03-20T19:41:22.102542Z] Loop 9621: Loss: 1.64e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0847 +[2026-03-20T19:41:22.957723Z] Loop 9622: Loss: 1.64e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0827 +[2026-03-20T19:41:23.811264Z] Loop 9623: Loss: 1.75e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0808 +[2026-03-20T19:41:24.665371Z] Loop 9624: Loss: 1.70e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0858 +[2026-03-20T19:41:25.519598Z] Loop 9625: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0895 +[2026-03-20T19:41:26.372934Z] Loop 9626: Loss: 1.78e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0856 +[2026-03-20T19:41:27.226932Z] Loop 9627: Loss: 1.83e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0907 +[2026-03-20T19:41:28.080532Z] Loop 9628: Loss: 1.70e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0865 +[2026-03-20T19:41:28.934325Z] Loop 9629: Loss: 1.64e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0853 +[2026-03-20T19:41:29.827767Z] Loop 9630: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0846 +[2026-03-20T19:41:30.681338Z] Loop 9631: Loss: 1.63e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0827 +[2026-03-20T19:41:31.535688Z] Loop 9632: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0811 +[2026-03-20T19:41:32.389018Z] Loop 9633: Loss: 1.66e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0838 +[2026-03-20T19:41:33.242696Z] Loop 9634: Loss: 1.64e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0797 +[2026-03-20T19:41:34.096611Z] Loop 9635: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0838 +[2026-03-20T19:41:34.951042Z] Loop 9636: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0789 +[2026-03-20T19:41:35.805244Z] Loop 9637: Loss: 1.62e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0806 +[2026-03-20T19:41:36.658328Z] Loop 9638: Loss: 1.60e-02, Avg Return: 0.865, Regret: 0.0007, Entropy: 0.0803 +[2026-03-20T19:41:37.512487Z] Loop 9639: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0801 +[2026-03-20T19:41:38.407413Z] Loop 9640: Loss: 1.57e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0806 +[2026-03-20T19:41:39.261480Z] Loop 9641: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0827 +[2026-03-20T19:41:40.115057Z] Loop 9642: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0807 +[2026-03-20T19:41:40.970155Z] Loop 9643: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0842 +[2026-03-20T19:41:41.825428Z] Loop 9644: Loss: 1.73e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0822 +[2026-03-20T19:41:42.679420Z] Loop 9645: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0874 +[2026-03-20T19:41:43.533582Z] Loop 9646: Loss: 1.80e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0878 +[2026-03-20T19:41:44.388207Z] Loop 9647: Loss: 1.75e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0864 +[2026-03-20T19:41:45.243778Z] Loop 9648: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0840 +[2026-03-20T19:41:46.099816Z] Loop 9649: Loss: 1.74e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0850 +[2026-03-20T19:41:46.993815Z] Loop 9650: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0803 +[2026-03-20T19:41:47.847291Z] Loop 9651: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0794 +[2026-03-20T19:41:48.701553Z] Loop 9652: Loss: 1.59e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0790 +[2026-03-20T19:41:49.556173Z] Loop 9653: Loss: 1.64e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0825 +[2026-03-20T19:41:50.410062Z] Loop 9654: Loss: 1.85e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0894 +[2026-03-20T19:41:51.263517Z] Loop 9655: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0839 +[2026-03-20T19:41:52.119367Z] Loop 9656: Loss: 1.64e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0822 +[2026-03-20T19:41:52.974633Z] Loop 9657: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0845 +[2026-03-20T19:41:53.829599Z] Loop 9658: Loss: 1.76e-02, Avg Return: 0.860, Regret: 0.0003, Entropy: 0.0889 +[2026-03-20T19:41:54.683806Z] Loop 9659: Loss: 1.91e-02, Avg Return: 0.860, Regret: 0.0003, Entropy: 0.0944 +[2026-03-20T19:41:55.580711Z] Loop 9660: Loss: 1.87e-02, Avg Return: 0.859, Regret: 0.0044, Entropy: 0.0937 +[2026-03-20T19:41:56.434357Z] Loop 9661: Loss: 2.01e-02, Avg Return: 0.859, Regret: 0.0044, Entropy: 0.0968 +[2026-03-20T19:41:57.289051Z] Loop 9662: Loss: 1.99e-02, Avg Return: 0.858, Regret: 0.0044, Entropy: 0.0958 +[2026-03-20T19:41:58.143455Z] Loop 9663: Loss: 1.89e-02, Avg Return: 0.857, Regret: 0.0044, Entropy: 0.0952 +[2026-03-20T19:41:58.998527Z] Loop 9664: Loss: 2.02e-02, Avg Return: 0.858, Regret: 0.0044, Entropy: 0.0947 +[2026-03-20T19:41:59.852586Z] Loop 9665: Loss: 1.89e-02, Avg Return: 0.860, Regret: 0.0044, Entropy: 0.0924 +[2026-03-20T19:42:00.707945Z] Loop 9666: Loss: 1.93e-02, Avg Return: 0.862, Regret: 0.0044, Entropy: 0.0922 +[2026-03-20T19:42:01.562252Z] Loop 9667: Loss: 1.80e-02, Avg Return: 0.861, Regret: 0.0044, Entropy: 0.0858 +[2026-03-20T19:42:02.418055Z] Loop 9668: Loss: 1.76e-02, Avg Return: 0.863, Regret: 0.0044, Entropy: 0.0882 +[2026-03-20T19:42:03.271989Z] Loop 9669: Loss: 1.89e-02, Avg Return: 0.862, Regret: 0.0044, Entropy: 0.0945 +[2026-03-20T19:42:04.165063Z] Loop 9670: Loss: 1.71e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0879 +[2026-03-20T19:42:05.019456Z] Loop 9671: Loss: 1.65e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0834 +[2026-03-20T19:42:05.874630Z] Loop 9672: Loss: 1.63e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0854 +[2026-03-20T19:42:06.729377Z] Loop 9673: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0857 +[2026-03-20T19:42:07.583939Z] Loop 9674: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0844 +[2026-03-20T19:42:08.439402Z] Loop 9675: Loss: 1.85e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0903 +[2026-03-20T19:42:09.295257Z] Loop 9676: Loss: 1.85e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0947 +[2026-03-20T19:42:10.150337Z] Loop 9677: Loss: 1.87e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0947 +[2026-03-20T19:42:11.003525Z] Loop 9678: Loss: 1.94e-02, Avg Return: 0.861, Regret: 0.0002, Entropy: 0.0964 +[2026-03-20T19:42:11.856746Z] Loop 9679: Loss: 1.86e-02, Avg Return: 0.858, Regret: 0.0002, Entropy: 0.0952 +[2026-03-20T19:42:12.751853Z] Loop 9680: Loss: 1.97e-02, Avg Return: 0.857, Regret: 0.0064, Entropy: 0.0977 +[2026-03-20T19:42:13.606678Z] Loop 9681: Loss: 1.86e-02, Avg Return: 0.859, Regret: 0.0064, Entropy: 0.0940 +[2026-03-20T19:42:14.461375Z] Loop 9682: Loss: 1.77e-02, Avg Return: 0.861, Regret: 0.0064, Entropy: 0.0903 +[2026-03-20T19:42:15.315182Z] Loop 9683: Loss: 1.67e-02, Avg Return: 0.861, Regret: 0.0064, Entropy: 0.0855 +[2026-03-20T19:42:16.169760Z] Loop 9684: Loss: 1.68e-02, Avg Return: 0.862, Regret: 0.0064, Entropy: 0.0850 +[2026-03-20T19:42:17.025372Z] Loop 9685: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0064, Entropy: 0.0831 +[2026-03-20T19:42:17.880427Z] Loop 9686: Loss: 1.73e-02, Avg Return: 0.862, Regret: 0.0064, Entropy: 0.0856 +[2026-03-20T19:42:18.733856Z] Loop 9687: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0064, Entropy: 0.0833 +[2026-03-20T19:42:19.587879Z] Loop 9688: Loss: 1.84e-02, Avg Return: 0.864, Regret: 0.0064, Entropy: 0.0866 +[2026-03-20T19:42:20.441894Z] Loop 9689: Loss: 1.75e-02, Avg Return: 0.864, Regret: 0.0064, Entropy: 0.0883 +[2026-03-20T19:42:21.338243Z] Loop 9690: Loss: 1.73e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0858 +[2026-03-20T19:42:22.193241Z] Loop 9691: Loss: 1.65e-02, Avg Return: 0.861, Regret: 0.0001, Entropy: 0.0844 +[2026-03-20T19:42:23.048123Z] Loop 9692: Loss: 1.76e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0842 +[2026-03-20T19:42:23.902108Z] Loop 9693: Loss: 1.65e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0831 +[2026-03-20T19:42:24.756882Z] Loop 9694: Loss: 1.75e-02, Avg Return: 0.865, Regret: 0.0001, Entropy: 0.0890 +[2026-03-20T19:42:25.611280Z] Loop 9695: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0876 +[2026-03-20T19:42:26.466068Z] Loop 9696: Loss: 1.82e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0897 +[2026-03-20T19:42:27.320043Z] Loop 9697: Loss: 1.81e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0924 +[2026-03-20T19:42:28.173854Z] Loop 9698: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0864 +[2026-03-20T19:42:29.028626Z] Loop 9699: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0930 +[2026-03-20T19:42:29.922988Z] Loop 9700: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0877 +[2026-03-20T19:42:30.775387Z] Loop 9701: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0909 +[2026-03-20T19:42:31.628989Z] Loop 9702: Loss: 1.76e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0886 +[2026-03-20T19:42:32.483203Z] Loop 9703: Loss: 1.87e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0925 +[2026-03-20T19:42:33.337620Z] Loop 9704: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0917 +[2026-03-20T19:42:34.190940Z] Loop 9705: Loss: 1.93e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0925 +[2026-03-20T19:42:35.044547Z] Loop 9706: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0937 +[2026-03-20T19:42:35.898435Z] Loop 9707: Loss: 1.91e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0929 +[2026-03-20T19:42:36.752885Z] Loop 9708: Loss: 1.89e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0949 +[2026-03-20T19:42:37.606585Z] Loop 9709: Loss: 1.82e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0951 +[2026-03-20T19:42:38.499243Z] Loop 9710: Loss: 1.81e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0904 +[2026-03-20T19:42:39.352314Z] Loop 9711: Loss: 1.76e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0892 +[2026-03-20T19:42:40.207136Z] Loop 9712: Loss: 1.79e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0905 +[2026-03-20T19:42:41.061717Z] Loop 9713: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0849 +[2026-03-20T19:42:41.915735Z] Loop 9714: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0847 +[2026-03-20T19:42:42.769407Z] Loop 9715: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0880 +[2026-03-20T19:42:43.624282Z] Loop 9716: Loss: 1.81e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0865 +[2026-03-20T19:42:44.478600Z] Loop 9717: Loss: 1.81e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0924 +[2026-03-20T19:42:45.332400Z] Loop 9718: Loss: 1.81e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0903 +[2026-03-20T19:42:46.185056Z] Loop 9719: Loss: 1.86e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0888 +[2026-03-20T19:42:47.079625Z] Loop 9720: Loss: 1.83e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0907 +[2026-03-20T19:42:47.935384Z] Loop 9721: Loss: 1.90e-02, Avg Return: 0.865, Regret: 0.0003, Entropy: 0.0932 +[2026-03-20T19:42:48.791241Z] Loop 9722: Loss: 1.91e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0937 +[2026-03-20T19:42:49.645610Z] Loop 9723: Loss: 1.86e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0935 +[2026-03-20T19:42:50.501300Z] Loop 9724: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0892 +[2026-03-20T19:42:51.355960Z] Loop 9725: Loss: 1.54e-02, Avg Return: 0.861, Regret: 0.0003, Entropy: 0.0818 +[2026-03-20T19:42:52.211397Z] Loop 9726: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0822 +[2026-03-20T19:42:53.067130Z] Loop 9727: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0801 +[2026-03-20T19:42:53.921756Z] Loop 9728: Loss: 1.39e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0709 +[2026-03-20T19:42:54.775193Z] Loop 9729: Loss: 1.46e-02, Avg Return: 0.861, Regret: 0.0003, Entropy: 0.0796 +[2026-03-20T19:42:55.670291Z] Loop 9730: Loss: 1.45e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0766 +[2026-03-20T19:42:56.524402Z] Loop 9731: Loss: 1.43e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.0770 +[2026-03-20T19:42:57.379046Z] Loop 9732: Loss: 1.41e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.0767 +[2026-03-20T19:42:58.232596Z] Loop 9733: Loss: 1.58e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.0797 +[2026-03-20T19:42:59.085905Z] Loop 9734: Loss: 1.50e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.0812 +[2026-03-20T19:42:59.939601Z] Loop 9735: Loss: 1.50e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.0833 +[2026-03-20T19:43:00.793997Z] Loop 9736: Loss: 1.55e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.0815 +[2026-03-20T19:43:01.647575Z] Loop 9737: Loss: 1.62e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.0826 +[2026-03-20T19:43:02.501201Z] Loop 9738: Loss: 1.61e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.0849 +[2026-03-20T19:43:03.355107Z] Loop 9739: Loss: 1.67e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.0873 +[2026-03-20T19:43:04.249169Z] Loop 9740: Loss: 1.65e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0834 +[2026-03-20T19:43:05.103477Z] Loop 9741: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0831 +[2026-03-20T19:43:05.956564Z] Loop 9742: Loss: 1.72e-02, Avg Return: 0.864, Regret: 0.0019, Entropy: 0.0874 +[2026-03-20T19:43:06.810371Z] Loop 9743: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0019, Entropy: 0.0855 +[2026-03-20T19:43:07.665061Z] Loop 9744: Loss: 1.71e-02, Avg Return: 0.864, Regret: 0.0019, Entropy: 0.0886 +[2026-03-20T19:43:08.520926Z] Loop 9745: Loss: 1.99e-02, Avg Return: 0.863, Regret: 0.0019, Entropy: 0.0954 +[2026-03-20T19:43:09.374885Z] Loop 9746: Loss: 2.06e-02, Avg Return: 0.864, Regret: 0.0019, Entropy: 0.0994 +[2026-03-20T19:43:10.227826Z] Loop 9747: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0949 +[2026-03-20T19:43:11.082759Z] Loop 9748: Loss: 1.94e-02, Avg Return: 0.863, Regret: 0.0019, Entropy: 0.0989 +[2026-03-20T19:43:11.937127Z] Loop 9749: Loss: 1.97e-02, Avg Return: 0.863, Regret: 0.0019, Entropy: 0.0931 +[2026-03-20T19:43:12.831661Z] Loop 9750: Loss: 1.98e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0974 +[2026-03-20T19:43:13.685012Z] Loop 9751: Loss: 1.84e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0929 +[2026-03-20T19:43:14.539197Z] Loop 9752: Loss: 1.81e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0908 +[2026-03-20T19:43:15.395192Z] Loop 9753: Loss: 1.84e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0906 +[2026-03-20T19:43:16.248582Z] Loop 9754: Loss: 1.92e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0983 +[2026-03-20T19:43:17.102260Z] Loop 9755: Loss: 1.85e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0954 +[2026-03-20T19:43:17.956545Z] Loop 9756: Loss: 2.00e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.1022 +[2026-03-20T19:43:18.811465Z] Loop 9757: Loss: 1.99e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.1042 +[2026-03-20T19:43:19.665840Z] Loop 9758: Loss: 1.92e-02, Avg Return: 0.861, Regret: 0.0002, Entropy: 0.1023 +[2026-03-20T19:43:20.519625Z] Loop 9759: Loss: 2.08e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.1042 +[2026-03-20T19:43:21.413638Z] Loop 9760: Loss: 2.06e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.1074 +[2026-03-20T19:43:22.267170Z] Loop 9761: Loss: 2.13e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.1048 +[2026-03-20T19:43:23.121321Z] Loop 9762: Loss: 1.93e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.1048 +[2026-03-20T19:43:23.975492Z] Loop 9763: Loss: 2.03e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.1063 +[2026-03-20T19:43:24.829092Z] Loop 9764: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0985 +[2026-03-20T19:43:25.683328Z] Loop 9765: Loss: 1.93e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.1010 +[2026-03-20T19:43:26.537513Z] Loop 9766: Loss: 1.94e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.1012 +[2026-03-20T19:43:27.393128Z] Loop 9767: Loss: 1.99e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.1004 +[2026-03-20T19:43:28.247365Z] Loop 9768: Loss: 1.96e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.1036 +[2026-03-20T19:43:29.101235Z] Loop 9769: Loss: 1.97e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.1022 +[2026-03-20T19:43:29.996342Z] Loop 9770: Loss: 1.96e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.1055 +[2026-03-20T19:43:30.850773Z] Loop 9771: Loss: 2.10e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.1082 +[2026-03-20T19:43:31.704408Z] Loop 9772: Loss: 2.13e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.1050 +[2026-03-20T19:43:32.558181Z] Loop 9773: Loss: 2.12e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.1065 +[2026-03-20T19:43:33.412044Z] Loop 9774: Loss: 2.08e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.1092 +[2026-03-20T19:43:34.267095Z] Loop 9775: Loss: 2.19e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.1116 +[2026-03-20T19:43:35.121555Z] Loop 9776: Loss: 2.14e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.1124 +[2026-03-20T19:43:35.976254Z] Loop 9777: Loss: 2.23e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.1178 +[2026-03-20T19:43:36.829770Z] Loop 9778: Loss: 2.26e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.1186 +[2026-03-20T19:43:37.684322Z] Loop 9779: Loss: 2.31e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.1189 +[2026-03-20T19:43:38.579056Z] Loop 9780: Loss: 2.49e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.1262 +[2026-03-20T19:43:39.433294Z] Loop 9781: Loss: 2.62e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.1369 +[2026-03-20T19:43:40.287284Z] Loop 9782: Loss: 2.68e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.1409 +[2026-03-20T19:43:41.142059Z] Loop 9783: Loss: 2.88e-02, Avg Return: 0.860, Regret: 0.0014, Entropy: 0.1464 +[2026-03-20T19:43:41.997377Z] Loop 9784: Loss: 2.98e-02, Avg Return: 0.860, Regret: 0.0014, Entropy: 0.1518 +[2026-03-20T19:43:42.851056Z] Loop 9785: Loss: 3.00e-02, Avg Return: 0.859, Regret: 0.0014, Entropy: 0.1520 +[2026-03-20T19:43:43.704214Z] Loop 9786: Loss: 3.06e-02, Avg Return: 0.858, Regret: 0.0014, Entropy: 0.1541 +[2026-03-20T19:43:44.558222Z] Loop 9787: Loss: 3.01e-02, Avg Return: 0.859, Regret: 0.0014, Entropy: 0.1547 +[2026-03-20T19:43:45.411705Z] Loop 9788: Loss: 2.74e-02, Avg Return: 0.860, Regret: 0.0014, Entropy: 0.1428 +[2026-03-20T19:43:46.266972Z] Loop 9789: Loss: 2.72e-02, Avg Return: 0.860, Regret: 0.0014, Entropy: 0.1421 +[2026-03-20T19:43:47.162717Z] Loop 9790: Loss: 2.61e-02, Avg Return: 0.861, Regret: 0.0029, Entropy: 0.1330 +[2026-03-20T19:43:48.017219Z] Loop 9791: Loss: 2.59e-02, Avg Return: 0.860, Regret: 0.0029, Entropy: 0.1325 +[2026-03-20T19:43:48.870640Z] Loop 9792: Loss: 2.55e-02, Avg Return: 0.859, Regret: 0.0029, Entropy: 0.1320 +[2026-03-20T19:43:49.724271Z] Loop 9793: Loss: 2.49e-02, Avg Return: 0.862, Regret: 0.0029, Entropy: 0.1316 +[2026-03-20T19:43:50.577982Z] Loop 9794: Loss: 2.46e-02, Avg Return: 0.863, Regret: 0.0029, Entropy: 0.1272 +[2026-03-20T19:43:51.432419Z] Loop 9795: Loss: 2.67e-02, Avg Return: 0.862, Regret: 0.0029, Entropy: 0.1309 +[2026-03-20T19:43:52.285291Z] Loop 9796: Loss: 2.50e-02, Avg Return: 0.864, Regret: 0.0029, Entropy: 0.1197 +[2026-03-20T19:43:53.138289Z] Loop 9797: Loss: 2.39e-02, Avg Return: 0.863, Regret: 0.0029, Entropy: 0.1188 +[2026-03-20T19:43:53.992285Z] Loop 9798: Loss: 2.40e-02, Avg Return: 0.864, Regret: 0.0029, Entropy: 0.1193 +[2026-03-20T19:43:54.847955Z] Loop 9799: Loss: 2.29e-02, Avg Return: 0.864, Regret: 0.0029, Entropy: 0.1171 +[2026-03-20T19:43:55.742169Z] Loop 9800: Loss: 2.30e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.1149 +[2026-03-20T19:43:56.596215Z] Loop 9801: Loss: 2.12e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.1146 +[2026-03-20T19:43:57.450810Z] Loop 9802: Loss: 2.23e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.1159 +[2026-03-20T19:43:58.305636Z] Loop 9803: Loss: 2.14e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.1117 +[2026-03-20T19:43:59.161237Z] Loop 9804: Loss: 2.13e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.1103 +[2026-03-20T19:44:00.014126Z] Loop 9805: Loss: 2.15e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.1122 +[2026-03-20T19:44:00.866637Z] Loop 9806: Loss: 1.96e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.1003 +[2026-03-20T19:44:01.720830Z] Loop 9807: Loss: 2.13e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.1061 +[2026-03-20T19:44:02.574909Z] Loop 9808: Loss: 1.99e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.1046 +[2026-03-20T19:44:03.429245Z] Loop 9809: Loss: 2.01e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.1039 +[2026-03-20T19:44:04.322598Z] Loop 9810: Loss: 2.03e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.1015 +[2026-03-20T19:44:05.177416Z] Loop 9811: Loss: 2.04e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.1040 +[2026-03-20T19:44:06.032174Z] Loop 9812: Loss: 2.11e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.1040 +[2026-03-20T19:44:06.887244Z] Loop 9813: Loss: 2.09e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.1063 +[2026-03-20T19:44:07.741069Z] Loop 9814: Loss: 2.17e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.1076 +[2026-03-20T19:44:08.595177Z] Loop 9815: Loss: 2.02e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.1038 +[2026-03-20T19:44:09.451196Z] Loop 9816: Loss: 1.99e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.1036 +[2026-03-20T19:44:10.307084Z] Loop 9817: Loss: 1.95e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0991 +[2026-03-20T19:44:11.162544Z] Loop 9818: Loss: 2.09e-02, Avg Return: 0.864, Regret: 0.0018, Entropy: 0.1054 +[2026-03-20T19:44:12.017689Z] Loop 9819: Loss: 2.14e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.1113 +[2026-03-20T19:44:12.911749Z] Loop 9820: Loss: 2.48e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.1188 +[2026-03-20T19:44:13.766581Z] Loop 9821: Loss: 2.38e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.1157 +[2026-03-20T19:44:14.621804Z] Loop 9822: Loss: 2.21e-02, Avg Return: 0.865, Regret: 0.0006, Entropy: 0.1122 +[2026-03-20T19:44:15.476428Z] Loop 9823: Loss: 2.19e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.1126 +[2026-03-20T19:44:16.330076Z] Loop 9824: Loss: 2.23e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.1160 +[2026-03-20T19:44:17.184338Z] Loop 9825: Loss: 2.05e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.1008 +[2026-03-20T19:44:18.039434Z] Loop 9826: Loss: 1.82e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0955 +[2026-03-20T19:44:18.893563Z] Loop 9827: Loss: 1.63e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0878 +[2026-03-20T19:44:19.747351Z] Loop 9828: Loss: 1.78e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0903 +[2026-03-20T19:44:20.601422Z] Loop 9829: Loss: 1.77e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0894 +[2026-03-20T19:44:21.495673Z] Loop 9830: Loss: 2.03e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0968 +[2026-03-20T19:44:22.351459Z] Loop 9831: Loss: 1.84e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0910 +[2026-03-20T19:44:23.206221Z] Loop 9832: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0866 +[2026-03-20T19:44:24.061454Z] Loop 9833: Loss: 1.81e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0951 +[2026-03-20T19:44:24.918189Z] Loop 9834: Loss: 1.78e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0884 +[2026-03-20T19:44:25.773580Z] Loop 9835: Loss: 1.85e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0941 +[2026-03-20T19:44:26.628135Z] Loop 9836: Loss: 1.81e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0909 +[2026-03-20T19:44:27.481646Z] Loop 9837: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0887 +[2026-03-20T19:44:28.336919Z] Loop 9838: Loss: 1.89e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0955 +[2026-03-20T19:44:29.191403Z] Loop 9839: Loss: 1.82e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0859 +[2026-03-20T19:44:30.083862Z] Loop 9840: Loss: 1.83e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0899 +[2026-03-20T19:44:30.938087Z] Loop 9841: Loss: 1.81e-02, Avg Return: 0.861, Regret: 0.0003, Entropy: 0.0922 +[2026-03-20T19:44:31.793965Z] Loop 9842: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0894 +[2026-03-20T19:44:32.649385Z] Loop 9843: Loss: 1.91e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0928 +[2026-03-20T19:44:33.503090Z] Loop 9844: Loss: 1.86e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0886 +[2026-03-20T19:44:34.357892Z] Loop 9845: Loss: 1.77e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0896 +[2026-03-20T19:44:35.212260Z] Loop 9846: Loss: 1.65e-02, Avg Return: 0.865, Regret: 0.0003, Entropy: 0.0880 +[2026-03-20T19:44:36.066482Z] Loop 9847: Loss: 1.76e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0869 +[2026-03-20T19:44:36.921441Z] Loop 9848: Loss: 1.77e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0862 +[2026-03-20T19:44:37.775924Z] Loop 9849: Loss: 1.73e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0841 +[2026-03-20T19:44:38.672953Z] Loop 9850: Loss: 1.66e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0820 +[2026-03-20T19:44:39.528260Z] Loop 9851: Loss: 1.78e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0868 +[2026-03-20T19:44:40.382276Z] Loop 9852: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0838 +[2026-03-20T19:44:41.236788Z] Loop 9853: Loss: 1.73e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0837 +[2026-03-20T19:44:42.091758Z] Loop 9854: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0858 +[2026-03-20T19:44:42.945381Z] Loop 9855: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0870 +[2026-03-20T19:44:43.798648Z] Loop 9856: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0820 +[2026-03-20T19:44:44.652226Z] Loop 9857: Loss: 1.56e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0843 +[2026-03-20T19:44:45.506825Z] Loop 9858: Loss: 1.67e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0835 +[2026-03-20T19:44:46.360640Z] Loop 9859: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0858 +[2026-03-20T19:44:47.253408Z] Loop 9860: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0818 +[2026-03-20T19:44:48.106493Z] Loop 9861: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0841 +[2026-03-20T19:44:48.960792Z] Loop 9862: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0857 +[2026-03-20T19:44:49.814789Z] Loop 9863: Loss: 1.72e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0857 +[2026-03-20T19:44:50.667957Z] Loop 9864: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0892 +[2026-03-20T19:44:51.521439Z] Loop 9865: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0870 +[2026-03-20T19:44:52.375757Z] Loop 9866: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0904 +[2026-03-20T19:44:53.228685Z] Loop 9867: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0871 +[2026-03-20T19:44:54.082508Z] Loop 9868: Loss: 1.76e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0884 +[2026-03-20T19:44:54.935090Z] Loop 9869: Loss: 1.83e-02, Avg Return: 0.865, Regret: 0.0008, Entropy: 0.0925 +[2026-03-20T19:44:55.828204Z] Loop 9870: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0871 +[2026-03-20T19:44:56.682181Z] Loop 9871: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0906 +[2026-03-20T19:44:57.536271Z] Loop 9872: Loss: 1.76e-02, Avg Return: 0.865, Regret: 0.0003, Entropy: 0.0878 +[2026-03-20T19:44:58.390458Z] Loop 9873: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0873 +[2026-03-20T19:44:59.244959Z] Loop 9874: Loss: 1.83e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0920 +[2026-03-20T19:45:00.099074Z] Loop 9875: Loss: 1.76e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0865 +[2026-03-20T19:45:00.953263Z] Loop 9876: Loss: 1.81e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0903 +[2026-03-20T19:45:01.807975Z] Loop 9877: Loss: 1.82e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0912 +[2026-03-20T19:45:02.663224Z] Loop 9878: Loss: 1.72e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0869 +[2026-03-20T19:45:03.518239Z] Loop 9879: Loss: 1.84e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0926 +[2026-03-20T19:45:04.413357Z] Loop 9880: Loss: 1.92e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0948 +[2026-03-20T19:45:05.268729Z] Loop 9881: Loss: 1.87e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0925 +[2026-03-20T19:45:06.122572Z] Loop 9882: Loss: 1.83e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0925 +[2026-03-20T19:45:06.975687Z] Loop 9883: Loss: 1.82e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0913 +[2026-03-20T19:45:07.829497Z] Loop 9884: Loss: 1.94e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0947 +[2026-03-20T19:45:08.684492Z] Loop 9885: Loss: 1.80e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0929 +[2026-03-20T19:45:09.538398Z] Loop 9886: Loss: 1.99e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0971 +[2026-03-20T19:45:10.392709Z] Loop 9887: Loss: 1.84e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0929 +[2026-03-20T19:45:11.247005Z] Loop 9888: Loss: 1.97e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0962 +[2026-03-20T19:45:12.102539Z] Loop 9889: Loss: 1.89e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0946 +[2026-03-20T19:45:12.998356Z] Loop 9890: Loss: 1.82e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0926 +[2026-03-20T19:45:13.853413Z] Loop 9891: Loss: 1.84e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0942 +[2026-03-20T19:45:14.707697Z] Loop 9892: Loss: 1.89e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0935 +[2026-03-20T19:45:15.562660Z] Loop 9893: Loss: 1.86e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0941 +[2026-03-20T19:45:16.417533Z] Loop 9894: Loss: 1.84e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0952 +[2026-03-20T19:45:17.271909Z] Loop 9895: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0916 +[2026-03-20T19:45:18.125517Z] Loop 9896: Loss: 1.77e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0900 +[2026-03-20T19:45:18.979863Z] Loop 9897: Loss: 1.73e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0904 +[2026-03-20T19:45:19.834812Z] Loop 9898: Loss: 1.73e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0875 +[2026-03-20T19:45:20.688733Z] Loop 9899: Loss: 1.79e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0883 +[2026-03-20T19:45:21.582271Z] Loop 9900: Loss: 1.92e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0915 +[2026-03-20T19:45:22.436273Z] Loop 9901: Loss: 1.77e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0914 +[2026-03-20T19:45:23.290591Z] Loop 9902: Loss: 1.90e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0937 +[2026-03-20T19:45:24.144726Z] Loop 9903: Loss: 1.87e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0895 +[2026-03-20T19:45:24.999524Z] Loop 9904: Loss: 1.88e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0957 +[2026-03-20T19:45:25.852942Z] Loop 9905: Loss: 1.95e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0964 +[2026-03-20T19:45:26.706288Z] Loop 9906: Loss: 1.83e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0940 +[2026-03-20T19:45:27.560767Z] Loop 9907: Loss: 1.84e-02, Avg Return: 0.860, Regret: 0.0010, Entropy: 0.0902 +[2026-03-20T19:45:28.415628Z] Loop 9908: Loss: 1.74e-02, Avg Return: 0.860, Regret: 0.0010, Entropy: 0.0913 +[2026-03-20T19:45:29.269505Z] Loop 9909: Loss: 1.62e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0900 +[2026-03-20T19:45:30.163631Z] Loop 9910: Loss: 1.83e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.0958 +[2026-03-20T19:45:31.019375Z] Loop 9911: Loss: 1.71e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.0896 +[2026-03-20T19:45:31.873950Z] Loop 9912: Loss: 1.80e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.0898 +[2026-03-20T19:45:32.728141Z] Loop 9913: Loss: 1.69e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.0915 +[2026-03-20T19:45:33.581403Z] Loop 9914: Loss: 1.87e-02, Avg Return: 0.861, Regret: 0.0023, Entropy: 0.0908 +[2026-03-20T19:45:34.434700Z] Loop 9915: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.0906 +[2026-03-20T19:45:35.289108Z] Loop 9916: Loss: 1.76e-02, Avg Return: 0.864, Regret: 0.0023, Entropy: 0.0883 +[2026-03-20T19:45:36.143460Z] Loop 9917: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0023, Entropy: 0.0851 +[2026-03-20T19:45:36.997667Z] Loop 9918: Loss: 1.73e-02, Avg Return: 0.864, Regret: 0.0023, Entropy: 0.0856 +[2026-03-20T19:45:37.852333Z] Loop 9919: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.0837 +[2026-03-20T19:45:38.748275Z] Loop 9920: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0851 +[2026-03-20T19:45:39.603386Z] Loop 9921: Loss: 1.62e-02, Avg Return: 0.865, Regret: 0.0004, Entropy: 0.0847 +[2026-03-20T19:45:40.459594Z] Loop 9922: Loss: 1.56e-02, Avg Return: 0.865, Regret: 0.0004, Entropy: 0.0842 +[2026-03-20T19:45:41.314025Z] Loop 9923: Loss: 1.77e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0860 +[2026-03-20T19:45:42.168924Z] Loop 9924: Loss: 1.63e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0847 +[2026-03-20T19:45:43.025045Z] Loop 9925: Loss: 1.56e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0831 +[2026-03-20T19:45:43.880287Z] Loop 9926: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0860 +[2026-03-20T19:45:44.736394Z] Loop 9927: Loss: 1.72e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0838 +[2026-03-20T19:45:45.591423Z] Loop 9928: Loss: 1.72e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0867 +[2026-03-20T19:45:46.447096Z] Loop 9929: Loss: 1.70e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0843 +[2026-03-20T19:45:47.342043Z] Loop 9930: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0817 +[2026-03-20T19:45:48.196721Z] Loop 9931: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0799 +[2026-03-20T19:45:49.051374Z] Loop 9932: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0779 +[2026-03-20T19:45:49.906848Z] Loop 9933: Loss: 1.61e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0791 +[2026-03-20T19:45:50.762587Z] Loop 9934: Loss: 1.68e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0830 +[2026-03-20T19:45:51.617986Z] Loop 9935: Loss: 1.88e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0915 +[2026-03-20T19:45:52.472970Z] Loop 9936: Loss: 1.82e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0898 +[2026-03-20T19:45:53.328951Z] Loop 9937: Loss: 1.85e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0874 +[2026-03-20T19:45:54.183601Z] Loop 9938: Loss: 1.85e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0870 +[2026-03-20T19:45:55.038545Z] Loop 9939: Loss: 1.68e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0831 +[2026-03-20T19:45:55.933608Z] Loop 9940: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0818 +[2026-03-20T19:45:56.788568Z] Loop 9941: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0798 +[2026-03-20T19:45:57.642721Z] Loop 9942: Loss: 1.54e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0791 +[2026-03-20T19:45:58.498370Z] Loop 9943: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0786 +[2026-03-20T19:45:59.353403Z] Loop 9944: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0811 +[2026-03-20T19:46:00.208884Z] Loop 9945: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0869 +[2026-03-20T19:46:01.062737Z] Loop 9946: Loss: 1.68e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0855 +[2026-03-20T19:46:01.916200Z] Loop 9947: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0850 +[2026-03-20T19:46:02.770319Z] Loop 9948: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0837 +[2026-03-20T19:46:03.626596Z] Loop 9949: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0878 +[2026-03-20T19:46:04.519880Z] Loop 9950: Loss: 1.62e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0838 +[2026-03-20T19:46:05.374606Z] Loop 9951: Loss: 1.53e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0801 +[2026-03-20T19:46:06.230031Z] Loop 9952: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0797 +[2026-03-20T19:46:07.085460Z] Loop 9953: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0805 +[2026-03-20T19:46:07.939398Z] Loop 9954: Loss: 1.52e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0778 +[2026-03-20T19:46:08.793588Z] Loop 9955: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0820 +[2026-03-20T19:46:09.648265Z] Loop 9956: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0825 +[2026-03-20T19:46:10.504978Z] Loop 9957: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0842 +[2026-03-20T19:46:11.360023Z] Loop 9958: Loss: 1.56e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0821 +[2026-03-20T19:46:12.214599Z] Loop 9959: Loss: 1.77e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0866 +[2026-03-20T19:46:13.108541Z] Loop 9960: Loss: 1.79e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.0881 +[2026-03-20T19:46:13.964415Z] Loop 9961: Loss: 1.75e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.0869 +[2026-03-20T19:46:14.820071Z] Loop 9962: Loss: 1.78e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.0860 +[2026-03-20T19:46:15.675141Z] Loop 9963: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0872 +[2026-03-20T19:46:16.530589Z] Loop 9964: Loss: 1.57e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.0840 +[2026-03-20T19:46:17.385782Z] Loop 9965: Loss: 1.54e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.0820 +[2026-03-20T19:46:18.240867Z] Loop 9966: Loss: 1.51e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.0802 +[2026-03-20T19:46:19.095916Z] Loop 9967: Loss: 1.46e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.0837 +[2026-03-20T19:46:19.950524Z] Loop 9968: Loss: 1.61e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.0838 +[2026-03-20T19:46:20.805697Z] Loop 9969: Loss: 1.52e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.0816 +[2026-03-20T19:46:21.702195Z] Loop 9970: Loss: 1.60e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.0799 +[2026-03-20T19:46:22.557043Z] Loop 9971: Loss: 1.58e-02, Avg Return: 0.860, Regret: 0.0025, Entropy: 0.0843 +[2026-03-20T19:46:23.411895Z] Loop 9972: Loss: 1.62e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0838 +[2026-03-20T19:46:24.265806Z] Loop 9973: Loss: 1.74e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.0862 +[2026-03-20T19:46:25.119257Z] Loop 9974: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0863 +[2026-03-20T19:46:25.973159Z] Loop 9975: Loss: 1.67e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0831 +[2026-03-20T19:46:26.827369Z] Loop 9976: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0840 +[2026-03-20T19:46:27.681279Z] Loop 9977: Loss: 1.82e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.0904 +[2026-03-20T19:46:28.535121Z] Loop 9978: Loss: 1.81e-02, Avg Return: 0.860, Regret: 0.0025, Entropy: 0.0906 +[2026-03-20T19:46:29.388947Z] Loop 9979: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0025, Entropy: 0.0861 +[2026-03-20T19:46:30.282801Z] Loop 9980: Loss: 1.61e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0805 +[2026-03-20T19:46:31.137267Z] Loop 9981: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0783 +[2026-03-20T19:46:31.991722Z] Loop 9982: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0796 +[2026-03-20T19:46:32.844914Z] Loop 9983: Loss: 1.63e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0790 +[2026-03-20T19:46:33.699547Z] Loop 9984: Loss: 1.63e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0790 +[2026-03-20T19:46:34.554110Z] Loop 9985: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0816 +[2026-03-20T19:46:35.408779Z] Loop 9986: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0834 +[2026-03-20T19:46:36.262473Z] Loop 9987: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0838 +[2026-03-20T19:46:37.116836Z] Loop 9988: Loss: 1.61e-02, Avg Return: 0.864, Regret: 0.0016, Entropy: 0.0854 +[2026-03-20T19:46:37.970578Z] Loop 9989: Loss: 1.73e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0875 +[2026-03-20T19:46:38.862776Z] Loop 9990: Loss: 1.76e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0921 +[2026-03-20T19:46:39.717295Z] Loop 9991: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0896 +[2026-03-20T19:46:40.571282Z] Loop 9992: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0887 +[2026-03-20T19:46:41.425846Z] Loop 9993: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0903 +[2026-03-20T19:46:42.280061Z] Loop 9994: Loss: 1.90e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0915 +[2026-03-20T19:46:43.134743Z] Loop 9995: Loss: 1.80e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0938 +[2026-03-20T19:46:43.988949Z] Loop 9996: Loss: 1.87e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0961 +[2026-03-20T19:46:44.843834Z] Loop 9997: Loss: 1.91e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0954 +[2026-03-20T19:46:45.698301Z] Loop 9998: Loss: 1.86e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0908 +[2026-03-20T19:46:46.553265Z] Loop 9999: Loss: 1.84e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0964 +[2026-03-20T19:46:47.449114Z] Loop 10000: Loss: 1.84e-02, Avg Return: 0.865, Regret: 0.0006, Entropy: 0.0929 +[2026-03-20T19:46:48.302389Z] Loop 10001: Loss: 1.86e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0958 +[2026-03-20T19:46:49.156332Z] Loop 10002: Loss: 1.96e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.1028 +[2026-03-20T19:46:50.010436Z] Loop 10003: Loss: 2.09e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.1042 +[2026-03-20T19:46:50.864332Z] Loop 10004: Loss: 2.08e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.1092 +[2026-03-20T19:46:51.717780Z] Loop 10005: Loss: 2.15e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.1098 +[2026-03-20T19:46:52.571792Z] Loop 10006: Loss: 2.16e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.1077 +[2026-03-20T19:46:53.426192Z] Loop 10007: Loss: 2.12e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.1050 +[2026-03-20T19:46:54.280399Z] Loop 10008: Loss: 1.90e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0983 +[2026-03-20T19:46:55.133286Z] Loop 10009: Loss: 1.82e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0945 +[2026-03-20T19:46:56.026756Z] Loop 10010: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0926 +[2026-03-20T19:46:56.882015Z] Loop 10011: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0865 +[2026-03-20T19:46:57.736709Z] Loop 10012: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0865 +[2026-03-20T19:46:58.591437Z] Loop 10013: Loss: 1.63e-02, Avg Return: 0.865, Regret: 0.0004, Entropy: 0.0861 +[2026-03-20T19:46:59.445311Z] Loop 10014: Loss: 1.68e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0894 +[2026-03-20T19:47:00.299659Z] Loop 10015: Loss: 1.70e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0891 +[2026-03-20T19:47:01.154981Z] Loop 10016: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0824 +[2026-03-20T19:47:02.009189Z] Loop 10017: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0880 +[2026-03-20T19:47:02.862774Z] Loop 10018: Loss: 1.47e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0785 +[2026-03-20T19:47:03.716785Z] Loop 10019: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0783 +[2026-03-20T19:47:04.612152Z] Loop 10020: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0789 +[2026-03-20T19:47:05.465825Z] Loop 10021: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0814 +[2026-03-20T19:47:06.320028Z] Loop 10022: Loss: 1.62e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0816 +[2026-03-20T19:47:07.174333Z] Loop 10023: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0802 +[2026-03-20T19:47:08.028986Z] Loop 10024: Loss: 1.47e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0749 +[2026-03-20T19:47:08.883047Z] Loop 10025: Loss: 1.39e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0770 +[2026-03-20T19:47:09.737252Z] Loop 10026: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0771 +[2026-03-20T19:47:10.591287Z] Loop 10027: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0831 +[2026-03-20T19:47:11.445489Z] Loop 10028: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0814 +[2026-03-20T19:47:12.300311Z] Loop 10029: Loss: 1.62e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0818 +[2026-03-20T19:47:13.194114Z] Loop 10030: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0802 +[2026-03-20T19:47:14.048444Z] Loop 10031: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0802 +[2026-03-20T19:47:14.901748Z] Loop 10032: Loss: 1.67e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0843 +[2026-03-20T19:47:15.754803Z] Loop 10033: Loss: 1.42e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0777 +[2026-03-20T19:47:16.609048Z] Loop 10034: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0806 +[2026-03-20T19:47:17.464076Z] Loop 10035: Loss: 1.57e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0777 +[2026-03-20T19:47:18.318139Z] Loop 10036: Loss: 1.43e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0743 +[2026-03-20T19:47:19.173541Z] Loop 10037: Loss: 1.40e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0734 +[2026-03-20T19:47:20.029955Z] Loop 10038: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0730 +[2026-03-20T19:47:20.885750Z] Loop 10039: Loss: 1.47e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0727 +[2026-03-20T19:47:21.779767Z] Loop 10040: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0787 +[2026-03-20T19:47:22.633758Z] Loop 10041: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0837 +[2026-03-20T19:47:23.487549Z] Loop 10042: Loss: 1.78e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0871 +[2026-03-20T19:47:24.343338Z] Loop 10043: Loss: 1.81e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0886 +[2026-03-20T19:47:25.197793Z] Loop 10044: Loss: 1.54e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0787 +[2026-03-20T19:47:26.051785Z] Loop 10045: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0763 +[2026-03-20T19:47:26.904116Z] Loop 10046: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0776 +[2026-03-20T19:47:27.757111Z] Loop 10047: Loss: 1.64e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0798 +[2026-03-20T19:47:28.611253Z] Loop 10048: Loss: 1.52e-02, Avg Return: 0.861, Regret: 0.0004, Entropy: 0.0772 +[2026-03-20T19:47:29.465619Z] Loop 10049: Loss: 1.53e-02, Avg Return: 0.861, Regret: 0.0004, Entropy: 0.0749 +[2026-03-20T19:47:30.357726Z] Loop 10050: Loss: 1.56e-02, Avg Return: 0.861, Regret: 0.0031, Entropy: 0.0785 +[2026-03-20T19:47:31.212537Z] Loop 10051: Loss: 1.70e-02, Avg Return: 0.861, Regret: 0.0031, Entropy: 0.0863 +[2026-03-20T19:47:32.067700Z] Loop 10052: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0031, Entropy: 0.0819 +[2026-03-20T19:47:32.922355Z] Loop 10053: Loss: 1.54e-02, Avg Return: 0.861, Regret: 0.0031, Entropy: 0.0789 +[2026-03-20T19:47:33.775597Z] Loop 10054: Loss: 1.59e-02, Avg Return: 0.861, Regret: 0.0031, Entropy: 0.0780 +[2026-03-20T19:47:34.628960Z] Loop 10055: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0031, Entropy: 0.0765 +[2026-03-20T19:47:35.482678Z] Loop 10056: Loss: 1.57e-02, Avg Return: 0.864, Regret: 0.0031, Entropy: 0.0793 +[2026-03-20T19:47:36.336345Z] Loop 10057: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0031, Entropy: 0.0766 +[2026-03-20T19:47:37.190208Z] Loop 10058: Loss: 1.47e-02, Avg Return: 0.864, Regret: 0.0031, Entropy: 0.0721 +[2026-03-20T19:47:38.043895Z] Loop 10059: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0031, Entropy: 0.0757 +[2026-03-20T19:47:38.936788Z] Loop 10060: Loss: 1.50e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0756 +[2026-03-20T19:47:39.791112Z] Loop 10061: Loss: 1.43e-02, Avg Return: 0.865, Regret: 0.0004, Entropy: 0.0722 +[2026-03-20T19:47:40.646489Z] Loop 10062: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0793 +[2026-03-20T19:47:41.501031Z] Loop 10063: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0797 +[2026-03-20T19:47:42.355139Z] Loop 10064: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0772 +[2026-03-20T19:47:43.208850Z] Loop 10065: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0771 +[2026-03-20T19:47:44.063532Z] Loop 10066: Loss: 1.56e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0769 +[2026-03-20T19:47:44.917595Z] Loop 10067: Loss: 1.62e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0808 +[2026-03-20T19:47:45.770583Z] Loop 10068: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0812 +[2026-03-20T19:47:46.623863Z] Loop 10069: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0774 +[2026-03-20T19:47:47.518033Z] Loop 10070: Loss: 1.47e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0739 +[2026-03-20T19:47:48.371659Z] Loop 10071: Loss: 1.35e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0735 +[2026-03-20T19:47:49.225385Z] Loop 10072: Loss: 1.41e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0715 +[2026-03-20T19:47:50.077861Z] Loop 10073: Loss: 1.28e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0696 +[2026-03-20T19:47:50.932270Z] Loop 10074: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0697 +[2026-03-20T19:47:51.787182Z] Loop 10075: Loss: 1.40e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0730 +[2026-03-20T19:47:52.641067Z] Loop 10076: Loss: 1.39e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0716 +[2026-03-20T19:47:53.494979Z] Loop 10077: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0719 +[2026-03-20T19:47:54.350075Z] Loop 10078: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0723 +[2026-03-20T19:47:55.205331Z] Loop 10079: Loss: 1.34e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0685 +[2026-03-20T19:47:56.100606Z] Loop 10080: Loss: 1.25e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0684 +[2026-03-20T19:47:56.955537Z] Loop 10081: Loss: 1.23e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0655 +[2026-03-20T19:47:57.809035Z] Loop 10082: Loss: 1.30e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0684 +[2026-03-20T19:47:58.662144Z] Loop 10083: Loss: 1.29e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0669 +[2026-03-20T19:47:59.515678Z] Loop 10084: Loss: 1.30e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0672 +[2026-03-20T19:48:00.371355Z] Loop 10085: Loss: 1.20e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0646 +[2026-03-20T19:48:01.225792Z] Loop 10086: Loss: 1.24e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0656 +[2026-03-20T19:48:02.080112Z] Loop 10087: Loss: 1.06e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0623 +[2026-03-20T19:48:02.935113Z] Loop 10088: Loss: 1.19e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0672 +[2026-03-20T19:48:03.790280Z] Loop 10089: Loss: 1.13e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0623 +[2026-03-20T19:48:04.682873Z] Loop 10090: Loss: 1.20e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0644 +[2026-03-20T19:48:05.536978Z] Loop 10091: Loss: 1.09e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0604 +[2026-03-20T19:48:06.390524Z] Loop 10092: Loss: 1.09e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0637 +[2026-03-20T19:48:07.244763Z] Loop 10093: Loss: 1.22e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0658 +[2026-03-20T19:48:08.098807Z] Loop 10094: Loss: 1.23e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0675 +[2026-03-20T19:48:08.953098Z] Loop 10095: Loss: 1.21e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0683 +[2026-03-20T19:48:09.806721Z] Loop 10096: Loss: 1.12e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0636 +[2026-03-20T19:48:10.660655Z] Loop 10097: Loss: 1.25e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0633 +[2026-03-20T19:48:11.515537Z] Loop 10098: Loss: 1.22e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0657 +[2026-03-20T19:48:12.370085Z] Loop 10099: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0704 +[2026-03-20T19:48:13.261470Z] Loop 10100: Loss: 1.11e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0604 +[2026-03-20T19:48:14.115479Z] Loop 10101: Loss: 1.15e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0626 +[2026-03-20T19:48:14.969520Z] Loop 10102: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0639 +[2026-03-20T19:48:15.824524Z] Loop 10103: Loss: 1.08e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0617 +[2026-03-20T19:48:16.678908Z] Loop 10104: Loss: 1.13e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0630 +[2026-03-20T19:48:17.534247Z] Loop 10105: Loss: 1.17e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0625 +[2026-03-20T19:48:18.388581Z] Loop 10106: Loss: 1.18e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0642 +[2026-03-20T19:48:19.242503Z] Loop 10107: Loss: 1.16e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0626 +[2026-03-20T19:48:20.096854Z] Loop 10108: Loss: 1.17e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0650 +[2026-03-20T19:48:20.950633Z] Loop 10109: Loss: 1.19e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0629 +[2026-03-20T19:48:21.845342Z] Loop 10110: Loss: 1.09e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0614 +[2026-03-20T19:48:22.699038Z] Loop 10111: Loss: 1.10e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0653 +[2026-03-20T19:48:23.554397Z] Loop 10112: Loss: 1.06e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0586 +[2026-03-20T19:48:24.409956Z] Loop 10113: Loss: 1.14e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0596 +[2026-03-20T19:48:25.264790Z] Loop 10114: Loss: 1.18e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0625 +[2026-03-20T19:48:26.119812Z] Loop 10115: Loss: 1.23e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0654 +[2026-03-20T19:48:26.976260Z] Loop 10116: Loss: 1.28e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0670 +[2026-03-20T19:48:27.830457Z] Loop 10117: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0686 +[2026-03-20T19:48:28.684539Z] Loop 10118: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0701 +[2026-03-20T19:48:29.537844Z] Loop 10119: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0759 +[2026-03-20T19:48:30.431906Z] Loop 10120: Loss: 1.35e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0724 +[2026-03-20T19:48:31.286288Z] Loop 10121: Loss: 1.46e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0759 +[2026-03-20T19:48:32.140383Z] Loop 10122: Loss: 1.47e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0784 +[2026-03-20T19:48:32.994357Z] Loop 10123: Loss: 1.40e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0738 +[2026-03-20T19:48:33.848951Z] Loop 10124: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0768 +[2026-03-20T19:48:34.703905Z] Loop 10125: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0784 +[2026-03-20T19:48:35.558221Z] Loop 10126: Loss: 1.52e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0794 +[2026-03-20T19:48:36.412515Z] Loop 10127: Loss: 1.47e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0774 +[2026-03-20T19:48:37.267839Z] Loop 10128: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0776 +[2026-03-20T19:48:38.122669Z] Loop 10129: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0751 +[2026-03-20T19:48:39.018818Z] Loop 10130: Loss: 1.47e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0751 +[2026-03-20T19:48:39.873241Z] Loop 10131: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0790 +[2026-03-20T19:48:40.727872Z] Loop 10132: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0797 +[2026-03-20T19:48:41.582477Z] Loop 10133: Loss: 1.62e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0879 +[2026-03-20T19:48:42.437050Z] Loop 10134: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0858 +[2026-03-20T19:48:43.291527Z] Loop 10135: Loss: 1.54e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0819 +[2026-03-20T19:48:44.145491Z] Loop 10136: Loss: 1.61e-02, Avg Return: 0.861, Regret: 0.0003, Entropy: 0.0866 +[2026-03-20T19:48:44.999437Z] Loop 10137: Loss: 1.64e-02, Avg Return: 0.860, Regret: 0.0003, Entropy: 0.0883 +[2026-03-20T19:48:45.853035Z] Loop 10138: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0833 +[2026-03-20T19:48:46.707148Z] Loop 10139: Loss: 1.56e-02, Avg Return: 0.861, Regret: 0.0003, Entropy: 0.0848 +[2026-03-20T19:48:47.600951Z] Loop 10140: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0801 +[2026-03-20T19:48:48.454522Z] Loop 10141: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0826 +[2026-03-20T19:48:49.307709Z] Loop 10142: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0814 +[2026-03-20T19:48:50.162883Z] Loop 10143: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0791 +[2026-03-20T19:48:51.018949Z] Loop 10144: Loss: 1.65e-02, Avg Return: 0.865, Regret: 0.0009, Entropy: 0.0826 +[2026-03-20T19:48:51.872736Z] Loop 10145: Loss: 1.59e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0836 +[2026-03-20T19:48:52.726343Z] Loop 10146: Loss: 1.72e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0891 +[2026-03-20T19:48:53.580418Z] Loop 10147: Loss: 1.81e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0917 +[2026-03-20T19:48:54.434577Z] Loop 10148: Loss: 1.88e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0947 +[2026-03-20T19:48:55.287564Z] Loop 10149: Loss: 1.84e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0903 +[2026-03-20T19:48:56.179853Z] Loop 10150: Loss: 1.84e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0921 +[2026-03-20T19:48:57.033160Z] Loop 10151: Loss: 1.90e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0977 +[2026-03-20T19:48:57.887427Z] Loop 10152: Loss: 1.83e-02, Avg Return: 0.860, Regret: 0.0007, Entropy: 0.0936 +[2026-03-20T19:48:58.740634Z] Loop 10153: Loss: 1.74e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0925 +[2026-03-20T19:48:59.594566Z] Loop 10154: Loss: 1.71e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0856 +[2026-03-20T19:49:00.448750Z] Loop 10155: Loss: 1.70e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0893 +[2026-03-20T19:49:01.302334Z] Loop 10156: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0891 +[2026-03-20T19:49:02.156382Z] Loop 10157: Loss: 1.70e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0880 +[2026-03-20T19:49:03.010677Z] Loop 10158: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0888 +[2026-03-20T19:49:03.863556Z] Loop 10159: Loss: 1.68e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0894 +[2026-03-20T19:49:04.756826Z] Loop 10160: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0858 +[2026-03-20T19:49:05.610939Z] Loop 10161: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0017, Entropy: 0.0845 +[2026-03-20T19:49:06.466654Z] Loop 10162: Loss: 1.57e-02, Avg Return: 0.864, Regret: 0.0017, Entropy: 0.0830 +[2026-03-20T19:49:07.320983Z] Loop 10163: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0017, Entropy: 0.0814 +[2026-03-20T19:49:08.174930Z] Loop 10164: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0017, Entropy: 0.0859 +[2026-03-20T19:49:09.030020Z] Loop 10165: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0017, Entropy: 0.0794 +[2026-03-20T19:49:09.884682Z] Loop 10166: Loss: 1.52e-02, Avg Return: 0.864, Regret: 0.0017, Entropy: 0.0827 +[2026-03-20T19:49:10.738543Z] Loop 10167: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0017, Entropy: 0.0842 +[2026-03-20T19:49:11.591819Z] Loop 10168: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0783 +[2026-03-20T19:49:12.445459Z] Loop 10169: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0775 +[2026-03-20T19:49:13.339802Z] Loop 10170: Loss: 1.40e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0732 +[2026-03-20T19:49:14.194032Z] Loop 10171: Loss: 1.40e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0735 +[2026-03-20T19:49:15.048776Z] Loop 10172: Loss: 1.23e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0701 +[2026-03-20T19:49:15.902545Z] Loop 10173: Loss: 1.34e-02, Avg Return: 0.865, Regret: 0.0002, Entropy: 0.0710 +[2026-03-20T19:49:16.756262Z] Loop 10174: Loss: 1.30e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0697 +[2026-03-20T19:49:17.611705Z] Loop 10175: Loss: 1.32e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0723 +[2026-03-20T19:49:18.466339Z] Loop 10176: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0747 +[2026-03-20T19:49:19.320022Z] Loop 10177: Loss: 1.24e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0680 +[2026-03-20T19:49:20.173381Z] Loop 10178: Loss: 1.34e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0723 +[2026-03-20T19:49:21.027800Z] Loop 10179: Loss: 1.32e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0708 +[2026-03-20T19:49:21.921946Z] Loop 10180: Loss: 1.29e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0692 +[2026-03-20T19:49:22.776137Z] Loop 10181: Loss: 1.27e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0685 +[2026-03-20T19:49:23.629416Z] Loop 10182: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0703 +[2026-03-20T19:49:24.484598Z] Loop 10183: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0724 +[2026-03-20T19:49:25.339815Z] Loop 10184: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0677 +[2026-03-20T19:49:26.194757Z] Loop 10185: Loss: 1.34e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0704 +[2026-03-20T19:49:27.048548Z] Loop 10186: Loss: 1.17e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0668 +[2026-03-20T19:49:27.903845Z] Loop 10187: Loss: 1.23e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0663 +[2026-03-20T19:49:28.758338Z] Loop 10188: Loss: 1.29e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0704 +[2026-03-20T19:49:29.613806Z] Loop 10189: Loss: 1.25e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0673 +[2026-03-20T19:49:30.511581Z] Loop 10190: Loss: 1.30e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0680 +[2026-03-20T19:49:31.366569Z] Loop 10191: Loss: 1.34e-02, Avg Return: 0.865, Regret: 0.0003, Entropy: 0.0702 +[2026-03-20T19:49:32.222206Z] Loop 10192: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0685 +[2026-03-20T19:49:33.077615Z] Loop 10193: Loss: 1.38e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0777 +[2026-03-20T19:49:33.932039Z] Loop 10194: Loss: 1.32e-02, Avg Return: 0.865, Regret: 0.0003, Entropy: 0.0704 +[2026-03-20T19:49:34.786939Z] Loop 10195: Loss: 1.37e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0727 +[2026-03-20T19:49:35.641558Z] Loop 10196: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0712 +[2026-03-20T19:49:36.497064Z] Loop 10197: Loss: 1.31e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0692 +[2026-03-20T19:49:37.352371Z] Loop 10198: Loss: 1.27e-02, Avg Return: 0.861, Regret: 0.0003, Entropy: 0.0704 +[2026-03-20T19:49:38.208099Z] Loop 10199: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0710 +[2026-03-20T19:49:39.105777Z] Loop 10200: Loss: 1.40e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0703 +[2026-03-20T19:49:39.959543Z] Loop 10201: Loss: 1.32e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0736 +[2026-03-20T19:49:40.813849Z] Loop 10202: Loss: 1.42e-02, Avg Return: 0.865, Regret: 0.0002, Entropy: 0.0734 +[2026-03-20T19:49:41.668466Z] Loop 10203: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0759 +[2026-03-20T19:49:42.523752Z] Loop 10204: Loss: 1.30e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0708 +[2026-03-20T19:49:43.378236Z] Loop 10205: Loss: 1.45e-02, Avg Return: 0.865, Regret: 0.0002, Entropy: 0.0734 +[2026-03-20T19:49:44.232432Z] Loop 10206: Loss: 1.40e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0761 +[2026-03-20T19:49:45.086766Z] Loop 10207: Loss: 1.64e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0849 +[2026-03-20T19:49:45.941252Z] Loop 10208: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0795 +[2026-03-20T19:49:46.795798Z] Loop 10209: Loss: 1.56e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0837 +[2026-03-20T19:49:47.691803Z] Loop 10210: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0824 +[2026-03-20T19:49:48.547149Z] Loop 10211: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0831 +[2026-03-20T19:49:49.401213Z] Loop 10212: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0812 +[2026-03-20T19:49:50.255171Z] Loop 10213: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0852 +[2026-03-20T19:49:51.109844Z] Loop 10214: Loss: 1.63e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0839 +[2026-03-20T19:49:51.964293Z] Loop 10215: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0840 +[2026-03-20T19:49:52.818309Z] Loop 10216: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0849 +[2026-03-20T19:49:53.672840Z] Loop 10217: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0856 +[2026-03-20T19:49:54.527283Z] Loop 10218: Loss: 1.76e-02, Avg Return: 0.861, Regret: 0.0002, Entropy: 0.0896 +[2026-03-20T19:49:55.381105Z] Loop 10219: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0937 +[2026-03-20T19:49:56.275023Z] Loop 10220: Loss: 1.63e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.0845 +[2026-03-20T19:49:57.130352Z] Loop 10221: Loss: 1.76e-02, Avg Return: 0.860, Regret: 0.0028, Entropy: 0.0881 +[2026-03-20T19:49:57.985328Z] Loop 10222: Loss: 1.71e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.0868 +[2026-03-20T19:49:58.838525Z] Loop 10223: Loss: 1.73e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.0895 +[2026-03-20T19:49:59.691603Z] Loop 10224: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.0854 +[2026-03-20T19:50:00.545681Z] Loop 10225: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.0830 +[2026-03-20T19:50:01.400310Z] Loop 10226: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0028, Entropy: 0.0805 +[2026-03-20T19:50:02.255679Z] Loop 10227: Loss: 1.64e-02, Avg Return: 0.863, Regret: 0.0028, Entropy: 0.0832 +[2026-03-20T19:50:03.109991Z] Loop 10228: Loss: 1.56e-02, Avg Return: 0.864, Regret: 0.0028, Entropy: 0.0808 +[2026-03-20T19:50:03.963820Z] Loop 10229: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0028, Entropy: 0.0822 +[2026-03-20T19:50:04.860265Z] Loop 10230: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0792 +[2026-03-20T19:50:05.714650Z] Loop 10231: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0815 +[2026-03-20T19:50:06.569141Z] Loop 10232: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0833 +[2026-03-20T19:50:07.423143Z] Loop 10233: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0790 +[2026-03-20T19:50:08.277710Z] Loop 10234: Loss: 1.73e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0875 +[2026-03-20T19:50:09.132249Z] Loop 10235: Loss: 1.55e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0826 +[2026-03-20T19:50:09.986360Z] Loop 10236: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0863 +[2026-03-20T19:50:10.840122Z] Loop 10237: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0905 +[2026-03-20T19:50:11.694762Z] Loop 10238: Loss: 1.89e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0931 +[2026-03-20T19:50:12.549565Z] Loop 10239: Loss: 1.86e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0941 +[2026-03-20T19:50:13.442849Z] Loop 10240: Loss: 1.90e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0975 +[2026-03-20T19:50:14.295797Z] Loop 10241: Loss: 1.90e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0960 +[2026-03-20T19:50:15.151431Z] Loop 10242: Loss: 1.96e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0978 +[2026-03-20T19:50:16.006166Z] Loop 10243: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0939 +[2026-03-20T19:50:16.860274Z] Loop 10244: Loss: 1.95e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0963 +[2026-03-20T19:50:17.713804Z] Loop 10245: Loss: 1.88e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0991 +[2026-03-20T19:50:18.568341Z] Loop 10246: Loss: 1.93e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0966 +[2026-03-20T19:50:19.421683Z] Loop 10247: Loss: 1.84e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0953 +[2026-03-20T19:50:20.274991Z] Loop 10248: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0887 +[2026-03-20T19:50:21.128387Z] Loop 10249: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0872 +[2026-03-20T19:50:22.022580Z] Loop 10250: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0872 +[2026-03-20T19:50:22.876050Z] Loop 10251: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0917 +[2026-03-20T19:50:23.730117Z] Loop 10252: Loss: 1.76e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0893 +[2026-03-20T19:50:24.584129Z] Loop 10253: Loss: 1.71e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0870 +[2026-03-20T19:50:25.437957Z] Loop 10254: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0877 +[2026-03-20T19:50:26.290868Z] Loop 10255: Loss: 1.77e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0926 +[2026-03-20T19:50:27.144117Z] Loop 10256: Loss: 1.79e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0906 +[2026-03-20T19:50:27.998652Z] Loop 10257: Loss: 1.67e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0863 +[2026-03-20T19:50:28.852458Z] Loop 10258: Loss: 1.73e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0904 +[2026-03-20T19:50:29.704758Z] Loop 10259: Loss: 1.77e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0877 +[2026-03-20T19:50:30.599809Z] Loop 10260: Loss: 1.61e-02, Avg Return: 0.865, Regret: 0.0007, Entropy: 0.0848 +[2026-03-20T19:50:31.454534Z] Loop 10261: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0918 +[2026-03-20T19:50:32.308692Z] Loop 10262: Loss: 1.64e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0880 +[2026-03-20T19:50:33.162543Z] Loop 10263: Loss: 1.79e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0906 +[2026-03-20T19:50:34.016593Z] Loop 10264: Loss: 1.72e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0890 +[2026-03-20T19:50:34.871679Z] Loop 10265: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0861 +[2026-03-20T19:50:35.725815Z] Loop 10266: Loss: 1.88e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0919 +[2026-03-20T19:50:36.579838Z] Loop 10267: Loss: 1.97e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0966 +[2026-03-20T19:50:37.433851Z] Loop 10268: Loss: 1.91e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0928 +[2026-03-20T19:50:38.288872Z] Loop 10269: Loss: 1.88e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0965 +[2026-03-20T19:50:39.184605Z] Loop 10270: Loss: 1.92e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0963 +[2026-03-20T19:50:40.039211Z] Loop 10271: Loss: 1.80e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0936 +[2026-03-20T19:50:40.893377Z] Loop 10272: Loss: 1.82e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0910 +[2026-03-20T19:50:41.748707Z] Loop 10273: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0928 +[2026-03-20T19:50:42.603399Z] Loop 10274: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0961 +[2026-03-20T19:50:43.457632Z] Loop 10275: Loss: 1.77e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0894 +[2026-03-20T19:50:44.311617Z] Loop 10276: Loss: 1.77e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0872 +[2026-03-20T19:50:45.165823Z] Loop 10277: Loss: 1.61e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0849 +[2026-03-20T19:50:46.019832Z] Loop 10278: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0787 +[2026-03-20T19:50:46.873765Z] Loop 10279: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0803 +[2026-03-20T19:50:47.768052Z] Loop 10280: Loss: 1.49e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0806 +[2026-03-20T19:50:48.622444Z] Loop 10281: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0814 +[2026-03-20T19:50:49.476045Z] Loop 10282: Loss: 1.62e-02, Avg Return: 0.865, Regret: 0.0006, Entropy: 0.0816 +[2026-03-20T19:50:50.329709Z] Loop 10283: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0789 +[2026-03-20T19:50:51.183954Z] Loop 10284: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0826 +[2026-03-20T19:50:52.038836Z] Loop 10285: Loss: 1.47e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0801 +[2026-03-20T19:50:52.891802Z] Loop 10286: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0806 +[2026-03-20T19:50:53.744628Z] Loop 10287: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0834 +[2026-03-20T19:50:54.598601Z] Loop 10288: Loss: 1.56e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.0857 +[2026-03-20T19:50:55.453855Z] Loop 10289: Loss: 1.43e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.0801 +[2026-03-20T19:50:56.350339Z] Loop 10290: Loss: 1.55e-02, Avg Return: 0.860, Regret: 0.0029, Entropy: 0.0811 +[2026-03-20T19:50:57.204408Z] Loop 10291: Loss: 1.40e-02, Avg Return: 0.860, Regret: 0.0029, Entropy: 0.0766 +[2026-03-20T19:50:58.058245Z] Loop 10292: Loss: 1.51e-02, Avg Return: 0.858, Regret: 0.0029, Entropy: 0.0803 +[2026-03-20T19:50:58.913719Z] Loop 10293: Loss: 1.55e-02, Avg Return: 0.858, Regret: 0.0029, Entropy: 0.0797 +[2026-03-20T19:50:59.767804Z] Loop 10294: Loss: 1.54e-02, Avg Return: 0.859, Regret: 0.0029, Entropy: 0.0813 +[2026-03-20T19:51:00.622058Z] Loop 10295: Loss: 1.59e-02, Avg Return: 0.858, Regret: 0.0029, Entropy: 0.0826 +[2026-03-20T19:51:01.475677Z] Loop 10296: Loss: 1.65e-02, Avg Return: 0.859, Regret: 0.0029, Entropy: 0.0825 +[2026-03-20T19:51:02.330574Z] Loop 10297: Loss: 1.48e-02, Avg Return: 0.860, Regret: 0.0029, Entropy: 0.0769 +[2026-03-20T19:51:03.185168Z] Loop 10298: Loss: 1.55e-02, Avg Return: 0.860, Regret: 0.0029, Entropy: 0.0796 +[2026-03-20T19:51:04.040070Z] Loop 10299: Loss: 1.42e-02, Avg Return: 0.860, Regret: 0.0029, Entropy: 0.0757 +[2026-03-20T19:51:04.937212Z] Loop 10300: Loss: 1.32e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.0715 +[2026-03-20T19:51:05.791929Z] Loop 10301: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0021, Entropy: 0.0770 +[2026-03-20T19:51:06.646989Z] Loop 10302: Loss: 1.46e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.0775 +[2026-03-20T19:51:07.502024Z] Loop 10303: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0021, Entropy: 0.0748 +[2026-03-20T19:51:08.357121Z] Loop 10304: Loss: 1.50e-02, Avg Return: 0.865, Regret: 0.0021, Entropy: 0.0793 +[2026-03-20T19:51:09.212573Z] Loop 10305: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0021, Entropy: 0.0739 +[2026-03-20T19:51:10.066482Z] Loop 10306: Loss: 1.47e-02, Avg Return: 0.864, Regret: 0.0021, Entropy: 0.0798 +[2026-03-20T19:51:10.920724Z] Loop 10307: Loss: 1.35e-02, Avg Return: 0.864, Regret: 0.0021, Entropy: 0.0727 +[2026-03-20T19:51:11.776104Z] Loop 10308: Loss: 1.34e-02, Avg Return: 0.865, Regret: 0.0021, Entropy: 0.0741 +[2026-03-20T19:51:12.633764Z] Loop 10309: Loss: 1.35e-02, Avg Return: 0.864, Regret: 0.0021, Entropy: 0.0708 +[2026-03-20T19:51:13.528447Z] Loop 10310: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0731 +[2026-03-20T19:51:14.383147Z] Loop 10311: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0733 +[2026-03-20T19:51:15.239123Z] Loop 10312: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0726 +[2026-03-20T19:51:16.094416Z] Loop 10313: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0706 +[2026-03-20T19:51:16.949023Z] Loop 10314: Loss: 1.32e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0720 +[2026-03-20T19:51:17.804499Z] Loop 10315: Loss: 1.32e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0684 +[2026-03-20T19:51:18.660370Z] Loop 10316: Loss: 1.40e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0734 +[2026-03-20T19:51:19.516486Z] Loop 10317: Loss: 1.43e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0728 +[2026-03-20T19:51:20.370500Z] Loop 10318: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0732 +[2026-03-20T19:51:21.224726Z] Loop 10319: Loss: 1.40e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0748 +[2026-03-20T19:51:22.123231Z] Loop 10320: Loss: 1.34e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0733 +[2026-03-20T19:51:22.977782Z] Loop 10321: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0713 +[2026-03-20T19:51:23.832974Z] Loop 10322: Loss: 1.39e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0740 +[2026-03-20T19:51:24.687504Z] Loop 10323: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0719 +[2026-03-20T19:51:25.543977Z] Loop 10324: Loss: 1.34e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0715 +[2026-03-20T19:51:26.398550Z] Loop 10325: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0770 +[2026-03-20T19:51:27.252776Z] Loop 10326: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0716 +[2026-03-20T19:51:28.106762Z] Loop 10327: Loss: 1.39e-02, Avg Return: 0.861, Regret: 0.0002, Entropy: 0.0749 +[2026-03-20T19:51:28.961645Z] Loop 10328: Loss: 1.30e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0727 +[2026-03-20T19:51:29.817072Z] Loop 10329: Loss: 1.41e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0748 +[2026-03-20T19:51:30.714646Z] Loop 10330: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0758 +[2026-03-20T19:51:31.570289Z] Loop 10331: Loss: 1.44e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0774 +[2026-03-20T19:51:32.426563Z] Loop 10332: Loss: 1.35e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0732 +[2026-03-20T19:51:33.280457Z] Loop 10333: Loss: 1.33e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0770 +[2026-03-20T19:51:34.135286Z] Loop 10334: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0739 +[2026-03-20T19:51:34.990137Z] Loop 10335: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0782 +[2026-03-20T19:51:35.844674Z] Loop 10336: Loss: 1.40e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0768 +[2026-03-20T19:51:36.698330Z] Loop 10337: Loss: 1.51e-02, Avg Return: 0.865, Regret: 0.0005, Entropy: 0.0798 +[2026-03-20T19:51:37.553328Z] Loop 10338: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0750 +[2026-03-20T19:51:38.407202Z] Loop 10339: Loss: 1.51e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0751 +[2026-03-20T19:51:39.303956Z] Loop 10340: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0750 +[2026-03-20T19:51:40.158048Z] Loop 10341: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0747 +[2026-03-20T19:51:41.012405Z] Loop 10342: Loss: 1.47e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0787 +[2026-03-20T19:51:41.867325Z] Loop 10343: Loss: 1.51e-02, Avg Return: 0.865, Regret: 0.0002, Entropy: 0.0772 +[2026-03-20T19:51:42.722720Z] Loop 10344: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0787 +[2026-03-20T19:51:43.576342Z] Loop 10345: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0775 +[2026-03-20T19:51:44.429761Z] Loop 10346: Loss: 1.53e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0780 +[2026-03-20T19:51:45.284061Z] Loop 10347: Loss: 1.48e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0763 +[2026-03-20T19:51:46.138901Z] Loop 10348: Loss: 1.39e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0747 +[2026-03-20T19:51:46.993503Z] Loop 10349: Loss: 1.46e-02, Avg Return: 0.865, Regret: 0.0002, Entropy: 0.0744 +[2026-03-20T19:51:47.887286Z] Loop 10350: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0782 +[2026-03-20T19:51:48.741551Z] Loop 10351: Loss: 1.47e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0767 +[2026-03-20T19:51:49.596715Z] Loop 10352: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0794 +[2026-03-20T19:51:50.451201Z] Loop 10353: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0770 +[2026-03-20T19:51:51.306404Z] Loop 10354: Loss: 1.45e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0761 +[2026-03-20T19:51:52.160272Z] Loop 10355: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0761 +[2026-03-20T19:51:53.014600Z] Loop 10356: Loss: 1.46e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.0763 +[2026-03-20T19:51:53.869504Z] Loop 10357: Loss: 1.44e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0737 +[2026-03-20T19:51:54.723651Z] Loop 10358: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0785 +[2026-03-20T19:51:55.577423Z] Loop 10359: Loss: 1.50e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0765 +[2026-03-20T19:51:56.471282Z] Loop 10360: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0695 +[2026-03-20T19:51:57.325785Z] Loop 10361: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0741 +[2026-03-20T19:51:58.180225Z] Loop 10362: Loss: 1.37e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0718 +[2026-03-20T19:51:59.034251Z] Loop 10363: Loss: 1.35e-02, Avg Return: 0.865, Regret: 0.0004, Entropy: 0.0733 +[2026-03-20T19:51:59.888324Z] Loop 10364: Loss: 1.25e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0667 +[2026-03-20T19:52:00.742351Z] Loop 10365: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0661 +[2026-03-20T19:52:01.596568Z] Loop 10366: Loss: 1.18e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0651 +[2026-03-20T19:52:02.451172Z] Loop 10367: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0634 +[2026-03-20T19:52:03.304291Z] Loop 10368: Loss: 1.17e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0615 +[2026-03-20T19:52:04.158334Z] Loop 10369: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0717 +[2026-03-20T19:52:05.052020Z] Loop 10370: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0673 +[2026-03-20T19:52:05.907064Z] Loop 10371: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0687 +[2026-03-20T19:52:06.760848Z] Loop 10372: Loss: 1.28e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0709 +[2026-03-20T19:52:07.614339Z] Loop 10373: Loss: 1.23e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0652 +[2026-03-20T19:52:08.468406Z] Loop 10374: Loss: 1.29e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0700 +[2026-03-20T19:52:09.323023Z] Loop 10375: Loss: 1.27e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0725 +[2026-03-20T19:52:10.176910Z] Loop 10376: Loss: 1.36e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0712 +[2026-03-20T19:52:11.030288Z] Loop 10377: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0694 +[2026-03-20T19:52:11.883680Z] Loop 10378: Loss: 1.32e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0696 +[2026-03-20T19:52:12.738479Z] Loop 10379: Loss: 1.22e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0665 +[2026-03-20T19:52:13.632278Z] Loop 10380: Loss: 1.25e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0683 +[2026-03-20T19:52:14.485975Z] Loop 10381: Loss: 1.22e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0666 +[2026-03-20T19:52:15.339906Z] Loop 10382: Loss: 1.26e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0673 +[2026-03-20T19:52:16.195101Z] Loop 10383: Loss: 1.17e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0668 +[2026-03-20T19:52:17.051010Z] Loop 10384: Loss: 1.27e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0696 +[2026-03-20T19:52:17.905898Z] Loop 10385: Loss: 1.19e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0654 +[2026-03-20T19:52:18.760534Z] Loop 10386: Loss: 1.19e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0665 +[2026-03-20T19:52:19.615544Z] Loop 10387: Loss: 1.25e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0667 +[2026-03-20T19:52:20.469830Z] Loop 10388: Loss: 1.16e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0652 +[2026-03-20T19:52:21.324133Z] Loop 10389: Loss: 1.18e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0650 +[2026-03-20T19:52:22.218438Z] Loop 10390: Loss: 1.24e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0662 +[2026-03-20T19:52:23.073518Z] Loop 10391: Loss: 1.07e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0577 +[2026-03-20T19:52:23.928221Z] Loop 10392: Loss: 1.13e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0636 +[2026-03-20T19:52:24.782143Z] Loop 10393: Loss: 1.24e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0657 +[2026-03-20T19:52:25.637737Z] Loop 10394: Loss: 1.13e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0619 +[2026-03-20T19:52:26.491226Z] Loop 10395: Loss: 1.08e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0593 +[2026-03-20T19:52:27.345225Z] Loop 10396: Loss: 1.15e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0645 +[2026-03-20T19:52:28.199556Z] Loop 10397: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0667 +[2026-03-20T19:52:29.052979Z] Loop 10398: Loss: 1.16e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0642 +[2026-03-20T19:52:29.907197Z] Loop 10399: Loss: 1.19e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0632 +[2026-03-20T19:52:30.800668Z] Loop 10400: Loss: 1.22e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0667 +[2026-03-20T19:52:31.655387Z] Loop 10401: Loss: 1.24e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0657 +[2026-03-20T19:52:32.509814Z] Loop 10402: Loss: 1.27e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0709 +[2026-03-20T19:52:33.366238Z] Loop 10403: Loss: 1.17e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0680 +[2026-03-20T19:52:34.220361Z] Loop 10404: Loss: 1.40e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0729 +[2026-03-20T19:52:35.073550Z] Loop 10405: Loss: 1.35e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0711 +[2026-03-20T19:52:35.928021Z] Loop 10406: Loss: 1.49e-02, Avg Return: 0.860, Regret: 0.0002, Entropy: 0.0785 +[2026-03-20T19:52:36.783469Z] Loop 10407: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0786 +[2026-03-20T19:52:37.639361Z] Loop 10408: Loss: 1.47e-02, Avg Return: 0.861, Regret: 0.0002, Entropy: 0.0766 +[2026-03-20T19:52:38.492950Z] Loop 10409: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0763 +[2026-03-20T19:52:39.386691Z] Loop 10410: Loss: 1.46e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0766 +[2026-03-20T19:52:40.241543Z] Loop 10411: Loss: 1.30e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0728 +[2026-03-20T19:52:41.094865Z] Loop 10412: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0716 +[2026-03-20T19:52:41.948492Z] Loop 10413: Loss: 1.37e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0707 +[2026-03-20T19:52:42.802419Z] Loop 10414: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0717 +[2026-03-20T19:52:43.656436Z] Loop 10415: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0700 +[2026-03-20T19:52:44.511557Z] Loop 10416: Loss: 1.34e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0716 +[2026-03-20T19:52:45.365866Z] Loop 10417: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0757 +[2026-03-20T19:52:46.220904Z] Loop 10418: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0759 +[2026-03-20T19:52:47.075004Z] Loop 10419: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0688 +[2026-03-20T19:52:47.968408Z] Loop 10420: Loss: 1.32e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0740 +[2026-03-20T19:52:48.822270Z] Loop 10421: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0751 +[2026-03-20T19:52:49.676615Z] Loop 10422: Loss: 1.48e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0789 +[2026-03-20T19:52:50.531567Z] Loop 10423: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0782 +[2026-03-20T19:52:51.385805Z] Loop 10424: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0716 +[2026-03-20T19:52:52.239877Z] Loop 10425: Loss: 1.45e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0757 +[2026-03-20T19:52:53.093492Z] Loop 10426: Loss: 1.38e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0756 +[2026-03-20T19:52:53.947004Z] Loop 10427: Loss: 1.30e-02, Avg Return: 0.865, Regret: 0.0002, Entropy: 0.0718 +[2026-03-20T19:52:54.800671Z] Loop 10428: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0753 +[2026-03-20T19:52:55.655525Z] Loop 10429: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0809 +[2026-03-20T19:52:56.549393Z] Loop 10430: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0801 +[2026-03-20T19:52:57.403303Z] Loop 10431: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0781 +[2026-03-20T19:52:58.257358Z] Loop 10432: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0785 +[2026-03-20T19:52:59.111886Z] Loop 10433: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0769 +[2026-03-20T19:52:59.966445Z] Loop 10434: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0834 +[2026-03-20T19:53:00.820974Z] Loop 10435: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0806 +[2026-03-20T19:53:01.673851Z] Loop 10436: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0844 +[2026-03-20T19:53:02.526580Z] Loop 10437: Loss: 1.48e-02, Avg Return: 0.861, Regret: 0.0004, Entropy: 0.0805 +[2026-03-20T19:53:03.381825Z] Loop 10438: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0814 +[2026-03-20T19:53:04.235702Z] Loop 10439: Loss: 1.55e-02, Avg Return: 0.861, Regret: 0.0004, Entropy: 0.0823 +[2026-03-20T19:53:05.129610Z] Loop 10440: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0820 +[2026-03-20T19:53:05.983951Z] Loop 10441: Loss: 1.60e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.0843 +[2026-03-20T19:53:06.840279Z] Loop 10442: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0843 +[2026-03-20T19:53:07.693993Z] Loop 10443: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0833 +[2026-03-20T19:53:08.548701Z] Loop 10444: Loss: 1.40e-02, Avg Return: 0.864, Regret: 0.0015, Entropy: 0.0801 +[2026-03-20T19:53:09.403563Z] Loop 10445: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0784 +[2026-03-20T19:53:10.258634Z] Loop 10446: Loss: 1.39e-02, Avg Return: 0.865, Regret: 0.0015, Entropy: 0.0757 +[2026-03-20T19:53:11.113795Z] Loop 10447: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0769 +[2026-03-20T19:53:11.970593Z] Loop 10448: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0754 +[2026-03-20T19:53:12.824701Z] Loop 10449: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0777 +[2026-03-20T19:53:13.717616Z] Loop 10450: Loss: 1.45e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0801 +[2026-03-20T19:53:14.571608Z] Loop 10451: Loss: 1.40e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0793 +[2026-03-20T19:53:15.426155Z] Loop 10452: Loss: 1.47e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0800 +[2026-03-20T19:53:16.280782Z] Loop 10453: Loss: 1.48e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0822 +[2026-03-20T19:53:17.135573Z] Loop 10454: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0860 +[2026-03-20T19:53:17.989195Z] Loop 10455: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0756 +[2026-03-20T19:53:18.843458Z] Loop 10456: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0859 +[2026-03-20T19:53:19.697993Z] Loop 10457: Loss: 1.50e-02, Avg Return: 0.861, Regret: 0.0003, Entropy: 0.0858 +[2026-03-20T19:53:20.553135Z] Loop 10458: Loss: 1.47e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0809 +[2026-03-20T19:53:21.407020Z] Loop 10459: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0796 +[2026-03-20T19:53:22.298778Z] Loop 10460: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0851 +[2026-03-20T19:53:23.152523Z] Loop 10461: Loss: 1.50e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0828 +[2026-03-20T19:53:24.007577Z] Loop 10462: Loss: 1.46e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0783 +[2026-03-20T19:53:24.861546Z] Loop 10463: Loss: 1.50e-02, Avg Return: 0.866, Regret: 0.0004, Entropy: 0.0822 +[2026-03-20T19:53:25.714962Z] Loop 10464: Loss: 1.43e-02, Avg Return: 0.865, Regret: 0.0004, Entropy: 0.0825 +[2026-03-20T19:53:26.568556Z] Loop 10465: Loss: 1.52e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0855 +[2026-03-20T19:53:27.423960Z] Loop 10466: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0859 +[2026-03-20T19:53:28.278495Z] Loop 10467: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0882 +[2026-03-20T19:53:29.131607Z] Loop 10468: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0869 +[2026-03-20T19:53:29.984972Z] Loop 10469: Loss: 1.56e-02, Avg Return: 0.865, Regret: 0.0004, Entropy: 0.0869 +[2026-03-20T19:53:30.877315Z] Loop 10470: Loss: 1.56e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0895 +[2026-03-20T19:53:31.732001Z] Loop 10471: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0917 +[2026-03-20T19:53:32.587148Z] Loop 10472: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0907 +[2026-03-20T19:53:33.442693Z] Loop 10473: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0955 +[2026-03-20T19:53:34.297304Z] Loop 10474: Loss: 1.67e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0978 +[2026-03-20T19:53:35.150883Z] Loop 10475: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0986 +[2026-03-20T19:53:36.005882Z] Loop 10476: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0957 +[2026-03-20T19:53:36.861456Z] Loop 10477: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0936 +[2026-03-20T19:53:37.715634Z] Loop 10478: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0913 +[2026-03-20T19:53:38.570135Z] Loop 10479: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0992 +[2026-03-20T19:53:39.463718Z] Loop 10480: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0917 +[2026-03-20T19:53:40.318685Z] Loop 10481: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0887 +[2026-03-20T19:53:41.173200Z] Loop 10482: Loss: 1.54e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0907 +[2026-03-20T19:53:42.028842Z] Loop 10483: Loss: 1.50e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0873 +[2026-03-20T19:53:42.883733Z] Loop 10484: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0895 +[2026-03-20T19:53:43.739162Z] Loop 10485: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0870 +[2026-03-20T19:53:44.593999Z] Loop 10486: Loss: 1.50e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0873 +[2026-03-20T19:53:45.448797Z] Loop 10487: Loss: 1.71e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0893 +[2026-03-20T19:53:46.302396Z] Loop 10488: Loss: 1.59e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0864 +[2026-03-20T19:53:47.156281Z] Loop 10489: Loss: 1.51e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0841 +[2026-03-20T19:53:48.050516Z] Loop 10490: Loss: 1.64e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0867 +[2026-03-20T19:53:48.904545Z] Loop 10491: Loss: 1.53e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0832 +[2026-03-20T19:53:49.759502Z] Loop 10492: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0807 +[2026-03-20T19:53:50.615426Z] Loop 10493: Loss: 1.56e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0818 +[2026-03-20T19:53:51.470963Z] Loop 10494: Loss: 1.38e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0768 +[2026-03-20T19:53:52.326080Z] Loop 10495: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0793 +[2026-03-20T19:53:53.180999Z] Loop 10496: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0757 +[2026-03-20T19:53:54.035956Z] Loop 10497: Loss: 1.47e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0777 +[2026-03-20T19:53:54.889583Z] Loop 10498: Loss: 1.41e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0772 +[2026-03-20T19:53:55.744287Z] Loop 10499: Loss: 1.43e-02, Avg Return: 0.861, Regret: 0.0004, Entropy: 0.0767 +[2026-03-20T19:53:56.638608Z] Loop 10500: Loss: 1.33e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0708 +[2026-03-20T19:53:57.493308Z] Loop 10501: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0702 +[2026-03-20T19:53:58.348211Z] Loop 10502: Loss: 1.43e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0778 +[2026-03-20T19:53:59.203411Z] Loop 10503: Loss: 1.31e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0747 +[2026-03-20T19:54:00.057594Z] Loop 10504: Loss: 1.33e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0724 +[2026-03-20T19:54:00.911935Z] Loop 10505: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0770 +[2026-03-20T19:54:01.766098Z] Loop 10506: Loss: 1.32e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0705 +[2026-03-20T19:54:02.620690Z] Loop 10507: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0745 +[2026-03-20T19:54:03.474637Z] Loop 10508: Loss: 1.29e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0697 +[2026-03-20T19:54:04.329698Z] Loop 10509: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0717 +[2026-03-20T19:54:05.223301Z] Loop 10510: Loss: 1.23e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0707 +[2026-03-20T19:54:06.077780Z] Loop 10511: Loss: 1.25e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0705 +[2026-03-20T19:54:06.932373Z] Loop 10512: Loss: 1.33e-02, Avg Return: 0.865, Regret: 0.0004, Entropy: 0.0723 +[2026-03-20T19:54:07.786565Z] Loop 10513: Loss: 1.30e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0718 +[2026-03-20T19:54:08.640067Z] Loop 10514: Loss: 1.32e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0713 +[2026-03-20T19:54:09.494542Z] Loop 10515: Loss: 1.36e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0703 +[2026-03-20T19:54:10.349446Z] Loop 10516: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0713 +[2026-03-20T19:54:11.204150Z] Loop 10517: Loss: 1.26e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0705 +[2026-03-20T19:54:12.057404Z] Loop 10518: Loss: 1.24e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0708 +[2026-03-20T19:54:12.911158Z] Loop 10519: Loss: 1.36e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0717 +[2026-03-20T19:54:13.803720Z] Loop 10520: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0738 +[2026-03-20T19:54:14.658719Z] Loop 10521: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0728 +[2026-03-20T19:54:15.512051Z] Loop 10522: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0739 +[2026-03-20T19:54:16.365717Z] Loop 10523: Loss: 1.40e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0730 +[2026-03-20T19:54:17.220405Z] Loop 10524: Loss: 1.35e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0755 +[2026-03-20T19:54:18.074847Z] Loop 10525: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0747 +[2026-03-20T19:54:18.928250Z] Loop 10526: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0781 +[2026-03-20T19:54:19.781198Z] Loop 10527: Loss: 1.36e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0728 +[2026-03-20T19:54:20.635768Z] Loop 10528: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0753 +[2026-03-20T19:54:21.489998Z] Loop 10529: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0738 +[2026-03-20T19:54:22.381483Z] Loop 10530: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0759 +[2026-03-20T19:54:23.234762Z] Loop 10531: Loss: 1.33e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0724 +[2026-03-20T19:54:24.089509Z] Loop 10532: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0682 +[2026-03-20T19:54:24.943419Z] Loop 10533: Loss: 1.32e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0740 +[2026-03-20T19:54:25.797484Z] Loop 10534: Loss: 1.30e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0718 +[2026-03-20T19:54:26.650967Z] Loop 10535: Loss: 1.32e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0731 +[2026-03-20T19:54:27.505748Z] Loop 10536: Loss: 1.41e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0713 +[2026-03-20T19:54:28.359594Z] Loop 10537: Loss: 1.40e-02, Avg Return: 0.865, Regret: 0.0005, Entropy: 0.0753 +[2026-03-20T19:54:29.213675Z] Loop 10538: Loss: 1.33e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0728 +[2026-03-20T19:54:30.067658Z] Loop 10539: Loss: 1.43e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0783 +[2026-03-20T19:54:30.962367Z] Loop 10540: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0718 +[2026-03-20T19:54:31.817772Z] Loop 10541: Loss: 1.37e-02, Avg Return: 0.865, Regret: 0.0003, Entropy: 0.0748 +[2026-03-20T19:54:32.672425Z] Loop 10542: Loss: 1.43e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0767 +[2026-03-20T19:54:33.526424Z] Loop 10543: Loss: 1.42e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0774 +[2026-03-20T19:54:34.380549Z] Loop 10544: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0803 +[2026-03-20T19:54:35.233988Z] Loop 10545: Loss: 1.64e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0874 +[2026-03-20T19:54:36.087996Z] Loop 10546: Loss: 1.55e-02, Avg Return: 0.861, Regret: 0.0003, Entropy: 0.0850 +[2026-03-20T19:54:36.943151Z] Loop 10547: Loss: 1.70e-02, Avg Return: 0.859, Regret: 0.0003, Entropy: 0.0910 +[2026-03-20T19:54:37.797599Z] Loop 10548: Loss: 1.83e-02, Avg Return: 0.856, Regret: 0.0003, Entropy: 0.0984 +[2026-03-20T19:54:38.651503Z] Loop 10549: Loss: 1.79e-02, Avg Return: 0.855, Regret: 0.0003, Entropy: 0.0984 +[2026-03-20T19:54:39.544201Z] Loop 10550: Loss: 1.89e-02, Avg Return: 0.858, Regret: 0.0054, Entropy: 0.0988 +[2026-03-20T19:54:40.398755Z] Loop 10551: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0054, Entropy: 0.0867 +[2026-03-20T19:54:41.252895Z] Loop 10552: Loss: 1.34e-02, Avg Return: 0.862, Regret: 0.0054, Entropy: 0.0787 +[2026-03-20T19:54:42.106662Z] Loop 10553: Loss: 1.44e-02, Avg Return: 0.864, Regret: 0.0054, Entropy: 0.0769 +[2026-03-20T19:54:42.959933Z] Loop 10554: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0054, Entropy: 0.0777 +[2026-03-20T19:54:43.812921Z] Loop 10555: Loss: 1.44e-02, Avg Return: 0.864, Regret: 0.0054, Entropy: 0.0741 +[2026-03-20T19:54:44.667735Z] Loop 10556: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0054, Entropy: 0.0727 +[2026-03-20T19:54:45.522218Z] Loop 10557: Loss: 1.48e-02, Avg Return: 0.864, Regret: 0.0054, Entropy: 0.0793 +[2026-03-20T19:54:46.376162Z] Loop 10558: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0054, Entropy: 0.0786 +[2026-03-20T19:54:47.229241Z] Loop 10559: Loss: 1.28e-02, Avg Return: 0.865, Regret: 0.0054, Entropy: 0.0689 +[2026-03-20T19:54:48.121191Z] Loop 10560: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0746 +[2026-03-20T19:54:48.976000Z] Loop 10561: Loss: 1.45e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0748 +[2026-03-20T19:54:49.830537Z] Loop 10562: Loss: 1.49e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0775 +[2026-03-20T19:54:50.683983Z] Loop 10563: Loss: 1.45e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0747 +[2026-03-20T19:54:51.537599Z] Loop 10564: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0757 +[2026-03-20T19:54:52.393299Z] Loop 10565: Loss: 1.39e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0776 +[2026-03-20T19:54:53.247605Z] Loop 10566: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0755 +[2026-03-20T19:54:54.102350Z] Loop 10567: Loss: 1.34e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0734 +[2026-03-20T19:54:54.958112Z] Loop 10568: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0754 +[2026-03-20T19:54:55.813822Z] Loop 10569: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0736 +[2026-03-20T19:54:56.707101Z] Loop 10570: Loss: 1.29e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0727 +[2026-03-20T19:54:57.562042Z] Loop 10571: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0773 +[2026-03-20T19:54:58.415998Z] Loop 10572: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0772 +[2026-03-20T19:54:59.269409Z] Loop 10573: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0744 +[2026-03-20T19:55:00.123276Z] Loop 10574: Loss: 1.42e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0754 +[2026-03-20T19:55:00.978659Z] Loop 10575: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0749 +[2026-03-20T19:55:01.833689Z] Loop 10576: Loss: 1.31e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0729 +[2026-03-20T19:55:02.688594Z] Loop 10577: Loss: 1.40e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0785 +[2026-03-20T19:55:03.543702Z] Loop 10578: Loss: 1.46e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0753 +[2026-03-20T19:55:04.398409Z] Loop 10579: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0800 +[2026-03-20T19:55:05.292442Z] Loop 10580: Loss: 1.35e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0739 +[2026-03-20T19:55:06.146548Z] Loop 10581: Loss: 1.36e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0740 +[2026-03-20T19:55:06.999662Z] Loop 10582: Loss: 1.41e-02, Avg Return: 0.861, Regret: 0.0005, Entropy: 0.0742 +[2026-03-20T19:55:07.854148Z] Loop 10583: Loss: 1.27e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0695 +[2026-03-20T19:55:08.708750Z] Loop 10584: Loss: 1.30e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0738 +[2026-03-20T19:55:09.563920Z] Loop 10585: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0702 +[2026-03-20T19:55:10.416920Z] Loop 10586: Loss: 1.31e-02, Avg Return: 0.865, Regret: 0.0005, Entropy: 0.0742 +[2026-03-20T19:55:11.270688Z] Loop 10587: Loss: 1.47e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0792 +[2026-03-20T19:55:12.125602Z] Loop 10588: Loss: 1.41e-02, Avg Return: 0.866, Regret: 0.0005, Entropy: 0.0759 +[2026-03-20T19:55:12.979594Z] Loop 10589: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0714 +[2026-03-20T19:55:13.871765Z] Loop 10590: Loss: 1.36e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0715 +[2026-03-20T19:55:14.726180Z] Loop 10591: Loss: 1.45e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0756 +[2026-03-20T19:55:15.580078Z] Loop 10592: Loss: 1.33e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0759 +[2026-03-20T19:55:16.434581Z] Loop 10593: Loss: 1.29e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0734 +[2026-03-20T19:55:17.288768Z] Loop 10594: Loss: 1.43e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0750 +[2026-03-20T19:55:18.142991Z] Loop 10595: Loss: 1.42e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0758 +[2026-03-20T19:55:18.998306Z] Loop 10596: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0723 +[2026-03-20T19:55:19.852685Z] Loop 10597: Loss: 1.36e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0748 +[2026-03-20T19:55:20.706294Z] Loop 10598: Loss: 1.30e-02, Avg Return: 0.865, Regret: 0.0002, Entropy: 0.0731 +[2026-03-20T19:55:21.560016Z] Loop 10599: Loss: 1.33e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0733 +[2026-03-20T19:55:22.454460Z] Loop 10600: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0758 +[2026-03-20T19:55:23.308552Z] Loop 10601: Loss: 1.39e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0744 +[2026-03-20T19:55:24.163235Z] Loop 10602: Loss: 1.39e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0746 +[2026-03-20T19:55:25.018052Z] Loop 10603: Loss: 1.29e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0712 +[2026-03-20T19:55:25.871673Z] Loop 10604: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0762 +[2026-03-20T19:55:26.725455Z] Loop 10605: Loss: 1.35e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0756 +[2026-03-20T19:55:27.581072Z] Loop 10606: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0771 +[2026-03-20T19:55:28.435564Z] Loop 10607: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0745 +[2026-03-20T19:55:29.289654Z] Loop 10608: Loss: 1.50e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.0787 +[2026-03-20T19:55:30.144036Z] Loop 10609: Loss: 1.42e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0768 +[2026-03-20T19:55:31.040632Z] Loop 10610: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.0809 +[2026-03-20T19:55:31.894548Z] Loop 10611: Loss: 1.36e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0729 +[2026-03-20T19:55:32.748626Z] Loop 10612: Loss: 1.41e-02, Avg Return: 0.860, Regret: 0.0020, Entropy: 0.0743 +[2026-03-20T19:55:33.602225Z] Loop 10613: Loss: 1.55e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.0805 +[2026-03-20T19:55:34.456194Z] Loop 10614: Loss: 1.44e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.0764 +[2026-03-20T19:55:35.310497Z] Loop 10615: Loss: 1.41e-02, Avg Return: 0.860, Regret: 0.0020, Entropy: 0.0757 +[2026-03-20T19:55:36.163872Z] Loop 10616: Loss: 1.65e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.0867 +[2026-03-20T19:55:37.017584Z] Loop 10617: Loss: 1.50e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.0824 +[2026-03-20T19:55:37.871927Z] Loop 10618: Loss: 1.41e-02, Avg Return: 0.860, Regret: 0.0020, Entropy: 0.0758 +[2026-03-20T19:55:38.726010Z] Loop 10619: Loss: 1.42e-02, Avg Return: 0.860, Regret: 0.0020, Entropy: 0.0756 +[2026-03-20T19:55:39.618658Z] Loop 10620: Loss: 1.45e-02, Avg Return: 0.860, Regret: 0.0027, Entropy: 0.0765 +[2026-03-20T19:55:40.472274Z] Loop 10621: Loss: 1.43e-02, Avg Return: 0.860, Regret: 0.0027, Entropy: 0.0773 +[2026-03-20T19:55:41.326278Z] Loop 10622: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0027, Entropy: 0.0790 +[2026-03-20T19:55:42.180038Z] Loop 10623: Loss: 1.43e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.0736 +[2026-03-20T19:55:43.034737Z] Loop 10624: Loss: 1.50e-02, Avg Return: 0.862, Regret: 0.0027, Entropy: 0.0771 +[2026-03-20T19:55:43.889122Z] Loop 10625: Loss: 1.43e-02, Avg Return: 0.864, Regret: 0.0027, Entropy: 0.0769 +[2026-03-20T19:55:44.742716Z] Loop 10626: Loss: 1.33e-02, Avg Return: 0.863, Regret: 0.0027, Entropy: 0.0719 +[2026-03-20T19:55:45.596801Z] Loop 10627: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0027, Entropy: 0.0729 +[2026-03-20T19:55:46.451349Z] Loop 10628: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0027, Entropy: 0.0728 +[2026-03-20T19:55:47.304644Z] Loop 10629: Loss: 1.35e-02, Avg Return: 0.864, Regret: 0.0027, Entropy: 0.0732 +[2026-03-20T19:55:48.195542Z] Loop 10630: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0712 +[2026-03-20T19:55:49.050372Z] Loop 10631: Loss: 1.27e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0709 +[2026-03-20T19:55:49.905405Z] Loop 10632: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0750 +[2026-03-20T19:55:50.759638Z] Loop 10633: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0751 +[2026-03-20T19:55:51.614352Z] Loop 10634: Loss: 1.24e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0716 +[2026-03-20T19:55:52.468938Z] Loop 10635: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0738 +[2026-03-20T19:55:53.322843Z] Loop 10636: Loss: 1.30e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0743 +[2026-03-20T19:55:54.177170Z] Loop 10637: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0763 +[2026-03-20T19:55:55.031401Z] Loop 10638: Loss: 1.26e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0708 +[2026-03-20T19:55:55.888562Z] Loop 10639: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0763 +[2026-03-20T19:55:56.780471Z] Loop 10640: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0799 +[2026-03-20T19:55:57.634341Z] Loop 10641: Loss: 1.45e-02, Avg Return: 0.859, Regret: 0.0020, Entropy: 0.0748 +[2026-03-20T19:55:58.489917Z] Loop 10642: Loss: 1.42e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.0743 +[2026-03-20T19:55:59.346303Z] Loop 10643: Loss: 1.50e-02, Avg Return: 0.860, Regret: 0.0020, Entropy: 0.0757 +[2026-03-20T19:56:00.200854Z] Loop 10644: Loss: 1.49e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.0789 +[2026-03-20T19:56:01.054680Z] Loop 10645: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0758 +[2026-03-20T19:56:01.910109Z] Loop 10646: Loss: 1.45e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0754 +[2026-03-20T19:56:02.764894Z] Loop 10647: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.0755 +[2026-03-20T19:56:03.618574Z] Loop 10648: Loss: 1.51e-02, Avg Return: 0.864, Regret: 0.0020, Entropy: 0.0798 +[2026-03-20T19:56:04.472119Z] Loop 10649: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0733 +[2026-03-20T19:56:05.364752Z] Loop 10650: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0692 +[2026-03-20T19:56:06.219654Z] Loop 10651: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0691 +[2026-03-20T19:56:07.074615Z] Loop 10652: Loss: 1.36e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0757 +[2026-03-20T19:56:07.929355Z] Loop 10653: Loss: 1.36e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0751 +[2026-03-20T19:56:08.784600Z] Loop 10654: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0755 +[2026-03-20T19:56:09.639817Z] Loop 10655: Loss: 1.42e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0752 +[2026-03-20T19:56:10.494973Z] Loop 10656: Loss: 1.50e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0757 +[2026-03-20T19:56:11.348943Z] Loop 10657: Loss: 1.41e-02, Avg Return: 0.865, Regret: 0.0006, Entropy: 0.0762 +[2026-03-20T19:56:12.203705Z] Loop 10658: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0760 +[2026-03-20T19:56:13.058210Z] Loop 10659: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0841 +[2026-03-20T19:56:13.950898Z] Loop 10660: Loss: 1.51e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0780 +[2026-03-20T19:56:14.805368Z] Loop 10661: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0805 +[2026-03-20T19:56:15.661344Z] Loop 10662: Loss: 1.48e-02, Avg Return: 0.861, Regret: 0.0003, Entropy: 0.0774 +[2026-03-20T19:56:16.514481Z] Loop 10663: Loss: 1.41e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0752 +[2026-03-20T19:56:17.368825Z] Loop 10664: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0777 +[2026-03-20T19:56:18.224151Z] Loop 10665: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0768 +[2026-03-20T19:56:19.079580Z] Loop 10666: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0789 +[2026-03-20T19:56:19.933424Z] Loop 10667: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0817 +[2026-03-20T19:56:20.787518Z] Loop 10668: Loss: 1.58e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0827 +[2026-03-20T19:56:21.642142Z] Loop 10669: Loss: 1.50e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0799 +[2026-03-20T19:56:22.535588Z] Loop 10670: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0761 +[2026-03-20T19:56:23.390653Z] Loop 10671: Loss: 1.51e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0808 +[2026-03-20T19:56:24.244774Z] Loop 10672: Loss: 1.46e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0792 +[2026-03-20T19:56:25.098436Z] Loop 10673: Loss: 1.39e-02, Avg Return: 0.861, Regret: 0.0004, Entropy: 0.0768 +[2026-03-20T19:56:25.953431Z] Loop 10674: Loss: 1.45e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0783 +[2026-03-20T19:56:26.807331Z] Loop 10675: Loss: 1.39e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0774 +[2026-03-20T19:56:27.661654Z] Loop 10676: Loss: 1.33e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0721 +[2026-03-20T19:56:28.516555Z] Loop 10677: Loss: 1.30e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0667 +[2026-03-20T19:56:29.371734Z] Loop 10678: Loss: 1.24e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0682 +[2026-03-20T19:56:30.226240Z] Loop 10679: Loss: 1.23e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0713 +[2026-03-20T19:56:31.120852Z] Loop 10680: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0724 +[2026-03-20T19:56:31.975146Z] Loop 10681: Loss: 1.29e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0697 +[2026-03-20T19:56:32.830859Z] Loop 10682: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0701 +[2026-03-20T19:56:33.686393Z] Loop 10683: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0697 +[2026-03-20T19:56:34.541325Z] Loop 10684: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0690 +[2026-03-20T19:56:35.395268Z] Loop 10685: Loss: 1.33e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0720 +[2026-03-20T19:56:36.249442Z] Loop 10686: Loss: 1.23e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0651 +[2026-03-20T19:56:37.103093Z] Loop 10687: Loss: 1.27e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0688 +[2026-03-20T19:56:37.956562Z] Loop 10688: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0703 +[2026-03-20T19:56:38.811023Z] Loop 10689: Loss: 1.32e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0723 +[2026-03-20T19:56:39.703874Z] Loop 10690: Loss: 1.25e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0683 +[2026-03-20T19:56:40.558525Z] Loop 10691: Loss: 1.15e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0663 +[2026-03-20T19:56:41.413486Z] Loop 10692: Loss: 1.31e-02, Avg Return: 0.865, Regret: 0.0004, Entropy: 0.0660 +[2026-03-20T19:56:42.269323Z] Loop 10693: Loss: 1.33e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0713 +[2026-03-20T19:56:43.124408Z] Loop 10694: Loss: 1.31e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0706 +[2026-03-20T19:56:43.977759Z] Loop 10695: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0722 +[2026-03-20T19:56:44.833785Z] Loop 10696: Loss: 1.30e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0706 +[2026-03-20T19:56:45.689509Z] Loop 10697: Loss: 1.29e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0700 +[2026-03-20T19:56:46.543970Z] Loop 10698: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0719 +[2026-03-20T19:56:47.397624Z] Loop 10699: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0685 +[2026-03-20T19:56:48.291419Z] Loop 10700: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0667 +[2026-03-20T19:56:49.146034Z] Loop 10701: Loss: 1.21e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0651 +[2026-03-20T19:56:50.000685Z] Loop 10702: Loss: 1.25e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0665 +[2026-03-20T19:56:50.855880Z] Loop 10703: Loss: 1.27e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0685 +[2026-03-20T19:56:51.709267Z] Loop 10704: Loss: 1.25e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0650 +[2026-03-20T19:56:52.562927Z] Loop 10705: Loss: 1.27e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0668 +[2026-03-20T19:56:53.418269Z] Loop 10706: Loss: 1.24e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0690 +[2026-03-20T19:56:54.272622Z] Loop 10707: Loss: 1.33e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0675 +[2026-03-20T19:56:55.127117Z] Loop 10708: Loss: 1.22e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0685 +[2026-03-20T19:56:55.981533Z] Loop 10709: Loss: 1.38e-02, Avg Return: 0.859, Regret: 0.0009, Entropy: 0.0716 +[2026-03-20T19:56:56.874762Z] Loop 10710: Loss: 1.28e-02, Avg Return: 0.862, Regret: 0.0026, Entropy: 0.0680 +[2026-03-20T19:56:57.728921Z] Loop 10711: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0026, Entropy: 0.0713 +[2026-03-20T19:56:58.583091Z] Loop 10712: Loss: 1.24e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.0685 +[2026-03-20T19:56:59.437533Z] Loop 10713: Loss: 1.36e-02, Avg Return: 0.859, Regret: 0.0026, Entropy: 0.0728 +[2026-03-20T19:57:00.291679Z] Loop 10714: Loss: 1.36e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.0733 +[2026-03-20T19:57:01.146262Z] Loop 10715: Loss: 1.22e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.0658 +[2026-03-20T19:57:02.000158Z] Loop 10716: Loss: 1.25e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.0674 +[2026-03-20T19:57:02.855460Z] Loop 10717: Loss: 1.30e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.0679 +[2026-03-20T19:57:03.710313Z] Loop 10718: Loss: 1.45e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.0770 +[2026-03-20T19:57:04.564186Z] Loop 10719: Loss: 1.36e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.0707 +[2026-03-20T19:57:05.456962Z] Loop 10720: Loss: 1.34e-02, Avg Return: 0.860, Regret: 0.0031, Entropy: 0.0707 +[2026-03-20T19:57:06.311483Z] Loop 10721: Loss: 1.22e-02, Avg Return: 0.860, Regret: 0.0031, Entropy: 0.0702 +[2026-03-20T19:57:07.164512Z] Loop 10722: Loss: 1.31e-02, Avg Return: 0.858, Regret: 0.0031, Entropy: 0.0697 +[2026-03-20T19:57:08.017834Z] Loop 10723: Loss: 1.29e-02, Avg Return: 0.860, Regret: 0.0031, Entropy: 0.0700 +[2026-03-20T19:57:08.872825Z] Loop 10724: Loss: 1.28e-02, Avg Return: 0.861, Regret: 0.0031, Entropy: 0.0673 +[2026-03-20T19:57:09.727029Z] Loop 10725: Loss: 1.40e-02, Avg Return: 0.862, Regret: 0.0031, Entropy: 0.0719 +[2026-03-20T19:57:10.580092Z] Loop 10726: Loss: 1.22e-02, Avg Return: 0.862, Regret: 0.0031, Entropy: 0.0679 +[2026-03-20T19:57:11.434629Z] Loop 10727: Loss: 1.23e-02, Avg Return: 0.862, Regret: 0.0031, Entropy: 0.0657 +[2026-03-20T19:57:12.291110Z] Loop 10728: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0031, Entropy: 0.0728 +[2026-03-20T19:57:13.146662Z] Loop 10729: Loss: 1.17e-02, Avg Return: 0.861, Regret: 0.0031, Entropy: 0.0650 +[2026-03-20T19:57:14.040819Z] Loop 10730: Loss: 1.15e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.0638 +[2026-03-20T19:57:14.894722Z] Loop 10731: Loss: 1.11e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0612 +[2026-03-20T19:57:15.749178Z] Loop 10732: Loss: 1.26e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0674 +[2026-03-20T19:57:16.604051Z] Loop 10733: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0684 +[2026-03-20T19:57:17.458558Z] Loop 10734: Loss: 1.14e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0628 +[2026-03-20T19:57:18.312475Z] Loop 10735: Loss: 1.24e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0645 +[2026-03-20T19:57:19.166838Z] Loop 10736: Loss: 1.16e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0654 +[2026-03-20T19:57:20.022774Z] Loop 10737: Loss: 1.25e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0654 +[2026-03-20T19:57:20.877895Z] Loop 10738: Loss: 1.20e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0639 +[2026-03-20T19:57:21.732979Z] Loop 10739: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0712 +[2026-03-20T19:57:22.628128Z] Loop 10740: Loss: 1.22e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0673 +[2026-03-20T19:57:23.482270Z] Loop 10741: Loss: 1.15e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0661 +[2026-03-20T19:57:24.337656Z] Loop 10742: Loss: 1.23e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0664 +[2026-03-20T19:57:25.193783Z] Loop 10743: Loss: 1.14e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0636 +[2026-03-20T19:57:26.050288Z] Loop 10744: Loss: 1.23e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0659 +[2026-03-20T19:57:26.905328Z] Loop 10745: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0644 +[2026-03-20T19:57:27.760211Z] Loop 10746: Loss: 1.15e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0650 +[2026-03-20T19:57:28.615465Z] Loop 10747: Loss: 1.23e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0665 +[2026-03-20T19:57:29.470186Z] Loop 10748: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0688 +[2026-03-20T19:57:30.324759Z] Loop 10749: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0721 +[2026-03-20T19:57:31.216308Z] Loop 10750: Loss: 1.26e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0705 +[2026-03-20T19:57:32.071116Z] Loop 10751: Loss: 1.34e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0706 +[2026-03-20T19:57:32.926224Z] Loop 10752: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0688 +[2026-03-20T19:57:33.781160Z] Loop 10753: Loss: 1.31e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0704 +[2026-03-20T19:57:34.635652Z] Loop 10754: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0670 +[2026-03-20T19:57:35.489373Z] Loop 10755: Loss: 1.28e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0703 +[2026-03-20T19:57:36.344957Z] Loop 10756: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0708 +[2026-03-20T19:57:37.201224Z] Loop 10757: Loss: 1.28e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0713 +[2026-03-20T19:57:38.055406Z] Loop 10758: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0713 +[2026-03-20T19:57:38.909843Z] Loop 10759: Loss: 1.27e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0695 +[2026-03-20T19:57:39.802985Z] Loop 10760: Loss: 1.29e-02, Avg Return: 0.865, Regret: 0.0006, Entropy: 0.0701 +[2026-03-20T19:57:40.656815Z] Loop 10761: Loss: 1.25e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0704 +[2026-03-20T19:57:41.511965Z] Loop 10762: Loss: 1.12e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0645 +[2026-03-20T19:57:42.366224Z] Loop 10763: Loss: 1.18e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0676 +[2026-03-20T19:57:43.220394Z] Loop 10764: Loss: 1.24e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0668 +[2026-03-20T19:57:44.075112Z] Loop 10765: Loss: 1.24e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0637 +[2026-03-20T19:57:44.929666Z] Loop 10766: Loss: 1.19e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0678 +[2026-03-20T19:57:45.784978Z] Loop 10767: Loss: 1.19e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0670 +[2026-03-20T19:57:46.639671Z] Loop 10768: Loss: 1.16e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.0624 +[2026-03-20T19:57:47.494293Z] Loop 10769: Loss: 1.28e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.0672 +[2026-03-20T19:57:48.387122Z] Loop 10770: Loss: 1.36e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.0712 +[2026-03-20T19:57:49.241739Z] Loop 10771: Loss: 1.35e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.0698 +[2026-03-20T19:57:50.095484Z] Loop 10772: Loss: 1.29e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.0689 +[2026-03-20T19:57:50.949693Z] Loop 10773: Loss: 1.30e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.0667 +[2026-03-20T19:57:51.803631Z] Loop 10774: Loss: 1.30e-02, Avg Return: 0.863, Regret: 0.0021, Entropy: 0.0647 +[2026-03-20T19:57:52.657597Z] Loop 10775: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0021, Entropy: 0.0680 +[2026-03-20T19:57:53.511619Z] Loop 10776: Loss: 1.31e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.0704 +[2026-03-20T19:57:54.365220Z] Loop 10777: Loss: 1.20e-02, Avg Return: 0.863, Regret: 0.0021, Entropy: 0.0664 +[2026-03-20T19:57:55.218733Z] Loop 10778: Loss: 1.21e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.0643 +[2026-03-20T19:57:56.072820Z] Loop 10779: Loss: 1.28e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.0674 +[2026-03-20T19:57:56.963767Z] Loop 10780: Loss: 1.15e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0651 +[2026-03-20T19:57:57.817717Z] Loop 10781: Loss: 1.18e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0662 +[2026-03-20T19:57:58.672508Z] Loop 10782: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0659 +[2026-03-20T19:57:59.527676Z] Loop 10783: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0668 +[2026-03-20T19:58:00.381090Z] Loop 10784: Loss: 1.21e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0661 +[2026-03-20T19:58:01.235950Z] Loop 10785: Loss: 1.20e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0669 +[2026-03-20T19:58:02.090885Z] Loop 10786: Loss: 1.19e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0670 +[2026-03-20T19:58:02.946276Z] Loop 10787: Loss: 1.22e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0694 +[2026-03-20T19:58:03.800420Z] Loop 10788: Loss: 1.16e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0620 +[2026-03-20T19:58:04.654858Z] Loop 10789: Loss: 1.23e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0692 +[2026-03-20T19:58:05.548212Z] Loop 10790: Loss: 1.13e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0632 +[2026-03-20T19:58:06.402409Z] Loop 10791: Loss: 1.25e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0717 +[2026-03-20T19:58:07.256087Z] Loop 10792: Loss: 1.12e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0642 +[2026-03-20T19:58:08.110395Z] Loop 10793: Loss: 1.22e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0667 +[2026-03-20T19:58:08.964279Z] Loop 10794: Loss: 1.25e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0672 +[2026-03-20T19:58:09.818636Z] Loop 10795: Loss: 1.17e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0627 +[2026-03-20T19:58:10.672937Z] Loop 10796: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0702 +[2026-03-20T19:58:11.528507Z] Loop 10797: Loss: 1.20e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0659 +[2026-03-20T19:58:12.383166Z] Loop 10798: Loss: 1.19e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0681 +[2026-03-20T19:58:13.237185Z] Loop 10799: Loss: 1.21e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0655 +[2026-03-20T19:58:14.130079Z] Loop 10800: Loss: 1.19e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0658 +[2026-03-20T19:58:14.984698Z] Loop 10801: Loss: 1.23e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0667 +[2026-03-20T19:58:15.840257Z] Loop 10802: Loss: 1.15e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0653 +[2026-03-20T19:58:16.695116Z] Loop 10803: Loss: 1.18e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0640 +[2026-03-20T19:58:17.548784Z] Loop 10804: Loss: 1.23e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0663 +[2026-03-20T19:58:18.403483Z] Loop 10805: Loss: 1.18e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0653 +[2026-03-20T19:58:19.258836Z] Loop 10806: Loss: 1.22e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0650 +[2026-03-20T19:58:20.113816Z] Loop 10807: Loss: 1.19e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0659 +[2026-03-20T19:58:20.967264Z] Loop 10808: Loss: 1.22e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0662 +[2026-03-20T19:58:21.820177Z] Loop 10809: Loss: 1.28e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0682 +[2026-03-20T19:58:22.713579Z] Loop 10810: Loss: 1.26e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0677 +[2026-03-20T19:58:23.567999Z] Loop 10811: Loss: 1.16e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0657 +[2026-03-20T19:58:24.422528Z] Loop 10812: Loss: 1.18e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0668 +[2026-03-20T19:58:25.276568Z] Loop 10813: Loss: 1.20e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0654 +[2026-03-20T19:58:26.130921Z] Loop 10814: Loss: 1.33e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0731 +[2026-03-20T19:58:26.987083Z] Loop 10815: Loss: 1.18e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.0671 +[2026-03-20T19:58:27.842460Z] Loop 10816: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0708 +[2026-03-20T19:58:28.696550Z] Loop 10817: Loss: 1.32e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0722 +[2026-03-20T19:58:29.551318Z] Loop 10818: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0739 +[2026-03-20T19:58:30.406436Z] Loop 10819: Loss: 1.45e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0767 +[2026-03-20T19:58:31.301608Z] Loop 10820: Loss: 1.45e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.0798 +[2026-03-20T19:58:32.155662Z] Loop 10821: Loss: 1.49e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.0790 +[2026-03-20T19:58:33.010030Z] Loop 10822: Loss: 1.50e-02, Avg Return: 0.860, Regret: 0.0024, Entropy: 0.0813 +[2026-03-20T19:58:33.864304Z] Loop 10823: Loss: 1.50e-02, Avg Return: 0.859, Regret: 0.0024, Entropy: 0.0822 +[2026-03-20T19:58:34.718423Z] Loop 10824: Loss: 1.31e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.0781 +[2026-03-20T19:58:35.573089Z] Loop 10825: Loss: 1.38e-02, Avg Return: 0.860, Regret: 0.0024, Entropy: 0.0764 +[2026-03-20T19:58:36.427593Z] Loop 10826: Loss: 1.35e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.0743 +[2026-03-20T19:58:37.281059Z] Loop 10827: Loss: 1.21e-02, Avg Return: 0.864, Regret: 0.0024, Entropy: 0.0669 +[2026-03-20T19:58:38.134741Z] Loop 10828: Loss: 1.33e-02, Avg Return: 0.863, Regret: 0.0024, Entropy: 0.0682 +[2026-03-20T19:58:38.988608Z] Loop 10829: Loss: 1.37e-02, Avg Return: 0.864, Regret: 0.0024, Entropy: 0.0724 +[2026-03-20T19:58:39.880727Z] Loop 10830: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0692 +[2026-03-20T19:58:40.734281Z] Loop 10831: Loss: 1.24e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0660 +[2026-03-20T19:58:41.587509Z] Loop 10832: Loss: 1.11e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0640 +[2026-03-20T19:58:42.441664Z] Loop 10833: Loss: 1.23e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0679 +[2026-03-20T19:58:43.296164Z] Loop 10834: Loss: 1.25e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0675 +[2026-03-20T19:58:44.150468Z] Loop 10835: Loss: 1.16e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0631 +[2026-03-20T19:58:45.004778Z] Loop 10836: Loss: 1.24e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0660 +[2026-03-20T19:58:45.859929Z] Loop 10837: Loss: 1.19e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0654 +[2026-03-20T19:58:46.714099Z] Loop 10838: Loss: 1.22e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0649 +[2026-03-20T19:58:47.568463Z] Loop 10839: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0702 +[2026-03-20T19:58:48.459013Z] Loop 10840: Loss: 1.20e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.0665 +[2026-03-20T19:58:49.312735Z] Loop 10841: Loss: 1.18e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.0646 +[2026-03-20T19:58:50.167175Z] Loop 10842: Loss: 1.22e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.0670 +[2026-03-20T19:58:51.020498Z] Loop 10843: Loss: 1.29e-02, Avg Return: 0.860, Regret: 0.0024, Entropy: 0.0721 +[2026-03-20T19:58:51.874308Z] Loop 10844: Loss: 1.31e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.0687 +[2026-03-20T19:58:52.728531Z] Loop 10845: Loss: 1.34e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.0701 +[2026-03-20T19:58:53.582810Z] Loop 10846: Loss: 1.20e-02, Avg Return: 0.863, Regret: 0.0024, Entropy: 0.0674 +[2026-03-20T19:58:54.436134Z] Loop 10847: Loss: 1.19e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.0691 +[2026-03-20T19:58:55.290373Z] Loop 10848: Loss: 1.23e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.0673 +[2026-03-20T19:58:56.142977Z] Loop 10849: Loss: 1.19e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.0645 +[2026-03-20T19:58:57.034837Z] Loop 10850: Loss: 1.15e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.0651 +[2026-03-20T19:58:57.888131Z] Loop 10851: Loss: 1.14e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.0650 +[2026-03-20T19:58:58.742161Z] Loop 10852: Loss: 1.20e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0646 +[2026-03-20T19:58:59.595498Z] Loop 10853: Loss: 1.32e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0661 +[2026-03-20T19:59:00.448684Z] Loop 10854: Loss: 1.19e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0677 +[2026-03-20T19:59:01.303237Z] Loop 10855: Loss: 1.10e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0600 +[2026-03-20T19:59:02.156679Z] Loop 10856: Loss: 1.18e-02, Avg Return: 0.863, Regret: 0.0022, Entropy: 0.0636 +[2026-03-20T19:59:03.011868Z] Loop 10857: Loss: 1.25e-02, Avg Return: 0.863, Regret: 0.0022, Entropy: 0.0675 +[2026-03-20T19:59:03.864769Z] Loop 10858: Loss: 1.34e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0676 +[2026-03-20T19:59:04.717468Z] Loop 10859: Loss: 1.13e-02, Avg Return: 0.863, Regret: 0.0022, Entropy: 0.0642 +[2026-03-20T19:59:05.611525Z] Loop 10860: Loss: 1.24e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0681 +[2026-03-20T19:59:06.466878Z] Loop 10861: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0644 +[2026-03-20T19:59:07.321468Z] Loop 10862: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0683 +[2026-03-20T19:59:08.175496Z] Loop 10863: Loss: 1.36e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0701 +[2026-03-20T19:59:09.029468Z] Loop 10864: Loss: 1.25e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0646 +[2026-03-20T19:59:09.885030Z] Loop 10865: Loss: 1.31e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0684 +[2026-03-20T19:59:10.740541Z] Loop 10866: Loss: 1.19e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0651 +[2026-03-20T19:59:11.594411Z] Loop 10867: Loss: 1.23e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0644 +[2026-03-20T19:59:12.448393Z] Loop 10868: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0722 +[2026-03-20T19:59:13.302792Z] Loop 10869: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0708 +[2026-03-20T19:59:14.195399Z] Loop 10870: Loss: 1.57e-02, Avg Return: 0.865, Regret: 0.0003, Entropy: 0.0802 +[2026-03-20T19:59:15.049910Z] Loop 10871: Loss: 1.45e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0772 +[2026-03-20T19:59:15.903441Z] Loop 10872: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0760 +[2026-03-20T19:59:16.757532Z] Loop 10873: Loss: 1.64e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0822 +[2026-03-20T19:59:17.612080Z] Loop 10874: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0809 +[2026-03-20T19:59:18.467131Z] Loop 10875: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0828 +[2026-03-20T19:59:19.320487Z] Loop 10876: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0840 +[2026-03-20T19:59:20.173981Z] Loop 10877: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0831 +[2026-03-20T19:59:21.028197Z] Loop 10878: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0806 +[2026-03-20T19:59:21.883100Z] Loop 10879: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0841 +[2026-03-20T19:59:22.775171Z] Loop 10880: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0852 +[2026-03-20T19:59:23.628841Z] Loop 10881: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0824 +[2026-03-20T19:59:24.483916Z] Loop 10882: Loss: 1.63e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0823 +[2026-03-20T19:59:25.338692Z] Loop 10883: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0809 +[2026-03-20T19:59:26.192910Z] Loop 10884: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0761 +[2026-03-20T19:59:27.047385Z] Loop 10885: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0755 +[2026-03-20T19:59:27.902760Z] Loop 10886: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0693 +[2026-03-20T19:59:28.756467Z] Loop 10887: Loss: 1.30e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0691 +[2026-03-20T19:59:29.610978Z] Loop 10888: Loss: 1.25e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0658 +[2026-03-20T19:59:30.464710Z] Loop 10889: Loss: 1.27e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0681 +[2026-03-20T19:59:31.363392Z] Loop 10890: Loss: 1.34e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0699 +[2026-03-20T19:59:32.216872Z] Loop 10891: Loss: 1.31e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0704 +[2026-03-20T19:59:33.071571Z] Loop 10892: Loss: 1.30e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0711 +[2026-03-20T19:59:33.926127Z] Loop 10893: Loss: 1.26e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0676 +[2026-03-20T19:59:34.780279Z] Loop 10894: Loss: 1.10e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0623 +[2026-03-20T19:59:35.634362Z] Loop 10895: Loss: 1.22e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0620 +[2026-03-20T19:59:36.489244Z] Loop 10896: Loss: 1.25e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0677 +[2026-03-20T19:59:37.343901Z] Loop 10897: Loss: 1.19e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0645 +[2026-03-20T19:59:38.198951Z] Loop 10898: Loss: 1.22e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0664 +[2026-03-20T19:59:39.052385Z] Loop 10899: Loss: 1.12e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0623 +[2026-03-20T19:59:39.946491Z] Loop 10900: Loss: 1.17e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0618 +[2026-03-20T19:59:40.801958Z] Loop 10901: Loss: 1.20e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0653 +[2026-03-20T19:59:41.656813Z] Loop 10902: Loss: 1.15e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0628 +[2026-03-20T19:59:42.510560Z] Loop 10903: Loss: 1.11e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0620 +[2026-03-20T19:59:43.364655Z] Loop 10904: Loss: 1.11e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0607 +[2026-03-20T19:59:44.220227Z] Loop 10905: Loss: 1.12e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0613 +[2026-03-20T19:59:45.075208Z] Loop 10906: Loss: 1.14e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0630 +[2026-03-20T19:59:45.930046Z] Loop 10907: Loss: 1.19e-02, Avg Return: 0.861, Regret: 0.0005, Entropy: 0.0626 +[2026-03-20T19:59:46.783873Z] Loop 10908: Loss: 1.12e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0638 +[2026-03-20T19:59:47.639085Z] Loop 10909: Loss: 1.20e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0632 +[2026-03-20T19:59:48.532242Z] Loop 10910: Loss: 1.29e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0689 +[2026-03-20T19:59:49.386506Z] Loop 10911: Loss: 1.19e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0648 +[2026-03-20T19:59:50.241211Z] Loop 10912: Loss: 1.20e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0636 +[2026-03-20T19:59:51.096079Z] Loop 10913: Loss: 1.24e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0703 +[2026-03-20T19:59:51.951581Z] Loop 10914: Loss: 1.24e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0698 +[2026-03-20T19:59:52.805994Z] Loop 10915: Loss: 1.21e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0667 +[2026-03-20T19:59:53.660777Z] Loop 10916: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0730 +[2026-03-20T19:59:54.514771Z] Loop 10917: Loss: 1.26e-02, Avg Return: 0.860, Regret: 0.0018, Entropy: 0.0700 +[2026-03-20T19:59:55.368810Z] Loop 10918: Loss: 1.37e-02, Avg Return: 0.859, Regret: 0.0018, Entropy: 0.0730 +[2026-03-20T19:59:56.223069Z] Loop 10919: Loss: 1.41e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0745 +[2026-03-20T19:59:57.115044Z] Loop 10920: Loss: 1.35e-02, Avg Return: 0.860, Regret: 0.0032, Entropy: 0.0714 +[2026-03-20T19:59:57.969469Z] Loop 10921: Loss: 1.25e-02, Avg Return: 0.862, Regret: 0.0032, Entropy: 0.0668 +[2026-03-20T19:59:58.822956Z] Loop 10922: Loss: 1.26e-02, Avg Return: 0.861, Regret: 0.0032, Entropy: 0.0664 +[2026-03-20T19:59:59.676521Z] Loop 10923: Loss: 1.08e-02, Avg Return: 0.862, Regret: 0.0032, Entropy: 0.0615 +[2026-03-20T20:00:00.531103Z] Loop 10924: Loss: 1.15e-02, Avg Return: 0.863, Regret: 0.0032, Entropy: 0.0632 +[2026-03-20T20:00:01.386249Z] Loop 10925: Loss: 1.14e-02, Avg Return: 0.862, Regret: 0.0032, Entropy: 0.0630 +[2026-03-20T20:00:02.240141Z] Loop 10926: Loss: 1.04e-02, Avg Return: 0.862, Regret: 0.0032, Entropy: 0.0598 +[2026-03-20T20:00:03.094621Z] Loop 10927: Loss: 1.15e-02, Avg Return: 0.863, Regret: 0.0032, Entropy: 0.0633 +[2026-03-20T20:00:03.948470Z] Loop 10928: Loss: 1.07e-02, Avg Return: 0.863, Regret: 0.0032, Entropy: 0.0599 +[2026-03-20T20:00:04.803594Z] Loop 10929: Loss: 1.23e-02, Avg Return: 0.863, Regret: 0.0032, Entropy: 0.0611 +[2026-03-20T20:00:05.695746Z] Loop 10930: Loss: 1.12e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0626 +[2026-03-20T20:00:06.549319Z] Loop 10931: Loss: 1.12e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0631 +[2026-03-20T20:00:07.403247Z] Loop 10932: Loss: 1.06e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0601 +[2026-03-20T20:00:08.258461Z] Loop 10933: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0631 +[2026-03-20T20:00:09.112769Z] Loop 10934: Loss: 1.07e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0601 +[2026-03-20T20:00:09.966439Z] Loop 10935: Loss: 1.14e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0604 +[2026-03-20T20:00:10.820590Z] Loop 10936: Loss: 1.17e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0641 +[2026-03-20T20:00:11.676398Z] Loop 10937: Loss: 1.19e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0636 +[2026-03-20T20:00:12.531040Z] Loop 10938: Loss: 1.12e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0621 +[2026-03-20T20:00:13.385193Z] Loop 10939: Loss: 1.19e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0660 +[2026-03-20T20:00:14.277592Z] Loop 10940: Loss: 1.20e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0630 +[2026-03-20T20:00:15.132917Z] Loop 10941: Loss: 1.07e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0620 +[2026-03-20T20:00:15.988200Z] Loop 10942: Loss: 1.16e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0655 +[2026-03-20T20:00:16.843483Z] Loop 10943: Loss: 1.24e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0651 +[2026-03-20T20:00:17.698734Z] Loop 10944: Loss: 1.20e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0630 +[2026-03-20T20:00:18.553400Z] Loop 10945: Loss: 1.15e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0611 +[2026-03-20T20:00:19.408327Z] Loop 10946: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0659 +[2026-03-20T20:00:20.262185Z] Loop 10947: Loss: 1.13e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0624 +[2026-03-20T20:00:21.116118Z] Loop 10948: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0664 +[2026-03-20T20:00:21.970725Z] Loop 10949: Loss: 1.13e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0641 +[2026-03-20T20:00:22.862732Z] Loop 10950: Loss: 1.23e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0660 +[2026-03-20T20:00:23.716990Z] Loop 10951: Loss: 1.20e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0662 +[2026-03-20T20:00:24.571715Z] Loop 10952: Loss: 1.30e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0683 +[2026-03-20T20:00:25.426781Z] Loop 10953: Loss: 1.29e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0686 +[2026-03-20T20:00:26.281249Z] Loop 10954: Loss: 1.04e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0629 +[2026-03-20T20:00:27.135620Z] Loop 10955: Loss: 1.24e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0675 +[2026-03-20T20:00:27.990711Z] Loop 10956: Loss: 1.24e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0677 +[2026-03-20T20:00:28.845668Z] Loop 10957: Loss: 1.24e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0686 +[2026-03-20T20:00:29.699321Z] Loop 10958: Loss: 1.28e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0717 +[2026-03-20T20:00:30.552753Z] Loop 10959: Loss: 1.17e-02, Avg Return: 0.861, Regret: 0.0005, Entropy: 0.0664 +[2026-03-20T20:00:31.445209Z] Loop 10960: Loss: 1.32e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0683 +[2026-03-20T20:00:32.299587Z] Loop 10961: Loss: 1.29e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0713 +[2026-03-20T20:00:33.153221Z] Loop 10962: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0703 +[2026-03-20T20:00:34.007397Z] Loop 10963: Loss: 1.17e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0651 +[2026-03-20T20:00:34.862054Z] Loop 10964: Loss: 1.15e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0684 +[2026-03-20T20:00:35.716307Z] Loop 10965: Loss: 1.31e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0709 +[2026-03-20T20:00:36.571003Z] Loop 10966: Loss: 1.25e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0670 +[2026-03-20T20:00:37.424337Z] Loop 10967: Loss: 1.25e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0686 +[2026-03-20T20:00:38.278929Z] Loop 10968: Loss: 1.36e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0705 +[2026-03-20T20:00:39.132659Z] Loop 10969: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0716 +[2026-03-20T20:00:40.026528Z] Loop 10970: Loss: 1.29e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0707 +[2026-03-20T20:00:40.880762Z] Loop 10971: Loss: 1.25e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0703 +[2026-03-20T20:00:41.734439Z] Loop 10972: Loss: 1.30e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0707 +[2026-03-20T20:00:42.588774Z] Loop 10973: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0695 +[2026-03-20T20:00:43.442822Z] Loop 10974: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0703 +[2026-03-20T20:00:44.296434Z] Loop 10975: Loss: 1.18e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0703 +[2026-03-20T20:00:45.149583Z] Loop 10976: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0763 +[2026-03-20T20:00:46.003102Z] Loop 10977: Loss: 1.38e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0770 +[2026-03-20T20:00:46.857698Z] Loop 10978: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0810 +[2026-03-20T20:00:47.713113Z] Loop 10979: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0772 +[2026-03-20T20:00:48.607782Z] Loop 10980: Loss: 1.48e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.0810 +[2026-03-20T20:00:49.460354Z] Loop 10981: Loss: 1.49e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.0789 +[2026-03-20T20:00:50.313405Z] Loop 10982: Loss: 1.54e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0804 +[2026-03-20T20:00:51.168739Z] Loop 10983: Loss: 1.33e-02, Avg Return: 0.864, Regret: 0.0025, Entropy: 0.0731 +[2026-03-20T20:00:52.023521Z] Loop 10984: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0025, Entropy: 0.0717 +[2026-03-20T20:00:52.877021Z] Loop 10985: Loss: 1.24e-02, Avg Return: 0.863, Regret: 0.0025, Entropy: 0.0677 +[2026-03-20T20:00:53.731065Z] Loop 10986: Loss: 1.31e-02, Avg Return: 0.866, Regret: 0.0025, Entropy: 0.0715 +[2026-03-20T20:00:54.585991Z] Loop 10987: Loss: 1.22e-02, Avg Return: 0.864, Regret: 0.0025, Entropy: 0.0663 +[2026-03-20T20:00:55.440982Z] Loop 10988: Loss: 1.28e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0671 +[2026-03-20T20:00:56.294478Z] Loop 10989: Loss: 1.32e-02, Avg Return: 0.864, Regret: 0.0025, Entropy: 0.0708 +[2026-03-20T20:00:57.186590Z] Loop 10990: Loss: 1.20e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0687 +[2026-03-20T20:00:58.041051Z] Loop 10991: Loss: 1.24e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0667 +[2026-03-20T20:00:58.895801Z] Loop 10992: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0689 +[2026-03-20T20:00:59.749963Z] Loop 10993: Loss: 1.26e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0686 +[2026-03-20T20:01:00.603420Z] Loop 10994: Loss: 1.24e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0661 +[2026-03-20T20:01:01.457538Z] Loop 10995: Loss: 1.29e-02, Avg Return: 0.866, Regret: 0.0001, Entropy: 0.0701 +[2026-03-20T20:01:02.311861Z] Loop 10996: Loss: 1.23e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0671 +[2026-03-20T20:01:03.166603Z] Loop 10997: Loss: 1.25e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0667 +[2026-03-20T20:01:04.021122Z] Loop 10998: Loss: 1.23e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0689 +[2026-03-20T20:01:04.876592Z] Loop 10999: Loss: 1.36e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0712 +[2026-03-20T20:01:05.770470Z] Loop 11000: Loss: 1.26e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0687 +[2026-03-20T20:01:06.625237Z] Loop 11001: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0719 +[2026-03-20T20:01:07.478668Z] Loop 11002: Loss: 1.21e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0638 +[2026-03-20T20:01:08.333040Z] Loop 11003: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0716 +[2026-03-20T20:01:09.186599Z] Loop 11004: Loss: 1.32e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0741 +[2026-03-20T20:01:10.040758Z] Loop 11005: Loss: 1.28e-02, Avg Return: 0.865, Regret: 0.0002, Entropy: 0.0683 +[2026-03-20T20:01:10.895055Z] Loop 11006: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0712 +[2026-03-20T20:01:11.749454Z] Loop 11007: Loss: 1.37e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0729 +[2026-03-20T20:01:12.602540Z] Loop 11008: Loss: 1.40e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0749 +[2026-03-20T20:01:13.456016Z] Loop 11009: Loss: 1.57e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0764 +[2026-03-20T20:01:14.348885Z] Loop 11010: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0784 +[2026-03-20T20:01:15.202708Z] Loop 11011: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0797 +[2026-03-20T20:01:16.057203Z] Loop 11012: Loss: 1.43e-02, Avg Return: 0.861, Regret: 0.0003, Entropy: 0.0781 +[2026-03-20T20:01:16.911030Z] Loop 11013: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0807 +[2026-03-20T20:01:17.766327Z] Loop 11014: Loss: 1.48e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0774 +[2026-03-20T20:01:18.622333Z] Loop 11015: Loss: 1.61e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0848 +[2026-03-20T20:01:19.478638Z] Loop 11016: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0826 +[2026-03-20T20:01:20.333586Z] Loop 11017: Loss: 1.57e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0828 +[2026-03-20T20:01:21.189351Z] Loop 11018: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0811 +[2026-03-20T20:01:22.045625Z] Loop 11019: Loss: 1.77e-02, Avg Return: 0.859, Regret: 0.0003, Entropy: 0.0859 +[2026-03-20T20:01:22.939746Z] Loop 11020: Loss: 1.60e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.0824 +[2026-03-20T20:01:23.793911Z] Loop 11021: Loss: 1.61e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.0865 +[2026-03-20T20:01:24.649549Z] Loop 11022: Loss: 1.72e-02, Avg Return: 0.860, Regret: 0.0028, Entropy: 0.0864 +[2026-03-20T20:01:25.505237Z] Loop 11023: Loss: 1.67e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.0842 +[2026-03-20T20:01:26.359372Z] Loop 11024: Loss: 1.69e-02, Avg Return: 0.860, Regret: 0.0028, Entropy: 0.0915 +[2026-03-20T20:01:27.214004Z] Loop 11025: Loss: 1.58e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.0845 +[2026-03-20T20:01:28.067877Z] Loop 11026: Loss: 1.75e-02, Avg Return: 0.864, Regret: 0.0028, Entropy: 0.0894 +[2026-03-20T20:01:28.922867Z] Loop 11027: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.0822 +[2026-03-20T20:01:29.776582Z] Loop 11028: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0028, Entropy: 0.0865 +[2026-03-20T20:01:30.631094Z] Loop 11029: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0028, Entropy: 0.0852 +[2026-03-20T20:01:31.524338Z] Loop 11030: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0842 +[2026-03-20T20:01:32.378788Z] Loop 11031: Loss: 1.50e-02, Avg Return: 0.861, Regret: 0.0005, Entropy: 0.0803 +[2026-03-20T20:01:33.233028Z] Loop 11032: Loss: 1.48e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0793 +[2026-03-20T20:01:34.087275Z] Loop 11033: Loss: 1.52e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0809 +[2026-03-20T20:01:34.942292Z] Loop 11034: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0831 +[2026-03-20T20:01:35.795431Z] Loop 11035: Loss: 1.54e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0845 +[2026-03-20T20:01:36.648773Z] Loop 11036: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0814 +[2026-03-20T20:01:37.503161Z] Loop 11037: Loss: 1.58e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0836 +[2026-03-20T20:01:38.358427Z] Loop 11038: Loss: 1.53e-02, Avg Return: 0.860, Regret: 0.0005, Entropy: 0.0817 +[2026-03-20T20:01:39.212776Z] Loop 11039: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0831 +[2026-03-20T20:01:40.105470Z] Loop 11040: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0794 +[2026-03-20T20:01:40.958932Z] Loop 11041: Loss: 1.51e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0771 +[2026-03-20T20:01:41.814165Z] Loop 11042: Loss: 1.34e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0728 +[2026-03-20T20:01:42.669104Z] Loop 11043: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0705 +[2026-03-20T20:01:43.523365Z] Loop 11044: Loss: 1.26e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0634 +[2026-03-20T20:01:44.377551Z] Loop 11045: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0663 +[2026-03-20T20:01:45.232610Z] Loop 11046: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0618 +[2026-03-20T20:01:46.087928Z] Loop 11047: Loss: 1.30e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0685 +[2026-03-20T20:01:46.942976Z] Loop 11048: Loss: 1.20e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0681 +[2026-03-20T20:01:47.796947Z] Loop 11049: Loss: 1.26e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0665 +[2026-03-20T20:01:48.690214Z] Loop 11050: Loss: 1.37e-02, Avg Return: 0.865, Regret: 0.0001, Entropy: 0.0710 +[2026-03-20T20:01:49.544262Z] Loop 11051: Loss: 1.37e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0699 +[2026-03-20T20:01:50.398983Z] Loop 11052: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0695 +[2026-03-20T20:01:51.252411Z] Loop 11053: Loss: 1.24e-02, Avg Return: 0.865, Regret: 0.0001, Entropy: 0.0653 +[2026-03-20T20:01:52.106646Z] Loop 11054: Loss: 1.24e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0663 +[2026-03-20T20:01:52.961740Z] Loop 11055: Loss: 1.38e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0705 +[2026-03-20T20:01:53.817027Z] Loop 11056: Loss: 1.31e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0674 +[2026-03-20T20:01:54.670713Z] Loop 11057: Loss: 1.28e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0676 +[2026-03-20T20:01:55.524394Z] Loop 11058: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0674 +[2026-03-20T20:01:56.377904Z] Loop 11059: Loss: 1.27e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0713 +[2026-03-20T20:01:57.271894Z] Loop 11060: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0744 +[2026-03-20T20:01:58.126299Z] Loop 11061: Loss: 1.44e-02, Avg Return: 0.860, Regret: 0.0018, Entropy: 0.0740 +[2026-03-20T20:01:58.980241Z] Loop 11062: Loss: 1.41e-02, Avg Return: 0.858, Regret: 0.0018, Entropy: 0.0728 +[2026-03-20T20:01:59.834400Z] Loop 11063: Loss: 1.53e-02, Avg Return: 0.856, Regret: 0.0018, Entropy: 0.0759 +[2026-03-20T20:02:00.688753Z] Loop 11064: Loss: 1.36e-02, Avg Return: 0.858, Regret: 0.0018, Entropy: 0.0758 +[2026-03-20T20:02:01.543662Z] Loop 11065: Loss: 1.46e-02, Avg Return: 0.860, Regret: 0.0018, Entropy: 0.0761 +[2026-03-20T20:02:02.398041Z] Loop 11066: Loss: 1.46e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0728 +[2026-03-20T20:02:03.251257Z] Loop 11067: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0666 +[2026-03-20T20:02:04.104630Z] Loop 11068: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0682 +[2026-03-20T20:02:04.959624Z] Loop 11069: Loss: 1.30e-02, Avg Return: 0.864, Regret: 0.0018, Entropy: 0.0727 +[2026-03-20T20:02:05.851613Z] Loop 11070: Loss: 1.32e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0698 +[2026-03-20T20:02:06.706295Z] Loop 11071: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0682 +[2026-03-20T20:02:07.560983Z] Loop 11072: Loss: 1.31e-02, Avg Return: 0.865, Regret: 0.0003, Entropy: 0.0715 +[2026-03-20T20:02:08.417153Z] Loop 11073: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0672 +[2026-03-20T20:02:09.271693Z] Loop 11074: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0759 +[2026-03-20T20:02:10.125432Z] Loop 11075: Loss: 1.36e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0704 +[2026-03-20T20:02:10.979396Z] Loop 11076: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0746 +[2026-03-20T20:02:11.833923Z] Loop 11077: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0722 +[2026-03-20T20:02:12.688872Z] Loop 11078: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0752 +[2026-03-20T20:02:13.542955Z] Loop 11079: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0797 +[2026-03-20T20:02:14.436165Z] Loop 11080: Loss: 1.56e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0782 +[2026-03-20T20:02:15.291727Z] Loop 11081: Loss: 1.40e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0741 +[2026-03-20T20:02:16.146095Z] Loop 11082: Loss: 1.43e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0730 +[2026-03-20T20:02:17.000149Z] Loop 11083: Loss: 1.56e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0819 +[2026-03-20T20:02:17.854901Z] Loop 11084: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0815 +[2026-03-20T20:02:18.709672Z] Loop 11085: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0831 +[2026-03-20T20:02:19.564067Z] Loop 11086: Loss: 1.48e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0806 +[2026-03-20T20:02:20.419884Z] Loop 11087: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0778 +[2026-03-20T20:02:21.274579Z] Loop 11088: Loss: 1.75e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0916 +[2026-03-20T20:02:22.130113Z] Loop 11089: Loss: 1.70e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0863 +[2026-03-20T20:02:23.026816Z] Loop 11090: Loss: 1.69e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0853 +[2026-03-20T20:02:23.881409Z] Loop 11091: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0861 +[2026-03-20T20:02:24.735420Z] Loop 11092: Loss: 1.75e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0893 +[2026-03-20T20:02:25.590199Z] Loop 11093: Loss: 1.73e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0917 +[2026-03-20T20:02:26.444788Z] Loop 11094: Loss: 1.68e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0879 +[2026-03-20T20:02:27.299407Z] Loop 11095: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0869 +[2026-03-20T20:02:28.155058Z] Loop 11096: Loss: 1.67e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0874 +[2026-03-20T20:02:29.010574Z] Loop 11097: Loss: 1.43e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0760 +[2026-03-20T20:02:29.865484Z] Loop 11098: Loss: 1.38e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0762 +[2026-03-20T20:02:30.720287Z] Loop 11099: Loss: 1.36e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0736 +[2026-03-20T20:02:31.617640Z] Loop 11100: Loss: 1.33e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0748 +[2026-03-20T20:02:32.472864Z] Loop 11101: Loss: 1.33e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0735 +[2026-03-20T20:02:33.327475Z] Loop 11102: Loss: 1.44e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0774 +[2026-03-20T20:02:34.181623Z] Loop 11103: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0760 +[2026-03-20T20:02:35.035310Z] Loop 11104: Loss: 1.40e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0725 +[2026-03-20T20:02:35.890809Z] Loop 11105: Loss: 1.24e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0710 +[2026-03-20T20:02:36.747206Z] Loop 11106: Loss: 1.33e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0723 +[2026-03-20T20:02:37.601077Z] Loop 11107: Loss: 1.37e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.0725 +[2026-03-20T20:02:38.454484Z] Loop 11108: Loss: 1.27e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0717 +[2026-03-20T20:02:39.309638Z] Loop 11109: Loss: 1.44e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0771 +[2026-03-20T20:02:40.202033Z] Loop 11110: Loss: 1.29e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0713 +[2026-03-20T20:02:41.056294Z] Loop 11111: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0772 +[2026-03-20T20:02:41.910145Z] Loop 11112: Loss: 1.46e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0822 +[2026-03-20T20:02:42.765428Z] Loop 11113: Loss: 1.43e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0792 +[2026-03-20T20:02:43.619862Z] Loop 11114: Loss: 1.43e-02, Avg Return: 0.860, Regret: 0.0010, Entropy: 0.0796 +[2026-03-20T20:02:44.474451Z] Loop 11115: Loss: 1.41e-02, Avg Return: 0.860, Regret: 0.0010, Entropy: 0.0772 +[2026-03-20T20:02:45.328492Z] Loop 11116: Loss: 1.40e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0766 +[2026-03-20T20:02:46.181807Z] Loop 11117: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0724 +[2026-03-20T20:02:47.035784Z] Loop 11118: Loss: 1.34e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0758 +[2026-03-20T20:02:47.889886Z] Loop 11119: Loss: 1.27e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0725 +[2026-03-20T20:02:48.784394Z] Loop 11120: Loss: 1.29e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0714 +[2026-03-20T20:02:49.637555Z] Loop 11121: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0717 +[2026-03-20T20:02:50.491313Z] Loop 11122: Loss: 1.27e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0698 +[2026-03-20T20:02:51.345676Z] Loop 11123: Loss: 1.24e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0684 +[2026-03-20T20:02:52.200256Z] Loop 11124: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0703 +[2026-03-20T20:02:53.054136Z] Loop 11125: Loss: 1.29e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0709 +[2026-03-20T20:02:53.906432Z] Loop 11126: Loss: 1.33e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0737 +[2026-03-20T20:02:54.759654Z] Loop 11127: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0787 +[2026-03-20T20:02:55.614592Z] Loop 11128: Loss: 1.40e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0737 +[2026-03-20T20:02:56.468523Z] Loop 11129: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0748 +[2026-03-20T20:02:57.362017Z] Loop 11130: Loss: 1.30e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0705 +[2026-03-20T20:02:58.215313Z] Loop 11131: Loss: 1.56e-02, Avg Return: 0.860, Regret: 0.0019, Entropy: 0.0828 +[2026-03-20T20:02:59.069798Z] Loop 11132: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0829 +[2026-03-20T20:02:59.923506Z] Loop 11133: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0747 +[2026-03-20T20:03:00.777361Z] Loop 11134: Loss: 1.38e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0743 +[2026-03-20T20:03:01.631370Z] Loop 11135: Loss: 1.39e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0742 +[2026-03-20T20:03:02.485120Z] Loop 11136: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0019, Entropy: 0.0693 +[2026-03-20T20:03:03.338999Z] Loop 11137: Loss: 1.36e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0718 +[2026-03-20T20:03:04.193106Z] Loop 11138: Loss: 1.37e-02, Avg Return: 0.864, Regret: 0.0019, Entropy: 0.0739 +[2026-03-20T20:03:05.047131Z] Loop 11139: Loss: 1.21e-02, Avg Return: 0.864, Regret: 0.0019, Entropy: 0.0698 +[2026-03-20T20:03:05.939208Z] Loop 11140: Loss: 1.34e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0740 +[2026-03-20T20:03:06.793173Z] Loop 11141: Loss: 1.35e-02, Avg Return: 0.865, Regret: 0.0003, Entropy: 0.0751 +[2026-03-20T20:03:07.647304Z] Loop 11142: Loss: 1.23e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0707 +[2026-03-20T20:03:08.501589Z] Loop 11143: Loss: 1.29e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0711 +[2026-03-20T20:03:09.355861Z] Loop 11144: Loss: 1.29e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0706 +[2026-03-20T20:03:10.209947Z] Loop 11145: Loss: 1.31e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0728 +[2026-03-20T20:03:11.064722Z] Loop 11146: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0695 +[2026-03-20T20:03:11.919200Z] Loop 11147: Loss: 1.20e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0690 +[2026-03-20T20:03:12.773971Z] Loop 11148: Loss: 1.31e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0722 +[2026-03-20T20:03:13.628105Z] Loop 11149: Loss: 1.17e-02, Avg Return: 0.861, Regret: 0.0003, Entropy: 0.0665 +[2026-03-20T20:03:14.521435Z] Loop 11150: Loss: 1.33e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0722 +[2026-03-20T20:03:15.374527Z] Loop 11151: Loss: 1.36e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0723 +[2026-03-20T20:03:16.230207Z] Loop 11152: Loss: 1.47e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.0757 +[2026-03-20T20:03:17.083821Z] Loop 11153: Loss: 1.43e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0758 +[2026-03-20T20:03:17.936686Z] Loop 11154: Loss: 1.35e-02, Avg Return: 0.860, Regret: 0.0025, Entropy: 0.0724 +[2026-03-20T20:03:18.790847Z] Loop 11155: Loss: 1.41e-02, Avg Return: 0.860, Regret: 0.0025, Entropy: 0.0758 +[2026-03-20T20:03:19.645212Z] Loop 11156: Loss: 1.38e-02, Avg Return: 0.860, Regret: 0.0025, Entropy: 0.0750 +[2026-03-20T20:03:20.499452Z] Loop 11157: Loss: 1.37e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.0777 +[2026-03-20T20:03:21.352764Z] Loop 11158: Loss: 1.42e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0702 +[2026-03-20T20:03:22.206583Z] Loop 11159: Loss: 1.42e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0740 +[2026-03-20T20:03:23.098866Z] Loop 11160: Loss: 1.42e-02, Avg Return: 0.864, Regret: 0.0013, Entropy: 0.0752 +[2026-03-20T20:03:23.953447Z] Loop 11161: Loss: 1.44e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0754 +[2026-03-20T20:03:24.806736Z] Loop 11162: Loss: 1.42e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0796 +[2026-03-20T20:03:25.660154Z] Loop 11163: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0813 +[2026-03-20T20:03:26.514562Z] Loop 11164: Loss: 1.58e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0798 +[2026-03-20T20:03:27.368758Z] Loop 11165: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0825 +[2026-03-20T20:03:28.222368Z] Loop 11166: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0860 +[2026-03-20T20:03:29.076088Z] Loop 11167: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0826 +[2026-03-20T20:03:29.929687Z] Loop 11168: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0833 +[2026-03-20T20:03:30.783939Z] Loop 11169: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0874 +[2026-03-20T20:03:31.676825Z] Loop 11170: Loss: 1.58e-02, Avg Return: 0.864, Regret: 0.0013, Entropy: 0.0828 +[2026-03-20T20:03:32.530380Z] Loop 11171: Loss: 1.50e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0805 +[2026-03-20T20:03:33.383900Z] Loop 11172: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0836 +[2026-03-20T20:03:34.237773Z] Loop 11173: Loss: 1.73e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0915 +[2026-03-20T20:03:35.092271Z] Loop 11174: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0852 +[2026-03-20T20:03:35.947311Z] Loop 11175: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0876 +[2026-03-20T20:03:36.799827Z] Loop 11176: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0886 +[2026-03-20T20:03:37.653093Z] Loop 11177: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0881 +[2026-03-20T20:03:38.506870Z] Loop 11178: Loss: 1.72e-02, Avg Return: 0.864, Regret: 0.0013, Entropy: 0.0882 +[2026-03-20T20:03:39.361852Z] Loop 11179: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0941 +[2026-03-20T20:03:40.252901Z] Loop 11180: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0929 +[2026-03-20T20:03:41.106917Z] Loop 11181: Loss: 1.76e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0912 +[2026-03-20T20:03:41.960602Z] Loop 11182: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0974 +[2026-03-20T20:03:42.815812Z] Loop 11183: Loss: 1.89e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0958 +[2026-03-20T20:03:43.669814Z] Loop 11184: Loss: 1.91e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0986 +[2026-03-20T20:03:44.523192Z] Loop 11185: Loss: 1.85e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0959 +[2026-03-20T20:03:45.376918Z] Loop 11186: Loss: 1.80e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0984 +[2026-03-20T20:03:46.231438Z] Loop 11187: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0982 +[2026-03-20T20:03:47.085454Z] Loop 11188: Loss: 1.87e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0978 +[2026-03-20T20:03:47.939159Z] Loop 11189: Loss: 1.86e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.1012 +[2026-03-20T20:03:48.830679Z] Loop 11190: Loss: 1.90e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.1008 +[2026-03-20T20:03:49.684630Z] Loop 11191: Loss: 2.03e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.1052 +[2026-03-20T20:03:50.538832Z] Loop 11192: Loss: 1.89e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.1007 +[2026-03-20T20:03:51.392692Z] Loop 11193: Loss: 1.93e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.1009 +[2026-03-20T20:03:52.247397Z] Loop 11194: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0958 +[2026-03-20T20:03:53.102028Z] Loop 11195: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0929 +[2026-03-20T20:03:53.956697Z] Loop 11196: Loss: 1.70e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0913 +[2026-03-20T20:03:54.811097Z] Loop 11197: Loss: 1.84e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.1011 +[2026-03-20T20:03:55.664456Z] Loop 11198: Loss: 1.73e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0955 +[2026-03-20T20:03:56.518107Z] Loop 11199: Loss: 1.95e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.1000 +[2026-03-20T20:03:57.411059Z] Loop 11200: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0968 +[2026-03-20T20:03:58.266253Z] Loop 11201: Loss: 1.86e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0988 +[2026-03-20T20:03:59.120575Z] Loop 11202: Loss: 1.75e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0966 +[2026-03-20T20:03:59.974284Z] Loop 11203: Loss: 1.76e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0930 +[2026-03-20T20:04:00.828558Z] Loop 11204: Loss: 1.81e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0971 +[2026-03-20T20:04:01.682992Z] Loop 11205: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0945 +[2026-03-20T20:04:02.538001Z] Loop 11206: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0956 +[2026-03-20T20:04:03.391565Z] Loop 11207: Loss: 1.83e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0987 +[2026-03-20T20:04:04.244934Z] Loop 11208: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0958 +[2026-03-20T20:04:05.098938Z] Loop 11209: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0907 +[2026-03-20T20:04:05.992546Z] Loop 11210: Loss: 1.77e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0948 +[2026-03-20T20:04:06.847356Z] Loop 11211: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0869 +[2026-03-20T20:04:07.701063Z] Loop 11212: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0873 +[2026-03-20T20:04:08.555149Z] Loop 11213: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0877 +[2026-03-20T20:04:09.410814Z] Loop 11214: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0872 +[2026-03-20T20:04:10.265138Z] Loop 11215: Loss: 1.69e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0880 +[2026-03-20T20:04:11.118319Z] Loop 11216: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0820 +[2026-03-20T20:04:11.972302Z] Loop 11217: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0790 +[2026-03-20T20:04:12.826825Z] Loop 11218: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0792 +[2026-03-20T20:04:13.681749Z] Loop 11219: Loss: 1.34e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0719 +[2026-03-20T20:04:14.573253Z] Loop 11220: Loss: 1.32e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0725 +[2026-03-20T20:04:15.426996Z] Loop 11221: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0755 +[2026-03-20T20:04:16.280769Z] Loop 11222: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0737 +[2026-03-20T20:04:17.134955Z] Loop 11223: Loss: 1.33e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0687 +[2026-03-20T20:04:17.989577Z] Loop 11224: Loss: 1.29e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0736 +[2026-03-20T20:04:18.844122Z] Loop 11225: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0689 +[2026-03-20T20:04:19.698310Z] Loop 11226: Loss: 1.24e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0676 +[2026-03-20T20:04:20.552622Z] Loop 11227: Loss: 1.29e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0672 +[2026-03-20T20:04:21.407881Z] Loop 11228: Loss: 1.18e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0677 +[2026-03-20T20:04:22.262512Z] Loop 11229: Loss: 1.14e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0640 +[2026-03-20T20:04:23.154802Z] Loop 11230: Loss: 1.17e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0651 +[2026-03-20T20:04:24.009029Z] Loop 11231: Loss: 1.23e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0695 +[2026-03-20T20:04:24.863531Z] Loop 11232: Loss: 1.21e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0665 +[2026-03-20T20:04:25.717894Z] Loop 11233: Loss: 1.26e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0665 +[2026-03-20T20:04:26.572456Z] Loop 11234: Loss: 1.17e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0643 +[2026-03-20T20:04:27.426883Z] Loop 11235: Loss: 1.49e-02, Avg Return: 0.860, Regret: 0.0006, Entropy: 0.0779 +[2026-03-20T20:04:28.281052Z] Loop 11236: Loss: 1.54e-02, Avg Return: 0.860, Regret: 0.0006, Entropy: 0.0786 +[2026-03-20T20:04:29.135788Z] Loop 11237: Loss: 1.50e-02, Avg Return: 0.858, Regret: 0.0006, Entropy: 0.0834 +[2026-03-20T20:04:29.990501Z] Loop 11238: Loss: 1.40e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.0792 +[2026-03-20T20:04:30.843830Z] Loop 11239: Loss: 1.59e-02, Avg Return: 0.858, Regret: 0.0006, Entropy: 0.0787 +[2026-03-20T20:04:31.736137Z] Loop 11240: Loss: 1.38e-02, Avg Return: 0.859, Regret: 0.0043, Entropy: 0.0749 +[2026-03-20T20:04:32.590098Z] Loop 11241: Loss: 1.40e-02, Avg Return: 0.859, Regret: 0.0043, Entropy: 0.0736 +[2026-03-20T20:04:33.444386Z] Loop 11242: Loss: 1.31e-02, Avg Return: 0.860, Regret: 0.0043, Entropy: 0.0711 +[2026-03-20T20:04:34.299250Z] Loop 11243: Loss: 1.26e-02, Avg Return: 0.860, Regret: 0.0043, Entropy: 0.0720 +[2026-03-20T20:04:35.153297Z] Loop 11244: Loss: 1.19e-02, Avg Return: 0.861, Regret: 0.0043, Entropy: 0.0664 +[2026-03-20T20:04:36.008683Z] Loop 11245: Loss: 1.14e-02, Avg Return: 0.861, Regret: 0.0043, Entropy: 0.0655 +[2026-03-20T20:04:36.864031Z] Loop 11246: Loss: 1.29e-02, Avg Return: 0.861, Regret: 0.0043, Entropy: 0.0708 +[2026-03-20T20:04:37.718855Z] Loop 11247: Loss: 1.15e-02, Avg Return: 0.862, Regret: 0.0043, Entropy: 0.0672 +[2026-03-20T20:04:38.572740Z] Loop 11248: Loss: 1.21e-02, Avg Return: 0.862, Regret: 0.0043, Entropy: 0.0672 +[2026-03-20T20:04:39.427987Z] Loop 11249: Loss: 1.19e-02, Avg Return: 0.863, Regret: 0.0043, Entropy: 0.0649 +[2026-03-20T20:04:40.321042Z] Loop 11250: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0669 +[2026-03-20T20:04:41.175451Z] Loop 11251: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0667 +[2026-03-20T20:04:42.029620Z] Loop 11252: Loss: 1.28e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0701 +[2026-03-20T20:04:42.884222Z] Loop 11253: Loss: 1.31e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0691 +[2026-03-20T20:04:43.738144Z] Loop 11254: Loss: 1.16e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0646 +[2026-03-20T20:04:44.592566Z] Loop 11255: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0681 +[2026-03-20T20:04:45.446344Z] Loop 11256: Loss: 1.21e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0653 +[2026-03-20T20:04:46.299422Z] Loop 11257: Loss: 1.30e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0674 +[2026-03-20T20:04:47.152932Z] Loop 11258: Loss: 1.21e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0682 +[2026-03-20T20:04:48.007066Z] Loop 11259: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0727 +[2026-03-20T20:04:48.900324Z] Loop 11260: Loss: 1.34e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0693 +[2026-03-20T20:04:49.754670Z] Loop 11261: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0729 +[2026-03-20T20:04:50.607996Z] Loop 11262: Loss: 1.37e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0722 +[2026-03-20T20:04:51.462485Z] Loop 11263: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0763 +[2026-03-20T20:04:52.316675Z] Loop 11264: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0746 +[2026-03-20T20:04:53.171517Z] Loop 11265: Loss: 1.35e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0722 +[2026-03-20T20:04:54.025056Z] Loop 11266: Loss: 1.28e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0736 +[2026-03-20T20:04:54.878582Z] Loop 11267: Loss: 1.36e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0721 +[2026-03-20T20:04:55.733397Z] Loop 11268: Loss: 1.39e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0743 +[2026-03-20T20:04:56.588483Z] Loop 11269: Loss: 1.45e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0761 +[2026-03-20T20:04:57.480961Z] Loop 11270: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0760 +[2026-03-20T20:04:58.334990Z] Loop 11271: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0803 +[2026-03-20T20:04:59.190550Z] Loop 11272: Loss: 1.59e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0846 +[2026-03-20T20:05:00.046177Z] Loop 11273: Loss: 1.53e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0852 +[2026-03-20T20:05:00.901377Z] Loop 11274: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0843 +[2026-03-20T20:05:01.756365Z] Loop 11275: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0890 +[2026-03-20T20:05:02.613423Z] Loop 11276: Loss: 1.60e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0874 +[2026-03-20T20:05:03.468166Z] Loop 11277: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0886 +[2026-03-20T20:05:04.323880Z] Loop 11278: Loss: 1.60e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0822 +[2026-03-20T20:05:05.178362Z] Loop 11279: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0829 +[2026-03-20T20:05:06.071553Z] Loop 11280: Loss: 1.52e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0786 +[2026-03-20T20:05:06.924933Z] Loop 11281: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0776 +[2026-03-20T20:05:07.779476Z] Loop 11282: Loss: 1.32e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0698 +[2026-03-20T20:05:08.634317Z] Loop 11283: Loss: 1.39e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0725 +[2026-03-20T20:05:09.488253Z] Loop 11284: Loss: 1.30e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0692 +[2026-03-20T20:05:10.341470Z] Loop 11285: Loss: 1.39e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0715 +[2026-03-20T20:05:11.196607Z] Loop 11286: Loss: 1.34e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0715 +[2026-03-20T20:05:12.051871Z] Loop 11287: Loss: 1.30e-02, Avg Return: 0.865, Regret: 0.0002, Entropy: 0.0681 +[2026-03-20T20:05:12.907617Z] Loop 11288: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0711 +[2026-03-20T20:05:13.760709Z] Loop 11289: Loss: 1.39e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0728 +[2026-03-20T20:05:14.653021Z] Loop 11290: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0719 +[2026-03-20T20:05:15.507970Z] Loop 11291: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0739 +[2026-03-20T20:05:16.362299Z] Loop 11292: Loss: 1.25e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0699 +[2026-03-20T20:05:17.216927Z] Loop 11293: Loss: 1.32e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0723 +[2026-03-20T20:05:18.070843Z] Loop 11294: Loss: 1.30e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0703 +[2026-03-20T20:05:18.925400Z] Loop 11295: Loss: 1.24e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0682 +[2026-03-20T20:05:19.779170Z] Loop 11296: Loss: 1.27e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0694 +[2026-03-20T20:05:20.633803Z] Loop 11297: Loss: 1.22e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0679 +[2026-03-20T20:05:21.487162Z] Loop 11298: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0705 +[2026-03-20T20:05:22.340993Z] Loop 11299: Loss: 1.18e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0656 +[2026-03-20T20:05:23.232314Z] Loop 11300: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0737 +[2026-03-20T20:05:24.087065Z] Loop 11301: Loss: 1.23e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0689 +[2026-03-20T20:05:24.942347Z] Loop 11302: Loss: 1.23e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0674 +[2026-03-20T20:05:25.797420Z] Loop 11303: Loss: 1.30e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0722 +[2026-03-20T20:05:26.651343Z] Loop 11304: Loss: 1.22e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0692 +[2026-03-20T20:05:27.505745Z] Loop 11305: Loss: 1.39e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0735 +[2026-03-20T20:05:28.360047Z] Loop 11306: Loss: 1.37e-02, Avg Return: 0.865, Regret: 0.0004, Entropy: 0.0739 +[2026-03-20T20:05:29.213542Z] Loop 11307: Loss: 1.39e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0765 +[2026-03-20T20:05:30.066722Z] Loop 11308: Loss: 1.45e-02, Avg Return: 0.861, Regret: 0.0004, Entropy: 0.0751 +[2026-03-20T20:05:30.920200Z] Loop 11309: Loss: 1.31e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0706 +[2026-03-20T20:05:31.813515Z] Loop 11310: Loss: 1.49e-02, Avg Return: 0.860, Regret: 0.0029, Entropy: 0.0786 +[2026-03-20T20:05:32.668236Z] Loop 11311: Loss: 1.42e-02, Avg Return: 0.860, Regret: 0.0029, Entropy: 0.0761 +[2026-03-20T20:05:33.522506Z] Loop 11312: Loss: 1.41e-02, Avg Return: 0.859, Regret: 0.0029, Entropy: 0.0767 +[2026-03-20T20:05:34.376660Z] Loop 11313: Loss: 1.50e-02, Avg Return: 0.859, Regret: 0.0029, Entropy: 0.0779 +[2026-03-20T20:05:35.230987Z] Loop 11314: Loss: 1.50e-02, Avg Return: 0.860, Regret: 0.0029, Entropy: 0.0768 +[2026-03-20T20:05:36.086307Z] Loop 11315: Loss: 1.43e-02, Avg Return: 0.862, Regret: 0.0029, Entropy: 0.0775 +[2026-03-20T20:05:36.939475Z] Loop 11316: Loss: 1.33e-02, Avg Return: 0.863, Regret: 0.0029, Entropy: 0.0744 +[2026-03-20T20:05:37.793080Z] Loop 11317: Loss: 1.30e-02, Avg Return: 0.862, Regret: 0.0029, Entropy: 0.0707 +[2026-03-20T20:05:38.647578Z] Loop 11318: Loss: 1.32e-02, Avg Return: 0.861, Regret: 0.0029, Entropy: 0.0706 +[2026-03-20T20:05:39.502218Z] Loop 11319: Loss: 1.36e-02, Avg Return: 0.864, Regret: 0.0029, Entropy: 0.0726 +[2026-03-20T20:05:40.395445Z] Loop 11320: Loss: 1.42e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0721 +[2026-03-20T20:05:41.248263Z] Loop 11321: Loss: 1.46e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0796 +[2026-03-20T20:05:42.102557Z] Loop 11322: Loss: 1.29e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0720 +[2026-03-20T20:05:42.956787Z] Loop 11323: Loss: 1.20e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0693 +[2026-03-20T20:05:43.811125Z] Loop 11324: Loss: 1.28e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0672 +[2026-03-20T20:05:44.664181Z] Loop 11325: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0692 +[2026-03-20T20:05:45.517902Z] Loop 11326: Loss: 1.28e-02, Avg Return: 0.865, Regret: 0.0006, Entropy: 0.0724 +[2026-03-20T20:05:46.372777Z] Loop 11327: Loss: 1.25e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0664 +[2026-03-20T20:05:47.228257Z] Loop 11328: Loss: 1.32e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0723 +[2026-03-20T20:05:48.082052Z] Loop 11329: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0729 +[2026-03-20T20:05:48.974563Z] Loop 11330: Loss: 1.30e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0708 +[2026-03-20T20:05:49.828391Z] Loop 11331: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0782 +[2026-03-20T20:05:50.683326Z] Loop 11332: Loss: 1.37e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0727 +[2026-03-20T20:05:51.537147Z] Loop 11333: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0762 +[2026-03-20T20:05:52.392111Z] Loop 11334: Loss: 1.35e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0728 +[2026-03-20T20:05:53.246140Z] Loop 11335: Loss: 1.36e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0727 +[2026-03-20T20:05:54.100643Z] Loop 11336: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0752 +[2026-03-20T20:05:54.955928Z] Loop 11337: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0810 +[2026-03-20T20:05:55.810852Z] Loop 11338: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0799 +[2026-03-20T20:05:56.664872Z] Loop 11339: Loss: 1.39e-02, Avg Return: 0.860, Regret: 0.0003, Entropy: 0.0761 +[2026-03-20T20:05:57.557953Z] Loop 11340: Loss: 1.40e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.0776 +[2026-03-20T20:05:58.413582Z] Loop 11341: Loss: 1.46e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.0800 +[2026-03-20T20:05:59.267929Z] Loop 11342: Loss: 1.42e-02, Avg Return: 0.862, Regret: 0.0027, Entropy: 0.0774 +[2026-03-20T20:06:00.122284Z] Loop 11343: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0027, Entropy: 0.0822 +[2026-03-20T20:06:00.976019Z] Loop 11344: Loss: 1.47e-02, Avg Return: 0.860, Regret: 0.0027, Entropy: 0.0818 +[2026-03-20T20:06:01.831405Z] Loop 11345: Loss: 1.43e-02, Avg Return: 0.862, Regret: 0.0027, Entropy: 0.0776 +[2026-03-20T20:06:02.685711Z] Loop 11346: Loss: 1.35e-02, Avg Return: 0.862, Regret: 0.0027, Entropy: 0.0766 +[2026-03-20T20:06:03.539119Z] Loop 11347: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0027, Entropy: 0.0756 +[2026-03-20T20:06:04.392003Z] Loop 11348: Loss: 1.45e-02, Avg Return: 0.862, Regret: 0.0027, Entropy: 0.0791 +[2026-03-20T20:06:05.245451Z] Loop 11349: Loss: 1.21e-02, Avg Return: 0.862, Regret: 0.0027, Entropy: 0.0714 +[2026-03-20T20:06:06.140438Z] Loop 11350: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0751 +[2026-03-20T20:06:06.995494Z] Loop 11351: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0748 +[2026-03-20T20:06:07.849723Z] Loop 11352: Loss: 1.29e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0710 +[2026-03-20T20:06:08.704028Z] Loop 11353: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0720 +[2026-03-20T20:06:09.558781Z] Loop 11354: Loss: 1.40e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0763 +[2026-03-20T20:06:10.412256Z] Loop 11355: Loss: 1.25e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0730 +[2026-03-20T20:06:11.266265Z] Loop 11356: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0760 +[2026-03-20T20:06:12.120534Z] Loop 11357: Loss: 1.22e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0725 +[2026-03-20T20:06:12.973875Z] Loop 11358: Loss: 1.40e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0762 +[2026-03-20T20:06:13.828091Z] Loop 11359: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0787 +[2026-03-20T20:06:14.720283Z] Loop 11360: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0773 +[2026-03-20T20:06:15.574496Z] Loop 11361: Loss: 1.47e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.0818 +[2026-03-20T20:06:16.427570Z] Loop 11362: Loss: 1.48e-02, Avg Return: 0.860, Regret: 0.0015, Entropy: 0.0800 +[2026-03-20T20:06:17.280721Z] Loop 11363: Loss: 1.71e-02, Avg Return: 0.860, Regret: 0.0015, Entropy: 0.0871 +[2026-03-20T20:06:18.135544Z] Loop 11364: Loss: 1.61e-02, Avg Return: 0.859, Regret: 0.0015, Entropy: 0.0831 +[2026-03-20T20:06:18.989692Z] Loop 11365: Loss: 1.36e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0760 +[2026-03-20T20:06:19.843268Z] Loop 11366: Loss: 1.51e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.0799 +[2026-03-20T20:06:20.696855Z] Loop 11367: Loss: 1.31e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0720 +[2026-03-20T20:06:21.550734Z] Loop 11368: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0707 +[2026-03-20T20:06:22.404868Z] Loop 11369: Loss: 1.37e-02, Avg Return: 0.864, Regret: 0.0015, Entropy: 0.0744 +[2026-03-20T20:06:23.297895Z] Loop 11370: Loss: 1.35e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0693 +[2026-03-20T20:06:24.152506Z] Loop 11371: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0679 +[2026-03-20T20:06:25.007732Z] Loop 11372: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0686 +[2026-03-20T20:06:25.863124Z] Loop 11373: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0698 +[2026-03-20T20:06:26.718737Z] Loop 11374: Loss: 1.25e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0718 +[2026-03-20T20:06:27.573702Z] Loop 11375: Loss: 1.25e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0702 +[2026-03-20T20:06:28.428926Z] Loop 11376: Loss: 1.30e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0691 +[2026-03-20T20:06:29.284319Z] Loop 11377: Loss: 1.32e-02, Avg Return: 0.861, Regret: 0.0005, Entropy: 0.0728 +[2026-03-20T20:06:30.140123Z] Loop 11378: Loss: 1.23e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0715 +[2026-03-20T20:06:30.995695Z] Loop 11379: Loss: 1.29e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0694 +[2026-03-20T20:06:31.891550Z] Loop 11380: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0706 +[2026-03-20T20:06:32.746294Z] Loop 11381: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0672 +[2026-03-20T20:06:33.601003Z] Loop 11382: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0696 +[2026-03-20T20:06:34.455718Z] Loop 11383: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0737 +[2026-03-20T20:06:35.311251Z] Loop 11384: Loss: 1.27e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0672 +[2026-03-20T20:06:36.165372Z] Loop 11385: Loss: 1.20e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0669 +[2026-03-20T20:06:37.020312Z] Loop 11386: Loss: 1.30e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0677 +[2026-03-20T20:06:37.875247Z] Loop 11387: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0677 +[2026-03-20T20:06:38.729665Z] Loop 11388: Loss: 1.18e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0653 +[2026-03-20T20:06:39.582965Z] Loop 11389: Loss: 1.34e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0668 +[2026-03-20T20:06:40.474270Z] Loop 11390: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0677 +[2026-03-20T20:06:41.328978Z] Loop 11391: Loss: 1.19e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0645 +[2026-03-20T20:06:42.183800Z] Loop 11392: Loss: 1.09e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0624 +[2026-03-20T20:06:43.037988Z] Loop 11393: Loss: 1.32e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0691 +[2026-03-20T20:06:43.892221Z] Loop 11394: Loss: 1.38e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0696 +[2026-03-20T20:06:44.746509Z] Loop 11395: Loss: 1.30e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0734 +[2026-03-20T20:06:45.602755Z] Loop 11396: Loss: 1.32e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0701 +[2026-03-20T20:06:46.457334Z] Loop 11397: Loss: 1.28e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0699 +[2026-03-20T20:06:47.310965Z] Loop 11398: Loss: 1.42e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0712 +[2026-03-20T20:06:48.163980Z] Loop 11399: Loss: 1.28e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0691 +[2026-03-20T20:06:49.057504Z] Loop 11400: Loss: 1.34e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0671 +[2026-03-20T20:06:49.911819Z] Loop 11401: Loss: 1.15e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0640 +[2026-03-20T20:06:50.768053Z] Loop 11402: Loss: 1.11e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0629 +[2026-03-20T20:06:51.622861Z] Loop 11403: Loss: 1.15e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0646 +[2026-03-20T20:06:52.477660Z] Loop 11404: Loss: 1.26e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0695 +[2026-03-20T20:06:53.332311Z] Loop 11405: Loss: 1.14e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0629 +[2026-03-20T20:06:54.187731Z] Loop 11406: Loss: 1.20e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0662 +[2026-03-20T20:06:55.041500Z] Loop 11407: Loss: 1.23e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0659 +[2026-03-20T20:06:55.896094Z] Loop 11408: Loss: 1.13e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0670 +[2026-03-20T20:06:56.751764Z] Loop 11409: Loss: 1.12e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0643 +[2026-03-20T20:06:57.647218Z] Loop 11410: Loss: 1.22e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0667 +[2026-03-20T20:06:58.501209Z] Loop 11411: Loss: 1.17e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0661 +[2026-03-20T20:06:59.355417Z] Loop 11412: Loss: 1.27e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0661 +[2026-03-20T20:07:00.209433Z] Loop 11413: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0661 +[2026-03-20T20:07:01.063627Z] Loop 11414: Loss: 1.15e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0633 +[2026-03-20T20:07:01.917815Z] Loop 11415: Loss: 1.21e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0653 +[2026-03-20T20:07:02.771623Z] Loop 11416: Loss: 1.22e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0662 +[2026-03-20T20:07:03.625023Z] Loop 11417: Loss: 1.30e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0667 +[2026-03-20T20:07:04.478822Z] Loop 11418: Loss: 1.14e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0655 +[2026-03-20T20:07:05.333438Z] Loop 11419: Loss: 1.25e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0633 +[2026-03-20T20:07:06.226368Z] Loop 11420: Loss: 1.23e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0647 +[2026-03-20T20:07:07.079399Z] Loop 11421: Loss: 1.24e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0666 +[2026-03-20T20:07:07.933148Z] Loop 11422: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0701 +[2026-03-20T20:07:08.787929Z] Loop 11423: Loss: 1.34e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0685 +[2026-03-20T20:07:09.643627Z] Loop 11424: Loss: 1.24e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0671 +[2026-03-20T20:07:10.498124Z] Loop 11425: Loss: 1.35e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0701 +[2026-03-20T20:07:11.351754Z] Loop 11426: Loss: 1.22e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0643 +[2026-03-20T20:07:12.205834Z] Loop 11427: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0733 +[2026-03-20T20:07:13.061915Z] Loop 11428: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0707 +[2026-03-20T20:07:13.916307Z] Loop 11429: Loss: 1.43e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0715 +[2026-03-20T20:07:14.808174Z] Loop 11430: Loss: 1.48e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0788 +[2026-03-20T20:07:15.661732Z] Loop 11431: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0857 +[2026-03-20T20:07:16.517764Z] Loop 11432: Loss: 1.64e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0855 +[2026-03-20T20:07:17.372330Z] Loop 11433: Loss: 1.77e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0913 +[2026-03-20T20:07:18.226575Z] Loop 11434: Loss: 1.99e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.1000 +[2026-03-20T20:07:19.082102Z] Loop 11435: Loss: 2.14e-02, Avg Return: 0.860, Regret: 0.0007, Entropy: 0.1073 +[2026-03-20T20:07:19.936105Z] Loop 11436: Loss: 2.26e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.1138 +[2026-03-20T20:07:20.790322Z] Loop 11437: Loss: 2.25e-02, Avg Return: 0.860, Regret: 0.0007, Entropy: 0.1140 +[2026-03-20T20:07:21.644024Z] Loop 11438: Loss: 2.04e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.1062 +[2026-03-20T20:07:22.497291Z] Loop 11439: Loss: 2.26e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.1126 +[2026-03-20T20:07:23.388927Z] Loop 11440: Loss: 2.37e-02, Avg Return: 0.861, Regret: 0.0032, Entropy: 0.1235 +[2026-03-20T20:07:24.242854Z] Loop 11441: Loss: 2.54e-02, Avg Return: 0.859, Regret: 0.0032, Entropy: 0.1301 +[2026-03-20T20:07:25.096151Z] Loop 11442: Loss: 2.59e-02, Avg Return: 0.858, Regret: 0.0032, Entropy: 0.1326 +[2026-03-20T20:07:25.949453Z] Loop 11443: Loss: 2.58e-02, Avg Return: 0.855, Regret: 0.0032, Entropy: 0.1387 +[2026-03-20T20:07:26.803503Z] Loop 11444: Loss: 2.89e-02, Avg Return: 0.853, Regret: 0.0032, Entropy: 0.1496 +[2026-03-20T20:07:27.657733Z] Loop 11445: Loss: 2.82e-02, Avg Return: 0.852, Regret: 0.0032, Entropy: 0.1529 +[2026-03-20T20:07:28.512353Z] Loop 11446: Loss: 2.81e-02, Avg Return: 0.856, Regret: 0.0032, Entropy: 0.1538 +[2026-03-20T20:07:29.366162Z] Loop 11447: Loss: 2.72e-02, Avg Return: 0.859, Regret: 0.0032, Entropy: 0.1381 +[2026-03-20T20:07:30.219382Z] Loop 11448: Loss: 2.34e-02, Avg Return: 0.860, Regret: 0.0032, Entropy: 0.1217 +[2026-03-20T20:07:31.073080Z] Loop 11449: Loss: 2.23e-02, Avg Return: 0.863, Regret: 0.0032, Entropy: 0.1137 +[2026-03-20T20:07:31.966127Z] Loop 11450: Loss: 2.08e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.1050 +[2026-03-20T20:07:32.820870Z] Loop 11451: Loss: 1.96e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0969 +[2026-03-20T20:07:33.675404Z] Loop 11452: Loss: 1.90e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0963 +[2026-03-20T20:07:34.529606Z] Loop 11453: Loss: 1.86e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0943 +[2026-03-20T20:07:35.384625Z] Loop 11454: Loss: 1.98e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0956 +[2026-03-20T20:07:36.237882Z] Loop 11455: Loss: 1.87e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0956 +[2026-03-20T20:07:37.091571Z] Loop 11456: Loss: 1.76e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0931 +[2026-03-20T20:07:37.945068Z] Loop 11457: Loss: 1.87e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0957 +[2026-03-20T20:07:38.798644Z] Loop 11458: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0948 +[2026-03-20T20:07:39.653143Z] Loop 11459: Loss: 1.78e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0900 +[2026-03-20T20:07:40.545953Z] Loop 11460: Loss: 1.90e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0979 +[2026-03-20T20:07:41.399610Z] Loop 11461: Loss: 1.85e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0932 +[2026-03-20T20:07:42.253755Z] Loop 11462: Loss: 1.95e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.1001 +[2026-03-20T20:07:43.108453Z] Loop 11463: Loss: 1.99e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.1011 +[2026-03-20T20:07:43.962454Z] Loop 11464: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0926 +[2026-03-20T20:07:44.816470Z] Loop 11465: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0986 +[2026-03-20T20:07:45.669319Z] Loop 11466: Loss: 1.83e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0958 +[2026-03-20T20:07:46.522364Z] Loop 11467: Loss: 2.03e-02, Avg Return: 0.860, Regret: 0.0016, Entropy: 0.1023 +[2026-03-20T20:07:47.376607Z] Loop 11468: Loss: 2.01e-02, Avg Return: 0.860, Regret: 0.0016, Entropy: 0.1041 +[2026-03-20T20:07:48.230754Z] Loop 11469: Loss: 1.93e-02, Avg Return: 0.859, Regret: 0.0016, Entropy: 0.1028 +[2026-03-20T20:07:49.125182Z] Loop 11470: Loss: 2.02e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.1037 +[2026-03-20T20:07:49.979520Z] Loop 11471: Loss: 2.01e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.1038 +[2026-03-20T20:07:50.833972Z] Loop 11472: Loss: 1.83e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.0982 +[2026-03-20T20:07:51.688318Z] Loop 11473: Loss: 1.95e-02, Avg Return: 0.863, Regret: 0.0024, Entropy: 0.0982 +[2026-03-20T20:07:52.543079Z] Loop 11474: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.0906 +[2026-03-20T20:07:53.397271Z] Loop 11475: Loss: 1.79e-02, Avg Return: 0.863, Regret: 0.0024, Entropy: 0.0920 +[2026-03-20T20:07:54.250924Z] Loop 11476: Loss: 1.92e-02, Avg Return: 0.863, Regret: 0.0024, Entropy: 0.0976 +[2026-03-20T20:07:55.104807Z] Loop 11477: Loss: 1.97e-02, Avg Return: 0.863, Regret: 0.0024, Entropy: 0.0982 +[2026-03-20T20:07:55.958800Z] Loop 11478: Loss: 1.91e-02, Avg Return: 0.864, Regret: 0.0024, Entropy: 0.0989 +[2026-03-20T20:07:56.813350Z] Loop 11479: Loss: 1.84e-02, Avg Return: 0.863, Regret: 0.0024, Entropy: 0.0901 +[2026-03-20T20:07:57.706642Z] Loop 11480: Loss: 1.75e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0877 +[2026-03-20T20:07:58.560648Z] Loop 11481: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0896 +[2026-03-20T20:07:59.415410Z] Loop 11482: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0829 +[2026-03-20T20:08:00.269908Z] Loop 11483: Loss: 1.76e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0900 +[2026-03-20T20:08:01.124004Z] Loop 11484: Loss: 1.81e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.0956 +[2026-03-20T20:08:01.977310Z] Loop 11485: Loss: 1.93e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0985 +[2026-03-20T20:08:02.832548Z] Loop 11486: Loss: 2.27e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.1102 +[2026-03-20T20:08:03.688415Z] Loop 11487: Loss: 2.33e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.1169 +[2026-03-20T20:08:04.542565Z] Loop 11488: Loss: 2.44e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.1231 +[2026-03-20T20:08:05.397081Z] Loop 11489: Loss: 2.52e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.1197 +[2026-03-20T20:08:06.292424Z] Loop 11490: Loss: 2.59e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1296 +[2026-03-20T20:08:07.147999Z] Loop 11491: Loss: 2.61e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1255 +[2026-03-20T20:08:08.002035Z] Loop 11492: Loss: 2.62e-02, Avg Return: 0.863, Regret: 0.0019, Entropy: 0.1325 +[2026-03-20T20:08:08.855370Z] Loop 11493: Loss: 2.36e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.1176 +[2026-03-20T20:08:09.708639Z] Loop 11494: Loss: 2.22e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.1117 +[2026-03-20T20:08:10.562598Z] Loop 11495: Loss: 1.97e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1022 +[2026-03-20T20:08:11.416327Z] Loop 11496: Loss: 1.85e-02, Avg Return: 0.864, Regret: 0.0019, Entropy: 0.0955 +[2026-03-20T20:08:12.270457Z] Loop 11497: Loss: 1.81e-02, Avg Return: 0.863, Regret: 0.0019, Entropy: 0.0919 +[2026-03-20T20:08:13.123452Z] Loop 11498: Loss: 1.58e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0841 +[2026-03-20T20:08:13.977266Z] Loop 11499: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0863 +[2026-03-20T20:08:14.869293Z] Loop 11500: Loss: 1.62e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0865 +[2026-03-20T20:08:15.723160Z] Loop 11501: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0854 +[2026-03-20T20:08:16.577436Z] Loop 11502: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0823 +[2026-03-20T20:08:17.433537Z] Loop 11503: Loss: 1.62e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0848 +[2026-03-20T20:08:18.288206Z] Loop 11504: Loss: 1.71e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0864 +[2026-03-20T20:08:19.143561Z] Loop 11505: Loss: 1.63e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0838 +[2026-03-20T20:08:19.998182Z] Loop 11506: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0826 +[2026-03-20T20:08:20.852211Z] Loop 11507: Loss: 1.90e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0936 +[2026-03-20T20:08:21.706693Z] Loop 11508: Loss: 1.79e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0856 +[2026-03-20T20:08:22.561435Z] Loop 11509: Loss: 1.70e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0866 +[2026-03-20T20:08:23.458044Z] Loop 11510: Loss: 1.69e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0871 +[2026-03-20T20:08:24.311965Z] Loop 11511: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0828 +[2026-03-20T20:08:25.165149Z] Loop 11512: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0824 +[2026-03-20T20:08:26.019056Z] Loop 11513: Loss: 1.71e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0835 +[2026-03-20T20:08:26.873641Z] Loop 11514: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0839 +[2026-03-20T20:08:27.727801Z] Loop 11515: Loss: 1.58e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0771 +[2026-03-20T20:08:28.581019Z] Loop 11516: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0810 +[2026-03-20T20:08:29.433982Z] Loop 11517: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0778 +[2026-03-20T20:08:30.288481Z] Loop 11518: Loss: 1.58e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0794 +[2026-03-20T20:08:31.141927Z] Loop 11519: Loss: 1.50e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0796 +[2026-03-20T20:08:32.035100Z] Loop 11520: Loss: 1.64e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0845 +[2026-03-20T20:08:32.888681Z] Loop 11521: Loss: 1.54e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0784 +[2026-03-20T20:08:33.743249Z] Loop 11522: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0870 +[2026-03-20T20:08:34.597368Z] Loop 11523: Loss: 1.85e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0923 +[2026-03-20T20:08:35.450615Z] Loop 11524: Loss: 1.77e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0894 +[2026-03-20T20:08:36.303999Z] Loop 11525: Loss: 1.71e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0837 +[2026-03-20T20:08:37.158472Z] Loop 11526: Loss: 1.64e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0847 +[2026-03-20T20:08:38.012816Z] Loop 11527: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0834 +[2026-03-20T20:08:38.867062Z] Loop 11528: Loss: 1.63e-02, Avg Return: 0.860, Regret: 0.0008, Entropy: 0.0871 +[2026-03-20T20:08:39.721382Z] Loop 11529: Loss: 1.78e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0914 +[2026-03-20T20:08:40.617346Z] Loop 11530: Loss: 1.81e-02, Avg Return: 0.861, Regret: 0.0023, Entropy: 0.0909 +[2026-03-20T20:08:41.471178Z] Loop 11531: Loss: 1.93e-02, Avg Return: 0.860, Regret: 0.0023, Entropy: 0.1006 +[2026-03-20T20:08:42.325064Z] Loop 11532: Loss: 2.00e-02, Avg Return: 0.861, Regret: 0.0023, Entropy: 0.1017 +[2026-03-20T20:08:43.179418Z] Loop 11533: Loss: 2.03e-02, Avg Return: 0.860, Regret: 0.0023, Entropy: 0.1015 +[2026-03-20T20:08:44.032376Z] Loop 11534: Loss: 2.00e-02, Avg Return: 0.860, Regret: 0.0023, Entropy: 0.1040 +[2026-03-20T20:08:44.885168Z] Loop 11535: Loss: 2.10e-02, Avg Return: 0.860, Regret: 0.0023, Entropy: 0.1056 +[2026-03-20T20:08:45.738461Z] Loop 11536: Loss: 1.97e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.0980 +[2026-03-20T20:08:46.592318Z] Loop 11537: Loss: 1.88e-02, Avg Return: 0.861, Regret: 0.0023, Entropy: 0.0967 +[2026-03-20T20:08:47.446756Z] Loop 11538: Loss: 1.96e-02, Avg Return: 0.863, Regret: 0.0023, Entropy: 0.1005 +[2026-03-20T20:08:48.299989Z] Loop 11539: Loss: 1.91e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.0975 +[2026-03-20T20:08:49.192878Z] Loop 11540: Loss: 1.84e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0939 +[2026-03-20T20:08:50.046760Z] Loop 11541: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0960 +[2026-03-20T20:08:50.901705Z] Loop 11542: Loss: 1.74e-02, Avg Return: 0.864, Regret: 0.0013, Entropy: 0.0932 +[2026-03-20T20:08:51.755574Z] Loop 11543: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0879 +[2026-03-20T20:08:52.609402Z] Loop 11544: Loss: 1.68e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0899 +[2026-03-20T20:08:53.463056Z] Loop 11545: Loss: 1.67e-02, Avg Return: 0.864, Regret: 0.0013, Entropy: 0.0866 +[2026-03-20T20:08:54.317343Z] Loop 11546: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0856 +[2026-03-20T20:08:55.170646Z] Loop 11547: Loss: 1.61e-02, Avg Return: 0.864, Regret: 0.0013, Entropy: 0.0868 +[2026-03-20T20:08:56.024920Z] Loop 11548: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0801 +[2026-03-20T20:08:56.879655Z] Loop 11549: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0791 +[2026-03-20T20:08:57.773452Z] Loop 11550: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0829 +[2026-03-20T20:08:58.627770Z] Loop 11551: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0801 +[2026-03-20T20:08:59.480941Z] Loop 11552: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0834 +[2026-03-20T20:09:00.335629Z] Loop 11553: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0844 +[2026-03-20T20:09:01.190381Z] Loop 11554: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0777 +[2026-03-20T20:09:02.045967Z] Loop 11555: Loss: 1.48e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0790 +[2026-03-20T20:09:02.900140Z] Loop 11556: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0789 +[2026-03-20T20:09:03.755812Z] Loop 11557: Loss: 1.58e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0820 +[2026-03-20T20:09:04.610632Z] Loop 11558: Loss: 1.38e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0800 +[2026-03-20T20:09:05.465011Z] Loop 11559: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0790 +[2026-03-20T20:09:06.358387Z] Loop 11560: Loss: 1.43e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0795 +[2026-03-20T20:09:07.212418Z] Loop 11561: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0795 +[2026-03-20T20:09:08.066695Z] Loop 11562: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0781 +[2026-03-20T20:09:08.920668Z] Loop 11563: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0792 +[2026-03-20T20:09:09.775648Z] Loop 11564: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0798 +[2026-03-20T20:09:10.631719Z] Loop 11565: Loss: 1.54e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0791 +[2026-03-20T20:09:11.485985Z] Loop 11566: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0869 +[2026-03-20T20:09:12.340348Z] Loop 11567: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0802 +[2026-03-20T20:09:13.196340Z] Loop 11568: Loss: 1.62e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0832 +[2026-03-20T20:09:14.050856Z] Loop 11569: Loss: 1.73e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0837 +[2026-03-20T20:09:14.945322Z] Loop 11570: Loss: 1.73e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0863 +[2026-03-20T20:09:15.798340Z] Loop 11571: Loss: 1.71e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.0865 +[2026-03-20T20:09:16.652900Z] Loop 11572: Loss: 1.70e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0852 +[2026-03-20T20:09:17.508032Z] Loop 11573: Loss: 1.68e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0826 +[2026-03-20T20:09:18.361445Z] Loop 11574: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0810 +[2026-03-20T20:09:19.214736Z] Loop 11575: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0860 +[2026-03-20T20:09:20.068469Z] Loop 11576: Loss: 1.58e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.0829 +[2026-03-20T20:09:20.923565Z] Loop 11577: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0801 +[2026-03-20T20:09:21.777159Z] Loop 11578: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0799 +[2026-03-20T20:09:22.632666Z] Loop 11579: Loss: 1.58e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.0839 +[2026-03-20T20:09:23.526447Z] Loop 11580: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0807 +[2026-03-20T20:09:24.381434Z] Loop 11581: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0830 +[2026-03-20T20:09:25.236929Z] Loop 11582: Loss: 1.54e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0779 +[2026-03-20T20:09:26.092308Z] Loop 11583: Loss: 1.64e-02, Avg Return: 0.861, Regret: 0.0017, Entropy: 0.0827 +[2026-03-20T20:09:26.947236Z] Loop 11584: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0808 +[2026-03-20T20:09:27.802140Z] Loop 11585: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0825 +[2026-03-20T20:09:28.656460Z] Loop 11586: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0017, Entropy: 0.0818 +[2026-03-20T20:09:29.510211Z] Loop 11587: Loss: 1.70e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0848 +[2026-03-20T20:09:30.363989Z] Loop 11588: Loss: 1.62e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0850 +[2026-03-20T20:09:31.217681Z] Loop 11589: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0794 +[2026-03-20T20:09:32.111005Z] Loop 11590: Loss: 1.54e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0787 +[2026-03-20T20:09:32.965899Z] Loop 11591: Loss: 1.52e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0814 +[2026-03-20T20:09:33.819789Z] Loop 11592: Loss: 1.52e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0799 +[2026-03-20T20:09:34.674380Z] Loop 11593: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0771 +[2026-03-20T20:09:35.527858Z] Loop 11594: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0788 +[2026-03-20T20:09:36.382168Z] Loop 11595: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0780 +[2026-03-20T20:09:37.237494Z] Loop 11596: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0797 +[2026-03-20T20:09:38.093175Z] Loop 11597: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0796 +[2026-03-20T20:09:38.948979Z] Loop 11598: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0793 +[2026-03-20T20:09:39.804780Z] Loop 11599: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0781 +[2026-03-20T20:09:40.698520Z] Loop 11600: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0806 +[2026-03-20T20:09:41.553270Z] Loop 11601: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0812 +[2026-03-20T20:09:42.408108Z] Loop 11602: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0779 +[2026-03-20T20:09:43.262174Z] Loop 11603: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0786 +[2026-03-20T20:09:44.117948Z] Loop 11604: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0753 +[2026-03-20T20:09:44.973019Z] Loop 11605: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0728 +[2026-03-20T20:09:45.827840Z] Loop 11606: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0799 +[2026-03-20T20:09:46.681696Z] Loop 11607: Loss: 1.55e-02, Avg Return: 0.860, Regret: 0.0011, Entropy: 0.0810 +[2026-03-20T20:09:47.537291Z] Loop 11608: Loss: 1.74e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0831 +[2026-03-20T20:09:48.392255Z] Loop 11609: Loss: 1.82e-02, Avg Return: 0.860, Regret: 0.0011, Entropy: 0.0906 +[2026-03-20T20:09:49.287330Z] Loop 11610: Loss: 1.85e-02, Avg Return: 0.858, Regret: 0.0048, Entropy: 0.0907 +[2026-03-20T20:09:50.141281Z] Loop 11611: Loss: 1.82e-02, Avg Return: 0.859, Regret: 0.0048, Entropy: 0.0892 +[2026-03-20T20:09:50.996200Z] Loop 11612: Loss: 1.79e-02, Avg Return: 0.855, Regret: 0.0048, Entropy: 0.0864 +[2026-03-20T20:09:51.850226Z] Loop 11613: Loss: 1.77e-02, Avg Return: 0.858, Regret: 0.0048, Entropy: 0.0864 +[2026-03-20T20:09:52.704406Z] Loop 11614: Loss: 1.59e-02, Avg Return: 0.859, Regret: 0.0048, Entropy: 0.0841 +[2026-03-20T20:09:53.558199Z] Loop 11615: Loss: 1.72e-02, Avg Return: 0.861, Regret: 0.0048, Entropy: 0.0863 +[2026-03-20T20:09:54.412400Z] Loop 11616: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0048, Entropy: 0.0819 +[2026-03-20T20:09:55.265847Z] Loop 11617: Loss: 1.64e-02, Avg Return: 0.861, Regret: 0.0048, Entropy: 0.0836 +[2026-03-20T20:09:56.120309Z] Loop 11618: Loss: 1.57e-02, Avg Return: 0.864, Regret: 0.0048, Entropy: 0.0859 +[2026-03-20T20:09:56.974591Z] Loop 11619: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0048, Entropy: 0.0869 +[2026-03-20T20:09:57.868117Z] Loop 11620: Loss: 1.73e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0839 +[2026-03-20T20:09:58.721606Z] Loop 11621: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0853 +[2026-03-20T20:09:59.576548Z] Loop 11622: Loss: 1.60e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0824 +[2026-03-20T20:10:00.432616Z] Loop 11623: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0850 +[2026-03-20T20:10:01.287095Z] Loop 11624: Loss: 1.67e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0875 +[2026-03-20T20:10:02.142304Z] Loop 11625: Loss: 1.70e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0867 +[2026-03-20T20:10:02.997831Z] Loop 11626: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0867 +[2026-03-20T20:10:03.853653Z] Loop 11627: Loss: 1.80e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0902 +[2026-03-20T20:10:04.708791Z] Loop 11628: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0849 +[2026-03-20T20:10:05.563077Z] Loop 11629: Loss: 1.63e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0826 +[2026-03-20T20:10:06.466845Z] Loop 11630: Loss: 1.74e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0870 +[2026-03-20T20:10:07.322189Z] Loop 11631: Loss: 1.69e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.0893 +[2026-03-20T20:10:08.177210Z] Loop 11632: Loss: 1.80e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0895 +[2026-03-20T20:10:09.031546Z] Loop 11633: Loss: 1.79e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.0950 +[2026-03-20T20:10:09.885931Z] Loop 11634: Loss: 1.85e-02, Avg Return: 0.860, Regret: 0.0015, Entropy: 0.0942 +[2026-03-20T20:10:10.740856Z] Loop 11635: Loss: 1.84e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.0910 +[2026-03-20T20:10:11.596456Z] Loop 11636: Loss: 1.69e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0901 +[2026-03-20T20:10:12.451345Z] Loop 11637: Loss: 1.72e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.0881 +[2026-03-20T20:10:13.305227Z] Loop 11638: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0882 +[2026-03-20T20:10:14.160976Z] Loop 11639: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0853 +[2026-03-20T20:10:15.057917Z] Loop 11640: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0843 +[2026-03-20T20:10:15.912204Z] Loop 11641: Loss: 1.64e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0868 +[2026-03-20T20:10:16.766313Z] Loop 11642: Loss: 1.64e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0893 +[2026-03-20T20:10:17.620740Z] Loop 11643: Loss: 1.62e-02, Avg Return: 0.864, Regret: 0.0013, Entropy: 0.0840 +[2026-03-20T20:10:18.473930Z] Loop 11644: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0935 +[2026-03-20T20:10:19.328320Z] Loop 11645: Loss: 1.87e-02, Avg Return: 0.864, Regret: 0.0013, Entropy: 0.0955 +[2026-03-20T20:10:20.183689Z] Loop 11646: Loss: 1.88e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0962 +[2026-03-20T20:10:21.039168Z] Loop 11647: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0887 +[2026-03-20T20:10:21.892686Z] Loop 11648: Loss: 1.76e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0886 +[2026-03-20T20:10:22.746394Z] Loop 11649: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0851 +[2026-03-20T20:10:23.639666Z] Loop 11650: Loss: 1.63e-02, Avg Return: 0.860, Regret: 0.0008, Entropy: 0.0816 +[2026-03-20T20:10:24.495132Z] Loop 11651: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0820 +[2026-03-20T20:10:25.349281Z] Loop 11652: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0794 +[2026-03-20T20:10:26.202520Z] Loop 11653: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0799 +[2026-03-20T20:10:27.056845Z] Loop 11654: Loss: 1.47e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0779 +[2026-03-20T20:10:27.912007Z] Loop 11655: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0786 +[2026-03-20T20:10:28.766344Z] Loop 11656: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0783 +[2026-03-20T20:10:29.620155Z] Loop 11657: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0790 +[2026-03-20T20:10:30.473609Z] Loop 11658: Loss: 1.53e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0774 +[2026-03-20T20:10:31.327818Z] Loop 11659: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0816 +[2026-03-20T20:10:32.222088Z] Loop 11660: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0779 +[2026-03-20T20:10:33.076291Z] Loop 11661: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0780 +[2026-03-20T20:10:33.929307Z] Loop 11662: Loss: 1.50e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0779 +[2026-03-20T20:10:34.784060Z] Loop 11663: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0765 +[2026-03-20T20:10:35.638213Z] Loop 11664: Loss: 1.63e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0800 +[2026-03-20T20:10:36.492044Z] Loop 11665: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0798 +[2026-03-20T20:10:37.345748Z] Loop 11666: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0775 +[2026-03-20T20:10:38.199152Z] Loop 11667: Loss: 1.61e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0802 +[2026-03-20T20:10:39.053065Z] Loop 11668: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0800 +[2026-03-20T20:10:39.907170Z] Loop 11669: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0844 +[2026-03-20T20:10:40.800911Z] Loop 11670: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0798 +[2026-03-20T20:10:41.656816Z] Loop 11671: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0807 +[2026-03-20T20:10:42.510433Z] Loop 11672: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0838 +[2026-03-20T20:10:43.364890Z] Loop 11673: Loss: 1.63e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0811 +[2026-03-20T20:10:44.219555Z] Loop 11674: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0823 +[2026-03-20T20:10:45.073873Z] Loop 11675: Loss: 1.62e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0831 +[2026-03-20T20:10:45.928478Z] Loop 11676: Loss: 1.73e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0847 +[2026-03-20T20:10:46.782709Z] Loop 11677: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0796 +[2026-03-20T20:10:47.637718Z] Loop 11678: Loss: 1.67e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0790 +[2026-03-20T20:10:48.491463Z] Loop 11679: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0753 +[2026-03-20T20:10:49.384418Z] Loop 11680: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0786 +[2026-03-20T20:10:50.238028Z] Loop 11681: Loss: 1.46e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.0767 +[2026-03-20T20:10:51.093094Z] Loop 11682: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0736 +[2026-03-20T20:10:51.946870Z] Loop 11683: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0739 +[2026-03-20T20:10:52.799586Z] Loop 11684: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0780 +[2026-03-20T20:10:53.653222Z] Loop 11685: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0746 +[2026-03-20T20:10:54.508276Z] Loop 11686: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0740 +[2026-03-20T20:10:55.362879Z] Loop 11687: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0724 +[2026-03-20T20:10:56.215980Z] Loop 11688: Loss: 1.44e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0750 +[2026-03-20T20:10:57.069556Z] Loop 11689: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0014, Entropy: 0.0727 +[2026-03-20T20:10:57.963009Z] Loop 11690: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0749 +[2026-03-20T20:10:58.816818Z] Loop 11691: Loss: 1.42e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0751 +[2026-03-20T20:10:59.670397Z] Loop 11692: Loss: 1.67e-02, Avg Return: 0.860, Regret: 0.0006, Entropy: 0.0829 +[2026-03-20T20:11:00.523685Z] Loop 11693: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0855 +[2026-03-20T20:11:01.378536Z] Loop 11694: Loss: 1.54e-02, Avg Return: 0.859, Regret: 0.0006, Entropy: 0.0776 +[2026-03-20T20:11:02.234322Z] Loop 11695: Loss: 1.42e-02, Avg Return: 0.858, Regret: 0.0006, Entropy: 0.0758 +[2026-03-20T20:11:03.089164Z] Loop 11696: Loss: 1.48e-02, Avg Return: 0.857, Regret: 0.0006, Entropy: 0.0773 +[2026-03-20T20:11:03.943557Z] Loop 11697: Loss: 1.50e-02, Avg Return: 0.858, Regret: 0.0006, Entropy: 0.0791 +[2026-03-20T20:11:04.798921Z] Loop 11698: Loss: 1.58e-02, Avg Return: 0.857, Regret: 0.0006, Entropy: 0.0792 +[2026-03-20T20:11:05.653620Z] Loop 11699: Loss: 1.66e-02, Avg Return: 0.857, Regret: 0.0006, Entropy: 0.0836 +[2026-03-20T20:11:06.547417Z] Loop 11700: Loss: 1.55e-02, Avg Return: 0.857, Regret: 0.0060, Entropy: 0.0791 +[2026-03-20T20:11:07.401830Z] Loop 11701: Loss: 1.48e-02, Avg Return: 0.859, Regret: 0.0060, Entropy: 0.0815 +[2026-03-20T20:11:08.255295Z] Loop 11702: Loss: 1.44e-02, Avg Return: 0.859, Regret: 0.0060, Entropy: 0.0771 +[2026-03-20T20:11:09.109527Z] Loop 11703: Loss: 1.49e-02, Avg Return: 0.861, Regret: 0.0060, Entropy: 0.0806 +[2026-03-20T20:11:09.963411Z] Loop 11704: Loss: 1.42e-02, Avg Return: 0.860, Regret: 0.0060, Entropy: 0.0724 +[2026-03-20T20:11:10.818450Z] Loop 11705: Loss: 1.34e-02, Avg Return: 0.861, Regret: 0.0060, Entropy: 0.0736 +[2026-03-20T20:11:11.672322Z] Loop 11706: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0060, Entropy: 0.0729 +[2026-03-20T20:11:12.525946Z] Loop 11707: Loss: 1.40e-02, Avg Return: 0.862, Regret: 0.0060, Entropy: 0.0740 +[2026-03-20T20:11:13.379392Z] Loop 11708: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0060, Entropy: 0.0778 +[2026-03-20T20:11:14.232974Z] Loop 11709: Loss: 1.43e-02, Avg Return: 0.862, Regret: 0.0060, Entropy: 0.0739 +[2026-03-20T20:11:15.128650Z] Loop 11710: Loss: 1.32e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0690 +[2026-03-20T20:11:15.981815Z] Loop 11711: Loss: 1.42e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0735 +[2026-03-20T20:11:16.834165Z] Loop 11712: Loss: 1.42e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0749 +[2026-03-20T20:11:17.687783Z] Loop 11713: Loss: 1.45e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0768 +[2026-03-20T20:11:18.542965Z] Loop 11714: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0808 +[2026-03-20T20:11:19.396745Z] Loop 11715: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0826 +[2026-03-20T20:11:20.250720Z] Loop 11716: Loss: 1.72e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0867 +[2026-03-20T20:11:21.103913Z] Loop 11717: Loss: 1.66e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0837 +[2026-03-20T20:11:21.958459Z] Loop 11718: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0840 +[2026-03-20T20:11:22.812427Z] Loop 11719: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0760 +[2026-03-20T20:11:23.705695Z] Loop 11720: Loss: 1.41e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0718 +[2026-03-20T20:11:24.559927Z] Loop 11721: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0765 +[2026-03-20T20:11:25.415827Z] Loop 11722: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0792 +[2026-03-20T20:11:26.269453Z] Loop 11723: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0873 +[2026-03-20T20:11:27.123490Z] Loop 11724: Loss: 1.81e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0899 +[2026-03-20T20:11:27.976756Z] Loop 11725: Loss: 1.76e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0861 +[2026-03-20T20:11:28.830438Z] Loop 11726: Loss: 1.83e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0914 +[2026-03-20T20:11:29.683957Z] Loop 11727: Loss: 1.96e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0943 +[2026-03-20T20:11:30.538111Z] Loop 11728: Loss: 1.91e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0938 +[2026-03-20T20:11:31.391575Z] Loop 11729: Loss: 1.87e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0948 +[2026-03-20T20:11:32.285284Z] Loop 11730: Loss: 1.84e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0907 +[2026-03-20T20:11:33.139721Z] Loop 11731: Loss: 1.77e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0906 +[2026-03-20T20:11:33.994340Z] Loop 11732: Loss: 1.92e-02, Avg Return: 0.859, Regret: 0.0019, Entropy: 0.0958 +[2026-03-20T20:11:34.848572Z] Loop 11733: Loss: 1.88e-02, Avg Return: 0.856, Regret: 0.0019, Entropy: 0.0961 +[2026-03-20T20:11:35.702176Z] Loop 11734: Loss: 1.97e-02, Avg Return: 0.856, Regret: 0.0019, Entropy: 0.1003 +[2026-03-20T20:11:36.555760Z] Loop 11735: Loss: 1.67e-02, Avg Return: 0.859, Regret: 0.0019, Entropy: 0.0883 +[2026-03-20T20:11:37.410436Z] Loop 11736: Loss: 1.60e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0825 +[2026-03-20T20:11:38.265233Z] Loop 11737: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0019, Entropy: 0.0827 +[2026-03-20T20:11:39.119360Z] Loop 11738: Loss: 1.57e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0792 +[2026-03-20T20:11:39.972444Z] Loop 11739: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0825 +[2026-03-20T20:11:40.865215Z] Loop 11740: Loss: 1.82e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0886 +[2026-03-20T20:11:41.719505Z] Loop 11741: Loss: 1.95e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0937 +[2026-03-20T20:11:42.573291Z] Loop 11742: Loss: 1.77e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0872 +[2026-03-20T20:11:43.426968Z] Loop 11743: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0800 +[2026-03-20T20:11:44.280788Z] Loop 11744: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0777 +[2026-03-20T20:11:45.136220Z] Loop 11745: Loss: 1.59e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0796 +[2026-03-20T20:11:45.990293Z] Loop 11746: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0799 +[2026-03-20T20:11:46.843454Z] Loop 11747: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0768 +[2026-03-20T20:11:47.697122Z] Loop 11748: Loss: 1.68e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0835 +[2026-03-20T20:11:48.551758Z] Loop 11749: Loss: 1.71e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0887 +[2026-03-20T20:11:49.445741Z] Loop 11750: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0872 +[2026-03-20T20:11:50.299724Z] Loop 11751: Loss: 1.78e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0895 +[2026-03-20T20:11:51.153118Z] Loop 11752: Loss: 1.86e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0905 +[2026-03-20T20:11:52.007194Z] Loop 11753: Loss: 1.77e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0874 +[2026-03-20T20:11:52.862021Z] Loop 11754: Loss: 1.79e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0903 +[2026-03-20T20:11:53.716696Z] Loop 11755: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0845 +[2026-03-20T20:11:54.571079Z] Loop 11756: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0886 +[2026-03-20T20:11:55.427149Z] Loop 11757: Loss: 1.64e-02, Avg Return: 0.861, Regret: 0.0004, Entropy: 0.0843 +[2026-03-20T20:11:56.282480Z] Loop 11758: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0839 +[2026-03-20T20:11:57.137573Z] Loop 11759: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0890 +[2026-03-20T20:11:58.031371Z] Loop 11760: Loss: 1.73e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0947 +[2026-03-20T20:11:58.885238Z] Loop 11761: Loss: 2.08e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1000 +[2026-03-20T20:11:59.738709Z] Loop 11762: Loss: 2.12e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1048 +[2026-03-20T20:12:00.592230Z] Loop 11763: Loss: 2.17e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1126 +[2026-03-20T20:12:01.445689Z] Loop 11764: Loss: 2.31e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1147 +[2026-03-20T20:12:02.299963Z] Loop 11765: Loss: 2.33e-02, Avg Return: 0.860, Regret: 0.0019, Entropy: 0.1160 +[2026-03-20T20:12:03.153490Z] Loop 11766: Loss: 2.35e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.1198 +[2026-03-20T20:12:04.007338Z] Loop 11767: Loss: 2.69e-02, Avg Return: 0.860, Regret: 0.0019, Entropy: 0.1310 +[2026-03-20T20:12:04.861639Z] Loop 11768: Loss: 2.67e-02, Avg Return: 0.860, Regret: 0.0019, Entropy: 0.1338 +[2026-03-20T20:12:05.717006Z] Loop 11769: Loss: 2.75e-02, Avg Return: 0.859, Regret: 0.0019, Entropy: 0.1370 +[2026-03-20T20:12:06.610263Z] Loop 11770: Loss: 2.71e-02, Avg Return: 0.860, Regret: 0.0037, Entropy: 0.1299 +[2026-03-20T20:12:07.464242Z] Loop 11771: Loss: 2.61e-02, Avg Return: 0.859, Regret: 0.0037, Entropy: 0.1321 +[2026-03-20T20:12:08.318907Z] Loop 11772: Loss: 2.52e-02, Avg Return: 0.859, Regret: 0.0037, Entropy: 0.1254 +[2026-03-20T20:12:09.174229Z] Loop 11773: Loss: 2.36e-02, Avg Return: 0.861, Regret: 0.0037, Entropy: 0.1169 +[2026-03-20T20:12:10.028806Z] Loop 11774: Loss: 2.32e-02, Avg Return: 0.861, Regret: 0.0037, Entropy: 0.1175 +[2026-03-20T20:12:10.882920Z] Loop 11775: Loss: 2.40e-02, Avg Return: 0.861, Regret: 0.0037, Entropy: 0.1231 +[2026-03-20T20:12:11.738004Z] Loop 11776: Loss: 2.42e-02, Avg Return: 0.861, Regret: 0.0037, Entropy: 0.1204 +[2026-03-20T20:12:12.593562Z] Loop 11777: Loss: 2.60e-02, Avg Return: 0.861, Regret: 0.0037, Entropy: 0.1259 +[2026-03-20T20:12:13.449270Z] Loop 11778: Loss: 2.47e-02, Avg Return: 0.859, Regret: 0.0037, Entropy: 0.1253 +[2026-03-20T20:12:14.302960Z] Loop 11779: Loss: 2.53e-02, Avg Return: 0.859, Regret: 0.0037, Entropy: 0.1299 +[2026-03-20T20:12:15.196093Z] Loop 11780: Loss: 2.60e-02, Avg Return: 0.859, Regret: 0.0039, Entropy: 0.1291 +[2026-03-20T20:12:16.049365Z] Loop 11781: Loss: 2.69e-02, Avg Return: 0.859, Regret: 0.0039, Entropy: 0.1304 +[2026-03-20T20:12:16.903305Z] Loop 11782: Loss: 2.54e-02, Avg Return: 0.860, Regret: 0.0039, Entropy: 0.1252 +[2026-03-20T20:12:17.756483Z] Loop 11783: Loss: 2.37e-02, Avg Return: 0.859, Regret: 0.0039, Entropy: 0.1167 +[2026-03-20T20:12:18.610355Z] Loop 11784: Loss: 2.55e-02, Avg Return: 0.862, Regret: 0.0039, Entropy: 0.1200 +[2026-03-20T20:12:19.463429Z] Loop 11785: Loss: 2.36e-02, Avg Return: 0.861, Regret: 0.0039, Entropy: 0.1178 +[2026-03-20T20:12:20.316752Z] Loop 11786: Loss: 2.34e-02, Avg Return: 0.863, Regret: 0.0039, Entropy: 0.1154 +[2026-03-20T20:12:21.171199Z] Loop 11787: Loss: 2.26e-02, Avg Return: 0.863, Regret: 0.0039, Entropy: 0.1076 +[2026-03-20T20:12:22.024790Z] Loop 11788: Loss: 2.20e-02, Avg Return: 0.863, Regret: 0.0039, Entropy: 0.1079 +[2026-03-20T20:12:22.878314Z] Loop 11789: Loss: 1.87e-02, Avg Return: 0.863, Regret: 0.0039, Entropy: 0.0952 +[2026-03-20T20:12:23.771956Z] Loop 11790: Loss: 1.94e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0953 +[2026-03-20T20:12:24.627562Z] Loop 11791: Loss: 1.88e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0907 +[2026-03-20T20:12:25.481479Z] Loop 11792: Loss: 1.75e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0884 +[2026-03-20T20:12:26.334294Z] Loop 11793: Loss: 1.93e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.1006 +[2026-03-20T20:12:27.188158Z] Loop 11794: Loss: 2.02e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0996 +[2026-03-20T20:12:28.042522Z] Loop 11795: Loss: 2.07e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.1031 +[2026-03-20T20:12:28.897043Z] Loop 11796: Loss: 2.37e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.1169 +[2026-03-20T20:12:29.751361Z] Loop 11797: Loss: 2.50e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.1202 +[2026-03-20T20:12:30.605344Z] Loop 11798: Loss: 2.38e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.1137 +[2026-03-20T20:12:31.459480Z] Loop 11799: Loss: 2.20e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.1134 +[2026-03-20T20:12:32.355825Z] Loop 11800: Loss: 2.35e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.1167 +[2026-03-20T20:12:33.210162Z] Loop 11801: Loss: 2.30e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.1080 +[2026-03-20T20:12:34.063930Z] Loop 11802: Loss: 2.31e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.1125 +[2026-03-20T20:12:34.918327Z] Loop 11803: Loss: 2.52e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.1197 +[2026-03-20T20:12:35.773569Z] Loop 11804: Loss: 2.29e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.1102 +[2026-03-20T20:12:36.627974Z] Loop 11805: Loss: 1.84e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0895 +[2026-03-20T20:12:37.483108Z] Loop 11806: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0799 +[2026-03-20T20:12:38.336765Z] Loop 11807: Loss: 1.37e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0755 +[2026-03-20T20:12:39.192227Z] Loop 11808: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0701 +[2026-03-20T20:12:40.047032Z] Loop 11809: Loss: 1.40e-02, Avg Return: 0.865, Regret: 0.0012, Entropy: 0.0766 +[2026-03-20T20:12:40.943369Z] Loop 11810: Loss: 1.65e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0814 +[2026-03-20T20:12:41.798227Z] Loop 11811: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0797 +[2026-03-20T20:12:42.653076Z] Loop 11812: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0780 +[2026-03-20T20:12:43.508637Z] Loop 11813: Loss: 1.43e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0740 +[2026-03-20T20:12:44.363979Z] Loop 11814: Loss: 1.37e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0739 +[2026-03-20T20:12:45.217592Z] Loop 11815: Loss: 1.39e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0730 +[2026-03-20T20:12:46.071992Z] Loop 11816: Loss: 1.25e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0663 +[2026-03-20T20:12:46.926906Z] Loop 11817: Loss: 1.40e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0692 +[2026-03-20T20:12:47.782003Z] Loop 11818: Loss: 1.42e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0728 +[2026-03-20T20:12:48.636857Z] Loop 11819: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0770 +[2026-03-20T20:12:49.530554Z] Loop 11820: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0772 +[2026-03-20T20:12:50.385334Z] Loop 11821: Loss: 1.46e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0770 +[2026-03-20T20:12:51.240667Z] Loop 11822: Loss: 1.54e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0754 +[2026-03-20T20:12:52.097981Z] Loop 11823: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0757 +[2026-03-20T20:12:52.952077Z] Loop 11824: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0763 +[2026-03-20T20:12:53.805578Z] Loop 11825: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0820 +[2026-03-20T20:12:54.659096Z] Loop 11826: Loss: 1.73e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0806 +[2026-03-20T20:12:55.514392Z] Loop 11827: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0831 +[2026-03-20T20:12:56.369071Z] Loop 11828: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0850 +[2026-03-20T20:12:57.222673Z] Loop 11829: Loss: 1.78e-02, Avg Return: 0.859, Regret: 0.0004, Entropy: 0.0880 +[2026-03-20T20:12:58.115612Z] Loop 11830: Loss: 1.76e-02, Avg Return: 0.857, Regret: 0.0066, Entropy: 0.0828 +[2026-03-20T20:12:58.970834Z] Loop 11831: Loss: 1.60e-02, Avg Return: 0.852, Regret: 0.0066, Entropy: 0.0786 +[2026-03-20T20:12:59.825154Z] Loop 11832: Loss: 1.61e-02, Avg Return: 0.854, Regret: 0.0066, Entropy: 0.0824 +[2026-03-20T20:13:00.680121Z] Loop 11833: Loss: 1.53e-02, Avg Return: 0.856, Regret: 0.0066, Entropy: 0.0778 +[2026-03-20T20:13:01.534098Z] Loop 11834: Loss: 1.37e-02, Avg Return: 0.859, Regret: 0.0066, Entropy: 0.0737 +[2026-03-20T20:13:02.388604Z] Loop 11835: Loss: 1.52e-02, Avg Return: 0.861, Regret: 0.0066, Entropy: 0.0775 +[2026-03-20T20:13:03.242085Z] Loop 11836: Loss: 1.51e-02, Avg Return: 0.861, Regret: 0.0066, Entropy: 0.0764 +[2026-03-20T20:13:04.096673Z] Loop 11837: Loss: 1.52e-02, Avg Return: 0.862, Regret: 0.0066, Entropy: 0.0740 +[2026-03-20T20:13:04.951111Z] Loop 11838: Loss: 1.40e-02, Avg Return: 0.863, Regret: 0.0066, Entropy: 0.0724 +[2026-03-20T20:13:05.804724Z] Loop 11839: Loss: 1.35e-02, Avg Return: 0.861, Regret: 0.0066, Entropy: 0.0705 +[2026-03-20T20:13:06.698193Z] Loop 11840: Loss: 1.46e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0731 +[2026-03-20T20:13:07.552519Z] Loop 11841: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0726 +[2026-03-20T20:13:08.406094Z] Loop 11842: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0703 +[2026-03-20T20:13:09.259802Z] Loop 11843: Loss: 1.45e-02, Avg Return: 0.864, Regret: 0.0015, Entropy: 0.0731 +[2026-03-20T20:13:10.113688Z] Loop 11844: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0703 +[2026-03-20T20:13:10.968298Z] Loop 11845: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0732 +[2026-03-20T20:13:11.822152Z] Loop 11846: Loss: 1.32e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0701 +[2026-03-20T20:13:12.675741Z] Loop 11847: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0723 +[2026-03-20T20:13:13.529843Z] Loop 11848: Loss: 1.44e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.0704 +[2026-03-20T20:13:14.383511Z] Loop 11849: Loss: 1.37e-02, Avg Return: 0.864, Regret: 0.0015, Entropy: 0.0699 +[2026-03-20T20:13:15.276010Z] Loop 11850: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0721 +[2026-03-20T20:13:16.129354Z] Loop 11851: Loss: 1.32e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0670 +[2026-03-20T20:13:16.982908Z] Loop 11852: Loss: 1.31e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0663 +[2026-03-20T20:13:17.836142Z] Loop 11853: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0701 +[2026-03-20T20:13:18.690232Z] Loop 11854: Loss: 1.32e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0656 +[2026-03-20T20:13:19.544764Z] Loop 11855: Loss: 1.35e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0700 +[2026-03-20T20:13:20.398535Z] Loop 11856: Loss: 1.35e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0683 +[2026-03-20T20:13:21.252603Z] Loop 11857: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0727 +[2026-03-20T20:13:22.107303Z] Loop 11858: Loss: 1.49e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0744 +[2026-03-20T20:13:22.961637Z] Loop 11859: Loss: 1.49e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0754 +[2026-03-20T20:13:23.855827Z] Loop 11860: Loss: 1.43e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0731 +[2026-03-20T20:13:24.709254Z] Loop 11861: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0802 +[2026-03-20T20:13:25.563085Z] Loop 11862: Loss: 1.74e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0829 +[2026-03-20T20:13:26.418412Z] Loop 11863: Loss: 1.68e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0851 +[2026-03-20T20:13:27.273113Z] Loop 11864: Loss: 1.93e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0921 +[2026-03-20T20:13:28.127169Z] Loop 11865: Loss: 1.86e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0914 +[2026-03-20T20:13:28.982475Z] Loop 11866: Loss: 1.87e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0940 +[2026-03-20T20:13:29.837807Z] Loop 11867: Loss: 1.79e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0859 +[2026-03-20T20:13:30.691631Z] Loop 11868: Loss: 1.72e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0868 +[2026-03-20T20:13:31.545808Z] Loop 11869: Loss: 1.76e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0852 +[2026-03-20T20:13:32.439597Z] Loop 11870: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0858 +[2026-03-20T20:13:33.293410Z] Loop 11871: Loss: 1.68e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0824 +[2026-03-20T20:13:34.147385Z] Loop 11872: Loss: 1.70e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0805 +[2026-03-20T20:13:35.001324Z] Loop 11873: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0773 +[2026-03-20T20:13:35.856288Z] Loop 11874: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0775 +[2026-03-20T20:13:36.710507Z] Loop 11875: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0778 +[2026-03-20T20:13:37.564845Z] Loop 11876: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0730 +[2026-03-20T20:13:38.419605Z] Loop 11877: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0762 +[2026-03-20T20:13:39.274504Z] Loop 11878: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0747 +[2026-03-20T20:13:40.127454Z] Loop 11879: Loss: 1.50e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0766 +[2026-03-20T20:13:41.020341Z] Loop 11880: Loss: 1.41e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0688 +[2026-03-20T20:13:41.874796Z] Loop 11881: Loss: 1.44e-02, Avg Return: 0.860, Regret: 0.0016, Entropy: 0.0746 +[2026-03-20T20:13:42.730109Z] Loop 11882: Loss: 1.40e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0734 +[2026-03-20T20:13:43.583947Z] Loop 11883: Loss: 1.43e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0752 +[2026-03-20T20:13:44.438417Z] Loop 11884: Loss: 1.61e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0807 +[2026-03-20T20:13:45.292816Z] Loop 11885: Loss: 1.60e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0785 +[2026-03-20T20:13:46.148583Z] Loop 11886: Loss: 1.56e-02, Avg Return: 0.860, Regret: 0.0016, Entropy: 0.0791 +[2026-03-20T20:13:47.003932Z] Loop 11887: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0782 +[2026-03-20T20:13:47.857236Z] Loop 11888: Loss: 1.65e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0838 +[2026-03-20T20:13:48.710682Z] Loop 11889: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0824 +[2026-03-20T20:13:49.604899Z] Loop 11890: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0800 +[2026-03-20T20:13:50.459115Z] Loop 11891: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0791 +[2026-03-20T20:13:51.313473Z] Loop 11892: Loss: 1.61e-02, Avg Return: 0.864, Regret: 0.0016, Entropy: 0.0814 +[2026-03-20T20:13:52.166593Z] Loop 11893: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0808 +[2026-03-20T20:13:53.020487Z] Loop 11894: Loss: 1.54e-02, Avg Return: 0.864, Regret: 0.0016, Entropy: 0.0751 +[2026-03-20T20:13:53.874343Z] Loop 11895: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0743 +[2026-03-20T20:13:54.728807Z] Loop 11896: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0766 +[2026-03-20T20:13:55.583050Z] Loop 11897: Loss: 1.42e-02, Avg Return: 0.865, Regret: 0.0016, Entropy: 0.0733 +[2026-03-20T20:13:56.437190Z] Loop 11898: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0798 +[2026-03-20T20:13:57.291986Z] Loop 11899: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0798 +[2026-03-20T20:13:58.187207Z] Loop 11900: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0783 +[2026-03-20T20:13:59.042255Z] Loop 11901: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0785 +[2026-03-20T20:13:59.897883Z] Loop 11902: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0796 +[2026-03-20T20:14:00.752183Z] Loop 11903: Loss: 1.49e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0757 +[2026-03-20T20:14:01.606586Z] Loop 11904: Loss: 1.54e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0777 +[2026-03-20T20:14:02.461185Z] Loop 11905: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0798 +[2026-03-20T20:14:03.315037Z] Loop 11906: Loss: 1.41e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0734 +[2026-03-20T20:14:04.170108Z] Loop 11907: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0733 +[2026-03-20T20:14:05.023936Z] Loop 11908: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0761 +[2026-03-20T20:14:05.878941Z] Loop 11909: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0765 +[2026-03-20T20:14:06.772475Z] Loop 11910: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0732 +[2026-03-20T20:14:07.625976Z] Loop 11911: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0739 +[2026-03-20T20:14:08.479666Z] Loop 11912: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0783 +[2026-03-20T20:14:09.334754Z] Loop 11913: Loss: 1.64e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0783 +[2026-03-20T20:14:10.188673Z] Loop 11914: Loss: 1.75e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0837 +[2026-03-20T20:14:11.042523Z] Loop 11915: Loss: 1.73e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0862 +[2026-03-20T20:14:11.897857Z] Loop 11916: Loss: 1.70e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0866 +[2026-03-20T20:14:12.754263Z] Loop 11917: Loss: 1.65e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0854 +[2026-03-20T20:14:13.609219Z] Loop 11918: Loss: 1.64e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0821 +[2026-03-20T20:14:14.463065Z] Loop 11919: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0788 +[2026-03-20T20:14:15.356938Z] Loop 11920: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0857 +[2026-03-20T20:14:16.211501Z] Loop 11921: Loss: 1.77e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0902 +[2026-03-20T20:14:17.065937Z] Loop 11922: Loss: 1.80e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0907 +[2026-03-20T20:14:17.919568Z] Loop 11923: Loss: 1.66e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0851 +[2026-03-20T20:14:18.772347Z] Loop 11924: Loss: 1.78e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0872 +[2026-03-20T20:14:19.625974Z] Loop 11925: Loss: 1.68e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0846 +[2026-03-20T20:14:20.481562Z] Loop 11926: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0834 +[2026-03-20T20:14:21.335680Z] Loop 11927: Loss: 1.64e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0834 +[2026-03-20T20:14:22.189216Z] Loop 11928: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0841 +[2026-03-20T20:14:23.041973Z] Loop 11929: Loss: 1.59e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0818 +[2026-03-20T20:14:23.935160Z] Loop 11930: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0787 +[2026-03-20T20:14:24.790093Z] Loop 11931: Loss: 1.60e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0807 +[2026-03-20T20:14:25.645204Z] Loop 11932: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0785 +[2026-03-20T20:14:26.500468Z] Loop 11933: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0813 +[2026-03-20T20:14:27.354607Z] Loop 11934: Loss: 1.60e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0824 +[2026-03-20T20:14:28.209637Z] Loop 11935: Loss: 1.50e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0817 +[2026-03-20T20:14:29.064921Z] Loop 11936: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0847 +[2026-03-20T20:14:29.918797Z] Loop 11937: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0823 +[2026-03-20T20:14:30.772254Z] Loop 11938: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0831 +[2026-03-20T20:14:31.625209Z] Loop 11939: Loss: 1.67e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0840 +[2026-03-20T20:14:32.520535Z] Loop 11940: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0805 +[2026-03-20T20:14:33.375471Z] Loop 11941: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0888 +[2026-03-20T20:14:34.229043Z] Loop 11942: Loss: 1.75e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0896 +[2026-03-20T20:14:35.083613Z] Loop 11943: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0902 +[2026-03-20T20:14:35.939097Z] Loop 11944: Loss: 1.93e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0985 +[2026-03-20T20:14:36.793623Z] Loop 11945: Loss: 2.06e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.1077 +[2026-03-20T20:14:37.649016Z] Loop 11946: Loss: 2.21e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.1139 +[2026-03-20T20:14:38.503352Z] Loop 11947: Loss: 2.38e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.1177 +[2026-03-20T20:14:39.357032Z] Loop 11948: Loss: 2.53e-02, Avg Return: 0.860, Regret: 0.0007, Entropy: 0.1235 +[2026-03-20T20:14:40.210366Z] Loop 11949: Loss: 2.83e-02, Avg Return: 0.860, Regret: 0.0007, Entropy: 0.1373 +[2026-03-20T20:14:41.104716Z] Loop 11950: Loss: 2.82e-02, Avg Return: 0.859, Regret: 0.0041, Entropy: 0.1434 +[2026-03-20T20:14:41.957944Z] Loop 11951: Loss: 2.97e-02, Avg Return: 0.859, Regret: 0.0041, Entropy: 0.1442 +[2026-03-20T20:14:42.811085Z] Loop 11952: Loss: 2.72e-02, Avg Return: 0.862, Regret: 0.0041, Entropy: 0.1370 +[2026-03-20T20:14:43.664306Z] Loop 11953: Loss: 2.71e-02, Avg Return: 0.863, Regret: 0.0041, Entropy: 0.1276 +[2026-03-20T20:14:44.518085Z] Loop 11954: Loss: 2.43e-02, Avg Return: 0.863, Regret: 0.0041, Entropy: 0.1195 +[2026-03-20T20:14:45.372686Z] Loop 11955: Loss: 2.46e-02, Avg Return: 0.863, Regret: 0.0041, Entropy: 0.1216 +[2026-03-20T20:14:46.226339Z] Loop 11956: Loss: 2.25e-02, Avg Return: 0.862, Regret: 0.0041, Entropy: 0.1141 +[2026-03-20T20:14:47.079720Z] Loop 11957: Loss: 2.25e-02, Avg Return: 0.863, Regret: 0.0041, Entropy: 0.1111 +[2026-03-20T20:14:47.934145Z] Loop 11958: Loss: 2.34e-02, Avg Return: 0.863, Regret: 0.0041, Entropy: 0.1169 +[2026-03-20T20:14:48.789069Z] Loop 11959: Loss: 2.28e-02, Avg Return: 0.864, Regret: 0.0041, Entropy: 0.1123 +[2026-03-20T20:14:49.682748Z] Loop 11960: Loss: 2.42e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.1183 +[2026-03-20T20:14:50.536197Z] Loop 11961: Loss: 2.36e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.1174 +[2026-03-20T20:14:51.390486Z] Loop 11962: Loss: 2.49e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.1170 +[2026-03-20T20:14:52.246470Z] Loop 11963: Loss: 2.60e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.1195 +[2026-03-20T20:14:53.101997Z] Loop 11964: Loss: 2.44e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.1180 +[2026-03-20T20:14:53.956799Z] Loop 11965: Loss: 2.38e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.1191 +[2026-03-20T20:14:54.811826Z] Loop 11966: Loss: 2.39e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.1161 +[2026-03-20T20:14:55.667390Z] Loop 11967: Loss: 2.27e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.1076 +[2026-03-20T20:14:56.523376Z] Loop 11968: Loss: 2.23e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.1120 +[2026-03-20T20:14:57.377302Z] Loop 11969: Loss: 2.09e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.1018 +[2026-03-20T20:14:58.270786Z] Loop 11970: Loss: 2.04e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.1008 +[2026-03-20T20:14:59.125487Z] Loop 11971: Loss: 2.00e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0990 +[2026-03-20T20:14:59.980378Z] Loop 11972: Loss: 1.77e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0896 +[2026-03-20T20:15:00.834695Z] Loop 11973: Loss: 1.69e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0835 +[2026-03-20T20:15:01.688681Z] Loop 11974: Loss: 1.42e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0726 +[2026-03-20T20:15:02.543710Z] Loop 11975: Loss: 1.33e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0745 +[2026-03-20T20:15:03.398398Z] Loop 11976: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0768 +[2026-03-20T20:15:04.252529Z] Loop 11977: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0739 +[2026-03-20T20:15:05.107666Z] Loop 11978: Loss: 1.53e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0778 +[2026-03-20T20:15:05.961650Z] Loop 11979: Loss: 1.49e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0778 +[2026-03-20T20:15:06.856248Z] Loop 11980: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0771 +[2026-03-20T20:15:07.711463Z] Loop 11981: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0833 +[2026-03-20T20:15:08.566995Z] Loop 11982: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0817 +[2026-03-20T20:15:09.422811Z] Loop 11983: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0811 +[2026-03-20T20:15:10.277600Z] Loop 11984: Loss: 1.62e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0825 +[2026-03-20T20:15:11.132948Z] Loop 11985: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0826 +[2026-03-20T20:15:11.987450Z] Loop 11986: Loss: 1.54e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0784 +[2026-03-20T20:15:12.843043Z] Loop 11987: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0779 +[2026-03-20T20:15:13.696556Z] Loop 11988: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0755 +[2026-03-20T20:15:14.550625Z] Loop 11989: Loss: 1.57e-02, Avg Return: 0.865, Regret: 0.0005, Entropy: 0.0776 +[2026-03-20T20:15:15.448294Z] Loop 11990: Loss: 1.63e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0806 +[2026-03-20T20:15:16.302684Z] Loop 11991: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0761 +[2026-03-20T20:15:17.157303Z] Loop 11992: Loss: 1.69e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0823 +[2026-03-20T20:15:18.011927Z] Loop 11993: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0742 +[2026-03-20T20:15:18.866755Z] Loop 11994: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0828 +[2026-03-20T20:15:19.720919Z] Loop 11995: Loss: 1.76e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0853 +[2026-03-20T20:15:20.575888Z] Loop 11996: Loss: 1.70e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0828 +[2026-03-20T20:15:21.430597Z] Loop 11997: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0869 +[2026-03-20T20:15:22.284268Z] Loop 11998: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0867 +[2026-03-20T20:15:23.138399Z] Loop 11999: Loss: 1.83e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0901 +[2026-03-20T20:15:24.034015Z] Loop 12000: Loss: 1.78e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0838 +[2026-03-20T20:15:24.887927Z] Loop 12001: Loss: 1.83e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0881 +[2026-03-20T20:15:25.743225Z] Loop 12002: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0828 +[2026-03-20T20:15:26.597261Z] Loop 12003: Loss: 1.79e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0872 +[2026-03-20T20:15:27.451386Z] Loop 12004: Loss: 1.82e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0899 +[2026-03-20T20:15:28.306577Z] Loop 12005: Loss: 1.93e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0908 +[2026-03-20T20:15:29.161315Z] Loop 12006: Loss: 1.92e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0941 +[2026-03-20T20:15:30.017087Z] Loop 12007: Loss: 1.95e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0915 +[2026-03-20T20:15:30.872590Z] Loop 12008: Loss: 1.72e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0844 +[2026-03-20T20:15:31.728998Z] Loop 12009: Loss: 1.69e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0838 +[2026-03-20T20:15:32.623762Z] Loop 12010: Loss: 1.63e-02, Avg Return: 0.865, Regret: 0.0002, Entropy: 0.0806 +[2026-03-20T20:15:33.477094Z] Loop 12011: Loss: 1.61e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0758 +[2026-03-20T20:15:34.331520Z] Loop 12012: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0754 +[2026-03-20T20:15:35.186971Z] Loop 12013: Loss: 1.51e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0730 +[2026-03-20T20:15:36.040707Z] Loop 12014: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0744 +[2026-03-20T20:15:36.894666Z] Loop 12015: Loss: 1.58e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0786 +[2026-03-20T20:15:37.748579Z] Loop 12016: Loss: 1.62e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0835 +[2026-03-20T20:15:38.602930Z] Loop 12017: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0880 +[2026-03-20T20:15:39.457363Z] Loop 12018: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0790 +[2026-03-20T20:15:40.311077Z] Loop 12019: Loss: 1.38e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0755 +[2026-03-20T20:15:41.203727Z] Loop 12020: Loss: 1.54e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0791 +[2026-03-20T20:15:42.058386Z] Loop 12021: Loss: 1.81e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0898 +[2026-03-20T20:15:42.913072Z] Loop 12022: Loss: 2.09e-02, Avg Return: 0.859, Regret: 0.0019, Entropy: 0.0965 +[2026-03-20T20:15:43.767963Z] Loop 12023: Loss: 2.08e-02, Avg Return: 0.859, Regret: 0.0019, Entropy: 0.1019 +[2026-03-20T20:15:44.622131Z] Loop 12024: Loss: 2.08e-02, Avg Return: 0.859, Regret: 0.0019, Entropy: 0.1011 +[2026-03-20T20:15:45.476269Z] Loop 12025: Loss: 1.99e-02, Avg Return: 0.859, Regret: 0.0019, Entropy: 0.0980 +[2026-03-20T20:15:46.330626Z] Loop 12026: Loss: 1.97e-02, Avg Return: 0.859, Regret: 0.0019, Entropy: 0.0956 +[2026-03-20T20:15:47.185893Z] Loop 12027: Loss: 1.89e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0937 +[2026-03-20T20:15:48.040048Z] Loop 12028: Loss: 1.95e-02, Avg Return: 0.860, Regret: 0.0019, Entropy: 0.0967 +[2026-03-20T20:15:48.894444Z] Loop 12029: Loss: 2.06e-02, Avg Return: 0.858, Regret: 0.0019, Entropy: 0.0988 +[2026-03-20T20:15:49.787882Z] Loop 12030: Loss: 1.95e-02, Avg Return: 0.861, Regret: 0.0029, Entropy: 0.0993 +[2026-03-20T20:15:50.642121Z] Loop 12031: Loss: 1.83e-02, Avg Return: 0.861, Regret: 0.0029, Entropy: 0.0938 +[2026-03-20T20:15:51.495983Z] Loop 12032: Loss: 1.93e-02, Avg Return: 0.860, Regret: 0.0029, Entropy: 0.0947 +[2026-03-20T20:15:52.350034Z] Loop 12033: Loss: 1.81e-02, Avg Return: 0.861, Regret: 0.0029, Entropy: 0.0916 +[2026-03-20T20:15:53.204519Z] Loop 12034: Loss: 1.73e-02, Avg Return: 0.860, Regret: 0.0029, Entropy: 0.0892 +[2026-03-20T20:15:54.059362Z] Loop 12035: Loss: 1.77e-02, Avg Return: 0.860, Regret: 0.0029, Entropy: 0.0888 +[2026-03-20T20:15:54.914343Z] Loop 12036: Loss: 1.77e-02, Avg Return: 0.861, Regret: 0.0029, Entropy: 0.0903 +[2026-03-20T20:15:55.770456Z] Loop 12037: Loss: 1.70e-02, Avg Return: 0.861, Regret: 0.0029, Entropy: 0.0894 +[2026-03-20T20:15:56.623659Z] Loop 12038: Loss: 1.72e-02, Avg Return: 0.861, Regret: 0.0029, Entropy: 0.0889 +[2026-03-20T20:15:57.476933Z] Loop 12039: Loss: 1.80e-02, Avg Return: 0.859, Regret: 0.0029, Entropy: 0.0933 +[2026-03-20T20:15:58.373159Z] Loop 12040: Loss: 1.91e-02, Avg Return: 0.861, Regret: 0.0017, Entropy: 0.0969 +[2026-03-20T20:15:59.227817Z] Loop 12041: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0986 +[2026-03-20T20:16:00.081475Z] Loop 12042: Loss: 1.98e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0966 +[2026-03-20T20:16:00.935436Z] Loop 12043: Loss: 1.94e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0938 +[2026-03-20T20:16:01.790876Z] Loop 12044: Loss: 2.00e-02, Avg Return: 0.863, Regret: 0.0017, Entropy: 0.0990 +[2026-03-20T20:16:02.645524Z] Loop 12045: Loss: 2.14e-02, Avg Return: 0.863, Regret: 0.0017, Entropy: 0.1033 +[2026-03-20T20:16:03.500265Z] Loop 12046: Loss: 2.16e-02, Avg Return: 0.863, Regret: 0.0017, Entropy: 0.1024 +[2026-03-20T20:16:04.353262Z] Loop 12047: Loss: 2.18e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.1026 +[2026-03-20T20:16:05.207336Z] Loop 12048: Loss: 2.09e-02, Avg Return: 0.863, Regret: 0.0017, Entropy: 0.1001 +[2026-03-20T20:16:06.065111Z] Loop 12049: Loss: 2.08e-02, Avg Return: 0.865, Regret: 0.0017, Entropy: 0.1002 +[2026-03-20T20:16:06.960443Z] Loop 12050: Loss: 2.02e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0999 +[2026-03-20T20:16:07.814811Z] Loop 12051: Loss: 2.07e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0984 +[2026-03-20T20:16:08.668714Z] Loop 12052: Loss: 2.00e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0967 +[2026-03-20T20:16:09.522500Z] Loop 12053: Loss: 1.86e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0932 +[2026-03-20T20:16:10.376801Z] Loop 12054: Loss: 1.98e-02, Avg Return: 0.865, Regret: 0.0003, Entropy: 0.0951 +[2026-03-20T20:16:11.230965Z] Loop 12055: Loss: 1.88e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0883 +[2026-03-20T20:16:12.084609Z] Loop 12056: Loss: 1.83e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0921 +[2026-03-20T20:16:12.939346Z] Loop 12057: Loss: 1.86e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0930 +[2026-03-20T20:16:13.793609Z] Loop 12058: Loss: 1.82e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0889 +[2026-03-20T20:16:14.648471Z] Loop 12059: Loss: 1.64e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0852 +[2026-03-20T20:16:15.541199Z] Loop 12060: Loss: 1.62e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0805 +[2026-03-20T20:16:16.395071Z] Loop 12061: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0750 +[2026-03-20T20:16:17.248379Z] Loop 12062: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0714 +[2026-03-20T20:16:18.103034Z] Loop 12063: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0702 +[2026-03-20T20:16:18.958016Z] Loop 12064: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0735 +[2026-03-20T20:16:19.811611Z] Loop 12065: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0742 +[2026-03-20T20:16:20.664885Z] Loop 12066: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0710 +[2026-03-20T20:16:21.518613Z] Loop 12067: Loss: 1.35e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0703 +[2026-03-20T20:16:22.373897Z] Loop 12068: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0749 +[2026-03-20T20:16:23.228662Z] Loop 12069: Loss: 1.33e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0682 +[2026-03-20T20:16:24.120982Z] Loop 12070: Loss: 1.45e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0736 +[2026-03-20T20:16:24.974253Z] Loop 12071: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0706 +[2026-03-20T20:16:25.830095Z] Loop 12072: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0742 +[2026-03-20T20:16:26.684125Z] Loop 12073: Loss: 1.47e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0740 +[2026-03-20T20:16:27.537811Z] Loop 12074: Loss: 1.40e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0705 +[2026-03-20T20:16:28.391904Z] Loop 12075: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0755 +[2026-03-20T20:16:29.246984Z] Loop 12076: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0771 +[2026-03-20T20:16:30.101548Z] Loop 12077: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0800 +[2026-03-20T20:16:30.955494Z] Loop 12078: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0796 +[2026-03-20T20:16:31.809136Z] Loop 12079: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0792 +[2026-03-20T20:16:32.704133Z] Loop 12080: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0844 +[2026-03-20T20:16:33.558684Z] Loop 12081: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0825 +[2026-03-20T20:16:34.413696Z] Loop 12082: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0763 +[2026-03-20T20:16:35.268332Z] Loop 12083: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0737 +[2026-03-20T20:16:36.124301Z] Loop 12084: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0744 +[2026-03-20T20:16:36.978591Z] Loop 12085: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0740 +[2026-03-20T20:16:37.832836Z] Loop 12086: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0740 +[2026-03-20T20:16:38.686783Z] Loop 12087: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0740 +[2026-03-20T20:16:39.541181Z] Loop 12088: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0791 +[2026-03-20T20:16:40.395125Z] Loop 12089: Loss: 1.65e-02, Avg Return: 0.865, Regret: 0.0011, Entropy: 0.0821 +[2026-03-20T20:16:41.289854Z] Loop 12090: Loss: 1.51e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0779 +[2026-03-20T20:16:42.144070Z] Loop 12091: Loss: 1.62e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0830 +[2026-03-20T20:16:42.999523Z] Loop 12092: Loss: 1.70e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0853 +[2026-03-20T20:16:43.854035Z] Loop 12093: Loss: 1.78e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0902 +[2026-03-20T20:16:44.709327Z] Loop 12094: Loss: 1.77e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0877 +[2026-03-20T20:16:45.564282Z] Loop 12095: Loss: 1.88e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0897 +[2026-03-20T20:16:46.419719Z] Loop 12096: Loss: 1.80e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0914 +[2026-03-20T20:16:47.273784Z] Loop 12097: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0864 +[2026-03-20T20:16:48.128883Z] Loop 12098: Loss: 1.82e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0886 +[2026-03-20T20:16:48.983905Z] Loop 12099: Loss: 1.82e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0883 +[2026-03-20T20:16:49.879152Z] Loop 12100: Loss: 1.85e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0915 +[2026-03-20T20:16:50.733436Z] Loop 12101: Loss: 1.99e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0979 +[2026-03-20T20:16:51.588855Z] Loop 12102: Loss: 2.04e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0995 +[2026-03-20T20:16:52.444134Z] Loop 12103: Loss: 1.99e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0986 +[2026-03-20T20:16:53.299771Z] Loop 12104: Loss: 1.89e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0944 +[2026-03-20T20:16:54.154639Z] Loop 12105: Loss: 1.98e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0965 +[2026-03-20T20:16:55.008085Z] Loop 12106: Loss: 2.01e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0999 +[2026-03-20T20:16:55.862193Z] Loop 12107: Loss: 2.10e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.1061 +[2026-03-20T20:16:56.719356Z] Loop 12108: Loss: 2.16e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.1083 +[2026-03-20T20:16:57.573636Z] Loop 12109: Loss: 2.11e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.1109 +[2026-03-20T20:16:58.469890Z] Loop 12110: Loss: 2.11e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.1035 +[2026-03-20T20:16:59.323988Z] Loop 12111: Loss: 1.80e-02, Avg Return: 0.860, Regret: 0.0021, Entropy: 0.0948 +[2026-03-20T20:17:00.177243Z] Loop 12112: Loss: 1.83e-02, Avg Return: 0.860, Regret: 0.0021, Entropy: 0.0921 +[2026-03-20T20:17:01.031580Z] Loop 12113: Loss: 2.08e-02, Avg Return: 0.860, Regret: 0.0021, Entropy: 0.0994 +[2026-03-20T20:17:01.885369Z] Loop 12114: Loss: 2.04e-02, Avg Return: 0.859, Regret: 0.0021, Entropy: 0.1052 +[2026-03-20T20:17:02.740528Z] Loop 12115: Loss: 2.04e-02, Avg Return: 0.859, Regret: 0.0021, Entropy: 0.1083 +[2026-03-20T20:17:03.594704Z] Loop 12116: Loss: 2.22e-02, Avg Return: 0.857, Regret: 0.0021, Entropy: 0.1141 +[2026-03-20T20:17:04.448599Z] Loop 12117: Loss: 2.21e-02, Avg Return: 0.858, Regret: 0.0021, Entropy: 0.1104 +[2026-03-20T20:17:05.303513Z] Loop 12118: Loss: 2.14e-02, Avg Return: 0.857, Regret: 0.0021, Entropy: 0.1053 +[2026-03-20T20:17:06.157667Z] Loop 12119: Loss: 2.30e-02, Avg Return: 0.858, Regret: 0.0021, Entropy: 0.1122 +[2026-03-20T20:17:07.053562Z] Loop 12120: Loss: 2.22e-02, Avg Return: 0.856, Regret: 0.0067, Entropy: 0.1099 +[2026-03-20T20:17:07.907850Z] Loop 12121: Loss: 2.28e-02, Avg Return: 0.856, Regret: 0.0067, Entropy: 0.1131 +[2026-03-20T20:17:08.763250Z] Loop 12122: Loss: 2.22e-02, Avg Return: 0.855, Regret: 0.0067, Entropy: 0.1100 +[2026-03-20T20:17:09.618506Z] Loop 12123: Loss: 2.22e-02, Avg Return: 0.855, Regret: 0.0067, Entropy: 0.1130 +[2026-03-20T20:17:10.472160Z] Loop 12124: Loss: 2.40e-02, Avg Return: 0.858, Regret: 0.0067, Entropy: 0.1142 +[2026-03-20T20:17:11.324938Z] Loop 12125: Loss: 2.24e-02, Avg Return: 0.860, Regret: 0.0067, Entropy: 0.1113 +[2026-03-20T20:17:12.178109Z] Loop 12126: Loss: 2.37e-02, Avg Return: 0.860, Regret: 0.0067, Entropy: 0.1132 +[2026-03-20T20:17:13.032468Z] Loop 12127: Loss: 2.22e-02, Avg Return: 0.860, Regret: 0.0067, Entropy: 0.1121 +[2026-03-20T20:17:13.886923Z] Loop 12128: Loss: 2.45e-02, Avg Return: 0.859, Regret: 0.0067, Entropy: 0.1198 +[2026-03-20T20:17:14.739729Z] Loop 12129: Loss: 2.47e-02, Avg Return: 0.858, Regret: 0.0067, Entropy: 0.1199 +[2026-03-20T20:17:15.632466Z] Loop 12130: Loss: 2.39e-02, Avg Return: 0.862, Regret: 0.0035, Entropy: 0.1128 +[2026-03-20T20:17:16.486505Z] Loop 12131: Loss: 2.44e-02, Avg Return: 0.860, Regret: 0.0035, Entropy: 0.1206 +[2026-03-20T20:17:17.340487Z] Loop 12132: Loss: 2.45e-02, Avg Return: 0.860, Regret: 0.0035, Entropy: 0.1200 +[2026-03-20T20:17:18.194826Z] Loop 12133: Loss: 2.40e-02, Avg Return: 0.861, Regret: 0.0035, Entropy: 0.1192 +[2026-03-20T20:17:19.048778Z] Loop 12134: Loss: 2.39e-02, Avg Return: 0.861, Regret: 0.0035, Entropy: 0.1181 +[2026-03-20T20:17:19.903909Z] Loop 12135: Loss: 2.23e-02, Avg Return: 0.862, Regret: 0.0035, Entropy: 0.1133 +[2026-03-20T20:17:20.758398Z] Loop 12136: Loss: 2.33e-02, Avg Return: 0.863, Regret: 0.0035, Entropy: 0.1162 +[2026-03-20T20:17:21.612549Z] Loop 12137: Loss: 2.39e-02, Avg Return: 0.860, Regret: 0.0035, Entropy: 0.1199 +[2026-03-20T20:17:22.466757Z] Loop 12138: Loss: 2.38e-02, Avg Return: 0.861, Regret: 0.0035, Entropy: 0.1174 +[2026-03-20T20:17:23.320385Z] Loop 12139: Loss: 2.44e-02, Avg Return: 0.861, Regret: 0.0035, Entropy: 0.1198 +[2026-03-20T20:17:24.216432Z] Loop 12140: Loss: 2.35e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.1187 +[2026-03-20T20:17:25.069763Z] Loop 12141: Loss: 2.48e-02, Avg Return: 0.860, Regret: 0.0021, Entropy: 0.1224 +[2026-03-20T20:17:25.923753Z] Loop 12142: Loss: 2.34e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.1169 +[2026-03-20T20:17:26.778079Z] Loop 12143: Loss: 2.56e-02, Avg Return: 0.863, Regret: 0.0021, Entropy: 0.1183 +[2026-03-20T20:17:27.632856Z] Loop 12144: Loss: 2.37e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.1199 +[2026-03-20T20:17:28.485857Z] Loop 12145: Loss: 2.42e-02, Avg Return: 0.863, Regret: 0.0021, Entropy: 0.1209 +[2026-03-20T20:17:29.339369Z] Loop 12146: Loss: 2.53e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.1216 +[2026-03-20T20:17:30.193339Z] Loop 12147: Loss: 2.52e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.1215 +[2026-03-20T20:17:31.046883Z] Loop 12148: Loss: 2.41e-02, Avg Return: 0.863, Regret: 0.0021, Entropy: 0.1199 +[2026-03-20T20:17:31.901008Z] Loop 12149: Loss: 2.32e-02, Avg Return: 0.860, Regret: 0.0021, Entropy: 0.1168 +[2026-03-20T20:17:32.795815Z] Loop 12150: Loss: 2.22e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.1169 +[2026-03-20T20:17:33.649346Z] Loop 12151: Loss: 2.26e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.1151 +[2026-03-20T20:17:34.503678Z] Loop 12152: Loss: 2.24e-02, Avg Return: 0.860, Regret: 0.0018, Entropy: 0.1186 +[2026-03-20T20:17:35.358528Z] Loop 12153: Loss: 2.28e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.1174 +[2026-03-20T20:17:36.213173Z] Loop 12154: Loss: 2.52e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.1225 +[2026-03-20T20:17:37.066557Z] Loop 12155: Loss: 2.47e-02, Avg Return: 0.860, Regret: 0.0018, Entropy: 0.1261 +[2026-03-20T20:17:37.919112Z] Loop 12156: Loss: 2.60e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.1301 +[2026-03-20T20:17:38.772583Z] Loop 12157: Loss: 2.59e-02, Avg Return: 0.860, Regret: 0.0018, Entropy: 0.1370 +[2026-03-20T20:17:39.626789Z] Loop 12158: Loss: 2.51e-02, Avg Return: 0.860, Regret: 0.0018, Entropy: 0.1300 +[2026-03-20T20:17:40.480299Z] Loop 12159: Loss: 2.62e-02, Avg Return: 0.860, Regret: 0.0018, Entropy: 0.1291 +[2026-03-20T20:17:41.373847Z] Loop 12160: Loss: 2.40e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.1252 +[2026-03-20T20:17:42.227960Z] Loop 12161: Loss: 2.29e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.1193 +[2026-03-20T20:17:43.083608Z] Loop 12162: Loss: 2.26e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.1172 +[2026-03-20T20:17:43.938852Z] Loop 12163: Loss: 2.36e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.1201 +[2026-03-20T20:17:44.793149Z] Loop 12164: Loss: 2.47e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.1252 +[2026-03-20T20:17:45.646125Z] Loop 12165: Loss: 2.51e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.1255 +[2026-03-20T20:17:46.501136Z] Loop 12166: Loss: 2.58e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.1283 +[2026-03-20T20:17:47.355246Z] Loop 12167: Loss: 2.60e-02, Avg Return: 0.860, Regret: 0.0025, Entropy: 0.1241 +[2026-03-20T20:17:48.208972Z] Loop 12168: Loss: 2.51e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.1219 +[2026-03-20T20:17:49.062475Z] Loop 12169: Loss: 2.51e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.1237 +[2026-03-20T20:17:49.956655Z] Loop 12170: Loss: 2.55e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.1206 +[2026-03-20T20:17:50.810737Z] Loop 12171: Loss: 2.42e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.1220 +[2026-03-20T20:17:51.665019Z] Loop 12172: Loss: 2.51e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.1257 +[2026-03-20T20:17:52.519521Z] Loop 12173: Loss: 2.57e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.1216 +[2026-03-20T20:17:53.373234Z] Loop 12174: Loss: 2.52e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.1249 +[2026-03-20T20:17:54.226555Z] Loop 12175: Loss: 2.43e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.1241 +[2026-03-20T20:17:55.080865Z] Loop 12176: Loss: 2.44e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.1217 +[2026-03-20T20:17:55.935568Z] Loop 12177: Loss: 2.36e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.1203 +[2026-03-20T20:17:56.790199Z] Loop 12178: Loss: 2.26e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.1095 +[2026-03-20T20:17:57.644026Z] Loop 12179: Loss: 2.15e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.1088 +[2026-03-20T20:17:58.538943Z] Loop 12180: Loss: 2.06e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.1069 +[2026-03-20T20:17:59.394306Z] Loop 12181: Loss: 2.12e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.1076 +[2026-03-20T20:18:00.249183Z] Loop 12182: Loss: 2.11e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.1108 +[2026-03-20T20:18:01.103574Z] Loop 12183: Loss: 2.08e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.1102 +[2026-03-20T20:18:01.957769Z] Loop 12184: Loss: 2.27e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.1162 +[2026-03-20T20:18:02.812887Z] Loop 12185: Loss: 2.54e-02, Avg Return: 0.860, Regret: 0.0009, Entropy: 0.1299 +[2026-03-20T20:18:03.668135Z] Loop 12186: Loss: 2.78e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.1381 +[2026-03-20T20:18:04.522808Z] Loop 12187: Loss: 2.71e-02, Avg Return: 0.859, Regret: 0.0009, Entropy: 0.1402 +[2026-03-20T20:18:05.375880Z] Loop 12188: Loss: 2.99e-02, Avg Return: 0.858, Regret: 0.0009, Entropy: 0.1496 +[2026-03-20T20:18:06.230624Z] Loop 12189: Loss: 3.06e-02, Avg Return: 0.856, Regret: 0.0009, Entropy: 0.1515 +[2026-03-20T20:18:07.126161Z] Loop 12190: Loss: 3.11e-02, Avg Return: 0.857, Regret: 0.0071, Entropy: 0.1523 +[2026-03-20T20:18:07.979308Z] Loop 12191: Loss: 2.90e-02, Avg Return: 0.859, Regret: 0.0071, Entropy: 0.1422 +[2026-03-20T20:18:08.833592Z] Loop 12192: Loss: 2.50e-02, Avg Return: 0.859, Regret: 0.0071, Entropy: 0.1276 +[2026-03-20T20:18:09.688778Z] Loop 12193: Loss: 2.51e-02, Avg Return: 0.861, Regret: 0.0071, Entropy: 0.1206 +[2026-03-20T20:18:10.543939Z] Loop 12194: Loss: 2.33e-02, Avg Return: 0.859, Regret: 0.0071, Entropy: 0.1153 +[2026-03-20T20:18:11.398592Z] Loop 12195: Loss: 2.43e-02, Avg Return: 0.862, Regret: 0.0071, Entropy: 0.1157 +[2026-03-20T20:18:12.253679Z] Loop 12196: Loss: 2.29e-02, Avg Return: 0.859, Regret: 0.0071, Entropy: 0.1133 +[2026-03-20T20:18:13.108663Z] Loop 12197: Loss: 2.16e-02, Avg Return: 0.859, Regret: 0.0071, Entropy: 0.1114 +[2026-03-20T20:18:13.963056Z] Loop 12198: Loss: 2.24e-02, Avg Return: 0.858, Regret: 0.0071, Entropy: 0.1092 +[2026-03-20T20:18:14.818312Z] Loop 12199: Loss: 2.22e-02, Avg Return: 0.858, Regret: 0.0071, Entropy: 0.1101 +[2026-03-20T20:18:15.711755Z] Loop 12200: Loss: 2.16e-02, Avg Return: 0.858, Regret: 0.0045, Entropy: 0.1045 +[2026-03-20T20:18:16.567140Z] Loop 12201: Loss: 2.16e-02, Avg Return: 0.858, Regret: 0.0045, Entropy: 0.1115 +[2026-03-20T20:18:17.420942Z] Loop 12202: Loss: 2.25e-02, Avg Return: 0.857, Regret: 0.0045, Entropy: 0.1101 +[2026-03-20T20:18:18.274713Z] Loop 12203: Loss: 2.17e-02, Avg Return: 0.858, Regret: 0.0045, Entropy: 0.1046 +[2026-03-20T20:18:19.128754Z] Loop 12204: Loss: 2.23e-02, Avg Return: 0.858, Regret: 0.0045, Entropy: 0.1103 +[2026-03-20T20:18:19.983940Z] Loop 12205: Loss: 2.15e-02, Avg Return: 0.858, Regret: 0.0045, Entropy: 0.1037 +[2026-03-20T20:18:20.837307Z] Loop 12206: Loss: 2.00e-02, Avg Return: 0.857, Regret: 0.0045, Entropy: 0.1023 +[2026-03-20T20:18:21.690216Z] Loop 12207: Loss: 2.22e-02, Avg Return: 0.858, Regret: 0.0045, Entropy: 0.1077 +[2026-03-20T20:18:22.543720Z] Loop 12208: Loss: 2.12e-02, Avg Return: 0.857, Regret: 0.0045, Entropy: 0.1076 +[2026-03-20T20:18:23.399339Z] Loop 12209: Loss: 2.16e-02, Avg Return: 0.858, Regret: 0.0045, Entropy: 0.1071 +[2026-03-20T20:18:24.296196Z] Loop 12210: Loss: 2.15e-02, Avg Return: 0.860, Regret: 0.0034, Entropy: 0.1083 +[2026-03-20T20:18:25.150716Z] Loop 12211: Loss: 2.09e-02, Avg Return: 0.862, Regret: 0.0034, Entropy: 0.1022 +[2026-03-20T20:18:26.004580Z] Loop 12212: Loss: 1.87e-02, Avg Return: 0.860, Regret: 0.0034, Entropy: 0.0932 +[2026-03-20T20:18:26.858796Z] Loop 12213: Loss: 1.52e-02, Avg Return: 0.862, Regret: 0.0034, Entropy: 0.0820 +[2026-03-20T20:18:27.713254Z] Loop 12214: Loss: 1.59e-02, Avg Return: 0.864, Regret: 0.0034, Entropy: 0.0822 +[2026-03-20T20:18:28.566491Z] Loop 12215: Loss: 1.67e-02, Avg Return: 0.862, Regret: 0.0034, Entropy: 0.0849 +[2026-03-20T20:18:29.420144Z] Loop 12216: Loss: 1.94e-02, Avg Return: 0.864, Regret: 0.0034, Entropy: 0.0938 +[2026-03-20T20:18:30.273730Z] Loop 12217: Loss: 2.16e-02, Avg Return: 0.864, Regret: 0.0034, Entropy: 0.1047 +[2026-03-20T20:18:31.127480Z] Loop 12218: Loss: 2.28e-02, Avg Return: 0.862, Regret: 0.0034, Entropy: 0.1082 +[2026-03-20T20:18:31.981313Z] Loop 12219: Loss: 2.15e-02, Avg Return: 0.864, Regret: 0.0034, Entropy: 0.1002 +[2026-03-20T20:18:32.875754Z] Loop 12220: Loss: 2.14e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0974 +[2026-03-20T20:18:33.729381Z] Loop 12221: Loss: 1.97e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0921 +[2026-03-20T20:18:34.583476Z] Loop 12222: Loss: 1.83e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0888 +[2026-03-20T20:18:35.438008Z] Loop 12223: Loss: 1.78e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0861 +[2026-03-20T20:18:36.291677Z] Loop 12224: Loss: 1.82e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0893 +[2026-03-20T20:18:37.146230Z] Loop 12225: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0884 +[2026-03-20T20:18:38.000345Z] Loop 12226: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0811 +[2026-03-20T20:18:38.855671Z] Loop 12227: Loss: 1.54e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0788 +[2026-03-20T20:18:39.710143Z] Loop 12228: Loss: 1.40e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0721 +[2026-03-20T20:18:40.564614Z] Loop 12229: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0739 +[2026-03-20T20:18:41.460245Z] Loop 12230: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0749 +[2026-03-20T20:18:42.315076Z] Loop 12231: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0791 +[2026-03-20T20:18:43.169757Z] Loop 12232: Loss: 1.73e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0840 +[2026-03-20T20:18:44.023553Z] Loop 12233: Loss: 1.73e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0854 +[2026-03-20T20:18:44.877169Z] Loop 12234: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0803 +[2026-03-20T20:18:45.730222Z] Loop 12235: Loss: 1.62e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0811 +[2026-03-20T20:18:46.584633Z] Loop 12236: Loss: 1.55e-02, Avg Return: 0.860, Regret: 0.0008, Entropy: 0.0773 +[2026-03-20T20:18:47.439919Z] Loop 12237: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0777 +[2026-03-20T20:18:48.293230Z] Loop 12238: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0756 +[2026-03-20T20:18:49.146703Z] Loop 12239: Loss: 1.63e-02, Avg Return: 0.860, Regret: 0.0008, Entropy: 0.0783 +[2026-03-20T20:18:50.041324Z] Loop 12240: Loss: 1.43e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0767 +[2026-03-20T20:18:50.895749Z] Loop 12241: Loss: 1.52e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0782 +[2026-03-20T20:18:51.749417Z] Loop 12242: Loss: 1.55e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.0813 +[2026-03-20T20:18:52.602491Z] Loop 12243: Loss: 1.68e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0810 +[2026-03-20T20:18:53.457269Z] Loop 12244: Loss: 1.59e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.0804 +[2026-03-20T20:18:54.311401Z] Loop 12245: Loss: 1.48e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.0752 +[2026-03-20T20:18:55.164964Z] Loop 12246: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0022, Entropy: 0.0777 +[2026-03-20T20:18:56.018376Z] Loop 12247: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0022, Entropy: 0.0778 +[2026-03-20T20:18:56.872580Z] Loop 12248: Loss: 1.62e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0831 +[2026-03-20T20:18:57.727161Z] Loop 12249: Loss: 1.68e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0801 +[2026-03-20T20:18:58.620489Z] Loop 12250: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0828 +[2026-03-20T20:18:59.474051Z] Loop 12251: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0794 +[2026-03-20T20:19:00.328139Z] Loop 12252: Loss: 1.75e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0850 +[2026-03-20T20:19:01.182508Z] Loop 12253: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0831 +[2026-03-20T20:19:02.036499Z] Loop 12254: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0810 +[2026-03-20T20:19:02.891671Z] Loop 12255: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0824 +[2026-03-20T20:19:03.745155Z] Loop 12256: Loss: 1.69e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0825 +[2026-03-20T20:19:04.598804Z] Loop 12257: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0800 +[2026-03-20T20:19:05.452459Z] Loop 12258: Loss: 1.72e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0828 +[2026-03-20T20:19:06.306607Z] Loop 12259: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0814 +[2026-03-20T20:19:07.201627Z] Loop 12260: Loss: 1.59e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0795 +[2026-03-20T20:19:08.054838Z] Loop 12261: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0792 +[2026-03-20T20:19:08.909062Z] Loop 12262: Loss: 1.63e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0834 +[2026-03-20T20:19:09.764675Z] Loop 12263: Loss: 1.80e-02, Avg Return: 0.865, Regret: 0.0004, Entropy: 0.0844 +[2026-03-20T20:19:10.618960Z] Loop 12264: Loss: 1.60e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0779 +[2026-03-20T20:19:11.472855Z] Loop 12265: Loss: 1.47e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0776 +[2026-03-20T20:19:12.326167Z] Loop 12266: Loss: 1.49e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0752 +[2026-03-20T20:19:13.180599Z] Loop 12267: Loss: 1.55e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0743 +[2026-03-20T20:19:14.033992Z] Loop 12268: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0782 +[2026-03-20T20:19:14.887935Z] Loop 12269: Loss: 1.64e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0796 +[2026-03-20T20:19:15.781816Z] Loop 12270: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0805 +[2026-03-20T20:19:16.636338Z] Loop 12271: Loss: 1.64e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0790 +[2026-03-20T20:19:17.491757Z] Loop 12272: Loss: 1.59e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0802 +[2026-03-20T20:19:18.346740Z] Loop 12273: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0779 +[2026-03-20T20:19:19.201356Z] Loop 12274: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0732 +[2026-03-20T20:19:20.056402Z] Loop 12275: Loss: 1.48e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0751 +[2026-03-20T20:19:20.911245Z] Loop 12276: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0730 +[2026-03-20T20:19:21.766427Z] Loop 12277: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0758 +[2026-03-20T20:19:22.620068Z] Loop 12278: Loss: 1.44e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0749 +[2026-03-20T20:19:23.473163Z] Loop 12279: Loss: 1.54e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0747 +[2026-03-20T20:19:24.366770Z] Loop 12280: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0701 +[2026-03-20T20:19:25.220839Z] Loop 12281: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0729 +[2026-03-20T20:19:26.075296Z] Loop 12282: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0693 +[2026-03-20T20:19:26.928919Z] Loop 12283: Loss: 1.34e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0705 +[2026-03-20T20:19:27.782873Z] Loop 12284: Loss: 1.27e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0634 +[2026-03-20T20:19:28.637490Z] Loop 12285: Loss: 1.38e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0741 +[2026-03-20T20:19:29.491983Z] Loop 12286: Loss: 1.36e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0710 +[2026-03-20T20:19:30.346226Z] Loop 12287: Loss: 1.64e-02, Avg Return: 0.860, Regret: 0.0008, Entropy: 0.0811 +[2026-03-20T20:19:31.200179Z] Loop 12288: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0776 +[2026-03-20T20:19:32.053707Z] Loop 12289: Loss: 1.55e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0800 +[2026-03-20T20:19:32.948104Z] Loop 12290: Loss: 1.71e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0849 +[2026-03-20T20:19:33.802741Z] Loop 12291: Loss: 1.68e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0823 +[2026-03-20T20:19:34.656203Z] Loop 12292: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0801 +[2026-03-20T20:19:35.509777Z] Loop 12293: Loss: 1.77e-02, Avg Return: 0.863, Regret: 0.0017, Entropy: 0.0836 +[2026-03-20T20:19:36.363936Z] Loop 12294: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0816 +[2026-03-20T20:19:37.219228Z] Loop 12295: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0831 +[2026-03-20T20:19:38.072887Z] Loop 12296: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0017, Entropy: 0.0781 +[2026-03-20T20:19:38.925959Z] Loop 12297: Loss: 1.45e-02, Avg Return: 0.864, Regret: 0.0017, Entropy: 0.0753 +[2026-03-20T20:19:39.779666Z] Loop 12298: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0017, Entropy: 0.0749 +[2026-03-20T20:19:40.634482Z] Loop 12299: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0017, Entropy: 0.0720 +[2026-03-20T20:19:41.528583Z] Loop 12300: Loss: 1.43e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0733 +[2026-03-20T20:19:42.382407Z] Loop 12301: Loss: 1.58e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0789 +[2026-03-20T20:19:43.236920Z] Loop 12302: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0773 +[2026-03-20T20:19:44.091868Z] Loop 12303: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0814 +[2026-03-20T20:19:44.945341Z] Loop 12304: Loss: 1.68e-02, Avg Return: 0.865, Regret: 0.0001, Entropy: 0.0847 +[2026-03-20T20:19:45.798915Z] Loop 12305: Loss: 1.55e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0771 +[2026-03-20T20:19:46.652355Z] Loop 12306: Loss: 1.43e-02, Avg Return: 0.865, Regret: 0.0001, Entropy: 0.0749 +[2026-03-20T20:19:47.506198Z] Loop 12307: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0715 +[2026-03-20T20:19:48.360022Z] Loop 12308: Loss: 1.47e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0731 +[2026-03-20T20:19:49.213510Z] Loop 12309: Loss: 1.39e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0706 +[2026-03-20T20:19:50.109728Z] Loop 12310: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0751 +[2026-03-20T20:19:50.964355Z] Loop 12311: Loss: 1.57e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0767 +[2026-03-20T20:19:51.819472Z] Loop 12312: Loss: 1.73e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0823 +[2026-03-20T20:19:52.674052Z] Loop 12313: Loss: 1.70e-02, Avg Return: 0.861, Regret: 0.0004, Entropy: 0.0821 +[2026-03-20T20:19:53.527918Z] Loop 12314: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0852 +[2026-03-20T20:19:54.383362Z] Loop 12315: Loss: 1.80e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0869 +[2026-03-20T20:19:55.238196Z] Loop 12316: Loss: 1.72e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0886 +[2026-03-20T20:19:56.092755Z] Loop 12317: Loss: 1.76e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0868 +[2026-03-20T20:19:56.946580Z] Loop 12318: Loss: 1.78e-02, Avg Return: 0.860, Regret: 0.0004, Entropy: 0.0883 +[2026-03-20T20:19:57.801924Z] Loop 12319: Loss: 1.85e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0912 +[2026-03-20T20:19:58.695710Z] Loop 12320: Loss: 1.90e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0900 +[2026-03-20T20:19:59.549845Z] Loop 12321: Loss: 1.75e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.0884 +[2026-03-20T20:20:00.403563Z] Loop 12322: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0864 +[2026-03-20T20:20:01.258439Z] Loop 12323: Loss: 1.93e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.0938 +[2026-03-20T20:20:02.112803Z] Loop 12324: Loss: 1.83e-02, Avg Return: 0.860, Regret: 0.0014, Entropy: 0.0901 +[2026-03-20T20:20:02.968622Z] Loop 12325: Loss: 1.84e-02, Avg Return: 0.860, Regret: 0.0014, Entropy: 0.0894 +[2026-03-20T20:20:03.822163Z] Loop 12326: Loss: 1.88e-02, Avg Return: 0.860, Regret: 0.0014, Entropy: 0.0892 +[2026-03-20T20:20:04.676605Z] Loop 12327: Loss: 1.79e-02, Avg Return: 0.859, Regret: 0.0014, Entropy: 0.0866 +[2026-03-20T20:20:05.529393Z] Loop 12328: Loss: 1.78e-02, Avg Return: 0.859, Regret: 0.0014, Entropy: 0.0869 +[2026-03-20T20:20:06.383709Z] Loop 12329: Loss: 1.81e-02, Avg Return: 0.858, Regret: 0.0014, Entropy: 0.0878 +[2026-03-20T20:20:07.276839Z] Loop 12330: Loss: 1.62e-02, Avg Return: 0.859, Regret: 0.0059, Entropy: 0.0827 +[2026-03-20T20:20:08.130876Z] Loop 12331: Loss: 1.67e-02, Avg Return: 0.857, Regret: 0.0059, Entropy: 0.0799 +[2026-03-20T20:20:08.984728Z] Loop 12332: Loss: 1.51e-02, Avg Return: 0.858, Regret: 0.0059, Entropy: 0.0787 +[2026-03-20T20:20:09.838005Z] Loop 12333: Loss: 1.53e-02, Avg Return: 0.856, Regret: 0.0059, Entropy: 0.0769 +[2026-03-20T20:20:10.691709Z] Loop 12334: Loss: 1.55e-02, Avg Return: 0.857, Regret: 0.0059, Entropy: 0.0773 +[2026-03-20T20:20:11.545890Z] Loop 12335: Loss: 1.50e-02, Avg Return: 0.856, Regret: 0.0059, Entropy: 0.0760 +[2026-03-20T20:20:12.399142Z] Loop 12336: Loss: 1.51e-02, Avg Return: 0.858, Regret: 0.0059, Entropy: 0.0822 +[2026-03-20T20:20:13.252790Z] Loop 12337: Loss: 1.59e-02, Avg Return: 0.859, Regret: 0.0059, Entropy: 0.0760 +[2026-03-20T20:20:14.105552Z] Loop 12338: Loss: 1.61e-02, Avg Return: 0.859, Regret: 0.0059, Entropy: 0.0781 +[2026-03-20T20:20:14.959545Z] Loop 12339: Loss: 1.65e-02, Avg Return: 0.859, Regret: 0.0059, Entropy: 0.0806 +[2026-03-20T20:20:15.851764Z] Loop 12340: Loss: 1.67e-02, Avg Return: 0.860, Regret: 0.0031, Entropy: 0.0870 +[2026-03-20T20:20:16.706817Z] Loop 12341: Loss: 1.88e-02, Avg Return: 0.860, Regret: 0.0031, Entropy: 0.0944 +[2026-03-20T20:20:17.561604Z] Loop 12342: Loss: 2.00e-02, Avg Return: 0.861, Regret: 0.0031, Entropy: 0.0956 +[2026-03-20T20:20:18.416883Z] Loop 12343: Loss: 1.94e-02, Avg Return: 0.862, Regret: 0.0031, Entropy: 0.0963 +[2026-03-20T20:20:19.272882Z] Loop 12344: Loss: 1.93e-02, Avg Return: 0.862, Regret: 0.0031, Entropy: 0.0934 +[2026-03-20T20:20:20.128458Z] Loop 12345: Loss: 1.66e-02, Avg Return: 0.861, Regret: 0.0031, Entropy: 0.0823 +[2026-03-20T20:20:20.983197Z] Loop 12346: Loss: 1.54e-02, Avg Return: 0.862, Regret: 0.0031, Entropy: 0.0779 +[2026-03-20T20:20:21.838177Z] Loop 12347: Loss: 1.63e-02, Avg Return: 0.862, Regret: 0.0031, Entropy: 0.0813 +[2026-03-20T20:20:22.691749Z] Loop 12348: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0031, Entropy: 0.0766 +[2026-03-20T20:20:23.546026Z] Loop 12349: Loss: 1.62e-02, Avg Return: 0.865, Regret: 0.0031, Entropy: 0.0784 +[2026-03-20T20:20:24.439015Z] Loop 12350: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0788 +[2026-03-20T20:20:25.294072Z] Loop 12351: Loss: 1.71e-02, Avg Return: 0.865, Regret: 0.0003, Entropy: 0.0815 +[2026-03-20T20:20:26.148951Z] Loop 12352: Loss: 1.59e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0786 +[2026-03-20T20:20:27.003618Z] Loop 12353: Loss: 1.42e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0758 +[2026-03-20T20:20:27.858830Z] Loop 12354: Loss: 1.53e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0772 +[2026-03-20T20:20:28.712686Z] Loop 12355: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0739 +[2026-03-20T20:20:29.566355Z] Loop 12356: Loss: 1.46e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0744 +[2026-03-20T20:20:30.419757Z] Loop 12357: Loss: 1.54e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0793 +[2026-03-20T20:20:31.275232Z] Loop 12358: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0778 +[2026-03-20T20:20:32.130139Z] Loop 12359: Loss: 1.55e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0791 +[2026-03-20T20:20:33.025593Z] Loop 12360: Loss: 1.67e-02, Avg Return: 0.865, Regret: 0.0002, Entropy: 0.0792 +[2026-03-20T20:20:33.879506Z] Loop 12361: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0819 +[2026-03-20T20:20:34.733577Z] Loop 12362: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0815 +[2026-03-20T20:20:35.588654Z] Loop 12363: Loss: 1.54e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0802 +[2026-03-20T20:20:36.442597Z] Loop 12364: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0824 +[2026-03-20T20:20:37.296872Z] Loop 12365: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0787 +[2026-03-20T20:20:38.151840Z] Loop 12366: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0801 +[2026-03-20T20:20:39.007498Z] Loop 12367: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0775 +[2026-03-20T20:20:39.863139Z] Loop 12368: Loss: 1.51e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0775 +[2026-03-20T20:20:40.716767Z] Loop 12369: Loss: 1.59e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0798 +[2026-03-20T20:20:41.610944Z] Loop 12370: Loss: 1.53e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0781 +[2026-03-20T20:20:42.465922Z] Loop 12371: Loss: 1.72e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0818 +[2026-03-20T20:20:43.321550Z] Loop 12372: Loss: 1.54e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0784 +[2026-03-20T20:20:44.177138Z] Loop 12373: Loss: 1.58e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0801 +[2026-03-20T20:20:45.031368Z] Loop 12374: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0765 +[2026-03-20T20:20:45.886071Z] Loop 12375: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0722 +[2026-03-20T20:20:46.741249Z] Loop 12376: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0706 +[2026-03-20T20:20:47.596292Z] Loop 12377: Loss: 1.47e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0736 +[2026-03-20T20:20:48.451153Z] Loop 12378: Loss: 1.51e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0757 +[2026-03-20T20:20:49.305342Z] Loop 12379: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0846 +[2026-03-20T20:20:50.201658Z] Loop 12380: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0800 +[2026-03-20T20:20:51.057174Z] Loop 12381: Loss: 1.83e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0813 +[2026-03-20T20:20:51.911882Z] Loop 12382: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0799 +[2026-03-20T20:20:52.766851Z] Loop 12383: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0803 +[2026-03-20T20:20:53.621451Z] Loop 12384: Loss: 1.61e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.0806 +[2026-03-20T20:20:54.476772Z] Loop 12385: Loss: 1.63e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0813 +[2026-03-20T20:20:55.332545Z] Loop 12386: Loss: 1.71e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0825 +[2026-03-20T20:20:56.187793Z] Loop 12387: Loss: 1.58e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.0823 +[2026-03-20T20:20:57.042804Z] Loop 12388: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0830 +[2026-03-20T20:20:57.898860Z] Loop 12389: Loss: 1.47e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.0805 +[2026-03-20T20:20:58.794799Z] Loop 12390: Loss: 1.74e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.0856 +[2026-03-20T20:20:59.648973Z] Loop 12391: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0801 +[2026-03-20T20:21:00.503071Z] Loop 12392: Loss: 1.50e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.0782 +[2026-03-20T20:21:01.358106Z] Loop 12393: Loss: 1.70e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.0821 +[2026-03-20T20:21:02.213054Z] Loop 12394: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0022, Entropy: 0.0814 +[2026-03-20T20:21:03.069221Z] Loop 12395: Loss: 1.67e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.0808 +[2026-03-20T20:21:03.926397Z] Loop 12396: Loss: 1.76e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.0843 +[2026-03-20T20:21:04.783818Z] Loop 12397: Loss: 1.66e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.0864 +[2026-03-20T20:21:05.639342Z] Loop 12398: Loss: 1.83e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.0860 +[2026-03-20T20:21:06.494706Z] Loop 12399: Loss: 1.76e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.0869 +[2026-03-20T20:21:07.396738Z] Loop 12400: Loss: 1.79e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0874 +[2026-03-20T20:21:08.252534Z] Loop 12401: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0880 +[2026-03-20T20:21:09.108316Z] Loop 12402: Loss: 1.66e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0858 +[2026-03-20T20:21:09.963925Z] Loop 12403: Loss: 1.76e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0861 +[2026-03-20T20:21:10.819968Z] Loop 12404: Loss: 1.71e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0831 +[2026-03-20T20:21:11.677422Z] Loop 12405: Loss: 1.72e-02, Avg Return: 0.860, Regret: 0.0019, Entropy: 0.0873 +[2026-03-20T20:21:12.532173Z] Loop 12406: Loss: 2.00e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0936 +[2026-03-20T20:21:13.386810Z] Loop 12407: Loss: 1.95e-02, Avg Return: 0.863, Regret: 0.0019, Entropy: 0.0937 +[2026-03-20T20:21:14.241279Z] Loop 12408: Loss: 1.95e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0890 +[2026-03-20T20:21:15.096795Z] Loop 12409: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0939 +[2026-03-20T20:21:15.993064Z] Loop 12410: Loss: 1.91e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0930 +[2026-03-20T20:21:16.847764Z] Loop 12411: Loss: 1.83e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0926 +[2026-03-20T20:21:17.702011Z] Loop 12412: Loss: 1.79e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0903 +[2026-03-20T20:21:18.558315Z] Loop 12413: Loss: 1.87e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0899 +[2026-03-20T20:21:19.414370Z] Loop 12414: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0949 +[2026-03-20T20:21:20.274581Z] Loop 12415: Loss: 1.79e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0938 +[2026-03-20T20:21:21.133598Z] Loop 12416: Loss: 1.92e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0972 +[2026-03-20T20:21:21.988717Z] Loop 12417: Loss: 2.11e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.1046 +[2026-03-20T20:21:22.844076Z] Loop 12418: Loss: 2.30e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.1105 +[2026-03-20T20:21:23.698739Z] Loop 12419: Loss: 2.45e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.1138 +[2026-03-20T20:21:24.591936Z] Loop 12420: Loss: 2.33e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.1166 +[2026-03-20T20:21:25.446230Z] Loop 12421: Loss: 2.42e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.1172 +[2026-03-20T20:21:26.300414Z] Loop 12422: Loss: 2.44e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.1183 +[2026-03-20T20:21:27.155131Z] Loop 12423: Loss: 2.45e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.1198 +[2026-03-20T20:21:28.008422Z] Loop 12424: Loss: 2.46e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.1182 +[2026-03-20T20:21:28.863189Z] Loop 12425: Loss: 2.57e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.1217 +[2026-03-20T20:21:29.716592Z] Loop 12426: Loss: 2.50e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.1244 +[2026-03-20T20:21:30.570486Z] Loop 12427: Loss: 2.49e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.1216 +[2026-03-20T20:21:31.425602Z] Loop 12428: Loss: 2.63e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.1237 +[2026-03-20T20:21:32.280308Z] Loop 12429: Loss: 2.46e-02, Avg Return: 0.865, Regret: 0.0010, Entropy: 0.1225 +[2026-03-20T20:21:33.174507Z] Loop 12430: Loss: 2.43e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.1212 +[2026-03-20T20:21:34.029008Z] Loop 12431: Loss: 2.52e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.1242 +[2026-03-20T20:21:34.884181Z] Loop 12432: Loss: 2.49e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.1226 +[2026-03-20T20:21:35.738842Z] Loop 12433: Loss: 2.56e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.1257 +[2026-03-20T20:21:36.592886Z] Loop 12434: Loss: 2.74e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.1294 +[2026-03-20T20:21:37.446633Z] Loop 12435: Loss: 2.55e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.1227 +[2026-03-20T20:21:38.301237Z] Loop 12436: Loss: 2.54e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.1256 +[2026-03-20T20:21:39.155842Z] Loop 12437: Loss: 2.50e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.1225 +[2026-03-20T20:21:40.009186Z] Loop 12438: Loss: 2.43e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.1206 +[2026-03-20T20:21:40.862629Z] Loop 12439: Loss: 2.44e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.1175 +[2026-03-20T20:21:41.756586Z] Loop 12440: Loss: 2.41e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.1191 +[2026-03-20T20:21:42.611475Z] Loop 12441: Loss: 2.45e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.1192 +[2026-03-20T20:21:43.465768Z] Loop 12442: Loss: 2.48e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.1221 +[2026-03-20T20:21:44.320333Z] Loop 12443: Loss: 2.58e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.1190 +[2026-03-20T20:21:45.173500Z] Loop 12444: Loss: 2.56e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.1247 +[2026-03-20T20:21:46.027049Z] Loop 12445: Loss: 2.58e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.1224 +[2026-03-20T20:21:46.882006Z] Loop 12446: Loss: 2.60e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.1214 +[2026-03-20T20:21:47.736408Z] Loop 12447: Loss: 2.60e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.1257 +[2026-03-20T20:21:48.589931Z] Loop 12448: Loss: 2.44e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.1199 +[2026-03-20T20:21:49.443553Z] Loop 12449: Loss: 2.34e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.1132 +[2026-03-20T20:21:50.338119Z] Loop 12450: Loss: 2.18e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.1080 +[2026-03-20T20:21:51.192065Z] Loop 12451: Loss: 2.04e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.1077 +[2026-03-20T20:21:52.047948Z] Loop 12452: Loss: 2.13e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.1086 +[2026-03-20T20:21:52.901620Z] Loop 12453: Loss: 2.17e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.1117 +[2026-03-20T20:21:53.754782Z] Loop 12454: Loss: 2.38e-02, Avg Return: 0.860, Regret: 0.0009, Entropy: 0.1208 +[2026-03-20T20:21:54.608411Z] Loop 12455: Loss: 2.48e-02, Avg Return: 0.860, Regret: 0.0009, Entropy: 0.1197 +[2026-03-20T20:21:55.462861Z] Loop 12456: Loss: 2.54e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.1231 +[2026-03-20T20:21:56.317775Z] Loop 12457: Loss: 2.57e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.1277 +[2026-03-20T20:21:57.172002Z] Loop 12458: Loss: 2.68e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.1294 +[2026-03-20T20:21:58.025714Z] Loop 12459: Loss: 2.69e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.1322 +[2026-03-20T20:21:58.920445Z] Loop 12460: Loss: 2.74e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.1345 +[2026-03-20T20:21:59.775195Z] Loop 12461: Loss: 2.66e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.1328 +[2026-03-20T20:22:00.627947Z] Loop 12462: Loss: 2.73e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.1351 +[2026-03-20T20:22:01.480825Z] Loop 12463: Loss: 2.78e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.1339 +[2026-03-20T20:22:02.334782Z] Loop 12464: Loss: 2.80e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.1409 +[2026-03-20T20:22:03.189176Z] Loop 12465: Loss: 2.60e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.1325 +[2026-03-20T20:22:04.042497Z] Loop 12466: Loss: 2.66e-02, Avg Return: 0.863, Regret: 0.0022, Entropy: 0.1290 +[2026-03-20T20:22:04.895443Z] Loop 12467: Loss: 2.57e-02, Avg Return: 0.863, Regret: 0.0022, Entropy: 0.1271 +[2026-03-20T20:22:05.748820Z] Loop 12468: Loss: 2.40e-02, Avg Return: 0.863, Regret: 0.0022, Entropy: 0.1184 +[2026-03-20T20:22:06.602480Z] Loop 12469: Loss: 2.21e-02, Avg Return: 0.863, Regret: 0.0022, Entropy: 0.1102 +[2026-03-20T20:22:07.495289Z] Loop 12470: Loss: 2.14e-02, Avg Return: 0.865, Regret: 0.0011, Entropy: 0.1072 +[2026-03-20T20:22:08.348478Z] Loop 12471: Loss: 2.02e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.1003 +[2026-03-20T20:22:09.201624Z] Loop 12472: Loss: 2.01e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.1044 +[2026-03-20T20:22:10.055948Z] Loop 12473: Loss: 2.05e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.1028 +[2026-03-20T20:22:10.910242Z] Loop 12474: Loss: 2.20e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.1079 +[2026-03-20T20:22:11.763300Z] Loop 12475: Loss: 2.30e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.1144 +[2026-03-20T20:22:12.616157Z] Loop 12476: Loss: 2.40e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.1123 +[2026-03-20T20:22:13.469505Z] Loop 12477: Loss: 2.37e-02, Avg Return: 0.859, Regret: 0.0011, Entropy: 0.1171 +[2026-03-20T20:22:14.323454Z] Loop 12478: Loss: 2.40e-02, Avg Return: 0.860, Regret: 0.0011, Entropy: 0.1187 +[2026-03-20T20:22:15.176734Z] Loop 12479: Loss: 2.32e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.1138 +[2026-03-20T20:22:16.068966Z] Loop 12480: Loss: 2.34e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1180 +[2026-03-20T20:22:16.924213Z] Loop 12481: Loss: 2.36e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1134 +[2026-03-20T20:22:17.777715Z] Loop 12482: Loss: 2.28e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.1145 +[2026-03-20T20:22:18.631786Z] Loop 12483: Loss: 2.25e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1100 +[2026-03-20T20:22:19.485342Z] Loop 12484: Loss: 2.22e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.1091 +[2026-03-20T20:22:20.339456Z] Loop 12485: Loss: 2.09e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.1016 +[2026-03-20T20:22:21.193455Z] Loop 12486: Loss: 1.84e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0897 +[2026-03-20T20:22:22.048465Z] Loop 12487: Loss: 1.67e-02, Avg Return: 0.864, Regret: 0.0013, Entropy: 0.0843 +[2026-03-20T20:22:22.902728Z] Loop 12488: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0787 +[2026-03-20T20:22:23.756025Z] Loop 12489: Loss: 1.54e-02, Avg Return: 0.864, Regret: 0.0013, Entropy: 0.0778 +[2026-03-20T20:22:24.647621Z] Loop 12490: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0782 +[2026-03-20T20:22:25.501904Z] Loop 12491: Loss: 1.58e-02, Avg Return: 0.861, Regret: 0.0005, Entropy: 0.0781 +[2026-03-20T20:22:26.357408Z] Loop 12492: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0779 +[2026-03-20T20:22:27.211218Z] Loop 12493: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0830 +[2026-03-20T20:22:28.064785Z] Loop 12494: Loss: 1.71e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0814 +[2026-03-20T20:22:28.918780Z] Loop 12495: Loss: 1.66e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0788 +[2026-03-20T20:22:29.774758Z] Loop 12496: Loss: 1.47e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0760 +[2026-03-20T20:22:30.629150Z] Loop 12497: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0727 +[2026-03-20T20:22:31.482455Z] Loop 12498: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0745 +[2026-03-20T20:22:32.335823Z] Loop 12499: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0782 +[2026-03-20T20:22:33.228661Z] Loop 12500: Loss: 1.71e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0812 +[2026-03-20T20:22:34.082456Z] Loop 12501: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0803 +[2026-03-20T20:22:34.936190Z] Loop 12502: Loss: 1.51e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0746 +[2026-03-20T20:22:35.790291Z] Loop 12503: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0723 +[2026-03-20T20:22:36.645676Z] Loop 12504: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0762 +[2026-03-20T20:22:37.501179Z] Loop 12505: Loss: 1.46e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0728 +[2026-03-20T20:22:38.356323Z] Loop 12506: Loss: 1.44e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0723 +[2026-03-20T20:22:39.211471Z] Loop 12507: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0760 +[2026-03-20T20:22:40.067440Z] Loop 12508: Loss: 1.62e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0787 +[2026-03-20T20:22:40.921831Z] Loop 12509: Loss: 1.73e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0829 +[2026-03-20T20:22:41.814647Z] Loop 12510: Loss: 1.87e-02, Avg Return: 0.861, Regret: 0.0023, Entropy: 0.0897 +[2026-03-20T20:22:42.670495Z] Loop 12511: Loss: 1.82e-02, Avg Return: 0.861, Regret: 0.0023, Entropy: 0.0894 +[2026-03-20T20:22:43.523870Z] Loop 12512: Loss: 1.85e-02, Avg Return: 0.860, Regret: 0.0023, Entropy: 0.0936 +[2026-03-20T20:22:44.377115Z] Loop 12513: Loss: 2.02e-02, Avg Return: 0.863, Regret: 0.0023, Entropy: 0.0946 +[2026-03-20T20:22:45.232116Z] Loop 12514: Loss: 1.91e-02, Avg Return: 0.861, Regret: 0.0023, Entropy: 0.0932 +[2026-03-20T20:22:46.086061Z] Loop 12515: Loss: 1.70e-02, Avg Return: 0.861, Regret: 0.0023, Entropy: 0.0882 +[2026-03-20T20:22:46.942105Z] Loop 12516: Loss: 1.56e-02, Avg Return: 0.860, Regret: 0.0023, Entropy: 0.0814 +[2026-03-20T20:22:47.795182Z] Loop 12517: Loss: 1.57e-02, Avg Return: 0.857, Regret: 0.0023, Entropy: 0.0774 +[2026-03-20T20:22:48.649713Z] Loop 12518: Loss: 1.62e-02, Avg Return: 0.856, Regret: 0.0023, Entropy: 0.0788 +[2026-03-20T20:22:49.503943Z] Loop 12519: Loss: 1.42e-02, Avg Return: 0.856, Regret: 0.0023, Entropy: 0.0767 +[2026-03-20T20:22:50.398033Z] Loop 12520: Loss: 1.52e-02, Avg Return: 0.856, Regret: 0.0080, Entropy: 0.0758 +[2026-03-20T20:22:51.251924Z] Loop 12521: Loss: 1.58e-02, Avg Return: 0.858, Regret: 0.0080, Entropy: 0.0785 +[2026-03-20T20:22:52.105976Z] Loop 12522: Loss: 1.55e-02, Avg Return: 0.857, Regret: 0.0080, Entropy: 0.0789 +[2026-03-20T20:22:52.960434Z] Loop 12523: Loss: 1.46e-02, Avg Return: 0.859, Regret: 0.0080, Entropy: 0.0755 +[2026-03-20T20:22:53.815396Z] Loop 12524: Loss: 1.38e-02, Avg Return: 0.858, Regret: 0.0080, Entropy: 0.0729 +[2026-03-20T20:22:54.669472Z] Loop 12525: Loss: 1.45e-02, Avg Return: 0.859, Regret: 0.0080, Entropy: 0.0771 +[2026-03-20T20:22:55.523209Z] Loop 12526: Loss: 1.43e-02, Avg Return: 0.860, Regret: 0.0080, Entropy: 0.0769 +[2026-03-20T20:22:56.377561Z] Loop 12527: Loss: 1.45e-02, Avg Return: 0.860, Regret: 0.0080, Entropy: 0.0743 +[2026-03-20T20:22:57.232765Z] Loop 12528: Loss: 1.41e-02, Avg Return: 0.860, Regret: 0.0080, Entropy: 0.0724 +[2026-03-20T20:22:58.087764Z] Loop 12529: Loss: 1.48e-02, Avg Return: 0.860, Regret: 0.0080, Entropy: 0.0779 +[2026-03-20T20:22:58.979527Z] Loop 12530: Loss: 1.55e-02, Avg Return: 0.860, Regret: 0.0035, Entropy: 0.0812 +[2026-03-20T20:22:59.834049Z] Loop 12531: Loss: 1.58e-02, Avg Return: 0.861, Regret: 0.0035, Entropy: 0.0806 +[2026-03-20T20:23:00.687894Z] Loop 12532: Loss: 1.57e-02, Avg Return: 0.861, Regret: 0.0035, Entropy: 0.0825 +[2026-03-20T20:23:01.541310Z] Loop 12533: Loss: 1.71e-02, Avg Return: 0.861, Regret: 0.0035, Entropy: 0.0854 +[2026-03-20T20:23:02.394603Z] Loop 12534: Loss: 1.61e-02, Avg Return: 0.860, Regret: 0.0035, Entropy: 0.0835 +[2026-03-20T20:23:03.247658Z] Loop 12535: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0035, Entropy: 0.0857 +[2026-03-20T20:23:04.100867Z] Loop 12536: Loss: 1.75e-02, Avg Return: 0.861, Regret: 0.0035, Entropy: 0.0894 +[2026-03-20T20:23:04.954437Z] Loop 12537: Loss: 1.68e-02, Avg Return: 0.860, Regret: 0.0035, Entropy: 0.0855 +[2026-03-20T20:23:05.808645Z] Loop 12538: Loss: 1.77e-02, Avg Return: 0.861, Regret: 0.0035, Entropy: 0.0915 +[2026-03-20T20:23:06.661710Z] Loop 12539: Loss: 1.76e-02, Avg Return: 0.863, Regret: 0.0035, Entropy: 0.0855 +[2026-03-20T20:23:07.553212Z] Loop 12540: Loss: 1.86e-02, Avg Return: 0.860, Regret: 0.0015, Entropy: 0.0931 +[2026-03-20T20:23:08.406333Z] Loop 12541: Loss: 1.79e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0890 +[2026-03-20T20:23:09.259991Z] Loop 12542: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0905 +[2026-03-20T20:23:10.114619Z] Loop 12543: Loss: 1.89e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0947 +[2026-03-20T20:23:10.968226Z] Loop 12544: Loss: 1.75e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0880 +[2026-03-20T20:23:11.822272Z] Loop 12545: Loss: 1.63e-02, Avg Return: 0.865, Regret: 0.0015, Entropy: 0.0844 +[2026-03-20T20:23:12.676344Z] Loop 12546: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0906 +[2026-03-20T20:23:13.531248Z] Loop 12547: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0803 +[2026-03-20T20:23:14.384280Z] Loop 12548: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0838 +[2026-03-20T20:23:15.237346Z] Loop 12549: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0798 +[2026-03-20T20:23:16.131221Z] Loop 12550: Loss: 1.43e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0755 +[2026-03-20T20:23:16.985536Z] Loop 12551: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0779 +[2026-03-20T20:23:17.839446Z] Loop 12552: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0777 +[2026-03-20T20:23:18.692723Z] Loop 12553: Loss: 1.43e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0725 +[2026-03-20T20:23:19.546928Z] Loop 12554: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0761 +[2026-03-20T20:23:20.402402Z] Loop 12555: Loss: 1.40e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0749 +[2026-03-20T20:23:21.256127Z] Loop 12556: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0744 +[2026-03-20T20:23:22.110263Z] Loop 12557: Loss: 1.44e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0730 +[2026-03-20T20:23:22.964606Z] Loop 12558: Loss: 1.31e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.0692 +[2026-03-20T20:23:23.818368Z] Loop 12559: Loss: 1.24e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0692 +[2026-03-20T20:23:24.711244Z] Loop 12560: Loss: 1.28e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0638 +[2026-03-20T20:23:25.565007Z] Loop 12561: Loss: 1.34e-02, Avg Return: 0.861, Regret: 0.0017, Entropy: 0.0687 +[2026-03-20T20:23:26.418158Z] Loop 12562: Loss: 1.32e-02, Avg Return: 0.861, Regret: 0.0017, Entropy: 0.0692 +[2026-03-20T20:23:27.271995Z] Loop 12563: Loss: 1.23e-02, Avg Return: 0.861, Regret: 0.0017, Entropy: 0.0660 +[2026-03-20T20:23:28.126728Z] Loop 12564: Loss: 1.30e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0642 +[2026-03-20T20:23:28.981618Z] Loop 12565: Loss: 1.36e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0717 +[2026-03-20T20:23:29.835488Z] Loop 12566: Loss: 1.36e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0696 +[2026-03-20T20:23:30.690028Z] Loop 12567: Loss: 1.35e-02, Avg Return: 0.861, Regret: 0.0017, Entropy: 0.0667 +[2026-03-20T20:23:31.544329Z] Loop 12568: Loss: 1.31e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0697 +[2026-03-20T20:23:32.399173Z] Loop 12569: Loss: 1.33e-02, Avg Return: 0.861, Regret: 0.0017, Entropy: 0.0729 +[2026-03-20T20:23:33.293499Z] Loop 12570: Loss: 1.33e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0715 +[2026-03-20T20:23:34.146634Z] Loop 12571: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0698 +[2026-03-20T20:23:35.000783Z] Loop 12572: Loss: 1.30e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0691 +[2026-03-20T20:23:35.856133Z] Loop 12573: Loss: 1.32e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0681 +[2026-03-20T20:23:36.710883Z] Loop 12574: Loss: 1.31e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0689 +[2026-03-20T20:23:37.565551Z] Loop 12575: Loss: 1.20e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0660 +[2026-03-20T20:23:38.420053Z] Loop 12576: Loss: 1.43e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0734 +[2026-03-20T20:23:39.274516Z] Loop 12577: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0706 +[2026-03-20T20:23:40.129597Z] Loop 12578: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0729 +[2026-03-20T20:23:40.984466Z] Loop 12579: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0725 +[2026-03-20T20:23:41.876083Z] Loop 12580: Loss: 1.39e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0713 +[2026-03-20T20:23:42.729137Z] Loop 12581: Loss: 1.33e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0734 +[2026-03-20T20:23:43.583841Z] Loop 12582: Loss: 1.26e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0710 +[2026-03-20T20:23:44.439404Z] Loop 12583: Loss: 1.31e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0703 +[2026-03-20T20:23:45.293214Z] Loop 12584: Loss: 1.34e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0730 +[2026-03-20T20:23:46.147002Z] Loop 12585: Loss: 1.29e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0694 +[2026-03-20T20:23:47.001523Z] Loop 12586: Loss: 1.31e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0720 +[2026-03-20T20:23:47.855702Z] Loop 12587: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0713 +[2026-03-20T20:23:48.709205Z] Loop 12588: Loss: 1.26e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0692 +[2026-03-20T20:23:49.562399Z] Loop 12589: Loss: 1.33e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0718 +[2026-03-20T20:23:50.455317Z] Loop 12590: Loss: 1.36e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0722 +[2026-03-20T20:23:51.309189Z] Loop 12591: Loss: 1.38e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0761 +[2026-03-20T20:23:52.163323Z] Loop 12592: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0771 +[2026-03-20T20:23:53.017112Z] Loop 12593: Loss: 1.36e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0753 +[2026-03-20T20:23:53.871818Z] Loop 12594: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0768 +[2026-03-20T20:23:54.726923Z] Loop 12595: Loss: 1.45e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0779 +[2026-03-20T20:23:55.581379Z] Loop 12596: Loss: 1.32e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0689 +[2026-03-20T20:23:56.436395Z] Loop 12597: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0723 +[2026-03-20T20:23:57.290495Z] Loop 12598: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0743 +[2026-03-20T20:23:58.144584Z] Loop 12599: Loss: 1.33e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0714 +[2026-03-20T20:23:59.037462Z] Loop 12600: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0672 +[2026-03-20T20:23:59.892602Z] Loop 12601: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0713 +[2026-03-20T20:24:00.747266Z] Loop 12602: Loss: 1.38e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0707 +[2026-03-20T20:24:01.601117Z] Loop 12603: Loss: 1.30e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0708 +[2026-03-20T20:24:02.456495Z] Loop 12604: Loss: 1.32e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0699 +[2026-03-20T20:24:03.310571Z] Loop 12605: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0696 +[2026-03-20T20:24:04.164273Z] Loop 12606: Loss: 1.26e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0672 +[2026-03-20T20:24:05.019087Z] Loop 12607: Loss: 1.29e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0708 +[2026-03-20T20:24:05.874707Z] Loop 12608: Loss: 1.29e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0738 +[2026-03-20T20:24:06.728358Z] Loop 12609: Loss: 1.36e-02, Avg Return: 0.860, Regret: 0.0012, Entropy: 0.0740 +[2026-03-20T20:24:07.621763Z] Loop 12610: Loss: 1.40e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.0705 +[2026-03-20T20:24:08.476710Z] Loop 12611: Loss: 1.44e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0733 +[2026-03-20T20:24:09.331606Z] Loop 12612: Loss: 1.28e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.0725 +[2026-03-20T20:24:10.185611Z] Loop 12613: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0025, Entropy: 0.0736 +[2026-03-20T20:24:11.040163Z] Loop 12614: Loss: 1.40e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0751 +[2026-03-20T20:24:11.894994Z] Loop 12615: Loss: 1.36e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.0746 +[2026-03-20T20:24:12.747873Z] Loop 12616: Loss: 1.43e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.0773 +[2026-03-20T20:24:13.600764Z] Loop 12617: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0796 +[2026-03-20T20:24:14.454787Z] Loop 12618: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0025, Entropy: 0.0817 +[2026-03-20T20:24:15.310050Z] Loop 12619: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0025, Entropy: 0.0794 +[2026-03-20T20:24:16.203391Z] Loop 12620: Loss: 1.62e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.0825 +[2026-03-20T20:24:17.056608Z] Loop 12621: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0878 +[2026-03-20T20:24:17.910875Z] Loop 12622: Loss: 1.73e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0890 +[2026-03-20T20:24:18.766523Z] Loop 12623: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0869 +[2026-03-20T20:24:19.619986Z] Loop 12624: Loss: 1.82e-02, Avg Return: 0.864, Regret: 0.0015, Entropy: 0.0907 +[2026-03-20T20:24:20.472711Z] Loop 12625: Loss: 1.84e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0948 +[2026-03-20T20:24:21.326388Z] Loop 12626: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0908 +[2026-03-20T20:24:22.181964Z] Loop 12627: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0874 +[2026-03-20T20:24:23.037263Z] Loop 12628: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0872 +[2026-03-20T20:24:23.892373Z] Loop 12629: Loss: 1.71e-02, Avg Return: 0.864, Regret: 0.0015, Entropy: 0.0875 +[2026-03-20T20:24:24.787741Z] Loop 12630: Loss: 1.76e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0864 +[2026-03-20T20:24:25.643126Z] Loop 12631: Loss: 1.57e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0846 +[2026-03-20T20:24:26.498384Z] Loop 12632: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0785 +[2026-03-20T20:24:27.353337Z] Loop 12633: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0803 +[2026-03-20T20:24:28.210051Z] Loop 12634: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0805 +[2026-03-20T20:24:29.065339Z] Loop 12635: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0750 +[2026-03-20T20:24:29.919742Z] Loop 12636: Loss: 1.41e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0766 +[2026-03-20T20:24:30.773527Z] Loop 12637: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0764 +[2026-03-20T20:24:31.628865Z] Loop 12638: Loss: 1.60e-02, Avg Return: 0.865, Regret: 0.0004, Entropy: 0.0790 +[2026-03-20T20:24:32.484865Z] Loop 12639: Loss: 1.57e-02, Avg Return: 0.865, Regret: 0.0004, Entropy: 0.0797 +[2026-03-20T20:24:33.379617Z] Loop 12640: Loss: 1.62e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0814 +[2026-03-20T20:24:34.234527Z] Loop 12641: Loss: 1.64e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0835 +[2026-03-20T20:24:35.089727Z] Loop 12642: Loss: 1.57e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0844 +[2026-03-20T20:24:35.944768Z] Loop 12643: Loss: 1.53e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0831 +[2026-03-20T20:24:36.800884Z] Loop 12644: Loss: 1.54e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0818 +[2026-03-20T20:24:37.655600Z] Loop 12645: Loss: 1.53e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0811 +[2026-03-20T20:24:38.509965Z] Loop 12646: Loss: 1.73e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0899 +[2026-03-20T20:24:39.364604Z] Loop 12647: Loss: 1.52e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0799 +[2026-03-20T20:24:40.218248Z] Loop 12648: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0831 +[2026-03-20T20:24:41.071820Z] Loop 12649: Loss: 1.67e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0893 +[2026-03-20T20:24:41.964973Z] Loop 12650: Loss: 1.76e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0909 +[2026-03-20T20:24:42.819608Z] Loop 12651: Loss: 1.73e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0882 +[2026-03-20T20:24:43.673974Z] Loop 12652: Loss: 1.81e-02, Avg Return: 0.859, Regret: 0.0012, Entropy: 0.0953 +[2026-03-20T20:24:44.527456Z] Loop 12653: Loss: 1.84e-02, Avg Return: 0.858, Regret: 0.0012, Entropy: 0.0942 +[2026-03-20T20:24:45.381317Z] Loop 12654: Loss: 1.81e-02, Avg Return: 0.859, Regret: 0.0012, Entropy: 0.0918 +[2026-03-20T20:24:46.235522Z] Loop 12655: Loss: 1.65e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0900 +[2026-03-20T20:24:47.090114Z] Loop 12656: Loss: 1.73e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0903 +[2026-03-20T20:24:47.943106Z] Loop 12657: Loss: 1.80e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0914 +[2026-03-20T20:24:48.796372Z] Loop 12658: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0920 +[2026-03-20T20:24:49.650535Z] Loop 12659: Loss: 1.84e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0955 +[2026-03-20T20:24:50.546499Z] Loop 12660: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0883 +[2026-03-20T20:24:51.400644Z] Loop 12661: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0941 +[2026-03-20T20:24:52.255127Z] Loop 12662: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0892 +[2026-03-20T20:24:53.111136Z] Loop 12663: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0804 +[2026-03-20T20:24:53.966321Z] Loop 12664: Loss: 1.71e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0857 +[2026-03-20T20:24:54.820849Z] Loop 12665: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0865 +[2026-03-20T20:24:55.675271Z] Loop 12666: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0896 +[2026-03-20T20:24:56.528820Z] Loop 12667: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0870 +[2026-03-20T20:24:57.382806Z] Loop 12668: Loss: 1.79e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0948 +[2026-03-20T20:24:58.238211Z] Loop 12669: Loss: 1.72e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0917 +[2026-03-20T20:24:59.132382Z] Loop 12670: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0932 +[2026-03-20T20:24:59.985698Z] Loop 12671: Loss: 1.92e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0989 +[2026-03-20T20:25:00.839375Z] Loop 12672: Loss: 1.94e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.1047 +[2026-03-20T20:25:01.696400Z] Loop 12673: Loss: 2.02e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.1067 +[2026-03-20T20:25:02.551636Z] Loop 12674: Loss: 2.28e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.1185 +[2026-03-20T20:25:03.405356Z] Loop 12675: Loss: 2.35e-02, Avg Return: 0.861, Regret: 0.0004, Entropy: 0.1218 +[2026-03-20T20:25:04.259312Z] Loop 12676: Loss: 2.29e-02, Avg Return: 0.861, Regret: 0.0004, Entropy: 0.1176 +[2026-03-20T20:25:05.113045Z] Loop 12677: Loss: 2.34e-02, Avg Return: 0.865, Regret: 0.0004, Entropy: 0.1184 +[2026-03-20T20:25:05.967170Z] Loop 12678: Loss: 2.12e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.1128 +[2026-03-20T20:25:06.821097Z] Loop 12679: Loss: 2.21e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.1148 +[2026-03-20T20:25:07.713908Z] Loop 12680: Loss: 2.21e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.1148 +[2026-03-20T20:25:08.568275Z] Loop 12681: Loss: 2.00e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.1049 +[2026-03-20T20:25:09.422007Z] Loop 12682: Loss: 1.91e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.1038 +[2026-03-20T20:25:10.275912Z] Loop 12683: Loss: 1.83e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0976 +[2026-03-20T20:25:11.130139Z] Loop 12684: Loss: 1.86e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.1039 +[2026-03-20T20:25:11.983912Z] Loop 12685: Loss: 1.75e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.1022 +[2026-03-20T20:25:12.837544Z] Loop 12686: Loss: 1.95e-02, Avg Return: 0.859, Regret: 0.0011, Entropy: 0.1081 +[2026-03-20T20:25:13.691139Z] Loop 12687: Loss: 2.07e-02, Avg Return: 0.860, Regret: 0.0011, Entropy: 0.1106 +[2026-03-20T20:25:14.545364Z] Loop 12688: Loss: 2.04e-02, Avg Return: 0.859, Regret: 0.0011, Entropy: 0.1074 +[2026-03-20T20:25:15.398214Z] Loop 12689: Loss: 1.91e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.1024 +[2026-03-20T20:25:16.290367Z] Loop 12690: Loss: 1.71e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.0956 +[2026-03-20T20:25:17.145139Z] Loop 12691: Loss: 1.63e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.0922 +[2026-03-20T20:25:17.999430Z] Loop 12692: Loss: 1.60e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.0899 +[2026-03-20T20:25:18.853665Z] Loop 12693: Loss: 1.54e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.0838 +[2026-03-20T20:25:19.707718Z] Loop 12694: Loss: 1.54e-02, Avg Return: 0.864, Regret: 0.0027, Entropy: 0.0846 +[2026-03-20T20:25:20.562864Z] Loop 12695: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0027, Entropy: 0.0804 +[2026-03-20T20:25:21.418095Z] Loop 12696: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0027, Entropy: 0.0790 +[2026-03-20T20:25:22.273413Z] Loop 12697: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0027, Entropy: 0.0765 +[2026-03-20T20:25:23.128063Z] Loop 12698: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0027, Entropy: 0.0740 +[2026-03-20T20:25:23.982088Z] Loop 12699: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0027, Entropy: 0.0712 +[2026-03-20T20:25:24.874537Z] Loop 12700: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0686 +[2026-03-20T20:25:25.730222Z] Loop 12701: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0709 +[2026-03-20T20:25:26.584590Z] Loop 12702: Loss: 1.33e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0701 +[2026-03-20T20:25:27.439915Z] Loop 12703: Loss: 1.24e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0670 +[2026-03-20T20:25:28.294239Z] Loop 12704: Loss: 1.23e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0677 +[2026-03-20T20:25:29.148606Z] Loop 12705: Loss: 1.21e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0660 +[2026-03-20T20:25:30.003256Z] Loop 12706: Loss: 1.30e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0680 +[2026-03-20T20:25:30.857970Z] Loop 12707: Loss: 1.29e-02, Avg Return: 0.861, Regret: 0.0005, Entropy: 0.0669 +[2026-03-20T20:25:31.712416Z] Loop 12708: Loss: 1.28e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0689 +[2026-03-20T20:25:32.567371Z] Loop 12709: Loss: 1.32e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0701 +[2026-03-20T20:25:33.461710Z] Loop 12710: Loss: 1.31e-02, Avg Return: 0.860, Regret: 0.0012, Entropy: 0.0682 +[2026-03-20T20:25:34.316070Z] Loop 12711: Loss: 1.28e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0709 +[2026-03-20T20:25:35.170485Z] Loop 12712: Loss: 1.31e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0708 +[2026-03-20T20:25:36.025449Z] Loop 12713: Loss: 1.31e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0701 +[2026-03-20T20:25:36.879561Z] Loop 12714: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0714 +[2026-03-20T20:25:37.734516Z] Loop 12715: Loss: 1.24e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0671 +[2026-03-20T20:25:38.587538Z] Loop 12716: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0687 +[2026-03-20T20:25:39.441497Z] Loop 12717: Loss: 1.26e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0656 +[2026-03-20T20:25:40.295794Z] Loop 12718: Loss: 1.29e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0682 +[2026-03-20T20:25:41.150211Z] Loop 12719: Loss: 1.23e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0672 +[2026-03-20T20:25:42.044600Z] Loop 12720: Loss: 1.37e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0707 +[2026-03-20T20:25:42.897917Z] Loop 12721: Loss: 1.29e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0693 +[2026-03-20T20:25:43.751945Z] Loop 12722: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0694 +[2026-03-20T20:25:44.606732Z] Loop 12723: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0718 +[2026-03-20T20:25:45.460348Z] Loop 12724: Loss: 1.51e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0761 +[2026-03-20T20:25:46.313609Z] Loop 12725: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0767 +[2026-03-20T20:25:47.167464Z] Loop 12726: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0744 +[2026-03-20T20:25:48.022575Z] Loop 12727: Loss: 1.40e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0755 +[2026-03-20T20:25:48.877796Z] Loop 12728: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0755 +[2026-03-20T20:25:49.732964Z] Loop 12729: Loss: 1.48e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0782 +[2026-03-20T20:25:50.626707Z] Loop 12730: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0767 +[2026-03-20T20:25:51.480686Z] Loop 12731: Loss: 1.61e-02, Avg Return: 0.865, Regret: 0.0001, Entropy: 0.0835 +[2026-03-20T20:25:52.335387Z] Loop 12732: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0786 +[2026-03-20T20:25:53.189094Z] Loop 12733: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0818 +[2026-03-20T20:25:54.042412Z] Loop 12734: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0832 +[2026-03-20T20:25:54.897828Z] Loop 12735: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0864 +[2026-03-20T20:25:55.752684Z] Loop 12736: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0836 +[2026-03-20T20:25:56.607749Z] Loop 12737: Loss: 1.67e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0860 +[2026-03-20T20:25:57.461804Z] Loop 12738: Loss: 1.72e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0820 +[2026-03-20T20:25:58.316349Z] Loop 12739: Loss: 1.56e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0830 +[2026-03-20T20:25:59.207908Z] Loop 12740: Loss: 1.69e-02, Avg Return: 0.865, Regret: 0.0001, Entropy: 0.0826 +[2026-03-20T20:26:00.062995Z] Loop 12741: Loss: 1.64e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0829 +[2026-03-20T20:26:00.918821Z] Loop 12742: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0835 +[2026-03-20T20:26:01.775377Z] Loop 12743: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0816 +[2026-03-20T20:26:02.630100Z] Loop 12744: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0839 +[2026-03-20T20:26:03.484986Z] Loop 12745: Loss: 1.71e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0903 +[2026-03-20T20:26:04.339359Z] Loop 12746: Loss: 1.74e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0923 +[2026-03-20T20:26:05.195187Z] Loop 12747: Loss: 1.79e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0909 +[2026-03-20T20:26:06.049711Z] Loop 12748: Loss: 1.97e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0976 +[2026-03-20T20:26:06.904576Z] Loop 12749: Loss: 2.18e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.1058 +[2026-03-20T20:26:07.798556Z] Loop 12750: Loss: 2.26e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.1070 +[2026-03-20T20:26:08.653642Z] Loop 12751: Loss: 2.07e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.1026 +[2026-03-20T20:26:09.508310Z] Loop 12752: Loss: 1.95e-02, Avg Return: 0.860, Regret: 0.0016, Entropy: 0.0979 +[2026-03-20T20:26:10.362350Z] Loop 12753: Loss: 1.81e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0892 +[2026-03-20T20:26:11.216526Z] Loop 12754: Loss: 1.69e-02, Avg Return: 0.864, Regret: 0.0016, Entropy: 0.0878 +[2026-03-20T20:26:12.070970Z] Loop 12755: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0812 +[2026-03-20T20:26:12.925243Z] Loop 12756: Loss: 1.54e-02, Avg Return: 0.864, Regret: 0.0016, Entropy: 0.0797 +[2026-03-20T20:26:13.778871Z] Loop 12757: Loss: 1.52e-02, Avg Return: 0.864, Regret: 0.0016, Entropy: 0.0779 +[2026-03-20T20:26:14.633278Z] Loop 12758: Loss: 1.51e-02, Avg Return: 0.864, Regret: 0.0016, Entropy: 0.0780 +[2026-03-20T20:26:15.487032Z] Loop 12759: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0736 +[2026-03-20T20:26:16.379398Z] Loop 12760: Loss: 1.42e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0733 +[2026-03-20T20:26:17.233571Z] Loop 12761: Loss: 1.37e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0728 +[2026-03-20T20:26:18.088577Z] Loop 12762: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0749 +[2026-03-20T20:26:18.943310Z] Loop 12763: Loss: 1.33e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0708 +[2026-03-20T20:26:19.797400Z] Loop 12764: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0705 +[2026-03-20T20:26:20.652091Z] Loop 12765: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0675 +[2026-03-20T20:26:21.507233Z] Loop 12766: Loss: 1.33e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0705 +[2026-03-20T20:26:22.360507Z] Loop 12767: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0691 +[2026-03-20T20:26:23.214453Z] Loop 12768: Loss: 1.33e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0709 +[2026-03-20T20:26:24.069622Z] Loop 12769: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0702 +[2026-03-20T20:26:24.961698Z] Loop 12770: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0691 +[2026-03-20T20:26:25.814981Z] Loop 12771: Loss: 1.27e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0661 +[2026-03-20T20:26:26.668961Z] Loop 12772: Loss: 1.28e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0665 +[2026-03-20T20:26:27.524471Z] Loop 12773: Loss: 1.28e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0716 +[2026-03-20T20:26:28.379462Z] Loop 12774: Loss: 1.23e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0654 +[2026-03-20T20:26:29.233546Z] Loop 12775: Loss: 1.36e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0673 +[2026-03-20T20:26:30.088872Z] Loop 12776: Loss: 1.35e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0690 +[2026-03-20T20:26:30.943348Z] Loop 12777: Loss: 1.36e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0699 +[2026-03-20T20:26:31.798125Z] Loop 12778: Loss: 1.32e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0703 +[2026-03-20T20:26:32.651931Z] Loop 12779: Loss: 1.31e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0706 +[2026-03-20T20:26:33.544381Z] Loop 12780: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0722 +[2026-03-20T20:26:34.398144Z] Loop 12781: Loss: 1.26e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0706 +[2026-03-20T20:26:35.253136Z] Loop 12782: Loss: 1.34e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0707 +[2026-03-20T20:26:36.107434Z] Loop 12783: Loss: 1.29e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0676 +[2026-03-20T20:26:36.961143Z] Loop 12784: Loss: 1.28e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0698 +[2026-03-20T20:26:37.813972Z] Loop 12785: Loss: 1.20e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0642 +[2026-03-20T20:26:38.668316Z] Loop 12786: Loss: 1.19e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0652 +[2026-03-20T20:26:39.523407Z] Loop 12787: Loss: 1.23e-02, Avg Return: 0.864, Regret: 0.0018, Entropy: 0.0651 +[2026-03-20T20:26:40.377236Z] Loop 12788: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0655 +[2026-03-20T20:26:41.229583Z] Loop 12789: Loss: 1.32e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0667 +[2026-03-20T20:26:42.120927Z] Loop 12790: Loss: 1.16e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0641 +[2026-03-20T20:26:42.975874Z] Loop 12791: Loss: 1.20e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0630 +[2026-03-20T20:26:43.830072Z] Loop 12792: Loss: 1.11e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0617 +[2026-03-20T20:26:44.684992Z] Loop 12793: Loss: 1.20e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0630 +[2026-03-20T20:26:45.539764Z] Loop 12794: Loss: 1.24e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0661 +[2026-03-20T20:26:46.395248Z] Loop 12795: Loss: 1.15e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.0625 +[2026-03-20T20:26:47.250698Z] Loop 12796: Loss: 1.17e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0617 +[2026-03-20T20:26:48.105464Z] Loop 12797: Loss: 1.20e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0631 +[2026-03-20T20:26:48.960211Z] Loop 12798: Loss: 1.35e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0672 +[2026-03-20T20:26:49.814856Z] Loop 12799: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0677 +[2026-03-20T20:26:50.709667Z] Loop 12800: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0666 +[2026-03-20T20:26:51.565554Z] Loop 12801: Loss: 1.29e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0669 +[2026-03-20T20:26:52.420601Z] Loop 12802: Loss: 1.31e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0683 +[2026-03-20T20:26:53.275307Z] Loop 12803: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0757 +[2026-03-20T20:26:54.129839Z] Loop 12804: Loss: 1.32e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0727 +[2026-03-20T20:26:54.984254Z] Loop 12805: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0802 +[2026-03-20T20:26:55.838924Z] Loop 12806: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0782 +[2026-03-20T20:26:56.692396Z] Loop 12807: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0850 +[2026-03-20T20:26:57.545828Z] Loop 12808: Loss: 1.82e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0880 +[2026-03-20T20:26:58.400028Z] Loop 12809: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0907 +[2026-03-20T20:26:59.293431Z] Loop 12810: Loss: 1.89e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0998 +[2026-03-20T20:27:00.148787Z] Loop 12811: Loss: 1.93e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0983 +[2026-03-20T20:27:01.002890Z] Loop 12812: Loss: 1.96e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0981 +[2026-03-20T20:27:01.857145Z] Loop 12813: Loss: 2.04e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.1019 +[2026-03-20T20:27:02.712154Z] Loop 12814: Loss: 2.30e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.1123 +[2026-03-20T20:27:03.566044Z] Loop 12815: Loss: 2.34e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.1147 +[2026-03-20T20:27:04.418519Z] Loop 12816: Loss: 2.33e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.1141 +[2026-03-20T20:27:05.272128Z] Loop 12817: Loss: 2.18e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.1068 +[2026-03-20T20:27:06.125768Z] Loop 12818: Loss: 2.34e-02, Avg Return: 0.859, Regret: 0.0008, Entropy: 0.1122 +[2026-03-20T20:27:06.980033Z] Loop 12819: Loss: 2.19e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.1114 +[2026-03-20T20:27:07.875642Z] Loop 12820: Loss: 2.25e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.1080 +[2026-03-20T20:27:08.729013Z] Loop 12821: Loss: 2.19e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.1059 +[2026-03-20T20:27:09.583629Z] Loop 12822: Loss: 2.05e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.1039 +[2026-03-20T20:27:10.438264Z] Loop 12823: Loss: 1.76e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0909 +[2026-03-20T20:27:11.294481Z] Loop 12824: Loss: 1.70e-02, Avg Return: 0.864, Regret: 0.0016, Entropy: 0.0862 +[2026-03-20T20:27:12.148233Z] Loop 12825: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0830 +[2026-03-20T20:27:13.001153Z] Loop 12826: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0016, Entropy: 0.0789 +[2026-03-20T20:27:13.855354Z] Loop 12827: Loss: 1.52e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0785 +[2026-03-20T20:27:14.710060Z] Loop 12828: Loss: 1.33e-02, Avg Return: 0.864, Regret: 0.0016, Entropy: 0.0748 +[2026-03-20T20:27:15.564129Z] Loop 12829: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0766 +[2026-03-20T20:27:16.457185Z] Loop 12830: Loss: 1.37e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0715 +[2026-03-20T20:27:17.310272Z] Loop 12831: Loss: 1.34e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0733 +[2026-03-20T20:27:18.165312Z] Loop 12832: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0699 +[2026-03-20T20:27:19.018978Z] Loop 12833: Loss: 1.32e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0680 +[2026-03-20T20:27:19.872325Z] Loop 12834: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0702 +[2026-03-20T20:27:20.725822Z] Loop 12835: Loss: 1.27e-02, Avg Return: 0.865, Regret: 0.0001, Entropy: 0.0672 +[2026-03-20T20:27:21.580511Z] Loop 12836: Loss: 1.16e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0598 +[2026-03-20T20:27:22.435586Z] Loop 12837: Loss: 1.15e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0633 +[2026-03-20T20:27:23.289149Z] Loop 12838: Loss: 1.22e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0677 +[2026-03-20T20:27:24.142472Z] Loop 12839: Loss: 1.13e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0595 +[2026-03-20T20:27:25.035830Z] Loop 12840: Loss: 1.09e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0593 +[2026-03-20T20:27:25.890024Z] Loop 12841: Loss: 1.13e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0618 +[2026-03-20T20:27:26.744094Z] Loop 12842: Loss: 1.14e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0604 +[2026-03-20T20:27:27.598932Z] Loop 12843: Loss: 1.29e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0663 +[2026-03-20T20:27:28.453168Z] Loop 12844: Loss: 1.25e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0664 +[2026-03-20T20:27:29.308350Z] Loop 12845: Loss: 1.25e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0663 +[2026-03-20T20:27:30.162986Z] Loop 12846: Loss: 1.36e-02, Avg Return: 0.861, Regret: 0.0005, Entropy: 0.0713 +[2026-03-20T20:27:31.017046Z] Loop 12847: Loss: 1.47e-02, Avg Return: 0.861, Regret: 0.0005, Entropy: 0.0719 +[2026-03-20T20:27:31.870477Z] Loop 12848: Loss: 1.34e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0711 +[2026-03-20T20:27:32.723900Z] Loop 12849: Loss: 1.35e-02, Avg Return: 0.861, Regret: 0.0005, Entropy: 0.0663 +[2026-03-20T20:27:33.616319Z] Loop 12850: Loss: 1.26e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0674 +[2026-03-20T20:27:34.470487Z] Loop 12851: Loss: 1.21e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0640 +[2026-03-20T20:27:35.324773Z] Loop 12852: Loss: 1.18e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0634 +[2026-03-20T20:27:36.178538Z] Loop 12853: Loss: 1.23e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0651 +[2026-03-20T20:27:37.032255Z] Loop 12854: Loss: 1.20e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0664 +[2026-03-20T20:27:37.887406Z] Loop 12855: Loss: 1.12e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0631 +[2026-03-20T20:27:38.741170Z] Loop 12856: Loss: 1.15e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0654 +[2026-03-20T20:27:39.594086Z] Loop 12857: Loss: 1.14e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0629 +[2026-03-20T20:27:40.447669Z] Loop 12858: Loss: 1.28e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0684 +[2026-03-20T20:27:41.301755Z] Loop 12859: Loss: 1.08e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0619 +[2026-03-20T20:27:42.194673Z] Loop 12860: Loss: 1.21e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0687 +[2026-03-20T20:27:43.048341Z] Loop 12861: Loss: 1.10e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0633 +[2026-03-20T20:27:43.902162Z] Loop 12862: Loss: 1.10e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0623 +[2026-03-20T20:27:44.756583Z] Loop 12863: Loss: 1.13e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0640 +[2026-03-20T20:27:45.610700Z] Loop 12864: Loss: 1.28e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0670 +[2026-03-20T20:27:46.465132Z] Loop 12865: Loss: 1.14e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0634 +[2026-03-20T20:27:47.318420Z] Loop 12866: Loss: 1.26e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0677 +[2026-03-20T20:27:48.172412Z] Loop 12867: Loss: 1.22e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0660 +[2026-03-20T20:27:49.026278Z] Loop 12868: Loss: 1.23e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0679 +[2026-03-20T20:27:49.879721Z] Loop 12869: Loss: 1.24e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0697 +[2026-03-20T20:27:50.772274Z] Loop 12870: Loss: 1.23e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0649 +[2026-03-20T20:27:51.627447Z] Loop 12871: Loss: 1.27e-02, Avg Return: 0.865, Regret: 0.0004, Entropy: 0.0668 +[2026-03-20T20:27:52.482165Z] Loop 12872: Loss: 1.17e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0667 +[2026-03-20T20:27:53.336271Z] Loop 12873: Loss: 1.15e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0636 +[2026-03-20T20:27:54.190544Z] Loop 12874: Loss: 1.27e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0683 +[2026-03-20T20:27:55.044588Z] Loop 12875: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0694 +[2026-03-20T20:27:55.897798Z] Loop 12876: Loss: 1.34e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0731 +[2026-03-20T20:27:56.752905Z] Loop 12877: Loss: 1.35e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0721 +[2026-03-20T20:27:57.605919Z] Loop 12878: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0711 +[2026-03-20T20:27:58.460516Z] Loop 12879: Loss: 1.30e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0679 +[2026-03-20T20:27:59.353840Z] Loop 12880: Loss: 1.31e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0739 +[2026-03-20T20:28:00.208061Z] Loop 12881: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0686 +[2026-03-20T20:28:01.061772Z] Loop 12882: Loss: 1.32e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0741 +[2026-03-20T20:28:01.917350Z] Loop 12883: Loss: 1.40e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0741 +[2026-03-20T20:28:02.771095Z] Loop 12884: Loss: 1.17e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0706 +[2026-03-20T20:28:03.624659Z] Loop 12885: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0690 +[2026-03-20T20:28:04.477655Z] Loop 12886: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0723 +[2026-03-20T20:28:05.331410Z] Loop 12887: Loss: 1.40e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0730 +[2026-03-20T20:28:06.185650Z] Loop 12888: Loss: 1.34e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0689 +[2026-03-20T20:28:07.040284Z] Loop 12889: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0732 +[2026-03-20T20:28:07.935600Z] Loop 12890: Loss: 1.30e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0735 +[2026-03-20T20:28:08.790039Z] Loop 12891: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0684 +[2026-03-20T20:28:09.644578Z] Loop 12892: Loss: 1.40e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0704 +[2026-03-20T20:28:10.497597Z] Loop 12893: Loss: 1.14e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0660 +[2026-03-20T20:28:11.351397Z] Loop 12894: Loss: 1.24e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0674 +[2026-03-20T20:28:12.206273Z] Loop 12895: Loss: 1.31e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0695 +[2026-03-20T20:28:13.060118Z] Loop 12896: Loss: 1.26e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0654 +[2026-03-20T20:28:13.914053Z] Loop 12897: Loss: 1.29e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0674 +[2026-03-20T20:28:14.769181Z] Loop 12898: Loss: 1.29e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0676 +[2026-03-20T20:28:15.624687Z] Loop 12899: Loss: 1.23e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0662 +[2026-03-20T20:28:16.518764Z] Loop 12900: Loss: 1.19e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0641 +[2026-03-20T20:28:17.374620Z] Loop 12901: Loss: 1.19e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0640 +[2026-03-20T20:28:18.230511Z] Loop 12902: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0658 +[2026-03-20T20:28:19.085364Z] Loop 12903: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0663 +[2026-03-20T20:28:19.941300Z] Loop 12904: Loss: 1.20e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0678 +[2026-03-20T20:28:20.795732Z] Loop 12905: Loss: 1.19e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0660 +[2026-03-20T20:28:21.649968Z] Loop 12906: Loss: 1.22e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0650 +[2026-03-20T20:28:22.503657Z] Loop 12907: Loss: 1.21e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0667 +[2026-03-20T20:28:23.357421Z] Loop 12908: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0677 +[2026-03-20T20:28:24.211931Z] Loop 12909: Loss: 1.31e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0687 +[2026-03-20T20:28:25.104914Z] Loop 12910: Loss: 1.29e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0671 +[2026-03-20T20:28:25.959484Z] Loop 12911: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0662 +[2026-03-20T20:28:26.814097Z] Loop 12912: Loss: 1.19e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0664 +[2026-03-20T20:28:27.668791Z] Loop 12913: Loss: 1.21e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0651 +[2026-03-20T20:28:28.525237Z] Loop 12914: Loss: 1.16e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0661 +[2026-03-20T20:28:29.380206Z] Loop 12915: Loss: 1.18e-02, Avg Return: 0.861, Regret: 0.0004, Entropy: 0.0683 +[2026-03-20T20:28:30.233280Z] Loop 12916: Loss: 1.25e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0679 +[2026-03-20T20:28:31.086670Z] Loop 12917: Loss: 1.33e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0720 +[2026-03-20T20:28:31.941626Z] Loop 12918: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0693 +[2026-03-20T20:28:32.795683Z] Loop 12919: Loss: 1.29e-02, Avg Return: 0.861, Regret: 0.0004, Entropy: 0.0699 +[2026-03-20T20:28:33.690233Z] Loop 12920: Loss: 1.25e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0659 +[2026-03-20T20:28:34.544553Z] Loop 12921: Loss: 1.27e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0678 +[2026-03-20T20:28:35.399905Z] Loop 12922: Loss: 1.26e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.0686 +[2026-03-20T20:28:36.254986Z] Loop 12923: Loss: 1.30e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0676 +[2026-03-20T20:28:37.110685Z] Loop 12924: Loss: 1.29e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0711 +[2026-03-20T20:28:37.964827Z] Loop 12925: Loss: 1.36e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0746 +[2026-03-20T20:28:38.819227Z] Loop 12926: Loss: 1.25e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0717 +[2026-03-20T20:28:39.674294Z] Loop 12927: Loss: 1.19e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0672 +[2026-03-20T20:28:40.528467Z] Loop 12928: Loss: 1.28e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0708 +[2026-03-20T20:28:41.382009Z] Loop 12929: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0695 +[2026-03-20T20:28:42.275045Z] Loop 12930: Loss: 1.22e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0681 +[2026-03-20T20:28:43.129321Z] Loop 12931: Loss: 1.23e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0664 +[2026-03-20T20:28:43.983587Z] Loop 12932: Loss: 1.21e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0613 +[2026-03-20T20:28:44.840178Z] Loop 12933: Loss: 1.24e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0669 +[2026-03-20T20:28:45.695293Z] Loop 12934: Loss: 1.21e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0654 +[2026-03-20T20:28:46.549300Z] Loop 12935: Loss: 1.26e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0688 +[2026-03-20T20:28:47.403852Z] Loop 12936: Loss: 1.17e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0654 +[2026-03-20T20:28:48.258842Z] Loop 12937: Loss: 1.28e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0703 +[2026-03-20T20:28:49.111959Z] Loop 12938: Loss: 1.29e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0667 +[2026-03-20T20:28:49.964664Z] Loop 12939: Loss: 1.24e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0672 +[2026-03-20T20:28:50.856140Z] Loop 12940: Loss: 1.20e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0653 +[2026-03-20T20:28:51.710331Z] Loop 12941: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0711 +[2026-03-20T20:28:52.564342Z] Loop 12942: Loss: 1.22e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0644 +[2026-03-20T20:28:53.418025Z] Loop 12943: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0660 +[2026-03-20T20:28:54.271294Z] Loop 12944: Loss: 1.25e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0666 +[2026-03-20T20:28:55.126069Z] Loop 12945: Loss: 1.24e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0655 +[2026-03-20T20:28:55.979654Z] Loop 12946: Loss: 1.23e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0646 +[2026-03-20T20:28:56.833110Z] Loop 12947: Loss: 1.37e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0681 +[2026-03-20T20:28:57.687184Z] Loop 12948: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0714 +[2026-03-20T20:28:58.542830Z] Loop 12949: Loss: 1.29e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0694 +[2026-03-20T20:28:59.436047Z] Loop 12950: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0692 +[2026-03-20T20:29:00.291199Z] Loop 12951: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0704 +[2026-03-20T20:29:01.145265Z] Loop 12952: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0704 +[2026-03-20T20:29:02.000362Z] Loop 12953: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0710 +[2026-03-20T20:29:02.853828Z] Loop 12954: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0728 +[2026-03-20T20:29:03.707363Z] Loop 12955: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0746 +[2026-03-20T20:29:04.561994Z] Loop 12956: Loss: 1.24e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0665 +[2026-03-20T20:29:05.417441Z] Loop 12957: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0710 +[2026-03-20T20:29:06.271981Z] Loop 12958: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0720 +[2026-03-20T20:29:07.125580Z] Loop 12959: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0786 +[2026-03-20T20:29:08.019098Z] Loop 12960: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0746 +[2026-03-20T20:29:08.873745Z] Loop 12961: Loss: 1.34e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0751 +[2026-03-20T20:29:09.727380Z] Loop 12962: Loss: 1.29e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0704 +[2026-03-20T20:29:10.581753Z] Loop 12963: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0756 +[2026-03-20T20:29:11.436619Z] Loop 12964: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0723 +[2026-03-20T20:29:12.290131Z] Loop 12965: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0777 +[2026-03-20T20:29:13.144579Z] Loop 12966: Loss: 1.35e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0732 +[2026-03-20T20:29:13.999149Z] Loop 12967: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0782 +[2026-03-20T20:29:14.853987Z] Loop 12968: Loss: 1.46e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0767 +[2026-03-20T20:29:15.708429Z] Loop 12969: Loss: 1.46e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0752 +[2026-03-20T20:29:16.600198Z] Loop 12970: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0753 +[2026-03-20T20:29:17.453534Z] Loop 12971: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0767 +[2026-03-20T20:29:18.308248Z] Loop 12972: Loss: 1.48e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0770 +[2026-03-20T20:29:19.163341Z] Loop 12973: Loss: 1.44e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0776 +[2026-03-20T20:29:20.017033Z] Loop 12974: Loss: 1.57e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0850 +[2026-03-20T20:29:20.871000Z] Loop 12975: Loss: 1.61e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0831 +[2026-03-20T20:29:21.724876Z] Loop 12976: Loss: 1.62e-02, Avg Return: 0.860, Regret: 0.0008, Entropy: 0.0847 +[2026-03-20T20:29:22.578070Z] Loop 12977: Loss: 1.69e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0846 +[2026-03-20T20:29:23.432531Z] Loop 12978: Loss: 1.79e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0906 +[2026-03-20T20:29:24.285889Z] Loop 12979: Loss: 1.79e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0918 +[2026-03-20T20:29:25.179937Z] Loop 12980: Loss: 1.80e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0948 +[2026-03-20T20:29:26.033661Z] Loop 12981: Loss: 1.77e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0914 +[2026-03-20T20:29:26.888021Z] Loop 12982: Loss: 1.69e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0872 +[2026-03-20T20:29:27.741768Z] Loop 12983: Loss: 1.79e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0876 +[2026-03-20T20:29:28.595600Z] Loop 12984: Loss: 1.88e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0935 +[2026-03-20T20:29:29.449034Z] Loop 12985: Loss: 1.94e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0957 +[2026-03-20T20:29:30.303108Z] Loop 12986: Loss: 2.04e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0996 +[2026-03-20T20:29:31.156336Z] Loop 12987: Loss: 1.99e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.1015 +[2026-03-20T20:29:32.010080Z] Loop 12988: Loss: 1.99e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0980 +[2026-03-20T20:29:32.864550Z] Loop 12989: Loss: 2.07e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.1038 +[2026-03-20T20:29:33.757162Z] Loop 12990: Loss: 2.04e-02, Avg Return: 0.860, Regret: 0.0033, Entropy: 0.1012 +[2026-03-20T20:29:34.610286Z] Loop 12991: Loss: 2.07e-02, Avg Return: 0.860, Regret: 0.0033, Entropy: 0.1020 +[2026-03-20T20:29:35.464654Z] Loop 12992: Loss: 1.93e-02, Avg Return: 0.860, Regret: 0.0033, Entropy: 0.0938 +[2026-03-20T20:29:36.317825Z] Loop 12993: Loss: 1.84e-02, Avg Return: 0.860, Regret: 0.0033, Entropy: 0.0941 +[2026-03-20T20:29:37.171861Z] Loop 12994: Loss: 1.93e-02, Avg Return: 0.861, Regret: 0.0033, Entropy: 0.0923 +[2026-03-20T20:29:38.026483Z] Loop 12995: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0033, Entropy: 0.0868 +[2026-03-20T20:29:38.881771Z] Loop 12996: Loss: 1.79e-02, Avg Return: 0.863, Regret: 0.0033, Entropy: 0.0916 +[2026-03-20T20:29:39.735655Z] Loop 12997: Loss: 2.09e-02, Avg Return: 0.863, Regret: 0.0033, Entropy: 0.0988 +[2026-03-20T20:29:40.589286Z] Loop 12998: Loss: 2.03e-02, Avg Return: 0.864, Regret: 0.0033, Entropy: 0.0976 +[2026-03-20T20:29:41.444251Z] Loop 12999: Loss: 2.01e-02, Avg Return: 0.863, Regret: 0.0033, Entropy: 0.1017 +[2026-03-20T20:29:42.337319Z] Loop 13000: Loss: 1.82e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0930 +[2026-03-20T20:29:43.191220Z] Loop 13001: Loss: 1.80e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.0905 +[2026-03-20T20:29:44.044283Z] Loop 13002: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0838 +[2026-03-20T20:29:44.897726Z] Loop 13003: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0825 +[2026-03-20T20:29:45.752639Z] Loop 13004: Loss: 1.56e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0786 +[2026-03-20T20:29:46.606750Z] Loop 13005: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0815 +[2026-03-20T20:29:47.460141Z] Loop 13006: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0823 +[2026-03-20T20:29:48.314490Z] Loop 13007: Loss: 1.50e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0756 +[2026-03-20T20:29:49.169461Z] Loop 13008: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0724 +[2026-03-20T20:29:50.024622Z] Loop 13009: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0800 +[2026-03-20T20:29:50.918143Z] Loop 13010: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0740 +[2026-03-20T20:29:51.772160Z] Loop 13011: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0716 +[2026-03-20T20:29:52.627129Z] Loop 13012: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0729 +[2026-03-20T20:29:53.480900Z] Loop 13013: Loss: 1.35e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0694 +[2026-03-20T20:29:54.334207Z] Loop 13014: Loss: 1.40e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0718 +[2026-03-20T20:29:55.188270Z] Loop 13015: Loss: 1.37e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0688 +[2026-03-20T20:29:56.044275Z] Loop 13016: Loss: 1.30e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0675 +[2026-03-20T20:29:56.898479Z] Loop 13017: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0670 +[2026-03-20T20:29:57.751913Z] Loop 13018: Loss: 1.30e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0671 +[2026-03-20T20:29:58.605760Z] Loop 13019: Loss: 1.18e-02, Avg Return: 0.865, Regret: 0.0006, Entropy: 0.0623 +[2026-03-20T20:29:59.499609Z] Loop 13020: Loss: 1.28e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.0665 +[2026-03-20T20:30:00.353463Z] Loop 13021: Loss: 1.20e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0641 +[2026-03-20T20:30:01.209200Z] Loop 13022: Loss: 1.31e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0655 +[2026-03-20T20:30:02.064476Z] Loop 13023: Loss: 1.14e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0597 +[2026-03-20T20:30:02.918724Z] Loop 13024: Loss: 1.25e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0658 +[2026-03-20T20:30:03.772702Z] Loop 13025: Loss: 1.18e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0625 +[2026-03-20T20:30:04.627361Z] Loop 13026: Loss: 1.16e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0633 +[2026-03-20T20:30:05.481969Z] Loop 13027: Loss: 1.15e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0656 +[2026-03-20T20:30:06.336706Z] Loop 13028: Loss: 1.09e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.0623 +[2026-03-20T20:30:07.190466Z] Loop 13029: Loss: 1.20e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0636 +[2026-03-20T20:30:08.083261Z] Loop 13030: Loss: 1.18e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0642 +[2026-03-20T20:30:08.937334Z] Loop 13031: Loss: 1.23e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0674 +[2026-03-20T20:30:09.792631Z] Loop 13032: Loss: 1.23e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0646 +[2026-03-20T20:30:10.646225Z] Loop 13033: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0672 +[2026-03-20T20:30:11.499604Z] Loop 13034: Loss: 1.29e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0643 +[2026-03-20T20:30:12.353820Z] Loop 13035: Loss: 1.16e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0618 +[2026-03-20T20:30:13.208324Z] Loop 13036: Loss: 1.22e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0655 +[2026-03-20T20:30:14.063206Z] Loop 13037: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0644 +[2026-03-20T20:30:14.916988Z] Loop 13038: Loss: 1.23e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0658 +[2026-03-20T20:30:15.771115Z] Loop 13039: Loss: 1.14e-02, Avg Return: 0.860, Regret: 0.0016, Entropy: 0.0671 +[2026-03-20T20:30:16.665218Z] Loop 13040: Loss: 1.26e-02, Avg Return: 0.860, Regret: 0.0033, Entropy: 0.0724 +[2026-03-20T20:30:17.519169Z] Loop 13041: Loss: 1.34e-02, Avg Return: 0.860, Regret: 0.0033, Entropy: 0.0735 +[2026-03-20T20:30:18.373751Z] Loop 13042: Loss: 1.47e-02, Avg Return: 0.860, Regret: 0.0033, Entropy: 0.0760 +[2026-03-20T20:30:19.228104Z] Loop 13043: Loss: 1.37e-02, Avg Return: 0.860, Regret: 0.0033, Entropy: 0.0754 +[2026-03-20T20:30:20.082545Z] Loop 13044: Loss: 1.38e-02, Avg Return: 0.860, Regret: 0.0033, Entropy: 0.0747 +[2026-03-20T20:30:20.937245Z] Loop 13045: Loss: 1.40e-02, Avg Return: 0.861, Regret: 0.0033, Entropy: 0.0732 +[2026-03-20T20:30:21.791811Z] Loop 13046: Loss: 1.29e-02, Avg Return: 0.860, Regret: 0.0033, Entropy: 0.0668 +[2026-03-20T20:30:22.644760Z] Loop 13047: Loss: 1.07e-02, Avg Return: 0.861, Regret: 0.0033, Entropy: 0.0608 +[2026-03-20T20:30:23.497707Z] Loop 13048: Loss: 1.23e-02, Avg Return: 0.863, Regret: 0.0033, Entropy: 0.0654 +[2026-03-20T20:30:24.351594Z] Loop 13049: Loss: 1.16e-02, Avg Return: 0.863, Regret: 0.0033, Entropy: 0.0594 +[2026-03-20T20:30:25.245015Z] Loop 13050: Loss: 1.11e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0591 +[2026-03-20T20:30:26.098556Z] Loop 13051: Loss: 1.16e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0610 +[2026-03-20T20:30:26.952131Z] Loop 13052: Loss: 1.12e-02, Avg Return: 0.865, Regret: 0.0011, Entropy: 0.0579 +[2026-03-20T20:30:27.804873Z] Loop 13053: Loss: 1.16e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0591 +[2026-03-20T20:30:28.659494Z] Loop 13054: Loss: 1.15e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0595 +[2026-03-20T20:30:29.513257Z] Loop 13055: Loss: 1.06e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0570 +[2026-03-20T20:30:30.366560Z] Loop 13056: Loss: 1.09e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0575 +[2026-03-20T20:30:31.219843Z] Loop 13057: Loss: 1.22e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0615 +[2026-03-20T20:30:32.074581Z] Loop 13058: Loss: 1.16e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0611 +[2026-03-20T20:30:32.928945Z] Loop 13059: Loss: 1.11e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0619 +[2026-03-20T20:30:33.819298Z] Loop 13060: Loss: 1.18e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0595 +[2026-03-20T20:30:34.672394Z] Loop 13061: Loss: 1.07e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0591 +[2026-03-20T20:30:35.527949Z] Loop 13062: Loss: 1.12e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0601 +[2026-03-20T20:30:36.382562Z] Loop 13063: Loss: 1.18e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0616 +[2026-03-20T20:30:37.236954Z] Loop 13064: Loss: 1.26e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0655 +[2026-03-20T20:30:38.090887Z] Loop 13065: Loss: 1.23e-02, Avg Return: 0.861, Regret: 0.0005, Entropy: 0.0627 +[2026-03-20T20:30:38.946131Z] Loop 13066: Loss: 1.19e-02, Avg Return: 0.861, Regret: 0.0005, Entropy: 0.0678 +[2026-03-20T20:30:39.800222Z] Loop 13067: Loss: 1.23e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0674 +[2026-03-20T20:30:40.654324Z] Loop 13068: Loss: 1.44e-02, Avg Return: 0.860, Regret: 0.0005, Entropy: 0.0727 +[2026-03-20T20:30:41.508512Z] Loop 13069: Loss: 1.43e-02, Avg Return: 0.860, Regret: 0.0005, Entropy: 0.0767 +[2026-03-20T20:30:42.402594Z] Loop 13070: Loss: 1.39e-02, Avg Return: 0.860, Regret: 0.0030, Entropy: 0.0767 +[2026-03-20T20:30:43.256272Z] Loop 13071: Loss: 1.36e-02, Avg Return: 0.861, Regret: 0.0030, Entropy: 0.0734 +[2026-03-20T20:30:44.110680Z] Loop 13072: Loss: 1.19e-02, Avg Return: 0.862, Regret: 0.0030, Entropy: 0.0708 +[2026-03-20T20:30:44.964241Z] Loop 13073: Loss: 1.24e-02, Avg Return: 0.863, Regret: 0.0030, Entropy: 0.0681 +[2026-03-20T20:30:45.818395Z] Loop 13074: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0030, Entropy: 0.0603 +[2026-03-20T20:30:46.672137Z] Loop 13075: Loss: 1.22e-02, Avg Return: 0.863, Regret: 0.0030, Entropy: 0.0656 +[2026-03-20T20:30:47.526870Z] Loop 13076: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0030, Entropy: 0.0678 +[2026-03-20T20:30:48.381555Z] Loop 13077: Loss: 1.20e-02, Avg Return: 0.863, Regret: 0.0030, Entropy: 0.0650 +[2026-03-20T20:30:49.235973Z] Loop 13078: Loss: 1.19e-02, Avg Return: 0.864, Regret: 0.0030, Entropy: 0.0621 +[2026-03-20T20:30:50.089558Z] Loop 13079: Loss: 1.25e-02, Avg Return: 0.865, Regret: 0.0030, Entropy: 0.0672 +[2026-03-20T20:30:50.982464Z] Loop 13080: Loss: 1.39e-02, Avg Return: 0.865, Regret: 0.0003, Entropy: 0.0682 +[2026-03-20T20:30:51.836895Z] Loop 13081: Loss: 1.32e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0691 +[2026-03-20T20:30:52.691417Z] Loop 13082: Loss: 1.47e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0748 +[2026-03-20T20:30:53.545424Z] Loop 13083: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0761 +[2026-03-20T20:30:54.399404Z] Loop 13084: Loss: 1.45e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0713 +[2026-03-20T20:30:55.254315Z] Loop 13085: Loss: 1.51e-02, Avg Return: 0.860, Regret: 0.0003, Entropy: 0.0776 +[2026-03-20T20:30:56.109894Z] Loop 13086: Loss: 1.58e-02, Avg Return: 0.857, Regret: 0.0003, Entropy: 0.0816 +[2026-03-20T20:30:56.965624Z] Loop 13087: Loss: 1.53e-02, Avg Return: 0.856, Regret: 0.0003, Entropy: 0.0820 +[2026-03-20T20:30:57.819865Z] Loop 13088: Loss: 1.63e-02, Avg Return: 0.853, Regret: 0.0003, Entropy: 0.0871 +[2026-03-20T20:30:58.674199Z] Loop 13089: Loss: 1.76e-02, Avg Return: 0.853, Regret: 0.0003, Entropy: 0.0906 +[2026-03-20T20:30:59.570272Z] Loop 13090: Loss: 1.78e-02, Avg Return: 0.858, Regret: 0.0057, Entropy: 0.0909 +[2026-03-20T20:31:00.425621Z] Loop 13091: Loss: 1.79e-02, Avg Return: 0.859, Regret: 0.0057, Entropy: 0.0893 +[2026-03-20T20:31:01.281007Z] Loop 13092: Loss: 1.90e-02, Avg Return: 0.862, Regret: 0.0057, Entropy: 0.0964 +[2026-03-20T20:31:02.135968Z] Loop 13093: Loss: 1.87e-02, Avg Return: 0.862, Regret: 0.0057, Entropy: 0.0963 +[2026-03-20T20:31:02.990773Z] Loop 13094: Loss: 1.90e-02, Avg Return: 0.864, Regret: 0.0057, Entropy: 0.0940 +[2026-03-20T20:31:03.844219Z] Loop 13095: Loss: 1.65e-02, Avg Return: 0.865, Regret: 0.0057, Entropy: 0.0823 +[2026-03-20T20:31:04.699858Z] Loop 13096: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0057, Entropy: 0.0844 +[2026-03-20T20:31:05.554027Z] Loop 13097: Loss: 1.79e-02, Avg Return: 0.862, Regret: 0.0057, Entropy: 0.0880 +[2026-03-20T20:31:06.408330Z] Loop 13098: Loss: 1.69e-02, Avg Return: 0.864, Regret: 0.0057, Entropy: 0.0856 +[2026-03-20T20:31:07.263691Z] Loop 13099: Loss: 1.64e-02, Avg Return: 0.864, Regret: 0.0057, Entropy: 0.0842 +[2026-03-20T20:31:08.158162Z] Loop 13100: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0853 +[2026-03-20T20:31:09.013002Z] Loop 13101: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0886 +[2026-03-20T20:31:09.867728Z] Loop 13102: Loss: 1.82e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0890 +[2026-03-20T20:31:10.721836Z] Loop 13103: Loss: 1.78e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0889 +[2026-03-20T20:31:11.575772Z] Loop 13104: Loss: 1.99e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0945 +[2026-03-20T20:31:12.429700Z] Loop 13105: Loss: 1.93e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0949 +[2026-03-20T20:31:13.283632Z] Loop 13106: Loss: 1.90e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0945 +[2026-03-20T20:31:14.136849Z] Loop 13107: Loss: 2.05e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0985 +[2026-03-20T20:31:14.990457Z] Loop 13108: Loss: 1.90e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0949 +[2026-03-20T20:31:15.844789Z] Loop 13109: Loss: 1.88e-02, Avg Return: 0.861, Regret: 0.0003, Entropy: 0.0920 +[2026-03-20T20:31:16.740498Z] Loop 13110: Loss: 1.97e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0976 +[2026-03-20T20:31:17.594224Z] Loop 13111: Loss: 1.97e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0961 +[2026-03-20T20:31:18.447821Z] Loop 13112: Loss: 1.91e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0918 +[2026-03-20T20:31:19.302995Z] Loop 13113: Loss: 1.81e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0894 +[2026-03-20T20:31:20.157726Z] Loop 13114: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0845 +[2026-03-20T20:31:21.011584Z] Loop 13115: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0858 +[2026-03-20T20:31:21.865121Z] Loop 13116: Loss: 1.67e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0831 +[2026-03-20T20:31:22.721604Z] Loop 13117: Loss: 1.68e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0820 +[2026-03-20T20:31:23.576149Z] Loop 13118: Loss: 1.83e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0906 +[2026-03-20T20:31:24.430239Z] Loop 13119: Loss: 1.99e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.1000 +[2026-03-20T20:31:25.324582Z] Loop 13120: Loss: 2.15e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.1047 +[2026-03-20T20:31:26.178898Z] Loop 13121: Loss: 2.01e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.1017 +[2026-03-20T20:31:27.032937Z] Loop 13122: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0897 +[2026-03-20T20:31:27.886852Z] Loop 13123: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0831 +[2026-03-20T20:31:28.740464Z] Loop 13124: Loss: 1.57e-02, Avg Return: 0.860, Regret: 0.0016, Entropy: 0.0837 +[2026-03-20T20:31:29.594705Z] Loop 13125: Loss: 1.64e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0783 +[2026-03-20T20:31:30.449389Z] Loop 13126: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0843 +[2026-03-20T20:31:31.304129Z] Loop 13127: Loss: 1.60e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0828 +[2026-03-20T20:31:32.158580Z] Loop 13128: Loss: 1.52e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0791 +[2026-03-20T20:31:33.013424Z] Loop 13129: Loss: 1.49e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0772 +[2026-03-20T20:31:33.907063Z] Loop 13130: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.0726 +[2026-03-20T20:31:34.760948Z] Loop 13131: Loss: 1.49e-02, Avg Return: 0.860, Regret: 0.0028, Entropy: 0.0798 +[2026-03-20T20:31:35.614159Z] Loop 13132: Loss: 1.57e-02, Avg Return: 0.860, Regret: 0.0028, Entropy: 0.0817 +[2026-03-20T20:31:36.468522Z] Loop 13133: Loss: 1.53e-02, Avg Return: 0.859, Regret: 0.0028, Entropy: 0.0801 +[2026-03-20T20:31:37.321730Z] Loop 13134: Loss: 1.46e-02, Avg Return: 0.860, Regret: 0.0028, Entropy: 0.0779 +[2026-03-20T20:31:38.175853Z] Loop 13135: Loss: 1.45e-02, Avg Return: 0.858, Regret: 0.0028, Entropy: 0.0793 +[2026-03-20T20:31:39.028804Z] Loop 13136: Loss: 1.42e-02, Avg Return: 0.859, Regret: 0.0028, Entropy: 0.0759 +[2026-03-20T20:31:39.882932Z] Loop 13137: Loss: 1.45e-02, Avg Return: 0.859, Regret: 0.0028, Entropy: 0.0756 +[2026-03-20T20:31:40.735782Z] Loop 13138: Loss: 1.40e-02, Avg Return: 0.859, Regret: 0.0028, Entropy: 0.0729 +[2026-03-20T20:31:41.588670Z] Loop 13139: Loss: 1.37e-02, Avg Return: 0.859, Regret: 0.0028, Entropy: 0.0787 +[2026-03-20T20:31:42.480649Z] Loop 13140: Loss: 1.39e-02, Avg Return: 0.860, Regret: 0.0041, Entropy: 0.0786 +[2026-03-20T20:31:43.335094Z] Loop 13141: Loss: 1.37e-02, Avg Return: 0.859, Regret: 0.0041, Entropy: 0.0733 +[2026-03-20T20:31:44.189052Z] Loop 13142: Loss: 1.31e-02, Avg Return: 0.861, Regret: 0.0041, Entropy: 0.0711 +[2026-03-20T20:31:45.043189Z] Loop 13143: Loss: 1.14e-02, Avg Return: 0.862, Regret: 0.0041, Entropy: 0.0660 +[2026-03-20T20:31:45.898280Z] Loop 13144: Loss: 1.13e-02, Avg Return: 0.861, Regret: 0.0041, Entropy: 0.0601 +[2026-03-20T20:31:46.753551Z] Loop 13145: Loss: 1.07e-02, Avg Return: 0.863, Regret: 0.0041, Entropy: 0.0596 +[2026-03-20T20:31:47.608101Z] Loop 13146: Loss: 1.17e-02, Avg Return: 0.863, Regret: 0.0041, Entropy: 0.0612 +[2026-03-20T20:31:48.461064Z] Loop 13147: Loss: 1.12e-02, Avg Return: 0.864, Regret: 0.0041, Entropy: 0.0596 +[2026-03-20T20:31:49.313933Z] Loop 13148: Loss: 1.08e-02, Avg Return: 0.863, Regret: 0.0041, Entropy: 0.0572 +[2026-03-20T20:31:50.168766Z] Loop 13149: Loss: 9.81e-03, Avg Return: 0.863, Regret: 0.0041, Entropy: 0.0540 +[2026-03-20T20:31:51.063065Z] Loop 13150: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0595 +[2026-03-20T20:31:51.917466Z] Loop 13151: Loss: 1.08e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0573 +[2026-03-20T20:31:52.771939Z] Loop 13152: Loss: 1.05e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0570 +[2026-03-20T20:31:53.626116Z] Loop 13153: Loss: 1.08e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0595 +[2026-03-20T20:31:54.480291Z] Loop 13154: Loss: 1.10e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0585 +[2026-03-20T20:31:55.335292Z] Loop 13155: Loss: 1.13e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0599 +[2026-03-20T20:31:56.189171Z] Loop 13156: Loss: 1.09e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0568 +[2026-03-20T20:31:57.044043Z] Loop 13157: Loss: 1.12e-02, Avg Return: 0.865, Regret: 0.0005, Entropy: 0.0590 +[2026-03-20T20:31:57.898591Z] Loop 13158: Loss: 1.11e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0593 +[2026-03-20T20:31:58.752280Z] Loop 13159: Loss: 1.11e-02, Avg Return: 0.861, Regret: 0.0005, Entropy: 0.0597 +[2026-03-20T20:31:59.646910Z] Loop 13160: Loss: 1.20e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0641 +[2026-03-20T20:32:00.500814Z] Loop 13161: Loss: 1.18e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0615 +[2026-03-20T20:32:01.355179Z] Loop 13162: Loss: 1.16e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0634 +[2026-03-20T20:32:02.210254Z] Loop 13163: Loss: 1.22e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0658 +[2026-03-20T20:32:03.064677Z] Loop 13164: Loss: 1.16e-02, Avg Return: 0.860, Regret: 0.0016, Entropy: 0.0639 +[2026-03-20T20:32:03.918351Z] Loop 13165: Loss: 1.27e-02, Avg Return: 0.860, Regret: 0.0016, Entropy: 0.0673 +[2026-03-20T20:32:04.772129Z] Loop 13166: Loss: 1.27e-02, Avg Return: 0.860, Regret: 0.0016, Entropy: 0.0682 +[2026-03-20T20:32:05.626994Z] Loop 13167: Loss: 1.20e-02, Avg Return: 0.860, Regret: 0.0016, Entropy: 0.0665 +[2026-03-20T20:32:06.482372Z] Loop 13168: Loss: 1.18e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0648 +[2026-03-20T20:32:07.336642Z] Loop 13169: Loss: 1.20e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0647 +[2026-03-20T20:32:08.230024Z] Loop 13170: Loss: 1.24e-02, Avg Return: 0.860, Regret: 0.0027, Entropy: 0.0657 +[2026-03-20T20:32:09.083535Z] Loop 13171: Loss: 1.12e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.0635 +[2026-03-20T20:32:09.937802Z] Loop 13172: Loss: 1.29e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.0668 +[2026-03-20T20:32:10.791829Z] Loop 13173: Loss: 1.17e-02, Avg Return: 0.860, Regret: 0.0027, Entropy: 0.0664 +[2026-03-20T20:32:11.645769Z] Loop 13174: Loss: 1.16e-02, Avg Return: 0.860, Regret: 0.0027, Entropy: 0.0645 +[2026-03-20T20:32:12.499395Z] Loop 13175: Loss: 1.20e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.0644 +[2026-03-20T20:32:13.353675Z] Loop 13176: Loss: 1.31e-02, Avg Return: 0.861, Regret: 0.0027, Entropy: 0.0699 +[2026-03-20T20:32:14.207843Z] Loop 13177: Loss: 1.37e-02, Avg Return: 0.860, Regret: 0.0027, Entropy: 0.0767 +[2026-03-20T20:32:15.061808Z] Loop 13178: Loss: 1.35e-02, Avg Return: 0.859, Regret: 0.0027, Entropy: 0.0718 +[2026-03-20T20:32:15.915075Z] Loop 13179: Loss: 1.42e-02, Avg Return: 0.860, Regret: 0.0027, Entropy: 0.0763 +[2026-03-20T20:32:16.808575Z] Loop 13180: Loss: 1.43e-02, Avg Return: 0.861, Regret: 0.0031, Entropy: 0.0762 +[2026-03-20T20:32:17.662766Z] Loop 13181: Loss: 1.38e-02, Avg Return: 0.861, Regret: 0.0031, Entropy: 0.0718 +[2026-03-20T20:32:18.517040Z] Loop 13182: Loss: 1.28e-02, Avg Return: 0.861, Regret: 0.0031, Entropy: 0.0690 +[2026-03-20T20:32:19.370380Z] Loop 13183: Loss: 1.17e-02, Avg Return: 0.862, Regret: 0.0031, Entropy: 0.0690 +[2026-03-20T20:32:20.225915Z] Loop 13184: Loss: 1.31e-02, Avg Return: 0.862, Regret: 0.0031, Entropy: 0.0688 +[2026-03-20T20:32:21.080025Z] Loop 13185: Loss: 1.13e-02, Avg Return: 0.863, Regret: 0.0031, Entropy: 0.0644 +[2026-03-20T20:32:21.934532Z] Loop 13186: Loss: 1.20e-02, Avg Return: 0.864, Regret: 0.0031, Entropy: 0.0655 +[2026-03-20T20:32:22.787688Z] Loop 13187: Loss: 1.22e-02, Avg Return: 0.864, Regret: 0.0031, Entropy: 0.0651 +[2026-03-20T20:32:23.641060Z] Loop 13188: Loss: 1.32e-02, Avg Return: 0.862, Regret: 0.0031, Entropy: 0.0657 +[2026-03-20T20:32:24.495607Z] Loop 13189: Loss: 1.23e-02, Avg Return: 0.864, Regret: 0.0031, Entropy: 0.0671 +[2026-03-20T20:32:25.388004Z] Loop 13190: Loss: 1.17e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0643 +[2026-03-20T20:32:26.243059Z] Loop 13191: Loss: 1.25e-02, Avg Return: 0.865, Regret: 0.0002, Entropy: 0.0607 +[2026-03-20T20:32:27.098213Z] Loop 13192: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0656 +[2026-03-20T20:32:27.952910Z] Loop 13193: Loss: 1.17e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0645 +[2026-03-20T20:32:28.808031Z] Loop 13194: Loss: 1.25e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0641 +[2026-03-20T20:32:29.662967Z] Loop 13195: Loss: 1.26e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0645 +[2026-03-20T20:32:30.517179Z] Loop 13196: Loss: 1.22e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0636 +[2026-03-20T20:32:31.370812Z] Loop 13197: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0685 +[2026-03-20T20:32:32.224549Z] Loop 13198: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0670 +[2026-03-20T20:32:33.079319Z] Loop 13199: Loss: 1.33e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0694 +[2026-03-20T20:32:33.971843Z] Loop 13200: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0694 +[2026-03-20T20:32:34.825653Z] Loop 13201: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0680 +[2026-03-20T20:32:35.680769Z] Loop 13202: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0704 +[2026-03-20T20:32:36.535307Z] Loop 13203: Loss: 1.25e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0666 +[2026-03-20T20:32:37.390572Z] Loop 13204: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0668 +[2026-03-20T20:32:38.245442Z] Loop 13205: Loss: 1.29e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0672 +[2026-03-20T20:32:39.099184Z] Loop 13206: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0651 +[2026-03-20T20:32:39.953306Z] Loop 13207: Loss: 1.27e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0661 +[2026-03-20T20:32:40.807722Z] Loop 13208: Loss: 1.15e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0642 +[2026-03-20T20:32:41.661990Z] Loop 13209: Loss: 1.12e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0594 +[2026-03-20T20:32:42.555649Z] Loop 13210: Loss: 1.28e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.0654 +[2026-03-20T20:32:43.409553Z] Loop 13211: Loss: 1.24e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.0638 +[2026-03-20T20:32:44.263572Z] Loop 13212: Loss: 1.24e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.0674 +[2026-03-20T20:32:45.117134Z] Loop 13213: Loss: 1.19e-02, Avg Return: 0.860, Regret: 0.0021, Entropy: 0.0650 +[2026-03-20T20:32:45.972031Z] Loop 13214: Loss: 1.22e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.0660 +[2026-03-20T20:32:46.827035Z] Loop 13215: Loss: 1.40e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.0728 +[2026-03-20T20:32:47.681001Z] Loop 13216: Loss: 1.22e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.0683 +[2026-03-20T20:32:48.536350Z] Loop 13217: Loss: 1.31e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.0664 +[2026-03-20T20:32:49.389823Z] Loop 13218: Loss: 1.30e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.0686 +[2026-03-20T20:32:50.243582Z] Loop 13219: Loss: 1.37e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.0714 +[2026-03-20T20:32:51.137086Z] Loop 13220: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0017, Entropy: 0.0682 +[2026-03-20T20:32:51.991183Z] Loop 13221: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0720 +[2026-03-20T20:32:52.844846Z] Loop 13222: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0017, Entropy: 0.0715 +[2026-03-20T20:32:53.699511Z] Loop 13223: Loss: 1.40e-02, Avg Return: 0.863, Regret: 0.0017, Entropy: 0.0742 +[2026-03-20T20:32:54.554062Z] Loop 13224: Loss: 1.50e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0732 +[2026-03-20T20:32:55.406552Z] Loop 13225: Loss: 1.32e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0706 +[2026-03-20T20:32:56.260213Z] Loop 13226: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0756 +[2026-03-20T20:32:57.115092Z] Loop 13227: Loss: 1.41e-02, Avg Return: 0.865, Regret: 0.0017, Entropy: 0.0752 +[2026-03-20T20:32:57.969051Z] Loop 13228: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0017, Entropy: 0.0715 +[2026-03-20T20:32:58.822478Z] Loop 13229: Loss: 1.32e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0700 +[2026-03-20T20:32:59.716010Z] Loop 13230: Loss: 1.25e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0663 +[2026-03-20T20:33:00.571595Z] Loop 13231: Loss: 1.29e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0694 +[2026-03-20T20:33:01.425961Z] Loop 13232: Loss: 1.31e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0663 +[2026-03-20T20:33:02.279970Z] Loop 13233: Loss: 1.22e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0663 +[2026-03-20T20:33:03.133528Z] Loop 13234: Loss: 1.22e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0641 +[2026-03-20T20:33:03.988405Z] Loop 13235: Loss: 1.15e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0639 +[2026-03-20T20:33:04.843101Z] Loop 13236: Loss: 1.25e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0641 +[2026-03-20T20:33:05.697274Z] Loop 13237: Loss: 1.22e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0608 +[2026-03-20T20:33:06.551051Z] Loop 13238: Loss: 1.20e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0643 +[2026-03-20T20:33:07.405067Z] Loop 13239: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0653 +[2026-03-20T20:33:08.298993Z] Loop 13240: Loss: 1.27e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0660 +[2026-03-20T20:33:09.153278Z] Loop 13241: Loss: 1.11e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0624 +[2026-03-20T20:33:10.006601Z] Loop 13242: Loss: 1.11e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0623 +[2026-03-20T20:33:10.861288Z] Loop 13243: Loss: 1.20e-02, Avg Return: 0.865, Regret: 0.0004, Entropy: 0.0624 +[2026-03-20T20:33:11.716016Z] Loop 13244: Loss: 1.22e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0643 +[2026-03-20T20:33:12.570390Z] Loop 13245: Loss: 1.24e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0631 +[2026-03-20T20:33:13.425276Z] Loop 13246: Loss: 1.16e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0632 +[2026-03-20T20:33:14.280127Z] Loop 13247: Loss: 1.20e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0630 +[2026-03-20T20:33:15.135812Z] Loop 13248: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0635 +[2026-03-20T20:33:15.989843Z] Loop 13249: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0698 +[2026-03-20T20:33:16.884043Z] Loop 13250: Loss: 1.29e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0679 +[2026-03-20T20:33:17.738778Z] Loop 13251: Loss: 1.35e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0722 +[2026-03-20T20:33:18.593069Z] Loop 13252: Loss: 1.35e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0699 +[2026-03-20T20:33:19.448515Z] Loop 13253: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0719 +[2026-03-20T20:33:20.303351Z] Loop 13254: Loss: 1.31e-02, Avg Return: 0.865, Regret: 0.0007, Entropy: 0.0705 +[2026-03-20T20:33:21.157567Z] Loop 13255: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0706 +[2026-03-20T20:33:22.010976Z] Loop 13256: Loss: 1.37e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0728 +[2026-03-20T20:33:22.864448Z] Loop 13257: Loss: 1.45e-02, Avg Return: 0.865, Regret: 0.0007, Entropy: 0.0761 +[2026-03-20T20:33:23.719898Z] Loop 13258: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0725 +[2026-03-20T20:33:24.574684Z] Loop 13259: Loss: 1.39e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0736 +[2026-03-20T20:33:25.468376Z] Loop 13260: Loss: 1.40e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0719 +[2026-03-20T20:33:26.321116Z] Loop 13261: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0704 +[2026-03-20T20:33:27.176085Z] Loop 13262: Loss: 1.46e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0744 +[2026-03-20T20:33:28.030411Z] Loop 13263: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0739 +[2026-03-20T20:33:28.883953Z] Loop 13264: Loss: 1.30e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0698 +[2026-03-20T20:33:29.737684Z] Loop 13265: Loss: 1.25e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0685 +[2026-03-20T20:33:30.591459Z] Loop 13266: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0698 +[2026-03-20T20:33:31.445649Z] Loop 13267: Loss: 1.32e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0686 +[2026-03-20T20:33:32.299376Z] Loop 13268: Loss: 1.21e-02, Avg Return: 0.865, Regret: 0.0001, Entropy: 0.0659 +[2026-03-20T20:33:33.152596Z] Loop 13269: Loss: 1.23e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0669 +[2026-03-20T20:33:34.047085Z] Loop 13270: Loss: 1.27e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0669 +[2026-03-20T20:33:34.901596Z] Loop 13271: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0714 +[2026-03-20T20:33:35.755622Z] Loop 13272: Loss: 1.43e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0724 +[2026-03-20T20:33:36.609666Z] Loop 13273: Loss: 1.39e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0738 +[2026-03-20T20:33:37.463696Z] Loop 13274: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0740 +[2026-03-20T20:33:38.317415Z] Loop 13275: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0740 +[2026-03-20T20:33:39.172500Z] Loop 13276: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0796 +[2026-03-20T20:33:40.028108Z] Loop 13277: Loss: 1.48e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0812 +[2026-03-20T20:33:40.883204Z] Loop 13278: Loss: 1.40e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0775 +[2026-03-20T20:33:41.737468Z] Loop 13279: Loss: 1.50e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0772 +[2026-03-20T20:33:42.632154Z] Loop 13280: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0851 +[2026-03-20T20:33:43.485131Z] Loop 13281: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0813 +[2026-03-20T20:33:44.339177Z] Loop 13282: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0804 +[2026-03-20T20:33:45.192591Z] Loop 13283: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0805 +[2026-03-20T20:33:46.046811Z] Loop 13284: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0022, Entropy: 0.0699 +[2026-03-20T20:33:46.900777Z] Loop 13285: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0763 +[2026-03-20T20:33:47.754285Z] Loop 13286: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0022, Entropy: 0.0755 +[2026-03-20T20:33:48.607830Z] Loop 13287: Loss: 1.31e-02, Avg Return: 0.864, Regret: 0.0022, Entropy: 0.0703 +[2026-03-20T20:33:49.461123Z] Loop 13288: Loss: 1.26e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0699 +[2026-03-20T20:33:50.314381Z] Loop 13289: Loss: 1.33e-02, Avg Return: 0.864, Regret: 0.0022, Entropy: 0.0692 +[2026-03-20T20:33:51.207727Z] Loop 13290: Loss: 1.32e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0699 +[2026-03-20T20:33:52.062807Z] Loop 13291: Loss: 1.42e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0718 +[2026-03-20T20:33:52.916787Z] Loop 13292: Loss: 1.38e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0683 +[2026-03-20T20:33:53.770305Z] Loop 13293: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0716 +[2026-03-20T20:33:54.624759Z] Loop 13294: Loss: 1.25e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0655 +[2026-03-20T20:33:55.479975Z] Loop 13295: Loss: 1.24e-02, Avg Return: 0.865, Regret: 0.0003, Entropy: 0.0682 +[2026-03-20T20:33:56.333794Z] Loop 13296: Loss: 1.12e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0629 +[2026-03-20T20:33:57.187953Z] Loop 13297: Loss: 1.28e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0686 +[2026-03-20T20:33:58.042512Z] Loop 13298: Loss: 1.25e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0669 +[2026-03-20T20:33:58.897145Z] Loop 13299: Loss: 1.14e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0630 +[2026-03-20T20:33:59.791810Z] Loop 13300: Loss: 1.25e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0669 +[2026-03-20T20:34:00.646063Z] Loop 13301: Loss: 1.29e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0691 +[2026-03-20T20:34:01.501659Z] Loop 13302: Loss: 1.24e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0617 +[2026-03-20T20:34:02.356765Z] Loop 13303: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0658 +[2026-03-20T20:34:03.211703Z] Loop 13304: Loss: 1.08e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0600 +[2026-03-20T20:34:04.065749Z] Loop 13305: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0667 +[2026-03-20T20:34:04.919512Z] Loop 13306: Loss: 1.16e-02, Avg Return: 0.861, Regret: 0.0004, Entropy: 0.0642 +[2026-03-20T20:34:05.773841Z] Loop 13307: Loss: 1.18e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0647 +[2026-03-20T20:34:06.628205Z] Loop 13308: Loss: 1.22e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0634 +[2026-03-20T20:34:07.483225Z] Loop 13309: Loss: 1.20e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0617 +[2026-03-20T20:34:08.378346Z] Loop 13310: Loss: 1.23e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0646 +[2026-03-20T20:34:09.232634Z] Loop 13311: Loss: 1.18e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0631 +[2026-03-20T20:34:10.087008Z] Loop 13312: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0636 +[2026-03-20T20:34:10.941961Z] Loop 13313: Loss: 1.16e-02, Avg Return: 0.865, Regret: 0.0006, Entropy: 0.0614 +[2026-03-20T20:34:11.797244Z] Loop 13314: Loss: 1.25e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0660 +[2026-03-20T20:34:12.651432Z] Loop 13315: Loss: 1.14e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0629 +[2026-03-20T20:34:13.505028Z] Loop 13316: Loss: 1.17e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0630 +[2026-03-20T20:34:14.360933Z] Loop 13317: Loss: 1.23e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0689 +[2026-03-20T20:34:15.218298Z] Loop 13318: Loss: 1.14e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0610 +[2026-03-20T20:34:16.072471Z] Loop 13319: Loss: 1.13e-02, Avg Return: 0.865, Regret: 0.0006, Entropy: 0.0625 +[2026-03-20T20:34:16.965093Z] Loop 13320: Loss: 1.18e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0618 +[2026-03-20T20:34:17.820540Z] Loop 13321: Loss: 1.20e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0638 +[2026-03-20T20:34:18.675745Z] Loop 13322: Loss: 1.26e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0655 +[2026-03-20T20:34:19.530313Z] Loop 13323: Loss: 1.22e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0640 +[2026-03-20T20:34:20.384855Z] Loop 13324: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0662 +[2026-03-20T20:34:21.239203Z] Loop 13325: Loss: 1.19e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0638 +[2026-03-20T20:34:22.093376Z] Loop 13326: Loss: 1.24e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0682 +[2026-03-20T20:34:22.947620Z] Loop 13327: Loss: 1.18e-02, Avg Return: 0.861, Regret: 0.0003, Entropy: 0.0647 +[2026-03-20T20:34:23.801264Z] Loop 13328: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0727 +[2026-03-20T20:34:24.655829Z] Loop 13329: Loss: 1.23e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0697 +[2026-03-20T20:34:25.549900Z] Loop 13330: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0698 +[2026-03-20T20:34:26.403807Z] Loop 13331: Loss: 1.30e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0726 +[2026-03-20T20:34:27.257783Z] Loop 13332: Loss: 1.29e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0703 +[2026-03-20T20:34:28.111310Z] Loop 13333: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0722 +[2026-03-20T20:34:28.964746Z] Loop 13334: Loss: 1.29e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0714 +[2026-03-20T20:34:29.819219Z] Loop 13335: Loss: 1.35e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0705 +[2026-03-20T20:34:30.673445Z] Loop 13336: Loss: 1.29e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0722 +[2026-03-20T20:34:31.527507Z] Loop 13337: Loss: 1.31e-02, Avg Return: 0.864, Regret: 0.0013, Entropy: 0.0700 +[2026-03-20T20:34:32.381413Z] Loop 13338: Loss: 1.22e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0666 +[2026-03-20T20:34:33.235850Z] Loop 13339: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0703 +[2026-03-20T20:34:34.129526Z] Loop 13340: Loss: 1.22e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0649 +[2026-03-20T20:34:34.985094Z] Loop 13341: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0700 +[2026-03-20T20:34:35.838960Z] Loop 13342: Loss: 1.35e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0720 +[2026-03-20T20:34:36.692363Z] Loop 13343: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0704 +[2026-03-20T20:34:37.547178Z] Loop 13344: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0747 +[2026-03-20T20:34:38.402824Z] Loop 13345: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0721 +[2026-03-20T20:34:39.257276Z] Loop 13346: Loss: 1.30e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0710 +[2026-03-20T20:34:40.111825Z] Loop 13347: Loss: 1.26e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0720 +[2026-03-20T20:34:40.967233Z] Loop 13348: Loss: 1.24e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0676 +[2026-03-20T20:34:41.823415Z] Loop 13349: Loss: 1.32e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0687 +[2026-03-20T20:34:42.718779Z] Loop 13350: Loss: 1.22e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0661 +[2026-03-20T20:34:43.573077Z] Loop 13351: Loss: 1.25e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0681 +[2026-03-20T20:34:44.427969Z] Loop 13352: Loss: 1.19e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0665 +[2026-03-20T20:34:45.282842Z] Loop 13353: Loss: 1.23e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0658 +[2026-03-20T20:34:46.137400Z] Loop 13354: Loss: 1.12e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0578 +[2026-03-20T20:34:46.992247Z] Loop 13355: Loss: 1.10e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0607 +[2026-03-20T20:34:47.846305Z] Loop 13356: Loss: 1.14e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0597 +[2026-03-20T20:34:48.701131Z] Loop 13357: Loss: 1.07e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0578 +[2026-03-20T20:34:49.555417Z] Loop 13358: Loss: 1.05e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0589 +[2026-03-20T20:34:50.409359Z] Loop 13359: Loss: 1.15e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0578 +[2026-03-20T20:34:51.303081Z] Loop 13360: Loss: 1.13e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0605 +[2026-03-20T20:34:52.157213Z] Loop 13361: Loss: 1.05e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0594 +[2026-03-20T20:34:53.011671Z] Loop 13362: Loss: 1.13e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0592 +[2026-03-20T20:34:53.866035Z] Loop 13363: Loss: 1.15e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0619 +[2026-03-20T20:34:54.720162Z] Loop 13364: Loss: 1.14e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0601 +[2026-03-20T20:34:55.574323Z] Loop 13365: Loss: 1.10e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0577 +[2026-03-20T20:34:56.429097Z] Loop 13366: Loss: 1.16e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0621 +[2026-03-20T20:34:57.282306Z] Loop 13367: Loss: 1.13e-02, Avg Return: 0.865, Regret: 0.0006, Entropy: 0.0613 +[2026-03-20T20:34:58.136566Z] Loop 13368: Loss: 1.16e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0611 +[2026-03-20T20:34:58.990067Z] Loop 13369: Loss: 1.13e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0626 +[2026-03-20T20:34:59.883708Z] Loop 13370: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0647 +[2026-03-20T20:35:00.738105Z] Loop 13371: Loss: 1.13e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0597 +[2026-03-20T20:35:01.593257Z] Loop 13372: Loss: 1.20e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0671 +[2026-03-20T20:35:02.448373Z] Loop 13373: Loss: 1.20e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0645 +[2026-03-20T20:35:03.302710Z] Loop 13374: Loss: 1.18e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0644 +[2026-03-20T20:35:04.155866Z] Loop 13375: Loss: 1.30e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0676 +[2026-03-20T20:35:05.010764Z] Loop 13376: Loss: 1.40e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.0722 +[2026-03-20T20:35:05.865215Z] Loop 13377: Loss: 1.48e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.0751 +[2026-03-20T20:35:06.718443Z] Loop 13378: Loss: 1.59e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.0782 +[2026-03-20T20:35:07.571346Z] Loop 13379: Loss: 1.50e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.0751 +[2026-03-20T20:35:08.467215Z] Loop 13380: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0775 +[2026-03-20T20:35:09.322375Z] Loop 13381: Loss: 1.68e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0822 +[2026-03-20T20:35:10.176059Z] Loop 13382: Loss: 1.70e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.0873 +[2026-03-20T20:35:11.029645Z] Loop 13383: Loss: 1.95e-02, Avg Return: 0.858, Regret: 0.0022, Entropy: 0.0884 +[2026-03-20T20:35:11.883877Z] Loop 13384: Loss: 1.70e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.0837 +[2026-03-20T20:35:12.738292Z] Loop 13385: Loss: 1.87e-02, Avg Return: 0.859, Regret: 0.0022, Entropy: 0.0867 +[2026-03-20T20:35:13.592493Z] Loop 13386: Loss: 1.84e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.0865 +[2026-03-20T20:35:14.446016Z] Loop 13387: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0022, Entropy: 0.0771 +[2026-03-20T20:35:15.300334Z] Loop 13388: Loss: 1.30e-02, Avg Return: 0.863, Regret: 0.0022, Entropy: 0.0678 +[2026-03-20T20:35:16.153828Z] Loop 13389: Loss: 1.36e-02, Avg Return: 0.864, Regret: 0.0022, Entropy: 0.0710 +[2026-03-20T20:35:17.047924Z] Loop 13390: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0665 +[2026-03-20T20:35:17.902997Z] Loop 13391: Loss: 1.16e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0638 +[2026-03-20T20:35:18.757523Z] Loop 13392: Loss: 1.18e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0636 +[2026-03-20T20:35:19.610716Z] Loop 13393: Loss: 1.32e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0693 +[2026-03-20T20:35:20.465061Z] Loop 13394: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0686 +[2026-03-20T20:35:21.319386Z] Loop 13395: Loss: 1.30e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0685 +[2026-03-20T20:35:22.173038Z] Loop 13396: Loss: 1.27e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0732 +[2026-03-20T20:35:23.028372Z] Loop 13397: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0738 +[2026-03-20T20:35:23.883746Z] Loop 13398: Loss: 1.24e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0664 +[2026-03-20T20:35:24.738675Z] Loop 13399: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0685 +[2026-03-20T20:35:25.634698Z] Loop 13400: Loss: 1.33e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0725 +[2026-03-20T20:35:26.488376Z] Loop 13401: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0753 +[2026-03-20T20:35:27.341622Z] Loop 13402: Loss: 1.33e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0736 +[2026-03-20T20:35:28.196137Z] Loop 13403: Loss: 1.40e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0776 +[2026-03-20T20:35:29.050562Z] Loop 13404: Loss: 1.36e-02, Avg Return: 0.865, Regret: 0.0001, Entropy: 0.0742 +[2026-03-20T20:35:29.903800Z] Loop 13405: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0778 +[2026-03-20T20:35:30.756880Z] Loop 13406: Loss: 1.42e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0783 +[2026-03-20T20:35:31.611401Z] Loop 13407: Loss: 1.33e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0730 +[2026-03-20T20:35:32.465287Z] Loop 13408: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0722 +[2026-03-20T20:35:33.318820Z] Loop 13409: Loss: 1.33e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0721 +[2026-03-20T20:35:34.212479Z] Loop 13410: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0736 +[2026-03-20T20:35:35.066470Z] Loop 13411: Loss: 1.33e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0715 +[2026-03-20T20:35:35.919971Z] Loop 13412: Loss: 1.31e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0725 +[2026-03-20T20:35:36.773570Z] Loop 13413: Loss: 1.32e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0715 +[2026-03-20T20:35:37.627836Z] Loop 13414: Loss: 1.37e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0754 +[2026-03-20T20:35:38.482957Z] Loop 13415: Loss: 1.45e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0721 +[2026-03-20T20:35:39.337706Z] Loop 13416: Loss: 1.39e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0748 +[2026-03-20T20:35:40.191816Z] Loop 13417: Loss: 1.43e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0756 +[2026-03-20T20:35:41.046382Z] Loop 13418: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0738 +[2026-03-20T20:35:41.903846Z] Loop 13419: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0700 +[2026-03-20T20:35:42.800811Z] Loop 13420: Loss: 1.36e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0723 +[2026-03-20T20:35:43.654413Z] Loop 13421: Loss: 1.30e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0688 +[2026-03-20T20:35:44.509040Z] Loop 13422: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0783 +[2026-03-20T20:35:45.363136Z] Loop 13423: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0732 +[2026-03-20T20:35:46.216893Z] Loop 13424: Loss: 1.50e-02, Avg Return: 0.865, Regret: 0.0002, Entropy: 0.0793 +[2026-03-20T20:35:47.071058Z] Loop 13425: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0772 +[2026-03-20T20:35:47.925369Z] Loop 13426: Loss: 1.52e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0785 +[2026-03-20T20:35:48.781239Z] Loop 13427: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0807 +[2026-03-20T20:35:49.635735Z] Loop 13428: Loss: 1.53e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0794 +[2026-03-20T20:35:50.489746Z] Loop 13429: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0779 +[2026-03-20T20:35:51.384255Z] Loop 13430: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0806 +[2026-03-20T20:35:52.239718Z] Loop 13431: Loss: 1.57e-02, Avg Return: 0.865, Regret: 0.0007, Entropy: 0.0824 +[2026-03-20T20:35:53.094017Z] Loop 13432: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0846 +[2026-03-20T20:35:53.947740Z] Loop 13433: Loss: 1.65e-02, Avg Return: 0.865, Regret: 0.0007, Entropy: 0.0869 +[2026-03-20T20:35:54.801937Z] Loop 13434: Loss: 1.66e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0857 +[2026-03-20T20:35:55.656604Z] Loop 13435: Loss: 1.54e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0804 +[2026-03-20T20:35:56.511410Z] Loop 13436: Loss: 1.46e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0753 +[2026-03-20T20:35:57.367130Z] Loop 13437: Loss: 1.40e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0749 +[2026-03-20T20:35:58.222549Z] Loop 13438: Loss: 1.36e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0743 +[2026-03-20T20:35:59.075882Z] Loop 13439: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0749 +[2026-03-20T20:35:59.970189Z] Loop 13440: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0728 +[2026-03-20T20:36:00.823706Z] Loop 13441: Loss: 1.43e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0758 +[2026-03-20T20:36:01.677907Z] Loop 13442: Loss: 1.45e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0813 +[2026-03-20T20:36:02.532267Z] Loop 13443: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0776 +[2026-03-20T20:36:03.386961Z] Loop 13444: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0836 +[2026-03-20T20:36:04.240690Z] Loop 13445: Loss: 1.43e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0809 +[2026-03-20T20:36:05.094355Z] Loop 13446: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0893 +[2026-03-20T20:36:05.948603Z] Loop 13447: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0910 +[2026-03-20T20:36:06.803832Z] Loop 13448: Loss: 1.76e-02, Avg Return: 0.860, Regret: 0.0006, Entropy: 0.1000 +[2026-03-20T20:36:07.659504Z] Loop 13449: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0972 +[2026-03-20T20:36:08.554725Z] Loop 13450: Loss: 1.81e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.1034 +[2026-03-20T20:36:09.407676Z] Loop 13451: Loss: 1.78e-02, Avg Return: 0.859, Regret: 0.0016, Entropy: 0.0999 +[2026-03-20T20:36:10.261159Z] Loop 13452: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0965 +[2026-03-20T20:36:11.115463Z] Loop 13453: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0950 +[2026-03-20T20:36:11.971292Z] Loop 13454: Loss: 1.71e-02, Avg Return: 0.864, Regret: 0.0016, Entropy: 0.0928 +[2026-03-20T20:36:12.825602Z] Loop 13455: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0865 +[2026-03-20T20:36:13.679934Z] Loop 13456: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0917 +[2026-03-20T20:36:14.535104Z] Loop 13457: Loss: 1.82e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0956 +[2026-03-20T20:36:15.390094Z] Loop 13458: Loss: 1.66e-02, Avg Return: 0.864, Regret: 0.0016, Entropy: 0.0849 +[2026-03-20T20:36:16.244625Z] Loop 13459: Loss: 1.68e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0900 +[2026-03-20T20:36:17.138427Z] Loop 13460: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0887 +[2026-03-20T20:36:17.993654Z] Loop 13461: Loss: 1.72e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0927 +[2026-03-20T20:36:18.848998Z] Loop 13462: Loss: 1.91e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0941 +[2026-03-20T20:36:19.704197Z] Loop 13463: Loss: 1.73e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0951 +[2026-03-20T20:36:20.558196Z] Loop 13464: Loss: 1.82e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0936 +[2026-03-20T20:36:21.413153Z] Loop 13465: Loss: 1.80e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0987 +[2026-03-20T20:36:22.267340Z] Loop 13466: Loss: 1.93e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.1011 +[2026-03-20T20:36:23.121166Z] Loop 13467: Loss: 2.05e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.1069 +[2026-03-20T20:36:23.975165Z] Loop 13468: Loss: 2.24e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.1124 +[2026-03-20T20:36:24.829545Z] Loop 13469: Loss: 2.30e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.1140 +[2026-03-20T20:36:25.722393Z] Loop 13470: Loss: 2.51e-02, Avg Return: 0.865, Regret: 0.0009, Entropy: 0.1254 +[2026-03-20T20:36:26.575730Z] Loop 13471: Loss: 2.60e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.1278 +[2026-03-20T20:36:27.430667Z] Loop 13472: Loss: 2.61e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.1323 +[2026-03-20T20:36:28.285262Z] Loop 13473: Loss: 2.41e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.1223 +[2026-03-20T20:36:29.139020Z] Loop 13474: Loss: 2.39e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.1259 +[2026-03-20T20:36:29.994099Z] Loop 13475: Loss: 2.42e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.1244 +[2026-03-20T20:36:30.848779Z] Loop 13476: Loss: 2.41e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.1288 +[2026-03-20T20:36:31.704600Z] Loop 13477: Loss: 2.44e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.1300 +[2026-03-20T20:36:32.558574Z] Loop 13478: Loss: 2.62e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.1367 +[2026-03-20T20:36:33.413688Z] Loop 13479: Loss: 2.65e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.1378 +[2026-03-20T20:36:34.309692Z] Loop 13480: Loss: 2.66e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.1413 +[2026-03-20T20:36:35.164226Z] Loop 13481: Loss: 2.75e-02, Avg Return: 0.862, Regret: 0.0026, Entropy: 0.1452 +[2026-03-20T20:36:36.017850Z] Loop 13482: Loss: 2.79e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.1469 +[2026-03-20T20:36:36.870832Z] Loop 13483: Loss: 2.89e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.1470 +[2026-03-20T20:36:37.724717Z] Loop 13484: Loss: 2.82e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.1417 +[2026-03-20T20:36:38.579552Z] Loop 13485: Loss: 2.80e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.1433 +[2026-03-20T20:36:39.433028Z] Loop 13486: Loss: 2.66e-02, Avg Return: 0.860, Regret: 0.0026, Entropy: 0.1404 +[2026-03-20T20:36:40.285558Z] Loop 13487: Loss: 2.54e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.1303 +[2026-03-20T20:36:41.138451Z] Loop 13488: Loss: 2.32e-02, Avg Return: 0.861, Regret: 0.0026, Entropy: 0.1241 +[2026-03-20T20:36:41.993119Z] Loop 13489: Loss: 2.17e-02, Avg Return: 0.862, Regret: 0.0026, Entropy: 0.1135 +[2026-03-20T20:36:42.887936Z] Loop 13490: Loss: 2.00e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.1080 +[2026-03-20T20:36:43.741593Z] Loop 13491: Loss: 1.97e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.1057 +[2026-03-20T20:36:44.595280Z] Loop 13492: Loss: 1.93e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.1009 +[2026-03-20T20:36:45.449095Z] Loop 13493: Loss: 1.75e-02, Avg Return: 0.863, Regret: 0.0019, Entropy: 0.0960 +[2026-03-20T20:36:46.303042Z] Loop 13494: Loss: 1.83e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0953 +[2026-03-20T20:36:47.156221Z] Loop 13495: Loss: 1.87e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0933 +[2026-03-20T20:36:48.009528Z] Loop 13496: Loss: 1.86e-02, Avg Return: 0.860, Regret: 0.0019, Entropy: 0.0969 +[2026-03-20T20:36:48.863742Z] Loop 13497: Loss: 1.83e-02, Avg Return: 0.862, Regret: 0.0019, Entropy: 0.0964 +[2026-03-20T20:36:49.717447Z] Loop 13498: Loss: 1.86e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0960 +[2026-03-20T20:36:50.571835Z] Loop 13499: Loss: 1.81e-02, Avg Return: 0.861, Regret: 0.0019, Entropy: 0.0943 +[2026-03-20T20:36:51.465541Z] Loop 13500: Loss: 1.96e-02, Avg Return: 0.861, Regret: 0.0030, Entropy: 0.1003 +[2026-03-20T20:36:52.318598Z] Loop 13501: Loss: 1.89e-02, Avg Return: 0.860, Regret: 0.0030, Entropy: 0.0979 +[2026-03-20T20:36:53.172177Z] Loop 13502: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0030, Entropy: 0.0917 +[2026-03-20T20:36:54.026647Z] Loop 13503: Loss: 1.79e-02, Avg Return: 0.861, Regret: 0.0030, Entropy: 0.0916 +[2026-03-20T20:36:54.881677Z] Loop 13504: Loss: 1.74e-02, Avg Return: 0.862, Regret: 0.0030, Entropy: 0.0890 +[2026-03-20T20:36:55.735547Z] Loop 13505: Loss: 1.69e-02, Avg Return: 0.862, Regret: 0.0030, Entropy: 0.0856 +[2026-03-20T20:36:56.589590Z] Loop 13506: Loss: 1.75e-02, Avg Return: 0.863, Regret: 0.0030, Entropy: 0.0893 +[2026-03-20T20:36:57.443555Z] Loop 13507: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0030, Entropy: 0.0853 +[2026-03-20T20:36:58.298218Z] Loop 13508: Loss: 1.71e-02, Avg Return: 0.862, Regret: 0.0030, Entropy: 0.0872 +[2026-03-20T20:36:59.152132Z] Loop 13509: Loss: 1.65e-02, Avg Return: 0.864, Regret: 0.0030, Entropy: 0.0860 +[2026-03-20T20:37:00.044614Z] Loop 13510: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0886 +[2026-03-20T20:37:00.898859Z] Loop 13511: Loss: 1.84e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0926 +[2026-03-20T20:37:01.754688Z] Loop 13512: Loss: 1.89e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0961 +[2026-03-20T20:37:02.609632Z] Loop 13513: Loss: 2.00e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0968 +[2026-03-20T20:37:03.463629Z] Loop 13514: Loss: 2.18e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.1074 +[2026-03-20T20:37:04.316776Z] Loop 13515: Loss: 2.20e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.1094 +[2026-03-20T20:37:05.171286Z] Loop 13516: Loss: 2.13e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.1029 +[2026-03-20T20:37:06.025371Z] Loop 13517: Loss: 2.16e-02, Avg Return: 0.860, Regret: 0.0005, Entropy: 0.1072 +[2026-03-20T20:37:06.879738Z] Loop 13518: Loss: 2.14e-02, Avg Return: 0.856, Regret: 0.0005, Entropy: 0.1028 +[2026-03-20T20:37:07.732918Z] Loop 13519: Loss: 2.03e-02, Avg Return: 0.856, Regret: 0.0005, Entropy: 0.1037 +[2026-03-20T20:37:08.628325Z] Loop 13520: Loss: 1.82e-02, Avg Return: 0.861, Regret: 0.0031, Entropy: 0.0931 +[2026-03-20T20:37:09.482206Z] Loop 13521: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0031, Entropy: 0.0857 +[2026-03-20T20:37:10.336469Z] Loop 13522: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0031, Entropy: 0.0777 +[2026-03-20T20:37:11.190278Z] Loop 13523: Loss: 1.46e-02, Avg Return: 0.864, Regret: 0.0031, Entropy: 0.0738 +[2026-03-20T20:37:12.043288Z] Loop 13524: Loss: 1.34e-02, Avg Return: 0.865, Regret: 0.0031, Entropy: 0.0723 +[2026-03-20T20:37:12.896481Z] Loop 13525: Loss: 1.35e-02, Avg Return: 0.864, Regret: 0.0031, Entropy: 0.0702 +[2026-03-20T20:37:13.750381Z] Loop 13526: Loss: 1.34e-02, Avg Return: 0.865, Regret: 0.0031, Entropy: 0.0688 +[2026-03-20T20:37:14.604909Z] Loop 13527: Loss: 1.27e-02, Avg Return: 0.864, Regret: 0.0031, Entropy: 0.0657 +[2026-03-20T20:37:15.458840Z] Loop 13528: Loss: 1.20e-02, Avg Return: 0.864, Regret: 0.0031, Entropy: 0.0662 +[2026-03-20T20:37:16.312267Z] Loop 13529: Loss: 1.22e-02, Avg Return: 0.864, Regret: 0.0031, Entropy: 0.0695 +[2026-03-20T20:37:17.206425Z] Loop 13530: Loss: 1.22e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0684 +[2026-03-20T20:37:18.061245Z] Loop 13531: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0707 +[2026-03-20T20:37:18.916320Z] Loop 13532: Loss: 1.24e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0652 +[2026-03-20T20:37:19.769798Z] Loop 13533: Loss: 1.18e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0663 +[2026-03-20T20:37:20.623590Z] Loop 13534: Loss: 1.19e-02, Avg Return: 0.865, Regret: 0.0002, Entropy: 0.0629 +[2026-03-20T20:37:21.477716Z] Loop 13535: Loss: 1.29e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0683 +[2026-03-20T20:37:22.333286Z] Loop 13536: Loss: 1.19e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0655 +[2026-03-20T20:37:23.187958Z] Loop 13537: Loss: 1.20e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0645 +[2026-03-20T20:37:24.042047Z] Loop 13538: Loss: 1.13e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0645 +[2026-03-20T20:37:24.896680Z] Loop 13539: Loss: 1.19e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0642 +[2026-03-20T20:37:25.792697Z] Loop 13540: Loss: 1.18e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0625 +[2026-03-20T20:37:26.647399Z] Loop 13541: Loss: 1.35e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0688 +[2026-03-20T20:37:27.502462Z] Loop 13542: Loss: 1.29e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0669 +[2026-03-20T20:37:28.357436Z] Loop 13543: Loss: 1.21e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0677 +[2026-03-20T20:37:29.213529Z] Loop 13544: Loss: 1.26e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0678 +[2026-03-20T20:37:30.068740Z] Loop 13545: Loss: 1.14e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0653 +[2026-03-20T20:37:30.923073Z] Loop 13546: Loss: 1.27e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0687 +[2026-03-20T20:37:31.777356Z] Loop 13547: Loss: 1.27e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0677 +[2026-03-20T20:37:32.631674Z] Loop 13548: Loss: 1.23e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0671 +[2026-03-20T20:37:33.486143Z] Loop 13549: Loss: 1.17e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0637 +[2026-03-20T20:37:34.379309Z] Loop 13550: Loss: 1.29e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0682 +[2026-03-20T20:37:35.233164Z] Loop 13551: Loss: 1.10e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0600 +[2026-03-20T20:37:36.087867Z] Loop 13552: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0652 +[2026-03-20T20:37:36.942751Z] Loop 13553: Loss: 1.25e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0653 +[2026-03-20T20:37:37.796884Z] Loop 13554: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0707 +[2026-03-20T20:37:38.650562Z] Loop 13555: Loss: 1.11e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0651 +[2026-03-20T20:37:39.505353Z] Loop 13556: Loss: 1.31e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0673 +[2026-03-20T20:37:40.359847Z] Loop 13557: Loss: 1.22e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0661 +[2026-03-20T20:37:41.214228Z] Loop 13558: Loss: 1.28e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0689 +[2026-03-20T20:37:42.068015Z] Loop 13559: Loss: 1.20e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0683 +[2026-03-20T20:37:42.963073Z] Loop 13560: Loss: 1.20e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0683 +[2026-03-20T20:37:43.816657Z] Loop 13561: Loss: 1.19e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0660 +[2026-03-20T20:37:44.670168Z] Loop 13562: Loss: 1.36e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0704 +[2026-03-20T20:37:45.524590Z] Loop 13563: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0718 +[2026-03-20T20:37:46.378546Z] Loop 13564: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0708 +[2026-03-20T20:37:47.232116Z] Loop 13565: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0767 +[2026-03-20T20:37:48.086072Z] Loop 13566: Loss: 1.40e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0732 +[2026-03-20T20:37:48.941080Z] Loop 13567: Loss: 1.58e-02, Avg Return: 0.861, Regret: 0.0005, Entropy: 0.0809 +[2026-03-20T20:37:49.795298Z] Loop 13568: Loss: 1.62e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0840 +[2026-03-20T20:37:50.649905Z] Loop 13569: Loss: 1.62e-02, Avg Return: 0.860, Regret: 0.0005, Entropy: 0.0795 +[2026-03-20T20:37:51.543655Z] Loop 13570: Loss: 1.57e-02, Avg Return: 0.859, Regret: 0.0045, Entropy: 0.0829 +[2026-03-20T20:37:52.398178Z] Loop 13571: Loss: 1.89e-02, Avg Return: 0.859, Regret: 0.0045, Entropy: 0.0924 +[2026-03-20T20:37:53.252518Z] Loop 13572: Loss: 1.97e-02, Avg Return: 0.859, Regret: 0.0045, Entropy: 0.0982 +[2026-03-20T20:37:54.107321Z] Loop 13573: Loss: 1.97e-02, Avg Return: 0.859, Regret: 0.0045, Entropy: 0.0995 +[2026-03-20T20:37:54.961286Z] Loop 13574: Loss: 1.98e-02, Avg Return: 0.859, Regret: 0.0045, Entropy: 0.0962 +[2026-03-20T20:37:55.815529Z] Loop 13575: Loss: 1.93e-02, Avg Return: 0.859, Regret: 0.0045, Entropy: 0.0983 +[2026-03-20T20:37:56.669118Z] Loop 13576: Loss: 1.98e-02, Avg Return: 0.860, Regret: 0.0045, Entropy: 0.0956 +[2026-03-20T20:37:57.523827Z] Loop 13577: Loss: 1.87e-02, Avg Return: 0.862, Regret: 0.0045, Entropy: 0.0926 +[2026-03-20T20:37:58.377097Z] Loop 13578: Loss: 1.90e-02, Avg Return: 0.861, Regret: 0.0045, Entropy: 0.0900 +[2026-03-20T20:37:59.230313Z] Loop 13579: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0045, Entropy: 0.0869 +[2026-03-20T20:38:00.122782Z] Loop 13580: Loss: 1.84e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0895 +[2026-03-20T20:38:00.976689Z] Loop 13581: Loss: 1.79e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0857 +[2026-03-20T20:38:01.830427Z] Loop 13582: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0835 +[2026-03-20T20:38:02.683819Z] Loop 13583: Loss: 1.54e-02, Avg Return: 0.864, Regret: 0.0014, Entropy: 0.0817 +[2026-03-20T20:38:03.536837Z] Loop 13584: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0803 +[2026-03-20T20:38:04.391216Z] Loop 13585: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0783 +[2026-03-20T20:38:05.245266Z] Loop 13586: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0847 +[2026-03-20T20:38:06.099678Z] Loop 13587: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0842 +[2026-03-20T20:38:06.952718Z] Loop 13588: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0808 +[2026-03-20T20:38:07.806031Z] Loop 13589: Loss: 1.67e-02, Avg Return: 0.864, Regret: 0.0014, Entropy: 0.0835 +[2026-03-20T20:38:08.700445Z] Loop 13590: Loss: 1.59e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0815 +[2026-03-20T20:38:09.554673Z] Loop 13591: Loss: 1.64e-02, Avg Return: 0.865, Regret: 0.0002, Entropy: 0.0807 +[2026-03-20T20:38:10.408856Z] Loop 13592: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0797 +[2026-03-20T20:38:11.262452Z] Loop 13593: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0812 +[2026-03-20T20:38:12.117019Z] Loop 13594: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0803 +[2026-03-20T20:38:12.971228Z] Loop 13595: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0834 +[2026-03-20T20:38:13.825084Z] Loop 13596: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0840 +[2026-03-20T20:38:14.678886Z] Loop 13597: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0800 +[2026-03-20T20:38:15.533357Z] Loop 13598: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0787 +[2026-03-20T20:38:16.388023Z] Loop 13599: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0850 +[2026-03-20T20:38:17.280319Z] Loop 13600: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0871 +[2026-03-20T20:38:18.133605Z] Loop 13601: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0859 +[2026-03-20T20:38:18.987588Z] Loop 13602: Loss: 1.87e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0925 +[2026-03-20T20:38:19.841571Z] Loop 13603: Loss: 2.08e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0997 +[2026-03-20T20:38:20.696346Z] Loop 13604: Loss: 2.35e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.1086 +[2026-03-20T20:38:21.550103Z] Loop 13605: Loss: 1.99e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0973 +[2026-03-20T20:38:22.403456Z] Loop 13606: Loss: 1.82e-02, Avg Return: 0.858, Regret: 0.0007, Entropy: 0.0912 +[2026-03-20T20:38:23.257811Z] Loop 13607: Loss: 1.97e-02, Avg Return: 0.856, Regret: 0.0007, Entropy: 0.0970 +[2026-03-20T20:38:24.112614Z] Loop 13608: Loss: 1.81e-02, Avg Return: 0.857, Regret: 0.0007, Entropy: 0.0934 +[2026-03-20T20:38:24.966661Z] Loop 13609: Loss: 1.82e-02, Avg Return: 0.860, Regret: 0.0007, Entropy: 0.0904 +[2026-03-20T20:38:25.860570Z] Loop 13610: Loss: 1.52e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.0784 +[2026-03-20T20:38:26.714728Z] Loop 13611: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0021, Entropy: 0.0689 +[2026-03-20T20:38:27.568957Z] Loop 13612: Loss: 1.27e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.0663 +[2026-03-20T20:38:28.423010Z] Loop 13613: Loss: 1.20e-02, Avg Return: 0.863, Regret: 0.0021, Entropy: 0.0639 +[2026-03-20T20:38:29.277778Z] Loop 13614: Loss: 1.12e-02, Avg Return: 0.863, Regret: 0.0021, Entropy: 0.0623 +[2026-03-20T20:38:30.132676Z] Loop 13615: Loss: 1.19e-02, Avg Return: 0.864, Regret: 0.0021, Entropy: 0.0633 +[2026-03-20T20:38:30.986635Z] Loop 13616: Loss: 1.18e-02, Avg Return: 0.864, Regret: 0.0021, Entropy: 0.0634 +[2026-03-20T20:38:31.841572Z] Loop 13617: Loss: 1.17e-02, Avg Return: 0.863, Regret: 0.0021, Entropy: 0.0599 +[2026-03-20T20:38:32.696684Z] Loop 13618: Loss: 1.15e-02, Avg Return: 0.865, Regret: 0.0021, Entropy: 0.0583 +[2026-03-20T20:38:33.549373Z] Loop 13619: Loss: 1.06e-02, Avg Return: 0.864, Regret: 0.0021, Entropy: 0.0590 +[2026-03-20T20:38:34.444530Z] Loop 13620: Loss: 1.08e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0567 +[2026-03-20T20:38:35.300063Z] Loop 13621: Loss: 1.16e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0628 +[2026-03-20T20:38:36.154528Z] Loop 13622: Loss: 1.12e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0565 +[2026-03-20T20:38:37.009689Z] Loop 13623: Loss: 1.17e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0602 +[2026-03-20T20:38:37.864076Z] Loop 13624: Loss: 1.18e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0618 +[2026-03-20T20:38:38.719250Z] Loop 13625: Loss: 1.09e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0585 +[2026-03-20T20:38:39.574115Z] Loop 13626: Loss: 1.06e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0562 +[2026-03-20T20:38:40.429104Z] Loop 13627: Loss: 1.11e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0604 +[2026-03-20T20:38:41.283120Z] Loop 13628: Loss: 1.14e-02, Avg Return: 0.865, Regret: 0.0001, Entropy: 0.0626 +[2026-03-20T20:38:42.137405Z] Loop 13629: Loss: 1.22e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0617 +[2026-03-20T20:38:43.033892Z] Loop 13630: Loss: 1.08e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0576 +[2026-03-20T20:38:43.889998Z] Loop 13631: Loss: 1.13e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0619 +[2026-03-20T20:38:44.744823Z] Loop 13632: Loss: 1.16e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0620 +[2026-03-20T20:38:45.598677Z] Loop 13633: Loss: 1.18e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0616 +[2026-03-20T20:38:46.452853Z] Loop 13634: Loss: 1.06e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0565 +[2026-03-20T20:38:47.308627Z] Loop 13635: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0619 +[2026-03-20T20:38:48.162707Z] Loop 13636: Loss: 1.20e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0625 +[2026-03-20T20:38:49.016690Z] Loop 13637: Loss: 1.24e-02, Avg Return: 0.865, Regret: 0.0003, Entropy: 0.0626 +[2026-03-20T20:38:49.870603Z] Loop 13638: Loss: 1.12e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0640 +[2026-03-20T20:38:50.725338Z] Loop 13639: Loss: 1.15e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0610 +[2026-03-20T20:38:51.619914Z] Loop 13640: Loss: 1.16e-02, Avg Return: 0.865, Regret: 0.0006, Entropy: 0.0608 +[2026-03-20T20:38:52.474420Z] Loop 13641: Loss: 1.19e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0617 +[2026-03-20T20:38:53.327516Z] Loop 13642: Loss: 1.19e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0637 +[2026-03-20T20:38:54.181903Z] Loop 13643: Loss: 1.27e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0628 +[2026-03-20T20:38:55.035890Z] Loop 13644: Loss: 1.25e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0657 +[2026-03-20T20:38:55.889671Z] Loop 13645: Loss: 1.13e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0597 +[2026-03-20T20:38:56.743362Z] Loop 13646: Loss: 1.18e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0629 +[2026-03-20T20:38:57.597598Z] Loop 13647: Loss: 1.24e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.0671 +[2026-03-20T20:38:58.452312Z] Loop 13648: Loss: 1.13e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0614 +[2026-03-20T20:38:59.307991Z] Loop 13649: Loss: 1.17e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.0628 +[2026-03-20T20:39:00.202617Z] Loop 13650: Loss: 1.24e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0642 +[2026-03-20T20:39:01.057340Z] Loop 13651: Loss: 1.28e-02, Avg Return: 0.860, Regret: 0.0025, Entropy: 0.0672 +[2026-03-20T20:39:01.912308Z] Loop 13652: Loss: 1.28e-02, Avg Return: 0.860, Regret: 0.0025, Entropy: 0.0637 +[2026-03-20T20:39:02.767843Z] Loop 13653: Loss: 1.28e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.0668 +[2026-03-20T20:39:03.622789Z] Loop 13654: Loss: 1.24e-02, Avg Return: 0.859, Regret: 0.0025, Entropy: 0.0643 +[2026-03-20T20:39:04.475984Z] Loop 13655: Loss: 1.21e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.0651 +[2026-03-20T20:39:05.329163Z] Loop 13656: Loss: 1.22e-02, Avg Return: 0.859, Regret: 0.0025, Entropy: 0.0656 +[2026-03-20T20:39:06.182409Z] Loop 13657: Loss: 1.17e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.0648 +[2026-03-20T20:39:07.036329Z] Loop 13658: Loss: 1.26e-02, Avg Return: 0.860, Regret: 0.0025, Entropy: 0.0673 +[2026-03-20T20:39:07.890992Z] Loop 13659: Loss: 1.17e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.0645 +[2026-03-20T20:39:08.787093Z] Loop 13660: Loss: 1.25e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.0652 +[2026-03-20T20:39:09.641900Z] Loop 13661: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0025, Entropy: 0.0705 +[2026-03-20T20:39:10.496996Z] Loop 13662: Loss: 1.24e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0641 +[2026-03-20T20:39:11.350213Z] Loop 13663: Loss: 1.24e-02, Avg Return: 0.860, Regret: 0.0025, Entropy: 0.0647 +[2026-03-20T20:39:12.204129Z] Loop 13664: Loss: 1.26e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.0679 +[2026-03-20T20:39:13.058479Z] Loop 13665: Loss: 1.30e-02, Avg Return: 0.860, Regret: 0.0025, Entropy: 0.0693 +[2026-03-20T20:39:13.913351Z] Loop 13666: Loss: 1.25e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.0685 +[2026-03-20T20:39:14.767878Z] Loop 13667: Loss: 1.24e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.0649 +[2026-03-20T20:39:15.622627Z] Loop 13668: Loss: 1.16e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.0628 +[2026-03-20T20:39:16.476457Z] Loop 13669: Loss: 1.25e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.0666 +[2026-03-20T20:39:17.371900Z] Loop 13670: Loss: 1.26e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.0662 +[2026-03-20T20:39:18.226874Z] Loop 13671: Loss: 1.21e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.0675 +[2026-03-20T20:39:19.081732Z] Loop 13672: Loss: 1.18e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.0629 +[2026-03-20T20:39:19.935763Z] Loop 13673: Loss: 1.24e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.0675 +[2026-03-20T20:39:20.791284Z] Loop 13674: Loss: 1.33e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.0682 +[2026-03-20T20:39:21.646644Z] Loop 13675: Loss: 1.15e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.0637 +[2026-03-20T20:39:22.500925Z] Loop 13676: Loss: 1.20e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.0653 +[2026-03-20T20:39:23.356060Z] Loop 13677: Loss: 1.26e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.0652 +[2026-03-20T20:39:24.211071Z] Loop 13678: Loss: 1.22e-02, Avg Return: 0.863, Regret: 0.0028, Entropy: 0.0629 +[2026-03-20T20:39:25.065349Z] Loop 13679: Loss: 1.24e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.0639 +[2026-03-20T20:39:25.962734Z] Loop 13680: Loss: 1.27e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.0655 +[2026-03-20T20:39:26.817699Z] Loop 13681: Loss: 1.17e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0628 +[2026-03-20T20:39:27.673844Z] Loop 13682: Loss: 1.15e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0600 +[2026-03-20T20:39:28.528889Z] Loop 13683: Loss: 1.23e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0657 +[2026-03-20T20:39:29.383906Z] Loop 13684: Loss: 1.25e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0660 +[2026-03-20T20:39:30.239329Z] Loop 13685: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0682 +[2026-03-20T20:39:31.095817Z] Loop 13686: Loss: 1.36e-02, Avg Return: 0.865, Regret: 0.0006, Entropy: 0.0701 +[2026-03-20T20:39:31.950377Z] Loop 13687: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0702 +[2026-03-20T20:39:32.804564Z] Loop 13688: Loss: 1.48e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0748 +[2026-03-20T20:39:33.659786Z] Loop 13689: Loss: 1.48e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0760 +[2026-03-20T20:39:34.556569Z] Loop 13690: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0751 +[2026-03-20T20:39:35.410948Z] Loop 13691: Loss: 1.39e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0711 +[2026-03-20T20:39:36.265310Z] Loop 13692: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0752 +[2026-03-20T20:39:37.120008Z] Loop 13693: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0747 +[2026-03-20T20:39:37.975252Z] Loop 13694: Loss: 1.47e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0749 +[2026-03-20T20:39:38.829519Z] Loop 13695: Loss: 1.45e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0744 +[2026-03-20T20:39:39.682951Z] Loop 13696: Loss: 1.47e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0768 +[2026-03-20T20:39:40.536160Z] Loop 13697: Loss: 1.46e-02, Avg Return: 0.865, Regret: 0.0001, Entropy: 0.0769 +[2026-03-20T20:39:41.391356Z] Loop 13698: Loss: 1.47e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0764 +[2026-03-20T20:39:42.245831Z] Loop 13699: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0797 +[2026-03-20T20:39:43.142720Z] Loop 13700: Loss: 1.60e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0830 +[2026-03-20T20:39:43.997275Z] Loop 13701: Loss: 1.71e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0860 +[2026-03-20T20:39:44.850738Z] Loop 13702: Loss: 1.93e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0951 +[2026-03-20T20:39:45.704728Z] Loop 13703: Loss: 1.88e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0971 +[2026-03-20T20:39:46.558978Z] Loop 13704: Loss: 1.97e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0963 +[2026-03-20T20:39:47.412958Z] Loop 13705: Loss: 1.94e-02, Avg Return: 0.865, Regret: 0.0003, Entropy: 0.0933 +[2026-03-20T20:39:48.267267Z] Loop 13706: Loss: 2.13e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.1034 +[2026-03-20T20:39:49.121354Z] Loop 13707: Loss: 2.05e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.1035 +[2026-03-20T20:39:49.976495Z] Loop 13708: Loss: 2.03e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0986 +[2026-03-20T20:39:50.831256Z] Loop 13709: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0908 +[2026-03-20T20:39:51.726733Z] Loop 13710: Loss: 1.83e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0927 +[2026-03-20T20:39:52.579998Z] Loop 13711: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0856 +[2026-03-20T20:39:53.434155Z] Loop 13712: Loss: 1.78e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0891 +[2026-03-20T20:39:54.288514Z] Loop 13713: Loss: 1.86e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0942 +[2026-03-20T20:39:55.141962Z] Loop 13714: Loss: 1.96e-02, Avg Return: 0.860, Regret: 0.0013, Entropy: 0.0938 +[2026-03-20T20:39:55.995870Z] Loop 13715: Loss: 1.88e-02, Avg Return: 0.859, Regret: 0.0013, Entropy: 0.0941 +[2026-03-20T20:39:56.850398Z] Loop 13716: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0890 +[2026-03-20T20:39:57.705033Z] Loop 13717: Loss: 1.90e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0957 +[2026-03-20T20:39:58.558290Z] Loop 13718: Loss: 1.90e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0966 +[2026-03-20T20:39:59.410802Z] Loop 13719: Loss: 1.83e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0952 +[2026-03-20T20:40:00.305250Z] Loop 13720: Loss: 1.85e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0987 +[2026-03-20T20:40:01.160937Z] Loop 13721: Loss: 1.86e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0978 +[2026-03-20T20:40:02.015471Z] Loop 13722: Loss: 1.84e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0954 +[2026-03-20T20:40:02.871163Z] Loop 13723: Loss: 1.77e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0944 +[2026-03-20T20:40:03.725303Z] Loop 13724: Loss: 1.94e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.1005 +[2026-03-20T20:40:04.580182Z] Loop 13725: Loss: 1.98e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0983 +[2026-03-20T20:40:05.433409Z] Loop 13726: Loss: 1.92e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0982 +[2026-03-20T20:40:06.287324Z] Loop 13727: Loss: 1.87e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0967 +[2026-03-20T20:40:07.140483Z] Loop 13728: Loss: 1.93e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0965 +[2026-03-20T20:40:07.994374Z] Loop 13729: Loss: 1.98e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0985 +[2026-03-20T20:40:08.888342Z] Loop 13730: Loss: 1.91e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0981 +[2026-03-20T20:40:09.742736Z] Loop 13731: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0966 +[2026-03-20T20:40:10.596559Z] Loop 13732: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0939 +[2026-03-20T20:40:11.450696Z] Loop 13733: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0911 +[2026-03-20T20:40:12.305300Z] Loop 13734: Loss: 1.69e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0882 +[2026-03-20T20:40:13.160194Z] Loop 13735: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0899 +[2026-03-20T20:40:14.014846Z] Loop 13736: Loss: 1.63e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0873 +[2026-03-20T20:40:14.869554Z] Loop 13737: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0860 +[2026-03-20T20:40:15.723877Z] Loop 13738: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0879 +[2026-03-20T20:40:16.578543Z] Loop 13739: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0842 +[2026-03-20T20:40:17.472008Z] Loop 13740: Loss: 1.69e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0884 +[2026-03-20T20:40:18.326551Z] Loop 13741: Loss: 1.77e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0884 +[2026-03-20T20:40:19.181085Z] Loop 13742: Loss: 1.65e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0867 +[2026-03-20T20:40:20.036132Z] Loop 13743: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0850 +[2026-03-20T20:40:20.891472Z] Loop 13744: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0890 +[2026-03-20T20:40:21.749377Z] Loop 13745: Loss: 1.73e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0892 +[2026-03-20T20:40:22.602820Z] Loop 13746: Loss: 1.82e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0921 +[2026-03-20T20:40:23.456448Z] Loop 13747: Loss: 1.83e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0965 +[2026-03-20T20:40:24.310758Z] Loop 13748: Loss: 1.97e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0970 +[2026-03-20T20:40:25.165588Z] Loop 13749: Loss: 2.04e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0981 +[2026-03-20T20:40:26.060026Z] Loop 13750: Loss: 2.19e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.1041 +[2026-03-20T20:40:26.913400Z] Loop 13751: Loss: 2.17e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.1033 +[2026-03-20T20:40:27.767351Z] Loop 13752: Loss: 1.97e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0966 +[2026-03-20T20:40:28.622445Z] Loop 13753: Loss: 1.90e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0961 +[2026-03-20T20:40:29.477533Z] Loop 13754: Loss: 1.87e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0950 +[2026-03-20T20:40:30.331214Z] Loop 13755: Loss: 1.99e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0939 +[2026-03-20T20:40:31.184038Z] Loop 13756: Loss: 1.98e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0998 +[2026-03-20T20:40:32.038701Z] Loop 13757: Loss: 2.05e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0998 +[2026-03-20T20:40:32.892506Z] Loop 13758: Loss: 1.92e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0986 +[2026-03-20T20:40:33.746709Z] Loop 13759: Loss: 1.97e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0997 +[2026-03-20T20:40:34.642902Z] Loop 13760: Loss: 2.02e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.1031 +[2026-03-20T20:40:35.497016Z] Loop 13761: Loss: 1.99e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0966 +[2026-03-20T20:40:36.353125Z] Loop 13762: Loss: 1.82e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0904 +[2026-03-20T20:40:37.208771Z] Loop 13763: Loss: 1.92e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0935 +[2026-03-20T20:40:38.065310Z] Loop 13764: Loss: 1.89e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0919 +[2026-03-20T20:40:38.920135Z] Loop 13765: Loss: 1.77e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0896 +[2026-03-20T20:40:39.775803Z] Loop 13766: Loss: 1.86e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0948 +[2026-03-20T20:40:40.631137Z] Loop 13767: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0962 +[2026-03-20T20:40:41.485636Z] Loop 13768: Loss: 1.86e-02, Avg Return: 0.861, Regret: 0.0004, Entropy: 0.0944 +[2026-03-20T20:40:42.338616Z] Loop 13769: Loss: 2.00e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0958 +[2026-03-20T20:40:43.231958Z] Loop 13770: Loss: 1.98e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.0980 +[2026-03-20T20:40:44.086324Z] Loop 13771: Loss: 2.01e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.0950 +[2026-03-20T20:40:44.940516Z] Loop 13772: Loss: 1.70e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.0857 +[2026-03-20T20:40:45.794655Z] Loop 13773: Loss: 1.87e-02, Avg Return: 0.860, Regret: 0.0021, Entropy: 0.0884 +[2026-03-20T20:40:46.649074Z] Loop 13774: Loss: 1.81e-02, Avg Return: 0.859, Regret: 0.0021, Entropy: 0.0892 +[2026-03-20T20:40:47.502934Z] Loop 13775: Loss: 1.69e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.0843 +[2026-03-20T20:40:48.357628Z] Loop 13776: Loss: 1.68e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.0861 +[2026-03-20T20:40:49.211867Z] Loop 13777: Loss: 1.73e-02, Avg Return: 0.863, Regret: 0.0021, Entropy: 0.0846 +[2026-03-20T20:40:50.065212Z] Loop 13778: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0021, Entropy: 0.0836 +[2026-03-20T20:40:50.918784Z] Loop 13779: Loss: 1.78e-02, Avg Return: 0.863, Regret: 0.0021, Entropy: 0.0899 +[2026-03-20T20:40:51.815127Z] Loop 13780: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0835 +[2026-03-20T20:40:52.669850Z] Loop 13781: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0835 +[2026-03-20T20:40:53.524796Z] Loop 13782: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0837 +[2026-03-20T20:40:54.379513Z] Loop 13783: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0851 +[2026-03-20T20:40:55.235022Z] Loop 13784: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0832 +[2026-03-20T20:40:56.089627Z] Loop 13785: Loss: 1.71e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0817 +[2026-03-20T20:40:56.942830Z] Loop 13786: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0824 +[2026-03-20T20:40:57.795036Z] Loop 13787: Loss: 1.79e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0878 +[2026-03-20T20:40:58.648418Z] Loop 13788: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0842 +[2026-03-20T20:40:59.504160Z] Loop 13789: Loss: 1.59e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0792 +[2026-03-20T20:41:00.399001Z] Loop 13790: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0805 +[2026-03-20T20:41:01.252503Z] Loop 13791: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0824 +[2026-03-20T20:41:02.107999Z] Loop 13792: Loss: 1.59e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0835 +[2026-03-20T20:41:02.962422Z] Loop 13793: Loss: 1.54e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0803 +[2026-03-20T20:41:03.816943Z] Loop 13794: Loss: 1.60e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0814 +[2026-03-20T20:41:04.670819Z] Loop 13795: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0852 +[2026-03-20T20:41:05.524249Z] Loop 13796: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0817 +[2026-03-20T20:41:06.378284Z] Loop 13797: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0874 +[2026-03-20T20:41:07.233096Z] Loop 13798: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0867 +[2026-03-20T20:41:08.087220Z] Loop 13799: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0860 +[2026-03-20T20:41:08.983128Z] Loop 13800: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0851 +[2026-03-20T20:41:09.836883Z] Loop 13801: Loss: 1.64e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0848 +[2026-03-20T20:41:10.690499Z] Loop 13802: Loss: 1.45e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0788 +[2026-03-20T20:41:11.545105Z] Loop 13803: Loss: 1.57e-02, Avg Return: 0.861, Regret: 0.0012, Entropy: 0.0855 +[2026-03-20T20:41:12.399455Z] Loop 13804: Loss: 1.62e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0798 +[2026-03-20T20:41:13.252354Z] Loop 13805: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0863 +[2026-03-20T20:41:14.105077Z] Loop 13806: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0788 +[2026-03-20T20:41:14.959705Z] Loop 13807: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0881 +[2026-03-20T20:41:15.813517Z] Loop 13808: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0823 +[2026-03-20T20:41:16.668644Z] Loop 13809: Loss: 1.76e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0851 +[2026-03-20T20:41:17.563011Z] Loop 13810: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0877 +[2026-03-20T20:41:18.418798Z] Loop 13811: Loss: 1.73e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0847 +[2026-03-20T20:41:19.273088Z] Loop 13812: Loss: 1.83e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0918 +[2026-03-20T20:41:20.127402Z] Loop 13813: Loss: 1.68e-02, Avg Return: 0.865, Regret: 0.0005, Entropy: 0.0850 +[2026-03-20T20:41:20.980743Z] Loop 13814: Loss: 1.63e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0834 +[2026-03-20T20:41:21.834799Z] Loop 13815: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0843 +[2026-03-20T20:41:22.688447Z] Loop 13816: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0852 +[2026-03-20T20:41:23.542671Z] Loop 13817: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0861 +[2026-03-20T20:41:24.396893Z] Loop 13818: Loss: 1.55e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0856 +[2026-03-20T20:41:25.250707Z] Loop 13819: Loss: 1.58e-02, Avg Return: 0.865, Regret: 0.0005, Entropy: 0.0856 +[2026-03-20T20:41:26.146216Z] Loop 13820: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0856 +[2026-03-20T20:41:26.999688Z] Loop 13821: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0865 +[2026-03-20T20:41:27.855807Z] Loop 13822: Loss: 1.74e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0919 +[2026-03-20T20:41:28.709912Z] Loop 13823: Loss: 1.75e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0910 +[2026-03-20T20:41:29.563579Z] Loop 13824: Loss: 1.71e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0883 +[2026-03-20T20:41:30.418137Z] Loop 13825: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0900 +[2026-03-20T20:41:31.273672Z] Loop 13826: Loss: 1.82e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0905 +[2026-03-20T20:41:32.128325Z] Loop 13827: Loss: 1.94e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0963 +[2026-03-20T20:41:32.982477Z] Loop 13828: Loss: 2.16e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.1051 +[2026-03-20T20:41:33.836089Z] Loop 13829: Loss: 2.29e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.1091 +[2026-03-20T20:41:34.730657Z] Loop 13830: Loss: 2.14e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.1050 +[2026-03-20T20:41:35.583976Z] Loop 13831: Loss: 2.16e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.1054 +[2026-03-20T20:41:36.436957Z] Loop 13832: Loss: 2.15e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.1060 +[2026-03-20T20:41:37.290834Z] Loop 13833: Loss: 2.05e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0985 +[2026-03-20T20:41:38.144668Z] Loop 13834: Loss: 1.86e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0952 +[2026-03-20T20:41:38.999967Z] Loop 13835: Loss: 1.82e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0907 +[2026-03-20T20:41:39.854138Z] Loop 13836: Loss: 1.70e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0847 +[2026-03-20T20:41:40.707445Z] Loop 13837: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0823 +[2026-03-20T20:41:41.561581Z] Loop 13838: Loss: 1.73e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0822 +[2026-03-20T20:41:42.415223Z] Loop 13839: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0823 +[2026-03-20T20:41:43.308228Z] Loop 13840: Loss: 1.67e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0853 +[2026-03-20T20:41:44.161893Z] Loop 13841: Loss: 1.68e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0792 +[2026-03-20T20:41:45.017048Z] Loop 13842: Loss: 1.68e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0846 +[2026-03-20T20:41:45.871804Z] Loop 13843: Loss: 1.60e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0857 +[2026-03-20T20:41:46.727487Z] Loop 13844: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0831 +[2026-03-20T20:41:47.582398Z] Loop 13845: Loss: 1.58e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0815 +[2026-03-20T20:41:48.436864Z] Loop 13846: Loss: 1.69e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0867 +[2026-03-20T20:41:49.291766Z] Loop 13847: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0879 +[2026-03-20T20:41:50.147400Z] Loop 13848: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0834 +[2026-03-20T20:41:51.001397Z] Loop 13849: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0839 +[2026-03-20T20:41:51.897989Z] Loop 13850: Loss: 1.64e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0834 +[2026-03-20T20:41:52.752089Z] Loop 13851: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0814 +[2026-03-20T20:41:53.606367Z] Loop 13852: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0827 +[2026-03-20T20:41:54.461292Z] Loop 13853: Loss: 1.70e-02, Avg Return: 0.861, Regret: 0.0004, Entropy: 0.0854 +[2026-03-20T20:41:55.316691Z] Loop 13854: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0858 +[2026-03-20T20:41:56.171052Z] Loop 13855: Loss: 1.69e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0877 +[2026-03-20T20:41:57.025594Z] Loop 13856: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0848 +[2026-03-20T20:41:57.881497Z] Loop 13857: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0843 +[2026-03-20T20:41:58.737048Z] Loop 13858: Loss: 1.69e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0853 +[2026-03-20T20:41:59.590622Z] Loop 13859: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0840 +[2026-03-20T20:42:00.484543Z] Loop 13860: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0841 +[2026-03-20T20:42:01.339260Z] Loop 13861: Loss: 1.62e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0853 +[2026-03-20T20:42:02.194820Z] Loop 13862: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0854 +[2026-03-20T20:42:03.050129Z] Loop 13863: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0845 +[2026-03-20T20:42:03.904712Z] Loop 13864: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0849 +[2026-03-20T20:42:04.758826Z] Loop 13865: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0853 +[2026-03-20T20:42:05.613448Z] Loop 13866: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0837 +[2026-03-20T20:42:06.468051Z] Loop 13867: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0854 +[2026-03-20T20:42:07.324398Z] Loop 13868: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0870 +[2026-03-20T20:42:08.179657Z] Loop 13869: Loss: 1.70e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0870 +[2026-03-20T20:42:09.074449Z] Loop 13870: Loss: 1.63e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0844 +[2026-03-20T20:42:09.928579Z] Loop 13871: Loss: 1.70e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0857 +[2026-03-20T20:42:10.783750Z] Loop 13872: Loss: 1.79e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0851 +[2026-03-20T20:42:11.637634Z] Loop 13873: Loss: 1.66e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0847 +[2026-03-20T20:42:12.491666Z] Loop 13874: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0838 +[2026-03-20T20:42:13.346414Z] Loop 13875: Loss: 1.66e-02, Avg Return: 0.861, Regret: 0.0005, Entropy: 0.0863 +[2026-03-20T20:42:14.201047Z] Loop 13876: Loss: 1.72e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0872 +[2026-03-20T20:42:15.056191Z] Loop 13877: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0900 +[2026-03-20T20:42:15.910777Z] Loop 13878: Loss: 1.83e-02, Avg Return: 0.861, Regret: 0.0005, Entropy: 0.0899 +[2026-03-20T20:42:16.765541Z] Loop 13879: Loss: 1.78e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0909 +[2026-03-20T20:42:17.660932Z] Loop 13880: Loss: 1.74e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0897 +[2026-03-20T20:42:18.515446Z] Loop 13881: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0880 +[2026-03-20T20:42:19.368937Z] Loop 13882: Loss: 1.78e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0904 +[2026-03-20T20:42:20.221882Z] Loop 13883: Loss: 1.84e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0903 +[2026-03-20T20:42:21.074894Z] Loop 13884: Loss: 1.73e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0908 +[2026-03-20T20:42:21.929452Z] Loop 13885: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0860 +[2026-03-20T20:42:22.784045Z] Loop 13886: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0939 +[2026-03-20T20:42:23.637194Z] Loop 13887: Loss: 1.99e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0968 +[2026-03-20T20:42:24.490548Z] Loop 13888: Loss: 2.01e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0988 +[2026-03-20T20:42:25.344633Z] Loop 13889: Loss: 2.07e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.1030 +[2026-03-20T20:42:26.237720Z] Loop 13890: Loss: 2.09e-02, Avg Return: 0.861, Regret: 0.0029, Entropy: 0.1041 +[2026-03-20T20:42:27.091787Z] Loop 13891: Loss: 2.02e-02, Avg Return: 0.861, Regret: 0.0029, Entropy: 0.1018 +[2026-03-20T20:42:27.946003Z] Loop 13892: Loss: 2.21e-02, Avg Return: 0.861, Regret: 0.0029, Entropy: 0.1101 +[2026-03-20T20:42:28.800954Z] Loop 13893: Loss: 2.25e-02, Avg Return: 0.862, Regret: 0.0029, Entropy: 0.1069 +[2026-03-20T20:42:29.655208Z] Loop 13894: Loss: 1.99e-02, Avg Return: 0.863, Regret: 0.0029, Entropy: 0.1020 +[2026-03-20T20:42:30.508398Z] Loop 13895: Loss: 2.00e-02, Avg Return: 0.860, Regret: 0.0029, Entropy: 0.1011 +[2026-03-20T20:42:31.362675Z] Loop 13896: Loss: 1.99e-02, Avg Return: 0.860, Regret: 0.0029, Entropy: 0.1006 +[2026-03-20T20:42:32.217558Z] Loop 13897: Loss: 2.00e-02, Avg Return: 0.861, Regret: 0.0029, Entropy: 0.1020 +[2026-03-20T20:42:33.072233Z] Loop 13898: Loss: 1.93e-02, Avg Return: 0.862, Regret: 0.0029, Entropy: 0.0973 +[2026-03-20T20:42:33.926330Z] Loop 13899: Loss: 1.97e-02, Avg Return: 0.862, Regret: 0.0029, Entropy: 0.0979 +[2026-03-20T20:42:34.822517Z] Loop 13900: Loss: 2.00e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.1002 +[2026-03-20T20:42:35.676427Z] Loop 13901: Loss: 1.99e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.1018 +[2026-03-20T20:42:36.530847Z] Loop 13902: Loss: 1.99e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0999 +[2026-03-20T20:42:37.385255Z] Loop 13903: Loss: 2.00e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0984 +[2026-03-20T20:42:38.240162Z] Loop 13904: Loss: 1.78e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0944 +[2026-03-20T20:42:39.097060Z] Loop 13905: Loss: 1.73e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0886 +[2026-03-20T20:42:39.950573Z] Loop 13906: Loss: 1.64e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0824 +[2026-03-20T20:42:40.804729Z] Loop 13907: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0807 +[2026-03-20T20:42:41.658813Z] Loop 13908: Loss: 1.68e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0877 +[2026-03-20T20:42:42.512210Z] Loop 13909: Loss: 1.76e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0865 +[2026-03-20T20:42:43.406841Z] Loop 13910: Loss: 1.64e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0837 +[2026-03-20T20:42:44.261715Z] Loop 13911: Loss: 1.71e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0868 +[2026-03-20T20:42:45.117156Z] Loop 13912: Loss: 1.79e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0901 +[2026-03-20T20:42:45.972469Z] Loop 13913: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0859 +[2026-03-20T20:42:46.827060Z] Loop 13914: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0857 +[2026-03-20T20:42:47.680804Z] Loop 13915: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0869 +[2026-03-20T20:42:48.536073Z] Loop 13916: Loss: 1.73e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0884 +[2026-03-20T20:42:49.390905Z] Loop 13917: Loss: 1.62e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0853 +[2026-03-20T20:42:50.245124Z] Loop 13918: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0830 +[2026-03-20T20:42:51.099698Z] Loop 13919: Loss: 1.67e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0889 +[2026-03-20T20:42:51.993812Z] Loop 13920: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0831 +[2026-03-20T20:42:52.847181Z] Loop 13921: Loss: 1.62e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0818 +[2026-03-20T20:42:53.701778Z] Loop 13922: Loss: 1.74e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0903 +[2026-03-20T20:42:54.556872Z] Loop 13923: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0818 +[2026-03-20T20:42:55.410829Z] Loop 13924: Loss: 1.67e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0860 +[2026-03-20T20:42:56.264661Z] Loop 13925: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0886 +[2026-03-20T20:42:57.119352Z] Loop 13926: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0801 +[2026-03-20T20:42:57.973060Z] Loop 13927: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0859 +[2026-03-20T20:42:58.827523Z] Loop 13928: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0861 +[2026-03-20T20:42:59.681681Z] Loop 13929: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0851 +[2026-03-20T20:43:00.576020Z] Loop 13930: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0917 +[2026-03-20T20:43:01.429922Z] Loop 13931: Loss: 1.73e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0878 +[2026-03-20T20:43:02.283390Z] Loop 13932: Loss: 1.75e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0907 +[2026-03-20T20:43:03.136393Z] Loop 13933: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0916 +[2026-03-20T20:43:03.989451Z] Loop 13934: Loss: 1.92e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0967 +[2026-03-20T20:43:04.843203Z] Loop 13935: Loss: 1.99e-02, Avg Return: 0.860, Regret: 0.0013, Entropy: 0.1018 +[2026-03-20T20:43:05.697352Z] Loop 13936: Loss: 1.90e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0995 +[2026-03-20T20:43:06.550368Z] Loop 13937: Loss: 2.05e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.1062 +[2026-03-20T20:43:07.403903Z] Loop 13938: Loss: 1.98e-02, Avg Return: 0.860, Regret: 0.0013, Entropy: 0.0996 +[2026-03-20T20:43:08.258252Z] Loop 13939: Loss: 1.80e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0956 +[2026-03-20T20:43:09.154857Z] Loop 13940: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0971 +[2026-03-20T20:43:10.008744Z] Loop 13941: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0929 +[2026-03-20T20:43:10.862397Z] Loop 13942: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0932 +[2026-03-20T20:43:11.716524Z] Loop 13943: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0958 +[2026-03-20T20:43:12.570365Z] Loop 13944: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0989 +[2026-03-20T20:43:13.424290Z] Loop 13945: Loss: 1.87e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0957 +[2026-03-20T20:43:14.277716Z] Loop 13946: Loss: 1.84e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0987 +[2026-03-20T20:43:15.131772Z] Loop 13947: Loss: 1.80e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0956 +[2026-03-20T20:43:15.985811Z] Loop 13948: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0968 +[2026-03-20T20:43:16.839967Z] Loop 13949: Loss: 1.72e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0929 +[2026-03-20T20:43:17.734140Z] Loop 13950: Loss: 1.81e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0969 +[2026-03-20T20:43:18.589138Z] Loop 13951: Loss: 1.73e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0921 +[2026-03-20T20:43:19.443738Z] Loop 13952: Loss: 1.63e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0890 +[2026-03-20T20:43:20.297910Z] Loop 13953: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0879 +[2026-03-20T20:43:21.152077Z] Loop 13954: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0836 +[2026-03-20T20:43:22.006549Z] Loop 13955: Loss: 1.62e-02, Avg Return: 0.864, Regret: 0.0018, Entropy: 0.0860 +[2026-03-20T20:43:22.860895Z] Loop 13956: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0838 +[2026-03-20T20:43:23.714799Z] Loop 13957: Loss: 1.63e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0868 +[2026-03-20T20:43:24.568754Z] Loop 13958: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0843 +[2026-03-20T20:43:25.422862Z] Loop 13959: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0856 +[2026-03-20T20:43:26.316351Z] Loop 13960: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0797 +[2026-03-20T20:43:27.170298Z] Loop 13961: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0805 +[2026-03-20T20:43:28.024803Z] Loop 13962: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0813 +[2026-03-20T20:43:28.879659Z] Loop 13963: Loss: 1.52e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0797 +[2026-03-20T20:43:29.733295Z] Loop 13964: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0808 +[2026-03-20T20:43:30.587259Z] Loop 13965: Loss: 1.40e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0766 +[2026-03-20T20:43:31.441873Z] Loop 13966: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0797 +[2026-03-20T20:43:32.297318Z] Loop 13967: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0811 +[2026-03-20T20:43:33.151617Z] Loop 13968: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0767 +[2026-03-20T20:43:34.005445Z] Loop 13969: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0799 +[2026-03-20T20:43:34.900647Z] Loop 13970: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0798 +[2026-03-20T20:43:35.754772Z] Loop 13971: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0838 +[2026-03-20T20:43:36.608752Z] Loop 13972: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0804 +[2026-03-20T20:43:37.462562Z] Loop 13973: Loss: 1.52e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0790 +[2026-03-20T20:43:38.316252Z] Loop 13974: Loss: 1.57e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.0832 +[2026-03-20T20:43:39.171155Z] Loop 13975: Loss: 1.52e-02, Avg Return: 0.865, Regret: 0.0006, Entropy: 0.0791 +[2026-03-20T20:43:40.025081Z] Loop 13976: Loss: 1.54e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0785 +[2026-03-20T20:43:40.879331Z] Loop 13977: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0851 +[2026-03-20T20:43:41.733576Z] Loop 13978: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0816 +[2026-03-20T20:43:42.588088Z] Loop 13979: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0813 +[2026-03-20T20:43:43.482448Z] Loop 13980: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0817 +[2026-03-20T20:43:44.336467Z] Loop 13981: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0829 +[2026-03-20T20:43:45.189548Z] Loop 13982: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0819 +[2026-03-20T20:43:46.043451Z] Loop 13983: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0829 +[2026-03-20T20:43:46.897429Z] Loop 13984: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0839 +[2026-03-20T20:43:47.750815Z] Loop 13985: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0799 +[2026-03-20T20:43:48.604927Z] Loop 13986: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0808 +[2026-03-20T20:43:49.459309Z] Loop 13987: Loss: 1.70e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0854 +[2026-03-20T20:43:50.313921Z] Loop 13988: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0865 +[2026-03-20T20:43:51.167999Z] Loop 13989: Loss: 1.62e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0832 +[2026-03-20T20:43:52.060640Z] Loop 13990: Loss: 1.68e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0874 +[2026-03-20T20:43:52.915556Z] Loop 13991: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0880 +[2026-03-20T20:43:53.769169Z] Loop 13992: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0875 +[2026-03-20T20:43:54.623379Z] Loop 13993: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0872 +[2026-03-20T20:43:55.477092Z] Loop 13994: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0941 +[2026-03-20T20:43:56.332344Z] Loop 13995: Loss: 1.73e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0907 +[2026-03-20T20:43:57.186123Z] Loop 13996: Loss: 1.84e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0953 +[2026-03-20T20:43:58.040298Z] Loop 13997: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0939 +[2026-03-20T20:43:58.893800Z] Loop 13998: Loss: 1.89e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0973 +[2026-03-20T20:43:59.748799Z] Loop 13999: Loss: 1.96e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.1029 +[2026-03-20T20:44:00.642797Z] Loop 14000: Loss: 1.88e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0989 +[2026-03-20T20:44:01.496267Z] Loop 14001: Loss: 1.91e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0975 +[2026-03-20T20:44:02.350013Z] Loop 14002: Loss: 1.89e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.1021 +[2026-03-20T20:44:03.205078Z] Loop 14003: Loss: 1.89e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.1025 +[2026-03-20T20:44:04.058658Z] Loop 14004: Loss: 2.10e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.1063 +[2026-03-20T20:44:04.912726Z] Loop 14005: Loss: 2.09e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.1129 +[2026-03-20T20:44:05.766816Z] Loop 14006: Loss: 1.96e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.1117 +[2026-03-20T20:44:06.620767Z] Loop 14007: Loss: 1.91e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.1032 +[2026-03-20T20:44:07.474586Z] Loop 14008: Loss: 1.92e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.1028 +[2026-03-20T20:44:08.327617Z] Loop 14009: Loss: 1.82e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.1013 +[2026-03-20T20:44:09.221911Z] Loop 14010: Loss: 1.97e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.1019 +[2026-03-20T20:44:10.076114Z] Loop 14011: Loss: 1.92e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0987 +[2026-03-20T20:44:10.930270Z] Loop 14012: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0947 +[2026-03-20T20:44:11.784204Z] Loop 14013: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0924 +[2026-03-20T20:44:12.637933Z] Loop 14014: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0887 +[2026-03-20T20:44:13.491949Z] Loop 14015: Loss: 1.79e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0919 +[2026-03-20T20:44:14.346303Z] Loop 14016: Loss: 1.64e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0858 +[2026-03-20T20:44:15.200439Z] Loop 14017: Loss: 1.55e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0797 +[2026-03-20T20:44:16.054976Z] Loop 14018: Loss: 1.47e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0784 +[2026-03-20T20:44:16.908398Z] Loop 14019: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0771 +[2026-03-20T20:44:17.802398Z] Loop 14020: Loss: 1.63e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0832 +[2026-03-20T20:44:18.655778Z] Loop 14021: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0805 +[2026-03-20T20:44:19.510660Z] Loop 14022: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0818 +[2026-03-20T20:44:20.364383Z] Loop 14023: Loss: 1.51e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0769 +[2026-03-20T20:44:21.220266Z] Loop 14024: Loss: 1.54e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0788 +[2026-03-20T20:44:22.075725Z] Loop 14025: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0791 +[2026-03-20T20:44:22.930590Z] Loop 14026: Loss: 1.52e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0815 +[2026-03-20T20:44:23.784900Z] Loop 14027: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0765 +[2026-03-20T20:44:24.639442Z] Loop 14028: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0797 +[2026-03-20T20:44:25.494478Z] Loop 14029: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0818 +[2026-03-20T20:44:26.392101Z] Loop 14030: Loss: 1.60e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0832 +[2026-03-20T20:44:27.246456Z] Loop 14031: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0801 +[2026-03-20T20:44:28.100386Z] Loop 14032: Loss: 1.61e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0802 +[2026-03-20T20:44:28.954309Z] Loop 14033: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0829 +[2026-03-20T20:44:29.808712Z] Loop 14034: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0840 +[2026-03-20T20:44:30.662635Z] Loop 14035: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0843 +[2026-03-20T20:44:31.515638Z] Loop 14036: Loss: 1.88e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0914 +[2026-03-20T20:44:32.371112Z] Loop 14037: Loss: 1.90e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0943 +[2026-03-20T20:44:33.226406Z] Loop 14038: Loss: 1.96e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0969 +[2026-03-20T20:44:34.081773Z] Loop 14039: Loss: 1.97e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0958 +[2026-03-20T20:44:34.976082Z] Loop 14040: Loss: 2.08e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.1019 +[2026-03-20T20:44:35.828881Z] Loop 14041: Loss: 2.14e-02, Avg Return: 0.859, Regret: 0.0025, Entropy: 0.1063 +[2026-03-20T20:44:36.682822Z] Loop 14042: Loss: 2.24e-02, Avg Return: 0.858, Regret: 0.0025, Entropy: 0.1090 +[2026-03-20T20:44:37.537830Z] Loop 14043: Loss: 2.11e-02, Avg Return: 0.857, Regret: 0.0025, Entropy: 0.1087 +[2026-03-20T20:44:38.393483Z] Loop 14044: Loss: 2.18e-02, Avg Return: 0.856, Regret: 0.0025, Entropy: 0.1097 +[2026-03-20T20:44:39.248771Z] Loop 14045: Loss: 2.19e-02, Avg Return: 0.859, Regret: 0.0025, Entropy: 0.1057 +[2026-03-20T20:44:40.103542Z] Loop 14046: Loss: 1.96e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0957 +[2026-03-20T20:44:40.959519Z] Loop 14047: Loss: 1.88e-02, Avg Return: 0.863, Regret: 0.0025, Entropy: 0.0919 +[2026-03-20T20:44:41.814377Z] Loop 14048: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0847 +[2026-03-20T20:44:42.668859Z] Loop 14049: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0804 +[2026-03-20T20:44:43.563873Z] Loop 14050: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0862 +[2026-03-20T20:44:44.417833Z] Loop 14051: Loss: 1.67e-02, Avg Return: 0.866, Regret: 0.0007, Entropy: 0.0818 +[2026-03-20T20:44:45.271872Z] Loop 14052: Loss: 1.69e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0858 +[2026-03-20T20:44:46.127329Z] Loop 14053: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0865 +[2026-03-20T20:44:46.981617Z] Loop 14054: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0839 +[2026-03-20T20:44:47.836240Z] Loop 14055: Loss: 1.71e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0877 +[2026-03-20T20:44:48.689947Z] Loop 14056: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0865 +[2026-03-20T20:44:49.544624Z] Loop 14057: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0869 +[2026-03-20T20:44:50.399242Z] Loop 14058: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0862 +[2026-03-20T20:44:51.252871Z] Loop 14059: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0894 +[2026-03-20T20:44:52.146667Z] Loop 14060: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0902 +[2026-03-20T20:44:53.001743Z] Loop 14061: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0911 +[2026-03-20T20:44:53.856072Z] Loop 14062: Loss: 1.59e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0841 +[2026-03-20T20:44:54.709691Z] Loop 14063: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0875 +[2026-03-20T20:44:55.563520Z] Loop 14064: Loss: 1.74e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0845 +[2026-03-20T20:44:56.418076Z] Loop 14065: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0849 +[2026-03-20T20:44:57.271845Z] Loop 14066: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0871 +[2026-03-20T20:44:58.126149Z] Loop 14067: Loss: 1.82e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0912 +[2026-03-20T20:44:58.979682Z] Loop 14068: Loss: 1.74e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0907 +[2026-03-20T20:44:59.833657Z] Loop 14069: Loss: 1.81e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0917 +[2026-03-20T20:45:00.728241Z] Loop 14070: Loss: 1.76e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0919 +[2026-03-20T20:45:01.582887Z] Loop 14071: Loss: 1.77e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0867 +[2026-03-20T20:45:02.437983Z] Loop 14072: Loss: 1.93e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0939 +[2026-03-20T20:45:03.291878Z] Loop 14073: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0948 +[2026-03-20T20:45:04.146224Z] Loop 14074: Loss: 1.93e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0977 +[2026-03-20T20:45:05.001480Z] Loop 14075: Loss: 1.98e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0972 +[2026-03-20T20:45:05.855481Z] Loop 14076: Loss: 2.17e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.1048 +[2026-03-20T20:45:06.709140Z] Loop 14077: Loss: 1.94e-02, Avg Return: 0.860, Regret: 0.0007, Entropy: 0.0973 +[2026-03-20T20:45:07.562405Z] Loop 14078: Loss: 2.10e-02, Avg Return: 0.860, Regret: 0.0007, Entropy: 0.1046 +[2026-03-20T20:45:08.415775Z] Loop 14079: Loss: 2.06e-02, Avg Return: 0.860, Regret: 0.0007, Entropy: 0.1030 +[2026-03-20T20:45:09.310677Z] Loop 14080: Loss: 2.12e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.1020 +[2026-03-20T20:45:10.165214Z] Loop 14081: Loss: 1.85e-02, Avg Return: 0.860, Regret: 0.0028, Entropy: 0.0971 +[2026-03-20T20:45:11.018115Z] Loop 14082: Loss: 2.01e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.0991 +[2026-03-20T20:45:11.871380Z] Loop 14083: Loss: 2.17e-02, Avg Return: 0.860, Regret: 0.0028, Entropy: 0.1062 +[2026-03-20T20:45:12.725902Z] Loop 14084: Loss: 2.22e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.1082 +[2026-03-20T20:45:13.579446Z] Loop 14085: Loss: 2.30e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.1100 +[2026-03-20T20:45:14.432809Z] Loop 14086: Loss: 2.50e-02, Avg Return: 0.860, Regret: 0.0028, Entropy: 0.1170 +[2026-03-20T20:45:15.286097Z] Loop 14087: Loss: 2.41e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.1180 +[2026-03-20T20:45:16.140392Z] Loop 14088: Loss: 2.40e-02, Avg Return: 0.860, Regret: 0.0028, Entropy: 0.1200 +[2026-03-20T20:45:16.995362Z] Loop 14089: Loss: 2.30e-02, Avg Return: 0.859, Regret: 0.0028, Entropy: 0.1169 +[2026-03-20T20:45:17.890770Z] Loop 14090: Loss: 2.25e-02, Avg Return: 0.859, Regret: 0.0043, Entropy: 0.1146 +[2026-03-20T20:45:18.743410Z] Loop 14091: Loss: 2.17e-02, Avg Return: 0.860, Regret: 0.0043, Entropy: 0.1163 +[2026-03-20T20:45:19.596888Z] Loop 14092: Loss: 2.24e-02, Avg Return: 0.858, Regret: 0.0043, Entropy: 0.1165 +[2026-03-20T20:45:20.451769Z] Loop 14093: Loss: 2.34e-02, Avg Return: 0.857, Regret: 0.0043, Entropy: 0.1246 +[2026-03-20T20:45:21.306417Z] Loop 14094: Loss: 2.46e-02, Avg Return: 0.857, Regret: 0.0043, Entropy: 0.1249 +[2026-03-20T20:45:22.159530Z] Loop 14095: Loss: 2.50e-02, Avg Return: 0.858, Regret: 0.0043, Entropy: 0.1290 +[2026-03-20T20:45:23.014117Z] Loop 14096: Loss: 2.40e-02, Avg Return: 0.860, Regret: 0.0043, Entropy: 0.1197 +[2026-03-20T20:45:23.869150Z] Loop 14097: Loss: 2.28e-02, Avg Return: 0.862, Regret: 0.0043, Entropy: 0.1157 +[2026-03-20T20:45:24.724376Z] Loop 14098: Loss: 2.11e-02, Avg Return: 0.861, Regret: 0.0043, Entropy: 0.1117 +[2026-03-20T20:45:25.578869Z] Loop 14099: Loss: 2.08e-02, Avg Return: 0.863, Regret: 0.0043, Entropy: 0.1075 +[2026-03-20T20:45:26.473454Z] Loop 14100: Loss: 2.16e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.1088 +[2026-03-20T20:45:27.326670Z] Loop 14101: Loss: 2.23e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.1092 +[2026-03-20T20:45:28.181527Z] Loop 14102: Loss: 2.25e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.1124 +[2026-03-20T20:45:29.036662Z] Loop 14103: Loss: 2.42e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.1169 +[2026-03-20T20:45:29.890143Z] Loop 14104: Loss: 2.48e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.1173 +[2026-03-20T20:45:30.743553Z] Loop 14105: Loss: 2.32e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.1099 +[2026-03-20T20:45:31.597562Z] Loop 14106: Loss: 2.22e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.1057 +[2026-03-20T20:45:32.452230Z] Loop 14107: Loss: 2.03e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0973 +[2026-03-20T20:45:33.306452Z] Loop 14108: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0957 +[2026-03-20T20:45:34.159676Z] Loop 14109: Loss: 1.67e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0826 +[2026-03-20T20:45:35.053642Z] Loop 14110: Loss: 1.62e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0780 +[2026-03-20T20:45:35.907958Z] Loop 14111: Loss: 1.46e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0726 +[2026-03-20T20:45:36.762190Z] Loop 14112: Loss: 1.41e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0667 +[2026-03-20T20:45:37.617376Z] Loop 14113: Loss: 1.31e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0667 +[2026-03-20T20:45:38.471628Z] Loop 14114: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0665 +[2026-03-20T20:45:39.326074Z] Loop 14115: Loss: 1.24e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0626 +[2026-03-20T20:45:40.179980Z] Loop 14116: Loss: 1.35e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0659 +[2026-03-20T20:45:41.034753Z] Loop 14117: Loss: 1.40e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0664 +[2026-03-20T20:45:41.888438Z] Loop 14118: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0749 +[2026-03-20T20:45:42.742171Z] Loop 14119: Loss: 1.51e-02, Avg Return: 0.861, Regret: 0.0001, Entropy: 0.0760 +[2026-03-20T20:45:43.635861Z] Loop 14120: Loss: 1.64e-02, Avg Return: 0.860, Regret: 0.0029, Entropy: 0.0789 +[2026-03-20T20:45:44.489670Z] Loop 14121: Loss: 1.57e-02, Avg Return: 0.861, Regret: 0.0029, Entropy: 0.0798 +[2026-03-20T20:45:45.343152Z] Loop 14122: Loss: 1.62e-02, Avg Return: 0.861, Regret: 0.0029, Entropy: 0.0770 +[2026-03-20T20:45:46.197196Z] Loop 14123: Loss: 1.50e-02, Avg Return: 0.862, Regret: 0.0029, Entropy: 0.0713 +[2026-03-20T20:45:47.051121Z] Loop 14124: Loss: 1.48e-02, Avg Return: 0.861, Regret: 0.0029, Entropy: 0.0713 +[2026-03-20T20:45:47.906062Z] Loop 14125: Loss: 1.39e-02, Avg Return: 0.861, Regret: 0.0029, Entropy: 0.0673 +[2026-03-20T20:45:48.760328Z] Loop 14126: Loss: 1.39e-02, Avg Return: 0.862, Regret: 0.0029, Entropy: 0.0695 +[2026-03-20T20:45:49.613560Z] Loop 14127: Loss: 1.24e-02, Avg Return: 0.862, Regret: 0.0029, Entropy: 0.0639 +[2026-03-20T20:45:50.466973Z] Loop 14128: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0029, Entropy: 0.0656 +[2026-03-20T20:45:51.321159Z] Loop 14129: Loss: 1.37e-02, Avg Return: 0.861, Regret: 0.0029, Entropy: 0.0654 +[2026-03-20T20:45:52.216788Z] Loop 14130: Loss: 1.36e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0682 +[2026-03-20T20:45:53.070692Z] Loop 14131: Loss: 1.25e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0656 +[2026-03-20T20:45:53.923723Z] Loop 14132: Loss: 1.23e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0626 +[2026-03-20T20:45:54.777169Z] Loop 14133: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0685 +[2026-03-20T20:45:55.631148Z] Loop 14134: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0680 +[2026-03-20T20:45:56.485341Z] Loop 14135: Loss: 1.28e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0693 +[2026-03-20T20:45:57.338123Z] Loop 14136: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0659 +[2026-03-20T20:45:58.191140Z] Loop 14137: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0689 +[2026-03-20T20:45:59.044488Z] Loop 14138: Loss: 1.35e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0692 +[2026-03-20T20:45:59.898743Z] Loop 14139: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0707 +[2026-03-20T20:46:00.793916Z] Loop 14140: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0770 +[2026-03-20T20:46:01.647304Z] Loop 14141: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0708 +[2026-03-20T20:46:02.501780Z] Loop 14142: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0721 +[2026-03-20T20:46:03.356977Z] Loop 14143: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0740 +[2026-03-20T20:46:04.211148Z] Loop 14144: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0733 +[2026-03-20T20:46:05.063533Z] Loop 14145: Loss: 1.40e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0694 +[2026-03-20T20:46:05.916132Z] Loop 14146: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0012, Entropy: 0.0709 +[2026-03-20T20:46:06.770761Z] Loop 14147: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0755 +[2026-03-20T20:46:07.624871Z] Loop 14148: Loss: 1.44e-02, Avg Return: 0.864, Regret: 0.0012, Entropy: 0.0688 +[2026-03-20T20:46:08.478170Z] Loop 14149: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0012, Entropy: 0.0681 +[2026-03-20T20:46:09.371772Z] Loop 14150: Loss: 1.47e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0689 +[2026-03-20T20:46:10.225804Z] Loop 14151: Loss: 1.56e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0750 +[2026-03-20T20:46:11.080229Z] Loop 14152: Loss: 1.46e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0697 +[2026-03-20T20:46:11.933850Z] Loop 14153: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0714 +[2026-03-20T20:46:12.787978Z] Loop 14154: Loss: 1.45e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0689 +[2026-03-20T20:46:13.641682Z] Loop 14155: Loss: 1.49e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0732 +[2026-03-20T20:46:14.495518Z] Loop 14156: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0694 +[2026-03-20T20:46:15.350163Z] Loop 14157: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0723 +[2026-03-20T20:46:16.204990Z] Loop 14158: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0777 +[2026-03-20T20:46:17.058888Z] Loop 14159: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0811 +[2026-03-20T20:46:17.953571Z] Loop 14160: Loss: 1.69e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0814 +[2026-03-20T20:46:18.807680Z] Loop 14161: Loss: 1.79e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0832 +[2026-03-20T20:46:19.663211Z] Loop 14162: Loss: 1.83e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0851 +[2026-03-20T20:46:20.517163Z] Loop 14163: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0805 +[2026-03-20T20:46:21.371355Z] Loop 14164: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0804 +[2026-03-20T20:46:22.226264Z] Loop 14165: Loss: 1.55e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0751 +[2026-03-20T20:46:23.082107Z] Loop 14166: Loss: 1.33e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0705 +[2026-03-20T20:46:23.937007Z] Loop 14167: Loss: 1.47e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0686 +[2026-03-20T20:46:24.790820Z] Loop 14168: Loss: 1.39e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0702 +[2026-03-20T20:46:25.645661Z] Loop 14169: Loss: 1.42e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0719 +[2026-03-20T20:46:26.541023Z] Loop 14170: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0692 +[2026-03-20T20:46:27.394882Z] Loop 14171: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0710 +[2026-03-20T20:46:28.249513Z] Loop 14172: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0703 +[2026-03-20T20:46:29.104229Z] Loop 14173: Loss: 1.50e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0704 +[2026-03-20T20:46:29.958424Z] Loop 14174: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0729 +[2026-03-20T20:46:30.812739Z] Loop 14175: Loss: 1.49e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0701 +[2026-03-20T20:46:31.667278Z] Loop 14176: Loss: 1.42e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0706 +[2026-03-20T20:46:32.521954Z] Loop 14177: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0754 +[2026-03-20T20:46:33.375391Z] Loop 14178: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0734 +[2026-03-20T20:46:34.229528Z] Loop 14179: Loss: 1.37e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0675 +[2026-03-20T20:46:35.122857Z] Loop 14180: Loss: 1.36e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0655 +[2026-03-20T20:46:35.978396Z] Loop 14181: Loss: 1.34e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0657 +[2026-03-20T20:46:36.833521Z] Loop 14182: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0648 +[2026-03-20T20:46:37.688068Z] Loop 14183: Loss: 1.32e-02, Avg Return: 0.865, Regret: 0.0001, Entropy: 0.0660 +[2026-03-20T20:46:38.542491Z] Loop 14184: Loss: 1.28e-02, Avg Return: 0.865, Regret: 0.0001, Entropy: 0.0630 +[2026-03-20T20:46:39.398037Z] Loop 14185: Loss: 1.35e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0661 +[2026-03-20T20:46:40.251816Z] Loop 14186: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0644 +[2026-03-20T20:46:41.105735Z] Loop 14187: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0681 +[2026-03-20T20:46:41.960593Z] Loop 14188: Loss: 1.32e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0689 +[2026-03-20T20:46:42.816206Z] Loop 14189: Loss: 1.43e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0710 +[2026-03-20T20:46:43.710113Z] Loop 14190: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0729 +[2026-03-20T20:46:44.564154Z] Loop 14191: Loss: 1.30e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0657 +[2026-03-20T20:46:45.419183Z] Loop 14192: Loss: 1.23e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0665 +[2026-03-20T20:46:46.274650Z] Loop 14193: Loss: 1.31e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0664 +[2026-03-20T20:46:47.129453Z] Loop 14194: Loss: 1.30e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0700 +[2026-03-20T20:46:47.983399Z] Loop 14195: Loss: 1.39e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0741 +[2026-03-20T20:46:48.837020Z] Loop 14196: Loss: 1.53e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0757 +[2026-03-20T20:46:49.692284Z] Loop 14197: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0814 +[2026-03-20T20:46:50.546304Z] Loop 14198: Loss: 1.84e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0899 +[2026-03-20T20:46:51.400196Z] Loop 14199: Loss: 1.92e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0896 +[2026-03-20T20:46:52.295044Z] Loop 14200: Loss: 1.90e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0912 +[2026-03-20T20:46:53.150185Z] Loop 14201: Loss: 1.93e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0915 +[2026-03-20T20:46:54.005709Z] Loop 14202: Loss: 1.93e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0918 +[2026-03-20T20:46:54.860786Z] Loop 14203: Loss: 1.84e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0909 +[2026-03-20T20:46:55.714850Z] Loop 14204: Loss: 1.79e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0880 +[2026-03-20T20:46:56.570302Z] Loop 14205: Loss: 1.94e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0935 +[2026-03-20T20:46:57.424766Z] Loop 14206: Loss: 1.92e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0943 +[2026-03-20T20:46:58.280188Z] Loop 14207: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0907 +[2026-03-20T20:46:59.135439Z] Loop 14208: Loss: 1.98e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0963 +[2026-03-20T20:46:59.990322Z] Loop 14209: Loss: 1.99e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0969 +[2026-03-20T20:47:00.886475Z] Loop 14210: Loss: 2.06e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0962 +[2026-03-20T20:47:01.742211Z] Loop 14211: Loss: 2.07e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.1010 +[2026-03-20T20:47:02.597887Z] Loop 14212: Loss: 2.14e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0989 +[2026-03-20T20:47:03.451052Z] Loop 14213: Loss: 2.18e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.1041 +[2026-03-20T20:47:04.304483Z] Loop 14214: Loss: 2.22e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.1081 +[2026-03-20T20:47:05.157810Z] Loop 14215: Loss: 2.23e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.1068 +[2026-03-20T20:47:06.012538Z] Loop 14216: Loss: 2.25e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.1066 +[2026-03-20T20:47:06.865805Z] Loop 14217: Loss: 2.18e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.1062 +[2026-03-20T20:47:07.719379Z] Loop 14218: Loss: 2.26e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.1068 +[2026-03-20T20:47:08.572567Z] Loop 14219: Loss: 2.25e-02, Avg Return: 0.865, Regret: 0.0006, Entropy: 0.1050 +[2026-03-20T20:47:09.466343Z] Loop 14220: Loss: 2.29e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.1066 +[2026-03-20T20:47:10.320379Z] Loop 14221: Loss: 2.21e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.1076 +[2026-03-20T20:47:11.173826Z] Loop 14222: Loss: 2.12e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.1014 +[2026-03-20T20:47:12.028092Z] Loop 14223: Loss: 1.99e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0957 +[2026-03-20T20:47:12.882829Z] Loop 14224: Loss: 1.81e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0879 +[2026-03-20T20:47:13.736024Z] Loop 14225: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0826 +[2026-03-20T20:47:14.591689Z] Loop 14226: Loss: 1.68e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0831 +[2026-03-20T20:47:15.444756Z] Loop 14227: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0802 +[2026-03-20T20:47:16.298123Z] Loop 14228: Loss: 1.75e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0832 +[2026-03-20T20:47:17.152331Z] Loop 14229: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0788 +[2026-03-20T20:47:18.046831Z] Loop 14230: Loss: 1.66e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0779 +[2026-03-20T20:47:18.901344Z] Loop 14231: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0771 +[2026-03-20T20:47:19.755505Z] Loop 14232: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0721 +[2026-03-20T20:47:20.610876Z] Loop 14233: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0771 +[2026-03-20T20:47:21.464383Z] Loop 14234: Loss: 1.49e-02, Avg Return: 0.865, Regret: 0.0003, Entropy: 0.0747 +[2026-03-20T20:47:22.317831Z] Loop 14235: Loss: 1.44e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0744 +[2026-03-20T20:47:23.171880Z] Loop 14236: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0734 +[2026-03-20T20:47:24.025815Z] Loop 14237: Loss: 1.47e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0737 +[2026-03-20T20:47:24.880332Z] Loop 14238: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0761 +[2026-03-20T20:47:25.733685Z] Loop 14239: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0746 +[2026-03-20T20:47:26.628605Z] Loop 14240: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0773 +[2026-03-20T20:47:27.482979Z] Loop 14241: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0756 +[2026-03-20T20:47:28.338633Z] Loop 14242: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0706 +[2026-03-20T20:47:29.192548Z] Loop 14243: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0719 +[2026-03-20T20:47:30.047571Z] Loop 14244: Loss: 1.50e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0740 +[2026-03-20T20:47:30.900777Z] Loop 14245: Loss: 1.42e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0723 +[2026-03-20T20:47:31.753849Z] Loop 14246: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0734 +[2026-03-20T20:47:32.608396Z] Loop 14247: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0782 +[2026-03-20T20:47:33.462130Z] Loop 14248: Loss: 1.57e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0762 +[2026-03-20T20:47:34.315566Z] Loop 14249: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0749 +[2026-03-20T20:47:35.209168Z] Loop 14250: Loss: 1.63e-02, Avg Return: 0.860, Regret: 0.0009, Entropy: 0.0799 +[2026-03-20T20:47:36.063539Z] Loop 14251: Loss: 1.79e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0835 +[2026-03-20T20:47:36.916861Z] Loop 14252: Loss: 1.73e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0835 +[2026-03-20T20:47:37.770676Z] Loop 14253: Loss: 1.85e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0896 +[2026-03-20T20:47:38.623627Z] Loop 14254: Loss: 1.94e-02, Avg Return: 0.860, Regret: 0.0009, Entropy: 0.0916 +[2026-03-20T20:47:39.477657Z] Loop 14255: Loss: 1.95e-02, Avg Return: 0.860, Regret: 0.0009, Entropy: 0.0932 +[2026-03-20T20:47:40.331624Z] Loop 14256: Loss: 1.88e-02, Avg Return: 0.860, Regret: 0.0009, Entropy: 0.0910 +[2026-03-20T20:47:41.185324Z] Loop 14257: Loss: 1.89e-02, Avg Return: 0.860, Regret: 0.0009, Entropy: 0.0924 +[2026-03-20T20:47:42.038825Z] Loop 14258: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0784 +[2026-03-20T20:47:42.893608Z] Loop 14259: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0727 +[2026-03-20T20:47:43.787911Z] Loop 14260: Loss: 1.31e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0673 +[2026-03-20T20:47:44.641327Z] Loop 14261: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0691 +[2026-03-20T20:47:45.496228Z] Loop 14262: Loss: 1.42e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0701 +[2026-03-20T20:47:46.349598Z] Loop 14263: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0708 +[2026-03-20T20:47:47.203040Z] Loop 14264: Loss: 1.32e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0687 +[2026-03-20T20:47:48.057565Z] Loop 14265: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0691 +[2026-03-20T20:47:48.912280Z] Loop 14266: Loss: 1.46e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0713 +[2026-03-20T20:47:49.768305Z] Loop 14267: Loss: 1.41e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0695 +[2026-03-20T20:47:50.621883Z] Loop 14268: Loss: 1.44e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0701 +[2026-03-20T20:47:51.475684Z] Loop 14269: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0663 +[2026-03-20T20:47:52.368863Z] Loop 14270: Loss: 1.33e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0630 +[2026-03-20T20:47:53.222726Z] Loop 14271: Loss: 1.25e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0638 +[2026-03-20T20:47:54.076913Z] Loop 14272: Loss: 1.18e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0610 +[2026-03-20T20:47:54.930772Z] Loop 14273: Loss: 1.27e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0595 +[2026-03-20T20:47:55.785267Z] Loop 14274: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0711 +[2026-03-20T20:47:56.641157Z] Loop 14275: Loss: 1.47e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0688 +[2026-03-20T20:47:57.496132Z] Loop 14276: Loss: 1.52e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0726 +[2026-03-20T20:47:58.351310Z] Loop 14277: Loss: 1.63e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0795 +[2026-03-20T20:47:59.206497Z] Loop 14278: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0833 +[2026-03-20T20:48:00.062418Z] Loop 14279: Loss: 1.85e-02, Avg Return: 0.861, Regret: 0.0003, Entropy: 0.0892 +[2026-03-20T20:48:00.956111Z] Loop 14280: Loss: 1.84e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.0864 +[2026-03-20T20:48:01.810251Z] Loop 14281: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0021, Entropy: 0.0836 +[2026-03-20T20:48:02.664716Z] Loop 14282: Loss: 1.68e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.0889 +[2026-03-20T20:48:03.519603Z] Loop 14283: Loss: 1.69e-02, Avg Return: 0.860, Regret: 0.0021, Entropy: 0.0844 +[2026-03-20T20:48:04.374175Z] Loop 14284: Loss: 1.63e-02, Avg Return: 0.860, Regret: 0.0021, Entropy: 0.0846 +[2026-03-20T20:48:05.228472Z] Loop 14285: Loss: 1.62e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.0827 +[2026-03-20T20:48:06.081963Z] Loop 14286: Loss: 1.53e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.0791 +[2026-03-20T20:48:06.935675Z] Loop 14287: Loss: 1.71e-02, Avg Return: 0.859, Regret: 0.0021, Entropy: 0.0833 +[2026-03-20T20:48:07.789720Z] Loop 14288: Loss: 1.56e-02, Avg Return: 0.861, Regret: 0.0021, Entropy: 0.0827 +[2026-03-20T20:48:08.643673Z] Loop 14289: Loss: 1.66e-02, Avg Return: 0.860, Regret: 0.0021, Entropy: 0.0821 +[2026-03-20T20:48:09.539329Z] Loop 14290: Loss: 1.34e-02, Avg Return: 0.860, Regret: 0.0030, Entropy: 0.0721 +[2026-03-20T20:48:10.393276Z] Loop 14291: Loss: 1.47e-02, Avg Return: 0.861, Regret: 0.0030, Entropy: 0.0753 +[2026-03-20T20:48:11.248398Z] Loop 14292: Loss: 1.67e-02, Avg Return: 0.860, Regret: 0.0030, Entropy: 0.0793 +[2026-03-20T20:48:12.104106Z] Loop 14293: Loss: 1.71e-02, Avg Return: 0.861, Regret: 0.0030, Entropy: 0.0799 +[2026-03-20T20:48:12.958999Z] Loop 14294: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0030, Entropy: 0.0842 +[2026-03-20T20:48:13.814715Z] Loop 14295: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0030, Entropy: 0.0856 +[2026-03-20T20:48:14.669179Z] Loop 14296: Loss: 1.87e-02, Avg Return: 0.862, Regret: 0.0030, Entropy: 0.0875 +[2026-03-20T20:48:15.523390Z] Loop 14297: Loss: 1.80e-02, Avg Return: 0.862, Regret: 0.0030, Entropy: 0.0783 +[2026-03-20T20:48:16.379407Z] Loop 14298: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0030, Entropy: 0.0738 +[2026-03-20T20:48:17.232875Z] Loop 14299: Loss: 1.38e-02, Avg Return: 0.862, Regret: 0.0030, Entropy: 0.0685 +[2026-03-20T20:48:18.126672Z] Loop 14300: Loss: 1.32e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0663 +[2026-03-20T20:48:18.980302Z] Loop 14301: Loss: 1.33e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0656 +[2026-03-20T20:48:19.835483Z] Loop 14302: Loss: 1.21e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0623 +[2026-03-20T20:48:20.689826Z] Loop 14303: Loss: 1.45e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0684 +[2026-03-20T20:48:21.543408Z] Loop 14304: Loss: 1.47e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0686 +[2026-03-20T20:48:22.397744Z] Loop 14305: Loss: 1.50e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0720 +[2026-03-20T20:48:23.253146Z] Loop 14306: Loss: 1.40e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0701 +[2026-03-20T20:48:24.108226Z] Loop 14307: Loss: 1.36e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0700 +[2026-03-20T20:48:24.963159Z] Loop 14308: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0718 +[2026-03-20T20:48:25.818032Z] Loop 14309: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0704 +[2026-03-20T20:48:26.715789Z] Loop 14310: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0689 +[2026-03-20T20:48:27.570252Z] Loop 14311: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0697 +[2026-03-20T20:48:28.425000Z] Loop 14312: Loss: 1.22e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0647 +[2026-03-20T20:48:29.278308Z] Loop 14313: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0684 +[2026-03-20T20:48:30.132392Z] Loop 14314: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0698 +[2026-03-20T20:48:30.987462Z] Loop 14315: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0745 +[2026-03-20T20:48:31.842408Z] Loop 14316: Loss: 1.52e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0766 +[2026-03-20T20:48:32.696595Z] Loop 14317: Loss: 1.49e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0742 +[2026-03-20T20:48:33.551376Z] Loop 14318: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0769 +[2026-03-20T20:48:34.405429Z] Loop 14319: Loss: 1.62e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0795 +[2026-03-20T20:48:35.298270Z] Loop 14320: Loss: 1.55e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0759 +[2026-03-20T20:48:36.151660Z] Loop 14321: Loss: 1.61e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0779 +[2026-03-20T20:48:37.005816Z] Loop 14322: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0802 +[2026-03-20T20:48:37.859011Z] Loop 14323: Loss: 1.40e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0741 +[2026-03-20T20:48:38.714093Z] Loop 14324: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0754 +[2026-03-20T20:48:39.568471Z] Loop 14325: Loss: 1.48e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0709 +[2026-03-20T20:48:40.422937Z] Loop 14326: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0711 +[2026-03-20T20:48:41.276727Z] Loop 14327: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0676 +[2026-03-20T20:48:42.128906Z] Loop 14328: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0673 +[2026-03-20T20:48:42.983511Z] Loop 14329: Loss: 1.31e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0682 +[2026-03-20T20:48:43.882463Z] Loop 14330: Loss: 1.46e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0693 +[2026-03-20T20:48:44.736586Z] Loop 14331: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0680 +[2026-03-20T20:48:45.590934Z] Loop 14332: Loss: 1.43e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0685 +[2026-03-20T20:48:46.445790Z] Loop 14333: Loss: 1.54e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0710 +[2026-03-20T20:48:47.302013Z] Loop 14334: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0672 +[2026-03-20T20:48:48.155801Z] Loop 14335: Loss: 1.40e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0683 +[2026-03-20T20:48:49.008757Z] Loop 14336: Loss: 1.44e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0704 +[2026-03-20T20:48:49.862264Z] Loop 14337: Loss: 1.30e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0625 +[2026-03-20T20:48:50.716415Z] Loop 14338: Loss: 1.32e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0673 +[2026-03-20T20:48:51.570218Z] Loop 14339: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0660 +[2026-03-20T20:48:52.466663Z] Loop 14340: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0699 +[2026-03-20T20:48:53.320116Z] Loop 14341: Loss: 1.38e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0684 +[2026-03-20T20:48:54.174259Z] Loop 14342: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0699 +[2026-03-20T20:48:55.028130Z] Loop 14343: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0741 +[2026-03-20T20:48:55.882352Z] Loop 14344: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0731 +[2026-03-20T20:48:56.734907Z] Loop 14345: Loss: 1.54e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0768 +[2026-03-20T20:48:57.587359Z] Loop 14346: Loss: 1.76e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0812 +[2026-03-20T20:48:58.441847Z] Loop 14347: Loss: 1.74e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0813 +[2026-03-20T20:48:59.295119Z] Loop 14348: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0808 +[2026-03-20T20:49:00.149131Z] Loop 14349: Loss: 1.67e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0796 +[2026-03-20T20:49:01.044809Z] Loop 14350: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0789 +[2026-03-20T20:49:01.900545Z] Loop 14351: Loss: 1.46e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0717 +[2026-03-20T20:49:02.754427Z] Loop 14352: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0699 +[2026-03-20T20:49:03.608002Z] Loop 14353: Loss: 1.33e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0677 +[2026-03-20T20:49:04.463917Z] Loop 14354: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0680 +[2026-03-20T20:49:05.317765Z] Loop 14355: Loss: 1.41e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0683 +[2026-03-20T20:49:06.171732Z] Loop 14356: Loss: 1.41e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0684 +[2026-03-20T20:49:07.027071Z] Loop 14357: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0638 +[2026-03-20T20:49:07.881182Z] Loop 14358: Loss: 1.32e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0652 +[2026-03-20T20:49:08.735374Z] Loop 14359: Loss: 1.20e-02, Avg Return: 0.865, Regret: 0.0010, Entropy: 0.0637 +[2026-03-20T20:49:09.630096Z] Loop 14360: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0654 +[2026-03-20T20:49:10.485688Z] Loop 14361: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0655 +[2026-03-20T20:49:11.343590Z] Loop 14362: Loss: 1.28e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0671 +[2026-03-20T20:49:12.197085Z] Loop 14363: Loss: 1.29e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0609 +[2026-03-20T20:49:13.050591Z] Loop 14364: Loss: 1.27e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0642 +[2026-03-20T20:49:13.904140Z] Loop 14365: Loss: 1.27e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0651 +[2026-03-20T20:49:14.758113Z] Loop 14366: Loss: 1.21e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0631 +[2026-03-20T20:49:15.611833Z] Loop 14367: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0633 +[2026-03-20T20:49:16.465575Z] Loop 14368: Loss: 1.20e-02, Avg Return: 0.865, Regret: 0.0002, Entropy: 0.0614 +[2026-03-20T20:49:17.319058Z] Loop 14369: Loss: 1.29e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0622 +[2026-03-20T20:49:18.213945Z] Loop 14370: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0633 +[2026-03-20T20:49:19.068391Z] Loop 14371: Loss: 1.21e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0623 +[2026-03-20T20:49:19.922241Z] Loop 14372: Loss: 1.29e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0640 +[2026-03-20T20:49:20.775827Z] Loop 14373: Loss: 1.21e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0623 +[2026-03-20T20:49:21.630793Z] Loop 14374: Loss: 1.28e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0639 +[2026-03-20T20:49:22.484656Z] Loop 14375: Loss: 1.19e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0598 +[2026-03-20T20:49:23.338148Z] Loop 14376: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0657 +[2026-03-20T20:49:24.192428Z] Loop 14377: Loss: 1.28e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0663 +[2026-03-20T20:49:25.046475Z] Loop 14378: Loss: 1.45e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0727 +[2026-03-20T20:49:25.901159Z] Loop 14379: Loss: 1.63e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0756 +[2026-03-20T20:49:26.795024Z] Loop 14380: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0744 +[2026-03-20T20:49:27.648932Z] Loop 14381: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0669 +[2026-03-20T20:49:28.502844Z] Loop 14382: Loss: 1.39e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0684 +[2026-03-20T20:49:29.356781Z] Loop 14383: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0661 +[2026-03-20T20:49:30.211527Z] Loop 14384: Loss: 1.37e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0676 +[2026-03-20T20:49:31.066179Z] Loop 14385: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0721 +[2026-03-20T20:49:31.919584Z] Loop 14386: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0753 +[2026-03-20T20:49:32.773464Z] Loop 14387: Loss: 1.84e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0848 +[2026-03-20T20:49:33.627424Z] Loop 14388: Loss: 2.10e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0996 +[2026-03-20T20:49:34.482113Z] Loop 14389: Loss: 2.23e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.1058 +[2026-03-20T20:49:35.375959Z] Loop 14390: Loss: 2.29e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1057 +[2026-03-20T20:49:36.228772Z] Loop 14391: Loss: 2.12e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.1041 +[2026-03-20T20:49:37.082741Z] Loop 14392: Loss: 2.23e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1064 +[2026-03-20T20:49:37.937269Z] Loop 14393: Loss: 2.27e-02, Avg Return: 0.860, Regret: 0.0013, Entropy: 0.1062 +[2026-03-20T20:49:38.790799Z] Loop 14394: Loss: 2.22e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1061 +[2026-03-20T20:49:39.643526Z] Loop 14395: Loss: 2.16e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.1052 +[2026-03-20T20:49:40.496794Z] Loop 14396: Loss: 2.21e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1074 +[2026-03-20T20:49:41.351183Z] Loop 14397: Loss: 2.15e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.1026 +[2026-03-20T20:49:42.205297Z] Loop 14398: Loss: 2.29e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1085 +[2026-03-20T20:49:43.057419Z] Loop 14399: Loss: 2.22e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.1058 +[2026-03-20T20:49:43.950142Z] Loop 14400: Loss: 2.22e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.1043 +[2026-03-20T20:49:44.805527Z] Loop 14401: Loss: 2.07e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0998 +[2026-03-20T20:49:45.659695Z] Loop 14402: Loss: 1.90e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0885 +[2026-03-20T20:49:46.513727Z] Loop 14403: Loss: 1.90e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0927 +[2026-03-20T20:49:47.366298Z] Loop 14404: Loss: 1.83e-02, Avg Return: 0.860, Regret: 0.0007, Entropy: 0.0957 +[2026-03-20T20:49:48.220868Z] Loop 14405: Loss: 1.88e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0952 +[2026-03-20T20:49:49.075432Z] Loop 14406: Loss: 1.94e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0966 +[2026-03-20T20:49:49.929718Z] Loop 14407: Loss: 1.95e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0999 +[2026-03-20T20:49:50.784468Z] Loop 14408: Loss: 1.92e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0972 +[2026-03-20T20:49:51.639261Z] Loop 14409: Loss: 1.81e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0893 +[2026-03-20T20:49:52.536096Z] Loop 14410: Loss: 1.75e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0880 +[2026-03-20T20:49:53.390384Z] Loop 14411: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0898 +[2026-03-20T20:49:54.244772Z] Loop 14412: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0877 +[2026-03-20T20:49:55.099189Z] Loop 14413: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0805 +[2026-03-20T20:49:55.953214Z] Loop 14414: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0831 +[2026-03-20T20:49:56.807960Z] Loop 14415: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0775 +[2026-03-20T20:49:57.662287Z] Loop 14416: Loss: 1.54e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0781 +[2026-03-20T20:49:58.516307Z] Loop 14417: Loss: 1.70e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0829 +[2026-03-20T20:49:59.370226Z] Loop 14418: Loss: 1.68e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0860 +[2026-03-20T20:50:00.224408Z] Loop 14419: Loss: 2.00e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0935 +[2026-03-20T20:50:01.119417Z] Loop 14420: Loss: 2.15e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.1027 +[2026-03-20T20:50:01.974777Z] Loop 14421: Loss: 2.16e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.1036 +[2026-03-20T20:50:02.830776Z] Loop 14422: Loss: 2.10e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.1006 +[2026-03-20T20:50:03.684623Z] Loop 14423: Loss: 1.84e-02, Avg Return: 0.865, Regret: 0.0001, Entropy: 0.0887 +[2026-03-20T20:50:04.540207Z] Loop 14424: Loss: 1.59e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0809 +[2026-03-20T20:50:05.395099Z] Loop 14425: Loss: 1.66e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0783 +[2026-03-20T20:50:06.249325Z] Loop 14426: Loss: 1.66e-02, Avg Return: 0.865, Regret: 0.0001, Entropy: 0.0796 +[2026-03-20T20:50:07.104848Z] Loop 14427: Loss: 1.76e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0812 +[2026-03-20T20:50:07.960346Z] Loop 14428: Loss: 1.73e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0808 +[2026-03-20T20:50:08.815235Z] Loop 14429: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0796 +[2026-03-20T20:50:09.711887Z] Loop 14430: Loss: 1.52e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0756 +[2026-03-20T20:50:10.565300Z] Loop 14431: Loss: 1.42e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0708 +[2026-03-20T20:50:11.419165Z] Loop 14432: Loss: 1.43e-02, Avg Return: 0.865, Regret: 0.0003, Entropy: 0.0705 +[2026-03-20T20:50:12.273720Z] Loop 14433: Loss: 1.41e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0702 +[2026-03-20T20:50:13.128449Z] Loop 14434: Loss: 1.40e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0690 +[2026-03-20T20:50:13.982467Z] Loop 14435: Loss: 1.41e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0702 +[2026-03-20T20:50:14.836160Z] Loop 14436: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0710 +[2026-03-20T20:50:15.690874Z] Loop 14437: Loss: 1.39e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0705 +[2026-03-20T20:50:16.545235Z] Loop 14438: Loss: 1.36e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0696 +[2026-03-20T20:50:17.398612Z] Loop 14439: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0664 +[2026-03-20T20:50:18.290744Z] Loop 14440: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0631 +[2026-03-20T20:50:19.145860Z] Loop 14441: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0696 +[2026-03-20T20:50:20.000563Z] Loop 14442: Loss: 1.37e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0685 +[2026-03-20T20:50:20.854975Z] Loop 14443: Loss: 1.30e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0657 +[2026-03-20T20:50:21.708631Z] Loop 14444: Loss: 1.25e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0636 +[2026-03-20T20:50:22.562667Z] Loop 14445: Loss: 1.17e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0590 +[2026-03-20T20:50:23.416819Z] Loop 14446: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0665 +[2026-03-20T20:50:24.271717Z] Loop 14447: Loss: 1.18e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0628 +[2026-03-20T20:50:25.126647Z] Loop 14448: Loss: 1.29e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0635 +[2026-03-20T20:50:25.980898Z] Loop 14449: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0678 +[2026-03-20T20:50:26.874783Z] Loop 14450: Loss: 1.23e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0616 +[2026-03-20T20:50:27.728601Z] Loop 14451: Loss: 1.19e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0637 +[2026-03-20T20:50:28.583549Z] Loop 14452: Loss: 1.24e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0635 +[2026-03-20T20:50:29.437596Z] Loop 14453: Loss: 1.23e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0617 +[2026-03-20T20:50:30.290229Z] Loop 14454: Loss: 1.22e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0645 +[2026-03-20T20:50:31.143095Z] Loop 14455: Loss: 1.14e-02, Avg Return: 0.861, Regret: 0.0002, Entropy: 0.0627 +[2026-03-20T20:50:31.998023Z] Loop 14456: Loss: 1.25e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0631 +[2026-03-20T20:50:32.852750Z] Loop 14457: Loss: 1.25e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0639 +[2026-03-20T20:50:33.705971Z] Loop 14458: Loss: 1.22e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0656 +[2026-03-20T20:50:34.559473Z] Loop 14459: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0633 +[2026-03-20T20:50:35.454013Z] Loop 14460: Loss: 1.25e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0638 +[2026-03-20T20:50:36.308455Z] Loop 14461: Loss: 1.14e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0602 +[2026-03-20T20:50:37.164184Z] Loop 14462: Loss: 1.16e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0622 +[2026-03-20T20:50:38.018632Z] Loop 14463: Loss: 1.22e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0626 +[2026-03-20T20:50:38.874033Z] Loop 14464: Loss: 1.17e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0582 +[2026-03-20T20:50:39.729489Z] Loop 14465: Loss: 1.18e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0592 +[2026-03-20T20:50:40.584194Z] Loop 14466: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0597 +[2026-03-20T20:50:41.438100Z] Loop 14467: Loss: 1.11e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0604 +[2026-03-20T20:50:42.292222Z] Loop 14468: Loss: 1.20e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0635 +[2026-03-20T20:50:43.146315Z] Loop 14469: Loss: 1.23e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0630 +[2026-03-20T20:50:44.040057Z] Loop 14470: Loss: 1.22e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0615 +[2026-03-20T20:50:44.893870Z] Loop 14471: Loss: 1.33e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0639 +[2026-03-20T20:50:45.748571Z] Loop 14472: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0693 +[2026-03-20T20:50:46.601915Z] Loop 14473: Loss: 1.50e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0726 +[2026-03-20T20:50:47.455409Z] Loop 14474: Loss: 1.47e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0717 +[2026-03-20T20:50:48.309304Z] Loop 14475: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0754 +[2026-03-20T20:50:49.164012Z] Loop 14476: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0813 +[2026-03-20T20:50:50.018811Z] Loop 14477: Loss: 1.68e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0808 +[2026-03-20T20:50:50.872443Z] Loop 14478: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0777 +[2026-03-20T20:50:51.725473Z] Loop 14479: Loss: 1.52e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0725 +[2026-03-20T20:50:52.619212Z] Loop 14480: Loss: 1.42e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0726 +[2026-03-20T20:50:53.471687Z] Loop 14481: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0667 +[2026-03-20T20:50:54.323771Z] Loop 14482: Loss: 1.17e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0637 +[2026-03-20T20:50:55.177624Z] Loop 14483: Loss: 1.35e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0691 +[2026-03-20T20:50:56.032115Z] Loop 14484: Loss: 1.39e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0720 +[2026-03-20T20:50:56.886596Z] Loop 14485: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0775 +[2026-03-20T20:50:57.740472Z] Loop 14486: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0779 +[2026-03-20T20:50:58.594360Z] Loop 14487: Loss: 1.62e-02, Avg Return: 0.860, Regret: 0.0002, Entropy: 0.0818 +[2026-03-20T20:50:59.449302Z] Loop 14488: Loss: 1.77e-02, Avg Return: 0.857, Regret: 0.0002, Entropy: 0.0877 +[2026-03-20T20:51:00.303263Z] Loop 14489: Loss: 1.76e-02, Avg Return: 0.858, Regret: 0.0002, Entropy: 0.0861 +[2026-03-20T20:51:01.196576Z] Loop 14490: Loss: 1.82e-02, Avg Return: 0.859, Regret: 0.0045, Entropy: 0.0865 +[2026-03-20T20:51:02.049647Z] Loop 14491: Loss: 1.87e-02, Avg Return: 0.860, Regret: 0.0045, Entropy: 0.0875 +[2026-03-20T20:51:02.904761Z] Loop 14492: Loss: 1.86e-02, Avg Return: 0.861, Regret: 0.0045, Entropy: 0.0871 +[2026-03-20T20:51:03.759454Z] Loop 14493: Loss: 1.83e-02, Avg Return: 0.862, Regret: 0.0045, Entropy: 0.0863 +[2026-03-20T20:51:04.613559Z] Loop 14494: Loss: 1.81e-02, Avg Return: 0.861, Regret: 0.0045, Entropy: 0.0879 +[2026-03-20T20:51:05.467117Z] Loop 14495: Loss: 1.74e-02, Avg Return: 0.861, Regret: 0.0045, Entropy: 0.0857 +[2026-03-20T20:51:06.321760Z] Loop 14496: Loss: 1.62e-02, Avg Return: 0.861, Regret: 0.0045, Entropy: 0.0820 +[2026-03-20T20:51:07.175688Z] Loop 14497: Loss: 1.62e-02, Avg Return: 0.862, Regret: 0.0045, Entropy: 0.0795 +[2026-03-20T20:51:08.030229Z] Loop 14498: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0045, Entropy: 0.0730 +[2026-03-20T20:51:08.884716Z] Loop 14499: Loss: 1.55e-02, Avg Return: 0.862, Regret: 0.0045, Entropy: 0.0718 +[2026-03-20T20:51:09.778705Z] Loop 14500: Loss: 1.32e-02, Avg Return: 0.860, Regret: 0.0023, Entropy: 0.0691 +[2026-03-20T20:51:10.632366Z] Loop 14501: Loss: 1.31e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.0626 +[2026-03-20T20:51:11.486603Z] Loop 14502: Loss: 1.19e-02, Avg Return: 0.861, Regret: 0.0023, Entropy: 0.0617 +[2026-03-20T20:51:12.340652Z] Loop 14503: Loss: 1.23e-02, Avg Return: 0.863, Regret: 0.0023, Entropy: 0.0609 +[2026-03-20T20:51:13.193537Z] Loop 14504: Loss: 1.16e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.0616 +[2026-03-20T20:51:14.046856Z] Loop 14505: Loss: 1.19e-02, Avg Return: 0.863, Regret: 0.0023, Entropy: 0.0606 +[2026-03-20T20:51:14.901174Z] Loop 14506: Loss: 1.20e-02, Avg Return: 0.863, Regret: 0.0023, Entropy: 0.0603 +[2026-03-20T20:51:15.755796Z] Loop 14507: Loss: 1.29e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.0656 +[2026-03-20T20:51:16.608721Z] Loop 14508: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0023, Entropy: 0.0674 +[2026-03-20T20:51:17.461073Z] Loop 14509: Loss: 1.19e-02, Avg Return: 0.863, Regret: 0.0023, Entropy: 0.0628 +[2026-03-20T20:51:18.354255Z] Loop 14510: Loss: 1.17e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0623 +[2026-03-20T20:51:19.208128Z] Loop 14511: Loss: 1.15e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0614 +[2026-03-20T20:51:20.062657Z] Loop 14512: Loss: 1.28e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0643 +[2026-03-20T20:51:20.917286Z] Loop 14513: Loss: 1.25e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0642 +[2026-03-20T20:51:21.772068Z] Loop 14514: Loss: 1.21e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0645 +[2026-03-20T20:51:22.628193Z] Loop 14515: Loss: 1.15e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0651 +[2026-03-20T20:51:23.484366Z] Loop 14516: Loss: 1.22e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0647 +[2026-03-20T20:51:24.340024Z] Loop 14517: Loss: 1.32e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0646 +[2026-03-20T20:51:25.194287Z] Loop 14518: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0655 +[2026-03-20T20:51:26.050047Z] Loop 14519: Loss: 1.14e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0601 +[2026-03-20T20:51:26.945317Z] Loop 14520: Loss: 1.26e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0650 +[2026-03-20T20:51:27.800799Z] Loop 14521: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0689 +[2026-03-20T20:51:28.655582Z] Loop 14522: Loss: 1.33e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0684 +[2026-03-20T20:51:29.509559Z] Loop 14523: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0790 +[2026-03-20T20:51:30.363610Z] Loop 14524: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0780 +[2026-03-20T20:51:31.217050Z] Loop 14525: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0778 +[2026-03-20T20:51:32.071482Z] Loop 14526: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0782 +[2026-03-20T20:51:32.926133Z] Loop 14527: Loss: 1.63e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0784 +[2026-03-20T20:51:33.780933Z] Loop 14528: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0764 +[2026-03-20T20:51:34.635669Z] Loop 14529: Loss: 1.57e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0773 +[2026-03-20T20:51:35.530077Z] Loop 14530: Loss: 1.57e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0734 +[2026-03-20T20:51:36.384396Z] Loop 14531: Loss: 1.48e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0720 +[2026-03-20T20:51:37.238642Z] Loop 14532: Loss: 1.45e-02, Avg Return: 0.865, Regret: 0.0003, Entropy: 0.0711 +[2026-03-20T20:51:38.092933Z] Loop 14533: Loss: 1.57e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0710 +[2026-03-20T20:51:38.947351Z] Loop 14534: Loss: 1.47e-02, Avg Return: 0.865, Regret: 0.0003, Entropy: 0.0691 +[2026-03-20T20:51:39.801647Z] Loop 14535: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0757 +[2026-03-20T20:51:40.656006Z] Loop 14536: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0721 +[2026-03-20T20:51:41.510896Z] Loop 14537: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0748 +[2026-03-20T20:51:42.364457Z] Loop 14538: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0716 +[2026-03-20T20:51:43.218916Z] Loop 14539: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0708 +[2026-03-20T20:51:44.112272Z] Loop 14540: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0731 +[2026-03-20T20:51:44.966536Z] Loop 14541: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0756 +[2026-03-20T20:51:45.821010Z] Loop 14542: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0753 +[2026-03-20T20:51:46.676028Z] Loop 14543: Loss: 1.55e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0745 +[2026-03-20T20:51:47.529776Z] Loop 14544: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0708 +[2026-03-20T20:51:48.383833Z] Loop 14545: Loss: 1.24e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0628 +[2026-03-20T20:51:49.237596Z] Loop 14546: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0640 +[2026-03-20T20:51:50.093099Z] Loop 14547: Loss: 1.10e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0584 +[2026-03-20T20:51:50.947697Z] Loop 14548: Loss: 1.22e-02, Avg Return: 0.865, Regret: 0.0001, Entropy: 0.0633 +[2026-03-20T20:51:51.801296Z] Loop 14549: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0639 +[2026-03-20T20:51:52.695100Z] Loop 14550: Loss: 1.17e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0608 +[2026-03-20T20:51:53.550681Z] Loop 14551: Loss: 1.27e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0619 +[2026-03-20T20:51:54.406078Z] Loop 14552: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0641 +[2026-03-20T20:51:55.260244Z] Loop 14553: Loss: 1.18e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0604 +[2026-03-20T20:51:56.114204Z] Loop 14554: Loss: 1.14e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0626 +[2026-03-20T20:51:56.969445Z] Loop 14555: Loss: 1.19e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0605 +[2026-03-20T20:51:57.823612Z] Loop 14556: Loss: 1.14e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0622 +[2026-03-20T20:51:58.678499Z] Loop 14557: Loss: 1.24e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0642 +[2026-03-20T20:51:59.531900Z] Loop 14558: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0651 +[2026-03-20T20:52:00.386156Z] Loop 14559: Loss: 1.19e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0642 +[2026-03-20T20:52:01.280401Z] Loop 14560: Loss: 1.33e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0652 +[2026-03-20T20:52:02.134831Z] Loop 14561: Loss: 1.21e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0647 +[2026-03-20T20:52:02.988557Z] Loop 14562: Loss: 1.12e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0602 +[2026-03-20T20:52:03.842522Z] Loop 14563: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0639 +[2026-03-20T20:52:04.697031Z] Loop 14564: Loss: 1.28e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0626 +[2026-03-20T20:52:05.552166Z] Loop 14565: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0644 +[2026-03-20T20:52:06.406567Z] Loop 14566: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0655 +[2026-03-20T20:52:07.261088Z] Loop 14567: Loss: 1.20e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0617 +[2026-03-20T20:52:08.115144Z] Loop 14568: Loss: 1.14e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0593 +[2026-03-20T20:52:08.969715Z] Loop 14569: Loss: 1.14e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0623 +[2026-03-20T20:52:09.863965Z] Loop 14570: Loss: 1.22e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0635 +[2026-03-20T20:52:10.718191Z] Loop 14571: Loss: 1.16e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0632 +[2026-03-20T20:52:11.572278Z] Loop 14572: Loss: 1.22e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0637 +[2026-03-20T20:52:12.425886Z] Loop 14573: Loss: 1.21e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0645 +[2026-03-20T20:52:13.280511Z] Loop 14574: Loss: 1.24e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0624 +[2026-03-20T20:52:14.135772Z] Loop 14575: Loss: 1.24e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0634 +[2026-03-20T20:52:14.988806Z] Loop 14576: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0676 +[2026-03-20T20:52:15.841561Z] Loop 14577: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0753 +[2026-03-20T20:52:16.695551Z] Loop 14578: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0756 +[2026-03-20T20:52:17.550727Z] Loop 14579: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0716 +[2026-03-20T20:52:18.445384Z] Loop 14580: Loss: 1.49e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0701 +[2026-03-20T20:52:19.298789Z] Loop 14581: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0651 +[2026-03-20T20:52:20.152652Z] Loop 14582: Loss: 1.34e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0652 +[2026-03-20T20:52:21.006857Z] Loop 14583: Loss: 1.33e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0647 +[2026-03-20T20:52:21.861222Z] Loop 14584: Loss: 1.26e-02, Avg Return: 0.865, Regret: 0.0001, Entropy: 0.0642 +[2026-03-20T20:52:22.715613Z] Loop 14585: Loss: 1.22e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0624 +[2026-03-20T20:52:23.569276Z] Loop 14586: Loss: 1.16e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0584 +[2026-03-20T20:52:24.422949Z] Loop 14587: Loss: 1.25e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0594 +[2026-03-20T20:52:25.277947Z] Loop 14588: Loss: 1.18e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0589 +[2026-03-20T20:52:26.132317Z] Loop 14589: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0652 +[2026-03-20T20:52:27.025174Z] Loop 14590: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0671 +[2026-03-20T20:52:27.879147Z] Loop 14591: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0656 +[2026-03-20T20:52:28.734084Z] Loop 14592: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0684 +[2026-03-20T20:52:29.588145Z] Loop 14593: Loss: 1.30e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0623 +[2026-03-20T20:52:30.442466Z] Loop 14594: Loss: 1.38e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0668 +[2026-03-20T20:52:31.297369Z] Loop 14595: Loss: 1.31e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0635 +[2026-03-20T20:52:32.151745Z] Loop 14596: Loss: 1.46e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0644 +[2026-03-20T20:52:33.005561Z] Loop 14597: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0673 +[2026-03-20T20:52:33.859396Z] Loop 14598: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0667 +[2026-03-20T20:52:34.712416Z] Loop 14599: Loss: 1.32e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0644 +[2026-03-20T20:52:35.606469Z] Loop 14600: Loss: 1.13e-02, Avg Return: 0.861, Regret: 0.0023, Entropy: 0.0573 +[2026-03-20T20:52:36.460036Z] Loop 14601: Loss: 1.07e-02, Avg Return: 0.858, Regret: 0.0023, Entropy: 0.0550 +[2026-03-20T20:52:37.313754Z] Loop 14602: Loss: 1.15e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.0600 +[2026-03-20T20:52:38.167933Z] Loop 14603: Loss: 1.05e-02, Avg Return: 0.861, Regret: 0.0023, Entropy: 0.0542 +[2026-03-20T20:52:39.022665Z] Loop 14604: Loss: 1.10e-02, Avg Return: 0.861, Regret: 0.0023, Entropy: 0.0546 +[2026-03-20T20:52:39.876256Z] Loop 14605: Loss: 1.18e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.0577 +[2026-03-20T20:52:40.730085Z] Loop 14606: Loss: 1.17e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.0560 +[2026-03-20T20:52:41.584521Z] Loop 14607: Loss: 1.13e-02, Avg Return: 0.863, Regret: 0.0023, Entropy: 0.0593 +[2026-03-20T20:52:42.438551Z] Loop 14608: Loss: 1.12e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.0590 +[2026-03-20T20:52:43.292307Z] Loop 14609: Loss: 1.30e-02, Avg Return: 0.863, Regret: 0.0023, Entropy: 0.0627 +[2026-03-20T20:52:44.185899Z] Loop 14610: Loss: 1.19e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0597 +[2026-03-20T20:52:45.039841Z] Loop 14611: Loss: 1.25e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0620 +[2026-03-20T20:52:45.894625Z] Loop 14612: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0690 +[2026-03-20T20:52:46.749135Z] Loop 14613: Loss: 1.28e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0660 +[2026-03-20T20:52:47.604573Z] Loop 14614: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0688 +[2026-03-20T20:52:48.458868Z] Loop 14615: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0639 +[2026-03-20T20:52:49.313430Z] Loop 14616: Loss: 1.28e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0640 +[2026-03-20T20:52:50.166584Z] Loop 14617: Loss: 1.38e-02, Avg Return: 0.865, Regret: 0.0006, Entropy: 0.0665 +[2026-03-20T20:52:51.019819Z] Loop 14618: Loss: 1.23e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0641 +[2026-03-20T20:52:51.874993Z] Loop 14619: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0665 +[2026-03-20T20:52:52.769446Z] Loop 14620: Loss: 1.22e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0607 +[2026-03-20T20:52:53.623648Z] Loop 14621: Loss: 1.26e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0611 +[2026-03-20T20:52:54.479076Z] Loop 14622: Loss: 1.22e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0632 +[2026-03-20T20:52:55.333649Z] Loop 14623: Loss: 1.23e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0634 +[2026-03-20T20:52:56.189629Z] Loop 14624: Loss: 1.09e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0595 +[2026-03-20T20:52:57.044309Z] Loop 14625: Loss: 1.40e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0659 +[2026-03-20T20:52:57.897904Z] Loop 14626: Loss: 1.20e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0619 +[2026-03-20T20:52:58.751448Z] Loop 14627: Loss: 1.30e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0617 +[2026-03-20T20:52:59.605645Z] Loop 14628: Loss: 1.25e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0659 +[2026-03-20T20:53:00.462466Z] Loop 14629: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0661 +[2026-03-20T20:53:01.357112Z] Loop 14630: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0710 +[2026-03-20T20:53:02.210874Z] Loop 14631: Loss: 1.33e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0663 +[2026-03-20T20:53:03.065781Z] Loop 14632: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0702 +[2026-03-20T20:53:03.919934Z] Loop 14633: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0810 +[2026-03-20T20:53:04.775239Z] Loop 14634: Loss: 1.78e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0804 +[2026-03-20T20:53:05.628339Z] Loop 14635: Loss: 1.63e-02, Avg Return: 0.865, Regret: 0.0002, Entropy: 0.0793 +[2026-03-20T20:53:06.482666Z] Loop 14636: Loss: 1.55e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0764 +[2026-03-20T20:53:07.336868Z] Loop 14637: Loss: 1.59e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0761 +[2026-03-20T20:53:08.191477Z] Loop 14638: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0808 +[2026-03-20T20:53:09.045944Z] Loop 14639: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0804 +[2026-03-20T20:53:09.940778Z] Loop 14640: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0788 +[2026-03-20T20:53:10.794456Z] Loop 14641: Loss: 1.63e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0786 +[2026-03-20T20:53:11.649627Z] Loop 14642: Loss: 1.77e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0804 +[2026-03-20T20:53:12.503399Z] Loop 14643: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0852 +[2026-03-20T20:53:13.358293Z] Loop 14644: Loss: 1.84e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0874 +[2026-03-20T20:53:14.212342Z] Loop 14645: Loss: 1.81e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0898 +[2026-03-20T20:53:15.067385Z] Loop 14646: Loss: 1.89e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0881 +[2026-03-20T20:53:15.921325Z] Loop 14647: Loss: 1.74e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0853 +[2026-03-20T20:53:16.777275Z] Loop 14648: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0805 +[2026-03-20T20:53:17.631004Z] Loop 14649: Loss: 1.74e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0838 +[2026-03-20T20:53:18.525395Z] Loop 14650: Loss: 1.55e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0780 +[2026-03-20T20:53:19.379978Z] Loop 14651: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0780 +[2026-03-20T20:53:20.235598Z] Loop 14652: Loss: 1.83e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0846 +[2026-03-20T20:53:21.091625Z] Loop 14653: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0860 +[2026-03-20T20:53:21.946931Z] Loop 14654: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0891 +[2026-03-20T20:53:22.800834Z] Loop 14655: Loss: 1.89e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0884 +[2026-03-20T20:53:23.655334Z] Loop 14656: Loss: 1.82e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0866 +[2026-03-20T20:53:24.509697Z] Loop 14657: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0830 +[2026-03-20T20:53:25.362867Z] Loop 14658: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0815 +[2026-03-20T20:53:26.216030Z] Loop 14659: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0737 +[2026-03-20T20:53:27.109897Z] Loop 14660: Loss: 1.41e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0705 +[2026-03-20T20:53:27.963876Z] Loop 14661: Loss: 1.50e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0729 +[2026-03-20T20:53:28.818337Z] Loop 14662: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0728 +[2026-03-20T20:53:29.672196Z] Loop 14663: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0723 +[2026-03-20T20:53:30.526520Z] Loop 14664: Loss: 1.46e-02, Avg Return: 0.865, Regret: 0.0001, Entropy: 0.0699 +[2026-03-20T20:53:31.381598Z] Loop 14665: Loss: 1.39e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0695 +[2026-03-20T20:53:32.235579Z] Loop 14666: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0706 +[2026-03-20T20:53:33.088693Z] Loop 14667: Loss: 1.42e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0671 +[2026-03-20T20:53:33.942228Z] Loop 14668: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0683 +[2026-03-20T20:53:34.796062Z] Loop 14669: Loss: 1.43e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0702 +[2026-03-20T20:53:35.689840Z] Loop 14670: Loss: 1.37e-02, Avg Return: 0.865, Regret: 0.0001, Entropy: 0.0678 +[2026-03-20T20:53:36.544298Z] Loop 14671: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0680 +[2026-03-20T20:53:37.399122Z] Loop 14672: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0704 +[2026-03-20T20:53:38.254083Z] Loop 14673: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0697 +[2026-03-20T20:53:39.108540Z] Loop 14674: Loss: 1.30e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0646 +[2026-03-20T20:53:39.962908Z] Loop 14675: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0689 +[2026-03-20T20:53:40.816889Z] Loop 14676: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0709 +[2026-03-20T20:53:41.670636Z] Loop 14677: Loss: 1.50e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0731 +[2026-03-20T20:53:42.525078Z] Loop 14678: Loss: 1.49e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0695 +[2026-03-20T20:53:43.380779Z] Loop 14679: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0710 +[2026-03-20T20:53:44.274976Z] Loop 14680: Loss: 1.53e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0742 +[2026-03-20T20:53:45.127703Z] Loop 14681: Loss: 1.49e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0734 +[2026-03-20T20:53:45.980637Z] Loop 14682: Loss: 1.46e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0728 +[2026-03-20T20:53:46.835562Z] Loop 14683: Loss: 1.50e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0734 +[2026-03-20T20:53:47.689287Z] Loop 14684: Loss: 1.50e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0767 +[2026-03-20T20:53:48.542319Z] Loop 14685: Loss: 1.54e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0780 +[2026-03-20T20:53:49.395460Z] Loop 14686: Loss: 1.32e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0704 +[2026-03-20T20:53:50.250100Z] Loop 14687: Loss: 1.47e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0733 +[2026-03-20T20:53:51.104004Z] Loop 14688: Loss: 1.44e-02, Avg Return: 0.865, Regret: 0.0002, Entropy: 0.0694 +[2026-03-20T20:53:51.958318Z] Loop 14689: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0704 +[2026-03-20T20:53:52.852799Z] Loop 14690: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0701 +[2026-03-20T20:53:53.712677Z] Loop 14691: Loss: 1.41e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0685 +[2026-03-20T20:53:54.567100Z] Loop 14692: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0713 +[2026-03-20T20:53:55.421591Z] Loop 14693: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0732 +[2026-03-20T20:53:56.275409Z] Loop 14694: Loss: 1.32e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0699 +[2026-03-20T20:53:57.129664Z] Loop 14695: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0690 +[2026-03-20T20:53:57.983768Z] Loop 14696: Loss: 1.33e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0654 +[2026-03-20T20:53:58.837338Z] Loop 14697: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0688 +[2026-03-20T20:53:59.692044Z] Loop 14698: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0681 +[2026-03-20T20:54:00.545274Z] Loop 14699: Loss: 1.34e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0662 +[2026-03-20T20:54:01.439562Z] Loop 14700: Loss: 1.47e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0688 +[2026-03-20T20:54:02.293820Z] Loop 14701: Loss: 1.35e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0652 +[2026-03-20T20:54:03.149131Z] Loop 14702: Loss: 1.44e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0715 +[2026-03-20T20:54:04.003823Z] Loop 14703: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0676 +[2026-03-20T20:54:04.857794Z] Loop 14704: Loss: 1.52e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0720 +[2026-03-20T20:54:05.711703Z] Loop 14705: Loss: 1.49e-02, Avg Return: 0.861, Regret: 0.0001, Entropy: 0.0711 +[2026-03-20T20:54:06.566068Z] Loop 14706: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0730 +[2026-03-20T20:54:07.421104Z] Loop 14707: Loss: 1.58e-02, Avg Return: 0.861, Regret: 0.0001, Entropy: 0.0752 +[2026-03-20T20:54:08.274972Z] Loop 14708: Loss: 1.44e-02, Avg Return: 0.861, Regret: 0.0001, Entropy: 0.0723 +[2026-03-20T20:54:09.128774Z] Loop 14709: Loss: 1.46e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0727 +[2026-03-20T20:54:10.023191Z] Loop 14710: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0643 +[2026-03-20T20:54:10.878723Z] Loop 14711: Loss: 1.29e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0642 +[2026-03-20T20:54:11.732622Z] Loop 14712: Loss: 1.25e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0627 +[2026-03-20T20:54:12.587050Z] Loop 14713: Loss: 1.32e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0662 +[2026-03-20T20:54:13.442128Z] Loop 14714: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0625 +[2026-03-20T20:54:14.296546Z] Loop 14715: Loss: 1.25e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0614 +[2026-03-20T20:54:15.150452Z] Loop 14716: Loss: 1.30e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0664 +[2026-03-20T20:54:16.003961Z] Loop 14717: Loss: 1.19e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0629 +[2026-03-20T20:54:16.857494Z] Loop 14718: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0673 +[2026-03-20T20:54:17.711058Z] Loop 14719: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0656 +[2026-03-20T20:54:18.604367Z] Loop 14720: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0675 +[2026-03-20T20:54:19.458647Z] Loop 14721: Loss: 1.30e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0650 +[2026-03-20T20:54:20.312779Z] Loop 14722: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0640 +[2026-03-20T20:54:21.166549Z] Loop 14723: Loss: 1.36e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0697 +[2026-03-20T20:54:22.020967Z] Loop 14724: Loss: 1.40e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0682 +[2026-03-20T20:54:22.875291Z] Loop 14725: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0739 +[2026-03-20T20:54:23.729976Z] Loop 14726: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0737 +[2026-03-20T20:54:24.584194Z] Loop 14727: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0765 +[2026-03-20T20:54:25.438841Z] Loop 14728: Loss: 1.50e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0721 +[2026-03-20T20:54:26.293900Z] Loop 14729: Loss: 1.52e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0729 +[2026-03-20T20:54:27.191704Z] Loop 14730: Loss: 1.44e-02, Avg Return: 0.865, Regret: 0.0008, Entropy: 0.0733 +[2026-03-20T20:54:28.045578Z] Loop 14731: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0706 +[2026-03-20T20:54:28.898760Z] Loop 14732: Loss: 1.51e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0730 +[2026-03-20T20:54:29.754266Z] Loop 14733: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0718 +[2026-03-20T20:54:30.609705Z] Loop 14734: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0710 +[2026-03-20T20:54:31.463275Z] Loop 14735: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0701 +[2026-03-20T20:54:32.317824Z] Loop 14736: Loss: 1.47e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0727 +[2026-03-20T20:54:33.173130Z] Loop 14737: Loss: 1.49e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0741 +[2026-03-20T20:54:34.027756Z] Loop 14738: Loss: 1.44e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0728 +[2026-03-20T20:54:34.880914Z] Loop 14739: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0738 +[2026-03-20T20:54:35.772311Z] Loop 14740: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0725 +[2026-03-20T20:54:36.627033Z] Loop 14741: Loss: 1.50e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0747 +[2026-03-20T20:54:37.482555Z] Loop 14742: Loss: 1.47e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0707 +[2026-03-20T20:54:38.337121Z] Loop 14743: Loss: 1.24e-02, Avg Return: 0.864, Regret: 0.0013, Entropy: 0.0642 +[2026-03-20T20:54:39.192035Z] Loop 14744: Loss: 1.20e-02, Avg Return: 0.864, Regret: 0.0013, Entropy: 0.0649 +[2026-03-20T20:54:40.046252Z] Loop 14745: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0660 +[2026-03-20T20:54:40.900107Z] Loop 14746: Loss: 1.29e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0663 +[2026-03-20T20:54:41.753570Z] Loop 14747: Loss: 1.29e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0654 +[2026-03-20T20:54:42.607110Z] Loop 14748: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0698 +[2026-03-20T20:54:43.460422Z] Loop 14749: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0712 +[2026-03-20T20:54:44.353842Z] Loop 14750: Loss: 1.51e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0749 +[2026-03-20T20:54:45.207979Z] Loop 14751: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0711 +[2026-03-20T20:54:46.062962Z] Loop 14752: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0723 +[2026-03-20T20:54:46.917199Z] Loop 14753: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0720 +[2026-03-20T20:54:47.771879Z] Loop 14754: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0708 +[2026-03-20T20:54:48.627130Z] Loop 14755: Loss: 1.39e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0671 +[2026-03-20T20:54:49.482080Z] Loop 14756: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0732 +[2026-03-20T20:54:50.338411Z] Loop 14757: Loss: 1.63e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0780 +[2026-03-20T20:54:51.193011Z] Loop 14758: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0879 +[2026-03-20T20:54:52.047983Z] Loop 14759: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0825 +[2026-03-20T20:54:52.942011Z] Loop 14760: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0766 +[2026-03-20T20:54:53.796430Z] Loop 14761: Loss: 1.49e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0712 +[2026-03-20T20:54:54.650826Z] Loop 14762: Loss: 1.39e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0690 +[2026-03-20T20:54:55.503662Z] Loop 14763: Loss: 1.37e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0711 +[2026-03-20T20:54:56.356595Z] Loop 14764: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0734 +[2026-03-20T20:54:57.210330Z] Loop 14765: Loss: 1.34e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0679 +[2026-03-20T20:54:58.064114Z] Loop 14766: Loss: 1.27e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0654 +[2026-03-20T20:54:58.916932Z] Loop 14767: Loss: 1.43e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0708 +[2026-03-20T20:54:59.769704Z] Loop 14768: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0704 +[2026-03-20T20:55:00.623497Z] Loop 14769: Loss: 1.40e-02, Avg Return: 0.860, Regret: 0.0011, Entropy: 0.0729 +[2026-03-20T20:55:01.518439Z] Loop 14770: Loss: 1.49e-02, Avg Return: 0.859, Regret: 0.0036, Entropy: 0.0779 +[2026-03-20T20:55:02.372708Z] Loop 14771: Loss: 1.52e-02, Avg Return: 0.860, Regret: 0.0036, Entropy: 0.0769 +[2026-03-20T20:55:03.228630Z] Loop 14772: Loss: 1.44e-02, Avg Return: 0.861, Regret: 0.0036, Entropy: 0.0729 +[2026-03-20T20:55:04.084136Z] Loop 14773: Loss: 1.36e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.0731 +[2026-03-20T20:55:04.938906Z] Loop 14774: Loss: 1.40e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.0695 +[2026-03-20T20:55:05.792787Z] Loop 14775: Loss: 1.38e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.0680 +[2026-03-20T20:55:06.646315Z] Loop 14776: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0036, Entropy: 0.0688 +[2026-03-20T20:55:07.501591Z] Loop 14777: Loss: 1.39e-02, Avg Return: 0.862, Regret: 0.0036, Entropy: 0.0687 +[2026-03-20T20:55:08.355329Z] Loop 14778: Loss: 1.52e-02, Avg Return: 0.864, Regret: 0.0036, Entropy: 0.0698 +[2026-03-20T20:55:09.210313Z] Loop 14779: Loss: 1.46e-02, Avg Return: 0.864, Regret: 0.0036, Entropy: 0.0727 +[2026-03-20T20:55:10.103892Z] Loop 14780: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0751 +[2026-03-20T20:55:10.958518Z] Loop 14781: Loss: 1.54e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0748 +[2026-03-20T20:55:11.812152Z] Loop 14782: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0764 +[2026-03-20T20:55:12.667340Z] Loop 14783: Loss: 1.72e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0797 +[2026-03-20T20:55:13.522907Z] Loop 14784: Loss: 1.72e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0807 +[2026-03-20T20:55:14.378471Z] Loop 14785: Loss: 1.65e-02, Avg Return: 0.865, Regret: 0.0003, Entropy: 0.0783 +[2026-03-20T20:55:15.233063Z] Loop 14786: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0734 +[2026-03-20T20:55:16.087599Z] Loop 14787: Loss: 1.32e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0669 +[2026-03-20T20:55:16.941778Z] Loop 14788: Loss: 1.39e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0662 +[2026-03-20T20:55:17.796468Z] Loop 14789: Loss: 1.36e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0662 +[2026-03-20T20:55:18.689982Z] Loop 14790: Loss: 1.30e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0659 +[2026-03-20T20:55:19.543828Z] Loop 14791: Loss: 1.30e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0626 +[2026-03-20T20:55:20.398741Z] Loop 14792: Loss: 1.29e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0634 +[2026-03-20T20:55:21.252986Z] Loop 14793: Loss: 1.30e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0682 +[2026-03-20T20:55:22.108187Z] Loop 14794: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0667 +[2026-03-20T20:55:22.962286Z] Loop 14795: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0648 +[2026-03-20T20:55:23.818054Z] Loop 14796: Loss: 1.20e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0628 +[2026-03-20T20:55:24.672921Z] Loop 14797: Loss: 1.20e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0608 +[2026-03-20T20:55:25.527595Z] Loop 14798: Loss: 1.15e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0627 +[2026-03-20T20:55:26.381377Z] Loop 14799: Loss: 1.18e-02, Avg Return: 0.861, Regret: 0.0003, Entropy: 0.0622 +[2026-03-20T20:55:27.275437Z] Loop 14800: Loss: 1.30e-02, Avg Return: 0.860, Regret: 0.0036, Entropy: 0.0681 +[2026-03-20T20:55:28.130782Z] Loop 14801: Loss: 1.42e-02, Avg Return: 0.858, Regret: 0.0036, Entropy: 0.0723 +[2026-03-20T20:55:28.985006Z] Loop 14802: Loss: 1.35e-02, Avg Return: 0.859, Regret: 0.0036, Entropy: 0.0728 +[2026-03-20T20:55:29.839528Z] Loop 14803: Loss: 1.27e-02, Avg Return: 0.860, Regret: 0.0036, Entropy: 0.0706 +[2026-03-20T20:55:30.693011Z] Loop 14804: Loss: 1.15e-02, Avg Return: 0.858, Regret: 0.0036, Entropy: 0.0669 +[2026-03-20T20:55:31.546138Z] Loop 14805: Loss: 1.22e-02, Avg Return: 0.860, Regret: 0.0036, Entropy: 0.0673 +[2026-03-20T20:55:32.399799Z] Loop 14806: Loss: 1.27e-02, Avg Return: 0.858, Regret: 0.0036, Entropy: 0.0676 +[2026-03-20T20:55:33.254270Z] Loop 14807: Loss: 1.25e-02, Avg Return: 0.858, Regret: 0.0036, Entropy: 0.0655 +[2026-03-20T20:55:34.107402Z] Loop 14808: Loss: 1.27e-02, Avg Return: 0.860, Regret: 0.0036, Entropy: 0.0648 +[2026-03-20T20:55:34.960863Z] Loop 14809: Loss: 1.19e-02, Avg Return: 0.860, Regret: 0.0036, Entropy: 0.0654 +[2026-03-20T20:55:35.855983Z] Loop 14810: Loss: 1.08e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.0615 +[2026-03-20T20:55:36.711275Z] Loop 14811: Loss: 1.05e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.0558 +[2026-03-20T20:55:37.565332Z] Loop 14812: Loss: 1.03e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.0544 +[2026-03-20T20:55:38.419735Z] Loop 14813: Loss: 1.09e-02, Avg Return: 0.863, Regret: 0.0028, Entropy: 0.0599 +[2026-03-20T20:55:39.274247Z] Loop 14814: Loss: 1.09e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.0574 +[2026-03-20T20:55:40.129229Z] Loop 14815: Loss: 1.10e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.0563 +[2026-03-20T20:55:40.984560Z] Loop 14816: Loss: 1.07e-02, Avg Return: 0.864, Regret: 0.0028, Entropy: 0.0602 +[2026-03-20T20:55:41.840530Z] Loop 14817: Loss: 1.12e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.0579 +[2026-03-20T20:55:42.694669Z] Loop 14818: Loss: 1.20e-02, Avg Return: 0.863, Regret: 0.0028, Entropy: 0.0621 +[2026-03-20T20:55:43.549591Z] Loop 14819: Loss: 1.10e-02, Avg Return: 0.865, Regret: 0.0028, Entropy: 0.0565 +[2026-03-20T20:55:44.444846Z] Loop 14820: Loss: 1.09e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0577 +[2026-03-20T20:55:45.300035Z] Loop 14821: Loss: 1.13e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0617 +[2026-03-20T20:55:46.153650Z] Loop 14822: Loss: 1.14e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0578 +[2026-03-20T20:55:47.007944Z] Loop 14823: Loss: 1.09e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0587 +[2026-03-20T20:55:47.862833Z] Loop 14824: Loss: 1.15e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0586 +[2026-03-20T20:55:48.717812Z] Loop 14825: Loss: 1.06e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0559 +[2026-03-20T20:55:49.572321Z] Loop 14826: Loss: 1.14e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0605 +[2026-03-20T20:55:50.426306Z] Loop 14827: Loss: 1.20e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0628 +[2026-03-20T20:55:51.280811Z] Loop 14828: Loss: 1.31e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0639 +[2026-03-20T20:55:52.135265Z] Loop 14829: Loss: 1.10e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0575 +[2026-03-20T20:55:53.028373Z] Loop 14830: Loss: 1.09e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0617 +[2026-03-20T20:55:53.883964Z] Loop 14831: Loss: 1.32e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0662 +[2026-03-20T20:55:54.738290Z] Loop 14832: Loss: 1.25e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0626 +[2026-03-20T20:55:55.592543Z] Loop 14833: Loss: 1.18e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0637 +[2026-03-20T20:55:56.447080Z] Loop 14834: Loss: 1.17e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0638 +[2026-03-20T20:55:57.300997Z] Loop 14835: Loss: 1.07e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0596 +[2026-03-20T20:55:58.155593Z] Loop 14836: Loss: 1.23e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0612 +[2026-03-20T20:55:59.010805Z] Loop 14837: Loss: 1.19e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0613 +[2026-03-20T20:55:59.865044Z] Loop 14838: Loss: 1.12e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0603 +[2026-03-20T20:56:00.719650Z] Loop 14839: Loss: 1.17e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0643 +[2026-03-20T20:56:01.615012Z] Loop 14840: Loss: 1.16e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0639 +[2026-03-20T20:56:02.469849Z] Loop 14841: Loss: 1.26e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0626 +[2026-03-20T20:56:03.325302Z] Loop 14842: Loss: 1.27e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0629 +[2026-03-20T20:56:04.182102Z] Loop 14843: Loss: 1.18e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0644 +[2026-03-20T20:56:05.037910Z] Loop 14844: Loss: 1.22e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0632 +[2026-03-20T20:56:05.894104Z] Loop 14845: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0659 +[2026-03-20T20:56:06.749820Z] Loop 14846: Loss: 1.14e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0598 +[2026-03-20T20:56:07.605216Z] Loop 14847: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0607 +[2026-03-20T20:56:08.460627Z] Loop 14848: Loss: 1.16e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0617 +[2026-03-20T20:56:09.316715Z] Loop 14849: Loss: 1.17e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0656 +[2026-03-20T20:56:10.213051Z] Loop 14850: Loss: 1.27e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0661 +[2026-03-20T20:56:11.068925Z] Loop 14851: Loss: 1.20e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0636 +[2026-03-20T20:56:11.924532Z] Loop 14852: Loss: 1.23e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0643 +[2026-03-20T20:56:12.779628Z] Loop 14853: Loss: 1.18e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0639 +[2026-03-20T20:56:13.635029Z] Loop 14854: Loss: 1.22e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0641 +[2026-03-20T20:56:14.490274Z] Loop 14855: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0632 +[2026-03-20T20:56:15.344653Z] Loop 14856: Loss: 1.26e-02, Avg Return: 0.865, Regret: 0.0004, Entropy: 0.0668 +[2026-03-20T20:56:16.202149Z] Loop 14857: Loss: 1.28e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0669 +[2026-03-20T20:56:17.056914Z] Loop 14858: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0676 +[2026-03-20T20:56:17.911957Z] Loop 14859: Loss: 1.28e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0672 +[2026-03-20T20:56:18.807971Z] Loop 14860: Loss: 1.30e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0670 +[2026-03-20T20:56:19.663108Z] Loop 14861: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0736 +[2026-03-20T20:56:20.517882Z] Loop 14862: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0746 +[2026-03-20T20:56:21.373093Z] Loop 14863: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0735 +[2026-03-20T20:56:22.228427Z] Loop 14864: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0756 +[2026-03-20T20:56:23.090124Z] Loop 14865: Loss: 1.45e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0731 +[2026-03-20T20:56:23.950506Z] Loop 14866: Loss: 1.47e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0755 +[2026-03-20T20:56:24.805112Z] Loop 14867: Loss: 1.45e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0745 +[2026-03-20T20:56:25.657907Z] Loop 14868: Loss: 1.43e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0701 +[2026-03-20T20:56:26.511114Z] Loop 14869: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0711 +[2026-03-20T20:56:27.404571Z] Loop 14870: Loss: 1.20e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0662 +[2026-03-20T20:56:28.258883Z] Loop 14871: Loss: 1.18e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0622 +[2026-03-20T20:56:29.113301Z] Loop 14872: Loss: 1.15e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0624 +[2026-03-20T20:56:29.967395Z] Loop 14873: Loss: 1.22e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0633 +[2026-03-20T20:56:30.821518Z] Loop 14874: Loss: 1.16e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0628 +[2026-03-20T20:56:31.676724Z] Loop 14875: Loss: 1.13e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0620 +[2026-03-20T20:56:32.531024Z] Loop 14876: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0647 +[2026-03-20T20:56:33.385143Z] Loop 14877: Loss: 1.15e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0595 +[2026-03-20T20:56:34.238960Z] Loop 14878: Loss: 1.16e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0601 +[2026-03-20T20:56:35.092938Z] Loop 14879: Loss: 1.18e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0608 +[2026-03-20T20:56:35.987172Z] Loop 14880: Loss: 1.21e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0647 +[2026-03-20T20:56:36.840544Z] Loop 14881: Loss: 1.18e-02, Avg Return: 0.865, Regret: 0.0009, Entropy: 0.0640 +[2026-03-20T20:56:37.694408Z] Loop 14882: Loss: 1.11e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0606 +[2026-03-20T20:56:38.548076Z] Loop 14883: Loss: 1.12e-02, Avg Return: 0.865, Regret: 0.0009, Entropy: 0.0620 +[2026-03-20T20:56:39.402404Z] Loop 14884: Loss: 1.14e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0597 +[2026-03-20T20:56:40.257094Z] Loop 14885: Loss: 1.24e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0652 +[2026-03-20T20:56:41.111956Z] Loop 14886: Loss: 1.29e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0643 +[2026-03-20T20:56:41.966122Z] Loop 14887: Loss: 1.15e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0602 +[2026-03-20T20:56:42.821194Z] Loop 14888: Loss: 1.18e-02, Avg Return: 0.865, Regret: 0.0009, Entropy: 0.0627 +[2026-03-20T20:56:43.676080Z] Loop 14889: Loss: 1.21e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0642 +[2026-03-20T20:56:44.570624Z] Loop 14890: Loss: 1.28e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0678 +[2026-03-20T20:56:45.424666Z] Loop 14891: Loss: 1.24e-02, Avg Return: 0.865, Regret: 0.0004, Entropy: 0.0641 +[2026-03-20T20:56:46.278944Z] Loop 14892: Loss: 1.10e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0601 +[2026-03-20T20:56:47.133293Z] Loop 14893: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0628 +[2026-03-20T20:56:47.987288Z] Loop 14894: Loss: 1.13e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0626 +[2026-03-20T20:56:48.841450Z] Loop 14895: Loss: 1.24e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0616 +[2026-03-20T20:56:49.695979Z] Loop 14896: Loss: 1.26e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0680 +[2026-03-20T20:56:50.550734Z] Loop 14897: Loss: 1.24e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0667 +[2026-03-20T20:56:51.405004Z] Loop 14898: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0642 +[2026-03-20T20:56:52.259972Z] Loop 14899: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0630 +[2026-03-20T20:56:53.152820Z] Loop 14900: Loss: 1.14e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0607 +[2026-03-20T20:56:54.006354Z] Loop 14901: Loss: 1.15e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0629 +[2026-03-20T20:56:54.860553Z] Loop 14902: Loss: 1.17e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0591 +[2026-03-20T20:56:55.715107Z] Loop 14903: Loss: 1.12e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0608 +[2026-03-20T20:56:56.569248Z] Loop 14904: Loss: 1.19e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0644 +[2026-03-20T20:56:57.423256Z] Loop 14905: Loss: 1.23e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0634 +[2026-03-20T20:56:58.278263Z] Loop 14906: Loss: 1.29e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0674 +[2026-03-20T20:56:59.133319Z] Loop 14907: Loss: 1.23e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0636 +[2026-03-20T20:56:59.987418Z] Loop 14908: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0700 +[2026-03-20T20:57:00.840567Z] Loop 14909: Loss: 1.33e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0710 +[2026-03-20T20:57:01.733243Z] Loop 14910: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.0811 +[2026-03-20T20:57:02.588096Z] Loop 14911: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.0779 +[2026-03-20T20:57:03.442558Z] Loop 14912: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0803 +[2026-03-20T20:57:04.297889Z] Loop 14913: Loss: 1.64e-02, Avg Return: 0.860, Regret: 0.0020, Entropy: 0.0824 +[2026-03-20T20:57:05.152567Z] Loop 14914: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0832 +[2026-03-20T20:57:06.008429Z] Loop 14915: Loss: 1.68e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.0849 +[2026-03-20T20:57:06.863213Z] Loop 14916: Loss: 1.89e-02, Avg Return: 0.859, Regret: 0.0020, Entropy: 0.0898 +[2026-03-20T20:57:07.718371Z] Loop 14917: Loss: 1.82e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0893 +[2026-03-20T20:57:08.571784Z] Loop 14918: Loss: 2.12e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0992 +[2026-03-20T20:57:09.427231Z] Loop 14919: Loss: 1.98e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0946 +[2026-03-20T20:57:10.322882Z] Loop 14920: Loss: 1.98e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0909 +[2026-03-20T20:57:11.177869Z] Loop 14921: Loss: 1.87e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0896 +[2026-03-20T20:57:12.032124Z] Loop 14922: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0804 +[2026-03-20T20:57:12.885897Z] Loop 14923: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0781 +[2026-03-20T20:57:13.739840Z] Loop 14924: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0767 +[2026-03-20T20:57:14.594307Z] Loop 14925: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0782 +[2026-03-20T20:57:15.449419Z] Loop 14926: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0772 +[2026-03-20T20:57:16.302957Z] Loop 14927: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0790 +[2026-03-20T20:57:17.156098Z] Loop 14928: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0771 +[2026-03-20T20:57:18.009650Z] Loop 14929: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0018, Entropy: 0.0779 +[2026-03-20T20:57:18.904215Z] Loop 14930: Loss: 1.47e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0757 +[2026-03-20T20:57:19.759368Z] Loop 14931: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0783 +[2026-03-20T20:57:20.612850Z] Loop 14932: Loss: 1.65e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0815 +[2026-03-20T20:57:21.466638Z] Loop 14933: Loss: 1.53e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0768 +[2026-03-20T20:57:22.321356Z] Loop 14934: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0742 +[2026-03-20T20:57:23.176422Z] Loop 14935: Loss: 1.53e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0778 +[2026-03-20T20:57:24.030524Z] Loop 14936: Loss: 1.52e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0777 +[2026-03-20T20:57:24.885462Z] Loop 14937: Loss: 1.54e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0789 +[2026-03-20T20:57:25.741272Z] Loop 14938: Loss: 1.57e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0778 +[2026-03-20T20:57:26.597227Z] Loop 14939: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0783 +[2026-03-20T20:57:27.490229Z] Loop 14940: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0797 +[2026-03-20T20:57:28.343272Z] Loop 14941: Loss: 1.67e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0860 +[2026-03-20T20:57:29.197443Z] Loop 14942: Loss: 1.75e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0877 +[2026-03-20T20:57:30.051423Z] Loop 14943: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0877 +[2026-03-20T20:57:30.905963Z] Loop 14944: Loss: 1.76e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0921 +[2026-03-20T20:57:31.759595Z] Loop 14945: Loss: 1.94e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0966 +[2026-03-20T20:57:32.613706Z] Loop 14946: Loss: 2.07e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.1030 +[2026-03-20T20:57:33.467896Z] Loop 14947: Loss: 2.12e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.1063 +[2026-03-20T20:57:34.322350Z] Loop 14948: Loss: 1.97e-02, Avg Return: 0.859, Regret: 0.0010, Entropy: 0.1062 +[2026-03-20T20:57:35.176322Z] Loop 14949: Loss: 2.14e-02, Avg Return: 0.860, Regret: 0.0010, Entropy: 0.1099 +[2026-03-20T20:57:36.069472Z] Loop 14950: Loss: 2.37e-02, Avg Return: 0.860, Regret: 0.0028, Entropy: 0.1174 +[2026-03-20T20:57:36.922625Z] Loop 14951: Loss: 2.42e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.1179 +[2026-03-20T20:57:37.776278Z] Loop 14952: Loss: 2.46e-02, Avg Return: 0.861, Regret: 0.0028, Entropy: 0.1220 +[2026-03-20T20:57:38.630799Z] Loop 14953: Loss: 2.46e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.1244 +[2026-03-20T20:57:39.484345Z] Loop 14954: Loss: 2.50e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.1247 +[2026-03-20T20:57:40.337522Z] Loop 14955: Loss: 2.33e-02, Avg Return: 0.863, Regret: 0.0028, Entropy: 0.1188 +[2026-03-20T20:57:41.190788Z] Loop 14956: Loss: 2.22e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.1193 +[2026-03-20T20:57:42.045030Z] Loop 14957: Loss: 2.18e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.1141 +[2026-03-20T20:57:42.899608Z] Loop 14958: Loss: 2.09e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.1056 +[2026-03-20T20:57:43.752860Z] Loop 14959: Loss: 1.99e-02, Avg Return: 0.862, Regret: 0.0028, Entropy: 0.1058 +[2026-03-20T20:57:44.645020Z] Loop 14960: Loss: 2.13e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.1036 +[2026-03-20T20:57:45.499787Z] Loop 14961: Loss: 2.00e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.1047 +[2026-03-20T20:57:46.354907Z] Loop 14962: Loss: 2.21e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.1037 +[2026-03-20T20:57:47.209515Z] Loop 14963: Loss: 1.98e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.1021 +[2026-03-20T20:57:48.062485Z] Loop 14964: Loss: 2.00e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.1033 +[2026-03-20T20:57:48.917062Z] Loop 14965: Loss: 2.04e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.1035 +[2026-03-20T20:57:49.770243Z] Loop 14966: Loss: 2.02e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.1018 +[2026-03-20T20:57:50.624765Z] Loop 14967: Loss: 1.97e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0972 +[2026-03-20T20:57:51.478959Z] Loop 14968: Loss: 1.98e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.1006 +[2026-03-20T20:57:52.333952Z] Loop 14969: Loss: 1.94e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0966 +[2026-03-20T20:57:53.227232Z] Loop 14970: Loss: 1.94e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.1010 +[2026-03-20T20:57:54.081741Z] Loop 14971: Loss: 1.98e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.1008 +[2026-03-20T20:57:54.936502Z] Loop 14972: Loss: 2.14e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.1027 +[2026-03-20T20:57:55.791564Z] Loop 14973: Loss: 2.15e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.1044 +[2026-03-20T20:57:56.646561Z] Loop 14974: Loss: 2.07e-02, Avg Return: 0.865, Regret: 0.0009, Entropy: 0.1006 +[2026-03-20T20:57:57.500993Z] Loop 14975: Loss: 2.17e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.1034 +[2026-03-20T20:57:58.356249Z] Loop 14976: Loss: 2.10e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0956 +[2026-03-20T20:57:59.210323Z] Loop 14977: Loss: 2.11e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0957 +[2026-03-20T20:58:00.064131Z] Loop 14978: Loss: 2.15e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.1032 +[2026-03-20T20:58:00.918685Z] Loop 14979: Loss: 2.21e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.1024 +[2026-03-20T20:58:01.813247Z] Loop 14980: Loss: 2.08e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.1007 +[2026-03-20T20:58:02.667069Z] Loop 14981: Loss: 2.17e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0991 +[2026-03-20T20:58:03.519972Z] Loop 14982: Loss: 2.07e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0983 +[2026-03-20T20:58:04.374358Z] Loop 14983: Loss: 2.08e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0965 +[2026-03-20T20:58:05.228349Z] Loop 14984: Loss: 2.07e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.1002 +[2026-03-20T20:58:06.081763Z] Loop 14985: Loss: 2.18e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.1006 +[2026-03-20T20:58:06.934917Z] Loop 14986: Loss: 1.71e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0841 +[2026-03-20T20:58:07.787775Z] Loop 14987: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0780 +[2026-03-20T20:58:08.641697Z] Loop 14988: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0786 +[2026-03-20T20:58:09.496392Z] Loop 14989: Loss: 1.52e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0765 +[2026-03-20T20:58:10.387898Z] Loop 14990: Loss: 1.61e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0781 +[2026-03-20T20:58:11.241325Z] Loop 14991: Loss: 1.56e-02, Avg Return: 0.865, Regret: 0.0001, Entropy: 0.0755 +[2026-03-20T20:58:12.094633Z] Loop 14992: Loss: 1.42e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0735 +[2026-03-20T20:58:12.949280Z] Loop 14993: Loss: 1.50e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0748 +[2026-03-20T20:58:13.802806Z] Loop 14994: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0759 +[2026-03-20T20:58:14.656737Z] Loop 14995: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0772 +[2026-03-20T20:58:15.510667Z] Loop 14996: Loss: 1.48e-02, Avg Return: 0.861, Regret: 0.0001, Entropy: 0.0741 +[2026-03-20T20:58:16.365118Z] Loop 14997: Loss: 1.52e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0787 +[2026-03-20T20:58:17.219186Z] Loop 14998: Loss: 1.54e-02, Avg Return: 0.860, Regret: 0.0001, Entropy: 0.0822 +[2026-03-20T20:58:18.073585Z] Loop 14999: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0836 +[2026-03-20T20:58:18.966596Z] Loop 15000: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0741 +[2026-03-20T20:58:19.820142Z] Loop 15001: Loss: 1.46e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0743 +[2026-03-20T20:58:20.674815Z] Loop 15002: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0704 +[2026-03-20T20:58:21.528996Z] Loop 15003: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0744 +[2026-03-20T20:58:22.382907Z] Loop 15004: Loss: 1.36e-02, Avg Return: 0.864, Regret: 0.0014, Entropy: 0.0707 +[2026-03-20T20:58:23.236853Z] Loop 15005: Loss: 1.29e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0680 +[2026-03-20T20:58:24.091879Z] Loop 15006: Loss: 1.39e-02, Avg Return: 0.864, Regret: 0.0014, Entropy: 0.0691 +[2026-03-20T20:58:24.946883Z] Loop 15007: Loss: 1.39e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0693 +[2026-03-20T20:58:25.800897Z] Loop 15008: Loss: 1.44e-02, Avg Return: 0.864, Regret: 0.0014, Entropy: 0.0721 +[2026-03-20T20:58:26.655091Z] Loop 15009: Loss: 1.33e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0693 +[2026-03-20T20:58:27.549431Z] Loop 15010: Loss: 1.39e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0707 +[2026-03-20T20:58:28.403526Z] Loop 15011: Loss: 1.29e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0647 +[2026-03-20T20:58:29.258181Z] Loop 15012: Loss: 1.23e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0634 +[2026-03-20T20:58:30.112355Z] Loop 15013: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0643 +[2026-03-20T20:58:30.965969Z] Loop 15014: Loss: 1.12e-02, Avg Return: 0.866, Regret: 0.0001, Entropy: 0.0600 +[2026-03-20T20:58:31.820133Z] Loop 15015: Loss: 1.22e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0613 +[2026-03-20T20:58:32.674682Z] Loop 15016: Loss: 1.17e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0627 +[2026-03-20T20:58:33.528924Z] Loop 15017: Loss: 1.20e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0652 +[2026-03-20T20:58:34.382251Z] Loop 15018: Loss: 1.17e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0620 +[2026-03-20T20:58:35.235400Z] Loop 15019: Loss: 1.17e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0608 +[2026-03-20T20:58:36.131080Z] Loop 15020: Loss: 1.10e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0609 +[2026-03-20T20:58:36.986405Z] Loop 15021: Loss: 1.21e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0671 +[2026-03-20T20:58:37.841086Z] Loop 15022: Loss: 1.12e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0599 +[2026-03-20T20:58:38.694694Z] Loop 15023: Loss: 1.13e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0615 +[2026-03-20T20:58:39.549519Z] Loop 15024: Loss: 1.11e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0553 +[2026-03-20T20:58:40.403467Z] Loop 15025: Loss: 1.21e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0630 +[2026-03-20T20:58:41.258221Z] Loop 15026: Loss: 1.16e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0619 +[2026-03-20T20:58:42.112178Z] Loop 15027: Loss: 1.16e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0632 +[2026-03-20T20:58:42.966175Z] Loop 15028: Loss: 1.22e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0652 +[2026-03-20T20:58:43.819853Z] Loop 15029: Loss: 1.12e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0597 +[2026-03-20T20:58:44.712522Z] Loop 15030: Loss: 1.11e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0608 +[2026-03-20T20:58:45.566816Z] Loop 15031: Loss: 1.16e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0583 +[2026-03-20T20:58:46.422659Z] Loop 15032: Loss: 1.12e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0629 +[2026-03-20T20:58:47.276713Z] Loop 15033: Loss: 1.15e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0612 +[2026-03-20T20:58:48.130869Z] Loop 15034: Loss: 1.19e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0637 +[2026-03-20T20:58:48.984734Z] Loop 15035: Loss: 1.19e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0641 +[2026-03-20T20:58:49.838584Z] Loop 15036: Loss: 1.16e-02, Avg Return: 0.861, Regret: 0.0005, Entropy: 0.0605 +[2026-03-20T20:58:50.692528Z] Loop 15037: Loss: 1.23e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0619 +[2026-03-20T20:58:51.546441Z] Loop 15038: Loss: 1.23e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0638 +[2026-03-20T20:58:52.400970Z] Loop 15039: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0640 +[2026-03-20T20:58:53.296238Z] Loop 15040: Loss: 1.19e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0639 +[2026-03-20T20:58:54.150366Z] Loop 15041: Loss: 1.28e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0654 +[2026-03-20T20:58:55.004473Z] Loop 15042: Loss: 1.25e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0666 +[2026-03-20T20:58:55.860086Z] Loop 15043: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0634 +[2026-03-20T20:58:56.715990Z] Loop 15044: Loss: 1.27e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0675 +[2026-03-20T20:58:57.569247Z] Loop 15045: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0676 +[2026-03-20T20:58:58.422927Z] Loop 15046: Loss: 1.33e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0662 +[2026-03-20T20:58:59.278009Z] Loop 15047: Loss: 1.41e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0708 +[2026-03-20T20:59:00.132657Z] Loop 15048: Loss: 1.42e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0705 +[2026-03-20T20:59:00.987195Z] Loop 15049: Loss: 1.40e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0709 +[2026-03-20T20:59:01.881258Z] Loop 15050: Loss: 1.45e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0743 +[2026-03-20T20:59:02.735792Z] Loop 15051: Loss: 1.38e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0698 +[2026-03-20T20:59:03.590497Z] Loop 15052: Loss: 1.36e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0723 +[2026-03-20T20:59:04.443958Z] Loop 15053: Loss: 1.44e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0735 +[2026-03-20T20:59:05.297610Z] Loop 15054: Loss: 1.42e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0733 +[2026-03-20T20:59:06.152813Z] Loop 15055: Loss: 1.38e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0682 +[2026-03-20T20:59:07.006732Z] Loop 15056: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0749 +[2026-03-20T20:59:07.860037Z] Loop 15057: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0018, Entropy: 0.0731 +[2026-03-20T20:59:08.713367Z] Loop 15058: Loss: 1.50e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0761 +[2026-03-20T20:59:09.566817Z] Loop 15059: Loss: 1.46e-02, Avg Return: 0.861, Regret: 0.0018, Entropy: 0.0754 +[2026-03-20T20:59:10.461125Z] Loop 15060: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0752 +[2026-03-20T20:59:11.315309Z] Loop 15061: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0778 +[2026-03-20T20:59:12.169161Z] Loop 15062: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0759 +[2026-03-20T20:59:13.022930Z] Loop 15063: Loss: 1.54e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0762 +[2026-03-20T20:59:13.877291Z] Loop 15064: Loss: 1.52e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0766 +[2026-03-20T20:59:14.732419Z] Loop 15065: Loss: 1.63e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0798 +[2026-03-20T20:59:15.587629Z] Loop 15066: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0793 +[2026-03-20T20:59:16.442408Z] Loop 15067: Loss: 1.67e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0827 +[2026-03-20T20:59:17.296628Z] Loop 15068: Loss: 1.87e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0850 +[2026-03-20T20:59:18.151501Z] Loop 15069: Loss: 1.69e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0840 +[2026-03-20T20:59:19.046130Z] Loop 15070: Loss: 1.77e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.0877 +[2026-03-20T20:59:19.901083Z] Loop 15071: Loss: 1.65e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.0857 +[2026-03-20T20:59:20.755311Z] Loop 15072: Loss: 1.71e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.0870 +[2026-03-20T20:59:21.610342Z] Loop 15073: Loss: 1.79e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0874 +[2026-03-20T20:59:22.464729Z] Loop 15074: Loss: 1.75e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.0919 +[2026-03-20T20:59:23.318973Z] Loop 15075: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0953 +[2026-03-20T20:59:24.173538Z] Loop 15076: Loss: 2.01e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.0990 +[2026-03-20T20:59:25.026636Z] Loop 15077: Loss: 2.18e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.1062 +[2026-03-20T20:59:25.879441Z] Loop 15078: Loss: 2.13e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.1044 +[2026-03-20T20:59:26.734839Z] Loop 15079: Loss: 2.10e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0996 +[2026-03-20T20:59:27.627154Z] Loop 15080: Loss: 1.80e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0882 +[2026-03-20T20:59:28.481966Z] Loop 15081: Loss: 1.73e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0864 +[2026-03-20T20:59:29.335575Z] Loop 15082: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0816 +[2026-03-20T20:59:30.190204Z] Loop 15083: Loss: 1.64e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0841 +[2026-03-20T20:59:31.044318Z] Loop 15084: Loss: 1.66e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0839 +[2026-03-20T20:59:31.898303Z] Loop 15085: Loss: 1.60e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0823 +[2026-03-20T20:59:32.751810Z] Loop 15086: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0814 +[2026-03-20T20:59:33.606247Z] Loop 15087: Loss: 1.64e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0832 +[2026-03-20T20:59:34.460076Z] Loop 15088: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0818 +[2026-03-20T20:59:35.313745Z] Loop 15089: Loss: 1.53e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0786 +[2026-03-20T20:59:36.206449Z] Loop 15090: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0803 +[2026-03-20T20:59:37.060917Z] Loop 15091: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0812 +[2026-03-20T20:59:37.914360Z] Loop 15092: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0804 +[2026-03-20T20:59:38.768387Z] Loop 15093: Loss: 1.54e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0777 +[2026-03-20T20:59:39.621959Z] Loop 15094: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0790 +[2026-03-20T20:59:40.477387Z] Loop 15095: Loss: 1.76e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0825 +[2026-03-20T20:59:41.332039Z] Loop 15096: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0819 +[2026-03-20T20:59:42.186179Z] Loop 15097: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0773 +[2026-03-20T20:59:43.041182Z] Loop 15098: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0798 +[2026-03-20T20:59:43.896678Z] Loop 15099: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0781 +[2026-03-20T20:59:44.789339Z] Loop 15100: Loss: 1.60e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0778 +[2026-03-20T20:59:45.643490Z] Loop 15101: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0813 +[2026-03-20T20:59:46.499692Z] Loop 15102: Loss: 1.64e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0825 +[2026-03-20T20:59:47.355794Z] Loop 15103: Loss: 1.56e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0791 +[2026-03-20T20:59:48.210932Z] Loop 15104: Loss: 1.47e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0759 +[2026-03-20T20:59:49.065603Z] Loop 15105: Loss: 1.46e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0757 +[2026-03-20T20:59:49.920038Z] Loop 15106: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0777 +[2026-03-20T20:59:50.775902Z] Loop 15107: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0762 +[2026-03-20T20:59:51.630608Z] Loop 15108: Loss: 1.54e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0805 +[2026-03-20T20:59:52.484938Z] Loop 15109: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0813 +[2026-03-20T20:59:53.396817Z] Loop 15110: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0017, Entropy: 0.0817 +[2026-03-20T20:59:54.253134Z] Loop 15111: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0805 +[2026-03-20T20:59:55.106875Z] Loop 15112: Loss: 1.68e-02, Avg Return: 0.862, Regret: 0.0017, Entropy: 0.0855 +[2026-03-20T20:59:55.960900Z] Loop 15113: Loss: 1.62e-02, Avg Return: 0.864, Regret: 0.0017, Entropy: 0.0854 +[2026-03-20T20:59:56.815137Z] Loop 15114: Loss: 1.60e-02, Avg Return: 0.864, Regret: 0.0017, Entropy: 0.0845 +[2026-03-20T20:59:57.669571Z] Loop 15115: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0017, Entropy: 0.0844 +[2026-03-20T20:59:58.523789Z] Loop 15116: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0017, Entropy: 0.0857 +[2026-03-20T20:59:59.377882Z] Loop 15117: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0017, Entropy: 0.0799 +[2026-03-20T21:00:00.231562Z] Loop 15118: Loss: 1.59e-02, Avg Return: 0.864, Regret: 0.0017, Entropy: 0.0805 +[2026-03-20T21:00:01.085462Z] Loop 15119: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0017, Entropy: 0.0822 +[2026-03-20T21:00:01.983830Z] Loop 15120: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0845 +[2026-03-20T21:00:02.839537Z] Loop 15121: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0820 +[2026-03-20T21:00:03.694821Z] Loop 15122: Loss: 1.64e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0808 +[2026-03-20T21:00:04.550202Z] Loop 15123: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0806 +[2026-03-20T21:00:05.404230Z] Loop 15124: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0771 +[2026-03-20T21:00:06.257973Z] Loop 15125: Loss: 1.47e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0755 +[2026-03-20T21:00:07.111963Z] Loop 15126: Loss: 1.48e-02, Avg Return: 0.865, Regret: 0.0003, Entropy: 0.0728 +[2026-03-20T21:00:07.965417Z] Loop 15127: Loss: 1.42e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0737 +[2026-03-20T21:00:08.818798Z] Loop 15128: Loss: 1.37e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0702 +[2026-03-20T21:00:09.672384Z] Loop 15129: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0681 +[2026-03-20T21:00:10.564456Z] Loop 15130: Loss: 1.43e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0744 +[2026-03-20T21:00:11.419275Z] Loop 15131: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0710 +[2026-03-20T21:00:12.273462Z] Loop 15132: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0702 +[2026-03-20T21:00:13.129804Z] Loop 15133: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0730 +[2026-03-20T21:00:13.983917Z] Loop 15134: Loss: 1.30e-02, Avg Return: 0.865, Regret: 0.0002, Entropy: 0.0695 +[2026-03-20T21:00:14.838400Z] Loop 15135: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0678 +[2026-03-20T21:00:15.691197Z] Loop 15136: Loss: 1.26e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0679 +[2026-03-20T21:00:16.543851Z] Loop 15137: Loss: 1.43e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0702 +[2026-03-20T21:00:17.398313Z] Loop 15138: Loss: 1.41e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0709 +[2026-03-20T21:00:18.253683Z] Loop 15139: Loss: 1.33e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0690 +[2026-03-20T21:00:19.148107Z] Loop 15140: Loss: 1.33e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0704 +[2026-03-20T21:00:20.002354Z] Loop 15141: Loss: 1.31e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0716 +[2026-03-20T21:00:20.856890Z] Loop 15142: Loss: 1.28e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0651 +[2026-03-20T21:00:21.711160Z] Loop 15143: Loss: 1.15e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0617 +[2026-03-20T21:00:22.565426Z] Loop 15144: Loss: 1.03e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0581 +[2026-03-20T21:00:23.418793Z] Loop 15145: Loss: 1.14e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.0643 +[2026-03-20T21:00:24.271619Z] Loop 15146: Loss: 1.33e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0670 +[2026-03-20T21:00:25.125370Z] Loop 15147: Loss: 1.31e-02, Avg Return: 0.860, Regret: 0.0006, Entropy: 0.0658 +[2026-03-20T21:00:25.978733Z] Loop 15148: Loss: 1.29e-02, Avg Return: 0.859, Regret: 0.0006, Entropy: 0.0638 +[2026-03-20T21:00:26.833370Z] Loop 15149: Loss: 1.41e-02, Avg Return: 0.859, Regret: 0.0006, Entropy: 0.0731 +[2026-03-20T21:00:27.725517Z] Loop 15150: Loss: 1.42e-02, Avg Return: 0.859, Regret: 0.0052, Entropy: 0.0727 +[2026-03-20T21:00:28.580074Z] Loop 15151: Loss: 1.28e-02, Avg Return: 0.859, Regret: 0.0052, Entropy: 0.0662 +[2026-03-20T21:00:29.434482Z] Loop 15152: Loss: 1.34e-02, Avg Return: 0.859, Regret: 0.0052, Entropy: 0.0675 +[2026-03-20T21:00:30.288470Z] Loop 15153: Loss: 1.13e-02, Avg Return: 0.862, Regret: 0.0052, Entropy: 0.0624 +[2026-03-20T21:00:31.142365Z] Loop 15154: Loss: 1.18e-02, Avg Return: 0.861, Regret: 0.0052, Entropy: 0.0628 +[2026-03-20T21:00:31.996482Z] Loop 15155: Loss: 1.24e-02, Avg Return: 0.862, Regret: 0.0052, Entropy: 0.0641 +[2026-03-20T21:00:32.850353Z] Loop 15156: Loss: 1.16e-02, Avg Return: 0.862, Regret: 0.0052, Entropy: 0.0646 +[2026-03-20T21:00:33.703891Z] Loop 15157: Loss: 1.16e-02, Avg Return: 0.861, Regret: 0.0052, Entropy: 0.0624 +[2026-03-20T21:00:34.557511Z] Loop 15158: Loss: 1.14e-02, Avg Return: 0.862, Regret: 0.0052, Entropy: 0.0601 +[2026-03-20T21:00:35.410799Z] Loop 15159: Loss: 1.22e-02, Avg Return: 0.863, Regret: 0.0052, Entropy: 0.0623 +[2026-03-20T21:00:36.303463Z] Loop 15160: Loss: 1.16e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0617 +[2026-03-20T21:00:37.157585Z] Loop 15161: Loss: 1.19e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0619 +[2026-03-20T21:00:38.013485Z] Loop 15162: Loss: 1.25e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0633 +[2026-03-20T21:00:38.867254Z] Loop 15163: Loss: 1.27e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0649 +[2026-03-20T21:00:39.720634Z] Loop 15164: Loss: 1.32e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0654 +[2026-03-20T21:00:40.575173Z] Loop 15165: Loss: 1.21e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0630 +[2026-03-20T21:00:41.430142Z] Loop 15166: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0630 +[2026-03-20T21:00:42.285016Z] Loop 15167: Loss: 1.43e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0714 +[2026-03-20T21:00:43.138786Z] Loop 15168: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0718 +[2026-03-20T21:00:43.993150Z] Loop 15169: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0728 +[2026-03-20T21:00:44.886594Z] Loop 15170: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0744 +[2026-03-20T21:00:45.741376Z] Loop 15171: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0728 +[2026-03-20T21:00:46.594964Z] Loop 15172: Loss: 1.54e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0744 +[2026-03-20T21:00:47.448534Z] Loop 15173: Loss: 1.57e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0733 +[2026-03-20T21:00:48.304011Z] Loop 15174: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0752 +[2026-03-20T21:00:49.158938Z] Loop 15175: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0748 +[2026-03-20T21:00:50.013401Z] Loop 15176: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0701 +[2026-03-20T21:00:50.868140Z] Loop 15177: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0716 +[2026-03-20T21:00:51.723598Z] Loop 15178: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0752 +[2026-03-20T21:00:52.579008Z] Loop 15179: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0747 +[2026-03-20T21:00:53.473431Z] Loop 15180: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0725 +[2026-03-20T21:00:54.327612Z] Loop 15181: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0776 +[2026-03-20T21:00:55.181391Z] Loop 15182: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0734 +[2026-03-20T21:00:56.034898Z] Loop 15183: Loss: 1.49e-02, Avg Return: 0.864, Regret: 0.0013, Entropy: 0.0756 +[2026-03-20T21:00:56.889571Z] Loop 15184: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0711 +[2026-03-20T21:00:57.743834Z] Loop 15185: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0735 +[2026-03-20T21:00:58.598126Z] Loop 15186: Loss: 1.41e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0747 +[2026-03-20T21:00:59.451539Z] Loop 15187: Loss: 1.43e-02, Avg Return: 0.864, Regret: 0.0013, Entropy: 0.0740 +[2026-03-20T21:01:00.305193Z] Loop 15188: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0765 +[2026-03-20T21:01:01.159457Z] Loop 15189: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0794 +[2026-03-20T21:01:02.051232Z] Loop 15190: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0864 +[2026-03-20T21:01:02.904135Z] Loop 15191: Loss: 1.69e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0855 +[2026-03-20T21:01:03.758418Z] Loop 15192: Loss: 1.82e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0895 +[2026-03-20T21:01:04.612977Z] Loop 15193: Loss: 1.82e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0899 +[2026-03-20T21:01:05.467414Z] Loop 15194: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0819 +[2026-03-20T21:01:06.320921Z] Loop 15195: Loss: 1.78e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0862 +[2026-03-20T21:01:07.174867Z] Loop 15196: Loss: 1.80e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0883 +[2026-03-20T21:01:08.029993Z] Loop 15197: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0840 +[2026-03-20T21:01:08.884414Z] Loop 15198: Loss: 1.88e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0914 +[2026-03-20T21:01:09.738091Z] Loop 15199: Loss: 1.83e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0898 +[2026-03-20T21:01:10.631953Z] Loop 15200: Loss: 1.94e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0905 +[2026-03-20T21:01:11.485987Z] Loop 15201: Loss: 2.05e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0968 +[2026-03-20T21:01:12.340078Z] Loop 15202: Loss: 2.10e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0980 +[2026-03-20T21:01:13.194164Z] Loop 15203: Loss: 2.19e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.1060 +[2026-03-20T21:01:14.047699Z] Loop 15204: Loss: 2.11e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.1038 +[2026-03-20T21:01:14.902468Z] Loop 15205: Loss: 2.03e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0992 +[2026-03-20T21:01:15.756726Z] Loop 15206: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0942 +[2026-03-20T21:01:16.611284Z] Loop 15207: Loss: 1.84e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0872 +[2026-03-20T21:01:17.464746Z] Loop 15208: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0925 +[2026-03-20T21:01:18.319301Z] Loop 15209: Loss: 1.87e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0924 +[2026-03-20T21:01:19.213282Z] Loop 15210: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0984 +[2026-03-20T21:01:20.067769Z] Loop 15211: Loss: 1.90e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0934 +[2026-03-20T21:01:20.922399Z] Loop 15212: Loss: 1.80e-02, Avg Return: 0.861, Regret: 0.0020, Entropy: 0.0935 +[2026-03-20T21:01:21.775716Z] Loop 15213: Loss: 1.97e-02, Avg Return: 0.862, Regret: 0.0020, Entropy: 0.0970 +[2026-03-20T21:01:22.631454Z] Loop 15214: Loss: 1.81e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.0953 +[2026-03-20T21:01:23.486440Z] Loop 15215: Loss: 1.83e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.0891 +[2026-03-20T21:01:24.342114Z] Loop 15216: Loss: 1.87e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.0928 +[2026-03-20T21:01:25.195982Z] Loop 15217: Loss: 1.88e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.0916 +[2026-03-20T21:01:26.049655Z] Loop 15218: Loss: 1.86e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.0947 +[2026-03-20T21:01:26.903424Z] Loop 15219: Loss: 1.79e-02, Avg Return: 0.863, Regret: 0.0020, Entropy: 0.0890 +[2026-03-20T21:01:27.796630Z] Loop 15220: Loss: 1.85e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0934 +[2026-03-20T21:01:28.650218Z] Loop 15221: Loss: 1.85e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0918 +[2026-03-20T21:01:29.503554Z] Loop 15222: Loss: 1.83e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0958 +[2026-03-20T21:01:30.357079Z] Loop 15223: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0945 +[2026-03-20T21:01:31.212758Z] Loop 15224: Loss: 1.77e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0946 +[2026-03-20T21:01:32.067174Z] Loop 15225: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0994 +[2026-03-20T21:01:32.919863Z] Loop 15226: Loss: 1.94e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0954 +[2026-03-20T21:01:33.773079Z] Loop 15227: Loss: 1.85e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0940 +[2026-03-20T21:01:34.627492Z] Loop 15228: Loss: 1.85e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.0955 +[2026-03-20T21:01:35.482190Z] Loop 15229: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0948 +[2026-03-20T21:01:36.374532Z] Loop 15230: Loss: 1.78e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0937 +[2026-03-20T21:01:37.227529Z] Loop 15231: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0953 +[2026-03-20T21:01:38.082120Z] Loop 15232: Loss: 1.73e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0948 +[2026-03-20T21:01:38.936790Z] Loop 15233: Loss: 1.81e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0907 +[2026-03-20T21:01:39.792025Z] Loop 15234: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0906 +[2026-03-20T21:01:40.644832Z] Loop 15235: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0914 +[2026-03-20T21:01:41.499796Z] Loop 15236: Loss: 1.87e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0903 +[2026-03-20T21:01:42.353451Z] Loop 15237: Loss: 1.83e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0913 +[2026-03-20T21:01:43.209017Z] Loop 15238: Loss: 1.82e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0953 +[2026-03-20T21:01:44.062513Z] Loop 15239: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0916 +[2026-03-20T21:01:44.959501Z] Loop 15240: Loss: 1.79e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0909 +[2026-03-20T21:01:45.812355Z] Loop 15241: Loss: 1.83e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0946 +[2026-03-20T21:01:46.666556Z] Loop 15242: Loss: 1.92e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0927 +[2026-03-20T21:01:47.520592Z] Loop 15243: Loss: 1.78e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0905 +[2026-03-20T21:01:48.374058Z] Loop 15244: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0889 +[2026-03-20T21:01:49.227873Z] Loop 15245: Loss: 1.83e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0916 +[2026-03-20T21:01:50.082893Z] Loop 15246: Loss: 1.85e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0889 +[2026-03-20T21:01:50.938831Z] Loop 15247: Loss: 1.92e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0951 +[2026-03-20T21:01:51.793595Z] Loop 15248: Loss: 1.77e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0918 +[2026-03-20T21:01:52.647403Z] Loop 15249: Loss: 1.75e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0919 +[2026-03-20T21:01:53.542595Z] Loop 15250: Loss: 1.94e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0985 +[2026-03-20T21:01:54.399014Z] Loop 15251: Loss: 1.81e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0950 +[2026-03-20T21:01:55.253993Z] Loop 15252: Loss: 1.88e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0971 +[2026-03-20T21:01:56.108899Z] Loop 15253: Loss: 2.02e-02, Avg Return: 0.865, Regret: 0.0006, Entropy: 0.1067 +[2026-03-20T21:01:56.963769Z] Loop 15254: Loss: 2.19e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.1121 +[2026-03-20T21:01:57.819349Z] Loop 15255: Loss: 2.39e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.1174 +[2026-03-20T21:01:58.673598Z] Loop 15256: Loss: 2.39e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.1187 +[2026-03-20T21:01:59.527248Z] Loop 15257: Loss: 2.49e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.1208 +[2026-03-20T21:02:00.382093Z] Loop 15258: Loss: 2.25e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.1124 +[2026-03-20T21:02:01.236394Z] Loop 15259: Loss: 2.09e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.1055 +[2026-03-20T21:02:02.129900Z] Loop 15260: Loss: 1.97e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0994 +[2026-03-20T21:02:02.984621Z] Loop 15261: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0977 +[2026-03-20T21:02:03.839685Z] Loop 15262: Loss: 1.83e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0999 +[2026-03-20T21:02:04.695651Z] Loop 15263: Loss: 1.93e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.1039 +[2026-03-20T21:02:05.549826Z] Loop 15264: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.1030 +[2026-03-20T21:02:06.403774Z] Loop 15265: Loss: 2.04e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.1121 +[2026-03-20T21:02:07.258159Z] Loop 15266: Loss: 2.19e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.1126 +[2026-03-20T21:02:08.112096Z] Loop 15267: Loss: 2.11e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.1108 +[2026-03-20T21:02:08.965672Z] Loop 15268: Loss: 2.01e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.1089 +[2026-03-20T21:02:09.820153Z] Loop 15269: Loss: 2.05e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.1117 +[2026-03-20T21:02:10.713188Z] Loop 15270: Loss: 2.15e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1120 +[2026-03-20T21:02:11.566514Z] Loop 15271: Loss: 2.10e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.1080 +[2026-03-20T21:02:12.420862Z] Loop 15272: Loss: 2.00e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.1019 +[2026-03-20T21:02:13.275249Z] Loop 15273: Loss: 2.07e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1049 +[2026-03-20T21:02:14.129076Z] Loop 15274: Loss: 1.94e-02, Avg Return: 0.864, Regret: 0.0013, Entropy: 0.0996 +[2026-03-20T21:02:14.983659Z] Loop 15275: Loss: 1.93e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1021 +[2026-03-20T21:02:15.836566Z] Loop 15276: Loss: 1.98e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.1009 +[2026-03-20T21:02:16.690200Z] Loop 15277: Loss: 1.92e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0968 +[2026-03-20T21:02:17.543776Z] Loop 15278: Loss: 1.82e-02, Avg Return: 0.864, Regret: 0.0013, Entropy: 0.0922 +[2026-03-20T21:02:18.397432Z] Loop 15279: Loss: 2.03e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.1014 +[2026-03-20T21:02:19.290542Z] Loop 15280: Loss: 1.94e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0945 +[2026-03-20T21:02:20.144227Z] Loop 15281: Loss: 1.94e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0978 +[2026-03-20T21:02:20.997225Z] Loop 15282: Loss: 1.93e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0946 +[2026-03-20T21:02:21.851429Z] Loop 15283: Loss: 1.82e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0895 +[2026-03-20T21:02:22.706330Z] Loop 15284: Loss: 1.80e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0914 +[2026-03-20T21:02:23.559217Z] Loop 15285: Loss: 1.86e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0924 +[2026-03-20T21:02:24.412275Z] Loop 15286: Loss: 1.83e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0916 +[2026-03-20T21:02:25.266637Z] Loop 15287: Loss: 1.85e-02, Avg Return: 0.861, Regret: 0.0009, Entropy: 0.0905 +[2026-03-20T21:02:26.120183Z] Loop 15288: Loss: 1.79e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0849 +[2026-03-20T21:02:26.973554Z] Loop 15289: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0834 +[2026-03-20T21:02:27.866788Z] Loop 15290: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0837 +[2026-03-20T21:02:28.720127Z] Loop 15291: Loss: 1.63e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0825 +[2026-03-20T21:02:29.574954Z] Loop 15292: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0845 +[2026-03-20T21:02:30.430230Z] Loop 15293: Loss: 1.79e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0880 +[2026-03-20T21:02:31.284850Z] Loop 15294: Loss: 1.89e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0934 +[2026-03-20T21:02:32.138526Z] Loop 15295: Loss: 1.98e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0960 +[2026-03-20T21:02:32.992288Z] Loop 15296: Loss: 2.07e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0984 +[2026-03-20T21:02:33.846789Z] Loop 15297: Loss: 2.06e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.1010 +[2026-03-20T21:02:34.701240Z] Loop 15298: Loss: 1.93e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0947 +[2026-03-20T21:02:35.555415Z] Loop 15299: Loss: 1.92e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0962 +[2026-03-20T21:02:36.448643Z] Loop 15300: Loss: 1.84e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0898 +[2026-03-20T21:02:37.302029Z] Loop 15301: Loss: 1.90e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0918 +[2026-03-20T21:02:38.157310Z] Loop 15302: Loss: 1.75e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0879 +[2026-03-20T21:02:39.010625Z] Loop 15303: Loss: 1.82e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0895 +[2026-03-20T21:02:39.864054Z] Loop 15304: Loss: 1.72e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0845 +[2026-03-20T21:02:40.717458Z] Loop 15305: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0891 +[2026-03-20T21:02:41.571593Z] Loop 15306: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0829 +[2026-03-20T21:02:42.426637Z] Loop 15307: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0773 +[2026-03-20T21:02:43.282583Z] Loop 15308: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0773 +[2026-03-20T21:02:44.136431Z] Loop 15309: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0746 +[2026-03-20T21:02:45.028393Z] Loop 15310: Loss: 1.47e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0731 +[2026-03-20T21:02:45.883607Z] Loop 15311: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0765 +[2026-03-20T21:02:46.737698Z] Loop 15312: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0730 +[2026-03-20T21:02:47.591065Z] Loop 15313: Loss: 1.51e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0752 +[2026-03-20T21:02:48.445727Z] Loop 15314: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0739 +[2026-03-20T21:02:49.300156Z] Loop 15315: Loss: 1.37e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0721 +[2026-03-20T21:02:50.154336Z] Loop 15316: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0771 +[2026-03-20T21:02:51.009161Z] Loop 15317: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0779 +[2026-03-20T21:02:51.864558Z] Loop 15318: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0733 +[2026-03-20T21:02:52.718720Z] Loop 15319: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0707 +[2026-03-20T21:02:53.609905Z] Loop 15320: Loss: 1.51e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0744 +[2026-03-20T21:02:54.463188Z] Loop 15321: Loss: 1.41e-02, Avg Return: 0.865, Regret: 0.0003, Entropy: 0.0717 +[2026-03-20T21:02:55.317253Z] Loop 15322: Loss: 1.45e-02, Avg Return: 0.865, Regret: 0.0003, Entropy: 0.0691 +[2026-03-20T21:02:56.171100Z] Loop 15323: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0763 +[2026-03-20T21:02:57.025222Z] Loop 15324: Loss: 1.41e-02, Avg Return: 0.865, Regret: 0.0003, Entropy: 0.0719 +[2026-03-20T21:02:57.879314Z] Loop 15325: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0712 +[2026-03-20T21:02:58.733652Z] Loop 15326: Loss: 1.44e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0694 +[2026-03-20T21:02:59.588310Z] Loop 15327: Loss: 1.44e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0714 +[2026-03-20T21:03:00.442267Z] Loop 15328: Loss: 1.39e-02, Avg Return: 0.865, Regret: 0.0003, Entropy: 0.0728 +[2026-03-20T21:03:01.296942Z] Loop 15329: Loss: 1.45e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0711 +[2026-03-20T21:03:02.190900Z] Loop 15330: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0695 +[2026-03-20T21:03:03.043868Z] Loop 15331: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0734 +[2026-03-20T21:03:03.898429Z] Loop 15332: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0717 +[2026-03-20T21:03:04.754072Z] Loop 15333: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0725 +[2026-03-20T21:03:05.608547Z] Loop 15334: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0684 +[2026-03-20T21:03:06.463499Z] Loop 15335: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0733 +[2026-03-20T21:03:07.317828Z] Loop 15336: Loss: 1.37e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0697 +[2026-03-20T21:03:08.173106Z] Loop 15337: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0701 +[2026-03-20T21:03:09.028523Z] Loop 15338: Loss: 1.40e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0698 +[2026-03-20T21:03:09.883060Z] Loop 15339: Loss: 1.40e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0737 +[2026-03-20T21:03:10.777595Z] Loop 15340: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0685 +[2026-03-20T21:03:11.632110Z] Loop 15341: Loss: 1.28e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0666 +[2026-03-20T21:03:12.487061Z] Loop 15342: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0711 +[2026-03-20T21:03:13.341260Z] Loop 15343: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0706 +[2026-03-20T21:03:14.194582Z] Loop 15344: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0742 +[2026-03-20T21:03:15.048542Z] Loop 15345: Loss: 1.47e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0719 +[2026-03-20T21:03:15.902388Z] Loop 15346: Loss: 1.48e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0706 +[2026-03-20T21:03:16.756074Z] Loop 15347: Loss: 1.40e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0735 +[2026-03-20T21:03:17.609584Z] Loop 15348: Loss: 1.47e-02, Avg Return: 0.865, Regret: 0.0001, Entropy: 0.0740 +[2026-03-20T21:03:18.463660Z] Loop 15349: Loss: 1.45e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0733 +[2026-03-20T21:03:19.356235Z] Loop 15350: Loss: 1.44e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0739 +[2026-03-20T21:03:20.210594Z] Loop 15351: Loss: 1.56e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0755 +[2026-03-20T21:03:21.064049Z] Loop 15352: Loss: 1.51e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0756 +[2026-03-20T21:03:21.918606Z] Loop 15353: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0776 +[2026-03-20T21:03:22.772107Z] Loop 15354: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0785 +[2026-03-20T21:03:23.626069Z] Loop 15355: Loss: 1.54e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0786 +[2026-03-20T21:03:24.480343Z] Loop 15356: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0810 +[2026-03-20T21:03:25.335134Z] Loop 15357: Loss: 1.68e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0802 +[2026-03-20T21:03:26.189675Z] Loop 15358: Loss: 1.70e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0828 +[2026-03-20T21:03:27.043188Z] Loop 15359: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0796 +[2026-03-20T21:03:27.936367Z] Loop 15360: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0808 +[2026-03-20T21:03:28.792714Z] Loop 15361: Loss: 1.77e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0867 +[2026-03-20T21:03:29.646150Z] Loop 15362: Loss: 1.76e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0883 +[2026-03-20T21:03:30.499397Z] Loop 15363: Loss: 1.86e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0911 +[2026-03-20T21:03:31.354470Z] Loop 15364: Loss: 1.88e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0946 +[2026-03-20T21:03:32.208965Z] Loop 15365: Loss: 1.98e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0987 +[2026-03-20T21:03:33.063032Z] Loop 15366: Loss: 2.06e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.1008 +[2026-03-20T21:03:33.916664Z] Loop 15367: Loss: 2.16e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.1044 +[2026-03-20T21:03:34.771007Z] Loop 15368: Loss: 2.02e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.1012 +[2026-03-20T21:03:35.625870Z] Loop 15369: Loss: 2.11e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.1029 +[2026-03-20T21:03:36.517157Z] Loop 15370: Loss: 2.09e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.1023 +[2026-03-20T21:03:37.370611Z] Loop 15371: Loss: 2.05e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.1003 +[2026-03-20T21:03:38.224634Z] Loop 15372: Loss: 2.06e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0989 +[2026-03-20T21:03:39.078637Z] Loop 15373: Loss: 2.17e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.1047 +[2026-03-20T21:03:39.932224Z] Loop 15374: Loss: 2.06e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0974 +[2026-03-20T21:03:40.785164Z] Loop 15375: Loss: 1.88e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0943 +[2026-03-20T21:03:41.640031Z] Loop 15376: Loss: 1.93e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0955 +[2026-03-20T21:03:42.496184Z] Loop 15377: Loss: 1.92e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0963 +[2026-03-20T21:03:43.350145Z] Loop 15378: Loss: 1.86e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0925 +[2026-03-20T21:03:44.204201Z] Loop 15379: Loss: 1.85e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0919 +[2026-03-20T21:03:45.096212Z] Loop 15380: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0915 +[2026-03-20T21:03:45.950463Z] Loop 15381: Loss: 1.75e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0899 +[2026-03-20T21:03:46.805877Z] Loop 15382: Loss: 1.76e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0896 +[2026-03-20T21:03:47.659956Z] Loop 15383: Loss: 1.78e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0891 +[2026-03-20T21:03:48.514001Z] Loop 15384: Loss: 1.72e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0867 +[2026-03-20T21:03:49.368443Z] Loop 15385: Loss: 1.69e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0872 +[2026-03-20T21:03:50.223377Z] Loop 15386: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0851 +[2026-03-20T21:03:51.077894Z] Loop 15387: Loss: 1.69e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0867 +[2026-03-20T21:03:51.933068Z] Loop 15388: Loss: 1.83e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0885 +[2026-03-20T21:03:52.787293Z] Loop 15389: Loss: 1.85e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0899 +[2026-03-20T21:03:53.680784Z] Loop 15390: Loss: 2.01e-02, Avg Return: 0.866, Regret: 0.0004, Entropy: 0.0970 +[2026-03-20T21:03:54.535326Z] Loop 15391: Loss: 2.14e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0986 +[2026-03-20T21:03:55.390879Z] Loop 15392: Loss: 1.84e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0903 +[2026-03-20T21:03:56.245536Z] Loop 15393: Loss: 1.78e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0862 +[2026-03-20T21:03:57.099841Z] Loop 15394: Loss: 1.82e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0882 +[2026-03-20T21:03:57.955429Z] Loop 15395: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0794 +[2026-03-20T21:03:58.810596Z] Loop 15396: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0782 +[2026-03-20T21:03:59.665362Z] Loop 15397: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0763 +[2026-03-20T21:04:00.518952Z] Loop 15398: Loss: 1.34e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0718 +[2026-03-20T21:04:01.372325Z] Loop 15399: Loss: 1.49e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0775 +[2026-03-20T21:04:02.268051Z] Loop 15400: Loss: 1.39e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0711 +[2026-03-20T21:04:03.122926Z] Loop 15401: Loss: 1.40e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0706 +[2026-03-20T21:04:03.976895Z] Loop 15402: Loss: 1.32e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0662 +[2026-03-20T21:04:04.831226Z] Loop 15403: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0644 +[2026-03-20T21:04:05.686335Z] Loop 15404: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0702 +[2026-03-20T21:04:06.541726Z] Loop 15405: Loss: 1.25e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0660 +[2026-03-20T21:04:07.396932Z] Loop 15406: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0665 +[2026-03-20T21:04:08.251210Z] Loop 15407: Loss: 1.18e-02, Avg Return: 0.865, Regret: 0.0001, Entropy: 0.0633 +[2026-03-20T21:04:09.106226Z] Loop 15408: Loss: 1.30e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0645 +[2026-03-20T21:04:09.960638Z] Loop 15409: Loss: 1.22e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0595 +[2026-03-20T21:04:10.854524Z] Loop 15410: Loss: 1.22e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0618 +[2026-03-20T21:04:11.708479Z] Loop 15411: Loss: 1.24e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0632 +[2026-03-20T21:04:12.564268Z] Loop 15412: Loss: 1.17e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0630 +[2026-03-20T21:04:13.418375Z] Loop 15413: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0653 +[2026-03-20T21:04:14.272392Z] Loop 15414: Loss: 1.19e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0646 +[2026-03-20T21:04:15.127599Z] Loop 15415: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0640 +[2026-03-20T21:04:15.982903Z] Loop 15416: Loss: 1.38e-02, Avg Return: 0.861, Regret: 0.0004, Entropy: 0.0675 +[2026-03-20T21:04:16.837329Z] Loop 15417: Loss: 1.11e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0644 +[2026-03-20T21:04:17.692063Z] Loop 15418: Loss: 1.28e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0655 +[2026-03-20T21:04:18.546674Z] Loop 15419: Loss: 1.22e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0661 +[2026-03-20T21:04:19.444302Z] Loop 15420: Loss: 1.31e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0700 +[2026-03-20T21:04:20.297776Z] Loop 15421: Loss: 1.36e-02, Avg Return: 0.860, Regret: 0.0011, Entropy: 0.0703 +[2026-03-20T21:04:21.151916Z] Loop 15422: Loss: 1.30e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0672 +[2026-03-20T21:04:22.006799Z] Loop 15423: Loss: 1.13e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0611 +[2026-03-20T21:04:22.861531Z] Loop 15424: Loss: 1.30e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0668 +[2026-03-20T21:04:23.715565Z] Loop 15425: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0700 +[2026-03-20T21:04:24.569766Z] Loop 15426: Loss: 1.36e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0689 +[2026-03-20T21:04:25.424310Z] Loop 15427: Loss: 1.30e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0657 +[2026-03-20T21:04:26.279305Z] Loop 15428: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0717 +[2026-03-20T21:04:27.134609Z] Loop 15429: Loss: 1.39e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0677 +[2026-03-20T21:04:28.028517Z] Loop 15430: Loss: 1.35e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.0726 +[2026-03-20T21:04:28.883384Z] Loop 15431: Loss: 1.26e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.0663 +[2026-03-20T21:04:29.737669Z] Loop 15432: Loss: 1.35e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.0672 +[2026-03-20T21:04:30.591889Z] Loop 15433: Loss: 1.30e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.0684 +[2026-03-20T21:04:31.445141Z] Loop 15434: Loss: 1.38e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.0714 +[2026-03-20T21:04:32.299599Z] Loop 15435: Loss: 1.37e-02, Avg Return: 0.860, Regret: 0.0024, Entropy: 0.0719 +[2026-03-20T21:04:33.155410Z] Loop 15436: Loss: 1.29e-02, Avg Return: 0.860, Regret: 0.0024, Entropy: 0.0627 +[2026-03-20T21:04:34.010255Z] Loop 15437: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0024, Entropy: 0.0683 +[2026-03-20T21:04:34.865792Z] Loop 15438: Loss: 1.26e-02, Avg Return: 0.861, Regret: 0.0024, Entropy: 0.0684 +[2026-03-20T21:04:35.719502Z] Loop 15439: Loss: 1.23e-02, Avg Return: 0.860, Regret: 0.0024, Entropy: 0.0652 +[2026-03-20T21:04:36.613115Z] Loop 15440: Loss: 1.22e-02, Avg Return: 0.860, Regret: 0.0023, Entropy: 0.0649 +[2026-03-20T21:04:37.468221Z] Loop 15441: Loss: 1.20e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.0656 +[2026-03-20T21:04:38.322196Z] Loop 15442: Loss: 1.36e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.0685 +[2026-03-20T21:04:39.175905Z] Loop 15443: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.0697 +[2026-03-20T21:04:40.029235Z] Loop 15444: Loss: 1.42e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.0716 +[2026-03-20T21:04:40.883420Z] Loop 15445: Loss: 1.46e-02, Avg Return: 0.860, Regret: 0.0023, Entropy: 0.0752 +[2026-03-20T21:04:41.737979Z] Loop 15446: Loss: 1.40e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.0705 +[2026-03-20T21:04:42.592408Z] Loop 15447: Loss: 1.36e-02, Avg Return: 0.861, Regret: 0.0023, Entropy: 0.0713 +[2026-03-20T21:04:43.445686Z] Loop 15448: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0023, Entropy: 0.0733 +[2026-03-20T21:04:44.299259Z] Loop 15449: Loss: 1.40e-02, Avg Return: 0.862, Regret: 0.0023, Entropy: 0.0715 +[2026-03-20T21:04:45.192728Z] Loop 15450: Loss: 1.30e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0669 +[2026-03-20T21:04:46.047629Z] Loop 15451: Loss: 1.33e-02, Avg Return: 0.864, Regret: 0.0015, Entropy: 0.0687 +[2026-03-20T21:04:46.902743Z] Loop 15452: Loss: 1.39e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0716 +[2026-03-20T21:04:47.756848Z] Loop 15453: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0761 +[2026-03-20T21:04:48.611656Z] Loop 15454: Loss: 1.42e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0731 +[2026-03-20T21:04:49.466439Z] Loop 15455: Loss: 1.44e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0742 +[2026-03-20T21:04:50.320301Z] Loop 15456: Loss: 1.45e-02, Avg Return: 0.860, Regret: 0.0015, Entropy: 0.0735 +[2026-03-20T21:04:51.175164Z] Loop 15457: Loss: 1.45e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0755 +[2026-03-20T21:04:52.029798Z] Loop 15458: Loss: 1.46e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0730 +[2026-03-20T21:04:52.885041Z] Loop 15459: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0706 +[2026-03-20T21:04:53.779287Z] Loop 15460: Loss: 1.40e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0702 +[2026-03-20T21:04:54.632881Z] Loop 15461: Loss: 1.36e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0741 +[2026-03-20T21:04:55.487754Z] Loop 15462: Loss: 1.33e-02, Avg Return: 0.864, Regret: 0.0013, Entropy: 0.0684 +[2026-03-20T21:04:56.342648Z] Loop 15463: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0738 +[2026-03-20T21:04:57.197291Z] Loop 15464: Loss: 1.52e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0738 +[2026-03-20T21:04:58.051402Z] Loop 15465: Loss: 1.43e-02, Avg Return: 0.864, Regret: 0.0013, Entropy: 0.0750 +[2026-03-20T21:04:58.905523Z] Loop 15466: Loss: 1.57e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0788 +[2026-03-20T21:04:59.759016Z] Loop 15467: Loss: 1.67e-02, Avg Return: 0.860, Regret: 0.0013, Entropy: 0.0828 +[2026-03-20T21:05:00.612885Z] Loop 15468: Loss: 1.59e-02, Avg Return: 0.858, Regret: 0.0013, Entropy: 0.0865 +[2026-03-20T21:05:01.467075Z] Loop 15469: Loss: 1.75e-02, Avg Return: 0.855, Regret: 0.0013, Entropy: 0.0944 +[2026-03-20T21:05:02.361385Z] Loop 15470: Loss: 1.74e-02, Avg Return: 0.857, Regret: 0.0072, Entropy: 0.0900 +[2026-03-20T21:05:03.214793Z] Loop 15471: Loss: 1.88e-02, Avg Return: 0.857, Regret: 0.0072, Entropy: 0.0953 +[2026-03-20T21:05:04.068620Z] Loop 15472: Loss: 1.66e-02, Avg Return: 0.862, Regret: 0.0072, Entropy: 0.0895 +[2026-03-20T21:05:04.922298Z] Loop 15473: Loss: 1.65e-02, Avg Return: 0.861, Regret: 0.0072, Entropy: 0.0890 +[2026-03-20T21:05:05.776897Z] Loop 15474: Loss: 1.65e-02, Avg Return: 0.861, Regret: 0.0072, Entropy: 0.0868 +[2026-03-20T21:05:06.629046Z] Loop 15475: Loss: 1.60e-02, Avg Return: 0.864, Regret: 0.0072, Entropy: 0.0822 +[2026-03-20T21:05:07.480792Z] Loop 15476: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0072, Entropy: 0.0808 +[2026-03-20T21:05:08.334581Z] Loop 15477: Loss: 1.50e-02, Avg Return: 0.865, Regret: 0.0072, Entropy: 0.0783 +[2026-03-20T21:05:09.188887Z] Loop 15478: Loss: 1.29e-02, Avg Return: 0.864, Regret: 0.0072, Entropy: 0.0709 +[2026-03-20T21:05:10.042555Z] Loop 15479: Loss: 1.40e-02, Avg Return: 0.865, Regret: 0.0072, Entropy: 0.0713 +[2026-03-20T21:05:10.934151Z] Loop 15480: Loss: 1.40e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0708 +[2026-03-20T21:05:11.787810Z] Loop 15481: Loss: 1.33e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0685 +[2026-03-20T21:05:12.642376Z] Loop 15482: Loss: 1.47e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0709 +[2026-03-20T21:05:13.495760Z] Loop 15483: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0717 +[2026-03-20T21:05:14.348979Z] Loop 15484: Loss: 1.43e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0759 +[2026-03-20T21:05:15.203159Z] Loop 15485: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0744 +[2026-03-20T21:05:16.058780Z] Loop 15486: Loss: 1.43e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0709 +[2026-03-20T21:05:16.913207Z] Loop 15487: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0742 +[2026-03-20T21:05:17.767771Z] Loop 15488: Loss: 1.43e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0715 +[2026-03-20T21:05:18.623209Z] Loop 15489: Loss: 1.43e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0725 +[2026-03-20T21:05:19.516857Z] Loop 15490: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0718 +[2026-03-20T21:05:20.370778Z] Loop 15491: Loss: 1.41e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0713 +[2026-03-20T21:05:21.225714Z] Loop 15492: Loss: 1.47e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0721 +[2026-03-20T21:05:22.079195Z] Loop 15493: Loss: 1.46e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0747 +[2026-03-20T21:05:22.932647Z] Loop 15494: Loss: 1.58e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0789 +[2026-03-20T21:05:23.786724Z] Loop 15495: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0760 +[2026-03-20T21:05:24.640417Z] Loop 15496: Loss: 1.60e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0796 +[2026-03-20T21:05:25.494847Z] Loop 15497: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0808 +[2026-03-20T21:05:26.350939Z] Loop 15498: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0772 +[2026-03-20T21:05:27.205876Z] Loop 15499: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0824 +[2026-03-20T21:05:28.097817Z] Loop 15500: Loss: 1.54e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0775 +[2026-03-20T21:05:28.952217Z] Loop 15501: Loss: 1.63e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0819 +[2026-03-20T21:05:29.805698Z] Loop 15502: Loss: 1.74e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0843 +[2026-03-20T21:05:30.659991Z] Loop 15503: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0833 +[2026-03-20T21:05:31.514294Z] Loop 15504: Loss: 1.85e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0883 +[2026-03-20T21:05:32.368694Z] Loop 15505: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0863 +[2026-03-20T21:05:33.222604Z] Loop 15506: Loss: 1.78e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0863 +[2026-03-20T21:05:34.076253Z] Loop 15507: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0871 +[2026-03-20T21:05:34.930232Z] Loop 15508: Loss: 1.84e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0903 +[2026-03-20T21:05:35.784557Z] Loop 15509: Loss: 1.76e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0925 +[2026-03-20T21:05:36.676394Z] Loop 15510: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0898 +[2026-03-20T21:05:37.530420Z] Loop 15511: Loss: 1.82e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0911 +[2026-03-20T21:05:38.383539Z] Loop 15512: Loss: 1.85e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0909 +[2026-03-20T21:05:39.239440Z] Loop 15513: Loss: 1.84e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0914 +[2026-03-20T21:05:40.094467Z] Loop 15514: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0832 +[2026-03-20T21:05:40.948517Z] Loop 15515: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0814 +[2026-03-20T21:05:41.802784Z] Loop 15516: Loss: 1.66e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0864 +[2026-03-20T21:05:42.657619Z] Loop 15517: Loss: 1.70e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0840 +[2026-03-20T21:05:43.512511Z] Loop 15518: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0816 +[2026-03-20T21:05:44.367316Z] Loop 15519: Loss: 1.61e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0812 +[2026-03-20T21:05:45.259189Z] Loop 15520: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0764 +[2026-03-20T21:05:46.114148Z] Loop 15521: Loss: 1.62e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0793 +[2026-03-20T21:05:46.968634Z] Loop 15522: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0812 +[2026-03-20T21:05:47.823886Z] Loop 15523: Loss: 1.52e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0782 +[2026-03-20T21:05:48.677599Z] Loop 15524: Loss: 1.45e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0735 +[2026-03-20T21:05:49.531628Z] Loop 15525: Loss: 1.48e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0741 +[2026-03-20T21:05:50.385147Z] Loop 15526: Loss: 1.57e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0765 +[2026-03-20T21:05:51.238754Z] Loop 15527: Loss: 1.48e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0765 +[2026-03-20T21:05:52.092943Z] Loop 15528: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0775 +[2026-03-20T21:05:52.946437Z] Loop 15529: Loss: 1.50e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0748 +[2026-03-20T21:05:53.839207Z] Loop 15530: Loss: 1.41e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0727 +[2026-03-20T21:05:54.692474Z] Loop 15531: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0706 +[2026-03-20T21:05:55.546808Z] Loop 15532: Loss: 1.20e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0637 +[2026-03-20T21:05:56.400962Z] Loop 15533: Loss: 1.26e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0663 +[2026-03-20T21:05:57.254159Z] Loop 15534: Loss: 1.16e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0627 +[2026-03-20T21:06:03.426244Z] Loop 15535: Loss: 1.26e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0669 +[2026-03-20T21:06:04.281546Z] Loop 15536: Loss: 1.18e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0642 +[2026-03-20T21:06:05.136282Z] Loop 15537: Loss: 1.32e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0675 +[2026-03-20T21:06:05.990182Z] Loop 15538: Loss: 1.22e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0654 +[2026-03-20T21:06:06.844636Z] Loop 15539: Loss: 1.12e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0573 +[2026-03-20T21:06:07.738510Z] Loop 15540: Loss: 1.20e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0616 +[2026-03-20T21:06:08.593287Z] Loop 15541: Loss: 1.15e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0622 +[2026-03-20T21:06:09.446544Z] Loop 15542: Loss: 1.24e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0639 +[2026-03-20T21:06:10.299589Z] Loop 15543: Loss: 1.18e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0625 +[2026-03-20T21:06:11.153700Z] Loop 15544: Loss: 1.26e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0650 +[2026-03-20T21:06:12.008448Z] Loop 15545: Loss: 1.25e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0634 +[2026-03-20T21:06:12.862971Z] Loop 15546: Loss: 1.16e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0636 +[2026-03-20T21:06:13.717495Z] Loop 15547: Loss: 1.23e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0636 +[2026-03-20T21:06:14.571580Z] Loop 15548: Loss: 1.23e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0616 +[2026-03-20T21:06:15.425892Z] Loop 15549: Loss: 1.24e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0672 +[2026-03-20T21:06:16.318787Z] Loop 15550: Loss: 1.07e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0600 +[2026-03-20T21:06:17.172085Z] Loop 15551: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0634 +[2026-03-20T21:06:18.025751Z] Loop 15552: Loss: 1.17e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0653 +[2026-03-20T21:06:18.879878Z] Loop 15553: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0668 +[2026-03-20T21:06:19.733681Z] Loop 15554: Loss: 1.30e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0713 +[2026-03-20T21:06:20.587590Z] Loop 15555: Loss: 1.28e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0658 +[2026-03-20T21:06:21.442213Z] Loop 15556: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0733 +[2026-03-20T21:06:22.296589Z] Loop 15557: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0715 +[2026-03-20T21:06:23.150583Z] Loop 15558: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0756 +[2026-03-20T21:06:24.005328Z] Loop 15559: Loss: 1.36e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.0736 +[2026-03-20T21:06:24.898060Z] Loop 15560: Loss: 1.37e-02, Avg Return: 0.860, Regret: 0.0025, Entropy: 0.0766 +[2026-03-20T21:06:25.751862Z] Loop 15561: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0773 +[2026-03-20T21:06:26.605374Z] Loop 15562: Loss: 1.39e-02, Avg Return: 0.860, Regret: 0.0025, Entropy: 0.0757 +[2026-03-20T21:06:27.459593Z] Loop 15563: Loss: 1.52e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0786 +[2026-03-20T21:06:28.313399Z] Loop 15564: Loss: 1.47e-02, Avg Return: 0.861, Regret: 0.0025, Entropy: 0.0772 +[2026-03-20T21:06:29.166629Z] Loop 15565: Loss: 1.42e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0765 +[2026-03-20T21:06:30.020646Z] Loop 15566: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0025, Entropy: 0.0734 +[2026-03-20T21:06:30.874449Z] Loop 15567: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0025, Entropy: 0.0709 +[2026-03-20T21:06:31.728562Z] Loop 15568: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0025, Entropy: 0.0720 +[2026-03-20T21:06:32.581132Z] Loop 15569: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0025, Entropy: 0.0707 +[2026-03-20T21:06:33.472295Z] Loop 15570: Loss: 1.25e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0697 +[2026-03-20T21:06:34.327433Z] Loop 15571: Loss: 1.30e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0689 +[2026-03-20T21:06:35.181847Z] Loop 15572: Loss: 1.30e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0717 +[2026-03-20T21:06:36.035718Z] Loop 15573: Loss: 1.40e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0724 +[2026-03-20T21:06:36.889326Z] Loop 15574: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0729 +[2026-03-20T21:06:37.742842Z] Loop 15575: Loss: 1.33e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0700 +[2026-03-20T21:06:38.598186Z] Loop 15576: Loss: 1.40e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0727 +[2026-03-20T21:06:39.453059Z] Loop 15577: Loss: 1.30e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0695 +[2026-03-20T21:06:40.306568Z] Loop 15578: Loss: 1.42e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0763 +[2026-03-20T21:06:41.160144Z] Loop 15579: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0775 +[2026-03-20T21:06:42.053777Z] Loop 15580: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0772 +[2026-03-20T21:06:42.908868Z] Loop 15581: Loss: 1.54e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0819 +[2026-03-20T21:06:43.763100Z] Loop 15582: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0805 +[2026-03-20T21:06:44.616455Z] Loop 15583: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0818 +[2026-03-20T21:06:45.470090Z] Loop 15584: Loss: 1.63e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0782 +[2026-03-20T21:06:46.323991Z] Loop 15585: Loss: 1.56e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0792 +[2026-03-20T21:06:47.178096Z] Loop 15586: Loss: 1.54e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0792 +[2026-03-20T21:06:48.031408Z] Loop 15587: Loss: 1.51e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0769 +[2026-03-20T21:06:48.884888Z] Loop 15588: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0729 +[2026-03-20T21:06:49.739794Z] Loop 15589: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0764 +[2026-03-20T21:06:50.632557Z] Loop 15590: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0729 +[2026-03-20T21:06:51.486972Z] Loop 15591: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0734 +[2026-03-20T21:06:52.340865Z] Loop 15592: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0737 +[2026-03-20T21:06:53.195259Z] Loop 15593: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0745 +[2026-03-20T21:06:54.050892Z] Loop 15594: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0729 +[2026-03-20T21:06:54.905695Z] Loop 15595: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0692 +[2026-03-20T21:06:55.761316Z] Loop 15596: Loss: 1.25e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0676 +[2026-03-20T21:06:56.615482Z] Loop 15597: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0669 +[2026-03-20T21:06:57.469956Z] Loop 15598: Loss: 1.25e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0669 +[2026-03-20T21:06:58.324940Z] Loop 15599: Loss: 1.24e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0665 +[2026-03-20T21:06:59.216509Z] Loop 15600: Loss: 1.33e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0672 +[2026-03-20T21:07:00.070065Z] Loop 15601: Loss: 1.24e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0683 +[2026-03-20T21:07:00.923676Z] Loop 15602: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0681 +[2026-03-20T21:07:01.778359Z] Loop 15603: Loss: 1.20e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0635 +[2026-03-20T21:07:02.632529Z] Loop 15604: Loss: 1.23e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0638 +[2026-03-20T21:07:03.486764Z] Loop 15605: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0669 +[2026-03-20T21:07:04.340280Z] Loop 15606: Loss: 1.31e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0678 +[2026-03-20T21:07:05.194885Z] Loop 15607: Loss: 1.24e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0671 +[2026-03-20T21:07:06.049599Z] Loop 15608: Loss: 1.33e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0711 +[2026-03-20T21:07:06.903175Z] Loop 15609: Loss: 1.24e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0634 +[2026-03-20T21:07:07.794160Z] Loop 15610: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0690 +[2026-03-20T21:07:08.648448Z] Loop 15611: Loss: 1.22e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0643 +[2026-03-20T21:07:09.502682Z] Loop 15612: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0614 +[2026-03-20T21:07:10.356732Z] Loop 15613: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0671 +[2026-03-20T21:07:11.211730Z] Loop 15614: Loss: 1.29e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0668 +[2026-03-20T21:07:12.066701Z] Loop 15615: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0708 +[2026-03-20T21:07:12.920226Z] Loop 15616: Loss: 1.32e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0658 +[2026-03-20T21:07:13.773947Z] Loop 15617: Loss: 1.33e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0701 +[2026-03-20T21:07:14.628301Z] Loop 15618: Loss: 1.29e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0685 +[2026-03-20T21:07:15.481086Z] Loop 15619: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0732 +[2026-03-20T21:07:16.373125Z] Loop 15620: Loss: 1.38e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0726 +[2026-03-20T21:07:17.227248Z] Loop 15621: Loss: 1.43e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0715 +[2026-03-20T21:07:18.080977Z] Loop 15622: Loss: 1.36e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0726 +[2026-03-20T21:07:18.935292Z] Loop 15623: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0768 +[2026-03-20T21:07:19.789359Z] Loop 15624: Loss: 1.43e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0758 +[2026-03-20T21:07:20.643875Z] Loop 15625: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0727 +[2026-03-20T21:07:21.498037Z] Loop 15626: Loss: 1.46e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0751 +[2026-03-20T21:07:22.352434Z] Loop 15627: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0772 +[2026-03-20T21:07:23.206153Z] Loop 15628: Loss: 1.34e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0691 +[2026-03-20T21:07:24.059766Z] Loop 15629: Loss: 1.39e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0683 +[2026-03-20T21:07:24.953699Z] Loop 15630: Loss: 1.37e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0689 +[2026-03-20T21:07:25.808673Z] Loop 15631: Loss: 1.20e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0643 +[2026-03-20T21:07:26.663538Z] Loop 15632: Loss: 1.23e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0657 +[2026-03-20T21:07:27.517246Z] Loop 15633: Loss: 1.17e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0662 +[2026-03-20T21:07:28.372211Z] Loop 15634: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0683 +[2026-03-20T21:07:29.227313Z] Loop 15635: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0668 +[2026-03-20T21:07:30.082323Z] Loop 15636: Loss: 1.30e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0680 +[2026-03-20T21:07:30.938909Z] Loop 15637: Loss: 1.34e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0675 +[2026-03-20T21:07:31.793170Z] Loop 15638: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0657 +[2026-03-20T21:07:32.648186Z] Loop 15639: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0673 +[2026-03-20T21:07:33.542705Z] Loop 15640: Loss: 1.32e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0680 +[2026-03-20T21:07:34.396054Z] Loop 15641: Loss: 1.31e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0683 +[2026-03-20T21:07:35.251552Z] Loop 15642: Loss: 1.25e-02, Avg Return: 0.865, Regret: 0.0002, Entropy: 0.0678 +[2026-03-20T21:07:36.105673Z] Loop 15643: Loss: 1.24e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0645 +[2026-03-20T21:07:36.960046Z] Loop 15644: Loss: 1.32e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0705 +[2026-03-20T21:07:37.814815Z] Loop 15645: Loss: 1.33e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0734 +[2026-03-20T21:07:38.668841Z] Loop 15646: Loss: 1.40e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0750 +[2026-03-20T21:07:39.522600Z] Loop 15647: Loss: 1.51e-02, Avg Return: 0.861, Regret: 0.0002, Entropy: 0.0803 +[2026-03-20T21:07:40.376091Z] Loop 15648: Loss: 1.46e-02, Avg Return: 0.860, Regret: 0.0002, Entropy: 0.0771 +[2026-03-20T21:07:41.229793Z] Loop 15649: Loss: 1.49e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0792 +[2026-03-20T21:07:42.124320Z] Loop 15650: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0702 +[2026-03-20T21:07:42.977637Z] Loop 15651: Loss: 1.30e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0662 +[2026-03-20T21:07:43.831587Z] Loop 15652: Loss: 1.32e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0682 +[2026-03-20T21:07:44.686077Z] Loop 15653: Loss: 1.29e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0675 +[2026-03-20T21:07:45.541904Z] Loop 15654: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0757 +[2026-03-20T21:07:46.396334Z] Loop 15655: Loss: 1.54e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0759 +[2026-03-20T21:07:47.251491Z] Loop 15656: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0757 +[2026-03-20T21:07:48.106084Z] Loop 15657: Loss: 1.60e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0819 +[2026-03-20T21:07:48.960397Z] Loop 15658: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0773 +[2026-03-20T21:07:49.813880Z] Loop 15659: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0795 +[2026-03-20T21:07:50.708908Z] Loop 15660: Loss: 1.63e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0847 +[2026-03-20T21:07:51.563090Z] Loop 15661: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0793 +[2026-03-20T21:07:52.419463Z] Loop 15662: Loss: 1.82e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0905 +[2026-03-20T21:07:53.273661Z] Loop 15663: Loss: 1.93e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0941 +[2026-03-20T21:07:54.126754Z] Loop 15664: Loss: 2.11e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0974 +[2026-03-20T21:07:54.979686Z] Loop 15665: Loss: 2.09e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0990 +[2026-03-20T21:07:55.833941Z] Loop 15666: Loss: 2.00e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0998 +[2026-03-20T21:07:56.688637Z] Loop 15667: Loss: 2.05e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.1028 +[2026-03-20T21:07:57.542826Z] Loop 15668: Loss: 2.19e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.1039 +[2026-03-20T21:07:58.395776Z] Loop 15669: Loss: 2.24e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.1054 +[2026-03-20T21:07:59.288931Z] Loop 15670: Loss: 2.28e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.1087 +[2026-03-20T21:08:00.144065Z] Loop 15671: Loss: 2.13e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.1018 +[2026-03-20T21:08:00.998293Z] Loop 15672: Loss: 2.02e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0993 +[2026-03-20T21:08:01.852162Z] Loop 15673: Loss: 1.95e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0981 +[2026-03-20T21:08:02.706520Z] Loop 15674: Loss: 1.96e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0963 +[2026-03-20T21:08:03.560645Z] Loop 15675: Loss: 1.89e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0915 +[2026-03-20T21:08:04.414952Z] Loop 15676: Loss: 1.85e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0933 +[2026-03-20T21:08:05.267927Z] Loop 15677: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0895 +[2026-03-20T21:08:06.121409Z] Loop 15678: Loss: 1.82e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0913 +[2026-03-20T21:08:06.975789Z] Loop 15679: Loss: 1.94e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0929 +[2026-03-20T21:08:07.871709Z] Loop 15680: Loss: 1.87e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0937 +[2026-03-20T21:08:08.726092Z] Loop 15681: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0970 +[2026-03-20T21:08:09.580196Z] Loop 15682: Loss: 1.95e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0973 +[2026-03-20T21:08:10.433231Z] Loop 15683: Loss: 1.93e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.1003 +[2026-03-20T21:08:11.288995Z] Loop 15684: Loss: 1.88e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0964 +[2026-03-20T21:08:12.145612Z] Loop 15685: Loss: 1.99e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0979 +[2026-03-20T21:08:12.999502Z] Loop 15686: Loss: 1.96e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0987 +[2026-03-20T21:08:13.851955Z] Loop 15687: Loss: 1.90e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0990 +[2026-03-20T21:08:14.704994Z] Loop 15688: Loss: 2.07e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.1041 +[2026-03-20T21:08:15.559996Z] Loop 15689: Loss: 2.06e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.1049 +[2026-03-20T21:08:16.454290Z] Loop 15690: Loss: 1.97e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.1005 +[2026-03-20T21:08:17.307531Z] Loop 15691: Loss: 1.99e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.1014 +[2026-03-20T21:08:18.161714Z] Loop 15692: Loss: 2.10e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.1041 +[2026-03-20T21:08:19.015907Z] Loop 15693: Loss: 1.98e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0964 +[2026-03-20T21:08:19.870143Z] Loop 15694: Loss: 2.05e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.1013 +[2026-03-20T21:08:20.724079Z] Loop 15695: Loss: 2.16e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.1014 +[2026-03-20T21:08:21.576678Z] Loop 15696: Loss: 2.16e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.1027 +[2026-03-20T21:08:22.430167Z] Loop 15697: Loss: 2.09e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.1024 +[2026-03-20T21:08:23.285093Z] Loop 15698: Loss: 2.05e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.1024 +[2026-03-20T21:08:24.140100Z] Loop 15699: Loss: 1.98e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.1020 +[2026-03-20T21:08:25.035459Z] Loop 15700: Loss: 1.85e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0947 +[2026-03-20T21:08:25.890431Z] Loop 15701: Loss: 1.95e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0957 +[2026-03-20T21:08:26.745465Z] Loop 15702: Loss: 2.04e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.1004 +[2026-03-20T21:08:27.599630Z] Loop 15703: Loss: 1.90e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0948 +[2026-03-20T21:08:28.453318Z] Loop 15704: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0933 +[2026-03-20T21:08:29.307490Z] Loop 15705: Loss: 1.80e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0933 +[2026-03-20T21:08:30.161516Z] Loop 15706: Loss: 1.73e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0869 +[2026-03-20T21:08:31.015565Z] Loop 15707: Loss: 1.82e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0926 +[2026-03-20T21:08:31.869200Z] Loop 15708: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0854 +[2026-03-20T21:08:32.724023Z] Loop 15709: Loss: 1.78e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0885 +[2026-03-20T21:08:33.616559Z] Loop 15710: Loss: 1.73e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0864 +[2026-03-20T21:08:34.471195Z] Loop 15711: Loss: 1.71e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0886 +[2026-03-20T21:08:35.325651Z] Loop 15712: Loss: 1.60e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.0818 +[2026-03-20T21:08:36.181014Z] Loop 15713: Loss: 1.70e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.0870 +[2026-03-20T21:08:37.036421Z] Loop 15714: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0830 +[2026-03-20T21:08:37.890026Z] Loop 15715: Loss: 1.64e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0803 +[2026-03-20T21:08:38.744458Z] Loop 15716: Loss: 1.65e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0786 +[2026-03-20T21:08:39.599765Z] Loop 15717: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0815 +[2026-03-20T21:08:40.454056Z] Loop 15718: Loss: 1.63e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0829 +[2026-03-20T21:08:41.308866Z] Loop 15719: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0803 +[2026-03-20T21:08:42.202801Z] Loop 15720: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0809 +[2026-03-20T21:08:43.057834Z] Loop 15721: Loss: 1.47e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0785 +[2026-03-20T21:08:43.912940Z] Loop 15722: Loss: 1.69e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0824 +[2026-03-20T21:08:44.766668Z] Loop 15723: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0818 +[2026-03-20T21:08:45.621346Z] Loop 15724: Loss: 1.64e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0843 +[2026-03-20T21:08:46.476494Z] Loop 15725: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0848 +[2026-03-20T21:08:47.331188Z] Loop 15726: Loss: 1.74e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0865 +[2026-03-20T21:08:48.185346Z] Loop 15727: Loss: 1.68e-02, Avg Return: 0.861, Regret: 0.0008, Entropy: 0.0851 +[2026-03-20T21:08:49.038801Z] Loop 15728: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0813 +[2026-03-20T21:08:49.893518Z] Loop 15729: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0815 +[2026-03-20T21:08:50.787356Z] Loop 15730: Loss: 1.63e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0821 +[2026-03-20T21:08:51.641841Z] Loop 15731: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0832 +[2026-03-20T21:08:52.495656Z] Loop 15732: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0824 +[2026-03-20T21:08:53.351063Z] Loop 15733: Loss: 1.62e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0830 +[2026-03-20T21:08:54.206612Z] Loop 15734: Loss: 1.72e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0833 +[2026-03-20T21:08:55.061845Z] Loop 15735: Loss: 1.76e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0889 +[2026-03-20T21:08:55.917718Z] Loop 15736: Loss: 1.78e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0863 +[2026-03-20T21:08:56.771847Z] Loop 15737: Loss: 1.95e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0961 +[2026-03-20T21:08:57.627703Z] Loop 15738: Loss: 2.05e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0962 +[2026-03-20T21:08:58.482865Z] Loop 15739: Loss: 1.99e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0944 +[2026-03-20T21:08:59.378444Z] Loop 15740: Loss: 2.03e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0968 +[2026-03-20T21:09:00.231982Z] Loop 15741: Loss: 2.00e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0953 +[2026-03-20T21:09:01.085955Z] Loop 15742: Loss: 1.98e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0929 +[2026-03-20T21:09:01.940780Z] Loop 15743: Loss: 2.01e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0918 +[2026-03-20T21:09:02.795774Z] Loop 15744: Loss: 2.11e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.1019 +[2026-03-20T21:09:03.649613Z] Loop 15745: Loss: 2.22e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.1033 +[2026-03-20T21:09:04.503009Z] Loop 15746: Loss: 2.17e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.1037 +[2026-03-20T21:09:05.356658Z] Loop 15747: Loss: 2.12e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.1024 +[2026-03-20T21:09:06.211928Z] Loop 15748: Loss: 1.85e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0914 +[2026-03-20T21:09:07.066643Z] Loop 15749: Loss: 1.77e-02, Avg Return: 0.865, Regret: 0.0002, Entropy: 0.0865 +[2026-03-20T21:09:07.959131Z] Loop 15750: Loss: 1.81e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0877 +[2026-03-20T21:09:08.813116Z] Loop 15751: Loss: 1.70e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0816 +[2026-03-20T21:09:09.667953Z] Loop 15752: Loss: 1.76e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0863 +[2026-03-20T21:09:10.522988Z] Loop 15753: Loss: 1.66e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0812 +[2026-03-20T21:09:11.377549Z] Loop 15754: Loss: 1.60e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0806 +[2026-03-20T21:09:12.231162Z] Loop 15755: Loss: 1.52e-02, Avg Return: 0.865, Regret: 0.0001, Entropy: 0.0793 +[2026-03-20T21:09:13.084539Z] Loop 15756: Loss: 1.57e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0771 +[2026-03-20T21:09:13.939739Z] Loop 15757: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0741 +[2026-03-20T21:09:14.794939Z] Loop 15758: Loss: 1.53e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0778 +[2026-03-20T21:09:15.648516Z] Loop 15759: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0774 +[2026-03-20T21:09:16.540367Z] Loop 15760: Loss: 1.53e-02, Avg Return: 0.865, Regret: 0.0001, Entropy: 0.0772 +[2026-03-20T21:09:17.395618Z] Loop 15761: Loss: 1.44e-02, Avg Return: 0.865, Regret: 0.0001, Entropy: 0.0707 +[2026-03-20T21:09:18.250413Z] Loop 15762: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0737 +[2026-03-20T21:09:19.104533Z] Loop 15763: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0724 +[2026-03-20T21:09:19.958064Z] Loop 15764: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0696 +[2026-03-20T21:09:20.812858Z] Loop 15765: Loss: 1.29e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0687 +[2026-03-20T21:09:21.667568Z] Loop 15766: Loss: 1.39e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0695 +[2026-03-20T21:09:22.522258Z] Loop 15767: Loss: 1.23e-02, Avg Return: 0.865, Regret: 0.0001, Entropy: 0.0649 +[2026-03-20T21:09:23.376484Z] Loop 15768: Loss: 1.18e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0616 +[2026-03-20T21:09:24.230751Z] Loop 15769: Loss: 1.24e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0647 +[2026-03-20T21:09:25.124671Z] Loop 15770: Loss: 1.06e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0577 +[2026-03-20T21:09:25.979193Z] Loop 15771: Loss: 1.18e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0626 +[2026-03-20T21:09:26.834279Z] Loop 15772: Loss: 1.17e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0595 +[2026-03-20T21:09:27.689358Z] Loop 15773: Loss: 1.24e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0636 +[2026-03-20T21:09:28.543686Z] Loop 15774: Loss: 1.11e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0583 +[2026-03-20T21:09:29.398006Z] Loop 15775: Loss: 1.11e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0599 +[2026-03-20T21:09:30.251781Z] Loop 15776: Loss: 1.24e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0650 +[2026-03-20T21:09:31.105748Z] Loop 15777: Loss: 1.11e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0601 +[2026-03-20T21:09:31.959600Z] Loop 15778: Loss: 1.27e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0683 +[2026-03-20T21:09:32.814474Z] Loop 15779: Loss: 1.24e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0652 +[2026-03-20T21:09:33.707188Z] Loop 15780: Loss: 1.24e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0665 +[2026-03-20T21:09:34.561458Z] Loop 15781: Loss: 1.15e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0634 +[2026-03-20T21:09:35.415270Z] Loop 15782: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0648 +[2026-03-20T21:09:36.269500Z] Loop 15783: Loss: 1.30e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0647 +[2026-03-20T21:09:37.123468Z] Loop 15784: Loss: 1.24e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0665 +[2026-03-20T21:09:37.977953Z] Loop 15785: Loss: 1.14e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0615 +[2026-03-20T21:09:38.831633Z] Loop 15786: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0594 +[2026-03-20T21:09:39.686597Z] Loop 15787: Loss: 1.11e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0595 +[2026-03-20T21:09:40.541438Z] Loop 15788: Loss: 1.12e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0630 +[2026-03-20T21:09:41.395773Z] Loop 15789: Loss: 1.14e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0646 +[2026-03-20T21:09:42.288415Z] Loop 15790: Loss: 1.19e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0645 +[2026-03-20T21:09:43.141868Z] Loop 15791: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0648 +[2026-03-20T21:09:43.996127Z] Loop 15792: Loss: 1.12e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0603 +[2026-03-20T21:09:44.849553Z] Loop 15793: Loss: 1.15e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0618 +[2026-03-20T21:09:45.702970Z] Loop 15794: Loss: 1.07e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0597 +[2026-03-20T21:09:46.555777Z] Loop 15795: Loss: 1.19e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0667 +[2026-03-20T21:09:47.410066Z] Loop 15796: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0662 +[2026-03-20T21:09:48.265835Z] Loop 15797: Loss: 1.32e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0675 +[2026-03-20T21:09:49.120227Z] Loop 15798: Loss: 1.10e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0616 +[2026-03-20T21:09:49.974446Z] Loop 15799: Loss: 1.30e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0650 +[2026-03-20T21:09:50.865969Z] Loop 15800: Loss: 1.19e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0632 +[2026-03-20T21:09:51.719713Z] Loop 15801: Loss: 1.18e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0631 +[2026-03-20T21:09:52.574918Z] Loop 15802: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0669 +[2026-03-20T21:09:53.429807Z] Loop 15803: Loss: 1.25e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0640 +[2026-03-20T21:09:54.285468Z] Loop 15804: Loss: 1.22e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0638 +[2026-03-20T21:09:55.139986Z] Loop 15805: Loss: 1.42e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0687 +[2026-03-20T21:09:55.994781Z] Loop 15806: Loss: 1.39e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0714 +[2026-03-20T21:09:56.849978Z] Loop 15807: Loss: 1.32e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0711 +[2026-03-20T21:09:57.705000Z] Loop 15808: Loss: 1.50e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0747 +[2026-03-20T21:09:58.559536Z] Loop 15809: Loss: 1.34e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0699 +[2026-03-20T21:09:59.452507Z] Loop 15810: Loss: 1.51e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0742 +[2026-03-20T21:10:00.307618Z] Loop 15811: Loss: 1.34e-02, Avg Return: 0.861, Regret: 0.0005, Entropy: 0.0750 +[2026-03-20T21:10:01.161626Z] Loop 15812: Loss: 1.46e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0798 +[2026-03-20T21:10:02.016348Z] Loop 15813: Loss: 1.39e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0723 +[2026-03-20T21:10:02.870669Z] Loop 15814: Loss: 1.46e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0760 +[2026-03-20T21:10:03.726056Z] Loop 15815: Loss: 1.36e-02, Avg Return: 0.861, Regret: 0.0005, Entropy: 0.0700 +[2026-03-20T21:10:04.580995Z] Loop 15816: Loss: 1.38e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0735 +[2026-03-20T21:10:05.436223Z] Loop 15817: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0710 +[2026-03-20T21:10:06.290377Z] Loop 15818: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0667 +[2026-03-20T21:10:07.145728Z] Loop 15819: Loss: 1.30e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0711 +[2026-03-20T21:10:08.039246Z] Loop 15820: Loss: 1.28e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0677 +[2026-03-20T21:10:08.893202Z] Loop 15821: Loss: 1.23e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0655 +[2026-03-20T21:10:09.747525Z] Loop 15822: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0013, Entropy: 0.0681 +[2026-03-20T21:10:10.602059Z] Loop 15823: Loss: 1.29e-02, Avg Return: 0.864, Regret: 0.0013, Entropy: 0.0685 +[2026-03-20T21:10:11.456619Z] Loop 15824: Loss: 1.25e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0704 +[2026-03-20T21:10:12.311142Z] Loop 15825: Loss: 1.37e-02, Avg Return: 0.860, Regret: 0.0013, Entropy: 0.0708 +[2026-03-20T21:10:13.165768Z] Loop 15826: Loss: 1.32e-02, Avg Return: 0.862, Regret: 0.0013, Entropy: 0.0700 +[2026-03-20T21:10:14.021309Z] Loop 15827: Loss: 1.40e-02, Avg Return: 0.860, Regret: 0.0013, Entropy: 0.0747 +[2026-03-20T21:10:14.874295Z] Loop 15828: Loss: 1.28e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0711 +[2026-03-20T21:10:15.727932Z] Loop 15829: Loss: 1.23e-02, Avg Return: 0.861, Regret: 0.0013, Entropy: 0.0697 +[2026-03-20T21:10:16.621561Z] Loop 15830: Loss: 1.32e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0689 +[2026-03-20T21:10:17.475857Z] Loop 15831: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0641 +[2026-03-20T21:10:18.329175Z] Loop 15832: Loss: 1.18e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0662 +[2026-03-20T21:10:19.182929Z] Loop 15833: Loss: 1.27e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0646 +[2026-03-20T21:10:20.037617Z] Loop 15834: Loss: 1.15e-02, Avg Return: 0.865, Regret: 0.0009, Entropy: 0.0603 +[2026-03-20T21:10:20.892428Z] Loop 15835: Loss: 1.20e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0624 +[2026-03-20T21:10:21.745844Z] Loop 15836: Loss: 1.16e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0632 +[2026-03-20T21:10:22.600178Z] Loop 15837: Loss: 1.18e-02, Avg Return: 0.864, Regret: 0.0009, Entropy: 0.0616 +[2026-03-20T21:10:23.454398Z] Loop 15838: Loss: 1.15e-02, Avg Return: 0.862, Regret: 0.0009, Entropy: 0.0608 +[2026-03-20T21:10:24.310013Z] Loop 15839: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0009, Entropy: 0.0635 +[2026-03-20T21:10:25.204566Z] Loop 15840: Loss: 1.29e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0665 +[2026-03-20T21:10:26.058616Z] Loop 15841: Loss: 1.23e-02, Avg Return: 0.865, Regret: 0.0001, Entropy: 0.0644 +[2026-03-20T21:10:26.912617Z] Loop 15842: Loss: 1.26e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0595 +[2026-03-20T21:10:27.768247Z] Loop 15843: Loss: 1.24e-02, Avg Return: 0.865, Regret: 0.0001, Entropy: 0.0629 +[2026-03-20T21:10:28.623608Z] Loop 15844: Loss: 1.20e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0633 +[2026-03-20T21:10:29.476926Z] Loop 15845: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0641 +[2026-03-20T21:10:30.330617Z] Loop 15846: Loss: 1.29e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0671 +[2026-03-20T21:10:31.185474Z] Loop 15847: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0695 +[2026-03-20T21:10:32.040396Z] Loop 15848: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0704 +[2026-03-20T21:10:32.894323Z] Loop 15849: Loss: 1.52e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0731 +[2026-03-20T21:10:33.787196Z] Loop 15850: Loss: 1.50e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0745 +[2026-03-20T21:10:34.640980Z] Loop 15851: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0770 +[2026-03-20T21:10:35.495513Z] Loop 15852: Loss: 1.56e-02, Avg Return: 0.861, Regret: 0.0003, Entropy: 0.0774 +[2026-03-20T21:10:36.349990Z] Loop 15853: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0825 +[2026-03-20T21:10:37.203771Z] Loop 15854: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0822 +[2026-03-20T21:10:38.058830Z] Loop 15855: Loss: 1.74e-02, Avg Return: 0.861, Regret: 0.0003, Entropy: 0.0874 +[2026-03-20T21:10:38.914101Z] Loop 15856: Loss: 1.61e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0856 +[2026-03-20T21:10:39.769293Z] Loop 15857: Loss: 1.65e-02, Avg Return: 0.860, Regret: 0.0003, Entropy: 0.0855 +[2026-03-20T21:10:40.622937Z] Loop 15858: Loss: 1.59e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0823 +[2026-03-20T21:10:41.475704Z] Loop 15859: Loss: 1.50e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0793 +[2026-03-20T21:10:42.368115Z] Loop 15860: Loss: 1.52e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0797 +[2026-03-20T21:10:43.222602Z] Loop 15861: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0815 +[2026-03-20T21:10:44.077263Z] Loop 15862: Loss: 1.62e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0832 +[2026-03-20T21:10:44.931230Z] Loop 15863: Loss: 1.60e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0835 +[2026-03-20T21:10:45.784801Z] Loop 15864: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0854 +[2026-03-20T21:10:46.640301Z] Loop 15865: Loss: 1.67e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0833 +[2026-03-20T21:10:47.495293Z] Loop 15866: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0868 +[2026-03-20T21:10:48.349646Z] Loop 15867: Loss: 1.90e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0949 +[2026-03-20T21:10:49.202703Z] Loop 15868: Loss: 1.88e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0904 +[2026-03-20T21:10:50.057254Z] Loop 15869: Loss: 1.93e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0929 +[2026-03-20T21:10:50.950461Z] Loop 15870: Loss: 1.76e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.0907 +[2026-03-20T21:10:51.803846Z] Loop 15871: Loss: 1.80e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.0900 +[2026-03-20T21:10:52.657499Z] Loop 15872: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0907 +[2026-03-20T21:10:53.512285Z] Loop 15873: Loss: 1.87e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0930 +[2026-03-20T21:10:54.366833Z] Loop 15874: Loss: 1.80e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.0908 +[2026-03-20T21:10:55.220124Z] Loop 15875: Loss: 1.87e-02, Avg Return: 0.860, Regret: 0.0022, Entropy: 0.0928 +[2026-03-20T21:10:56.074635Z] Loop 15876: Loss: 2.09e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.1008 +[2026-03-20T21:10:56.928235Z] Loop 15877: Loss: 2.10e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.1012 +[2026-03-20T21:10:57.781779Z] Loop 15878: Loss: 2.08e-02, Avg Return: 0.861, Regret: 0.0022, Entropy: 0.1021 +[2026-03-20T21:10:58.635862Z] Loop 15879: Loss: 1.99e-02, Avg Return: 0.862, Regret: 0.0022, Entropy: 0.0960 +[2026-03-20T21:10:59.528020Z] Loop 15880: Loss: 1.88e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0911 +[2026-03-20T21:11:00.382501Z] Loop 15881: Loss: 1.77e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0860 +[2026-03-20T21:11:01.236956Z] Loop 15882: Loss: 1.63e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0815 +[2026-03-20T21:11:02.091379Z] Loop 15883: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0770 +[2026-03-20T21:11:02.945705Z] Loop 15884: Loss: 1.68e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0835 +[2026-03-20T21:11:03.800041Z] Loop 15885: Loss: 1.70e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0833 +[2026-03-20T21:11:04.654848Z] Loop 15886: Loss: 1.89e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0893 +[2026-03-20T21:11:05.509076Z] Loop 15887: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0872 +[2026-03-20T21:11:06.363356Z] Loop 15888: Loss: 1.75e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0819 +[2026-03-20T21:11:07.217572Z] Loop 15889: Loss: 1.91e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0927 +[2026-03-20T21:11:08.111965Z] Loop 15890: Loss: 1.97e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0950 +[2026-03-20T21:11:08.966281Z] Loop 15891: Loss: 1.90e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.0919 +[2026-03-20T21:11:09.819977Z] Loop 15892: Loss: 2.00e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.0969 +[2026-03-20T21:11:10.673475Z] Loop 15893: Loss: 2.10e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.1011 +[2026-03-20T21:11:11.528453Z] Loop 15894: Loss: 2.23e-02, Avg Return: 0.861, Regret: 0.0015, Entropy: 0.1100 +[2026-03-20T21:11:12.381112Z] Loop 15895: Loss: 2.35e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.1114 +[2026-03-20T21:11:13.233673Z] Loop 15896: Loss: 2.40e-02, Avg Return: 0.863, Regret: 0.0015, Entropy: 0.1162 +[2026-03-20T21:11:14.088008Z] Loop 15897: Loss: 2.38e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.1167 +[2026-03-20T21:11:14.942619Z] Loop 15898: Loss: 2.39e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.1132 +[2026-03-20T21:11:15.796380Z] Loop 15899: Loss: 2.37e-02, Avg Return: 0.862, Regret: 0.0015, Entropy: 0.1123 +[2026-03-20T21:11:16.688252Z] Loop 15900: Loss: 2.37e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.1156 +[2026-03-20T21:11:17.541776Z] Loop 15901: Loss: 2.27e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.1108 +[2026-03-20T21:11:18.397162Z] Loop 15902: Loss: 2.28e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.1124 +[2026-03-20T21:11:19.251860Z] Loop 15903: Loss: 2.14e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.1108 +[2026-03-20T21:11:20.104549Z] Loop 15904: Loss: 2.25e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.1147 +[2026-03-20T21:11:20.956700Z] Loop 15905: Loss: 2.43e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.1188 +[2026-03-20T21:11:21.812442Z] Loop 15906: Loss: 2.22e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.1130 +[2026-03-20T21:11:22.666670Z] Loop 15907: Loss: 2.26e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.1128 +[2026-03-20T21:11:23.519851Z] Loop 15908: Loss: 2.27e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.1090 +[2026-03-20T21:11:24.373207Z] Loop 15909: Loss: 2.09e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.1106 +[2026-03-20T21:11:25.266572Z] Loop 15910: Loss: 2.09e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.1031 +[2026-03-20T21:11:26.122047Z] Loop 15911: Loss: 1.84e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0975 +[2026-03-20T21:11:26.976276Z] Loop 15912: Loss: 1.93e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0981 +[2026-03-20T21:11:27.830320Z] Loop 15913: Loss: 1.78e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0904 +[2026-03-20T21:11:28.685184Z] Loop 15914: Loss: 1.65e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0842 +[2026-03-20T21:11:29.540250Z] Loop 15915: Loss: 1.59e-02, Avg Return: 0.864, Regret: 0.0010, Entropy: 0.0806 +[2026-03-20T21:11:30.394495Z] Loop 15916: Loss: 1.63e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0836 +[2026-03-20T21:11:31.248215Z] Loop 15917: Loss: 1.64e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0837 +[2026-03-20T21:11:32.102673Z] Loop 15918: Loss: 1.70e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0808 +[2026-03-20T21:11:32.956721Z] Loop 15919: Loss: 1.89e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0922 +[2026-03-20T21:11:33.848838Z] Loop 15920: Loss: 2.18e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.1010 +[2026-03-20T21:11:34.702384Z] Loop 15921: Loss: 2.21e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.1028 +[2026-03-20T21:11:35.556241Z] Loop 15922: Loss: 2.09e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0998 +[2026-03-20T21:11:36.410613Z] Loop 15923: Loss: 1.96e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0939 +[2026-03-20T21:11:37.266331Z] Loop 15924: Loss: 2.12e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0997 +[2026-03-20T21:11:38.121213Z] Loop 15925: Loss: 1.91e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0945 +[2026-03-20T21:11:38.976776Z] Loop 15926: Loss: 1.90e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0910 +[2026-03-20T21:11:39.830350Z] Loop 15927: Loss: 1.86e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0899 +[2026-03-20T21:11:40.683232Z] Loop 15928: Loss: 1.82e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0874 +[2026-03-20T21:11:41.537949Z] Loop 15929: Loss: 1.89e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0903 +[2026-03-20T21:11:42.432400Z] Loop 15930: Loss: 1.89e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0883 +[2026-03-20T21:11:43.287246Z] Loop 15931: Loss: 1.76e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0889 +[2026-03-20T21:11:44.142264Z] Loop 15932: Loss: 1.83e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0881 +[2026-03-20T21:11:44.998065Z] Loop 15933: Loss: 1.82e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0856 +[2026-03-20T21:11:45.854148Z] Loop 15934: Loss: 1.73e-02, Avg Return: 0.865, Regret: 0.0001, Entropy: 0.0875 +[2026-03-20T21:11:46.709371Z] Loop 15935: Loss: 1.75e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0874 +[2026-03-20T21:11:47.563621Z] Loop 15936: Loss: 1.70e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0851 +[2026-03-20T21:11:48.417502Z] Loop 15937: Loss: 1.62e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0809 +[2026-03-20T21:11:49.273718Z] Loop 15938: Loss: 1.60e-02, Avg Return: 0.865, Regret: 0.0001, Entropy: 0.0766 +[2026-03-20T21:11:50.128879Z] Loop 15939: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0815 +[2026-03-20T21:11:51.026478Z] Loop 15940: Loss: 1.64e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0800 +[2026-03-20T21:11:51.879085Z] Loop 15941: Loss: 1.63e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0787 +[2026-03-20T21:11:52.732925Z] Loop 15942: Loss: 1.50e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0749 +[2026-03-20T21:11:53.587167Z] Loop 15943: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0770 +[2026-03-20T21:11:54.440738Z] Loop 15944: Loss: 1.56e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0742 +[2026-03-20T21:11:55.294217Z] Loop 15945: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0761 +[2026-03-20T21:11:56.148424Z] Loop 15946: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0718 +[2026-03-20T21:11:57.002546Z] Loop 15947: Loss: 1.39e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0693 +[2026-03-20T21:11:57.856324Z] Loop 15948: Loss: 1.40e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0712 +[2026-03-20T21:11:58.709756Z] Loop 15949: Loss: 1.36e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0675 +[2026-03-20T21:11:59.603893Z] Loop 15950: Loss: 1.40e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0697 +[2026-03-20T21:12:00.459230Z] Loop 15951: Loss: 1.22e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0649 +[2026-03-20T21:12:01.314145Z] Loop 15952: Loss: 1.22e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0649 +[2026-03-20T21:12:02.169888Z] Loop 15953: Loss: 1.23e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0649 +[2026-03-20T21:12:03.025151Z] Loop 15954: Loss: 1.31e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0674 +[2026-03-20T21:12:03.880320Z] Loop 15955: Loss: 1.22e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0637 +[2026-03-20T21:12:04.734905Z] Loop 15956: Loss: 1.26e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0642 +[2026-03-20T21:12:05.590250Z] Loop 15957: Loss: 1.29e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0666 +[2026-03-20T21:12:06.446148Z] Loop 15958: Loss: 1.31e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0715 +[2026-03-20T21:12:07.300117Z] Loop 15959: Loss: 1.32e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0673 +[2026-03-20T21:12:08.194933Z] Loop 15960: Loss: 1.49e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0717 +[2026-03-20T21:12:09.048793Z] Loop 15961: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0714 +[2026-03-20T21:12:09.903962Z] Loop 15962: Loss: 1.29e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0687 +[2026-03-20T21:12:10.758852Z] Loop 15963: Loss: 1.40e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0736 +[2026-03-20T21:12:11.613115Z] Loop 15964: Loss: 1.40e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0726 +[2026-03-20T21:12:12.468288Z] Loop 15965: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0732 +[2026-03-20T21:12:13.323536Z] Loop 15966: Loss: 1.33e-02, Avg Return: 0.865, Regret: 0.0003, Entropy: 0.0685 +[2026-03-20T21:12:14.177689Z] Loop 15967: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0669 +[2026-03-20T21:12:15.032025Z] Loop 15968: Loss: 1.32e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0691 +[2026-03-20T21:12:15.885291Z] Loop 15969: Loss: 1.45e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0720 +[2026-03-20T21:12:16.778412Z] Loop 15970: Loss: 1.49e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0763 +[2026-03-20T21:12:17.633238Z] Loop 15971: Loss: 1.35e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0722 +[2026-03-20T21:12:18.486226Z] Loop 15972: Loss: 1.43e-02, Avg Return: 0.865, Regret: 0.0001, Entropy: 0.0721 +[2026-03-20T21:12:19.340069Z] Loop 15973: Loss: 1.45e-02, Avg Return: 0.865, Regret: 0.0001, Entropy: 0.0670 +[2026-03-20T21:12:20.194609Z] Loop 15974: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0725 +[2026-03-20T21:12:21.048381Z] Loop 15975: Loss: 1.38e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0696 +[2026-03-20T21:12:21.902445Z] Loop 15976: Loss: 1.49e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0744 +[2026-03-20T21:12:22.756386Z] Loop 15977: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0781 +[2026-03-20T21:12:23.610191Z] Loop 15978: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0762 +[2026-03-20T21:12:24.464672Z] Loop 15979: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0786 +[2026-03-20T21:12:25.358728Z] Loop 15980: Loss: 1.60e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0813 +[2026-03-20T21:12:26.214072Z] Loop 15981: Loss: 1.66e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0810 +[2026-03-20T21:12:27.068582Z] Loop 15982: Loss: 1.66e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0837 +[2026-03-20T21:12:27.922905Z] Loop 15983: Loss: 1.73e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0844 +[2026-03-20T21:12:28.777157Z] Loop 15984: Loss: 1.71e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0890 +[2026-03-20T21:12:29.631015Z] Loop 15985: Loss: 1.80e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0874 +[2026-03-20T21:12:30.485041Z] Loop 15986: Loss: 1.85e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0928 +[2026-03-20T21:12:31.338976Z] Loop 15987: Loss: 2.10e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.1040 +[2026-03-20T21:12:32.194327Z] Loop 15988: Loss: 2.10e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.1041 +[2026-03-20T21:12:33.049533Z] Loop 15989: Loss: 2.01e-02, Avg Return: 0.865, Regret: 0.0001, Entropy: 0.1015 +[2026-03-20T21:12:33.944434Z] Loop 15990: Loss: 1.87e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.0934 +[2026-03-20T21:12:34.799536Z] Loop 15991: Loss: 2.01e-02, Avg Return: 0.864, Regret: 0.0005, Entropy: 0.1001 +[2026-03-20T21:12:35.654852Z] Loop 15992: Loss: 1.67e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0883 +[2026-03-20T21:12:36.509486Z] Loop 15993: Loss: 1.69e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0876 +[2026-03-20T21:12:37.364043Z] Loop 15994: Loss: 1.63e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0873 +[2026-03-20T21:12:38.216945Z] Loop 15995: Loss: 1.64e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0857 +[2026-03-20T21:12:39.070819Z] Loop 15996: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0859 +[2026-03-20T21:12:39.926558Z] Loop 15997: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0914 +[2026-03-20T21:12:40.780956Z] Loop 15998: Loss: 1.63e-02, Avg Return: 0.862, Regret: 0.0005, Entropy: 0.0865 +[2026-03-20T21:12:41.634965Z] Loop 15999: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0005, Entropy: 0.0938 +[2026-03-20T21:12:42.527609Z] Loop 16000: Loss: 1.69e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0911 +[2026-03-20T21:12:43.382333Z] Loop 16001: Loss: 1.67e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0915 +[2026-03-20T21:12:44.236040Z] Loop 16002: Loss: 1.78e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0934 +[2026-03-20T21:12:45.089625Z] Loop 16003: Loss: 1.74e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0929 +[2026-03-20T21:12:45.943336Z] Loop 16004: Loss: 1.80e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0927 +[2026-03-20T21:12:46.797852Z] Loop 16005: Loss: 1.68e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0867 +[2026-03-20T21:12:47.652163Z] Loop 16006: Loss: 1.83e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0939 +[2026-03-20T21:12:48.505987Z] Loop 16007: Loss: 1.70e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0905 +[2026-03-20T21:12:49.359397Z] Loop 16008: Loss: 1.87e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0937 +[2026-03-20T21:12:50.214104Z] Loop 16009: Loss: 1.86e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0908 +[2026-03-20T21:12:51.106738Z] Loop 16010: Loss: 1.83e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0914 +[2026-03-20T21:12:51.960193Z] Loop 16011: Loss: 1.87e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0921 +[2026-03-20T21:12:52.813713Z] Loop 16012: Loss: 1.84e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0962 +[2026-03-20T21:12:53.668455Z] Loop 16013: Loss: 2.02e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.1029 +[2026-03-20T21:12:54.522445Z] Loop 16014: Loss: 2.08e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.1033 +[2026-03-20T21:12:55.376756Z] Loop 16015: Loss: 2.15e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.1036 +[2026-03-20T21:12:56.230945Z] Loop 16016: Loss: 2.05e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.1027 +[2026-03-20T21:12:57.086020Z] Loop 16017: Loss: 2.08e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0993 +[2026-03-20T21:12:57.939357Z] Loop 16018: Loss: 2.01e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0982 +[2026-03-20T21:12:58.792660Z] Loop 16019: Loss: 2.08e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.1004 +[2026-03-20T21:12:59.686691Z] Loop 16020: Loss: 1.99e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0988 +[2026-03-20T21:13:00.543084Z] Loop 16021: Loss: 1.92e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0956 +[2026-03-20T21:13:01.398072Z] Loop 16022: Loss: 1.91e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0984 +[2026-03-20T21:13:02.252699Z] Loop 16023: Loss: 1.92e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0982 +[2026-03-20T21:13:03.107627Z] Loop 16024: Loss: 1.95e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.1020 +[2026-03-20T21:13:03.961908Z] Loop 16025: Loss: 1.82e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0945 +[2026-03-20T21:13:04.816262Z] Loop 16026: Loss: 1.82e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0982 +[2026-03-20T21:13:05.670467Z] Loop 16027: Loss: 1.87e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.1015 +[2026-03-20T21:13:06.524821Z] Loop 16028: Loss: 2.00e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0999 +[2026-03-20T21:13:07.379871Z] Loop 16029: Loss: 1.93e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0966 +[2026-03-20T21:13:08.273650Z] Loop 16030: Loss: 1.90e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0967 +[2026-03-20T21:13:09.127669Z] Loop 16031: Loss: 1.77e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0952 +[2026-03-20T21:13:09.980701Z] Loop 16032: Loss: 1.83e-02, Avg Return: 0.864, Regret: 0.0016, Entropy: 0.0918 +[2026-03-20T21:13:10.836305Z] Loop 16033: Loss: 1.72e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0919 +[2026-03-20T21:13:11.691137Z] Loop 16034: Loss: 1.81e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0903 +[2026-03-20T21:13:12.545604Z] Loop 16035: Loss: 1.68e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0868 +[2026-03-20T21:13:13.401048Z] Loop 16036: Loss: 1.73e-02, Avg Return: 0.862, Regret: 0.0016, Entropy: 0.0868 +[2026-03-20T21:13:14.256450Z] Loop 16037: Loss: 1.71e-02, Avg Return: 0.863, Regret: 0.0016, Entropy: 0.0848 +[2026-03-20T21:13:15.112040Z] Loop 16038: Loss: 2.00e-02, Avg Return: 0.861, Regret: 0.0016, Entropy: 0.0970 +[2026-03-20T21:13:15.967320Z] Loop 16039: Loss: 1.97e-02, Avg Return: 0.865, Regret: 0.0016, Entropy: 0.0983 +[2026-03-20T21:13:16.863404Z] Loop 16040: Loss: 2.09e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0963 +[2026-03-20T21:13:17.718093Z] Loop 16041: Loss: 2.16e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.1004 +[2026-03-20T21:13:18.572742Z] Loop 16042: Loss: 2.06e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.1014 +[2026-03-20T21:13:19.427537Z] Loop 16043: Loss: 2.08e-02, Avg Return: 0.861, Regret: 0.0006, Entropy: 0.1007 +[2026-03-20T21:13:20.282592Z] Loop 16044: Loss: 2.03e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0983 +[2026-03-20T21:13:21.137617Z] Loop 16045: Loss: 1.77e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0878 +[2026-03-20T21:13:21.991715Z] Loop 16046: Loss: 1.63e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0822 +[2026-03-20T21:13:22.845604Z] Loop 16047: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0814 +[2026-03-20T21:13:23.699458Z] Loop 16048: Loss: 1.46e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0753 +[2026-03-20T21:13:24.552934Z] Loop 16049: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0699 +[2026-03-20T21:13:25.445117Z] Loop 16050: Loss: 1.24e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0666 +[2026-03-20T21:13:26.299559Z] Loop 16051: Loss: 1.23e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0671 +[2026-03-20T21:13:27.155640Z] Loop 16052: Loss: 1.22e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0631 +[2026-03-20T21:13:28.011219Z] Loop 16053: Loss: 1.30e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0653 +[2026-03-20T21:13:28.865495Z] Loop 16054: Loss: 1.17e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0656 +[2026-03-20T21:13:29.719753Z] Loop 16055: Loss: 1.16e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0618 +[2026-03-20T21:13:30.576291Z] Loop 16056: Loss: 1.17e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0618 +[2026-03-20T21:13:31.431716Z] Loop 16057: Loss: 1.12e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0615 +[2026-03-20T21:13:32.286903Z] Loop 16058: Loss: 1.18e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0619 +[2026-03-20T21:13:33.142202Z] Loop 16059: Loss: 1.17e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0619 +[2026-03-20T21:13:34.035181Z] Loop 16060: Loss: 1.17e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0620 +[2026-03-20T21:13:34.889205Z] Loop 16061: Loss: 1.20e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0644 +[2026-03-20T21:13:35.744086Z] Loop 16062: Loss: 1.15e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0608 +[2026-03-20T21:13:36.598837Z] Loop 16063: Loss: 1.11e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0589 +[2026-03-20T21:13:37.454737Z] Loop 16064: Loss: 1.07e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0590 +[2026-03-20T21:13:38.310523Z] Loop 16065: Loss: 1.06e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0610 +[2026-03-20T21:13:39.165567Z] Loop 16066: Loss: 1.02e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0575 +[2026-03-20T21:13:40.019457Z] Loop 16067: Loss: 1.10e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0587 +[2026-03-20T21:13:40.874302Z] Loop 16068: Loss: 1.08e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0613 +[2026-03-20T21:13:41.729326Z] Loop 16069: Loss: 1.15e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0625 +[2026-03-20T21:13:42.623970Z] Loop 16070: Loss: 1.14e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0598 +[2026-03-20T21:13:43.479283Z] Loop 16071: Loss: 1.17e-02, Avg Return: 0.861, Regret: 0.0011, Entropy: 0.0597 +[2026-03-20T21:13:44.334170Z] Loop 16072: Loss: 1.08e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0602 +[2026-03-20T21:13:45.187073Z] Loop 16073: Loss: 1.05e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0597 +[2026-03-20T21:13:46.041554Z] Loop 16074: Loss: 1.04e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0569 +[2026-03-20T21:13:46.895575Z] Loop 16075: Loss: 1.09e-02, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0558 +[2026-03-20T21:13:47.750215Z] Loop 16076: Loss: 9.81e-03, Avg Return: 0.863, Regret: 0.0011, Entropy: 0.0547 +[2026-03-20T21:13:48.604934Z] Loop 16077: Loss: 1.03e-02, Avg Return: 0.864, Regret: 0.0011, Entropy: 0.0565 +[2026-03-20T21:13:49.459065Z] Loop 16078: Loss: 1.09e-02, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0574 +[2026-03-20T21:13:50.313421Z] Loop 16079: Loss: 9.98e-03, Avg Return: 0.862, Regret: 0.0011, Entropy: 0.0564 +[2026-03-20T21:13:51.205224Z] Loop 16080: Loss: 1.04e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0536 +[2026-03-20T21:13:52.058577Z] Loop 16081: Loss: 1.10e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0579 +[2026-03-20T21:13:52.912127Z] Loop 16082: Loss: 9.73e-03, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0538 +[2026-03-20T21:13:53.765634Z] Loop 16083: Loss: 1.05e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0535 +[2026-03-20T21:13:54.619930Z] Loop 16084: Loss: 1.02e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0522 +[2026-03-20T21:13:55.473102Z] Loop 16085: Loss: 1.09e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0545 +[2026-03-20T21:13:56.326269Z] Loop 16086: Loss: 1.01e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0536 +[2026-03-20T21:13:57.180544Z] Loop 16087: Loss: 9.71e-03, Avg Return: 0.865, Regret: 0.0007, Entropy: 0.0510 +[2026-03-20T21:13:58.034527Z] Loop 16088: Loss: 1.06e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0535 +[2026-03-20T21:13:58.887991Z] Loop 16089: Loss: 1.07e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0590 +[2026-03-20T21:13:59.779033Z] Loop 16090: Loss: 1.04e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0537 +[2026-03-20T21:14:00.632640Z] Loop 16091: Loss: 9.90e-03, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0527 +[2026-03-20T21:14:01.487356Z] Loop 16092: Loss: 1.04e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0565 +[2026-03-20T21:14:02.341075Z] Loop 16093: Loss: 1.07e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0565 +[2026-03-20T21:14:03.194687Z] Loop 16094: Loss: 1.07e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0557 +[2026-03-20T21:14:04.048406Z] Loop 16095: Loss: 1.13e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0564 +[2026-03-20T21:14:04.902751Z] Loop 16096: Loss: 1.11e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0580 +[2026-03-20T21:14:05.757337Z] Loop 16097: Loss: 1.22e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0586 +[2026-03-20T21:14:06.611505Z] Loop 16098: Loss: 1.10e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0608 +[2026-03-20T21:14:07.465321Z] Loop 16099: Loss: 1.34e-02, Avg Return: 0.862, Regret: 0.0003, Entropy: 0.0634 +[2026-03-20T21:14:08.356691Z] Loop 16100: Loss: 1.26e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0623 +[2026-03-20T21:14:09.211233Z] Loop 16101: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0669 +[2026-03-20T21:14:10.065383Z] Loop 16102: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0670 +[2026-03-20T21:14:10.919791Z] Loop 16103: Loss: 1.29e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0643 +[2026-03-20T21:14:11.773746Z] Loop 16104: Loss: 1.32e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0683 +[2026-03-20T21:14:12.629606Z] Loop 16105: Loss: 1.36e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0702 +[2026-03-20T21:14:13.483776Z] Loop 16106: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0685 +[2026-03-20T21:14:14.338512Z] Loop 16107: Loss: 1.46e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0696 +[2026-03-20T21:14:15.191039Z] Loop 16108: Loss: 1.41e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0705 +[2026-03-20T21:14:16.044286Z] Loop 16109: Loss: 1.52e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0723 +[2026-03-20T21:14:16.937033Z] Loop 16110: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0745 +[2026-03-20T21:14:17.792336Z] Loop 16111: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0755 +[2026-03-20T21:14:18.647762Z] Loop 16112: Loss: 1.51e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0794 +[2026-03-20T21:14:19.503504Z] Loop 16113: Loss: 1.64e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0797 +[2026-03-20T21:14:20.358212Z] Loop 16114: Loss: 1.51e-02, Avg Return: 0.865, Regret: 0.0002, Entropy: 0.0755 +[2026-03-20T21:14:21.212170Z] Loop 16115: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0778 +[2026-03-20T21:14:22.066701Z] Loop 16116: Loss: 1.50e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0744 +[2026-03-20T21:14:22.921408Z] Loop 16117: Loss: 1.56e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0752 +[2026-03-20T21:14:23.775533Z] Loop 16118: Loss: 1.52e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0749 +[2026-03-20T21:14:24.629741Z] Loop 16119: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0741 +[2026-03-20T21:14:25.523063Z] Loop 16120: Loss: 1.51e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0743 +[2026-03-20T21:14:26.377561Z] Loop 16121: Loss: 1.47e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0768 +[2026-03-20T21:14:27.231506Z] Loop 16122: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0780 +[2026-03-20T21:14:28.085682Z] Loop 16123: Loss: 1.53e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0821 +[2026-03-20T21:14:28.939954Z] Loop 16124: Loss: 1.73e-02, Avg Return: 0.861, Regret: 0.0004, Entropy: 0.0867 +[2026-03-20T21:14:29.794728Z] Loop 16125: Loss: 1.89e-02, Avg Return: 0.860, Regret: 0.0004, Entropy: 0.0916 +[2026-03-20T21:14:30.648602Z] Loop 16126: Loss: 1.83e-02, Avg Return: 0.859, Regret: 0.0004, Entropy: 0.0972 +[2026-03-20T21:14:31.501909Z] Loop 16127: Loss: 1.88e-02, Avg Return: 0.858, Regret: 0.0004, Entropy: 0.0981 +[2026-03-20T21:14:32.356007Z] Loop 16128: Loss: 1.84e-02, Avg Return: 0.859, Regret: 0.0004, Entropy: 0.0960 +[2026-03-20T21:14:33.210506Z] Loop 16129: Loss: 1.68e-02, Avg Return: 0.858, Regret: 0.0004, Entropy: 0.0909 +[2026-03-20T21:14:34.105636Z] Loop 16130: Loss: 1.72e-02, Avg Return: 0.860, Regret: 0.0034, Entropy: 0.0900 +[2026-03-20T21:14:34.959812Z] Loop 16131: Loss: 1.54e-02, Avg Return: 0.861, Regret: 0.0034, Entropy: 0.0827 +[2026-03-20T21:14:35.813458Z] Loop 16132: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0034, Entropy: 0.0817 +[2026-03-20T21:14:36.668526Z] Loop 16133: Loss: 1.42e-02, Avg Return: 0.862, Regret: 0.0034, Entropy: 0.0755 +[2026-03-20T21:14:37.523571Z] Loop 16134: Loss: 1.42e-02, Avg Return: 0.861, Regret: 0.0034, Entropy: 0.0780 +[2026-03-20T21:14:38.377331Z] Loop 16135: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0034, Entropy: 0.0821 +[2026-03-20T21:14:39.230621Z] Loop 16136: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0034, Entropy: 0.0793 +[2026-03-20T21:14:40.085150Z] Loop 16137: Loss: 1.50e-02, Avg Return: 0.861, Regret: 0.0034, Entropy: 0.0798 +[2026-03-20T21:14:40.942122Z] Loop 16138: Loss: 1.52e-02, Avg Return: 0.861, Regret: 0.0034, Entropy: 0.0782 +[2026-03-20T21:14:41.796184Z] Loop 16139: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0034, Entropy: 0.0761 +[2026-03-20T21:14:42.692453Z] Loop 16140: Loss: 1.58e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0813 +[2026-03-20T21:14:43.546658Z] Loop 16141: Loss: 1.52e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0781 +[2026-03-20T21:14:44.400816Z] Loop 16142: Loss: 1.48e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0762 +[2026-03-20T21:14:45.254913Z] Loop 16143: Loss: 1.44e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.0729 +[2026-03-20T21:14:46.110048Z] Loop 16144: Loss: 1.44e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.0750 +[2026-03-20T21:14:46.964604Z] Loop 16145: Loss: 1.47e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0710 +[2026-03-20T21:14:47.820165Z] Loop 16146: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0756 +[2026-03-20T21:14:48.675289Z] Loop 16147: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0777 +[2026-03-20T21:14:49.529746Z] Loop 16148: Loss: 1.55e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.0772 +[2026-03-20T21:14:50.383715Z] Loop 16149: Loss: 1.57e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.0765 +[2026-03-20T21:14:51.278012Z] Loop 16150: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0767 +[2026-03-20T21:14:52.132783Z] Loop 16151: Loss: 1.41e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0716 +[2026-03-20T21:14:52.987779Z] Loop 16152: Loss: 1.45e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0764 +[2026-03-20T21:14:53.842077Z] Loop 16153: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0733 +[2026-03-20T21:14:54.695909Z] Loop 16154: Loss: 1.36e-02, Avg Return: 0.864, Regret: 0.0008, Entropy: 0.0705 +[2026-03-20T21:14:55.549716Z] Loop 16155: Loss: 1.41e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0715 +[2026-03-20T21:14:56.404083Z] Loop 16156: Loss: 1.43e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0724 +[2026-03-20T21:14:57.257711Z] Loop 16157: Loss: 1.40e-02, Avg Return: 0.862, Regret: 0.0008, Entropy: 0.0706 +[2026-03-20T21:14:58.110964Z] Loop 16158: Loss: 1.28e-02, Avg Return: 0.863, Regret: 0.0008, Entropy: 0.0656 +[2026-03-20T21:14:58.964228Z] Loop 16159: Loss: 1.38e-02, Avg Return: 0.865, Regret: 0.0008, Entropy: 0.0700 +[2026-03-20T21:14:59.860866Z] Loop 16160: Loss: 1.44e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0686 +[2026-03-20T21:15:00.715778Z] Loop 16161: Loss: 1.38e-02, Avg Return: 0.865, Regret: 0.0003, Entropy: 0.0693 +[2026-03-20T21:15:01.570538Z] Loop 16162: Loss: 1.35e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0699 +[2026-03-20T21:15:02.426851Z] Loop 16163: Loss: 1.41e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0717 +[2026-03-20T21:15:03.282876Z] Loop 16164: Loss: 1.44e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0706 +[2026-03-20T21:15:04.138022Z] Loop 16165: Loss: 1.34e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0667 +[2026-03-20T21:15:04.994160Z] Loop 16166: Loss: 1.25e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0635 +[2026-03-20T21:15:05.848665Z] Loop 16167: Loss: 1.39e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0689 +[2026-03-20T21:15:06.703865Z] Loop 16168: Loss: 1.29e-02, Avg Return: 0.863, Regret: 0.0003, Entropy: 0.0651 +[2026-03-20T21:15:07.559270Z] Loop 16169: Loss: 1.20e-02, Avg Return: 0.864, Regret: 0.0003, Entropy: 0.0616 +[2026-03-20T21:15:08.453412Z] Loop 16170: Loss: 1.16e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0637 +[2026-03-20T21:15:09.307347Z] Loop 16171: Loss: 1.09e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0595 +[2026-03-20T21:15:10.160766Z] Loop 16172: Loss: 1.08e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0562 +[2026-03-20T21:15:11.014390Z] Loop 16173: Loss: 1.04e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0556 +[2026-03-20T21:15:11.868132Z] Loop 16174: Loss: 1.02e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0565 +[2026-03-20T21:15:12.723298Z] Loop 16175: Loss: 1.08e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0560 +[2026-03-20T21:15:13.578497Z] Loop 16176: Loss: 1.05e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0557 +[2026-03-20T21:15:14.432713Z] Loop 16177: Loss: 1.07e-02, Avg Return: 0.863, Regret: 0.0002, Entropy: 0.0570 +[2026-03-20T21:15:15.287080Z] Loop 16178: Loss: 1.01e-02, Avg Return: 0.864, Regret: 0.0002, Entropy: 0.0539 +[2026-03-20T21:15:16.141518Z] Loop 16179: Loss: 1.08e-02, Avg Return: 0.862, Regret: 0.0002, Entropy: 0.0557 +[2026-03-20T21:15:17.035220Z] Loop 16180: Loss: 1.04e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0556 +[2026-03-20T21:15:17.889601Z] Loop 16181: Loss: 1.07e-02, Avg Return: 0.865, Regret: 0.0004, Entropy: 0.0540 +[2026-03-20T21:15:18.745236Z] Loop 16182: Loss: 1.12e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0574 +[2026-03-20T21:15:19.601457Z] Loop 16183: Loss: 9.93e-03, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0556 +[2026-03-20T21:15:20.456764Z] Loop 16184: Loss: 1.08e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0598 +[2026-03-20T21:15:21.311251Z] Loop 16185: Loss: 1.04e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0571 +[2026-03-20T21:15:22.165142Z] Loop 16186: Loss: 1.21e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0637 +[2026-03-20T21:15:23.020642Z] Loop 16187: Loss: 1.12e-02, Avg Return: 0.861, Regret: 0.0004, Entropy: 0.0612 +[2026-03-20T21:15:23.875944Z] Loop 16188: Loss: 1.13e-02, Avg Return: 0.858, Regret: 0.0004, Entropy: 0.0659 +[2026-03-20T21:15:24.730068Z] Loop 16189: Loss: 1.23e-02, Avg Return: 0.859, Regret: 0.0004, Entropy: 0.0651 +[2026-03-20T21:15:25.622512Z] Loop 16190: Loss: 1.26e-02, Avg Return: 0.859, Regret: 0.0043, Entropy: 0.0687 +[2026-03-20T21:15:26.476157Z] Loop 16191: Loss: 1.22e-02, Avg Return: 0.859, Regret: 0.0043, Entropy: 0.0672 +[2026-03-20T21:15:27.330371Z] Loop 16192: Loss: 1.23e-02, Avg Return: 0.859, Regret: 0.0043, Entropy: 0.0681 +[2026-03-20T21:15:28.183821Z] Loop 16193: Loss: 1.23e-02, Avg Return: 0.861, Regret: 0.0043, Entropy: 0.0684 +[2026-03-20T21:15:29.036731Z] Loop 16194: Loss: 1.25e-02, Avg Return: 0.861, Regret: 0.0043, Entropy: 0.0659 +[2026-03-20T21:15:29.890345Z] Loop 16195: Loss: 1.21e-02, Avg Return: 0.862, Regret: 0.0043, Entropy: 0.0656 +[2026-03-20T21:15:30.743515Z] Loop 16196: Loss: 1.15e-02, Avg Return: 0.862, Regret: 0.0043, Entropy: 0.0662 +[2026-03-20T21:15:31.597454Z] Loop 16197: Loss: 1.19e-02, Avg Return: 0.862, Regret: 0.0043, Entropy: 0.0664 +[2026-03-20T21:15:32.450781Z] Loop 16198: Loss: 1.19e-02, Avg Return: 0.862, Regret: 0.0043, Entropy: 0.0681 +[2026-03-20T21:15:33.303955Z] Loop 16199: Loss: 1.18e-02, Avg Return: 0.863, Regret: 0.0043, Entropy: 0.0635 +[2026-03-20T21:15:34.197172Z] Loop 16200: Loss: 1.17e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0642 +[2026-03-20T21:15:35.050940Z] Loop 16201: Loss: 1.14e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0644 +[2026-03-20T21:15:35.905140Z] Loop 16202: Loss: 1.30e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0643 +[2026-03-20T21:15:36.757987Z] Loop 16203: Loss: 1.15e-02, Avg Return: 0.862, Regret: 0.0007, Entropy: 0.0633 +[2026-03-20T21:15:37.612029Z] Loop 16204: Loss: 1.13e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0631 +[2026-03-20T21:15:38.468005Z] Loop 16205: Loss: 1.16e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0637 +[2026-03-20T21:15:39.323205Z] Loop 16206: Loss: 1.22e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0670 +[2026-03-20T21:15:40.176945Z] Loop 16207: Loss: 1.18e-02, Avg Return: 0.864, Regret: 0.0007, Entropy: 0.0675 +[2026-03-20T21:15:41.029981Z] Loop 16208: Loss: 1.14e-02, Avg Return: 0.861, Regret: 0.0007, Entropy: 0.0642 +[2026-03-20T21:15:41.884265Z] Loop 16209: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0007, Entropy: 0.0712 +[2026-03-20T21:15:42.777158Z] Loop 16210: Loss: 1.37e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0722 +[2026-03-20T21:15:43.630633Z] Loop 16211: Loss: 1.30e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0728 +[2026-03-20T21:15:44.484489Z] Loop 16212: Loss: 1.34e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0724 +[2026-03-20T21:15:45.338713Z] Loop 16213: Loss: 1.36e-02, Avg Return: 0.861, Regret: 0.0010, Entropy: 0.0756 +[2026-03-20T21:15:46.194129Z] Loop 16214: Loss: 1.32e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0734 +[2026-03-20T21:15:47.049672Z] Loop 16215: Loss: 1.34e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0757 +[2026-03-20T21:15:47.904053Z] Loop 16216: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0723 +[2026-03-20T21:15:48.757713Z] Loop 16217: Loss: 1.21e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0670 +[2026-03-20T21:15:49.612194Z] Loop 16218: Loss: 1.14e-02, Avg Return: 0.863, Regret: 0.0010, Entropy: 0.0645 +[2026-03-20T21:15:50.466400Z] Loop 16219: Loss: 1.24e-02, Avg Return: 0.862, Regret: 0.0010, Entropy: 0.0666 +[2026-03-20T21:15:51.358785Z] Loop 16220: Loss: 1.24e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0651 +[2026-03-20T21:15:52.212468Z] Loop 16221: Loss: 1.24e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0653 +[2026-03-20T21:15:53.068044Z] Loop 16222: Loss: 1.13e-02, Avg Return: 0.865, Regret: 0.0004, Entropy: 0.0608 +[2026-03-20T21:15:53.922622Z] Loop 16223: Loss: 1.34e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0680 +[2026-03-20T21:15:54.776719Z] Loop 16224: Loss: 1.28e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0653 +[2026-03-20T21:15:55.631022Z] Loop 16225: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0699 +[2026-03-20T21:15:56.485103Z] Loop 16226: Loss: 1.37e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0678 +[2026-03-20T21:15:57.338551Z] Loop 16227: Loss: 1.33e-02, Avg Return: 0.862, Regret: 0.0004, Entropy: 0.0674 +[2026-03-20T21:15:58.192647Z] Loop 16228: Loss: 1.48e-02, Avg Return: 0.864, Regret: 0.0004, Entropy: 0.0741 +[2026-03-20T21:15:59.046602Z] Loop 16229: Loss: 1.42e-02, Avg Return: 0.863, Regret: 0.0004, Entropy: 0.0746 +[2026-03-20T21:15:59.942553Z] Loop 16230: Loss: 1.49e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0732 +[2026-03-20T21:16:00.796758Z] Loop 16231: Loss: 1.48e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0739 +[2026-03-20T21:16:01.650514Z] Loop 16232: Loss: 1.51e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0761 +[2026-03-20T21:16:02.504688Z] Loop 16233: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0759 +[2026-03-20T21:16:03.359912Z] Loop 16234: Loss: 1.56e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0754 +[2026-03-20T21:16:04.213706Z] Loop 16235: Loss: 1.54e-02, Avg Return: 0.865, Regret: 0.0001, Entropy: 0.0768 +[2026-03-20T21:16:05.066954Z] Loop 16236: Loss: 1.55e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0794 +[2026-03-20T21:16:05.921167Z] Loop 16237: Loss: 1.78e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0830 +[2026-03-20T21:16:06.776175Z] Loop 16238: Loss: 1.67e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0792 +[2026-03-20T21:16:07.630573Z] Loop 16239: Loss: 1.66e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0798 +[2026-03-20T21:16:08.523417Z] Loop 16240: Loss: 1.67e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0824 +[2026-03-20T21:16:09.376994Z] Loop 16241: Loss: 1.50e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0735 +[2026-03-20T21:16:10.232839Z] Loop 16242: Loss: 1.57e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0741 +[2026-03-20T21:16:11.087304Z] Loop 16243: Loss: 1.53e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0764 +[2026-03-20T21:16:11.941879Z] Loop 16244: Loss: 1.50e-02, Avg Return: 0.865, Regret: 0.0001, Entropy: 0.0744 +[2026-03-20T21:16:12.795959Z] Loop 16245: Loss: 1.45e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0714 +[2026-03-20T21:16:13.650317Z] Loop 16246: Loss: 1.35e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0688 +[2026-03-20T21:16:14.504391Z] Loop 16247: Loss: 1.39e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0678 +[2026-03-20T21:16:15.358343Z] Loop 16248: Loss: 1.23e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0677 +[2026-03-20T21:16:16.212153Z] Loop 16249: Loss: 1.36e-02, Avg Return: 0.862, Regret: 0.0001, Entropy: 0.0708 +[2026-03-20T21:16:17.106776Z] Loop 16250: Loss: 1.29e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0660 +[2026-03-20T21:16:17.961787Z] Loop 16251: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0666 +[2026-03-20T21:16:18.815680Z] Loop 16252: Loss: 1.35e-02, Avg Return: 0.865, Regret: 0.0001, Entropy: 0.0668 +[2026-03-20T21:16:19.668992Z] Loop 16253: Loss: 1.25e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0635 +[2026-03-20T21:16:20.523472Z] Loop 16254: Loss: 1.31e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0649 +[2026-03-20T21:16:21.377816Z] Loop 16255: Loss: 1.31e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0657 +[2026-03-20T21:16:22.232685Z] Loop 16256: Loss: 1.27e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0647 +[2026-03-20T21:16:23.086101Z] Loop 16257: Loss: 1.26e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0620 +[2026-03-20T21:16:23.940692Z] Loop 16258: Loss: 1.38e-02, Avg Return: 0.863, Regret: 0.0001, Entropy: 0.0678 +[2026-03-20T21:16:24.795206Z] Loop 16259: Loss: 1.36e-02, Avg Return: 0.864, Regret: 0.0001, Entropy: 0.0690 +[2026-03-20T21:16:25.687297Z] Loop 16260: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0702 +[2026-03-20T21:16:26.542243Z] Loop 16261: Loss: 1.45e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0751 +[2026-03-20T21:16:27.396222Z] Loop 16262: Loss: 1.49e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0709 +[2026-03-20T21:16:28.249601Z] Loop 16263: Loss: 1.56e-02, Avg Return: 0.865, Regret: 0.0006, Entropy: 0.0739 +[2026-03-20T21:16:29.103480Z] Loop 16264: Loss: 1.50e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0753 +[2026-03-20T21:16:29.958673Z] Loop 16265: Loss: 1.52e-02, Avg Return: 0.862, Regret: 0.0006, Entropy: 0.0731 +[2026-03-20T21:16:30.812776Z] Loop 16266: Loss: 1.44e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0729 +[2026-03-20T21:16:31.666468Z] Loop 16267: Loss: 1.53e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0768 +[2026-03-20T21:16:32.520075Z] Loop 16268: Loss: 1.41e-02, Avg Return: 0.864, Regret: 0.0006, Entropy: 0.0728 +[2026-03-20T21:16:33.374926Z] Loop 16269: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0006, Entropy: 0.0775 +[2026-03-20T21:16:34.267596Z] Loop 16270: Loss: 1.58e-02, Avg Return: 0.863, Regret: 0.0014, Entropy: 0.0783 +[2026-03-20T21:16:35.121541Z] Loop 16271: Loss: 1.59e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0818 +[2026-03-20T21:16:35.975564Z] Loop 16272: Loss: 1.61e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0814 +[2026-03-20T21:16:36.829798Z] Loop 16273: Loss: 1.63e-02, Avg Return: 0.861, Regret: 0.0014, Entropy: 0.0852 +[2026-03-20T21:16:37.684677Z] Loop 16274: Loss: 1.75e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0858 +[2026-03-20T21:16:38.537931Z] Loop 16275: Loss: 1.68e-02, Avg Return: 0.862, Regret: 0.0014, Entropy: 0.0862